3928 files changed, 103583 insertions, 67105 deletions

diff --git a/.mailmap b/.mailmap
index 04998f7bda81..bd9f1025ac44 100644
--- a/.mailmap
+++ b/.mailmap
@@ -191,10 +191,11 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
-Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <geliang.tang@linux.dev>
+Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
@@ -289,6 +290,7 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
 John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
 John Keeping <john@keeping.me.uk> <john@metanate.com>
+John Moon <john@jmoon.dev> <quic_johmoo@quicinc.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
 <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
@@ -323,6 +325,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com>
 Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org>
 Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org>
 Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
+Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
@@ -344,6 +347,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
 Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
 Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
 Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
@@ -550,6 +554,7 @@ Senthilkumar N L <quic_snlakshm@quicinc.com> <snlakshm@codeaurora.org>
 Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com>
 Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com>
 Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
+Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com>
 Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
 Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
 Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com>
@@ -605,6 +610,11 @@ TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
 TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
 Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@intel.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@linux.intel.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@sophos.com>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@onelan.co.uk>
+Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
diff --git a/CREDITS b/CREDITS
index 5797e8f7e92b..3c2bb55847c6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -63,6 +63,11 @@ D: dosfs, LILO, some fd features, ATM, various other hacks here and there
 S: Buenos Aires
 S: Argentina
 
+NTFS FILESYSTEM
+N: Anton Altaparmakov
+E: anton@tuxera.com
+D: NTFS filesystem
+
 N: Tim Alpaerts
 E: tim_alpaerts@toyota-motor-europe.com
 D: 802.2 class II logical link control layer,
@@ -2161,6 +2166,19 @@ N: Mike Kravetz
 E: mike.kravetz@oracle.com
 D: Maintenance and development of the hugetlb subsystem
 
+N: Seth Jennings
+E: sjenning@redhat.com
+D: Creation and maintenance of zswap
+
+N: Dan Streetman
+E: ddstreet@ieee.org
+D: Maintenance and development of zswap
+D: Creation and maintenance of the zpool API
+
+N: Vitaly Wool
+E: vitaly.wool@konsulko.com
+D: Maintenance and development of zswap
+
 N: Andreas S. Krebs
 E: akrebs@altavista.net
 D: CYPRESS CY82C693 chipset IDE, Digital's PC-Alpha 164SX boards
diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
index 906ff3ca928a..5bff64d256c2 100644
--- a/Documentation/ABI/testing/sysfs-class-net-queues
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_cpus
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_cpus
 Date:		March 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -8,7 +8,7 @@ Description:
 		network device queue. Possible values depend on the number
 		of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt
 Date:		April 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -16,7 +16,7 @@ Description:
 		Number of Receive Packet Steering flows being currently
 		processed by this particular network device receive queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_timeout
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_timeout
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -24,7 +24,7 @@ Description:
 		Indicates the number of transmit timeout events seen by this
 		network interface transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_maxrate
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate
 Date:		March 2015
 KernelVersion:	4.1
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		A Mbps max-rate set for the queue, a value of zero means disabled,
 		default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_cpus
 Date:		November 2010
 KernelVersion:	2.6.38
 Contact:	netdev@vger.kernel.org
@@ -42,7 +42,7 @@ Description:
 		network device transmit queue. Possible values depend on the
 		number of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs
 Date:		June 2018
 KernelVersion:	4.18.0
 Contact:	netdev@vger.kernel.org
@@ -53,7 +53,7 @@ Description:
 		number of available receive queue(s) in the network device.
 		Default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -62,7 +62,7 @@ Description:
 		of this particular network device transmit queue.
 		Default value is 1000.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -70,7 +70,7 @@ Description:
 		Indicates the number of bytes (objects) in flight on this
 		network device transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -79,7 +79,7 @@ Description:
 		on this network device transmit queue. This value is clamped
 		to be within the bounds defined by limit_max and limit_min.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -88,7 +88,7 @@ Description:
 		queued on this network device transmit queue. See
 		include/linux/dynamic_queue_limits.h for the default value.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics
index 55db27815361..53e508c6936a 100644
--- a/Documentation/ABI/testing/sysfs-class-net-statistics
+++ b/Documentation/ABI/testing/sysfs-class-net-statistics
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/statistics/collisions
+What:		/sys/class/net/<iface>/statistics/collisions
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -6,7 +6,7 @@ Description:
 		Indicates the number of collisions seen by this network device.
 		This value might not be relevant with all MAC layers.
 
-What:		/sys/class/<iface>/statistics/multicast
+What:		/sys/class/net/<iface>/statistics/multicast
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -14,7 +14,7 @@ Description:
 		Indicates the number of multicast packets received by this
 		network device.
 
-What:		/sys/class/<iface>/statistics/rx_bytes
+What:		/sys/class/net/<iface>/statistics/rx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -23,7 +23,7 @@ Description:
 		See the network driver for the exact meaning of when this
 		value is incremented.
 
-What:		/sys/class/<iface>/statistics/rx_compressed
+What:		/sys/class/net/<iface>/statistics/rx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		network device. This value might only be relevant for interfaces
 		that support packet compression (e.g: PPP).
 
-What:		/sys/class/<iface>/statistics/rx_crc_errors
+What:		/sys/class/net/<iface>/statistics/rx_crc_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -41,7 +41,7 @@ Description:
 		by this network device. Note that the specific meaning might
 		depend on the MAC layer used by the interface.
 
-What:		/sys/class/<iface>/statistics/rx_dropped
+What:		/sys/class/net/<iface>/statistics/rx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -51,7 +51,7 @@ Description:
 		packet processing. See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_errors
+What:		/sys/class/net/<iface>/statistics/rx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -59,7 +59,7 @@ Description:
 		Indicates the number of receive errors on this network device.
 		See the network driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/rx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -68,7 +68,7 @@ Description:
 		network device. See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_frame_errors
+What:		/sys/class/net/<iface>/statistics/rx_frame_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -78,7 +78,7 @@ Description:
 		on the MAC layer protocol used. See the network driver for
 		the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_length_errors
+What:		/sys/class/net/<iface>/statistics/rx_length_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -87,7 +87,7 @@ Description:
 		error, oversized or undersized. See the network driver for the
 		exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_missed_errors
+What:		/sys/class/net/<iface>/statistics/rx_missed_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -96,7 +96,7 @@ Description:
 		due to lack of capacity in the receive side. See the network
 		driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_nohandler
+What:		/sys/class/net/<iface>/statistics/rx_nohandler
 Date:		February 2016
 KernelVersion:	4.6
 Contact:	netdev@vger.kernel.org
@@ -104,7 +104,7 @@ Description:
 		Indicates the number of received packets that were dropped on
 		an inactive device by the network core.
 
-What:		/sys/class/<iface>/statistics/rx_over_errors
+What:		/sys/class/net/<iface>/statistics/rx_over_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -114,7 +114,7 @@ Description:
 		(e.g: larger than MTU). See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/rx_packets
+What:		/sys/class/net/<iface>/statistics/rx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -122,7 +122,7 @@ Description:
 		Indicates the total number of good packets received by this
 		network device.
 
-What:		/sys/class/<iface>/statistics/tx_aborted_errors
+What:		/sys/class/net/<iface>/statistics/tx_aborted_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -132,7 +132,7 @@ Description:
 		a medium collision). See the network driver for the exact
 		meaning of this value.
 
-What:		/sys/class/<iface>/statistics/tx_bytes
+What:		/sys/class/net/<iface>/statistics/tx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -143,7 +143,7 @@ Description:
 		transmitted packets or all packets that have been queued for
 		transmission.
 
-What:		/sys/class/<iface>/statistics/tx_carrier_errors
+What:		/sys/class/net/<iface>/statistics/tx_carrier_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -152,7 +152,7 @@ Description:
 		because of carrier errors (e.g: physical link down). See the
 		network driver for the exact meaning of this value.
 
-What:		/sys/class/<iface>/statistics/tx_compressed
+What:		/sys/class/net/<iface>/statistics/tx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -161,7 +161,7 @@ Description:
 		this might only be relevant for devices that support
 		compression (e.g: PPP).
 
-What:		/sys/class/<iface>/statistics/tx_dropped
+What:		/sys/class/net/<iface>/statistics/tx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -170,7 +170,7 @@ Description:
 		See the driver for the exact reasons as to why the packets were
 		dropped.
 
-What:		/sys/class/<iface>/statistics/tx_errors
+What:		/sys/class/net/<iface>/statistics/tx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -179,7 +179,7 @@ Description:
 		a network device. See the driver for the exact reasons as to
 		why the packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/tx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -188,7 +188,7 @@ Description:
 		FIFO error. See the driver for the exact reasons as to why the
 		packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_heartbeat_errors
+What:		/sys/class/net/<iface>/statistics/tx_heartbeat_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -197,7 +197,7 @@ Description:
 		reported as heartbeat errors. See the driver for the exact
 		reasons as to why the packets were dropped.
 
-What:		/sys/class/<iface>/statistics/tx_packets
+What:		/sys/class/net/<iface>/statistics/tx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -206,7 +206,7 @@ Description:
 		device. See the driver for whether this reports the number of all
 		attempted or successful transmissions.
 
-What:		/sys/class/<iface>/statistics/tx_window_errors
+What:		/sys/class/net/<iface>/statistics/tx_window_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index a1db6db47505..710d47be11e0 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -516,6 +516,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/mds
 		/sys/devices/system/cpu/vulnerabilities/meltdown
 		/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+		/sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling
 		/sys/devices/system/cpu/vulnerabilities/retbleed
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
index 8d7d8f05f6cd..92fe7c5c5ac1 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/in0_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -6,7 +6,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RW. Card reactive sustained  (PL1/Tau) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_rated_max
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -28,7 +28,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_max_interval
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -37,7 +37,7 @@ Description:	RW. Sustained power limit interval (Tau in PL1/Tau) in
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/power1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -50,7 +50,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/curr1_crit
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
@@ -63,7 +63,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 
 		Only supported for particular Intel i915 graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/energy1_input
 Date:		February 2023
 KernelVersion:	6.2
 Contact:	intel-gfx@lists.freedesktop.org
diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
index 8c321bc9dc04..023fd82de3f7 100644
--- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
+++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon
@@ -1,4 +1,4 @@
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -12,7 +12,7 @@ Description:	RW. Card reactive sustained  (PL1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_rated_max
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -20,7 +20,7 @@ Description:	RO. Card default power limit (default TDP setting).
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -33,7 +33,7 @@ Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/curr1_crit
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -44,7 +44,7 @@ Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 		the operating frequency if the power averaged over a window
 		exceeds this limit.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/in0_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -52,7 +52,7 @@ Description:	RO. Current Voltage in millivolt.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/energy1_input
 Date:		September 2023
 KernelVersion:	6.5
 Contact:	intel-xe@lists.freedesktop.org
@@ -60,7 +60,7 @@ Description:	RO. Energy input of device in microjoules.
 
 		Only supported for particular Intel xe graphics platforms.
 
-What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_max_interval
 Date:		October 2023
 KernelVersion:	6.6
 Contact:	intel-xe@lists.freedesktop.org
diff --git a/Documentation/ABI/testing/sysfs-nvmem-cells b/Documentation/ABI/testing/sysfs-nvmem-cells
index 7af70adf3690..c7c9444f92a8 100644
--- a/Documentation/ABI/testing/sysfs-nvmem-cells
+++ b/Documentation/ABI/testing/sysfs-nvmem-cells
@@ -4,18 +4,18 @@ KernelVersion:	6.5
 Contact:	Miquel Raynal <miquel.raynal@bootlin.com>
 Description:
 		The "cells" folder contains one file per cell exposed by the
-		NVMEM device. The name of the file is: <name>@<where>, with
-		<name> being the cell name and <where> its location in the NVMEM
-		device, in hexadecimal (without the '0x' prefix, to mimic device
-		tree node names). The length of the file is the size of the cell
-		(when known). The content of the file is the binary content of
-		the cell (may sometimes be ASCII, likely without trailing
-		character).
+		NVMEM device. The name of the file is: "<name>@<byte>,<bit>",
+		with <name> being the cell name and <where> its location in
+		the NVMEM device, in hexadecimal bytes and bits (without the
+		'0x' prefix, to mimic device tree node names). The length of
+		the file is the size of the cell (when known). The content of
+		the file is the binary content of the cell (may sometimes be
+		ASCII, likely without trailing character).
 		Note: This file is only present if CONFIG_NVMEM_SYSFS
 		is enabled.
 
 		Example::
 
-		  hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d
+		  hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d,0
 		  00000000  54 4e 34 38 4d 2d 50 2d  44 4e         |TN48M-P-DN|
 		  0000000a
diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst
index 2d42998a89a6..3e6407de231c 100644
--- a/Documentation/RCU/checklist.rst
+++ b/Documentation/RCU/checklist.rst
@@ -68,7 +68,8 @@ over a rather long period of time, but improvements are always welcome!
 	rcu_read_lock_sched(), or by the appropriate update-side lock.
 	Explicit disabling of preemption (preempt_disable(), for example)
 	can serve as rcu_read_lock_sched(), but is less readable and
-	prevents lockdep from detecting locking issues.
+	prevents lockdep from detecting locking issues.  Acquiring a
+	spinlock also enters an RCU read-side critical section.
 
 	Please note that you *cannot* rely on code known to be built
 	only in non-preemptible kernels.  Such code can and will break,
@@ -382,16 +383,17 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	Do not assume that RCU callbacks will be executed on the same
-	CPU that executed the corresponding call_rcu() or call_srcu().
-	For example, if a given CPU goes offline while having an RCU
-	callback pending, then that RCU callback will execute on some
-	surviving CPU.	(If this was not the case, a self-spawning RCU
-	callback would prevent the victim CPU from ever going offline.)
-	Furthermore, CPUs designated by rcu_nocbs= might well *always*
-	have their RCU callbacks executed on some other CPUs, in fact,
-	for some  real-time workloads, this is the whole point of using
-	the rcu_nocbs= kernel boot parameter.
+	Do not assume that RCU callbacks will be executed on
+	the same CPU that executed the corresponding call_rcu(),
+	call_srcu(), call_rcu_tasks(), call_rcu_tasks_rude(), or
+	call_rcu_tasks_trace().  For example, if a given CPU goes offline
+	while having an RCU callback pending, then that RCU callback
+	will execute on some surviving CPU.  (If this was not the case,
+	a self-spawning RCU callback would prevent the victim CPU from
+	ever going offline.)  Furthermore, CPUs designated by rcu_nocbs=
+	might well *always* have their RCU callbacks executed on some
+	other CPUs, in fact, for some  real-time workloads, this is the
+	whole point of using the rcu_nocbs= kernel boot parameter.
 
 	In addition, do not assume that callbacks queued in a given order
 	will be invoked in that order, even if they all are queued on the
@@ -444,7 +446,7 @@ over a rather long period of time, but improvements are always welcome!
 	real-time workloads than is synchronize_rcu_expedited().
 
 	It is also permissible to sleep in RCU Tasks Trace read-side
-	critical, which are delimited by rcu_read_lock_trace() and
+	critical section, which are delimited by rcu_read_lock_trace() and
 	rcu_read_unlock_trace().  However, this is a specialized flavor
 	of RCU, and you should not use it without first checking with
 	its current users.  In most cases, you should instead use SRCU.
@@ -490,6 +492,12 @@ over a rather long period of time, but improvements are always welcome!
 		since the last time that you passed that same object to
 		call_rcu() (or friends).
 
+	CONFIG_RCU_STRICT_GRACE_PERIOD:
+		combine with KASAN to check for pointers leaked out
+		of RCU read-side critical sections.  This Kconfig
+		option is tough on both performance and scalability,
+		and so is limited to four-CPU systems.
+
 	__rcu sparse checks:
 		tag the pointer to the RCU-protected data structure
 		with __rcu, and sparse will warn you if you access that
diff --git a/Documentation/RCU/rcu_dereference.rst b/Documentation/RCU/rcu_dereference.rst
index 659d5913784d..2524dcdadde2 100644
--- a/Documentation/RCU/rcu_dereference.rst
+++ b/Documentation/RCU/rcu_dereference.rst
@@ -408,7 +408,10 @@ member of the rcu_dereference() to use in various situations:
 	RCU flavors, an RCU read-side critical section is entered
 	using rcu_read_lock(), anything that disables bottom halves,
 	anything that disables interrupts, or anything that disables
-	preemption.
+	preemption.  Please note that spinlock critical sections
+	are also implied RCU read-side critical sections, even when
+	they are preemptible, as they are in kernels built with
+	CONFIG_PREEMPT_RT=y.
 
 2.	If the access might be within an RCU read-side critical section
 	on the one hand, or protected by (say) my_lock on the other,
diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst
index 60ce02475142..872ac665223f 100644
--- a/Documentation/RCU/whatisRCU.rst
+++ b/Documentation/RCU/whatisRCU.rst
@@ -172,14 +172,25 @@ rcu_read_lock()
 	critical section.  Reference counts may be used in conjunction
 	with RCU to maintain longer-term references to data structures.
 
+	Note that anything that disables bottom halves, preemption,
+	or interrupts also enters an RCU read-side critical section.
+	Acquiring a spinlock also enters an RCU read-side critical
+	sections, even for spinlocks that do not disable preemption,
+	as is the case in kernels built with CONFIG_PREEMPT_RT=y.
+	Sleeplocks do *not* enter RCU read-side critical sections.
+
 rcu_read_unlock()
 ^^^^^^^^^^^^^^^^^
 	void rcu_read_unlock(void);
 
 	This temporal primitives is used by a reader to inform the
 	reclaimer that the reader is exiting an RCU read-side critical
-	section.  Note that RCU read-side critical sections may be nested
-	and/or overlapping.
+	section.  Anything that enables bottom halves, preemption,
+	or interrupts also exits an RCU read-side critical section.
+	Releasing a spinlock also exits an RCU read-side critical section.
+
+	Note that RCU read-side critical sections may be nested and/or
+	overlapping.
 
 synchronize_rcu()
 ^^^^^^^^^^^^^^^^^
@@ -952,8 +963,8 @@ unfortunately any spinlock in a ``SLAB_TYPESAFE_BY_RCU`` object must be
 initialized after each and every call to kmem_cache_alloc(), which renders
 reference-free spinlock acquisition completely unsafe.  Therefore, when
 using ``SLAB_TYPESAFE_BY_RCU``, make proper use of a reference counter.
-(Those willing to use a kmem_cache constructor may also use locking,
-including cache-friendly sequence locking.)
+(Those willing to initialize their locks in a kmem_cache constructor
+may also use locking, including cache-friendly sequence locking.)
 
 With traditional reference counting -- such as that implemented by the
 kref library in Linux -- there is typically code that runs when the last
diff --git a/Documentation/admin-guide/RAS/address-translation.rst b/Documentation/admin-guide/RAS/address-translation.rst
new file mode 100644
index 000000000000..f0ca17b43cd3
--- /dev/null
+++ b/Documentation/admin-guide/RAS/address-translation.rst
@@ -0,0 +1,24 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Address translation
+===================
+
+x86 AMD
+-------
+
+Zen-based AMD systems include a Data Fabric that manages the layout of
+physical memory. Devices attached to the Fabric, like memory controllers,
+I/O, etc., may not have a complete view of the system physical memory map.
+These devices may provide a "normalized", i.e. device physical, address
+when reporting memory errors. Normalized addresses must be translated to
+a system physical address for the kernel to action on the memory.
+
+AMD Address Translation Library (CONFIG_AMD_ATL) provides translation for
+this case.
+
+Glossary of acronyms used in address translation for Zen-based systems
+
+* CCM               = Cache Coherent Moderator
+* COD               = Cluster-on-Die
+* COH_ST            = Coherent Station
+* DF                = Data Fabric
diff --git a/Documentation/RAS/ras.rst b/Documentation/admin-guide/RAS/error-decoding.rst
index 2556b397cd27..26a72f3fe5de 100644
--- a/Documentation/RAS/ras.rst
+++ b/Documentation/admin-guide/RAS/error-decoding.rst
@@ -1,15 +1,10 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-Reliability, Availability and Serviceability features
-=====================================================
-
-This documents different aspects of the RAS functionality present in the
-kernel.
-
 Error decoding
----------------
+==============
 
-* x86
+x86
+---
 
 Error decoding on AMD systems should be done using the rasdaemon tool:
 https://github.com/mchehab/rasdaemon/
diff --git a/Documentation/admin-guide/RAS/index.rst b/Documentation/admin-guide/RAS/index.rst
new file mode 100644
index 000000000000..f4087040a7c0
--- /dev/null
+++ b/Documentation/admin-guide/RAS/index.rst
@@ -0,0 +1,7 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. toctree::
+   :maxdepth: 2
+
+   main
+   error-decoding
+   address-translation
diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/RAS/main.rst
index 8e03751d126d..7ac1d4ccc509 100644
--- a/Documentation/admin-guide/ras.rst
+++ b/Documentation/admin-guide/RAS/main.rst
@@ -1,8 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
 .. include:: <isonum.txt>
 
-============================================
-Reliability, Availability and Serviceability
-============================================
+==================================================
+Reliability, Availability and Serviceability (RAS)
+==================================================
+
+This documents different aspects of the RAS functionality present in the
+kernel.
 
 RAS concepts
 ************
diff --git a/Documentation/admin-guide/cgroup-v1/cpusets.rst b/Documentation/admin-guide/cgroup-v1/cpusets.rst
index ae646d621a8a..7d3415eea05d 100644
--- a/Documentation/admin-guide/cgroup-v1/cpusets.rst
+++ b/Documentation/admin-guide/cgroup-v1/cpusets.rst
@@ -179,7 +179,7 @@ files describing that cpuset:
  - cpuset.mem_hardwall flag:  is memory allocation hardwalled
  - cpuset.memory_pressure: measure of how much paging pressure in cpuset
  - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes
- - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
+ - cpuset.memory_spread_slab flag: OBSOLETE. Doesn't have any function.
  - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset
  - cpuset.sched_relax_domain_level: the searching range when migrating tasks
 
diff --git a/Documentation/admin-guide/cgroup-v1/hugetlb.rst b/Documentation/admin-guide/cgroup-v1/hugetlb.rst
index 0fa724d82abb..493a8e386700 100644
--- a/Documentation/admin-guide/cgroup-v1/hugetlb.rst
+++ b/Documentation/admin-guide/cgroup-v1/hugetlb.rst
@@ -65,10 +65,12 @@ files include::
 
 1. Page fault accounting
 
-hugetlb.<hugepagesize>.limit_in_bytes
-hugetlb.<hugepagesize>.max_usage_in_bytes
-hugetlb.<hugepagesize>.usage_in_bytes
-hugetlb.<hugepagesize>.failcnt
+::
+
+  hugetlb.<hugepagesize>.limit_in_bytes
+  hugetlb.<hugepagesize>.max_usage_in_bytes
+  hugetlb.<hugepagesize>.usage_in_bytes
+  hugetlb.<hugepagesize>.failcnt
 
 The HugeTLB controller allows users to limit the HugeTLB usage (page fault) per
 control group and enforces the limit during page fault. Since HugeTLB
@@ -82,10 +84,12 @@ getting SIGBUS.
 
 2. Reservation accounting
 
-hugetlb.<hugepagesize>.rsvd.limit_in_bytes
-hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes
-hugetlb.<hugepagesize>.rsvd.usage_in_bytes
-hugetlb.<hugepagesize>.rsvd.failcnt
+::
+
+  hugetlb.<hugepagesize>.rsvd.limit_in_bytes
+  hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes
+  hugetlb.<hugepagesize>.rsvd.usage_in_bytes
+  hugetlb.<hugepagesize>.rsvd.failcnt
 
 The HugeTLB controller allows to limit the HugeTLB reservations per control
 group and enforces the controller limit at reservation time and at the fault of
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index de99caabf65a..ff0b440ef2dc 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -21,3 +21,4 @@ are configurable at compile, boot or run time.
    cross-thread-rsb
    srso
    gather_data_sampling
+   reg-file-data-sampling
diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
new file mode 100644
index 000000000000..0585d02b9a6c
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
@@ -0,0 +1,104 @@
+==================================
+Register File Data Sampling (RFDS)
+==================================
+
+Register File Data Sampling (RFDS) is a microarchitectural vulnerability that
+only affects Intel Atom parts(also branded as E-cores). RFDS may allow
+a malicious actor to infer data values previously used in floating point
+registers, vector registers, or integer registers. RFDS does not provide the
+ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS.
+
+Affected Processors
+===================
+Below is the list of affected Intel processors [#f1]_:
+
+   ===================  ============
+   Common name          Family_Model
+   ===================  ============
+   ATOM_GOLDMONT           06_5CH
+   ATOM_GOLDMONT_D         06_5FH
+   ATOM_GOLDMONT_PLUS      06_7AH
+   ATOM_TREMONT_D          06_86H
+   ATOM_TREMONT            06_96H
+   ALDERLAKE               06_97H
+   ALDERLAKE_L             06_9AH
+   ATOM_TREMONT_L          06_9CH
+   RAPTORLAKE              06_B7H
+   RAPTORLAKE_P            06_BAH
+   ATOM_GRACEMONT          06_BEH
+   RAPTORLAKE_S            06_BFH
+   ===================  ============
+
+As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and
+RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as
+vulnerable in Linux because they share the same family/model with an affected
+part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or
+CPUID.HYBRID. This information could be used to distinguish between the
+affected and unaffected parts, but it is deemed not worth adding complexity as
+the reporting is fixed automatically when these parts enumerate RFDS_NO.
+
+Mitigation
+==========
+Intel released a microcode update that enables software to clear sensitive
+information using the VERW instruction. Like MDS, RFDS deploys the same
+mitigation strategy to force the CPU to clear the affected buffers before an
+attacker can extract the secrets. This is achieved by using the otherwise
+unused and obsolete VERW instruction in combination with a microcode update.
+The microcode clears the affected CPU buffers when the VERW instruction is
+executed.
+
+Mitigation points
+-----------------
+VERW is executed by the kernel before returning to user space, and by KVM
+before VMentry. None of the affected cores support SMT, so VERW is not required
+at C-state transitions.
+
+New bits in IA32_ARCH_CAPABILITIES
+----------------------------------
+Newer processors and microcode update on existing affected processors added new
+bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate
+vulnerability and mitigation capability:
+
+- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS.
+- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the
+  microcode that clears the affected buffers on VERW execution.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows to control RFDS mitigation at boot time with the
+parameter "reg_file_data_sampling=". The valid arguments are:
+
+  ==========  =================================================================
+  on          If the CPU is vulnerable, enable mitigation; CPU buffer clearing
+              on exit to userspace and before entering a VM.
+  off         Disables mitigation.
+  ==========  =================================================================
+
+Mitigation default is selected by CONFIG_MITIGATION_RFDS.
+
+Mitigation status information
+-----------------------------
+The Linux kernel provides a sysfs interface to enumerate the current
+vulnerability status of the system: whether the system is vulnerable, and
+which mitigations are active. The relevant sysfs file is:
+
+	/sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling
+
+The possible values in this file are:
+
+  .. list-table::
+
+     * - 'Not affected'
+       - The processor is not vulnerable
+     * - 'Vulnerable'
+       - The processor is vulnerable, but no mitigation enabled
+     * - 'Vulnerable: No microcode'
+       - The processor is vulnerable but microcode is not updated.
+     * - 'Mitigation: Clear Register File'
+       - The processor is vulnerable and the CPU buffer clearing mitigation is
+	 enabled.
+
+References
+----------
+.. [#f1] Affected Processors
+   https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 32a8893e5617..cce768afec6b 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -473,8 +473,8 @@ Spectre variant 2
    -mindirect-branch=thunk-extern -mindirect-branch-register options.
    If the kernel is compiled with a Clang compiler, the compiler needs
    to support -mretpoline-external-thunk option.  The kernel config
-   CONFIG_RETPOLINE needs to be turned on, and the CPU needs to run with
-   the latest updated microcode.
+   CONFIG_MITIGATION_RETPOLINE needs to be turned on, and the CPU needs
+   to run with the latest updated microcode.
 
    On Intel Skylake-era systems the mitigation covers most, but not all,
    cases. See :ref:`[3] <spec_ref3>` for more details.
@@ -609,8 +609,8 @@ kernel command line.
 		Selecting 'on' will, and 'auto' may, choose a
 		mitigation method at run time according to the
 		CPU, the available microcode, the setting of the
-		CONFIG_RETPOLINE configuration option, and the
-		compiler with which the kernel was built.
+		CONFIG_MITIGATION_RETPOLINE configuration option,
+		and the compiler with which the kernel was built.
 
 		Selecting 'on' will also enable the mitigation
 		against user space to user space task attacks.
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index fb40a1f6f79e..dfc06fab9432 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -122,7 +122,7 @@ configure specific aspects of kernel behavior to your liking.
    pmf
    pnp
    rapidio
-   ras
+   RAS/index
    rtc
    serial-console
    svga
diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst
index 5762e7477a0c..0302a93b1d40 100644
--- a/Documentation/admin-guide/kdump/kdump.rst
+++ b/Documentation/admin-guide/kdump/kdump.rst
@@ -191,9 +191,7 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
    CPU is enough for kdump kernel to dump vmcore on most of systems.
 
    However, you can also specify nr_cpus=X to enable multiple processors
-   in kdump kernel. In this case, "disable_cpu_apicid=" is needed to
-   tell kdump kernel which cpu is 1st kernel's BSP. Please refer to
-   admin-guide/kernel-parameters.txt for more details.
+   in kdump kernel.
 
    With CONFIG_SMP=n, the above things are not related.
 
@@ -454,8 +452,7 @@ Notes on loading the dump-capture kernel:
   to use multi-thread programs with it, such as parallel dump feature of
   makedumpfile. Otherwise, the multi-thread program may have a great
   performance degradation. To enable multi-cpu support, you should bring up an
-  SMP dump-capture kernel and specify maxcpus/nr_cpus, disable_cpu_apicid=[X]
-  options while loading it.
+  SMP dump-capture kernel and specify maxcpus/nr_cpus options while loading it.
 
 * For s390x there are two kdump modes: If a ELF header is specified with
   the elfcorehdr= kernel parameter, it is used by the kdump kernel as it
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 4410384596a9..e8bdf5e86a9b 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -108,6 +108,7 @@ is applicable::
 	CMA	Contiguous Memory Area support is enabled.
 	DRM	Direct Rendering Management support is enabled.
 	DYNAMIC_DEBUG Build in debug messages and enable them at runtime
+	EARLY	Parameter processed too early to be embedded in initrd.
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
 	EVM	Extended Verification Module
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 31b3a25680d0..825398d66c69 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -9,7 +9,7 @@
 			accept_memory=eager can be used to accept all memory
 			at once during boot.
 
-	acpi=		[HW,ACPI,X86,ARM64,RISCV64]
+	acpi=		[HW,ACPI,X86,ARM64,RISCV64,EARLY]
 			Advanced Configuration and Power Interface
 			Format: { force | on | off | strict | noirq | rsdt |
 				  copy_dsdt }
@@ -26,7 +26,7 @@
 
 			See also Documentation/power/runtime_pm.rst, pci=noacpi
 
-	acpi_apic_instance=	[ACPI, IOAPIC]
+	acpi_apic_instance=	[ACPI,IOAPIC,EARLY]
 			Format: <int>
 			2: use 2nd APIC table, if available
 			1,0: use 1st APIC table
@@ -41,7 +41,7 @@
 			If set to native, use the device's native backlight mode.
 			If set to none, disable the ACPI backlight interface.
 
-	acpi_force_32bit_fadt_addr
+	acpi_force_32bit_fadt_addr [ACPI,EARLY]
 			force FADT to use 32 bit addresses rather than the
 			64 bit X_* addresses. Some firmware have broken 64
 			bit addresses for force ACPI ignore these and use
@@ -97,7 +97,7 @@
 			no: ACPI OperationRegions are not marked as reserved,
 			no further checks are performed.
 
-	acpi_force_table_verification	[HW,ACPI]
+	acpi_force_table_verification	[HW,ACPI,EARLY]
 			Enable table checksum verification during early stage.
 			By default, this is disabled due to x86 early mapping
 			size limitation.
@@ -137,7 +137,7 @@
 	acpi_no_memhotplug [ACPI] Disable memory hotplug.  Useful for kdump
 			   kernels.
 
-	acpi_no_static_ssdt	[HW,ACPI]
+	acpi_no_static_ssdt	[HW,ACPI,EARLY]
 			Disable installation of static SSDTs at early boot time
 			By default, SSDTs contained in the RSDT/XSDT will be
 			installed automatically and they will appear under
@@ -151,7 +151,7 @@
 			Ignore the ACPI-based watchdog interface (WDAT) and let
 			a native driver control the watchdog device instead.
 
-	acpi_rsdp=	[ACPI,EFI,KEXEC]
+	acpi_rsdp=	[ACPI,EFI,KEXEC,EARLY]
 			Pass the RSDP address to the kernel, mostly used
 			on machines running EFI runtime service to boot the
 			second kernel for kdump.
@@ -228,10 +228,10 @@
 			to assume that this machine's pmtimer latches its value
 			and always returns good values.
 
-	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
+	acpi_sci=	[HW,ACPI,EARLY] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
 
-	acpi_skip_timer_override [HW,ACPI]
+	acpi_skip_timer_override [HW,ACPI,EARLY]
 			Recognize and ignore IRQ0/pin2 Interrupt Override.
 			For broken nForce2 BIOS resulting in XT-PIC timer.
 
@@ -266,11 +266,11 @@
 			behave incorrectly in some ways with respect to system
 			suspend and resume to be ignored (use wisely).
 
-	acpi_use_timer_override [HW,ACPI]
+	acpi_use_timer_override [HW,ACPI,EARLY]
 			Use timer override. For some broken Nvidia NF5 boards
 			that require a timer override, but don't have HPET
 
-	add_efi_memmap	[EFI; X86] Include EFI memory map in
+	add_efi_memmap	[EFI,X86,EARLY] Include EFI memory map in
 			kernel's map of available physical RAM.
 
 	agp=		[AGP]
@@ -307,7 +307,7 @@
 			do not want to use tracing_snapshot_alloc() as it needs
 			to be done where GFP_KERNEL allocations are allowed.
 
-	allow_mismatched_32bit_el0 [ARM64]
+	allow_mismatched_32bit_el0 [ARM64,EARLY]
 			Allow execve() of 32-bit applications and setting of the
 			PER_LINUX32 personality on systems where only a strict
 			subset of the CPUs support 32-bit EL0. When this
@@ -351,7 +351,7 @@
 			             This mode requires kvm-amd.avic=1.
 			             (Default when IOMMU HW support is present.)
 
-	amd_pstate=	[X86]
+	amd_pstate=	[X86,EARLY]
 			disable
 			  Do not enable amd_pstate as the default
 			  scaling driver for the supported processors
@@ -391,7 +391,7 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86,EARLY] Advanced Programmable Interrupt Controller
 			Change the output verbosity while booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
@@ -401,7 +401,7 @@
 			Format: apic=driver_name
 			Examples: apic=bigsmp
 
-	apic_extnmi=	[APIC,X86] External NMI delivery setting
+	apic_extnmi=	[APIC,X86,EARLY] External NMI delivery setting
 			Format: { bsp (default) | all | none }
 			bsp:  External NMI is delivered only to CPU 0
 			all:  External NMIs are broadcast to all CPUs as a
@@ -508,21 +508,22 @@
 	bert_disable	[ACPI]
 			Disable BERT OS support on buggy BIOSes.
 
-	bgrt_disable	[ACPI][X86]
+	bgrt_disable	[ACPI,X86,EARLY]
 			Disable BGRT to avoid flickering OEM logo.
 
 	blkdevparts=	Manual partition parsing of block device(s) for
 			embedded devices based on command line input.
 			See Documentation/block/cmdline-partition.rst
 
-	boot_delay=	Milliseconds to delay each printk during boot.
+	boot_delay=	[KNL,EARLY]
+			Milliseconds to delay each printk during boot.
 			Only works if CONFIG_BOOT_PRINTK_DELAY is enabled,
 			and you may also have to specify "lpj=".  Boot_delay
 			values larger than 10 seconds (10000) are assumed
 			erroneous and ignored.
 			Format: integer
 
-	bootconfig	[KNL]
+	bootconfig	[KNL,EARLY]
 			Extended command line options can be added to an initrd
 			and this will cause the kernel to look for it.
 
@@ -557,7 +558,7 @@
 			trust validation.
 			format: { id:<keyid> | builtin }
 
-	cca=		[MIPS] Override the kernel pages' cache coherency
+	cca=		[MIPS,EARLY] Override the kernel pages' cache coherency
 			algorithm.  Accepted values range from 0 to 7
 			inclusive. See arch/mips/include/asm/pgtable-bits.h
 			for platform specific values (SB1, Loongson3 and
@@ -672,19 +673,13 @@
 			[X86-64] hpet,tsc
 
 	clocksource.arm_arch_timer.evtstrm=
-			[ARM,ARM64]
+			[ARM,ARM64,EARLY]
 			Format: <bool>
 			Enable/disable the eventstream feature of the ARM
 			architected timer so that code using WFE-based polling
 			loops can be debugged more effectively on production
 			systems.
 
-	clocksource.max_cswd_read_retries= [KNL]
-			Number of clocksource_watchdog() retries due to
-			external delays before the clock will be marked
-			unstable.  Defaults to two retries, that is,
-			three attempts to read the clock under test.
-
 	clocksource.verify_n_cpus= [KNL]
 			Limit the number of CPUs checked for clocksources
 			marked with CLOCK_SOURCE_VERIFY_PERCPU that
@@ -702,7 +697,7 @@
 			10 seconds when built into the kernel.
 
 	cma=nn[MG]@[start[MG][-end[MG]]]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel global memory area for
 			contiguous memory allocations and optionally the
 			placement constraint by the physical address range of
@@ -711,7 +706,7 @@
 			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel per-numa memory area for
 			contiguous memory allocations. A value of 0 disables
 			per-numa CMA altogether. And If this option is not
@@ -722,7 +717,7 @@
 			they will fallback to the global default memory area.
 
 	numa_cma=<node>:nn[MG][,<node>:nn[MG]]
-			[KNL,CMA]
+			[KNL,CMA,EARLY]
 			Sets the size of kernel numa memory area for
 			contiguous memory allocations. It will reserve CMA
 			area for the specified node.
@@ -739,7 +734,7 @@
 			a hypervisor.
 			Default: yes
 
-	coherent_pool=nn[KMG]	[ARM,KNL]
+	coherent_pool=nn[KMG]	[ARM,KNL,EARLY]
 			Sets the size of memory pool for coherent, atomic dma
 			allocations, by default set to 256K.
 
@@ -757,7 +752,7 @@
 	condev=		[HW,S390] console device
 	conmode=
 
-	con3215_drop=	[S390] 3215 console drop mode.
+	con3215_drop=	[S390,EARLY] 3215 console drop mode.
 			Format: y|n|Y|N|1|0
 			When set to true, drop data on the 3215 console when
 			the console buffer is full. In this case the
@@ -863,7 +858,7 @@
 			kernel before the cpufreq driver probes.
 
 	cpu_init_udelay=N
-			[X86] Delay for N microsec between assert and de-assert
+			[X86,EARLY] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs
 			on every CPU online, such as boot, and resume from suspend.
 			Default: 10000
@@ -883,7 +878,7 @@
 			kernel more unstable.
 
 	crashkernel=size[KMG][@offset[KMG]]
-			[KNL] Using kexec, Linux can switch to a 'crash kernel'
+			[KNL,EARLY] Using kexec, Linux can switch to a 'crash kernel'
 			upon panic. This parameter reserves the physical
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
@@ -954,10 +949,10 @@
 			Format: <port#>,<type>
 			See also Documentation/input/devices/joystick-parport.rst
 
-	debug		[KNL] Enable kernel debugging (events log level).
+	debug		[KNL,EARLY] Enable kernel debugging (events log level).
 
 	debug_boot_weak_hash
-			[KNL] Enable printing [hashed] pointers early in the
+			[KNL,EARLY] Enable printing [hashed] pointers early in the
 			boot sequence.  If enabled, we use a weak hash instead
 			of siphash to hash pointers.  Use this option if you are
 			seeing instances of '(___ptrval___)') and need to see a
@@ -974,10 +969,10 @@
 			will print _a_lot_ more information - normally only
 			useful to lockdep developers.
 
-	debug_objects	[KNL] Enable object debugging
+	debug_objects	[KNL,EARLY] Enable object debugging
 
 	debug_guardpage_minorder=
-			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+			[KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this
 			parameter allows control of the order of pages that will
 			be intentionally kept free (and hence protected) by the
 			buddy allocator. Bigger value increase the probability
@@ -996,7 +991,7 @@
 			help tracking down these problems.
 
 	debug_pagealloc=
-			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
+			[KNL,EARLY] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
 			enables the feature at boot time. By default, it is
 			disabled and the system will work mostly the same as a
 			kernel built without CONFIG_DEBUG_PAGEALLOC.
@@ -1004,8 +999,8 @@
 			useful to also enable the page_owner functionality.
 			on: enable the feature
 
-	debugfs=    	[KNL] This parameter enables what is exposed to userspace
-			and debugfs internal clients.
+	debugfs=    	[KNL,EARLY] This parameter enables what is exposed to
+			userspace and debugfs internal clients.
 			Format: { on, no-mount, off }
 			on: 	All functions are enabled.
 			no-mount:
@@ -1084,7 +1079,7 @@
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
-	disable_1tb_segments [PPC]
+	disable_1tb_segments [PPC,EARLY]
 			Disables the use of 1TB hash page table segments. This
 			causes the kernel to fall back to 256MB segments which
 			can be useful when debugging issues that require an SLB
@@ -1093,41 +1088,32 @@
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.rst.
 
-	disable_radix	[PPC]
+	disable_radix	[PPC,EARLY]
 			Disable RADIX MMU mode on POWER9
 
 	disable_tlbie	[PPC]
 			Disable TLBIE instruction. Currently does not work
 			with KVM, with HASH MMU, or with coherent accelerators.
 
-	disable_cpu_apicid= [X86,APIC,SMP]
-			Format: <int>
-			The number of initial APIC ID for the
-			corresponding CPU to be disabled at boot,
-			mostly used for the kdump 2nd kernel to
-			disable BSP to wake up multiple CPUs without
-			causing system reset or hang due to sending
-			INIT from AP to BSP.
-
-	disable_ddw	[PPC/PSERIES]
+	disable_ddw	[PPC/PSERIES,EARLY]
 			Disable Dynamic DMA Window support. Use this
 			to workaround buggy firmware.
 
 	disable_ipv6=	[IPV6]
 			See Documentation/networking/ipv6.rst.
 
-	disable_mtrr_cleanup [X86]
+	disable_mtrr_cleanup [X86,EARLY]
 			The kernel tries to adjust MTRR layout from continuous
 			to discrete, to make X server driver able to add WB
 			entry later. This parameter disables that.
 
-	disable_mtrr_trim [X86, Intel and AMD only]
+	disable_mtrr_trim [X86, Intel and AMD only,EARLY]
 			By default the kernel will trim any uncacheable
 			memory out of your available memory pool based on
 			MTRR settings.  This parameter disables that behavior,
 			possibly causing your machine to run very slowly.
 
-	disable_timer_pin_1 [X86]
+	disable_timer_pin_1 [X86,EARLY]
 			Disable PIN 1 of APIC timer
 			Can be useful to work around chipset bugs.
 
@@ -1150,6 +1136,26 @@
 			The filter can be disabled or changed to another
 			driver later using sysfs.
 
+	reg_file_data_sampling=
+			[X86] Controls mitigation for Register File Data
+			Sampling (RFDS) vulnerability. RFDS is a CPU
+			vulnerability which may allow userspace to infer
+			kernel data values previously stored in floating point
+			registers, vector registers, or integer registers.
+			RFDS only affects Intel Atom processors.
+
+			on:	Turns ON the mitigation.
+			off:	Turns OFF the mitigation.
+
+			This parameter overrides the compile time default set
+			by CONFIG_MITIGATION_RFDS. Mitigation cannot be
+			disabled when other VERW based mitigations (like MDS)
+			are enabled. In order to disable RFDS mitigation all
+			VERW based mitigations need to be disabled.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
+
 	driver_async_probe=  [KNL]
 			List of driver names to be probed asynchronously. *
 			matches with all driver names. If * is specified, the
@@ -1177,7 +1183,7 @@
 
 	dscc4.setup=	[NET]
 
-	dt_cpu_ftrs=	[PPC]
+	dt_cpu_ftrs=	[PPC,EARLY]
 			Format: {"off" | "known"}
 			Control how the dt_cpu_ftrs device-tree binding is
 			used for CPU feature discovery and setup (if it
@@ -1197,12 +1203,12 @@
 			Documentation/admin-guide/dynamic-debug-howto.rst
 			for details.
 
-	early_ioremap_debug [KNL]
+	early_ioremap_debug [KNL,EARLY]
 			Enable debug messages in early_ioremap support. This
 			is useful for tracking down temporary early mappings
 			which are not unmapped.
 
-	earlycon=	[KNL] Output early console device and options.
+	earlycon=	[KNL,EARLY] Output early console device and options.
 
 			When used with no options, the early console is
 			determined by stdout-path property in device tree's
@@ -1338,7 +1344,7 @@
 			address must be provided, and the serial port must
 			already be setup and configured.
 
-	earlyprintk=	[X86,SH,ARM,M68k,S390]
+	earlyprintk=	[X86,SH,ARM,M68k,S390,UM,EARLY]
 			earlyprintk=vga
 			earlyprintk=sclp
 			earlyprintk=xen
@@ -1396,7 +1402,7 @@
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
-	efi=		[EFI]
+	efi=		[EFI,EARLY]
 			Format: { "debug", "disable_early_pci_dma",
 				  "nochunk", "noruntime", "nosoftreserve",
 				  "novamap", "no_disable_early_pci_dma" }
@@ -1417,13 +1423,13 @@
 			no_disable_early_pci_dma: Leave the busmaster bit set
 			on all PCI bridges while in the EFI boot stub
 
-	efi_no_storage_paranoia [EFI; X86]
+	efi_no_storage_paranoia [EFI,X86,EARLY]
 			Using this parameter you can use more than 50% of
 			your efi variable storage. Use this parameter only if
 			you are really sure that your UEFI does sane gc and
 			fulfills the spec otherwise your board may brick.
 
-	efi_fake_mem=	nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI; X86]
+	efi_fake_mem=	nn[KMG]@ss[KMG]:aa[,nn[KMG]@ss[KMG]:aa,..] [EFI,X86,EARLY]
 			Add arbitrary attribute to specific memory range by
 			updating original EFI memory map.
 			Region of memory which aa attribute is added to is
@@ -1454,7 +1460,7 @@
 	eisa_irq_edge=	[PARISC,HW]
 			See header of drivers/parisc/eisa.c.
 
-	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
+	ekgdboc=	[X86,KGDB,EARLY] Allow early kernel console debugging
 			Format: ekgdboc=kbd
 
 			This is designed to be used in conjunction with
@@ -1469,13 +1475,13 @@
 			See comment before function elanfreq_setup() in
 			arch/x86/kernel/cpu/cpufreq/elanfreq.c.
 
-	elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390]
+	elfcorehdr=[size[KMG]@]offset[KMG] [PPC,SH,X86,S390,EARLY]
 			Specifies physical address of start of kernel core
 			image elf header and optionally the size. Generally
 			kexec loader will pass this option to capture kernel.
 			See Documentation/admin-guide/kdump/kdump.rst for details.
 
-	enable_mtrr_cleanup [X86]
+	enable_mtrr_cleanup [X86,EARLY]
 			The kernel tries to adjust MTRR layout from continuous
 			to discrete, to make X server driver able to add WB
 			entry later. This parameter enables that.
@@ -1508,7 +1514,7 @@
 			Permit 'security.evm' to be updated regardless of
 			current integrity status.
 
-	early_page_ext [KNL] Enforces page_ext initialization to earlier
+	early_page_ext [KNL,EARLY] Enforces page_ext initialization to earlier
 			stages so cover more early boot allocations.
 			Please note that as side effect some optimizations
 			might be disabled to achieve that (e.g. parallelized
@@ -1539,6 +1545,12 @@
 			Warning: use of this parameter will taint the kernel
 			and may cause unknown problems.
 
+	fred=		[X86-64]
+			Enable/disable Flexible Return and Event Delivery.
+			Format: { on | off }
+			on: enable FRED when it's present.
+			off: disable FRED, the default setting.
+
 	ftrace=[tracer]
 			[FTRACE] will set and start the specified tracer
 			as early as possible in order to facilitate early
@@ -1600,7 +1612,7 @@
 			can be changed at run time by the max_graph_depth file
 			in the tracefs tracing directory. default: 0 (no limit)
 
-	fw_devlink=	[KNL] Create device links between consumer and supplier
+	fw_devlink=	[KNL,EARLY] Create device links between consumer and supplier
 			devices by scanning the firmware to infer the
 			consumer/supplier relationships. This feature is
 			especially useful when drivers are loaded as modules as
@@ -1619,12 +1631,12 @@
 			rpm --	Like "on", but also use to order runtime PM.
 
 	fw_devlink.strict=<bool>
-			[KNL] Treat all inferred dependencies as mandatory
+			[KNL,EARLY] Treat all inferred dependencies as mandatory
 			dependencies. This only applies for fw_devlink=on|rpm.
 			Format: <bool>
 
 	fw_devlink.sync_state =
-			[KNL] When all devices that could probe have finished
+			[KNL,EARLY] When all devices that could probe have finished
 			probing, this parameter controls what to do with
 			devices that haven't yet received their sync_state()
 			calls.
@@ -1645,12 +1657,12 @@
 
 	gamma=		[HW,DRM]
 
-	gart_fix_e820=	[X86-64] disable the fix e820 for K8 GART
+	gart_fix_e820=	[X86-64,EARLY] disable the fix e820 for K8 GART
 			Format: off | on
 			default: on
 
 	gather_data_sampling=
-			[X86,INTEL] Control the Gather Data Sampling (GDS)
+			[X86,INTEL,EARLY] Control the Gather Data Sampling (GDS)
 			mitigation.
 
 			Gather Data Sampling is a hardware vulnerability which
@@ -1748,7 +1760,7 @@
 				(that will set all pages holding image data
 				during restoration read-only).
 
-	highmem=nn[KMG]	[KNL,BOOT] forces the highmem zone to have an exact
+	highmem=nn[KMG]	[KNL,BOOT,EARLY] forces the highmem zone to have an exact
 			size of <nn>. This works even on boxes that have no
 			highmem otherwise. This also works to reduce highmem
 			size on bigger boxes.
@@ -1759,7 +1771,7 @@
 
 	hlt		[BUGS=ARM,SH]
 
-	hostname=	[KNL] Set the hostname (aka UTS nodename).
+	hostname=	[KNL,EARLY] Set the hostname (aka UTS nodename).
 			Format: <string>
 			This allows setting the system's hostname during early
 			startup. This sets the name returned by gethostname.
@@ -1804,7 +1816,7 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
-	hugetlb_cma=	[HW,CMA] The size of a CMA area used for allocation
+	hugetlb_cma=	[HW,CMA,EARLY] The size of a CMA area used for allocation
 			of gigantic hugepages. Or using node format, the size
 			of a CMA area per node can be specified.
 			Format: nn[KMGTPE] or (node format)
@@ -1850,9 +1862,10 @@
 				If specified, z/VM IUCV HVC accepts connections
 				from listed z/VM user IDs only.
 
-	hv_nopvspin	[X86,HYPER_V] Disables the paravirt spinlock optimizations
-				      which allow the hypervisor to 'idle' the
-				      guest on lock contention.
+	hv_nopvspin	[X86,HYPER_V,EARLY]
+			Disables the paravirt spinlock optimizations
+			which allow the hypervisor to 'idle' the guest
+			on lock contention.
 
 	i2c_bus=	[HW]	Override the default board specific I2C bus speed
 				or register an additional I2C bus that is not
@@ -1917,7 +1930,7 @@
 			Format: <io>[,<membase>[,<icn_id>[,<icn_id2>]]]
 
 
-	idle=		[X86]
+	idle=		[X86,EARLY]
 			Format: idle=poll, idle=halt, idle=nomwait
 			Poll forces a polling idle loop that can slightly
 			improve the performance of waking up a idle CPU, but
@@ -1973,7 +1986,7 @@
 			mode generally follows that for the NaN encoding,
 			except where unsupported by hardware.
 
-	ignore_loglevel	[KNL]
+	ignore_loglevel	[KNL,EARLY]
 			Ignore loglevel setting - this will print /all/
 			kernel messages to the console. Useful for debugging.
 			We also add it as printk module parameter, so users
@@ -2091,21 +2104,21 @@
 			unpacking being completed before device_ and
 			late_ initcalls.
 
-	initrd=		[BOOT] Specify the location of the initial ramdisk
+	initrd=		[BOOT,EARLY] Specify the location of the initial ramdisk
 
-	initrdmem=	[KNL] Specify a physical address and size from which to
+	initrdmem=	[KNL,EARLY] Specify a physical address and size from which to
 			load the initrd. If an initrd is compiled in or
 			specified in the bootparams, it takes priority over this
 			setting.
 			Format: ss[KMG],nn[KMG]
 			Default is 0, 0
 
-	init_on_alloc=	[MM] Fill newly allocated pages and heap objects with
+	init_on_alloc=	[MM,EARLY] Fill newly allocated pages and heap objects with
 			zeroes.
 			Format: 0 | 1
 			Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
 
-	init_on_free=	[MM] Fill freed pages and heap objects with zeroes.
+	init_on_free=	[MM,EARLY] Fill freed pages and heap objects with zeroes.
 			Format: 0 | 1
 			Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
 
@@ -2161,7 +2174,7 @@
 			0	disables intel_idle and fall back on acpi_idle.
 			1 to 9	specify maximum depth of C-state.
 
-	intel_pstate=	[X86]
+	intel_pstate=	[X86,EARLY]
 			disable
 			  Do not enable intel_pstate as the default
 			  scaling driver for the supported processors
@@ -2205,7 +2218,7 @@
 			  Allow per-logical-CPU P-State performance control limits using
 			  cpufreq sysfs interface
 
-	intremap=	[X86-64, Intel-IOMMU]
+	intremap=	[X86-64,Intel-IOMMU,EARLY]
 			on	enable Interrupt Remapping (default)
 			off	disable Interrupt Remapping
 			nosid	disable Source ID checking
@@ -2217,7 +2230,7 @@
 		strict	regions from userspace.
 		relaxed
 
-	iommu=		[X86]
+	iommu=		[X86,EARLY]
 		off
 		force
 		noforce
@@ -2232,7 +2245,7 @@
 		nobypass	[PPC/POWERNV]
 			Disable IOMMU bypass, using IOMMU for PCI devices.
 
-	iommu.forcedac=	[ARM64, X86] Control IOVA allocation for PCI devices.
+	iommu.forcedac=	[ARM64,X86,EARLY] Control IOVA allocation for PCI devices.
 			Format: { "0" | "1" }
 			0 - Try to allocate a 32-bit DMA address first, before
 			  falling back to the full range if needed.
@@ -2240,7 +2253,7 @@
 			  forcing Dual Address Cycle for PCI cards supporting
 			  greater than 32-bit addressing.
 
-	iommu.strict=	[ARM64, X86, S390] Configure TLB invalidation behaviour
+	iommu.strict=	[ARM64,X86,S390,EARLY] Configure TLB invalidation behaviour
 			Format: { "0" | "1" }
 			0 - Lazy mode.
 			  Request that DMA unmap operations use deferred
@@ -2256,7 +2269,7 @@
 			legacy driver-specific options takes precedence.
 
 	iommu.passthrough=
-			[ARM64, X86] Configure DMA to bypass the IOMMU by default.
+			[ARM64,X86,EARLY] Configure DMA to bypass the IOMMU by default.
 			Format: { "0" | "1" }
 			0 - Use IOMMU translation for DMA.
 			1 - Bypass the IOMMU for DMA.
@@ -2266,7 +2279,7 @@
 			See comment before marvel_specify_io7 in
 			arch/alpha/kernel/core_marvel.c.
 
-	io_delay=	[X86] I/O delay method
+	io_delay=	[X86,EARLY] I/O delay method
 		0x80
 			Standard port 0x80 based delay
 		0xed
@@ -2279,28 +2292,28 @@
 	ip=		[IP_PNP]
 			See Documentation/admin-guide/nfs/nfsroot.rst.
 
-	ipcmni_extend	[KNL] Extend the maximum number of unique System V
+	ipcmni_extend	[KNL,EARLY] Extend the maximum number of unique System V
 			IPC identifiers from 32,768 to 16,777,216.
 
 	irqaffinity=	[SMP] Set the default irq affinity mask
 			The argument is a cpu list, as described above.
 
 	irqchip.gicv2_force_probe=
-			[ARM, ARM64]
+			[ARM,ARM64,EARLY]
 			Format: <bool>
 			Force the kernel to look for the second 4kB page
 			of a GICv2 controller even if the memory range
 			exposed by the device tree is too small.
 
 	irqchip.gicv3_nolpi=
-			[ARM, ARM64]
+			[ARM,ARM64,EARLY]
 			Force the kernel to ignore the availability of
 			LPIs (and by consequence ITSs). Intended for system
 			that use the kernel as a bootloader, and thus want
 			to let secondary kernels in charge of setting up
 			LPIs.
 
-	irqchip.gicv3_pseudo_nmi= [ARM64]
+	irqchip.gicv3_pseudo_nmi= [ARM64,EARLY]
 			Enables support for pseudo-NMIs in the kernel. This
 			requires the kernel to be built with
 			CONFIG_ARM64_PSEUDO_NMI.
@@ -2445,7 +2458,7 @@
 			parameter KASAN will print report only for the first
 			invalid access.
 
-	keep_bootcon	[KNL]
+	keep_bootcon	[KNL,EARLY]
 			Do not unregister boot console at start. This is only
 			useful for debugging when something happens in the window
 			between unregistering the boot console and initializing
@@ -2453,7 +2466,7 @@
 
 	keepinitrd	[HW,ARM] See retain_initrd.
 
-	kernelcore=	[KNL,X86,IA-64,PPC]
+	kernelcore=	[KNL,X86,IA-64,PPC,EARLY]
 			Format: nn[KMGTPE] | nn% | "mirror"
 			This parameter specifies the amount of memory usable by
 			the kernel for non-movable allocations.  The requested
@@ -2478,7 +2491,7 @@
 			for Movable pages.  "nn[KMGTPE]", "nn%", and "mirror"
 			are exclusive, so you cannot specify multiple forms.
 
-	kgdbdbgp=	[KGDB,HW] kgdb over EHCI usb debug port.
+	kgdbdbgp=	[KGDB,HW,EARLY] kgdb over EHCI usb debug port.
 			Format: <Controller#>[,poll interval]
 			The controller # is the number of the ehci usb debug
 			port as it is probed via PCI.  The poll interval is
@@ -2499,7 +2512,7 @@
 			 kms, kbd format: kms,kbd
 			 kms, kbd and serial format: kms,kbd,<ser_dev>[,baud]
 
-	kgdboc_earlycon=	[KGDB,HW]
+	kgdboc_earlycon=	[KGDB,HW,EARLY]
 			If the boot console provides the ability to read
 			characters and can work in polling mode, you can use
 			this parameter to tell kgdb to use it as a backend
@@ -2514,14 +2527,14 @@
 			blank and the first boot console that implements
 			read() will be picked.
 
-	kgdbwait	[KGDB] Stop kernel execution and enter the
+	kgdbwait	[KGDB,EARLY] Stop kernel execution and enter the
 			kernel debugger at the earliest opportunity.
 
 	kmac=		[MIPS] Korina ethernet MAC address.
 			Configure the RouterBoard 532 series on-chip
 			Ethernet adapter MAC address.
 
-	kmemleak=	[KNL] Boot-time kmemleak enable/disable
+	kmemleak=	[KNL,EARLY] Boot-time kmemleak enable/disable
 			Valid arguments: on, off
 			Default: on
 			Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
@@ -2540,8 +2553,8 @@
 			See also Documentation/trace/kprobetrace.rst "Kernel
 			Boot Parameter" section.
 
-	kpti=		[ARM64] Control page table isolation of user
-			and kernel address spaces.
+	kpti=		[ARM64,EARLY] Control page table isolation of
+			user and kernel address spaces.
 			Default: enabled on cores which need mitigation.
 			0: force disabled
 			1: force enabled
@@ -2618,7 +2631,8 @@
 			for NPT.
 
 	kvm-arm.mode=
-			[KVM,ARM] Select one of KVM/arm64's modes of operation.
+			[KVM,ARM,EARLY] Select one of KVM/arm64's modes of
+			operation.
 
 			none: Forcefully disable KVM.
 
@@ -2638,22 +2652,22 @@
 			used with extreme caution.
 
 	kvm-arm.vgic_v3_group0_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 group-0
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0
 			system registers
 
 	kvm-arm.vgic_v3_group1_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 group-1
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 group-1
 			system registers
 
 	kvm-arm.vgic_v3_common_trap=
-			[KVM,ARM] Trap guest accesses to GICv3 common
+			[KVM,ARM,EARLY] Trap guest accesses to GICv3 common
 			system registers
 
 	kvm-arm.vgic_v4_enable=
-			[KVM,ARM] Allow use of GICv4 for direct injection of
-			LPIs.
+			[KVM,ARM,EARLY] Allow use of GICv4 for direct
+			injection of LPIs.
 
-	kvm_cma_resv_ratio=n [PPC]
+	kvm_cma_resv_ratio=n [PPC,EARLY]
 			Reserves given percentage from system memory area for
 			contiguous memory allocation for KVM hash pagetable
 			allocation.
@@ -2706,7 +2720,7 @@
 			(enabled). Disable by KVM if hardware lacks support
 			for it.
 
-	l1d_flush=	[X86,INTEL]
+	l1d_flush=	[X86,INTEL,EARLY]
 			Control mitigation for L1D based snooping vulnerability.
 
 			Certain CPUs are vulnerable to an exploit against CPU
@@ -2723,7 +2737,7 @@
 
 			on         - enable the interface for the mitigation
 
-	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
+	l1tf=           [X86,EARLY] Control mitigation of the L1TF vulnerability on
 			      affected CPUs
 
 			The kernel PTE inversion protection is unconditionally
@@ -2792,7 +2806,7 @@
 
 	l3cr=		[PPC]
 
-	lapic		[X86-32,APIC] Enable the local APIC even if BIOS
+	lapic		[X86-32,APIC,EARLY] Enable the local APIC even if BIOS
 			disabled it.
 
 	lapic=		[X86,APIC] Do not use TSC deadline
@@ -2800,7 +2814,7 @@
 			back to the programmable timer unit in the LAPIC.
 			Format: notscdeadline
 
-	lapic_timer_c2_ok	[X86,APIC] trust the local apic timer
+	lapic_timer_c2_ok	[X86,APIC,EARLY] trust the local apic timer
 			in C2 power state.
 
 	libata.dma=	[LIBATA] DMA control
@@ -2924,7 +2938,7 @@
 	lockd.nlm_udpport=M	[NFS] Assign UDP port.
 			Format: <integer>
 
-	lockdown=	[SECURITY]
+	lockdown=	[SECURITY,EARLY]
 			{ integrity | confidentiality }
 			Enable the kernel lockdown feature. If set to
 			integrity, kernel features that allow userland to
@@ -3031,7 +3045,8 @@
 	logibm.irq=	[HW,MOUSE] Logitech Bus Mouse Driver
 			Format: <irq>
 
-	loglevel=	All Kernel Messages with a loglevel smaller than the
+	loglevel=	[KNL,EARLY]
+			All Kernel Messages with a loglevel smaller than the
 			console loglevel will be printed to the console. It can
 			also be changed with klogd or other programs. The
 			loglevels are defined as follows:
@@ -3045,13 +3060,15 @@
 			6 (KERN_INFO)		informational
 			7 (KERN_DEBUG)		debug-level messages
 
-	log_buf_len=n[KMG]	Sets the size of the printk ring buffer,
-			in bytes.  n must be a power of two and greater
-			than the minimal size. The minimal size is defined
-			by LOG_BUF_SHIFT kernel config parameter. There is
-			also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
-			that allows to increase the default size depending on
-			the number of CPUs. See init/Kconfig for more details.
+	log_buf_len=n[KMG] [KNL,EARLY]
+			Sets the size of the printk ring buffer, in bytes.
+			n must be a power of two and greater than the
+			minimal size. The minimal size is defined by
+			LOG_BUF_SHIFT kernel config parameter. There
+			is also CONFIG_LOG_CPU_MAX_BUF_SHIFT config
+			parameter that allows to increase the default size
+			depending on the number of CPUs. See init/Kconfig
+			for more details.
 
 	logo.nologo	[FB] Disables display of the built-in Linux logo.
 			This may be used to provide more screen space for
@@ -3109,7 +3126,7 @@
 	max_addr=nn[KMG]	[KNL,BOOT,IA-64] All physical memory greater
 			than or equal to this physical address is ignored.
 
-	maxcpus=	[SMP] Maximum number of processors that	an SMP kernel
+	maxcpus=	[SMP,EARLY] Maximum number of processors that an SMP kernel
 			will bring up during bootup.  maxcpus=n : n >= 0 limits
 			the kernel to bring up 'n' processors. Surely after
 			bootup you can bring up the other plugged cpu by executing
@@ -3136,7 +3153,7 @@
 			Format: <first>,<last>
 			Specifies range of consoles to be captured by the MDA.
 
-	mds=		[X86,INTEL]
+	mds=		[X86,INTEL,EARLY]
 			Control mitigation for the Micro-architectural Data
 			Sampling (MDS) vulnerability.
 
@@ -3168,11 +3185,12 @@
 
 			For details see: Documentation/admin-guide/hw-vuln/mds.rst
 
-	mem=nn[KMG]	[HEXAGON] Set the memory size.
+	mem=nn[KMG]	[HEXAGON,EARLY] Set the memory size.
 			Must be specified, otherwise memory size will be 0.
 
-	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
-			Amount of memory to be used in cases as follows:
+	mem=nn[KMG]	[KNL,BOOT,EARLY] Force usage of a specific amount
+			of memory Amount of memory to be used in cases
+			as follows:
 
 			1 for test;
 			2 when the kernel is not able to see the whole system memory;
@@ -3196,8 +3214,8 @@
 			if system memory of hypervisor is not sufficient.
 
 	mem=nn[KMG]@ss[KMG]
-			[ARM,MIPS] - override the memory layout reported by
-			firmware.
+			[ARM,MIPS,EARLY] - override the memory layout
+			reported by firmware.
 			Define a memory region of size nn[KMG] starting at
 			ss[KMG].
 			Multiple different regions can be specified with
@@ -3206,7 +3224,7 @@
 	mem=nopentium	[BUGS=X86-32] Disable usage of 4MB pages for kernel
 			memory.
 
-	memblock=debug	[KNL] Enable memblock debug messages.
+	memblock=debug	[KNL,EARLY] Enable memblock debug messages.
 
 	memchunk=nn[KMG]
 			[KNL,SH] Allow user to override the default size for
@@ -3220,14 +3238,14 @@
 			option.
 			See Documentation/admin-guide/mm/memory-hotplug.rst.
 
-	memmap=exactmap	[KNL,X86] Enable setting of an exact
+	memmap=exactmap	[KNL,X86,EARLY] Enable setting of an exact
 			E820 memory map, as specified by the user.
 			Such memmap=exactmap lines can be constructed based on
 			BIOS output or other requirements. See the memmap=nn@ss
 			option description.
 
 	memmap=nn[KMG]@ss[KMG]
-			[KNL, X86, MIPS, XTENSA] Force usage of a specific region of memory.
+			[KNL, X86,MIPS,XTENSA,EARLY] Force usage of a specific region of memory.
 			Region of memory to be used is from ss to ss+nn.
 			If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
 			which limits max address to nn[KMG].
@@ -3237,11 +3255,11 @@
 				memmap=100M@2G,100M#3G,1G!1024G
 
 	memmap=nn[KMG]#ss[KMG]
-			[KNL,ACPI] Mark specific memory as ACPI data.
+			[KNL,ACPI,EARLY] Mark specific memory as ACPI data.
 			Region of memory to be marked is from ss to ss+nn.
 
 	memmap=nn[KMG]$ss[KMG]
-			[KNL,ACPI] Mark specific memory as reserved.
+			[KNL,ACPI,EARLY] Mark specific memory as reserved.
 			Region of memory to be reserved is from ss to ss+nn.
 			Example: Exclude memory from 0x18690000-0x1869ffff
 			         memmap=64K$0x18690000
@@ -3251,14 +3269,14 @@
 			like Grub2, otherwise '$' and the following number
 			will be eaten.
 
-	memmap=nn[KMG]!ss[KMG]
+	memmap=nn[KMG]!ss[KMG,EARLY]
 			[KNL,X86] Mark specific memory as protected.
 			Region of memory to be used, from ss to ss+nn.
 			The memory region may be marked as e820 type 12 (0xc)
 			and is NVDIMM or ADR memory.
 
 	memmap=<size>%<offset>-<oldtype>+<newtype>
-			[KNL,ACPI] Convert memory within the specified region
+			[KNL,ACPI,EARLY] Convert memory within the specified region
 			from <oldtype> to <newtype>. If "-<oldtype>" is left
 			out, the whole region will be marked as <newtype>,
 			even if previously unavailable. If "+<newtype>" is left
@@ -3266,7 +3284,7 @@
 			specified as e820 types, e.g., 1 = RAM, 2 = reserved,
 			3 = ACPI, 12 = PRAM.
 
-	memory_corruption_check=0/1 [X86]
+	memory_corruption_check=0/1 [X86,EARLY]
 			Some BIOSes seem to corrupt the first 64k of
 			memory when doing things like suspend/resume.
 			Setting this option will scan the memory
@@ -3278,13 +3296,13 @@
 			affects the same memory, you can use memmap=
 			to prevent the kernel from using that memory.
 
-	memory_corruption_check_size=size [X86]
+	memory_corruption_check_size=size [X86,EARLY]
 			By default it checks for corruption in the low
 			64k, making this memory unavailable for normal
 			use.  Use this parameter to scan for
 			corruption in more or less memory.
 
-	memory_corruption_check_period=seconds [X86]
+	memory_corruption_check_period=seconds [X86,EARLY]
 			By default it checks for corruption every 60
 			seconds.  Use this parameter to check at some
 			other rate.  0 disables periodic checking.
@@ -3308,7 +3326,7 @@
 			Note that even when enabled, there are a few cases where
 			the feature is not effective.
 
-	memtest=	[KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest
+	memtest=	[KNL,X86,ARM,M68K,PPC,RISCV,EARLY] Enable memtest
 			Format: <integer>
 			default : 0 <disable>
 			Specifies the number of memtest passes to be
@@ -3320,9 +3338,7 @@
 
 	mem_encrypt=	[X86-64] AMD Secure Memory Encryption (SME) control
 			Valid arguments: on, off
-			Default (depends on kernel configuration option):
-			  on  (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y)
-			  off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n)
+			Default: off
 			mem_encrypt=on:		Activate SME
 			mem_encrypt=off:	Do not activate SME
 
@@ -3376,7 +3392,7 @@
 			https://repo.or.cz/w/linux-2.6/mini2440.git
 
 	mitigations=
-			[X86,PPC,S390,ARM64] Control optional mitigations for
+			[X86,PPC,S390,ARM64,EARLY] Control optional mitigations for
 			CPU vulnerabilities.  This is a set of curated,
 			arch-independent options, each of which is an
 			aggregation of existing arch-specific options.
@@ -3398,7 +3414,9 @@
 					       nospectre_bhb [ARM64]
 					       nospectre_v1 [X86,PPC]
 					       nospectre_v2 [X86,PPC,S390,ARM64]
+					       reg_file_data_sampling=off [X86]
 					       retbleed=off [X86]
+					       spec_rstack_overflow=off [X86]
 					       spec_store_bypass_disable=off [X86,PPC]
 					       spectre_v2_user=off [X86]
 					       srbds=off [X86,INTEL]
@@ -3429,7 +3447,7 @@
 					       retbleed=auto,nosmt [X86]
 
 	mminit_loglevel=
-			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
+			[KNL,EARLY] When CONFIG_DEBUG_MEMORY_INIT is set, this
 			parameter allows control of the logging verbosity for
 			the additional memory initialisation checks. A value
 			of 0 disables mminit logging and a level of 4 will
@@ -3437,7 +3455,7 @@
 			so loglevel=8 may also need to be specified.
 
 	mmio_stale_data=
-			[X86,INTEL] Control mitigation for the Processor
+			[X86,INTEL,EARLY] Control mitigation for the Processor
 			MMIO Stale Data vulnerabilities.
 
 			Processor MMIO Stale Data is a class of
@@ -3512,7 +3530,7 @@
 	mousedev.yres=	[MOUSE] Vertical screen resolution, used for devices
 			reporting absolute coordinates, such as tablets
 
-	movablecore=	[KNL,X86,IA-64,PPC]
+	movablecore=	[KNL,X86,IA-64,PPC,EARLY]
 			Format: nn[KMGTPE] | nn%
 			This parameter is the complement to kernelcore=, it
 			specifies the amount of memory used for migratable
@@ -3523,7 +3541,7 @@
 			that the amount of memory usable for all allocations
 			is not too small.
 
-	movable_node	[KNL] Boot-time switch to make hotplugable memory
+	movable_node	[KNL,EARLY] Boot-time switch to make hotplugable memory
 			NUMA nodes to be movable. This means that the memory
 			of such nodes will be usable only for movable
 			allocations which rules out almost all kernel
@@ -3547,21 +3565,21 @@
 			[HW] Make the MicroTouch USB driver use raw coordinates
 			('y', default) or cooked coordinates ('n')
 
-	mtrr=debug	[X86]
+	mtrr=debug	[X86,EARLY]
 			Enable printing debug information related to MTRR
 			registers at boot time.
 
-	mtrr_chunk_size=nn[KMG] [X86]
+	mtrr_chunk_size=nn[KMG,X86,EARLY]
 			used for mtrr cleanup. It is largest continuous chunk
 			that could hold holes aka. UC entries.
 
-	mtrr_gran_size=nn[KMG] [X86]
+	mtrr_gran_size=nn[KMG,X86,EARLY]
 			Used for mtrr cleanup. It is granularity of mtrr block.
 			Default is 1.
 			Large value could prevent small alignment from
 			using up MTRRs.
 
-	mtrr_spare_reg_nr=n [X86]
+	mtrr_spare_reg_nr=n [X86,EARLY]
 			Format: <integer>
 			Range: 0,7 : spare reg number
 			Default : 1
@@ -3747,10 +3765,10 @@
 			emulation library even if a 387 maths coprocessor
 			is present.
 
-	no4lvl		[RISCV] Disable 4-level and 5-level paging modes. Forces
-			kernel to use 3-level paging instead.
+	no4lvl		[RISCV,EARLY] Disable 4-level and 5-level paging modes.
+			Forces kernel to use 3-level paging instead.
 
-	no5lvl		[X86-64,RISCV] Disable 5-level paging mode. Forces
+	no5lvl		[X86-64,RISCV,EARLY] Disable 5-level paging mode. Forces
 			kernel to use 4-level paging instead.
 
 	noaliencache	[MM, NUMA, SLAB] Disables the allocation of alien
@@ -3759,15 +3777,15 @@
 
 	noalign		[KNL,ARM]
 
-	noaltinstr	[S390] Disables alternative instructions patching
-			(CPU alternatives feature).
+	noaltinstr	[S390,EARLY] Disables alternative instructions
+			patching (CPU alternatives feature).
 
-	noapic		[SMP,APIC] Tells the kernel to not make use of any
+	noapic		[SMP,APIC,EARLY] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
 	noautogroup	Disable scheduler automatic task group creation.
 
-	nocache		[ARM]
+	nocache		[ARM,EARLY]
 
 	no_console_suspend
 			[HW] Never suspend the console
@@ -3785,13 +3803,13 @@
 			turn on/off it dynamically.
 
 	no_debug_objects
-			[KNL] Disable object debugging
+			[KNL,EARLY] Disable object debugging
 
 	nodsp		[SH] Disable hardware DSP at boot time.
 
-	noefi		Disable EFI runtime services support.
+	noefi		[EFI,EARLY] Disable EFI runtime services support.
 
-	no_entry_flush  [PPC] Don't flush the L1-D cache when entering the kernel.
+	no_entry_flush  [PPC,EARLY] Don't flush the L1-D cache when entering the kernel.
 
 	noexec		[IA-64]
 
@@ -3822,6 +3840,7 @@
 			real-time systems.
 
 	no_hash_pointers
+			[KNL,EARLY]
 			Force pointers printed to the console or buffers to be
 			unhashed.  By default, when a pointer is printed via %p
 			format string, that pointer is "hashed", i.e. obscured
@@ -3846,9 +3865,9 @@
 			the impact of the sleep instructions. This is also
 			useful when using JTAG debugger.
 
-	nohugeiomap	[KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
+	nohugeiomap	[KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings.
 
-	nohugevmalloc	[KNL,X86,PPC,ARM64] Disable kernel huge vmalloc mappings.
+	nohugevmalloc	[KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings.
 
 	nohz=		[KNL] Boottime enable/disable dynamic ticks
 			Valid arguments: on, off
@@ -3870,13 +3889,13 @@
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
-	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+	nointremap	[X86-64,Intel-IOMMU,EARLY] Do not enable interrupt
 			remapping.
 			[Deprecated - use intremap=off]
 
 	nointroute	[IA-64]
 
-	noinvpcid	[X86] Disable the INVPCID cpu feature.
+	noinvpcid	[X86,EARLY] Disable the INVPCID cpu feature.
 
 	noiotrap	[SH] Disables trapped I/O port accesses.
 
@@ -3887,19 +3906,19 @@
 
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
-	nokaslr		[KNL]
+	nokaslr		[KNL,EARLY]
 			When CONFIG_RANDOMIZE_BASE is set, this disables
 			kernel and module base offset ASLR (Address Space
 			Layout Randomization).
 
-	no-kvmapf	[X86,KVM] Disable paravirtualized asynchronous page
+	no-kvmapf	[X86,KVM,EARLY] Disable paravirtualized asynchronous page
 			fault handling.
 
-	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
+	no-kvmclock	[X86,KVM,EARLY] Disable paravirtualized KVM clock driver
 
-	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
+	nolapic		[X86-32,APIC,EARLY] Do not enable or use the local APIC.
 
-	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
+	nolapic_timer	[X86-32,APIC,EARLY] Do not use the local APIC timer.
 
 	nomca		[IA-64] Disable machine check abort handling
 
@@ -3924,23 +3943,23 @@
 			shutdown the other cpus.  Instead use the REBOOT_VECTOR
 			irq.
 
-	nopat		[X86] Disable PAT (page attribute table extension of
+	nopat		[X86,EARLY] Disable PAT (page attribute table extension of
 			pagetables) support.
 
-	nopcid		[X86-64] Disable the PCID cpu feature.
+	nopcid		[X86-64,EARLY] Disable the PCID cpu feature.
 
 	nopku		[X86] Disable Memory Protection Keys CPU feature found
 			in some Intel CPUs.
 
-	nopti		[X86-64]
+	nopti		[X86-64,EARLY]
 			Equivalent to pti=off
 
-	nopv=		[X86,XEN,KVM,HYPER_V,VMWARE]
+	nopv=		[X86,XEN,KVM,HYPER_V,VMWARE,EARLY]
 			Disables the PV optimizations forcing the guest to run
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
-	nopvspin	[X86,XEN,KVM]
+	nopvspin	[X86,XEN,KVM,EARLY]
 			Disables the qspinlock slow path using PV optimizations
 			which allow the hypervisor to 'idle' the guest on lock
 			contention.
@@ -3960,20 +3979,20 @@
 			This is required for the Braillex ib80-piezo Braille
 			reader made by F.H. Papenmeier (Germany).
 
-	nosgx		[X86-64,SGX] Disables Intel SGX kernel support.
+	nosgx		[X86-64,SGX,EARLY] Disables Intel SGX kernel support.
 
-	nosmap		[PPC]
+	nosmap		[PPC,EARLY]
 			Disable SMAP (Supervisor Mode Access Prevention)
 			even if it is supported by processor.
 
-	nosmep		[PPC64s]
+	nosmep		[PPC64s,EARLY]
 			Disable SMEP (Supervisor Mode Execution Prevention)
 			even if it is supported by processor.
 
-	nosmp		[SMP] Tells an SMP kernel to act as a UP kernel,
+	nosmp		[SMP,EARLY] Tells an SMP kernel to act as a UP kernel,
 			and disable the IO APIC.  legacy for "maxcpus=0".
 
-	nosmt		[KNL,MIPS,PPC,S390] Disable symmetric multithreading (SMT).
+	nosmt		[KNL,MIPS,PPC,S390,EARLY] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
 			[KNL,X86,PPC] Disable symmetric multithreading (SMT).
@@ -3983,22 +4002,23 @@
 	nosoftlockup	[KNL] Disable the soft-lockup detector.
 
 	nospec_store_bypass_disable
-			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+			[HW,EARLY] Disable all mitigations for the Speculative
+			Store Bypass vulnerability
 
-	nospectre_bhb	[ARM64] Disable all mitigations for Spectre-BHB (branch
+	nospectre_bhb	[ARM64,EARLY] Disable all mitigations for Spectre-BHB (branch
 			history injection) vulnerability. System may allow data leaks
 			with this option.
 
-	nospectre_v1	[X86,PPC] Disable mitigations for Spectre Variant 1
+	nospectre_v1	[X86,PPC,EARLY] Disable mitigations for Spectre Variant 1
 			(bounds check bypass). With this option data leaks are
 			possible in the system.
 
-	nospectre_v2	[X86,PPC_E500,ARM64] Disable all mitigations for
-			the Spectre variant 2 (indirect branch prediction)
-			vulnerability. System may allow data leaks with this
-			option.
+	nospectre_v2	[X86,PPC_E500,ARM64,EARLY] Disable all mitigations
+			for the Spectre variant 2 (indirect branch
+			prediction) vulnerability. System may allow data
+			leaks with this option.
 
-	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES,RISCV] Disable
+	no-steal-acc	[X86,PV_OPS,ARM64,PPC/PSERIES,RISCV,EARLY] Disable
 			paravirtualized steal time accounting. steal time is
 			computed, but won't influence scheduler behaviour
 
@@ -4008,7 +4028,7 @@
 			broken timer IRQ sources.
 
 	no_uaccess_flush
-	                [PPC] Don't flush the L1-D cache after accessing user data.
+	                [PPC,EARLY] Don't flush the L1-D cache after accessing user data.
 
 	novmcoredd	[KNL,KDUMP]
 			Disable device dump. Device dump allows drivers to
@@ -4022,15 +4042,15 @@
 			is set.
 
 	no-vmw-sched-clock
-			[X86,PV_OPS] Disable paravirtualized VMware scheduler
-			clock and use the default one.
+			[X86,PV_OPS,EARLY] Disable paravirtualized VMware
+			scheduler clock and use the default one.
 
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
 			soft-lockup and NMI watchdog (hard-lockup).
 
-	nowb		[ARM]
+	nowb		[ARM,EARLY]
 
-	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.
+	nox2apic	[X86-64,APIC,EARLY] Do not enable x2APIC mode.
 
 			NOTE: this parameter will be ignored on systems with the
 			LEGACY_XAPIC_DISABLED bit set in the
@@ -4068,7 +4088,7 @@
 			purges which is reported from either PAL_VM_SUMMARY or
 			SAL PALO.
 
-	nr_cpus=	[SMP] Maximum number of processors that	an SMP kernel
+	nr_cpus=	[SMP,EARLY] Maximum number of processors that an SMP kernel
 			could support.  nr_cpus=n : n >= 1 limits the kernel to
 			support 'n' processors. It could be larger than the
 			number of already plugged CPU during bootup, later in
@@ -4079,8 +4099,9 @@
 
 	nr_uarts=	[SERIAL] maximum number of UARTs to be registered.
 
-	numa=off 	[KNL, ARM64, PPC, RISCV, SPARC, X86] Disable NUMA, Only
-			set up a single NUMA node spanning all memory.
+	numa=off 	[KNL, ARM64, PPC, RISCV, SPARC, X86, EARLY]
+			Disable NUMA, Only set up a single NUMA node
+			spanning all memory.
 
 	numa_balancing=	[KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
 			NUMA balancing.
@@ -4091,7 +4112,7 @@
 			This can be set from sysctl after boot.
 			See Documentation/admin-guide/sysctl/vm.rst for details.
 
-	ohci1394_dma=early	[HW] enable debugging via the ohci1394 driver.
+	ohci1394_dma=early	[HW,EARLY] enable debugging via the ohci1394 driver.
 			See Documentation/core-api/debugging-via-ohci1394.rst for more
 			info.
 
@@ -4117,7 +4138,8 @@
 				   Once locked, the boundary cannot be changed.
 				   1 indicates lock status, 0 indicates unlock status.
 
-	oops=panic	Always panic on oopses. Default is to just kill the
+	oops=panic	[KNL,EARLY]
+			Always panic on oopses. Default is to just kill the
 			process, but there is a small probability of
 			deadlocking the machine.
 			This will also cause panics on machine check exceptions.
@@ -4133,13 +4155,13 @@
 			can be read from sysfs at:
 			/sys/module/page_alloc/parameters/shuffle.
 
-	page_owner=	[KNL] Boot-time page_owner enabling option.
+	page_owner=	[KNL,EARLY] Boot-time page_owner enabling option.
 			Storage of the information about who allocated
 			each page is disabled in default. With this switch,
 			we can turn it on.
 			on: enable the feature
 
-	page_poison=	[KNL] Boot-time parameter changing the state of
+	page_poison=	[KNL,EARLY] Boot-time parameter changing the state of
 			poisoning on the buddy allocator, available with
 			CONFIG_PAGE_POISONING=y.
 			off: turn off poisoning (default)
@@ -4157,7 +4179,8 @@
 			timeout < 0: reboot immediately
 			Format: <timeout>
 
-	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
+	panic_on_taint=	[KNL,EARLY]
+			Bitmask for conditionally calling panic() in add_taint()
 			Format: <hex>[,nousertaint]
 			Hexadecimal bitmask representing the set of TAINT flags
 			that will cause the kernel to panic when add_taint() is
@@ -4313,7 +4336,7 @@
 
 	pcbit=		[HW,ISDN]
 
-	pci=option[,option...]	[PCI] various PCI subsystem options.
+	pci=option[,option...]	[PCI,EARLY] various PCI subsystem options.
 
 				Some options herein operate on a specific device
 				or a set of devices (<pci_dev>). These are
@@ -4582,7 +4605,8 @@
 			Format: { 0 | 1 }
 			See arch/parisc/kernel/pdc_chassis.c
 
-	percpu_alloc=	Select which percpu first chunk allocator to use.
+	percpu_alloc=	[MM,EARLY]
+			Select which percpu first chunk allocator to use.
 			Currently supported values are "embed" and "page".
 			Archs may support subset or none of the	selections.
 			See comments in mm/percpu.c for details on each
@@ -4651,12 +4675,12 @@
 			execution priority.
 
 	ppc_strict_facility_enable
-			[PPC] This option catches any kernel floating point,
+			[PPC,ENABLE] This option catches any kernel floating point,
 			Altivec, VSX and SPE outside of regions specifically
 			allowed (eg kernel_enable_fpu()/kernel_disable_fpu()).
 			There is some performance impact when enabling this.
 
-	ppc_tm=		[PPC]
+	ppc_tm=		[PPC,EARLY]
 			Format: {"off"}
 			Disable Hardware Transactional Memory
 
@@ -4766,7 +4790,7 @@
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
 
-	quiet		[KNL] Disable most log messages
+	quiet		[KNL,EARLY] Disable most log messages
 
 	r128=		[HW,DRM]
 
@@ -4783,17 +4807,17 @@
 	ramdisk_start=	[RAM] RAM disk image start address
 
 	random.trust_cpu=off
-			[KNL] Disable trusting the use of the CPU's
+			[KNL,EARLY] Disable trusting the use of the CPU's
 			random number generator (if available) to
 			initialize the kernel's RNG.
 
 	random.trust_bootloader=off
-			[KNL] Disable trusting the use of the a seed
+			[KNL,EARLY] Disable trusting the use of the a seed
 			passed by the bootloader (if available) to
 			initialize the kernel's RNG.
 
 	randomize_kstack_offset=
-			[KNL] Enable or disable kernel stack offset
+			[KNL,EARLY] Enable or disable kernel stack offset
 			randomization, which provides roughly 5 bits of
 			entropy, frustrating memory corruption attacks
 			that depend on stack address determinism or
@@ -5034,6 +5058,11 @@
 			this kernel boot parameter, forcibly setting it
 			to zero.
 
+	rcutree.enable_rcu_lazy= [KNL]
+			To save power, batch RCU callbacks and flush after
+			delay, memory pressure or callback list growing too
+			big.
+
 	rcuscale.gp_async= [KNL]
 			Measure performance of asynchronous
 			grace-period primitives such as call_rcu().
@@ -5484,7 +5513,7 @@
 			Run specified binary instead of /init from the ramdisk,
 			used for early userspace startup. See initrd.
 
-	rdrand=		[X86]
+	rdrand=		[X86,EARLY]
 			force - Override the decision by the kernel to hide the
 				advertisement of RDRAND support (this affects
 				certain AMD processors because of buggy BIOS
@@ -5580,7 +5609,7 @@
 			them.  If <base> is less than 0x10000, the region
 			is assumed to be I/O ports; otherwise it is memory.
 
-	reservetop=	[X86-32]
+	reservetop=	[X86-32,EARLY]
 			Format: nn[KMG]
 			Reserves a hole at the top of the kernel virtual
 			address space.
@@ -5665,7 +5694,7 @@
 			[KNL] Disable ring 3 MONITOR/MWAIT feature on supported
 			CPUs.
 
-	riscv_isa_fallback [RISCV]
+	riscv_isa_fallback [RISCV,EARLY]
 			When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit
 			falling back to detecting extension support by parsing
 			"riscv,isa" property on devicetree systems when the
@@ -5674,13 +5703,14 @@
 
 	ro		[KNL] Mount root device read-only on boot
 
-	rodata=		[KNL]
+	rodata=		[KNL,EARLY]
 		on	Mark read-only kernel memory as read-only (default).
 		off	Leave read-only kernel memory writable for debugging.
 		full	Mark read-only kernel memory and aliases as read-only
 		        [arm64]
 
 	rockchip.usb_uart
+			[EARLY]
 			Enable the uart passthrough on the designated usb port
 			on Rockchip SoCs. When active, the signals of the
 			debug-uart get routed to the D+ and D- pins of the usb
@@ -5741,7 +5771,7 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
-	sched_verbose	[KNL] Enables verbose scheduler debug messages.
+	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
 			Allowed values are enable and disable. This feature
@@ -5856,7 +5886,7 @@
 			non-zero "wait" parameter.  See weight_single
 			and weight_many.
 
-	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
+	skew_tick=	[KNL,EARLY] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.
 			Format: { "0" | "1" }
@@ -5987,10 +6017,10 @@
 				1: Fast pin select (default)
 				2: ATC IRMode
 
-	smt=		[KNL,MIPS,S390] Set the maximum number of threads (logical
-			CPUs) to use per physical CPU on systems capable of
-			symmetric multithreading (SMT). Will be capped to the
-			actual hardware limit.
+	smt=		[KNL,MIPS,S390,EARLY] Set the maximum number of threads
+			(logical CPUs) to use per physical CPU on systems
+			capable of symmetric multithreading (SMT). Will
+			be capped to the actual hardware limit.
 			Format: <integer>
 			Default: -1 (no limit)
 
@@ -6012,7 +6042,7 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/admin-guide/laptops/sonypi.rst
 
-	spectre_v2=	[X86] Control mitigation of Spectre variant 2
+	spectre_v2=	[X86,EARLY] Control mitigation of Spectre variant 2
 			(indirect branch speculation) vulnerability.
 			The default operation protects the kernel from
 			user space attacks.
@@ -6027,8 +6057,8 @@
 			Selecting 'on' will, and 'auto' may, choose a
 			mitigation method at run time according to the
 			CPU, the available microcode, the setting of the
-			CONFIG_RETPOLINE configuration option, and the
-			compiler with which the kernel was built.
+			CONFIG_MITIGATION_RETPOLINE configuration option,
+			and the compiler with which the kernel was built.
 
 			Selecting 'on' will also enable the mitigation
 			against user space to user space task attacks.
@@ -6092,7 +6122,7 @@
 			spectre_v2_user=auto.
 
 	spec_rstack_overflow=
-			[X86] Control RAS overflow mitigation on AMD Zen CPUs
+			[X86,EARLY] Control RAS overflow mitigation on AMD Zen CPUs
 
 			off		- Disable mitigation
 			microcode	- Enable microcode mitigation only
@@ -6103,7 +6133,7 @@
 					  (cloud-specific mitigation)
 
 	spec_store_bypass_disable=
-			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			[HW,EARLY] Control Speculative Store Bypass (SSB) Disable mitigation
 			(Speculative Store Bypass vulnerability)
 
 			Certain CPUs are vulnerable to an exploit against a
@@ -6199,7 +6229,7 @@
 			#DB exception for bus lock is triggered only when
 			CPL > 0.
 
-	srbds=		[X86,INTEL]
+	srbds=		[X86,INTEL,EARLY]
 			Control the Special Register Buffer Data Sampling
 			(SRBDS) mitigation.
 
@@ -6286,7 +6316,7 @@
 			srcutree.convert_to_big must have the 0x10 bit
 			set for contention-based conversions to occur.
 
-	ssbd=		[ARM64,HW]
+	ssbd=		[ARM64,HW,EARLY]
 			Speculative Store Bypass Disable control
 
 			On CPUs that are vulnerable to the Speculative
@@ -6310,7 +6340,7 @@
 			growing up) the main stack are reserved for no other
 			mapping. Default value is 256 pages.
 
-	stack_depot_disable= [KNL]
+	stack_depot_disable= [KNL,EARLY]
 			Setting this to true through kernel command line will
 			disable the stack depot thereby saving the static memory
 			consumed by the stack hash table. By default this is set
@@ -6349,12 +6379,12 @@
 			be used to filter out binaries which have
 			not yet been made aware of AT_MINSIGSTKSZ.
 
-	stress_hpt	[PPC]
+	stress_hpt	[PPC,EARLY]
 			Limits the number of kernel HPT entries in the hash
 			page table to increase the rate of hash page table
 			faults on kernel addresses.
 
-	stress_slb	[PPC]
+	stress_slb	[PPC,EARLY]
 			Limits the number of kernel SLB entries, and flushes
 			them frequently to increase the rate of SLB faults
 			on kernel addresses.
@@ -6414,7 +6444,7 @@
 			This parameter controls use of the Protected
 			Execution Facility on pSeries.
 
-	swiotlb=	[ARM,IA-64,PPC,MIPS,X86]
+	swiotlb=	[ARM,IA-64,PPC,MIPS,X86,EARLY]
 			Format: { <int> [,<int>] | force | noforce }
 			<int> -- Number of I/O TLB slabs
 			<int> -- Second integer after comma. Number of swiotlb
@@ -6424,7 +6454,7 @@
 			         wouldn't be automatically used by the kernel
 			noforce -- Never use bounce buffers (for debugging)
 
-	switches=	[HW,M68k]
+	switches=	[HW,M68k,EARLY]
 
 	sysctl.*=	[KNL]
 			Set a sysctl parameter, right before loading the init
@@ -6483,11 +6513,11 @@
 			<deci-seconds>: poll all this frequency
 			0: no polling (default)
 
-	threadirqs	[KNL]
+	threadirqs	[KNL,EARLY]
 			Force threading of all interrupt handlers except those
 			marked explicitly IRQF_NO_THREAD.
 
-	topology=	[S390]
+	topology=	[S390,EARLY]
 			Format: {off | on}
 			Specify if the kernel should make use of the cpu
 			topology information if the hardware supports this.
@@ -6728,7 +6758,7 @@
 			can be overridden by a later tsc=nowatchdog.  A console
 			message will flag any such suppression or overriding.
 
-	tsc_early_khz=  [X86] Skip early TSC calibration and use the given
+	tsc_early_khz=  [X86,EARLY] Skip early TSC calibration and use the given
 			value instead. Useful when the early TSC frequency discovery
 			procedure is not reliable, such as on overclocked systems
 			with CPUID.16h support and partial CPUID.15h support.
@@ -6763,7 +6793,7 @@
 			See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
 			for more details.
 
-	tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
+	tsx_async_abort= [X86,INTEL,EARLY] Control mitigation for the TSX Async
 			Abort (TAA) vulnerability.
 
 			Similar to Micro-architectural Data Sampling (MDS)
@@ -6829,7 +6859,7 @@
 	unknown_nmi_panic
 			[X86] Cause panic on unknown NMI.
 
-	unwind_debug	[X86-64]
+	unwind_debug	[X86-64,EARLY]
 			Enable unwinder debug output.  This can be
 			useful for debugging certain unwinder error
 			conditions, including corrupt stacks and
@@ -7019,7 +7049,7 @@
 			Example: user_debug=31
 
 	userpte=
-			[X86] Flags controlling user PTE allocations.
+			[X86,EARLY] Flags controlling user PTE allocations.
 
 				nohigh = do not allocate PTE pages in
 					HIGHMEM regardless of setting
@@ -7048,7 +7078,7 @@
 	vector=		[IA-64,SMP]
 			vector=percpu: enable percpu vector domain
 
-	video=		[FB] Frame buffer configuration
+	video=		[FB,EARLY] Frame buffer configuration
 			See Documentation/fb/modedb.rst.
 
 	video.brightness_switch_enabled= [ACPI]
@@ -7096,13 +7126,13 @@
 			  P	Enable page structure init time poisoning
 			  -	Disable all of the above options
 
-	vmalloc=nn[KMG]	[KNL,BOOT] Forces the vmalloc area to have an exact
-			size of <nn>. This can be used to increase the
-			minimum size (128MB on x86). It can also be used to
-			decrease the size and leave more room for directly
-			mapped kernel RAM.
+	vmalloc=nn[KMG]	[KNL,BOOT,EARLY] Forces the vmalloc area to have an
+			exact size of <nn>. This can be used to increase
+			the minimum size (128MB on x86). It can also be
+			used to decrease the size and leave more room
+			for directly mapped kernel RAM.
 
-	vmcp_cma=nn[MG]	[KNL,S390]
+	vmcp_cma=nn[MG]	[KNL,S390,EARLY]
 			Sets the memory size reserved for contiguous memory
 			allocations for the vmcp device driver.
 
@@ -7115,7 +7145,7 @@
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
-	vsyscall=	[X86-64]
+	vsyscall=	[X86-64,EARLY]
 			Controls the behavior of vsyscalls (i.e. calls to
 			fixed addresses of 0xffffffffff600x00 from legacy
 			code).  Most statically-linked binaries and older
@@ -7225,6 +7255,15 @@
 			threshold repeatedly. They are likely good
 			candidates for using WQ_UNBOUND workqueues instead.
 
+	workqueue.cpu_intensive_warning_thresh=<uint>
+			If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
+			will report the work functions which violate the
+			intensive_threshold_us repeatedly. In order to prevent
+			spurious warnings, start printing only after a work
+			function has violated this threshold number of times.
+
+			The default is 4 times. 0 disables the warning.
+
 	workqueue.power_efficient
 			Per-cpu workqueues are generally preferred because
 			they show better performance thanks to cache
@@ -7263,13 +7302,13 @@
 			When enabled, memory and cache locality will be
 			impacted.
 
-	writecombine=	[LOONGARCH] Control the MAT (Memory Access Type) of
-			ioremap_wc().
+	writecombine=	[LOONGARCH,EARLY] Control the MAT (Memory Access
+			Type) of ioremap_wc().
 
 			on   - Enable writecombine, use WUC for ioremap_wc()
 			off  - Disable writecombine, use SUC for ioremap_wc()
 
-	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
+	x2apic_phys	[X86-64,APIC,EARLY] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
 
@@ -7280,7 +7319,7 @@
 			save/restore/migration must be enabled to handle larger
 			domains.
 
-	xen_emul_unplug=		[HW,X86,XEN]
+	xen_emul_unplug=		[HW,X86,XEN,EARLY]
 			Unplug Xen emulated devices
 			Format: [unplug0,][unplug1]
 			ide-disks -- unplug primary master IDE devices
@@ -7292,17 +7331,17 @@
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
-	xen_legacy_crash	[X86,XEN]
+	xen_legacy_crash	[X86,XEN,EARLY]
 			Crash from Xen panic notifier, without executing late
 			panic() code such as dumping handler.
 
-	xen_msr_safe=	[X86,XEN]
+	xen_msr_safe=	[X86,XEN,EARLY]
 			Format: <bool>
 			Select whether to always use non-faulting (safe) MSR
 			access functions when running as Xen PV guest. The
 			default value is controlled by CONFIG_XEN_PV_MSR_SAFE.
 
-	xen_nopvspin	[X86,XEN]
+	xen_nopvspin	[X86,XEN,EARLY]
 			Disables the qspinlock slowpath using Xen PV optimizations.
 			This parameter is obsoleted by "nopvspin" parameter, which
 			has equivalent effect for XEN platform.
@@ -7314,7 +7353,7 @@
 			has equivalent effect for XEN platform.
 
 	xen_no_vector_callback
-			[KNL,X86,XEN] Disable the vector callback for Xen
+			[KNL,X86,XEN,EARLY] Disable the vector callback for Xen
 			event channel interrupts.
 
 	xen_scrub_pages=	[XEN]
@@ -7323,7 +7362,7 @@
 			with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
 			Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
 
-	xen_timer_slop=	[X86-64,XEN]
+	xen_timer_slop=	[X86-64,XEN,EARLY]
 			Set the timer slop (in nanoseconds) for the virtual Xen
 			timers (default is 100000). This adjusts the minimum
 			delta of virtualized Xen timers, where lower values
@@ -7376,7 +7415,7 @@
 			host controller quirks. Meaning of each bit can be
 			consulted in header drivers/usb/host/xhci.h.
 
-	xmon		[PPC]
+	xmon		[PPC,EARLY]
 			Format: { early | on | rw | ro | off }
 			Controls if xmon debugger is enabled. Default is off.
 			Passing only "xmon" is equivalent to "xmon=early".
diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index e8c2ce1f9df6..45a7f4932fe0 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -243,3 +243,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ASR            | ASR8601         | #8601001        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2139208        | ARM64_ERRATUM_2139208       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2067961        | ARM64_ERRATUM_2067961       |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2253138        | ARM64_ERRATUM_2253138       |
++----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst
index 07caa8fff852..414bc7402ae7 100644
--- a/Documentation/arch/x86/amd-memory-encryption.rst
+++ b/Documentation/arch/x86/amd-memory-encryption.rst
@@ -87,14 +87,14 @@ The state of SME in the Linux kernel can be documented as follows:
 	  kernel is non-zero).
 
 SME can also be enabled and activated in the BIOS. If SME is enabled and
-activated in the BIOS, then all memory accesses will be encrypted and it will
-not be necessary to activate the Linux memory encryption support.  If the BIOS
-merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate
-memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or
-by supplying mem_encrypt=on on the kernel command line.  However, if BIOS does
-not enable SME, then Linux will not be able to activate memory encryption, even
-if configured to do so by default or the mem_encrypt=on command line parameter
-is specified.
+activated in the BIOS, then all memory accesses will be encrypted and it
+will not be necessary to activate the Linux memory encryption support.
+
+If the BIOS merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG),
+then memory encryption can be enabled by supplying mem_encrypt=on on the
+kernel command line.  However, if BIOS does not enable SME, then Linux
+will not be able to activate memory encryption, even if configured to do
+so by default or the mem_encrypt=on command line parameter is specified.
 
 Secure Nested Paging (SNP)
 ==========================
diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst
index c513855a54bb..4fd492cb4970 100644
--- a/Documentation/arch/x86/boot.rst
+++ b/Documentation/arch/x86/boot.rst
@@ -878,7 +878,8 @@ Protocol:	2.10+
   address if possible.
 
   A non-relocatable kernel will unconditionally move itself and to run
-  at this address.
+  at this address. A relocatable kernel will move itself to this address if it
+  loaded below this address.
 
 ============	=======
 Field name:	init_size
diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst
index e73fdff62c0a..c58c72362911 100644
--- a/Documentation/arch/x86/mds.rst
+++ b/Documentation/arch/x86/mds.rst
@@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing:
 
     mds_clear_cpu_buffers()
 
+Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path.
+Other than CFLAGS.ZF, this macro doesn't clobber any registers.
+
 The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state
 (idle) transitions.
 
@@ -138,17 +141,30 @@ Mitigation points
 
    When transitioning from kernel to user space the CPU buffers are flushed
    on affected CPUs when the mitigation is not disabled on the kernel
-   command line. The migitation is enabled through the static key
-   mds_user_clear.
-
-   The mitigation is invoked in prepare_exit_to_usermode() which covers
-   all but one of the kernel to user space transitions.  The exception
-   is when we return from a Non Maskable Interrupt (NMI), which is
-   handled directly in do_nmi().
-
-   (The reason that NMI is special is that prepare_exit_to_usermode() can
-    enable IRQs.  In NMI context, NMIs are blocked, and we don't want to
-    enable IRQs with NMIs blocked.)
+   command line. The mitigation is enabled through the feature flag
+   X86_FEATURE_CLEAR_CPU_BUF.
+
+   The mitigation is invoked just before transitioning to userspace after
+   user registers are restored. This is done to minimize the window in
+   which kernel data could be accessed after VERW e.g. via an NMI after
+   VERW.
+
+   **Corner case not handled**
+   Interrupts returning to kernel don't clear CPUs buffers since the
+   exit-to-user path is expected to do that anyways. But, there could be
+   a case when an NMI is generated in kernel after the exit-to-user path
+   has cleared the buffers. This case is not handled and NMI returning to
+   kernel don't clear CPU buffers because:
+
+   1. It is rare to get an NMI after VERW, but before returning to userspace.
+   2. For an unprivileged user, there is no known way to make that NMI
+      less rare or target it.
+   3. It would take a large number of these precisely-timed NMIs to mount
+      an actual attack.  There's presumably not enough bandwidth.
+   4. The NMI in question occurs after a VERW, i.e. when user state is
+      restored and most interesting data is already scrubbed. Whats left
+      is only the data that NMI touches, and that may or may not be of
+      any interest.
 
 
 2. C-State transition
diff --git a/Documentation/arch/x86/pti.rst b/Documentation/arch/x86/pti.rst
index e08d35177bc0..57e8392f61d3 100644
--- a/Documentation/arch/x86/pti.rst
+++ b/Documentation/arch/x86/pti.rst
@@ -26,9 +26,9 @@ comments in pti.c).
 
 This approach helps to ensure that side-channel attacks leveraging
 the paging structures do not function when PTI is enabled.  It can be
-enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time.
-Once enabled at compile-time, it can be disabled at boot with the
-'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt).
+enabled by setting CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=y at compile
+time.  Once enabled at compile-time, it can be disabled at boot with
+the 'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt).
 
 Page Table Management
 =====================
diff --git a/Documentation/arch/x86/topology.rst b/Documentation/arch/x86/topology.rst
index 08ebf9edbfc1..7352ab89a55a 100644
--- a/Documentation/arch/x86/topology.rst
+++ b/Documentation/arch/x86/topology.rst
@@ -47,17 +47,21 @@ AMD nomenclature for package is 'Node'.
 
 Package-related topology information in the kernel:
 
-  - cpuinfo_x86.x86_max_cores:
+  - topology_num_threads_per_package()
 
-    The number of cores in a package. This information is retrieved via CPUID.
+    The number of threads in a package.
 
-  - cpuinfo_x86.x86_max_dies:
+  - topology_num_cores_per_package()
 
-    The number of dies in a package. This information is retrieved via CPUID.
+    The number of cores in a package.
+
+  - topology_max_dies_per_package()
+
+    The maximum number of dies in a package.
 
   - cpuinfo_x86.topo.die_id:
 
-    The physical ID of the die. This information is retrieved via CPUID.
+    The physical ID of the die.
 
   - cpuinfo_x86.topo.pkg_id:
 
@@ -96,16 +100,6 @@ are SMT- or CMT-type threads.
 AMDs nomenclature for a CMT core is "Compute Unit". The kernel always uses
 "core".
 
-Core-related topology information in the kernel:
-
-  - smp_num_siblings:
-
-    The number of threads in a core. The number of threads in a package can be
-    calculated by::
-
-	threads_per_package = cpuinfo_x86.x86_max_cores * smp_num_siblings
-
-
 Threads
 =======
 A thread is a single scheduling unit. It's the equivalent to a logical Linux
diff --git a/Documentation/arch/x86/x86_64/fred.rst b/Documentation/arch/x86/x86_64/fred.rst
new file mode 100644
index 000000000000..9f57e7b91f7e
--- /dev/null
+++ b/Documentation/arch/x86/x86_64/fred.rst
@@ -0,0 +1,96 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================================
+Flexible Return and Event Delivery (FRED)
+=========================================
+
+Overview
+========
+
+The FRED architecture defines simple new transitions that change
+privilege level (ring transitions). The FRED architecture was
+designed with the following goals:
+
+1) Improve overall performance and response time by replacing event
+   delivery through the interrupt descriptor table (IDT event
+   delivery) and event return by the IRET instruction with lower
+   latency transitions.
+
+2) Improve software robustness by ensuring that event delivery
+   establishes the full supervisor context and that event return
+   establishes the full user context.
+
+The new transitions defined by the FRED architecture are FRED event
+delivery and, for returning from events, two FRED return instructions.
+FRED event delivery can effect a transition from ring 3 to ring 0, but
+it is used also to deliver events incident to ring 0. One FRED
+instruction (ERETU) effects a return from ring 0 to ring 3, while the
+other (ERETS) returns while remaining in ring 0. Collectively, FRED
+event delivery and the FRED return instructions are FRED transitions.
+
+In addition to these transitions, the FRED architecture defines a new
+instruction (LKGS) for managing the state of the GS segment register.
+The LKGS instruction can be used by 64-bit operating systems that do
+not use the new FRED transitions.
+
+Furthermore, the FRED architecture is easy to extend for future CPU
+architectures.
+
+Software based event dispatching
+================================
+
+FRED operates differently from IDT in terms of event handling. Instead
+of directly dispatching an event to its handler based on the event
+vector, FRED requires the software to dispatch an event to its handler
+based on both the event's type and vector. Therefore, an event dispatch
+framework must be implemented to facilitate the event-to-handler
+dispatch process. The FRED event dispatch framework takes control
+once an event is delivered, and employs a two-level dispatch.
+
+The first level dispatching is event type based, and the second level
+dispatching is event vector based.
+
+Full supervisor/user context
+============================
+
+FRED event delivery atomically save and restore full supervisor/user
+context upon event delivery and return. Thus it avoids the problem of
+transient states due to %cr2 and/or %dr6, and it is no longer needed
+to handle all the ugly corner cases caused by half baked entry states.
+
+FRED allows explicit unblock of NMI with new event return instructions
+ERETS/ERETU, avoiding the mess caused by IRET which unconditionally
+unblocks NMI, e.g., when an exception happens during NMI handling.
+
+FRED always restores the full value of %rsp, thus ESPFIX is no longer
+needed when FRED is enabled.
+
+LKGS
+====
+
+LKGS behaves like the MOV to GS instruction except that it loads the
+base address into the IA32_KERNEL_GS_BASE MSR instead of the GS
+segment’s descriptor cache. With LKGS, it ends up with avoiding
+mucking with kernel GS, i.e., an operating system can always operate
+with its own GS base address.
+
+Because FRED event delivery from ring 3 and ERETU both swap the value
+of the GS base address and that of the IA32_KERNEL_GS_BASE MSR, plus
+the introduction of LKGS instruction, the SWAPGS instruction is no
+longer needed when FRED is enabled, thus is disallowed (#UD).
+
+Stack levels
+============
+
+4 stack levels 0~3 are introduced to replace the nonreentrant IST for
+event handling, and each stack level should be configured to use a
+dedicated stack.
+
+The current stack level could be unchanged or go higher upon FRED
+event delivery. If unchanged, the CPU keeps using the current event
+stack. If higher, the CPU switches to a new event stack specified by
+the MSR of the new stack level, i.e., MSR_IA32_FRED_RSP[123].
+
+Only execution of a FRED return instruction ERET[US], could lower the
+current stack level, causing the CPU to switch back to the stack it was
+on before a previous event delivery that promoted the stack level.
diff --git a/Documentation/arch/x86/x86_64/index.rst b/Documentation/arch/x86/x86_64/index.rst
index a56070fc8e77..ad15e9bd623f 100644
--- a/Documentation/arch/x86/x86_64/index.rst
+++ b/Documentation/arch/x86/x86_64/index.rst
@@ -15,3 +15,4 @@ x86_64 Support
    cpu-hotplug-spec
    machinecheck
    fsgs
+   fred
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 5830b01c5642..da64c9fb7e07 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -388,6 +388,12 @@ latex_elements = {
         verbatimhintsturnover=false,
     ''',
 
+    #
+    # Some of our authors are fond of deep nesting; tell latex to
+    # cope.
+    #
+    'maxlistdepth': '10',
+
     # For CJK One-half spacing, need to be in front of hyperref
     'extrapackages': r'\usepackage{setspace}',
 
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index 3599cf9267b4..ed73c612174d 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -77,10 +77,12 @@ wants a function to be executed asynchronously it has to set up a work
 item pointing to that function and queue that work item on a
 workqueue.
 
-Special purpose threads, called worker threads, execute the functions
-off of the queue, one after the other.  If no work is queued, the
-worker threads become idle.  These worker threads are managed in so
-called worker-pools.
+A work item can be executed in either a thread or the BH (softirq) context.
+
+For threaded workqueues, special purpose threads, called [k]workers, execute
+the functions off of the queue, one after the other. If no work is queued,
+the worker threads become idle. These worker threads are managed in
+worker-pools.
 
 The cmwq design differentiates between the user-facing workqueues that
 subsystems and drivers queue work items on and the backend mechanism
@@ -91,6 +93,12 @@ for high priority ones, for each possible CPU and some extra
 worker-pools to serve work items queued on unbound workqueues - the
 number of these backing pools is dynamic.
 
+BH workqueues use the same framework. However, as there can only be one
+concurrent execution context, there's no need to worry about concurrency.
+Each per-CPU BH worker pool contains only one pseudo worker which represents
+the BH execution context. A BH workqueue can be considered a convenience
+interface to softirq.
+
 Subsystems and drivers can create and queue work items through special
 workqueue API functions as they see fit. They can influence some
 aspects of the way the work items are executed by setting flags on the
@@ -106,7 +114,7 @@ unless specifically overridden, a work item of a bound workqueue will
 be queued on the worklist of either normal or highpri worker-pool that
 is associated to the CPU the issuer is running on.
 
-For any worker pool implementation, managing the concurrency level
+For any thread pool implementation, managing the concurrency level
 (how many execution contexts are active) is an important issue.  cmwq
 tries to keep the concurrency at a minimal but sufficient level.
 Minimal to save resources and sufficient in that the system is used at
@@ -164,6 +172,17 @@ resources, scheduled and executed.
 ``flags``
 ---------
 
+``WQ_BH``
+  BH workqueues can be considered a convenience interface to softirq. BH
+  workqueues are always per-CPU and all BH work items are executed in the
+  queueing CPU's softirq context in the queueing order.
+
+  All BH workqueues must have 0 ``max_active`` and ``WQ_HIGHPRI`` is the
+  only allowed additional flag.
+
+  BH work items cannot sleep. All other features such as delayed queueing,
+  flushing and canceling are supported.
+
 ``WQ_UNBOUND``
   Work items queued to an unbound wq are served by the special
   worker-pools which host workers which are not bound to any
@@ -237,15 +256,11 @@ may queue at the same time.  Unless there is a specific need for
 throttling the number of active work items, specifying '0' is
 recommended.
 
-Some users depend on the strict execution ordering of ST wq.  The
-combination of ``@max_active`` of 1 and ``WQ_UNBOUND`` used to
-achieve this behavior.  Work items on such wq were always queued to the
-unbound worker-pools and only one work item could be active at any given
-time thus achieving the same ordering property as ST wq.
-
-In the current implementation the above configuration only guarantees
-ST behavior within a given NUMA node. Instead ``alloc_ordered_workqueue()`` should
-be used to achieve system-wide ST behavior.
+Some users depend on strict execution ordering where only one work item
+is in flight at any given time and the work items are processed in
+queueing order. While the combination of ``@max_active`` of 1 and
+``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
+case. Use ``alloc_ordered_queue()`` instead.
 
 
 Example Execution Scenarios
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index ab376b316c36..7f3582a67318 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -245,6 +245,10 @@ Contributing new tests (details)
    TEST_PROGS, TEST_GEN_PROGS mean it is the executable tested by
    default.
 
+   TEST_GEN_MODS_DIR should be used by tests that require modules to be built
+   before the test starts. The variable will contain the name of the directory
+   containing the modules.
+
    TEST_CUSTOM_PROGS should be used by tests that require custom build
    rules and prevent common build rule use.
 
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index a9efab50eed8..22955d56b379 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -671,8 +671,23 @@ Testing Static Functions
 ------------------------
 
 If we do not want to expose functions or variables for testing, one option is to
-conditionally ``#include`` the test file at the end of your .c file. For
-example:
+conditionally export the used symbol. For example:
+
+.. code-block:: c
+
+	/* In my_file.c */
+
+	VISIBLE_IF_KUNIT int do_interesting_thing();
+	EXPORT_SYMBOL_IF_KUNIT(do_interesting_thing);
+
+	/* In my_file.h */
+
+	#if IS_ENABLED(CONFIG_KUNIT)
+		int do_interesting_thing(void);
+	#endif
+
+Alternatively, you could conditionally ``#include`` the test file at the end of
+your .c file. For example:
 
 .. code-block:: c
 
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index 2323fd5b7cda..129cf698fa8a 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -28,7 +28,10 @@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE
 find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \
 		-name 'processed-schema*' \)
 
-find_cmd = $(find_all_cmd) | sed 's|^$(srctree)/$(src)/||' | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | sed 's|^|$(srctree)/$(src)/|'
+find_cmd = $(find_all_cmd) | \
+		sed 's|^$(srctree)/||' | \
+		grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | \
+		sed 's|^|$(srctree)/|'
 CHK_DT_DOCS := $(shell $(find_cmd))
 
 quiet_cmd_yamllint = LINT    $(src)
diff --git a/Documentation/devicetree/bindings/arm/amlogic.yaml b/Documentation/devicetree/bindings/arm/amlogic.yaml
index caab7ceeda45..949537cea6be 100644
--- a/Documentation/devicetree/bindings/arm/amlogic.yaml
+++ b/Documentation/devicetree/bindings/arm/amlogic.yaml
@@ -7,19 +7,11 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Amlogic SoC based Platforms
 
 maintainers:
+  - Neil Armstrong <neil.armstrong@linaro.org>
+  - Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+  - Jerome Brunet <jbrunet@baylibre.com>
   - Kevin Hilman <khilman@baylibre.com>
 
-description: |+
-  Work in progress statement:
-
-  Device tree files and bindings applying to Amlogic SoCs and boards are
-  considered "unstable". Any Amlogic device tree binding may change at
-  any time. Be sure to use a device tree binary and a kernel image
-  generated from the same source tree.
-
-  Please refer to Documentation/devicetree/bindings/ABI.rst for a definition of a
-  stable binding/ABI.
-
 properties:
   $nodename:
     const: '/'
@@ -146,6 +138,7 @@ properties:
           - enum:
               - amediatech,x96-max
               - amlogic,u200
+              - freebox,fbx8am
               - radxa,zero
               - seirobotics,sei510
           - const: amlogic,g12a
diff --git a/Documentation/devicetree/bindings/arm/arm,realview.yaml b/Documentation/devicetree/bindings/arm/arm,realview.yaml
index d1bdee98f9af..3c5f1688dbd7 100644
--- a/Documentation/devicetree/bindings/arm/arm,realview.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,realview.yaml
@@ -10,9 +10,9 @@ maintainers:
   - Linus Walleij <linus.walleij@linaro.org>
 
 description: |+
-  The ARM RealView series of reference designs were built to explore the ARM
-  11, Cortex A-8 and Cortex A-9 CPUs. This included new features compared to
-  the earlier CPUs such as TrustZone and multicore (MPCore).
+  The ARM RealView series of reference designs were built to explore the Arm11,
+  Cortex-A8, and Cortex-A9 CPUs. This included new features compared to the
+  earlier CPUs such as TrustZone and multicore (MPCore).
 
 properties:
   $nodename:
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.yaml b/Documentation/devicetree/bindings/arm/atmel-at91.yaml
index 89d75fbb1de4..82f37328cc69 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.yaml
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.yaml
@@ -179,6 +179,12 @@ properties:
           - const: microchip,sama7g5
           - const: microchip,sama7
 
+      - description: Microchip SAMA7G54 Curiosity Board
+        items:
+          - const: microchip,sama7g54-curiosity
+          - const: microchip,sama7g5
+          - const: microchip,sama7
+
       - description: Microchip LAN9662 Evaluation Boards.
         items:
           - enum:
diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml
index 228dcc5c7d6f..0027201e19f8 100644
--- a/Documentation/devicetree/bindings/arm/fsl.yaml
+++ b/Documentation/devicetree/bindings/arm/fsl.yaml
@@ -384,7 +384,8 @@ properties:
               - toradex,apalis_imx6q-ixora      # Apalis iMX6Q/D Module on Ixora Carrier Board
               - toradex,apalis_imx6q-ixora-v1.1 # Apalis iMX6Q/D Module on Ixora V1.1 Carrier Board
               - toradex,apalis_imx6q-ixora-v1.2 # Apalis iMX6Q/D Module on Ixora V1.2 Carrier Board
-              - toradex,apalis_imx6q-eval       # Apalis iMX6Q/D Module on Apalis Evaluation Board
+              - toradex,apalis_imx6q-eval       # Apalis iMX6Q/D Module on Apalis Evaluation Board v1.0/v1.1
+              - toradex,apalis_imx6q-eval-v1.2  # Apalis iMX6Q/D Module on Apalis Evaluation Board v1.2
           - const: toradex,apalis_imx6q
           - const: fsl,imx6q
 
@@ -469,6 +470,7 @@ properties:
               - prt,prtvt7                # Protonic VT7 board
               - rex,imx6dl-rex-basic      # Rex Basic i.MX6 Dual Lite Board
               - riot,imx6s-riotboard      # RIoTboard i.MX6S
+              - sielaff,imx6dl-board      # Sielaff i.MX6 Solo Board
               - skov,imx6dl-skov-revc-lt2 # SKOV IMX6 CPU SoloCore lt2
               - skov,imx6dl-skov-revc-lt6 # SKOV IMX6 CPU SoloCore lt6
               - solidrun,cubox-i/dl            # SolidRun Cubox-i Solo/DualLite
@@ -708,6 +710,7 @@ properties:
               - toradex,colibri-imx6ull      # Colibri iMX6ULL Modules
               - toradex,colibri-imx6ull-emmc # Colibri iMX6ULL 1GB (eMMC) Module
               - toradex,colibri-imx6ull-wifi # Colibri iMX6ULL Wi-Fi / BT Modules
+              - uni-t,uti260b             # UNI-T UTi260B Thermal Camera
           - const: fsl,imx6ull
 
       - description: i.MX6ULL Armadeus Systems OPOS6ULDev Board
@@ -1026,7 +1029,7 @@ properties:
         items:
           - enum:
               - dimonoff,gateway-evk # i.MX8MN Dimonoff Gateway EVK Board
-              - rve,rve-gateway # i.MX8MN RVE Gateway Board
+              - rve,gateway # i.MX8MN RVE Gateway Board
               - variscite,var-som-mx8mn-symphony
           - const: variscite,var-som-mx8mn
           - const: fsl,imx8mn
@@ -1194,7 +1197,8 @@ properties:
       - description: i.MX8QM Boards with Toradex Apalis iMX8 Modules
         items:
           - enum:
-              - toradex,apalis-imx8-eval            # Apalis iMX8 Module on Apalis Evaluation Board
+              - toradex,apalis-imx8-eval            # Apalis iMX8 Module on Apalis Evaluation V1.0/V1.1 Board
+              - toradex,apalis-imx8-eval-v1.2       # Apalis iMX8 Module on Apalis Evaluation V1.2 Board
               - toradex,apalis-imx8-ixora-v1.1      # Apalis iMX8 Module on Ixora V1.1 Carrier Board
           - const: toradex,apalis-imx8
           - const: fsl,imx8qm
@@ -1202,7 +1206,8 @@ properties:
       - description: i.MX8QM Boards with Toradex Apalis iMX8 V1.1 Modules
         items:
           - enum:
-              - toradex,apalis-imx8-v1.1-eval       # Apalis iMX8 V1.1 Module on Apalis Eval. Board
+              - toradex,apalis-imx8-v1.1-eval       # Apalis iMX8 V1.1 Module on Apalis Eval. V1.0/V1.1 Board
+              - toradex,apalis-imx8-v1.1-eval-v1.2  # Apalis iMX8 V1.1 Module on Apalis Eval. V1.2 Board
               - toradex,apalis-imx8-v1.1-ixora-v1.1 # Apalis iMX8 V1.1 Module on Ixora V1.1 C. Board
               - toradex,apalis-imx8-v1.1-ixora-v1.2 # Apalis iMX8 V1.1 Module on Ixora V1.2 C. Board
           - const: toradex,apalis-imx8-v1.1
@@ -1232,6 +1237,22 @@ properties:
           - const: toradex,colibri-imx8x
           - const: fsl,imx8qxp
 
+      - description:
+          TQMa8Xx is a series of SOM featuring NXP i.MX8X system-on-chip
+          variants. It is designed to be clicked on different carrier boards
+          MBa8Xx is the starterkit
+        oneOf:
+          - items:
+              - enum:
+                  - tq,imx8dxp-tqma8xdp-mba8xx # TQ-Systems GmbH TQMa8XDP SOM on MBa8Xx
+              - const: tq,imx8dxp-tqma8xdp     # TQ-Systems GmbH TQMa8XDP SOM (with i.MX8DXP)
+              - const: fsl,imx8dxp
+          - items:
+              - enum:
+                  - tq,imx8qxp-tqma8xqp-mba8xx # TQ-Systems GmbH TQMa8XQP SOM on MBa8Xx
+              - const: tq,imx8qxp-tqma8xqp     # TQ-Systems GmbH TQMa8XQP SOM (with i.MX8QXP)
+              - const: fsl,imx8qxp
+
       - description: i.MX8ULP based Boards
         items:
           - enum:
@@ -1275,6 +1296,18 @@ properties:
           - const: tq,imx93-tqma9352        # TQ-Systems GmbH i.MX93 TQMa93xxCA/LA SOM
           - const: fsl,imx93
 
+      - description: PHYTEC phyCORE-i.MX93 SoM based boards
+        items:
+          - const: phytec,imx93-phyboard-segin # phyBOARD-Segin with i.MX93
+          - const: phytec,imx93-phycore-som    # phyCORE-i.MX93 SoM
+          - const: fsl,imx93
+
+      - description: Variscite VAR-SOM-MX93 based boards
+        items:
+          - const: variscite,var-som-mx93-symphony
+          - const: variscite,var-som-mx93
+          - const: fsl,imx93
+
       - description:
           Freescale Vybrid Platform Device Tree Bindings
 
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-38x.txt b/Documentation/devicetree/bindings/arm/marvell/armada-38x.txt
deleted file mode 100644
index 202953f1887e..000000000000
--- a/Documentation/devicetree/bindings/arm/marvell/armada-38x.txt
+++ /dev/null
@@ -1,27 +0,0 @@
-Marvell Armada 38x Platforms Device Tree Bindings
--------------------------------------------------
-
-Boards with a SoC of the Marvell Armada 38x family shall have the
-following property:
-
-Required root node property:
-
- - compatible: must contain "marvell,armada380"
-
-In addition, boards using the Marvell Armada 385 SoC shall have the
-following property before the previous one:
-
-Required root node property:
-
-compatible: must contain "marvell,armada385"
-
-In addition, boards using the Marvell Armada 388 SoC shall have the
-following property before the previous one:
-
-Required root node property:
-
-compatible: must contain "marvell,armada388"
-
-Example:
-
-compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada380";
diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-38x.yaml b/Documentation/devicetree/bindings/arm/marvell/armada-38x.yaml
new file mode 100644
index 000000000000..cdf805b5db95
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-38x.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/marvell/armada-38x.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Armada 38x Platforms
+
+maintainers:
+  - Gregory CLEMENT <gregory.clement@bootlin.com>
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+
+      - description:
+          Netgear Armada 380 GS110EM Managed Switch.
+        items:
+          - const: netgear,gs110emx
+          - const: marvell,armada380
+
+      - description:
+          Marvell Armada 385 Development Boards.
+        items:
+          - enum:
+              - marvell,a385-db-amc
+              - marvell,a385-db-ap
+          - const: marvell,armada385
+          - const: marvell,armada380
+
+      - description:
+          SolidRun Armada 385 based single-board computers.
+        items:
+          - enum:
+              - solidrun,clearfog-gtr-l8
+              - solidrun,clearfog-gtr-s4
+          - const: marvell,armada385
+          - const: marvell,armada380
+
+      - description:
+          Kobol Armada 388 based Helios-4 NAS.
+        items:
+          - const: kobol,helios4
+          - const: marvell,armada388
+          - const: marvell,armada385
+          - const: marvell,armada380
+
+      - description:
+          Marvell Armada 388 Development Boards.
+        items:
+          - enum:
+              - marvell,a388-gp
+          - const: marvell,armada388
+          - const: marvell,armada385
+          - const: marvell,armada380
+
+      - description:
+          SolidRun Armada 388 clearfog family single-board computers.
+        items:
+          - enum:
+              - solidrun,clearfog-base-a1
+              - solidrun,clearfog-pro-a1
+          - const: solidrun,clearfog-a1
+          - const: marvell,armada388
+          - const: marvell,armada385
+          - const: marvell,armada380
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/arm/mediatek.yaml b/Documentation/devicetree/bindings/arm/mediatek.yaml
index 6f2f64ae76fc..09f9ffd3ff7b 100644
--- a/Documentation/devicetree/bindings/arm/mediatek.yaml
+++ b/Documentation/devicetree/bindings/arm/mediatek.yaml
@@ -17,6 +17,7 @@ properties:
     const: '/'
   compatible:
     oneOf:
+      # Sort by SoC (last) compatible, then board compatible
       - items:
           - enum:
               - mediatek,mt2701-evb
@@ -84,6 +85,11 @@ properties:
           - const: mediatek,mt7629
       - items:
           - enum:
+              - xiaomi,ax3000t
+          - const: mediatek,mt7981b
+      - items:
+          - enum:
+              - acelink,ew-7886cax
               - bananapi,bpi-r3
               - mediatek,mt7986a-rfb
           - const: mediatek,mt7986a
@@ -93,6 +99,10 @@ properties:
           - const: mediatek,mt7986b
       - items:
           - enum:
+              - bananapi,bpi-r4
+          - const: mediatek,mt7988a
+      - items:
+          - enum:
               - mediatek,mt8127-moose
           - const: mediatek,mt8127
       - items:
@@ -129,75 +139,10 @@ properties:
           - enum:
               - mediatek,mt8173-evb
           - const: mediatek,mt8173
-      - items:
-          - enum:
-              - mediatek,mt8183-evb
-          - const: mediatek,mt8183
-      - description: Google Hayato rev5
-        items:
-          - const: google,hayato-rev5-sku2
-          - const: google,hayato-sku2
-          - const: google,hayato
-          - const: mediatek,mt8192
-      - description: Google Hayato
-        items:
-          - const: google,hayato-rev1
-          - const: google,hayato
-          - const: mediatek,mt8192
-      - description: Google Spherion rev4 (Acer Chromebook 514)
-        items:
-          - const: google,spherion-rev4
-          - const: google,spherion
-          - const: mediatek,mt8192
-      - description: Google Spherion (Acer Chromebook 514)
-        items:
-          - const: google,spherion-rev3
-          - const: google,spherion-rev2
-          - const: google,spherion-rev1
-          - const: google,spherion-rev0
-          - const: google,spherion
-          - const: mediatek,mt8192
-      - description: Acer Tomato (Acer Chromebook Spin 513 CP513-2H)
-        items:
-          - enum:
-              - google,tomato-rev2
-              - google,tomato-rev1
-          - const: google,tomato
-          - const: mediatek,mt8195
-      - description: Acer Tomato rev3 - 4 (Acer Chromebook Spin 513 CP513-2H)
-        items:
-          - const: google,tomato-rev4
-          - const: google,tomato-rev3
-          - const: google,tomato
-          - const: mediatek,mt8195
-      - items:
-          - enum:
-              - mediatek,mt8186-evb
-          - const: mediatek,mt8186
-      - items:
-          - enum:
-              - mediatek,mt8188-evb
-          - const: mediatek,mt8188
-      - items:
-          - enum:
-              - mediatek,mt8192-evb
-          - const: mediatek,mt8192
-      - items:
-          - enum:
-              - mediatek,mt8195-demo
-              - mediatek,mt8195-evb
-          - const: mediatek,mt8195
       - description: Google Burnet (HP Chromebook x360 11MK G3 EE)
         items:
           - const: google,burnet
           - const: mediatek,mt8183
-      - description: Google Krane (Lenovo IdeaPad Duet, 10e,...)
-        items:
-          - enum:
-              - google,krane-sku0
-              - google,krane-sku176
-          - const: google,krane
-          - const: mediatek,mt8183
       - description: Google Cozmo (Acer Chromebook 314)
         items:
           - const: google,cozmo
@@ -255,6 +200,13 @@ properties:
               - google,kodama-sku32
           - const: google,kodama
           - const: mediatek,mt8183
+      - description: Google Krane (Lenovo IdeaPad Duet, 10e,...)
+        items:
+          - enum:
+              - google,krane-sku0
+              - google,krane-sku176
+          - const: google,krane
+          - const: mediatek,mt8183
       - description: Google Makomo (Lenovo 100e Chromebook 2nd Gen MTK 2)
         items:
           - enum:
@@ -278,8 +230,123 @@ properties:
           - const: mediatek,mt8183
       - items:
           - enum:
+              - mediatek,mt8183-evb
+          - const: mediatek,mt8183
+      - items:
+          - enum:
               - mediatek,mt8183-pumpkin
           - const: mediatek,mt8183
+      - description: Google Magneton (Lenovo IdeaPad Slim 3 Chromebook (14M868))
+        items:
+          - const: google,steelix-sku393219
+          - const: google,steelix-sku393216
+          - const: google,steelix
+          - const: mediatek,mt8186
+      - description: Google Magneton (Lenovo IdeaPad Slim 3 Chromebook (14M868))
+        items:
+          - const: google,steelix-sku393220
+          - const: google,steelix-sku393217
+          - const: google,steelix
+          - const: mediatek,mt8186
+      - description: Google Magneton (Lenovo IdeaPad Slim 3 Chromebook (14M868))
+        items:
+          - const: google,steelix-sku393221
+          - const: google,steelix-sku393218
+          - const: google,steelix
+          - const: mediatek,mt8186
+      - description: Google Rusty (Lenovo 100e Chromebook Gen 4)
+        items:
+          - const: google,steelix-sku196609
+          - const: google,steelix-sku196608
+          - const: google,steelix
+          - const: mediatek,mt8186
+      - description: Google Steelix (Lenovo 300e Yoga Chromebook Gen 4)
+        items:
+          - enum:
+              - google,steelix-sku131072
+              - google,steelix-sku131073
+          - const: google,steelix
+          - const: mediatek,mt8186
+      - description: Google Tentacruel (ASUS Chromebook CM14 Flip CM1402F)
+        items:
+          - const: google,tentacruel-sku262147
+          - const: google,tentacruel-sku262146
+          - const: google,tentacruel-sku262145
+          - const: google,tentacruel-sku262144
+          - const: google,tentacruel
+          - const: mediatek,mt8186
+      - description: Google Tentacruel (ASUS Chromebook CM14 Flip CM1402F)
+        items:
+          - const: google,tentacruel-sku262151
+          - const: google,tentacruel-sku262150
+          - const: google,tentacruel-sku262149
+          - const: google,tentacruel-sku262148
+          - const: google,tentacruel
+          - const: mediatek,mt8186
+      - description: Google Tentacool (ASUS Chromebook CM14 CM1402C)
+        items:
+          - const: google,tentacruel-sku327681
+          - const: google,tentacruel
+          - const: mediatek,mt8186
+      - description: Google Tentacool (ASUS Chromebook CM14 CM1402C)
+        items:
+          - const: google,tentacruel-sku327683
+          - const: google,tentacruel
+          - const: mediatek,mt8186
+      - items:
+          - enum:
+              - mediatek,mt8186-evb
+          - const: mediatek,mt8186
+      - items:
+          - enum:
+              - mediatek,mt8188-evb
+          - const: mediatek,mt8188
+      - description: Google Hayato
+        items:
+          - const: google,hayato-rev1
+          - const: google,hayato
+          - const: mediatek,mt8192
+      - description: Google Hayato rev5
+        items:
+          - const: google,hayato-rev5-sku2
+          - const: google,hayato-sku2
+          - const: google,hayato
+          - const: mediatek,mt8192
+      - description: Google Spherion (Acer Chromebook 514)
+        items:
+          - const: google,spherion-rev3
+          - const: google,spherion-rev2
+          - const: google,spherion-rev1
+          - const: google,spherion-rev0
+          - const: google,spherion
+          - const: mediatek,mt8192
+      - description: Google Spherion rev4 (Acer Chromebook 514)
+        items:
+          - const: google,spherion-rev4
+          - const: google,spherion
+          - const: mediatek,mt8192
+      - items:
+          - enum:
+              - mediatek,mt8192-evb
+          - const: mediatek,mt8192
+      - description: Acer Tomato (Acer Chromebook Spin 513 CP513-2H)
+        items:
+          - enum:
+              - google,tomato-rev2
+              - google,tomato-rev1
+          - const: google,tomato
+          - const: mediatek,mt8195
+      - description: Acer Tomato rev3 - 4 (Acer Chromebook Spin 513 CP513-2H)
+        items:
+          - const: google,tomato-rev4
+          - const: google,tomato-rev3
+          - const: google,tomato
+          - const: mediatek,mt8195
+      - items:
+          - enum:
+              - mediatek,mt8195-demo
+              - mediatek,mt8195-evb
+          - const: mediatek,mt8195
       - items:
           - enum:
               - mediatek,mt8365-evk
@@ -287,6 +354,7 @@ properties:
       - items:
           - enum:
               - mediatek,mt8395-evk
+              - radxa,nio-12l
           - const: mediatek,mt8395
           - const: mediatek,mt8195
       - items:
diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,saw2.txt b/Documentation/devicetree/bindings/arm/msm/qcom,saw2.txt
deleted file mode 100644
index c0e3c3a42bea..000000000000
--- a/Documentation/devicetree/bindings/arm/msm/qcom,saw2.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-SPM AVS Wrapper 2 (SAW2)
-
-The SAW2 is a wrapper around the Subsystem Power Manager (SPM) and the
-Adaptive Voltage Scaling (AVS) hardware. The SPM is a programmable
-power-controller that transitions a piece of hardware (like a processor or
-subsystem) into and out of low power modes via a direct connection to
-the PMIC. It can also be wired up to interact with other processors in the
-system, notifying them when a low power state is entered or exited.
-
-Multiple revisions of the SAW hardware are supported using these Device Nodes.
-SAW2 revisions differ in the register offset and configuration data. Also, the
-same revision of the SAW in different SoCs may have different configuration
-data due the differences in hardware capabilities. Hence the SoC name, the
-version of the SAW hardware in that SoC and the distinction between cpu (big
-or Little) or cache, may be needed to uniquely identify the SAW register
-configuration and initialization data. The compatible string is used to
-indicate this parameter.
-
-PROPERTIES
-
-- compatible:
-	Usage: required
-	Value type: <string>
-	Definition: Must have
-			"qcom,saw2"
-		    A more specific value could be one of:
-			"qcom,apq8064-saw2-v1.1-cpu"
-			"qcom,msm8226-saw2-v2.1-cpu"
-			"qcom,msm8974-saw2-v2.1-cpu"
-			"qcom,apq8084-saw2-v2.1-cpu"
-
-- reg:
-	Usage: required
-	Value type: <prop-encoded-array>
-	Definition: the first element specifies the base address and size of
-		    the register region. An optional second element specifies
-		    the base address and size of the alias register region.
-
-- regulator:
-	Usage: optional
-	Value type: boolean
-	Definition: Indicates that this SPM device acts as a regulator device
-			device for the core (CPU or Cache) the SPM is attached
-			to.
-
-Example 1:
-
-	power-controller@2099000 {
-		compatible = "qcom,saw2";
-		reg = <0x02099000 0x1000>, <0x02009000 0x1000>;
-		regulator;
-	};
-
-Example 2:
-	saw0: power-controller@f9089000 {
-		compatible = "qcom,apq8084-saw2-v2.1-cpu", "qcom,saw2";
-		reg = <0xf9089000 0x1000>, <0xf9009000 0x1000>;
-	};
diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml
index 1a5fb889a444..66beaac60e1d 100644
--- a/Documentation/devicetree/bindings/arm/qcom.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom.yaml
@@ -10,17 +10,10 @@ maintainers:
   - Bjorn Andersson <bjorn.andersson@linaro.org>
 
 description: |
-  Some qcom based bootloaders identify the dtb blob based on a set of
-  device properties like SoC and platform and revisions of those components.
-  To support this scheme, we encode this information into the board compatible
-  string.
-
-  Each board must specify a top-level board compatible string with the following
-  format:
-
-  	compatible = "qcom,<SoC>[-<soc_version>][-<foundry_id>]-<board>[/<subtype>][-<board_version>]"
-
-  The 'SoC' and 'board' elements are required. All other elements are optional.
+  For devices using the Qualcomm SoC the "compatible" properties consists of
+  one or several "manufacturer,model" strings, describing the device itself,
+  followed by one or several "qcom,<SoC>" strings, describing the SoC used in
+  the device.
 
   The 'SoC' element must be one of the following strings:
 
@@ -90,43 +83,9 @@ description: |
         sm8650
         x1e80100
 
-  The 'board' element must be one of the following strings:
-
-        adp
-        cdp
-        dragonboard
-        idp
-        liquid
-        mtp
-        qcp
-        qrd
-        rb2
-        ride
-        sbc
-        x100
-
-  The 'soc_version' and 'board_version' elements take the form of v<Major>.<Minor>
-  where the minor number may be omitted when it's zero, i.e.  v1.0 is the same
-  as v1. If all versions of the 'board_version' elements match, then a
-  wildcard '*' should be used, e.g. 'v*'.
-
-  The 'foundry_id' and 'subtype' elements are one or more digits from 0 to 9.
-
-  Examples:
-
-  	"qcom,msm8916-v1-cdp-pm8916-v2.1"
-
-  A CDP board with an msm8916 SoC, version 1 paired with a pm8916 PMIC of version
-  2.1.
-
-  	"qcom,apq8074-v2.0-2-dragonboard/1-v0.1"
-
-  A dragonboard board v0.1 of subtype 1 with an apq8074 SoC version 2, made in
-  foundry 2.
-
   There are many devices in the list below that run the standard ChromeOS
   bootloader setup and use the open source depthcharge bootloader to boot the
-  OS. These devices do not use the scheme described above. For details, see:
+  OS. These devices use the bootflow explained at
   https://docs.kernel.org/arch/arm/google/chromebook-boot-flow.html
 
 properties:
@@ -187,6 +146,7 @@ properties:
               - microsoft,superman-lte
               - microsoft,tesla
               - motorola,peregrine
+              - samsung,matisselte
           - const: qcom,msm8926
           - const: qcom,msm8226
 
@@ -244,11 +204,15 @@ properties:
               - samsung,a5u-eur
               - samsung,e5
               - samsung,e7
+              - samsung,fortuna3g
+              - samsung,gprimeltecan
               - samsung,grandmax
+              - samsung,grandprimelte
               - samsung,gt510
               - samsung,gt58
               - samsung,j5
               - samsung,j5x
+              - samsung,rossa
               - samsung,serranove
               - thwc,uf896
               - thwc,ufi001c
@@ -988,6 +952,7 @@ properties:
 
       - items:
           - enum:
+              - xiaomi,curtana
               - xiaomi,joyeuse
           - const: qcom,sm7125
 
@@ -1035,6 +1000,7 @@ properties:
 
       - items:
           - enum:
+              - qcom,sm8550-hdk
               - qcom,sm8550-mtp
               - qcom,sm8550-qrd
           - const: qcom,sm8550
diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml
index 5cf5cbef2cf5..fcf7316ecd74 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip.yaml
@@ -37,29 +37,16 @@ properties:
               - anbernic,rg351v
           - const: rockchip,rk3326
 
-      - description: Anbernic RG353P
+      - description: Anbernic RK3566 Handheld Gaming Console
         items:
-          - const: anbernic,rg353p
-          - const: rockchip,rk3566
-
-      - description: Anbernic RG353PS
-        items:
-          - const: anbernic,rg353ps
-          - const: rockchip,rk3566
-
-      - description: Anbernic RG353V
-        items:
-          - const: anbernic,rg353v
-          - const: rockchip,rk3566
-
-      - description: Anbernic RG353VS
-        items:
-          - const: anbernic,rg353vs
-          - const: rockchip,rk3566
-
-      - description: Anbernic RG503
-        items:
-          - const: anbernic,rg503
+          - enum:
+              - anbernic,rg353p
+              - anbernic,rg353ps
+              - anbernic,rg353v
+              - anbernic,rg353vs
+              - anbernic,rg503
+              - anbernic,rg-arc-d
+              - anbernic,rg-arc-s
           - const: rockchip,rk3566
 
       - description: Asus Tinker board
@@ -237,6 +224,13 @@ properties:
               - friendlyarm,nanopi-r5s
           - const: rockchip,rk3568
 
+      - description: FriendlyElec NanoPi R6 series boards
+        items:
+          - enum:
+              - friendlyarm,nanopi-r6c
+              - friendlyarm,nanopi-r6s
+          - const: rockchip,rk3588s
+
       - description: FriendlyElec NanoPC T6
         items:
           - const: friendlyarm,nanopc-t6
@@ -626,9 +620,9 @@ properties:
           - const: openailab,eaidk-610
           - const: rockchip,rk3399
 
-      - description: Orange Pi RK3399 board
+      - description: Xunlong Orange Pi RK3399 board
         items:
-          - const: rockchip,rk3399-orangepi
+          - const: xunlong,rk3399-orangepi
           - const: rockchip,rk3399
 
       - description: Phytec phyCORE-RK3288 Rapid Development Kit
@@ -655,6 +649,14 @@ properties:
           - const: pine64,pinephone-pro
           - const: rockchip,rk3399
 
+      - description: Pine64 PineTab2
+        items:
+          - enum:
+              - pine64,pinetab2-v0.1
+              - pine64,pinetab2-v2.0
+          - const: pine64,pinetab2
+          - const: rockchip,rk3566
+
       - description: Pine64 Rock64
         items:
           - const: pine64,rock64
@@ -692,11 +694,17 @@ properties:
       - description: Powkiddy RK3566 Handheld Gaming Console
         items:
           - enum:
+              - powkiddy,rgb10max3
               - powkiddy,rgb30
               - powkiddy,rk2023
               - powkiddy,x55
           - const: rockchip,rk3566
 
+      - description: QNAP TS-433-4G 4-Bay NAS
+        items:
+          - const: qnap,ts433
+          - const: rockchip,rk3568
+
       - description: Radxa Compute Module 3(CM3)
         items:
           - enum:
@@ -878,6 +886,11 @@ properties:
           - const: rockchip,rv1108-evb
           - const: rockchip,rv1108
 
+      - description: Rockchip Toybrick TB-RK3588X board
+        items:
+          - const: rockchip,rk3588-toybrick-x0
+          - const: rockchip,rk3588
+
       - description: Theobroma Systems PX30-uQ7 with Haikou baseboard
         items:
           - const: tsd,px30-ringneck-haikou
@@ -898,6 +911,12 @@ properties:
           - const: tsd,rk3588-jaguar
           - const: rockchip,rk3588
 
+      - description: Theobroma Systems RK3588-Q7 with Haikou baseboard
+        items:
+          - const: tsd,rk3588-tiger-haikou
+          - const: tsd,rk3588-tiger
+          - const: rockchip,rk3588
+
       - description: Tronsmart Orion R68 Meta
         items:
           - const: tronsmart,orion-r68-meta
@@ -940,9 +959,9 @@ properties:
           - const: rockchip,rk3568-evb1-v10
           - const: rockchip,rk3568
 
-      - description: Rockchip RK3568 Banana Pi R2 Pro
+      - description: Sinovoip RK3568 Banana Pi R2 Pro
         items:
-          - const: rockchip,rk3568-bpi-r2pro
+          - const: sinovoip,rk3568-bpi-r2pro
           - const: rockchip,rk3568
 
       - description: Sonoff iHost Smart Home Hub
diff --git a/Documentation/devicetree/bindings/arm/sunxi.yaml b/Documentation/devicetree/bindings/arm/sunxi.yaml
index a9d8e85565b8..09d835db6db5 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi.yaml
@@ -815,6 +815,12 @@ properties:
           - const: allwinner,r7-tv-dongle
           - const: allwinner,sun5i-a10s
 
+      - description: Remix Mini PC
+        items:
+          - const: jide,remix-mini-pc
+          - const: allwinner,sun50i-h64
+          - const: allwinner,sun50i-a64
+
       - description: RerVision H3-DVK
         items:
           - const: rervision,h3-dvk
@@ -835,6 +841,12 @@ properties:
           - const: sinlinx,sina33
           - const: allwinner,sun8i-a33
 
+      - description: Sipeed Longan Pi 3H board for the Sipeed Longan Module 3H
+        items:
+          - const: sipeed,longan-pi-3h
+          - const: sipeed,longan-module-3h
+          - const: allwinner,sun50i-h618
+
       - description: SourceParts PopStick v1.1
         items:
           - const: sourceparts,popstick-v1.1
diff --git a/Documentation/devicetree/bindings/arm/tegra.yaml b/Documentation/devicetree/bindings/arm/tegra.yaml
index fcf956406168..8fb4923517d0 100644
--- a/Documentation/devicetree/bindings/arm/tegra.yaml
+++ b/Documentation/devicetree/bindings/arm/tegra.yaml
@@ -64,6 +64,14 @@ properties:
       - items:
           - const: asus,tf700t
           - const: nvidia,tegra30
+      - description: LG Optimus 4X P880
+        items:
+          - const: lg,p880
+          - const: nvidia,tegra30
+      - description: LG Optimus Vu P895
+        items:
+          - const: lg,p895
+          - const: nvidia,tegra30
       - items:
           - const: toradex,apalis_t30-eval
           - const: toradex,apalis_t30
diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra186-pmc.yaml b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra186-pmc.yaml
index 0faa403f68c8..ea4fbf655220 100644
--- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra186-pmc.yaml
+++ b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra186-pmc.yaml
@@ -27,7 +27,7 @@ properties:
       - const: pmc
       - const: wake
       - const: aotag
-      - const: scratch
+      - enum: [ scratch, misc ]
       - const: misc
 
   interrupt-controller: true
@@ -41,25 +41,43 @@ properties:
     description: If present, inverts the PMU interrupt signal.
     $ref: /schemas/types.yaml#/definitions/flag
 
-if:
-  properties:
-    compatible:
-      contains:
-        const: nvidia,tegra186-pmc
-then:
-  properties:
-    reg:
-      maxItems: 4
-
-    reg-names:
-      maxItems: 4
-else:
-  properties:
-    reg:
-      minItems: 5
-
-    reg-names:
-      minItems: 5
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: nvidia,tegra186-pmc
+    then:
+      properties:
+        reg:
+          maxItems: 4
+        reg-names:
+          maxItems: 4
+          contains:
+            const: scratch
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: nvidia,tegra194-pmc
+    then:
+      properties:
+        reg:
+          minItems: 5
+        reg-names:
+          minItems: 5
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: nvidia,tegra234-pmc
+    then:
+      properties:
+        reg-names:
+          contains:
+            const: misc
 
 patternProperties:
   "^[a-z0-9]+-[a-z0-9]+$":
diff --git a/Documentation/devicetree/bindings/arm/ti/k3.yaml b/Documentation/devicetree/bindings/arm/ti/k3.yaml
index c6506bccfe88..52b51fd7044e 100644
--- a/Documentation/devicetree/bindings/arm/ti/k3.yaml
+++ b/Documentation/devicetree/bindings/arm/ti/k3.yaml
@@ -87,12 +87,20 @@ properties:
           - const: tq,am642-tqma6442l
           - const: ti,am642
 
+      - description: K3 AM642 SoC SolidRun SoM based boards
+        items:
+          - enum:
+              - solidrun,am642-hummingboard-t
+          - const: solidrun,am642-sr-som
+          - const: ti,am642
+
       - description: K3 AM654 SoC
         items:
           - enum:
               - siemens,iot2050-advanced
               - siemens,iot2050-advanced-m2
               - siemens,iot2050-advanced-pg2
+              - siemens,iot2050-advanced-sm
               - siemens,iot2050-basic
               - siemens,iot2050-basic-pg2
               - ti,am654-evm
@@ -123,6 +131,12 @@ properties:
               - ti,j721s2-evm
           - const: ti,j721s2
 
+      - description: K3 J722S SoC and Boards
+        items:
+          - enum:
+              - ti,j722s-evm
+          - const: ti,j722s
+
       - description: K3 J784s4 SoC
         items:
           - enum:
diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
index b29ce598f9aa..9952e0ef7767 100644
--- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
+++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Ceva AHCI SATA Controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
   The Ceva SATA controller mostly conforms to the AHCI interface with some
diff --git a/Documentation/devicetree/bindings/bus/imx-weim.txt b/Documentation/devicetree/bindings/bus/imx-weim.txt
deleted file mode 100644
index e7f502070d77..000000000000
--- a/Documentation/devicetree/bindings/bus/imx-weim.txt
+++ /dev/null
@@ -1,117 +0,0 @@
-Device tree bindings for i.MX Wireless External Interface Module (WEIM)
-
-The term "wireless" does not imply that the WEIM is literally an interface
-without wires. It simply means that this module was originally designed for
-wireless and mobile applications that use low-power technology.
-
-The actual devices are instantiated from the child nodes of a WEIM node.
-
-Required properties:
-
- - compatible:		Should contain one of the following:
-			  "fsl,imx1-weim"
-			  "fsl,imx27-weim"
-			  "fsl,imx51-weim"
-			  "fsl,imx50-weim"
-			  "fsl,imx6q-weim"
- - reg:			A resource specifier for the register space
-			(see the example below)
- - clocks:		the clock, see the example below.
- - #address-cells:	Must be set to 2 to allow memory address translation
- - #size-cells:		Must be set to 1 to allow CS address passing
- - ranges:		Must be set up to reflect the memory layout with four
-			integer values for each chip-select line in use:
-
-			   <cs-number> 0 <physical address of mapping> <size>
-
-Optional properties:
-
- - fsl,weim-cs-gpr:	For "fsl,imx50-weim" and "fsl,imx6q-weim" type of
-			devices, it should be the phandle to the system General
-			Purpose Register controller that contains WEIM CS GPR
-			register, e.g. IOMUXC_GPR1 on i.MX6Q.  IOMUXC_GPR1[11:0]
-			should be set up as one of the following 4 possible
-			values depending on the CS space configuration.
-
-			IOMUXC_GPR1[11:0]    CS0    CS1    CS2    CS3
-			---------------------------------------------
-				05	    128M     0M     0M     0M
-				033          64M    64M     0M     0M
-				0113         64M    32M    32M     0M
-				01111        32M    32M    32M    32M
-
-			In case that the property is absent, the reset value or
-			what bootloader sets up in IOMUXC_GPR1[11:0] will be
-			used.
-
- - fsl,burst-clk-enable	For "fsl,imx50-weim" and "fsl,imx6q-weim" type of
-			devices, the presence of this property indicates that
-			the weim bus should operate in Burst Clock Mode.
-
- - fsl,continuous-burst-clk	Make Burst Clock to output continuous clock.
-			Without this option Burst Clock will output clock
-			only when necessary. This takes effect only if
-			"fsl,burst-clk-enable" is set.
-
-Timing property for child nodes. It is mandatory, not optional.
-
- - fsl,weim-cs-timing:	The timing array, contains timing values for the
-			child node. We get the CS indexes from the address
-			ranges in the child node's "reg" property.
-			The number of registers depends on the selected chip:
-			For i.MX1, i.MX21 ("fsl,imx1-weim") there are two
-			registers: CSxU, CSxL.
-			For i.MX25, i.MX27, i.MX31 and i.MX35 ("fsl,imx27-weim")
-			there are three registers: CSCRxU, CSCRxL, CSCRxA.
-			For i.MX50, i.MX53 ("fsl,imx50-weim"),
-			i.MX51 ("fsl,imx51-weim") and i.MX6Q ("fsl,imx6q-weim")
-			there are six registers: CSxGCR1, CSxGCR2, CSxRCR1,
-			CSxRCR2, CSxWCR1, CSxWCR2.
-
-Example for an imx6q-sabreauto board, the NOR flash connected to the WEIM:
-
-	weim: weim@21b8000 {
-		compatible = "fsl,imx6q-weim";
-		reg = <0x021b8000 0x4000>;
-		clocks = <&clks 196>;
-		#address-cells = <2>;
-		#size-cells = <1>;
-		ranges = <0 0 0x08000000 0x08000000>;
-		fsl,weim-cs-gpr = <&gpr>;
-
-		nor@0,0 {
-			compatible = "cfi-flash";
-			reg = <0 0 0x02000000>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			bank-width = <2>;
-			fsl,weim-cs-timing = <0x00620081 0x00000001 0x1c022000
-					0x0000c000 0x1404a38e 0x00000000>;
-		};
-	};
-
-Example for an imx6q-based board, a multi-chipselect device connected to WEIM:
-
-In this case, both chip select 0 and 1 will be configured with the same timing
-array values.
-
-	weim: weim@21b8000 {
-		compatible = "fsl,imx6q-weim";
-		reg = <0x021b8000 0x4000>;
-		clocks = <&clks 196>;
-		#address-cells = <2>;
-		#size-cells = <1>;
-		ranges = <0 0 0x08000000 0x02000000
-			  1 0 0x0a000000 0x02000000
-			  2 0 0x0c000000 0x02000000
-			  3 0 0x0e000000 0x02000000>;
-		fsl,weim-cs-gpr = <&gpr>;
-
-		acme@0 {
-			compatible = "acme,whatever";
-			reg = <0 0 0x100>, <0 0x400000 0x800>,
-				<1 0x400000 0x800>;
-			fsl,weim-cs-timing = <0x024400b1 0x00001010 0x20081100
-				0x00000000 0xa0000240 0x00000000>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
index 3eebc03a309b..1d2bcea41c85 100644
--- a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
@@ -30,14 +30,16 @@ properties:
       - google,gs101-cmu-top
       - google,gs101-cmu-apm
       - google,gs101-cmu-misc
+      - google,gs101-cmu-peric0
+      - google,gs101-cmu-peric1
 
   clocks:
     minItems: 1
-    maxItems: 2
+    maxItems: 3
 
   clock-names:
     minItems: 1
-    maxItems: 2
+    maxItems: 3
 
   "#clock-cells":
     const: 1
@@ -85,8 +87,30 @@ allOf:
 
         clock-names:
           items:
-            - const: dout_cmu_misc_bus
-            - const: dout_cmu_misc_sss
+            - const: bus
+            - const: sss
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - google,gs101-cmu-peric0
+              - google,gs101-cmu-peric1
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: External reference clock (24.576 MHz)
+            - description: Connectivity Peripheral 0/1 bus clock (from CMU_TOP)
+            - description: Connectivity Peripheral 0/1 IP clock (from CMU_TOP)
+
+        clock-names:
+          items:
+            - const: oscclk
+            - const: bus
+            - const: ip
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml
index 6c4846b34e4b..a1085ef4fd05 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sc8180x.yaml
@@ -31,10 +31,15 @@ properties:
       - const: bi_tcxo_ao
       - const: sleep_clk
 
+  power-domains:
+    items:
+      - description: CX domain
+
 required:
   - compatible
   - clocks
   - clock-names
+  - power-domains
 
 allOf:
   - $ref: qcom,gcc.yaml#
@@ -44,6 +49,7 @@ unevaluatedProperties: false
 examples:
   - |
     #include <dt-bindings/clock/qcom,rpmh.h>
+    #include <dt-bindings/power/qcom-rpmpd.h>
     clock-controller@100000 {
       compatible = "qcom,gcc-sc8180x";
       reg = <0x00100000 0x1f0000>;
@@ -51,6 +57,7 @@ examples:
                <&rpmhcc RPMH_CXO_CLK_A>,
                <&sleep_clk>;
       clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk";
+      power-domains = <&rpmhpd SC8180X_CX>;
       #clock-cells = <1>;
       #reset-cells = <1>;
       #power-domain-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
index 48986460f994..fa0e5b6b02b8 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
@@ -17,6 +17,7 @@ description: |
     include/dt-bindings/clock/qcom,sm8450-camcc.h
     include/dt-bindings/clock/qcom,sm8550-camcc.h
     include/dt-bindings/clock/qcom,sc8280xp-camcc.h
+    include/dt-bindings/clock/qcom,x1e80100-camcc.h
 
 allOf:
   - $ref: qcom,gcc.yaml#
@@ -27,6 +28,7 @@ properties:
       - qcom,sc8280xp-camcc
       - qcom,sm8450-camcc
       - qcom,sm8550-camcc
+      - qcom,x1e80100-camcc
 
   clocks:
     items:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
index 1a384e8532a5..36974309cf69 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
@@ -18,6 +18,7 @@ description: |
     include/dt-bindings/clock/qcom,sm8550-gpucc.h
     include/dt-bindings/reset/qcom,sm8450-gpucc.h
     include/dt-bindings/reset/qcom,sm8650-gpucc.h
+    include/dt-bindings/reset/qcom,x1e80100-gpucc.h
 
 properties:
   compatible:
@@ -25,6 +26,7 @@ properties:
       - qcom,sm8450-gpucc
       - qcom,sm8550-gpucc
       - qcom,sm8650-gpucc
+      - qcom,x1e80100-gpucc
 
   clocks:
     items:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml
index c129f8c16b50..bad0260764d4 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-dispcc.yaml
@@ -14,12 +14,17 @@ description: |
   Qualcomm display clock control module provides the clocks, resets and power
   domains on SM8550.
 
-  See also:: include/dt-bindings/clock/qcom,sm8550-dispcc.h
+  See also:
+  - include/dt-bindings/clock/qcom,sm8550-dispcc.h
+  - include/dt-bindings/clock/qcom,sm8650-dispcc.h
+  - include/dt-bindings/clock/qcom,x1e80100-dispcc.h
 
 properties:
   compatible:
     enum:
       - qcom,sm8550-dispcc
+      - qcom,sm8650-dispcc
+      - qcom,x1e80100-dispcc
 
   clocks:
     items:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
index af16b05eac96..48fdd562d743 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
@@ -23,6 +23,7 @@ properties:
       - enum:
           - qcom,sm8550-tcsr
           - qcom,sm8650-tcsr
+          - qcom,x1e80100-tcsr
       - const: syscon
 
   clocks:
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
deleted file mode 100644
index 5e0c45c380f5..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
+++ /dev/null
@@ -1,106 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/clock/qcom,sm8650-dispcc.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Qualcomm Display Clock & Reset Controller for SM8650
-
-maintainers:
-  - Bjorn Andersson <andersson@kernel.org>
-  - Neil Armstrong <neil.armstrong@linaro.org>
-
-description: |
-  Qualcomm display clock control module provides the clocks, resets and power
-  domains on SM8650.
-
-  See also:: include/dt-bindings/clock/qcom,sm8650-dispcc.h
-
-properties:
-  compatible:
-    enum:
-      - qcom,sm8650-dispcc
-
-  clocks:
-    items:
-      - description: Board XO source
-      - description: Board Always On XO source
-      - description: Display's AHB clock
-      - description: sleep clock
-      - description: Byte clock from DSI PHY0
-      - description: Pixel clock from DSI PHY0
-      - description: Byte clock from DSI PHY1
-      - description: Pixel clock from DSI PHY1
-      - description: Link clock from DP PHY0
-      - description: VCO DIV clock from DP PHY0
-      - description: Link clock from DP PHY1
-      - description: VCO DIV clock from DP PHY1
-      - description: Link clock from DP PHY2
-      - description: VCO DIV clock from DP PHY2
-      - description: Link clock from DP PHY3
-      - description: VCO DIV clock from DP PHY3
-
-  '#clock-cells':
-    const: 1
-
-  '#reset-cells':
-    const: 1
-
-  '#power-domain-cells':
-    const: 1
-
-  reg:
-    maxItems: 1
-
-  power-domains:
-    description:
-      A phandle and PM domain specifier for the MMCX power domain.
-    maxItems: 1
-
-  required-opps:
-    description:
-      A phandle to an OPP node describing required MMCX performance point.
-    maxItems: 1
-
-required:
-  - compatible
-  - reg
-  - clocks
-  - '#clock-cells'
-  - '#reset-cells'
-  - '#power-domain-cells'
-
-additionalProperties: false
-
-examples:
-  - |
-    #include <dt-bindings/clock/qcom,sm8650-gcc.h>
-    #include <dt-bindings/clock/qcom,rpmh.h>
-    #include <dt-bindings/power/qcom-rpmpd.h>
-    #include <dt-bindings/power/qcom,rpmhpd.h>
-    clock-controller@af00000 {
-      compatible = "qcom,sm8650-dispcc";
-      reg = <0x0af00000 0x10000>;
-      clocks = <&rpmhcc RPMH_CXO_CLK>,
-               <&rpmhcc RPMH_CXO_CLK_A>,
-               <&gcc GCC_DISP_AHB_CLK>,
-               <&sleep_clk>,
-               <&dsi0_phy 0>,
-               <&dsi0_phy 1>,
-               <&dsi1_phy 0>,
-               <&dsi1_phy 1>,
-               <&dp0_phy 0>,
-               <&dp0_phy 1>,
-               <&dp1_phy 0>,
-               <&dp1_phy 1>,
-               <&dp2_phy 0>,
-               <&dp2_phy 1>,
-               <&dp3_phy 0>,
-               <&dp3_phy 1>;
-      #clock-cells = <1>;
-      #reset-cells = <1>;
-      #power-domain-cells = <1>;
-      power-domains = <&rpmhpd RPMHPD_MMCX>;
-      required-opps = <&rpmhpd_opp_low_svs>;
-    };
-...
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.yaml b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.yaml
index 9c3dc6c4fa94..084259d30232 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.yaml
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.yaml
@@ -50,6 +50,7 @@ properties:
       - renesas,r8a779a0-cpg-mssr # R-Car V3U
       - renesas,r8a779f0-cpg-mssr # R-Car S4-8
       - renesas,r8a779g0-cpg-mssr # R-Car V4H
+      - renesas,r8a779h0-cpg-mssr # R-Car V4M
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
index 21d995f29a1e..b8e9cf6ce4e6 100644
--- a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
@@ -29,19 +29,22 @@ properties:
 
   audio-ports:
     description:
-      Array of 8-bit values, 2 values per DAI (Documentation/sound/soc/dai.rst).
+      Array of 2 values per DAI (Documentation/sound/soc/dai.rst).
       The implementation allows one or two DAIs.
       If two DAIs are defined, they must be of different type.
     $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    minItems: 1
+    maxItems: 2
     items:
-      minItems: 1
       items:
         - description: |
             The first value defines the DAI type: TDA998x_SPDIF or TDA998x_I2S
             (see include/dt-bindings/display/tda998x.h).
+          enum: [ 1, 2 ]
         - description:
             The second value defines the tda998x AP_ENA reg content when the
             DAI in question is used.
+          maximum: 0xff
 
   '#sound-dai-cells':
     enum: [ 0, 1 ]
diff --git a/Documentation/devicetree/bindings/display/panel/novatek,nt35510.yaml b/Documentation/devicetree/bindings/display/panel/novatek,nt35510.yaml
index bc92928c805b..619edcf6c791 100644
--- a/Documentation/devicetree/bindings/display/panel/novatek,nt35510.yaml
+++ b/Documentation/devicetree/bindings/display/panel/novatek,nt35510.yaml
@@ -29,6 +29,7 @@ properties:
   vddi-supply:
     description: regulator that supplies the vddi voltage
   backlight: true
+  port: true
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/firmware/xilinx/xlnx,zynqmp-firmware.yaml b/Documentation/devicetree/bindings/firmware/xilinx/xlnx,zynqmp-firmware.yaml
index 8e584857ddd4..ab8f32c440df 100644
--- a/Documentation/devicetree/bindings/firmware/xilinx/xlnx,zynqmp-firmware.yaml
+++ b/Documentation/devicetree/bindings/firmware/xilinx/xlnx,zynqmp-firmware.yaml
@@ -26,6 +26,12 @@ properties:
       - description: For implementations complying for Versal.
         const: xlnx,versal-firmware
 
+      - description: For implementations complying for Versal NET.
+        items:
+          - enum:
+              - xlnx,versal-net-firmware
+          - const: xlnx,versal-firmware
+
   method:
     description: |
                  The method of calling the PM-API firmware layer.
@@ -41,7 +47,53 @@ properties:
   "#power-domain-cells":
     const: 1
 
-  versal_fpga:
+  clock-controller:
+    $ref: /schemas/clock/xlnx,versal-clk.yaml#
+    description: The clock controller is a hardware block of Xilinx versal
+      clock tree. It reads required input clock frequencies from the devicetree
+      and acts as clock provider for all clock consumers of PS clocks.list of
+      clock specifiers which are external input clocks to the given clock
+      controller.
+    type: object
+
+  gpio:
+    $ref: /schemas/gpio/xlnx,zynqmp-gpio-modepin.yaml#
+    description: The gpio node describes connect to PS_MODE pins via firmware
+      interface.
+    type: object
+
+  soc-nvmem:
+    $ref: /schemas/nvmem/xlnx,zynqmp-nvmem.yaml#
+    description: The ZynqMP MPSoC provides access to the hardware related data
+      like SOC revision, IDCODE and specific purpose efuses.
+    type: object
+
+  pcap:
+    $ref: /schemas/fpga/xlnx,zynqmp-pcap-fpga.yaml
+    description: The ZynqMP SoC uses the PCAP (Processor Configuration Port) to
+      configure the Programmable Logic (PL). The configuration uses the
+      firmware interface.
+    type: object
+
+  pinctrl:
+    $ref: /schemas/pinctrl/xlnx,zynqmp-pinctrl.yaml#
+    description: The pinctrl node provides access to pinconfig and pincontrol
+      functionality available in firmware.
+    type: object
+
+  power-management:
+    $ref: /schemas/power/reset/xlnx,zynqmp-power.yaml#
+    description: The zynqmp-power node describes the power management
+      configurations. It will control remote suspend/shutdown interfaces.
+    type: object
+
+  reset-controller:
+    $ref: /schemas/reset/xlnx,zynqmp-reset.yaml#
+    description: The reset-controller node describes connection to the reset
+      functionality via firmware interface.
+    type: object
+
+  versal-fpga:
     $ref: /schemas/fpga/xlnx,versal-fpga.yaml#
     description: Compatible of the FPGA device.
     type: object
@@ -53,15 +105,6 @@ properties:
       vector.
     type: object
 
-  clock-controller:
-    $ref: /schemas/clock/xlnx,versal-clk.yaml#
-    description: The clock controller is a hardware block of Xilinx versal
-      clock tree. It reads required input clock frequencies from the devicetree
-      and acts as clock provider for all clock consumers of PS clocks.list of
-      clock specifiers which are external input clocks to the given clock
-      controller.
-    type: object
-
 required:
   - compatible
 
@@ -73,7 +116,38 @@ examples:
     firmware {
       zynqmp_firmware: zynqmp-firmware {
         #power-domain-cells = <1>;
+        soc-nvmem {
+          compatible = "xlnx,zynqmp-nvmem-fw";
+          nvmem-layout {
+            compatible = "fixed-layout";
+            #address-cells = <1>;
+            #size-cells = <1>;
+
+            soc_revision: soc-revision@0 {
+                reg = <0x0 0x4>;
+            };
+          };
+        };
+        gpio {
+          compatible = "xlnx,zynqmp-gpio-modepin";
+          gpio-controller;
+          #gpio-cells = <2>;
+        };
+        pcap {
+          compatible = "xlnx,zynqmp-pcap-fpga";
         };
+        pinctrl {
+          compatible = "xlnx,zynqmp-pinctrl";
+        };
+        power-management {
+          compatible = "xlnx,zynqmp-power";
+          interrupts = <0 35 4>;
+        };
+        reset-controller {
+          compatible = "xlnx,zynqmp-reset";
+          #reset-cells = <1>;
+        };
+      };
     };
 
     sata {
@@ -84,7 +158,7 @@ examples:
       compatible = "xlnx,versal-firmware";
       method = "smc";
 
-      versal_fpga: versal_fpga {
+      versal_fpga: versal-fpga {
         compatible = "xlnx,versal-fpga";
       };
 
diff --git a/Documentation/devicetree/bindings/fpga/xlnx,versal-fpga.yaml b/Documentation/devicetree/bindings/fpga/xlnx,versal-fpga.yaml
index 26f18834caa3..80833462f620 100644
--- a/Documentation/devicetree/bindings/fpga/xlnx,versal-fpga.yaml
+++ b/Documentation/devicetree/bindings/fpga/xlnx,versal-fpga.yaml
@@ -26,7 +26,7 @@ additionalProperties: false
 
 examples:
   - |
-    versal_fpga: versal_fpga {
+    versal_fpga: versal-fpga {
          compatible = "xlnx,versal-fpga";
     };
 
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
index b1fd632718d4..bb93baa88879 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
@@ -12,7 +12,8 @@ description:
   PS_MODE). Every pin can be configured as input/output.
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/gpu/img,powervr.yaml b/Documentation/devicetree/bindings/gpu/img,powervr-rogue.yaml
index a13298f1a182..256e252f8087 100644
--- a/Documentation/devicetree/bindings/gpu/img,powervr.yaml
+++ b/Documentation/devicetree/bindings/gpu/img,powervr-rogue.yaml
@@ -2,10 +2,10 @@
 # Copyright (c) 2023 Imagination Technologies Ltd.
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/gpu/img,powervr.yaml#
+$id: http://devicetree.org/schemas/gpu/img,powervr-rogue.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Imagination Technologies PowerVR and IMG GPU
+title: Imagination Technologies PowerVR and IMG Rogue GPUs
 
 maintainers:
   - Frank Binns <frank.binns@imgtec.com>
diff --git a/Documentation/devicetree/bindings/gpu/img,powervr-sgx.yaml b/Documentation/devicetree/bindings/gpu/img,powervr-sgx.yaml
new file mode 100644
index 000000000000..f5898b04381c
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpu/img,powervr-sgx.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (c) 2023 Imagination Technologies Ltd.
+# Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/gpu/img,powervr-sgx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Imagination Technologies PowerVR SGX GPUs
+
+maintainers:
+  - Frank Binns <frank.binns@imgtec.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - ti,omap3430-gpu # Rev 121
+              - ti,omap3630-gpu # Rev 125
+          - const: img,powervr-sgx530
+      - items:
+          - enum:
+              - ingenic,jz4780-gpu # Rev 130
+              - ti,omap4430-gpu # Rev 120
+          - const: img,powervr-sgx540
+      - items:
+          - enum:
+              - allwinner,sun6i-a31-gpu # MP2 Rev 115
+              - ti,omap4470-gpu # MP1 Rev 112
+              - ti,omap5432-gpu # MP2 Rev 105
+              - ti,am5728-gpu # MP2 Rev 116
+              - ti,am6548-gpu # MP1 Rev 117
+          - const: img,powervr-sgx544
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 3
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: core
+      - const: mem
+      - const: sys
+
+  power-domains:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ti,am6548-gpu
+    then:
+      required:
+        - power-domains
+    else:
+      properties:
+        power-domains: false
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun6i-a31-gpu
+              - ingenic,jz4780-gpu
+    then:
+      required:
+        - clocks
+        - clock-names
+    else:
+      properties:
+        clocks: false
+        clock-names: false
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun6i-a31-gpu
+    then:
+      properties:
+        clocks:
+          minItems: 2
+          maxItems: 2
+        clock-names:
+          minItems: 2
+          maxItems: 2
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ingenic,jz4780-gpu
+    then:
+      properties:
+        clocks:
+          maxItems: 1
+        clock-names:
+          maxItems: 1
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/soc/ti,sci_pm_domain.h>
+
+    gpu@7000000 {
+        compatible = "ti,am6548-gpu", "img,powervr-sgx544";
+        reg = <0x7000000 0x10000>;
+        interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
+        power-domains = <&k3_pds 65 TI_SCI_PD_EXCLUSIVE>;
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    gpu: gpu@1c40000 {
+        compatible = "allwinner,sun6i-a31-gpu", "img,powervr-sgx544";
+        reg = <0x01c40000 0x10000>;
+        interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu 1>, <&ccu 2>;
+        clock-names = "core", "mem";
+    };
diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
index df9c57bca2a8..cc8bba5537b9 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml
@@ -33,6 +33,7 @@ properties:
           - const: samsung,exynos7-hsi2c
       - items:
           - enum:
+              - google,gs101-hsi2c
               - samsung,exynos850-hsi2c
           - const: samsung,exynosautov9-hsi2c
       - const: samsung,exynos5-hsi2c    # Exynos5250 and Exynos5420
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.yaml
index 3d06db98e978..a93744763787 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.yaml
@@ -36,6 +36,7 @@ properties:
               - amlogic,meson-a1-gpio-intc
               - amlogic,meson-s4-gpio-intc
               - amlogic,c3-gpio-intc
+              - amlogic,t7-gpio-intc
           - const: amlogic,meson-gpio-intc
 
   reg:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/starfive,jh8100-intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/starfive,jh8100-intc.yaml
new file mode 100644
index 000000000000..ada5788602d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/starfive,jh8100-intc.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/starfive,jh8100-intc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: StarFive External Interrupt Controller
+
+description:
+  StarFive SoC JH8100 contain a external interrupt controller. It can be used
+  to handle high-level input interrupt signals. It also send the output
+  interrupt signal to RISC-V PLIC.
+
+maintainers:
+  - Changhuang Liang <changhuang.liang@starfivetech.com>
+
+properties:
+  compatible:
+    const: starfive,jh8100-intc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    description: APB clock for the interrupt controller
+    maxItems: 1
+
+  resets:
+    description: APB reset for the interrupt controller
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  interrupt-controller: true
+
+  "#interrupt-cells":
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+  - interrupts
+  - interrupt-controller
+  - "#interrupt-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    interrupt-controller@12260000 {
+      compatible = "starfive,jh8100-intc";
+      reg = <0x12260000 0x10000>;
+      clocks = <&syscrg_ne 76>;
+      resets = <&syscrg_ne 13>;
+      interrupts = <45>;
+      interrupt-controller;
+      #interrupt-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml
index a2051b31fa29..b45743d0a9ec 100644
--- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml
+++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml
@@ -16,14 +16,18 @@ description: |+
 
 properties:
   compatible:
-    enum:
-      - mediatek,mt8173-vcodec-enc-vp8
-      - mediatek,mt8173-vcodec-enc
-      - mediatek,mt8183-vcodec-enc
-      - mediatek,mt8188-vcodec-enc
-      - mediatek,mt8192-vcodec-enc
-      - mediatek,mt8195-vcodec-enc
-
+    oneOf:
+      - items:
+          - enum:
+              - mediatek,mt8173-vcodec-enc-vp8
+              - mediatek,mt8173-vcodec-enc
+              - mediatek,mt8183-vcodec-enc
+              - mediatek,mt8188-vcodec-enc
+              - mediatek,mt8192-vcodec-enc
+              - mediatek,mt8195-vcodec-enc
+      - items:
+          - const: mediatek,mt8186-vcodec-enc
+          - const: mediatek,mt8183-vcodec-enc
   reg:
     maxItems: 1
 
@@ -109,10 +113,7 @@ allOf:
       properties:
         compatible:
           enum:
-            - mediatek,mt8173-vcodec-enc
-            - mediatek,mt8188-vcodec-enc
-            - mediatek,mt8192-vcodec-enc
-            - mediatek,mt8195-vcodec-enc
+            - mediatek,mt8173-vcodec-enc-vp8
 
     then:
       properties:
@@ -122,8 +123,8 @@ allOf:
             maxItems: 1
         clock-names:
           items:
-            - const: venc_sel
-    else:  # for vp8 hw encoder
+            - const: venc_lt_sel
+    else:
       properties:
         clock:
           items:
@@ -131,7 +132,7 @@ allOf:
             maxItems: 1
         clock-names:
           items:
-            - const: venc_lt_sel
+            - const: venc_sel
 
 additionalProperties: false
 
diff --git a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml
index 37800e1908cc..83c020a673d6 100644
--- a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml
+++ b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml
@@ -38,7 +38,8 @@ properties:
     maxItems: 1
 
   iommus:
-    maxItems: 2
+    minItems: 2
+    maxItems: 4
     description: |
       Points to the respective IOMMU block with master port as argument, see
       Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml for details.
diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim-peripherals.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim-peripherals.yaml
new file mode 100644
index 000000000000..82fc5f4a1ed6
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim-peripherals.yaml
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/memory-controllers/fsl/fsl,imx-weim-peripherals.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: i.MX WEIM Bus Peripheral Nodes
+
+maintainers:
+  - Shawn Guo <shawnguo@kernel.org>
+  - Sascha Hauer <s.hauer@pengutronix.de>
+
+description:
+  This binding is meant for the child nodes of the WEIM node. The node
+  represents any device connected to the WEIM bus. It may be a Flash chip,
+  RAM chip or Ethernet controller, etc. These properties are meant for
+  configuring the WEIM settings/timings and will accompany the bindings
+  supported by the respective device.
+
+properties:
+  reg: true
+
+  fsl,weim-cs-timing:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description:
+      Timing values for the child node.
+    minItems: 2
+    maxItems: 6
+
+# the WEIM child will have its own native properties
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim.yaml
new file mode 100644
index 000000000000..3f40ca5b13f6
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim.yaml
@@ -0,0 +1,204 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/memory-controllers/fsl/fsl,imx-weim.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: i.MX Wireless External Interface Module (WEIM)
+
+maintainers:
+  - Shawn Guo <shawnguo@kernel.org>
+  - Sascha Hauer <s.hauer@pengutronix.de>
+
+description:
+  The term "wireless" does not imply that the WEIM is literally an interface
+  without wires. It simply means that this module was originally designed for
+  wireless and mobile applications that use low-power technology. The actual
+  devices are instantiated from the child nodes of a WEIM node.
+
+properties:
+  $nodename:
+    pattern: "^memory-controller@[0-9a-f]+$"
+
+  compatible:
+    oneOf:
+      - enum:
+          - fsl,imx1-weim
+          - fsl,imx27-weim
+          - fsl,imx50-weim
+          - fsl,imx51-weim
+          - fsl,imx6q-weim
+      - items:
+          - enum:
+              - fsl,imx31-weim
+              - fsl,imx35-weim
+          - const: fsl,imx27-weim
+      - items:
+          - enum:
+              - fsl,imx6sx-weim
+              - fsl,imx6ul-weim
+          - const: fsl,imx6q-weim
+
+  "#address-cells":
+    const: 2
+
+  "#size-cells":
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  ranges: true
+
+  fsl,weim-cs-gpr:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: |
+      Phandle to the system General Purpose Register controller that contains
+      WEIM CS GPR register, e.g. IOMUXC_GPR1 on i.MX6Q. IOMUXC_GPR1[11:0]
+      should be set up as one of the following 4 possible values depending on
+      the CS space configuration.
+
+      IOMUXC_GPR1[11:0]    CS0    CS1    CS2    CS3
+      ---------------------------------------------
+              05          128M     0M     0M     0M
+              033          64M    64M     0M     0M
+              0113         64M    32M    32M     0M
+              01111        32M    32M    32M    32M
+
+      In case that the property is absent, the reset value or what bootloader
+      sets up in IOMUXC_GPR1[11:0] will be used.
+
+  fsl,burst-clk-enable:
+    type: boolean
+    description:
+      The presence of this property indicates that the weim bus should operate
+      in Burst Clock Mode.
+
+  fsl,continuous-burst-clk:
+    type: boolean
+    description:
+      Make Burst Clock to output continuous clock. Without this option Burst
+      Clock will output clock only when necessary.
+
+patternProperties:
+  "^.*@[0-7],[0-9a-f]+$":
+    type: object
+    description: Devices attached to chip selects are represented as subnodes.
+    $ref: fsl,imx-weim-peripherals.yaml
+    additionalProperties: true
+    required:
+      - fsl,weim-cs-timing
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - "#address-cells"
+  - "#size-cells"
+  - ranges
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          not:
+            contains:
+              enum:
+                - fsl,imx50-weim
+                - fsl,imx6q-weim
+    then:
+      properties:
+        fsl,weim-cs-gpr: false
+        fsl,burst-clk-enable: false
+  - if:
+      not:
+        required:
+          - fsl,burst-clk-enable
+    then:
+      properties:
+        fsl,continuous-burst-clk: false
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx1-weim
+    then:
+      patternProperties:
+        "^.*@[0-7],[0-9a-f]+$":
+          properties:
+            fsl,weim-cs-timing:
+              items:
+                items:
+                  - description: CSxU
+                  - description: CSxL
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx27-weim
+              - fsl,imx31-weim
+              - fsl,imx35-weim
+    then:
+      patternProperties:
+        "^.*@[0-7],[0-9a-f]+$":
+          properties:
+            fsl,weim-cs-timing:
+              items:
+                items:
+                  - description: CSCRxU
+                  - description: CSCRxL
+                  - description: CSCRxA
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,imx50-weim
+              - fsl,imx51-weim
+              - fsl,imx6q-weim
+              - fsl,imx6sx-weim
+              - fsl,imx6ul-weim
+    then:
+      patternProperties:
+        "^.*@[0-7],[0-9a-f]+$":
+          properties:
+            fsl,weim-cs-timing:
+              items:
+                items:
+                  - description: CSxGCR1
+                  - description: CSxGCR2
+                  - description: CSxRCR1
+                  - description: CSxRCR2
+                  - description: CSxWCR1
+                  - description: CSxWCR2
+
+additionalProperties: false
+
+examples:
+  - |
+    memory-controller@21b8000 {
+        compatible = "fsl,imx6q-weim";
+        reg = <0x021b8000 0x4000>;
+        clocks = <&clks 196>;
+        #address-cells = <2>;
+        #size-cells = <1>;
+        ranges = <0 0 0x08000000 0x08000000>;
+        fsl,weim-cs-gpr = <&gpr>;
+
+        flash@0,0 {
+            compatible = "cfi-flash";
+            reg = <0 0 0x02000000>;
+            #address-cells = <1>;
+            #size-cells = <1>;
+            bank-width = <2>;
+            fsl,weim-cs-timing = <0x00620081 0x00000001 0x1c022000
+                                  0x0000c000 0x1404a38e 0x00000000>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/memory-controllers/mc-peripheral-props.yaml b/Documentation/devicetree/bindings/memory-controllers/mc-peripheral-props.yaml
index 8d9dae15ade0..00deeb09f87d 100644
--- a/Documentation/devicetree/bindings/memory-controllers/mc-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/mc-peripheral-props.yaml
@@ -37,5 +37,6 @@ allOf:
   - $ref: ingenic,nemc-peripherals.yaml#
   - $ref: intel,ixp4xx-expansion-peripheral-props.yaml#
   - $ref: ti,gpmc-child.yaml#
+  - $ref: fsl/fsl,imx-weim-peripherals.yaml
 
 additionalProperties: true
diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-emc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-emc.yaml
index f54e553e6c0e..71896cb10692 100644
--- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-emc.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra20-emc.yaml
@@ -145,7 +145,7 @@ patternProperties:
   "^emc-table@[0-9]+$":
     $ref: "#/$defs/emc-table"
 
-  "^emc-tables@[a-z0-9-]+$":
+  "^emc-tables@[a-f0-9-]+$":
     type: object
     properties:
       reg:
diff --git a/Documentation/devicetree/bindings/memory-controllers/renesas,rpc-if.yaml b/Documentation/devicetree/bindings/memory-controllers/renesas,rpc-if.yaml
index 25f3bb9890ae..d7745dd53b51 100644
--- a/Documentation/devicetree/bindings/memory-controllers/renesas,rpc-if.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/renesas,rpc-if.yaml
@@ -45,6 +45,7 @@ properties:
       - items:
           - enum:
               - renesas,r8a779g0-rpc-if       # R-Car V4H
+              - renesas,r8a779h0-rpc-if       # R-Car V4M
           - const: renesas,rcar-gen4-rpc-if   # a generic R-Car gen4 device
 
       - items:
diff --git a/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml b/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
index 14f1833d37c9..84ac6f50a6fc 100644
--- a/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
@@ -23,7 +23,9 @@ maintainers:
 
 properties:
   compatible:
-    const: st,stm32mp1-fmc2-ebi
+    enum:
+      - st,stm32mp1-fmc2-ebi
+      - st,stm32mp25-fmc2-ebi
 
   reg:
     maxItems: 1
@@ -34,6 +36,9 @@ properties:
   resets:
     maxItems: 1
 
+  power-domains:
+    maxItems: 1
+
   "#address-cells":
     const: 2
 
diff --git a/Documentation/devicetree/bindings/net/marvell,prestera.yaml b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
index 5ea8b73663a5..16ff892f7bbd 100644
--- a/Documentation/devicetree/bindings/net/marvell,prestera.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
@@ -78,8 +78,8 @@ examples:
     pcie@0 {
         #address-cells = <3>;
         #size-cells = <2>;
-        ranges = <0x0 0x0 0x0 0x0 0x0 0x0>;
-        reg = <0x0 0x0 0x0 0x0 0x0 0x0>;
+        ranges = <0x02000000 0x0 0x100000 0x10000000 0x0 0x0>;
+        reg = <0x0 0x1000>;
         device_type = "pci";
 
         switch@0,0 {
diff --git a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
index 475aff7714d6..ea35d19be829 100644
--- a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml
@@ -65,9 +65,11 @@ properties:
 
   rx-internal-delay-ps:
     enum: [0, 1800]
+    default: 0
 
   tx-internal-delay-ps:
     enum: [0, 2000]
+    default: 0
 
   '#address-cells':
     const: 1
diff --git a/Documentation/devicetree/bindings/power/renesas,rcar-sysc.yaml b/Documentation/devicetree/bindings/power/renesas,rcar-sysc.yaml
index 0720b54881c2..e76fb273490f 100644
--- a/Documentation/devicetree/bindings/power/renesas,rcar-sysc.yaml
+++ b/Documentation/devicetree/bindings/power/renesas,rcar-sysc.yaml
@@ -45,6 +45,7 @@ properties:
       - renesas,r8a779a0-sysc # R-Car V3U
       - renesas,r8a779f0-sysc # R-Car S4-8
       - renesas,r8a779g0-sysc # R-Car V4H
+      - renesas,r8a779h0-sysc # R-Car V4M
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/renesas,rst.yaml b/Documentation/devicetree/bindings/reset/renesas,rst.yaml
index e7e487247751..58b4a45d3380 100644
--- a/Documentation/devicetree/bindings/reset/renesas,rst.yaml
+++ b/Documentation/devicetree/bindings/reset/renesas,rst.yaml
@@ -50,6 +50,7 @@ properties:
       - renesas,r8a779a0-rst      # R-Car V3U
       - renesas,r8a779f0-rst      # R-Car S4-8
       - renesas,r8a779g0-rst      # R-Car V4H
+      - renesas,r8a779h0-rst      # R-Car V4M
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
index 49db66801429..1f1b42dde94d 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Zynq UltraScale+ MPSoC and Versal reset
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 description: |
   The Zynq UltraScale+ MPSoC and Versal has several different resets.
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,pbs.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,pbs.yaml
new file mode 100644
index 000000000000..b502ca72266a
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,pbs.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/soc/qcom/qcom,pbs.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Technologies, Inc. Programmable Boot Sequencer
+
+maintainers:
+  - Anjelique Melendez <quic_amelende@quicinc.com>
+
+description: |
+  The Qualcomm Technologies, Inc. Programmable Boot Sequencer (PBS)
+  supports triggering power up and power down sequences for clients
+  upon request.
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - qcom,pmi632-pbs
+      - const: qcom,pbs
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/spmi/spmi.h>
+
+    pmic@0 {
+      reg = <0x0 SPMI_USID>;
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      pbs@7400 {
+        compatible = "qcom,pmi632-pbs", "qcom,pbs";
+        reg = <0x7400>;
+      };
+    };
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
index 61df97ffe1e4..d3f3259ef77d 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,pmic-glink.yaml
@@ -32,6 +32,7 @@ properties:
       - items:
           - enum:
               - qcom,sm8650-pmic-glink
+              - qcom,x1e80100-pmic-glink
           - const: qcom,sm8550-pmic-glink
           - const: qcom,pmic-glink
 
@@ -65,6 +66,7 @@ allOf:
               enum:
                 - qcom,sm8450-pmic-glink
                 - qcom,sm8550-pmic-glink
+                - qcom,x1e80100-pmic-glink
     then:
       properties:
         orientation-gpios: false
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
index 031800985b5e..9410404f87f1 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,rpm-master-stats.yaml
@@ -35,6 +35,8 @@ properties:
     description: Phandle to an RPM MSG RAM slice containing the master stats
     minItems: 1
     maxItems: 5
+    items:
+      maxItems: 1
 
   qcom,master-names:
     $ref: /schemas/types.yaml#/definitions/string-array
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,spm.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,saw2.yaml
index 20c8cd38ff0d..ca4bce817273 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,spm.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,saw2.yaml
@@ -1,23 +1,33 @@
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/soc/qcom/qcom,spm.yaml#
+$id: http://devicetree.org/schemas/soc/qcom/qcom,saw2.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Qualcomm Subsystem Power Manager
+title: Qualcomm Subsystem Power Manager / SPM AVS Wrapper 2 (SAW2)
 
 maintainers:
   - Andy Gross <agross@kernel.org>
   - Bjorn Andersson <bjorn.andersson@linaro.org>
 
 description: |
-  This binding describes the Qualcomm Subsystem Power Manager, used to control
-  the peripheral logic surrounding the application cores in Qualcomm platforms.
+  The Qualcomm Subsystem Power Manager is used to control the peripheral logic
+  surrounding the application cores in Qualcomm platforms.
+
+  The SAW2 is a wrapper around the Subsystem Power Manager (SPM) and the
+  Adaptive Voltage Scaling (AVS) hardware. The SPM is a programmable
+  power-controller that transitions a piece of hardware (like a processor or
+  subsystem) into and out of low power modes via a direct connection to
+  the PMIC. It can also be wired up to interact with other processors in the
+  system, notifying them when a low power state is entered or exited.
 
 properties:
   compatible:
     items:
       - enum:
+          - qcom,ipq4019-saw2-cpu
+          - qcom,ipq4019-saw2-l2
+          - qcom,ipq8064-saw2-cpu
           - qcom,sdm660-gold-saw2-v4.1-l2
           - qcom,sdm660-silver-saw2-v4.1-l2
           - qcom,msm8998-gold-saw2-v4.1-l2
@@ -26,16 +36,27 @@ properties:
           - qcom,msm8916-saw2-v3.0-cpu
           - qcom,msm8939-saw2-v3.0-cpu
           - qcom,msm8226-saw2-v2.1-cpu
+          - qcom,msm8226-saw2-v2.1-l2
+          - qcom,msm8960-saw2-cpu
           - qcom,msm8974-saw2-v2.1-cpu
+          - qcom,msm8974-saw2-v2.1-l2
           - qcom,msm8976-gold-saw2-v2.3-l2
           - qcom,msm8976-silver-saw2-v2.3-l2
           - qcom,apq8084-saw2-v2.1-cpu
+          - qcom,apq8084-saw2-v2.1-l2
           - qcom,apq8064-saw2-v1.1-cpu
       - const: qcom,saw2
 
   reg:
-    description: Base address and size of the SPM register region
-    maxItems: 1
+    items:
+      - description: Base address and size of the SPM register region
+      - description: Base address and size of the alias register region
+    minItems: 1
+
+  regulator:
+    $ref: /schemas/regulator/regulator.yaml#
+    description: Indicates that this SPM device acts as a regulator device
+      device for the core (CPU or Cache) the SPM is attached to.
 
 required:
   - compatible
@@ -82,4 +103,17 @@ examples:
         reg = <0x17912000 0x1000>;
     };
 
+  - |
+    /*
+     * Example 3: SAW2 with the bundled regulator definition.
+     */
+    power-manager@2089000 {
+        compatible = "qcom,apq8064-saw2-v1.1-cpu", "qcom,saw2";
+        reg = <0x02089000 0x1000>, <0x02009000 0x1000>;
+
+        regulator {
+            regulator-min-microvolt = <850000>;
+            regulator-max-microvolt = <1300000>;
+        };
+    };
 ...
diff --git a/Documentation/devicetree/bindings/soc/renesas/renesas-soc.yaml b/Documentation/devicetree/bindings/soc/renesas/renesas-soc.yaml
new file mode 100644
index 000000000000..5ddd31f30f26
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/renesas/renesas-soc.yaml
@@ -0,0 +1,73 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/soc/renesas/renesas-soc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas SoC compatibles naming convention
+
+maintainers:
+  - Geert Uytterhoeven <geert+renesas@glider.be>
+  - Niklas Söderlund <niklas.soderlund@ragnatech.se>
+
+description: |
+  Guidelines for new compatibles for SoC blocks/components.
+  When adding new compatibles in new bindings, use the format::
+    renesas,SoC-IP
+
+  For example::
+   renesas,r8a77965-csi2
+
+  When adding new compatibles to existing bindings, use the format in the
+  existing binding, even if it contradicts the above.
+
+select:
+  properties:
+    compatible:
+      contains:
+        pattern: "^renesas,.+-.+$"
+  required:
+    - compatible
+
+properties:
+  compatible:
+    minItems: 1
+    maxItems: 4
+    items:
+      anyOf:
+        # Preferred naming style for compatibles of SoC components
+        - pattern: "^renesas,(emev2|r(7s|8a|9a)[a-z0-9]+|rcar|rmobile|rz[a-z0-9]*|sh(7[a-z0-9]+)?|mobile)-[a-z0-9-]+$"
+        - pattern: "^renesas,(condor|falcon|gr-peach|gray-hawk|salvator|sk-rz|smar(c(2)?)?|spider|white-hawk)(.*)?$"
+
+        # Legacy compatibles
+        #
+        # New compatibles are not allowed.
+        - pattern: "^renesas,(can|cpg|dmac|du|(g)?ether(avb)?|gpio|hscif|(r)?i[i2]c|imr|intc|ipmmu|irqc|jpu|mmcif|msiof|mtu2|pci(e)?|pfc|pwm|[rq]spi|rcar_sound|sata|scif[ab]*|sdhi|thermal|tmu|tpu|usb(2|hs)?|vin|xhci)-[a-z0-9-]+$"
+        - pattern: "^renesas,(d|s)?bsc(3)?-(r8a73a4|r8a7740|sh73a0)$"
+        - pattern: "^renesas,em-(gio|sti|uart)$"
+        - pattern: "^renesas,fsi2-(r8a7740|sh73a0)$"
+        - pattern: "^renesas,hspi-r8a777[89]$"
+        - pattern: "^renesas,sysc-(r8a73a4|r8a7740|rmobile|sh73a0)$"
+        - enum:
+            - renesas,imr-lx4
+            - renesas,mtu2-r7s72100
+
+        # None SoC component compatibles
+        #
+        # Compatibles with the Renesas vendor prefix that do not relate to any SoC
+        # component are OK. New compatibles are allowed.
+        - enum:
+            - renesas,smp-sram
+
+        # Do not fail compatibles not matching the select pattern
+        #
+        # Some SoC components in addition to a Renesas compatible list
+        # compatibles not related to Renesas. The select pattern for this
+        # schema hits all compatibles that have at lest one Renesas compatible
+        # and try to validate all values in that compatible array, allow all
+        # that don't match the schema select pattern. For example,
+        #
+        #   compatible = "renesas,r9a07g044-mali", "arm,mali-bifrost";
+        - pattern: "^(?!renesas,.+-.+).+$"
+
+additionalProperties: true
diff --git a/Documentation/devicetree/bindings/soc/renesas/renesas.yaml b/Documentation/devicetree/bindings/soc/renesas/renesas.yaml
index 16ca3ff7b1ae..c1ce4da2dc32 100644
--- a/Documentation/devicetree/bindings/soc/renesas/renesas.yaml
+++ b/Documentation/devicetree/bindings/soc/renesas/renesas.yaml
@@ -348,12 +348,25 @@ properties:
               - renesas,white-hawk-cpu # White Hawk CPU board (RTP8A779G0ASKB0FC0SA000)
           - const: renesas,r8a779g0
 
+      - description: R-Car V4H (R8A779G2)
+        items:
+          - enum:
+              - renesas,white-hawk-single # White Hawk Single board (RTP8A779G2ASKB0F10SA001)
+          - const: renesas,r8a779g2
+          - const: renesas,r8a779g0
+
       - items:
           - enum:
               - renesas,white-hawk-breakout # White Hawk BreakOut board (RTP8A779G0ASKB0SB0SA000)
           - const: renesas,white-hawk-cpu
           - const: renesas,r8a779g0
 
+      - description: R-Car V4M (R8A779H0)
+        items:
+          - enum:
+              - renesas,gray-hawk-single # Gray Hawk Single board (RTP8A779H0ASKB0F10S)
+          - const: renesas,r8a779h0
+
       - description: R-Car H3e (R8A779M0)
         items:
           - enum:
@@ -475,12 +488,6 @@ properties:
               - renesas,r9a07g054l2 # Dual Cortex-A55 RZ/V2L
           - const: renesas,r9a07g054
 
-      - description: RZ/V2M (R9A09G011)
-        items:
-          - enum:
-              - renesas,rzv2mevk2   # RZ/V2M Eval Board v2.0
-          - const: renesas,r9a09g011
-
       - description: RZ/G3S (R9A08G045)
         items:
           - enum:
@@ -500,6 +507,12 @@ properties:
           - const: renesas,r9a08g045s33 # PCIe support
           - const: renesas,r9a08g045
 
+      - description: RZ/V2M (R9A09G011)
+        items:
+          - enum:
+              - renesas,rzv2mevk2   # RZ/V2M Eval Board v2.0
+          - const: renesas,r9a09g011
+
 additionalProperties: true
 
 ...
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index 9793ea6f0fe6..0b87c266760c 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -22,12 +22,15 @@ properties:
               - rockchip,rk3568-usb2phy-grf
               - rockchip,rk3588-bigcore0-grf
               - rockchip,rk3588-bigcore1-grf
+              - rockchip,rk3588-hdptxphy-grf
               - rockchip,rk3588-ioc
               - rockchip,rk3588-php-grf
               - rockchip,rk3588-pipe-phy-grf
               - rockchip,rk3588-sys-grf
               - rockchip,rk3588-pcie3-phy-grf
               - rockchip,rk3588-pcie3-pipe-grf
+              - rockchip,rk3588-usb-grf
+              - rockchip,rk3588-usbdpphy-grf
               - rockchip,rk3588-vo-grf
               - rockchip,rk3588-vop-grf
               - rockchip,rv1108-usbgrf
@@ -66,6 +69,9 @@ properties:
   reg:
     maxItems: 1
 
+  clocks:
+    maxItems: 1
+
   "#address-cells":
     const: 1
 
@@ -248,6 +254,22 @@ allOf:
 
           unevaluatedProperties: false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - rockchip,rk3588-vo-grf
+
+    then:
+      required:
+        - clocks
+
+    else:
+      properties:
+        clocks: false
+
+
 examples:
   - |
     #include <dt-bindings/clock/rk3399-cru.h>
diff --git a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
index 1794e3799f21..c0c6ce8fc786 100644
--- a/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
+++ b/Documentation/devicetree/bindings/soc/samsung/samsung,exynos-sysreg.yaml
@@ -72,6 +72,8 @@ allOf:
         compatible:
           contains:
             enum:
+              - google,gs101-peric0-sysreg
+              - google,gs101-peric1-sysreg
               - samsung,exynos850-cmgp-sysreg
               - samsung,exynos850-peri-sysreg
               - samsung,exynos850-sysreg
diff --git a/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml b/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
index d4c0fe1fe435..131aba5ed9f4 100644
--- a/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
+++ b/Documentation/devicetree/bindings/soc/xilinx/xilinx.yaml
@@ -117,20 +117,70 @@ properties:
           - const: xlnx,zynqmp
 
       - description: Xilinx Kria SOMs
+        minItems: 3
         items:
-          - const: xlnx,zynqmp-sm-k26-rev1
-          - const: xlnx,zynqmp-sm-k26-revB
-          - const: xlnx,zynqmp-sm-k26-revA
-          - const: xlnx,zynqmp-sm-k26
-          - const: xlnx,zynqmp
+          enum:
+            - xlnx,zynqmp-sm-k26-rev2
+            - xlnx,zynqmp-sm-k26-rev1
+            - xlnx,zynqmp-sm-k26-revB
+            - xlnx,zynqmp-sm-k26-revA
+            - xlnx,zynqmp-sm-k26
+            - xlnx,zynqmp
+        allOf:
+          - contains:
+              const: xlnx,zynqmp
+          - contains:
+              const: xlnx,zynqmp-sm-k26
 
       - description: Xilinx Kria SOMs (starter)
+        minItems: 3
         items:
-          - const: xlnx,zynqmp-smk-k26-rev1
-          - const: xlnx,zynqmp-smk-k26-revB
-          - const: xlnx,zynqmp-smk-k26-revA
-          - const: xlnx,zynqmp-smk-k26
-          - const: xlnx,zynqmp
+          enum:
+            - xlnx,zynqmp-smk-k26-rev2
+            - xlnx,zynqmp-smk-k26-rev1
+            - xlnx,zynqmp-smk-k26-revB
+            - xlnx,zynqmp-smk-k26-revA
+            - xlnx,zynqmp-smk-k26
+            - xlnx,zynqmp
+        allOf:
+          - contains:
+              const: xlnx,zynqmp
+          - contains:
+              const: xlnx,zynqmp-smk-k26
+
+      - description: Xilinx Kria SOM KV260 revA/Y/Z
+        minItems: 3
+        items:
+          enum:
+            - xlnx,zynqmp-sk-kv260-revA
+            - xlnx,zynqmp-sk-kv260-revY
+            - xlnx,zynqmp-sk-kv260-revZ
+            - xlnx,zynqmp-sk-kv260
+            - xlnx,zynqmp
+        allOf:
+          - contains:
+              const: xlnx,zynqmp-sk-kv260-revA
+          - contains:
+              const: xlnx,zynqmp-sk-kv260
+          - contains:
+              const: xlnx,zynqmp
+
+      - description: Xilinx Kria SOM KV260 rev2/1/B
+        minItems: 3
+        items:
+          enum:
+            - xlnx,zynqmp-sk-kv260-rev2
+            - xlnx,zynqmp-sk-kv260-rev1
+            - xlnx,zynqmp-sk-kv260-revB
+            - xlnx,zynqmp-sk-kv260
+            - xlnx,zynqmp
+        allOf:
+          - contains:
+              const: xlnx,zynqmp-sk-kv260-revB
+          - contains:
+              const: xlnx,zynqmp-sk-kv260
+          - contains:
+              const: xlnx,zynqmp
 
       - description: AMD MicroBlaze V (QEMU)
         items:
diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
index 8108c564dd78..aa32dc950e72 100644
--- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-spdif.yaml
@@ -22,6 +22,7 @@ properties:
       - const: allwinner,sun6i-a31-spdif
       - const: allwinner,sun8i-h3-spdif
       - const: allwinner,sun50i-h6-spdif
+      - const: allwinner,sun50i-h616-spdif
       - items:
           - const: allwinner,sun8i-a83t-spdif
           - const: allwinner,sun8i-h3-spdif
@@ -62,6 +63,8 @@ allOf:
             enum:
               - allwinner,sun6i-a31-spdif
               - allwinner,sun8i-h3-spdif
+              - allwinner,sun50i-h6-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       required:
@@ -73,7 +76,7 @@ allOf:
           contains:
             enum:
               - allwinner,sun8i-h3-spdif
-              - allwinner,sun50i-h6-spdif
+              - allwinner,sun50i-h616-spdif
 
     then:
       properties:
diff --git a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
index ec4b6e547ca6..cdcd7c6f21eb 100644
--- a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
+++ b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Google SC7280-Herobrine ASoC sound card driver
 
 maintainers:
-  - Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
   - Judy Hsiao <judyhsiao@chromium.org>
 
 description:
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
index c29d7942915c..241d20f3aad0 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max9808x.yaml
@@ -64,7 +64,7 @@ examples:
     #include <dt-bindings/clock/tegra30-car.h>
     #include <dt-bindings/soc/tegra-pmc.h>
     sound {
-        compatible = "lge,tegra-audio-max98089-p895",
+        compatible = "lg,tegra-audio-max98089-p895",
                      "nvidia,tegra-audio-max98089";
         nvidia,model = "LG Optimus Vu MAX98089";
 
diff --git a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
index a1c96985951f..cf07b8f787a6 100644
--- a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
+++ b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
@@ -56,7 +56,7 @@ properties:
   ranges: true
 
 patternProperties:
-  "^sram@[a-z0-9]+":
+  "^sram@[a-f0-9]+":
     $ref: /schemas/sram/sram.yaml#
     unevaluatedProperties: false
 
diff --git a/Documentation/devicetree/bindings/tpm/tpm-common.yaml b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
index 90390624a8be..3c1241b2a43f 100644
--- a/Documentation/devicetree/bindings/tpm/tpm-common.yaml
+++ b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
@@ -42,7 +42,7 @@ properties:
 
   resets:
     description: Reset controller to reset the TPM
-    $ref: /schemas/types.yaml#/definitions/phandle
+    maxItems: 1
 
   reset-gpios:
     description: Output GPIO pin to reset the TPM
diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
index 88cc1e3a0c88..b2b509b3944d 100644
--- a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
@@ -55,9 +55,12 @@ properties:
 
   samsung,sysreg:
     $ref: /schemas/types.yaml#/definitions/phandle-array
-    description: Should be phandle/offset pair. The phandle to the syscon node
-                 which indicates the FSYSx sysreg interface and the offset of
-                 the control register for UFS io coherency setting.
+    items:
+      - items:
+          - description: phandle to FSYSx sysreg node
+          - description: offset of the control register for UFS io coherency setting
+    description:
+      Phandle and offset to the FSYSx sysreg for UFS io coherency setting.
 
   dma-coherent: true
 
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
index bb373eb025a5..00f87a558c7d 100644
--- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx SuperSpeed DWC3 USB SoC controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index 6d4cfd943f58..445183d9d6db 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -16,8 +16,9 @@ description:
   USB 2.0 traffic.
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
   - Michal Simek <michal.simek@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
index 868dffe314bc..a7f75fe36665 100644
--- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
+++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Xilinx udc controller
 
 maintainers:
-  - Piyush Mehta <piyush.mehta@amd.com>
+  - Mubin Sayyed <mubin.sayyed@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 1a0dc04f1db4..d371eb572164 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -39,6 +39,8 @@ patternProperties:
     description: ShenZhen Asia Better Technology Ltd.
   "^acbel,.*":
     description: Acbel Polytech Inc.
+  "^acelink,.*":
+    description: Acelink Technology Co., Ltd.
   "^acer,.*":
     description: Acer Inc.
   "^acme,.*":
@@ -500,6 +502,8 @@ patternProperties:
     description: FocalTech Systems Co.,Ltd
   "^forlinx,.*":
     description: Baoding Forlinx Embedded Technology Co., Ltd.
+  "^freebox,.*":
+    description: Freebox SAS
   "^freecom,.*":
     description: Freecom Gmbh
   "^frida,.*":
@@ -719,6 +723,8 @@ patternProperties:
     description: JetHome (IP Sokolov P.A.)
   "^jianda,.*":
     description: Jiandangjing Technology Co., Ltd.
+  "^jide,.*":
+    description: Jide Tech
   "^joz,.*":
     description: JOZ BV
   "^kam,.*":
@@ -1484,6 +1490,8 @@ patternProperties:
     description: Ufi Space Co., Ltd.
   "^ugoos,.*":
     description: Ugoos Industrial Co., Ltd.
+  "^uni-t,.*":
+    description: Uni-Trend Technology (China) Co., Ltd.
   "^uniwest,.*":
     description: United Western Technologies Corp (UniWest)
   "^upisemi,.*":
diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst
index e3d593841aa7..ea8d16600e16 100644
--- a/Documentation/driver-api/dpll.rst
+++ b/Documentation/driver-api/dpll.rst
@@ -545,7 +545,7 @@ In such scenario, dpll device input signal shall be also configurable
 to drive dpll with signal recovered from the PHY netdevice.
 This is done by exposing a pin to the netdevice - attaching pin to the
 netdevice itself with
-``netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``.
+``dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``.
 Exposed pin id handle ``DPLL_A_PIN_ID`` is then identifiable by the user
 as it is attached to rtnetlink respond to get ``RTM_NEWLINK`` command in
 nested attribute ``IFLA_DPLL_PIN``.
diff --git a/Documentation/filesystems/files.rst b/Documentation/filesystems/files.rst
index 9e38e4c221ca..eb770f891b27 100644
--- a/Documentation/filesystems/files.rst
+++ b/Documentation/filesystems/files.rst
@@ -116,7 +116,7 @@ before and after the reference count increment. This pattern can be seen
 in get_file_rcu() and __files_get_rcu().
 
 In addition, it isn't possible to access or check fields in struct file
-without first aqcuiring a reference on it under rcu lookup. Not doing
+without first acquiring a reference on it under rcu lookup. Not doing
 that was always very dodgy and it was only usable for non-pointer data
 in struct file. With SLAB_TYPESAFE_BY_RCU it is necessary that callers
 either first acquire a reference or they must hold the files_lock of the
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index e86b886b64d0..04eaab01314b 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -338,11 +338,14 @@ Supported modes
 
 Currently, the following pairs of encryption modes are supported:
 
-- AES-256-XTS for contents and AES-256-CTS-CBC for filenames
+- AES-256-XTS for contents and AES-256-CBC-CTS for filenames
 - AES-256-XTS for contents and AES-256-HCTR2 for filenames
 - Adiantum for both contents and filenames
-- AES-128-CBC-ESSIV for contents and AES-128-CTS-CBC for filenames
-- SM4-XTS for contents and SM4-CTS-CBC for filenames
+- AES-128-CBC-ESSIV for contents and AES-128-CBC-CTS for filenames
+- SM4-XTS for contents and SM4-CBC-CTS for filenames
+
+Note: in the API, "CBC" means CBC-ESSIV, and "CTS" means CBC-CTS.
+So, for example, FSCRYPT_MODE_AES_256_CTS means AES-256-CBC-CTS.
 
 Authenticated encryption modes are not currently supported because of
 the difficulty of dealing with ciphertext expansion.  Therefore,
@@ -351,11 +354,11 @@ contents encryption uses a block cipher in `XTS mode
 `CBC-ESSIV mode
 <https://en.wikipedia.org/wiki/Disk_encryption_theory#Encrypted_salt-sector_initialization_vector_(ESSIV)>`_,
 or a wide-block cipher.  Filenames encryption uses a
-block cipher in `CTS-CBC mode
+block cipher in `CBC-CTS mode
 <https://en.wikipedia.org/wiki/Ciphertext_stealing>`_ or a wide-block
 cipher.
 
-The (AES-256-XTS, AES-256-CTS-CBC) pair is the recommended default.
+The (AES-256-XTS, AES-256-CBC-CTS) pair is the recommended default.
 It is also the only option that is *guaranteed* to always be supported
 if the kernel supports fscrypt at all; see `Kernel config options`_.
 
@@ -364,7 +367,7 @@ upgrades the filenames encryption to use a wide-block cipher.  (A
 *wide-block cipher*, also called a tweakable super-pseudorandom
 permutation, has the property that changing one bit scrambles the
 entire result.)  As described in `Filenames encryption`_, a wide-block
-cipher is the ideal mode for the problem domain, though CTS-CBC is the
+cipher is the ideal mode for the problem domain, though CBC-CTS is the
 "least bad" choice among the alternatives.  For more information about
 HCTR2, see `the HCTR2 paper <https://eprint.iacr.org/2021/1441.pdf>`_.
 
@@ -375,13 +378,13 @@ the work is done by XChaCha12, which is much faster than AES when AES
 acceleration is unavailable.  For more information about Adiantum, see
 `the Adiantum paper <https://eprint.iacr.org/2018/720.pdf>`_.
 
-The (AES-128-CBC-ESSIV, AES-128-CTS-CBC) pair exists only to support
+The (AES-128-CBC-ESSIV, AES-128-CBC-CTS) pair exists only to support
 systems whose only form of AES acceleration is an off-CPU crypto
 accelerator such as CAAM or CESA that does not support XTS.
 
 The remaining mode pairs are the "national pride ciphers":
 
-- (SM4-XTS, SM4-CTS-CBC)
+- (SM4-XTS, SM4-CBC-CTS)
 
 Generally speaking, these ciphers aren't "bad" per se, but they
 receive limited security review compared to the usual choices such as
@@ -393,7 +396,7 @@ Kernel config options
 
 Enabling fscrypt support (CONFIG_FS_ENCRYPTION) automatically pulls in
 only the basic support from the crypto API needed to use AES-256-XTS
-and AES-256-CTS-CBC encryption.  For optimal performance, it is
+and AES-256-CBC-CTS encryption.  For optimal performance, it is
 strongly recommended to also enable any available platform-specific
 kconfig options that provide acceleration for the algorithm(s) you
 wish to use.  Support for any "non-default" encryption modes typically
@@ -407,7 +410,7 @@ kernel crypto API (see `Inline encryption support`_); in that case,
 the file contents mode doesn't need to supported in the kernel crypto
 API, but the filenames mode still does.
 
-- AES-256-XTS and AES-256-CTS-CBC
+- AES-256-XTS and AES-256-CBC-CTS
     - Recommended:
         - arm64: CONFIG_CRYPTO_AES_ARM64_CE_BLK
         - x86: CONFIG_CRYPTO_AES_NI_INTEL
@@ -433,7 +436,7 @@ API, but the filenames mode still does.
         - x86: CONFIG_CRYPTO_NHPOLY1305_SSE2
         - x86: CONFIG_CRYPTO_NHPOLY1305_AVX2
 
-- AES-128-CBC-ESSIV and AES-128-CTS-CBC:
+- AES-128-CBC-ESSIV and AES-128-CBC-CTS:
     - Mandatory:
         - CONFIG_CRYPTO_ESSIV
         - CONFIG_CRYPTO_SHA256 or another SHA-256 implementation
@@ -521,7 +524,7 @@ alternatively has the file's nonce (for `DIRECT_KEY policies`_) or
 inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs.
 Thus, IV reuse is limited to within a single directory.
 
-With CTS-CBC, the IV reuse means that when the plaintext filenames share a
+With CBC-CTS, the IV reuse means that when the plaintext filenames share a
 common prefix at least as long as the cipher block size (16 bytes for AES), the
 corresponding encrypted filenames will also share a common prefix.  This is
 undesirable.  Adiantum and HCTR2 do not have this weakness, as they are
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index e18bc5ae3b35..0ea1e44fa028 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -98,7 +98,6 @@ Documentation for filesystem implementations.
    isofs
    nilfs2
    nfs/index
-   ntfs
    ntfs3
    ocfs2
    ocfs2-online-filecheck
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index d5bf4b6b7509..e664061ed55d 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -29,7 +29,7 @@ prototypes::
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 	struct vfsmount *(*d_automount)(struct path *path);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *);
+	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 
 locking rules:
 
diff --git a/Documentation/filesystems/ntfs.rst b/Documentation/filesystems/ntfs.rst
deleted file mode 100644
index 5bb093a26485..000000000000
--- a/Documentation/filesystems/ntfs.rst
+++ /dev/null
@@ -1,466 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-================================
-The Linux NTFS filesystem driver
-================================
-
-
-.. Table of contents
-
-   - Overview
-   - Web site
-   - Features
-   - Supported mount options
-   - Known bugs and (mis-)features
-   - Using NTFS volume and stripe sets
-     - The Device-Mapper driver
-     - The Software RAID / MD driver
-     - Limitations when using the MD driver
-
-
-Overview
-========
-
-Linux-NTFS comes with a number of user-space programs known as ntfsprogs.
-These include mkntfs, a full-featured ntfs filesystem format utility,
-ntfsundelete used for recovering files that were unintentionally deleted
-from an NTFS volume and ntfsresize which is used to resize an NTFS partition.
-See the web site for more information.
-
-To mount an NTFS 1.2/3.x (Windows NT4/2000/XP/2003) volume, use the file
-system type 'ntfs'.  The driver currently supports read-only mode (with no
-fault-tolerance, encryption or journalling) and very limited, but safe, write
-support.
-
-For fault tolerance and raid support (i.e. volume and stripe sets), you can
-use the kernel's Software RAID / MD driver.  See section "Using Software RAID
-with NTFS" for details.
-
-
-Web site
-========
-
-There is plenty of additional information on the linux-ntfs web site
-at http://www.linux-ntfs.org/
-
-The web site has a lot of additional information, such as a comprehensive
-FAQ, documentation on the NTFS on-disk format, information on the Linux-NTFS
-userspace utilities, etc.
-
-
-Features
-========
-
-- This is a complete rewrite of the NTFS driver that used to be in the 2.4 and
-  earlier kernels.  This new driver implements NTFS read support and is
-  functionally equivalent to the old ntfs driver and it also implements limited
-  write support.  The biggest limitation at present is that files/directories
-  cannot be created or deleted.  See below for the list of write features that
-  are so far supported.  Another limitation is that writing to compressed files
-  is not implemented at all.  Also, neither read nor write access to encrypted
-  files is so far implemented.
-- The new driver has full support for sparse files on NTFS 3.x volumes which
-  the old driver isn't happy with.
-- The new driver supports execution of binaries due to mmap() now being
-  supported.
-- The new driver supports loopback mounting of files on NTFS which is used by
-  some Linux distributions to enable the user to run Linux from an NTFS
-  partition by creating a large file while in Windows and then loopback
-  mounting the file while in Linux and creating a Linux filesystem on it that
-  is used to install Linux on it.
-- A comparison of the two drivers using::
-
-	time find . -type f -exec md5sum "{}" \;
-
-  run three times in sequence with each driver (after a reboot) on a 1.4GiB
-  NTFS partition, showed the new driver to be 20% faster in total time elapsed
-  (from 9:43 minutes on average down to 7:53).  The time spent in user space
-  was unchanged but the time spent in the kernel was decreased by a factor of
-  2.5 (from 85 CPU seconds down to 33).
-- The driver does not support short file names in general.  For backwards
-  compatibility, we implement access to files using their short file names if
-  they exist.  The driver will not create short file names however, and a
-  rename will discard any existing short file name.
-- The new driver supports exporting of mounted NTFS volumes via NFS.
-- The new driver supports async io (aio).
-- The new driver supports fsync(2), fdatasync(2), and msync(2).
-- The new driver supports readv(2) and writev(2).
-- The new driver supports access time updates (including mtime and ctime).
-- The new driver supports truncate(2) and open(2) with O_TRUNC.  But at present
-  only very limited support for highly fragmented files, i.e. ones which have
-  their data attribute split across multiple extents, is included.  Another
-  limitation is that at present truncate(2) will never create sparse files,
-  since to mark a file sparse we need to modify the directory entry for the
-  file and we do not implement directory modifications yet.
-- The new driver supports write(2) which can both overwrite existing data and
-  extend the file size so that you can write beyond the existing data.  Also,
-  writing into sparse regions is supported and the holes are filled in with
-  clusters.  But at present only limited support for highly fragmented files,
-  i.e. ones which have their data attribute split across multiple extents, is
-  included.  Another limitation is that write(2) will never create sparse
-  files, since to mark a file sparse we need to modify the directory entry for
-  the file and we do not implement directory modifications yet.
-
-Supported mount options
-=======================
-
-In addition to the generic mount options described by the manual page for the
-mount command (man 8 mount, also see man 5 fstab), the NTFS driver supports the
-following mount options:
-
-======================= =======================================================
-iocharset=name		Deprecated option.  Still supported but please use
-			nls=name in the future.  See description for nls=name.
-
-nls=name		Character set to use when returning file names.
-			Unlike VFAT, NTFS suppresses names that contain
-			unconvertible characters.  Note that most character
-			sets contain insufficient characters to represent all
-			possible Unicode characters that can exist on NTFS.
-			To be sure you are not missing any files, you are
-			advised to use nls=utf8 which is capable of
-			representing all Unicode characters.
-
-utf8=<bool>		Option no longer supported.  Currently mapped to
-			nls=utf8 but please use nls=utf8 in the future and
-			make sure utf8 is compiled either as module or into
-			the kernel.  See description for nls=name.
-
-uid=
-gid=
-umask=			Provide default owner, group, and access mode mask.
-			These options work as documented in mount(8).  By
-			default, the files/directories are owned by root and
-			he/she has read and write permissions, as well as
-			browse permission for directories.  No one else has any
-			access permissions.  I.e. the mode on all files is by
-			default rw------- and for directories rwx------, a
-			consequence of the default fmask=0177 and dmask=0077.
-			Using a umask of zero will grant all permissions to
-			everyone, i.e. all files and directories will have mode
-			rwxrwxrwx.
-
-fmask=
-dmask=			Instead of specifying umask which applies both to
-			files and directories, fmask applies only to files and
-			dmask only to directories.
-
-sloppy=<BOOL>		If sloppy is specified, ignore unknown mount options.
-			Otherwise the default behaviour is to abort mount if
-			any unknown options are found.
-
-show_sys_files=<BOOL>	If show_sys_files is specified, show the system files
-			in directory listings.  Otherwise the default behaviour
-			is to hide the system files.
-			Note that even when show_sys_files is specified, "$MFT"
-			will not be visible due to bugs/mis-features in glibc.
-			Further, note that irrespective of show_sys_files, all
-			files are accessible by name, i.e. you can always do
-			"ls -l \$UpCase" for example to specifically show the
-			system file containing the Unicode upcase table.
-
-case_sensitive=<BOOL>	If case_sensitive is specified, treat all file names as
-			case sensitive and create file names in the POSIX
-			namespace.  Otherwise the default behaviour is to treat
-			file names as case insensitive and to create file names
-			in the WIN32/LONG name space.  Note, the Linux NTFS
-			driver will never create short file names and will
-			remove them on rename/delete of the corresponding long
-			file name.
-			Note that files remain accessible via their short file
-			name, if it exists.  If case_sensitive, you will need
-			to provide the correct case of the short file name.
-
-disable_sparse=<BOOL>	If disable_sparse is specified, creation of sparse
-			regions, i.e. holes, inside files is disabled for the
-			volume (for the duration of this mount only).  By
-			default, creation of sparse regions is enabled, which
-			is consistent with the behaviour of traditional Unix
-			filesystems.
-
-errors=opt		What to do when critical filesystem errors are found.
-			Following values can be used for "opt":
-
-			  ========  =========================================
-			  continue  DEFAULT, try to clean-up as much as
-				    possible, e.g. marking a corrupt inode as
-				    bad so it is no longer accessed, and then
-				    continue.
-			  recover   At present only supported is recovery of
-				    the boot sector from the backup copy.
-				    If read-only mount, the recovery is done
-				    in memory only and not written to disk.
-			  ========  =========================================
-
-			Note that the options are additive, i.e. specifying::
-
-			   errors=continue,errors=recover
-
-			means the driver will attempt to recover and if that
-			fails it will clean-up as much as possible and
-			continue.
-
-mft_zone_multiplier=	Set the MFT zone multiplier for the volume (this
-			setting is not persistent across mounts and can be
-			changed from mount to mount but cannot be changed on
-			remount).  Values of 1 to 4 are allowed, 1 being the
-			default.  The MFT zone multiplier determines how much
-			space is reserved for the MFT on the volume.  If all
-			other space is used up, then the MFT zone will be
-			shrunk dynamically, so this has no impact on the
-			amount of free space.  However, it can have an impact
-			on performance by affecting fragmentation of the MFT.
-			In general use the default.  If you have a lot of small
-			files then use a higher value.  The values have the
-			following meaning:
-
-			      =====	    =================================
-			      Value	     MFT zone size (% of volume size)
-			      =====	    =================================
-				1		12.5%
-				2		25%
-				3		37.5%
-				4		50%
-			      =====	    =================================
-
-			Note this option is irrelevant for read-only mounts.
-======================= =======================================================
-
-
-Known bugs and (mis-)features
-=============================
-
-- The link count on each directory inode entry is set to 1, due to Linux not
-  supporting directory hard links.  This may well confuse some user space
-  applications, since the directory names will have the same inode numbers.
-  This also speeds up ntfs_read_inode() immensely.  And we haven't found any
-  problems with this approach so far.  If you find a problem with this, please
-  let us know.
-
-
-Please send bug reports/comments/feedback/abuse to the Linux-NTFS development
-list at sourceforge: linux-ntfs-dev@lists.sourceforge.net
-
-
-Using NTFS volume and stripe sets
-=================================
-
-For support of volume and stripe sets, you can either use the kernel's
-Device-Mapper driver or the kernel's Software RAID / MD driver.  The former is
-the recommended one to use for linear raid.  But the latter is required for
-raid level 5.  For striping and mirroring, either driver should work fine.
-
-
-The Device-Mapper driver
-------------------------
-
-You will need to create a table of the components of the volume/stripe set and
-how they fit together and load this into the kernel using the dmsetup utility
-(see man 8 dmsetup).
-
-Linear volume sets, i.e. linear raid, has been tested and works fine.  Even
-though untested, there is no reason why stripe sets, i.e. raid level 0, and
-mirrors, i.e. raid level 1 should not work, too.  Stripes with parity, i.e.
-raid level 5, unfortunately cannot work yet because the current version of the
-Device-Mapper driver does not support raid level 5.  You may be able to use the
-Software RAID / MD driver for raid level 5, see the next section for details.
-
-To create the table describing your volume you will need to know each of its
-components and their sizes in sectors, i.e. multiples of 512-byte blocks.
-
-For NT4 fault tolerant volumes you can obtain the sizes using fdisk.  So for
-example if one of your partitions is /dev/hda2 you would do::
-
-    $ fdisk -ul /dev/hda
-
-    Disk /dev/hda: 81.9 GB, 81964302336 bytes
-    255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors
-    Units = sectors of 1 * 512 = 512 bytes
-
-	Device Boot      Start         End      Blocks   Id  System
-	/dev/hda1   *          63     4209029     2104483+  83  Linux
-	/dev/hda2         4209030    37768814    16779892+  86  NTFS
-	/dev/hda3        37768815    46170809     4200997+  83  Linux
-
-And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 =
-33559785 sectors.
-
-For Win2k and later dynamic disks, you can for example use the ldminfo utility
-which is part of the Linux LDM tools (the latest version at the time of
-writing is linux-ldm-0.0.8.tar.bz2).  You can download it from:
-
-	http://www.linux-ntfs.org/
-
-Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go
-into it (cd linux-ldm-0.0.8) and change to the test directory (cd test).  You
-will find the precompiled (i386) ldminfo utility there.  NOTE: You will not be
-able to compile this yourself easily so use the binary version!
-
-Then you would use ldminfo in dump mode to obtain the necessary information::
-
-    $ ./ldminfo --dump /dev/hda
-
-This would dump the LDM database found on /dev/hda which describes all of your
-dynamic disks and all the volumes on them.  At the bottom you will see the
-VOLUME DEFINITIONS section which is all you really need.  You may need to look
-further above to determine which of the disks in the volume definitions is
-which device in Linux.  Hint: Run ldminfo on each of your dynamic disks and
-look at the Disk Id close to the top of the output for each (the PRIVATE HEADER
-section).  You can then find these Disk Ids in the VBLK DATABASE section in the
-<Disk> components where you will get the LDM Name for the disk that is found in
-the VOLUME DEFINITIONS section.
-
-Note you will also need to enable the LDM driver in the Linux kernel.  If your
-distribution did not enable it, you will need to recompile the kernel with it
-enabled.  This will create the LDM partitions on each device at boot time.  You
-would then use those devices (for /dev/hda they would be /dev/hda1, 2, 3, etc)
-in the Device-Mapper table.
-
-You can also bypass using the LDM driver by using the main device (e.g.
-/dev/hda) and then using the offsets of the LDM partitions into this device as
-the "Start sector of device" when creating the table.  Once again ldminfo would
-give you the correct information to do this.
-
-Assuming you know all your devices and their sizes things are easy.
-
-For a linear raid the table would look like this (note all values are in
-512-byte sectors)::
-
-    # Offset into	Size of this	Raid type	Device		Start sector
-    # volume	device						of device
-    0		1028161		linear		/dev/hda1	0
-    1028161		3903762		linear		/dev/hdb2	0
-    4931923		2103211		linear		/dev/hdc1	0
-
-For a striped volume, i.e. raid level 0, you will need to know the chunk size
-you used when creating the volume.  Windows uses 64kiB as the default, so it
-will probably be this unless you changes the defaults when creating the array.
-
-For a raid level 0 the table would look like this (note all values are in
-512-byte sectors)::
-
-    # Offset   Size	    Raid     Number   Chunk  1st        Start	2nd	  Start
-    # into     of the   type     of	      size   Device	in	Device	  in
-    # volume   volume	     stripes			device		  device
-    0	   2056320  striped  2	      128    /dev/hda1	0	/dev/hdb1 0
-
-If there are more than two devices, just add each of them to the end of the
-line.
-
-Finally, for a mirrored volume, i.e. raid level 1, the table would look like
-this (note all values are in 512-byte sectors)::
-
-    # Ofs Size   Raid   Log  Number Region Should Number Source  Start Target Start
-    # in  of the type   type of log size   sync?  of     Device  in    Device in
-    # vol volume		 params		     mirrors	     Device	  Device
-    0    2056320 mirror core 2	16     nosync 2	   /dev/hda1 0   /dev/hdb1 0
-
-If you are mirroring to multiple devices you can specify further targets at the
-end of the line.
-
-Note the "Should sync?" parameter "nosync" means that the two mirrors are
-already in sync which will be the case on a clean shutdown of Windows.  If the
-mirrors are not clean, you can specify the "sync" option instead of "nosync"
-and the Device-Mapper driver will then copy the entirety of the "Source Device"
-to the "Target Device" or if you specified multiple target devices to all of
-them.
-
-Once you have your table, save it in a file somewhere (e.g. /etc/ntfsvolume1),
-and hand it over to dmsetup to work with, like so::
-
-    $ dmsetup create myvolume1 /etc/ntfsvolume1
-
-You can obviously replace "myvolume1" with whatever name you like.
-
-If it all worked, you will now have the device /dev/device-mapper/myvolume1
-which you can then just use as an argument to the mount command as usual to
-mount the ntfs volume.  For example::
-
-    $ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1
-
-(You need to create the directory /mnt/myvol1 first and of course you can use
-anything you like instead of /mnt/myvol1 as long as it is an existing
-directory.)
-
-It is advisable to do the mount read-only to see if the volume has been setup
-correctly to avoid the possibility of causing damage to the data on the ntfs
-volume.
-
-
-The Software RAID / MD driver
------------------------------
-
-An alternative to using the Device-Mapper driver is to use the kernel's
-Software RAID / MD driver.  For which you need to set up your /etc/raidtab
-appropriately (see man 5 raidtab).
-
-Linear volume sets, i.e. linear raid, as well as stripe sets, i.e. raid level
-0, have been tested and work fine (though see section "Limitations when using
-the MD driver with NTFS volumes" especially if you want to use linear raid).
-Even though untested, there is no reason why mirrors, i.e. raid level 1, and
-stripes with parity, i.e. raid level 5, should not work, too.
-
-You have to use the "persistent-superblock 0" option for each raid-disk in the
-NTFS volume/stripe you are configuring in /etc/raidtab as the persistent
-superblock used by the MD driver would damage the NTFS volume.
-
-Windows by default uses a stripe chunk size of 64k, so you probably want the
-"chunk-size 64k" option for each raid-disk, too.
-
-For example, if you have a stripe set consisting of two partitions /dev/hda5
-and /dev/hdb1 your /etc/raidtab would look like this::
-
-    raiddev /dev/md0
-	    raid-level	0
-	    nr-raid-disks	2
-	    nr-spare-disks	0
-	    persistent-superblock	0
-	    chunk-size	64k
-	    device		/dev/hda5
-	    raid-disk	0
-	    device		/dev/hdb1
-	    raid-disk	1
-
-For linear raid, just change the raid-level above to "raid-level linear", for
-mirrors, change it to "raid-level 1", and for stripe sets with parity, change
-it to "raid-level 5".
-
-Note for stripe sets with parity you will also need to tell the MD driver
-which parity algorithm to use by specifying the option "parity-algorithm
-which", where you need to replace "which" with the name of the algorithm to
-use (see man 5 raidtab for available algorithms) and you will have to try the
-different available algorithms until you find one that works.  Make sure you
-are working read-only when playing with this as you may damage your data
-otherwise.  If you find which algorithm works please let us know (email the
-linux-ntfs developers list linux-ntfs-dev@lists.sourceforge.net or drop in on
-IRC in channel #ntfs on the irc.freenode.net network) so we can update this
-documentation.
-
-Once the raidtab is setup, run for example raid0run -a to start all devices or
-raid0run /dev/md0 to start a particular md device, in this case /dev/md0.
-
-Then just use the mount command as usual to mount the ntfs volume using for
-example::
-
-    mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume
-
-It is advisable to do the mount read-only to see if the md volume has been
-setup correctly to avoid the possibility of causing damage to the data on the
-ntfs volume.
-
-
-Limitations when using the Software RAID / MD driver
------------------------------------------------------
-
-Using the md driver will not work properly if any of your NTFS partitions have
-an odd number of sectors.  This is especially important for linear raid as all
-data after the first partition with an odd number of sectors will be offset by
-one or more sectors so if you mount such a partition with write support you
-will cause massive damage to the data on the volume which will only become
-apparent when you try to use the volume again under Windows.
-
-So when using linear raid, make sure that all your partitions have an even
-number of sectors BEFORE attempting to use it.  You have been warned!
-
-Even better is to simply use the Device-Mapper for linear raid and then you do
-not have this problem with odd numbers of sectors.
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index eebcc0f9e2bc..6e903a903f8f 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -1264,7 +1264,7 @@ defined:
 		char *(*d_dname)(struct dentry *, char *, int);
 		struct vfsmount *(*d_automount)(struct path *);
 		int (*d_manage)(const struct path *, bool);
-		struct dentry *(*d_real)(struct dentry *, const struct inode *);
+		struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 	};
 
 ``d_revalidate``
@@ -1419,16 +1419,14 @@ defined:
 	the dentry being transited from.
 
 ``d_real``
-	overlay/union type filesystems implement this method to return
-	one of the underlying dentries hidden by the overlay.  It is
-	used in two different modes:
+	overlay/union type filesystems implement this method to return one
+	of the underlying dentries of a regular file hidden by the overlay.
 
-	Called from file_dentry() it returns the real dentry matching
-	the inode argument.  The real dentry may be from a lower layer
-	already copied up, but still referenced from the file.  This
-	mode is selected with a non-NULL inode argument.
+	The 'type' argument takes the values D_REAL_DATA or D_REAL_METADATA
+	for returning the real underlying dentry that refers to the inode
+	hosting the file's data or metadata respectively.
 
-	With NULL inode the topmost real underlying dentry is returned.
+	For non-regular files, the 'dentry' argument is returned.
 
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries.  Child dentries are basically like files in a
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 36e61783437c..9dfdc826618c 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -113,7 +113,6 @@ to ReStructured Text format, or are simply too old.
    :maxdepth: 1
 
    staging/index
-   RAS/ras
 
 
 Translations
diff --git a/Documentation/kbuild/Kconfig.recursion-issue-01 b/Documentation/kbuild/Kconfig.recursion-issue-01
index e8877db0461f..ac49836d8ecf 100644
--- a/Documentation/kbuild/Kconfig.recursion-issue-01
+++ b/Documentation/kbuild/Kconfig.recursion-issue-01
@@ -16,13 +16,13 @@
 # that are possible for CORE. So for example if CORE_BELL_A_ADVANCED is 'y',
 # CORE must be 'y' too.
 #
-#  * What influences CORE_BELL_A_ADVANCED ?
+#  * What influences CORE_BELL_A_ADVANCED?
 #
 # As the name implies CORE_BELL_A_ADVANCED is an advanced feature of
 # CORE_BELL_A so naturally it depends on CORE_BELL_A. So if CORE_BELL_A is 'y'
 # we know CORE_BELL_A_ADVANCED can be 'y' too.
 #
-#   * What influences CORE_BELL_A ?
+#   * What influences CORE_BELL_A?
 #
 # CORE_BELL_A depends on CORE, so CORE influences CORE_BELL_A.
 #
@@ -34,7 +34,7 @@
 # the "recursive dependency detected" error.
 #
 # Reading the Documentation/kbuild/Kconfig.recursion-issue-01 file it may be
-# obvious that an easy to solution to this problem should just be the removal
+# obvious that an easy solution to this problem should just be the removal
 # of the "select CORE" from CORE_BELL_A_ADVANCED as that is implicit already
 # since CORE_BELL_A depends on CORE. Recursive dependency issues are not always
 # so trivial to resolve, we provide another example below of practical
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index b14aed18065f..3dcc9ece272a 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -384,8 +384,6 @@ operations:
             - type
 
       dump:
-        pre: dpll-lock-dumpit
-        post: dpll-unlock-dumpit
         reply: *dev-attrs
 
     -
@@ -473,8 +471,6 @@ operations:
             - fractional-frequency-offset
 
       dump:
-        pre: dpll-lock-dumpit
-        post: dpll-unlock-dumpit
         request:
           attributes:
             - id
diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 1ad01d52a863..8e4d19adee8c 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -942,6 +942,10 @@ attribute-sets:
       -
         name: gro-ipv4-max-size
         type: u32
+      -
+        name: dpll-pin
+        type: nest
+        nested-attributes: link-dpll-pin-attrs
   -
     name: af-spec-attrs
     attributes:
@@ -1627,6 +1631,12 @@ attribute-sets:
       -
         name: used
         type: u8
+  -
+    name: link-dpll-pin-attrs
+    attributes:
+      -
+        name: id
+        type: u32
 
 sub-messages:
   -
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index e33ad2401ad7..562f46b41274 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using
 `devlink port function set roce` command.
 
 Users may also set the function as migratable using
-'devlink port function set migratable' command.
+`devlink port function set migratable` command.
 
 Users may also set the IPsec crypto capability of the function using
 `devlink port function set ipsec_crypto` command.
diff --git a/Documentation/networking/net_cachelines/inet_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst
index a2babd0d7954..595d7ef5fc8b 100644
--- a/Documentation/networking/net_cachelines/inet_sock.rst
+++ b/Documentation/networking/net_cachelines/inet_sock.rst
@@ -1,9 +1,9 @@
 .. SPDX-License-Identifier: GPL-2.0
 .. Copyright (C) 2023 Google LLC
 
-=====================================================
-inet_connection_sock struct fast path usage breakdown
-=====================================================
+==========================================
+inet_sock struct fast path usage breakdown
+==========================================
 
 Type                    Name                  fastpath_tx_access  fastpath_rx_access  comment
 ..struct                ..inet_sock                                                     
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index e75a53593bb9..dceb49d56a91 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -136,8 +136,8 @@ struct_netpoll_info*                npinfo                  -
 possible_net_t                      nd_net                  -                   read_mostly         (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish
 void*                               ml_priv                                                         
 enum_netdev_ml_priv_type            ml_priv_type                                                    
-struct_pcpu_lstats__percpu*         lstats                                                          
-struct_pcpu_sw_netstats__percpu*    tstats                                                          
+struct_pcpu_lstats__percpu*         lstats                  read_mostly                             dev_lstats_add()
+struct_pcpu_sw_netstats__percpu*    tstats                  read_mostly                             dev_sw_netstats_tx_add()
 struct_pcpu_dstats__percpu*         dstats                                                          
 struct_garp_port*                   garp_port                                                       
 struct_mrp_port*                    mrp_port                                                        
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 97d7a5c8e01c..1c154cbd1848 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -38,13 +38,13 @@ u32                           max_window              read_mostly         -
 u32                           mss_cache               read_mostly         read_mostly         tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx)
 u32                           window_clamp            read_mostly         read_write          tcp_rcv_space_adjust,__tcp_select_window
 u32                           rcv_ssthresh            read_mostly         -                   __tcp_select_window
-u82                           scaling_ratio                                                   
+u8                            scaling_ratio           read_mostly         read_mostly         tcp_win_from_space
 struct                        tcp_rack                                                        
 u16                           advmss                  -                   read_mostly         tcp_rcv_space_adjust
 u8                            compressed_ack                                                  
 u8:2                          dup_ack_counter                                                 
 u8:1                          tlp_retrans                                                     
-u8:1                          tcp_usec_ts                                                     
+u8:1                          tcp_usec_ts             read_mostly         read_mostly
 u32                           chrono_start            read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u32[3]                        chrono_stat             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u8:2                          chrono_type             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 50b3d1cb1115..c78ecc1e176f 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
 GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  11.0.0           clang --version
-Rust (optional)        1.74.1           rustc --version
+Rust (optional)        1.76.0           rustc --version
 bindgen (optional)     0.65.1           bindgen --version
 GNU make               3.82             make --version
 bash                   4.2              bash --version
diff --git a/Documentation/process/cve.rst b/Documentation/process/cve.rst
new file mode 100644
index 000000000000..5e2753eff729
--- /dev/null
+++ b/Documentation/process/cve.rst
@@ -0,0 +1,121 @@
+====
+CVEs
+====
+
+Common Vulnerabilities and Exposure (CVE®) numbers were developed as an
+unambiguous way to identify, define, and catalog publicly disclosed
+security vulnerabilities.  Over time, their usefulness has declined with
+regards to the kernel project, and CVE numbers were very often assigned
+in inappropriate ways and for inappropriate reasons.  Because of this,
+the kernel development community has tended to avoid them.  However, the
+combination of continuing pressure to assign CVEs and other forms of
+security identifiers, and ongoing abuses by individuals and companies
+outside of the kernel community has made it clear that the kernel
+community should have control over those assignments.
+
+The Linux kernel developer team does have the ability to assign CVEs for
+potential Linux kernel security issues.  This assignment is independent
+of the :doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+A list of all assigned CVEs for the Linux kernel can be found in the
+archives of the linux-cve mailing list, as seen on
+https://lore.kernel.org/linux-cve-announce/.  To get notice of the
+assigned CVEs, please `subscribe
+<https://subspace.kernel.org/subscribing.html>`_ to that mailing list.
+
+Process
+=======
+
+As part of the normal stable release process, kernel changes that are
+potentially security issues are identified by the developers responsible
+for CVE number assignments and have CVE numbers automatically assigned
+to them.  These assignments are published on the linux-cve-announce
+mailing list as announcements on a frequent basis.
+
+Note, due to the layer at which the Linux kernel is in a system, almost
+any bug might be exploitable to compromise the security of the kernel,
+but the possibility of exploitation is often not evident when the bug is
+fixed.  Because of this, the CVE assignment team is overly cautious and
+assign CVE numbers to any bugfix that they identify.  This
+explains the seemingly large number of CVEs that are issued by the Linux
+kernel team.
+
+If the CVE assignment team misses a specific fix that any user feels
+should have a CVE assigned to it, please email them at <cve@kernel.org>
+and the team there will work with you on it.  Note that no potential
+security issues should be sent to this alias, it is ONLY for assignment
+of CVEs for fixes that are already in released kernel trees.  If you
+feel you have found an unfixed security issue, please follow the
+:doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+No CVEs will be automatically assigned for unfixed security issues in
+the Linux kernel; assignment will only automatically happen after a fix
+is available and applied to a stable kernel tree, and it will be tracked
+that way by the git commit id of the original fix.  If anyone wishes to
+have a CVE assigned before an issue is resolved with a commit, please
+contact the kernel CVE assignment team at <cve@kernel.org> to get an
+identifier assigned from their batch of reserved identifiers.
+
+No CVEs will be assigned for any issue found in a version of the kernel
+that is not currently being actively supported by the Stable/LTS kernel
+team.  A list of the currently supported kernel branches can be found at
+https://kernel.org/releases.html
+
+Disputes of assigned CVEs
+=========================
+
+The authority to dispute or modify an assigned CVE for a specific kernel
+change lies solely with the maintainers of the relevant subsystem
+affected.  This principle ensures a high degree of accuracy and
+accountability in vulnerability reporting.  Only those individuals with
+deep expertise and intimate knowledge of the subsystem can effectively
+assess the validity and scope of a reported vulnerability and determine
+its appropriate CVE designation.  Any attempt to modify or dispute a CVE
+outside of this designated authority could lead to confusion, inaccurate
+reporting, and ultimately, compromised systems.
+
+Invalid CVEs
+============
+
+If a security issue is found in a Linux kernel that is only supported by
+a Linux distribution due to the changes that have been made by that
+distribution, or due to the distribution supporting a kernel version
+that is no longer one of the kernel.org supported releases, then a CVE
+can not be assigned by the Linux kernel CVE team, and must be asked for
+from that Linux distribution itself.
+
+Any CVE that is assigned against the Linux kernel for an actively
+supported kernel version, by any group other than the kernel assignment
+CVE team should not be treated as a valid CVE.  Please notify the
+kernel CVE assignment team at <cve@kernel.org> so that they can work to
+invalidate such entries through the CNA remediation process.
+
+Applicability of specific CVEs
+==============================
+
+As the Linux kernel can be used in many different ways, with many
+different ways of accessing it by external users, or no access at all,
+the applicability of any specific CVE is up to the user of Linux to
+determine, it is not up to the CVE assignment team.  Please do not
+contact us to attempt to determine the applicability of any specific
+CVE.
+
+Also, as the source tree is so large, and any one system only uses a
+small subset of the source tree, any users of Linux should be aware that
+large numbers of assigned CVEs are not relevant for their systems.
+
+In short, we do not know your use case, and we do not know what portions
+of the kernel that you use, so there is no way for us to determine if a
+specific CVE is relevant for your system.
+
+As always, it is best to take all released kernel changes, as they are
+tested together in a unified whole by many community members, and not as
+individual cherry-picked changes.  Also note that for many bugs, the
+solution to the overall problem is not found in a single change, but by
+the sum of many fixes on top of each other.  Ideally CVEs will be
+assigned to all fixes for all issues, but sometimes we will fail to
+notice fixes, therefore assume that some changes without a CVE assigned
+might be relevant to take.
+
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 6cb732dfcc72..de9cbb7bd7eb 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -81,6 +81,7 @@ of special classes of bugs: regressions and security problems.
 
    handling-regressions
    security-bugs
+   cve
    embargoed-hardware-issues
 
 Maintainer information
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 84ee60fceef2..fd96e4a3cef9 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -431,7 +431,7 @@ patchwork checks
 Checks in patchwork are mostly simple wrappers around existing kernel
 scripts, the sources are available at:
 
-https://github.com/kuba-moo/nipa/tree/master/tests
+https://github.com/linux-netdev/nipa/tree/master/tests
 
 **Do not** post your patches just to run them through the checks.
 You must ensure that your patches are ready by testing them locally
diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst
index 08dd0f804410..497bb39727c8 100644
--- a/Documentation/process/maintainer-tip.rst
+++ b/Documentation/process/maintainer-tip.rst
@@ -304,13 +304,15 @@ following tag ordering scheme:
 
  - Reported-by: ``Reporter <reporter@mail>``
 
+ - Closes: ``URL or Message-ID of the bug report this is fixing``
+
  - Originally-by: ``Original author <original-author@mail>``
 
  - Suggested-by: ``Suggester <suggester@mail>``
 
  - Co-developed-by: ``Co-author <co-author@mail>``
 
-   Signed-off: ``Co-author <co-author@mail>``
+   Signed-off-by: ``Co-author <co-author@mail>``
 
    Note, that Co-developed-by and Signed-off-by of the co-author(s) must
    come in pairs.
@@ -478,7 +480,7 @@ Multi-line comments::
 	 * Larger multi-line comments should be split into paragraphs.
 	 */
 
-No tail comments:
+No tail comments (see below):
 
   Please refrain from using tail comments. Tail comments disturb the
   reading flow in almost all contexts, but especially in code::
@@ -499,6 +501,34 @@ No tail comments:
 	/* This magic initialization needs a comment. Maybe not? */
 	seed = MAGIC_CONSTANT;
 
+  Use C++ style, tail comments when documenting structs in headers to
+  achieve a more compact layout and better readability::
+
+        // eax
+        u32     x2apic_shift    :  5, // Number of bits to shift APIC ID right
+                                      // for the topology ID at the next level
+                                : 27; // Reserved
+        // ebx
+        u32     num_processors  : 16, // Number of processors at current level
+                                : 16; // Reserved
+
+  versus::
+
+	/* eax */
+	        /*
+	         * Number of bits to shift APIC ID right for the topology ID
+	         * at the next level
+	         */
+         u32     x2apic_shift    :  5,
+		 /* Reserved */
+				 : 27;
+
+	/* ebx */
+		/* Number of processors at current level */
+	u32     num_processors  : 16,
+		/* Reserved */
+				: 16;
+
 Comment the important things:
 
   Comments should be added where the operation is not obvious. Documenting
diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 692a3ba56cca..56c560a00b37 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -99,9 +99,8 @@ CVE assignment
 The security team does not assign CVEs, nor do we require them for
 reports or fixes, as this can needlessly complicate the process and may
 delay the bug handling.  If a reporter wishes to have a CVE identifier
-assigned, they should find one by themselves, for example by contacting
-MITRE directly.  However under no circumstances will a patch inclusion
-be delayed to wait for a CVE identifier to arrive.
+assigned for a confirmed issue, they can contact the :doc:`kernel CVE
+assignment team<../process/cve>` to obtain one.
 
 Non-disclosure agreements
 -------------------------
diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst
index 236c6dd3c647..081397827a7e 100644
--- a/Documentation/rust/general-information.rst
+++ b/Documentation/rust/general-information.rst
@@ -77,27 +77,3 @@ configuration:
 	#[cfg(CONFIG_X="y")]   // Enabled as a built-in (`y`)
 	#[cfg(CONFIG_X="m")]   // Enabled as a module   (`m`)
 	#[cfg(not(CONFIG_X))]  // Disabled
-
-
-Testing
--------
-
-There are the tests that come from the examples in the Rust documentation
-and get transformed into KUnit tests. These can be run via KUnit. For example
-via ``kunit_tool`` (``kunit.py``) on the command line::
-
-	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
-
-Alternatively, KUnit can run them as kernel built-in at boot. Refer to
-Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
-and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
-built-in vs. command line testing.
-
-Additionally, there are the ``#[test]`` tests. These can be run using
-the ``rusttest`` Make target::
-
-	make LLVM=1 rusttest
-
-This requires the kernel ``.config`` and downloads external repositories.
-It runs the ``#[test]`` tests on the host (currently) and thus is fairly
-limited in what these tests can test.
diff --git a/Documentation/rust/index.rst b/Documentation/rust/index.rst
index 965f2db529e0..46d35bd395cf 100644
--- a/Documentation/rust/index.rst
+++ b/Documentation/rust/index.rst
@@ -40,6 +40,7 @@ configurations.
     general-information
     coding-guidelines
     arch-support
+    testing
 
 .. only::  subproject and html
 
diff --git a/Documentation/rust/testing.rst b/Documentation/rust/testing.rst
new file mode 100644
index 000000000000..6658998d1b6c
--- /dev/null
+++ b/Documentation/rust/testing.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Testing
+=======
+
+This document contains useful information how to test the Rust code in the
+kernel.
+
+There are two sorts of tests:
+
+- The KUnit tests.
+- The ``#[test]`` tests.
+
+The KUnit tests
+---------------
+
+These are the tests that come from the examples in the Rust documentation. They
+get transformed into KUnit tests.
+
+Usage
+*****
+
+These tests can be run via KUnit. For example via ``kunit_tool`` (``kunit.py``)
+on the command line::
+
+	./tools/testing/kunit/kunit.py run --make_options LLVM=1 --arch x86_64 --kconfig_add CONFIG_RUST=y
+
+Alternatively, KUnit can run them as kernel built-in at boot. Refer to
+Documentation/dev-tools/kunit/index.rst for the general KUnit documentation
+and Documentation/dev-tools/kunit/architecture.rst for the details of kernel
+built-in vs. command line testing.
+
+To use these KUnit doctests, the following must be enabled::
+
+	CONFIG_KUNIT
+	   Kernel hacking -> Kernel Testing and Coverage -> KUnit - Enable support for unit tests
+	CONFIG_RUST_KERNEL_DOCTESTS
+	   Kernel hacking -> Rust hacking -> Doctests for the `kernel` crate
+
+in the kernel config system.
+
+KUnit tests are documentation tests
+***********************************
+
+These documentation tests are typically examples of usage of any item (e.g.
+function, struct, module...).
+
+They are very convenient because they are just written alongside the
+documentation. For instance:
+
+.. code-block:: rust
+
+	/// Sums two numbers.
+	///
+	/// ```
+	/// assert_eq!(mymod::f(10, 20), 30);
+	/// ```
+	pub fn f(a: i32, b: i32) -> i32 {
+	    a + b
+	}
+
+In userspace, the tests are collected and run via ``rustdoc``. Using the tool
+as-is would be useful already, since it allows verifying that examples compile
+(thus enforcing they are kept in sync with the code they document) and as well
+as running those that do not depend on in-kernel APIs.
+
+For the kernel, however, these tests get transformed into KUnit test suites.
+This means that doctests get compiled as Rust kernel objects, allowing them to
+run against a built kernel.
+
+A benefit of this KUnit integration is that Rust doctests get to reuse existing
+testing facilities. For instance, the kernel log would look like::
+
+	KTAP version 1
+	1..1
+	    KTAP version 1
+	    # Subtest: rust_doctests_kernel
+	    1..59
+	    # rust_doctest_kernel_build_assert_rs_0.location: rust/kernel/build_assert.rs:13
+	    ok 1 rust_doctest_kernel_build_assert_rs_0
+	    # rust_doctest_kernel_build_assert_rs_1.location: rust/kernel/build_assert.rs:56
+	    ok 2 rust_doctest_kernel_build_assert_rs_1
+	    # rust_doctest_kernel_init_rs_0.location: rust/kernel/init.rs:122
+	    ok 3 rust_doctest_kernel_init_rs_0
+	    ...
+	    # rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+	    ok 59 rust_doctest_kernel_types_rs_2
+	# rust_doctests_kernel: pass:59 fail:0 skip:0 total:59
+	# Totals: pass:59 fail:0 skip:0 total:59
+	ok 1 rust_doctests_kernel
+
+Tests using the `? <https://doc.rust-lang.org/reference/expressions/operator-expr.html#the-question-mark-operator>`_
+operator are also supported as usual, e.g.:
+
+.. code-block:: rust
+
+	/// ```
+	/// # use kernel::{spawn_work_item, workqueue};
+	/// spawn_work_item!(workqueue::system(), || pr_info!("x"))?;
+	/// # Ok::<(), Error>(())
+	/// ```
+
+The tests are also compiled with Clippy under ``CLIPPY=1``, just like normal
+code, thus also benefitting from extra linting.
+
+In order for developers to easily see which line of doctest code caused a
+failure, a KTAP diagnostic line is printed to the log. This contains the
+location (file and line) of the original test (i.e. instead of the location in
+the generated Rust file)::
+
+	# rust_doctest_kernel_types_rs_2.location: rust/kernel/types.rs:150
+
+Rust tests appear to assert using the usual ``assert!`` and ``assert_eq!``
+macros from the Rust standard library (``core``). We provide a custom version
+that forwards the call to KUnit instead. Importantly, these macros do not
+require passing context, unlike those for KUnit testing (i.e.
+``struct kunit *``). This makes them easier to use, and readers of the
+documentation do not need to care about which testing framework is used. In
+addition, it may allow us to test third-party code more easily in the future.
+
+A current limitation is that KUnit does not support assertions in other tasks.
+Thus, we presently simply print an error to the kernel log if an assertion
+actually failed. Additionally, doctests are not run for nonpublic functions.
+
+The ``#[test]`` tests
+---------------------
+
+Additionally, there are the ``#[test]`` tests. These can be run using the
+``rusttest`` Make target::
+
+	make LLVM=1 rusttest
+
+This requires the kernel ``.config`` and downloads external repositories. It
+runs the ``#[test]`` tests on the host (currently) and thus is fairly limited in
+what these tests can test.
diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py
index b9df61eb4501..03ace5f01b5c 100644
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -109,7 +109,7 @@ class KernelFeat(Directive):
             else:
                 out_lines += line + "\n"
 
-        nodeList = self.nestedParse(out_lines, fname)
+        nodeList = self.nestedParse(out_lines, self.arguments[0])
         return nodeList
 
     def nestedParse(self, lines, fname):
diff --git a/Documentation/sphinx/translations.py b/Documentation/sphinx/translations.py
index 47161e6eba99..32c2b32b2b5e 100644
--- a/Documentation/sphinx/translations.py
+++ b/Documentation/sphinx/translations.py
@@ -29,10 +29,7 @@ all_languages = {
 }
 
 class LanguagesNode(nodes.Element):
-    def __init__(self, current_language, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-        self.current_language = current_language
+    pass
 
 class TranslationsTransform(Transform):
     default_priority = 900
@@ -49,7 +46,8 @@ class TranslationsTransform(Transform):
             # normalize docname to be the untranslated one
             docname = os.path.join(*components[2:])
 
-        new_nodes = LanguagesNode(all_languages[this_lang_code])
+        new_nodes = LanguagesNode()
+        new_nodes['current_language'] = all_languages[this_lang_code]
 
         for lang_code, lang_name in all_languages.items():
             if lang_code == this_lang_code:
@@ -84,7 +82,7 @@ def process_languages(app, doctree, docname):
 
         html_content = app.builder.templates.render('translations.html',
             context={
-                'current_language': node.current_language,
+                'current_language': node['current_language'],
                 'languages': languages,
             })
 
diff --git a/Documentation/usb/gadget-testing.rst b/Documentation/usb/gadget-testing.rst
index 8cd62c466d20..077dfac7ed98 100644
--- a/Documentation/usb/gadget-testing.rst
+++ b/Documentation/usb/gadget-testing.rst
@@ -448,17 +448,17 @@ Function-specific configfs interface
 The function name to use when creating the function directory is "ncm".
 The NCM function provides these attributes in its function directory:
 
-	===============   ==================================================
-	ifname		  network device interface name associated with this
-			  function instance
-	qmult		  queue length multiplier for high and super speed
-	host_addr	  MAC address of host's end of this
-			  Ethernet over USB link
-	dev_addr	  MAC address of device's end of this
-			  Ethernet over USB link
-	max_segment_size  Segment size required for P2P connections. This
-			  will set MTU to (max_segment_size - 14 bytes)
-	===============   ==================================================
+	======================= ==================================================
+	ifname			network device interface name associated with this
+				function instance
+	qmult			queue length multiplier for high and super speed
+	host_addr		MAC address of host's end of this
+				Ethernet over USB link
+	dev_addr		MAC address of device's end of this
+				Ethernet over USB link
+	max_segment_size	Segment size required for P2P connections. This
+				will set MTU to 14 bytes
+	======================= ==================================================
 
 and after creating the functions/ncm.<instance name> they contain default
 values: qmult is 5, dev_addr and host_addr are randomly selected.
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 457e16f06e04..3731ecf1e437 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -82,8 +82,9 @@ Code  Seq#    Include File                                           Comments
 0x10  00-0F  drivers/char/s390/vmcp.h
 0x10  10-1F  arch/s390/include/uapi/sclp_ctl.h
 0x10  20-2F  arch/s390/include/uapi/asm/hypfs.h
-0x12  all    linux/fs.h
+0x12  all    linux/fs.h                                              BLK* ioctls
              linux/blkpg.h
+0x15  all    linux/fs.h                                              FS_IOC_* ioctls
 0x1b  all                                                            InfiniBand Subsystem
                                                                      <http://infiniband.sourceforge.net/>
 0x20  all    drivers/cdrom/cm206.h
diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst
index 68b0d2363af8..e1eaf6a830ce 100644
--- a/Documentation/virt/coco/sev-guest.rst
+++ b/Documentation/virt/coco/sev-guest.rst
@@ -67,6 +67,23 @@ counter (e.g. counter overflow), then -EIO will be returned.
                 };
         };
 
+The host ioctls are issued to a file descriptor of the /dev/sev device.
+The ioctl accepts the command ID/input structure documented below.
+
+::
+
+        struct sev_issue_cmd {
+                /* Command ID */
+                __u32 cmd;
+
+                /* Command request structure */
+                __u64 data;
+
+                /* Firmware error code on failure (see psp-sev.h) */
+                __u32 error;
+        };
+
+
 2.1 SNP_GET_REPORT
 ------------------
 
@@ -124,6 +141,41 @@ be updated with the expected value.
 
 See GHCB specification for further detail on how to parse the certificate blob.
 
+2.4 SNP_PLATFORM_STATUS
+-----------------------
+:Technology: sev-snp
+:Type: hypervisor ioctl cmd
+:Parameters (out): struct sev_user_data_snp_status
+:Returns (out): 0 on success, -negative on error
+
+The SNP_PLATFORM_STATUS command is used to query the SNP platform status. The
+status includes API major, minor version and more. See the SEV-SNP
+specification for further details.
+
+2.5 SNP_COMMIT
+--------------
+:Technology: sev-snp
+:Type: hypervisor ioctl cmd
+:Returns (out): 0 on success, -negative on error
+
+SNP_COMMIT is used to commit the currently installed firmware using the
+SEV-SNP firmware SNP_COMMIT command. This prevents roll-back to a previously
+committed firmware version. This will also update the reported TCB to match
+that of the currently installed firmware.
+
+2.6 SNP_SET_CONFIG
+------------------
+:Technology: sev-snp
+:Type: hypervisor ioctl cmd
+:Parameters (in): struct sev_user_data_snp_config
+:Returns (out): 0 on success, -negative on error
+
+SNP_SET_CONFIG is used to set the system-wide configuration such as
+reported TCB version in the attestation report. The command is similar
+to SNP_CONFIG command defined in the SEV-SNP spec. The current values of
+the firmware parameters affected by this command can be queried via
+SNP_PLATFORM_STATUS.
+
 3. SEV-SNP CPUID Enforcement
 ============================
 
diff --git a/Documentation/virt/hyperv/index.rst b/Documentation/virt/hyperv/index.rst
index 4a7a1b738bbe..de447e11b4a5 100644
--- a/Documentation/virt/hyperv/index.rst
+++ b/Documentation/virt/hyperv/index.rst
@@ -10,3 +10,4 @@ Hyper-V Enlightenments
    overview
    vmbus
    clocks
+   vpci
diff --git a/Documentation/virt/hyperv/vpci.rst b/Documentation/virt/hyperv/vpci.rst
new file mode 100644
index 000000000000..b65b2126ede3
--- /dev/null
+++ b/Documentation/virt/hyperv/vpci.rst
@@ -0,0 +1,316 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+PCI pass-thru devices
+=========================
+In a Hyper-V guest VM, PCI pass-thru devices (also called
+virtual PCI devices, or vPCI devices) are physical PCI devices
+that are mapped directly into the VM's physical address space.
+Guest device drivers can interact directly with the hardware
+without intermediation by the host hypervisor.  This approach
+provides higher bandwidth access to the device with lower
+latency, compared with devices that are virtualized by the
+hypervisor.  The device should appear to the guest just as it
+would when running on bare metal, so no changes are required
+to the Linux device drivers for the device.
+
+Hyper-V terminology for vPCI devices is "Discrete Device
+Assignment" (DDA).  Public documentation for Hyper-V DDA is
+available here: `DDA`_
+
+.. _DDA: https://learn.microsoft.com/en-us/windows-server/virtualization/hyper-v/plan/plan-for-deploying-devices-using-discrete-device-assignment
+
+DDA is typically used for storage controllers, such as NVMe,
+and for GPUs.  A similar mechanism for NICs is called SR-IOV
+and produces the same benefits by allowing a guest device
+driver to interact directly with the hardware.  See Hyper-V
+public documentation here: `SR-IOV`_
+
+.. _SR-IOV: https://learn.microsoft.com/en-us/windows-hardware/drivers/network/overview-of-single-root-i-o-virtualization--sr-iov-
+
+This discussion of vPCI devices includes DDA and SR-IOV
+devices.
+
+Device Presentation
+-------------------
+Hyper-V provides full PCI functionality for a vPCI device when
+it is operating, so the Linux device driver for the device can
+be used unchanged, provided it uses the correct Linux kernel
+APIs for accessing PCI config space and for other integration
+with Linux.  But the initial detection of the PCI device and
+its integration with the Linux PCI subsystem must use Hyper-V
+specific mechanisms.  Consequently, vPCI devices on Hyper-V
+have a dual identity.  They are initially presented to Linux
+guests as VMBus devices via the standard VMBus "offer"
+mechanism, so they have a VMBus identity and appear under
+/sys/bus/vmbus/devices.  The VMBus vPCI driver in Linux at
+drivers/pci/controller/pci-hyperv.c handles a newly introduced
+vPCI device by fabricating a PCI bus topology and creating all
+the normal PCI device data structures in Linux that would
+exist if the PCI device were discovered via ACPI on a bare-
+metal system.  Once those data structures are set up, the
+device also has a normal PCI identity in Linux, and the normal
+Linux device driver for the vPCI device can function as if it
+were running in Linux on bare-metal.  Because vPCI devices are
+presented dynamically through the VMBus offer mechanism, they
+do not appear in the Linux guest's ACPI tables.  vPCI devices
+may be added to a VM or removed from a VM at any time during
+the life of the VM, and not just during initial boot.
+
+With this approach, the vPCI device is a VMBus device and a
+PCI device at the same time.  In response to the VMBus offer
+message, the hv_pci_probe() function runs and establishes a
+VMBus connection to the vPCI VSP on the Hyper-V host.  That
+connection has a single VMBus channel.  The channel is used to
+exchange messages with the vPCI VSP for the purpose of setting
+up and configuring the vPCI device in Linux.  Once the device
+is fully configured in Linux as a PCI device, the VMBus
+channel is used only if Linux changes the vCPU to be interrupted
+in the guest, or if the vPCI device is removed from
+the VM while the VM is running.  The ongoing operation of the
+device happens directly between the Linux device driver for
+the device and the hardware, with VMBus and the VMBus channel
+playing no role.
+
+PCI Device Setup
+----------------
+PCI device setup follows a sequence that Hyper-V originally
+created for Windows guests, and that can be ill-suited for
+Linux guests due to differences in the overall structure of
+the Linux PCI subsystem compared with Windows.  Nonetheless,
+with a bit of hackery in the Hyper-V virtual PCI driver for
+Linux, the virtual PCI device is setup in Linux so that
+generic Linux PCI subsystem code and the Linux driver for the
+device "just work".
+
+Each vPCI device is set up in Linux to be in its own PCI
+domain with a host bridge.  The PCI domainID is derived from
+bytes 4 and 5 of the instance GUID assigned to the VMBus vPCI
+device.  The Hyper-V host does not guarantee that these bytes
+are unique, so hv_pci_probe() has an algorithm to resolve
+collisions.  The collision resolution is intended to be stable
+across reboots of the same VM so that the PCI domainIDs don't
+change, as the domainID appears in the user space
+configuration of some devices.
+
+hv_pci_probe() allocates a guest MMIO range to be used as PCI
+config space for the device.  This MMIO range is communicated
+to the Hyper-V host over the VMBus channel as part of telling
+the host that the device is ready to enter d0.  See
+hv_pci_enter_d0().  When the guest subsequently accesses this
+MMIO range, the Hyper-V host intercepts the accesses and maps
+them to the physical device PCI config space.
+
+hv_pci_probe() also gets BAR information for the device from
+the Hyper-V host, and uses this information to allocate MMIO
+space for the BARs.  That MMIO space is then setup to be
+associated with the host bridge so that it works when generic
+PCI subsystem code in Linux processes the BARs.
+
+Finally, hv_pci_probe() creates the root PCI bus.  At this
+point the Hyper-V virtual PCI driver hackery is done, and the
+normal Linux PCI machinery for scanning the root bus works to
+detect the device, to perform driver matching, and to
+initialize the driver and device.
+
+PCI Device Removal
+------------------
+A Hyper-V host may initiate removal of a vPCI device from a
+guest VM at any time during the life of the VM.  The removal
+is instigated by an admin action taken on the Hyper-V host and
+is not under the control of the guest OS.
+
+A guest VM is notified of the removal by an unsolicited
+"Eject" message sent from the host to the guest over the VMBus
+channel associated with the vPCI device.  Upon receipt of such
+a message, the Hyper-V virtual PCI driver in Linux
+asynchronously invokes Linux kernel PCI subsystem calls to
+shutdown and remove the device.  When those calls are
+complete, an "Ejection Complete" message is sent back to
+Hyper-V over the VMBus channel indicating that the device has
+been removed.  At this point, Hyper-V sends a VMBus rescind
+message to the Linux guest, which the VMBus driver in Linux
+processes by removing the VMBus identity for the device.  Once
+that processing is complete, all vestiges of the device having
+been present are gone from the Linux kernel.  The rescind
+message also indicates to the guest that Hyper-V has stopped
+providing support for the vPCI device in the guest.  If the
+guest were to attempt to access that device's MMIO space, it
+would be an invalid reference. Hypercalls affecting the device
+return errors, and any further messages sent in the VMBus
+channel are ignored.
+
+After sending the Eject message, Hyper-V allows the guest VM
+60 seconds to cleanly shutdown the device and respond with
+Ejection Complete before sending the VMBus rescind
+message.  If for any reason the Eject steps don't complete
+within the allowed 60 seconds, the Hyper-V host forcibly
+performs the rescind steps, which will likely result in
+cascading errors in the guest because the device is now no
+longer present from the guest standpoint and accessing the
+device MMIO space will fail.
+
+Because ejection is asynchronous and can happen at any point
+during the guest VM lifecycle, proper synchronization in the
+Hyper-V virtual PCI driver is very tricky.  Ejection has been
+observed even before a newly offered vPCI device has been
+fully setup.  The Hyper-V virtual PCI driver has been updated
+several times over the years to fix race conditions when
+ejections happen at inopportune times. Care must be taken when
+modifying this code to prevent re-introducing such problems.
+See comments in the code.
+
+Interrupt Assignment
+--------------------
+The Hyper-V virtual PCI driver supports vPCI devices using
+MSI, multi-MSI, or MSI-X.  Assigning the guest vCPU that will
+receive the interrupt for a particular MSI or MSI-X message is
+complex because of the way the Linux setup of IRQs maps onto
+the Hyper-V interfaces.  For the single-MSI and MSI-X cases,
+Linux calls hv_compse_msi_msg() twice, with the first call
+containing a dummy vCPU and the second call containing the
+real vCPU.  Furthermore, hv_irq_unmask() is finally called
+(on x86) or the GICD registers are set (on arm64) to specify
+the real vCPU again.  Each of these three calls interact
+with Hyper-V, which must decide which physical CPU should
+receive the interrupt before it is forwarded to the guest VM.
+Unfortunately, the Hyper-V decision-making process is a bit
+limited, and can result in concentrating the physical
+interrupts on a single CPU, causing a performance bottleneck.
+See details about how this is resolved in the extensive
+comment above the function hv_compose_msi_req_get_cpu().
+
+The Hyper-V virtual PCI driver implements the
+irq_chip.irq_compose_msi_msg function as hv_compose_msi_msg().
+Unfortunately, on Hyper-V the implementation requires sending
+a VMBus message to the Hyper-V host and awaiting an interrupt
+indicating receipt of a reply message.  Since
+irq_chip.irq_compose_msi_msg can be called with IRQ locks
+held, it doesn't work to do the normal sleep until awakened by
+the interrupt. Instead hv_compose_msi_msg() must send the
+VMBus message, and then poll for the completion message. As
+further complexity, the vPCI device could be ejected/rescinded
+while the polling is in progress, so this scenario must be
+detected as well.  See comments in the code regarding this
+very tricky area.
+
+Most of the code in the Hyper-V virtual PCI driver (pci-
+hyperv.c) applies to Hyper-V and Linux guests running on x86
+and on arm64 architectures.  But there are differences in how
+interrupt assignments are managed.  On x86, the Hyper-V
+virtual PCI driver in the guest must make a hypercall to tell
+Hyper-V which guest vCPU should be interrupted by each
+MSI/MSI-X interrupt, and the x86 interrupt vector number that
+the x86_vector IRQ domain has picked for the interrupt.  This
+hypercall is made by hv_arch_irq_unmask().  On arm64, the
+Hyper-V virtual PCI driver manages the allocation of an SPI
+for each MSI/MSI-X interrupt.  The Hyper-V virtual PCI driver
+stores the allocated SPI in the architectural GICD registers,
+which Hyper-V emulates, so no hypercall is necessary as with
+x86.  Hyper-V does not support using LPIs for vPCI devices in
+arm64 guest VMs because it does not emulate a GICv3 ITS.
+
+The Hyper-V virtual PCI driver in Linux supports vPCI devices
+whose drivers create managed or unmanaged Linux IRQs.  If the
+smp_affinity for an unmanaged IRQ is updated via the /proc/irq
+interface, the Hyper-V virtual PCI driver is called to tell
+the Hyper-V host to change the interrupt targeting and
+everything works properly.  However, on x86 if the x86_vector
+IRQ domain needs to reassign an interrupt vector due to
+running out of vectors on a CPU, there's no path to inform the
+Hyper-V host of the change, and things break.  Fortunately,
+guest VMs operate in a constrained device environment where
+using all the vectors on a CPU doesn't happen. Since such a
+problem is only a theoretical concern rather than a practical
+concern, it has been left unaddressed.
+
+DMA
+---
+By default, Hyper-V pins all guest VM memory in the host
+when the VM is created, and programs the physical IOMMU to
+allow the VM to have DMA access to all its memory.  Hence
+it is safe to assign PCI devices to the VM, and allow the
+guest operating system to program the DMA transfers.  The
+physical IOMMU prevents a malicious guest from initiating
+DMA to memory belonging to the host or to other VMs on the
+host. From the Linux guest standpoint, such DMA transfers
+are in "direct" mode since Hyper-V does not provide a virtual
+IOMMU in the guest.
+
+Hyper-V assumes that physical PCI devices always perform
+cache-coherent DMA.  When running on x86, this behavior is
+required by the architecture.  When running on arm64, the
+architecture allows for both cache-coherent and
+non-cache-coherent devices, with the behavior of each device
+specified in the ACPI DSDT.  But when a PCI device is assigned
+to a guest VM, that device does not appear in the DSDT, so the
+Hyper-V VMBus driver propagates cache-coherency information
+from the VMBus node in the ACPI DSDT to all VMBus devices,
+including vPCI devices (since they have a dual identity as a VMBus
+device and as a PCI device).  See vmbus_dma_configure().
+Current Hyper-V versions always indicate that the VMBus is
+cache coherent, so vPCI devices on arm64 always get marked as
+cache coherent and the CPU does not perform any sync
+operations as part of dma_map/unmap_*() calls.
+
+vPCI protocol versions
+----------------------
+As previously described, during vPCI device setup and teardown
+messages are passed over a VMBus channel between the Hyper-V
+host and the Hyper-v vPCI driver in the Linux guest.  Some
+messages have been revised in newer versions of Hyper-V, so
+the guest and host must agree on the vPCI protocol version to
+be used.  The version is negotiated when communication over
+the VMBus channel is first established.  See
+hv_pci_protocol_negotiation(). Newer versions of the protocol
+extend support to VMs with more than 64 vCPUs, and provide
+additional information about the vPCI device, such as the
+guest virtual NUMA node to which it is most closely affined in
+the underlying hardware.
+
+Guest NUMA node affinity
+------------------------
+When the vPCI protocol version provides it, the guest NUMA
+node affinity of the vPCI device is stored as part of the Linux
+device information for subsequent use by the Linux driver. See
+hv_pci_assign_numa_node().  If the negotiated protocol version
+does not support the host providing NUMA affinity information,
+the Linux guest defaults the device NUMA node to 0.  But even
+when the negotiated protocol version includes NUMA affinity
+information, the ability of the host to provide such
+information depends on certain host configuration options.  If
+the guest receives NUMA node value "0", it could mean NUMA
+node 0, or it could mean "no information is available".
+Unfortunately it is not possible to distinguish the two cases
+from the guest side.
+
+PCI config space access in a CoCo VM
+------------------------------------
+Linux PCI device drivers access PCI config space using a
+standard set of functions provided by the Linux PCI subsystem.
+In Hyper-V guests these standard functions map to functions
+hv_pcifront_read_config() and hv_pcifront_write_config()
+in the Hyper-V virtual PCI driver.  In normal VMs,
+these hv_pcifront_*() functions directly access the PCI config
+space, and the accesses trap to Hyper-V to be handled.
+But in CoCo VMs, memory encryption prevents Hyper-V
+from reading the guest instruction stream to emulate the
+access, so the hv_pcifront_*() functions must invoke
+hypercalls with explicit arguments describing the access to be
+made.
+
+Config Block back-channel
+-------------------------
+The Hyper-V host and Hyper-V virtual PCI driver in Linux
+together implement a non-standard back-channel communication
+path between the host and guest.  The back-channel path uses
+messages sent over the VMBus channel associated with the vPCI
+device.  The functions hyperv_read_cfg_blk() and
+hyperv_write_cfg_blk() are the primary interfaces provided to
+other parts of the Linux kernel.  As of this writing, these
+interfaces are used only by the Mellanox mlx5 driver to pass
+diagnostic data to a Hyper-V host running in the Azure public
+cloud.  The functions hyperv_read_cfg_blk() and
+hyperv_write_cfg_blk() are implemented in a separate module
+(pci-hyperv-intf.c, under CONFIG_PCI_HYPERV_INTERFACE) that
+effectively stubs them out when running in non-Hyper-V
+environments.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 3ec0b7a455a0..09c7e585ff58 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8791,6 +8791,11 @@ means the VM type with value @n is supported.  Possible values of @n are::
   #define KVM_X86_DEFAULT_VM	0
   #define KVM_X86_SW_PROTECTED_VM	1
 
+Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing.
+Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in
+production.  The behavior and effective ABI for software-protected VMs is
+unstable.
+
 9. Known KVM API problems
 =========================
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 8999497011a2..f31f987bda42 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -897,6 +897,12 @@ Q:	https://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/hw/efa/
 F:	include/uapi/rdma/efa-abi.h
 
+AMD ADDRESS TRANSLATION LIBRARY (ATL)
+M:	Yazen Ghannam <Yazen.Ghannam@amd.com>
+L:	linux-edac@vger.kernel.org
+S:	Supported
+F:	drivers/ras/amd/atl/*
+
 AMD AXI W1 DRIVER
 M:	Kris Chaplin <kris.chaplin@amd.com>
 R:	Thomas Delev <thomas.delev@amd.com>
@@ -1395,6 +1401,7 @@ F:	drivers/hwmon/max31760.c
 
 ANALOGBITS PLL LIBRARIES
 M:	Paul Walmsley <paul.walmsley@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 S:	Supported
 F:	drivers/clk/analogbits/*
 F:	include/linux/clk/analogbits*
@@ -2156,7 +2163,7 @@ M:	Shawn Guo <shawnguo@kernel.org>
 M:	Sascha Hauer <s.hauer@pengutronix.de>
 R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Fabio Estevam <festevam@gmail.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -2542,13 +2549,14 @@ F:	drivers/*/*/*wpcm*
 F:	drivers/*/*wpcm*
 
 ARM/NXP S32G ARCHITECTURE
-M:	Chester Lin <chester62515@gmail.com>
-R:	Andreas Färber <afaerber@suse.de>
+R:	Chester Lin <chester62515@gmail.com>
 R:	Matthias Brugger <mbrugger@suse.com>
-R:	NXP S32 Linux Team <s32@nxp.com>
+R:	Ghennadi Procopciuc <ghennadi.procopciuc@oss.nxp.com>
+L:	NXP S32 Linux Team <s32@nxp.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm64/boot/dts/freescale/s32g*.dts*
+F:	drivers/pinctrl/nxp/
 
 ARM/Orion SoC/Technologic Systems TS-78xx platform support
 M:	Alexander Clouter <alex@digriz.org.uk>
@@ -4169,14 +4177,14 @@ F:	drivers/firmware/broadcom/tee_bnxt_fw.c
 F:	drivers/net/ethernet/broadcom/bnxt/
 F:	include/linux/firmware/broadcom/tee_bnxt_fw.h
 
-BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M:	Arend van Spriel <aspriel@gmail.com>
-M:	Franky Lin <franky.lin@broadcom.com>
-M:	Hante Meuleman <hante.meuleman@broadcom.com>
+BROADCOM BRCM80211 IEEE802.11 WIRELESS DRIVERS
+M:	Arend van Spriel <arend.vanspriel@broadcom.com>
 L:	linux-wireless@vger.kernel.org
+L:	brcm80211@lists.linux.dev
 L:	brcm80211-dev-list.pdl@broadcom.com
 S:	Supported
 F:	drivers/net/wireless/broadcom/brcm80211/
+F:	include/linux/platform_data/brcmfmac.h
 
 BROADCOM BRCMSTB GPIO DRIVER
 M:	Doug Berger <opendmb@gmail.com>
@@ -5378,7 +5386,7 @@ CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
 M:	Roman Gushchin <roman.gushchin@linux.dev>
-M:	Shakeel Butt <shakeelb@google.com>
+M:	Shakeel Butt <shakeel.butt@linux.dev>
 R:	Muchun Song <muchun.song@linux.dev>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
@@ -5610,6 +5618,11 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/ctu,ctucanfd.yaml
 F:	drivers/net/can/ctucanfd/
 
+CVE ASSIGNMENT CONTACT
+M:	CVE Assignment Team <cve@kernel.org>
+S:	Maintained
+F:	Documentation/process/cve.rst
+
 CW1200 WLAN driver
 S:	Orphan
 F:	drivers/net/wireless/st/cw1200/
@@ -7577,7 +7590,6 @@ R:	Robert Richter <rric@kernel.org>
 L:	linux-edac@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next
-F:	Documentation/admin-guide/ras.rst
 F:	Documentation/driver-api/edac.rst
 F:	drivers/edac/
 F:	include/linux/edac.h
@@ -8160,6 +8172,7 @@ F:	include/uapi/scsi/fc/
 FILE LOCKING (flock() and fcntl()/lockf())
 M:	Jeff Layton <jlayton@kernel.org>
 M:	Chuck Lever <chuck.lever@oracle.com>
+R:	Alexander Aring <alex.aring@gmail.com>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/fcntl.c
@@ -8490,7 +8503,7 @@ FREESCALE IMX / MXC FEC DRIVER
 M:	Wei Fang <wei.fang@nxp.com>
 R:	Shenwei Wang <shenwei.wang@nxp.com>
 R:	Clark Wang <xiaoning.wang@nxp.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/fsl,fec.yaml
@@ -8525,7 +8538,7 @@ F:	drivers/i2c/busses/i2c-imx.c
 FREESCALE IMX LPI2C DRIVER
 M:	Dong Aisheng <aisheng.dong@nxp.com>
 L:	linux-i2c@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 F:	Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml
 F:	drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -9080,6 +9093,7 @@ F:	Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
 F:	arch/arm64/boot/dts/exynos/google/
 F:	drivers/clk/samsung/clk-gs101.c
 F:	include/dt-bindings/clock/google,gs101.h
+K:	[gG]oogle.?[tT]ensor
 
 GPD POCKET FAN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
@@ -10091,7 +10105,7 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git
 F:	Documentation/devicetree/bindings/i2c/
 F:	drivers/i2c/algos/
 F:	drivers/i2c/busses/
@@ -10283,7 +10297,7 @@ F:	drivers/scsi/ibmvscsi/ibmvscsi*
 F:	include/scsi/viosrp.h
 
 IBM Power Virtual SCSI Device Target Driver
-M:	Michael Cyr <mikecyr@linux.ibm.com>
+M:	Tyrel Datwyler <tyreld@linux.ibm.com>
 L:	linux-scsi@vger.kernel.org
 L:	target-devel@vger.kernel.org
 S:	Supported
@@ -10471,7 +10485,8 @@ M:	Donald Robson <donald.robson@imgtec.com>
 M:	Matt Coster <matt.coster@imgtec.com>
 S:	Supported
 T:	git git://anongit.freedesktop.org/drm/drm-misc
-F:	Documentation/devicetree/bindings/gpu/img,powervr.yaml
+F:	Documentation/devicetree/bindings/gpu/img,powervr-rogue.yaml
+F:	Documentation/devicetree/bindings/gpu/img,powervr-sgx.yaml
 F:	Documentation/gpu/imagination/
 F:	drivers/gpu/drm/imagination/
 F:	include/uapi/drm/pvr_drm.h
@@ -10729,7 +10744,7 @@ INTEL DRM I915 DRIVER (Meteor Lake, DG2 and older excluding Poulsbo, Moorestown
 M:	Jani Nikula <jani.nikula@linux.intel.com>
 M:	Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
 M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
-M:	Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
+M:	Tvrtko Ursulin <tursulin@ursulin.net>
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
 W:	https://drm.pages.freedesktop.org/intel-docs/
@@ -10801,11 +10816,11 @@ F:	drivers/gpio/gpio-tangier.h
 
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:	Zhenyu Wang <zhenyuw@linux.intel.com>
-M:	Zhi Wang <zhi.a.wang@intel.com>
+M:	Zhi Wang <zhi.wang.linux@gmail.com>
 L:	intel-gvt-dev@lists.freedesktop.org
 L:	intel-gfx@lists.freedesktop.org
 S:	Supported
-W:	https://01.org/igvt-g
+W:	https://github.com/intel/gvt-linux/wiki
 T:	git https://github.com/intel/gvt-linux.git
 F:	drivers/gpu/drm/i915/gvt/
 
@@ -11127,7 +11142,6 @@ S:	Supported
 F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
-M:	Gregory Greenman <gregory.greenman@intel.com>
 M:	Miri Korenblit <miriam.rachel.korenblit@intel.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
@@ -11152,6 +11166,16 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wwan/iosm/
 
+INTEL(R) FLEXIBLE RETURN AND EVENT DELIVERY
+M:	Xin Li <xin@zytor.com>
+M:	"H. Peter Anvin" <hpa@zytor.com>
+S:	Supported
+F:	Documentation/arch/x86/x86_64/fred.rst
+F:	arch/x86/entry/entry_64_fred.S
+F:	arch/x86/entry/entry_fred.c
+F:	arch/x86/include/asm/fred.h
+F:	arch/x86/kernel/fred.c
+
 INTEL(R) TRACE HUB
 M:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 S:	Supported
@@ -11725,6 +11749,7 @@ F:	fs/smb/server/
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendanhiggins@google.com>
 M:	David Gow <davidgow@google.com>
+R:	Rae Moar <rmoar@google.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained
@@ -12511,7 +12536,6 @@ F:	arch/powerpc/include/asm/livepatch.h
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
 F:	kernel/module/livepatch.c
-F:	lib/livepatch/
 F:	samples/livepatch/
 F:	tools/testing/selftests/livepatch/
 
@@ -12903,6 +12927,8 @@ M:	Alejandro Colomar <alx@kernel.org>
 L:	linux-man@vger.kernel.org
 S:	Maintained
 W:	http://www.kernel.org/doc/man-pages
+T:	git git://git.kernel.org/pub/scm/docs/man-pages/man-pages.git
+T:	git git://www.alejandro-colomar.es/src/alx/linux/man-pages/man-pages.git
 
 MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP)
 M:	Jeremy Kerr <jk@codeconstruct.com.au>
@@ -14104,6 +14130,17 @@ F:	mm/
 F:	tools/mm/
 F:	tools/testing/selftests/mm/
 
+MEMORY MAPPING
+M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Liam R. Howlett <Liam.Howlett@oracle.com>
+R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Lorenzo Stoakes <lstoakes@gmail.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	mm/mmap.c
+
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Richard Weinberger <richard@nod.at>
@@ -14362,7 +14399,7 @@ MICROCHIP MCP16502 PMIC DRIVER
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
-F:	Documentation/devicetree/bindings/regulator/mcp16502-regulator.txt
+F:	Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml
 F:	drivers/regulator/mcp16502.c
 
 MICROCHIP MCP3564 ADC DRIVER
@@ -15178,6 +15215,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
+F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
@@ -15185,6 +15223,7 @@ F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
 F:	include/linux/netdevice.h
+F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
 X:	drivers/net/wireless/
@@ -15233,6 +15272,8 @@ F:	Documentation/networking/
 F:	Documentation/networking/net_cachelines/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
+F:	include/linux/framer/framer-provider.h
+F:	include/linux/framer/framer.h
 F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
@@ -15320,7 +15361,7 @@ K:	\bmdo_
 NETWORKING [MPTCP]
 M:	Matthieu Baerts <matttbe@kernel.org>
 M:	Mat Martineau <martineau@kernel.org>
-R:	Geliang Tang <geliang.tang@linux.dev>
+R:	Geliang Tang <geliang@kernel.org>
 L:	netdev@vger.kernel.org
 L:	mptcp@lists.linux.dev
 S:	Maintained
@@ -15567,16 +15608,6 @@ W:	https://github.com/davejiang/linux/wiki
 T:	git https://github.com/davejiang/linux.git
 F:	drivers/ntb/hw/intel/
 
-NTFS FILESYSTEM
-M:	Anton Altaparmakov <anton@tuxera.com>
-R:	Namjae Jeon <linkinjeon@kernel.org>
-L:	linux-ntfs-dev@lists.sourceforge.net
-S:	Supported
-W:	http://www.tuxera.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs.git
-F:	Documentation/filesystems/ntfs.rst
-F:	fs/ntfs/
-
 NTFS3 FILESYSTEM
 M:	Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
 L:	ntfs3@lists.linux.dev
@@ -15705,7 +15736,7 @@ F:	drivers/iio/gyro/fxas21002c_spi.c
 NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER
 M:	Haibo Chen <haibo.chen@nxp.com>
 L:	linux-iio@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 F:	Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml
 F:	Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml
@@ -15742,7 +15773,7 @@ F:	drivers/gpu/drm/imx/dcss/
 NXP i.MX 8QXP ADC DRIVER
 M:	Cai Huoqing <cai.huoqing@linux.dev>
 M:	Haibo Chen <haibo.chen@nxp.com>
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 L:	linux-iio@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml
@@ -15750,7 +15781,7 @@ F:	drivers/iio/adc/imx8qxp-adc.c
 
 NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER
 M:	Mirela Rabulea <mirela.rabulea@nxp.com>
-R:	NXP Linux Team <linux-imx@nxp.com>
+L:	imx@lists.linux.dev
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml
@@ -15760,7 +15791,7 @@ NXP i.MX CLOCK DRIVERS
 M:	Abel Vesa <abelvesa@kernel.org>
 R:	Peng Fan <peng.fan@nxp.com>
 L:	linux-clk@vger.kernel.org
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx
 F:	Documentation/devicetree/bindings/clock/imx*
@@ -16721,6 +16752,7 @@ F:	drivers/pci/controller/dwc/*layerscape*
 PCI DRIVER FOR FU740
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 M:	Greentime Hu <greentime.hu@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml
@@ -16833,6 +16865,7 @@ F:	drivers/pci/controller/dwc/*designware*
 
 PCI DRIVER FOR TI DRA7XX/J721E
 M:	Vignesh Raghavendra <vigneshr@ti.com>
+R:	Siddharth Vadapalli <s-vadapalli@ti.com>
 L:	linux-omap@vger.kernel.org
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -16857,9 +16890,8 @@ F:	Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml
 F:	drivers/pci/controller/pcie-xilinx-cpm.c
 
 PCI ENDPOINT SUBSYSTEM
-M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 M:	Krzysztof Wilczyński <kw@linux.com>
-R:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
 R:	Kishon Vijay Abraham I <kishon@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
@@ -17179,7 +17211,7 @@ R:	John Garry <john.g.garry@oracle.com>
 R:	Will Deacon <will@kernel.org>
 R:	James Clark <james.clark@arm.com>
 R:	Mike Leach <mike.leach@linaro.org>
-R:	Leo Yan <leo.yan@linaro.org>
+R:	Leo Yan <leo.yan@linux.dev>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	tools/build/feature/test-libopencsd.c
@@ -17260,9 +17292,12 @@ M:	Shawn Guo <shawnguo@kernel.org>
 M:	Jacky Bai <ping.bai@nxp.com>
 R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 L:	linux-gpio@vger.kernel.org
+L:	NXP S32 Linux Team <s32@nxp.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/pinctrl/fsl,*
+F:	Documentation/devicetree/bindings/pinctrl/nxp,s32*
 F:	drivers/pinctrl/freescale/
+F:	drivers/pinctrl/nxp/
 
 PIN CONTROLLER - INTEL
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
@@ -17316,14 +17351,6 @@ S:	Supported
 F:	drivers/gpio/gpio-sama5d2-piobu.c
 F:	drivers/pinctrl/pinctrl-at91*
 
-PIN CONTROLLER - NXP S32
-M:	Chester Lin <clin@suse.com>
-R:	NXP S32 Linux Team <s32@nxp.com>
-L:	linux-gpio@vger.kernel.org
-S:	Maintained
-F:	Documentation/devicetree/bindings/pinctrl/nxp,s32*
-F:	drivers/pinctrl/nxp/
-
 PIN CONTROLLER - QUALCOMM
 M:	Bjorn Andersson <andersson@kernel.org>
 L:	linux-arm-msm@vger.kernel.org
@@ -17340,7 +17367,6 @@ F:	Documentation/devicetree/bindings/pinctrl/renesas,*
 F:	drivers/pinctrl/renesas/
 
 PIN CONTROLLER - SAMSUNG
-M:	Tomasz Figa <tomasz.figa@gmail.com>
 M:	Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 R:	Alim Akhtar <alim.akhtar@samsung.com>
@@ -17490,6 +17516,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
 F:	fs/timerfd.c
 F:	include/linux/time_namespace.h
 F:	include/linux/timer*
+F:	include/trace/events/timer*
 F:	kernel/time/*timer*
 F:	kernel/time/namespace.c
 
@@ -17526,6 +17553,7 @@ F:	Documentation/devicetree/bindings/power/supply/
 F:	drivers/power/supply/
 F:	include/linux/power/
 F:	include/linux/power_supply.h
+F:	tools/testing/selftests/power_supply/
 
 POWERNV OPERATOR PANEL LCD DISPLAY DRIVER
 M:	Suraj Jitindar Singh <sjitindarsingh@gmail.com>
@@ -17973,33 +18001,34 @@ F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATH12K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath12k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath12k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath12k/
+N:	ath12k
 
 QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath10k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
-F:	Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
 F:	drivers/net/wireless/ath/ath10k/
+N:	ath10k
 
 QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@kernel.org>
-M:	Jeff Johnson <quic_jjohnson@quicinc.com>
+M:	Jeff Johnson <jjohnson@kernel.org>
 L:	ath11k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath11k
 B:	https://wireless.wiki.kernel.org/en/users/Drivers/ath11k/bugreport
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
-F:	Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
 F:	drivers/net/wireless/ath/ath11k/
+N:	ath11k
 
 QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
 M:	Toke Høiland-Jørgensen <toke@toke.dk>
@@ -18082,7 +18111,6 @@ F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <vkoul@kernel.org>
-R:	Bhupesh Sharma <bhupesh.sharma@linaro.org>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
@@ -18354,11 +18382,17 @@ M:	Tony Luck <tony.luck@intel.com>
 M:	Borislav Petkov <bp@alien8.de>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
-F:	Documentation/admin-guide/ras.rst
+F:	Documentation/admin-guide/RAS
 F:	drivers/ras/
 F:	include/linux/ras.h
 F:	include/ras/ras_event.h
 
+RAS FRU MEMORY POISON MANAGER (FMPM)
+M:	Yazen Ghannam <Yazen.Ghannam@amd.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/ras/amd/fmpm.c
+
 RC-CORE / LIRC FRAMEWORK
 M:	Sean Young <sean@mess.org>
 L:	linux-media@vger.kernel.org
@@ -18429,7 +18463,7 @@ S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
 RDS - RELIABLE DATAGRAM SOCKETS
-M:	Santosh Shilimkar <santosh.shilimkar@oracle.com>
+M:	Allison Henderson <allison.henderson@oracle.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 L:	rds-devel@oss.oracle.com (moderated for non-subscribers)
@@ -18848,6 +18882,7 @@ F:	Documentation/devicetree/bindings/riscv/
 F:	arch/riscv/boot/dts/
 X:	arch/riscv/boot/dts/allwinner/
 X:	arch/riscv/boot/dts/renesas/
+X:	arch/riscv/boot/dts/sophgo/
 
 RISC-V PMU DRIVERS
 M:	Atish Patra <atishp@atishpatra.org>
@@ -19096,6 +19131,7 @@ F:	Documentation/rust/
 F:	rust/
 F:	samples/rust/
 F:	scripts/*rust*
+F:	tools/testing/selftests/rust/
 K:	\b(?i:rust)\b
 
 RXRPC SOCKETS (AF_RXRPC)
@@ -19389,7 +19425,6 @@ F:	drivers/media/platform/samsung/exynos4-is/
 SAMSUNG SOC CLOCK DRIVERS
 M:	Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
-M:	Tomasz Figa <tomasz.figa@gmail.com>
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 R:	Alim Akhtar <alim.akhtar@samsung.com>
 L:	linux-samsung-soc@vger.kernel.org
@@ -19631,7 +19666,7 @@ F:	drivers/mmc/host/sdhci-of-at91.c
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER
 M:	Haibo Chen <haibo.chen@nxp.com>
-L:	linux-imx@nxp.com
+L:	imx@lists.linux.dev
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-esdhc-imx.c
@@ -19966,36 +20001,15 @@ S:	Maintained
 F:	drivers/watchdog/simatic-ipc-wdt.c
 
 SIFIVE DRIVERS
-M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
+M:	Samuel Holland <samuel.holland@sifive.com>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
+F:	drivers/dma/sf-pdma/
 N:	sifive
+K:	fu[57]40
 K:	[^@]sifive
 
-SIFIVE CACHE DRIVER
-M:	Conor Dooley <conor@kernel.org>
-L:	linux-riscv@lists.infradead.org
-S:	Maintained
-F:	Documentation/devicetree/bindings/cache/sifive,ccache0.yaml
-F:	drivers/cache/sifive_ccache.c
-
-SIFIVE FU540 SYSTEM-ON-CHIP
-M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@dabbelt.com>
-L:	linux-riscv@lists.infradead.org
-S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git
-N:	fu540
-K:	fu540
-
-SIFIVE PDMA DRIVER
-M:	Green Wan <green.wan@sifive.com>
-S:	Maintained
-F:	Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
-F:	drivers/dma/sf-pdma/
-
-
 SILEAD TOUCHSCREEN DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-input@vger.kernel.org
@@ -20204,8 +20218,8 @@ F:	Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
 F:	drivers/net/ethernet/socionext/sni_ave.c
 
 SOCIONEXT (SNI) NETSEC NETWORK DRIVER
-M:	Jassi Brar <jaswinder.singh@linaro.org>
 M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
+M:	Masahisa Kojima <kojima.masahisa@socionext.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/socionext,synquacer-netsec.yaml
@@ -20446,12 +20460,13 @@ F:	drivers/char/sonypi.c
 F:	drivers/platform/x86/sony-laptop.c
 F:	include/linux/sony-laptop.h
 
-SOPHGO DEVICETREES
-M:	Chao Wei <chao.wei@sophgo.com>
+SOPHGO DEVICETREES and DRIVERS
 M:	Chen Wang <unicorn_wang@outlook.com>
+M:	Inochi Amaoto <inochiama@outlook.com>
+T:	git https://github.com/sophgo/linux.git
 S:	Maintained
-F:	arch/riscv/boot/dts/sophgo/
-F:	Documentation/devicetree/bindings/riscv/sophgo.yaml
+N:	sophgo
+K:	sophgo
 
 SOUND
 M:	Jaroslav Kysela <perex@perex.cz>
@@ -20958,6 +20973,12 @@ F:	Documentation/devicetree/bindings/phy/starfive,jh7110-usb-phy.yaml
 F:	drivers/phy/starfive/phy-jh7110-pcie.c
 F:	drivers/phy/starfive/phy-jh7110-usb.c
 
+STARFIVE JH8100 EXTERNAL INTERRUPT CONTROLLER DRIVER
+M:	Changhuang Liang <changhuang.liang@starfivetech.com>
+S:	Supported
+F:	Documentation/devicetree/bindings/interrupt-controller/starfive,jh8100-intc.yaml
+F:	drivers/irqchip/irq-starfive-jh8100-intc.c
+
 STATIC BRANCH/CALL
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Josh Poimboeuf <jpoimboe@kernel.org>
@@ -21323,6 +21344,7 @@ F:	drivers/clk/clk-sc[mp]i.c
 F:	drivers/cpufreq/sc[mp]i-cpufreq.c
 F:	drivers/firmware/arm_scmi/
 F:	drivers/firmware/arm_scpi.c
+F:	drivers/hwmon/scmi-hwmon.c
 F:	drivers/pmdomain/arm/
 F:	drivers/powercap/arm_scmi_powercap.c
 F:	drivers/regulator/scmi-regulator.c
@@ -22007,6 +22029,14 @@ F:	Documentation/devicetree/bindings/media/i2c/ti,ds90*
 F:	drivers/media/i2c/ds90*
 F:	include/media/i2c/ds90*
 
+TI HDC302X HUMIDITY DRIVER
+M:	Javier Carrasco <javier.carrasco.cruz@gmail.com>
+M:	Li peiyu <579lpy@gmail.com>
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
+F:	drivers/iio/humidity/hdc3020.c
+
 TI ICSSG ETHERNET DRIVER (ICSSG)
 R:	MD Danish Anwar <danishanwar@ti.com>
 R:	Roger Quadros <rogerq@kernel.org>
@@ -22862,9 +22892,8 @@ S:	Maintained
 F:	drivers/usb/typec/mux/pi3usb30532.c
 
 USB TYPEC PORT CONTROLLER DRIVERS
-M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-usb@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/typec/tcpm/
 
 USB UHCI DRIVER
@@ -24127,7 +24156,7 @@ F:	Documentation/devicetree/bindings/net/can/xilinx,can.yaml
 F:	drivers/net/can/xilinx_can.c
 
 XILINX EVENT MANAGEMENT DRIVER
-M:	Abhyuday Godhasara <abhyuday.godhasara@xilinx.com>
+M:	Michal Simek <michal.simek@amd.com>
 S:	Maintained
 F:	drivers/soc/xilinx/xlnx_event_manager.c
 F:	include/linux/firmware/xlnx-event-manager.h
@@ -24341,13 +24370,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs.git
 F:	Documentation/filesystems/zonefs.rst
 F:	fs/zonefs/
 
-ZPOOL COMPRESSED PAGE STORAGE API
-M:	Dan Streetman <ddstreet@ieee.org>
-L:	linux-mm@kvack.org
-S:	Maintained
-F:	include/linux/zpool.h
-F:	mm/zpool.c
-
 ZR36067 VIDEO FOR LINUX DRIVER
 M:	Corentin Labbe <clabbe@baylibre.com>
 L:	mjpeg-users@lists.sourceforge.net
@@ -24399,7 +24421,9 @@ M:	Nhat Pham <nphamcs@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/admin-guide/mm/zswap.rst
+F:	include/linux/zpool.h
 F:	include/linux/zswap.h
+F:	mm/zpool.c
 F:	mm/zswap.c
 
 THE REST
diff --git a/Makefile b/Makefile
index 6c0a4d294444..d18fa2a6240d 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
@@ -294,15 +294,15 @@ may-sync-config	:= 1
 single-build	:=
 
 ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
+    ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
 		need-config :=
-	endif
+    endif
 endif
 
 ifneq ($(filter $(no-sync-config-targets), $(MAKECMDGOALS)),)
-	ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
+    ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
 		may-sync-config :=
-	endif
+    endif
 endif
 
 need-compiler := $(may-sync-config)
@@ -323,9 +323,9 @@ endif
 # We cannot build single targets and the others at the same time
 ifneq ($(filter $(single-targets), $(MAKECMDGOALS)),)
 	single-build := 1
-	ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
+    ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
 		mixed-build := 1
-	endif
+    endif
 endif
 
 # For "make -j clean all", "make -j mrproper defconfig all", etc.
@@ -1201,7 +1201,7 @@ prepare0: archprepare
 # All the preparing..
 prepare: prepare0
 ifdef CONFIG_RUST
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh
 	$(Q)$(MAKE) $(build)=rust
 endif
 
@@ -1666,7 +1666,7 @@ help:
 	@echo  '                       (sparse by default)'
 	@echo  '  make C=2   [targets] Force check of all c source with $$CHECK'
 	@echo  '  make RECORDMCOUNT_WARN=1 [targets] Warn about ignored mcount sections'
-	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3 where'
+	@echo  '  make W=n   [targets] Enable extra build checks, n=1,2,3,c,e where'
 	@echo  '		1: warnings which may be relevant and do not occur too often'
 	@echo  '		2: warnings which occur quite often but may still be relevant'
 	@echo  '		3: more obscure warnings, can most likely be ignored'
@@ -1711,7 +1711,7 @@ $(DOC_TARGETS):
 # "Is Rust available?" target
 PHONY += rustavailable
 rustavailable:
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
+	+$(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh && echo "Rust is available!"
 
 # Documentation target
 #
diff --git a/arch/Kconfig b/arch/Kconfig
index c91917b50873..fd18b7db2c77 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -673,6 +673,7 @@ config SHADOW_CALL_STACK
 	bool "Shadow Call Stack"
 	depends on ARCH_SUPPORTS_SHADOW_CALL_STACK
 	depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER
+	depends on MMU
 	help
 	  This option enables the compiler's Shadow Call Stack, which
 	  uses a shadow stack to protect function return addresses from
@@ -1077,17 +1078,107 @@ config HAVE_ARCH_COMPAT_MMAP_BASES
 	  and vice-versa 32-bit applications to call 64-bit mmap().
 	  Required for applications doing different bitness syscalls.
 
+config HAVE_PAGE_SIZE_4KB
+	bool
+
+config HAVE_PAGE_SIZE_8KB
+	bool
+
+config HAVE_PAGE_SIZE_16KB
+	bool
+
+config HAVE_PAGE_SIZE_32KB
+	bool
+
+config HAVE_PAGE_SIZE_64KB
+	bool
+
+config HAVE_PAGE_SIZE_256KB
+	bool
+
+choice
+	prompt "MMU page size"
+
+config PAGE_SIZE_4KB
+	bool "4KiB pages"
+	depends on HAVE_PAGE_SIZE_4KB
+	help
+	  This option select the standard 4KiB Linux page size and the only
+	  available option on many architectures. Using 4KiB page size will
+	  minimize memory consumption and is therefore recommended for low
+	  memory systems.
+	  Some software that is written for x86 systems makes incorrect
+	  assumptions about the page size and only runs on 4KiB pages.
+
+config PAGE_SIZE_8KB
+	bool "8KiB pages"
+	depends on HAVE_PAGE_SIZE_8KB
+	help
+	  This option is the only supported page size on a few older
+	  processors, and can be slightly faster than 4KiB pages.
+
+config PAGE_SIZE_16KB
+	bool "16KiB pages"
+	depends on HAVE_PAGE_SIZE_16KB
+	help
+	  This option is usually a good compromise between memory
+	  consumption and performance for typical desktop and server
+	  workloads, often saving a level of page table lookups compared
+	  to 4KB pages as well as reducing TLB pressure and overhead of
+	  per-page operations in the kernel at the expense of a larger
+	  page cache.
+
+config PAGE_SIZE_32KB
+	bool "32KiB pages"
+	depends on HAVE_PAGE_SIZE_32KB
+	help
+	  Using 32KiB page size will result in slightly higher performance
+	  kernel at the price of higher memory consumption compared to
+	  16KiB pages.	This option is available only on cnMIPS cores.
+	  Note that you will need a suitable Linux distribution to
+	  support this.
+
+config PAGE_SIZE_64KB
+	bool "64KiB pages"
+	depends on HAVE_PAGE_SIZE_64KB
+	help
+	  Using 64KiB page size will result in slightly higher performance
+	  kernel at the price of much higher memory consumption compared to
+	  4KiB or 16KiB pages.
+	  This is not suitable for general-purpose workloads but the
+	  better performance may be worth the cost for certain types of
+	  supercomputing or database applications that work mostly with
+	  large in-memory data rather than small files.
+
+config PAGE_SIZE_256KB
+	bool "256KiB pages"
+	depends on HAVE_PAGE_SIZE_256KB
+	help
+	  256KiB pages have little practical value due to their extreme
+	  memory usage.  The kernel will only be able to run applications
+	  that have been compiled with '-zmax-page-size' set to 256KiB
+	  (the default is 64KiB or 4KiB on most architectures).
+
+endchoice
+
 config PAGE_SIZE_LESS_THAN_64KB
 	def_bool y
-	depends on !ARM64_64K_PAGES
 	depends on !PAGE_SIZE_64KB
-	depends on !PARISC_PAGE_SIZE_64KB
 	depends on PAGE_SIZE_LESS_THAN_256KB
 
 config PAGE_SIZE_LESS_THAN_256KB
 	def_bool y
 	depends on !PAGE_SIZE_256KB
 
+config PAGE_SHIFT
+	int
+	default 12 if PAGE_SIZE_4KB
+	default 13 if PAGE_SIZE_8KB
+	default 14 if PAGE_SIZE_16KB
+	default 15 if PAGE_SIZE_32KB
+	default 16 if PAGE_SIZE_64KB
+	default 18 if PAGE_SIZE_256KB
+
 # This allows to use a set of generic functions to determine mmap base
 # address by giving priority to top-down scheme only if the process
 # is not in legacy mode (compat task, unlimited stack size or
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index d6968d090d49..4f490250d323 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -14,6 +14,7 @@ config ALPHA
 	select PCI_DOMAINS if PCI
 	select PCI_SYSCALL if PCI
 	select HAVE_ASM_MODVERSIONS
+	select HAVE_PAGE_SIZE_8KB
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select NEED_DMA_MAP_STATE
diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h
index 4db1ebc0ed99..70419e6be1a3 100644
--- a/arch/alpha/include/asm/page.h
+++ b/arch/alpha/include/asm/page.h
@@ -6,7 +6,7 @@
 #include <asm/pal.h>
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	13
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 7439b2377df5..8e9dd63b220c 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -467,11 +467,6 @@ smp_prepare_cpus(unsigned int max_cpus)
 	smp_num_cpus = smp_num_probed;
 }
 
-void
-smp_prepare_boot_cpu(void)
-{
-}
-
 int
 __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 1b0483c51cc1..4092bec198be 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -284,14 +284,17 @@ choice
 
 config ARC_PAGE_SIZE_8K
 	bool "8KB"
+	select HAVE_PAGE_SIZE_8KB
 	help
 	  Choose between 8k vs 16k
 
 config ARC_PAGE_SIZE_16K
+	select HAVE_PAGE_SIZE_16KB
 	bool "16KB"
 
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
+	select HAVE_PAGE_SIZE_4KB
 	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index 9d9618079739..a339223d9e05 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -31,7 +31,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "nop							\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
@@ -47,7 +47,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "b %l[l_yes]						\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h
index 2a4ad619abfb..7fd9e741b527 100644
--- a/arch/arc/include/uapi/asm/page.h
+++ b/arch/arc/include/uapi/asm/page.h
@@ -13,10 +13,8 @@
 #include <linux/const.h>
 
 /* PAGE_SHIFT determines the page size */
-#if defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define PAGE_SHIFT 14
-#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define PAGE_SHIFT 12
+#ifdef __KERNEL__
+#define PAGE_SHIFT CONFIG_PAGE_SHIFT
 #else
 /*
  * Default 8k
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 8d9b188caa27..b2f2c59279a6 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -39,11 +39,6 @@ struct plat_smp_ops  __weak plat_smp_ops;
 /* XXX: per cpu ? Only needed once in early secondary boot */
 struct task_struct *secondary_idle_tsk;
 
-/* Called from start_kernel */
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask)
 {
 	unsigned long dt_root = of_get_flat_dt_root();
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0af6709570d1..9d52ba3a8ad1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -116,6 +116,7 @@ config ARM
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_OPTPROBES if !THUMB2_KERNEL
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCI if MMU
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 473280d5adce..d82908b1b1bb 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -158,9 +158,7 @@ textofs-$(CONFIG_ARCH_REALTEK)  := 0x00108000
 ifeq ($(CONFIG_ARCH_SA1100),y)
 textofs-$(CONFIG_SA1111) := 0x00208000
 endif
-textofs-$(CONFIG_ARCH_IPQ40XX) := 0x00208000
-textofs-$(CONFIG_ARCH_MSM8X60) := 0x00208000
-textofs-$(CONFIG_ARCH_MSM8960) := 0x00208000
+textofs-$(CONFIG_ARCH_QCOM_RESERVE_SMEM) := 0x00208000
 textofs-$(CONFIG_ARCH_MESON) := 0x00208000
 textofs-$(CONFIG_ARCH_AXXIA) := 0x00308000
 
diff --git a/arch/arm/boot/dts/allwinner/sun8i-r40-feta40i.dtsi b/arch/arm/boot/dts/allwinner/sun8i-r40-feta40i.dtsi
index 9f39b5a2bb35..c12361d0317f 100644
--- a/arch/arm/boot/dts/allwinner/sun8i-r40-feta40i.dtsi
+++ b/arch/arm/boot/dts/allwinner/sun8i-r40-feta40i.dtsi
@@ -42,6 +42,13 @@
 	vcc-pg-supply = <&reg_dldo1>;
 };
 
+&reg_aldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-3v3-tv-usb";
+};
+
 &reg_aldo2 {
 	regulator-always-on;
 	regulator-min-microvolt = <1800000>;
diff --git a/arch/arm/boot/dts/amazon/alpine.dtsi b/arch/arm/boot/dts/amazon/alpine.dtsi
index ff68dfb4eb78..90bd12feac01 100644
--- a/arch/arm/boot/dts/amazon/alpine.dtsi
+++ b/arch/arm/boot/dts/amazon/alpine.dtsi
@@ -167,7 +167,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <96>;
 			al,msi-num-spis = <64>;
diff --git a/arch/arm/boot/dts/amlogic/meson.dtsi b/arch/arm/boot/dts/amlogic/meson.dtsi
index 8e3860d5d916..8cb0fc78b2af 100644
--- a/arch/arm/boot/dts/amlogic/meson.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson.dtsi
@@ -23,7 +23,7 @@
 		#size-cells = <1>;
 		ranges;
 
-		cbus: cbus@c1100000 {
+		cbus: bus@c1100000 {
 			compatible = "simple-bus";
 			reg = <0xc1100000 0x200000>;
 			#address-cells = <1>;
@@ -206,7 +206,7 @@
 			};
 		};
 
-		aobus: aobus@c8100000 {
+		aobus: bus@c8100000 {
 			compatible = "simple-bus";
 			reg = <0xc8100000 0x100000>;
 			#address-cells = <1>;
@@ -302,7 +302,7 @@
 			reg = <0xd9040000 0x10000>;
 		};
 
-		secbus: secbus@da000000 {
+		secbus: bus@da000000 {
 			compatible = "simple-bus";
 			reg = <0xda000000 0x6000>;
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/amlogic/meson8.dtsi b/arch/arm/boot/dts/amlogic/meson8.dtsi
index 59932fbfd5d5..f57be9ae150f 100644
--- a/arch/arm/boot/dts/amlogic/meson8.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8.dtsi
@@ -645,7 +645,6 @@
 };
 
 &hwrng {
-	compatible = "amlogic,meson8-rng", "amlogic,meson-rng";
 	clocks = <&clkc CLKID_RNG0>;
 	clock-names = "core";
 };
diff --git a/arch/arm/boot/dts/amlogic/meson8b.dtsi b/arch/arm/boot/dts/amlogic/meson8b.dtsi
index 5198f5177c2c..2d9d24d3a95d 100644
--- a/arch/arm/boot/dts/amlogic/meson8b.dtsi
+++ b/arch/arm/boot/dts/amlogic/meson8b.dtsi
@@ -620,7 +620,6 @@
 };
 
 &hwrng {
-	compatible = "amlogic,meson8b-rng", "amlogic,meson-rng";
 	clocks = <&clkc CLKID_RNG0>;
 	clock-names = "core";
 };
diff --git a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts
index efed325af88d..d99bac02232b 100644
--- a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts
+++ b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts
@@ -451,7 +451,7 @@
 
 		/* Direct-mapped development chip ROM */
 		pb1176_rom@10200000 {
-			compatible = "direct-mapped";
+			compatible = "mtd-rom";
 			reg = <0x10200000 0x4000>;
 			bank-width = <1>;
 		};
diff --git a/arch/arm/boot/dts/arm/integratorap-im-pd1.dts b/arch/arm/boot/dts/arm/integratorap-im-pd1.dts
index 7072a70da00d..367850ea0912 100644
--- a/arch/arm/boot/dts/arm/integratorap-im-pd1.dts
+++ b/arch/arm/boot/dts/arm/integratorap-im-pd1.dts
@@ -129,8 +129,6 @@
 
 	bridge {
 		compatible = "ti,ths8134b", "ti,ths8134";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		ports {
 			#address-cells = <1>;
@@ -154,6 +152,7 @@
 
 	vga {
 		compatible = "vga-connector";
+		label = "J30";
 
 		port {
 			vga_con_in: endpoint {
diff --git a/arch/arm/boot/dts/arm/versatile-ab.dts b/arch/arm/boot/dts/arm/versatile-ab.dts
index f31dcf7e5862..de45aa99e260 100644
--- a/arch/arm/boot/dts/arm/versatile-ab.dts
+++ b/arch/arm/boot/dts/arm/versatile-ab.dts
@@ -32,8 +32,6 @@
 
 	bridge {
 		compatible = "ti,ths8134b", "ti,ths8134";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		ports {
 			#address-cells = <1>;
@@ -59,6 +57,7 @@
 
 	vga {
 		compatible = "vga-connector";
+		label = "J1";
 
 		port {
 			vga_con_in: endpoint {
diff --git a/arch/arm/boot/dts/arm/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/arm/vexpress-v2p-ca9.dts
index 5916e4877eac..8bf35666412b 100644
--- a/arch/arm/boot/dts/arm/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/arm/vexpress-v2p-ca9.dts
@@ -20,7 +20,9 @@
 	#address-cells = <1>;
 	#size-cells = <1>;
 
-	chosen { };
+	chosen {
+		stdout-path = &v2m_serial0;
+	};
 
 	aliases {
 		serial0 = &v2m_serial0;
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
index 530491ae5eb2..857cb26ed6d7 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g4.dtsi
@@ -466,7 +466,6 @@
 	i2c0: i2c-bus@40 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -482,7 +481,6 @@
 	i2c1: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -498,7 +496,6 @@
 	i2c2: i2c-bus@c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -515,7 +512,6 @@
 	i2c3: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -532,7 +528,6 @@
 	i2c4: i2c-bus@140 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -549,7 +544,6 @@
 	i2c5: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -566,7 +560,6 @@
 	i2c6: i2c-bus@1c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -583,7 +576,6 @@
 	i2c7: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -600,7 +592,6 @@
 	i2c8: i2c-bus@340 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -617,7 +608,6 @@
 	i2c9: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -634,7 +624,6 @@
 	i2c10: i2c-bus@3c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -651,7 +640,6 @@
 	i2c11: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -668,7 +656,6 @@
 	i2c12: i2c-bus@440 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
@@ -685,7 +672,6 @@
 	i2c13: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2400-i2c-bus";
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
index 04f98d1dbb97..e6f3cf3c721e 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g5.dtsi
@@ -363,6 +363,7 @@
 				interrupts = <40>;
 				reg = <0x1e780200 0x0100>;
 				clocks = <&syscon ASPEED_CLK_APB>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -594,7 +595,6 @@
 	i2c0: i2c-bus@40 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x40 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -610,7 +610,6 @@
 	i2c1: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x80 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -626,7 +625,6 @@
 	i2c2: i2c-bus@c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0xc0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -643,7 +641,6 @@
 	i2c3: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x100 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -660,7 +657,6 @@
 	i2c4: i2c-bus@140 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x140 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -677,7 +673,6 @@
 	i2c5: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x180 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -694,7 +689,6 @@
 	i2c6: i2c-bus@1c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x1c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -711,7 +705,6 @@
 	i2c7: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x300 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -728,7 +721,6 @@
 	i2c8: i2c-bus@340 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x340 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -745,7 +737,6 @@
 	i2c9: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x380 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -762,7 +753,6 @@
 	i2c10: i2c-bus@3c0 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x3c0 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -779,7 +769,6 @@
 	i2c11: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x400 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -796,7 +785,6 @@
 	i2c12: i2c-bus@440 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x440 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
@@ -813,7 +801,6 @@
 	i2c13: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 
 		reg = <0x480 0x40>;
 		compatible = "aspeed,ast2500-i2c-bus";
diff --git a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
index c4d1faade8be..29f94696d8b1 100644
--- a/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
+++ b/arch/arm/boot/dts/aspeed/aspeed-g6.dtsi
@@ -474,6 +474,7 @@
 				reg = <0x1e780500 0x100>;
 				interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&syscon ASPEED_CLK_APB2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -488,6 +489,7 @@
 				reg = <0x1e780600 0x100>;
 				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&syscon ASPEED_CLK_APB2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				bus-frequency = <12000000>;
 				pinctrl-names = "default";
@@ -902,7 +904,6 @@
 	i2c0: i2c-bus@80 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x80 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -917,7 +918,6 @@
 	i2c1: i2c-bus@100 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x100 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -932,7 +932,6 @@
 	i2c2: i2c-bus@180 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x180 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -947,7 +946,6 @@
 	i2c3: i2c-bus@200 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x200 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -962,7 +960,6 @@
 	i2c4: i2c-bus@280 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x280 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -977,7 +974,6 @@
 	i2c5: i2c-bus@300 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x300 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -992,7 +988,6 @@
 	i2c6: i2c-bus@380 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x380 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1007,7 +1002,6 @@
 	i2c7: i2c-bus@400 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x400 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1022,7 +1016,6 @@
 	i2c8: i2c-bus@480 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x480 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1037,7 +1030,6 @@
 	i2c9: i2c-bus@500 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x500 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1052,7 +1044,6 @@
 	i2c10: i2c-bus@580 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x580 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1067,7 +1058,6 @@
 	i2c11: i2c-bus@600 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x600 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1082,7 +1072,6 @@
 	i2c12: i2c-bus@680 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x680 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1097,7 +1086,6 @@
 	i2c13: i2c-bus@700 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x700 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1112,7 +1100,6 @@
 	i2c14: i2c-bus@780 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x780 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
@@ -1127,7 +1114,6 @@
 	i2c15: i2c-bus@800 {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		#interrupt-cells = <1>;
 		reg = <0x800 0x80>;
 		compatible = "aspeed,ast2600-i2c-bus";
 		clocks = <&syscon ASPEED_CLK_APB2>;
diff --git a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
index f9f79ed82518..07ca0d993c9f 100644
--- a/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-cygnus.dtsi
@@ -167,6 +167,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&mailbox>;
 			interrupts = <0>;
 		};
@@ -247,6 +248,7 @@
 			gpio-controller;
 			interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		i2c1: i2c@1800b000 {
@@ -518,6 +520,7 @@
 			gpio-controller;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinctrl 0 42 1>,
 					<&pinctrl 1 44 3>,
diff --git a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
index 788a6806191a..75545b10ef2f 100644
--- a/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-hr2.dtsi
@@ -200,6 +200,7 @@
 			gpio-controller;
 			ngpios = <4>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
index 9d20ba3b1ffb..6a4482c93167 100644
--- a/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm-nsp.dtsi
@@ -180,6 +180,7 @@
 			gpio-controller;
 			ngpios = <32>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinctrl 0 0 32>;
 		};
@@ -352,6 +353,7 @@
 			gpio-controller;
 			ngpios = <4>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm/boot/dts/gemini/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini/gemini-dlink-dir-685.dts
index 396149664297..b4dbcf8f168e 100644
--- a/arch/arm/boot/dts/gemini/gemini-dlink-dir-685.dts
+++ b/arch/arm/boot/dts/gemini/gemini-dlink-dir-685.dts
@@ -27,10 +27,10 @@
 	gpio_keys {
 		compatible = "gpio-keys";
 
-		button-esc {
+		button-reset {
 			debounce-interval = <100>;
 			wakeup-source;
-			linux,code = <KEY_ESC>;
+			linux,code = <KEY_RESTART>;
 			label = "reset";
 			/* Collides with LPC_LAD[0], UART DCD, SSP 97RST */
 			gpios = <&gpio0 8 GPIO_ACTIVE_LOW>;
@@ -187,7 +187,7 @@
 	};
 
 	/* This is a RealTek RTL8366RB switch and PHY using SMI over GPIO */
-	switch {
+	ethernet-switch {
 		compatible = "realtek,rtl8366rb";
 		/* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */
 		mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
@@ -204,36 +204,36 @@
 			#interrupt-cells = <1>;
 		};
 
-		ports {
+		ethernet-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			port@0 {
+			ethernet-port@0 {
 				reg = <0>;
 				label = "lan0";
 				phy-handle = <&phy0>;
 			};
-			port@1 {
+			ethernet-port@1 {
 				reg = <1>;
 				label = "lan1";
 				phy-handle = <&phy1>;
 			};
-			port@2 {
+			ethernet-port@2 {
 				reg = <2>;
 				label = "lan2";
 				phy-handle = <&phy2>;
 			};
-			port@3 {
+			ethernet-port@3 {
 				reg = <3>;
 				label = "lan3";
 				phy-handle = <&phy3>;
 			};
-			port@4 {
+			ethernet-port@4 {
 				reg = <4>;
 				label = "wan";
 				phy-handle = <&phy4>;
 			};
-			rtl8366rb_cpu_port: port@5 {
+			rtl8366rb_cpu_port: ethernet-port@5 {
 				reg = <5>;
 				label = "cpu";
 				ethernet = <&gmac0>;
@@ -252,27 +252,27 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			phy0: phy@0 {
+			phy0: ethernet-phy@0 {
 				reg = <0>;
 				interrupt-parent = <&switch_intc>;
 				interrupts = <0>;
 			};
-			phy1: phy@1 {
+			phy1: ethernet-phy@1 {
 				reg = <1>;
 				interrupt-parent = <&switch_intc>;
 				interrupts = <1>;
 			};
-			phy2: phy@2 {
+			phy2: ethernet-phy@2 {
 				reg = <2>;
 				interrupt-parent = <&switch_intc>;
 				interrupts = <2>;
 			};
-			phy3: phy@3 {
+			phy3: ethernet-phy@3 {
 				reg = <3>;
 				interrupt-parent = <&switch_intc>;
 				interrupts = <3>;
 			};
-			phy4: phy@4 {
+			phy4: ethernet-phy@4 {
 				reg = <4>;
 				interrupt-parent = <&switch_intc>;
 				interrupts = <12>;
diff --git a/arch/arm/boot/dts/gemini/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini/gemini-dlink-dns-313.dts
index 138c47e1ac1b..8c54d3a5a721 100644
--- a/arch/arm/boot/dts/gemini/gemini-dlink-dns-313.dts
+++ b/arch/arm/boot/dts/gemini/gemini-dlink-dns-313.dts
@@ -33,10 +33,10 @@
 	gpio_keys {
 		compatible = "gpio-keys";
 
-		button-esc {
+		button-reset {
 			debounce-interval = <100>;
 			wakeup-source;
-			linux,code = <KEY_ESC>;
+			linux,code = <KEY_RESTART>;
 			label = "reset";
 			gpios = <&gpio1 31 GPIO_ACTIVE_LOW>;
 		};
diff --git a/arch/arm/boot/dts/gemini/gemini-sl93512r.dts b/arch/arm/boot/dts/gemini/gemini-sl93512r.dts
index 91c19e8ebfe8..4992ec276de9 100644
--- a/arch/arm/boot/dts/gemini/gemini-sl93512r.dts
+++ b/arch/arm/boot/dts/gemini/gemini-sl93512r.dts
@@ -43,7 +43,7 @@
 		button-setup {
 			debounce-interval = <50>;
 			wakeup-source;
-			linux,code = <KEY_SETUP>;
+			linux,code = <KEY_RESTART>;
 			label = "factory reset";
 			/* Conflict with NAND flash */
 			gpios = <&gpio0 18 GPIO_ACTIVE_LOW>;
@@ -93,7 +93,7 @@
 		cs-gpios = <&gpio1 31 GPIO_ACTIVE_HIGH>;
 		num-chipselects = <1>;
 
-		switch@0 {
+		ethernet-switch@0 {
 			compatible = "vitesse,vsc7385";
 			reg = <0>;
 			/* Specified for 2.5 MHz or below */
@@ -101,27 +101,27 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					label = "lan1";
 				};
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "lan2";
 				};
-				port@2 {
+				ethernet-port@2 {
 					reg = <2>;
 					label = "lan3";
 				};
-				port@3 {
+				ethernet-port@3 {
 					reg = <3>;
 					label = "lan4";
 				};
-				vsc: port@6 {
+				vsc: ethernet-port@6 {
 					reg = <6>;
 					label = "cpu";
 					ethernet = <&gmac1>;
diff --git a/arch/arm/boot/dts/gemini/gemini-sq201.dts b/arch/arm/boot/dts/gemini/gemini-sq201.dts
index d0efd76695da..f8c6f6e5cdea 100644
--- a/arch/arm/boot/dts/gemini/gemini-sq201.dts
+++ b/arch/arm/boot/dts/gemini/gemini-sq201.dts
@@ -30,7 +30,7 @@
 		button-setup {
 			debounce-interval = <100>;
 			wakeup-source;
-			linux,code = <KEY_SETUP>;
+			linux,code = <KEY_RESTART>;
 			label = "factory reset";
 			/* Conflict with NAND flash */
 			gpios = <&gpio0 18 GPIO_ACTIVE_LOW>;
@@ -78,7 +78,7 @@
 		cs-gpios = <&gpio1 31 GPIO_ACTIVE_HIGH>;
 		num-chipselects = <1>;
 
-		switch@0 {
+		ethernet-switch@0 {
 			compatible = "vitesse,vsc7395";
 			reg = <0>;
 			/* Specified for 2.5 MHz or below */
@@ -86,27 +86,27 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 
-			ports {
+			ethernet-ports {
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				port@0 {
+				ethernet-port@0 {
 					reg = <0>;
 					label = "lan1";
 				};
-				port@1 {
+				ethernet-port@1 {
 					reg = <1>;
 					label = "lan2";
 				};
-				port@2 {
+				ethernet-port@2 {
 					reg = <2>;
 					label = "lan3";
 				};
-				port@3 {
+				ethernet-port@3 {
 					reg = <3>;
 					label = "lan4";
 				};
-				vsc: port@6 {
+				vsc: ethernet-port@6 {
 					reg = <6>;
 					label = "cpu";
 					ethernet = <&gmac1>;
diff --git a/arch/arm/boot/dts/gemini/gemini-wbd111.dts b/arch/arm/boot/dts/gemini/gemini-wbd111.dts
index 3c88c59ab481..6a0c89e0c918 100644
--- a/arch/arm/boot/dts/gemini/gemini-wbd111.dts
+++ b/arch/arm/boot/dts/gemini/gemini-wbd111.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "Wiliboard WBD-111";
-	compatible = "wiliboard,wbd111", "cortina,gemini";
+	compatible = "wiligear,wiliboard-wbd111", "cortina,gemini";
 	#address-cells = <1>;
 	#size-cells = <1>;
 
@@ -28,10 +28,10 @@
 	gpio_keys {
 		compatible = "gpio-keys";
 
-		button-setup {
+		button-reset {
 			debounce-interval = <100>;
 			wakeup-source;
-			linux,code = <KEY_SETUP>;
+			linux,code = <KEY_RESTART>;
 			label = "reset";
 			/* Conflict with ICE */
 			gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/boot/dts/gemini/gemini-wbd222.dts b/arch/arm/boot/dts/gemini/gemini-wbd222.dts
index ff72bbc4db3e..d8b34ebad4b0 100644
--- a/arch/arm/boot/dts/gemini/gemini-wbd222.dts
+++ b/arch/arm/boot/dts/gemini/gemini-wbd222.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "Wiliboard WBD-222";
-	compatible = "wiliboard,wbd222", "cortina,gemini";
+	compatible = "wiligear,wiliboard-wbd222", "cortina,gemini";
 	#address-cells = <1>;
 	#size-cells = <1>;
 
@@ -27,10 +27,10 @@
 	gpio_keys {
 		compatible = "gpio-keys";
 
-		button-setup {
+		button-reset {
 			debounce-interval = <100>;
 			wakeup-source;
-			linux,code = <KEY_SETUP>;
+			linux,code = <KEY_RESTART>;
 			label = "reset";
 			/* Conflict with ICE */
 			gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
index 4d70f6afd13a..6d5e69035f94 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-gateway-7001.dts
@@ -60,6 +60,8 @@
 			 * We have slots (IDSEL) 1 and 2 with one assigned IRQ
 			 * each handling all IRQs.
 			 */
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0xf800 0 0 7>;
 			interrupt-map =
 			/* IDSEL 1 */
 			<0x0800 0 0 1 &gpio0 11 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 1 is irq 11 */
diff --git a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
index 9ec0169bacf8..5f4c849915db 100644
--- a/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
+++ b/arch/arm/boot/dts/intel/ixp/intel-ixp42x-goramo-multilink.dts
@@ -89,6 +89,8 @@
 			 * The slots have Ethernet, Ethernet, NEC and MPCI.
 			 * The IDSELs are 11, 12, 13, 14.
 			 */
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0xf800 0 0 7>;
 			interrupt-map =
 			/* IDSEL 11 - Ethernet A */
 			<0x5800 0 0 1 &gpio0 4 IRQ_TYPE_LEVEL_LOW>, /* INT A on slot 11 is irq 4 */
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
index 1707d1b01545..cb85f8e31dfc 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-l8.dts
@@ -4,6 +4,18 @@
 
 / {
 	model = "SolidRun Clearfog GTR L8";
+	compatible = "solidrun,clearfog-gtr-l8", "marvell,armada385",
+		     "marvell,armada380";
+
+	/* CON25 */
+	sfp1: sfp-1 {
+		compatible = "sff,sfp";
+		pinctrl-0 = <&cf_gtr_sfp1_pins>;
+		pinctrl-names = "default";
+		i2c-bus = <&i2c0>;
+		mod-def0-gpio = <&gpio0 24 GPIO_ACTIVE_LOW>;
+		tx-disable-gpio = <&gpio1 22 GPIO_ACTIVE_HIGH>;
+	};
 };
 
 &mdio {
@@ -20,57 +32,65 @@
 
 			ethernet-port@1 {
 				reg = <1>;
-				label = "lan8";
+				label = "lan1";
 				phy-handle = <&switch0phy0>;
 			};
 
 			ethernet-port@2 {
 				reg = <2>;
-				label = "lan7";
+				label = "lan2";
 				phy-handle = <&switch0phy1>;
 			};
 
 			ethernet-port@3 {
 				reg = <3>;
-				label = "lan6";
+				label = "lan3";
 				phy-handle = <&switch0phy2>;
 			};
 
 			ethernet-port@4 {
 				reg = <4>;
-				label = "lan5";
+				label = "lan4";
 				phy-handle = <&switch0phy3>;
 			};
 
 			ethernet-port@5 {
 				reg = <5>;
-				label = "lan4";
+				label = "lan5";
 				phy-handle = <&switch0phy4>;
 			};
 
 			ethernet-port@6 {
 				reg = <6>;
-				label = "lan3";
+				label = "lan6";
 				phy-handle = <&switch0phy5>;
 			};
 
 			ethernet-port@7 {
 				reg = <7>;
-				label = "lan2";
+				label = "lan7";
 				phy-handle = <&switch0phy6>;
 			};
 
 			ethernet-port@8 {
 				reg = <8>;
-				label = "lan1";
+				label = "lan8";
 				phy-handle = <&switch0phy7>;
 			};
 
+			ethernet-port@9 {
+				reg = <9>;
+				label = "lan-sfp";
+				phy-mode = "sgmii";
+				sfp = <&sfp1>;
+				managed = "in-band-status";
+			};
+
 			ethernet-port@10 {
 				reg = <10>;
 				phy-mode = "2500base-x";
-
 				ethernet = <&eth1>;
+
 				fixed-link {
 					speed = <2500>;
 					full-duplex;
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
index a7678a784c18..5f83d981449a 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr-s4.dts
@@ -4,6 +4,8 @@
 
 / {
 	model = "SolidRun Clearfog GTR S4";
+	compatible = "solidrun,clearfog-gtr-s4", "marvell,armada385",
+		     "marvell,armada380";
 };
 
 &sfp0 {
diff --git a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
index d1452a04e904..f3a3cb6ac311 100644
--- a/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
+++ b/arch/arm/boot/dts/marvell/armada-385-clearfog-gtr.dtsi
@@ -141,18 +141,13 @@
 			};
 
 			pinctrl@18000 {
-				cf_gtr_switch_reset_pins: cf-gtr-switch-reset-pins {
-					marvell,pins = "mpp18";
-					marvell,function = "gpio";
-				};
-
-				cf_gtr_usb3_con_vbus: cf-gtr-usb3-con-vbus {
-					marvell,pins = "mpp22";
+				cf_gtr_fan_pwm: cf-gtr-fan-pwm {
+					marvell,pins = "mpp23";
 					marvell,function = "gpio";
 				};
 
-				cf_gtr_fan_pwm: cf-gtr-fan-pwm {
-					marvell,pins = "mpp23";
+				cf_gtr_front_button_pins: cf-gtr-front-button-pins {
+					marvell,pins = "mpp53";
 					marvell,function = "gpio";
 				};
 
@@ -162,6 +157,37 @@
 					marvell,function = "i2c1";
 				};
 
+				cf_gtr_isolation_pins: cf-gtr-isolation-pins {
+					marvell,pins = "mpp47";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_led_pins: led-pins {
+					marvell,pins = "mpp42", "mpp52";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_lte_disable_pins: lte-disable-pins {
+					marvell,pins = "mpp34";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_pci_pins: pci-pins {
+					// pci reset
+					marvell,pins = "mpp33", "mpp35", "mpp44";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_poe_reset_pins: cf-gtr-poe-reset-pins {
+					marvell,pins = "mpp48";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_rear_button_pins: cf-gtr-rear-button-pins {
+					marvell,pins = "mpp36";
+					marvell,function = "gpio";
+				};
+
 				cf_gtr_sdhci_pins: cf-gtr-sdhci-pins {
 					marvell,pins = "mpp21", "mpp28",
 						       "mpp37", "mpp38",
@@ -169,13 +195,15 @@
 					marvell,function = "sd0";
 				};
 
-				cf_gtr_isolation_pins: cf-gtr-isolation-pins {
-					marvell,pins = "mpp47";
+				cf_gtr_sfp0_pins: sfp0-pins {
+					/* sfp modabs, txdisable */
+					marvell,pins = "mpp25", "mpp46";
 					marvell,function = "gpio";
 				};
 
-				cf_gtr_poe_reset_pins: cf-gtr-poe-reset-pins {
-					marvell,pins = "mpp48";
+				cf_gtr_sfp1_pins: sfp1-pins {
+					/* sfp modabs, txdisable */
+					marvell,pins = "mpp24", "mpp54";
 					marvell,function = "gpio";
 				};
 
@@ -184,13 +212,18 @@
 					marvell,function = "spi1";
 				};
 
-				cf_gtr_front_button_pins: cf-gtr-front-button-pins {
-					marvell,pins = "mpp53";
+				cf_gtr_switch_reset_pins: cf-gtr-switch-reset-pins {
+					marvell,pins = "mpp18";
 					marvell,function = "gpio";
 				};
 
-				cf_gtr_rear_button_pins: cf-gtr-rear-button-pins {
-					marvell,pins = "mpp36";
+				cf_gtr_usb3_con_vbus: cf-gtr-usb3-con-vbus {
+					marvell,pins = "mpp22";
+					marvell,function = "gpio";
+				};
+
+				cf_gtr_wifi_disable_pins: wifi-disable-pins {
+					marvell,pins = "mpp30", "mpp31";
 					marvell,function = "gpio";
 				};
 			};
@@ -221,21 +254,26 @@
 		};
 
 		pcie {
+			pinctrl-0 = <&cf_gtr_pci_pins>;
+			pinctrl-names = "default";
 			status = "okay";
 			/*
 			 * The PCIe units are accessible through
 			 * the mini-PCIe connectors on the board.
 			 */
+			/* CON3 - serdes 0 */
 			pcie@1,0 {
 				reset-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 				status = "okay";
 			};
 
+			/* CON4 - serdes 2 */
 			pcie@2,0 {
 				reset-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
 				status = "okay";
 			};
 
+			/* CON2 - serdes 4 */
 			pcie@3,0 {
 				reset-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
 				status = "okay";
@@ -243,10 +281,12 @@
 		};
 	};
 
-	sfp0: sfp {
+	/* CON5 */
+	sfp0: sfp-0 {
 		compatible = "sff,sfp";
+		pinctrl-0 = <&cf_gtr_sfp0_pins>;
+		pinctrl-names = "default";
 		i2c-bus = <&i2c1>;
-		los-gpio = <&gpio1 22 GPIO_ACTIVE_HIGH>;
 		mod-def0-gpio = <&gpio0 25 GPIO_ACTIVE_LOW>;
 		tx-disable-gpio = <&gpio1 14 GPIO_ACTIVE_HIGH>;
 	};
@@ -273,6 +313,8 @@
 
 	gpio-leds {
 		compatible = "gpio-leds";
+		pinctrl-0 = <&cf_gtr_led_pins>;
+		pinctrl-names = "default";
 
 		led1 {
 			function = LED_FUNCTION_CPU;
@@ -408,7 +450,7 @@
 };
 
 &gpio0 {
-	pinctrl-0 = <&cf_gtr_fan_pwm>;
+	pinctrl-0 = <&cf_gtr_fan_pwm &cf_gtr_wifi_disable_pins>;
 	pinctrl-names = "default";
 
 	wifi-disable {
@@ -420,7 +462,7 @@
 };
 
 &gpio1 {
-	pinctrl-0 = <&cf_gtr_isolation_pins &cf_gtr_poe_reset_pins>;
+	pinctrl-0 = <&cf_gtr_isolation_pins &cf_gtr_poe_reset_pins &cf_gtr_lte_disable_pins>;
 	pinctrl-names = "default";
 
 	lte-disable {
diff --git a/arch/arm/boot/dts/marvell/armada-388-clearfog.dts b/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
index 3290ccad2374..09bf2e6d4ed0 100644
--- a/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
+++ b/arch/arm/boot/dts/marvell/armada-388-clearfog.dts
@@ -10,8 +10,9 @@
 
 / {
 	model = "SolidRun Clearfog A1";
-	compatible = "solidrun,clearfog-a1", "marvell,armada388",
-		"marvell,armada385", "marvell,armada380";
+	compatible = "solidrun,clearfog-pro-a1", "solidrun,clearfog-a1",
+		     "marvell,armada388", "marvell,armada385",
+		     "marvell,armada380";
 
 	soc {
 		internal-regs {
diff --git a/arch/arm/boot/dts/marvell/dove-cubox.dts b/arch/arm/boot/dts/marvell/dove-cubox.dts
index bfde99486a87..bcaaf8320c45 100644
--- a/arch/arm/boot/dts/marvell/dove-cubox.dts
+++ b/arch/arm/boot/dts/marvell/dove-cubox.dts
@@ -101,7 +101,7 @@
 		/* connect xtal input as source of pll0 and pll1 */
 		silabs,pll-source = <0 0>, <1 0>;
 
-		clkout0 {
+		clkout@0 {
 			reg = <0>;
 			silabs,drive-strength = <8>;
 			silabs,multisynth-source = <0>;
@@ -109,7 +109,7 @@
 			silabs,pll-master;
 		};
 
-		clkout2 {
+		clkout@2 {
 			reg = <2>;
 			silabs,drive-strength = <8>;
 			silabs,multisynth-source = <1>;
diff --git a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
index dffb9f84e67c..c841eb8e7fb1 100644
--- a/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
+++ b/arch/arm/boot/dts/marvell/kirkwood-l-50.dts
@@ -65,6 +65,7 @@
 			gpio2: gpio-expander@20 {
 				#gpio-cells = <2>;
 				#interrupt-cells = <2>;
+				interrupt-controller;
 				compatible = "semtech,sx1505q";
 				reg = <0x20>;
 
@@ -79,6 +80,7 @@
 			gpio3: gpio-expander@21 {
 				#gpio-cells = <2>;
 				#interrupt-cells = <2>;
+				interrupt-controller;
 				compatible = "semtech,sx1505q";
 				reg = <0x21>;
 
diff --git a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts
index 04f1ae1382e7..bc64348b8218 100644
--- a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts
+++ b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts
@@ -28,7 +28,7 @@
 &twsi1 {
 	status = "okay";
 	pmic: max8925@3c {
-		compatible = "maxium,max8925";
+		compatible = "maxim,max8925";
 		reg = <0x3c>;
 		interrupts = <1>;
 		interrupt-parent = <&intcmux4>;
diff --git a/arch/arm/boot/dts/microchip/Makefile b/arch/arm/boot/dts/microchip/Makefile
index efde9546c8f4..0c45c8d17468 100644
--- a/arch/arm/boot/dts/microchip/Makefile
+++ b/arch/arm/boot/dts/microchip/Makefile
@@ -11,6 +11,7 @@ DTC_FLAGS_at91-sama5d2_xplained := -@
 DTC_FLAGS_at91-sama5d3_eds := -@
 DTC_FLAGS_at91-sama5d3_xplained := -@
 DTC_FLAGS_at91-sama5d4_xplained := -@
+DTC_FLAGS_at91-sama7g54_curiosity := -@
 DTC_FLAGS_at91-sama7g5ek := -@
 dtb-$(CONFIG_SOC_AT91RM9200) += \
 	at91rm9200ek.dtb \
@@ -87,6 +88,7 @@ dtb-$(CONFIG_SOC_SAM_V7) += \
 	at91-sama5d4ek.dtb \
 	at91-vinco.dtb
 dtb-$(CONFIG_SOC_SAMA7G5) += \
+	at91-sama7g54_curiosity.dtb \
 	at91-sama7g5ek.dtb
 
 dtb-$(CONFIG_SOC_LAN966) += \
diff --git a/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts
new file mode 100644
index 000000000000..4f609e9e510e
--- /dev/null
+++ b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts
@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * at91-sama7g54_curiosity.dts - Device Tree file for SAMA7G54 Curiosity Board
+ *
+ * Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries
+ *
+ * Author: Mihai Sain <mihai.sain@microchip.com>
+ *
+ */
+/dts-v1/;
+#include "sama7g5-pinfunc.h"
+#include "sama7g5.dtsi"
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/mfd/atmel-flexcom.h>
+#include <dt-bindings/pinctrl/at91.h>
+
+/ {
+	model = "Microchip SAMA7G54 Curiosity";
+	compatible = "microchip,sama7g54-curiosity", "microchip,sama7g5", "microchip,sama7";
+
+	aliases {
+		serial0 = &uart3;
+		i2c0 = &i2c10;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_key_gpio_default>;
+
+		button-user {
+			label = "user-button";
+			gpios = <&pioA PIN_PD19 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_PROG1>;
+			wakeup-source;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_led_gpio_default>;
+
+		led-red {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_POWER;
+			gpios = <&pioA PIN_PD13 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led-green {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_BOOT;
+			gpios = <&pioA PIN_PD14 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+		};
+
+		led-blue {
+			color = <LED_COLOR_ID_BLUE>;
+			function = LED_FUNCTION_CPU;
+			gpios = <&pioA PIN_PB15 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	memory@60000000 {
+		device_type = "memory";
+		reg = <0x60000000 0x10000000>; /* 256 MiB DDR3L-1066 16-bit */
+	};
+};
+
+&adc {
+	vddana-supply = <&vddout25>;
+	vref-supply = <&vddout25>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_mikrobus1_an_default &pinctrl_mikrobus2_an_default>;
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&vddcpu>;
+};
+
+&dma0 {
+	status = "okay";
+};
+
+&dma1 {
+	status = "okay";
+};
+
+&dma2 {
+	status = "okay";
+};
+
+&ebi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_nand_default>;
+	status = "okay";
+
+	nand_controller: nand-controller {
+		status = "okay";
+
+		nand@3 {
+			reg = <0x3 0x0 0x800000>;
+			atmel,rb = <0>;
+			nand-bus-width = <8>;
+			nand-ecc-mode = "hw";
+			nand-ecc-strength = <8>;
+			nand-ecc-step-size = <512>;
+			nand-on-flash-bbt;
+			label = "nand";
+
+			partitions {
+				compatible = "fixed-partitions";
+				#address-cells = <1>;
+				#size-cells = <1>;
+
+				at91bootstrap@0 {
+					label = "nand: at91bootstrap";
+					reg = <0x0 0x40000>;
+				};
+
+				bootloader@40000 {
+					label = "nand: u-boot";
+					reg = <0x40000 0x100000>;
+				};
+
+				bootloaderenv@140000 {
+					label = "nand: u-boot env";
+					reg = <0x140000 0x40000>;
+				};
+
+				dtb@180000 {
+					label = "nand: device tree";
+					reg = <0x180000 0x80000>;
+				};
+
+				kernel@200000 {
+					label = "nand: kernel";
+					reg = <0x200000 0x600000>;
+				};
+
+				rootfs@800000 {
+					label = "nand: rootfs";
+					reg = <0x800000 0x1f800000>;
+				};
+			};
+		};
+	};
+};
+
+&flx3 {
+	atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>;
+	status = "okay";
+
+	uart3: serial@200 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_flx3_default>;
+		status = "okay";
+	};
+};
+
+&flx10 {
+	atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+	status = "okay";
+
+	i2c10: i2c@600 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_flx10_default>;
+		i2c-analog-filter;
+		i2c-digital-filter;
+		i2c-digital-filter-width-ns = <35>;
+		status = "okay";
+
+		eeprom@51 {
+			compatible = "atmel,24c02";
+			reg = <0x51>;
+			pagesize = <16>;
+			size = <256>;
+			vcc-supply = <&vdd_3v3>;
+		};
+
+		pmic@5b {
+			compatible = "microchip,mcp16502";
+			reg = <0x5b>;
+
+			regulators {
+				vdd_3v3: VDD_IO {
+					regulator-name = "VDD_IO";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-initial-mode = <2>;
+					regulator-allowed-modes = <2>, <4>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-on-in-suspend;
+						regulator-suspend-microvolt = <3300000>;
+						regulator-mode = <4>;
+					};
+
+					regulator-state-mem {
+						regulator-off-in-suspend;
+						regulator-mode = <4>;
+					};
+				};
+
+				vddioddr: VDD_DDR {
+					regulator-name = "VDD_DDR";
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-initial-mode = <2>;
+					regulator-allowed-modes = <2>, <4>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-on-in-suspend;
+						regulator-suspend-microvolt = <1350000>;
+						regulator-mode = <4>;
+					};
+
+					regulator-state-mem {
+						regulator-on-in-suspend;
+						regulator-suspend-microvolt = <1350000>;
+						regulator-mode = <4>;
+					};
+				};
+
+				vddcore: VDD_CORE {
+					regulator-name = "VDD_CORE";
+					regulator-min-microvolt = <1150000>;
+					regulator-max-microvolt = <1150000>;
+					regulator-initial-mode = <2>;
+					regulator-allowed-modes = <2>, <4>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-on-in-suspend;
+						regulator-suspend-voltage = <1150000>;
+						regulator-mode = <4>;
+					};
+
+					regulator-state-mem {
+						regulator-off-in-suspend;
+						regulator-mode = <4>;
+					};
+				};
+
+				vddcpu: VDD_OTHER {
+					regulator-name = "VDD_OTHER";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1250000>;
+					regulator-initial-mode = <2>;
+					regulator-allowed-modes = <2>, <4>;
+					regulator-ramp-delay = <3125>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-on-in-suspend;
+						regulator-suspend-voltage = <1050000>;
+						regulator-mode = <4>;
+					};
+
+					regulator-state-mem {
+						regulator-off-in-suspend;
+						regulator-mode = <4>;
+					};
+				};
+
+				vldo1: LDO1 {
+					regulator-name = "LDO1";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-suspend-voltage = <1800000>;
+						regulator-on-in-suspend;
+					};
+
+					regulator-state-mem {
+						regulator-off-in-suspend;
+					};
+				};
+
+				vldo2: LDO2 {
+					regulator-name = "LDO2";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+					regulator-always-on;
+
+					regulator-state-standby {
+						regulator-suspend-voltage = <3300000>;
+						regulator-on-in-suspend;
+					};
+
+					regulator-state-mem {
+						regulator-off-in-suspend;
+					};
+				};
+			};
+		};
+	};
+};
+
+&main_xtal {
+	clock-frequency = <24000000>;
+};
+
+&qspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_qspi1_default>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-max-frequency = <100000000>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
+		m25p,fast-read;
+	};
+};
+
+&pioA {
+	pinctrl_flx3_default: flx3-default {
+		pinmux = <PIN_PD16__FLEXCOM3_IO0>,
+			 <PIN_PD17__FLEXCOM3_IO1>;
+		bias-pull-up;
+	};
+
+	pinctrl_flx10_default: flx10-default {
+		pinmux = <PIN_PC30__FLEXCOM10_IO0>,
+			 <PIN_PC31__FLEXCOM10_IO1>;
+		bias-pull-up;
+	};
+
+	pinctrl_key_gpio_default: key-gpio-default {
+		pinmux = <PIN_PD19__GPIO>;
+		bias-pull-up;
+	};
+
+	pinctrl_led_gpio_default: led-gpio-default {
+		pinmux = <PIN_PD13__GPIO>,
+			 <PIN_PD14__GPIO>,
+			 <PIN_PB15__GPIO>;
+		bias-pull-up;
+	};
+
+	pinctrl_mikrobus1_an_default: mikrobus1-an-default {
+		pinmux = <PIN_PC15__GPIO>;
+		bias-disable;
+	};
+
+	pinctrl_mikrobus2_an_default: mikrobus2-an-default {
+		pinmux = <PIN_PC13__GPIO>;
+		bias-disable;
+	};
+
+	pinctrl_nand_default: nand-default {
+		pinmux = <PIN_PD9__D0>,
+			 <PIN_PD10__D1>,
+			 <PIN_PD11__D2>,
+			 <PIN_PC21__D3>,
+			 <PIN_PC22__D4>,
+			 <PIN_PC23__D5>,
+			 <PIN_PC24__D6>,
+			 <PIN_PD2__D7>,
+			 <PIN_PD3__NANDRDY>,
+			 <PIN_PD4__NCS3_NANDCS>,
+			 <PIN_PD5__NWE_NWR0_NANDWE>,
+			 <PIN_PD6__NRD_NANDOE>,
+			 <PIN_PD7__A21_NANDALE>,
+			 <PIN_PD8__A22_NANDCLE>;
+		bias-disable;
+		slew-rate = <0>;
+	};
+
+	pinctrl_qspi1_default: qspi1-default {
+		pinmux = <PIN_PB22__QSPI1_IO3>,
+			 <PIN_PB23__QSPI1_IO2>,
+			 <PIN_PB24__QSPI1_IO1>,
+			 <PIN_PB25__QSPI1_IO0>,
+			 <PIN_PB26__QSPI1_CS>,
+			 <PIN_PB27__QSPI1_SCK>;
+		bias-pull-up;
+		slew-rate = <0>;
+	};
+
+	pinctrl_sdmmc0_default: sdmmc0-default {
+		pinmux = <PIN_PA0__SDMMC0_CK>,
+			 <PIN_PA1__SDMMC0_CMD>,
+			 <PIN_PA2__SDMMC0_RSTN>,
+			 <PIN_PA3__SDMMC0_DAT0>,
+			 <PIN_PA4__SDMMC0_DAT1>,
+			 <PIN_PA5__SDMMC0_DAT2>,
+			 <PIN_PA6__SDMMC0_DAT3>;
+		bias-pull-up;
+		slew-rate = <0>;
+	};
+
+	pinctrl_sdmmc1_default: sdmmc1-default {
+		pinmux = <PIN_PB29__SDMMC1_CMD>,
+			 <PIN_PB30__SDMMC1_CK>,
+			 <PIN_PB31__SDMMC1_DAT0>,
+			 <PIN_PC0__SDMMC1_DAT1>,
+			 <PIN_PC1__SDMMC1_DAT2>,
+			 <PIN_PC2__SDMMC1_DAT3>,
+			 <PIN_PC4__SDMMC1_CD>;
+		bias-pull-up;
+		slew-rate = <0>;
+	};
+};
+
+&rtt {
+	atmel,rtt-rtc-time-reg = <&gpbr 0x0>;
+};
+
+/* M.2 slot for wireless card */
+&sdmmc0 {
+	bus-width = <4>;
+	cd-gpios = <&pioA 31 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	sdhci-caps-mask = <0x0 0x00200000>;
+	vmmc-supply = <&vdd_3v3>;
+	vqmmc-supply = <&vdd_3v3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sdmmc0_default>;
+	status = "okay";
+};
+
+/* micro SD socket */
+&sdmmc1 {
+	bus-width = <4>;
+	disable-wp;
+	sdhci-caps-mask = <0x0 0x00200000>;
+	vmmc-supply = <&vdd_3v3>;
+	vqmmc-supply = <&vdd_3v3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sdmmc1_default>;
+	status = "okay";
+};
+
+&slow_xtal {
+	clock-frequency = <32768>;
+};
+
+&shdwc {
+	debounce-delay-us = <976>;
+	status = "okay";
+
+	input@0 {
+		reg = <0>;
+	};
+};
+
+&tcb0 {
+	timer0: timer@0 {
+		compatible = "atmel,tcb-timer";
+		reg = <0>;
+	};
+
+	timer1: timer@1 {
+		compatible = "atmel,tcb-timer";
+		reg = <1>;
+	};
+};
+
+&trng {
+	status = "okay";
+};
+
+&vddout25 {
+	vin-supply = <&vdd_3v3>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/microchip/at91sam9g25-gardena-smart-gateway.dts b/arch/arm/boot/dts/microchip/at91sam9g25-gardena-smart-gateway.dts
index 92f2c05c873f..af70eb8a3a02 100644
--- a/arch/arm/boot/dts/microchip/at91sam9g25-gardena-smart-gateway.dts
+++ b/arch/arm/boot/dts/microchip/at91sam9g25-gardena-smart-gateway.dts
@@ -121,6 +121,8 @@
 };
 
 &usart3 {
+	atmel,use-dma-rx;
+	atmel,use-dma-tx;
 	status = "okay";
 
 	pinctrl-0 = <&pinctrl_usart3
diff --git a/arch/arm/boot/dts/microchip/at91sam9x5ek.dtsi b/arch/arm/boot/dts/microchip/at91sam9x5ek.dtsi
index 5f4eaa618ab4..9618b8d965b0 100644
--- a/arch/arm/boot/dts/microchip/at91sam9x5ek.dtsi
+++ b/arch/arm/boot/dts/microchip/at91sam9x5ek.dtsi
@@ -39,6 +39,8 @@
 };
 
 &dbgu {
+	atmel,use-dma-rx;
+	atmel,use-dma-tx;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi
index 73d570a17269..291540e5d81e 100644
--- a/arch/arm/boot/dts/microchip/sam9x60.dtsi
+++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi
@@ -179,7 +179,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(8))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(9))>;
@@ -202,7 +202,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(8))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(9))>;
@@ -220,7 +220,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(8))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(9))>;
@@ -248,7 +248,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(10))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(11))>;
@@ -271,7 +271,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(10))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(11))>;
@@ -289,7 +289,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(10))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(11))>;
@@ -377,7 +377,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(22))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(23))>;
@@ -399,7 +399,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(22))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(23))>;
@@ -426,7 +426,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(24))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(25))>;
@@ -448,7 +448,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(24))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(25))>;
@@ -583,7 +583,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(12))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(13))>;
@@ -605,7 +605,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(12))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(13))>;
@@ -632,7 +632,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(14))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(15))>;
@@ -654,7 +654,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(14))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(15))>;
@@ -681,7 +681,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(16))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(17))>;
@@ -703,7 +703,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(16))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(17))>;
@@ -730,7 +730,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(0))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(1))>;
@@ -753,7 +753,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(0))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(1))>;
@@ -771,7 +771,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(0))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(1))>;
@@ -798,7 +798,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(2))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(3))>;
@@ -821,7 +821,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(2))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(3))>;
@@ -839,7 +839,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(2))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(3))>;
@@ -866,7 +866,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(4))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(5))>;
@@ -889,7 +889,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(4))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(5))>;
@@ -907,7 +907,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(4))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(5))>;
@@ -934,7 +934,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(6))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(7))>;
@@ -957,7 +957,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(6))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(7))>;
@@ -975,7 +975,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(6))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(7))>;
@@ -1057,7 +1057,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(18))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(19))>;
@@ -1079,7 +1079,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(18))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(19))>;
@@ -1106,7 +1106,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(20))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(21))>;
@@ -1128,7 +1128,7 @@
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(20))>,
-						<&dma0
+					       <&dma0
 						(AT91_XDMAC_DT_MEM_IF(0) |
 						 AT91_XDMAC_DT_PER_IF(1) |
 						 AT91_XDMAC_DT_PERID(21))>;
diff --git a/arch/arm/boot/dts/microchip/sama7g5.dtsi b/arch/arm/boot/dts/microchip/sama7g5.dtsi
index 269e0a3ca269..75778be126a3 100644
--- a/arch/arm/boot/dts/microchip/sama7g5.dtsi
+++ b/arch/arm/boot/dts/microchip/sama7g5.dtsi
@@ -698,7 +698,7 @@
 		};
 
 		flx0: flexcom@e1818000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe1818000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 38>;
 			#address-cells = <1>;
@@ -714,7 +714,7 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 38>;
 				clock-names = "usart";
 				dmas = <&dma1 AT91_XDMAC_DT_PERID(6)>,
-					<&dma1 AT91_XDMAC_DT_PERID(5)>;
+				       <&dma1 AT91_XDMAC_DT_PERID(5)>;
 				dma-names = "tx", "rx";
 				atmel,use-dma-rx;
 				atmel,use-dma-tx;
@@ -723,7 +723,7 @@
 		};
 
 		flx1: flexcom@e181c000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe181c000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 39>;
 			#address-cells = <1>;
@@ -740,14 +740,14 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 39>;
 				atmel,fifo-size = <32>;
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(8)>,
-					<&dma0 AT91_XDMAC_DT_PERID(7)>;
+				       <&dma0 AT91_XDMAC_DT_PERID(7)>;
 				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 		};
 
 		flx3: flexcom@e1824000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe1824000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 41>;
 			#address-cells = <1>;
@@ -763,7 +763,7 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 41>;
 				clock-names = "usart";
 				dmas = <&dma1 AT91_XDMAC_DT_PERID(12)>,
-					<&dma1 AT91_XDMAC_DT_PERID(11)>;
+				       <&dma1 AT91_XDMAC_DT_PERID(11)>;
 				dma-names = "tx", "rx";
 				atmel,use-dma-rx;
 				atmel,use-dma-tx;
@@ -791,7 +791,7 @@
 		};
 
 		flx4: flexcom@e2018000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe2018000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 42>;
 			#address-cells = <1>;
@@ -807,7 +807,7 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 42>;
 				clock-names = "usart";
 				dmas = <&dma1 AT91_XDMAC_DT_PERID(14)>,
-					<&dma1 AT91_XDMAC_DT_PERID(13)>;
+				       <&dma1 AT91_XDMAC_DT_PERID(13)>;
 				dma-names = "tx", "rx";
 				atmel,use-dma-rx;
 				atmel,use-dma-tx;
@@ -817,7 +817,7 @@
 		};
 
 		flx7: flexcom@e2024000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe2024000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 45>;
 			#address-cells = <1>;
@@ -833,7 +833,7 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 45>;
 				clock-names = "usart";
 				dmas = <&dma1 AT91_XDMAC_DT_PERID(20)>,
-					<&dma1 AT91_XDMAC_DT_PERID(19)>;
+				       <&dma1 AT91_XDMAC_DT_PERID(19)>;
 				dma-names = "tx", "rx";
 				atmel,use-dma-rx;
 				atmel,use-dma-tx;
@@ -911,7 +911,7 @@
 		};
 
 		flx8: flexcom@e2818000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe2818000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 46>;
 			#address-cells = <1>;
@@ -928,14 +928,14 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 46>;
 				atmel,fifo-size = <32>;
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(22)>,
-					<&dma0 AT91_XDMAC_DT_PERID(21)>;
+				       <&dma0 AT91_XDMAC_DT_PERID(21)>;
 				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 		};
 
 		flx9: flexcom@e281c000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe281c000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 47>;
 			#address-cells = <1>;
@@ -952,14 +952,38 @@
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 47>;
 				atmel,fifo-size = <32>;
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(24)>,
-					<&dma0 AT91_XDMAC_DT_PERID(23)>;
+				       <&dma0 AT91_XDMAC_DT_PERID(23)>;
+				dma-names = "tx", "rx";
+				status = "disabled";
+			};
+		};
+
+		flx10: flexcom@e2820000 {
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
+			reg = <0xe2820000 0x200>;
+			clocks = <&pmc PMC_TYPE_PERIPHERAL 48>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0xe2820000 0x800>;
+			status = "disabled";
+
+			i2c10: i2c@600 {
+				compatible = "microchip,sama7g5-i2c", "microchip,sam9x60-i2c";
+				reg = <0x600 0x200>;
+				interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				clocks = <&pmc PMC_TYPE_PERIPHERAL 48>;
+				atmel,fifo-size = <32>;
+				dmas = <&dma0 AT91_XDMAC_DT_PERID(26)>,
+				       <&dma0 AT91_XDMAC_DT_PERID(25)>;
 				dma-names = "tx", "rx";
 				status = "disabled";
 			};
 		};
 
 		flx11: flexcom@e2824000 {
-			compatible = "atmel,sama5d2-flexcom";
+			compatible = "microchip,sama7g5-flexcom", "atmel,sama5d2-flexcom";
 			reg = <0xe2824000 0x200>;
 			clocks = <&pmc PMC_TYPE_PERIPHERAL 49>;
 			#address-cells = <1>;
@@ -977,7 +1001,7 @@
 				#size-cells = <0>;
 				atmel,fifo-size = <32>;
 				dmas = <&dma0 AT91_XDMAC_DT_PERID(28)>,
-					    <&dma0 AT91_XDMAC_DT_PERID(27)>;
+				       <&dma0 AT91_XDMAC_DT_PERID(27)>;
 				dma-names = "tx", "rx";
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
index fd671c7a1e5d..6e1f0f164cb4 100644
--- a/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
+++ b/arch/arm/boot/dts/nuvoton/nuvoton-wpcm450.dtsi
@@ -120,6 +120,7 @@
 				interrupts = <2 IRQ_TYPE_LEVEL_HIGH>,
 					     <3 IRQ_TYPE_LEVEL_HIGH>,
 					     <4 IRQ_TYPE_LEVEL_HIGH>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 			};
 
@@ -128,6 +129,7 @@
 				gpio-controller;
 				#gpio-cells = <2>;
 				interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 			};
 
diff --git a/arch/arm/boot/dts/nvidia/Makefile b/arch/arm/boot/dts/nvidia/Makefile
index 60091bf7e48b..96972559253c 100644
--- a/arch/arm/boot/dts/nvidia/Makefile
+++ b/arch/arm/boot/dts/nvidia/Makefile
@@ -39,5 +39,7 @@ dtb-$(CONFIG_ARCH_TEGRA_3x_SOC) += \
 	tegra30-cardhu-a02.dtb \
 	tegra30-cardhu-a04.dtb \
 	tegra30-colibri-eval-v3.dtb \
+	tegra30-lg-p880.dtb \
+	tegra30-lg-p895.dtb \
 	tegra30-ouya.dtb \
 	tegra30-pegatron-chagall.dtb
diff --git a/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi b/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi
index a2ee37180200..8125c1b3e8d7 100644
--- a/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra124-nyan.dtsi
@@ -338,6 +338,7 @@
 			interrupt-parent = <&gpio>;
 			interrupts = <TEGRA_GPIO(C, 7) IRQ_TYPE_LEVEL_LOW>;
 			reg = <0>;
+			wakeup-source;
 
 			google,cros-ec-spi-msg-delay = <2000>;
 
diff --git a/arch/arm/boot/dts/nvidia/tegra124-venice2.dts b/arch/arm/boot/dts/nvidia/tegra124-venice2.dts
index 3924ee385dee..df98dc2a67b8 100644
--- a/arch/arm/boot/dts/nvidia/tegra124-venice2.dts
+++ b/arch/arm/boot/dts/nvidia/tegra124-venice2.dts
@@ -857,6 +857,7 @@
 			interrupt-parent = <&gpio>;
 			interrupts = <TEGRA_GPIO(C, 7) IRQ_TYPE_LEVEL_LOW>;
 			reg = <0>;
+			wakeup-source;
 
 			google,cros-ec-spi-msg-delay = <2000>;
 
diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
index 1640763fd4af..ff0d684622f7 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-apalis-v1.1.dtsi
@@ -997,7 +997,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
index 3b6fad273cab..d38f1dd38a90 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-apalis.dtsi
@@ -980,7 +980,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nvidia/tegra30-asus-nexus7-grouper-common.dtsi b/arch/arm/boot/dts/nvidia/tegra30-asus-nexus7-grouper-common.dtsi
index a9342e04b14b..15f53babdc21 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-asus-nexus7-grouper-common.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-asus-nexus7-grouper-common.dtsi
@@ -915,6 +915,9 @@
 			reg = <0x1c>;
 
 			realtek,dmic1-data-pin = <1>;
+
+			clocks = <&tegra_pmc TEGRA_PMC_CLK_OUT_1>;
+			clock-names = "mclk";
 		};
 
 		nct72: temperature-sensor@4c {
diff --git a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
index 4eb526fe9c55..81c8a5fd92cc 100644
--- a/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
+++ b/arch/arm/boot/dts/nvidia/tegra30-colibri.dtsi
@@ -861,7 +861,6 @@
 			compatible = "st,stmpe811";
 			reg = <0x41>;
 			irq-gpio = <&gpio TEGRA_GPIO(V, 0) GPIO_ACTIVE_LOW>;
-			interrupt-controller;
 			id = <0>;
 			blocks = <0x5>;
 			irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/nvidia/tegra30-lg-p880.dts b/arch/arm/boot/dts/nvidia/tegra30-lg-p880.dts
new file mode 100644
index 000000000000..2f7754fd42a1
--- /dev/null
+++ b/arch/arm/boot/dts/nvidia/tegra30-lg-p880.dts
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+
+#include "tegra30-lg-x3.dtsi"
+
+/ {
+	model = "LG Optimus 4X HD P880";
+	compatible = "lg,p880", "nvidia,tegra30";
+
+	aliases {
+		mmc1 = &sdmmc3; /* uSD slot */
+		mmc2 = &sdmmc1; /* WiFi */
+	};
+
+	pinmux@70000868 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&state_default>;
+
+		state_default: pinmux {
+			/* WLAN SDIO pinmux */
+			host-wlan-wake {
+				nvidia,pins = "pu4";
+				nvidia,function = "pwm1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GNSS UART-B pinmux */
+			uartb-rxd {
+				nvidia,pins = "uart2_rxd_pc3";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uartb-txd {
+				nvidia,pins = "uart2_txd_pc2";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gps-reset {
+				nvidia,pins = "kb_row7_pr7";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* MicroSD pinmux */
+			sdmmc3-clk {
+				nvidia,pins = "sdmmc3_clk_pa6";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc3-data {
+				nvidia,pins = "sdmmc3_cmd_pa7",
+						"sdmmc3_dat0_pb7",
+						"sdmmc3_dat1_pb6",
+						"sdmmc3_dat2_pb5",
+						"sdmmc3_dat3_pb4";
+				nvidia,function = "sdmmc3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			microsd-detect {
+				nvidia,pins = "clk2_out_pw5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GPIO keys pinmux */
+			volume-up {
+				nvidia,pins = "ulpi_data6_po7";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Sensors pinmux */
+			current-alert-irq {
+				nvidia,pins = "uart2_rts_n_pj6";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* AUDIO pinmux */
+			sub-mic-ldo {
+				nvidia,pins = "gmi_cs7_n_pi6";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+		};
+	};
+
+	i2c@7000c400 {
+		touchscreen@20 {
+			rmi4-f11@11 {
+				syna,clip-x-high = <1110>;
+				syna,clip-y-high = <1973>;
+
+				touchscreen-inverted-y;
+			};
+		};
+	};
+
+	memory-controller@7000f000 {
+		emc-timings-0 {
+			/* SAMSUNG 1GB K4P8G304EB FGC1 533MHz */
+			nvidia,ram-code = <0>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emem-configuration = < 0x00050001 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x77230303 0x001f0000 >;
+			};
+
+			timing-25500000 {
+				clock-frequency = <25500000>;
+
+				nvidia,emem-configuration = < 0x00020001 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x73e30303 0x001f0000 >;
+			};
+
+			timing-51000000 {
+				clock-frequency = <51000000>;
+
+				nvidia,emem-configuration = < 0x00010001 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x72c30303 0x001f0000 >;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emem-configuration = < 0x00000001 0xc0000018
+					0x00000001 0x00000001 0x00000003 0x00000001
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060403 0x72430504 0x001f0000 >;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emem-configuration = < 0x00000003 0xc0000025
+					0x00000001 0x00000001 0x00000006 0x00000003
+					0x00000005 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000003 0x00000002
+					0x02030001 0x00070506 0x71e40a07 0x001f0000 >;
+			};
+
+			timing-266500000 {
+				clock-frequency = <266500000>;
+
+				nvidia,emem-configuration = < 0x00000004 0xC0000030
+					0x00000001 0x00000002 0x00000008 0x00000004
+					0x00000006 0x00000001 0x00000002 0x00000005
+					0x00000001 0x00000000 0x00000003 0x00000003
+					0x03030001 0x00090608 0x70040c09 0x001f0000 >;
+			};
+
+			timing-533000000 {
+				clock-frequency = <533000000>;
+
+				nvidia,emem-configuration = < 0x00000008 0xC0000060
+					0x00000003 0x00000004 0x00000010 0x0000000a
+					0x0000000d 0x00000002 0x00000002 0x00000008
+					0x00000002 0x00000000 0x00000004 0x00000005
+					0x05040002 0x00110b10 0x70281811 0x001f0000 >;
+			};
+		};
+	};
+
+	memory-controller@7000f400 {
+		emc-timings-0 {
+			/* SAMSUNG 1GB K4P8G304EB FGC1 533MHz */
+			nvidia,ram-code = <0>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-dyn-self-ref;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000000
+					0x00000001 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x0000002f 0x00000000 0x0000000b
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000002 0x00000002
+					0x00000003 0x00000008 0x00000004 0x00000001
+					0x00000002 0x00000036 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000009 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000164 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-25500000 {
+				clock-frequency = <25500000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-dyn-self-ref;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000001
+					0x00000003 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x00000060 0x00000000 0x00000018
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000004 0x00000004
+					0x00000003 0x00000008 0x00000004 0x00000001
+					0x00000002 0x0000006b 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x0000000a 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x800001c5 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-51000000 {
+				clock-frequency = <51000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-dyn-self-ref;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000003
+					0x00000006 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x000000c0 0x00000000 0x00000030
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000008 0x00000008
+					0x00000003 0x00000008 0x00000004 0x00000001
+					0x00000002 0x000000d5 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000013 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000287 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x0000000a>;
+				nvidia,emc-cfg-dyn-self-ref;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000006
+					0x0000000d 0x00000004 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x00000181 0x00000000 0x00000060
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x0000000f 0x0000000f
+					0x00000003 0x00000008 0x00000004 0x00000001
+					0x00000002 0x000001a9 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000025 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x8000040b 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010042>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000013>;
+				nvidia,emc-cfg-dyn-self-ref;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000000c
+					0x0000001a 0x00000008 0x00000003 0x00000005
+					0x00000004 0x00000001 0x00000006 0x00000003
+					0x00000003 0x00000002 0x00000002 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000c
+					0x0000000a 0x00000303 0x00000000 0x000000c0
+					0x00000001 0x00000001 0x00000003 0x00000000
+					0x00000001 0x00000007 0x0000001d 0x0000001d
+					0x00000004 0x0000000b 0x00000005 0x00000001
+					0x00000002 0x00000351 0x00000004 0x00000006
+					0x00000000 0x00000000 0x00004282 0x004400a4
+					0x00008000 0x00070000 0x00070000 0x00070000
+					0x00070000 0x00070000 0x00070000 0x00070000
+					0x00070000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00080000 0x00080000 0x00080000
+					0x00080000 0x000e0220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x0000004a 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000713 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-266500000 {
+				clock-frequency = <266500000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010042>;
+				nvidia,emc-mode-2 = <0x00020002>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000018>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000000f
+					0x00000022 0x0000000b 0x00000004 0x00000005
+					0x00000005 0x00000001 0x00000007 0x00000004
+					0x00000004 0x00000002 0x00000002 0x00000000
+					0x00000002 0x00000005 0x00000002 0x0000000c
+					0x0000000b 0x000003ef 0x00000000 0x000000fb
+					0x00000001 0x00000001 0x00000004 0x00000000
+					0x00000001 0x00000009 0x00000026 0x00000026
+					0x00000004 0x0000000e 0x00000006 0x00000001
+					0x00000002 0x00000455 0x00000000 0x00000004
+					0x00000000 0x00000000 0x00006282 0x003200a4
+					0x00008000 0x00050000 0x00050000 0x00050000
+					0x00050000 0x00050000 0x00050000 0x00050000
+					0x00050000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00060000 0x00060000 0x00060000
+					0x00060000 0x000b0220 0x0800003d 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000060 0x000a000a 0xa0f10000 0x00000000
+					0x00000000 0x800008ee 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-533000000 {
+				clock-frequency = <533000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x000100c2>;
+				nvidia,emc-mode-2 = <0x00020006>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000030>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000001f
+					0x00000045 0x00000016 0x00000009 0x00000008
+					0x00000009 0x00000003 0x0000000d 0x00000009
+					0x00000009 0x00000005 0x00000003 0x00000000
+					0x00000004 0x00000009 0x00000006 0x0000000d
+					0x00000010 0x000007df 0x00000000 0x000001f7
+					0x00000003 0x00000003 0x00000009 0x00000000
+					0x00000001 0x0000000f 0x0000004b 0x0000004b
+					0x00000008 0x0000001b 0x0000000c 0x00000001
+					0x00000002 0x000008aa 0x00000000 0x00000006
+					0x00000000 0x00000000 0x00006282 0xf0120091
+					0x00008000 0x0000000a 0x0000000a 0x0000000a
+					0x0000000a 0x0000000a 0x0000000a 0x0000000a
+					0x0000000a 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x0000000a 0x0000000a 0x0000000a
+					0x0000000a 0x00090220 0x0800003d 0x00000000
+					0x77ffc004 0x01f1f408 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x000000c0 0x000e000e 0xa0f10000 0x00000000
+					0x00000000 0x800010d9 0xe0000000 0xff00ff88 >;
+			};
+		};
+	};
+
+	sdmmc3: mmc@78000400 {
+		status = "okay";
+
+		cd-gpios = <&gpio TEGRA_GPIO(W, 5) GPIO_ACTIVE_LOW>;
+		bus-width = <4>;
+
+		vmmc-supply = <&vdd_usd>;
+		vqmmc-supply = <&vdd_1v8_vio>;
+	};
+
+	battery: battery-cell {
+		compatible = "simple-battery";
+		device-chemistry = "lithium-ion";
+		charge-full-design-microamp-hours = <2150000>;
+		energy-full-design-microwatt-hours = <8200000>;
+		operating-range-celsius = <0 45>;
+	};
+
+	gpio-keys {
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&gpio TEGRA_GPIO(O, 7) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <10>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+	};
+
+	sound {
+		compatible = "lg,tegra-audio-max98089-p880",
+			     "nvidia,tegra-audio-max98089";
+		nvidia,model = "LG Optimus 4X HD MAX98089";
+
+		nvidia,int-mic-en-gpios = <&gpio TEGRA_GPIO(I, 6) GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/arch/arm/boot/dts/nvidia/tegra30-lg-p895.dts b/arch/arm/boot/dts/nvidia/tegra30-lg-p895.dts
new file mode 100644
index 000000000000..e32fafc7f5e0
--- /dev/null
+++ b/arch/arm/boot/dts/nvidia/tegra30-lg-p895.dts
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+
+#include "tegra30-lg-x3.dtsi"
+
+/ {
+	model = "LG Optimus Vu P895";
+	compatible = "lg,p895", "nvidia,tegra30";
+
+	pinmux@70000868 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&state_default>;
+
+		state_default: pinmux {
+			/* GNSS UART-B pinmux */
+			uartb-cts-rxd {
+				nvidia,pins = "uart2_cts_n_pj5",
+						"uart2_rxd_pc3";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uartb-rts-txd {
+				nvidia,pins = "uart2_rts_n_pj6",
+						"uart2_txd_pc2";
+				nvidia,function = "uartb";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gps-reset {
+				nvidia,pins = "spdif_out_pk5";
+				nvidia,function = "spdif";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* GPIO keys pinmux */
+			memo-key {
+				nvidia,pins = "sdmmc3_dat1_pb6";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			volume-up {
+				nvidia,pins = "gmi_cs7_n_pi6";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Sensors pinmux */
+			current-alert-irq {
+				nvidia,pins = "spi1_cs0_n_px6";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Panel pinmux */
+			panel-vdd {
+				nvidia,pins = "pbb0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* AUDIO pinmux */
+			sub-mic-ldo {
+				nvidia,pins = "gmi_dqs_pi2";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Modem pinmux */
+			usim-detect {
+				nvidia,pins = "clk2_out_pw5";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GPIO power/drive control */
+			drive-sdmmc4 {
+				nvidia,pins = "drive_gma",
+						"drive_gmb",
+						"drive_gmc",
+						"drive_gmd";
+				nvidia,pull-down-strength = <9>;
+				nvidia,pull-up-strength = <9>;
+				nvidia,slew-rate-rising = <TEGRA_PIN_SLEW_RATE_SLOWEST>;
+				nvidia,slew-rate-falling = <TEGRA_PIN_SLEW_RATE_SLOWEST>;
+			};
+		};
+	};
+
+	i2c@7000c400 {
+		touchscreen@20 {
+			rmi4-f11@11 {
+				syna,clip-x-high = <1535>;
+				syna,clip-y-high = <2047>;
+			};
+		};
+	};
+
+	memory-controller@7000f000 {
+		emc-timings-2 {
+			/* Hynix 1GB H9TCNNN8JDMMPR LPDDR2 533MHz */
+			nvidia,ram-code = <2>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emem-configuration = < 0x00020001 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x77230303 0x001f0000 >;
+			};
+
+			timing-25500000 {
+				clock-frequency = <25500000>;
+
+				nvidia,emem-configuration = < 0x00030003 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x73e30303 0x001f0000 >;
+			};
+
+			timing-51000000 {
+				clock-frequency = <51000000>;
+
+				nvidia,emem-configuration = < 0x00010003 0xc0000010
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060402 0x72c30303 0x001f0000 >;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emem-configuration = < 0x00000003 0xc0000018
+					0x00000001 0x00000001 0x00000003 0x00000001
+					0x00000003 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000002 0x00000002
+					0x02020001 0x00060403 0x72430504 0x001f0000 >;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emem-configuration = < 0x00000006 0xc0000025
+					0x00000001 0x00000001 0x00000006 0x00000003
+					0x00000005 0x00000001 0x00000002 0x00000004
+					0x00000001 0x00000000 0x00000003 0x00000002
+					0x02030001 0x00070506 0x71e40a07 0x001f0000 >;
+			};
+
+			timing-266500000 {
+				clock-frequency = <266500000>;
+
+				nvidia,emem-configuration = < 0x00000008 0xc0000030
+					0x00000001 0x00000002 0x00000008 0x00000004
+					0x00000006 0x00000001 0x00000002 0x00000005
+					0x00000001 0x00000000 0x00000003 0x00000003
+					0x03030001 0x00090608 0x70040c09 0x001f0000 >;
+			};
+
+			timing-533000000 {
+				clock-frequency = <533000000>;
+
+				nvidia,emem-configuration = < 0x0000000f 0xc0000060
+					0x00000003 0x00000004 0x00000010 0x0000000a
+					0x0000000d 0x00000002 0x00000002 0x00000008
+					0x00000002 0x00000000 0x00000004 0x00000005
+					0x05040002 0x00110b10 0x70281811 0x001f0000 >;
+			};
+		};
+	};
+
+	memory-controller@7000f400 {
+		emc-timings-2 {
+			/* Hynix 1GB H9TCNNN8JDMMPR LPDDR2 533MHz */
+			nvidia,ram-code = <2>;
+
+			timing-12750000 {
+				clock-frequency = <12750000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000000
+					0x00000001 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x0000002f 0x00000000 0x0000000b
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000002 0x00000002
+					0x00000003 0x00000008 0x00000004 0x00000004
+					0x00000002 0x00000036 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000009 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000164 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-25500000 {
+				clock-frequency = <25500000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000001
+					0x00000003 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x00000060 0x00000000 0x00000018
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000004 0x00000004
+					0x00000003 0x00000008 0x00000004 0x00000004
+					0x00000002 0x0000006b 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x0000000a 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x800001c5 0xd0000000 0xff00ff00 >;
+			};
+
+			timing-51000000 {
+				clock-frequency = <51000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000009>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000003
+					0x00000006 0x00000002 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x000000c0 0x00000000 0x00000030
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x00000008 0x00000008
+					0x00000003 0x00000008 0x00000004 0x00000004
+					0x00000002 0x000000d5 0x00000004 0x00000004
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000013 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000287 0xd0000000 0xff00ff00 >;
+			};
+
+			timing-102000000 {
+				clock-frequency = <102000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010022>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x0000000a>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x00000006
+					0x0000000d 0x00000004 0x00000002 0x00000004
+					0x00000004 0x00000001 0x00000005 0x00000002
+					0x00000002 0x00000001 0x00000001 0x00000000
+					0x00000001 0x00000003 0x00000001 0x0000000b
+					0x00000009 0x00000181 0x00000000 0x00000060
+					0x00000001 0x00000001 0x00000002 0x00000000
+					0x00000001 0x00000007 0x0000000f 0x0000000f
+					0x00000003 0x00000008 0x00000004 0x00000004
+					0x00000002 0x000001a9 0x00000004 0x00000006
+					0x00000000 0x00000000 0x00004282 0x007800a4
+					0x00008000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x000fc000 0x000fc000 0x000fc000
+					0x000fc000 0x00100220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000025 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x8000040b 0xd0000000 0xff00ff00 >;
+			};
+
+			timing-204000000 {
+				clock-frequency = <204000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010042>;
+				nvidia,emc-mode-2 = <0x00020001>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000013>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000000c
+					0x0000001a 0x00000008 0x00000003 0x00000005
+					0x00000004 0x00000001 0x00000006 0x00000003
+					0x00000003 0x00000002 0x00000002 0x00000000
+					0x00000001 0x00000004 0x00000001 0x0000000c
+					0x0000000a 0x00000303 0x00000000 0x000000c0
+					0x00000001 0x00000001 0x00000003 0x00000000
+					0x00000001 0x00000007 0x0000001d 0x0000001d
+					0x00000004 0x0000000b 0x00000005 0x00000004
+					0x00000002 0x00000351 0x00000005 0x00000004
+					0x00000000 0x00000000 0x00004282 0x004400a4
+					0x00008000 0x00080000 0x00080000 0x00080000
+					0x00080000 0x00072000 0x00072000 0x00072000
+					0x00072000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00080000 0x00080000 0x00080000
+					0x00080000 0x000e0220 0x0800201c 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x0000004a 0x00090009 0xa0f10000 0x00000000
+					0x00000000 0x80000713 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-266500000 {
+				clock-frequency = <266500000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x00010042>;
+				nvidia,emc-mode-2 = <0x00020002>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000018>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000000f
+					0x00000022 0x0000000b 0x00000004 0x00000005
+					0x00000005 0x00000001 0x00000007 0x00000004
+					0x00000004 0x00000002 0x00000002 0x00000000
+					0x00000002 0x00000005 0x00000002 0x0000000c
+					0x0000000b 0x000003ef 0x00000000 0x000000fb
+					0x00000001 0x00000001 0x00000004 0x00000000
+					0x00000001 0x00000009 0x00000026 0x00000026
+					0x00000004 0x0000000e 0x00000006 0x00000004
+					0x00000002 0x00000455 0x00000000 0x00000004
+					0x00000000 0x00000000 0x00006282 0x003200a4
+					0x00008000 0x00070000 0x00070000 0x00070000
+					0x00070000 0x00072000 0x00072000 0x00072000
+					0x00072000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00080002 0x00080002 0x00080002
+					0x00080002 0x000e0220 0x0800003d 0x00000000
+					0x77ffc004 0x01f1f008 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x00000060 0x000a000a 0xa0f10000 0x00000000
+					0x00000000 0x800008ee 0xe0000000 0xff00ff00 >;
+			};
+
+			timing-533000000 {
+				clock-frequency = <533000000>;
+
+				nvidia,emc-auto-cal-interval = <0x001fffff>;
+				nvidia,emc-mode-1 = <0x000100c2>;
+				nvidia,emc-mode-2 = <0x00020006>;
+				nvidia,emc-mode-reset = <0x00000000>;
+				nvidia,emc-zcal-cnt-long = <0x00000030>;
+				nvidia,emc-cfg-periodic-qrst;
+
+				nvidia,emc-configuration =  < 0x0000001f
+					0x00000045 0x00000016 0x00000009 0x00000008
+					0x00000009 0x00000003 0x0000000d 0x00000009
+					0x00000009 0x00000005 0x00000003 0x00000000
+					0x00000004 0x0000000a 0x00000006 0x0000000d
+					0x00000010 0x000007df 0x00000000 0x000001f7
+					0x00000003 0x00000003 0x00000009 0x00000000
+					0x00000001 0x0000000f 0x0000004b 0x0000004b
+					0x00000008 0x0000001b 0x0000000c 0x00000004
+					0x00000002 0x000008aa 0x00000000 0x00000004
+					0x00000000 0x00000000 0x00006282 0xf0120091
+					0x00008000 0x0000000c 0x0000000c 0x0000000c
+					0x0000000c 0x0000000a 0x0000000a 0x0000000a
+					0x0000000a 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x00000000 0x00000000 0x00000000
+					0x00000000 0x0000000c 0x0000000c 0x0000000c
+					0x0000000c 0x000c0220 0x0800003d 0x00000000
+					0x77ffc004 0x01f1f408 0x00000000 0x00000007
+					0x08000068 0x08000000 0x00000802 0x00064000
+					0x000000c0 0x000e000e 0xa0f10000 0x00000000
+					0x00000000 0x800010d9 0xe0000000 0xff00ff88 >;
+			};
+		};
+	};
+
+	battery: battery-cell {
+		compatible = "simple-battery";
+		device-chemistry = "lithium-ion";
+		charge-full-design-microamp-hours = <2080000>;
+		energy-full-design-microwatt-hours = <7700000>;
+		operating-range-celsius = <0 45>;
+	};
+
+	gpio-keys {
+		key-memo {
+			label = "Memo";
+			gpios = <&gpio TEGRA_GPIO(B, 6) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_MEMO>;
+			debounce-interval = <10>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&gpio TEGRA_GPIO(I, 6) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <10>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+	};
+
+	gpio-leds {
+		led-power {
+			label = "power::white";
+			gpios = <&gpio TEGRA_GPIO(R, 3) GPIO_ACTIVE_HIGH>;
+
+			linux,default-trigger = "battery-charging";
+
+			color = <LED_COLOR_ID_WHITE>;
+			function = LED_FUNCTION_CHARGING;
+		};
+	};
+
+	regulator-lcd3v {
+		gpio = <&gpio TEGRA_GPIO(BB, 0) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	sound {
+		compatible = "lg,tegra-audio-max98089-p895",
+			     "nvidia,tegra-audio-max98089";
+		nvidia,model = "LG Optimus Vu MAX98089";
+
+		nvidia,int-mic-en-gpios = <&gpio TEGRA_GPIO(I, 2) GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/arch/arm/boot/dts/nvidia/tegra30-lg-x3.dtsi b/arch/arm/boot/dts/nvidia/tegra30-lg-x3.dtsi
new file mode 100644
index 000000000000..909260a5d0fb
--- /dev/null
+++ b/arch/arm/boot/dts/nvidia/tegra30-lg-x3.dtsi
@@ -0,0 +1,1812 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <dt-bindings/input/gpio-keys.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/mfd/max77620.h>
+#include <dt-bindings/thermal/thermal.h>
+
+#include "tegra30.dtsi"
+#include "tegra30-cpu-opp.dtsi"
+#include "tegra30-cpu-opp-microvolt.dtsi"
+
+/ {
+	chassis-type = "handset";
+
+	aliases {
+		mmc0 = &sdmmc4; /* eMMC */
+		mmc1 = &sdmmc1; /* WiFi */
+
+		rtc0 = &pmic;
+		rtc1 = "/rtc@7000e000";
+
+		serial0 = &uartd; /* Console */
+		serial1 = &uartc; /* Bluetooth */
+		serial2 = &uartb; /* GPS */
+	};
+
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 */
+	chosen { };
+
+	firmware {
+		trusted-foundations {
+			compatible = "tlm,trusted-foundations";
+			tlm,version-major = <2>;
+			tlm,version-minor = <8>;
+		};
+	};
+
+	memory@80000000 {
+		reg = <0x80000000 0x40000000>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		linux,cma@80000000 {
+			compatible = "shared-dma-pool";
+			alloc-ranges = <0x80000000 0x30000000>;
+			size = <0x10000000>;		/* 256MiB */
+			linux,cma-default;
+			reusable;
+		};
+
+		ramoops@bed00000 {
+			compatible = "ramoops";
+			reg = <0xbed00000 0x10000>;	/* 64kB */
+			console-size = <0x8000>;	/* 32kB */
+			record-size = <0x400>;		/* 1kB */
+			ecc-size = <16>;
+		};
+
+		trustzone@bfe00000 {
+			reg = <0xbfe00000 0x200000>;	/* 2MB */
+			no-map;
+		};
+	};
+
+	vde@6001a000 {
+		assigned-clocks = <&tegra_car TEGRA30_CLK_VDE>;
+		assigned-clock-parents = <&tegra_car TEGRA30_CLK_PLL_P>;
+		assigned-clock-rates = <408000000>;
+	};
+
+	pinmux@70000868 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&state_default>;
+
+		state_default: pinmux {
+			/* WLAN SDIO pinmux */
+			sdmmc1-clk {
+				nvidia,pins = "sdmmc1_clk_pz0";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc1-cmd {
+				nvidia,pins = "sdmmc1_cmd_pz1",
+						"sdmmc1_dat3_py4",
+						"sdmmc1_dat2_py5",
+						"sdmmc1_dat1_py6",
+						"sdmmc1_dat0_py7";
+				nvidia,function = "sdmmc1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			wlan-reset {
+				nvidia,pins = "pv3";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			wlan-host-wake {
+				nvidia,pins = "pu6";
+				nvidia,function = "pwm3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GNSS UART-B pinmux */
+			gps-pwr-en {
+				nvidia,pins = "kb_row6_pr6";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gps-ldo-en {
+				nvidia,pins = "ulpi_dir_py1";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			gps-clk-ref {
+				nvidia,pins = "gmi_ad8_ph0";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Bluetooth UART-C pinmux */
+			uartc-cts-rxd {
+				nvidia,pins = "uart3_cts_n_pa1",
+						"uart3_rxd_pw7";
+				nvidia,function = "uartc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			uartc-rts-txd {
+				nvidia,pins = "uart3_rts_n_pc0",
+						"uart3_txd_pw6";
+				nvidia,function = "uartc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			bt-reset {
+				nvidia,pins = "clk2_req_pcc5";
+				nvidia,function = "dap";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			bt-dev-wake {
+				nvidia,pins = "kb_row11_ps3";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			bt-host-wake {
+				nvidia,pins = "kb_row12_ps4";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			bt-pcm-dap4 {
+				nvidia,pins = "dap4_fs_pp4",
+						"dap4_din_pp5",
+						"dap4_dout_pp6",
+						"dap4_sclk_pp7";
+				nvidia,function = "i2s3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* EMMC pinmux */
+			sdmmc4-clk {
+				nvidia,pins = "sdmmc4_clk_pcc4";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4-data {
+				nvidia,pins = "sdmmc4_cmd_pt7",
+						"sdmmc4_dat0_paa0",
+						"sdmmc4_dat1_paa1",
+						"sdmmc4_dat2_paa2",
+						"sdmmc4_dat3_paa3",
+						"sdmmc4_dat4_paa4",
+						"sdmmc4_dat5_paa5",
+						"sdmmc4_dat6_paa6",
+						"sdmmc4_dat7_paa7";
+				nvidia,function = "sdmmc4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			sdmmc4-reset {
+				nvidia,pins = "sdmmc4_rst_n_pcc3";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* I2C pinmux */
+			gen1-i2c {
+				nvidia,pins = "gen1_i2c_scl_pc4",
+						"gen1_i2c_sda_pc5";
+				nvidia,function = "i2c1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+				nvidia,lock = <TEGRA_PIN_DISABLE>;
+			};
+			gen2-i2c {
+				nvidia,pins = "gen2_i2c_scl_pt5",
+						"gen2_i2c_sda_pt6";
+				nvidia,function = "i2c2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+				nvidia,lock = <TEGRA_PIN_DISABLE>;
+			};
+			cam-i2c {
+				nvidia,pins = "cam_i2c_scl_pbb1",
+						"cam_i2c_sda_pbb2";
+				nvidia,function = "i2c3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+				nvidia,lock = <TEGRA_PIN_DISABLE>;
+			};
+			ddc-i2c {
+				nvidia,pins = "ddc_scl_pv4",
+						"ddc_sda_pv5";
+				nvidia,function = "i2c4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,lock = <TEGRA_PIN_DISABLE>;
+			};
+			pwr-i2c {
+				nvidia,pins = "pwr_i2c_scl_pz6",
+						"pwr_i2c_sda_pz7";
+				nvidia,function = "i2cpwr";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+				nvidia,open-drain = <TEGRA_PIN_ENABLE>;
+				nvidia,lock = <TEGRA_PIN_DISABLE>;
+			};
+			mhl-i2c {
+				nvidia,pins = "kb_col6_pq6",
+						"kb_col7_pq7";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GPIO keys pinmux */
+			power-key {
+				nvidia,pins = "gmi_wp_n_pc7";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			volume-down {
+				nvidia,pins = "ulpi_data3_po4";
+				nvidia,function = "spi3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Sensors pinmux */
+			sen-vdd {
+				nvidia,pins = "spi1_miso_px7";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			proxi-vdd {
+				nvidia,pins = "spi2_miso_px1";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			sen-vio {
+				nvidia,pins = "lcd_dc1_pd2";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			nct-irq {
+				nvidia,pins = "gmi_iordy_pi5";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			bat-irq {
+				nvidia,pins = "kb_row8_ps0";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			charger-irq {
+				nvidia,pins = "gmi_cs1_n_pj2";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			mpu-irq {
+				nvidia,pins = "gmi_ad12_ph4";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			compass-irq {
+				nvidia,pins = "gmi_ad13_ph5";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			light-irq {
+				nvidia,pins = "gmi_cs4_n_pk2";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* LED pinmux */
+			backlight-en {
+				nvidia,pins = "lcd_dc0_pn6";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			flash-led-en {
+				nvidia,pins = "pbb3";
+				nvidia,function = "vgp3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			keypad-led {
+				nvidia,pins = "kb_row2_pr2",
+						"kb_row3_pr3";
+				nvidia,function = "rsvd3";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* NFC pinmux */
+			nfc-irq {
+				nvidia,pins = "spi2_cs1_n_pw2";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			nfc-ven {
+				nvidia,pins = "spi1_sck_px5";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			nfc-firm {
+				nvidia,pins = "kb_row0_pr0";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* DC pinmux */
+			lcd-pwr {
+				nvidia,pins = "lcd_pwr0_pb2",
+						"lcd_pwr1_pc1";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			lcd-wr-n {
+				nvidia,pins = "lcd_wr_n_pz3";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			lcd-id {
+				nvidia,pins = "lcd_m1_pw1";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			lcd-pclk {
+				nvidia,pins = "lcd_pclk_pb3",
+						"lcd_de_pj1",
+						"lcd_hsync_pj3",
+						"lcd_vsync_pj4";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			lcd-rgb-blue {
+				nvidia,pins = "lcd_d0_pe0",
+						"lcd_d1_pe1",
+						"lcd_d2_pe2",
+						"lcd_d3_pe3",
+						"lcd_d4_pe4",
+						"lcd_d5_pe5",
+						"lcd_d18_pm2",
+						"lcd_d19_pm3";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			lcd-rgb-green {
+				nvidia,pins = "lcd_d6_pe6",
+						"lcd_d7_pe7",
+						"lcd_d8_pf0",
+						"lcd_d9_pf1",
+						"lcd_d10_pf2",
+						"lcd_d11_pf3",
+						"lcd_d20_pm4",
+						"lcd_d21_pm5";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			lcd-rgb-red {
+				nvidia,pins = "lcd_d12_pf4",
+						"lcd_d13_pf5",
+						"lcd_d14_pf6",
+						"lcd_d15_pf7",
+						"lcd_d16_pm0",
+						"lcd_d17_pm1",
+						"lcd_d22_pm6",
+						"lcd_d23_pm7";
+				nvidia,function = "displaya";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Bridge pinmux */
+			bridge-reset {
+				nvidia,pins = "ulpi_data1_po2";
+				nvidia,function = "spi3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			rgb-ic-en {
+				nvidia,pins = "gmi_a18_pb1";
+				nvidia,function = "uartd";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			bridge-clk {
+				nvidia,pins = "clk3_out_pee0";
+				nvidia,function = "extperiph3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			rgb-bridge {
+				nvidia,pins = "lcd_sdin_pz2",
+						"lcd_sdout_pn5",
+						"lcd_cs0_n_pn4",
+						"lcd_sck_pz4";
+				nvidia,function = "spi5";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Panel pinmux */
+			panel-reset {
+				nvidia,pins = "lcd_cs1_n_pw0";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			panel-vio {
+				nvidia,pins = "ulpi_clk_py0";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Touchscreen pinmux */
+			touch-vdd {
+				nvidia,pins = "kb_col1_pq1";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			touch-vio {
+				nvidia,pins = "spi1_mosi_px4";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			touch-irq-n {
+				nvidia,pins = "kb_col3_pq3";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			touch-rst-n {
+				nvidia,pins = "ulpi_data0_po1";
+				nvidia,function = "spi3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			touch-maker-id {
+				nvidia,pins = "kb_col2_pq2";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MHL pinmux */
+			mhl-vio {
+				nvidia,pins = "pv2";
+				nvidia,function = "owr";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			mhl-rst-n {
+				nvidia,pins = "clk3_req_pee1";
+				nvidia,function = "dev3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			mhl-irq {
+				nvidia,pins = "crt_vsync_pv7";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			mhl-sel {
+				nvidia,pins = "kb_row10_ps2";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			hdmi-hpd {
+				nvidia,pins = "hdmi_int_pn7";
+				nvidia,function = "hdmi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* AUDIO pinmux */
+			hp-detect {
+				nvidia,pins = "pbb6";
+				nvidia,function = "vgp6";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			hp-hook {
+				nvidia,pins = "ulpi_data4_po5";
+				nvidia,function = "ulpi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ear-mic-en {
+				nvidia,pins = "spi2_mosi_px0";
+				nvidia,function = "spi2";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			audio-irq {
+				nvidia,pins = "spi2_cs2_n_pw3";
+				nvidia,function = "spi3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			audio-mclk {
+				nvidia,pins = "clk1_out_pw4";
+				nvidia,function = "extperiph1";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap-i2s0 {
+				nvidia,pins = "dap1_fs_pn0",
+						"dap1_din_pn1",
+						"dap1_dout_pn2",
+						"dap1_sclk_pn3";
+				nvidia,function = "i2s0";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			dap-i2s1 {
+				nvidia,pins = "dap2_fs_pa2",
+						"dap2_sclk_pa3",
+						"dap2_din_pa4",
+						"dap2_dout_pa5";
+				nvidia,function = "i2s1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* MUIC pinmux */
+			muic-irq {
+				nvidia,pins = "gmi_cs0_n_pj0";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			muic-dp2t {
+				nvidia,pins = "pcc2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			muic-usif {
+				nvidia,pins = "ulpi_stp_py3";
+				nvidia,function = "spi1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ifx-usb-vbus-en {
+				nvidia,pins = "kb_row4_pr4";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			pcb-rev {
+				nvidia,pins = "gmi_wait_pi7",
+						"gmi_rst_n_pi4";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			jtag-rtck {
+				nvidia,pins = "jtag_rtck_pu7";
+				nvidia,function = "rtck";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Camera pinmux */
+			cam-mclk {
+				nvidia,pins = "cam_mclk_pcc0";
+				nvidia,function = "vi_alt3";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			cam-pmic-en {
+				nvidia,pins = "pbb4";
+				nvidia,function = "vgp4";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			front-cam-rst {
+				nvidia,pins = "pbb5";
+				nvidia,function = "vgp5";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			front-cam-vio {
+				nvidia,pins = "ulpi_nxt_py2";
+				nvidia,function = "rsvd2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			rear-cam-rst {
+				nvidia,pins = "gmi_cs3_n_pk4";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			rear-cam-eprom-pr {
+				nvidia,pins = "gmi_cs2_n_pk3";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			rear-cam-vcm-pwdn {
+				nvidia,pins = "kb_row1_pr1";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* Haptic pinmux */
+			haptic-en {
+				nvidia,pins = "gmi_ad9_ph1";
+				nvidia,function = "gmi";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			haptic-osc {
+				nvidia,pins = "gmi_ad11_ph3";
+				nvidia,function = "pwm3";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+
+			/* Modem pinmux */
+			cp2ap-ack1-host-active {
+				nvidia,pins = "pu5";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			cp2ap-ack2-host-wakeup {
+				nvidia,pins = "pv0";
+				nvidia,function = "rsvd4";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ap2cp-ack2-suspend-req {
+				nvidia,pins = "kb_row14_ps6";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ap2cp-ack1-slave-wakeup {
+				nvidia,pins = "kb_row15_ps7";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_DOWN>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			cp-kkp {
+				nvidia,pins = "kb_col0_pq0";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			cp-crash-irq {
+				nvidia,pins = "kb_row13_ps5";
+				nvidia,function = "kbc";
+				nvidia,pull = <TEGRA_PIN_PULL_UP>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			ap2cp-uarta-tx-ipc {
+				nvidia,pins = "pu0";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			ap2cp-uarta-rx-ipc {
+				nvidia,pins = "pu1";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			fota-ap-cts-cp-rts {
+				nvidia,pins = "pu2";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			fota-ap-rts-cp-cts {
+				nvidia,pins = "pu3";
+				nvidia,function = "uarta";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_ENABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+			modem-enable {
+				nvidia,pins = "ulpi_data7_po0";
+				nvidia,function = "hsi";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			modem-reset {
+				nvidia,pins = "pv1";
+				nvidia,function = "rsvd1";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_DISABLE>;
+			};
+			dap-i2s2 {
+				nvidia,pins = "dap3_fs_pp0",
+						"dap3_din_pp1",
+						"dap3_dout_pp2",
+						"dap3_sclk_pp3";
+				nvidia,function = "i2s2";
+				nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+				nvidia,tristate = <TEGRA_PIN_DISABLE>;
+				nvidia,enable-input = <TEGRA_PIN_ENABLE>;
+			};
+
+			/* GPIO power/drive control */
+			drive-i2c {
+				nvidia,pins = "drive_dbg",
+						"drive_at5",
+						"drive_gme",
+						"drive_ddc",
+						"drive_ao1";
+				nvidia,high-speed-mode = <TEGRA_PIN_DISABLE>;
+				nvidia,schmitt = <TEGRA_PIN_ENABLE>;
+				nvidia,low-power-mode = <TEGRA_PIN_LP_DRIVE_DIV_1>;
+				nvidia,pull-down-strength = <31>;
+				nvidia,pull-up-strength = <31>;
+				nvidia,slew-rate-rising = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+				nvidia,slew-rate-falling = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+			};
+
+			drive-uart3 {
+				nvidia,pins = "drive_uart3";
+				nvidia,high-speed-mode = <TEGRA_PIN_DISABLE>;
+				nvidia,schmitt = <TEGRA_PIN_ENABLE>;
+				nvidia,low-power-mode = <TEGRA_PIN_LP_DRIVE_DIV_1>;
+				nvidia,pull-down-strength = <31>;
+				nvidia,pull-up-strength = <31>;
+				nvidia,slew-rate-rising = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+				nvidia,slew-rate-falling = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+			};
+
+			drive-gmi {
+				nvidia,pins = "drive_at3";
+				nvidia,high-speed-mode = <TEGRA_PIN_DISABLE>;
+				nvidia,schmitt = <TEGRA_PIN_ENABLE>;
+				nvidia,low-power-mode = <TEGRA_PIN_LP_DRIVE_DIV_1>;
+				nvidia,pull-down-strength = <31>;
+				nvidia,pull-up-strength = <31>;
+				nvidia,slew-rate-rising = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+				nvidia,slew-rate-falling = <TEGRA_PIN_SLEW_RATE_FASTEST>;
+			};
+		};
+	};
+
+	uartb: serial@70006040 {
+		compatible = "nvidia,tegra30-hsuart";
+		reset-names = "serial";
+		/delete-property/ reg-shift;
+		status = "okay";
+
+		/* GNSS GSD5T */
+	};
+
+	uartc: serial@70006200 {
+		compatible = "nvidia,tegra30-hsuart";
+		reset-names = "serial";
+		/delete-property/ reg-shift;
+		status = "okay";
+
+		nvidia,adjust-baud-rates = <0 9600 100>,
+					   <9600 115200 200>,
+					   <1000000 4000000 136>;
+
+		/* BCM4330B1 37.4 MHz Class 1.5 ExtLNA */
+		bluetooth {
+			compatible = "brcm,bcm4330-bt";
+			max-speed = <4000000>;
+
+			clocks = <&tegra_pmc TEGRA_PMC_CLK_BLINK>;
+			clock-names = "txco";
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(S, 4) IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "host-wakeup";
+
+			device-wakeup-gpios = <&gpio TEGRA_GPIO(S, 3) GPIO_ACTIVE_HIGH>;
+			shutdown-gpios = <&gpio TEGRA_GPIO(CC, 5) GPIO_ACTIVE_HIGH>;
+
+			vbat-supply = <&vdd_3v3_vbat>;
+			vddio-supply = <&vdd_1v8_vio>;
+		};
+	};
+
+	uartd: serial@70006300 {
+		/delete-property/ dmas;
+		/delete-property/ dma-names;
+		status = "okay";
+
+		/* Console */
+	};
+
+	pwm@7000a000 {
+		status = "okay";
+	};
+
+	gen1_i2c: i2c@7000c000 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		/* Aichi AMI306 digital compass */
+		magnetometer@e {
+			compatible = "asahi-kasei,ak8974";
+			reg = <0x0e>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(H, 5) IRQ_TYPE_EDGE_RISING>;
+
+			avdd-supply = <&vdd_3v0_sen>;
+			dvdd-supply = <&vdd_1v8_vio>;
+
+			mount-matrix = "-1",  "0",  "0",
+					"0",  "1",  "0",
+					"0",  "0", "-1";
+		};
+
+		max98089: audio-codec@10 {
+			compatible = "maxim,max98089";
+			reg = <0x10>;
+
+			clocks = <&tegra_pmc TEGRA_PMC_CLK_OUT_1>;
+			clock-names = "mclk";
+
+			assigned-clocks = <&tegra_pmc TEGRA_PMC_CLK_OUT_1>;
+			assigned-clock-parents = <&tegra_car TEGRA30_CLK_EXTERN1>;
+		};
+
+		nfc@28 {
+			compatible = "nxp,pn544-i2c";
+			reg = <0x28>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(W, 2) IRQ_TYPE_EDGE_RISING>;
+
+			enable-gpios = <&gpio TEGRA_GPIO(X, 5) GPIO_ACTIVE_HIGH>;
+			firmware-gpios = <&gpio TEGRA_GPIO(R, 0) GPIO_ACTIVE_HIGH>;
+		};
+
+		imu@68 {
+			compatible = "invensense,mpu6050";
+			reg = <0x68>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(H, 4) IRQ_TYPE_EDGE_RISING>;
+
+			vdd-supply = <&vdd_3v0_sen>;
+			vddio-supply = <&vdd_1v8_sen>;
+
+			mount-matrix =  "1",  "0",  "0",
+					"0",  "1",  "0",
+					"0",  "0", "-1";
+		};
+	};
+
+	gen2_i2c: i2c@7000c400 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		/* Synaptics RMI4 S3203B touchcreen */
+		touchscreen@20 {
+			compatible = "syna,rmi4-i2c";
+			reg = <0x20>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(Q, 3) IRQ_TYPE_EDGE_FALLING>;
+
+			vdd-supply = <&vdd_3v0_touch>;
+			vio-supply = <&vdd_1v8_touch>;
+
+			syna,reset-delay-ms = <20>;
+			syna,startup-delay-ms = <200>;
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			rmi4-f01@1 {
+				reg = <0x1>;
+				syna,nosleep-mode = <1>;
+			};
+
+			rmi4-f11@11 {
+				reg = <0x11>;
+				syna,sensor-type = <1>;
+
+				syna,clip-x-low = <0>;
+				syna,clip-y-low = <0>;
+			};
+		};
+	};
+
+	cam_i2c: i2c@7000c500 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		dw9714: coil@c {
+			compatible = "dongwoon,dw9714";
+			reg = <0x0c>;
+
+			enable-gpios = <&gpio TEGRA_GPIO(R, 1) GPIO_ACTIVE_HIGH>;
+
+			vcc-supply = <&vcc_focuser>;
+		};
+
+		camera-pmic@7d {
+			compatible = "ti,lp8720";
+			reg = <0x7d>;
+
+			enable-gpios = <&gpio TEGRA_GPIO(BB, 4) GPIO_ACTIVE_HIGH>;
+
+			vt_1v2_front: ldo1 {
+				regulator-name = "vt_1v2_dig";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+			};
+
+			vt_2v7_front: ldo2 {
+				regulator-name = "vt_2v7_vana";
+				regulator-min-microvolt = <2700000>;
+				regulator-max-microvolt = <2700000>;
+			};
+
+			vdd_2v7_rear: ldo3 {
+				regulator-name = "8m_2v7_vana";
+				regulator-min-microvolt = <2700000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			vio_1v8_rear: ldo4 {
+				regulator-name = "vio_1v8_cam";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+
+			vcc_focuser: ldo5 {
+				regulator-name = "8m_2v8_vcm";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+			};
+
+			vdd_1v2_rear: buck {
+				regulator-name = "8m_1v2_cam";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+			};
+		};
+	};
+
+	hdmi_ddc: i2c@7000c700 {
+		status = "okay";
+		clock-frequency = <100000>;
+	};
+
+	pwr_i2c: i2c@7000d000 {
+		status = "okay";
+		clock-frequency = <400000>;
+
+		pmic: max77663@1c {
+			compatible = "maxim,max77663";
+			reg = <0x1c>;
+
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+
+			#gpio-cells = <2>;
+			gpio-controller;
+
+			system-power-controller;
+
+			pinctrl-names = "default";
+			pinctrl-0 = <&max77663_default>;
+
+			max77663_default: pinmux {
+				gpio1 {
+					pins = "gpio1";
+					function = "gpio";
+					drive-open-drain = <1>;
+				};
+
+				gpio4 {
+					pins = "gpio4";
+					function = "32k-out1";
+				};
+			};
+
+			fps {
+				fps0 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+				};
+
+				fps1 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN1>;
+				};
+
+				fps2 {
+					maxim,fps-event-source = <MAX77620_FPS_EVENT_SRC_EN0>;
+				};
+			};
+
+			regulators {
+				in-sd0-supply = <&vdd_5v0_vbus>;
+				in-sd1-supply = <&vdd_5v0_vbus>;
+				in-sd2-supply = <&vdd_5v0_vbus>;
+				in-sd3-supply = <&vdd_5v0_vbus>;
+
+				in-ldo0-1-supply = <&vdd_1v8_vio>;
+				in-ldo2-supply   = <&vdd_3v3_vbat>;
+				in-ldo3-5-supply = <&vdd_3v3_vbat>;
+				in-ldo4-6-supply = <&vdd_3v3_vbat>;
+				in-ldo7-8-supply = <&vdd_1v8_vio>;
+
+				vdd_cpu: sd0 {
+					regulator-name = "vdd_cpu";
+					regulator-min-microvolt = <800000>;
+					regulator-max-microvolt = <1250000>;
+					regulator-coupled-with = <&vdd_core>;
+					regulator-coupled-max-spread = <300000>;
+					regulator-max-step-microvolt = <100000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					nvidia,tegra-cpu-regulator;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_core: sd1 {
+					regulator-name = "vdd_core";
+					regulator-min-microvolt = <950000>;
+					regulator-max-microvolt = <1350000>;
+					regulator-coupled-with = <&vdd_cpu>;
+					regulator-coupled-max-spread = <300000>;
+					regulator-max-step-microvolt = <100000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					nvidia,tegra-core-regulator;
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				vdd_1v8_vio: sd2 {
+					regulator-name = "vdd_1v8_gen";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				sd3 {
+					regulator-name = "vddio_ddr";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				ldo0 {
+					regulator-name = "avdd_pll";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+				};
+
+				ldo1 {
+					regulator-name = "vdd_ddr_hs";
+					regulator-min-microvolt = <1000000>;
+					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				avdd_3v3_periph: ldo2 {
+					regulator-name = "avdd_usb";
+					regulator-min-microvolt = <3300000>;
+					regulator-max-microvolt = <3300000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_usd: ldo3 {
+					regulator-name = "vdd_sdmmc3";
+					regulator-min-microvolt = <3000000>;
+					regulator-max-microvolt = <3000000>;
+					regulator-always-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				ldo4 {
+					regulator-name = "vdd_rtc";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				vcore_emmc: ldo5 {
+					regulator-name = "vdd_ddr_rx";
+					regulator-min-microvolt = <2850000>;
+					regulator-max-microvolt = <2850000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+				};
+
+				avdd_1v8_hdmi_pll: ldo6 {
+					regulator-name = "avdd_osc";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				vdd_1v2_mhl: ldo7 {
+					regulator-name = "vdd_1v2_mhl";
+					regulator-min-microvolt = <1050000>;
+					regulator-max-microvolt = <1250000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+
+				ldo8 {
+					regulator-name = "avdd_dsi_csi";
+					regulator-min-microvolt = <1200000>;
+					regulator-max-microvolt = <1200000>;
+
+					maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>;
+				};
+			};
+		};
+
+		fuel-gauge@36 {
+			compatible = "maxim,max17043";
+			reg = <0x36>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(S, 0) IRQ_TYPE_EDGE_FALLING>;
+
+			monitored-battery = <&battery>;
+
+			maxim,alert-low-soc-level = <10>;
+			wakeup-source;
+		};
+
+		power-sensor@40 {
+			compatible = "ti,ina230";
+			reg = <0x40>;
+
+			vs-supply = <&vdd_3v0_sen>;
+		};
+
+		nct72: temperature-sensor@4c {
+			compatible = "onnn,nct1008";
+			reg = <0x4c>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(I, 5) IRQ_TYPE_EDGE_FALLING>;
+
+			vcc-supply = <&vdd_3v0_sen>;
+			#thermal-sensor-cells = <1>;
+		};
+	};
+
+	i2c-mhl {
+		compatible = "i2c-gpio";
+
+		sda-gpios = <&gpio TEGRA_GPIO(Q, 7) (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&gpio TEGRA_GPIO(Q, 6) (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+
+		i2c-gpio,delay-us = <5>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
+
+	spi@7000dc00 {
+		status = "okay";
+		spi-max-frequency = <25000000>;
+
+		/* DSI bridge */
+	};
+
+	pmc@7000e400 {
+		status = "okay";
+		nvidia,invert-interrupt;
+		nvidia,suspend-mode = <2>;
+		nvidia,cpu-pwr-good-time = <2000>;
+		nvidia,cpu-pwr-off-time = <200>;
+		nvidia,core-pwr-good-time = <3845 3845>;
+		nvidia,core-pwr-off-time = <0>;
+		nvidia,core-power-req-active-high;
+		nvidia,sys-clock-req-active-high;
+		core-supply = <&vdd_core>;
+
+		i2c-thermtrip {
+			nvidia,i2c-controller-id = <4>;
+			nvidia,bus-addr = <0x1c>;
+			nvidia,reg-addr = <0x41>;
+			nvidia,reg-data = <0x02>;
+		};
+	};
+
+	hda@70030000 {
+		status = "okay";
+	};
+
+	ahub@70080000 {
+		/* HIFI CODEC */
+		i2s@70080300 {		/* i2s0 */
+			status = "okay";
+		};
+
+		/* BASEBAND */
+		i2s@70080500 {		/* i2s2 */
+			status = "okay";
+		};
+
+		/* BT SCO */
+		i2s@70080600 {		/* i2s3 */
+			status = "okay";
+		};
+	};
+
+	sdmmc1: mmc@78000000 {
+		status = "okay";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		assigned-clocks = <&tegra_car TEGRA30_CLK_SDMMC1>;
+		assigned-clock-parents = <&tegra_car TEGRA30_CLK_PLL_C>;
+		assigned-clock-rates = <50000000>;
+
+		max-frequency = <50000000>;
+		keep-power-in-suspend;
+		bus-width = <4>;
+		non-removable;
+
+		mmc-pwrseq = <&brcm_wifi_pwrseq>;
+		vmmc-supply = <&vdd_3v3_vbat>;
+		vqmmc-supply = <&vdd_1v8_vio>;
+
+		/* BCM4330B1 37.4 MHz Class 1.5 ExtLNA */
+		wifi@1 {
+			compatible = "brcm,bcm4329-fmac";
+			reg = <1>;
+
+			interrupt-parent = <&gpio>;
+			interrupts = <TEGRA_GPIO(U, 6) IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "host-wake";
+		};
+	};
+
+	sdmmc4: mmc@78000600 {
+		status = "okay";
+		bus-width = <8>;
+
+		non-removable;
+		mmc-ddr-1_8v;
+
+		vmmc-supply = <&vcore_emmc>;
+		vqmmc-supply = <&vdd_1v8_vio>;
+	};
+
+	/* Micro USB */
+	usb@7d000000 {
+		compatible = "nvidia,tegra30-udc";
+		status = "okay";
+		dr_mode = "peripheral";
+	};
+
+	usb-phy@7d000000 {
+		status = "okay";
+		dr_mode = "peripheral";
+		nvidia,hssync-start-delay = <0>;
+		nvidia,xcvr-lsfslew = <2>;
+		nvidia,xcvr-lsrslew = <2>;
+		vbus-supply = <&avdd_3v3_periph>;
+	};
+
+	/* PMIC has a built-in 32KHz oscillator which is used by PMC */
+	clk32k_in: clock-32k {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		clock-output-names = "pmic-oscillator";
+	};
+
+	gps_refclk: clock-gps {
+		compatible = "fixed-clock";
+		clock-frequency = <26000000>;
+		clock-accuracy = <100>;
+		#clock-cells = <0>;
+	};
+
+	gps_osc: clock-gps-osc-gate {
+		compatible = "gpio-gate-clock";
+		enable-gpios = <&gpio TEGRA_GPIO(H, 0) GPIO_ACTIVE_HIGH>;
+		clocks = <&gps_refclk>;
+		#clock-cells = <0>;
+	};
+
+	cpus {
+		cpu0: cpu@0 {
+			cpu-supply = <&vdd_cpu>;
+			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>;
+		};
+		cpu1: cpu@1 {
+			cpu-supply = <&vdd_cpu>;
+			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>;
+		};
+		cpu2: cpu@2 {
+			cpu-supply = <&vdd_cpu>;
+			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>;
+		};
+		cpu3: cpu@3 {
+			cpu-supply = <&vdd_cpu>;
+			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-power {
+			label = "Power";
+			gpios = <&gpio TEGRA_GPIO(C, 7) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_POWER>;
+			debounce-interval = <10>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+
+		key-volume-down {
+			label = "Volume Down";
+			gpios = <&gpio TEGRA_GPIO(O, 4) GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEDOWN>;
+			debounce-interval = <10>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led-keypad {
+			label = "keypad::white";
+			gpios = <&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+
+			color = <LED_COLOR_ID_WHITE>;
+			function = LED_FUNCTION_KBD_BACKLIGHT;
+		};
+	};
+
+	opp-table-actmon {
+		/delete-node/ opp-625000000;
+		/delete-node/ opp-667000000;
+		/delete-node/ opp-750000000;
+		/delete-node/ opp-800000000;
+		/delete-node/ opp-900000000;
+	};
+
+	opp-table-emc {
+		/delete-node/ opp-625000000-1200;
+		/delete-node/ opp-625000000-1250;
+		/delete-node/ opp-667000000-1200;
+		/delete-node/ opp-750000000-1300;
+		/delete-node/ opp-800000000-1300;
+		/delete-node/ opp-900000000-1350;
+	};
+
+	brcm_wifi_pwrseq: pwrseq-wifi {
+		compatible = "mmc-pwrseq-simple";
+
+		clocks = <&tegra_pmc TEGRA_PMC_CLK_BLINK>;
+		clock-names = "ext_clock";
+
+		reset-gpios = <&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_LOW>;
+		post-power-on-delay-ms = <300>;
+		power-off-delay-us = <300>;
+	};
+
+	vdd_5v0_vbus: regulator-vbus {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vdd_3v3_vbat: regulator-vbat {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_vbat";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vdd_5v0_vbus>;
+	};
+
+	vdd_3v0_sen: regulator-sen3v {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_3v0_sensor";
+		regulator-min-microvolt = <3000000>;
+		regulator-max-microvolt = <3000000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(X, 7) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vdd_3v0_proxi: regulator-proxi {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_3v0_proxi";
+		regulator-min-microvolt = <3000000>;
+		regulator-max-microvolt = <3000000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(X, 1) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vdd_1v8_sen: regulator-sen1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_1v8_sensor";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(D, 2) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vcc_3v0_lcd: regulator-lcd3v {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v0_lcd";
+		regulator-min-microvolt = <3000000>;
+		regulator-max-microvolt = <3000000>;
+		regulator-boot-on;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	iovcc_1v8_lcd: regulator-lcd1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "iovcc_1v8_lcd";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(Y, 0) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vio_1v8_mhl: regulator-mhl1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vio_1v8_mhl";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vdd_3v0_touch: regulator-touchpwr {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_3v0_touch";
+		regulator-min-microvolt = <3000000>;
+		regulator-max-microvolt = <3000000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(Q, 1) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vdd_1v8_touch: regulator-touchvio {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_1v8_touch";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(X, 4) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vcc_1v8_gps: regulator-gps {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v8_gps";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		gpio = <&gpio TEGRA_GPIO(Y, 1) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	vio_1v8_front: regulator-frontvio {
+		compatible = "regulator-fixed";
+		regulator-name = "vt_1v8_cam_vio";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&gpio TEGRA_GPIO(Y, 2) GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		vin-supply = <&vdd_3v3_vbat>;
+	};
+
+	sound {
+		nvidia,audio-routing =
+			"Headphone Jack", "HPL",
+			"Headphone Jack", "HPR",
+			"Int Spk", "SPKL",
+			"Int Spk", "SPKR",
+			"Earpiece", "RECL",
+			"Earpiece", "RECR",
+			"INA1", "Mic Jack",
+			"MIC1", "MICBIAS",
+			"MICBIAS", "Internal Mic 1",
+			"MIC2", "Internal Mic 2";
+
+		nvidia,i2s-controller = <&tegra_i2s0>;
+		nvidia,audio-codec = <&max98089>;
+
+		nvidia,hp-det-gpios = <&gpio TEGRA_GPIO(BB, 6) GPIO_ACTIVE_LOW>;
+		nvidia,mic-det-gpios = <&gpio TEGRA_GPIO(O, 5) GPIO_ACTIVE_HIGH>;
+		nvidia,ext-mic-en-gpios = <&gpio TEGRA_GPIO(X, 0) GPIO_ACTIVE_HIGH>;
+		nvidia,coupled-mic-hp-det;
+
+		clocks = <&tegra_car TEGRA30_CLK_PLL_A>,
+			 <&tegra_car TEGRA30_CLK_PLL_A_OUT0>,
+			 <&tegra_pmc TEGRA_PMC_CLK_OUT_1>;
+		clock-names = "pll_a", "pll_a_out0", "mclk";
+
+		assigned-clocks = <&tegra_car TEGRA30_CLK_EXTERN1>,
+				  <&tegra_pmc TEGRA_PMC_CLK_OUT_1>;
+
+		assigned-clock-parents = <&tegra_car TEGRA30_CLK_PLL_A_OUT0>,
+					 <&tegra_car TEGRA30_CLK_EXTERN1>;
+	};
+
+	thermal-zones {
+		/*
+		 * NCT72 has two sensors:
+		 *
+		 *	0: internal that monitors ambient/skin temperature
+		 *	1: external that is connected to the CPU's diode
+		 *
+		 * Ideally we should use userspace thermal governor,
+		 * but it's a much more complex solution. The "skin"
+		 * zone exists as a simpler solution which prevents
+		 * this device from getting too hot from a user's
+		 * tactile perspective. The CPU zone is intended to
+		 * protect silicon from damage.
+		 */
+
+		skin-thermal {
+			polling-delay-passive = <1000>; /* milliseconds */
+			polling-delay = <5000>; /* milliseconds */
+
+			thermal-sensors = <&nct72 0>;
+
+			trips {
+				trip0: skin-alert {
+					/* throttle at 50C until temperature drops to 49.8C */
+					temperature = <50000>;
+					hysteresis = <200>;
+					type = "passive";
+				};
+
+				trip1: skin-crit {
+					/* shut down at 60C */
+					temperature = <60000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&trip0>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&actmon THERMAL_NO_LIMIT
+								  THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu-thermal {
+			polling-delay-passive = <1000>; /* milliseconds */
+			polling-delay = <5000>; /* milliseconds */
+
+			thermal-sensors = <&nct72 1>;
+
+			trips {
+				trip2: cpu-alert {
+					/* throttle at 75C until temperature drops to 74.8C */
+					temperature = <75000>;
+					hysteresis = <200>;
+					type = "passive";
+				};
+
+				trip3: cpu-crit {
+					/* shut down at 90C */
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map1 {
+					trip = <&trip2>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&actmon THERMAL_NO_LIMIT
+								  THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/imx/Makefile b/arch/arm/boot/dts/nxp/imx/Makefile
index a724d1a7a9a0..4052cad859fa 100644
--- a/arch/arm/boot/dts/nxp/imx/Makefile
+++ b/arch/arm/boot/dts/nxp/imx/Makefile
@@ -45,7 +45,9 @@ dtb-$(CONFIG_SOC_IMX53) += \
 	imx53-mba53.dtb \
 	imx53-ppd.dtb \
 	imx53-qsb.dtb \
+	imx53-qsb-hdmi.dtb \
 	imx53-qsrb.dtb \
+	imx53-qsrb-hdmi.dtb \
 	imx53-sk-imx53.dtb \
 	imx53-sk-imx53-atm0700d4-lvds.dtb \
 	imx53-sk-imx53-atm0700d4-rgb.dtb \
@@ -54,6 +56,8 @@ dtb-$(CONFIG_SOC_IMX53) += \
 	imx53-tx53-x13x.dtb \
 	imx53-usbarmory.dtb \
 	imx53-voipac-bsb.dtb
+imx53-qsb-hdmi-dtbs := imx53-qsb.dtb imx53-qsb-hdmi.dtbo
+imx53-qsrb-hdmi-dtbs := imx53-qsrb.dtb imx53-qsb-hdmi.dtbo
 dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-alti6p.dtb \
 	imx6dl-apf6dev.dtb \
@@ -118,6 +122,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-sabrelite.dtb \
 	imx6dl-sabresd.dtb \
 	imx6dl-savageboard.dtb \
+	imx6dl-sielaff.dtb \
 	imx6dl-skov-revc-lt2.dtb \
 	imx6dl-skov-revc-lt6.dtb \
 	imx6dl-solidsense.dtb \
@@ -147,6 +152,7 @@ dtb-$(CONFIG_SOC_IMX6Q) += \
 	imx6dl-yapp4-phoenix.dtb \
 	imx6dl-yapp4-ursa.dtb \
 	imx6q-apalis-eval.dtb \
+	imx6q-apalis-eval-v1.2.dtb \
 	imx6q-apalis-ixora.dtb \
 	imx6q-apalis-ixora-v1.1.dtb \
 	imx6q-apalis-ixora-v1.2.dtb \
diff --git a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
index e66eef87a7a4..058e9435524f 100644
--- a/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx1-apf9328.dts
@@ -54,7 +54,7 @@
 		#size-cells = <1>;
 	};
 
-	eth: eth@4,c00000 {
+	eth: ethernet@4,c00000 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_eth>;
 		compatible = "davicom,dm9000";
diff --git a/arch/arm/boot/dts/nxp/imx/imx1.dtsi b/arch/arm/boot/dts/nxp/imx/imx1.dtsi
index 1ac10965fdfd..389ecb1ebf8f 100644
--- a/arch/arm/boot/dts/nxp/imx/imx1.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx1.dtsi
@@ -251,7 +251,7 @@
 			};
 		};
 
-		weim: weim@220000 {
+		weim: memory-controller@220000 {
 			#address-cells = <2>;
 			#size-cells = <1>;
 			compatible = "fsl,imx1-weim";
diff --git a/arch/arm/boot/dts/nxp/imx/imx27.dtsi b/arch/arm/boot/dts/nxp/imx/imx27.dtsi
index ec472695c71e..ec3ccc8f4095 100644
--- a/arch/arm/boot/dts/nxp/imx/imx27.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx27.dtsi
@@ -568,7 +568,7 @@
 			status = "disabled";
 		};
 
-		weim: weim@d8002000 {
+		weim: memory-controller@d8002000 {
 			#address-cells = <2>;
 			#size-cells = <1>;
 			compatible = "fsl,imx27-weim";
diff --git a/arch/arm/boot/dts/nxp/imx/imx31.dtsi b/arch/arm/boot/dts/nxp/imx/imx31.dtsi
index e1ae7c175f7d..00006c90d9a7 100644
--- a/arch/arm/boot/dts/nxp/imx/imx31.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx31.dtsi
@@ -352,7 +352,7 @@
 				status = "disabled";
 			};
 
-			weim: weim@b8002000 {
+			weim: memory-controller@b8002000 {
 				compatible = "fsl,imx31-weim", "fsl,imx27-weim";
 				reg = <0xb8002000 0x1000>;
 				clocks = <&clks 56>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx35.dtsi b/arch/arm/boot/dts/nxp/imx/imx35.dtsi
index 2d20e5541acc..442dc15677b8 100644
--- a/arch/arm/boot/dts/nxp/imx/imx35.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx35.dtsi
@@ -374,7 +374,7 @@
 				status = "disabled";
 			};
 
-			weim: weim@b8002000 {
+			weim: memory-controller@b8002000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				clocks = <&clks 0>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx51.dtsi b/arch/arm/boot/dts/nxp/imx/imx51.dtsi
index c96d6311dfa7..4efce49022e4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx51.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx51.dtsi
@@ -578,7 +578,7 @@
 				reg = <0x83fd8000 0x1000>;
 			};
 
-			weim: weim@83fda000 {
+			weim: memory-controller@83fda000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				compatible = "fsl,imx51-weim";
diff --git a/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso
new file mode 100644
index 000000000000..c84e9b052527
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * DT overlay for MCIMXHDMICARD as used with the iMX53 QSB or QSRB boards
+ */
+
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/gpio/gpio.h>
+
+/dts-v1/;
+/plugin/;
+
+&{/} {
+	/delete-node/ panel;
+
+	hdmi: connector-hdmi {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&sii9022_out>;
+			};
+		};
+	};
+
+	reg_1p2v: regulator-1p2v {
+		compatible = "regulator-fixed";
+		regulator-name = "1P2V";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-always-on;
+		vin-supply = <&reg_3p2v>;
+	};
+};
+
+&display0 {
+	status = "okay";
+};
+
+&display0 {
+	port@1 {
+		display0_out: endpoint {
+			remote-endpoint = <&sii9022_in>;
+		};
+	};
+};
+
+&i2c2 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	sii9022: bridge-hdmi@39 {
+		compatible = "sil,sii9022";
+		reg = <0x39>;
+		reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+		interrupts-extended = <&gpio3 31 IRQ_TYPE_LEVEL_LOW>;
+		iovcc-supply = <&reg_3p2v>;
+		#sound-dai-cells = <0>;
+		sil,i2s-data-lanes = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				sii9022_in: endpoint {
+					remote-endpoint = <&display0_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				sii9022_out: endpoint {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
+};
+
+&tve {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-sielaff.dts b/arch/arm/boot/dts/nxp/imx/imx6dl-sielaff.dts
new file mode 100644
index 000000000000..7de8d5f26518
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-sielaff.dts
@@ -0,0 +1,533 @@
+// SPDX-License-Identifier: GPL-2.0+ OR MIT
+/*
+ * Copyright (C) 2022 Kontron Electronics GmbH
+ */
+
+/dts-v1/;
+
+#include "imx6dl.dtsi"
+#include <dt-bindings/clock/imx6qdl-clock.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/ {
+	model = "Sielaff i.MX6 Solo";
+	compatible = "sielaff,imx6dl-board", "fsl,imx6dl";
+
+	chosen {
+		stdout-path = &uart2;
+	};
+
+	backlight: pwm-backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_backlight>;
+		pwms = <&pwm3 0 50000 0>;
+		brightness-levels = <0 0 64 88 112 136 184 232 255>;
+		default-brightness-level = <4>;
+		enable-gpios = <&gpio6 16 GPIO_ACTIVE_HIGH>;
+		power-supply = <&reg_backlight>;
+	};
+
+	cec {
+		compatible = "cec-gpio";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_hdmi_cec>;
+		cec-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>;
+		hdmi-phandle = <&hdmi>;
+	};
+
+	enet_ref: clock-enet-ref {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "enet-ref";
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_keys>;
+
+		key-0 {
+			gpios = <&gpio2 16 0>;
+			debounce-interval = <10>;
+			linux,code = <1>;
+		};
+
+		key-1 {
+			gpios = <&gpio3 27 0>;
+			debounce-interval = <10>;
+			linux,code = <2>;
+		};
+
+		key-2 {
+			gpios = <&gpio5 4 0>;
+			debounce-interval = <10>;
+			linux,code = <3>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpio_leds>;
+
+		led-debug {
+			label = "debug-led";
+			gpios = <&gpio5 21 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	memory@80000000 {
+		reg = <0x80000000 0x20000000>;
+		device_type = "memory";
+	};
+
+	osc_eth_phy: clock-osc-eth-phy {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+		clock-output-names = "osc-eth-phy";
+	};
+
+	panel {
+		compatible = "lg,lb070wv8";
+		backlight = <&backlight>;
+		power-supply = <&reg_3v3>;
+
+		port {
+			panel_in_lvds: endpoint {
+				remote-endpoint = <&lvds_out>;
+			};
+		};
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	reg_backlight: regulator-backlight {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_backlight>;
+		enable-active-high;
+		gpio = <&gpio1 23 GPIO_ACTIVE_HIGH>;
+		regulator-name = "backlight";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	reg_usb_otg_vbus: regulator-usb-otg-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usbotg_vbus>;
+		enable-active-high;
+		gpio = <&gpio4 15 GPIO_ACTIVE_HIGH>;
+		regulator-name = "usb_otg_vbus";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+};
+
+&ecspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi2>;
+	cs-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <20000000>;
+	};
+};
+
+&fec {
+	/*
+	 * Set PTP clock to external instead of internal reference, as the
+	 * REF_CLK from the PHY is fed back into the i.MX6 and the GPR
+	 * register needs to be set accordingly (see mach-imx6q.c).
+	 */
+	clocks = <&clks IMX6QDL_CLK_ENET>,
+		 <&clks IMX6QDL_CLK_ENET>,
+		 <&enet_ref>,
+		 <&clks IMX6QDL_CLK_ENET_REF>;
+	clock-names = "ipg", "ahb", "ptp", "enet_out";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_enet>;
+	phy-connection-type = "rmii";
+	phy-handle = <&ethphy>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy: ethernet-phy@1 {
+			reg = <1>;
+			clocks = <&osc_eth_phy>;
+			clock-names = "rmii-ref";
+			micrel,led-mode = <1>;
+			reset-assert-us = <500>;
+			reset-deassert-us = <100>;
+			reset-gpios = <&gpio5 2 GPIO_ACTIVE_LOW>;
+		};
+	};
+};
+
+&gpio1 {
+	gpio-line-names =
+		"", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "key-out", "key-in",
+		"", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "", "";
+};
+
+&gpio2 {
+	gpio-line-names =
+		"", "", "", "", "", "", "", "",
+		"lan9500a-rst", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "", "";
+};
+
+&gpmi {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	status = "okay";
+};
+
+&hdmi {
+	ddc-i2c-bus = <&i2c4>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	clock-frequency = <100000>;
+	status = "okay";
+
+	rtc@51 {
+		compatible = "nxp,pcf8563";
+		reg = <0x51>;
+	};
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	clock-frequency = <100000>;
+	status = "okay";
+
+	touchscreen@55 {
+		compatible = "sitronix,st1633";
+		reg = <0x55>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touch>;
+		interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+		interrupt-parent = <&gpio5>;
+		gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
+		status = "disabled";
+	};
+
+	touchscreen@5d {
+		compatible = "goodix,gt928";
+		reg = <0x5d>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_touch>;
+		interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-parent = <&gpio5>;
+		irq-gpios = <&gpio5 18 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+		status = "disabled";
+	};
+};
+
+&i2c4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c4>;
+	clock-frequency = <100000>;
+	status = "okay";
+};
+
+&ldb {
+	status = "okay";
+
+	lvds: lvds-channel@0 {
+		fsl,data-mapping = "spwg";
+		fsl,data-width = <24>;
+		status = "okay";
+
+		port@4 {
+			reg = <4>;
+
+			lvds_out: endpoint {
+				remote-endpoint = <&panel_in_lvds>;
+			};
+		};
+	};
+};
+
+&pwm3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm3>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+	status = "okay";
+};
+
+&uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart3>;
+	status = "okay";
+};
+
+&usbh1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbh1>;
+	disable-over-current;
+	status = "okay";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	usb1@1 {
+		compatible = "usb4b4,6570";
+		reg = <1>;
+		clocks = <&clks IMX6QDL_CLK_CKO>;
+
+		assigned-clocks = <&clks IMX6QDL_CLK_CKO>,
+				  <&clks IMX6QDL_CLK_CKO2_SEL>;
+		assigned-clock-parents = <&clks IMX6QDL_CLK_CKO2>,
+					 <&clks IMX6QDL_CLK_OSC>;
+		assigned-clock-rates = <12000000 0>;
+	};
+};
+
+&usbotg {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	dr_mode = "host";
+	over-current-active-low;
+	vbus-supply = <&reg_usb_otg_vbus>;
+	status = "okay";
+};
+
+&usdhc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc3>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	vmmc-supply = <&reg_3v3>;
+	voltage-ranges = <3300 3300>;
+	no-1-8-v;
+	status = "okay";
+};
+
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hog>;
+
+	pinctrl_hog: hoggrp {
+		fsl,pins = <
+			MX6QDL_PAD_RGMII_RD0__GPIO6_IO25	0x1b0b0	/* PMIC_IRQ */
+			MX6QDL_PAD_SD2_DAT3__GPIO1_IO12		0x1b0b0
+			MX6QDL_PAD_SD2_DAT1__GPIO1_IO14		0x1b0b0
+			MX6QDL_PAD_SD2_DAT0__GPIO1_IO15		0x1b0b0
+			MX6QDL_PAD_SD4_DAT0__GPIO2_IO08		0x1b0b0
+			MX6QDL_PAD_EIM_D29__GPIO3_IO29		0x1b0b0
+		>;
+	};
+
+	pinctrl_backlight: backlightgrp {
+		fsl,pins = <
+			MX6QDL_PAD_NANDF_CS3__GPIO6_IO16	0x100b1
+		>;
+	};
+
+	pinctrl_ecspi2: ecspi2grp {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_DAT10__ECSPI2_MISO	0x100b1
+			MX6QDL_PAD_CSI0_DAT9__ECSPI2_MOSI	0x100b1
+			MX6QDL_PAD_CSI0_DAT8__ECSPI2_SCLK	0x100b1
+			MX6QDL_PAD_CSI0_DAT11__GPIO5_IO29	0x100b1
+		>;
+	};
+
+	pinctrl_enet: enetgrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b0b0
+			MX6QDL_PAD_ENET_MDC__ENET_MDC		0x1b0b0
+			MX6QDL_PAD_ENET_RXD0__ENET_RX_DATA0	0x1b0b0
+			MX6QDL_PAD_ENET_RXD1__ENET_RX_DATA1	0x1b0b0
+			MX6QDL_PAD_ENET_CRS_DV__ENET_RX_EN	0x1b0b0
+			MX6QDL_PAD_ENET_RX_ER__ENET_RX_ER	0x1b0b0
+			MX6QDL_PAD_ENET_TXD0__ENET_TX_DATA0	0x1b0b0
+			MX6QDL_PAD_ENET_TXD1__ENET_TX_DATA1	0x1b0b0
+			MX6QDL_PAD_ENET_TX_EN__ENET_TX_EN	0x1b0b0
+			MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0x4001b0a8
+			MX6QDL_PAD_EIM_A25__GPIO5_IO02		0x100b1
+		>;
+	};
+
+	pinctrl_gpio_keys: gpiokeysgrp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_A22__GPIO2_IO16		0x1b080
+			MX6QDL_PAD_EIM_D27__GPIO3_IO27		0x1b080
+			MX6QDL_PAD_EIM_A24__GPIO5_IO04		0x1b080
+		>;
+	};
+
+	pinctrl_gpio_leds: gpioledsgrp {
+		fsl,pins = <
+			MX6QDL_PAD_CSI0_VSYNC__GPIO5_IO21	0x1b0b0
+		>;
+	};
+
+	pinctrl_gpmi_nand: gpminandgrp {
+		fsl,pins = <
+			MX6QDL_PAD_NANDF_CLE__NAND_CLE		0xb0b1
+			MX6QDL_PAD_NANDF_ALE__NAND_ALE		0xb0b1
+			MX6QDL_PAD_NANDF_WP_B__NAND_WP_B	0xb0b1
+			MX6QDL_PAD_NANDF_RB0__NAND_READY_B	0xb000
+			MX6QDL_PAD_NANDF_CS0__NAND_CE0_B	0xb0b1
+			MX6QDL_PAD_SD4_CMD__NAND_RE_B		0xb0b1
+			MX6QDL_PAD_SD4_CLK__NAND_WE_B		0xb0b1
+			MX6QDL_PAD_NANDF_D0__NAND_DATA00	0xb0b1
+			MX6QDL_PAD_NANDF_D1__NAND_DATA01	0xb0b1
+			MX6QDL_PAD_NANDF_D2__NAND_DATA02	0xb0b1
+			MX6QDL_PAD_NANDF_D3__NAND_DATA03	0xb0b1
+			MX6QDL_PAD_NANDF_D4__NAND_DATA04	0xb0b1
+			MX6QDL_PAD_NANDF_D5__NAND_DATA05	0xb0b1
+			MX6QDL_PAD_NANDF_D6__NAND_DATA06	0xb0b1
+			MX6QDL_PAD_NANDF_D7__NAND_DATA07	0xb0b1
+		>;
+	};
+
+	pinctrl_hdmi_cec: hdmicecgrp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_A21__GPIO2_IO17		0x1b8b1
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL3__I2C2_SCL		0x4001b8b1
+			MX6QDL_PAD_KEY_ROW3__I2C2_SDA		0x4001b8b1
+		>;
+	};
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_5__I2C3_SCL		0x4001f8b1
+			MX6QDL_PAD_GPIO_6__I2C3_SDA		0x4001f8b1
+		>;
+	};
+
+	pinctrl_i2c4: i2c4grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_7__I2C4_SCL		0x4001b8b1
+			MX6QDL_PAD_GPIO_8__I2C4_SDA		0x4001b8b1
+		>;
+	};
+
+	pinctrl_pwm3: pwm3grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD4_DAT1__PWM3_OUT		0x1b0b1
+		>;
+	};
+
+	pinctrl_reg_backlight: regbacklightgrp {
+		fsl,pins = <
+			MX6QDL_PAD_ENET_REF_CLK__GPIO1_IO23	0x1b0b1
+		>;
+	};
+
+	pinctrl_reg_usbotg_vbus: regusbotgvbusgrp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_ROW4__GPIO4_IO15		0x1b0b1
+		>;
+	};
+
+	pinctrl_touch: touchgrp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_2__GPIO1_IO02		0x1b0b0
+			MX6QDL_PAD_CSI0_PIXCLK__GPIO5_IO18	0x1b0b0
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_DAT7__UART1_TX_DATA 	0x1b0b1
+			MX6QDL_PAD_SD3_DAT6__UART1_RX_DATA 	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD4_DAT7__UART2_TX_DATA	0x1b0b1
+			MX6QDL_PAD_SD4_DAT4__UART2_RX_DATA	0x1b0b1
+		>;
+	};
+
+	pinctrl_uart3: uart3grp {
+		fsl,pins = <
+			MX6QDL_PAD_EIM_D24__UART3_TX_DATA	0x1b0b0
+			MX6QDL_PAD_EIM_D25__UART3_RX_DATA	0x1b0b0
+		>;
+	};
+
+	pinctrl_usbh1: usbh1grp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_3__USB_H1_OC		0x1b0b1
+			MX6QDL_PAD_CSI0_MCLK__CCM_CLKO1		0x1b0b0
+		>;
+	};
+
+	pinctrl_usbotg: usbotggrp {
+		fsl,pins = <
+			MX6QDL_PAD_KEY_COL4__USB_OTG_OC		0x1b0b1
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX6QDL_PAD_SD3_CMD__SD3_CMD		0x17059
+			MX6QDL_PAD_SD3_CLK__SD3_CLK		0x10059
+			MX6QDL_PAD_SD3_DAT0__SD3_DATA0		0x17059
+			MX6QDL_PAD_SD3_DAT1__SD3_DATA1		0x17059
+			MX6QDL_PAD_SD3_DAT2__SD3_DATA2		0x17059
+			MX6QDL_PAD_SD3_DAT3__SD3_DATA3		0x17059
+			MX6QDL_PAD_GPIO_4__GPIO1_IO04		0x100b1
+		>;
+	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX6QDL_PAD_GPIO_9__WDOG1_B		0x1b0b0
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi
index 3be38a3c4bb1..c32ea040fecd 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi
@@ -117,17 +117,9 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		phy_port2: phy@1 {
-			reg = <1>;
-		};
-
-		phy_port3: phy@2 {
-			reg = <2>;
-		};
-
 		switch@10 {
 			compatible = "qca,qca8334";
-			reg = <10>;
+			reg = <0x10>;
 			reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
 
 			switch_ports: ports {
@@ -149,15 +141,30 @@
 				eth2: port@2 {
 					reg = <2>;
 					label = "eth2";
+					phy-mode = "internal";
 					phy-handle = <&phy_port2>;
 				};
 
 				eth1: port@3 {
 					reg = <3>;
 					label = "eth1";
+					phy-mode = "internal";
 					phy-handle = <&phy_port3>;
 				};
 			};
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				phy_port2: ethernet-phy@1 {
+					reg = <1>;
+				};
+
+				phy_port3: ethernet-phy@2 {
+					reg = <2>;
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval-v1.2.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval-v1.2.dts
new file mode 100644
index 000000000000..15d4a98ee976
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval-v1.2.dts
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx6q-apalis-eval.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX6Q/D Module on Apalis Evaluation Board v1.2";
+	compatible = "toradex,apalis_imx6q-eval-v1.2", "toradex,apalis_imx6q",
+		     "fsl,imx6q";
+
+	reg_3v3_mmc: regulator-3v3-mmc {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 0 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_3v3_mmc>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "3.3V_MMC";
+		startup-delay-us = <10000>;
+	};
+
+	reg_3v3_sd: regulator-3v3-sd {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 1 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <100000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_3v3_sd>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "3.3V_SD";
+		startup-delay-us = <10000>;
+	};
+
+	reg_can1: regulator-can1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_can1_power>;
+		regulator-name = "5V_SW_CAN1";
+		startup-delay-us = <10000>;
+	};
+
+	reg_can2: regulator-can2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio2 2 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_can2_power>;
+		regulator-name = "5V_SW_CAN2";
+		startup-delay-us = <10000>;
+	};
+
+	sound-carrier {
+		compatible = "simple-audio-card";
+		simple-audio-card,bitclock-master = <&codec_dai>;
+		simple-audio-card,format = "i2s";
+		simple-audio-card,frame-master = <&codec_dai>;
+		simple-audio-card,name = "apalis-nau8822";
+		simple-audio-card,routing =
+			"Headphones", "LHP",
+			"Headphones", "RHP",
+			"Speaker", "LSPK",
+			"Speaker", "RSPK",
+			"Line Out", "AUXOUT1",
+			"Line Out", "AUXOUT2",
+			"LAUX", "Line In",
+			"RAUX", "Line In",
+			"LMICP", "Mic In",
+			"RMICP", "Mic In";
+		simple-audio-card,widgets =
+			"Headphones", "Headphones",
+			"Line Out", "Line Out",
+			"Speaker", "Speaker",
+			"Microphone", "Mic In",
+			"Line", "Line In";
+
+		codec_dai: simple-audio-card,codec {
+			sound-dai = <&nau8822_1a>;
+			system-clock-frequency = <12288000>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&ssi2>;
+		};
+	};
+};
+
+&can1 {
+	xceiver-supply = <&reg_can1>;
+	status = "okay";
+};
+
+&can2 {
+	xceiver-supply = <&reg_can2>;
+	status = "okay";
+};
+
+/* I2C1_SDA/SCL on MXM3 209/211 */
+&i2c1 {
+	/* Audio Codec */
+	nau8822_1a: audio-codec@1a {
+		compatible = "nuvoton,nau8822";
+		reg = <0x1a>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_nau8822>;
+		#sound-dai-cells = <0>;
+	};
+
+	/* Current measurement into module VCC */
+	hwmon@40 {
+		compatible = "ti,ina219";
+		reg = <0x40>;
+		shunt-resistor = <5000>;
+	};
+
+	/* Temperature Sensor */
+	temperature-sensor@4f {
+		compatible = "ti,tmp75c";
+		reg = <0x4f>;
+	};
+
+	/* EEPROM */
+	eeprom@57 {
+		compatible = "st,24c02", "atmel,24c02";
+		reg = <0x57>;
+		pagesize = <16>;
+		size = <256>;
+	};
+};
+
+&pcie {
+	status = "okay";
+};
+
+&ssi2 {
+	status = "okay";
+};
+
+/* MMC1 */
+&usdhc1 {
+	bus-width = <4>;
+	pinctrl-0 = <&pinctrl_usdhc1_4bit &pinctrl_mmc_cd>;
+	vmmc-supply = <&reg_3v3_mmc>;
+	status = "okay";
+};
+
+/* SD1 */
+&usdhc2 {
+	cd-gpios = <&gpio6 14 GPIO_ACTIVE_LOW>;
+	pinctrl-0 = <&pinctrl_usdhc2 &pinctrl_sd_cd>;
+	vmmc-supply = <&reg_3v3_sd>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_enable_3v3_mmc: enable3v3mmcgrp {
+		fsl,pins = <
+			/* MMC1_PWR_CTRL */
+			MX6QDL_PAD_NANDF_D0__GPIO2_IO00 0x1b0b0
+		>;
+	};
+
+	pinctrl_enable_3v3_sd: enable3v3sdgrp {
+		fsl,pins = <
+			/* SD1_PWR_CTRL */
+			MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x1b0b0
+		>;
+	};
+
+	pinctrl_enable_can1_power: enablecan1powergrp {
+		fsl,pins = <
+			/* CAN1_PWR_EN */
+			MX6QDL_PAD_NANDF_D3__GPIO2_IO03 0x1b0b0
+		>;
+	};
+
+	pinctrl_enable_can2_power: enablecan2powergrp {
+		fsl,pins = <
+			/* CAN2_PWR_EN */
+			MX6QDL_PAD_NANDF_D2__GPIO2_IO02 0x1b0b0
+		>;
+	};
+
+	pinctrl_nau8822: nau8822grp {
+		fsl,pins = <
+			MX6QDL_PAD_DISP0_DAT16__AUD5_TXC	0x130b0
+			MX6QDL_PAD_DISP0_DAT17__AUD5_TXD	0x130b0
+			MX6QDL_PAD_DISP0_DAT18__AUD5_TXFS	0x130b0
+			MX6QDL_PAD_DISP0_DAT19__AUD5_RXD	0x130b0
+		>;
+	};
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dts b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dts
index 3fc079dfd61e..e1077e2da5f4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dts
@@ -7,29 +7,13 @@
 
 /dts-v1/;
 
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/interrupt-controller/irq.h>
-#include "imx6q.dtsi"
-#include "imx6qdl-apalis.dtsi"
+#include "imx6q-apalis-eval.dtsi"
 
 / {
 	model = "Toradex Apalis iMX6Q/D Module on Apalis Evaluation Board";
 	compatible = "toradex,apalis_imx6q-eval", "toradex,apalis_imx6q",
 		     "fsl,imx6q";
 
-	aliases {
-		i2c0 = &i2c1;
-		i2c1 = &i2c3;
-		i2c2 = &i2c2;
-		rtc0 = &rtc_i2c;
-		rtc1 = &snvs_rtc;
-	};
-
-	chosen {
-		stdout-path = "serial0:115200n8";
-	};
-
 	reg_pcie_switch: regulator-pcie-switch {
 		compatible = "regulator-fixed";
 		enable-active-high;
@@ -40,14 +24,6 @@
 		startup-delay-us = <100000>;
 		status = "okay";
 	};
-
-	reg_3v3_sw: regulator-3v3-sw {
-		compatible = "regulator-fixed";
-		regulator-always-on;
-		regulator-max-microvolt = <3300000>;
-		regulator-min-microvolt = <3300000>;
-		regulator-name = "3.3V_SW";
-	};
 };
 
 &can1 {
@@ -62,102 +38,22 @@
 
 /* I2C1_SDA/SCL on MXM3 209/211 (e.g. RTC on carrier board) */
 &i2c1 {
-	status = "okay";
-
+	/* PCIe Switch */
 	pcie-switch@58 {
 		compatible = "plx,pex8605";
 		reg = <0x58>;
 	};
-
-	/* M41T0M6 real time clock on carrier board */
-	rtc_i2c: rtc@68 {
-		compatible = "st,m41t0";
-		reg = <0x68>;
-	};
-};
-
-/*
- * I2C3_SDA/SCL (CAM) on MXM3 pin 201/203 (e.g. camera sensor on carrier
- * board)
- */
-&i2c3 {
-	status = "okay";
 };
 
 &pcie {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_reset_moci>;
-	/* active-high meaning opposite of regular PERST# active-low polarity */
-	reset-gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
-	reset-gpio-active-high;
 	vpcie-supply = <&reg_pcie_switch>;
 	status = "okay";
 };
 
-&pwm1 {
-	status = "okay";
-};
-
-&pwm2 {
-	status = "okay";
-};
-
-&pwm3 {
-	status = "okay";
-};
-
-&pwm4 {
-	status = "okay";
-};
-
-&reg_usb_host_vbus {
-	status = "okay";
-};
-
-&reg_usb_otg_vbus {
-	status = "okay";
-};
-
-&sata {
-	status = "okay";
-};
-
 &sound_spdif {
 	status = "okay";
 };
 
-&spdif {
-	status = "okay";
-};
-
-&uart1 {
-	status = "okay";
-};
-
-&uart2 {
-	status = "okay";
-};
-
-&uart4 {
-	status = "okay";
-};
-
-&uart5 {
-	status = "okay";
-};
-
-&usbh1 {
-	disable-over-current;
-	vbus-supply = <&reg_usb_host_vbus>;
-	status = "okay";
-};
-
-&usbotg {
-	disable-over-current;
-	vbus-supply = <&reg_usb_otg_vbus>;
-	status = "okay";
-};
-
 /* MMC1 */
 &usdhc1 {
 	status = "okay";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dtsi
new file mode 100644
index 000000000000..b6c45ad3f430
--- /dev/null
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-apalis-eval.dtsi
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2014-2024 Toradex
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include "imx6q.dtsi"
+#include "imx6qdl-apalis.dtsi"
+
+/ {
+	aliases {
+		i2c0 = &i2c1;
+		i2c1 = &i2c3;
+		i2c2 = &i2c2;
+		rtc0 = &rtc_i2c;
+		rtc1 = &snvs_rtc;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	reg_3v3_sw: regulator-3v3-sw {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "3.3V_SW";
+	};
+};
+
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	/* M41T0M6 real time clock on carrier board */
+	rtc_i2c: rtc@68 {
+		compatible = "st,m41t0";
+		reg = <0x68>;
+	};
+};
+
+/*
+ * I2C3_SDA/SCL (CAM) on MXM3 pin 201/203 (e.g. camera sensor on carrier
+ * board)
+ */
+&i2c3 {
+	status = "okay";
+};
+
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_reset_moci>;
+	/* active-high meaning opposite of regular PERST# active-low polarity */
+	reset-gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+	reset-gpio-active-high;
+};
+
+&pwm1 {
+	status = "okay";
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&pwm3 {
+	status = "okay";
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&reg_usb_host_vbus {
+	status = "okay";
+};
+
+&reg_usb_otg_vbus {
+	status = "okay";
+};
+
+&sata {
+	status = "okay";
+};
+
+&spdif {
+	status = "okay";
+};
+
+&uart1 {
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&uart4 {
+	status = "okay";
+};
+
+&uart5 {
+	status = "okay";
+};
+
+&usbh1 {
+	disable-over-current;
+	vbus-supply = <&reg_usb_host_vbus>;
+	status = "okay";
+};
+
+&usbotg {
+	disable-over-current;
+	vbus-supply = <&reg_usb_otg_vbus>;
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
index db8c332df6a1..cad112e05475 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-b850v3.dts
@@ -227,7 +227,6 @@
 
 		#address-cells = <3>;
 		#size-cells = <2>;
-		#interrupt-cells = <1>;
 
 		bridge@2,1 {
 			compatible = "pci10b5,8605";
@@ -235,7 +234,6 @@
 
 			#address-cells = <3>;
 			#size-cells = <2>;
-			#interrupt-cells = <1>;
 
 			/* Intel Corporation I210 Gigabit Network Connection */
 			ethernet@3,0 {
@@ -250,7 +248,6 @@
 
 			#address-cells = <3>;
 			#size-cells = <2>;
-			#interrupt-cells = <1>;
 
 			/* Intel Corporation I210 Gigabit Network Connection */
 			switch_nic: ethernet@4,0 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
index 99f4f6ac71d4..c1ae7c47b442 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6q-bx50v3.dtsi
@@ -245,6 +245,7 @@
 				reg = <0x74>;
 				gpio-controller;
 				#gpio-cells = <2>;
+				#interrupt-cells = <2>;
 				interrupt-controller;
 				interrupt-parent = <&gpio2>;
 				interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
@@ -390,7 +391,6 @@
 
 		#address-cells = <3>;
 		#size-cells = <2>;
-		#interrupt-cells = <1>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
index 2ae93f57fe5a..ea40623d12e5 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
@@ -626,7 +626,6 @@
 		blocks = <0x5>;
 		id = <0>;
 		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
 		interrupt-parent = <&gpio4>;
 		irq-trigger = <0x1>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
index 55c90f6393ad..d3a7a6eeb8e0 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-colibri.dtsi
@@ -550,7 +550,6 @@
 		blocks = <0x5>;
 		interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio6>;
-		interrupt-controller;
 		id = <0>;
 		irq-trigger = <0x1>;
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
index a63e73adc1fc..42b2ba23aefc 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-emcon.dtsi
@@ -225,7 +225,6 @@
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
-		interrupt-controller;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard.dtsi
index bfade7149080..a955c77cd499 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard.dtsi
@@ -41,6 +41,11 @@
 #include <dt-bindings/sound/fsl-imx-audmux.h>
 
 / {
+	aliases {
+		rtc0 = &carrier_rtc;
+		rtc1 = &snvs_rtc;
+	};
+
 	/* Will be filled by the bootloader */
 	memory@10000000 {
 		device_type = "memory";
@@ -187,7 +192,7 @@
 	status = "okay";
 
 	/* Pro baseboard model */
-	rtc@68 {
+	carrier_rtc: rtc@68 {
 		compatible = "nxp,pcf8523";
 		reg = <0x68>;
 	};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard2.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard2.dtsi
index 0883ef99cded..e6017f9bf640 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard2.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-hummingboard2.dtsi
@@ -41,6 +41,11 @@
 #include <dt-bindings/sound/fsl-imx-audmux.h>
 
 / {
+	aliases {
+		rtc0 = &pcf8523;
+		rtc1 = &snvs_rtc;
+	};
+
 	/* Will be filled by the bootloader */
 	memory@10000000 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
index 113974520d54..c0c47adc5866 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
@@ -124,6 +124,7 @@
 		reg = <0x58>;
 		interrupt-parent = <&gpio2>;
 		interrupts = <9 IRQ_TYPE_LEVEL_LOW>; /* active-low GPIO2_9 */
+		#interrupt-cells = <2>;
 		interrupt-controller;
 
 		regulators {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
index 86b4269e0e01..85e278eb2016 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
@@ -100,6 +100,7 @@
 		interrupt-parent = <&gpio1>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		gpio-controller;
 		#gpio-cells = <2>;
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
index 2731faede1cb..d59d5d0e1d19 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
@@ -13,10 +13,14 @@
 	aliases {
 		can0 = &can1;
 		can1 = &can2;
+		ethernet0 = &fec;
+		ethernet1 = &lan1;
+		ethernet2 = &lan2;
 		mdio-gpio0 = &mdio;
 		nand = &gpmi;
 		rtc0 = &i2c_rtc;
 		rtc1 = &snvs;
+		switch0 = &switch;
 		usb0 = &usbh1;
 		usb1 = &usbotg;
 	};
@@ -60,7 +64,7 @@
 		gpios = <&gpio1 31 GPIO_ACTIVE_HIGH>,
 			<&gpio1 22 GPIO_ACTIVE_HIGH>;
 
-		switch@0 {
+		switch: switch@0 {
 			compatible = "microchip,ksz8873";
 			pinctrl-names = "default";
 			pinctrl-0 = <&pinctrl_switch>;
@@ -73,13 +77,13 @@
 				#address-cells = <1>;
 				#size-cells = <0>;
 
-				ports@0 {
+				lan1: ports@0 {
 					reg = <0>;
 					phy-mode = "internal";
 					label = "lan1";
 				};
 
-				ports@1 {
+				lan2: ports@1 {
 					reg = <1>;
 					phy-mode = "internal";
 					label = "lan2";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
index 81142c523fa8..8431b8a994f4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl.dtsi
@@ -1158,7 +1158,7 @@
 				status = "disabled";
 			};
 
-			weim: weim@21b8000 {
+			weim: memory-controller@21b8000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				compatible = "fsl,imx6q-weim";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6sl-tolino-shine2hd.dts b/arch/arm/boot/dts/nxp/imx/imx6sl-tolino-shine2hd.dts
index 815119c12bd4..5636fb3661e8 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6sl-tolino-shine2hd.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6sl-tolino-shine2hd.dts
@@ -141,8 +141,10 @@
 		interrupts = <6 IRQ_TYPE_EDGE_FALLING>;
 		vdd-supply = <&ldo1_reg>;
 		reset-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
-		x-size = <1072>;
-		y-size = <1448>;
+		touchscreen-size-x = <1072>;
+		touchscreen-size-y = <1448>;
+		touchscreen-swapped-x-y;
+		touchscreen-inverted-x;
 	};
 
 	/* TODO: TPS65185 PMIC for E Ink at 0x68 */
diff --git a/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi
index 28111efb19a6..6aa61235e39e 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6sl.dtsi
@@ -949,7 +949,7 @@
 				clocks = <&clks IMX6SL_CLK_DUMMY>;
 			};
 
-			weim: weim@21b8000 {
+			weim: memory-controller@21b8000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				reg = <0x021b8000 0x4000>;
diff --git a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
index df3a375f0a3e..0de359d62a47 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6sx.dtsi
@@ -1107,7 +1107,7 @@
 				status = "disabled";
 			};
 
-			weim: weim@21b8000 {
+			weim: memory-controller@21b8000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				compatible = "fsl,imx6sx-weim", "fsl,imx6q-weim";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
index 2ac40d69425b..f10f0525490b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-14x14-evk.dtsi
@@ -321,7 +321,7 @@
 &tsc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_tsc>;
-	xnur-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;
+	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 	measure-delay-time = <0xffff>;
 	pre-charge-time = <0xfff>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
index 875ae699c5cb..2ca18f3dad0a 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
@@ -203,7 +203,7 @@
 &tsc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_tsc>;
-	xnur-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;
+	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 };
 
 &sai2 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6uldev.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6uldev.dtsi
index 18cac19aa9b0..af337f18a266 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6uldev.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6uldev.dtsi
@@ -156,7 +156,7 @@
 &tsc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_tsc>;
-	xnur-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;
+	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 	measure-delay-time = <0xffff>;
 	pre-charge-time = <0xffff>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
index a27a7554c2e7..235aa676618b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul.dtsi
@@ -370,7 +370,7 @@
 				};
 			};
 
-			tsc: tsc@2040000 {
+			tsc: touchscreen@2040000 {
 				compatible = "fsl,imx6ul-tsc";
 				reg = <0x02040000 0x4000>, <0x0219c000 0x4000>;
 				interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
@@ -538,6 +538,8 @@
 				fsl,num-rx-queues = <1>;
 				fsl,stop-mode = <&gpr 0x10 4>;
 				fsl,magic-packet;
+				nvmem-cells = <&fec2_mac_addr>;
+				nvmem-cell-names = "mac-address";
 				status = "disabled";
 			};
 
@@ -638,6 +640,7 @@
 					nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
 					nvmem-cell-names = "calib", "temp_grade";
 					clocks = <&clks IMX6UL_CLK_PLL3_USB_OTG>;
+					#thermal-sensor-cells = <0>;
 				};
 			};
 
@@ -855,7 +858,6 @@
 				clocks = <&clks IMX6UL_CLK_USBOH3>;
 				fsl,usbphy = <&usbphy1>;
 				fsl,usbmisc = <&usbmisc 0>;
-				fsl,anatop = <&anatop>;
 				ahb-burst-config = <0x0>;
 				tx-burst-size-dword = <0x10>;
 				rx-burst-size-dword = <0x10>;
@@ -897,6 +899,8 @@
 				fsl,num-rx-queues = <1>;
 				fsl,stop-mode = <&gpr 0x10 3>;
 				fsl,magic-packet;
+				nvmem-cells = <&fec1_mac_addr>;
+				nvmem-cell-names = "mac-address";
 				status = "disabled";
 			};
 
@@ -975,7 +979,7 @@
 				clocks = <&clks IMX6UL_CLK_MMDC_P0_IPG>;
 			};
 
-			weim: weim@21b8000 {
+			weim: memory-controller@21b8000 {
 				#address-cells = <2>;
 				#size-cells = <1>;
 				compatible = "fsl,imx6ul-weim", "fsl,imx6q-weim";
@@ -1004,6 +1008,14 @@
 				cpu_speed_grade: speed-grade@10 {
 					reg = <0x10 4>;
 				};
+
+				fec1_mac_addr: mac-addr@88 {
+					reg = <0x88 6>;
+				};
+
+				fec2_mac_addr: mac-addr@8e {
+					reg = <0x8e 6>;
+				};
 			};
 
 			csi: csi@21c4000 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som-cfg-sdcard.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som-cfg-sdcard.dtsi
index 040421f9c970..5e39f8dc1351 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som-cfg-sdcard.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som-cfg-sdcard.dtsi
@@ -14,10 +14,12 @@
  */
 
 /*
- * To use usdhc1 as SD card, the WiFi node must be deleted.
+ * To use usdhc1 as SD card, the WiFi node must be deleted. The associated
+ * pwrseq node is also deleted in order to ensure that GPIO H is released.
  * BT is also not available, so remove BT from the UART node.
  */
 /delete-node/ &brcmf;
+/delete-node/ &usdhc1_pwrseq;
 /delete-node/ &bluetooth;
 
 / {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som.dtsi
index 830b5a5064f2..a74f5273f9b3 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcom-som.dtsi
@@ -52,7 +52,7 @@
 	};
 
 	/* SoM with WiFi/BT: WiFi pin WL_REG_ON is connected to a DHCOM GPIO */
-	/omit-if-no-ref/ usdhc1_pwrseq: usdhc1-pwrseq {
+	usdhc1_pwrseq: usdhc1-pwrseq {
 		compatible = "mmc-pwrseq-simple";
 		reset-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; /* GPIO H */
 	};
@@ -273,7 +273,7 @@
 	pinctrl-names = "default";
 	pre-charge-time = <0xfff>;
 	touchscreen-average-samples = <32>;
-	xnur-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>;
+	xnur-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 };
 
 /* DHCOM UART1 */
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcor-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcor-som.dtsi
index 45315adfaa86..75486e1b0c15 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-dhcor-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-dhcor-som.dtsi
@@ -28,10 +28,14 @@
 	/*
 	 * Due to the design as a solderable SOM, there are no capacitors
 	 * below the SoC, therefore higher voltages are required.
+	 * Due to CPU lifetime consideration of the SoC manufacturer and
+	 * the preferred area of operation in the industrial related
+	 * environment, set the maximum frequency for each DHCOM i.MX6ULL
+	 * to 792MHz, as with the industrial type.
 	 */
+	clock-frequency = <792000000>;
 	operating-points = <
 		/* kHz	uV */
-		900000	1275000
 		792000	1250000 /* Voltage increased */
 		528000	1175000
 		396000	1025000
@@ -39,7 +43,6 @@
 	>;
 	fsl,soc-operating-points = <
 		/* KHz	uV */
-		900000	1250000
 		792000	1250000 /* Voltage increased */
 		528000	1175000
 		396000	1175000
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull.dtsi
index 2bccd45e9fc2..8a1776067ecc 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull.dtsi
@@ -75,7 +75,7 @@
 				clocks = <&clks IMX6UL_CLK_DUMMY>;
 			};
 
-			iomuxc_snvs: iomuxc-snvs@2290000 {
+			iomuxc_snvs: pinctrl@2290000 {
 				compatible = "fsl,imx6ull-iomuxc-snvs";
 				reg = <0x02290000 0x4000>;
 			};
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
index 3df6dff7734a..1235a71c6abe 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
@@ -18,6 +18,8 @@
 		mmc0 = &usdhc3;
 		mmc1 = &usdhc1;
 		/delete-property/ mmc2;
+		rtc0 = &ds1339;
+		rtc1 = &snvs_rtc;
 	};
 
 	beeper {
@@ -32,11 +34,18 @@
 	gpio_buttons: gpio-keys {
 		compatible = "gpio-keys";
 
+		/*
+		 * NOTE: These buttons are attached to a GPIO-expander.
+		 * Enabling wakeup-source, enables wakeup on all inputs.
+		 * If PE_GPIO[3..6] are used as inputs, they cause a
+		 * wakeup as well.
+		 */
 		button-0 {
 			/* #SWITCH_A */
 			label = "S11";
 			linux,code = <KEY_1>;
 			gpios = <&pca9555 13 GPIO_ACTIVE_LOW>;
+			wakeup-source;
 		};
 
 		button-1 {
@@ -44,6 +53,7 @@
 			label = "S12";
 			linux,code = <KEY_2>;
 			gpios = <&pca9555 14 GPIO_ACTIVE_LOW>;
+			wakeup-source;
 		};
 
 		button-2 {
@@ -51,6 +61,7 @@
 			label = "S13";
 			linux,code = <KEY_3>;
 			gpios = <&pca9555 15 GPIO_ACTIVE_LOW>;
+			wakeup-source;
 		};
 	};
 
@@ -171,6 +182,14 @@
 		regulator-always-on;
 	};
 
+	reg_vcc_3v3: regulator-vcc-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
 	sound {
 		compatible = "fsl,imx-audio-tlv320aic32x4";
 		model = "imx-audio-tlv320aic32x4";
@@ -198,9 +217,9 @@
 
 &ecspi1 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_ecspi1>;
+	pinctrl-0 = <&pinctrl_ecspi1>, <&pinctrl_ecspi1_ss0>;
 	cs-gpios = <&gpio4 0 GPIO_ACTIVE_LOW>, <&gpio4 1 GPIO_ACTIVE_LOW>,
-		   <&gpio4 2 GPIO_ACTIVE_LOW>;
+		   <&gpio4 2 GPIO_ACTIVE_LOW>, <&gpio4 19 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
@@ -214,8 +233,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet1>;
 	phy-mode = "rgmii-id";
-	phy-reset-gpios = <&gpio7 15 GPIO_ACTIVE_LOW>;
-	phy-reset-duration = <1>;
 	phy-supply = <&reg_fec1_pwdn>;
 	phy-handle = <&ethphy1_0>;
 	fsl,magic-packet;
@@ -228,10 +245,15 @@
 		ethphy1_0: ethernet-phy@0 {
 			compatible = "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_enet1_phy>;
 			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_50_NS>;
 			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_50_NS>;
 			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+			reset-gpios = <&gpio7 15 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <1000>;
+			reset-deassert-us = <500>;
 		};
 	};
 };
@@ -290,13 +312,17 @@
 	lm75: temperature-sensor@49 {
 		compatible = "national,lm75";
 		reg = <0x49>;
+		vs-supply = <&reg_vcc_3v3>;
 	};
 };
 
 &i2c2 {
 	clock-frequency = <100000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c2>;
+	pinctrl-1 = <&pinctrl_i2c2_recovery>;
+	scl-gpios = <&gpio4 10 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio4 11 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 
 	tlv320aic32x4: audio-codec@18 {
@@ -319,13 +345,17 @@
 		interrupts = <12 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
+		vcc-supply = <&reg_vcc_3v3>;
 	};
 };
 
 &i2c3 {
 	clock-frequency = <100000>;
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c3>;
+	pinctrl-1 = <&pinctrl_i2c3_recovery>;
+	scl-gpios = <&gpio4 12 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio4 13 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 };
 
@@ -334,213 +364,213 @@
 	pinctrl-0 = <&pinctrl_hog_mba7_1>;
 
 	pinctrl_ecspi1: ecspi1grp {
+		fsl,pins =
+			<MX7D_PAD_ECSPI1_MISO__ECSPI1_MISO		0x7c>,
+			<MX7D_PAD_ECSPI1_MOSI__ECSPI1_MOSI		0x74>,
+			<MX7D_PAD_ECSPI1_SCLK__ECSPI1_SCLK		0x74>,
+			<MX7D_PAD_UART1_RX_DATA__GPIO4_IO0		0x74>,
+			<MX7D_PAD_UART1_TX_DATA__GPIO4_IO1		0x74>,
+			<MX7D_PAD_UART2_RX_DATA__GPIO4_IO2		0x74>;
+	};
+
+	pinctrl_ecspi1_ss0: ecspi1ss0grp {
 		fsl,pins = <
-			MX7D_PAD_ECSPI1_MISO__ECSPI1_MISO		0x7c
-			MX7D_PAD_ECSPI1_MOSI__ECSPI1_MOSI		0x74
-			MX7D_PAD_ECSPI1_SCLK__ECSPI1_SCLK		0x74
-			MX7D_PAD_UART1_RX_DATA__GPIO4_IO0		0x74
-			MX7D_PAD_UART1_TX_DATA__GPIO4_IO1		0x74
-			MX7D_PAD_UART2_RX_DATA__GPIO4_IO2		0x74
+			MX7D_PAD_ECSPI1_SS0__GPIO4_IO19			0x74
 		>;
 	};
 
 	pinctrl_ecspi2: ecspi2grp {
-		fsl,pins = <
-			MX7D_PAD_ECSPI2_MISO__ECSPI2_MISO		0x7c
-			MX7D_PAD_ECSPI2_MOSI__ECSPI2_MOSI		0x74
-			MX7D_PAD_ECSPI2_SCLK__ECSPI2_SCLK		0x74
-			MX7D_PAD_ECSPI2_SS0__ECSPI2_SS0			0x74
-		>;
+		fsl,pins =
+			<MX7D_PAD_ECSPI2_MISO__ECSPI2_MISO		0x7c>,
+			<MX7D_PAD_ECSPI2_MOSI__ECSPI2_MOSI		0x74>,
+			<MX7D_PAD_ECSPI2_SCLK__ECSPI2_SCLK		0x74>,
+			<MX7D_PAD_ECSPI2_SS0__ECSPI2_SS0		0x74>;
 	};
 
 	pinctrl_enet1: enet1grp {
-		fsl,pins = <
-			MX7D_PAD_GPIO1_IO10__ENET1_MDIO			0x02
-			MX7D_PAD_GPIO1_IO11__ENET1_MDC			0x00
-			MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC	0x71
-			MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0	0x71
-			MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1	0x71
-			MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2	0x71
-			MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3	0x71
-			MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL	0x71
-			MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC	0x79
-			MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0	0x79
-			MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1	0x79
-			MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2	0x79
-			MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3	0x79
-			MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x79
+		fsl,pins =
+			<MX7D_PAD_GPIO1_IO10__ENET1_MDIO			0x02>,
+			<MX7D_PAD_GPIO1_IO11__ENET1_MDC				0x00>,
+			<MX7D_PAD_ENET1_RGMII_TXC__ENET1_RGMII_TXC		0x71>,
+			<MX7D_PAD_ENET1_RGMII_TD0__ENET1_RGMII_TD0		0x71>,
+			<MX7D_PAD_ENET1_RGMII_TD1__ENET1_RGMII_TD1		0x71>,
+			<MX7D_PAD_ENET1_RGMII_TD2__ENET1_RGMII_TD2		0x71>,
+			<MX7D_PAD_ENET1_RGMII_TD3__ENET1_RGMII_TD3		0x71>,
+			<MX7D_PAD_ENET1_RGMII_TX_CTL__ENET1_RGMII_TX_CTL	0x71>,
+			<MX7D_PAD_ENET1_RGMII_RXC__ENET1_RGMII_RXC		0x79>,
+			<MX7D_PAD_ENET1_RGMII_RD0__ENET1_RGMII_RD0		0x79>,
+			<MX7D_PAD_ENET1_RGMII_RD1__ENET1_RGMII_RD1		0x79>,
+			<MX7D_PAD_ENET1_RGMII_RD2__ENET1_RGMII_RD2		0x79>,
+			<MX7D_PAD_ENET1_RGMII_RD3__ENET1_RGMII_RD3		0x79>,
+			<MX7D_PAD_ENET1_RGMII_RX_CTL__ENET1_RGMII_RX_CTL	0x79>;
+	};
+
+	pinctrl_enet1_phy: enet1phygrp {
+		fsl,pins =
 			/* Reset: SION, 100kPU, SRE_FAST, DSE_X1 */
-			MX7D_PAD_ENET1_COL__GPIO7_IO15		0x40000070
+			<MX7D_PAD_ENET1_COL__GPIO7_IO15				0x40000070>,
 			/* INT/PWDN: SION, 100kPU, HYS, SRE_FAST, DSE_X1 */
-			MX7D_PAD_GPIO1_IO09__GPIO1_IO9		0x40000078
-		>;
+			<MX7D_PAD_GPIO1_IO09__GPIO1_IO9				0x40000078>;
 	};
 
 	pinctrl_flexcan1: flexcan1grp {
-		fsl,pins = <
-			MX7D_PAD_GPIO1_IO12__FLEXCAN1_RX	0x5a
-			MX7D_PAD_GPIO1_IO13__FLEXCAN1_TX	0x52
-		>;
+		fsl,pins =
+			<MX7D_PAD_GPIO1_IO12__FLEXCAN1_RX	0x5a>,
+			<MX7D_PAD_GPIO1_IO13__FLEXCAN1_TX	0x52>;
 	};
 
 	pinctrl_flexcan2: flexcan2grp {
-		fsl,pins = <
-			MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX	0x5a
-			MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX	0x52
-		>;
+		fsl,pins =
+			<MX7D_PAD_GPIO1_IO14__FLEXCAN2_RX	0x5a>,
+			<MX7D_PAD_GPIO1_IO15__FLEXCAN2_TX	0x52>;
 	};
 
 	pinctrl_hog_mba7_1: hogmba71grp {
-		fsl,pins = <
+		fsl,pins =
 			/* Limitation: WDOG2_B / WDOG2_RESET not usable */
-			MX7D_PAD_ENET1_RX_CLK__GPIO7_IO13	0x4000007c
-			MX7D_PAD_ENET1_CRS__GPIO7_IO14		0x40000074
+			<MX7D_PAD_ENET1_RX_CLK__GPIO7_IO13	0x4000007c>,
+			<MX7D_PAD_ENET1_CRS__GPIO7_IO14		0x40000074>,
 			/* #BOOT_EN */
-			MX7D_PAD_UART2_TX_DATA__GPIO4_IO3	0x40000010
-		>;
+			<MX7D_PAD_UART2_TX_DATA__GPIO4_IO3	0x40000010>;
 	};
 
 	pinctrl_i2c2: i2c2grp {
-		fsl,pins = <
-			MX7D_PAD_I2C2_SCL__I2C2_SCL		0x40000078
-			MX7D_PAD_I2C2_SDA__I2C2_SDA		0x40000078
-		>;
+		fsl,pins =
+			<MX7D_PAD_I2C2_SCL__I2C2_SCL		0x40000078>,
+			<MX7D_PAD_I2C2_SDA__I2C2_SDA		0x40000078>;
+	};
+
+	pinctrl_i2c2_recovery: i2c2recoverygrp {
+		fsl,pins =
+			<MX7D_PAD_I2C2_SCL__GPIO4_IO10		0x40000078>,
+			<MX7D_PAD_I2C2_SDA__GPIO4_IO11		0x40000078>;
 	};
 
 	pinctrl_i2c3: i2c3grp {
-		fsl,pins = <
-			MX7D_PAD_I2C3_SCL__I2C3_SCL		0x40000078
-			MX7D_PAD_I2C3_SDA__I2C3_SDA		0x40000078
-		>;
+		fsl,pins =
+			<MX7D_PAD_I2C3_SCL__I2C3_SCL		0x40000078>,
+			<MX7D_PAD_I2C3_SDA__I2C3_SDA		0x40000078>;
+	};
+
+	pinctrl_i2c3_recovery: i2c3recoverygrp {
+		fsl,pins =
+			<MX7D_PAD_I2C3_SCL__GPIO4_IO12		0x40000078>,
+			<MX7D_PAD_I2C3_SDA__GPIO4_IO13		0x40000078>;
 	};
 
 	pinctrl_pca9555: pca95550grp {
-		fsl,pins = <
-			MX7D_PAD_ENET1_TX_CLK__GPIO7_IO12	0x78
-		>;
+		fsl,pins =
+			<MX7D_PAD_ENET1_TX_CLK__GPIO7_IO12	0x78>;
 	};
 
 	pinctrl_sai1: sai1grp {
-		fsl,pins = <
-			MX7D_PAD_SAI1_MCLK__SAI1_MCLK		0x11
-			MX7D_PAD_SAI1_RX_BCLK__SAI1_RX_BCLK	0x1c
-			MX7D_PAD_SAI1_RX_DATA__SAI1_RX_DATA0	0x1c
-			MX7D_PAD_SAI1_RX_SYNC__SAI2_RX_SYNC	0x1c
-
-			MX7D_PAD_SAI1_TX_BCLK__SAI1_TX_BCLK	0x1c
-			MX7D_PAD_SAI1_TX_DATA__SAI1_TX_DATA0	0x14
-			MX7D_PAD_SAI1_TX_SYNC__SAI1_TX_SYNC	0x14
-		>;
+		fsl,pins =
+			<MX7D_PAD_SAI1_MCLK__SAI1_MCLK		0x11>,
+			<MX7D_PAD_SAI1_RX_BCLK__SAI1_RX_BCLK	0x1c>,
+			<MX7D_PAD_SAI1_RX_DATA__SAI1_RX_DATA0	0x1c>,
+			<MX7D_PAD_SAI1_RX_SYNC__SAI2_RX_SYNC	0x1c>,
+
+			<MX7D_PAD_SAI1_TX_BCLK__SAI1_TX_BCLK	0x1c>,
+			<MX7D_PAD_SAI1_TX_DATA__SAI1_TX_DATA0	0x14>,
+			<MX7D_PAD_SAI1_TX_SYNC__SAI1_TX_SYNC	0x14>;
 	};
 
 	pinctrl_uart3: uart3grp {
-		fsl,pins = <
-			MX7D_PAD_UART3_RX_DATA__UART3_DCE_RX	0x7e
-			MX7D_PAD_UART3_TX_DATA__UART3_DCE_TX	0x76
-			MX7D_PAD_UART3_CTS_B__UART3_DCE_CTS	0x76
-			MX7D_PAD_UART3_RTS_B__UART3_DCE_RTS	0x7e
-		>;
+		fsl,pins =
+			<MX7D_PAD_UART3_RX_DATA__UART3_DCE_RX	0x7e>,
+			<MX7D_PAD_UART3_TX_DATA__UART3_DCE_TX	0x76>,
+			<MX7D_PAD_UART3_CTS_B__UART3_DCE_CTS	0x76>,
+			<MX7D_PAD_UART3_RTS_B__UART3_DCE_RTS	0x7e>;
 	};
 
 	pinctrl_uart4: uart4grp {
-		fsl,pins = <
-			MX7D_PAD_SAI2_TX_SYNC__UART4_DCE_RX	0x7e
-			MX7D_PAD_SAI2_TX_BCLK__UART4_DCE_TX	0x76
-			MX7D_PAD_SAI2_RX_DATA__UART4_DCE_CTS	0x76
-			MX7D_PAD_SAI2_TX_DATA__UART4_DCE_RTS	0x7e
-		>;
+		fsl,pins =
+			<MX7D_PAD_SAI2_TX_SYNC__UART4_DCE_RX	0x7e>,
+			<MX7D_PAD_SAI2_TX_BCLK__UART4_DCE_TX	0x76>,
+			<MX7D_PAD_SAI2_RX_DATA__UART4_DCE_CTS	0x76>,
+			<MX7D_PAD_SAI2_TX_DATA__UART4_DCE_RTS	0x7e>;
 	};
 
 	pinctrl_uart5: uart5grp {
-		fsl,pins = <
-			MX7D_PAD_I2C4_SCL__UART5_DCE_RX		0x7e
-			MX7D_PAD_I2C4_SDA__UART5_DCE_TX		0x76
-		>;
+		fsl,pins =
+			<MX7D_PAD_I2C4_SCL__UART5_DCE_RX	0x7e>,
+			<MX7D_PAD_I2C4_SDA__UART5_DCE_TX	0x76>;
 	};
 
 	pinctrl_uart6: uart6grp {
-		fsl,pins = <
-			MX7D_PAD_EPDC_DATA08__UART6_DCE_RX	0x7d
-			MX7D_PAD_EPDC_DATA09__UART6_DCE_TX	0x75
-			MX7D_PAD_EPDC_DATA11__UART6_DCE_CTS	0x75
-			MX7D_PAD_EPDC_DATA10__UART6_DCE_RTS	0x7d
-		>;
+		fsl,pins =
+			<MX7D_PAD_EPDC_DATA08__UART6_DCE_RX	0x7d>,
+			<MX7D_PAD_EPDC_DATA09__UART6_DCE_TX	0x75>,
+			<MX7D_PAD_EPDC_DATA11__UART6_DCE_CTS	0x75>,
+			<MX7D_PAD_EPDC_DATA10__UART6_DCE_RTS	0x7d>;
 	};
 
 	pinctrl_uart7: uart7grp {
-		fsl,pins = <
-			MX7D_PAD_EPDC_DATA12__UART7_DCE_RX	0x7e
-			MX7D_PAD_EPDC_DATA13__UART7_DCE_TX	0x76
-			MX7D_PAD_EPDC_DATA15__UART7_DCE_CTS	0x76
+		fsl,pins =
+			<MX7D_PAD_EPDC_DATA12__UART7_DCE_RX	0x7e>,
+			<MX7D_PAD_EPDC_DATA13__UART7_DCE_TX	0x76>,
+			<MX7D_PAD_EPDC_DATA15__UART7_DCE_CTS	0x76>,
 			/* Limitation: RTS is not connected */
-			MX7D_PAD_EPDC_DATA14__UART7_DCE_RTS	0x7e
-		>;
+			<MX7D_PAD_EPDC_DATA14__UART7_DCE_RTS	0x7e>;
 	};
 
-	pinctrl_usdhc1_gpio: usdhc1grp_gpio {
-		fsl,pins = <
+	pinctrl_usdhc1_gpio: usdhc1_gpiogrp {
+		fsl,pins =
 			/* WP */
-			MX7D_PAD_SD1_WP__GPIO5_IO1		0x7c
+			<MX7D_PAD_SD1_WP__GPIO5_IO1		0x7c>,
 			/* CD */
-			MX7D_PAD_SD1_CD_B__GPIO5_IO0		0x7c
+			<MX7D_PAD_SD1_CD_B__GPIO5_IO0		0x7c>,
 			/* VSELECT */
-			MX7D_PAD_GPIO1_IO08__SD1_VSELECT	0x59
-		>;
+			<MX7D_PAD_GPIO1_IO08__SD1_VSELECT	0x59>;
 	};
 
 	pinctrl_usdhc1: usdhc1grp {
-		fsl,pins = <
-			MX7D_PAD_SD1_CMD__SD1_CMD		0x5e
-			MX7D_PAD_SD1_CLK__SD1_CLK		0x57
-			MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5e
-			MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5e
-			MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5e
-			MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5e
-		>;
-	};
-
-	pinctrl_usdhc1_100mhz: usdhc1grp_100mhz {
-		fsl,pins = <
-			MX7D_PAD_SD1_CMD__SD1_CMD		0x5a
-			MX7D_PAD_SD1_CLK__SD1_CLK		0x57
-			MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5a
-			MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5a
-			MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5a
-			MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5a
-		>;
-	};
-
-	pinctrl_usdhc1_200mhz: usdhc1grp_200mhz {
-		fsl,pins = <
-			MX7D_PAD_SD1_CMD__SD1_CMD		0x5b
-			MX7D_PAD_SD1_CLK__SD1_CLK		0x57
-			MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5b
-			MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5b
-			MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5b
-			MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5b
-		>;
+		fsl,pins =
+			<MX7D_PAD_SD1_CMD__SD1_CMD		0x5e>,
+			<MX7D_PAD_SD1_CLK__SD1_CLK		0x57>,
+			<MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5e>,
+			<MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5e>,
+			<MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5e>,
+			<MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5e>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1_100mhzgrp {
+		fsl,pins =
+			<MX7D_PAD_SD1_CMD__SD1_CMD		0x5a>,
+			<MX7D_PAD_SD1_CLK__SD1_CLK		0x57>,
+			<MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5a>,
+			<MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5a>,
+			<MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5a>,
+			<MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5a>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1_200mhzgrp {
+		fsl,pins =
+			<MX7D_PAD_SD1_CMD__SD1_CMD		0x5b>,
+			<MX7D_PAD_SD1_CLK__SD1_CLK		0x57>,
+			<MX7D_PAD_SD1_DATA0__SD1_DATA0		0x5b>,
+			<MX7D_PAD_SD1_DATA1__SD1_DATA1		0x5b>,
+			<MX7D_PAD_SD1_DATA2__SD1_DATA2		0x5b>,
+			<MX7D_PAD_SD1_DATA3__SD1_DATA3		0x5b>;
 	};
 };
 
 &iomuxc_lpsr {
 	pinctrl_pwm1: pwm1grp {
-		fsl,pins = <
+		fsl,pins =
 			/* LCD_CONTRAST */
-			MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT	0x50
-		>;
+			<MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT	0x50>;
 	};
 
 	pinctrl_usbotg1: usbotg1grp {
-		fsl,pins = <
-			MX7D_PAD_LPSR_GPIO1_IO04__USB_OTG1_OC	0x5c
-			MX7D_PAD_LPSR_GPIO1_IO05__GPIO1_IO5	0x59
-		>;
+		fsl,pins =
+			<MX7D_PAD_LPSR_GPIO1_IO04__USB_OTG1_OC	0x5c>,
+			<MX7D_PAD_LPSR_GPIO1_IO05__GPIO1_IO5	0x59>;
 	};
 
 	pinctrl_wdog1: wdog1grp {
-		fsl,pins = <
-			MX7D_PAD_LPSR_GPIO1_IO00__WDOG1_WDOG_B	0x30
-		>;
+		fsl,pins =
+			<MX7D_PAD_LPSR_GPIO1_IO00__WDOG1_WDOG_B	0x30>;
 	};
 };
 
@@ -560,6 +590,10 @@
 	status = "okay";
 };
 
+&snvs_pwrkey {
+	status = "okay";
+};
+
 &uart3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
@@ -605,6 +639,7 @@
 };
 
 &usbh {
+	disable-over-current;
 	status = "okay";
 };
 
@@ -630,6 +665,8 @@
 	vmmc-supply = <&reg_sd1_vmmc>;
 	bus-width = <4>;
 	no-1-8-v;
+	no-sdio;
+	no-emmc;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
index 3fc3130f9def..028961eb7108 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-tqma7.dtsi
@@ -30,8 +30,11 @@
 };
 
 &i2c1 {
-	pinctrl-names = "default";
+	pinctrl-names = "default", "gpio";
 	pinctrl-0 = <&pinctrl_i2c1>;
+	pinctrl-1 = <&pinctrl_i2c1_recovery>;
+	scl-gpios = <&gpio4 8 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&gpio4 9 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	clock-frequency = <100000>;
 	status = "okay";
 
@@ -109,7 +112,7 @@
 			};
 
 			vgen4_reg: v33 {
-				regulator-min-microvolt = <2850000>;
+				regulator-min-microvolt = <3300000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
@@ -135,7 +138,7 @@
 	};
 
 	/* NXP SE97BTP with temperature sensor + eeprom, TQMa7x 02xx */
-	se97b: temperature-sensor-eeprom@1e {
+	se97b: temperature-sensor@1e {
 		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
 		reg = <0x1e>;
 	};
@@ -143,15 +146,18 @@
 	/* ST M24C64 */
 	m24c64: eeprom@50 {
 		compatible = "atmel,24c64";
+		read-only;
 		reg = <0x50>;
 		pagesize = <32>;
+		vcc-supply = <&vgen4_reg>;
 		status = "okay";
 	};
 
 	at24c02: eeprom@56 {
-		compatible = "atmel,24c02";
+		compatible = "nxp,se97b", "atmel,24c02";
 		reg = <0x56>;
 		pagesize = <16>;
+		vcc-supply = <&vgen4_reg>;
 		status = "okay";
 	};
 
@@ -163,91 +169,89 @@
 
 &iomuxc {
 	pinctrl_i2c1: i2c1grp {
-		fsl,pins = <
-			MX7D_PAD_I2C1_SDA__I2C1_SDA	0x40000078
-			MX7D_PAD_I2C1_SCL__I2C1_SCL	0x40000078
-		>;
+		fsl,pins =
+			<MX7D_PAD_I2C1_SDA__I2C1_SDA	0x40000078>,
+			<MX7D_PAD_I2C1_SCL__I2C1_SCL	0x40000078>;
+	};
+
+	pinctrl_i2c1_recovery: i2c1recoverygrp {
+		fsl,pins =
+			<MX7D_PAD_I2C1_SDA__GPIO4_IO9	0x40000078>,
+			<MX7D_PAD_I2C1_SCL__GPIO4_IO8	0x40000078>;
 	};
 
 	pinctrl_pmic1: pmic1grp {
-		fsl,pins = <
-			MX7D_PAD_SD2_RESET_B__GPIO5_IO11	0x4000005C
-		>;
+		fsl,pins =
+			<MX7D_PAD_SD2_RESET_B__GPIO5_IO11	0x4000005C>;
 	};
 
 	pinctrl_qspi: qspigrp {
-		fsl,pins = <
-			MX7D_PAD_EPDC_DATA00__QSPI_A_DATA0	0x5A
-			MX7D_PAD_EPDC_DATA01__QSPI_A_DATA1	0x5A
-			MX7D_PAD_EPDC_DATA02__QSPI_A_DATA2	0x5A
-			MX7D_PAD_EPDC_DATA03__QSPI_A_DATA3	0x5A
-			MX7D_PAD_EPDC_DATA05__QSPI_A_SCLK	0x11
-			MX7D_PAD_EPDC_DATA06__QSPI_A_SS0_B	0x54
-			MX7D_PAD_EPDC_DATA07__QSPI_A_SS1_B	0x54
-		>;
+		fsl,pins =
+			<MX7D_PAD_EPDC_DATA00__QSPI_A_DATA0	0x5A>,
+			<MX7D_PAD_EPDC_DATA01__QSPI_A_DATA1	0x5A>,
+			<MX7D_PAD_EPDC_DATA02__QSPI_A_DATA2	0x5A>,
+			<MX7D_PAD_EPDC_DATA03__QSPI_A_DATA3	0x5A>,
+			<MX7D_PAD_EPDC_DATA05__QSPI_A_SCLK	0x11>,
+			<MX7D_PAD_EPDC_DATA06__QSPI_A_SS0_B	0x54>,
+			<MX7D_PAD_EPDC_DATA07__QSPI_A_SS1_B	0x54>;
 	};
 
 	pinctrl_qspi_reset: qspi_resetgrp {
-		fsl,pins = <
+		fsl,pins =
 			/* #QSPI_RESET */
-			MX7D_PAD_EPDC_DATA04__GPIO2_IO4		0x52
-		>;
+			<MX7D_PAD_EPDC_DATA04__GPIO2_IO4	0x52>;
 	};
 
 	pinctrl_usdhc3: usdhc3grp {
-		fsl,pins = <
-			MX7D_PAD_SD3_CMD__SD3_CMD		0x59
-			MX7D_PAD_SD3_CLK__SD3_CLK		0x56
-			MX7D_PAD_SD3_DATA0__SD3_DATA0		0x59
-			MX7D_PAD_SD3_DATA1__SD3_DATA1		0x59
-			MX7D_PAD_SD3_DATA2__SD3_DATA2		0x59
-			MX7D_PAD_SD3_DATA3__SD3_DATA3		0x59
-			MX7D_PAD_SD3_DATA4__SD3_DATA4		0x59
-			MX7D_PAD_SD3_DATA5__SD3_DATA5		0x59
-			MX7D_PAD_SD3_DATA6__SD3_DATA6		0x59
-			MX7D_PAD_SD3_DATA7__SD3_DATA7		0x59
-			MX7D_PAD_SD3_STROBE__SD3_STROBE		0x19
-		>;
+		fsl,pins =
+			<MX7D_PAD_SD3_CMD__SD3_CMD		0x59>,
+			<MX7D_PAD_SD3_CLK__SD3_CLK		0x56>,
+			<MX7D_PAD_SD3_DATA0__SD3_DATA0		0x59>,
+			<MX7D_PAD_SD3_DATA1__SD3_DATA1		0x59>,
+			<MX7D_PAD_SD3_DATA2__SD3_DATA2		0x59>,
+			<MX7D_PAD_SD3_DATA3__SD3_DATA3		0x59>,
+			<MX7D_PAD_SD3_DATA4__SD3_DATA4		0x59>,
+			<MX7D_PAD_SD3_DATA5__SD3_DATA5		0x59>,
+			<MX7D_PAD_SD3_DATA6__SD3_DATA6		0x59>,
+			<MX7D_PAD_SD3_DATA7__SD3_DATA7		0x59>,
+			<MX7D_PAD_SD3_STROBE__SD3_STROBE	0x19>;
 	};
 
-	pinctrl_usdhc3_100mhz: usdhc3grp_100mhz {
-		fsl,pins = <
-			MX7D_PAD_SD3_CMD__SD3_CMD               0x5a
-			MX7D_PAD_SD3_CLK__SD3_CLK               0x51
-			MX7D_PAD_SD3_DATA0__SD3_DATA0           0x5a
-			MX7D_PAD_SD3_DATA1__SD3_DATA1           0x5a
-			MX7D_PAD_SD3_DATA2__SD3_DATA2           0x5a
-			MX7D_PAD_SD3_DATA3__SD3_DATA3           0x5a
-			MX7D_PAD_SD3_DATA4__SD3_DATA4           0x5a
-			MX7D_PAD_SD3_DATA5__SD3_DATA5           0x5a
-			MX7D_PAD_SD3_DATA6__SD3_DATA6           0x5a
-			MX7D_PAD_SD3_DATA7__SD3_DATA7           0x5a
-			MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1a
-		>;
+	pinctrl_usdhc3_100mhz: usdhc3_100mhzgrp {
+		fsl,pins =
+			<MX7D_PAD_SD3_CMD__SD3_CMD               0x5a>,
+			<MX7D_PAD_SD3_CLK__SD3_CLK               0x51>,
+			<MX7D_PAD_SD3_DATA0__SD3_DATA0           0x5a>,
+			<MX7D_PAD_SD3_DATA1__SD3_DATA1           0x5a>,
+			<MX7D_PAD_SD3_DATA2__SD3_DATA2           0x5a>,
+			<MX7D_PAD_SD3_DATA3__SD3_DATA3           0x5a>,
+			<MX7D_PAD_SD3_DATA4__SD3_DATA4           0x5a>,
+			<MX7D_PAD_SD3_DATA5__SD3_DATA5           0x5a>,
+			<MX7D_PAD_SD3_DATA6__SD3_DATA6           0x5a>,
+			<MX7D_PAD_SD3_DATA7__SD3_DATA7           0x5a>,
+			<MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1a>;
 	};
 
-	pinctrl_usdhc3_200mhz: usdhc3grp_200mhz {
-		fsl,pins = <
-			MX7D_PAD_SD3_CMD__SD3_CMD               0x5b
-			MX7D_PAD_SD3_CLK__SD3_CLK               0x51
-			MX7D_PAD_SD3_DATA0__SD3_DATA0           0x5b
-			MX7D_PAD_SD3_DATA1__SD3_DATA1           0x5b
-			MX7D_PAD_SD3_DATA2__SD3_DATA2           0x5b
-			MX7D_PAD_SD3_DATA3__SD3_DATA3           0x5b
-			MX7D_PAD_SD3_DATA4__SD3_DATA4           0x5b
-			MX7D_PAD_SD3_DATA5__SD3_DATA5           0x5b
-			MX7D_PAD_SD3_DATA6__SD3_DATA6           0x5b
-			MX7D_PAD_SD3_DATA7__SD3_DATA7           0x5b
-			MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1b
-		>;
+	pinctrl_usdhc3_200mhz: usdhc3_200mhzgrp {
+		fsl,pins =
+			<MX7D_PAD_SD3_CMD__SD3_CMD               0x5b>,
+			<MX7D_PAD_SD3_CLK__SD3_CLK               0x51>,
+			<MX7D_PAD_SD3_DATA0__SD3_DATA0           0x5b>,
+			<MX7D_PAD_SD3_DATA1__SD3_DATA1           0x5b>,
+			<MX7D_PAD_SD3_DATA2__SD3_DATA2           0x5b>,
+			<MX7D_PAD_SD3_DATA3__SD3_DATA3           0x5b>,
+			<MX7D_PAD_SD3_DATA4__SD3_DATA4           0x5b>,
+			<MX7D_PAD_SD3_DATA5__SD3_DATA5           0x5b>,
+			<MX7D_PAD_SD3_DATA6__SD3_DATA6           0x5b>,
+			<MX7D_PAD_SD3_DATA7__SD3_DATA7           0x5b>,
+			<MX7D_PAD_SD3_STROBE__SD3_STROBE         0x1b>;
 	};
 };
 
 &iomuxc_lpsr {
 	pinctrl_wdog1: wdog1grp {
-		fsl,pins = <
-			MX7D_PAD_LPSR_GPIO1_IO00__WDOG1_WDOG_B	0x30
-		>;
+		fsl,pins =
+			<MX7D_PAD_LPSR_GPIO1_IO00__WDOG1_WDOG_B	0x30>;
 	};
 };
 
@@ -265,10 +269,6 @@
 	};
 };
 
-&sdma {
-	status = "okay";
-};
-
 &usdhc3 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
@@ -278,6 +278,8 @@
 	assigned-clock-rates = <400000000>;
 	bus-width = <8>;
 	non-removable;
+	no-sd;
+	no-sdio;
 	vmmc-supply = <&vgen4_reg>;
 	vqmmc-supply = <&sw2_reg>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts b/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts
index 32bf9fa9d00e..0443faa3dfae 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-mba7.dts
@@ -21,8 +21,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
 	phy-mode = "rgmii-id";
-	phy-reset-gpios = <&gpio2 28 GPIO_ACTIVE_LOW>;
-	phy-reset-duration = <1>;
 	phy-supply = <&reg_fec2_pwdn>;
 	phy-handle = <&ethphy2_0>;
 	fsl,magic-packet;
@@ -35,59 +33,85 @@
 		ethphy2_0: ethernet-phy@0 {
 			compatible = "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_enet2_phy>;
 			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_50_NS>;
 			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_50_NS>;
 			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+			reset-gpios = <&gpio2 28 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <1000>;
+			reset-deassert-us = <500>;
 		};
 	};
 };
 
+&gpio2 {
+	pcie-dis-hog {
+		gpio-hog;
+		gpios = <29 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "pcie-dis";
+	};
+
+	pcie-rst-hog {
+		gpio-hog;
+		gpios = <12 GPIO_ACTIVE_HIGH>;
+		output-high;
+		line-name = "pcie-rst";
+	};
+};
+
 &iomuxc {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_hog_mba7_1>;
+	pinctrl-0 = <&pinctrl_hog_mba7_1>, <&pinctrl_hog_pcie>;
 
 	pinctrl_enet2: enet2grp {
-		fsl,pins = <
-			MX7D_PAD_SD2_CD_B__ENET2_MDIO			0x02
-			MX7D_PAD_SD2_WP__ENET2_MDC			0x00
-			MX7D_PAD_EPDC_GDSP__ENET2_RGMII_TXC		0x71
-			MX7D_PAD_EPDC_SDCE2__ENET2_RGMII_TD0		0x71
-			MX7D_PAD_EPDC_SDCE3__ENET2_RGMII_TD1		0x71
-			MX7D_PAD_EPDC_GDCLK__ENET2_RGMII_TD2		0x71
-			MX7D_PAD_EPDC_GDOE__ENET2_RGMII_TD3		0x71
-			MX7D_PAD_EPDC_GDRL__ENET2_RGMII_TX_CTL		0x71
-			MX7D_PAD_EPDC_SDCE1__ENET2_RGMII_RXC		0x79
-			MX7D_PAD_EPDC_SDCLK__ENET2_RGMII_RD0		0x79
-			MX7D_PAD_EPDC_SDLE__ENET2_RGMII_RD1		0x79
-			MX7D_PAD_EPDC_SDOE__ENET2_RGMII_RD2		0x79
-			MX7D_PAD_EPDC_SDSHR__ENET2_RGMII_RD3		0x79
-			MX7D_PAD_EPDC_SDCE0__ENET2_RGMII_RX_CTL		0x79
+		fsl,pins =
+			<MX7D_PAD_SD2_CD_B__ENET2_MDIO			0x02>,
+			<MX7D_PAD_SD2_WP__ENET2_MDC			0x00>,
+			<MX7D_PAD_EPDC_GDSP__ENET2_RGMII_TXC		0x71>,
+			<MX7D_PAD_EPDC_SDCE2__ENET2_RGMII_TD0		0x71>,
+			<MX7D_PAD_EPDC_SDCE3__ENET2_RGMII_TD1		0x71>,
+			<MX7D_PAD_EPDC_GDCLK__ENET2_RGMII_TD2		0x71>,
+			<MX7D_PAD_EPDC_GDOE__ENET2_RGMII_TD3		0x71>,
+			<MX7D_PAD_EPDC_GDRL__ENET2_RGMII_TX_CTL		0x71>,
+			<MX7D_PAD_EPDC_SDCE1__ENET2_RGMII_RXC		0x79>,
+			<MX7D_PAD_EPDC_SDCLK__ENET2_RGMII_RD0		0x79>,
+			<MX7D_PAD_EPDC_SDLE__ENET2_RGMII_RD1		0x79>,
+			<MX7D_PAD_EPDC_SDOE__ENET2_RGMII_RD2		0x79>,
+			<MX7D_PAD_EPDC_SDSHR__ENET2_RGMII_RD3		0x79>,
+			<MX7D_PAD_EPDC_SDCE0__ENET2_RGMII_RX_CTL	0x79>;
+	};
+
+	pinctrl_enet2_phy: enet2phygrp {
+		fsl,pins =
 			/* Reset: SION, 100kPU, SRE_FAST, DSE_X1 */
-			MX7D_PAD_EPDC_BDR0__GPIO2_IO28		0x40000070
+			<MX7D_PAD_EPDC_BDR0__GPIO2_IO28		0x40000070>,
 			/* INT/PWDN: SION, 100kPU, HYS, SRE_FAST, DSE_X1 */
-			MX7D_PAD_EPDC_PWR_STAT__GPIO2_IO31	0x40000078
-		>;
+			<MX7D_PAD_EPDC_PWR_STAT__GPIO2_IO31	0x40000078>;
 	};
 
-	pinctrl_pcie: pciegrp {
-		fsl,pins = <
-			/* #pcie_wake */
-			MX7D_PAD_EPDC_PWR_COM__GPIO2_IO30		0x70
+	pinctrl_hog_pcie: hogpciegrp {
+		fsl,pins =
 			/* #pcie_rst */
-			MX7D_PAD_SD2_CLK__GPIO5_IO12			0x70
+			<MX7D_PAD_SD2_CLK__GPIO5_IO12			0x70>,
 			/* #pcie_dis */
-			MX7D_PAD_EPDC_BDR1__GPIO2_IO29			0x70
-		>;
+			<MX7D_PAD_EPDC_BDR1__GPIO2_IO29			0x70>;
+	};
+
+	pinctrl_pcie: pciegrp {
+		fsl,pins =
+			/* #pcie_wake */
+			<MX7D_PAD_EPDC_PWR_COM__GPIO2_IO30		0x70>;
 	};
 };
 
 &iomuxc_lpsr {
 	pinctrl_usbotg2: usbotg2grp {
-		fsl,pins = <
-			MX7D_PAD_LPSR_GPIO1_IO06__USB_OTG2_OC	0x5c
-			MX7D_PAD_LPSR_GPIO1_IO07__GPIO1_IO7	0x59
-		>;
+		fsl,pins =
+			<MX7D_PAD_LPSR_GPIO1_IO06__USB_OTG2_OC	0x5c>,
+			<MX7D_PAD_LPSR_GPIO1_IO07__GPIO1_IO7	0x59>;
 	};
 };
 
@@ -98,16 +122,14 @@
 	/* probe deferral not supported */
 	/* pcie-bus-supply = <&reg_mpcie_1v5>; */
 	reset-gpio = <&gpio5 12 GPIO_ACTIVE_LOW>;
-	status = "okay";
+	status = "disabled";
 };
 
 &usbotg2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usbotg2>;
 	vbus-supply = <&reg_usb_otg2_vbus>;
-	srp-disable;
-	hnp-disable;
-	adp-disable;
+	disable-over-current;
 	dr_mode = "host";
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
index 12361fcbe24a..1b965652291b 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7d-pico-dwarf.dts
@@ -63,6 +63,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		#interrupt-cells = <2>;
+		interrupt-controller;
 		reg = <0x25>;
 	};
 
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
index ebf7befcc11e..9c81c6baa2d3 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi
@@ -834,16 +834,6 @@
 					<&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>;
 				clock-names = "pix", "axi";
 				status = "disabled";
-
-				port {
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					lcdif_out_mipi_dsi: endpoint@0 {
-						reg = <0>;
-						remote-endpoint = <&mipi_dsi_in_lcdif>;
-					};
-				};
 			};
 
 			mipi_csi: mipi-csi@30750000 {
@@ -895,22 +885,6 @@
 				samsung,esc-clock-frequency = <20000000>;
 				samsung,pll-clock-frequency = <24000000>;
 				status = "disabled";
-
-				ports {
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					port@0 {
-						reg = <0>;
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						mipi_dsi_in_lcdif: endpoint@0 {
-							reg = <0>;
-							remote-endpoint = <&lcdif_out_mipi_dsi>;
-						};
-					};
-				};
 			};
 		};
 
diff --git a/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi b/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
index d471cc5efa94..e86998ca77d6 100644
--- a/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
+++ b/arch/arm/boot/dts/nxp/ls/ls1021a.dtsi
@@ -808,7 +808,9 @@
 			dr_mode = "host";
 			snps,quirk-frame-length-adjustment = <0x20>;
 			snps,dis_rxdet_inp3_quirk;
+			usb3-lpm-capable;
 			snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>;
+			snps,host-vbus-glitches;
 		};
 
 		pcie@3400000 {
diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-evk.dts b/arch/arm/boot/dts/nxp/mxs/imx28-evk.dts
index 9ebb7371e235..330d3aff6b6c 100644
--- a/arch/arm/boot/dts/nxp/mxs/imx28-evk.dts
+++ b/arch/arm/boot/dts/nxp/mxs/imx28-evk.dts
@@ -198,7 +198,7 @@
 		clocks = <&saif0>;
 	};
 
-	at24@51 {
+	eeprom@51 {
 		compatible = "atmel,24c32";
 		pagesize = <32>;
 		reg = <0x51>;
diff --git a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
index b0ed68af0546..029f49be40e3 100644
--- a/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/nxp/vf/vf610-zii-dev-rev-b.dts
@@ -338,6 +338,7 @@
 		reg = <0x22>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
 		interrupt-controller;
 		interrupt-parent = <&gpio3>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm/boot/dts/qcom/Makefile b/arch/arm/boot/dts/qcom/Makefile
index 9cc1e14e6cd0..6478a39b3be5 100644
--- a/arch/arm/boot/dts/qcom/Makefile
+++ b/arch/arm/boot/dts/qcom/Makefile
@@ -36,6 +36,7 @@ dtb-$(CONFIG_ARCH_QCOM) += \
 	qcom-msm8926-microsoft-superman-lte.dtb \
 	qcom-msm8926-microsoft-tesla.dtb \
 	qcom-msm8926-motorola-peregrine.dtb \
+	qcom-msm8926-samsung-matisselte.dtb \
 	qcom-msm8960-cdp.dtb \
 	qcom-msm8960-samsung-expressatt.dtb \
 	qcom-msm8974-lge-nexus5-hammerhead.dtb \
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
index 0a1fd5eb3c6d..a70de21bf139 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-lg-lenok.dts
@@ -7,6 +7,7 @@
 
 #include "qcom-msm8226.dtsi"
 #include "pm8226.dtsi"
+#include <dt-bindings/clock/qcom,mmcc-msm8974.h>
 
 /delete-node/ &adsp_region;
 
@@ -56,6 +57,29 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&wlan_regulator_default_state>;
 	};
+
+	pwm_vibrator: pwm {
+		compatible = "clk-pwm";
+		clocks = <&mmcc CAMSS_GP0_CLK>;
+
+		pinctrl-0 = <&vibrator_clk_default_state>;
+		pinctrl-names = "default";
+
+		#pwm-cells = <2>;
+	};
+
+	vibrator {
+		compatible = "pwm-vibrator";
+
+		pwms = <&pwm_vibrator 0 10000>;
+		pwm-names = "enable";
+
+		vcc-supply = <&pm8226_l28>;
+		enable-gpios = <&tlmm 62 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&vibrator_en_default_state>;
+		pinctrl-names = "default";
+	};
 };
 
 &adsp {
@@ -330,6 +354,20 @@
 		};
 	};
 
+	vibrator_clk_default_state: vibrator-clk-default-state {
+		pins = "gpio33";
+		function = "gp0_clk";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	vibrator_en_default_state: vibrator-en-default-state {
+		pins = "gpio62";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
 	wlan_hostwake_default_state: wlan-hostwake-default-state {
 		pins = "gpio37";
 		function = "gpio";
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
index cffc069712b2..da3be658e822 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
+++ b/arch/arm/boot/dts/qcom/qcom-apq8026-samsung-matisse-wifi.dts
@@ -5,142 +5,13 @@
 
 /dts-v1/;
 
-#include <dt-bindings/input/input.h>
-#include "qcom-msm8226.dtsi"
-#include "pm8226.dtsi"
-
-/delete-node/ &adsp_region;
-/delete-node/ &smem_region;
+#include "qcom-msm8226-samsung-matisse-common.dtsi"
 
 / {
 	model = "Samsung Galaxy Tab 4 10.1";
 	compatible = "samsung,matisse-wifi", "qcom,apq8026";
 	chassis-type = "tablet";
 
-	aliases {
-		mmc0 = &sdhc_1; /* SDC1 eMMC slot */
-		mmc1 = &sdhc_2; /* SDC2 SD card slot */
-		display0 = &framebuffer0;
-	};
-
-	chosen {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		stdout-path = "display0";
-
-		framebuffer0: framebuffer@3200000 {
-			compatible = "simple-framebuffer";
-			reg = <0x03200000 0x800000>;
-			width = <1280>;
-			height = <800>;
-			stride = <(1280 * 3)>;
-			format = "r8g8b8";
-		};
-	};
-
-	gpio-hall-sensor {
-		compatible = "gpio-keys";
-
-		event-hall-sensor {
-			label = "Hall Effect Sensor";
-			gpios = <&tlmm 110 GPIO_ACTIVE_LOW>;
-			linux,input-type = <EV_SW>;
-			linux,code = <SW_LID>;
-			debounce-interval = <15>;
-			linux,can-disable;
-			wakeup-source;
-		};
-	};
-
-	gpio-keys {
-		compatible = "gpio-keys";
-		autorepeat;
-
-		key-home {
-			label = "Home";
-			gpios = <&tlmm 108 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_HOMEPAGE>;
-			debounce-interval = <15>;
-		};
-
-		key-volume-down {
-			label = "Volume Down";
-			gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_VOLUMEDOWN>;
-			debounce-interval = <15>;
-		};
-
-		key-volume-up {
-			label = "Volume Up";
-			gpios = <&tlmm 106 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_VOLUMEUP>;
-			debounce-interval = <15>;
-		};
-	};
-
-	i2c-backlight {
-		compatible = "i2c-gpio";
-		sda-gpios = <&tlmm 20 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
-		scl-gpios = <&tlmm 21 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
-
-		pinctrl-0 = <&backlight_i2c_default_state>;
-		pinctrl-names = "default";
-
-		i2c-gpio,delay-us = <4>;
-
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		backlight@2c {
-			compatible = "ti,lp8556";
-			reg = <0x2c>;
-
-			dev-ctrl = /bits/ 8 <0x80>;
-			init-brt = /bits/ 8 <0x3f>;
-
-			pwms = <&backlight_pwm 0 100000>;
-			pwm-names = "lp8556";
-
-			rom-a0h {
-				rom-addr = /bits/ 8 <0xa0>;
-				rom-val = /bits/ 8 <0x44>;
-			};
-
-			rom-a1h {
-				rom-addr = /bits/ 8 <0xa1>;
-				rom-val = /bits/ 8 <0x6c>;
-			};
-
-			rom-a5h {
-				rom-addr = /bits/ 8 <0xa5>;
-				rom-val = /bits/ 8 <0x24>;
-			};
-		};
-	};
-
-	backlight_pwm: pwm {
-		compatible = "clk-pwm";
-		#pwm-cells = <2>;
-		clocks = <&mmcc CAMSS_GP0_CLK>;
-		pinctrl-0 = <&backlight_pwm_default_state>;
-		pinctrl-names = "default";
-	};
-
-	reg_tsp_1p8v: regulator-tsp-1p8v {
-		compatible = "regulator-fixed";
-		regulator-name = "tsp_1p8v";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-
-		gpio = <&tlmm 31 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&tsp_en_default_state>;
-	};
-
 	reg_tsp_3p3v: regulator-tsp-3p3v {
 		compatible = "regulator-fixed";
 		regulator-name = "tsp_3p3v";
@@ -153,74 +24,6 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&tsp_en1_default_state>;
 	};
-
-	reserved-memory {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		framebuffer@3200000 {
-			reg = <0x03200000 0x800000>;
-			no-map;
-		};
-
-		mpss@8400000 {
-			reg = <0x08400000 0x1f00000>;
-			no-map;
-		};
-
-		mba@a300000 {
-			reg = <0x0a300000 0x100000>;
-			no-map;
-		};
-
-		reserved@cb00000 {
-			reg = <0x0cb00000 0x700000>;
-			no-map;
-		};
-
-		wcnss@d200000 {
-			reg = <0x0d200000 0x700000>;
-			no-map;
-		};
-
-		adsp_region: adsp@d900000 {
-			reg = <0x0d900000 0x1800000>;
-			no-map;
-		};
-
-		venus@f100000 {
-			reg = <0x0f100000 0x500000>;
-			no-map;
-		};
-
-		smem_region: smem@fa00000 {
-			reg = <0x0fa00000 0x100000>;
-			no-map;
-		};
-
-		reserved@fb00000 {
-			reg = <0x0fb00000 0x260000>;
-			no-map;
-		};
-
-		rfsa@fd60000 {
-			reg = <0x0fd60000 0x20000>;
-			no-map;
-		};
-
-		rmtfs@fd80000 {
-			compatible = "qcom,rmtfs-mem";
-			reg = <0x0fd80000 0x180000>;
-			no-map;
-
-			qcom,client-id = <1>;
-		};
-	};
-};
-
-&adsp {
-	status = "okay";
 };
 
 &blsp1_i2c2 {
@@ -243,21 +46,6 @@
 	};
 };
 
-&blsp1_i2c4 {
-	status = "okay";
-
-	muic: usb-switch@25 {
-		compatible = "siliconmitus,sm5502-muic";
-		reg = <0x25>;
-
-		interrupt-parent = <&tlmm>;
-		interrupts = <67 IRQ_TYPE_EDGE_FALLING>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&muic_int_default_state>;
-	};
-};
-
 &blsp1_i2c5 {
 	status = "okay";
 
@@ -268,6 +56,13 @@
 		interrupt-parent = <&tlmm>;
 		interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
 
+		linux,keycodes = <KEY_RESERVED>,
+				 <KEY_RESERVED>,
+				 <KEY_RESERVED>,
+				 <KEY_RESERVED>,
+				 <KEY_APPSELECT>,
+				 <KEY_BACK>;
+
 		pinctrl-names = "default";
 		pinctrl-0 = <&tsp_int_rst_default_state>;
 
@@ -278,242 +73,19 @@
 	};
 };
 
-&rpm_requests {
-	regulators {
-		compatible = "qcom,rpm-pm8226-regulators";
-
-		pm8226_s3: s3 {
-			regulator-min-microvolt = <1200000>;
-			regulator-max-microvolt = <1300000>;
-		};
-
-		pm8226_s4: s4 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-		};
-
-		pm8226_s5: s5 {
-			regulator-min-microvolt = <1150000>;
-			regulator-max-microvolt = <1150000>;
-		};
-
-		pm8226_l1: l1 {
-			regulator-min-microvolt = <1225000>;
-			regulator-max-microvolt = <1225000>;
-		};
-
-		pm8226_l2: l2 {
-			regulator-min-microvolt = <1200000>;
-			regulator-max-microvolt = <1200000>;
-		};
-
-		pm8226_l3: l3 {
-			regulator-min-microvolt = <750000>;
-			regulator-max-microvolt = <1337500>;
-			regulator-always-on;
-		};
-
-		pm8226_l4: l4 {
-			regulator-min-microvolt = <1200000>;
-			regulator-max-microvolt = <1200000>;
-		};
-
-		pm8226_l5: l5 {
-			regulator-min-microvolt = <1200000>;
-			regulator-max-microvolt = <1200000>;
-		};
-
-		pm8226_l6: l6 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-			regulator-always-on;
-		};
-
-		pm8226_l7: l7 {
-			regulator-min-microvolt = <1850000>;
-			regulator-max-microvolt = <1850000>;
-		};
-
-		pm8226_l8: l8 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-			regulator-always-on;
-		};
-
-		pm8226_l9: l9 {
-			regulator-min-microvolt = <2050000>;
-			regulator-max-microvolt = <2050000>;
-		};
-
-		pm8226_l10: l10 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-		};
-
-		pm8226_l12: l12 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-		};
-
-		pm8226_l14: l14 {
-			regulator-min-microvolt = <2750000>;
-			regulator-max-microvolt = <2750000>;
-		};
-
-		pm8226_l15: l15 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <3300000>;
-		};
-
-		pm8226_l16: l16 {
-			regulator-min-microvolt = <3000000>;
-			regulator-max-microvolt = <3350000>;
-		};
-
-		pm8226_l17: l17 {
-			regulator-min-microvolt = <2950000>;
-			regulator-max-microvolt = <2950000>;
-
-			regulator-system-load = <200000>;
-			regulator-allow-set-load;
-			regulator-always-on;
-		};
-
-		pm8226_l18: l18 {
-			regulator-min-microvolt = <2950000>;
-			regulator-max-microvolt = <2950000>;
-		};
-
-		pm8226_l19: l19 {
-			regulator-min-microvolt = <2850000>;
-			regulator-max-microvolt = <3000000>;
-		};
-
-		pm8226_l20: l20 {
-			regulator-min-microvolt = <3075000>;
-			regulator-max-microvolt = <3075000>;
-		};
-
-		pm8226_l21: l21 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <2950000>;
-		};
-
-		pm8226_l22: l22 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <3000000>;
-		};
-
-		pm8226_l23: l23 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <3300000>;
-		};
-
-		pm8226_l24: l24 {
-			regulator-min-microvolt = <1300000>;
-			regulator-max-microvolt = <1350000>;
-		};
-
-		pm8226_l25: l25 {
-			regulator-min-microvolt = <1775000>;
-			regulator-max-microvolt = <2125000>;
-		};
-
-		pm8226_l26: l26 {
-			regulator-min-microvolt = <1225000>;
-			regulator-max-microvolt = <1300000>;
-		};
-
-		pm8226_l27: l27 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <1800000>;
-		};
-
-		pm8226_l28: l28 {
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <2950000>;
-		};
-
-		pm8226_lvs1: lvs1 {};
-	};
-};
-
-&sdhc_1 {
-	vmmc-supply = <&pm8226_l17>;
-	vqmmc-supply = <&pm8226_l6>;
-
-	bus-width = <8>;
-	non-removable;
-
-	status = "okay";
+&pm8226_l3 {
+	regulator-max-microvolt = <1337500>;
 };
 
-&sdhc_2 {
-	vmmc-supply = <&pm8226_l18>;
-	vqmmc-supply = <&pm8226_l21>;
-
-	bus-width = <4>;
-	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
-
-	status = "okay";
+&pm8226_s4 {
+	regulator-max-microvolt = <1800000>;
 };
 
 &tlmm {
-	accel_int_default_state: accel-int-default-state {
-		pins = "gpio54";
-		function = "gpio";
-		drive-strength = <2>;
-		bias-disable;
-	};
-
-	backlight_i2c_default_state: backlight-i2c-default-state {
-		pins = "gpio20", "gpio21";
-		function = "gpio";
-		drive-strength = <2>;
-		bias-disable;
-	};
-
-	backlight_pwm_default_state: backlight-pwm-default-state {
-		pins = "gpio33";
-		function = "gp0_clk";
-	};
-
-	muic_int_default_state: muic-int-default-state {
-		pins = "gpio67";
-		function = "gpio";
-		drive-strength = <2>;
-		bias-disable;
-	};
-
-	tsp_en_default_state: tsp-en-default-state {
-		pins = "gpio31";
-		function = "gpio";
-		drive-strength = <2>;
-		bias-disable;
-	};
-
 	tsp_en1_default_state: tsp-en1-default-state {
 		pins = "gpio73";
 		function = "gpio";
 		drive-strength = <2>;
 		bias-disable;
 	};
-
-	tsp_int_rst_default_state: tsp-int-rst-default-state {
-		pins = "gpio17";
-		function = "gpio";
-		drive-strength = <10>;
-		bias-pull-up;
-	};
-};
-
-&usb {
-	extcon = <&muic>, <&muic>;
-	status = "okay";
-};
-
-&usb_hs_phy {
-	extcon = <&muic>;
-	v1p8-supply = <&pm8226_l10>;
-	v3p3-supply = <&pm8226_l20>;
 };
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
index 3faf57035d54..9a5ba978775a 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-apq8064.dtsi
@@ -190,7 +190,7 @@
 
 	cpu-pmu {
 		compatible = "qcom,krait-pmu";
-		interrupts = <1 10 0x304>;
+		interrupts = <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
 	};
 
 	clocks {
@@ -244,7 +244,7 @@
 
 		modem_smsm: modem@1 {
 			reg = <1>;
-			interrupts = <0 38 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_EDGE_RISING>;
 
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -252,7 +252,7 @@
 
 		q6_smsm: q6@2 {
 			reg = <2>;
-			interrupts = <0 89 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 89 IRQ_TYPE_EDGE_RISING>;
 
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -260,7 +260,7 @@
 
 		wcnss_smsm: wcnss@3 {
 			reg = <3>;
-			interrupts = <0 204 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 204 IRQ_TYPE_EDGE_RISING>;
 
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -268,7 +268,7 @@
 
 		dsps_smsm: dsps@4 {
 			reg = <4>;
-			interrupts = <0 137 IRQ_TYPE_EDGE_RISING>;
+			interrupts = <GIC_SPI 137 IRQ_TYPE_EDGE_RISING>;
 
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -299,7 +299,7 @@
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
-			interrupts = <0 16 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&ps_hold>;
@@ -321,9 +321,9 @@
 		timer@200a000 {
 			compatible = "qcom,kpss-wdt-apq8064", "qcom,kpss-timer",
 				     "qcom,msm-timer";
-			interrupts = <1 1 0x301>,
-				     <1 2 0x301>,
-				     <1 3 0x301>;
+			interrupts = <GIC_PPI 1 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>,
+				     <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>,
+				     <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>;
 			reg = <0x0200a000 0x100>;
 			clock-frequency = <27000000>;
 			cpu-offset = <0x80000>;
@@ -365,28 +365,44 @@
 			#clock-cells = <0>;
 		};
 
-		saw0: power-controller@2089000 {
+		saw0: power-manager@2089000 {
 			compatible = "qcom,apq8064-saw2-v1.1-cpu", "qcom,saw2";
 			reg = <0x02089000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw0_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
-		saw1: power-controller@2099000 {
+		saw1: power-manager@2099000 {
 			compatible = "qcom,apq8064-saw2-v1.1-cpu", "qcom,saw2";
 			reg = <0x02099000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw1_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
-		saw2: power-controller@20a9000 {
+		saw2: power-manager@20a9000 {
 			compatible = "qcom,apq8064-saw2-v1.1-cpu", "qcom,saw2";
 			reg = <0x020a9000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw2_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
-		saw3: power-controller@20b9000 {
+		saw3: power-manager@20b9000 {
 			compatible = "qcom,apq8064-saw2-v1.1-cpu", "qcom,saw2";
 			reg = <0x020b9000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw3_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
 		sps_sic_non_secure: sps-sic-non-secure@12100000 {
@@ -411,7 +427,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x12450000 0x100>,
 				      <0x12400000 0x03>;
-				interrupts = <0 193 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI1_UART_CLK>, <&gcc GSBI1_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -423,7 +439,7 @@
 				pinctrl-1 = <&i2c1_pins_sleep>;
 				pinctrl-names = "default", "sleep";
 				reg = <0x12460000 0x1000>;
-				interrupts = <0 194 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 194 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI1_QUP_CLK>, <&gcc GSBI1_H_CLK>;
 				clock-names = "core", "iface";
 				#address-cells = <1>;
@@ -452,7 +468,7 @@
 				pinctrl-0 = <&i2c2_pins>;
 				pinctrl-1 = <&i2c2_pins_sleep>;
 				pinctrl-names = "default", "sleep";
-				interrupts = <0 196 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI2_QUP_CLK>, <&gcc GSBI2_H_CLK>;
 				clock-names = "core", "iface";
 				#address-cells = <1>;
@@ -539,7 +555,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x1a240000 0x100>,
 				      <0x1a200000 0x03>;
-				interrupts = <0 154 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI5_UART_CLK>, <&gcc GSBI5_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -548,7 +564,7 @@
 			gsbi5_spi: spi@1a280000 {
 				compatible = "qcom,spi-qup-v1.1.1";
 				reg = <0x1a280000 0x1000>;
-				interrupts = <0 155 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
 				pinctrl-0 = <&spi5_default>;
 				pinctrl-1 = <&spi5_sleep>;
 				pinctrl-names = "default", "sleep";
@@ -575,7 +591,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x16540000 0x100>,
 				      <0x16500000 0x03>;
-				interrupts = <0 156 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI6_UART_CLK>, <&gcc GSBI6_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -611,7 +627,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x16640000 0x1000>,
 				      <0x16600000 0x1000>;
-				interrupts = <0 158 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 158 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI7_UART_CLK>, <&gcc GSBI7_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -908,7 +924,7 @@
 		sdcc3bam: dma-controller@12182000 {
 			compatible = "qcom,bam-v1.3.0";
 			reg = <0x12182000 0x8000>;
-			interrupts = <0 96 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc SDC3_H_CLK>;
 			clock-names = "bam_clk";
 			#dma-cells = <1>;
@@ -936,7 +952,7 @@
 		sdcc4bam: dma-controller@121c2000 {
 			compatible = "qcom,bam-v1.3.0";
 			reg = <0x121c2000 0x8000>;
-			interrupts = <0 95 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc SDC4_H_CLK>;
 			clock-names = "bam_clk";
 			#dma-cells = <1>;
@@ -965,7 +981,7 @@
 		sdcc1bam: dma-controller@12402000 {
 			compatible = "qcom,bam-v1.3.0";
 			reg = <0x12402000 0x8000>;
-			interrupts = <0 98 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc SDC1_H_CLK>;
 			clock-names = "bam_clk";
 			#dma-cells = <1>;
diff --git a/arch/arm/boot/dts/qcom/qcom-apq8084.dtsi b/arch/arm/boot/dts/qcom/qcom-apq8084.dtsi
index 2b1f9d0fb510..8204e64d9a97 100644
--- a/arch/arm/boot/dts/qcom/qcom-apq8084.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-apq8084.dtsi
@@ -629,30 +629,29 @@
 			};
 		};
 
-		saw0: power-controller@f9089000 {
+		saw0: power-manager@f9089000 {
 			compatible = "qcom,apq8084-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf9089000 0x1000>, <0xf9009000 0x1000>;
 		};
 
-		saw1: power-controller@f9099000 {
+		saw1: power-manager@f9099000 {
 			compatible = "qcom,apq8084-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf9099000 0x1000>, <0xf9009000 0x1000>;
 		};
 
-		saw2: power-controller@f90a9000 {
+		saw2: power-manager@f90a9000 {
 			compatible = "qcom,apq8084-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf90a9000 0x1000>, <0xf9009000 0x1000>;
 		};
 
-		saw3: power-controller@f90b9000 {
+		saw3: power-manager@f90b9000 {
 			compatible = "qcom,apq8084-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf90b9000 0x1000>, <0xf9009000 0x1000>;
 		};
 
-		saw_l2: power-controller@f9012000 {
-			compatible = "qcom,saw2";
+		saw_l2: power-manager@f9012000 {
+			compatible = "qcom,apq8084-saw2-v2.1-l2", "qcom,saw2";
 			reg = <0xf9012000 0x1000>;
-			regulator;
 		};
 
 		acc0: power-manager@f9088000 {
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk01.1.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk01.1.dtsi
index 0505270cf508..f7ac8f9d0b6f 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk01.1.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq4019-ap.dk01.1.dtsi
@@ -27,87 +27,83 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
+};
 
-	soc {
-		rng@22000 {
-			status = "okay";
-		};
-
-		pinctrl@1000000 {
-			serial_pins: serial_pinmux {
-				mux {
-					pins = "gpio60", "gpio61";
-					function = "blsp_uart0";
-					bias-disable;
-				};
-			};
-
-			spi_0_pins: spi_0_pinmux {
-				pinmux {
-					function = "blsp_spi0";
-					pins = "gpio55", "gpio56", "gpio57";
-				};
-				pinmux_cs {
-					function = "gpio";
-					pins = "gpio54";
-				};
-				pinconf {
-					pins = "gpio55", "gpio56", "gpio57";
-					drive-strength = <12>;
-					bias-disable;
-				};
-				pinconf_cs {
-					pins = "gpio54";
-					drive-strength = <2>;
-					bias-disable;
-					output-high;
-				};
-			};
-		};
+&prng {
+	status = "okay";
+};
 
-		blsp_dma: dma-controller@7884000 {
-			status = "okay";
+&tlmm {
+	serial_pins: serial_pinmux {
+		mux {
+			pins = "gpio60", "gpio61";
+			function = "blsp_uart0";
+			bias-disable;
 		};
+	};
 
-		spi@78b5000 {
-			pinctrl-0 = <&spi_0_pins>;
-			pinctrl-names = "default";
-			status = "okay";
-			cs-gpios = <&tlmm 54 GPIO_ACTIVE_HIGH>;
-
-			mx25l25635e@0 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				reg = <0>;
-				compatible = "mx25l25635e";
-				spi-max-frequency = <24000000>;
-			};
+	spi_0_pins: spi_0_pinmux {
+		pinmux {
+			function = "blsp_spi0";
+			pins = "gpio55", "gpio56", "gpio57";
 		};
-
-		serial@78af000 {
-			pinctrl-0 = <&serial_pins>;
-			pinctrl-names = "default";
-			status = "okay";
+		pinmux_cs {
+			function = "gpio";
+			pins = "gpio54";
 		};
-
-		cryptobam: dma-controller@8e04000 {
-			status = "okay";
+		pinconf {
+			pins = "gpio55", "gpio56", "gpio57";
+			drive-strength = <12>;
+			bias-disable;
 		};
-
-		crypto@8e3a000 {
-			status = "okay";
+		pinconf_cs {
+			pins = "gpio54";
+			drive-strength = <2>;
+			bias-disable;
+			output-high;
 		};
+	};
+};
 
-		watchdog@b017000 {
-			status = "okay";
-		};
+&blsp_dma {
+	status = "okay";
+};
 
-		wifi@a000000 {
-			status = "okay";
-		};
+&blsp1_spi1 {
+	pinctrl-0 = <&spi_0_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+	cs-gpios = <&tlmm 54 GPIO_ACTIVE_HIGH>;
 
-		wifi@a800000 {
-			status = "okay";
-		};
+	flash@0 {
+		reg = <0>;
+		compatible = "jedec,spi-nor";
+		spi-max-frequency = <24000000>;
 	};
 };
+
+&blsp1_uart1 {
+	pinctrl-0 = <&serial_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&cryptobam {
+	status = "okay";
+};
+
+&crypto {
+	status = "okay";
+};
+
+&watchdog {
+	status = "okay";
+};
+
+&wifi0 {
+	status = "okay";
+};
+
+&wifi1 {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
index f989bd741cd1..681cb3fc8085 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq4019.dtsi
@@ -162,10 +162,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <1 2 0xf08>,
-			     <1 3 0xf08>,
-			     <1 4 0xf08>,
-			     <1 1 0xf08>;
+		interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 4 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 1 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 		clock-frequency = <48000000>;
 		always-on;
 	};
@@ -350,34 +350,29 @@
 			reg = <0x0b0b8000 0x1000>, <0xb008000 0x1000>;
 		};
 
-		saw0: regulator@b089000 {
-			compatible = "qcom,saw2";
+		saw0: power-manager@b089000 {
+			compatible = "qcom,ipq4019-saw2-cpu", "qcom,saw2";
 			reg = <0x0b089000 0x1000>, <0x0b009000 0x1000>;
-			regulator;
 		};
 
-		saw1: regulator@b099000 {
-			compatible = "qcom,saw2";
+		saw1: power-manager@b099000 {
+			compatible = "qcom,ipq4019-saw2-cpu", "qcom,saw2";
 			reg = <0x0b099000 0x1000>, <0x0b009000 0x1000>;
-			regulator;
 		};
 
-		saw2: regulator@b0a9000 {
-			compatible = "qcom,saw2";
+		saw2: power-manager@b0a9000 {
+			compatible = "qcom,ipq4019-saw2-cpu", "qcom,saw2";
 			reg = <0x0b0a9000 0x1000>, <0x0b009000 0x1000>;
-			regulator;
 		};
 
-		saw3: regulator@b0b9000 {
-			compatible = "qcom,saw2";
+		saw3: power-manager@b0b9000 {
+			compatible = "qcom,ipq4019-saw2-cpu", "qcom,saw2";
 			reg = <0x0b0b9000 0x1000>, <0x0b009000 0x1000>;
-			regulator;
 		};
 
-		saw_l2: regulator@b012000 {
-			compatible = "qcom,saw2";
+		saw_l2: power-manager@b012000 {
+			compatible = "qcom,ipq4019-saw2-l2", "qcom,saw2";
 			reg = <0xb012000 0x1000>;
-			regulator;
 		};
 
 		blsp1_uart1: serial@78af000 {
@@ -684,7 +679,7 @@
 			clocks = <&gcc GCC_USB2_MASTER_CLK>,
 				 <&gcc GCC_USB2_SLEEP_CLK>,
 				 <&gcc GCC_USB2_MOCK_UTMI_CLK>;
-			clock-names = "master", "sleep", "mock_utmi";
+			clock-names = "core", "sleep", "mock_utmi";
 			ranges;
 			status = "disabled";
 
diff --git a/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
index 6a7f4dd0f775..2eb6758b6a3a 100644
--- a/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-ipq8064.dtsi
@@ -586,10 +586,9 @@
 			#clock-cells = <0>;
 		};
 
-		saw0: regulator@2089000 {
-			compatible = "qcom,saw2";
+		saw0: power-manager@2089000 {
+			compatible = "qcom,ipq8064-saw2-cpu", "qcom,saw2";
 			reg = <0x02089000 0x1000>, <0x02009000 0x1000>;
-			regulator;
 		};
 
 		acc1: clock-controller@2098000 {
@@ -601,10 +600,9 @@
 			#clock-cells = <0>;
 		};
 
-		saw1: regulator@2099000 {
-			compatible = "qcom,saw2";
+		saw1: power-manager@2099000 {
+			compatible = "qcom,ipq8064-saw2-cpu", "qcom,saw2";
 			reg = <0x02099000 0x1000>, <0x02009000 0x1000>;
-			regulator;
 		};
 
 		nss_common: syscon@3000000 {
@@ -623,7 +621,6 @@
 			ranges;
 
 			resets = <&gcc USB30_0_MASTER_RESET>;
-			reset-names = "master";
 
 			status = "disabled";
 
@@ -669,7 +666,6 @@
 			ranges;
 
 			resets = <&gcc USB30_1_MASTER_RESET>;
-			reset-names = "master";
 
 			status = "disabled";
 
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-samsung-matisse-common.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226-samsung-matisse-common.dtsi
new file mode 100644
index 000000000000..a15a44fc0181
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226-samsung-matisse-common.dtsi
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2022, Matti Lehtimäki <matti.lehtimaki@gmail.com>
+ */
+
+#include <dt-bindings/input/input.h>
+#include "qcom-msm8226.dtsi"
+#include "pm8226.dtsi"
+
+/delete-node/ &adsp_region;
+/delete-node/ &smem_region;
+
+/ {
+	aliases {
+		mmc0 = &sdhc_1; /* SDC1 eMMC slot */
+		mmc1 = &sdhc_2; /* SDC2 SD card slot */
+		display0 = &framebuffer0;
+	};
+
+	chosen {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		stdout-path = "display0";
+
+		framebuffer0: framebuffer@3200000 {
+			compatible = "simple-framebuffer";
+			reg = <0x03200000 0x800000>;
+			width = <1280>;
+			height = <800>;
+			stride = <(1280 * 3)>;
+			format = "r8g8b8";
+		};
+	};
+
+	gpio-hall-sensor {
+		compatible = "gpio-keys";
+
+		event-hall-sensor {
+			label = "Hall Effect Sensor";
+			gpios = <&tlmm 110 GPIO_ACTIVE_LOW>;
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_LID>;
+			debounce-interval = <15>;
+			linux,can-disable;
+			wakeup-source;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		autorepeat;
+
+		key-home {
+			label = "Home";
+			gpios = <&tlmm 108 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_HOMEPAGE>;
+			debounce-interval = <15>;
+		};
+
+		key-volume-down {
+			label = "Volume Down";
+			gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEDOWN>;
+			debounce-interval = <15>;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 106 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+			debounce-interval = <15>;
+		};
+	};
+
+	i2c-backlight {
+		compatible = "i2c-gpio";
+		sda-gpios = <&tlmm 20 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+		scl-gpios = <&tlmm 21 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+
+		pinctrl-0 = <&backlight_i2c_default_state>;
+		pinctrl-names = "default";
+
+		i2c-gpio,delay-us = <4>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		backlight@2c {
+			compatible = "ti,lp8556";
+			reg = <0x2c>;
+
+			dev-ctrl = /bits/ 8 <0x80>;
+			init-brt = /bits/ 8 <0x3f>;
+
+			pwms = <&backlight_pwm 0 100000>;
+			pwm-names = "lp8556";
+
+			rom-a0h {
+				rom-addr = /bits/ 8 <0xa0>;
+				rom-val = /bits/ 8 <0x44>;
+			};
+
+			rom-a1h {
+				rom-addr = /bits/ 8 <0xa1>;
+				rom-val = /bits/ 8 <0x6c>;
+			};
+
+			rom-a5h {
+				rom-addr = /bits/ 8 <0xa5>;
+				rom-val = /bits/ 8 <0x24>;
+			};
+		};
+	};
+
+	backlight_pwm: pwm {
+		compatible = "clk-pwm";
+		#pwm-cells = <2>;
+		clocks = <&mmcc CAMSS_GP0_CLK>;
+		pinctrl-0 = <&backlight_pwm_default_state>;
+		pinctrl-names = "default";
+	};
+
+	reg_tsp_1p8v: regulator-tsp-1p8v {
+		compatible = "regulator-fixed";
+		regulator-name = "tsp_1p8v";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+
+		gpio = <&tlmm 31 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&tsp_en_default_state>;
+	};
+
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		framebuffer@3200000 {
+			reg = <0x03200000 0x800000>;
+			no-map;
+		};
+
+		mpss@8400000 {
+			reg = <0x08400000 0x1f00000>;
+			no-map;
+		};
+
+		mba@a300000 {
+			reg = <0x0a300000 0x100000>;
+			no-map;
+		};
+
+		reserved@cb00000 {
+			reg = <0x0cb00000 0x700000>;
+			no-map;
+		};
+
+		wcnss@d200000 {
+			reg = <0x0d200000 0x700000>;
+			no-map;
+		};
+
+		adsp_region: adsp@d900000 {
+			reg = <0x0d900000 0x1800000>;
+			no-map;
+		};
+
+		venus@f100000 {
+			reg = <0x0f100000 0x500000>;
+			no-map;
+		};
+
+		smem_region: smem@fa00000 {
+			reg = <0x0fa00000 0x100000>;
+			no-map;
+		};
+
+		reserved@fb00000 {
+			reg = <0x0fb00000 0x260000>;
+			no-map;
+		};
+
+		rfsa@fd60000 {
+			reg = <0x0fd60000 0x20000>;
+			no-map;
+		};
+
+		rmtfs@fd80000 {
+			compatible = "qcom,rmtfs-mem";
+			reg = <0x0fd80000 0x180000>;
+			no-map;
+
+			qcom,client-id = <1>;
+		};
+	};
+};
+
+&adsp {
+	status = "okay";
+};
+
+&blsp1_i2c4 {
+	status = "okay";
+
+	muic: usb-switch@25 {
+		compatible = "siliconmitus,sm5502-muic";
+		reg = <0x25>;
+
+		interrupt-parent = <&tlmm>;
+		interrupts = <67 IRQ_TYPE_EDGE_FALLING>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&muic_int_default_state>;
+	};
+};
+
+&blsp1_uart3 {
+	status = "okay";
+};
+
+&rpm_requests {
+	regulators {
+		compatible = "qcom,rpm-pm8226-regulators";
+
+		pm8226_s3: s3 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		pm8226_s4: s4 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2200000>;
+		};
+
+		pm8226_s5: s5 {
+			regulator-min-microvolt = <1150000>;
+			regulator-max-microvolt = <1150000>;
+		};
+
+		pm8226_l1: l1 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1225000>;
+		};
+
+		pm8226_l2: l2 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l3: l3 {
+			regulator-min-microvolt = <750000>;
+			regulator-max-microvolt = <1350000>;
+			regulator-always-on;
+		};
+
+		pm8226_l4: l4 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l5: l5 {
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+		};
+
+		pm8226_l6: l6 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		pm8226_l7: l7 {
+			regulator-min-microvolt = <1850000>;
+			regulator-max-microvolt = <1850000>;
+		};
+
+		pm8226_l8: l8 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		pm8226_l9: l9 {
+			regulator-min-microvolt = <2050000>;
+			regulator-max-microvolt = <2050000>;
+		};
+
+		pm8226_l10: l10 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l12: l12 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l14: l14 {
+			regulator-min-microvolt = <2750000>;
+			regulator-max-microvolt = <2750000>;
+		};
+
+		pm8226_l15: l15 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3300000>;
+		};
+
+		pm8226_l16: l16 {
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3350000>;
+		};
+
+		pm8226_l17: l17 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+
+			regulator-system-load = <200000>;
+			regulator-allow-set-load;
+			regulator-always-on;
+		};
+
+		pm8226_l18: l18 {
+			regulator-min-microvolt = <2950000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l19: l19 {
+			regulator-min-microvolt = <2850000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		pm8226_l20: l20 {
+			regulator-min-microvolt = <3075000>;
+			regulator-max-microvolt = <3075000>;
+		};
+
+		pm8226_l21: l21 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_l22: l22 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		pm8226_l23: l23 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3300000>;
+		};
+
+		pm8226_l24: l24 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1350000>;
+		};
+
+		pm8226_l25: l25 {
+			regulator-min-microvolt = <1775000>;
+			regulator-max-microvolt = <2125000>;
+		};
+
+		pm8226_l26: l26 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		pm8226_l27: l27 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+
+		pm8226_l28: l28 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2950000>;
+		};
+
+		pm8226_lvs1: lvs1 {};
+	};
+};
+
+&sdhc_1 {
+	vmmc-supply = <&pm8226_l17>;
+	vqmmc-supply = <&pm8226_l6>;
+
+	bus-width = <8>;
+	non-removable;
+
+	status = "okay";
+};
+
+&sdhc_2 {
+	vmmc-supply = <&pm8226_l18>;
+	vqmmc-supply = <&pm8226_l21>;
+
+	bus-width = <4>;
+	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
+
+	status = "okay";
+};
+
+&tlmm {
+	accel_int_default_state: accel-int-default-state {
+		pins = "gpio54";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	backlight_i2c_default_state: backlight-i2c-default-state {
+		pins = "gpio20", "gpio21";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	backlight_pwm_default_state: backlight-pwm-default-state {
+		pins = "gpio33";
+		function = "gp0_clk";
+	};
+
+	muic_int_default_state: muic-int-default-state {
+		pins = "gpio67";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	tsp_en_default_state: tsp-en-default-state {
+		pins = "gpio31";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	tsp_int_rst_default_state: tsp-int-rst-default-state {
+		pins = "gpio17";
+		function = "gpio";
+		drive-strength = <10>;
+		bias-pull-up;
+	};
+};
+
+&usb {
+	extcon = <&muic>, <&muic>;
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&muic>;
+	v1p8-supply = <&pm8226_l10>;
+	v3p3-supply = <&pm8226_l20>;
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
index b492c95e5d30..270973e85625 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi
@@ -20,11 +20,6 @@
 
 	chosen { };
 
-	memory@0 {
-		device_type = "memory";
-		reg = <0x0 0x0>;
-	};
-
 	clocks {
 		xo_board: xo_board {
 			compatible = "fixed-clock";
@@ -39,6 +34,57 @@
 		};
 	};
 
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		CPU0: cpu@0 {
+			compatible = "arm,cortex-a7";
+			enable-method = "qcom,msm8226-smp";
+			device_type = "cpu";
+			reg = <0>;
+			next-level-cache = <&L2>;
+			qcom,acc = <&acc0>;
+			qcom,saw = <&saw0>;
+		};
+
+		CPU1: cpu@1 {
+			compatible = "arm,cortex-a7";
+			enable-method = "qcom,msm8226-smp";
+			device_type = "cpu";
+			reg = <1>;
+			next-level-cache = <&L2>;
+			qcom,acc = <&acc1>;
+			qcom,saw = <&saw1>;
+		};
+
+		CPU2: cpu@2 {
+			compatible = "arm,cortex-a7";
+			enable-method = "qcom,msm8226-smp";
+			device_type = "cpu";
+			reg = <2>;
+			next-level-cache = <&L2>;
+			qcom,acc = <&acc2>;
+			qcom,saw = <&saw2>;
+		};
+
+		CPU3: cpu@3 {
+			compatible = "arm,cortex-a7";
+			enable-method = "qcom,msm8226-smp";
+			device_type = "cpu";
+			reg = <3>;
+			next-level-cache = <&L2>;
+			qcom,acc = <&acc3>;
+			qcom,saw = <&saw3>;
+		};
+
+		L2: l2-cache {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+		};
+	};
+
 	firmware {
 		scm {
 			compatible = "qcom,scm-msm8226", "qcom,scm";
@@ -47,6 +93,11 @@
 		};
 	};
 
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0>;
+	};
+
 	pmu {
 		compatible = "arm,cortex-a7-pmu";
 		interrupts = <GIC_PPI 7 (GIC_CPU_MASK_SIMPLE(4) |
@@ -185,6 +236,117 @@
 			reg = <0xf9011000 0x1000>;
 		};
 
+		saw_l2: power-manager@f9012000 {
+			compatible = "qcom,msm8226-saw2-v2.1-l2", "qcom,saw2";
+			reg = <0xf9012000 0x1000>;
+		};
+
+		watchdog@f9017000 {
+			compatible = "qcom,apss-wdt-msm8226", "qcom,kpss-wdt";
+			reg = <0xf9017000 0x1000>;
+			interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&sleep_clk>;
+		};
+
+		timer@f9020000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0xf9020000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			frame@f9021000 {
+				frame-number = <0>;
+				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9021000 0x1000>,
+				      <0xf9022000 0x1000>;
+			};
+
+			frame@f9023000 {
+				frame-number = <1>;
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9023000 0x1000>;
+				status = "disabled";
+			};
+
+			frame@f9024000 {
+				frame-number = <2>;
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9024000 0x1000>;
+				status = "disabled";
+			};
+
+			frame@f9025000 {
+				frame-number = <3>;
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9025000 0x1000>;
+				status = "disabled";
+			};
+
+			frame@f9026000 {
+				frame-number = <4>;
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9026000 0x1000>;
+				status = "disabled";
+			};
+
+			frame@f9027000 {
+				frame-number = <5>;
+				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9027000 0x1000>;
+				status = "disabled";
+			};
+
+			frame@f9028000 {
+				frame-number = <6>;
+				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
+				reg = <0xf9028000 0x1000>;
+				status = "disabled";
+			};
+		};
+
+		acc0: power-manager@f9088000 {
+			compatible = "qcom,kpss-acc-v2";
+			reg = <0xf9088000 0x1000>, <0xf9008000 0x1000>;
+		};
+
+		saw0: power-manager@f9089000 {
+			compatible = "qcom,msm8226-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf9089000 0x1000>;
+		};
+
+		acc1: power-manager@f9098000 {
+			compatible = "qcom,kpss-acc-v2";
+			reg = <0xf9098000 0x1000>, <0xf9008000 0x1000>;
+		};
+
+		saw1: power-manager@f9099000 {
+			compatible = "qcom,msm8226-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf9099000 0x1000>;
+		};
+
+		acc2: power-manager@f90a8000 {
+			compatible = "qcom,kpss-acc-v2";
+			reg = <0xf90a8000 0x1000>, <0xf9008000 0x1000>;
+		};
+
+		saw2: power-manager@f90a9000 {
+			compatible = "qcom,msm8226-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf90a9000 0x1000>;
+		};
+
+		acc3: power-manager@f90b8000 {
+			compatible = "qcom,kpss-acc-v2";
+			reg = <0xf90b8000 0x1000>, <0xf9008000 0x1000>;
+		};
+
+		saw3: power-manager@f90b9000 {
+			compatible = "qcom,msm8226-saw2-v2.1-cpu", "qcom,saw2";
+			reg = <0xf90b9000 0x1000>;
+		};
+
 		sdhc_1: mmc@f9824900 {
 			compatible = "qcom,msm8226-sdhci", "qcom,sdhci-msm-v4";
 			reg = <0xf9824900 0x11c>, <0xf9824000 0x800>;
@@ -201,35 +363,35 @@
 			status = "disabled";
 		};
 
-		sdhc_2: mmc@f98a4900 {
+		sdhc_3: mmc@f9864900 {
 			compatible = "qcom,msm8226-sdhci", "qcom,sdhci-msm-v4";
-			reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>;
+			reg = <0xf9864900 0x11c>, <0xf9864000 0x800>;
 			reg-names = "hc", "core";
-			interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hc_irq", "pwr_irq";
-			clocks = <&gcc GCC_SDCC2_AHB_CLK>,
-				 <&gcc GCC_SDCC2_APPS_CLK>,
+			clocks = <&gcc GCC_SDCC3_AHB_CLK>,
+				 <&gcc GCC_SDCC3_APPS_CLK>,
 				 <&rpmcc RPM_SMD_XO_CLK_SRC>;
 			clock-names = "iface", "core", "xo";
 			pinctrl-names = "default";
-			pinctrl-0 = <&sdhc2_default_state>;
+			pinctrl-0 = <&sdhc3_default_state>;
 			status = "disabled";
 		};
 
-		sdhc_3: mmc@f9864900 {
+		sdhc_2: mmc@f98a4900 {
 			compatible = "qcom,msm8226-sdhci", "qcom,sdhci-msm-v4";
-			reg = <0xf9864900 0x11c>, <0xf9864000 0x800>;
+			reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>;
 			reg-names = "hc", "core";
-			interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hc_irq", "pwr_irq";
-			clocks = <&gcc GCC_SDCC3_AHB_CLK>,
-				 <&gcc GCC_SDCC3_APPS_CLK>,
+			clocks = <&gcc GCC_SDCC2_AHB_CLK>,
+				 <&gcc GCC_SDCC2_APPS_CLK>,
 				 <&rpmcc RPM_SMD_XO_CLK_SRC>;
 			clock-names = "iface", "core", "xo";
 			pinctrl-names = "default";
-			pinctrl-0 = <&sdhc3_default_state>;
+			pinctrl-0 = <&sdhc2_default_state>;
 			status = "disabled";
 		};
 
@@ -272,7 +434,6 @@
 		};
 
 		blsp1_i2c1: i2c@f9923000 {
-			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9923000 0x1000>;
 			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
@@ -282,10 +443,10 @@
 			pinctrl-0 = <&blsp1_i2c1_pins>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			status = "disabled";
 		};
 
 		blsp1_i2c2: i2c@f9924000 {
-			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9924000 0x1000>;
 			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
@@ -295,10 +456,10 @@
 			pinctrl-0 = <&blsp1_i2c2_pins>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			status = "disabled";
 		};
 
 		blsp1_i2c3: i2c@f9925000 {
-			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9925000 0x1000>;
 			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
@@ -308,10 +469,10 @@
 			pinctrl-0 = <&blsp1_i2c3_pins>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			status = "disabled";
 		};
 
 		blsp1_i2c4: i2c@f9926000 {
-			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9926000 0x1000>;
 			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
@@ -321,10 +482,10 @@
 			pinctrl-0 = <&blsp1_i2c4_pins>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			status = "disabled";
 		};
 
 		blsp1_i2c5: i2c@f9927000 {
-			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9927000 0x1000>;
 			interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
@@ -334,6 +495,7 @@
 			pinctrl-0 = <&blsp1_i2c5_pins>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			status = "disabled";
 		};
 
 		blsp1_i2c6: i2c@f9928000 {
@@ -351,33 +513,6 @@
 			status = "disabled";
 		};
 
-		cci: cci@fda0c000 {
-			compatible = "qcom,msm8226-cci";
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0xfda0c000 0x1000>;
-			interrupts = <GIC_SPI 50 IRQ_TYPE_EDGE_RISING>;
-			clocks = <&mmcc CAMSS_TOP_AHB_CLK>,
-				 <&mmcc CAMSS_CCI_CCI_AHB_CLK>,
-				 <&mmcc CAMSS_CCI_CCI_CLK>;
-			clock-names = "camss_top_ahb",
-				      "cci_ahb",
-				      "cci";
-
-			pinctrl-names = "default", "sleep";
-			pinctrl-0 = <&cci_default>;
-			pinctrl-1 = <&cci_sleep>;
-
-			status = "disabled";
-
-			cci_i2c0: i2c-bus@0 {
-				reg = <0>;
-				clock-frequency = <400000>;
-				#address-cells = <1>;
-				#size-cells = <0>;
-			};
-		};
-
 		usb: usb@f9a55000 {
 			compatible = "qcom,ci-hdrc";
 			reg = <0xf9a55000 0x200>,
@@ -417,6 +552,18 @@
 			};
 		};
 
+		rng@f9bff000 {
+			compatible = "qcom,prng";
+			reg = <0xf9bff000 0x200>;
+			clocks = <&gcc GCC_PRNG_AHB_CLK>;
+			clock-names = "core";
+		};
+
+		sram@fc190000 {
+			compatible = "qcom,msm8226-rpm-stats";
+			reg = <0xfc190000 0x10000>;
+		};
+
 		gcc: clock-controller@fc400000 {
 			compatible = "qcom,gcc-msm8226";
 			reg = <0xfc400000 0x4000>;
@@ -430,146 +577,28 @@
 				      "sleep_clk";
 		};
 
-		mmcc: clock-controller@fd8c0000 {
-			compatible = "qcom,mmcc-msm8226";
-			reg = <0xfd8c0000 0x6000>;
-			#clock-cells = <1>;
-			#reset-cells = <1>;
-			#power-domain-cells = <1>;
-
-			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
-				 <&gcc GCC_MMSS_GPLL0_CLK_SRC>,
-				 <&gcc GPLL0_VOTE>,
-				 <&gcc GPLL1_VOTE>,
-				 <&rpmcc RPM_SMD_GFX3D_CLK_SRC>,
-				 <&mdss_dsi0_phy 1>,
-				 <&mdss_dsi0_phy 0>;
-			clock-names = "xo",
-				      "mmss_gpll0_vote",
-				      "gpll0_vote",
-				      "gpll1_vote",
-				      "gfx3d_clk_src",
-				      "dsi0pll",
-				      "dsi0pllbyte";
-		};
-
-		tlmm: pinctrl@fd510000 {
-			compatible = "qcom,msm8226-pinctrl";
-			reg = <0xfd510000 0x4000>;
-			gpio-controller;
-			#gpio-cells = <2>;
-			gpio-ranges = <&tlmm 0 0 117>;
-			interrupt-controller;
-			#interrupt-cells = <2>;
-			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
-
-			blsp1_i2c1_pins: blsp1-i2c1-state {
-				pins = "gpio2", "gpio3";
-				function = "blsp_i2c1";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			blsp1_i2c2_pins: blsp1-i2c2-state {
-				pins = "gpio6", "gpio7";
-				function = "blsp_i2c2";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			blsp1_i2c3_pins: blsp1-i2c3-state {
-				pins = "gpio10", "gpio11";
-				function = "blsp_i2c3";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			blsp1_i2c4_pins: blsp1-i2c4-state {
-				pins = "gpio14", "gpio15";
-				function = "blsp_i2c4";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			blsp1_i2c5_pins: blsp1-i2c5-state {
-				pins = "gpio18", "gpio19";
-				function = "blsp_i2c5";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			blsp1_i2c6_pins: blsp1-i2c6-state {
-				pins = "gpio22", "gpio23";
-				function = "blsp_i2c6";
-				drive-strength = <2>;
-				bias-disable;
-			};
-
-			cci_default: cci-default-state {
-				pins = "gpio29", "gpio30";
-				function = "cci_i2c0";
-
-				drive-strength = <2>;
-				bias-disable;
-			};
+		rpm_msg_ram: sram@fc428000 {
+			compatible = "qcom,rpm-msg-ram";
+			reg = <0xfc428000 0x4000>;
 
-			cci_sleep: cci-sleep-state {
-				pins = "gpio29", "gpio30";
-				function = "gpio";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 0xfc428000 0x4000>;
 
-				drive-strength = <2>;
-				bias-disable;
+			apss_master_stats: sram@150 {
+				reg = <0x150 0x14>;
 			};
 
-			sdhc1_default_state: sdhc1-default-state {
-				clk-pins {
-					pins = "sdc1_clk";
-					drive-strength = <10>;
-					bias-disable;
-				};
-
-				cmd-data-pins {
-					pins = "sdc1_cmd", "sdc1_data";
-					drive-strength = <10>;
-					bias-pull-up;
-				};
+			mpss_master_stats: sram@b50 {
+				reg = <0xb50 0x14>;
 			};
 
-			sdhc2_default_state: sdhc2-default-state {
-				clk-pins {
-					pins = "sdc2_clk";
-					drive-strength = <10>;
-					bias-disable;
-				};
-
-				cmd-data-pins {
-					pins = "sdc2_cmd", "sdc2_data";
-					drive-strength = <10>;
-					bias-pull-up;
-				};
+			lpss_master_stats: sram@1550 {
+				reg = <0x1550 0x14>;
 			};
 
-			sdhc3_default_state: sdhc3-default-state {
-				clk-pins {
-					pins = "gpio44";
-					function = "sdc3";
-					drive-strength = <8>;
-					bias-disable;
-				};
-
-				cmd-pins {
-					pins = "gpio43";
-					function = "sdc3";
-					drive-strength = <8>;
-					bias-pull-up;
-				};
-
-				data-pins {
-					pins = "gpio39", "gpio40", "gpio41", "gpio42";
-					function = "sdc3";
-					drive-strength = <8>;
-					bias-pull-up;
-				};
+			pronto_master_stats: sram@1f50 {
+				reg = <0x1f50 0x14>;
 			};
 		};
 
@@ -714,170 +743,153 @@
 			#interrupt-cells = <4>;
 		};
 
-		rng@f9bff000 {
-			compatible = "qcom,prng";
-			reg = <0xf9bff000 0x200>;
-			clocks = <&gcc GCC_PRNG_AHB_CLK>;
-			clock-names = "core";
+		tcsr_mutex: hwlock@fd484000 {
+			compatible = "qcom,msm8226-tcsr-mutex", "qcom,tcsr-mutex";
+			reg = <0xfd484000 0x1000>;
+			#hwlock-cells = <1>;
 		};
 
-		timer@f9020000 {
-			compatible = "arm,armv7-timer-mem";
-			reg = <0xf9020000 0x1000>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges;
-
-			frame@f9021000 {
-				frame-number = <0>;
-				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9021000 0x1000>,
-				      <0xf9022000 0x1000>;
-			};
+		tlmm: pinctrl@fd510000 {
+			compatible = "qcom,msm8226-pinctrl";
+			reg = <0xfd510000 0x4000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&tlmm 0 0 117>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 
-			frame@f9023000 {
-				frame-number = <1>;
-				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9023000 0x1000>;
-				status = "disabled";
+			blsp1_i2c1_pins: blsp1-i2c1-state {
+				pins = "gpio2", "gpio3";
+				function = "blsp_i2c1";
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			frame@f9024000 {
-				frame-number = <2>;
-				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9024000 0x1000>;
-				status = "disabled";
+			blsp1_i2c2_pins: blsp1-i2c2-state {
+				pins = "gpio6", "gpio7";
+				function = "blsp_i2c2";
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			frame@f9025000 {
-				frame-number = <3>;
-				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9025000 0x1000>;
-				status = "disabled";
+			blsp1_i2c3_pins: blsp1-i2c3-state {
+				pins = "gpio10", "gpio11";
+				function = "blsp_i2c3";
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			frame@f9026000 {
-				frame-number = <4>;
-				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9026000 0x1000>;
-				status = "disabled";
+			blsp1_i2c4_pins: blsp1-i2c4-state {
+				pins = "gpio14", "gpio15";
+				function = "blsp_i2c4";
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			frame@f9027000 {
-				frame-number = <5>;
-				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9027000 0x1000>;
-				status = "disabled";
+			blsp1_i2c5_pins: blsp1-i2c5-state {
+				pins = "gpio18", "gpio19";
+				function = "blsp_i2c5";
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			frame@f9028000 {
-				frame-number = <6>;
-				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
-				reg = <0xf9028000 0x1000>;
-				status = "disabled";
+			blsp1_i2c6_pins: blsp1-i2c6-state {
+				pins = "gpio22", "gpio23";
+				function = "blsp_i2c6";
+				drive-strength = <2>;
+				bias-disable;
 			};
-		};
-
-		sram@fc190000 {
-			compatible = "qcom,msm8226-rpm-stats";
-			reg = <0xfc190000 0x10000>;
-		};
-
-		rpm_msg_ram: sram@fc428000 {
-			compatible = "qcom,rpm-msg-ram";
-			reg = <0xfc428000 0x4000>;
 
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 0xfc428000 0x4000>;
-
-			apss_master_stats: sram@150 {
-				reg = <0x150 0x14>;
-			};
+			cci_default: cci-default-state {
+				pins = "gpio29", "gpio30";
+				function = "cci_i2c0";
 
-			mpss_master_stats: sram@b50 {
-				reg = <0xb50 0x14>;
+				drive-strength = <2>;
+				bias-disable;
 			};
 
-			lpss_master_stats: sram@1550 {
-				reg = <0x1550 0x14>;
-			};
+			cci_sleep: cci-sleep-state {
+				pins = "gpio29", "gpio30";
+				function = "gpio";
 
-			pronto_master_stats: sram@1f50 {
-				reg = <0x1f50 0x14>;
+				drive-strength = <2>;
+				bias-disable;
 			};
-		};
-
-		tcsr_mutex: hwlock@fd484000 {
-			compatible = "qcom,msm8226-tcsr-mutex", "qcom,tcsr-mutex";
-			reg = <0xfd484000 0x1000>;
-			#hwlock-cells = <1>;
-		};
 
-		adsp: remoteproc@fe200000 {
-			compatible = "qcom,msm8226-adsp-pil";
-			reg = <0xfe200000 0x100>;
-
-			interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>,
-					      <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
-					      <&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
-					      <&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
-					      <&adsp_smp2p_in 3 IRQ_TYPE_EDGE_RISING>;
-			interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack";
-
-			power-domains = <&rpmpd MSM8226_VDDCX>;
-			power-domain-names = "cx";
-
-			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>;
-			clock-names = "xo";
-
-			memory-region = <&adsp_region>;
-
-			qcom,smem-states = <&adsp_smp2p_out 0>;
-			qcom,smem-state-names = "stop";
-
-			status = "disabled";
+			sdhc1_default_state: sdhc1-default-state {
+				clk-pins {
+					pins = "sdc1_clk";
+					drive-strength = <10>;
+					bias-disable;
+				};
 
-			smd-edge {
-				interrupts = <GIC_SPI 156 IRQ_TYPE_EDGE_RISING>;
+				cmd-data-pins {
+					pins = "sdc1_cmd", "sdc1_data";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
+			};
 
-				qcom,ipc = <&apcs 8 8>;
-				qcom,smd-edge = <1>;
+			sdhc2_default_state: sdhc2-default-state {
+				clk-pins {
+					pins = "sdc2_clk";
+					drive-strength = <10>;
+					bias-disable;
+				};
 
-				label = "lpass";
+				cmd-data-pins {
+					pins = "sdc2_cmd", "sdc2_data";
+					drive-strength = <10>;
+					bias-pull-up;
+				};
 			};
-		};
 
-		sram@fdd00000 {
-			compatible = "qcom,msm8226-ocmem";
-			reg = <0xfdd00000 0x2000>,
-			      <0xfec00000 0x20000>;
-			reg-names = "ctrl", "mem";
-			ranges = <0 0xfec00000 0x20000>;
-			clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>;
-			clock-names = "core";
+			sdhc3_default_state: sdhc3-default-state {
+				clk-pins {
+					pins = "gpio44";
+					function = "sdc3";
+					drive-strength = <8>;
+					bias-disable;
+				};
 
-			#address-cells = <1>;
-			#size-cells = <1>;
+				cmd-pins {
+					pins = "gpio43";
+					function = "sdc3";
+					drive-strength = <8>;
+					bias-pull-up;
+				};
 
-			gmu_sram: gmu-sram@0 {
-				reg = <0x0 0x20000>;
+				data-pins {
+					pins = "gpio39", "gpio40", "gpio41", "gpio42";
+					function = "sdc3";
+					drive-strength = <8>;
+					bias-pull-up;
+				};
 			};
 		};
 
-		sram@fe805000 {
-			compatible = "qcom,msm8226-imem", "syscon", "simple-mfd";
-			reg = <0xfe805000 0x1000>;
-
-			reboot-mode {
-				compatible = "syscon-reboot-mode";
-				offset = <0x65c>;
+		mmcc: clock-controller@fd8c0000 {
+			compatible = "qcom,mmcc-msm8226";
+			reg = <0xfd8c0000 0x6000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
 
-				mode-bootloader = <0x77665500>;
-				mode-normal = <0x77665501>;
-				mode-recovery = <0x77665502>;
-			};
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
+				 <&gcc GCC_MMSS_GPLL0_CLK_SRC>,
+				 <&gcc GPLL0_VOTE>,
+				 <&gcc GPLL1_VOTE>,
+				 <&rpmcc RPM_SMD_GFX3D_CLK_SRC>,
+				 <&mdss_dsi0_phy 1>,
+				 <&mdss_dsi0_phy 0>;
+			clock-names = "xo",
+				      "mmss_gpll0_vote",
+				      "gpll0_vote",
+				      "gpll1_vote",
+				      "gfx3d_clk_src",
+				      "dsi0pll",
+				      "dsi0pllbyte";
 		};
 
 		mdss: display-subsystem@fd900000 {
@@ -1007,6 +1019,33 @@
 			};
 		};
 
+		cci: cci@fda0c000 {
+			compatible = "qcom,msm8226-cci";
+			reg = <0xfda0c000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupts = <GIC_SPI 50 IRQ_TYPE_EDGE_RISING>;
+			clocks = <&mmcc CAMSS_TOP_AHB_CLK>,
+				 <&mmcc CAMSS_CCI_CCI_AHB_CLK>,
+				 <&mmcc CAMSS_CCI_CCI_CLK>;
+			clock-names = "camss_top_ahb",
+				      "cci_ahb",
+				      "cci";
+
+			pinctrl-names = "default", "sleep";
+			pinctrl-0 = <&cci_default>;
+			pinctrl-1 = <&cci_sleep>;
+
+			status = "disabled";
+
+			cci_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <400000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		gpu: adreno@fdb00000 {
 			compatible = "qcom,adreno-305.18", "qcom,adreno";
 			reg = <0xfdb00000 0x10000>;
@@ -1046,6 +1085,71 @@
 				};
 			};
 		};
+
+		sram@fdd00000 {
+			compatible = "qcom,msm8226-ocmem";
+			reg = <0xfdd00000 0x2000>,
+			      <0xfec00000 0x20000>;
+			reg-names = "ctrl", "mem";
+			ranges = <0 0xfec00000 0x20000>;
+			clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>;
+			clock-names = "core";
+
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			gmu_sram: gmu-sram@0 {
+				reg = <0x0 0x20000>;
+			};
+		};
+
+		adsp: remoteproc@fe200000 {
+			compatible = "qcom,msm8226-adsp-pil";
+			reg = <0xfe200000 0x100>;
+
+			interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&adsp_smp2p_in 3 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack";
+
+			power-domains = <&rpmpd MSM8226_VDDCX>;
+			power-domain-names = "cx";
+
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>;
+			clock-names = "xo";
+
+			memory-region = <&adsp_region>;
+
+			qcom,smem-states = <&adsp_smp2p_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			smd-edge {
+				interrupts = <GIC_SPI 156 IRQ_TYPE_EDGE_RISING>;
+
+				qcom,ipc = <&apcs 8 8>;
+				qcom,smd-edge = <1>;
+
+				label = "lpass";
+			};
+		};
+
+		sram@fe805000 {
+			compatible = "qcom,msm8226-imem", "syscon", "simple-mfd";
+			reg = <0xfe805000 0x1000>;
+
+			reboot-mode {
+				compatible = "syscon-reboot-mode";
+				offset = <0x65c>;
+
+				mode-bootloader = <0x77665500>;
+				mode-normal = <0x77665501>;
+				mode-recovery = <0x77665502>;
+			};
+		};
 	};
 
 	thermal-zones {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
index a7c245b9c8f9..455ba4bf1bf4 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8660.dtsi
@@ -47,7 +47,7 @@
 
 	cpu-pmu {
 		compatible = "qcom,scorpion-mp-pmu";
-		interrupts = <1 9 0x304>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
 	};
 
 	clocks {
@@ -89,12 +89,11 @@
 
 		timer@2000000 {
 			compatible = "qcom,scss-timer", "qcom,msm-timer";
-			interrupts = <1 0 0x301>,
-				     <1 1 0x301>,
-				     <1 2 0x301>;
+			interrupts = <GIC_PPI 0 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>,
+				     <GIC_PPI 1 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>,
+				     <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_EDGE_RISING)>;
 			reg = <0x02000000 0x100>;
-			clock-frequency = <27000000>,
-					  <32768>;
+			clock-frequency = <27000000>;
 			cpu-offset = <0x40000>;
 		};
 
@@ -105,7 +104,7 @@
 			gpio-controller;
 			gpio-ranges = <&tlmm 0 0 173>;
 			#gpio-cells = <2>;
-			interrupts = <0 16 0x4>;
+			interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
@@ -283,7 +282,7 @@
 				compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm";
 				reg = <0x19c40000 0x1000>,
 				      <0x19c00000 0x1000>;
-				interrupts = <0 195 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI12_UART_CLK>, <&gcc GSBI12_H_CLK>;
 				clock-names = "core", "iface";
 				status = "disabled";
@@ -292,7 +291,7 @@
 			gsbi12_i2c: i2c@19c80000 {
 				compatible = "qcom,i2c-qup-v1.1.1";
 				reg = <0x19c80000 0x1000>;
-				interrupts = <0 196 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&gcc GSBI12_QUP_CLK>, <&gcc GSBI12_H_CLK>;
 				clock-names = "core", "iface";
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts
index ed328b24335f..3037344eb240 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-htc-memul.dts
@@ -107,7 +107,20 @@
 		};
 
 		unknown@fb00000 {
-			reg = <0x0fb00000 0x1b00000>;
+			reg = <0x0fb00000 0x280000>;
+			no-map;
+		};
+
+		rmtfs@fd80000 {
+			compatible = "qcom,rmtfs-mem";
+			reg = <0x0fd80000 0x180000>;
+			no-map;
+
+			qcom,client-id = <1>;
+		};
+
+		unknown@ff00000 {
+			reg = <0x0ff00000 0x1700000>;
 			no-map;
 		};
 	};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8926-samsung-matisselte.dts b/arch/arm/boot/dts/qcom/qcom-msm8926-samsung-matisselte.dts
new file mode 100644
index 000000000000..d0e1bc39f8ef
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8926-samsung-matisselte.dts
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2022, Matti Lehtimäki <matti.lehtimaki@gmail.com>
+ * Copyright (c) 2023, Stefan Hansson <newbyte@postmarketos.org>
+ */
+
+/dts-v1/;
+
+#include "qcom-msm8226-samsung-matisse-common.dtsi"
+
+/ {
+	model = "Samsung Galaxy Tab 4 10.1 LTE";
+	compatible = "samsung,matisselte", "qcom,msm8926", "qcom,msm8226";
+	chassis-type = "tablet";
+
+	reg_tsp_3p3v: regulator-tsp-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "tsp_3p3v";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpio = <&tlmm 32 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&tsp_en1_default_state>;
+	};
+};
+
+&tlmm {
+	tsp_en1_default_state: tsp-en1-default-state {
+		pins = "gpio32";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960-pins.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8960-pins.dtsi
new file mode 100644
index 000000000000..4fa982771288
--- /dev/null
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960-pins.dtsi
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+&msmgpio {
+	i2c3_default_state: i2c3-default-state {
+		i2c3-pins {
+			pins = "gpio16", "gpio17";
+			function = "gsbi3";
+			drive-strength = <8>;
+			bias-disable;
+		};
+	};
+
+	i2c3_sleep_state: i2c3-sleep-state {
+		i2c3-pins {
+			pins = "gpio16", "gpio17";
+			function = "gpio";
+			drive-strength = <2>;
+			bias-bus-hold;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts b/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
index 1a5116336ff0..af6cc6393d74 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960-samsung-expressatt.dts
@@ -4,6 +4,9 @@
 
 #include "qcom-msm8960.dtsi"
 #include "pm8921.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
+#include <dt-bindings/input/gpio-keys.h>
 
 / {
 	model = "Samsung Galaxy Express SGH-I437";
@@ -19,6 +22,36 @@
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_keys_pin_a>;
+
+		key-home {
+			label = "Home";
+			gpios = <&msmgpio 40 GPIO_ACTIVE_LOW>;
+			debounce-interval = <5>;
+			linux,code = <KEY_HOMEPAGE>;
+			wakeup-event-action = <EV_ACT_ASSERTED>;
+			wakeup-source;
+		};
+
+		key-volume-up {
+			label = "Volume Up";
+			gpios = <&msmgpio 50 GPIO_ACTIVE_LOW>;
+			debounce-interval = <5>;
+			linux,code = <KEY_VOLUMEUP>;
+		};
+
+		key-volume-down {
+			label = "Volume Down";
+			gpios = <&msmgpio 81 GPIO_ACTIVE_LOW>;
+			debounce-interval = <5>;
+			linux,code = <KEY_VOLUMEDOWN>;
+		};
+	};
 };
 
 &gsbi5 {
@@ -52,6 +85,27 @@
 	status = "okay";
 };
 
+&gsbi3 {
+	qcom,mode = <GSBI_PROT_I2C>;
+	status = "okay";
+};
+
+&gsbi3_i2c {
+	status = "okay";
+
+	// Atmel mXT224S touchscreen
+	touchscreen@4a {
+		compatible = "atmel,maxtouch";
+		reg = <0x4a>;
+		interrupt-parent = <&msmgpio>;
+		interrupts = <11 IRQ_TYPE_EDGE_FALLING>;
+		vdda-supply = <&pm8921_lvs6>;
+		vdd-supply = <&pm8921_l17>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen>;
+	};
+};
+
 &msmgpio {
 	spi1_default: spi1-default-state {
 		mosi-pins {
@@ -83,6 +137,21 @@
 			bias-disable;
 		};
 	};
+
+	gpio_keys_pin_a: gpio-keys-active-state {
+		pins = "gpio40", "gpio50", "gpio81";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-disable;
+	};
+
+	touchscreen: touchscreen-int-state {
+		pins = "gpio11";
+		function = "gpio";
+		output-enable;
+		bias-disable;
+		drive-strength = <2>;
+	};
 };
 
 &pm8921 {
@@ -245,7 +314,7 @@
 		};
 
 		pm8921_l17: l17 {
-			regulator-min-microvolt = <1800000>;
+			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 			bias-pull-down;
 		};
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
index f420740e068e..922f9e49468a 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8960.dtsi
@@ -220,16 +220,24 @@
 			#clock-cells = <0>;
 		};
 
-		saw0: regulator@2089000 {
-			compatible = "qcom,saw2";
+		saw0: power-manager@2089000 {
+			compatible = "qcom,msm8960-saw2-cpu", "qcom,saw2";
 			reg = <0x02089000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw0_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
-		saw1: regulator@2099000 {
-			compatible = "qcom,saw2";
+		saw1: power-manager@2099000 {
+			compatible = "qcom,msm8960-saw2-cpu", "qcom,saw2";
 			reg = <0x02099000 0x1000>, <0x02009000 0x1000>;
-			regulator;
+
+			saw1_vreg: regulator {
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1300000>;
+			};
 		};
 
 		gsbi5: gsbi@16400000 {
@@ -359,5 +367,33 @@
 				};
 			};
 		};
+
+		gsbi3: gsbi@16200000 {
+			compatible = "qcom,gsbi-v1.0.0";
+			reg = <0x16200000 0x100>;
+			ranges;
+			cell-index = <3>;
+			clocks = <&gcc GSBI3_H_CLK>;
+			clock-names = "iface";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+
+			gsbi3_i2c: i2c@16280000 {
+				compatible = "qcom,i2c-qup-v1.1.1";
+				reg = <0x16280000 0x1000>;
+				pinctrl-0 = <&i2c3_default_state>;
+				pinctrl-1 = <&i2c3_sleep_state>;
+				pinctrl-names = "default", "sleep";
+				interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&gcc GSBI3_QUP_CLK>,
+					 <&gcc GSBI3_H_CLK>;
+				clock-names = "core", "iface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
+		};
 	};
 };
+#include "qcom-msm8960-pins.dtsi"
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
index b1413983787c..5efc38d712cc 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi
@@ -31,7 +31,7 @@
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
-		interrupts = <GIC_PPI 9 0xf04>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
 
 		CPU0: cpu@0 {
 			compatible = "qcom,krait";
@@ -110,7 +110,7 @@
 
 	pmu {
 		compatible = "qcom,krait-pmu";
-		interrupts = <GIC_PPI 7 0xf04>;
+		interrupts = <GIC_PPI 7 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
 	};
 
 	rpm: remoteproc {
@@ -346,10 +346,9 @@
 			reg = <0xf9011000 0x1000>;
 		};
 
-		saw_l2: power-controller@f9012000 {
-			compatible = "qcom,saw2";
+		saw_l2: power-manager@f9012000 {
+			compatible = "qcom,msm8974-saw2-v2.1-l2", "qcom,saw2";
 			reg = <0xf9012000 0x1000>;
-			regulator;
 		};
 
 		watchdog@f9017000 {
@@ -424,7 +423,7 @@
 			reg = <0xf9088000 0x1000>, <0xf9008000 0x1000>;
 		};
 
-		saw0: power-controller@f9089000 {
+		saw0: power-manager@f9089000 {
 			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf9089000 0x1000>, <0xf9009000 0x1000>;
 		};
@@ -434,7 +433,7 @@
 			reg = <0xf9098000 0x1000>, <0xf9008000 0x1000>;
 		};
 
-		saw1: power-controller@f9099000 {
+		saw1: power-manager@f9099000 {
 			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf9099000 0x1000>, <0xf9009000 0x1000>;
 		};
@@ -444,7 +443,7 @@
 			reg = <0xf90a8000 0x1000>, <0xf9008000 0x1000>;
 		};
 
-		saw2: power-controller@f90a9000 {
+		saw2: power-manager@f90a9000 {
 			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf90a9000 0x1000>, <0xf9009000 0x1000>;
 		};
@@ -454,7 +453,7 @@
 			reg = <0xf90b8000 0x1000>, <0xf9008000 0x1000>;
 		};
 
-		saw3: power-controller@f90b9000 {
+		saw3: power-manager@f90b9000 {
 			compatible = "qcom,msm8974-saw2-v2.1-cpu", "qcom,saw2";
 			reg = <0xf90b9000 0x1000>, <0xf9009000 0x1000>;
 		};
@@ -538,7 +537,7 @@
 			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9923000 0x1000>;
-			interrupts = <0 95 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP1_I2C_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>;
 			clock-names = "core", "iface";
 			pinctrl-names = "default", "sleep";
@@ -566,7 +565,7 @@
 			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9925000 0x1000>;
-			interrupts = <0 97 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>;
 			clock-names = "core", "iface";
 			pinctrl-names = "default", "sleep";
@@ -666,7 +665,7 @@
 			status = "disabled";
 			compatible = "qcom,i2c-qup-v2.1.1";
 			reg = <0xf9968000 0x1000>;
-			interrupts = <0 106 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&gcc GCC_BLSP2_QUP6_I2C_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>;
 			clock-names = "core", "iface";
 			pinctrl-names = "default", "sleep";
@@ -1234,7 +1233,7 @@
 
 		qfprom: qfprom@fc4bc000 {
 			compatible = "qcom,msm8974-qfprom", "qcom,qfprom";
-			reg = <0xfc4bc000 0x1000>;
+			reg = <0xfc4bc000 0x2100>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 
@@ -2403,10 +2402,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <GIC_PPI 2 0xf08>,
-			     <GIC_PPI 3 0xf08>,
-			     <GIC_PPI 4 0xf08>,
-			     <GIC_PPI 1 0xf08>;
+		interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 4 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 1 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 		clock-frequency = <19200000>;
 	};
 };
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
index 2045fc779f88..edc9aaf828c8 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-sdx55.dtsi
@@ -340,10 +340,10 @@
 					  "msi8";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 0 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 0 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 0 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 0 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 141 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 142 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 143 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 144 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_PCIE_PIPE_CLK>,
 				 <&gcc GCC_PCIE_AUX_CLK>,
@@ -580,12 +580,16 @@
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 51 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 51 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_GDSC>;
 
@@ -727,57 +731,57 @@
 
 			frame@17821000 {
 				frame-number = <0>;
-				interrupts = <GIC_SPI 7 0x4>,
-					     <GIC_SPI 6 0x4>;
+				interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17821000 0x1000>,
 				      <0x17822000 0x1000>;
 			};
 
 			frame@17823000 {
 				frame-number = <1>;
-				interrupts = <GIC_SPI 8 0x4>;
+				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17823000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17824000 {
 				frame-number = <2>;
-				interrupts = <GIC_SPI 9 0x4>;
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17824000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17825000 {
 				frame-number = <3>;
-				interrupts = <GIC_SPI 10 0x4>;
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17825000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17826000 {
 				frame-number = <4>;
-				interrupts = <GIC_SPI 11 0x4>;
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17826000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17827000 {
 				frame-number = <5>;
-				interrupts = <GIC_SPI 12 0x4>;
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17827000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17828000 {
 				frame-number = <6>;
-				interrupts = <GIC_SPI 13 0x4>;
+				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17828000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17829000 {
 				frame-number = <7>;
-				interrupts = <GIC_SPI 14 0x4>;
+				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17829000 0x1000>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
index 40591a4da6a4..a949454212e9 100644
--- a/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
+++ b/arch/arm/boot/dts/qcom/qcom-sdx65.dtsi
@@ -492,23 +492,25 @@
 			clocks = <&gcc GCC_USB30_SLV_AHB_CLK>,
 				 <&gcc GCC_USB30_MASTER_CLK>,
 				 <&gcc GCC_USB30_MSTR_AXI_CLK>,
-				 <&gcc GCC_USB30_MOCK_UTMI_CLK>,
-				 <&gcc GCC_USB30_SLEEP_CLK>;
-			clock-names = "cfg_noc", "core", "iface", "mock_utmi",
-					"sleep";
+				 <&gcc GCC_USB30_SLEEP_CLK>,
+				 <&gcc GCC_USB30_MOCK_UTMI_CLK>;
+			clock-names = "cfg_noc", "core", "iface", "sleep",
+				      "mock_utmi";
 
 			assigned-clocks = <&gcc GCC_USB30_MOCK_UTMI_CLK>,
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 76 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 19 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 18 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 19 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 76 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_GDSC>;
 
@@ -667,57 +669,57 @@
 
 			frame@17821000 {
 				frame-number = <0>;
-				interrupts = <GIC_SPI 7 0x4>,
-					     <GIC_SPI 6 0x4>;
+				interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17821000 0x1000>,
 				      <0x17822000 0x1000>;
 			};
 
 			frame@17823000 {
 				frame-number = <1>;
-				interrupts = <GIC_SPI 8 0x4>;
+				interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17823000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17824000 {
 				frame-number = <2>;
-				interrupts = <GIC_SPI 9 0x4>;
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17824000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17825000 {
 				frame-number = <3>;
-				interrupts = <GIC_SPI 10 0x4>;
+				interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17825000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17826000 {
 				frame-number = <4>;
-				interrupts = <GIC_SPI 11 0x4>;
+				interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17826000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17827000 {
 				frame-number = <5>;
-				interrupts = <GIC_SPI 12 0x4>;
+				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17827000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17828000 {
 				frame-number = <6>;
-				interrupts = <GIC_SPI 13 0x4>;
+				interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17828000 0x1000>;
 				status = "disabled";
 			};
 
 			frame@17829000 {
 				frame-number = <7>;
-				interrupts = <GIC_SPI 14 0x4>;
+				interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x17829000 0x1000>;
 				status = "disabled";
 			};
@@ -804,10 +806,10 @@
 
 	timer {
 		compatible = "arm,armv7-timer";
-		interrupts = <1 13 0xf08>,
-			<1 12 0xf08>,
-			<1 10 0xf08>,
-			<1 11 0xf08>;
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 12 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
 		clock-frequency = <19200000>;
 	};
 };
diff --git a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts
index ed75c01dbee1..3d02f065f71c 100644
--- a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts
+++ b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts
@@ -209,6 +209,18 @@
 	status = "okay";
 };
 
+&extal1_clk {
+	clock-frequency = <26000000>;
+};
+
+&extal2_clk {
+	clock-frequency = <48000000>;
+};
+
+&extalr_clk {
+	clock-frequency = <32768>;
+};
+
 &pfc {
 	scifa0_pins: scifa0 {
 		groups = "scifa0_data";
diff --git a/arch/arm/boot/dts/renesas/r8a73a4.dtsi b/arch/arm/boot/dts/renesas/r8a73a4.dtsi
index c39066967053..ac654ff45d0e 100644
--- a/arch/arm/boot/dts/renesas/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a73a4.dtsi
@@ -450,17 +450,20 @@
 		extalr_clk: extalr {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <32768>;
+			/* This value must be overridden by the board. */
+			clock-frequency = <0>;
 		};
 		extal1_clk: extal1 {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <25000000>;
+			/* This value must be overridden by the board. */
+			clock-frequency = <0>;
 		};
 		extal2_clk: extal2 {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <48000000>;
+			/* This value must be overridden by the board. */
+			clock-frequency = <0>;
 		};
 		fsiack_clk: fsiack {
 			compatible = "fixed-clock";
@@ -621,6 +624,13 @@
 			clock-div = <2>;
 			clock-mult = <1>;
 		};
+		cp_clk: cp {
+			compatible = "fixed-factor-clock";
+			clocks = <&main_div2_clk>;
+			#clock-cells = <0>;
+			clock-div = <1>;
+			clock-mult = <1>;
+		};
 		pll0_div2_clk: pll0_div2 {
 			compatible = "fixed-factor-clock";
 			clocks = <&cpg_clocks R8A73A4_CLK_PLL0>;
@@ -686,9 +696,8 @@
 		mstp4_clks: mstp4_clks@e6150140 {
 			compatible = "renesas,r8a73a4-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150140 0 4>, <0 0xe615004c 0 4>;
-			clocks = <&main_div2_clk>, <&cpg_clocks R8A73A4_CLK_ZS>,
-				 <&main_div2_clk>,
-				 <&cpg_clocks R8A73A4_CLK_HP>,
+			clocks = <&cp_clk>, <&cpg_clocks R8A73A4_CLK_ZS>,
+				 <&cp_clk>, <&cpg_clocks R8A73A4_CLK_HP>,
 				 <&cpg_clocks R8A73A4_CLK_HP>;
 			#clock-cells = <1>;
 			clock-indices = <
@@ -702,7 +711,7 @@
 		mstp5_clks: mstp5_clks@e6150144 {
 			compatible = "renesas,r8a73a4-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150144 0 4>, <0 0xe615003c 0 4>;
-			clocks = <&extal2_clk>, <&cpg_clocks R8A73A4_CLK_HP>;
+			clocks = <&cp_clk>, <&cpg_clocks R8A73A4_CLK_HP>;
 			#clock-cells = <1>;
 			clock-indices = <
 				R8A73A4_CLK_THERMAL R8A73A4_CLK_IIC8
diff --git a/arch/arm/boot/dts/renesas/r8a7740.dtsi b/arch/arm/boot/dts/renesas/r8a7740.dtsi
index 55884ec701f8..d13ab86c3ab4 100644
--- a/arch/arm/boot/dts/renesas/r8a7740.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7740.dtsi
@@ -459,6 +459,7 @@
 		interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2";
 		clocks = <&mstp1_clks R8A7740_CLK_TMU0>;
 		clock-names = "fck";
 		power-domains = <&pd_a4r>;
@@ -474,6 +475,7 @@
 		interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2";
 		clocks = <&mstp1_clks R8A7740_CLK_TMU1>;
 		clock-names = "fck";
 		power-domains = <&pd_a4r>;
diff --git a/arch/arm/boot/dts/renesas/r8a7778.dtsi b/arch/arm/boot/dts/renesas/r8a7778.dtsi
index 8d4530ed2fc6..b80e832c9277 100644
--- a/arch/arm/boot/dts/renesas/r8a7778.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7778.dtsi
@@ -199,7 +199,9 @@
 		reg = <0xffd80000 0x30>;
 		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 		clocks = <&mstp0_clks R8A7778_CLK_TMU0>;
 		clock-names = "fck";
 		power-domains = <&cpg_clocks>;
@@ -214,7 +216,9 @@
 		reg = <0xffd81000 0x30>;
 		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 		clocks = <&mstp0_clks R8A7778_CLK_TMU1>;
 		clock-names = "fck";
 		power-domains = <&cpg_clocks>;
@@ -230,6 +234,7 @@
 		interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2";
 		clocks = <&mstp0_clks R8A7778_CLK_TMU2>;
 		clock-names = "fck";
 		power-domains = <&cpg_clocks>;
@@ -250,6 +255,8 @@
 		reg =	<0xffd90000 0x1000>,	/* SRU */
 			<0xffd91000 0x240>,	/* SSI */
 			<0xfffe0000 0x24>;	/* ADG */
+		reg-names = "sru", "ssi", "adg";
+
 		clocks = <&mstp3_clks R8A7778_CLK_SSI8>,
 			<&mstp3_clks R8A7778_CLK_SSI7>,
 			<&mstp3_clks R8A7778_CLK_SSI6>,
diff --git a/arch/arm/boot/dts/renesas/r8a7779.dtsi b/arch/arm/boot/dts/renesas/r8a7779.dtsi
index 7743af5e2a6f..1944703cba4f 100644
--- a/arch/arm/boot/dts/renesas/r8a7779.dtsi
+++ b/arch/arm/boot/dts/renesas/r8a7779.dtsi
@@ -402,7 +402,9 @@
 		reg = <0xffd80000 0x30>;
 		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 		clocks = <&mstp0_clks R8A7779_CLK_TMU0>;
 		clock-names = "fck";
 		power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
@@ -417,7 +419,9 @@
 		reg = <0xffd81000 0x30>;
 		interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+			     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 		clocks = <&mstp0_clks R8A7779_CLK_TMU1>;
 		clock-names = "fck";
 		power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
@@ -433,6 +437,7 @@
 		interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "tuni0", "tuni1", "tuni2";
 		clocks = <&mstp0_clks R8A7779_CLK_TMU2>;
 		clock-names = "fck";
 		power-domains = <&sysc R8A7779_PD_ALWAYS_ON>;
diff --git a/arch/arm/boot/dts/renesas/r8a7790-lager.dts b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
index 2fba4d084001..8590981245a6 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-lager.dts
@@ -447,6 +447,7 @@
 			interrupt-parent = <&irqc0>;
 			interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 
 			rtc {
 				compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7790-stout.dts b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
index f9bc5b4f019d..683f7395fab0 100644
--- a/arch/arm/boot/dts/renesas/r8a7790-stout.dts
+++ b/arch/arm/boot/dts/renesas/r8a7790-stout.dts
@@ -347,6 +347,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
index e9c13bb03772..0efd9f98c75a 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-koelsch.dts
@@ -819,6 +819,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7791-porter.dts b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
index 7e8bc06715f6..93c86e921645 100644
--- a/arch/arm/boot/dts/renesas/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/renesas/r8a7791-porter.dts
@@ -413,6 +413,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		watchdog {
 			compatible = "dlg,da9063-watchdog";
diff --git a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
index 4f9838cf97ee..540a9ad28f28 100644
--- a/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
+++ b/arch/arm/boot/dts/renesas/r8a7792-blanche.dts
@@ -381,6 +381,7 @@
 		interrupt-parent = <&irqc>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7793-gose.dts b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
index 1744fdbf9e0c..1ea6c757893b 100644
--- a/arch/arm/boot/dts/renesas/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/renesas/r8a7793-gose.dts
@@ -759,6 +759,7 @@
 		interrupt-parent = <&irqc0>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-alt.dts b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
index c0d067df22a0..b5ecafbb2e4d 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-alt.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-alt.dts
@@ -453,6 +453,7 @@
 		interrupt-parent = <&gpio3>;
 		interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		rtc {
 			compatible = "dlg,da9063-rtc";
diff --git a/arch/arm/boot/dts/renesas/r8a7794-silk.dts b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
index 43d480a7f3ea..595e074085eb 100644
--- a/arch/arm/boot/dts/renesas/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/renesas/r8a7794-silk.dts
@@ -439,6 +439,7 @@
 		interrupt-parent = <&gpio3>;
 		interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
index 03a97881519a..21c1678f4e91 100644
--- a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
+++ b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
@@ -47,6 +47,17 @@
 		regulator-boot-on;
 	};
 
+	hdmi-connnector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&hdmi_connector_out>;
+			};
+		};
+	};
+
 	/*
 	 * This is a vbus-supply, which also supplies the GL852G usb hub,
 	 * thus has to be always-on
@@ -239,6 +250,10 @@
 	cpu-supply = <&vdd_arm>;
 };
 
+&display_subsystem {
+	status = "okay";
+};
+
 &emmc {
 	bus-width = <8>;
 	vmmc-supply = <&vcc_io>;
@@ -328,6 +343,16 @@
 	status = "okay";
 };
 
+&hdmi {
+	status = "okay";
+};
+
+&hdmi_out {
+	hdmi_connector_out: endpoint {
+		remote-endpoint = <&hdmi_connector_in>;
+	};
+};
+
 &mdio {
 	phy0: ethernet-phy@1 {
 		compatible = "ethernet-phy-ieee802.3-c22";
@@ -423,3 +448,7 @@
 &usb2phy_otg {
 	status = "okay";
 };
+
+&vop {
+	status = "okay";
+};
diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi
index e2264c40b924..fb98873fd94e 100644
--- a/arch/arm/boot/dts/rockchip/rk3128.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi
@@ -115,6 +115,12 @@
 		};
 	};
 
+	display_subsystem: display-subsystem {
+		compatible = "rockchip,display-subsystem";
+		ports = <&vop_out>;
+		status = "disabled";
+	};
+
 	gpu_opp_table: opp-table-1 {
 		compatible = "operating-points-v2";
 
@@ -246,6 +252,32 @@
 		};
 	};
 
+	vop: vop@1010e000 {
+		compatible = "rockchip,rk3126-vop";
+		reg = <0x1010e000 0x300>;
+		interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru ACLK_LCDC0>, <&cru DCLK_VOP>,
+			 <&cru HCLK_LCDC0>;
+		clock-names = "aclk_vop", "dclk_vop",
+			      "hclk_vop";
+		resets = <&cru SRST_VOP_A>, <&cru SRST_VOP_H>,
+			 <&cru SRST_VOP_D>;
+		reset-names = "axi", "ahb",
+			      "dclk";
+		power-domains = <&power RK3128_PD_VIO>;
+		status = "disabled";
+
+		vop_out: port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			vop_out_hdmi: endpoint@0 {
+				reg = <0>;
+				remote-endpoint = <&hdmi_in_vop>;
+			};
+		};
+	};
+
 	qos_gpu: qos@1012d000 {
 		compatible = "rockchip,rk3128-qos", "syscon";
 		reg = <0x1012d000 0x20>;
@@ -436,6 +468,34 @@
 		};
 	};
 
+	hdmi: hdmi@20034000 {
+		compatible = "rockchip,rk3128-inno-hdmi";
+		reg = <0x20034000 0x4000>;
+		interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru PCLK_HDMI>, <&cru DCLK_VOP>;
+		clock-names = "pclk", "ref";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hdmii2c_xfer &hdmi_hpd &hdmi_cec>;
+		power-domains = <&power RK3128_PD_VIO>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi_in: port@0 {
+				reg = <0>;
+				hdmi_in_vop: endpoint {
+					remote-endpoint = <&vop_out_hdmi>;
+				};
+			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
+			};
+		};
+	};
+
 	timer0: timer@20044000 {
 		compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
 		reg = <0x20044000 0x20>;
diff --git a/arch/arm/boot/dts/rockchip/rk322x.dtsi b/arch/arm/boot/dts/rockchip/rk322x.dtsi
index 831561fc1814..96421355c274 100644
--- a/arch/arm/boot/dts/rockchip/rk322x.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk322x.dtsi
@@ -736,14 +736,20 @@
 		status = "disabled";
 
 		ports {
-			hdmi_in: port {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				hdmi_in_vop: endpoint@0 {
-					reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi_in: port@0 {
+				reg = <0>;
+
+				hdmi_in_vop: endpoint {
 					remote-endpoint = <&vop_out_hdmi>;
 				};
 			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/rockchip/rk3288.dtsi b/arch/arm/boot/dts/rockchip/rk3288.dtsi
index ead343dc3df1..3f1d640afafa 100644
--- a/arch/arm/boot/dts/rockchip/rk3288.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3288.dtsi
@@ -1240,27 +1240,37 @@
 		compatible = "rockchip,rk3288-dw-hdmi";
 		reg = <0x0 0xff980000 0x0 0x20000>;
 		reg-io-width = <4>;
-		#sound-dai-cells = <0>;
-		rockchip,grf = <&grf>;
 		interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru  PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>;
 		clock-names = "iahb", "isfr", "cec";
 		power-domains = <&power RK3288_PD_VIO>;
+		rockchip,grf = <&grf>;
+		#sound-dai-cells = <0>;
 		status = "disabled";
 
 		ports {
-			hdmi_in: port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi_in: port@0 {
+				reg = <0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
+
 				hdmi_in_vopb: endpoint@0 {
 					reg = <0>;
 					remote-endpoint = <&vopb_out_hdmi>;
 				};
+
 				hdmi_in_vopl: endpoint@1 {
 					reg = <1>;
 					remote-endpoint = <&vopl_out_hdmi>;
 				};
 			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/rockchip/rv1108.dtsi b/arch/arm/boot/dts/rockchip/rv1108.dtsi
index abf3006f0a84..f3291f3bbc6f 100644
--- a/arch/arm/boot/dts/rockchip/rv1108.dtsi
+++ b/arch/arm/boot/dts/rockchip/rv1108.dtsi
@@ -196,7 +196,6 @@
 	pwm4: pwm@10280000 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280000 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -208,7 +207,6 @@
 	pwm5: pwm@10280010 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280010 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -220,7 +218,6 @@
 	pwm6: pwm@10280020 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280020 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -232,7 +229,6 @@
 	pwm7: pwm@10280030 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x10280030 0x10>;
-		interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -386,7 +382,6 @@
 	pwm0: pwm@20040000 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040000 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -398,7 +393,6 @@
 	pwm1: pwm@20040010 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040010 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -410,7 +404,6 @@
 	pwm2: pwm@20040020 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040020 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -422,7 +415,6 @@
 	pwm3: pwm@20040030 {
 		compatible = "rockchip,rv1108-pwm", "rockchip,rk3288-pwm";
 		reg = <0x20040030 0x10>;
-		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM0_PMU>, <&cru PCLK_PWM0_PMU>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi
index 32b329e87a0c..9a87dc0d5f66 100644
--- a/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi
+++ b/arch/arm/boot/dts/rockchip/rv1126-sonoff-ihost.dtsi
@@ -8,6 +8,8 @@
 	aliases {
 		ethernet0 = &gmac;
 		mmc0 = &emmc;
+		mmc1 = &sdio;
+		mmc2 = &sdmmc;
 	};
 
 	chosen {
@@ -325,7 +327,7 @@
 	pmuio1-supply = <&vcc3v3_sys>;
 	vccio1-supply = <&vcc_1v8>;
 	vccio2-supply = <&vccio_sd>;
-	vccio3-supply = <&vcc_1v8>;
+	vccio3-supply = <&vcc3v3_sd>;
 	vccio4-supply = <&vcc_dovdd>;
 	vccio5-supply = <&vcc_1v8>;
 	vccio6-supply = <&vcc_1v8>;
@@ -343,14 +345,14 @@
 	cap-sd-highspeed;
 	cap-sdio-irq;
 	keep-power-in-suspend;
-	max-frequency = <100000000>;
+	max-frequency = <50000000>;
 	mmc-pwrseq = <&sdio_pwrseq>;
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdmmc1_clk &sdmmc1_cmd &sdmmc1_bus4>;
 	rockchip,default-sample-phase = <90>;
-	sd-uhs-sdr104;
-	vmmc-supply = <&vcc3v3_sys>;
+	sd-uhs-sdr50;
+	vmmc-supply = <&vcc3v3_sd>;
 	vqmmc-supply = <&vcc_1v8>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/samsung/exynos4412-i9300.dts b/arch/arm/boot/dts/samsung/exynos4412-i9300.dts
index 61aca5798f38..b79d456e976d 100644
--- a/arch/arm/boot/dts/samsung/exynos4412-i9300.dts
+++ b/arch/arm/boot/dts/samsung/exynos4412-i9300.dts
@@ -18,7 +18,7 @@
 
 	memory@40000000 {
 		device_type = "memory";
-		reg = <0x40000000 0x40000000>;
+		reg = <0x40000000 0x3fc00000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/samsung/exynos4412-i9305.dts b/arch/arm/boot/dts/samsung/exynos4412-i9305.dts
index 77083f1a8273..1048ef5d9bc3 100644
--- a/arch/arm/boot/dts/samsung/exynos4412-i9305.dts
+++ b/arch/arm/boot/dts/samsung/exynos4412-i9305.dts
@@ -11,7 +11,7 @@
 
 	memory@40000000 {
 		device_type = "memory";
-		reg = <0x40000000 0x80000000>;
+		reg = <0x40000000 0x7fc00000>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/samsung/exynos4412-n710x.dts b/arch/arm/boot/dts/samsung/exynos4412-n710x.dts
index 0a151437fc73..eee1000dea92 100644
--- a/arch/arm/boot/dts/samsung/exynos4412-n710x.dts
+++ b/arch/arm/boot/dts/samsung/exynos4412-n710x.dts
@@ -9,7 +9,7 @@
 
 	memory@40000000 {
 		device_type = "memory";
-		reg = <0x40000000 0x80000000>;
+		reg = <0x40000000 0x7fc00000>;
 	};
 
 	/* bootargs are passed in by bootloader */
diff --git a/arch/arm/boot/dts/samsung/exynos4412-p4note.dtsi b/arch/arm/boot/dts/samsung/exynos4412-p4note.dtsi
index 0b89d5682f85..28a605802733 100644
--- a/arch/arm/boot/dts/samsung/exynos4412-p4note.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos4412-p4note.dtsi
@@ -23,7 +23,7 @@
 
 	memory@40000000 {
 		device_type = "memory";
-		reg = <0x40000000 0x80000000>;
+		reg = <0x40000000 0x7fc00000>;
 	};
 
 	aliases {
@@ -362,6 +362,39 @@
 	status = "okay";
 };
 
+&i2c_1 {
+	samsung,i2c-sda-delay = <100>;
+	samsung,i2c-slave-addr = <0x10>;
+	samsung,i2c-max-bus-freq = <400000>;
+	pinctrl-0 = <&i2c1_bus>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	accelerometer@19 {
+		compatible = "st,lsm330dlc-accel";
+		reg = <0x19>;
+		interrupt-parent = <&gpx0>;
+		interrupts = <0 IRQ_TYPE_EDGE_RISING>;
+		pinctrl-0 = <&accelerometer_irq>;
+		pinctrl-names = "default";
+		mount-matrix =	"1",  "0",  "0",
+				"0", "-1",  "0",
+				"0",  "0", "-1";
+	};
+
+	gyro@6b {
+		compatible = "st,lsm330dlc-gyro";
+		reg = <0x6b>;
+		interrupt-parent = <&gpx0>;
+		interrupts = <6 IRQ_TYPE_EDGE_RISING>;
+		pinctrl-0 = <&gyro_data_enable &gyro_irq>;
+		pinctrl-names = "default";
+		mount-matrix =	"1",  "0",  "0",
+				"0", "-1",  "0",
+				"0",  "0", "-1";
+	};
+};
+
 &i2c_3 {
 	samsung,i2c-sda-delay = <100>;
 	samsung,i2c-slave-addr = <0x10>;
@@ -844,6 +877,12 @@
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
 	};
 
+	gyro_data_enable: gyro-data-enable-pins {
+		samsung,pins = "gpl2-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
+	};
+
 	uart_sel: uart-sel-pins {
 		samsung,pins = "gpl2-7";
 		samsung,pin-function = <EXYNOS_PIN_FUNC_OUTPUT>;
@@ -894,12 +933,24 @@
 		samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
 	};
 
+	accelerometer_irq: accelerometer-irq-pins {
+		samsung,pins = "gpx0-0";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_INPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
 	stmpe_adc_irq: stmpe-adc-irq-pins {
 		samsung,pins = "gpx0-1";
 		samsung,pin-function = <EXYNOS_PIN_FUNC_INPUT>;
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
 	};
 
+	gyro_irq: gyro-irq-pins {
+		samsung,pins = "gpx0-6";
+		samsung,pin-function = <EXYNOS_PIN_FUNC_INPUT>;
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
+
 	max77686_irq: max77686-irq-pins {
 		samsung,pins = "gpx0-7";
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
diff --git a/arch/arm/boot/dts/samsung/exynos5420-galaxy-tab-common.dtsi b/arch/arm/boot/dts/samsung/exynos5420-galaxy-tab-common.dtsi
index f525b2f5e4e0..246040967082 100644
--- a/arch/arm/boot/dts/samsung/exynos5420-galaxy-tab-common.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos5420-galaxy-tab-common.dtsi
@@ -30,6 +30,7 @@
 
 	aliases {
 		mmc0 = &mmc_0;
+		mmc1 = &mmc_1;
 		mmc2 = &mmc_2;
 	};
 
@@ -39,7 +40,7 @@
 
 	memory@20000000 {
 		device_type = "memory";
-		reg = <0x20000000 0xc0000000>;
+		reg = <0x20000000 0xbfa00000>;
 	};
 
 	firmware@2073000 {
@@ -87,6 +88,13 @@
 			linux,code = <KEY_VOLUMEDOWN>;
 		};
 	};
+
+	mmc1_pwrseq: pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&gpy7 7 GPIO_ACTIVE_LOW>;
+		clocks = <&s2mps11_osc S2MPS11_CLK_BT>;
+		clock-names = "ext_clock";
+	};
 };
 
 &cci {
@@ -620,6 +628,25 @@
 	vqmmc-supply = <&ldo3_reg>;
 };
 
+/* WiFi */
+&mmc_1 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	card-detect-delay = <200>;
+	keep-power-in-suspend;
+	mmc-pwrseq = <&mmc1_pwrseq>;
+	non-removable;
+	pinctrl-0 = <&sd1_clk>, <&sd1_cmd>, <&sd1_int>, <&sd1_bus1>,
+		    <&sd1_bus4>, <&wifi_en>;
+	pinctrl-names = "default";
+	vqmmc-supply = <&ldo2_reg>;
+	samsung,dw-mshc-ciu-div = <1>;
+	samsung,dw-mshc-ddr-timing = <0 2>;
+	samsung,dw-mshc-sdr-timing = <0 1>;
+	status = "okay";
+};
+
 /* External sdcard */
 &mmc_2 {
 	status = "okay";
@@ -649,6 +676,11 @@
 		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
 		samsung,pin-drv = <EXYNOS5420_PIN_DRV_LV1>;
 	};
+
+	wifi_en: wifi-en-pins {
+		samsung,pins = "gpy7-7";
+		samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+	};
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/samsung/exynos5420-peach-pit.dts b/arch/arm/boot/dts/samsung/exynos5420-peach-pit.dts
index 4e757b6e28e1..3759742d38ca 100644
--- a/arch/arm/boot/dts/samsung/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/samsung/exynos5420-peach-pit.dts
@@ -967,6 +967,7 @@
 		reg = <0>;
 		spi-max-frequency = <3125000>;
 		google,has-vbc-nvram;
+		wakeup-source;
 
 		controller-data {
 			samsung,spi-feedback-delay = <1>;
diff --git a/arch/arm/boot/dts/samsung/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/samsung/exynos5422-odroidxu3-common.dtsi
index b4a851aa8881..4a4c55a4beb3 100644
--- a/arch/arm/boot/dts/samsung/exynos5422-odroidxu3-common.dtsi
+++ b/arch/arm/boot/dts/samsung/exynos5422-odroidxu3-common.dtsi
@@ -55,7 +55,7 @@
 	thermal-zones {
 		cpu0_thermal: cpu0-thermal {
 			thermal-sensors = <&tmu_cpu0>;
-			polling-delay-passive = <250>;
+			polling-delay-passive = <0>;
 			polling-delay = <0>;
 			trips {
 				cpu0_alert0: cpu-alert-0 {
@@ -78,12 +78,6 @@
 					hysteresis = <0>; /* millicelsius */
 					type = "critical";
 				};
-				/*
-				 * Exynos542x supports only 4 trip-points
-				 * so for these polling mode is required.
-				 * Start polling at temperature level of last
-				 * interrupt-driven trip: cpu0_alert2
-				 */
 				cpu0_alert3: cpu-alert-3 {
 					temperature = <70000>; /* millicelsius */
 					hysteresis = <10000>; /* millicelsius */
@@ -144,7 +138,7 @@
 		};
 		cpu1_thermal: cpu1-thermal {
 			thermal-sensors = <&tmu_cpu1>;
-			polling-delay-passive = <250>;
+			polling-delay-passive = <0>;
 			polling-delay = <0>;
 			trips {
 				cpu1_alert0: cpu-alert-0 {
@@ -217,7 +211,7 @@
 		};
 		cpu2_thermal: cpu2-thermal {
 			thermal-sensors = <&tmu_cpu2>;
-			polling-delay-passive = <250>;
+			polling-delay-passive = <0>;
 			polling-delay = <0>;
 			trips {
 				cpu2_alert0: cpu-alert-0 {
@@ -290,7 +284,7 @@
 		};
 		cpu3_thermal: cpu3-thermal {
 			thermal-sensors = <&tmu_cpu3>;
-			polling-delay-passive = <250>;
+			polling-delay-passive = <0>;
 			polling-delay = <0>;
 			trips {
 				cpu3_alert0: cpu-alert-0 {
@@ -363,7 +357,7 @@
 		};
 		gpu_thermal: gpu-thermal {
 			thermal-sensors = <&tmu_gpu>;
-			polling-delay-passive = <250>;
+			polling-delay-passive = <0>;
 			polling-delay = <0>;
 			trips {
 				gpu_alert0: gpu-alert-0 {
diff --git a/arch/arm/boot/dts/samsung/exynos5800-peach-pi.dts b/arch/arm/boot/dts/samsung/exynos5800-peach-pi.dts
index f91bc4ae008e..9bbbdce9103a 100644
--- a/arch/arm/boot/dts/samsung/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/samsung/exynos5800-peach-pi.dts
@@ -949,6 +949,7 @@
 		reg = <0>;
 		spi-max-frequency = <3125000>;
 		google,has-vbc-nvram;
+		wakeup-source;
 
 		controller-data {
 			samsung,spi-feedback-delay = <1>;
diff --git a/arch/arm/boot/dts/st/Makefile b/arch/arm/boot/dts/st/Makefile
index 7892ad69b441..9fedd6776208 100644
--- a/arch/arm/boot/dts/st/Makefile
+++ b/arch/arm/boot/dts/st/Makefile
@@ -23,6 +23,7 @@ dtb-$(CONFIG_ARCH_STM32) += \
 	stm32f469-disco.dtb \
 	stm32f746-disco.dtb \
 	stm32f769-disco.dtb \
+	stm32f769-disco-mb1166-reva09.dtb \
 	stm32429i-eval.dtb \
 	stm32746g-eval.dtb \
 	stm32h743i-eval.dtb \
diff --git a/arch/arm/boot/dts/st/stih407-pinctrl.dtsi b/arch/arm/boot/dts/st/stih407-pinctrl.dtsi
index 7815669fe813..dcb821f567fa 100644
--- a/arch/arm/boot/dts/st/stih407-pinctrl.dtsi
+++ b/arch/arm/boot/dts/st/stih407-pinctrl.dtsi
@@ -462,14 +462,14 @@
 			serial0 {
 				pinctrl_serial0: serial0-0 {
 					st,pins {
-						tx =  <&pio17 0 ALT1 OUT>;
-						rx =  <&pio17 1 ALT1 IN>;
+						tx = <&pio17 0 ALT1 OUT>;
+						rx = <&pio17 1 ALT1 IN>;
 					};
 				};
 				pinctrl_serial0_hw_flowctrl: serial0-0_hw_flowctrl {
 					st,pins {
-						tx =  <&pio17 0 ALT1 OUT>;
-						rx =  <&pio17 1 ALT1 IN>;
+						tx = <&pio17 0 ALT1 OUT>;
+						rx = <&pio17 1 ALT1 IN>;
 						cts = <&pio17 2 ALT1 IN>;
 						rts = <&pio17 3 ALT1 OUT>;
 					};
diff --git a/arch/arm/boot/dts/st/stm32429i-eval.dts b/arch/arm/boot/dts/st/stm32429i-eval.dts
index 576235ec3c51..afa417b34b25 100644
--- a/arch/arm/boot/dts/st/stm32429i-eval.dts
+++ b/arch/arm/boot/dts/st/stm32429i-eval.dts
@@ -222,7 +222,6 @@
 		reg = <0x42>;
 		interrupts = <8 3>;
 		interrupt-parent = <&gpioi>;
-		interrupt-controller;
 		wakeup-source;
 
 		stmpegpio: stmpe_gpio {
diff --git a/arch/arm/boot/dts/st/stm32f769-disco-mb1166-reva09.dts b/arch/arm/boot/dts/st/stm32f769-disco-mb1166-reva09.dts
new file mode 100644
index 000000000000..ff7ff32371d0
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32f769-disco-mb1166-reva09.dts
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Dario Binacchi <dario.binacchi@amarulasolutions.com>
+ */
+
+#include "stm32f769-disco.dts"
+
+&panel0 {
+	compatible = "frida,frd400b25025", "novatek,nt35510";
+	vddi-supply = <&vcc_3v3>;
+	vdd-supply = <&vcc_3v3>;
+	/delete-property/power-supply;
+};
diff --git a/arch/arm/boot/dts/st/stm32f769-disco.dts b/arch/arm/boot/dts/st/stm32f769-disco.dts
index 5d12ae25b327..52c5baf58ab9 100644
--- a/arch/arm/boot/dts/st/stm32f769-disco.dts
+++ b/arch/arm/boot/dts/st/stm32f769-disco.dts
@@ -41,7 +41,7 @@
  */
 
 /dts-v1/;
-#include "stm32f746.dtsi"
+#include "stm32f769.dtsi"
 #include "stm32f769-pinctrl.dtsi"
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/gpio/gpio.h>
@@ -60,6 +60,19 @@
 		reg = <0xC0000000 0x1000000>;
 	};
 
+	reserved-memory {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		linux,dma {
+			compatible = "shared-dma-pool";
+			linux,dma-default;
+			no-map;
+			size = <0x100000>;
+		};
+	};
+
 	aliases {
 		serial0 = &usart1;
 	};
@@ -92,9 +105,9 @@
 		clock-names = "main_clk";
 	};
 
-	mmc_vcard: mmc_vcard {
+	vcc_3v3: vcc-3v3 {
 		compatible = "regulator-fixed";
-		regulator-name = "mmc_vcard";
+		regulator-name = "vcc_3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
@@ -114,6 +127,45 @@
 	clock-frequency = <25000000>;
 };
 
+&dsi {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			dsi_in: endpoint {
+				remote-endpoint = <&ltdc_out_dsi>;
+			};
+		};
+
+		port@1 {
+			reg = <1>;
+			dsi_out: endpoint {
+				remote-endpoint = <&dsi_panel_in>;
+			};
+		};
+	};
+
+	panel0: panel@0 {
+		compatible = "orisetech,otm8009a";
+		reg = <0>; /* dsi virtual channel (0..3) */
+		reset-gpios = <&gpioj 15 GPIO_ACTIVE_LOW>;
+		power-supply = <&vcc_3v3>;
+		status = "okay";
+
+		port {
+			dsi_panel_in: endpoint {
+				remote-endpoint = <&dsi_out>;
+			};
+		};
+	};
+};
+
 &i2c1 {
 	pinctrl-0 = <&i2c1_pins_b>;
 	pinctrl-names = "default";
@@ -122,13 +174,23 @@
 	status = "okay";
 };
 
+&ltdc {
+	status = "okay";
+
+	port {
+		ltdc_out_dsi: endpoint {
+			remote-endpoint = <&dsi_in>;
+		};
+	};
+};
+
 &rtc {
 	status = "okay";
 };
 
 &sdio2 {
 	status = "okay";
-	vmmc-supply = <&mmc_vcard>;
+	vmmc-supply = <&vcc_3v3>;
 	cd-gpios = <&gpioi 15 GPIO_ACTIVE_LOW>;
 	broken-cd;
 	pinctrl-names = "default", "opendrain", "sleep";
diff --git a/arch/arm/boot/dts/st/stm32f769.dtsi b/arch/arm/boot/dts/st/stm32f769.dtsi
new file mode 100644
index 000000000000..4e7d9032149c
--- /dev/null
+++ b/arch/arm/boot/dts/st/stm32f769.dtsi
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Dario Binacchi <dario.binacchi@amarulasolutions.com>
+ */
+
+#include "stm32f746.dtsi"
+
+/ {
+	soc {
+		dsi: dsi@40016c00 {
+			compatible = "st,stm32-dsi";
+			reg = <0x40016c00 0x800>;
+			clocks = <&rcc 1 CLK_F769_DSI>, <&clk_hse>;
+			clock-names = "pclk", "ref";
+			resets = <&rcc STM32F7_APB2_RESET(DSI)>;
+			reset-names = "apb";
+			status = "disabled";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/st/stm32mp131.dtsi b/arch/arm/boot/dts/st/stm32mp131.dtsi
index b04d24c939c3..3900f32da797 100644
--- a/arch/arm/boot/dts/st/stm32mp131.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp131.dtsi
@@ -1315,6 +1315,13 @@
 			status = "disabled";
 		};
 
+		crc1: crc@58009000 {
+			compatible = "st,stm32f7-crc";
+			reg = <0x58009000 0x400>;
+			clocks = <&rcc CRC1>;
+			status = "disabled";
+		};
+
 		usbh_ohci: usb@5800c000 {
 			compatible = "generic-ohci";
 			reg = <0x5800c000 0x1000>;
diff --git a/arch/arm/boot/dts/st/stm32mp135f-dk.dts b/arch/arm/boot/dts/st/stm32mp135f-dk.dts
index eea740d097c7..52171214a308 100644
--- a/arch/arm/boot/dts/st/stm32mp135f-dk.dts
+++ b/arch/arm/boot/dts/st/stm32mp135f-dk.dts
@@ -93,6 +93,14 @@
 	};
 };
 
+&crc1 {
+	status = "okay";
+};
+
+&cryp {
+	status = "okay";
+};
+
 &i2c1 {
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&i2c1_pins_a>;
diff --git a/arch/arm/boot/dts/st/stm32mp157.dtsi b/arch/arm/boot/dts/st/stm32mp157.dtsi
index 6197d878894d..97cd24227cef 100644
--- a/arch/arm/boot/dts/st/stm32mp157.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp157.dtsi
@@ -20,7 +20,7 @@
 		dsi: dsi@5a000000 {
 			compatible = "st,stm32-dsi";
 			reg = <0x5a000000 0x800>;
-			clocks = <&rcc DSI_K>, <&clk_hse>, <&rcc DSI_PX>;
+			clocks = <&rcc DSI>, <&clk_hse>, <&rcc DSI_PX>;
 			clock-names = "pclk", "ref", "px_clk";
 			phy-dsi-supply = <&reg18>;
 			resets = <&rcc DSI_R>;
diff --git a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
index ce5937270aa1..306e1bc2a514 100644
--- a/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157a-dk1-scmi.dts
@@ -30,7 +30,7 @@
 };
 
 &dsi {
-	clocks = <&rcc DSI_K>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
+	clocks = <&rcc DSI>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
 };
 
 &gpioz {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
index c20a73841c1f..956da5f26c1c 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-dk2-scmi.dts
@@ -36,7 +36,7 @@
 
 &dsi {
 	phy-dsi-supply = <&scmi_reg18>;
-	clocks = <&rcc DSI_K>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
+	clocks = <&rcc DSI>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
 };
 
 &gpioz {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
index 510cca5acb79..7a701f7ef0c7 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-dk2.dts
@@ -64,7 +64,6 @@
 		reg = <0x38>;
 		interrupts = <2 2>;
 		interrupt-parent = <&gpiof>;
-		interrupt-controller;
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <800>;
 		status = "okay";
diff --git a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
index 5e2eaf57ce22..8e4b0db198c2 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-ed1-scmi.dts
@@ -35,7 +35,7 @@
 };
 
 &dsi {
-	clocks = <&rcc DSI_K>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
+	clocks = <&rcc DSI>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
 };
 
 &gpioz {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
index 3226fb945a8e..72b9cab2d990 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-ev1-scmi.dts
@@ -36,7 +36,7 @@
 
 &dsi {
 	phy-dsi-supply = <&scmi_reg18>;
-	clocks = <&rcc DSI_K>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
+	clocks = <&rcc DSI>, <&scmi_clk CK_SCMI_HSE>, <&rcc DSI_PX>;
 };
 
 &gpioz {
diff --git a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts
index 8a34d15e9005..4cc177031661 100644
--- a/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts
+++ b/arch/arm/boot/dts/st/stm32mp157c-lxa-tac-gen2.dts
@@ -148,7 +148,7 @@
 		compatible = "ti,lmp92064";
 		reg = <0>;
 
-		reset-gpios = <&gpioa 4 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpioa 4 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 		shunt-resistor-micro-ohms = <15000>;
 		spi-max-frequency = <5000000>;
 		vdd-supply = <&reg_pb_3v3>;
diff --git a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
index fc3a2386dbb9..cfaf8adde319 100644
--- a/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp15xc-lxa-tac.dtsi
@@ -409,7 +409,7 @@ baseboard_eeprom: &sip_eeprom {
 &spi2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&spi2_pins_c>;
-	cs-gpios = <&gpiof 12 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpiof 12 (GPIO_ACTIVE_LOW | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 };
 
@@ -471,6 +471,10 @@ baseboard_eeprom: &sip_eeprom {
 		interrupt-parent = <&gpioa>;
 		interrupts = <6 IRQ_TYPE_EDGE_RISING>;
 
+		/* Reduce RGMII EMI emissions by reducing drive strength */
+		microchip,hi-drive-strength-microamp = <2000>;
+		microchip,lo-drive-strength-microamp = <8000>;
+
 		ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/arm/boot/dts/ti/davinci/da850.dtsi b/arch/arm/boot/dts/ti/davinci/da850.dtsi
index f759fdfe1b10..1d3fb5397ce3 100644
--- a/arch/arm/boot/dts/ti/davinci/da850.dtsi
+++ b/arch/arm/boot/dts/ti/davinci/da850.dtsi
@@ -536,7 +536,7 @@
 			reg = <0x40000 0x1000>;
 			cap-sd-highspeed;
 			cap-mmc-highspeed;
-			interrupts = <16>;
+			interrupts = <16>, <17>;
 			dmas = <&edma0 16 0>, <&edma0 17 0>;
 			dma-names = "rx", "tx";
 			clocks = <&psc0 5>;
@@ -566,7 +566,7 @@
 			reg = <0x21b000 0x1000>;
 			cap-sd-highspeed;
 			cap-mmc-highspeed;
-			interrupts = <72>;
+			interrupts = <72>, <73>;
 			dmas = <&edma1 28 0>, <&edma1 29 0>;
 			dma-names = "rx", "tx";
 			clocks = <&psc1 18>;
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-clocks.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-clocks.dtsi
index 0397c3423d2d..20bab90ee0ba 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-clocks.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for Keystone 2 clock tree
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 clocks {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2e-clocks.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2e-clocks.dtsi
index cf30e007fea3..74720dbf3110 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2e-clocks.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Edison SoC specific device tree
  *
- * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 clocks {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2e-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2e-evm.dts
index 6978d6a362f3..58099ce8d449 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2e-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2e-evm.dts
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Edison EVM device tree
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
index 5c88a90903b8..e586350ae4dc 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2e-netcp.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for Keystone 2 Edison Netcp driver
  *
- * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2e.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2e.dtsi
index 65c32946c522..662aa33cba11 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2e.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2e.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Edison soc device tree
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
index f0ddbbcdc972..bf5f67d70235 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g-evm.dts
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for K2G EVM
  *
- * Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2016-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g-ice.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2g-ice.dts
index 6ceb0d5c6388..264e1e0d23c8 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g-ice.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g-ice.dts
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for K2G Industrial Communication Engine EVM
  *
- * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
index 7109ca031617..974c8f2fa740 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g-netcp.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for K2G Netcp driver
  *
- * Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 qmss: qmss@4020000 {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2g.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2g.dtsi
index 102d59694d90..790b29ab0fa2 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2g.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2g.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for K2G SOC
  *
- * Copyright (C) 2016-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2016-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-clocks.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-clocks.dtsi
index 4ba6912176ef..3ca4722087c9 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-clocks.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Kepler/Hawking SoC clock nodes
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 clocks {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
index 8dfb54295027..b824fad9a4ec 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-evm.dts
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Kepler/Hawking EVM device tree
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
index c2ee775eab6a..3ab1b5d6f9bc 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk-netcp.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for Keystone 2 Hawking Netcp driver
  *
- * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2hk.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2hk.dtsi
index da6d3934c2e8..4fdf4b30384f 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2hk.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2hk.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Kepler/Hawking soc specific device tree
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2l-clocks.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2l-clocks.dtsi
index 635528064dea..fcfc2fb6cc2d 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2l-clocks.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 lamarr SoC clock nodes
  *
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 clocks {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2l-evm.dts b/arch/arm/boot/dts/ti/keystone/keystone-k2l-evm.dts
index be619e39a16f..ccda63ab12fe 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2l-evm.dts
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2l-evm.dts
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Lamarr EVM device tree
  *
- * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
index 1afebd7458c1..b8f880faaa31 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2l-netcp.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for Keystone 2 Lamarr Netcp driver
  *
- * Copyright (C) 2015-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2015-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 qmss: qmss@2a40000 {
diff --git a/arch/arm/boot/dts/ti/keystone/keystone-k2l.dtsi b/arch/arm/boot/dts/ti/keystone/keystone-k2l.dtsi
index 2062fe561642..330b437b667f 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone-k2l.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone-k2l.dtsi
@@ -2,7 +2,7 @@
 /*
  * Keystone 2 Lamarr SoC specific device tree
  *
- * Copyright (C) 2014-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/reset/ti-syscon.h>
diff --git a/arch/arm/boot/dts/ti/keystone/keystone.dtsi b/arch/arm/boot/dts/ti/keystone/keystone.dtsi
index 1fd04bb37a15..ff16428860a9 100644
--- a/arch/arm/boot/dts/ti/keystone/keystone.dtsi
+++ b/arch/arm/boot/dts/ti/keystone/keystone.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir2110.dts b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir2110.dts
index ea5882ed7010..f82d2231dfaa 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir2110.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir2110.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir3220.dts b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir3220.dts
index ea4f8dde6424..74a2191af146 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir3220.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir3220.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir5221.dts b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir5221.dts
index ec914f27d11d..723ff88f76ac 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-baltos-ir5221.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-baltos-ir5221.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-baltos-leds.dtsi b/arch/arm/boot/dts/ti/omap/am335x-baltos-leds.dtsi
index 6a52e42b9e81..049fd8e1b40f 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-baltos-leds.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-baltos-leds.dtsi
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /*#include "am33xx.dtsi"*/
diff --git a/arch/arm/boot/dts/ti/omap/am335x-baltos.dtsi b/arch/arm/boot/dts/ti/omap/am335x-baltos.dtsi
index c14d5b70c72f..a4beb718559c 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-baltos.dtsi
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 #include "am33xx.dtsi"
diff --git a/arch/arm/boot/dts/ti/omap/am335x-base0033.dts b/arch/arm/boot/dts/ti/omap/am335x-base0033.dts
index eba843e22ea1..46078af4b7a3 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-base0033.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-base0033.dts
@@ -2,7 +2,7 @@
 /*
  * am335x-base0033.dts - Device Tree file for IGEP AQUILA EXPANSION
  *
- * Copyright (C) 2013 ISEE 2007 SL - http://www.isee.biz
+ * Copyright (C) 2013 ISEE 2007 SL - https://www.isee.biz
  */
 
 #include "am335x-igep0033.dtsi"
diff --git a/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi b/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi
index 96451c8a815c..2d0216840ff5 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-bone-common.dtsi
@@ -289,8 +289,8 @@
 	 * For details, see linux-omap mailing list May 2015 thread
 	 *	[PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller
 	 * In particular, messages:
-	 *	http://www.spinics.net/lists/linux-omap/msg118585.html
-	 *	http://www.spinics.net/lists/linux-omap/msg118615.html
+	 *	https://www.spinics.net/lists/linux-omap/msg118585.html
+	 *	https://www.spinics.net/lists/linux-omap/msg118615.html
 	 *
 	 * You can override this later with
 	 *	&tps {  /delete-property/ ti,pmic-shutdown-controller;  }
diff --git a/arch/arm/boot/dts/ti/omap/am335x-cm-t335.dts b/arch/arm/boot/dts/ti/omap/am335x-cm-t335.dts
index 72990e7ffe10..06767ea164b5 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-cm-t335.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-cm-t335.dts
@@ -2,7 +2,7 @@
 /*
  * am335x-cm-t335.dts - Device Tree file for Compulab CM-T335
  *
- * Copyright (C) 2014 - 2015 CompuLab Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2014 - 2015 CompuLab Ltd. - https://www.compulab.co.il/
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts b/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts
index 57f78846c42d..eba888dcd60e 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-evmsk.dts
@@ -5,7 +5,7 @@
 
 /*
  * AM335x Starter Kit
- * http://www.ti.com/tool/tmdssk3358
+ * https://www.ti.com/tool/tmdssk3358
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-guardian.dts b/arch/arm/boot/dts/ti/omap/am335x-guardian.dts
index 205fe0ed7352..56e5d954a490 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-guardian.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-guardian.dts
@@ -303,8 +303,8 @@
    * For details, see linux-omap mailing list May 2015 thread
    *  [PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller
    * In particular, messages:
-   *  http://www.spinics.net/lists/linux-omap/msg118585.html
-   *  http://www.spinics.net/lists/linux-omap/msg118615.html
+   *  https://www.spinics.net/lists/linux-omap/msg118585.html
+   *  https://www.spinics.net/lists/linux-omap/msg118615.html
    *
    * You can override this later with
    *  &tps {  /delete-property/ ti,pmic-shutdown-controller;  }
diff --git a/arch/arm/boot/dts/ti/omap/am335x-icev2.dts b/arch/arm/boot/dts/ti/omap/am335x-icev2.dts
index 3c4228927f56..6f0f4fba043b 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-icev2.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-icev2.dts
@@ -5,7 +5,7 @@
 
 /*
  * AM335x ICE V2 board
- * http://www.ti.com/tool/tmdsice3359
+ * https://www.ti.com/tool/tmdsice3359
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-igep0033.dtsi b/arch/arm/boot/dts/ti/omap/am335x-igep0033.dtsi
index e85c33fd42f0..c7a4a5476489 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-igep0033.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-igep0033.dtsi
@@ -2,7 +2,7 @@
 /*
  * am335x-igep0033.dtsi - Device Tree file for IGEP COM AQUILA AM335x
  *
- * Copyright (C) 2013 ISEE 2007 SL - http://www.isee.biz
+ * Copyright (C) 2013 ISEE 2007 SL - https://www.isee.biz
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myc.dtsi b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myc.dtsi
index 584599269217..9c9359844a20 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myc.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myc.dtsi
@@ -2,7 +2,7 @@
 /* SPDX-FileCopyrightText: Alexander Shiyan, <shc_work@mail.ru> */
 
 /* Based on code by myc_c335x.dts, MYiRtech.com */
-/* Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ */
+/* Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ */
 
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts
index d3bba79b9358..fd91a3c01a63 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-myirtech-myd.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /* SPDX-FileCopyrightText: Alexander Shiyan, <shc_work@mail.ru> */
 /* Based on code by myd_c335x.dts, MYiRtech.com */
-/* Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ */
+/* Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ */
 
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/am335x-nano.dts b/arch/arm/boot/dts/ti/omap/am335x-nano.dts
index a475c0d91306..26b5510cb3d1 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-nano.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-nano.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2013 Newflow Ltd - http://www.newflow.co.uk/
+ * Copyright (C) 2013 Newflow Ltd - https://www.newflow.co.uk/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/am335x-netcan-plus-1xx.dts b/arch/arm/boot/dts/ti/omap/am335x-netcan-plus-1xx.dts
index f7fad48e36ed..546e88f8fbad 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-netcan-plus-1xx.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-netcan-plus-1xx.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts
index 76751a324ad7..f66d57bb685e 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-2xx.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-8xx.dts b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-8xx.dts
index 5a9fcec040fa..5fb2c629f35c 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-8xx.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-netcom-plus-8xx.dts
@@ -5,7 +5,7 @@
 
 /*
  * VScom OnRISC
- * http://www.vscom.de
+ * https://www.vscom.de
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts b/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts
index 3c9444e98c14..f38f5bff2b96 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-pdu001.dts
@@ -3,7 +3,7 @@
  *
  * EETS GmbH PDU001 board device tree file
  *
- * Copyright (C) 2018 EETS GmbH - http://www.eets.ch/
+ * Copyright (C) 2018 EETS GmbH - https://www.eets.ch/
  *
  * Copyright (C) 2011, Texas Instruments, Incorporated - https://www.ti.com/
  *
diff --git a/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-extended-wifi.dts b/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-extended-wifi.dts
index 5522759def26..7c9f65126c63 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-extended-wifi.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-extended-wifi.dts
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2021 Sancloud Ltd
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-lite.dts b/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-lite.dts
index b1b400226d83..c6c96f6182a8 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-lite.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-sancloud-bbe-lite.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/
  * Copyright (C) 2021 SanCloud Ltd
  */
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am335x-sbc-t335.dts b/arch/arm/boot/dts/ti/omap/am335x-sbc-t335.dts
index 596774c84744..2841e95d9a09 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-sbc-t335.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-sbc-t335.dts
@@ -2,7 +2,7 @@
 /*
  * am335x-sbc-t335.dts - Device Tree file for Compulab SBC-T335
  *
- * Copyright (C) 2014 - 2015 CompuLab Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2014 - 2015 CompuLab Ltd. - https://www.compulab.co.il/
  */
 
 #include "am335x-cm-t335.dts"
diff --git a/arch/arm/boot/dts/ti/omap/am335x-sl50.dts b/arch/arm/boot/dts/ti/omap/am335x-sl50.dts
index 1115c812f6c8..757ebd96b3f0 100644
--- a/arch/arm/boot/dts/ti/omap/am335x-sl50.dts
+++ b/arch/arm/boot/dts/ti/omap/am335x-sl50.dts
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2015 Toby Churchill - http://www.toby-churchill.com/
+ * Copyright (C) 2015 Toby Churchill - https://www.toby-churchill.com/
+ * url above is defunct
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
index 5b9e01a8aa5d..989d5a6edeed 100644
--- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi
@@ -640,10 +640,11 @@
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x1000000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap3630-gpu", "img,powervr-sgx530";
+				reg = <0x0 0x10000>; /* 64kB */
+				interrupts = <37>;
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/ti/omap/am3517.dtsi b/arch/arm/boot/dts/ti/omap/am3517.dtsi
index 77e58e686fb1..19aad715dff7 100644
--- a/arch/arm/boot/dts/ti/omap/am3517.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am3517.dtsi
@@ -162,12 +162,13 @@
 			clock-names = "fck", "ick";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0 0x50000000 0x4000>;
+			ranges = <0 0x50000000 0x10000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap3430-gpu", "img,powervr-sgx530";
+				reg = <0x0 0x10000>; /* 64kB */
+				interrupts = <21>;
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/ti/omap/am4372.dtsi b/arch/arm/boot/dts/ti/omap/am4372.dtsi
index 9d2c064534f7..5fd1b380ece6 100644
--- a/arch/arm/boot/dts/ti/omap/am4372.dtsi
+++ b/arch/arm/boot/dts/ti/omap/am4372.dtsi
@@ -719,6 +719,12 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x1000000>;
+
+			gpu@0 {
+				compatible = "ti,omap3630-gpu", "img,powervr-sgx530";
+				reg = <0x0 0x10000>; /* 64kB */
+				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/ti/omap/am437x-cm-t43.dts b/arch/arm/boot/dts/ti/omap/am437x-cm-t43.dts
index 9ec75d03eaff..172516a7667e 100644
--- a/arch/arm/boot/dts/ti/omap/am437x-cm-t43.dts
+++ b/arch/arm/boot/dts/ti/omap/am437x-cm-t43.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2015 CompuLab, Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2015 CompuLab, Ltd. - https://www.compulab.co.il/
  */
 
 /dts-v1/;
diff --git a/arch/arm/boot/dts/ti/omap/am437x-sbc-t43.dts b/arch/arm/boot/dts/ti/omap/am437x-sbc-t43.dts
index 34a5407bee15..5ec57dcb0659 100644
--- a/arch/arm/boot/dts/ti/omap/am437x-sbc-t43.dts
+++ b/arch/arm/boot/dts/ti/omap/am437x-sbc-t43.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2015 CompuLab, Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2015 CompuLab, Ltd. - https://www.compulab.co.il/
  */
 
 #include "am437x-cm-t43.dts"
diff --git a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
index c8e55642f9c6..eb1ec85aba28 100644
--- a/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
+++ b/arch/arm/boot/dts/ti/omap/am5729-beagleboneai.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2014-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2014-2019 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -415,7 +415,6 @@
 		reg = <0x41>;
 		interrupts = <30 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&gpio2>;
-		interrupt-controller;
 		id = <0>;
 		blocks = <0x5>;
 		irq-trigger = <0x1>;
diff --git a/arch/arm/boot/dts/ti/omap/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/ti/omap/am57xx-cl-som-am57x.dts
index 4fd831ff206f..d6e3152b02f7 100644
--- a/arch/arm/boot/dts/ti/omap/am57xx-cl-som-am57x.dts
+++ b/arch/arm/boot/dts/ti/omap/am57xx-cl-som-am57x.dts
@@ -2,7 +2,7 @@
 /*
  * Support for CompuLab CL-SOM-AM57x System-on-Module
  *
- * Copyright (C) 2015 CompuLab Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2015 CompuLab Ltd. - https://www.compulab.co.il/
  * Author: Dmitry Lifshitz <lifshitz@compulab.co.il>
  */
 
diff --git a/arch/arm/boot/dts/ti/omap/am57xx-sbc-am57x.dts b/arch/arm/boot/dts/ti/omap/am57xx-sbc-am57x.dts
index 363115afb0a4..64675f4edb60 100644
--- a/arch/arm/boot/dts/ti/omap/am57xx-sbc-am57x.dts
+++ b/arch/arm/boot/dts/ti/omap/am57xx-sbc-am57x.dts
@@ -2,7 +2,7 @@
 /*
  * Support for CompuLab SBC-AM57x single board computer
  *
- * Copyright (C) 2015 CompuLab Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2015 CompuLab Ltd. - https://www.compulab.co.il/
  * Author: Dmitry Lifshitz <lifshitz@compulab.co.il>
  */
 
diff --git a/arch/arm/boot/dts/ti/omap/compulab-sb-som.dtsi b/arch/arm/boot/dts/ti/omap/compulab-sb-som.dtsi
index f5e6216718d8..8a8fa1b2b26c 100644
--- a/arch/arm/boot/dts/ti/omap/compulab-sb-som.dtsi
+++ b/arch/arm/boot/dts/ti/omap/compulab-sb-som.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2015 CompuLab, Ltd. - http://www.compulab.co.il/
+ * Copyright (C) 2015 CompuLab, Ltd. - https://www.compulab.co.il/
  */
 
 / {
diff --git a/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi b/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi
index 5733e3a4ea8e..6e67d99832ac 100644
--- a/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7-l4.dtsi
@@ -80,7 +80,7 @@
 						};
 					};
 
-					phy_gmii_sel: phy-gmii-sel {
+					phy_gmii_sel: phy-gmii-sel@554 {
 						compatible = "ti,dra7xx-phy-gmii-sel";
 						reg = <0x554 0x4>;
 						#phy-cells = <1>;
diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi
index 6509c742fb58..164fa88c459e 100644
--- a/arch/arm/boot/dts/ti/omap/dra7.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi
@@ -638,7 +638,7 @@
 			};
 		};
 
-		abb_mpu: regulator-abb-mpu {
+		abb_mpu: regulator-abb-mpu@4ae07ddc {
 			compatible = "ti,abb-v3";
 			regulator-name = "abb_mpu";
 			#address-cells = <0>;
@@ -671,7 +671,7 @@
 			>;
 		};
 
-		abb_ivahd: regulator-abb-ivahd {
+		abb_ivahd: regulator-abb-ivahd@4ae07e34 {
 			compatible = "ti,abb-v3";
 			regulator-name = "abb_ivahd";
 			#address-cells = <0>;
@@ -704,7 +704,7 @@
 			>;
 		};
 
-		abb_dspeve: regulator-abb-dspeve {
+		abb_dspeve: regulator-abb-dspeve@4ae07e30 {
 			compatible = "ti,abb-v3";
 			regulator-name = "abb_dspeve";
 			#address-cells = <0>;
@@ -737,7 +737,7 @@
 			>;
 		};
 
-		abb_gpu: regulator-abb-gpu {
+		abb_gpu: regulator-abb-gpu@4ae07de4 {
 			compatible = "ti,abb-v3";
 			regulator-name = "abb_gpu";
 			#address-cells = <0>;
@@ -850,12 +850,19 @@
 					<SYSC_IDLE_SMART>;
 			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
 					<SYSC_IDLE_NO>,
-					<SYSC_IDLE_SMART>;
+					<SYSC_IDLE_SMART>,
+					<SYSC_IDLE_SMART_WKUP>;
 			clocks = <&gpu_clkctrl DRA7_GPU_CLKCTRL 0>;
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x2000000>;
+
+			gpu@0 {
+				compatible = "ti,am5728-gpu", "img,powervr-sgx544";
+				reg = <0x0 0x10000>; /* 64kB */
+				interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+			};
 		};
 
 		crossbar_mpu: crossbar@4a002a48 {
diff --git a/arch/arm/boot/dts/ti/omap/dra74x-p.dtsi b/arch/arm/boot/dts/ti/omap/dra74x-p.dtsi
index 006189dad7a7..bb5239ae164d 100644
--- a/arch/arm/boot/dts/ti/omap/dra74x-p.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra74x-p.dtsi
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2017 Texas Instruments Incorporated - https://www.ti.com/
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/boot/dts/ti/omap/dra7xx-clocks.dtsi b/arch/arm/boot/dts/ti/omap/dra7xx-clocks.dtsi
index 04a7a6d1d529..06466d36caa9 100644
--- a/arch/arm/boot/dts/ti/omap/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/ti/omap/dra7xx-clocks.dtsi
@@ -1685,7 +1685,7 @@
 		reg = <0x0558>;
 	};
 
-	sys_32k_ck: clock-sys-32k {
+	sys_32k_ck: clock-sys-32k@6c4 {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
 		clock-output-names = "sys_32k_ck";
diff --git a/arch/arm/boot/dts/ti/omap/omap34xx.dtsi b/arch/arm/boot/dts/ti/omap/omap34xx.dtsi
index fc7233ac183a..acdd0ee34421 100644
--- a/arch/arm/boot/dts/ti/omap/omap34xx.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap34xx.dtsi
@@ -164,12 +164,13 @@
 			clock-names = "fck", "ick";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0 0x50000000 0x4000>;
+			ranges = <0 0x50000000 0x10000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap3430-gpu", "img,powervr-sgx530";
+				reg = <0x0 0x10000>; /* 64kB */
+				interrupts = <21>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/ti/omap/omap36xx.dtsi b/arch/arm/boot/dts/ti/omap/omap36xx.dtsi
index e6d8070c1bf8..c3d79ecd56e3 100644
--- a/arch/arm/boot/dts/ti/omap/omap36xx.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap36xx.dtsi
@@ -211,10 +211,11 @@
 			#size-cells = <1>;
 			ranges = <0 0x50000000 0x2000000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap3630-gpu", "img,powervr-sgx530";
+				reg = <0x0 0x2000000>; /* 32MB */
+				interrupts = <21>;
+			};
 		};
 	};
 
diff --git a/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts b/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
index 24f7d0285f79..339e52ba3614 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-epson-embt2ws.dts
@@ -85,6 +85,7 @@
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; /* IRQ_SYS_1N cascaded to gic */
 		interrupt-controller;
 		#interrupt-cells = <1>;
+		system-power-controller;
 
 		rtc {
 			compatible = "ti,twl4030-rtc";
diff --git a/arch/arm/boot/dts/ti/omap/omap4-panda-common.dtsi b/arch/arm/boot/dts/ti/omap/omap4-panda-common.dtsi
index f528511c2537..97706d6296a6 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-panda-common.dtsi
@@ -408,6 +408,7 @@
 		reg = <0x48>;
 		/* IRQ# = 7 */
 		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; /* IRQ_SYS_1N cascaded to gic */
+		system-power-controller;
 	};
 
 	twl6040: twl@4b {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-sdp.dts b/arch/arm/boot/dts/ti/omap/omap4-sdp.dts
index b2cb93edbc3a..b535d24c6140 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-sdp.dts
+++ b/arch/arm/boot/dts/ti/omap/omap4-sdp.dts
@@ -439,7 +439,7 @@
 
 	/*
 	 * Ambient Light Sensor
-	 * http://www.rohm.com/products/databook/sensor/pdf/bh1780gli-e.pdf
+	 * https://www.rohm.com/products/databook/sensor/pdf/bh1780gli-e.pdf (defunct)
 	 */
 	bh1780@29 {
 		compatible = "rohm,bh1780";
diff --git a/arch/arm/boot/dts/ti/omap/omap4.dtsi b/arch/arm/boot/dts/ti/omap/omap4.dtsi
index 2bbff9032be3..559b2bfe4ca7 100644
--- a/arch/arm/boot/dts/ti/omap/omap4.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4.dtsi
@@ -501,10 +501,11 @@
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x2000000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap4430-gpu", "img,powervr-sgx540";
+				reg = <0x0 0x2000000>; /* 32MB */
+				interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+			};
 		};
 
 		/*
diff --git a/arch/arm/boot/dts/ti/omap/omap5-igep0050.dts b/arch/arm/boot/dts/ti/omap/omap5-igep0050.dts
index d4ca2e3a14dd..0368e32f67e7 100644
--- a/arch/arm/boot/dts/ti/omap/omap5-igep0050.dts
+++ b/arch/arm/boot/dts/ti/omap/omap5-igep0050.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2013 ISEE 2007 SL - http://www.isee.biz/
+ * Copyright (C) 2013 ISEE 2007 SL - https://www.isee.biz/
  */
 /dts-v1/;
 
diff --git a/arch/arm/boot/dts/ti/omap/omap5.dtsi b/arch/arm/boot/dts/ti/omap/omap5.dtsi
index bac6fa838793..6a66214ad0e2 100644
--- a/arch/arm/boot/dts/ti/omap/omap5.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap5.dtsi
@@ -453,10 +453,11 @@
 			#size-cells = <1>;
 			ranges = <0 0x56000000 0x2000000>;
 
-			/*
-			 * Closed source PowerVR driver, no child device
-			 * binding or driver in mainline
-			 */
+			gpu@0 {
+				compatible = "ti,omap5432-gpu", "img,powervr-sgx544";
+				reg = <0x0 0x2000000>; /* 32MB */
+				interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+			};
 		};
 
 		target-module@58000000 {
diff --git a/arch/arm/boot/dts/ti/omap/twl4030.dtsi b/arch/arm/boot/dts/ti/omap/twl4030.dtsi
index 93e07c18781b..a5d9c5738317 100644
--- a/arch/arm/boot/dts/ti/omap/twl4030.dtsi
+++ b/arch/arm/boot/dts/ti/omap/twl4030.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /*
diff --git a/arch/arm/boot/dts/ti/omap/twl6030.dtsi b/arch/arm/boot/dts/ti/omap/twl6030.dtsi
index 9d588cfaa5cb..8da969035c41 100644
--- a/arch/arm/boot/dts/ti/omap/twl6030.dtsi
+++ b/arch/arm/boot/dts/ti/omap/twl6030.dtsi
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /*
  * Integrated Power Management Chip
- * http://www.ti.com/lit/ds/symlink/twl6030.pdf
+ * https://www.ti.com/lit/ds/symlink/twl6030.pdf
  */
 &twl {
 	compatible = "ti,twl6030";
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index c98d5ff8a1ed..7ad48fdda1da 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -318,8 +318,11 @@ CONFIG_EXTCON_MAX77693=y
 CONFIG_EXTCON_MAX8997=y
 CONFIG_EXYNOS5422_DMC=y
 CONFIG_IIO=y
+CONFIG_IIO_ST_ACCEL_3AXIS=m
+# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set
 CONFIG_EXYNOS_ADC=y
 CONFIG_STMPE_ADC=y
+CONFIG_IIO_ST_GYRO_3AXIS=m
 CONFIG_CM36651=y
 CONFIG_AK8975=y
 CONFIG_SENSORS_ISL29018=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 0a90583f9f01..92d649a817b3 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -208,6 +208,7 @@ CONFIG_PINCTRL_IMX8MQ=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_MXC=y
 CONFIG_GPIO_SIOX=m
+CONFIG_GPIO_VF610=y
 CONFIG_GPIO_MAX732X=y
 CONFIG_GPIO_PCA953X=y
 CONFIG_GPIO_PCF857X=y
@@ -297,6 +298,7 @@ CONFIG_FB_MODE_HELPERS=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_L4F00242T03=y
 CONFIG_LCD_PLATFORM=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_GPIO=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index ecb3e286107a..b2955dcb5a53 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -183,6 +183,7 @@ CONFIG_PCIE_RCAR_HOST=y
 CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCI_LAYERSCAPE=y
 CONFIG_PCI_DRA7XX_EP=y
+CONFIG_PCI_KEYSTONE_HOST=y
 CONFIG_PCI_ENDPOINT=y
 CONFIG_PCI_ENDPOINT_CONFIGFS=y
 CONFIG_PCI_EPF_TEST=m
@@ -191,6 +192,7 @@ CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_OMAP_OCP2SCP=y
 CONFIG_ARM_SCMI_PROTOCOL=y
 CONFIG_RASPBERRYPI_FIRMWARE=y
+CONFIG_TI_SCI_PROTOCOL=y
 CONFIG_TRUSTED_FOUNDATIONS=y
 CONFIG_BCM47XX_NVRAM=y
 CONFIG_BCM47XX_SPROM=y
@@ -280,6 +282,8 @@ CONFIG_DWMAC_DWC_QOS_ETH=y
 CONFIG_TI_CPSW=y
 CONFIG_TI_CPSW_SWITCHDEV=y
 CONFIG_TI_CPTS=y
+CONFIG_TI_KEYSTONE_NETCP=y
+CONFIG_TI_KEYSTONE_NETCP_ETHSS=y
 CONFIG_XILINX_EMACLITE=y
 CONFIG_SFP=m
 CONFIG_BROADCOM_PHY=y
@@ -292,6 +296,8 @@ CONFIG_CAN_AT91=m
 CONFIG_CAN_FLEXCAN=m
 CONFIG_CAN_SUN4I=y
 CONFIG_CAN_XILINXCAN=y
+CONFIG_CAN_C_CAN=m
+CONFIG_CAN_C_CAN_PLATFORM=m
 CONFIG_CAN_RCAR=m
 CONFIG_CAN_MCP251X=y
 CONFIG_MDIO_MSCC_MIIM=m
@@ -335,6 +341,7 @@ CONFIG_INPUT_MISC=y
 CONFIG_INPUT_PM8941_PWRKEY=y
 CONFIG_INPUT_MAX77693_HAPTIC=m
 CONFIG_INPUT_MAX8997_HAPTIC=m
+CONFIG_INPUT_GPIO_DECODER=m
 CONFIG_INPUT_CPCAP_PWRBUTTON=m
 CONFIG_INPUT_AXP20X_PEK=m
 CONFIG_INPUT_DA9063_ONKEY=m
@@ -436,6 +443,7 @@ CONFIG_SPI_ATMEL_QUADSPI=m
 CONFIG_SPI_BCM2835=y
 CONFIG_SPI_BCM2835AUX=y
 CONFIG_SPI_CADENCE=y
+CONFIG_SPI_CADENCE_QUADSPI=y
 CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_FSL_QUADSPI=m
 CONFIG_SPI_GXP=m
@@ -769,6 +777,7 @@ CONFIG_FB_EFI=y
 CONFIG_FB_WM8505=y
 CONFIG_FB_SH_MOBILE_LCDC=y
 CONFIG_FB_SIMPLE=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 CONFIG_BACKLIGHT_AS3711=y
 CONFIG_BACKLIGHT_GPIO=y
@@ -1047,7 +1056,6 @@ CONFIG_KEYBOARD_NVEC=y
 CONFIG_SERIO_NVEC_PS2=y
 CONFIG_NVEC_POWER=y
 CONFIG_NVEC_PAZ00=y
-CONFIG_STAGING_BOARD=y
 CONFIG_CHROME_PLATFORMS=y
 CONFIG_CROS_EC=m
 CONFIG_CROS_EC_I2C=m
@@ -1073,6 +1081,7 @@ CONFIG_HWSPINLOCK_OMAP=y
 CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_OMAP2PLUS_MBOX=y
 CONFIG_BCM2835_MBOX=y
+CONFIG_TI_MESSAGE_MANAGER=y
 CONFIG_QCOM_APCS_IPC=y
 CONFIG_STM32_IPCC=m
 CONFIG_QCOM_IPCC=y
@@ -1133,11 +1142,15 @@ CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y
 CONFIG_ARCH_TEGRA_114_SOC=y
 CONFIG_ARCH_TEGRA_124_SOC=y
+CONFIG_SOC_TI=y
+CONFIG_KEYSTONE_NAVIGATOR_QMSS=y
+CONFIG_KEYSTONE_NAVIGATOR_DMA=y
 CONFIG_RASPBERRYPI_POWER=y
 CONFIG_QCOM_CPR=y
 CONFIG_QCOM_RPMHPD=y
 CONFIG_QCOM_RPMPD=y
 CONFIG_ROCKCHIP_PM_DOMAINS=y
+CONFIG_TI_SCI_PM_DOMAINS=y
 CONFIG_ARM_EXYNOS_BUS_DEVFREQ=m
 CONFIG_ARM_TEGRA_DEVFREQ=m
 CONFIG_DEVFREQ_EVENT_EXYNOS_NOCP=m
@@ -1150,6 +1163,8 @@ CONFIG_STM32_FMC2_EBI=y
 CONFIG_EXYNOS5422_DMC=m
 CONFIG_IIO=y
 CONFIG_IIO_SW_TRIGGER=y
+CONFIG_IIO_ST_ACCEL_3AXIS=m
+# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set
 CONFIG_ASPEED_ADC=m
 CONFIG_AT91_ADC=m
 CONFIG_AT91_SAMA5D2_ADC=m
@@ -1169,6 +1184,7 @@ CONFIG_IIO_CROS_EC_SENSORS_CORE=m
 CONFIG_IIO_CROS_EC_SENSORS=m
 CONFIG_STM32_DAC=m
 CONFIG_MPU3050_I2C=y
+CONFIG_IIO_ST_GYRO_3AXIS=m
 CONFIG_CM36651=m
 CONFIG_IIO_CROS_EC_LIGHT_PROX=m
 CONFIG_SENSORS_ISL29018=y
@@ -1193,10 +1209,13 @@ CONFIG_PWM_STM32=m
 CONFIG_PWM_STM32_LP=m
 CONFIG_PWM_SUN4I=y
 CONFIG_PWM_TEGRA=y
+CONFIG_PWM_TIECAP=m
 CONFIG_PWM_VT8500=y
 CONFIG_KEYSTONE_IRQ=y
 CONFIG_RESET_MCHP_SPARX5=y
 CONFIG_RESET_SCMI=y
+CONFIG_RESET_TI_SCI=m
+CONFIG_RESET_TI_SYSCON=m
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_SUN9I_USB=y
 CONFIG_PHY_BRCM_USB=m
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index c47a638172a8..091e1840933c 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -191,8 +191,6 @@ CONFIG_DW_DMAC=y
 CONFIG_RZN1_DMAMUX=y
 CONFIG_RCAR_DMAC=y
 CONFIG_RENESAS_USB_DMAC=y
-CONFIG_STAGING=y
-CONFIG_STAGING_BOARD=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_ARCH_EMEV2=y
 CONFIG_ARCH_R8A7794=y
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index d68101655b74..9f21e170320f 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -4,7 +4,6 @@
 
 #include <asm/auxvec.h>
 #include <asm/hwcap.h>
-#include <asm/vdso_datapage.h>
 
 /*
  * ELF register definitions..
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index e12d7d096fc0..e4eb54f6cd9f 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -11,7 +11,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(nop) "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
@@ -25,7 +25,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 119aa85d1feb..62af9f7f9e96 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -8,7 +8,7 @@
 #define _ASMARM_PAGE_H
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT		12
+#define PAGE_SHIFT		CONFIG_PAGE_SHIFT
 #define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~((1 << PAGE_SHIFT) - 1))
 
diff --git a/arch/arm/include/asm/vdso_datapage.h b/arch/arm/include/asm/vdso_datapage.h
deleted file mode 100644
index bef68f59928d..000000000000
--- a/arch/arm/include/asm/vdso_datapage.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Adapted from arm64 version.
- *
- * Copyright (C) 2012 ARM Limited
- */
-#ifndef __ASM_VDSO_DATAPAGE_H
-#define __ASM_VDSO_DATAPAGE_H
-
-#ifdef __KERNEL__
-
-#ifndef __ASSEMBLY__
-
-#include <vdso/datapage.h>
-#include <asm/page.h>
-
-union vdso_data_store {
-	struct vdso_data	data[CS_BASES];
-	u8			page[PAGE_SIZE];
-};
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASM_VDSO_DATAPAGE_H */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 219cbc7e5d13..4915662842ff 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -21,10 +21,12 @@
 #include <asm/mpu.h>
 #include <asm/procinfo.h>
 #include <asm/suspend.h>
-#include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
 #include <linux/arm-smccc.h>
+
+#include <vdso/datapage.h>
+
 #include "signal.h"
 
 /*
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index f297d66a8a76..d499ad461b00 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -21,7 +21,6 @@
 #include <asm/cacheflush.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
-#include <asm/vdso_datapage.h>
 #include <clocksource/arm_arch_timer.h>
 #include <vdso/helpers.h>
 #include <vdso/vsyscall.h>
@@ -35,9 +34,6 @@ extern char vdso_start[], vdso_end[];
 /* Total number of pages needed for the data and text portions of the VDSO. */
 unsigned int vdso_total_pages __ro_after_init;
 
-/*
- * The VDSO data page.
- */
 static union vdso_data_store vdso_data_store __page_aligned_data;
 struct vdso_data *vdso_data = vdso_data_store.data;
 
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 71b113976420..8b1ec60a9a46 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -339,6 +339,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = {
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
 		GPIO_LOOKUP_IDX("G", 0, NULL, 1,
 				GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN),
+		{ }
 	},
 };
 
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 444a7eaa320c..25893d109190 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -452,7 +452,7 @@ static int mmdc_pmu_init(struct mmdc_pmu *pmu_mmdc,
 		.active_events = 0,
 	};
 
-	pmu_mmdc->id = ida_simple_get(&mmdc_ida, 0, 0, GFP_KERNEL);
+	pmu_mmdc->id = ida_alloc(&mmdc_ida, GFP_KERNEL);
 
 	return pmu_mmdc->id;
 }
@@ -461,7 +461,7 @@ static void imx_mmdc_remove(struct platform_device *pdev)
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
-	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
+	ida_free(&mmdc_ida, pmu_mmdc->id);
 	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
 	iounmap(pmu_mmdc->mmdc_base);
@@ -529,7 +529,7 @@ pmu_register_err:
 	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
 pmu_release_id:
-	ida_simple_remove(&mmdc_ida, pmu_mmdc->id);
+	ida_free(&mmdc_ida, pmu_mmdc->id);
 pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index cbf703f0d850..a643b71e30a3 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -4,7 +4,6 @@ menuconfig ARCH_OMAP1
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5
 	depends on CPU_LITTLE_ENDIAN
 	depends on ATAGS
-	select ARCH_OMAP
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-omap2/am33xx-restart.c b/arch/arm/mach-omap2/am33xx-restart.c
index ef2f18a56b65..fcf3d557aa78 100644
--- a/arch/arm/mach-omap2/am33xx-restart.c
+++ b/arch/arm/mach-omap2/am33xx-restart.c
@@ -9,7 +9,7 @@
 #include "prm.h"
 
 /**
- * am3xx_restart - trigger a software restart of the SoC
+ * am33xx_restart - trigger a software restart of the SoC
  * @mode: the "reboot mode", see arch/arm/kernel/{setup,process}.c
  * @cmd: passed from the userspace program rebooting the system (if provided)
  *
@@ -18,7 +18,8 @@
  */
 void am33xx_restart(enum reboot_mode mode, const char *cmd)
 {
-	/* TODO: Handle mode and cmd if necessary */
+	/* TODO: Handle cmd if necessary */
+	prm_reboot_mode = mode;
 
 	omap_prm_reset_system();
 }
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index fde6ccb3df6e..68e0baad2bbf 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -246,6 +246,12 @@ DT_MACHINE_START(AM33XX_DT, "Generic AM33XX (Flattened Device Tree)")
 	.init_time	= omap_init_time_of,
 	.dt_compat	= am33xx_boards_compat,
 	.restart	= am33xx_restart,
+	/*
+	 * Historically am33xx supported only REBOOT_WARM even though default
+	 * reboot_mode was REBOOT_COLD. Reflect legacy de-facto behaviour in
+	 * SYSFS.
+	 */
+	.reboot_mode	= REBOOT_WARM,
 MACHINE_END
 #endif
 
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index be4557d1fdac..011076a5952f 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -162,7 +162,7 @@ static int omap2_select_table_rate(struct clk_hw *hw, unsigned long rate,
 }
 
 /**
- * omap2xxx_clkt_vps_check_bootloader_rate - determine which of the rate
+ * omap2xxx_clkt_vps_check_bootloader_rates - determine which of the rate
  * table sets matches the current CORE DPLL hardware rate
  *
  * Check the MPU rate set by bootloader.  Sets the 'curr_prcm_set'
diff --git a/arch/arm/mach-omap2/clockdomain.c b/arch/arm/mach-omap2/clockdomain.c
index d145e7ac709b..69dc5b839335 100644
--- a/arch/arm/mach-omap2/clockdomain.c
+++ b/arch/arm/mach-omap2/clockdomain.c
@@ -990,7 +990,7 @@ void clkdm_allow_idle(struct clockdomain *clkdm)
 }
 
 /**
- * clkdm_deny_idle - disable hwsup idle transitions for clkdm
+ * clkdm_deny_idle_nolock - disable hwsup idle transitions for clkdm
  * @clkdm: struct clockdomain *
  *
  * Prevent the hardware from automatically switching the clockdomain
@@ -1110,7 +1110,7 @@ void clkdm_del_autodeps(struct clockdomain *clkdm)
 /**
  * clkdm_clk_enable - add an enabled downstream clock to this clkdm
  * @clkdm: struct clockdomain *
- * @clk: struct clk * of the enabled downstream clock
+ * @unused: struct clk * of the enabled downstream clock
  *
  * Increment the usecount of the clockdomain @clkdm and ensure that it
  * is awake before @clk is enabled.  Intended to be called by
diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c
index c824d4e3db63..acdf72a541c0 100644
--- a/arch/arm/mach-omap2/cm33xx.c
+++ b/arch/arm/mach-omap2/cm33xx.c
@@ -357,7 +357,7 @@ static int am33xx_clkdm_save_context(struct clockdomain *clkdm)
 }
 
 /**
- * am33xx_restore_save_context - Restore the clockdomain transition context
+ * am33xx_clkdm_restore_context - Restore the clockdomain transition context
  * @clkdm: The clockdomain pointer whose context needs to be restored
  *
  * Restore the clockdomain transition context.
diff --git a/arch/arm/mach-omap2/cminst44xx.c b/arch/arm/mach-omap2/cminst44xx.c
index 46670521b278..49483a888046 100644
--- a/arch/arm/mach-omap2/cminst44xx.c
+++ b/arch/arm/mach-omap2/cminst44xx.c
@@ -237,7 +237,7 @@ static void omap4_cminst_clkdm_disable_hwsup(u8 part, u16 inst, u16 cdoffs)
 }
 
 /**
- * omap4_cminst_clkdm_force_sleep - try to take a clockdomain out of idle
+ * omap4_cminst_clkdm_force_wakeup - try to take a clockdomain out of idle
  * @part: PRCM partition ID that the clockdomain registers exist in
  * @inst: CM instance register offset (*_INST macro)
  * @cdoffs: Clockdomain register offset (*_CDOFFS macro)
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 29c7350b06ab..c2e1aecd07cc 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -47,7 +47,7 @@ static void __init omap_optee_init_check(void)
 }
 
 /**
- * omap_sec_dispatcher: Routine to dispatch low power secure
+ * omap_secure_dispatcher - Routine to dispatch low power secure
  * service routines
  * @idx: The HAL API index
  * @flag: The flag indicating criticality of operation
@@ -183,7 +183,7 @@ static u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs,
 /**
  * rx51_secure_update_aux_cr: Routine to modify the contents of Auxiliary Control Register
  *  @set_bits: bits to set in ACR
- *  @clr_bits: bits to clear in ACR
+ *  @clear_bits: bits to clear in ACR
  *
  * Return the non-zero error value on failure.
 */
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index ba71928c0fcb..111677878d9c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -900,7 +900,7 @@ static int _init_interface_clks(struct omap_hwmod *oh)
 }
 
 /**
- * _init_opt_clk - get a struct clk * for the hwmod's optional clocks
+ * _init_opt_clks - get a struct clk * for the hwmod's optional clocks
  * @oh: struct omap_hwmod *
  *
  * Called from _init_clocks().  Populates the @oh omap_hwmod_opt_clk
@@ -2297,7 +2297,7 @@ static void __init parse_module_flags(struct omap_hwmod *oh,
 /**
  * _init - initialize internal data for the hwmod @oh
  * @oh: struct omap_hwmod *
- * @n: (unused)
+ * @data: (unused)
  *
  * Look up the clocks and the address space used by the MPU to access
  * registers belonging to the hwmod @oh.  @oh must already be
@@ -2493,7 +2493,7 @@ static void _setup_postsetup(struct omap_hwmod *oh)
 /**
  * _setup - prepare IP block hardware for use
  * @oh: struct omap_hwmod *
- * @n: (unused, pass NULL)
+ * @data: (unused, pass NULL)
  *
  * Configure the IP block represented by @oh.  This may include
  * enabling the IP block, resetting it, and placing it into a
@@ -3367,8 +3367,9 @@ static int omap_hwmod_check_module(struct device *dev,
  * omap_hwmod_allocate_module - allocate new module
  * @dev: struct device
  * @oh: module
+ * @data: module data
  * @sysc_fields: sysc register bits
- * @clockdomain: clockdomain
+ * @clkdm: clockdomain
  * @rev_offs: revision register offset
  * @sysc_offs: sysconfig register offset
  * @syss_offs: sysstatus register offset
diff --git a/arch/arm/mach-omap2/omap_hwmod_common_data.c b/arch/arm/mach-omap2/omap_hwmod_common_data.c
index 246f1e5da99f..439232233c39 100644
--- a/arch/arm/mach-omap2/omap_hwmod_common_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_common_data.c
@@ -20,7 +20,7 @@
 
 #include "omap_hwmod_common_data.h"
 
-/**
+/*
  * struct omap_hwmod_sysc_type1 - TYPE1 sysconfig scheme.
  *
  * To be used by hwmod structure to specify the sysconfig offsets
@@ -36,7 +36,7 @@ struct sysc_regbits omap_hwmod_sysc_type1 = {
 	.autoidle_shift	= SYSC_TYPE1_AUTOIDLE_SHIFT,
 };
 
-/**
+/*
  * struct omap_hwmod_sysc_type2 - TYPE2 sysconfig scheme.
  *
  * To be used by hwmod structure to specify the sysconfig offsets if the
@@ -50,7 +50,7 @@ struct sysc_regbits omap_hwmod_sysc_type2 = {
 	.dmadisable_shift = SYSC_TYPE2_DMADISABLE_SHIFT,
 };
 
-/**
+/*
  * struct omap_hwmod_sysc_type3 - TYPE3 sysconfig scheme.
  * Used by some IPs on AM33xx
  */
diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c
index 668dc84fd31e..4f31e61c0c90 100644
--- a/arch/arm/mach-omap2/pmic-cpcap.c
+++ b/arch/arm/mach-omap2/pmic-cpcap.c
@@ -18,10 +18,10 @@
 #include "vc.h"
 
 /**
- * omap_cpcap_vsel_to_vdc - convert CPCAP VSEL value to microvolts DC
+ * omap_cpcap_vsel_to_uv - convert CPCAP VSEL value to microvolts DC
  * @vsel: CPCAP VSEL value to convert
  *
- * Returns the microvolts DC that the CPCAP PMIC should generate when
+ * Returns: the microvolts DC that the CPCAP PMIC should generate when
  * programmed with @vsel.
  */
 static unsigned long omap_cpcap_vsel_to_uv(unsigned char vsel)
@@ -35,7 +35,7 @@ static unsigned long omap_cpcap_vsel_to_uv(unsigned char vsel)
  * omap_cpcap_uv_to_vsel - convert microvolts DC to CPCAP VSEL value
  * @uv: microvolts DC to convert
  *
- * Returns the VSEL value necessary for the CPCAP PMIC to
+ * Returns: the VSEL value necessary for the CPCAP PMIC to
  * generate an output voltage equal to or greater than @uv microvolts DC.
  */
 static unsigned char omap_cpcap_uv_to_vsel(unsigned long uv)
@@ -82,10 +82,10 @@ static struct omap_voltdm_pmic omap_cpcap_iva = {
 };
 
 /**
- * omap_max8952_vsel_to_vdc - convert MAX8952 VSEL value to microvolts DC
+ * omap_max8952_vsel_to_uv - convert MAX8952 VSEL value to microvolts DC
  * @vsel: MAX8952 VSEL value to convert
  *
- * Returns the microvolts DC that the MAX8952 Regulator should generate when
+ * Returns: the microvolts DC that the MAX8952 Regulator should generate when
  * programmed with @vsel.
  */
 static unsigned long omap_max8952_vsel_to_uv(unsigned char vsel)
@@ -99,7 +99,7 @@ static unsigned long omap_max8952_vsel_to_uv(unsigned char vsel)
  * omap_max8952_uv_to_vsel - convert microvolts DC to MAX8952 VSEL value
  * @uv: microvolts DC to convert
  *
- * Returns the VSEL value necessary for the MAX8952 Regulator to
+ * Returns: the VSEL value necessary for the MAX8952 Regulator to
  * generate an output voltage equal to or greater than @uv microvolts DC.
  */
 static unsigned char omap_max8952_uv_to_vsel(unsigned long uv)
@@ -129,10 +129,10 @@ static struct omap_voltdm_pmic omap443x_max8952_mpu = {
 };
 
 /**
- * omap_fan5355_vsel_to_vdc - convert FAN535503 VSEL value to microvolts DC
+ * omap_fan535503_vsel_to_uv - convert FAN535503 VSEL value to microvolts DC
  * @vsel: FAN535503 VSEL value to convert
  *
- * Returns the microvolts DC that the FAN535503 Regulator should generate when
+ * Returns: the microvolts DC that the FAN535503 Regulator should generate when
  * programmed with @vsel.
  */
 static unsigned long omap_fan535503_vsel_to_uv(unsigned char vsel)
@@ -144,10 +144,10 @@ static unsigned long omap_fan535503_vsel_to_uv(unsigned char vsel)
 }
 
 /**
- * omap_fan535508_vsel_to_vdc - convert FAN535508 VSEL value to microvolts DC
+ * omap_fan535508_vsel_to_uv - convert FAN535508 VSEL value to microvolts DC
  * @vsel: FAN535508 VSEL value to convert
  *
- * Returns the microvolts DC that the FAN535508 Regulator should generate when
+ * Returns: the microvolts DC that the FAN535508 Regulator should generate when
  * programmed with @vsel.
  */
 static unsigned long omap_fan535508_vsel_to_uv(unsigned char vsel)
@@ -165,7 +165,7 @@ static unsigned long omap_fan535508_vsel_to_uv(unsigned char vsel)
  * omap_fan535503_uv_to_vsel - convert microvolts DC to FAN535503 VSEL value
  * @uv: microvolts DC to convert
  *
- * Returns the VSEL value necessary for the MAX8952 Regulator to
+ * Returns: the VSEL value necessary for the MAX8952 Regulator to
  * generate an output voltage equal to or greater than @uv microvolts DC.
  */
 static unsigned char omap_fan535503_uv_to_vsel(unsigned long uv)
@@ -184,7 +184,7 @@ static unsigned char omap_fan535503_uv_to_vsel(unsigned long uv)
  * omap_fan535508_uv_to_vsel - convert microvolts DC to FAN535508 VSEL value
  * @uv: microvolts DC to convert
  *
- * Returns the VSEL value necessary for the MAX8952 Regulator to
+ * Returns: the VSEL value necessary for the MAX8952 Regulator to
  * generate an output voltage equal to or greater than @uv microvolts DC.
  */
 static unsigned char omap_fan535508_uv_to_vsel(unsigned long uv)
diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 5e05dd1324e7..2441d96b7144 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -1162,7 +1162,7 @@ static int pwrdm_save_context(struct powerdomain *pwrdm, void *unused)
 }
 
 /**
- * pwrdm_save_context - restore powerdomain registers
+ * pwrdm_restore_context - restore powerdomain registers
  *
  * Restore powerdomain control registers after a suspend or resume
  * event.
diff --git a/arch/arm/mach-omap2/prm-regbits-33xx.h b/arch/arm/mach-omap2/prm-regbits-33xx.h
index 3748c5266ae1..9b97f8c76cd1 100644
--- a/arch/arm/mach-omap2/prm-regbits-33xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-33xx.h
@@ -15,6 +15,7 @@
 #define AM33XX_GFX_MEM_STATEST_MASK			(0x3 << 4)
 #define AM33XX_GLOBAL_WARM_SW_RST_MASK			(1 << 1)
 #define AM33XX_RST_GLOBAL_WARM_SW_MASK			(1 << 0)
+#define AM33XX_RST_GLOBAL_COLD_SW_MASK			(1 << 1)
 #define AM33XX_PRUSS_MEM_ONSTATE_MASK			(0x3 << 5)
 #define AM33XX_PRUSS_MEM_RETSTATE_MASK			(1 << 7)
 #define AM33XX_PRUSS_MEM_STATEST_MASK			(0x3 << 23)
diff --git a/arch/arm/mach-omap2/prm.h b/arch/arm/mach-omap2/prm.h
index fc45a7ed09bb..fc53a27eed01 100644
--- a/arch/arm/mach-omap2/prm.h
+++ b/arch/arm/mach-omap2/prm.h
@@ -15,6 +15,7 @@
 # ifndef __ASSEMBLER__
 extern struct omap_domain_base prm_base;
 extern u16 prm_features;
+extern enum reboot_mode prm_reboot_mode;
 int omap_prcm_init(void);
 int omap2_prcm_base_init(void);
 # endif
diff --git a/arch/arm/mach-omap2/prm33xx.c b/arch/arm/mach-omap2/prm33xx.c
index 4b65a0f9cf7d..505d685d6792 100644
--- a/arch/arm/mach-omap2/prm33xx.c
+++ b/arch/arm/mach-omap2/prm33xx.c
@@ -10,15 +10,12 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/reboot.h>
 
 #include "powerdomain.h"
 #include "prm33xx.h"
 #include "prm-regbits-33xx.h"
 
-#define AM33XX_PRM_RSTCTRL_OFFSET		0x0000
-
-#define AM33XX_RST_GLOBAL_WARM_SW_MASK		(1 << 0)
-
 /* Read a register in a PRM instance */
 static u32 am33xx_prm_read_reg(s16 inst, u16 idx)
 {
@@ -322,10 +319,19 @@ static int am33xx_check_vcvp(void)
  *
  * Immediately reboots the device through warm reset.
  */
-static void am33xx_prm_global_warm_sw_reset(void)
+static void am33xx_prm_global_sw_reset(void)
 {
-	am33xx_prm_rmw_reg_bits(AM33XX_RST_GLOBAL_WARM_SW_MASK,
-				AM33XX_RST_GLOBAL_WARM_SW_MASK,
+	/*
+	 * Historically AM33xx performed warm reset for all requested reboot_mode.
+	 * Keep this behaviour unchanged for all except newly added REBOOT_COLD.
+	 */
+	u32 mask = AM33XX_RST_GLOBAL_WARM_SW_MASK;
+
+	if (prm_reboot_mode == REBOOT_COLD)
+		mask = AM33XX_RST_GLOBAL_COLD_SW_MASK;
+
+	am33xx_prm_rmw_reg_bits(mask,
+				mask,
 				AM33XX_PRM_DEVICE_MOD,
 				AM33XX_PRM_RSTCTRL_OFFSET);
 
@@ -386,7 +392,7 @@ static struct prm_ll_data am33xx_prm_ll_data = {
 	.assert_hardreset		= am33xx_prm_assert_hardreset,
 	.deassert_hardreset		= am33xx_prm_deassert_hardreset,
 	.is_hardreset_asserted		= am33xx_prm_is_hardreset_asserted,
-	.reset_system			= am33xx_prm_global_warm_sw_reset,
+	.reset_system			= am33xx_prm_global_sw_reset,
 };
 
 int __init am33xx_prm_init(const struct omap_prcm_init_data *data)
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 25093c1e5b9a..6c555438dd48 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -407,7 +407,7 @@ static bool omap44xx_prm_was_any_context_lost_old(u8 part, s16 inst, u16 idx)
 }
 
 /**
- * omap44xx_prm_clear_context_lost_flags_old - clear context loss flags
+ * omap44xx_prm_clear_context_loss_flags_old - clear context loss flags
  * @part: PRM partition ID (e.g., OMAP4430_PRM_PARTITION)
  * @inst: PRM instance offset (e.g., OMAP4430_PRM_MPU_INST)
  * @idx: CONTEXT register offset
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index fd896f2295a1..ee4588acda50 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -67,6 +67,12 @@ struct omap_domain_base prm_base;
 u16 prm_features;
 
 /*
+ * Platforms that implement different reboot modes can store the requested
+ * mode here.
+ */
+enum reboot_mode prm_reboot_mode;
+
+/*
  * prm_ll_data: function pointers to SoC-specific implementations of
  * common PRM functions
  */
@@ -370,7 +376,7 @@ bool prm_was_any_context_lost_old(u8 part, s16 inst, u16 idx)
 }
 
 /**
- * prm_clear_context_lost_flags_old - clear context loss flags (old API)
+ * prm_clear_context_loss_flags_old - clear context loss flags (old API)
  * @part: PRM partition ID (e.g., OMAP4430_PRM_PARTITION)
  * @inst: PRM instance offset (e.g., OMAP4430_PRM_MPU_INST)
  * @idx: CONTEXT register offset
@@ -497,6 +503,7 @@ int omap_prm_clear_mod_irqs(s16 module, u8 regs, u32 wkst_mask)
 
 /**
  * omap_prm_vp_check_txdone - check voltage processor TX done status
+ * @vp_id: unique VP instance ID
  *
  * Checks if voltage processor transmission has been completed.
  * Returns non-zero if a transmission has completed, 0 otherwise.
@@ -514,6 +521,7 @@ u32 omap_prm_vp_check_txdone(u8 vp_id)
 
 /**
  * omap_prm_vp_clear_txdone - clears voltage processor TX done status
+ * @vp_id: unique VP instance ID
  *
  * Clears the status bit for completed voltage processor transmission
  * returned by prm_vp_check_txdone.
diff --git a/arch/arm/mach-omap2/wd_timer.c b/arch/arm/mach-omap2/wd_timer.c
index d4ea56a5f75a..898e7e332981 100644
--- a/arch/arm/mach-omap2/wd_timer.c
+++ b/arch/arm/mach-omap2/wd_timer.c
@@ -57,7 +57,7 @@ int omap2_wd_timer_disable(struct omap_hwmod *oh)
 }
 
 /**
- * omap2_wdtimer_reset - reset and disable the WDTIMER IP block
+ * omap2_wd_timer_reset - reset and disable the WDTIMER IP block
  * @oh: struct omap_hwmod *
  *
  * After the WDTIMER IP blocks are reset on OMAP2/3, we must also take
@@ -71,6 +71,8 @@ int omap2_wd_timer_disable(struct omap_hwmod *oh)
  * during a normal merge window.  omap_hwmod_softreset() should be
  * renamed to omap_hwmod_set_ocp_softreset(), and omap_hwmod_softreset()
  * should call the hwmod _ocp_softreset() code.
+ *
+ * Returns: %0 on success or -errno value on error.
  */
 int omap2_wd_timer_reset(struct omap_hwmod *oh)
 {
diff --git a/arch/arm/mach-qcom/Kconfig b/arch/arm/mach-qcom/Kconfig
index 12a812e61c16..f4765be1b2a0 100644
--- a/arch/arm/mach-qcom/Kconfig
+++ b/arch/arm/mach-qcom/Kconfig
@@ -4,46 +4,21 @@ menuconfig ARCH_QCOM
 	depends on ARCH_MULTI_V7
 	select ARM_GIC
 	select ARM_AMBA
+	select CLKSRC_QCOM
+	select HAVE_ARM_ARCH_TIMER
 	select PINCTRL
 	select QCOM_SCM if SMP
 	help
 	  Support for Qualcomm's devicetree based systems.
+	  This includes support for a few devices with ARM64 SoC, that have
+	  ARM32 signed firmware that does not allow booting ARM64 kernels.
 
 if ARCH_QCOM
 
-config ARCH_IPQ40XX
-	bool "Enable support for IPQ40XX"
-	select CLKSRC_QCOM
-	select HAVE_ARM_ARCH_TIMER
-
-config ARCH_MSM8X60
-	bool "Enable support for MSM8X60"
-	select CLKSRC_QCOM
-
-config ARCH_MSM8909
-	bool "Enable support for MSM8909"
-	select HAVE_ARM_ARCH_TIMER
-
-config ARCH_MSM8916
-	bool "Enable support for MSM8916"
-	select HAVE_ARM_ARCH_TIMER
+config ARCH_QCOM_RESERVE_SMEM
+	bool "Reserve SMEM at the beginning of RAM"
 	help
-	  Enable support for the Qualcomm Snapdragon 410 (MSM8916/APQ8016).
-
-	  Note that ARM64 is the main supported architecture for MSM8916.
-	  The ARM32 option is intended for a few devices with signed firmware
-	  that does not allow booting ARM64 kernels.
-
-config ARCH_MSM8960
-	bool "Enable support for MSM8960"
-	select CLKSRC_QCOM
-
-config ARCH_MSM8974
-	bool "Enable support for MSM8974"
-	select HAVE_ARM_ARCH_TIMER
-
-config ARCH_MDM9615
-	bool "Enable support for MDM9615"
-	select CLKSRC_QCOM
+	  Reserve 2MB at the beginning of the System RAM for shared mem.
+	  This is required on IPQ40xx, MSM8x60 and MSM8960 platforms.
 
 endif
diff --git a/arch/arm/mach-s3c/cpu.h b/arch/arm/mach-s3c/cpu.h
index d0adc9b40e25..a0187606b999 100644
--- a/arch/arm/mach-s3c/cpu.h
+++ b/arch/arm/mach-s3c/cpu.h
@@ -76,6 +76,6 @@ extern void s3c24xx_init_uartdevs(char *name,
 				  struct s3c24xx_uart_resources *res,
 				  struct s3c2410_uartcfg *cfg, int no);
 
-extern struct bus_type s3c6410_subsys;
+extern const struct bus_type s3c6410_subsys;
 
 #endif
diff --git a/arch/arm/mach-s3c/s3c6410.c b/arch/arm/mach-s3c/s3c6410.c
index e79f18d0ca81..a29276a4fde5 100644
--- a/arch/arm/mach-s3c/s3c6410.c
+++ b/arch/arm/mach-s3c/s3c6410.c
@@ -57,7 +57,7 @@ void __init s3c6410_init_irq(void)
 	s3c64xx_init_irq(~0 & ~(1 << 7), ~0);
 }
 
-struct bus_type s3c6410_subsys = {
+const struct bus_type s3c6410_subsys = {
 	.name		= "s3c6410-core",
 	.dev_name	= "s3c6410-core",
 };
diff --git a/arch/arm/mach-s3c/s3c64xx.c b/arch/arm/mach-s3c/s3c64xx.c
index 9f9717874d67..6c70ea7f2931 100644
--- a/arch/arm/mach-s3c/s3c64xx.c
+++ b/arch/arm/mach-s3c/s3c64xx.c
@@ -149,7 +149,7 @@ static struct map_desc s3c_iodesc[] __initdata = {
 	},
 };
 
-static struct bus_type s3c64xx_subsys = {
+static const struct bus_type s3c64xx_subsys = {
 	.name		= "s3c64xx-core",
 	.dev_name	= "s3c64xx-core",
 };
diff --git a/arch/arm/mach-s5pv210/pm.c b/arch/arm/mach-s5pv210/pm.c
index d59c094cdea8..6fa70f787df4 100644
--- a/arch/arm/mach-s5pv210/pm.c
+++ b/arch/arm/mach-s5pv210/pm.c
@@ -47,7 +47,7 @@ static void s3c_pm_do_save(struct sleep_save *ptr, int count)
 }
 
 /**
- * s3c_pm_do_restore() - restore register values from the save list.
+ * s3c_pm_do_restore_core() - restore register values from the save list.
  * @ptr: Pointer to an array of registers.
  * @count: Size of the ptr array.
  *
diff --git a/arch/arm/mach-zynq/slcr.c b/arch/arm/mach-zynq/slcr.c
index 9765b3f4c2fc..6aae14b0736c 100644
--- a/arch/arm/mach-zynq/slcr.c
+++ b/arch/arm/mach-zynq/slcr.c
@@ -10,7 +10,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/of_address.h>
 #include <linux/regmap.h>
-#include <linux/clk/zynq.h>
 #include "common.h"
 
 /* register offsets */
@@ -146,7 +145,7 @@ void zynq_slcr_cpu_stop(int cpu)
 }
 
 /**
- * zynq_slcr_cpu_state - Read/write cpu state
+ * zynq_slcr_cpu_state_read - Read cpu state
  * @cpu:	cpu number
  *
  * SLCR_REBOOT_STATUS save upper 2 bits (31/30 cpu states for cpu0 and cpu1)
@@ -165,7 +164,7 @@ bool zynq_slcr_cpu_state_read(int cpu)
 }
 
 /**
- * zynq_slcr_cpu_state - Read/write cpu state
+ * zynq_slcr_cpu_state_write - Write cpu state
  * @cpu:	cpu number
  * @die:	cpu state - true if cpu is going to die
  *
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index e96fb40b9cc3..07565b593ed6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -298,6 +298,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		goto done;
 	}
 	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index aa7c1d435139..29290b8cb36d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -277,27 +277,21 @@ config 64BIT
 config MMU
 	def_bool y
 
-config ARM64_PAGE_SHIFT
-	int
-	default 16 if ARM64_64K_PAGES
-	default 14 if ARM64_16K_PAGES
-	default 12
-
 config ARM64_CONT_PTE_SHIFT
 	int
-	default 5 if ARM64_64K_PAGES
-	default 7 if ARM64_16K_PAGES
+	default 5 if PAGE_SIZE_64KB
+	default 7 if PAGE_SIZE_16KB
 	default 4
 
 config ARM64_CONT_PMD_SHIFT
 	int
-	default 5 if ARM64_64K_PAGES
-	default 5 if ARM64_16K_PAGES
+	default 5 if PAGE_SIZE_64KB
+	default 5 if PAGE_SIZE_16KB
 	default 4
 
 config ARCH_MMAP_RND_BITS_MIN
-	default 14 if ARM64_64K_PAGES
-	default 16 if ARM64_16K_PAGES
+	default 14 if PAGE_SIZE_64KB
+	default 16 if PAGE_SIZE_16KB
 	default 18
 
 # max bits determined by the following formula:
@@ -1259,11 +1253,13 @@ choice
 
 config ARM64_4K_PAGES
 	bool "4KB"
+	select HAVE_PAGE_SIZE_4KB
 	help
 	  This feature enables 4KB pages support.
 
 config ARM64_16K_PAGES
 	bool "16KB"
+	select HAVE_PAGE_SIZE_16KB
 	help
 	  The system will use 16KB pages support. AArch32 emulation
 	  requires applications compiled with 16K (or a multiple of 16K)
@@ -1271,6 +1267,7 @@ config ARM64_16K_PAGES
 
 config ARM64_64K_PAGES
 	bool "64KB"
+	select HAVE_PAGE_SIZE_64KB
 	help
 	  This feature enables 64KB pages support (4KB by default)
 	  allowing only two levels of page tables and faster TLB
@@ -1291,19 +1288,19 @@ choice
 
 config ARM64_VA_BITS_36
 	bool "36-bit" if EXPERT
-	depends on ARM64_16K_PAGES
+	depends on PAGE_SIZE_16KB
 
 config ARM64_VA_BITS_39
 	bool "39-bit"
-	depends on ARM64_4K_PAGES
+	depends on PAGE_SIZE_4KB
 
 config ARM64_VA_BITS_42
 	bool "42-bit"
-	depends on ARM64_64K_PAGES
+	depends on PAGE_SIZE_64KB
 
 config ARM64_VA_BITS_47
 	bool "47-bit"
-	depends on ARM64_16K_PAGES
+	depends on PAGE_SIZE_16KB
 
 config ARM64_VA_BITS_48
 	bool "48-bit"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 47ecc4cff9d2..a88cdf910687 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -195,7 +195,7 @@ vdso_prepare: prepare0
 	include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
 ifdef CONFIG_COMPAT_VDSO
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
-	include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
+	arch/arm64/kernel/vdso32/vdso.so
 endif
 endif
 
diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile
index 91d505b385de..21149b346a60 100644
--- a/arch/arm64/boot/dts/allwinner/Makefile
+++ b/arch/arm64/boot/dts/allwinner/Makefile
@@ -16,6 +16,7 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-pinetab.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-pinetab-early-adopter.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-sopine-baseboard.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a64-teres-i.dtb
+dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h64-remix-mini-pc.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-a100-allwinner-perf1.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h5-bananapi-m2-plus.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h5-bananapi-m2-plus-v1.2.dtb
@@ -42,5 +43,7 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-cb1-manta.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb
+dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-longanpi-3h.dtb
+dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero2w.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb
 dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 9ec49ac2f6fd..381d58cea092 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -291,6 +291,8 @@
 };
 
 &spdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spdif_tx_pin>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi
index 4903d6358112..855b7d43bc50 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi
@@ -166,6 +166,8 @@
 };
 
 &spdif {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spdif_tx_pin>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index ca1d287a0a01..d11e5041bae9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -406,6 +406,7 @@
 				function = "spi1";
 			};
 
+			/omit-if-no-ref/
 			spdif_tx_pin: spdif-tx-pin {
 				pins = "PH7";
 				function = "spdif";
@@ -655,10 +656,8 @@
 			clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>;
 			clock-names = "apb", "spdif";
 			resets = <&ccu RST_BUS_SPDIF>;
-			dmas = <&dma 2>;
-			dma-names = "tx";
-			pinctrl-names = "default";
-			pinctrl-0 = <&spdif_tx_pin>;
+			dmas = <&dma 2>, <&dma 2>;
+			dma-names = "rx", "tx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1-manta.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1-manta.dts
index dbce61b355d6..4bfb52609c94 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1-manta.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1-manta.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0+ or MIT)
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
 /*
  * Copyright (C) 2023 Martin Botka <martin.botka@somainline.org>.
  */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1.dtsi
index 1fed2b46cfe8..af421ba24ce0 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-cb1.dtsi
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0+ or MIT)
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
 /*
  * Copyright (C) 2023 Martin Botka <martin.botka@somainline.org>.
  */
@@ -93,7 +93,7 @@
 		interrupt-controller;
 		#interrupt-cells = <1>;
 
-		regulators{
+		regulators {
 			reg_dcdc1: dcdc1 {
 				regulator-name = "vdd-gpu-sys";
 				regulator-min-microvolt = <810000>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-pi.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-pi.dts
index 832f08b2b260..ff84a3794470 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-pi.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-bigtreetech-pi.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: (GPL-2.0+ or MIT)
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
 /*
  * Copyright (C) 2023 Martin Botka <martin@biqu3d.com>.
  */
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616.dtsi
index d549d277d972..b2e85e52d1a1 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h616.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h616.dtsi
@@ -9,6 +9,7 @@
 #include <dt-bindings/clock/sun6i-rtc.h>
 #include <dt-bindings/reset/sun50i-h616-ccu.h>
 #include <dt-bindings/reset/sun50i-h6-r-ccu.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	interrupt-parent = <&gic>;
@@ -133,11 +134,28 @@
 			#reset-cells = <1>;
 		};
 
+		dma: dma-controller@3002000 {
+			compatible = "allwinner,sun50i-h616-dma",
+				     "allwinner,sun50i-a100-dma";
+			reg = <0x03002000 0x1000>;
+			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_DMA>, <&ccu CLK_MBUS_DMA>;
+			clock-names = "bus", "mbus";
+			dma-channels = <16>;
+			dma-requests = <49>;
+			resets = <&ccu RST_BUS_DMA>;
+			#dma-cells = <1>;
+		};
+
 		sid: efuse@3006000 {
 			compatible = "allwinner,sun50i-h616-sid", "allwinner,sun50i-a64-sid";
 			reg = <0x03006000 0x1000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			ths_calibration: thermal-sensor-calibration@14 {
+				reg = <0x14 0x8>;
+			};
 		};
 
 		watchdog: watchdog@30090a0 {
@@ -240,6 +258,11 @@
 				function = "spi1";
 			};
 
+			spdif_tx_pin: spdif-tx-pin {
+				pins = "PH4";
+				function = "spdif";
+			};
+
 			uart0_ph_pins: uart0-ph-pins {
 				pins = "PH0", "PH1";
 				function = "uart0";
@@ -256,6 +279,12 @@
 				pins = "PG8", "PG9";
 				function = "uart1";
 			};
+
+			/omit-if-no-ref/
+			x32clk_fanout_pin: x32clk-fanout-pin {
+				pins = "PG10";
+				function = "clock";
+			};
 		};
 
 		gic: interrupt-controller@3021000 {
@@ -339,6 +368,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART0>;
+			dmas = <&dma 14>, <&dma 14>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART0>;
 			status = "disabled";
 		};
@@ -350,6 +381,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART1>;
+			dmas = <&dma 15>, <&dma 15>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART1>;
 			status = "disabled";
 		};
@@ -361,6 +394,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART2>;
+			dmas = <&dma 16>, <&dma 16>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART2>;
 			status = "disabled";
 		};
@@ -372,6 +407,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART3>;
+			dmas = <&dma 17>, <&dma 17>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART3>;
 			status = "disabled";
 		};
@@ -383,6 +420,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART4>;
+			dmas = <&dma 18>, <&dma 18>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART4>;
 			status = "disabled";
 		};
@@ -394,6 +433,8 @@
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			clocks = <&ccu CLK_BUS_UART5>;
+			dmas = <&dma 19>, <&dma 19>;
+			dma-names = "tx", "rx";
 			resets = <&ccu RST_BUS_UART5>;
 			status = "disabled";
 		};
@@ -405,6 +446,8 @@
 			reg = <0x05002000 0x400>;
 			interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_I2C0>;
+			dmas = <&dma 43>, <&dma 43>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_I2C0>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&i2c0_pins>;
@@ -420,6 +463,8 @@
 			reg = <0x05002400 0x400>;
 			interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_I2C1>;
+			dmas = <&dma 44>, <&dma 44>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_I2C1>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -433,6 +478,8 @@
 			reg = <0x05002800 0x400>;
 			interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_I2C2>;
+			dmas = <&dma 45>, <&dma 45>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_I2C2>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -446,6 +493,8 @@
 			reg = <0x05002c00 0x400>;
 			interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_I2C3>;
+			dmas = <&dma 46>, <&dma 46>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_I2C3>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -459,6 +508,8 @@
 			reg = <0x05003000 0x400>;
 			interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_I2C4>;
+			dmas = <&dma 47>, <&dma 47>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_I2C4>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -472,6 +523,8 @@
 			interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_SPI0>, <&ccu CLK_SPI0>;
 			clock-names = "ahb", "mod";
+			dmas = <&dma 22>, <&dma 22>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_SPI0>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -485,6 +538,8 @@
 			interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_BUS_SPI1>, <&ccu CLK_SPI1>;
 			clock-names = "ahb", "mod";
+			dmas = <&dma 23>, <&dma 23>;
+			dma-names = "rx", "tx";
 			resets = <&ccu RST_BUS_SPI1>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -511,6 +566,34 @@
 			};
 		};
 
+		spdif: spdif@5093000 {
+			compatible = "allwinner,sun50i-h616-spdif";
+			reg = <0x05093000 0x400>;
+			interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>;
+			clock-names = "apb", "spdif";
+			resets = <&ccu RST_BUS_SPDIF>;
+			dmas = <&dma 2>;
+			dma-names = "tx";
+			pinctrl-names = "default";
+			pinctrl-0 = <&spdif_tx_pin>;
+			#sound-dai-cells = <0>;
+			status = "disabled";
+		};
+
+		ths: thermal-sensor@5070400 {
+			compatible = "allwinner,sun50i-h616-ths";
+			reg = <0x05070400 0x400>;
+			interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&ccu CLK_BUS_THS>;
+			clock-names = "bus";
+			resets = <&ccu RST_BUS_THS>;
+			nvmem-cells = <&ths_calibration>;
+			nvmem-cell-names = "calibration";
+			allwinner,sram = <&syscon>;
+			#thermal-sensor-cells = <1>;
+		};
+
 		usbotg: usb@5100000 {
 			compatible = "allwinner,sun50i-h616-musb",
 				     "allwinner,sun8i-h3-musb";
@@ -734,6 +817,8 @@
 			reg = <0x07081400 0x400>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&r_ccu CLK_R_APB2_I2C>;
+			dmas = <&dma 48>, <&dma 48>;
+			dma-names = "rx", "tx";
 			resets = <&r_ccu RST_R_APB2_I2C>;
 			status = "disabled";
 			#address-cells = <1>;
@@ -755,4 +840,74 @@
 			#size-cells = <0>;
 		};
 	};
+
+	thermal-zones {
+		cpu-thermal {
+			polling-delay-passive = <500>;
+			polling-delay = <1000>;
+			thermal-sensors = <&ths 2>;
+			sustainable-power = <1000>;
+
+			trips {
+				cpu_threshold: cpu-trip-0 {
+					temperature = <60000>;
+					type = "passive";
+					hysteresis = <0>;
+				};
+				cpu_target: cpu-trip-1 {
+					temperature = <70000>;
+					type = "passive";
+					hysteresis = <0>;
+				};
+				cpu_critical: cpu-trip-2 {
+					temperature = <110000>;
+					type = "critical";
+					hysteresis = <0>;
+				};
+			};
+		};
+
+		gpu-thermal {
+			polling-delay-passive = <500>;
+			polling-delay = <1000>;
+			thermal-sensors = <&ths 0>;
+			sustainable-power = <1100>;
+
+			trips {
+				gpu_temp_critical: gpu-trip-0 {
+					temperature = <110000>;
+					type = "critical";
+					hysteresis = <0>;
+				};
+			};
+		};
+
+		ve-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&ths 1>;
+
+			trips {
+				ve_temp_critical: ve-trip-0 {
+					temperature = <110000>;
+					type = "critical";
+					hysteresis = <0>;
+				};
+			};
+		};
+
+		ddr-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+			thermal-sensors = <&ths 3>;
+
+			trips {
+				ddr_temp_critical: ddr-trip-0 {
+					temperature = <110000>;
+					type = "critical";
+					hysteresis = <0>;
+				};
+			};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-longan-module-3h.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h618-longan-module-3h.dtsi
new file mode 100644
index 000000000000..8c1263a3939e
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-longan-module-3h.dtsi
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) Jisheng Zhang <jszhang@kernel.org>
+ */
+
+#include "sun50i-h616.dtsi"
+
+&mmc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc2_pins>;
+	vmmc-supply = <&reg_dldo1>;
+	vqmmc-supply = <&reg_aldo1>;
+	bus-width = <8>;
+	non-removable;
+	cap-mmc-hw-reset;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	status = "okay";
+};
+
+&r_i2c {
+	status = "okay";
+
+	axp313: pmic@36 {
+		compatible = "x-powers,axp313a";
+		reg = <0x36>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+
+		regulators {
+			reg_aldo1: aldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc-1v8-pll";
+			};
+
+			reg_dldo1: dldo1 {
+				regulator-always-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc-3v3-io";
+			};
+
+			reg_dcdc1: dcdc1 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <990000>;
+				regulator-name = "vdd-gpu-sys";
+			};
+
+			reg_dcdc2: dcdc2 {
+				regulator-always-on;
+				regulator-min-microvolt = <810000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-cpu";
+			};
+
+			reg_dcdc3: dcdc3 {
+				regulator-always-on;
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1100000>;
+				regulator-name = "vdd-dram";
+			};
+		};
+	};
+};
+
+&pio {
+	vcc-pc-supply = <&reg_dldo1>;
+	vcc-pf-supply = <&reg_dldo1>;
+	vcc-pg-supply = <&reg_aldo1>;
+	vcc-ph-supply = <&reg_dldo1>;
+	vcc-pi-supply = <&reg_dldo1>;
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-longanpi-3h.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-longanpi-3h.dts
new file mode 100644
index 000000000000..18b29c6b867f
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-longanpi-3h.dts
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) Jisheng Zhang <jszhang@kernel.org>
+ */
+
+/dts-v1/;
+
+#include "sun50i-h618-longan-module-3h.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	model = "Sipeed Longan Pi 3H";
+	compatible = "sipeed,longan-pi-3h", "sipeed,longan-module-3h", "allwinner,sun50i-h618";
+
+	aliases {
+		ethernet0 = &emac0;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			color = <LED_COLOR_ID_ORANGE>;
+			function = LED_FUNCTION_INDICATOR;
+			function-enumerator = <0>;
+			gpios = <&pio 6 2 GPIO_ACTIVE_LOW>; /* PG2 */
+		};
+
+		led-1 {
+			color = <LED_COLOR_ID_ORANGE>;
+			function = LED_FUNCTION_INDICATOR;
+			function-enumerator = <1>;
+			gpios = <&pio 6 4 GPIO_ACTIVE_LOW>; /* PG4 */
+		};
+	};
+
+	reg_vcc5v: regulator-vcc5v {
+		/* board wide 5V supply directly from the USB-C socket */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	reg_vcc3v3: regulator-vcc3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+		vin-supply = <&reg_vcc5v>;
+	};
+};
+
+&axp313 {
+	vin1-supply = <&reg_vcc5v>;
+	vin2-supply = <&reg_vcc5v>;
+	vin3-supply = <&reg_vcc5v>;
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&ehci2 {
+	status = "okay";
+};
+
+&ohci2 {
+	status = "okay";
+};
+
+/* WiFi & BT combo module is connected to this Host */
+&ehci3 {
+	status = "okay";
+};
+
+&ohci3 {
+	status = "okay";
+};
+
+&emac0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ext_rgmii_pins>;
+	phy-mode = "rgmii";
+	phy-handle = <&ext_rgmii_phy>;
+	allwinner,rx-delay-ps = <3100>;
+	allwinner,tx-delay-ps = <700>;
+	phy-supply = <&reg_vcc3v3>;
+	status = "okay";
+};
+
+&mdio0 {
+	ext_rgmii_phy: ethernet-phy@1 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <1>;
+	};
+};
+
+&mmc0 {
+	bus-width = <4>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;	/* PF6 */
+	vmmc-supply = <&reg_vcc3v3>;
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&usbotg {
+	/*
+	 * PHY0 pins are connected to a USB-C socket, but a role switch
+	 * is not implemented: both CC pins are pulled to GND.
+	 * The VBUS pins power the device, so a fixed peripheral mode
+	 * is the best choice.
+	 * The board can be powered via GPIOs, in this case port0 *can*
+	 * act as a host (with a cable/adapter ignoring CC), as VBUS is
+	 * then provided by the GPIOs. Any user of this setup would
+	 * need to adjust the DT accordingly: dr_mode set to "host",
+	 * enabling OHCI0 and EHCI0.
+	 */
+	dr_mode = "peripheral";
+	status = "okay";
+};
+
+&usbphy {
+	usb1_vbus-supply = <&reg_vcc5v>;
+	usb2_vbus-supply = <&reg_vcc5v>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts
index 8ea1fd41aeba..ac0a2b7ea6f3 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-transpeed-8k618-t.dts
@@ -15,6 +15,7 @@
 	compatible = "transpeed,8k618-t", "allwinner,sun50i-h618";
 
 	aliases {
+		ethernet1 = &sdio_wifi;
 		serial0 = &uart0;
 	};
 
@@ -39,6 +40,15 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		clocks = <&rtc CLK_OSC32K_FANOUT>;
+		clock-names = "ext_clock";
+		pinctrl-0 = <&x32clk_fanout_pin>;
+		pinctrl-names = "default";
+		reset-gpios = <&pio 6 18 GPIO_ACTIVE_LOW>; /* PG18 */
+	};
 };
 
 &ehci0 {
@@ -60,6 +70,19 @@
 	status = "okay";
 };
 
+&mmc1 {
+	vmmc-supply = <&reg_dldo1>;
+	vqmmc-supply = <&reg_aldo1>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+
+	sdio_wifi: wifi@1 {
+		reg = <1>;
+	};
+};
+
 &mmc2 {
 	vmmc-supply = <&reg_dldo1>;
 	vqmmc-supply = <&reg_aldo1>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h64-remix-mini-pc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h64-remix-mini-pc.dts
new file mode 100644
index 000000000000..b6e3c169797f
--- /dev/null
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h64-remix-mini-pc.dts
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+// Copyright (c) 2023 ARM Ltd.
+
+/dts-v1/;
+
+#include "sun50i-a64.dtsi"
+#include "sun50i-a64-cpu-opp.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	model = "Remix Mini PC";
+	compatible = "jide,remix-mini-pc", "allwinner,sun50i-h64",
+		     "allwinner,sun50i-a64";
+
+	aliases {
+		ethernet1 = &rtl8723bs;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	reg_vcc5v: regulator-5v {
+		/* board wide 5V supply directly from the DC input */
+		compatible = "regulator-fixed";
+		regulator-name = "vcc-5v";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+	};
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&r_pio 0 2 GPIO_ACTIVE_LOW>; /* PL2 */
+		post-power-on-delay-ms = <200>;
+	};
+};
+
+&codec {
+	status = "okay";
+};
+
+&codec_analog {
+	cpvdd-supply = <&reg_eldo1>;
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
+&cpu1 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
+&cpu2 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
+&cpu3 {
+	cpu-supply = <&reg_dcdc2>;
+};
+
+&dai {
+	status = "okay";
+};
+
+&de {
+	status = "okay";
+};
+
+&ehci0 {
+	status = "okay";
+};
+
+&ehci1 {
+	status = "okay";
+};
+
+&hdmi {
+	hvcc-supply = <&reg_dldo1>;
+	status = "okay";
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+/* Connects to the AC200 chip */
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	status = "okay";
+};
+
+&i2c0_pins {
+	bias-pull-up;
+};
+
+&mmc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc0_pins>;
+	vmmc-supply = <&reg_dcdc1>;
+	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	bus-width = <4>;
+	status = "okay";
+};
+
+&mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc1_pins>;
+	vmmc-supply = <&reg_aldo1>;
+	vqmmc-supply = <&reg_dldo4>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	bus-width = <4>;
+	non-removable;
+	status = "okay";
+
+	rtl8723bs: wifi@1 {
+		reg = <1>;
+		interrupt-parent = <&r_pio>;
+		interrupts = <0 3 IRQ_TYPE_LEVEL_LOW>; /* PL3 */
+		interrupt-names = "host-wake";
+	};
+};
+
+&mmc2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc2_pins>, <&mmc2_ds_pin>;
+	vmmc-supply = <&reg_dcdc1>;
+	vqmmc-supply = <&reg_eldo1>;
+	bus-width = <8>;
+	non-removable;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	cap-mmc-hw-reset;
+	status = "okay";
+};
+
+&ohci0 {
+	status = "okay";
+};
+
+&ohci1 {
+	status = "okay";
+};
+
+&pio {
+	vcc-pb-supply = <&reg_dcdc1>;
+	vcc-pc-supply = <&reg_dcdc1>;
+	vcc-pd-supply = <&reg_dcdc1>;
+	vcc-pe-supply = <&reg_dcdc1>;
+	vcc-pf-supply = <&reg_dcdc1>;
+	vcc-pg-supply = <&reg_dldo4>;
+	vcc-ph-supply = <&reg_dcdc1>;
+};
+
+&r_ir {
+	status = "okay";
+};
+
+&r_pio {
+	/*
+	 * We cannot add that supply for now since it would create a circular
+	 * dependency between pinctrl, the regulator and the RSB Bus.
+	 *
+	 * vcc-pl-supply = <&reg_aldo2>;
+	 */
+};
+
+&r_rsb {
+	status = "okay";
+
+	axp803: pmic@3a3 {
+		compatible = "x-powers,axp803";
+		reg = <0x3a3>;
+		interrupt-parent = <&r_intc>;
+		interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_LOW>;
+		x-powers,drive-vbus-en;
+
+		vin1-supply = <&reg_vcc5v>;
+		vin2-supply = <&reg_vcc5v>;
+		vin3-supply = <&reg_vcc5v>;
+		vin5-supply = <&reg_vcc5v>;
+		vin6-supply = <&reg_vcc5v>;
+		aldoin-supply = <&reg_vcc5v>;
+		dldoin-supply = <&reg_vcc5v>;
+		eldoin-supply = <&reg_vcc5v>;
+		fldoin-supply = <&reg_vcc5v>;
+		drivevbus-supply = <&reg_vcc5v>;
+		ips-supply = <&reg_vcc5v>;
+
+		status = "okay";
+	};
+};
+
+#include "axp803.dtsi"
+
+&ac_power_supply {
+	status = "okay";
+};
+
+&reg_dcdc1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-3v3";
+};
+
+&reg_dcdc2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1040000>;
+	regulator-max-microvolt = <1300000>;
+	regulator-name = "vdd-cpux";
+};
+
+/* DCDC3 is polyphased with DCDC2 */
+
+&reg_dcdc5 {
+	regulator-always-on;
+	regulator-min-microvolt = <1500000>;
+	regulator-max-microvolt = <1500000>;
+	regulator-name = "vcc-dram";
+};
+
+/* Deviates from the reset default of 1.1V. */
+&reg_dcdc6 {
+	regulator-always-on;
+	regulator-min-microvolt = <1200000>;
+	regulator-max-microvolt = <1200000>;
+	regulator-name = "vdd-sys";
+};
+
+&reg_aldo1 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi";
+};
+
+&reg_aldo2 {
+	/* Specifying R_PIO consumer would create circular dependency. */
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-pl";
+};
+
+&reg_aldo3 {
+	regulator-always-on;
+	regulator-min-microvolt = <3000000>;
+	regulator-max-microvolt = <3000000>;
+	regulator-name = "vcc-pll-avcc";
+};
+
+/* AC200 power supply */
+&reg_dldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-ave-33";
+};
+
+&reg_dldo4 {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+	regulator-name = "vcc-wifi-io";
+};
+
+&reg_drivevbus {
+	regulator-name = "usb0-vbus";
+	status = "okay";
+};
+
+&reg_eldo1 {
+	regulator-always-on;
+	regulator-min-microvolt = <1800000>;
+	regulator-max-microvolt = <1800000>;
+	regulator-name = "vcc-cpvdd-dram-emmc";
+};
+
+/* Supplies the arisc management core, needed by TF-A to power off cores. */
+&reg_fldo2 {
+	regulator-always-on;
+	regulator-min-microvolt = <1100000>;
+	regulator-max-microvolt = <1100000>;
+	regulator-name = "vdd-cpus";
+};
+
+&reg_rtc_ldo {
+	regulator-name = "vcc-rtc";
+};
+
+&simplefb_hdmi {
+	vcc-hdmi-supply = <&reg_dcdc1>;
+};
+
+&sound {
+	simple-audio-card,aux-devs = <&codec_analog>;
+	simple-audio-card,widgets = "Microphone", "Microphone Jack",
+				    "Headphone", "Headphone Jack";
+	simple-audio-card,routing =
+			"Left DAC", "DACL",
+			"Right DAC", "DACR",
+			"Headphone Jack", "HP",
+			"ADCL", "Left ADC",
+			"ADCR", "Right ADC",
+			"MIC2", "Microphone Jack";
+	status = "okay";
+};
+
+/* On the (unpopulated) UART pads. */
+&uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_pb_pins>;
+	status = "okay";
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>, <&uart1_rts_cts_pins>;
+	uart-has-rtscts;
+	status = "okay";
+
+	bluetooth {
+		compatible = "realtek,rtl8723bs-bt";
+		enable-gpios = <&r_pio 0 4 GPIO_ACTIVE_HIGH>; /* PL4 */
+		max-speed = <1500000>;
+	};
+};
+
+&usb_otg {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy {
+	usb0_vbus-supply = <&reg_drivevbus>;
+	usb1_vbus-supply = <&reg_drivevbus>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
index dccbba6e7f98..dbf2dce8d1d6 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi
@@ -145,7 +145,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <160>;
 			al,msi-num-spis = <160>;
diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
index 39481d7fd7d4..3ea178acdddf 100644
--- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
+++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi
@@ -355,7 +355,6 @@
 		msix: msix@fbe00000 {
 			compatible = "al,alpine-msix";
 			reg = <0x0 0xfbe00000 0x0 0x100000>;
-			interrupt-controller;
 			msi-controller;
 			al,msi-base-spi = <336>;
 			al,msi-num-spis = <959>;
diff --git a/arch/arm64/boot/dts/amlogic/Makefile b/arch/arm64/boot/dts/amlogic/Makefile
index cc8b34bd583d..1ab160bf928a 100644
--- a/arch/arm64/boot/dts/amlogic/Makefile
+++ b/arch/arm64/boot/dts/amlogic/Makefile
@@ -8,6 +8,8 @@ dtb-$(CONFIG_ARCH_MESON) += meson-axg-jethome-jethub-j100.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-axg-jethome-jethub-j110-rev-2.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-axg-jethome-jethub-j110-rev-3.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-axg-s400.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-g12a-fbx8am-brcm.dtb
+dtb-$(CONFIG_ARCH_MESON) += meson-g12a-fbx8am-realtek.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-g12a-radxa-zero.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-g12a-sei510.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-g12a-u200.dtb
@@ -80,3 +82,7 @@ dtb-$(CONFIG_ARCH_MESON) += meson-sm1-odroid-hc4.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-sm1-sei610.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-sm1-x96-air-gbit.dtb
 dtb-$(CONFIG_ARCH_MESON) += meson-sm1-x96-air.dtb
+
+# Overlays
+meson-g12a-fbx8am-brcm-dtbs	:= meson-g12a-fbx8am.dtb meson-g12a-fbx8am-brcm.dtbo
+meson-g12a-fbx8am-realtek-dtbs	:= meson-g12a-fbx8am.dtb meson-g12a-fbx8am-realtek.dtbo
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
index 2ad1f8eef199..32a754fe7990 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-c3.dtsi
@@ -6,6 +6,7 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/reset/amlogic,c3-reset.h>
 
 / {
 	cpus {
@@ -81,6 +82,12 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xfe000000 0x0 0x480000>;
 
+			reset: reset-controller@2000 {
+				compatible = "amlogic,c3-reset";
+				reg = <0x0 0x2000 0x0 0x98>;
+				#reset-cells = <1>;
+			};
+
 			watchdog@2100 {
 				compatible = "amlogic,c3-wdt", "amlogic,t7-wdt";
 				reg = <0x0 0x2100 0x0 0x10>;
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
index a03c7667d2b6..5248bdf824ea 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
@@ -54,7 +54,7 @@
 			enable-method = "psci";
 		};
 
-		cpu101: cpu@101{
+		cpu101: cpu@101 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a53";
 			reg = <0x0 0x101>;
@@ -171,6 +171,16 @@
 				};
 			};
 
+			gpio_intc: interrupt-controller@4080 {
+				compatible = "amlogic,t7-gpio-intc",
+					     "amlogic,meson-gpio-intc";
+				reg = <0x0 0x4080 0x0 0x20>;
+				interrupt-controller;
+				#interrupt-cells = <2>;
+				amlogic,channel-interrupts =
+					<10 11 12 13 14 15 16 17 18 19 20 21>;
+			};
+
 			uart_a: serial@78000 {
 				compatible = "amlogic,t7-uart", "amlogic,meson-s4-uart";
 				reg = <0x0 0x78000 0x0 0x18>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-a1-ad402.dts b/arch/arm64/boot/dts/amlogic/meson-a1-ad402.dts
index 1c20516fa653..4bc30af05848 100644
--- a/arch/arm64/boot/dts/amlogic/meson-a1-ad402.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-a1-ad402.dts
@@ -106,7 +106,7 @@
 	pinctrl-0 = <&spifc_pins>;
 	pinctrl-names = "default";
 
-	spi_nand@0 {
+	flash@0 {
 		compatible = "spi-nand";
 		status = "okay";
 		reg = <0>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-a1.dtsi b/arch/arm64/boot/dts/amlogic/meson-a1.dtsi
index 648e7f49424f..c03e207ea6c5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-a1.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-a1.dtsi
@@ -450,6 +450,8 @@
 				 <&clkc_periphs CLKID_USB_BUS>,
 				 <&clkc_periphs CLKID_USB_CTRL_IN>;
 			clock-names = "usb_ctrl", "usb_bus", "xtal_usb_ctrl";
+			assigned-clocks = <&clkc_periphs CLKID_USB_BUS>;
+			assigned-clock-rates = <64000000>;
 			resets = <&reset RESET_USBCTRL>;
 			reset-name = "usb_ctrl";
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j1xx.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j1xx.dtsi
index db605f3a22b4..9b65ae818e2f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j1xx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j1xx.dtsi
@@ -35,7 +35,7 @@
 		reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -44,7 +44,7 @@
 		regulator-always-on;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC5V";
 		regulator-min-microvolt = <5000000>;
@@ -52,7 +52,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -61,7 +61,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -70,7 +70,7 @@
 		regulator-always-on;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <3300000>;
@@ -79,7 +79,7 @@
 		regulator-always-on;
 	};
 
-	vccq_1v8: regulator-vccq_1v8 {
+	vccq_1v8: regulator-vccq-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCCQ_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -88,7 +88,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr: regulator-usb_pwr {
+	usb_pwr: regulator-usb-pwr {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR";
 		regulator-min-microvolt = <5000000>;
@@ -332,19 +332,3 @@
 		"", "", "", "", "", // 80 - 84
 		"", ""; // 85-86
 };
-
-&cpu0 {
-	#cooling-cells = <2>;
-};
-
-&cpu1 {
-	#cooling-cells = <2>;
-};
-
-&cpu2 {
-	#cooling-cells = <2>;
-};
-
-&cpu3 {
-	#cooling-cells = <2>;
-};
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
index c8905663bc75..7ed526f45175 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts
@@ -12,7 +12,7 @@
 	compatible = "amlogic,s400", "amlogic,a113d", "amlogic,meson-axg";
 	model = "Amlogic Meson AXG S400 Development Board";
 
-	adc_keys {
+	keys {
 		compatible = "adc-keys";
 		io-channels = <&saradc 0>;
 		io-channel-names = "buttons";
@@ -111,7 +111,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	main_12v: regulator-main_12v {
+	main_12v: regulator-main-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "12V";
 		regulator-min-microvolt = <12000000>;
@@ -119,7 +119,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -128,7 +128,7 @@
 		regulator-always-on;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC5V";
 		regulator-min-microvolt = <5000000>;
@@ -139,7 +139,7 @@
 		enable-active-high;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -148,7 +148,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -157,7 +157,7 @@
 		regulator-always-on;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
@@ -166,7 +166,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr: regulator-usb_pwr {
+	usb_pwr: regulator-usb-pwr {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index 7e5ac9db93f8..6d12b760b90f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -74,6 +74,8 @@
 			enable-method = "psci";
 			next-level-cache = <&l2>;
 			clocks = <&scpi_dvfs 0>;
+			dynamic-power-coefficient = <140>;
+			#cooling-cells = <2>;
 		};
 
 		cpu1: cpu@1 {
@@ -83,6 +85,8 @@
 			enable-method = "psci";
 			next-level-cache = <&l2>;
 			clocks = <&scpi_dvfs 0>;
+			dynamic-power-coefficient = <140>;
+			#cooling-cells = <2>;
 		};
 
 		cpu2: cpu@2 {
@@ -92,6 +96,8 @@
 			enable-method = "psci";
 			next-level-cache = <&l2>;
 			clocks = <&scpi_dvfs 0>;
+			dynamic-power-coefficient = <140>;
+			#cooling-cells = <2>;
 		};
 
 		cpu3: cpu@3 {
@@ -101,6 +107,8 @@
 			enable-method = "psci";
 			next-level-cache = <&l2>;
 			clocks = <&scpi_dvfs 0>;
+			dynamic-power-coefficient = <140>;
+			#cooling-cells = <2>;
 		};
 
 		l2: l2-cache0 {
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index ff68b911b729..9d5eab6595d0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -2502,6 +2502,9 @@
 		clocks = <&clkc CLKID_NNA_CORE_CLK>,
 			 <&clkc CLKID_NNA_AXI_CLK>;
 		clock-names = "core", "bus";
+		assigned-clocks = <&clkc CLKID_NNA_CORE_CLK>,
+				  <&clkc CLKID_NNA_AXI_CLK>;
+		assigned-clock-rates = <800000000>, <800000000>;
 		resets = <&reset RESET_NNA>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-brcm.dtso b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-brcm.dtso
new file mode 100644
index 000000000000..9591fdc31ee0
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-brcm.dtso
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+// Copyright (c) 2024 Freebox SAS
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/meson-g12a-gpio.h>
+
+&uart_A {
+	bluetooth {
+		compatible = "brcm,bcm43438-bt";
+		shutdown-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
+		max-speed = <2000000>;
+		clocks = <&wifi32k>;
+		clock-names = "lpo";
+		vbat-supply = <&vddao_3v3>;
+		vddio-supply = <&vddio_ao1v8>;
+	};
+};
+
+&sd_emmc_a {
+	/* Per mmc-controller.yaml */
+	#address-cells = <1>;
+	#size-cells = <0>;
+	/* NB: may be either AP6398S or AP6398SR3 wifi module */
+	brcmf: wifi@1 {
+		reg = <1>;
+		compatible = "brcm,bcm4329-fmac";
+	};
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-realtek.dtso b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-realtek.dtso
new file mode 100644
index 000000000000..55fff35b09ae
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am-realtek.dtso
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+// Copyright (c) 2024 Freebox SAS
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/gpio/meson-g12a-gpio.h>
+
+&uart_A {
+	bluetooth {
+		compatible = "realtek,rtl8822cs-bt";
+		enable-gpios = <&gpio GPIOX_17 GPIO_ACTIVE_HIGH>;
+		host-wake-gpios = <&gpio GPIOX_19 GPIO_ACTIVE_HIGH>;
+		device-wake-gpios = <&gpio GPIOX_18 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&sd_emmc_a {
+	/* No explicit compatible for rtl8822cs sdio */
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts
new file mode 100644
index 000000000000..af211d8f3952
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-fbx8am.dts
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+// Copyright (c) 2024 Freebox SAS
+
+/*
+ * SEI codename: SEI530FB (based on SEI510)
+ * Freebox codename: fbx8am
+ * Commercial names: Freebox Pop, Player TV Free 4K
+ */
+
+/dts-v1/;
+
+#include "meson-g12a.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/gpio/meson-g12a-gpio.h>
+#include <dt-bindings/sound/meson-g12a-tohdmitx.h>
+
+/ {
+	compatible = "freebox,fbx8am", "amlogic,g12a";
+	model = "Freebox Player Pop";
+	chassis-type = "embedded";
+
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+	};
+
+	gpio-keys-polled {
+		compatible = "gpio-keys-polled";
+		poll-interval = <100>;
+
+		/* Physical user-accessible reset button near USB port */
+		power-button {
+			label = "Reset";
+			linux,code = <BTN_MISC>;
+			gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>;
+		};
+	};
+
+	spdif_dit: audio-codec-2 {
+		#sound-dai-cells = <0>;
+		compatible = "linux,spdif-dit";
+		status = "okay";
+		sound-name-prefix = "DIT";
+	};
+
+	aliases {
+		serial0 = &uart_AO;
+		ethernet0 = &ethmac;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		reset-gpios = <&gpio BOOT_12 GPIO_ACTIVE_LOW>;
+	};
+
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&hdmi_tx_tmds_out>;
+			};
+		};
+	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x80000000>;
+	};
+
+	ao_5v: regulator-ao-5v {
+		compatible = "regulator-fixed";
+		regulator-name = "AO_5V";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_in>;
+		regulator-always-on;
+	};
+
+	dc_in: regulator-dc-in {
+		compatible = "regulator-fixed";
+		regulator-name = "DC_IN";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		regulator-always-on;
+	};
+
+	emmc_1v8: regulator-emmc-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "EMMC_1V8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vddao_3v3>;
+		regulator-always-on;
+	};
+
+	vddao_3v3: regulator-vddao-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VDDAO_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&ao_5v>;
+		regulator-always-on;
+	};
+
+	vddao_3v3_t: regulator-vddao-3v3-t {
+		compatible = "regulator-fixed";
+		regulator-name = "VDDAO_3V3_T";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vddao_3v3>;
+		gpio = <&gpio GPIOH_8 GPIO_OPEN_DRAIN>;
+		enable-active-high;
+	};
+
+	vddcpu: regulator-vddcpu {
+		/*
+		 * SY8120B1ABC DC/DC Regulator.
+		 */
+		compatible = "pwm-regulator";
+
+		regulator-name = "VDDCPU";
+		regulator-min-microvolt = <721000>;
+		regulator-max-microvolt = <1022000>;
+
+		pwm-supply = <&ao_5v>;
+
+		pwms = <&pwm_AO_cd 1 1250 0>;
+		pwm-dutycycle-range = <100 0>;
+
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	vddio_ao1v8: regulator-vddio-ao1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "VDDIO_AO1V8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&vddao_3v3>;
+		regulator-always-on;
+	};
+
+	sdio_pwrseq: sdio-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		reset-gpios = <&gpio GPIOX_6 GPIO_ACTIVE_LOW>;
+		post-power-on-delay-ms = <10>; /* required for 43752 */
+		clocks = <&wifi32k>;
+		clock-names = "ext_clock";
+	};
+
+	wifi32k: wifi32k {
+		compatible = "pwm-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+		pwms = <&pwm_ef 0 30518 0>; /* PWM_E at 32.768KHz */
+	};
+
+	sound {
+		compatible = "amlogic,axg-sound-card";
+		model = "fbx8am";
+		audio-aux-devs = <&tdmout_b>;
+		audio-routing = "TDMOUT_B IN 0", "FRDDR_A OUT 1",
+				"TDMOUT_B IN 1", "FRDDR_B OUT 1",
+				"TDMOUT_B IN 2", "FRDDR_C OUT 1",
+				"TDM_B Playback", "TDMOUT_B OUT",
+				"SPDIFOUT_A IN 0", "FRDDR_A OUT 3",
+				"SPDIFOUT_A IN 1", "FRDDR_B OUT 3",
+				"SPDIFOUT_A IN 2", "FRDDR_C OUT 3";
+
+		assigned-clocks = <&clkc CLKID_MPLL2>,
+				  <&clkc CLKID_MPLL0>,
+				  <&clkc CLKID_MPLL1>;
+		assigned-clock-parents = <0>, <0>, <0>;
+		assigned-clock-rates = <294912000>,
+				       <270950400>,
+				       <393216000>;
+
+		dai-link-0 {
+			sound-dai = <&frddr_a>;
+		};
+
+		dai-link-1 {
+			sound-dai = <&frddr_b>;
+		};
+
+		dai-link-2 {
+			sound-dai = <&frddr_c>;
+		};
+
+		/* 8ch hdmi interface */
+		dai-link-3 {
+			sound-dai = <&tdmif_b>;
+			dai-format = "i2s";
+			dai-tdm-slot-tx-mask-0 = <1 1>;
+			dai-tdm-slot-tx-mask-1 = <1 1>;
+			dai-tdm-slot-tx-mask-2 = <1 1>;
+			dai-tdm-slot-tx-mask-3 = <1 1>;
+			mclk-fs = <256>;
+
+			codec {
+				sound-dai = <&tohdmitx TOHDMITX_I2S_IN_B>;
+			};
+		};
+
+		/* spdif hdmi or toslink interface */
+		dai-link-4 {
+			sound-dai = <&spdifout_a>;
+
+			codec-0 {
+			sound-dai = <&spdif_dit>;
+			};
+
+			codec-1 {
+				sound-dai = <&tohdmitx TOHDMITX_SPDIF_IN_A>;
+			};
+		};
+
+		/* spdif hdmi interface */
+		dai-link-5 {
+			sound-dai = <&spdifout_b>;
+
+			codec {
+				sound-dai = <&tohdmitx TOHDMITX_SPDIF_IN_B>;
+			};
+		};
+
+		/* hdmi glue */
+		dai-link-6 {
+			sound-dai = <&tohdmitx TOHDMITX_I2S_OUT>;
+
+			codec {
+				sound-dai = <&hdmi_tx>;
+			};
+		};
+	};
+};
+
+&arb {
+	status = "okay";
+};
+
+&cecb_AO {
+	pinctrl-0 = <&cec_ao_b_h_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+	hdmi-phandle = <&hdmi_tx>;
+};
+
+&clkc_audio {
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&vddcpu>;
+	operating-points-v2 = <&cpu_opp_table>;
+	clocks = <&clkc CLKID_CPU_CLK>;
+	clock-latency = <50000>;
+};
+
+&cpu1 {
+	cpu-supply = <&vddcpu>;
+	operating-points-v2 = <&cpu_opp_table>;
+	clocks = <&clkc CLKID_CPU_CLK>;
+	clock-latency = <50000>;
+};
+
+&cpu2 {
+	cpu-supply = <&vddcpu>;
+	operating-points-v2 = <&cpu_opp_table>;
+	clocks = <&clkc CLKID_CPU_CLK>;
+	clock-latency = <50000>;
+};
+
+&cpu3 {
+	cpu-supply = <&vddcpu>;
+	operating-points-v2 = <&cpu_opp_table>;
+	clocks = <&clkc CLKID_CPU_CLK>;
+	clock-latency = <50000>;
+};
+
+&ethmac {
+	status = "okay";
+	phy-handle = <&internal_ephy>;
+	phy-mode = "rmii";
+};
+
+&frddr_a {
+	status = "okay";
+};
+
+&frddr_b {
+	status = "okay";
+};
+
+&frddr_c {
+	status = "okay";
+};
+
+&spdifout_a {
+	pinctrl-0 = <&spdif_out_h_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&spdifout_b {
+	status = "okay";
+};
+
+&hdmi_tx {
+	status = "okay";
+	pinctrl-0 = <&hdmitx_hpd_pins>, <&hdmitx_ddc_pins>;
+	pinctrl-names = "default";
+};
+
+&hdmi_tx_tmds_port {
+	hdmi_tx_tmds_out: endpoint {
+		remote-endpoint = <&hdmi_connector_in>;
+	};
+};
+
+&i2c3 {
+	status = "okay";
+	pinctrl-0 = <&i2c3_sda_a_pins>, <&i2c3_sck_a_pins>;
+	pinctrl-names = "default";
+};
+
+&ir {
+	status = "okay";
+	pinctrl-0 = <&remote_input_ao_pins>;
+	pinctrl-names = "default";
+};
+
+&pwm_AO_cd {
+	pinctrl-0 = <&pwm_ao_d_e_pins>;
+	pinctrl-names = "default";
+	clocks = <&xtal>;
+	clock-names = "clkin1";
+	status = "okay";
+};
+
+&pwm_ef {
+	status = "okay";
+	pinctrl-0 = <&pwm_e_pins>;
+	pinctrl-names = "default";
+	clocks = <&xtal>;
+	clock-names = "clkin0";
+};
+
+&pdm {
+	pinctrl-0 = <&pdm_din0_z_pins>, <&pdm_din1_z_pins>,
+		    <&pdm_din2_z_pins>, <&pdm_din3_z_pins>,
+		    <&pdm_dclk_z_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&saradc {
+	status = "okay";
+	vref-supply = <&vddio_ao1v8>;
+};
+
+/* SDIO */
+&sd_emmc_a {
+	status = "okay";
+	pinctrl-0 = <&sdio_pins>;
+	pinctrl-1 = <&sdio_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	bus-width = <4>;
+	cap-sd-highspeed;
+	sd-uhs-sdr50;
+	max-frequency = <100000000>;
+
+	non-removable;
+	disable-wp;
+
+	/* WiFi firmware requires power to be kept while in suspend */
+	keep-power-in-suspend;
+
+	mmc-pwrseq = <&sdio_pwrseq>;
+
+	vmmc-supply = <&vddao_3v3>;
+	vqmmc-supply = <&vddio_ao1v8>;
+};
+
+/* SD card */
+&sd_emmc_b {
+	status = "okay";
+	pinctrl-0 = <&sdcard_c_pins>;
+	pinctrl-1 = <&sdcard_clk_gate_c_pins>;
+	pinctrl-names = "default", "clk-gate";
+
+	bus-width = <4>;
+	cap-sd-highspeed;
+	max-frequency = <50000000>;
+	disable-wp;
+
+	cd-gpios = <&gpio GPIOC_6 GPIO_ACTIVE_LOW>;
+	vmmc-supply = <&vddao_3v3>;
+	vqmmc-supply = <&vddao_3v3>;
+};
+
+/* eMMC */
+&sd_emmc_c {
+	status = "okay";
+	pinctrl-0 = <&emmc_ctrl_pins>, <&emmc_data_8b_pins>, <&emmc_ds_pins>;
+	pinctrl-1 = <&emmc_clk_gate_pins>;
+	pinctrl-names = "default", "clk-gate";
+
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	max-frequency = <200000000>;
+	non-removable;
+	disable-wp;
+
+	mmc-pwrseq = <&emmc_pwrseq>;
+	vmmc-supply = <&vddao_3v3>;
+	vqmmc-supply = <&emmc_1v8>;
+};
+
+&tdmif_b {
+	status = "okay";
+};
+
+&tdmout_b {
+	status = "okay";
+};
+
+&tohdmitx {
+	status = "okay";
+};
+
+&uart_A {
+	status = "okay";
+	pinctrl-0 = <&uart_a_pins>, <&uart_a_cts_rts_pins>;
+	pinctrl-names = "default";
+	uart-has-rtscts;
+};
+
+&uart_AO {
+	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
+};
+
+&usb {
+	status = "okay";
+	dr_mode = "host";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
index fcd7e1d8e16f..15b9bc280706 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-radxa-zero.dts
@@ -60,7 +60,7 @@
 		clock-names = "ext_clock";
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -68,7 +68,7 @@
 		regulator-always-on;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -77,7 +77,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -86,7 +86,7 @@
 		regulator-always-on;
 	};
 
-	hdmi_pw: regulator-hdmi_pw {
+	hdmi_pw: regulator-hdmi-pw {
 		compatible = "regulator-fixed";
 		regulator-name = "HDMI_PW";
 		regulator-min-microvolt = <5000000>;
@@ -95,7 +95,7 @@
 		regulator-always-on;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -104,7 +104,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
index 4c4550dd4711..61cb8135a392 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-sei510.dts
@@ -15,7 +15,7 @@
 	compatible = "seirobotics,sei510", "amlogic,g12a";
 	model = "SEI Robotics SEI510";
 
-	adc_keys {
+	keys {
 		compatible = "adc-keys";
 		io-channels = <&saradc 0>;
 		io-channel-names = "buttons";
@@ -83,7 +83,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -92,7 +92,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -100,7 +100,7 @@
 		regulator-always-on;
 	};
 
-	emmc_1v8: regulator-emmc_1v8 {
+	emmc_1v8: regulator-emmc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "EMMC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -109,7 +109,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -118,7 +118,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3_t: regultor-vddao_3v3_t {
+	vddao_3v3_t: regulator-vddao-3v3-t {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3_T";
 		regulator-min-microvolt = <3300000>;
@@ -147,7 +147,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao1v8: regulator-vddio_ao1v8 {
+	vddio_ao1v8: regulator-vddio-ao1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO1V8";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
index 8355ddd7e9ae..3da7922d83f1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-u200.dts
@@ -75,7 +75,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	flash_1v8: regulator-flash_1v8 {
+	flash_1v8: regulator-flash-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "FLASH_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -84,7 +84,7 @@
 		regulator-always-on;
 	};
 
-	main_12v: regulator-main_12v {
+	main_12v: regulator-main-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "12V";
 		regulator-min-microvolt = <12000000>;
@@ -92,7 +92,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr_en: regulator-usb_pwr_en {
+	usb_pwr_en: regulator-usb-pwr-en {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR_EN";
 		regulator-min-microvolt = <5000000>;
@@ -103,7 +103,7 @@
 		enable-active-high;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -112,7 +112,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -122,7 +122,7 @@
 		/* FIXME: actually controlled by VDDCPU_B_EN */
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_5V";
 		regulator-min-microvolt = <5000000>;
@@ -133,7 +133,7 @@
 		enable-active-high;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -142,7 +142,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
index 9b55982b6a6b..05c7a1e3f1b7 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12a-x96-max.dts
@@ -66,7 +66,7 @@
 		clock-names = "ext_clock";
 	};
 
-	flash_1v8: regulator-flash_1v8 {
+	flash_1v8: regulator-flash-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "FLASH_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -75,7 +75,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -83,7 +83,7 @@
 		regulator-always-on;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -92,7 +92,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -102,7 +102,7 @@
 		/* FIXME: actually controlled by VDDCPU_B_EN */
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_5V";
 		regulator-min-microvolt = <5000000>;
@@ -112,7 +112,7 @@
 		gpio = <&gpio GPIOH_8 GPIO_OPEN_DRAIN>;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -121,7 +121,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi
index 91c9769fda20..d80dd9a3da31 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2.dtsi
@@ -19,7 +19,7 @@
 		status = "okay";
 	};
 
-	hub_5v: regulator-hub_5v {
+	hub_5v: regulator-hub-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "HUB_5V";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
index 9e12a34b2840..09d959aefb18 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid.dtsi
@@ -48,7 +48,7 @@
 		};
 	};
 
-	tflash_vdd: regulator-tflash_vdd {
+	tflash_vdd: regulator-tflash-vdd {
 		compatible = "regulator-fixed";
 
 		regulator-name = "TFLASH_VDD";
@@ -60,7 +60,7 @@
 		regulator-always-on;
 	};
 
-	tf_io: gpio-regulator-tf_io {
+	tf_io: gpio-regulator-tf-io {
 		compatible = "regulator-gpio";
 
 		regulator-name = "TF_IO";
@@ -74,7 +74,7 @@
 			 <1800000 1>;
 	};
 
-	flash_1v8: regulator-flash_1v8 {
+	flash_1v8: regulator-flash-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "FLASH_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -83,7 +83,7 @@
 		regulator-always-on;
 	};
 
-	main_12v: regulator-main_12v {
+	main_12v: regulator-main-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "12V";
 		regulator-min-microvolt = <12000000>;
@@ -91,7 +91,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr_en: regulator-usb_pwr_en {
+	usb_pwr_en: regulator-usb-pwr-en {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR_EN";
 		regulator-min-microvolt = <5000000>;
@@ -103,7 +103,7 @@
 		enable-active-high;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "5V";
 		regulator-min-microvolt = <5000000>;
@@ -114,7 +114,7 @@
 		enable-active-high;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -123,7 +123,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -171,7 +171,7 @@
 		regulator-always-on;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -180,7 +180,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
index ac8b7178257e..4cb6930ffb19 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-w400.dtsi
@@ -39,7 +39,7 @@
 		clock-names = "ext_clock";
 	};
 
-	flash_1v8: regulator-flash_1v8 {
+	flash_1v8: regulator-flash-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "FLASH_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -48,7 +48,7 @@
 		regulator-always-on;
 	};
 
-	main_12v: regulator-main_12v {
+	main_12v: regulator-main-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "12V";
 		regulator-min-microvolt = <12000000>;
@@ -56,7 +56,7 @@
 		regulator-always-on;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_5V";
 		regulator-min-microvolt = <5000000>;
@@ -67,7 +67,7 @@
 		enable-active-high;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -76,7 +76,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
index 5e7b9273b062..efd662a452e8 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-libretech-pc.dtsi
@@ -84,7 +84,7 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -93,7 +93,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -120,7 +120,7 @@
 		};
 	};
 
-	vcc_card: regulator-vcc_card {
+	vcc_card: regulator-vcc-card {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_CARD";
 		regulator-min-microvolt = <3300000>;
@@ -141,7 +141,7 @@
 		gpio = <&gpio GPIOH_3 GPIO_OPEN_DRAIN>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -150,7 +150,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao3v3: regulator-vddio_ao3v3 {
+	vddio_ao3v3: regulator-vddio-ao3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO3V3";
 		regulator-min-microvolt = <3300000>;
@@ -159,7 +159,7 @@
 		regulator-always-on;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index e59c3c92b1e7..08d6b69ba469 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -50,28 +50,28 @@
 		regulator-always-on;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
index 4aab1ab705b4..cca129ce2c58 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts
@@ -78,21 +78,21 @@
 			 <3300000 1>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index e6d2de7c45a9..c431986e6a33 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -67,7 +67,7 @@
 		regulator-always-on;
 	};
 
-	hdmi_p5v0: regulator-hdmi_p5v0 {
+	hdmi_p5v0: regulator-hdmi-p5v0 {
 		compatible = "regulator-fixed";
 		regulator-name = "HDMI_P5V0";
 		regulator-min-microvolt = <5000000>;
@@ -76,7 +76,7 @@
 		vin-supply = <&p5v0>;
 	};
 
-	tflash_vdd: regulator-tflash_vdd {
+	tflash_vdd: regulator-tflash-vdd {
 		compatible = "regulator-fixed";
 
 		regulator-name = "TFLASH_VDD";
@@ -92,7 +92,7 @@
 		vin-supply = <&vddio_ao3v3>;
 	};
 
-	tf_io: gpio-regulator-tf_io {
+	tf_io: gpio-regulator-tf-io {
 		compatible = "regulator-gpio";
 
 		regulator-name = "TF_IO";
@@ -148,7 +148,7 @@
 		vin-supply = <&p5v0>;
 	};
 
-	ddr3_1v5: regulator-ddr3_1v5 {
+	ddr3_1v5: regulator-ddr3-1v5 {
 		compatible = "regulator-fixed";
 		regulator-name = "DDR3_1V5";
 		regulator-min-microvolt = <1500000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
index 591455c50e88..7f94716876d3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p200.dts
@@ -21,14 +21,14 @@
 		sound-name-prefix = "DIT";
 	};
 
-	avdd18_usb_adc: regulator-avdd18_usb_adc {
+	avdd18_usb_adc: regulator-avdd18-usb-adc {
 		compatible = "regulator-fixed";
 		regulator-name = "AVDD18_USB_ADC";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	adc_keys {
+	keys {
 		compatible = "adc-keys";
 		io-channels = <&saradc 0>;
 		io-channel-names = "buttons";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
index e803a466fe4e..52d57773a77f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi
@@ -53,21 +53,21 @@
 		regulator-settling-time-down-us = <150000>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
index 74df32534231..255e93a0b36d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi
@@ -47,28 +47,28 @@
 		enable-active-high;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
index 94dafb955301..deb295227189 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi
@@ -49,21 +49,21 @@
 		enable-active-high;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -71,7 +71,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
index a29b49f051ae..90ef9c17d80b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
@@ -42,7 +42,7 @@
 		};
 	};
 
-	dc_5v: regulator-dc_5v {
+	dc_5v: regulator-dc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_5V";
 		regulator-min-microvolt = <5000000>;
@@ -89,7 +89,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -98,7 +98,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -107,7 +107,7 @@
 		regulator-always-on;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
index c0d6eb55100a..08a4718219b1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
@@ -64,28 +64,28 @@
 		reg = <0x0 0x0 0x0 0x20000000>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
index a18d6d241a5a..2b94b6e5285e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905w-jethome-jethub-j80.dts
@@ -37,28 +37,28 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
index c8d74e61dec1..89fe5110f7a2 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts
@@ -42,21 +42,21 @@
 			 <3300000 1>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc-v2.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc-v2.dts
index 2825db91e462..63b20860067c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc-v2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc-v2.dts
@@ -67,7 +67,7 @@
 		reg = <0x0 0x0 0x0 0x80000000>;
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -76,7 +76,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -93,7 +93,7 @@
 		regulator-always-on;
 	};
 
-	vcc_card: regulator-vcc_card {
+	vcc_card: regulator-vcc-card {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_CARD";
 		regulator-min-microvolt = <3300000>;
@@ -114,7 +114,7 @@
 		gpio = <&gpio GPIOH_3 GPIO_OPEN_DRAIN>;
 	};
 
-	vddio_ao3v3: regulator-vddio_ao3v3 {
+	vddio_ao3v3: regulator-vddio-ao3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO3V3";
 		regulator-min-microvolt = <3300000>;
@@ -139,7 +139,7 @@
 		regulator-settling-time-down-us = <50000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -148,7 +148,7 @@
 		regulator-always-on;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC 1V8";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 27093e6ac9e2..8b26c9661be1 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -93,7 +93,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -117,7 +117,7 @@
 		regulator-settling-time-down-us = <50000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -125,7 +125,7 @@
 	};
 
 	/* This is provided by LDOs on the eMMC daugther card */
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index f1acca5c4434..c79f9f2099bf 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -42,21 +42,21 @@
 			 <3300000 1>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index a150cc0e18ff..7e7dc87ede2d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -39,28 +39,28 @@
 		regulator-always-on;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 860f307494c5..07e7c3bedea0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -112,28 +112,28 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddio_boot: regulator-vddio_boot {
+	vddio_boot: regulator-vddio-boot {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_BOOT";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-s912-libretech-pc.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-s912-libretech-pc.dts
index 4eda9f634c42..a66f19851ac9 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-s912-libretech-pc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-s912-libretech-pc.dts
@@ -14,7 +14,7 @@
 		     "amlogic,meson-gxm";
 	model = "Libre Computer AML-S912-PC";
 
-	typec2_vbus: regulator-typec2_vbus {
+	typec2_vbus: regulator-typec2-vbus {
 		compatible = "regulator-fixed";
 		regulator-name = "TYPEC2_VBUS";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi
index 514a6dd4b124..e78cc9b577a0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-khadas-vim3.dtsi
@@ -80,7 +80,7 @@
 		clock-names = "ext_clock";
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -88,7 +88,7 @@
 		regulator-always-on;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_5V";
 		regulator-min-microvolt = <5000000>;
@@ -99,7 +99,7 @@
 		enable-active-high;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -108,7 +108,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -118,7 +118,7 @@
 		/* FIXME: actually controlled by VDDCPU_B_EN */
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO1V8";
 		regulator-min-microvolt = <1800000>;
@@ -127,7 +127,7 @@
 		regulator-always-on;
 	};
 
-	emmc_1v8: regulator-emmc_1v8 {
+	emmc_1v8: regulator-emmc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "EMMC_AO1V8";
 		regulator-min-microvolt = <1800000>;
@@ -136,7 +136,7 @@
 		regulator-always-on;
 	};
 
-	vsys_3v3: regulator-vsys_3v3 {
+	vsys_3v3: regulator-vsys-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VSYS_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -145,7 +145,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr: regulator-usb_pwr {
+	usb_pwr: regulator-usb-pwr {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi b/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
index 35e8f5bae990..082b72703cdf 100644
--- a/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-libretech-cottonwood.dtsi
@@ -150,7 +150,7 @@
 		gpio-open-drain;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -171,7 +171,7 @@
 		pwm-dutycycle-range = <100 0>;
 	};
 
-	vddio_ao18: regulator-vddio_ao18 {
+	vddio_ao18: regulator-vddio-ao18 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO18";
 		regulator-min-microvolt = <1800000>;
@@ -180,7 +180,7 @@
 		vin-supply = <&vddao_3v3>;
 	};
 
-	vddio_c: regulator-vddio_c {
+	vddio_c: regulator-vddio-c {
 		compatible = "regulator-gpio";
 		regulator-name = "VDDIO_C";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
index 46a34731f7e2..d1fa8b8bf795 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-ac2xx.dtsi
@@ -54,7 +54,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -63,7 +63,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -71,7 +71,7 @@
 		regulator-always-on;
 	};
 
-	emmc_1v8: regulator-emmc_1v8 {
+	emmc_1v8: regulator-emmc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "EMMC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -80,7 +80,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -105,7 +105,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao1v8: regulator-vddio_ao1v8 {
+	vddio_ao1v8: regulator-vddio-ao1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO1V8";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
index 62404743e62d..81dce862902a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi.dtsi
@@ -82,7 +82,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	emmc_1v8: regulator-emmc_1v8 {
+	emmc_1v8: regulator-emmc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "EMMC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -91,7 +91,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -99,7 +99,7 @@
 		regulator-always-on;
 	};
 
-	vddio_c: regulator-vddio_c {
+	vddio_c: regulator-vddio-c {
 		compatible = "regulator-gpio";
 		regulator-name = "VDDIO_C";
 		regulator-min-microvolt = <1800000>;
@@ -116,7 +116,7 @@
 			 <3300000 1>;
 	};
 
-	tflash_vdd: regulator-tflash_vdd {
+	tflash_vdd: regulator-tflash-vdd {
 		compatible = "regulator-fixed";
 		regulator-name = "TFLASH_VDD";
 		regulator-min-microvolt = <3300000>;
@@ -127,7 +127,7 @@
 		regulator-always-on;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -136,7 +136,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -165,7 +165,7 @@
 	};
 
 	/* USB Hub Power Enable */
-	vl_pwr_en: regulator-vl_pwr_en {
+	vl_pwr_en: regulator-vl-pwr-en {
 		compatible = "regulator-fixed";
 		regulator-name = "VL_PWR_EN";
 		regulator-min-microvolt = <5000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
index 846a2d6c20e5..0170139b8d32 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
@@ -43,7 +43,7 @@
 	};
 
 	/* Powers the SATA Disk 0 regulator, which is enabled when a disk load is detected */
-	p12v_0: regulator-p12v_0 {
+	p12v_0: regulator-p12v-0 {
 		compatible = "regulator-fixed";
 		regulator-name = "P12V_0";
 		regulator-min-microvolt = <12000000>;
@@ -56,7 +56,7 @@
 	};
 
 	/* Powers the SATA Disk 1 regulator, which is enabled when a disk load is detected */
-	p12v_1: regulator-p12v_1 {
+	p12v_1: regulator-p12v-1 {
 		compatible = "regulator-fixed";
 		regulator-name = "P12V_1";
 		regulator-min-microvolt = <12000000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
index 1db2327bbd13..951eb8e3f0c0 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid.dtsi
@@ -28,7 +28,7 @@
 		reset-gpios = <&gpio BOOT_12 GPIO_ACTIVE_LOW>;
 	};
 
-	tflash_vdd: regulator-tflash_vdd {
+	tflash_vdd: regulator-tflash-vdd {
 		compatible = "regulator-fixed";
 
 		regulator-name = "TFLASH_VDD";
@@ -40,7 +40,7 @@
 		regulator-always-on;
 	};
 
-	tf_io: gpio-regulator-tf_io {
+	tf_io: gpio-regulator-tf-io {
 		compatible = "regulator-gpio";
 
 		regulator-name = "TF_IO";
@@ -59,7 +59,7 @@
 			 <1800000 1>;
 	};
 
-	flash_1v8: regulator-flash_1v8 {
+	flash_1v8: regulator-flash-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "FLASH_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -68,7 +68,7 @@
 		regulator-always-on;
 	};
 
-	main_12v: regulator-main_12v {
+	main_12v: regulator-main-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "12V";
 		regulator-min-microvolt = <12000000>;
@@ -76,7 +76,7 @@
 		regulator-always-on;
 	};
 
-	vcc_5v: regulator-vcc_5v {
+	vcc_5v: regulator-vcc-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "5V";
 		regulator-min-microvolt = <5000000>;
@@ -87,7 +87,7 @@
 		enable-active-high;
 	};
 
-	vcc_1v8: regulator-vcc_1v8 {
+	vcc_1v8: regulator-vcc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -96,7 +96,7 @@
 		regulator-always-on;
 	};
 
-	vcc_3v3: regulator-vcc_3v3 {
+	vcc_3v3: regulator-vcc-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -125,7 +125,7 @@
 		regulator-always-on;
 	};
 
-	usb_pwr_en: regulator-usb_pwr_en {
+	usb_pwr_en: regulator-usb-pwr-en {
 		compatible = "regulator-fixed";
 		regulator-name = "USB_PWR_EN";
 		regulator-min-microvolt = <5000000>;
@@ -137,7 +137,7 @@
 		enable-active-high;
 	};
 
-	vddao_1v8: regulator-vddao_1v8 {
+	vddao_1v8: regulator-vddao-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -146,7 +146,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
index 109932068dbe..3581e14cbf18 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-sei610.dts
@@ -127,7 +127,7 @@
 		reg = <0x0 0x0 0x0 0x40000000>;
 	};
 
-	ao_5v: regulator-ao_5v {
+	ao_5v: regulator-ao-5v {
 		compatible = "regulator-fixed";
 		regulator-name = "AO_5V";
 		regulator-min-microvolt = <5000000>;
@@ -136,7 +136,7 @@
 		regulator-always-on;
 	};
 
-	dc_in: regulator-dc_in {
+	dc_in: regulator-dc-in {
 		compatible = "regulator-fixed";
 		regulator-name = "DC_IN";
 		regulator-min-microvolt = <5000000>;
@@ -144,7 +144,7 @@
 		regulator-always-on;
 	};
 
-	emmc_1v8: regulator-emmc_1v8 {
+	emmc_1v8: regulator-emmc-1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "EMMC_1V8";
 		regulator-min-microvolt = <1800000>;
@@ -153,7 +153,7 @@
 		regulator-always-on;
 	};
 
-	vddao_3v3: regulator-vddao_3v3 {
+	vddao_3v3: regulator-vddao-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3";
 		regulator-min-microvolt = <3300000>;
@@ -163,7 +163,7 @@
 	};
 
 	/* Used by Tuner, RGB Led & IR Emitter LED array */
-	vddao_3v3_t: regulator-vddao_3v3_t {
+	vddao_3v3_t: regulator-vddao-3v3-t {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDAO_3V3_T";
 		regulator-min-microvolt = <3300000>;
@@ -192,7 +192,7 @@
 		regulator-always-on;
 	};
 
-	vddio_ao1v8: regulator-vddio_ao1v8 {
+	vddio_ao1v8: regulator-vddio-ao1v8 {
 		compatible = "regulator-fixed";
 		regulator-name = "VDDIO_AO1V8";
 		regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 9dcd25ec2c04..896d1f33b5b6 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -586,6 +586,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index f049687d6b96..d8516ec0dae7 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -450,6 +450,7 @@
 			#gpio-cells = <2>;
 			gpio-controller;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-ranges = <&pinmux 0 0 16>,
 					<&pinmux 16 71 2>,
diff --git a/arch/arm64/boot/dts/exynos/exynos850.dtsi b/arch/arm64/boot/dts/exynos/exynos850.dtsi
index da3f4a791e68..2ba67c3d0681 100644
--- a/arch/arm64/boot/dts/exynos/exynos850.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos850.dtsi
@@ -184,6 +184,16 @@
 			clock-names = "fin_pll", "mct";
 		};
 
+		pdma0: dma-controller@120c0000 {
+			compatible = "arm,pl330", "arm,primecell";
+			reg = <0x120c0000 0x1000>;
+			clocks = <&cmu_core CLK_GOUT_PDMA_CORE_ACLK>;
+			clock-names = "apb_pclk";
+			#dma-cells = <1>;
+			interrupts = <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>;
+			arm,pl330-broken-no-flushp;
+		};
+
 		gic: interrupt-controller@12a01000 {
 			compatible = "arm,gic-400";
 			#interrupt-cells = <3>;
@@ -728,6 +738,24 @@
 				 <&cmu_peri CLK_GOUT_SPI0_IPCLK>;
 			clock-names = "pclk", "ipclk";
 			status = "disabled";
+
+			spi_0: spi@13940000 {
+				compatible = "samsung,exynos850-spi";
+				reg = <0x13940000 0x30>;
+				clocks = <&cmu_peri CLK_GOUT_SPI0_PCLK>,
+					 <&cmu_peri CLK_GOUT_SPI0_IPCLK>;
+				clock-names = "spi", "spi_busclk0";
+				dmas = <&pdma0 5>, <&pdma0 4>;
+				dma-names = "tx", "rx";
+				interrupts = <GIC_SPI 221 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi0_pins>;
+				pinctrl-names = "default";
+				num-cs = <1>;
+				samsung,spi-src-clk = <0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
 		};
 
 		usi_cmgp0: usi@11d000c0 {
@@ -769,6 +797,24 @@
 				clock-names = "uart", "clk_uart_baud0";
 				status = "disabled";
 			};
+
+			spi_1: spi@11d00000 {
+				compatible = "samsung,exynos850-spi";
+				reg = <0x11d00000 0x30>;
+				clocks = <&cmu_cmgp CLK_GOUT_CMGP_USI0_PCLK>,
+					 <&cmu_cmgp CLK_GOUT_CMGP_USI0_IPCLK>;
+				clock-names = "spi", "spi_busclk0";
+				dmas = <&pdma0 12>, <&pdma0 13>;
+				dma-names = "tx", "rx";
+				interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi1_pins>;
+				pinctrl-names = "default";
+				num-cs = <1>;
+				samsung,spi-src-clk = <0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
 		};
 
 		usi_cmgp1: usi@11d200c0 {
@@ -810,6 +856,24 @@
 				clock-names = "uart", "clk_uart_baud0";
 				status = "disabled";
 			};
+
+			spi_2: spi@11d20000 {
+				compatible = "samsung,exynos850-spi";
+				reg = <0x11d20000 0x30>;
+				clocks = <&cmu_cmgp CLK_GOUT_CMGP_USI1_PCLK>,
+					 <&cmu_cmgp CLK_GOUT_CMGP_USI1_IPCLK>;
+				clock-names = "spi", "spi_busclk0";
+				dmas = <&pdma0 14>, <&pdma0 15>;
+				dma-names = "tx", "rx";
+				interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
+				pinctrl-0 = <&spi2_pins>;
+				pinctrl-names = "default";
+				num-cs = <1>;
+				samsung,spi-src-clk = <0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				status = "disabled";
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
index 4a71f752200d..6ccade2c8cb4 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
+++ b/arch/arm64/boot/dts/exynos/google/gs101-oriole.dts
@@ -63,6 +63,20 @@
 	clock-frequency = <200000000>;
 };
 
+&hsi2c_8 {
+	status = "okay";
+
+	eeprom: eeprom@50 {
+		compatible = "atmel,24c08";
+		reg = <0x50>;
+	};
+};
+
+&hsi2c_12 {
+	status = "okay";
+	/* TODO: add the devices once drivers exist */
+};
+
 &pinctrl_far_alive {
 	key_voldown: key-voldown-pins {
 		samsung,pins = "gpa7-3";
@@ -99,6 +113,16 @@
 	status = "okay";
 };
 
+&usi8 {
+	samsung,mode = <USI_V2_I2C>;
+	status = "okay";
+};
+
+&usi12 {
+	samsung,mode = <USI_V2_I2C>;
+	status = "okay";
+};
+
 &watchdog_cl0 {
 	timeout-sec = <30>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi
index e6a9776d4d62..a675f822acec 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/exynos/google/gs101-pinctrl.dtsi
@@ -251,7 +251,7 @@
 		#interrupt-cells = <2>;
 	};
 
-	pcie0_clkreq: pcie0-clkreq-pins{
+	pcie0_clkreq: pcie0-clkreq-pins {
 		samsung,pins = "gph0-1";
 		samsung,pin-function = <GS101_PIN_FUNC_2>;
 		samsung,pin-pud = <GS101_PIN_PULL_UP>;
diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
index d838e3a7af6e..55e6bcb3689e 100644
--- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi
+++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi
@@ -73,7 +73,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0000>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -83,7 +83,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0100>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -93,7 +93,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0200>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -103,7 +103,7 @@
 			compatible = "arm,cortex-a55";
 			reg = <0x0300>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ANANKE_CPU_SLEEP>;
+			cpu-idle-states = <&ANANKE_CPU_SLEEP>;
 			capacity-dmips-mhz = <250>;
 			dynamic-power-coefficient = <70>;
 		};
@@ -113,7 +113,7 @@
 			compatible = "arm,cortex-a76";
 			reg = <0x0400>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ENYO_CPU_SLEEP>;
+			cpu-idle-states = <&ENYO_CPU_SLEEP>;
 			capacity-dmips-mhz = <620>;
 			dynamic-power-coefficient = <284>;
 		};
@@ -123,7 +123,7 @@
 			compatible = "arm,cortex-a76";
 			reg = <0x0500>;
 			enable-method = "psci";
-			cpu-idle-states =  <&ENYO_CPU_SLEEP>;
+			cpu-idle-states = <&ENYO_CPU_SLEEP>;
 			capacity-dmips-mhz = <620>;
 			dynamic-power-coefficient = <284>;
 		};
@@ -133,7 +133,7 @@
 			compatible = "arm,cortex-x1";
 			reg = <0x0600>;
 			enable-method = "psci";
-			cpu-idle-states =  <&HERA_CPU_SLEEP>;
+			cpu-idle-states = <&HERA_CPU_SLEEP>;
 			capacity-dmips-mhz = <1024>;
 			dynamic-power-coefficient = <650>;
 		};
@@ -143,7 +143,7 @@
 			compatible = "arm,cortex-x1";
 			reg = <0x0700>;
 			enable-method = "psci";
-			cpu-idle-states =  <&HERA_CPU_SLEEP>;
+			cpu-idle-states = <&HERA_CPU_SLEEP>;
 			capacity-dmips-mhz = <1024>;
 			dynamic-power-coefficient = <650>;
 		};
@@ -180,14 +180,6 @@
 		};
 	};
 
-	/* TODO replace with CCF clock */
-	dummy_clk: clock-3 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <12345>;
-		clock-output-names = "pclk";
-	};
-
 	/* ect node is required to be present by bootloader */
 	ect {
 	};
@@ -292,6 +284,26 @@
 			clock-names = "bus", "sss";
 		};
 
+		timer@10050000 {
+			compatible = "google,gs101-mct",
+				     "samsung,exynos4210-mct";
+			reg = <0x10050000 0x800>;
+			interrupts = <GIC_SPI 753 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 754 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 755 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 756 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 757 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 758 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 759 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 760 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 761 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 762 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 763 IRQ_TYPE_LEVEL_HIGH 0>,
+				     <GIC_SPI 764 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&ext_24_5m>, <&cmu_misc CLK_GOUT_MISC_MCT_PCLK>;
+			clock-names = "fin_pll", "mct";
+		};
+
 		watchdog_cl0: watchdog@10060000 {
 			compatible = "google,gs101-wdt";
 			reg = <0x10060000 0x100>;
@@ -339,9 +351,20 @@
 			};
 		};
 
+		cmu_peric0: clock-controller@10800000 {
+			compatible = "google,gs101-cmu-peric0";
+			reg = <0x10800000 0x4000>;
+			#clock-cells = <1>;
+			clocks = <&ext_24_5m>,
+				 <&cmu_top CLK_DOUT_CMU_PERIC0_BUS>,
+				 <&cmu_top CLK_DOUT_CMU_PERIC0_IP>;
+			clock-names = "oscclk", "bus", "ip";
+		};
+
 		sysreg_peric0: syscon@10820000 {
 			compatible = "google,gs101-peric0-sysreg", "syscon";
 			reg = <0x10820000 0x10000>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_SYSREG_PERIC0_PCLK>;
 		};
 
 		pinctrl_peric0: pinctrl@10840000 {
@@ -350,6 +373,35 @@
 			interrupts = <GIC_SPI 625 IRQ_TYPE_LEVEL_HIGH 0>;
 		};
 
+		usi8: usi@109700c0 {
+			compatible = "google,gs101-usi",
+				     "samsung,exynos850-usi";
+			reg = <0x109700c0 0x20>;
+			ranges;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_7>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_7>;
+			clock-names = "pclk", "ipclk";
+			samsung,sysreg = <&sysreg_peric0 0x101c>;
+			status = "disabled";
+
+			hsi2c_8: i2c@10970000 {
+				compatible = "google,gs101-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
+				reg = <0x10970000 0xc0>;
+				interrupts = <GIC_SPI 642 IRQ_TYPE_LEVEL_HIGH 0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&hsi2c8_bus>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_7>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_7>;
+				clock-names = "hsi2c", "hsi2c_pclk";
+				status = "disabled";
+			};
+		};
+
 		usi_uart: usi@10a000c0 {
 			compatible = "google,gs101-usi",
 				     "samsung,exynos850-usi";
@@ -357,7 +409,8 @@
 			ranges;
 			#address-cells = <1>;
 			#size-cells = <1>;
-			clocks = <&dummy_clk>, <&dummy_clk>;
+			clocks = <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP1_PCLK_0>,
+				 <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP1_IPCLK_0>;
 			clock-names = "pclk", "ipclk";
 			samsung,sysreg = <&sysreg_peric0 0x1020>;
 			samsung,mode = <USI_V2_UART>;
@@ -366,19 +419,30 @@
 			serial_0: serial@10a00000 {
 				compatible = "google,gs101-uart";
 				reg = <0x10a00000 0xc0>;
-				reg-io-width = <4>;
 				interrupts = <GIC_SPI 634
 					      IRQ_TYPE_LEVEL_HIGH 0>;
-				clocks = <&dummy_clk 0>, <&dummy_clk 0>;
+				clocks = <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP1_PCLK_0>,
+					 <&cmu_peric0 CLK_GOUT_PERIC0_PERIC0_TOP1_IPCLK_0>;
 				clock-names = "uart", "clk_uart_baud0";
 				samsung,uart-fifosize = <256>;
 				status = "disabled";
 			};
 		};
 
+		cmu_peric1: clock-controller@10c00000 {
+			compatible = "google,gs101-cmu-peric1";
+			reg = <0x10c00000 0x4000>;
+			#clock-cells = <1>;
+			clocks = <&ext_24_5m>,
+				 <&cmu_top CLK_DOUT_CMU_PERIC1_BUS>,
+				 <&cmu_top CLK_DOUT_CMU_PERIC1_IP>;
+			clock-names = "oscclk", "bus", "ip";
+		};
+
 		sysreg_peric1: syscon@10c20000 {
 			compatible = "google,gs101-peric1-sysreg", "syscon";
 			reg = <0x10c20000 0x10000>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_SYSREG_PERIC1_PCLK>;
 		};
 
 		pinctrl_peric1: pinctrl@10c40000 {
@@ -387,6 +451,35 @@
 			interrupts = <GIC_SPI 644 IRQ_TYPE_LEVEL_HIGH 0>;
 		};
 
+		usi12: usi@10d500c0 {
+			compatible = "google,gs101-usi",
+				     "samsung,exynos850-usi";
+			reg = <0x10d500c0 0x20>;
+			ranges;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&cmu_peric1 CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_5>,
+				 <&cmu_peric1 CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_5>;
+			clock-names = "pclk", "ipclk";
+			samsung,sysreg = <&sysreg_peric1 0x1010>;
+			status = "disabled";
+
+			hsi2c_12: i2c@10d50000 {
+				compatible = "google,gs101-hsi2c",
+					     "samsung,exynosautov9-hsi2c";
+				reg = <0x10d50000 0xc0>;
+				interrupts = <GIC_SPI 655 IRQ_TYPE_LEVEL_HIGH 0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				pinctrl-0 = <&hsi2c12_bus>;
+				pinctrl-names = "default";
+				clocks = <&cmu_peric1 CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_5>,
+					 <&cmu_peric1 CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_5>;
+				clock-names = "hsi2c", "hsi2c_pclk";
+				status = "disabled";
+			};
+		};
+
 		pinctrl_hsi1: pinctrl@11840000 {
 			compatible = "google,gs101-pinctrl";
 			reg = <0x11840000 0x00001000>;
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index 2e027675d7bb..045250d0a040 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -20,23 +20,41 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-frwy.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-qds.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-rdb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1046a-tqmls1046a-mbls10xxa.dtb
+DTC_FLAGS_fsl-ls1088a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-qds.dtb
+DTC_FLAGS_fsl-ls1088a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-rdb.dtb
+DTC_FLAGS_fsl-ls1088a-ten64 := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-ten64.dtb
+DTC_FLAGS_fsl-ls1088a-tqmls1088a-mbls10xxa := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1088a-tqmls1088a-mbls10xxa.dtb
+DTC_FLAGS_fsl-ls2080a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-qds.dtb
+DTC_FLAGS_fsl-ls2080a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-rdb.dtb
+DTC_FLAGS_fsl-ls2081a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2081a-rdb.dtb
+DTC_FLAGS_fsl-ls2080a-simu := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-simu.dtb
+DTC_FLAGS_fsl-ls2088a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-qds.dtb
+DTC_FLAGS_fsl-ls2088a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2088a-rdb.dtb
+DTC_FLAGS_fsl-lx2160a-bluebox3 := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3.dtb
+DTC_FLAGS_fsl-lx2160a-bluebox3-rev-a := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-bluebox3-rev-a.dtb
+DTC_FLAGS_fsl-lx2160a-clearfog-cx := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-clearfog-cx.dtb
+DTC_FLAGS_fsl-lx2160a-honeycomb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-honeycomb.dtb
+DTC_FLAGS_fsl-lx2160a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-qds.dtb
+DTC_FLAGS_fsl-lx2160a-rdb := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-rdb.dtb
+DTC_FLAGS_fsl-lx2162a-clearfog := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-clearfog.dtb
+DTC_FLAGS_fsl-lx2162a-qds := -Wno-interrupt_map
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2162a-qds.dtb
 
 fsl-ls1028a-qds-13bb-dtbs := fsl-ls1028a-qds.dtb fsl-ls1028a-qds-13bb.dtbo
@@ -53,6 +71,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-85bb.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-899b.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls1028a-qds-9999.dtb
 
+DTC_FLAGS_fsl-lx2160a-tqmlx2160a-mblx2160a := -Wno-interrupt_map
 fsl-lx2160a-tqmlx2160a-mblx2160a-12-11-x-dtbs := fsl-lx2160a-tqmlx2160a-mblx2160a.dtb \
 	fsl-lx2160a-tqmlx2160a-mblx2160a_12_x_x.dtbo \
 	fsl-lx2160a-tqmlx2160a-mblx2160a_x_11_x.dtbo
@@ -80,6 +99,7 @@ dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-14-8-x.dtb
 dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-lx2160a-tqmlx2160a-mblx2160a-14-7-x.dtb
 
 dtb-$(CONFIG_ARCH_MXC) += imx8dxl-evk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8dxp-tqma8xdp-mba8xx.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-data-modul-edm-sbc.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mm-ddr4-evk.dtb
@@ -133,7 +153,9 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mn-var-som-symphony.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-venice-gw7902.dtb
 
 imx8mn-tqma8mqnl-mba8mx-lvds-tm070jvhg33-dtbs += imx8mn-tqma8mqnl-mba8mx.dtb imx8mn-tqma8mqnl-mba8mx-lvds-tm070jvhg33.dtbo
+imx8mn-tqma8mqnl-mba8mx-usbotg-dtbs += imx8mn-tqma8mqnl-mba8mx.dtb imx8mn-tqma8mqnl-mba8mx-usbotg.dtbo
 dtb-$(CONFIG_ARCH_MXC) += imx8mn-tqma8mqnl-mba8mx-lvds-tm070jvhg33.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mn-tqma8mqnl-mba8mx-usbotg.dtb
 
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-beacon-kit.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8mp-data-modul-edm-sbc.dtb
@@ -188,8 +210,10 @@ imx8mq-tqma8mq-mba8mx-lvds-tm070jvhg33-dtbs += imx8mq-tqma8mq-mba8mx.dtb imx8mq-
 dtb-$(CONFIG_ARCH_MXC) += imx8mq-tqma8mq-mba8mx-lvds-tm070jvhg33.dtb
 
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-eval.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-eval-v1.2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-ixora-v1.1.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-v1.1-eval.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-v1.1-eval-v1.2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-v1.1-ixora-v1.1.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-apalis-v1.1-ixora-v1.2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qm-mek.dtb
@@ -199,10 +223,13 @@ dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-eval-v3.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-iris.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-colibri-iris-v2.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8qxp-mek.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8qxp-tqma8xqp-mba8xx.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx8ulp-evk.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-11x11-evk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx93-phyboard-segin.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxca.dtb
 dtb-$(CONFIG_ARCH_MXC) += imx93-tqma9352-mba93xxla.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx93-var-som-symphony.dtb
 
 imx8mm-venice-gw72xx-0x-imx219-dtbs	:= imx8mm-venice-gw72xx-0x.dtb imx8mm-venice-gw72xx-0x-imx219.dtbo
 imx8mm-venice-gw72xx-0x-rpidsi-dtbs	:= imx8mm-venice-gw72xx-0x.dtb imx8mm-venice-gw72xx-0x-rpidsi.dtbo
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
index 1e3fe3897b52..fe9093b3c02e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
@@ -290,7 +290,7 @@
 		dcfg: dcfg@1ee0000 {
 			compatible = "fsl,ls1012a-dcfg",
 				     "syscon";
-			reg = <0x0 0x1ee0000 0x0 0x10000>;
+			reg = <0x0 0x1ee0000 0x0 0x1000>;
 			big-endian;
 		};
 
@@ -351,24 +351,26 @@
 		};
 
 		i2c0: i2c@2180000 {
-			compatible = "fsl,vf610-i2c";
+			compatible = "fsl,ls1012a-i2c", "fsl,vf610-i2c";
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x2180000 0x0 0x10000>;
 			interrupts = <0 56 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(4)>;
+			scl-gpios = <&gpio0 2 0>;
 			status = "disabled";
 		};
 
 		i2c1: i2c@2190000 {
-			compatible = "fsl,vf610-i2c";
+			compatible = "fsl,ls1012a-i2c", "fsl,vf610-i2c";
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0x0 0x2190000 0x0 0x10000>;
 			interrupts = <0 57 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(4)>;
+			scl-gpios = <&gpio0 13 0>;
 			status = "disabled";
 		};
 
@@ -499,6 +501,7 @@
 			snps,quirk-frame-length-adjustment = <0x20>;
 			snps,dis_rxdet_inp3_quirk;
 			snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>;
+			snps,host-vbus-glitches;
 		};
 
 		sata: sata@3200000 {
@@ -550,6 +553,7 @@
 					<0000 0 0 2 &gic 0 111 IRQ_TYPE_LEVEL_HIGH>,
 					<0000 0 0 3 &gic 0 112 IRQ_TYPE_LEVEL_HIGH>,
 					<0000 0 0 4 &gic 0 113 IRQ_TYPE_LEVEL_HIGH>;
+			big-endian;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 1515cec23147..754a64be739c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -485,7 +485,6 @@
 				<0x00030005 0x00000042>,
 				<0x00030006 0x0000004c>,
 				<0x00030007 0x00000056>;
-			big-endian;
 			#thermal-sensor-cells = <1>;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index 8616d5e0c388..604bf88d70b3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -591,6 +591,8 @@
 			reg = <0x00 0x03400000 0x0 0x00100000>,
 			      <0x20 0x00000000 0x8 0x00000000>;
 			reg-names = "regs", "addr_space";
+			interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>; /* PME interrupt */
+			interrupt-names = "pme";
 			num-ib-windows = <24>;
 			num-ob-windows = <256>;
 			max-functions = /bits/ 8 <2>;
@@ -628,6 +630,8 @@
 			reg = <0x00 0x03500000 0x0 0x00100000>,
 			      <0x28 0x00000000 0x8 0x00000000>;
 			reg-names = "regs", "addr_space";
+			interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>; /* PME interrupt */
+			interrupt-names = "pme";
 			num-ib-windows = <6>;
 			num-ob-windows = <6>;
 			status = "disabled";
@@ -664,6 +668,8 @@
 			reg = <0x00 0x03600000 0x0 0x00100000>,
 			      <0x30 0x00000000 0x8 0x00000000>;
 			reg-names = "regs", "addr_space";
+			interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>; /* PME interrupt */
+			interrupt-names = "pme";
 			num-ib-windows = <6>;
 			num-ob-windows = <6>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 6640b49670ae..e665c629e1a1 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -949,34 +949,50 @@
 		};
 
 		uart0: serial@21c0000 {
-			compatible = "arm,sbsa-uart","arm,pl011";
+			compatible = "arm,pl011", "arm,primecell";
+			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>,
+				 <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>;
+			clock-names = "uartclk", "apb_pclk";
 			reg = <0x0 0x21c0000 0x0 0x1000>;
 			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
-			current-speed = <115200>;
 			status = "disabled";
 		};
 
 		uart1: serial@21d0000 {
-			compatible = "arm,sbsa-uart","arm,pl011";
+			compatible = "arm,pl011", "arm,primecell";
+			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>,
+				 <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>;
+			clock-names = "uartclk", "apb_pclk";
 			reg = <0x0 0x21d0000 0x0 0x1000>;
 			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
-			current-speed = <115200>;
 			status = "disabled";
 		};
 
 		uart2: serial@21e0000 {
-			compatible = "arm,sbsa-uart","arm,pl011";
+			compatible = "arm,pl011", "arm,primecell";
+			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>,
+				 <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>;
+			clock-names = "uartclk", "apb_pclk";
 			reg = <0x0 0x21e0000 0x0 0x1000>;
 			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
-			current-speed = <115200>;
 			status = "disabled";
 		};
 
 		uart3: serial@21f0000 {
-			compatible = "arm,sbsa-uart","arm,pl011";
+			compatible = "arm,pl011", "arm,primecell";
+			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>,
+				 <&clockgen QORIQ_CLK_PLATFORM_PLL
+					    QORIQ_CLK_PLL_DIV(8)>;
+			clock-names = "uartclk", "apb_pclk";
 			reg = <0x0 0x21f0000 0x0 0x1000>;
 			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
-			current-speed = <115200>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.1.dtsi
new file mode 100644
index 000000000000..0f77f78f4d96
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.1.dtsi
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024 Toradex
+ */
+
+#include "imx8-apalis-eval.dtsi"
+
+/* Apalis CAN1 */
+&flexcan1 {
+	status = "okay";
+};
+
+/* Apalis CAN2 */
+&flexcan2 {
+	status = "okay";
+};
+
+/* Apalis MMC1 */
+&usdhc2 {
+	status = "okay";
+};
+
+/* Apalis SD1 */
+&usdhc3 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.2.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.2.dtsi
new file mode 100644
index 000000000000..f5c6a0164f36
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-eval-v1.2.dtsi
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024 Toradex
+ */
+
+#include "imx8-apalis-eval.dtsi"
+
+/ {
+	reg_3v3_mmc: regulator-3v3-mmc {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_3v3_mmc>;
+		enable-active-high;
+		gpio = <&lsio_gpio5 19 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <100000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "3.3V_MMC";
+		startup-delay-us = <10000>;
+	};
+
+	reg_3v3_sd: regulator-3v3-sd {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_3v3_sd>;
+		enable-active-high;
+		gpio = <&lsio_gpio5 20 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <100000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "3.3V_SD";
+		startup-delay-us = <10000>;
+	};
+
+	reg_can1: regulator-can1 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_can1_power>;
+		enable-active-high;
+		gpio = <&lsio_gpio5 22 GPIO_ACTIVE_HIGH>;
+		regulator-name = "5V_SW_CAN1";
+		startup-delay-us = <10000>;
+	};
+
+	reg_can2: regulator-can2 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_enable_can2_power>;
+		enable-active-high;
+		gpio = <&lsio_gpio5 21 GPIO_ACTIVE_HIGH>;
+		regulator-name = "5V_SW_CAN2";
+		startup-delay-us = <10000>;
+	};
+};
+
+/* Apalis CAN1 */
+&flexcan1 {
+	xceiver-supply = <&reg_can1>;
+	status = "okay";
+};
+
+/* Apalis CAN2 */
+&flexcan2 {
+	xceiver-supply = <&reg_can2>;
+	status = "okay";
+};
+
+/* Apalis I2C1 */
+&i2c2 {
+	status = "okay";
+
+	/* Power/Current Measurement Sensor */
+	hwmon@40 {
+		compatible = "ti,ina219";
+		reg = <0x40>;
+		shunt-resistor = <5000>;
+	};
+
+	temperature-sensor@4f {
+		compatible = "ti,tmp75c";
+		reg = <0x4f>;
+	};
+
+	eeprom@57 {
+		compatible = "st,24c02", "atmel,24c02";
+		reg = <0x57>;
+	};
+};
+
+/* Apalis MMC1 */
+&usdhc2 {
+	pinctrl-0 = <&pinctrl_usdhc2_4bit>, <&pinctrl_mmc1_cd>;
+	pinctrl-1 = <&pinctrl_usdhc2_4bit_100mhz>, <&pinctrl_mmc1_cd>;
+	pinctrl-2 = <&pinctrl_usdhc2_4bit_200mhz>, <&pinctrl_mmc1_cd>;
+	pinctrl-3 = <&pinctrl_usdhc2_4bit_sleep>, <&pinctrl_mmc1_cd_sleep>;
+	bus-width = <4>;
+	vmmc-supply = <&reg_3v3_mmc>;
+	status = "okay";
+};
+
+/* Apalis SD1 */
+&usdhc3 {
+	vmmc-supply = <&reg_3v3_sd>;
+	status = "okay";
+};
+
+&iomuxc {
+
+	pinctrl_enable_3v3_mmc: enable3v3mmcgrp {
+		fsl,pins = <IMX8QM_USDHC1_DATA4_LSIO_GPIO5_IO19	0x00000021>; /* MXM3_148 */
+	};
+
+	pinctrl_enable_3v3_sd: enable3v3sdgrp {
+		fsl,pins = <IMX8QM_USDHC1_DATA5_LSIO_GPIO5_IO20	0x00000021>; /* MXM3_152 */
+	};
+
+	pinctrl_enable_can1_power: enablecan1powergrp {
+		fsl,pins = <IMX8QM_USDHC1_DATA7_LSIO_GPIO5_IO22	0x00000021>; /* MXM3_158 */
+	};
+
+	pinctrl_enable_can2_power: enablecan2powergrp {
+		fsl,pins = <IMX8QM_USDHC1_DATA6_LSIO_GPIO5_IO21	0x00000021>; /* MXM3_156 */
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-eval.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-eval.dtsi
index 685d4294f4f1..deecb96a1596 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-eval.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-eval.dtsi
@@ -35,18 +35,6 @@
 	status = "okay";
 };
 
-/* Apalis CAN1 */
-&flexcan1 {
-	status = "okay";
-};
-
-/* Apalis CAN2 */
-&flexcan2 {
-	status = "okay";
-};
-
-/* TODO: GPU */
-
 /* Apalis I2C1 */
 &i2c2 {
 	status = "okay";
@@ -132,13 +120,3 @@
 };
 
 /* TODO: Apalis USBH4 SuperSpeed */
-
-/* Apalis MMC1 */
-&usdhc2 {
-	status = "okay";
-};
-
-/* Apalis SD1 */
-&usdhc3 {
-	status = "okay";
-};
diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
index f69b0c17560a..160153853b68 100644
--- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi
@@ -261,7 +261,6 @@
 			reset-assert-us = <2>;
 			reset-deassert-us = <2>;
 			reset-gpios = <&lsio_gpio1 11 GPIO_ACTIVE_LOW>;
-			reset-names = "phy";
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
index f057c6b21b30..07afeb78ed56 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi
@@ -4,6 +4,7 @@
  *	Dong Aisheng <aisheng.dong@nxp.com>
  */
 
+#include <dt-bindings/clock/imx8-clock.h>
 #include <dt-bindings/clock/imx8-lpcg.h>
 #include <dt-bindings/firmware/imx/rsrc.h>
 
@@ -14,12 +15,174 @@ audio_ipg_clk: clock-audio-ipg {
 	clock-output-names = "audio_ipg_clk";
 };
 
+clk_ext_aud_mclk0: clock-ext-aud-mclk0 {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "ext_aud_mclk0";
+};
+
+clk_ext_aud_mclk1: clock-ext-aud-mclk1 {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "ext_aud_mclk1";
+};
+
+clk_esai0_rx_clk: clock-esai0-rx {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "esai0_rx_clk";
+};
+
+clk_esai0_rx_hf_clk: clock-esai0-rx-hf {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "esai0_rx_hf_clk";
+};
+
+clk_esai0_tx_clk: clock-esai0-tx {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "esai0_tx_clk";
+};
+
+clk_esai0_tx_hf_clk: clock-esai0-tx-hf {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "esai0_tx_hf_clk";
+};
+
+clk_spdif0_rx: clock-spdif0-rx {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "spdif0_rx";
+};
+
+clk_sai0_rx_bclk: clock-sai0-rx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai0_rx_bclk";
+};
+
+clk_sai0_tx_bclk: clock-sai0-tx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai0_tx_bclk";
+};
+
+clk_sai1_rx_bclk: clock-sai1-rx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai1_rx_bclk";
+};
+
+clk_sai1_tx_bclk: clock-sai1-tx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai1_tx_bclk";
+};
+
+clk_sai2_rx_bclk: clock-sai2-rx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai2_rx_bclk";
+};
+
+clk_sai3_rx_bclk: clock-sai3-rx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai3_rx_bclk";
+};
+
+clk_sai4_rx_bclk: clock-sai4-rx-bclk {
+	compatible = "fixed-clock";
+	#clock-cells = <0>;
+	clock-frequency = <0>;
+	clock-output-names = "sai4_rx_bclk";
+};
+
 audio_subsys: bus@59000000 {
 	compatible = "simple-bus";
 	#address-cells = <1>;
 	#size-cells = <1>;
 	ranges = <0x59000000 0x0 0x59000000 0x1000000>;
 
+	sai0: sai@59040000 {
+		compatible = "fsl,imx8qm-sai";
+		reg = <0x59040000 0x10000>;
+		interrupts = <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&sai0_lpcg 1>,
+			 <&clk_dummy>,
+			 <&sai0_lpcg 0>,
+			 <&clk_dummy>,
+			 <&clk_dummy>;
+		clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+		dma-names = "rx", "tx";
+		dmas = <&edma0 12 0 1>, <&edma0 13 0 0>;
+		power-domains = <&pd IMX_SC_R_SAI_0>;
+		status = "disabled";
+	};
+
+	sai1: sai@59050000 {
+		compatible = "fsl,imx8qm-sai";
+		reg = <0x59050000 0x10000>;
+		interrupts = <GIC_SPI 316 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&sai1_lpcg 1>,
+			 <&clk_dummy>,
+			 <&sai1_lpcg 0>,
+			 <&clk_dummy>,
+			 <&clk_dummy>;
+		clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+		dma-names = "rx", "tx";
+		dmas = <&edma0 14 0 1>, <&edma0 15 0 0>;
+		power-domains = <&pd IMX_SC_R_SAI_1>;
+		status = "disabled";
+	};
+
+	sai2: sai@59060000 {
+		compatible = "fsl,imx8qm-sai";
+		reg = <0x59060000 0x10000>;
+		interrupts = <GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&sai2_lpcg 1>,
+			 <&clk_dummy>,
+			 <&sai2_lpcg 0>,
+			 <&clk_dummy>,
+			 <&clk_dummy>;
+		clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+		dma-names = "rx";
+		dmas = <&edma0 16 0 1>;
+		power-domains = <&pd IMX_SC_R_SAI_2>;
+		status = "disabled";
+	};
+
+	sai3: sai@59070000 {
+		compatible = "fsl,imx8qm-sai";
+		reg = <0x59070000 0x10000>;
+		interrupts = <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&sai3_lpcg 1>,
+			 <&clk_dummy>,
+			 <&sai3_lpcg 0>,
+			 <&clk_dummy>,
+			 <&clk_dummy>;
+		clock-names = "bus", "mclk0", "mclk1", "mclk2", "mclk3";
+		dma-names = "rx";
+		dmas = <&edma0 17 0 1>;
+		power-domains = <&pd IMX_SC_R_SAI_3>;
+		status = "disabled";
+	};
+
 	edma0: dma-controller@591f0000 {
 		compatible = "fsl,imx8qm-edma";
 		reg = <0x591f0000 0x190000>;
@@ -76,6 +239,54 @@ audio_subsys: bus@59000000 {
 				<&pd IMX_SC_R_DMA_0_CH23>;
 	};
 
+	sai0_lpcg: clock-controller@59440000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59440000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_SAI0_MCLK_SEL>,
+			 <&audio_ipg_clk>;
+		clock-indices = <IMX_LPCG_CLK_0>, <IMX_LPCG_CLK_4>;
+		clock-output-names = "sai0_lpcg_mclk",
+				     "sai0_lpcg_ipg_clk";
+		power-domains = <&pd IMX_SC_R_SAI_0>;
+	};
+
+	sai1_lpcg: clock-controller@59450000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59450000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_SAI1_MCLK_SEL>,
+			 <&audio_ipg_clk>;
+		clock-indices = <IMX_LPCG_CLK_0>, <IMX_LPCG_CLK_4>;
+		clock-output-names = "sai1_lpcg_mclk",
+				     "sai1_lpcg_ipg_clk";
+		power-domains = <&pd IMX_SC_R_SAI_1>;
+	};
+
+	sai2_lpcg: clock-controller@59460000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59460000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_SAI2_MCLK_SEL>,
+			 <&audio_ipg_clk>;
+		clock-indices = <IMX_LPCG_CLK_0>, <IMX_LPCG_CLK_4>;
+		clock-output-names = "sai2_lpcg_mclk",
+				     "sai2_lpcg_ipg_clk";
+		power-domains = <&pd IMX_SC_R_SAI_2>;
+	};
+
+	sai3_lpcg: clock-controller@59470000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59470000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_SAI3_MCLK_SEL>,
+			 <&audio_ipg_clk>;
+		clock-indices = <IMX_LPCG_CLK_0>, <IMX_LPCG_CLK_4>;
+		clock-output-names = "sai3_lpcg_mclk",
+				     "sai3_lpcg_ipg_clk";
+		power-domains = <&pd IMX_SC_R_SAI_3>;
+	};
+
 	dsp_lpcg: clock-controller@59580000 {
 		compatible = "fsl,imx8qxp-lpcg";
 		reg = <0x59580000 0x10000>;
@@ -151,4 +362,123 @@ audio_subsys: bus@59000000 {
 				<&pd IMX_SC_R_DMA_1_CH9>,
 				<&pd IMX_SC_R_DMA_1_CH10>;
 	};
+
+	aud_rec0_lpcg: clock-controller@59d00000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d00000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_MST_BUS>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "aud_rec_clk0_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_AUDIO_PLL_0>;
+	};
+
+	aud_rec1_lpcg: clock-controller@59d10000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d10000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&clk IMX_SC_R_AUDIO_PLL_1 IMX_SC_PM_CLK_MST_BUS>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "aud_rec_clk1_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_AUDIO_PLL_1>;
+	};
+
+	aud_pll_div0_lpcg: clock-controller@59d20000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d20000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_SLV_BUS>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "aud_pll_div_clk0_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_AUDIO_PLL_0>;
+	};
+
+	aud_pll_div1_lpcg: clock-controller@59d30000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d30000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&clk IMX_SC_R_AUDIO_PLL_1 IMX_SC_PM_CLK_SLV_BUS>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "aud_pll_div_clk1_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_AUDIO_PLL_1>;
+	};
+
+	mclkout0_lpcg: clock-controller@59d50000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d50000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_MCLKOUT0_SEL>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "mclkout0_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_MCLK_OUT_0>;
+	};
+
+	mclkout1_lpcg: clock-controller@59d60000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x59d60000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&acm IMX_ADMA_ACM_MCLKOUT1_SEL>;
+		clock-indices = <IMX_LPCG_CLK_0>;
+		clock-output-names = "mclkout1_lpcg_clk";
+		power-domains = <&pd IMX_SC_R_MCLK_OUT_1>;
+	};
+
+	acm: acm@59e00000 {
+		compatible = "fsl,imx8qxp-acm";
+		reg = <0x59e00000 0x1d0000>;
+		#clock-cells = <1>;
+		power-domains = <&pd IMX_SC_R_AUDIO_CLK_0>,
+				<&pd IMX_SC_R_AUDIO_CLK_1>,
+				<&pd IMX_SC_R_MCLK_OUT_0>,
+				<&pd IMX_SC_R_MCLK_OUT_1>,
+				<&pd IMX_SC_R_AUDIO_PLL_0>,
+				<&pd IMX_SC_R_AUDIO_PLL_1>,
+				<&pd IMX_SC_R_ASRC_0>,
+				<&pd IMX_SC_R_ASRC_1>,
+				<&pd IMX_SC_R_ESAI_0>,
+				<&pd IMX_SC_R_SAI_0>,
+				<&pd IMX_SC_R_SAI_1>,
+				<&pd IMX_SC_R_SAI_2>,
+				<&pd IMX_SC_R_SAI_3>,
+				<&pd IMX_SC_R_SAI_4>,
+				<&pd IMX_SC_R_SAI_5>,
+				<&pd IMX_SC_R_SPDIF_0>,
+				<&pd IMX_SC_R_MQS_0>;
+		clocks = <&aud_rec0_lpcg IMX_LPCG_CLK_0>,
+			 <&aud_rec1_lpcg IMX_LPCG_CLK_0>,
+			 <&aud_pll_div0_lpcg IMX_LPCG_CLK_0>,
+			 <&aud_pll_div1_lpcg IMX_LPCG_CLK_0>,
+			 <&clk_ext_aud_mclk0>,
+			 <&clk_ext_aud_mclk1>,
+			 <&clk_esai0_rx_clk>,
+			 <&clk_esai0_rx_hf_clk>,
+			 <&clk_esai0_tx_clk>,
+			 <&clk_esai0_tx_hf_clk>,
+			 <&clk_spdif0_rx>,
+			 <&clk_sai0_rx_bclk>,
+			 <&clk_sai0_tx_bclk>,
+			 <&clk_sai1_rx_bclk>,
+			 <&clk_sai1_tx_bclk>,
+			 <&clk_sai2_rx_bclk>,
+			 <&clk_sai3_rx_bclk>,
+			 <&clk_sai4_rx_bclk>;
+		clock-names = "aud_rec_clk0_lpcg_clk",
+			      "aud_rec_clk1_lpcg_clk",
+			      "aud_pll_div_clk0_lpcg_clk",
+			      "aud_pll_div_clk1_lpcg_clk",
+			      "ext_aud_mclk0",
+			      "ext_aud_mclk1",
+			      "esai0_rx_clk",
+			      "esai0_rx_hf_clk",
+			      "esai0_tx_clk",
+			      "esai0_tx_hf_clk",
+			      "spdif0_rx",
+			      "sai0_rx_bclk",
+			      "sai0_tx_bclk",
+			      "sai1_rx_bclk",
+			      "sai1_tx_bclk",
+			      "sai2_rx_bclk",
+			      "sai3_rx_bclk",
+			      "sai4_rx_bclk";
+	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
index b0bb77150adc..cab3468b1875 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
@@ -5,6 +5,7 @@
  */
 
 #include <dt-bindings/clock/imx8-lpcg.h>
+#include <dt-bindings/dma/fsl-edma.h>
 #include <dt-bindings/firmware/imx/rsrc.h>
 
 dma_ipg_clk: clock-dma-ipg {
@@ -93,8 +94,8 @@ dma_subsys: bus@5a000000 {
 		assigned-clocks = <&clk IMX_SC_R_UART_0 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <80000000>;
 		power-domains = <&pd IMX_SC_R_UART_0>;
-		dma-names = "tx","rx";
-		dmas = <&edma2 9 0 0>, <&edma2 8 0 1>;
+		dma-names = "rx", "tx";
+		dmas = <&edma2 8 0 FSL_EDMA_RX>, <&edma2 9 0 0>;
 		status = "disabled";
 	};
 
@@ -107,8 +108,8 @@ dma_subsys: bus@5a000000 {
 		assigned-clocks = <&clk IMX_SC_R_UART_1 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <80000000>;
 		power-domains = <&pd IMX_SC_R_UART_1>;
-		dma-names = "tx","rx";
-		dmas = <&edma2 11 0 0>, <&edma2 10 0 1>;
+		dma-names = "rx", "tx";
+		dmas = <&edma2 10 0 FSL_EDMA_RX>, <&edma2 11 0 0>;
 		status = "disabled";
 	};
 
@@ -121,8 +122,8 @@ dma_subsys: bus@5a000000 {
 		assigned-clocks = <&clk IMX_SC_R_UART_2 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <80000000>;
 		power-domains = <&pd IMX_SC_R_UART_2>;
-		dma-names = "tx","rx";
-		dmas = <&edma2 13 0 0>, <&edma2 12 0 1>;
+		dma-names = "rx", "tx";
+		dmas = <&edma2 12 0 FSL_EDMA_RX>, <&edma2 13 0 0>;
 		status = "disabled";
 	};
 
@@ -135,8 +136,8 @@ dma_subsys: bus@5a000000 {
 		assigned-clocks = <&clk IMX_SC_R_UART_3 IMX_SC_PM_CLK_PER>;
 		assigned-clock-rates = <80000000>;
 		power-domains = <&pd IMX_SC_R_UART_3>;
-		dma-names = "tx","rx";
-		dmas = <&edma2 15 0 0>, <&edma2 14 0 1>;
+		dma-names = "rx", "tx";
+		dmas = <&edma2 14 0 FSL_EDMA_RX>, <&edma2 15 0 0>;
 		status = "disabled";
 	};
 
@@ -192,29 +193,6 @@ dma_subsys: bus@5a000000 {
 				<&pd IMX_SC_R_DMA_2_CH15>;
 	};
 
-	edma3: dma-controller@5a9f0000 {
-		compatible = "fsl,imx8qm-edma";
-		reg = <0x5a9f0000 0x90000>;
-		#dma-cells = <3>;
-		dma-channels = <8>;
-		interrupts = <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>;
-		power-domains = <&pd IMX_SC_R_DMA_3_CH0>,
-				<&pd IMX_SC_R_DMA_3_CH1>,
-				<&pd IMX_SC_R_DMA_3_CH2>,
-				<&pd IMX_SC_R_DMA_3_CH3>,
-				<&pd IMX_SC_R_DMA_3_CH4>,
-				<&pd IMX_SC_R_DMA_3_CH5>,
-				<&pd IMX_SC_R_DMA_3_CH6>,
-				<&pd IMX_SC_R_DMA_3_CH7>;
-	};
-
 	spi0_lpcg: clock-controller@5a400000 {
 		compatible = "fsl,imx8qxp-lpcg";
 		reg = <0x5a400000 0x10000>;
@@ -460,6 +438,29 @@ dma_subsys: bus@5a000000 {
 		status = "disabled";
 	};
 
+	edma3: dma-controller@5a9f0000 {
+		compatible = "fsl,imx8qm-edma";
+		reg = <0x5a9f0000 0x90000>;
+		#dma-cells = <3>;
+		dma-channels = <8>;
+		interrupts = <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>;
+		power-domains = <&pd IMX_SC_R_DMA_3_CH0>,
+				<&pd IMX_SC_R_DMA_3_CH1>,
+				<&pd IMX_SC_R_DMA_3_CH2>,
+				<&pd IMX_SC_R_DMA_3_CH3>,
+				<&pd IMX_SC_R_DMA_3_CH4>,
+				<&pd IMX_SC_R_DMA_3_CH5>,
+				<&pd IMX_SC_R_DMA_3_CH6>,
+				<&pd IMX_SC_R_DMA_3_CH7>;
+	};
+
 	i2c0_lpcg: clock-controller@5ac00000 {
 		compatible = "fsl,imx8qxp-lpcg";
 		reg = <0x5ac00000 0x10000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-gpu0.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-gpu0.dtsi
new file mode 100644
index 000000000000..9b8a44aa63d6
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-gpu0.dtsi
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2019 NXP
+ *	Dong Aisheng <aisheng.dong@nxp.com>
+ */
+
+#include <dt-bindings/firmware/imx/rsrc.h>
+
+gpu0_subsys: bus@53000000 {
+	compatible = "simple-bus";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	ranges = <0x53000000 0x0 0x53000000 0x1000000>;
+
+	gpu_3d0: gpu@53100000 {
+		compatible = "vivante,gc";
+		reg = <0x53100000 0x40000>;
+		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clk IMX_SC_R_GPU_0_PID0 IMX_SC_PM_CLK_PER>,
+			 <&clk IMX_SC_R_GPU_0_PID0 IMX_SC_PM_CLK_MISC>;
+		clock-names = "core", "shader";
+		assigned-clocks = <&clk IMX_SC_R_GPU_0_PID0 IMX_SC_PM_CLK_PER>,
+				  <&clk IMX_SC_R_GPU_0_PID0 IMX_SC_PM_CLK_MISC>;
+		assigned-clock-rates = <700000000>, <850000000>;
+		power-domains = <&pd IMX_SC_R_GPU_0_PID0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
index b972658efb17..2123d431e061 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
@@ -81,6 +81,24 @@
 		status = "disabled";
 	};
 
+	reg_can0_stby: regulator-4 {
+		compatible = "regulator-fixed";
+		regulator-name = "can0-stby";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pca6416_3 0 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_can1_stby: regulator-5 {
+		compatible = "regulator-fixed";
+		regulator-name = "can1-stby";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&pca6416_3 1 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
 	reg_usdhc2_vmmc: regulator-3 {
 		compatible = "regulator-fixed";
 		regulator-name = "SD1_SPWR";
@@ -261,12 +279,81 @@
 	};
 };
 
+&i2c3 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-frequency = <100000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+	status = "okay";
+
+	pca6416_3: gpio@20 {
+		compatible = "ti,tca6416";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-parent = <&lsio_gpio2>;
+		interrupts = <5 IRQ_TYPE_EDGE_RISING>;
+	};
+
+	pca9548_2: i2c-mux@70 {
+		compatible = "nxp,pca9548";
+		reg = <0x70>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0>;
+		};
+
+		i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x1>;
+		};
+
+		i2c@2 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x2>;
+		};
+
+		i2c@3 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x3>;
+		};
+
+		i2c@4 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x4>;
+		};
+	};
+};
+
 &lpuart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_lpuart0>;
 	status = "okay";
 };
 
+&flexcan2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan2>;
+	xceiver-supply = <&reg_can0_stby>;
+	status = "okay";
+};
+
+&flexcan3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan3>;
+	xceiver-supply = <&reg_can1_stby>;
+	status = "okay";
+};
+
 &lsio_gpio4 {
 	status = "okay";
 };
@@ -436,6 +523,20 @@
 		>;
 	};
 
+	pinctrl_flexcan2: flexcan2grp {
+		fsl,pins = <
+			IMX8DXL_UART2_TX_ADMA_FLEXCAN1_TX	0x00000021
+			IMX8DXL_UART2_RX_ADMA_FLEXCAN1_RX	0x00000021
+		>;
+	};
+
+	pinctrl_flexcan3: flexcan3grp {
+		fsl,pins = <
+			IMX8DXL_FLEXCAN2_TX_ADMA_FLEXCAN2_TX	0x00000021
+			IMX8DXL_FLEXCAN2_RX_ADMA_FLEXCAN2_RX	0x00000021
+		>;
+	};
+
 	pinctrl_fec1: fec1grp {
 		fsl,pins = <
 			IMX8DXL_COMP_CTL_GPIO_1V8_3V3_ENET_ENETB0_PAD		0x000014a0
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-ss-adma.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl-ss-adma.dtsi
index 0a477f6318f1..5d012c95222f 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-ss-adma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-ss-adma.dtsi
@@ -15,6 +15,63 @@
 	interrupts = <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
 };
 
+&edma0 {
+	reg = <0x591f0000 0x1a0000>;
+	#dma-cells = <3>;
+	dma-channels = <25>;
+	dma-channel-mask = <0x1c0cc0>;
+	interrupts = <GIC_SPI 262 IRQ_TYPE_LEVEL_HIGH>, /* asrc 0 */
+		<GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 264 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 267 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>, /* spdif0 */
+		<GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>, /* sai0 */
+		<GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>, /* sai1 */
+		<GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>, /* sai2 */
+		<GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>, /* sai3 */
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 0   IRQ_TYPE_LEVEL_HIGH>,
+		<GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>, /* gpt0 */
+		<GIC_SPI 269 IRQ_TYPE_LEVEL_HIGH>, /* gpt1 */
+		<GIC_SPI 270 IRQ_TYPE_LEVEL_HIGH>, /* gpt2 */
+		<GIC_SPI 271 IRQ_TYPE_LEVEL_HIGH>; /* gpt3 */
+	power-domains = <&pd IMX_SC_R_DMA_0_CH0>,
+			<&pd IMX_SC_R_DMA_0_CH1>,
+			<&pd IMX_SC_R_DMA_0_CH2>,
+			<&pd IMX_SC_R_DMA_0_CH3>,
+			<&pd IMX_SC_R_DMA_0_CH4>,
+			<&pd IMX_SC_R_DMA_0_CH5>,
+			<&pd IMX_SC_R_DMA_0_CH6>,
+			<&pd IMX_SC_R_DMA_0_CH7>,
+			<&pd IMX_SC_R_DMA_0_CH8>,
+			<&pd IMX_SC_R_DMA_0_CH9>,
+			<&pd IMX_SC_R_DMA_0_CH10>,
+			<&pd IMX_SC_R_DMA_0_CH11>,
+			<&pd IMX_SC_R_DMA_0_CH12>,
+			<&pd IMX_SC_R_DMA_0_CH13>,
+			<&pd IMX_SC_R_DMA_0_CH14>,
+			<&pd IMX_SC_R_DMA_0_CH15>,
+			<&pd IMX_SC_R_DMA_0_CH16>,
+			<&pd IMX_SC_R_DMA_0_CH17>,
+			<&pd IMX_SC_R_DMA_0_CH18>,
+			<&pd IMX_SC_R_DMA_0_CH19>,
+			<&pd IMX_SC_R_DMA_0_CH20>,
+			<&pd IMX_SC_R_DMA_0_CH21>,
+			<&pd IMX_SC_R_DMA_0_CH22>,
+			<&pd IMX_SC_R_DMA_0_CH23>,
+			<&pd IMX_SC_R_DMA_0_CH24>;
+};
+
 &edma2 {
 	interrupts = <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>,
 		     <GIC_SPI 289 IRQ_TYPE_LEVEL_HIGH>,
@@ -45,24 +102,44 @@
 		     <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>;
 };
 
+&flexcan1 {
+	interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&flexcan2 {
+	interrupts = <GIC_SPI 239 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&flexcan3 {
+	interrupts = <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>;
+};
+
 &i2c0 {
 	compatible = "fsl,imx8dxl-lpi2c", "fsl,imx7ulp-lpi2c";
 	interrupts = <GIC_SPI 222 IRQ_TYPE_LEVEL_HIGH>;
+	dma-names = "tx","rx";
+	dmas = <&edma3 1 0 0>, <&edma3 0 0 FSL_EDMA_RX>;
 };
 
 &i2c1 {
 	compatible = "fsl,imx8dxl-lpi2c", "fsl,imx7ulp-lpi2c";
 	interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
+	dma-names = "tx","rx";
+	dmas = <&edma3 3 0 0>, <&edma3 2 0 FSL_EDMA_RX>;
 };
 
 &i2c2 {
 	compatible = "fsl,imx8dxl-lpi2c", "fsl,imx7ulp-lpi2c";
 	interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
+	dma-names = "tx","rx";
+	dmas = <&edma3 5 0 0>, <&edma3 4 0 FSL_EDMA_RX>;
 };
 
 &i2c3 {
 	compatible = "fsl,imx8dxl-lpi2c", "fsl,imx7ulp-lpi2c";
 	interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+	dma-names = "tx","rx";
+	dmas = <&edma3 7 0 0>, <&edma3 6 0 FSL_EDMA_RX>;
 };
 
 &lpuart0 {
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi
index f580eb6db9a6..a0674c5c5576 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi
@@ -4,6 +4,7 @@
  */
 
 #include <dt-bindings/clock/imx8-clock.h>
+#include <dt-bindings/dma/fsl-edma.h>
 #include <dt-bindings/firmware/imx/rsrc.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp-mba8xx.dts b/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp-mba8xx.dts
new file mode 100644
index 000000000000..f35514b7b338
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp-mba8xx.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+/dts-v1/;
+
+#include "imx8dxp-tqma8xdp.dtsi"
+#include "mba8xx.dtsi"
+
+/ {
+	model = "TQ-Systems i.MX8DXP TQMa8XDP on MBa8Xx";
+	compatible = "tq,imx8dxp-tqma8xdp-mba8xx", "tq,imx8dxp-tqma8xdp", "fsl,imx8dxp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp.dtsi b/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp.dtsi
new file mode 100644
index 000000000000..e2de8517aa0e
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8dxp-tqma8xdp.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+#include "imx8dxp.dtsi"
+#include "tqma8xx.dtsi"
+
+/ {
+	model = "TQ-Systems i.MX8DXP TQMa8XDP";
+	compatible = "tq,imx8dxp-tqma8xdp", "fsl,imx8dxp";
+};
+
+&pmic_thermal {
+	cooling-maps {
+		map0 {
+			cooling-device =
+				<&A35_0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&A35_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8dxp.dtsi b/arch/arm64/boot/dts/freescale/imx8dxp.dtsi
new file mode 100644
index 000000000000..a8f7352332c0
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8dxp.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017-2019 NXP
+ */
+
+/dts-v1/;
+
+#include "imx8qxp.dtsi"
+
+/delete-node/ &A35_2;
+/delete-node/ &A35_3;
+
+&thermal_zones {
+	cpu0-thermal {
+		cooling-maps {
+			map0 {
+				cooling-device =
+				<&A35_0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+				<&A35_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index b53104ed8919..bd5b365867fd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -151,6 +151,28 @@
 			clocks = <&clk IMX8MM_CLK_SAI3_ROOT>;
 		};
 	};
+
+	sound-micfil {
+		compatible = "fsl,imx-audio-card";
+		model = "micfil-audio";
+
+		pri-dai-link {
+			link-name = "micfil hifi";
+			format = "i2s";
+
+			cpu {
+				sound-dai = <&micfil>;
+			};
+		};
+	};
+
+	sound-spdif {
+		compatible = "fsl,imx-audio-spdif";
+		model = "imx-spdif";
+		spdif-controller = <&spdif1>;
+		spdif-out;
+		spdif-in;
+	};
 };
 
 &A53_0 {
@@ -434,6 +456,16 @@
 	status = "okay";
 };
 
+&micfil {
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pdm>;
+	assigned-clocks = <&clk IMX8MM_CLK_PDM>;
+	assigned-clock-parents = <&clk IMX8MM_AUDIO_PLL1_OUT>;
+	assigned-clock-rates = <196608000>;
+	status = "okay";
+};
+
 &mipi_csi {
 	status = "okay";
 
@@ -509,6 +541,24 @@
 	status = "okay";
 };
 
+&spdif1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spdif1>;
+	assigned-clocks = <&clk IMX8MM_CLK_SPDIF1>;
+	assigned-clock-parents = <&clk IMX8MM_AUDIO_PLL1_OUT>;
+	assigned-clock-rates = <24576000>;
+	clocks = <&clk IMX8MM_CLK_AUDIO_AHB>, <&clk IMX8MM_CLK_24M>,
+		 <&clk IMX8MM_CLK_SPDIF1>, <&clk IMX8MM_CLK_DUMMY>,
+		 <&clk IMX8MM_CLK_DUMMY>, <&clk IMX8MM_CLK_DUMMY>,
+		 <&clk IMX8MM_CLK_AUDIO_AHB>, <&clk IMX8MM_CLK_DUMMY>,
+		 <&clk IMX8MM_CLK_DUMMY>, <&clk IMX8MM_CLK_DUMMY>,
+		 <&clk IMX8MM_AUDIO_PLL1_OUT>, <&clk IMX8MM_AUDIO_PLL2_OUT>;
+	clock-names = "core", "rxtx0", "rxtx1", "rxtx2", "rxtx3",
+		      "rxtx4", "rxtx5", "rxtx6", "rxtx7", "spba",
+		      "pll8k", "pll11k";
+	status = "okay";
+};
+
 &uart2 { /* console */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart2>;
@@ -636,6 +686,18 @@
 		>;
 	};
 
+	pinctrl_pdm: pdmgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI5_MCLK_SAI5_MCLK        0xd6
+			MX8MM_IOMUXC_SAI5_RXC_PDM_CLK           0xd6
+			MX8MM_IOMUXC_SAI5_RXFS_SAI5_RX_SYNC     0xd6
+			MX8MM_IOMUXC_SAI5_RXD0_PDM_DATA0        0xd6
+			MX8MM_IOMUXC_SAI5_RXD1_PDM_DATA1        0xd6
+			MX8MM_IOMUXC_SAI5_RXD2_PDM_DATA2        0xd6
+			MX8MM_IOMUXC_SAI5_RXD3_PDM_DATA3        0xd6
+		>;
+	};
+
 	pinctrl_pmic: pmicirqgrp {
 		fsl,pins = <
 			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x141
@@ -666,6 +728,13 @@
 		>;
 	};
 
+	pinctrl_spdif1: spdif1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SPDIF_TX_SPDIF1_OUT	0xd6
+			MX8MM_IOMUXC_SPDIF_RX_SPDIF1_IN		0xd6
+		>;
+	};
+
 	pinctrl_typec1: typec1grp {
 		fsl,pins = <
 			MX8MM_IOMUXC_SD1_STROBE_GPIO2_IO11	0x159
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts
index 8b16bd68576c..33f8d7d1970e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts
@@ -25,23 +25,21 @@
 
 	leds {
 		compatible = "gpio-leds";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_gpio_led>;
 
 		led1 {
 			label = "led1";
-			gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio1 5 GPIO_ACTIVE_LOW>;
 			linux,default-trigger = "heartbeat";
 		};
 
 		led2 {
 			label = "led2";
-			gpios = <&gpio1 13 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio3 8 GPIO_ACTIVE_LOW>;
 		};
 
 		led3 {
 			label = "led3";
-			gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio3 7 GPIO_ACTIVE_LOW>;
 		};
 	};
 
@@ -52,24 +50,12 @@
 
 	reg_rst_eth2: regulator-rst-eth2 {
 		compatible = "regulator-fixed";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_usb_eth2>;
-		gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio1 1 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 		regulator-always-on;
 		regulator-name = "rst-usb-eth2";
 	};
 
-	reg_usb1_vbus: regulator-usb1-vbus {
-		compatible = "regulator-fixed";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_reg_usb1_vbus>;
-		gpio = <&gpio3 25 GPIO_ACTIVE_LOW>;
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		regulator-name = "usb1-vbus";
-	};
-
 	reg_vdd_5v: regulator-5v {
 		compatible = "regulator-fixed";
 		regulator-always-on;
@@ -80,9 +66,6 @@
 };
 
 &ecspi2 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_ecspi2>;
-	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
 	can@0 {
@@ -91,7 +74,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_can>;
 		clocks = <&osc_can>;
-		interrupts-extended = <&gpio4 28 IRQ_TYPE_LEVEL_LOW>;
+		interrupts-extended = <&gpio5 1 IRQ_TYPE_LEVEL_LOW>;
 		/*
 		 * Limit the SPI clock to 15 MHz to prevent issues
 		 * with corrupted data due to chip errata.
@@ -103,9 +86,6 @@
 };
 
 &ecspi3 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_ecspi3>;
-	cs-gpios = <&gpio5 25 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
 	eeram@0 {
@@ -117,8 +97,8 @@
 
 &fec1 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_enet>;
-	phy-connection-type = "rgmii-rxid";
+	pinctrl-0 = <&pinctrl_enet_rgmii>;
+	phy-connection-type = "rgmii-id";
 	phy-handle = <&ethphy>;
 	status = "okay";
 
@@ -127,55 +107,101 @@
 		#size-cells = <0>;
 
 		ethphy: ethernet-phy@0 {
+			compatible = "ethernet-phy-id4f51.e91b";
 			reg = <0>;
-			reset-assert-us = <1>;
-			reset-deassert-us = <15000>;
-			reset-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <10000>;
+			reset-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
 		};
 	};
 };
 
+/*
+ * Rename SoM signals according to board usage:
+ *   GPIO_B_0      -> DIO1_OUT
+ *   GPIO_B_1      -> DIO2_OUT
+ */
 &gpio1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_gpio1>;
-	gpio-line-names = "", "", "", "dio1-out", "", "", "dio1-in", "dio2-out",
-			  "dio2-in", "dio3-out", "dio3-in", "dio4-out", "", "", "", "",
-			  "", "", "", "", "", "", "", "",
-			  "", "", "", "", "", "", "", "";
+	gpio-line-names = "", "GPIO_A_0", "", "GPIO_A_1",
+			  "", "GPIO_A_2", "GPIO_A_3", "GPIO_A_4",
+			  "GPIO_A_5", "GPIO_A_6", "GPIO_A_7", "DIO1_OUT",
+			  "DIO2_OUT", "USB_A_OC#", "CAM_MCK", "USB_B_OC#",
+			  "ETH_MDC", "ETH_MDIO", "ETH_A_(S)(R)(G)MII_TXD3",
+			  "ETH_A_(S)(R)(G)MII_TXD2", "ETH_A_(S)(R)(G)MII_TXD1",
+			  "ETH_A_(S)(R)(G)MII_TXD0", "ETH_A_(R)(G)MII_TX_EN(_ER)",
+			  "ETH_A_(R)(G)MII_TX_CLK", "ETH_A_(R)(G)MII_RX_DV(_ER)",
+			  "ETH_A_(R)(G)MII_RX_CLK", "ETH_A_(S)(R)(G)MII_RXD0",
+			  "ETH_A_(S)(R)(G)MII_RXD1", "ETH_A_(R)(G)MII_RXD2",
+			  "ETH_A_(R)(G)MII_RXD3";
 };
 
-&gpio5 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_gpio5>;
-	gpio-line-names = "", "", "dio4-in", "", "", "", "", "",
-			  "", "", "", "", "", "", "", "",
-			  "", "", "", "", "", "", "", "",
-			  "", "", "", "", "", "", "", "";
+/*
+ * Rename SoM signals according to board usage:
+ *   GPIO_B_2      -> DIO3_OUT
+ *   GPIO_B_3      -> DIO4_OUT
+ */
+&gpio3 {
+	gpio-line-names = "GPIO_C_5", "GPIO_C_4", "SDIO_B_CD#", "SDIO_B_D5",
+			  "SDIO_B_D6", "SDIO_B_D7", "GPIO_C_0", "GPIO_C_1",
+			  "GPIO_C_2", "GPIO_C_3", "SDIO_B_D0", "SDIO_B_D1",
+			  "SDIO_B_D2", "SDIO_B_D3", "", "SDIO_B_D4",
+			  "CARRIER_PWR_EN", "SDIO_B_CLK", "SDIO_B_CMD", "DIO3_OUT",
+			  "USB_B_EN", "DIO4_OUT", "PCIe_CLKREQ#", "PCIe_A_PERST#",
+			  "PCIe_WAKE#", "USB_A_EN";
 };
 
-&i2c4 {
-	clock-frequency = <100000>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_i2c4>;
+/*
+ * Rename SoM signals according to board usage:
+ *   GPIO_B_4      -> DIO1_IN
+ *   GPIO_B_5      -> DIO2_IN
+ *   GPIO_B_6      -> DIO3_IN
+ *   GPIO_B_7      -> DIO4_IN
+ */
+&gpio4 {
+	gpio-line-names = "GPIO_C_7", "", "I2S_A_DATA_IN", "I2S_B_DATA_IN",
+			  "DIO1_IN", "BOOT_SEL0#", "BOOT_SEL1#", "",
+			  "", "", "I2S_LRCLK", "I2S_BITCLK",
+			  "I2S_A_DATA_OUT", "I2S_B_DATA_OUT", "DIO2_IN", "DIO3_IN",
+			  "DIO4_IN", "SPI_A_/WP_(IO2)", "SPI_A_/HOLD_(IO3)", "GPIO_C_6",
+			  "I2S_MCLK", "UART_A_TX", "UART_A_RX", "UART_A_CTS",
+			  "UART_A_RTS", "", "", "",
+			  "PCIe_SM_ALERT", "UART_B_RTS", "UART_B_CTS", "UART_B_RX";
+};
+
+&i2c3 {
 	status = "okay";
+
+	usb-hub@2c {
+		compatible = "microchip,usb2514b";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb_hub>;
+		reg = <0x2c>;
+		non-removable-ports = <0>, <3>;
+		reset-gpios = <&gpio5 2 GPIO_ACTIVE_LOW>;
+	};
 };
 
 &pwm2 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_pwm2>;
 	status = "okay";
 };
 
+&reg_usb2_vbus {
+	status = "disabled";
+};
+
+&reg_usdhc2_vcc {
+	status = "disabled";
+};
+
+&reg_usdhc3_vcc {
+	status = "disabled";
+};
+
 &uart1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart1>;
 	uart-has-rtscts;
 	status = "okay";
 };
 
 &uart2 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_uart2>;
 	linux,rs485-enabled-at-boot-time;
 	uart-has-rtscts;
 	status = "okay";
@@ -183,8 +209,6 @@
 
 &usbotg1 {
 	dr_mode = "otg";
-	disable-over-current;
-	vbus-supply = <&reg_usb1_vbus>;
 	status = "okay";
 };
 
@@ -195,14 +219,17 @@
 	#size-cells = <0>;
 	status = "okay";
 
+	/* VBUS is controlled by the hub */
+	/delete-property/ vbus-supply;
+
 	usb1@1 {
-		compatible = "usb424,9514";
+		compatible = "usb424,2514";
 		reg = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 
 		usbnet: ethernet@1 {
-			compatible = "usb424,ec00";
+			compatible = "usbb95,772b";
 			reg = <1>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
 		};
@@ -210,167 +237,20 @@
 };
 
 &usdhc2 {
-	pinctrl-names = "default", "state_100mhz", "state_200mhz";
-	pinctrl-0 = <&pinctrl_usdhc2>;
-	pinctrl-1 = <&pinctrl_usdhc2_100mhz>;
-	pinctrl-2 = <&pinctrl_usdhc2_200mhz>;
 	vmmc-supply = <&reg_vdd_3v3>;
-	vqmmc-supply = <&reg_nvcc_sd>;
-	cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
 &iomuxc {
 	pinctrl_can: cangrp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28		0x19
-		>;
-	};
-
-	pinctrl_ecspi2: ecspi2grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO		0x82
-			MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI		0x82
-			MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK		0x82
-			MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13		0x19
-		>;
-	};
-
-	pinctrl_ecspi3: ecspi3grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_UART2_RXD_ECSPI3_MISO		0x82
-			MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI		0x82
-			MX8MM_IOMUXC_UART1_RXD_ECSPI3_SCLK		0x82
-			MX8MM_IOMUXC_UART2_TXD_GPIO5_IO25		0x19
-		>;
-	};
-
-	pinctrl_enet: enetgrp {
-		fsl,pins = <
-			MX8MM_IOMUXC_ENET_MDC_ENET1_MDC			0x3
-			MX8MM_IOMUXC_ENET_MDIO_ENET1_MDIO		0x3
-			MX8MM_IOMUXC_ENET_TD3_ENET1_RGMII_TD3		0x1f
-			MX8MM_IOMUXC_ENET_TD2_ENET1_RGMII_TD2		0x1f
-			MX8MM_IOMUXC_ENET_TD1_ENET1_RGMII_TD1		0x1f
-			MX8MM_IOMUXC_ENET_TD0_ENET1_RGMII_TD0		0x1f
-			MX8MM_IOMUXC_ENET_RD3_ENET1_RGMII_RD3		0x91
-			MX8MM_IOMUXC_ENET_RD2_ENET1_RGMII_RD2		0x91
-			MX8MM_IOMUXC_ENET_RD1_ENET1_RGMII_RD1		0x91
-			MX8MM_IOMUXC_ENET_RD0_ENET1_RGMII_RD0		0x91
-			MX8MM_IOMUXC_ENET_TXC_ENET1_RGMII_TXC		0x1f
-			MX8MM_IOMUXC_ENET_RXC_ENET1_RGMII_RXC		0x91
-			MX8MM_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL	0x91
-			MX8MM_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL	0x1f
-			MX8MM_IOMUXC_GPIO1_IO01_GPIO1_IO1		0x19 /* PHY RST */
-			MX8MM_IOMUXC_GPIO1_IO05_GPIO1_IO5		0x19 /* ETH IRQ */
-		>;
-	};
-
-	pinctrl_gpio_led: gpioledgrp {
-		fsl,pins = <
-			MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12		0x19
-			MX8MM_IOMUXC_GPIO1_IO13_GPIO1_IO13		0x19
-			MX8MM_IOMUXC_GPIO1_IO14_GPIO1_IO14		0x19
-		>;
-	};
-
-	pinctrl_gpio1: gpio1grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x19
-			MX8MM_IOMUXC_GPIO1_IO07_GPIO1_IO7		0x19
-			MX8MM_IOMUXC_GPIO1_IO09_GPIO1_IO9		0x19
-			MX8MM_IOMUXC_GPIO1_IO11_GPIO1_IO11		0x19
-			MX8MM_IOMUXC_GPIO1_IO06_GPIO1_IO6		0x19
-			MX8MM_IOMUXC_GPIO1_IO08_GPIO1_IO8		0x19
-			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10		0x19
-		>;
-	};
-
-	pinctrl_gpio5: gpio5grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SAI3_MCLK_GPIO5_IO2		0x19
-		>;
-	};
-
-	pinctrl_i2c4: i2c4grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL			0x400001c3
-			MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA			0x400001c3
-		>;
-	};
-
-	pinctrl_pwm2: pwm2grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SPDIF_RX_PWM2_OUT			0x19
-		>;
-	};
-
-	pinctrl_reg_usb1_vbus: regusb1vbusgrp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SAI5_MCLK_GPIO3_IO25		0x19
-		>;
-	};
-
-	pinctrl_uart1: uart1grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX		0x140
-			MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX		0x140
-			MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B		0x140
-			MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B		0x140
-		>;
-	};
-
-	pinctrl_uart2: uart2grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX		0x140
-			MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX		0x140
-			MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B		0x140
-			MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B		0x140
-		>;
-	};
-
-	pinctrl_usb_eth2: usbeth2grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_NAND_CE1_B_GPIO3_IO2		0x19
-		>;
-	};
-
-	pinctrl_usdhc2: usdhc2grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x190
-			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d0
-			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d0
-			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d0
-			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d0
-			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d0
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
-		>;
-	};
-
-	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
-		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x194
-			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d4
-			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d4
-			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d4
-			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d4
-			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d4
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
+			MX8MM_IOMUXC_SAI3_TXD_GPIO5_IO1			0x19  /* SDIO_B_PWR_EN */
 		>;
 	};
 
-	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+	pinctrl_usb_hub: usbhubgrp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x196
-			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d6
-			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d6
-			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d6
-			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d6
-			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d6
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
+			MX8MM_IOMUXC_SAI3_MCLK_GPIO5_IO2		0x19 /* SDIO_B_WP */
 		>;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
index dcec57c20399..aab8e2421650 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts
@@ -279,8 +279,8 @@
 
 	pinctrl_i2c4: i2c4grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL			0x400001c3
-			MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA			0x400001c3
+			MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL			0x40000083
+			MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA			0x40000083
 		>;
 	};
 
@@ -292,19 +292,19 @@
 
 	pinctrl_uart1: uart1grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX		0x140
-			MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX		0x140
-			MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B		0x140
-			MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B		0x140
+			MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX		0x0
+			MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX		0x0
+			MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B		0x0
+			MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B		0x0
 		>;
 	};
 
 	pinctrl_uart2: uart2grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX		0x140
-			MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX		0x140
-			MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B		0x140
-			MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B		0x140
+			MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX		0x0
+			MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX		0x0
+			MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B		0x0
+			MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B		0x0
 		>;
 	};
 
@@ -316,40 +316,40 @@
 
 	pinctrl_usdhc2: usdhc2grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x190
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x90
 			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d0
 			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d0
 			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d0
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d0
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d0
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
+			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
 		>;
 	};
 
 	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x194
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x94
 			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d4
 			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d4
 			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d4
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d4
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d4
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
+			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
 		>;
 	};
 
 	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x196
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x96
 			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d6
 			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d6
 			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d6
 			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d6
 			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d6
-			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x019
-			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x1d0
+			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0xd0
 		>;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
index 6e75ab879bf5..663ae52b4852 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi
@@ -3,6 +3,7 @@
  * Copyright (C) 2022 Kontron Electronics GmbH
  */
 
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include "imx8mm.dtsi"
 
@@ -28,6 +29,73 @@
 	chosen {
 		stdout-path = &uart3;
 	};
+
+	reg_vdd_carrier: regulator-vdd-carrier {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_vdd_carrier>;
+		gpio = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-name = "VDD_CARRIER";
+
+		regulator-state-standby {
+			regulator-on-in-suspend;
+		};
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+
+		regulator-state-disk {
+			regulator-off-in-suspend;
+		};
+	};
+
+	reg_usb1_vbus: regulator-usb1-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usb1_vbus>;
+		enable-active-high;
+		gpio = <&gpio3 25 GPIO_ACTIVE_HIGH>;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "VBUS_USB1";
+	};
+
+	reg_usb2_vbus: regulator-usb2-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usb2_vbus>;
+		enable-active-high;
+		gpio = <&gpio3 20 GPIO_ACTIVE_HIGH>;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-name = "VBUS_USB2";
+	};
+
+	reg_usdhc2_vcc: regulator-usdhc2-vcc {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usdhc2_vcc>;
+		enable-active-high;
+		gpio = <&gpio2 19 GPIO_ACTIVE_HIGH>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "VCC_SDIO_A";
+	};
+
+	reg_usdhc3_vcc: regulator-usdhc3-vcc {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usdhc3_vcc>;
+		enable-active-high;
+		gpio = <&gpio5 1 GPIO_ACTIVE_HIGH>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "VCC_SDIO_B";
+	};
 };
 
 &A53_0 {
@@ -96,6 +164,79 @@
 	};
 };
 
+&ecspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi2>, <&pinctrl_ecspi2_gpio>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+};
+
+&ecspi3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_ecspi3>;
+	cs-gpios = <&gpio5 25 GPIO_ACTIVE_LOW>;
+};
+
+&gpio1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio1>;
+	gpio-line-names = "", "GPIO_A_0", "", "GPIO_A_1",
+			  "", "GPIO_A_2", "GPIO_A_3", "GPIO_A_4",
+			  "GPIO_A_5", "GPIO_A_6", "GPIO_A_7", "GPIO_B_0",
+			  "GPIO_B_1", "USB_A_OC#", "CAM_MCK", "USB_B_OC#",
+			  "ETH_MDC", "ETH_MDIO", "ETH_A_(S)(R)(G)MII_TXD3",
+			  "ETH_A_(S)(R)(G)MII_TXD2", "ETH_A_(S)(R)(G)MII_TXD1",
+			  "ETH_A_(S)(R)(G)MII_TXD0", "ETH_A_(R)(G)MII_TX_EN(_ER)",
+			  "ETH_A_(R)(G)MII_TX_CLK", "ETH_A_(R)(G)MII_RX_DV(_ER)",
+			  "ETH_A_(R)(G)MII_RX_CLK", "ETH_A_(S)(R)(G)MII_RXD0",
+			  "ETH_A_(S)(R)(G)MII_RXD1", "ETH_A_(R)(G)MII_RXD2",
+			  "ETH_A_(R)(G)MII_RXD3";
+};
+
+&gpio2 {
+	gpio-line-names = "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "SDIO_A_CD#", "SDIO_A_CLK", "SDIO_A_CMD", "SDIO_A_D0",
+			  "SDIO_A_D1", "SDIO_A_D2", "SDIO_A_D3", "SDIO_A_PWR_EN",
+			  "SDIO_A_WP";
+};
+
+&gpio3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio3>;
+	gpio-line-names = "GPIO_C_5", "GPIO_C_4", "SDIO_B_CD#", "SDIO_B_D5",
+			  "SDIO_B_D6", "SDIO_B_D7", "GPIO_C_0", "GPIO_C_1",
+			  "GPIO_C_2", "GPIO_C_3", "SDIO_B_D0", "SDIO_B_D1",
+			  "SDIO_B_D2", "SDIO_B_D3", "", "SDIO_B_D4",
+			  "CARRIER_PWR_EN", "SDIO_B_CLK", "SDIO_B_CMD", "GPIO_B_2",
+			  "USB_B_EN", "GPIO_B_3", "PCIe_CLKREQ#", "PCIe_A_PERST#",
+			  "PCIe_WAKE#", "USB_A_EN";
+};
+
+&gpio4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio4>;
+	gpio-line-names = "GPIO_C_7", "", "I2S_A_DATA_IN", "I2S_B_DATA_IN",
+			  "GPIO_B_4", "BOOT_SEL0#", "BOOT_SEL1#", "",
+			  "", "", "I2S_LRCLK", "I2S_BITCLK",
+			  "I2S_A_DATA_OUT", "I2S_B_DATA_OUT", "GPIO_B_5", "GPIO_B_6",
+			  "GPIO_B_7", "SPI_A_/WP_(IO2)", "SPI_A_/HOLD_(IO3)", "GPIO_C_6",
+			  "I2S_MCLK", "UART_A_TX", "UART_A_RX", "UART_A_CTS",
+			  "UART_A_RTS", "", "", "",
+			  "PCIe_SM_ALERT", "UART_B_RTS", "UART_B_CTS", "UART_B_RX";
+};
+
+&gpio5 {
+	gpio-line-names = "UART_B_TX", "SDIO_B_PWR_EN", "SDIO_B_WP", "PWM_2",
+			  "PWM_1", "PWM_0", "", "",
+			  "", "", "SPI_A_SCK", "SPI_A_SDO_(IO1)",
+			  "SPI_A_SCK", "SPI_A_CS0#", "", "",
+			  "I2C_A_SCL", "I2C_A_SDA", "I2C_B_SCL", "I2C_B_SDA",
+			  "PCIe_SMCLK", "PCIe_SMDAT", "SPI_B_SCK", "SPI_B_SDO",
+			  "SPI_B_SDI", "SPI_B_CS0#", "UART_CON_RX", "UART_CON_TX",
+			  "UART_C_RX", "UART_C_TX";
+};
+
 &i2c1 {
 	clock-frequency = <400000>;
 	pinctrl-names = "default";
@@ -205,22 +346,86 @@
 		};
 	};
 
+	eeprom: eeprom@50 {
+		compatible = "atmel,24c64";
+		reg = <0x50>;
+		address-width = <16>;
+		pagesize = <32>;
+		size = <8192>;
+	};
+
 	rv3028: rtc@52 {
 		compatible = "microcrystal,rv3028";
 		reg = <0x52>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_rtc>;
-		interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_HIGH>;
-		trickle-diode-disable;
+		interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_LOW>;
 	};
 };
 
+&i2c2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c3>;
+};
+
+&i2c4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c4>;
+};
+
+&pwm1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm1>;
+};
+
+&pwm2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm2>;
+};
+
+&pwm3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm3>;
+};
+
+&uart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+};
+
 &uart3 { /* console */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart3>;
 	status = "okay";
 };
 
+&uart4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart4>;
+};
+
+&usbotg1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usb1>;
+	vbus-supply = <&reg_usb1_vbus>;
+};
+
+&usbotg2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usb2>;
+	vbus-supply = <&reg_usb2_vbus>;
+};
+
 &usdhc1 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc1>;
@@ -233,6 +438,26 @@
 	status = "okay";
 };
 
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
+	vmmc-supply = <&reg_usdhc2_vcc>;
+	vqmmc-supply = <&reg_nvcc_sd>;
+	cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
+};
+
+&usdhc3 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc3>, <&pinctrl_usdhc3_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc3_100mhz>, <&pinctrl_usdhc3_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc3_200mhz>, <&pinctrl_usdhc3_gpio>;
+	vmmc-supply = <&reg_usdhc3_vcc>;
+	vqmmc-supply = <&reg_nvcc_sd>;
+	cd-gpios = <&gpio3 2 GPIO_ACTIVE_LOW>;
+};
+
 &wdog1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_wdog>;
@@ -241,6 +466,12 @@
 };
 
 &iomuxc {
+	pinctrl_csi_mck: csimckgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO14_CCMSRCGPCMIX_CLKO1	0x59 /* CAM_MCK */
+		>;
+	};
+
 	pinctrl_ecspi1: ecspi1grp {
 		fsl,pins = <
 			MX8MM_IOMUXC_ECSPI1_MISO_ECSPI1_MISO		0x82
@@ -250,10 +481,140 @@
 		>;
 	};
 
+	pinctrl_ecspi2: ecspi2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO		0x82 /* SPI_A_SDI_(IO0) */
+			MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI		0x82 /* SPI_A_SDO_(IO1) */
+			MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK		0x82 /* SPI_A_SCK */
+			MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13		0x19 /* SPI_A_CS0# */
+		>;
+	};
+
+	pinctrl_ecspi2_gpio: ecspi2gpiogrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_TXD5_GPIO4_IO17		0x19 /* SPI_A_/WP_(IO2) */
+			MX8MM_IOMUXC_SAI1_TXD6_GPIO4_IO18		0x19 /* SPI_A_/HOLD_(IO3) */
+		>;
+	};
+
+	pinctrl_ecspi3: ecspi3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_UART2_RXD_ECSPI3_MISO		0x82 /* SPI_B_SDI */
+			MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI		0x82 /* SPI_B_SDO */
+			MX8MM_IOMUXC_UART1_RXD_ECSPI3_SCLK		0x82 /* SPI_B_SCK */
+			MX8MM_IOMUXC_UART2_TXD_GPIO5_IO25		0x19 /* SPI_B_CS0# */
+		>;
+	};
+
+	pinctrl_enet_rgmii: enetrgmiigrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_ENET_MDC_ENET1_MDC			0x03 /* ETH_MDC */
+			MX8MM_IOMUXC_ENET_MDIO_ENET1_MDIO		0x03 /* ETH_MDIO */
+			MX8MM_IOMUXC_ENET_TD3_ENET1_RGMII_TD3		0x1f /* ETH_A_(S)(R)(G)MII_TXD3 */
+			MX8MM_IOMUXC_ENET_TD2_ENET1_RGMII_TD2		0x1f /* ETH_A_(S)(R)(G)MII_TXD2 */
+			MX8MM_IOMUXC_ENET_TD1_ENET1_RGMII_TD1		0x1f /* ETH_A_(S)(R)(G)MII_TXD1 */
+			MX8MM_IOMUXC_ENET_TD0_ENET1_RGMII_TD0		0x1f /* ETH_A_(S)(R)(G)MII_TXD0 */
+			MX8MM_IOMUXC_ENET_RD3_ENET1_RGMII_RD3		0x91 /* ETH_A_(R)(G)MII_RXD3 */
+			MX8MM_IOMUXC_ENET_RD2_ENET1_RGMII_RD2		0x91 /* ETH_A_(R)(G)MII_RXD2 */
+			MX8MM_IOMUXC_ENET_RD1_ENET1_RGMII_RD1		0x91 /* ETH_A_(S)(R)(G)MII_RXD1 */
+			MX8MM_IOMUXC_ENET_RD0_ENET1_RGMII_RD0		0x91 /* ETH_A_(S)(R)(G)MII_RXD0 */
+			MX8MM_IOMUXC_ENET_TXC_ENET1_RGMII_TXC		0x1f /* ETH_A_(R)(G)MII_TX_CLK */
+			MX8MM_IOMUXC_ENET_RXC_ENET1_RGMII_RXC		0x91 /* ETH_A_(R)(G)MII_RX_CLK */
+			MX8MM_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL	0x91 /* ETH_A_(R)(G)MII_RX_DV(_ER) */
+			MX8MM_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL	0x1f /* ETH_A_(R)(G)MII_TX_EN(_ER) */
+		>;
+	};
+
+	pinctrl_enet_rmii: enetrmiigrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_ENET_MDC_ENET1_MDC			0x03 /* ETH_MDC */
+			MX8MM_IOMUXC_ENET_MDIO_ENET1_MDIO		0x03 /* ETH_MDIO */
+			MX8MM_IOMUXC_ENET_TD2_ENET1_TX_CLK		0x4000001f /* ETH_A_(S)(R)(G)MII_TXD2 */
+			MX8MM_IOMUXC_ENET_TD1_ENET1_RGMII_TD1		0x56 /* ETH_A_(S)(R)(G)MII_TXD1 */
+			MX8MM_IOMUXC_ENET_TD0_ENET1_RGMII_TD0		0x56 /* ETH_A_(S)(R)(G)MII_TXD0 */
+			MX8MM_IOMUXC_ENET_RD1_ENET1_RGMII_RD1		0x56 /* ETH_A_(S)(R)(G)MII_RXD1 */
+			MX8MM_IOMUXC_ENET_RD0_ENET1_RGMII_RD0		0x56 /* ETH_A_(S)(R)(G)MII_RXD0 */
+			MX8MM_IOMUXC_ENET_RXC_ENET1_RX_ER		0x56 /* ETH_A_(R)(G)MII_RX_CLK */
+			MX8MM_IOMUXC_ENET_RX_CTL_ENET1_RGMII_RX_CTL	0x56 /* ETH_A_(R)(G)MII_RX_DV(_ER) */
+			MX8MM_IOMUXC_ENET_TX_CTL_ENET1_RGMII_TX_CTL	0x56 /* ETH_A_(R)(G)MII_TX_EN(_ER) */
+		>;
+	};
+
+	pinctrl_gpio1: gpio1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO01_GPIO1_IO1		0x19 /* GPIO_A_0 */
+			MX8MM_IOMUXC_GPIO1_IO03_GPIO1_IO3		0x19 /* GPIO_A_1 */
+			MX8MM_IOMUXC_GPIO1_IO05_GPIO1_IO5		0x19 /* GPIO_A_2 */
+			MX8MM_IOMUXC_GPIO1_IO06_GPIO1_IO6		0x19 /* GPIO_A_3 */
+			MX8MM_IOMUXC_GPIO1_IO07_GPIO1_IO7		0x19 /* GPIO_A_4 */
+			MX8MM_IOMUXC_GPIO1_IO08_GPIO1_IO8		0x19 /* GPIO_A_5 */
+			MX8MM_IOMUXC_GPIO1_IO09_GPIO1_IO9		0x19 /* GPIO_A_6 */
+			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10		0x19 /* GPIO_A_7 */
+			MX8MM_IOMUXC_GPIO1_IO11_GPIO1_IO11		0x19 /* GPIO_B_0 */
+			MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12		0x19 /* GPIO_B_1 */
+		>;
+	};
+
+	pinctrl_gpio3: gpio3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_ALE_GPIO3_IO0			0x19 /* GPIO_C_5 */
+			MX8MM_IOMUXC_NAND_CE0_B_GPIO3_IO1		0x19 /* GPIO_C_4 */
+			MX8MM_IOMUXC_NAND_DATA00_GPIO3_IO6		0x19 /* GPIO_C_0 */
+			MX8MM_IOMUXC_NAND_DATA01_GPIO3_IO7		0x19 /* GPIO_C_1 */
+			MX8MM_IOMUXC_NAND_DATA02_GPIO3_IO8		0x19 /* GPIO_C_2 */
+			MX8MM_IOMUXC_NAND_DATA03_GPIO3_IO9		0x19 /* GPIO_C_3 */
+			MX8MM_IOMUXC_SAI5_RXFS_GPIO3_IO19		0x19 /* GPIO_B_2 */
+			MX8MM_IOMUXC_SAI5_RXD0_GPIO3_IO21		0x19 /* GPIO_B_3 */
+		>;
+	};
+
+	pinctrl_gpio4: gpio4grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0		0x19 /* GPIO_C_7 */
+			MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4		0x19 /* GPIO_B_4 */
+			MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5		0x19 /* BOOT_SEL0# */
+			MX8MM_IOMUXC_SAI1_RXD4_GPIO4_IO6		0x19 /* BOOT_SEL1# */
+			MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14		0x19 /* GPIO_B_5 */
+			MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15		0x19 /* GPIO_B_6 */
+			MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16		0x19 /* GPIO_B_7 */
+			MX8MM_IOMUXC_SAI1_TXD7_GPIO4_IO19		0x19 /* GPIO_C_6 */
+		>;
+	};
+
 	pinctrl_i2c1: i2c1grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL			0x400001c3
-			MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA			0x400001c3
+			MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL			0x40000083
+			MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA			0x40000083
+		>;
+	};
+
+	pinctrl_i2c2: i2c2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_I2C2_SCL_I2C2_SCL			0x40000083 /* I2C_A_SCL */
+			MX8MM_IOMUXC_I2C2_SDA_I2C2_SDA			0x40000083 /* I2C_A_SDA */
+		>;
+	};
+
+	pinctrl_i2c3: i2c3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_I2C3_SCL_I2C3_SCL			0x40000083 /* I2C_B_SCL */
+			MX8MM_IOMUXC_I2C3_SDA_I2C3_SDA			0x40000083 /* I2C_B_SDA */
+		>;
+	};
+
+	pinctrl_i2c4: i2c4grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL			0x40000083 /* PCIe_SMCLK and I2C_CAM_SCL/CSI_TX_P */
+			MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA			0x40000083 /* PCIe_SMDAT and I2C_CAM_SDA/CSI_TX_N */
+		>;
+	};
+
+	pinctrl_pcie: pciegrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI5_RXD1_GPIO3_IO22		0x19 /* PCIe_CLKREQ# */
+			MX8MM_IOMUXC_SAI5_RXD2_GPIO3_IO23		0x19 /* PCIe_A_PERST# */
+			MX8MM_IOMUXC_SAI5_RXD3_GPIO3_IO24		0x19 /* PCIe_WAKE# */
+			MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28		0x19 /* PCIe_SM_ALERT */
 		>;
 	};
 
@@ -263,16 +624,113 @@
 		>;
 	};
 
+	pinctrl_pwm1: pwm1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SPDIF_EXT_CLK_PWM1_OUT		0x19 /* PWM_0 */
+		>;
+	};
+
+	pinctrl_pwm2: pwm2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SPDIF_RX_PWM2_OUT			0x19 /* PWM_1 */
+		>;
+	};
+
+	pinctrl_pwm3: pwm3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SPDIF_TX_PWM3_OUT			0x19 /* PWM_2 */
+		>;
+	};
+
+	pinctrl_reg_usb1_vbus: regusb1vbusgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI5_MCLK_GPIO3_IO25		0x19 /* USB_A_EN */
+		>;
+	};
+
+	pinctrl_reg_usb2_vbus: regusb2vbusgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI5_RXC_GPIO3_IO20		0x19 /* USB_B_EN */
+		>;
+	};
+
+	pinctrl_reg_usdhc2_vcc: regusdhc2vccgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SD2_RESET_B_GPIO2_IO19		0x19 /* SDIO_A_PWR_EN */
+		>;
+	};
+
+	pinctrl_reg_usdhc3_vcc: regusdhc3vccgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI3_TXD_GPIO5_IO1			0x19 /* SDIO_B_PWR_EN */
+		>;
+	};
+
+	pinctrl_reg_vdd_carrier: regvddcarriergrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_READY_B_GPIO3_IO16		0x19 /* CARRIER_PWR_EN */
+		>;
+	};
+
 	pinctrl_rtc: rtcgrp {
 		fsl,pins = <
 			MX8MM_IOMUXC_SAI1_RXC_GPIO4_IO1			0x19
 		>;
 	};
 
+	pinctrl_sai1: sai1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_RXD0_SAI1_RX_DATA0		0xd6 /* I2S_A_DATA_IN */
+			MX8MM_IOMUXC_SAI1_TXD0_SAI1_TX_DATA0		0xd6 /* I2S_A_DATA_OUT */
+			MX8MM_IOMUXC_SAI1_RXD1_SAI1_RX_DATA1		0xd6 /* I2S_B_DATA_IN */
+			MX8MM_IOMUXC_SAI1_TXD1_SAI1_TX_DATA1		0xd6 /* I2S_B_DATA_OUT */
+			MX8MM_IOMUXC_SAI1_MCLK_SAI1_MCLK		0xd6 /* I2S_MCLK */
+			MX8MM_IOMUXC_SAI1_TXFS_SAI1_TX_SYNC		0xd6 /* I2S_LRCLK */
+			MX8MM_IOMUXC_SAI1_TXC_SAI1_TX_BCLK		0xd6 /* I2S_BITCLK */
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX		0x0 /* UART_A_RX */
+			MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX		0x0 /* UART_A_TX */
+			MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B		0x0 /* UART_A_CTS */
+			MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B		0x0 /* UART_A_RTS */
+		>;
+	};
+
+	pinctrl_uart2: uart2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX		0x0 /* UART_B_RX */
+			MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX		0x0 /* UART_B_TX */
+			MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B		0x0 /* UART_B_CTS */
+			MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B		0x0 /* UART_B_RTS */
+		>;
+	};
+
 	pinctrl_uart3: uart3grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_UART3_RXD_UART3_DCE_RX		0x140
-			MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX		0x140
+			MX8MM_IOMUXC_UART3_RXD_UART3_DCE_RX		0x140 /* UART_CON_RX */
+			MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX		0x140 /* UART_CON_TX */
+		>;
+	};
+
+	pinctrl_uart4: uart4grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_UART4_RXD_UART4_DCE_RX		0x0 /* UART_C_RX */
+			MX8MM_IOMUXC_UART4_TXD_UART4_DCE_TX		0x0 /* UART_C_TX */
+		>;
+	};
+
+	pinctrl_usb1: usb1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC		0x19 /* USB_A_OC# */
+		>;
+	};
+
+	pinctrl_usb2: usb2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO15_USB2_OTG_OC		0x19 /* USB_B_OC# */
 		>;
 	};
 
@@ -327,6 +785,103 @@
 		>;
 	};
 
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x90 /* SDIO_A_CLK */
+			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d0 /* SDIO_A_CMD */
+			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d0 /* SDIO_A_D0 */
+			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d0 /* SDIO_A_D1 */
+			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d0 /* SDIO_A_D2 */
+			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d0 /* SDIO_A_D3 */
+			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+		>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x94 /* SDIO_A_CLK */
+			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d4 /* SDIO_A_CMD */
+			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d4 /* SDIO_A_D0 */
+			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d4 /* SDIO_A_D1 */
+			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d4 /* SDIO_A_D2 */
+			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d4 /* SDIO_A_D3 */
+			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+		>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK			0x96 /* SDIO_A_CLK */
+			MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD			0x1d6 /* SDIO_A_CMD */
+			MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0		0x1d6 /* SDIO_A_D0 */
+			MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1		0x1d6 /* SDIO_A_D1 */
+			MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2		0x1d6 /* SDIO_A_D2 */
+			MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3		0x1d6 /* SDIO_A_D3 */
+			MX8MM_IOMUXC_SD2_WP_USDHC2_WP			0x400000d6 /* SDIO_A_WP */
+			MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT		0x90
+		>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12		0x19 /* SDIO_A_CD# */
+		>;
+	};
+
+	pinctrl_usdhc3: usdhc3grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_WE_B_USDHC3_CLK		0x90 /* SDIO_B_CLK */
+			MX8MM_IOMUXC_NAND_WP_B_USDHC3_CMD		0x90 /* SDIO_B_CMD */
+			MX8MM_IOMUXC_NAND_DATA04_USDHC3_DATA0		0x90 /* SDIO_B_D0 */
+			MX8MM_IOMUXC_NAND_DATA05_USDHC3_DATA1		0x90 /* SDIO_B_D1 */
+			MX8MM_IOMUXC_NAND_DATA06_USDHC3_DATA2		0x90 /* SDIO_B_D2 */
+			MX8MM_IOMUXC_NAND_DATA07_USDHC3_DATA3		0x90 /* SDIO_B_D3 */
+			MX8MM_IOMUXC_NAND_RE_B_USDHC3_DATA4		0x90 /* SDIO_B_D4 */
+			MX8MM_IOMUXC_NAND_CE2_B_USDHC3_DATA5		0x90 /* SDIO_B_D5 */
+			MX8MM_IOMUXC_NAND_CE3_B_USDHC3_DATA6		0x90 /* SDIO_B_D6 */
+			MX8MM_IOMUXC_NAND_CLE_USDHC3_DATA7		0x90 /* SDIO_B_D7 */
+		>;
+	};
+
+	pinctrl_usdhc3_100mhz: usdhc3-100mhzgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_WE_B_USDHC3_CLK		0x94 /* SDIO_B_CLK */
+			MX8MM_IOMUXC_NAND_WP_B_USDHC3_CMD		0x94 /* SDIO_B_CMD */
+			MX8MM_IOMUXC_NAND_DATA04_USDHC3_DATA0		0x94 /* SDIO_B_D0 */
+			MX8MM_IOMUXC_NAND_DATA05_USDHC3_DATA1		0x94 /* SDIO_B_D1 */
+			MX8MM_IOMUXC_NAND_DATA06_USDHC3_DATA2		0x94 /* SDIO_B_D2 */
+			MX8MM_IOMUXC_NAND_DATA07_USDHC3_DATA3		0x94 /* SDIO_B_D3 */
+			MX8MM_IOMUXC_NAND_RE_B_USDHC3_DATA4		0x94 /* SDIO_B_D4 */
+			MX8MM_IOMUXC_NAND_CE2_B_USDHC3_DATA5		0x94 /* SDIO_B_D5 */
+			MX8MM_IOMUXC_NAND_CE3_B_USDHC3_DATA6		0x94 /* SDIO_B_D6 */
+			MX8MM_IOMUXC_NAND_CLE_USDHC3_DATA7		0x94 /* SDIO_B_D7 */
+		>;
+	};
+
+	pinctrl_usdhc3_200mhz: usdhc3-200mhzgrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_WE_B_USDHC3_CLK		0x96 /* SDIO_B_CLK */
+			MX8MM_IOMUXC_NAND_WP_B_USDHC3_CMD		0x96 /* SDIO_B_CMD */
+			MX8MM_IOMUXC_NAND_DATA04_USDHC3_DATA0		0x96 /* SDIO_B_D0 */
+			MX8MM_IOMUXC_NAND_DATA05_USDHC3_DATA1		0x96 /* SDIO_B_D1 */
+			MX8MM_IOMUXC_NAND_DATA06_USDHC3_DATA2		0x96 /* SDIO_B_D2 */
+			MX8MM_IOMUXC_NAND_DATA07_USDHC3_DATA3		0x96 /* SDIO_B_D3 */
+			MX8MM_IOMUXC_NAND_RE_B_USDHC3_DATA4		0x96 /* SDIO_B_D4 */
+			MX8MM_IOMUXC_NAND_CE2_B_USDHC3_DATA5		0x96 /* SDIO_B_D5 */
+			MX8MM_IOMUXC_NAND_CE3_B_USDHC3_DATA6		0x96 /* SDIO_B_D6 */
+			MX8MM_IOMUXC_NAND_CLE_USDHC3_DATA7		0x96 /* SDIO_B_D7 */
+		>;
+	};
+
+	pinctrl_usdhc3_gpio: usdhc3gpiogrp {
+		fsl,pins = <
+			MX8MM_IOMUXC_NAND_CE1_B_GPIO3_IO2		0x19 /* SDIO_B_CD# */
+			MX8MM_IOMUXC_SAI3_MCLK_GPIO5_IO2		0x19 /* SDIO_B_WP */
+		>;
+	};
+
 	pinctrl_wdog: wdoggrp {
 		fsl,pins = <
 			MX8MM_IOMUXC_GPIO1_IO02_WDOG1_WDOG_B		0xc6
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi
index 1f8326613ee9..2076148e0862 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi
@@ -237,8 +237,8 @@
 
 	pinctrl_i2c1: i2c1grp {
 		fsl,pins = <
-			MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL			0x400001c3
-			MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA			0x400001c3
+			MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL			0x40000083
+			MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA			0x40000083
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
index ea6e8b85169f..01b632b220dc 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts
@@ -5,6 +5,8 @@
 
 /dts-v1/;
 
+#include <dt-bindings/phy/phy-imx8-pcie.h>
+
 #include "imx8mm-tqma8mqml.dtsi"
 #include "mba8mx.dtsi"
 
@@ -74,19 +76,23 @@
 };
 
 &pcie_phy {
-	clocks = <&pcie0_refclk>;
+	fsl,refclk-pad-mode = <IMX8_PCIE_REFCLK_PAD_INPUT>;
+	fsl,clkreq-unsupported;
+	clocks = <&pcieclk 2>;
+	clock-names = "ref";
 	status = "okay";
 };
 
+/* PCIe slot on X36 */
 &pcie0 {
 	reset-gpio = <&expander0 14 GPIO_ACTIVE_LOW>;
-	clocks = <&clk IMX8MM_CLK_PCIE1_ROOT>, <&pcie0_refclk>,
+	clocks = <&clk IMX8MM_CLK_PCIE1_ROOT>, <&pcieclk 3>,
 		 <&clk IMX8MM_CLK_PCIE1_AUX>;
 	assigned-clocks = <&clk IMX8MM_CLK_PCIE1_AUX>,
-				<&clk IMX8MM_CLK_PCIE1_CTRL>;
+			  <&clk IMX8MM_CLK_PCIE1_CTRL>;
 	assigned-clock-rates = <10000000>, <250000000>;
 	assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_50M>,
-				<&clk IMX8MM_SYS_PLL2_250M>;
+				 <&clk IMX8MM_SYS_PLL2_250M>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi
index 6425773f68e0..41c966147b94 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi
@@ -47,25 +47,20 @@
 		gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>;
 		status = "okay";
 	};
-
-	reg_usb_otg1_vbus: regulator-usb-otg1 {
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_reg_usb1_en>;
-		compatible = "regulator-fixed";
-		regulator-name = "usb_otg1_vbus";
-		gpio = <&gpio1 10 GPIO_ACTIVE_HIGH>;
-		enable-active-high;
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-	};
 };
 
-/* off-board header */
 &ecspi2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_spi2>;
-	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>,
+		   <&gpio1 10 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	tpm@1 {
+		compatible = "tcg,tpm_tis-spi";
+		reg = <0x1>;
+		spi-max-frequency = <36000000>;
+	};
 };
 
 &gpio1 {
@@ -144,9 +139,10 @@
 };
 
 &usbotg1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg1>;
 	dr_mode = "otg";
 	over-current-active-low;
-	vbus-supply = <&reg_usb_otg1_vbus>;
 	status = "okay";
 };
 
@@ -204,20 +200,13 @@
 		>;
 	};
 
-	pinctrl_reg_usb1_en: regusb1grp {
-		fsl,pins = <
-			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10	0x41
-			MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12	0x141
-			MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC	0x41
-		>;
-	};
-
 	pinctrl_spi2: spi2grp {
 		fsl,pins = <
 			MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK	0xd6
 			MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI	0xd6
 			MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO	0xd6
 			MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13	0xd6
+			MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10	0xd6
 		>;
 	};
 
@@ -234,4 +223,11 @@
 			MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX	0x140
 		>;
 	};
+
+	pinctrl_usbotg1: usbotg1grp {
+		fsl,pins = <
+			MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12	0x141
+			MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC	0x41
+		>;
+	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
index 87b80e2412cb..5e2cbaf27e0f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
@@ -285,7 +285,8 @@
 &ecspi1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_spi1>;
-	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>,
+		   <&gpio4 24 GPIO_ACTIVE_LOW>;
 	status = "okay";
 
 	flash@0 {
@@ -294,6 +295,12 @@
 		spi-max-frequency = <40000000>;
 		status = "okay";
 	};
+
+	tpm@1 {
+		compatible = "tcg,tpm_tis-spi";
+		reg = <0x1>;
+		spi-max-frequency = <36000000>;
+	};
 };
 
 &fec1 {
@@ -319,7 +326,7 @@
 
 &gpio4 {
 	gpio-line-names = "", "", "", "",
-		"", "", "uart3_rs232#", "uart3_rs422#",
+		"dig1_ctl", "dig2_ctl", "uart3_rs232#", "uart3_rs422#",
 		"uart3_rs485#", "", "", "", "", "", "", "",
 		"", "", "", "", "", "", "", "",
 		"", "", "", "uart4_rs485#", "", "sim1det#", "sim2det#", "";
@@ -842,6 +849,8 @@
 
 	pinctrl_hog: hoggrp {
 		fsl,pins = <
+			MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4	0x40000041 /* DIG1_CTL */
+			MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5	0x40000041 /* DIG2_CTL */
 			MX8MM_IOMUXC_SPDIF_TX_GPIO5_IO3		0x40000041 /* DIG2_OUT */
 			MX8MM_IOMUXC_SPDIF_RX_GPIO5_IO4		0x40000041 /* DIG2_IN */
 			MX8MM_IOMUXC_GPIO1_IO06_GPIO1_IO6	0x40000041 /* DIG1_IN */
@@ -987,6 +996,7 @@
 			MX8MM_IOMUXC_ECSPI1_MOSI_ECSPI1_MOSI	0x82
 			MX8MM_IOMUXC_ECSPI1_MISO_ECSPI1_MISO	0x82
 			MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9	0x140
+			MX8MM_IOMUXC_SAI2_TXFS_GPIO4_IO24	0x140
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mn-beacon-kit.dts
index 35b8d2060cd9..bbd80896db96 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-beacon-kit.dts
@@ -99,8 +99,6 @@
 };
 
 &lcdif {
-	assigned-clocks = <&clk IMX8MN_VIDEO_PLL1>;
-	assigned-clock-rates = <594000000>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
index a0e13d3324ed..269e70f66a13 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dtsi
@@ -110,6 +110,20 @@
 		spdif-out;
 		spdif-in;
 	};
+
+	sound-micfil {
+		compatible = "fsl,imx-audio-card";
+		model = "micfil-audio";
+
+		pri-dai-link {
+			link-name = "micfil hifi";
+			format = "i2s";
+
+			cpu {
+				sound-dai = <&micfil>;
+			};
+		};
+	};
 };
 
 &easrc {
@@ -285,6 +299,16 @@
 	status = "okay";
 };
 
+&micfil {
+	#sound-dai-cells = <0>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pdm>;
+	assigned-clocks = <&clk IMX8MN_CLK_PDM>;
+	assigned-clock-parents = <&clk IMX8MN_AUDIO_PLL1_OUT>;
+	assigned-clock-rates = <196608000>;
+	status = "okay";
+};
+
 &mipi_csi {
 	status = "okay";
 
@@ -522,6 +546,18 @@
 		>;
 	};
 
+	pinctrl_pdm: pdmgrp {
+		fsl,pins = <
+			MX8MN_IOMUXC_SAI5_MCLK_SAI5_MCLK	0xd6
+			MX8MN_IOMUXC_SAI5_RXC_PDM_CLK		0xd6
+			MX8MN_IOMUXC_SAI5_RXFS_SAI5_RX_SYNC	0xd6
+			MX8MN_IOMUXC_SAI5_RXD0_PDM_BIT_STREAM0	0xd6
+			MX8MN_IOMUXC_SAI5_RXD1_PDM_BIT_STREAM1	0xd6
+			MX8MN_IOMUXC_SAI5_RXD2_PDM_BIT_STREAM2	0xd6
+			MX8MN_IOMUXC_SAI5_RXD3_PDM_BIT_STREAM3	0xd6
+		>;
+	};
+
 	pinctrl_pmic: pmicirqgrp {
 		fsl,pins = <
 			MX8MN_IOMUXC_GPIO1_IO03_GPIO1_IO3	0x141
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts b/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts
index 1b633bd1ebb6..ea1855171fb0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-rve-gateway.dts
@@ -10,7 +10,7 @@
 
 / {
 	model = "RVE gateway";
-	compatible = "rve,rve-gateway", "variscite,var-som-mx8mn", "fsl,imx8mn";
+	compatible = "rve,gateway", "variscite,var-som-mx8mn", "fsl,imx8mn";
 
 	crystal_duart_24m: crystal-duart-24m {
 		compatible = "fixed-clock";
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx-usbotg.dtso b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx-usbotg.dtso
new file mode 100644
index 000000000000..96db07fc9bec
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx-usbotg.dtso
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR MIT)
+/*
+ * Copyright (c) 2022-2024 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+#include "imx8mn-pinfunc.h"
+
+&{/} {
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		type = "micro";
+		label = "X19";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb1_connector>;
+		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb1_drd_sw>;
+			};
+		};
+	};
+};
+
+&rst_usb_hub_hog {
+	output-low;
+};
+
+&sel_usb_hub_hog {
+	output-low;
+};
+
+&usbotg1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg>;
+	dr_mode = "otg";
+	srp-disable;
+	hnp-disable;
+	adp-disable;
+	power-active-high;
+	/delete-property/ disable-over-current;
+	over-current-active-low;
+	usb-role-switch;
+	status = "okay";
+
+	port {
+		usb1_drd_sw: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
+	};
+};
+
+&iomuxc {
+	pinctrl_usb1_connector: usb1-connectorgrp {
+		fsl,pins = <MX8MN_IOMUXC_GPIO1_IO10_GPIO1_IO10		0x1c0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
index c07d59147ab5..433d8bba4425 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-tqma8mqnl-mba8mx.dts
@@ -41,7 +41,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usb0hub_sel>;
 
-	sel-usb-hub-hog {
+	sel_usb_hub_hog: sel-usb-hub-hog {
 		gpio-hog;
 		gpios = <1 GPIO_ACTIVE_HIGH>;
 		output-high;
@@ -198,8 +198,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <MX8MN_IOMUXC_GPIO1_IO12_USB1_OTG_PWR	0x84>,
-			   <MX8MN_IOMUXC_GPIO1_IO13_USB1_OTG_OC		0x84>,
-			   <MX8MN_IOMUXC_GPIO1_IO10_USB1_OTG_ID		0x1C4>;
+			   <MX8MN_IOMUXC_GPIO1_IO13_USB1_OTG_OC		0x84>;
 	};
 
 	pinctrl_usdhc2: usdhc2grp {
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
index f38ee2266b25..a6b94d1957c9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som-symphony.dts
@@ -128,14 +128,9 @@
 		pinctrl-0 = <&pinctrl_ptn5150>;
 		status = "okay";
 
-		connector {
-			compatible = "usb-c-connector";
-			label = "USB-C";
-
-			port {
-				typec1_dr_sw: endpoint {
-					remote-endpoint = <&usb1_drd_sw>;
-				};
+		port {
+			typec1_dr_sw: endpoint {
+				remote-endpoint = <&usb1_drd_sw>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 136e75c51251..932c8b05c75f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -1168,7 +1168,7 @@
 							 <&clk IMX8MN_SYS_PLL1_800M>;
 				assigned-clock-rates = <266000000>,
 						       <24000000>,
-						       <594000000>,
+						       <24000000>,
 						       <500000000>,
 						       <200000000>;
 				#power-domain-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-beacon-som.dtsi
index e5da90804780..8be251b69378 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-som.dtsi
@@ -50,6 +50,8 @@
 	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	snps,force_thresh_dma_mode;
+	snps,mtl-rx-config = <&mtl_rx_setup>;
+	snps,mtl-tx-config = <&mtl_tx_setup>;
 	status = "okay";
 
 	mdio {
@@ -66,6 +68,71 @@
 			interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 		};
 	};
+
+	mtl_rx_setup: rx-queues-config {
+		snps,rx-queues-to-use = <5>;
+		snps,rx-sched-sp;
+
+		queue0 {
+			snps,dcb-algorithm;
+			snps,priority = <0x1>;
+			snps,map-to-dma-channel = <0>;
+		};
+
+		queue1 {
+			snps,dcb-algorithm;
+			snps,priority = <0x2>;
+			snps,map-to-dma-channel = <1>;
+		};
+
+		queue2 {
+			snps,dcb-algorithm;
+			snps,priority = <0x4>;
+			snps,map-to-dma-channel = <2>;
+		};
+
+		queue3 {
+			snps,dcb-algorithm;
+			snps,priority = <0x8>;
+			snps,map-to-dma-channel = <3>;
+		};
+
+		queue4 {
+			snps,dcb-algorithm;
+			snps,priority = <0xf0>;
+			snps,map-to-dma-channel = <4>;
+		};
+	};
+
+	mtl_tx_setup: tx-queues-config {
+		snps,tx-queues-to-use = <5>;
+		snps,tx-sched-sp;
+
+		queue0 {
+			snps,dcb-algorithm;
+			snps,priority = <0x1>;
+		};
+
+		queue1 {
+			snps,dcb-algorithm;
+			snps,priority = <0x2>;
+		};
+
+		queue2 {
+			snps,dcb-algorithm;
+			snps,priority = <0x4>;
+		};
+
+		queue3 {
+			snps,dcb-algorithm;
+			snps,priority = <0x8>;
+		};
+
+		queue4 {
+			snps,dcb-algorithm;
+			snps,priority = <0xf0>;
+		};
+	};
 };
 
 &flexspi {
@@ -206,6 +273,10 @@
 	assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_80M>;
 	uart-has-rtscts;
 	status = "okay";
+
+	bluetooth {
+		compatible = "nxp,88w8997-bt";
+	};
 };
 
 &usdhc1 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
index d98a040860a4..7e1b58dbe23a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
@@ -6,6 +6,7 @@
 /dts-v1/;
 
 #include <dt-bindings/net/qca-ar803x.h>
+#include <dt-bindings/phy/phy-imx8-pcie.h>
 #include "imx8mp.dtsi"
 
 / {
@@ -45,6 +46,19 @@
 		clock-frequency = <25000000>;
 	};
 
+	clk_pwm4: clock-pwm4 {
+		compatible = "pwm-clock";
+		#clock-cells = <0>;
+		clock-frequency = <12000000>;
+		clock-output-names = "codec-pwm4";
+		/*
+		 * 1 / 83 ns ~= 12 MHz , but since the PWM input clock is 24 MHz
+		 * and the calculated PWM period is 1 and duty cycle is 50%, the
+		 * result is exactly 12 MHz, which is fine for SGTL5000 MCLK.
+		 */
+		pwms = <&pwm4 0 83 0>;
+	};
+
 	panel: panel {
 		/* Compatible string is filled in by panel board DT Overlay. */
 		backlight = <&backlight>;
@@ -82,6 +96,24 @@
 		vin-supply = <&buck4>;
 	};
 
+	sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,name = "SGTL5000-Card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,bitclock-master = <&codec_dai>;
+		simple-audio-card,frame-master = <&codec_dai>;
+		simple-audio-card,widgets = "Headphone", "Headphone Jack";
+		simple-audio-card,routing = "Headphone Jack", "HP_OUT";
+
+		cpu_dai: simple-audio-card,cpu {
+			sound-dai = <&sai3>;
+		};
+
+		codec_dai: simple-audio-card,codec {
+			sound-dai = <&sgtl5000>;
+		};
+	};
+
 	watchdog { /* TPS3813 */
 		compatible = "linux,wdt-gpio";
 		pinctrl-names = "default";
@@ -121,7 +153,7 @@
 	flash@0 {	/* W25Q128JVEI */
 		compatible = "jedec,spi-nor";
 		reg = <0>;
-		spi-max-frequency = <100000000>;	/* Up to 133 MHz */
+		spi-max-frequency = <40000000>;
 		spi-tx-bus-width = <1>;
 		spi-rx-bus-width = <1>;
 	};
@@ -288,6 +320,15 @@
 	sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
 	status = "okay";
 
+	sgtl5000: audio-codec@a {
+		compatible = "fsl,sgtl5000";
+		reg = <0x0a>;
+		#sound-dai-cells = <0>;
+		clocks = <&clk_pwm4>;
+		VDDA-supply = <&buck4>;
+		VDDIO-supply = <&buck4>;
+	};
+
 	usb-hub@2c {
 		compatible = "microchip,usb2514bi";
 		reg = <0x2c>;
@@ -429,6 +470,21 @@
 	status = "okay";
 };
 
+&pcie_phy {
+	clocks = <&pcieclk 0>;
+	clock-names = "ref";
+	fsl,refclk-pad-mode = <IMX8_PCIE_REFCLK_PAD_INPUT>;
+	status = "okay";
+};
+
+&pcie {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pcie0>;
+	fsl,max-link-speed = <3>;
+	reset-gpio = <&gpio1 5 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
 &pwm1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_panel_pwm>;
@@ -436,6 +492,23 @@
 	status = "disabled";
 };
 
+&pwm4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm4>;
+	status = "okay";
+};
+
+&sai3 {
+	#clock-cells = <0>;
+	#sound-dai-cells = <0>;
+	assigned-clocks = <&clk IMX8MP_CLK_SAI3>;
+	assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL1_OUT>;
+	assigned-clock-rates = <12288000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai3>;
+	status = "okay";
+};
+
 /* SD slot */
 &usdhc2 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
@@ -486,7 +559,7 @@
 &uart4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_uart4>;
-	status = "okay";
+	status = "disabled";
 };
 
 &usb3_phy0 {
@@ -785,6 +858,12 @@
 		>;
 	};
 
+	pinctrl_pwm4: pwm4-grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI3_MCLK__PWM4_OUT		0xd6
+		>;
+	};
+
 	pinctrl_rtc: rtc-grp {
 		fsl,pins = <
 			/* RTC_IRQ# */
@@ -816,7 +895,6 @@
 			MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_SAI3_TX_SYNC	0xd6
 			MX8MP_IOMUXC_SAI3_TXD__AUDIOMIX_SAI3_TX_DATA00	0xd6
 			MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_SAI3_TX_BCLK	0xd6
-			MX8MP_IOMUXC_SAI3_MCLK__AUDIOMIX_SAI3_MCLK	0xd6
 			MX8MP_IOMUXC_SAI3_RXD__AUDIOMIX_SAI3_RX_DATA00	0xd6
 		>;
 	};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
index fea67a9282f0..b749e28e5ede 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk3.dts
@@ -175,14 +175,10 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_ptn5150>;
 
-				connector {
-					compatible = "usb-c-connector";
-					label = "USB-C";
-
-					port {
-						ptn5150_out_ep: endpoint {
-							remote-endpoint = <&dwc3_0_ep>;
-						};
+				port {
+
+					ptn5150_out_ep: endpoint {
+						remote-endpoint = <&dwc3_0_ep>;
 					};
 				};
 			};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
index 4ae4fdab461e..43f1d45ccc96 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
@@ -255,7 +255,7 @@
 				  <&clk IMX8MP_AUDIO_PLL2_OUT>;
 		assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
 		assigned-clock-rates = <13000000>, <13000000>, <156000000>;
-		reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>;
 		status = "disabled";
 
 		ports {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index f87fa5a948cc..9beba8d6a0df 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -23,7 +23,7 @@
 
 		port {
 			hdmi_connector_in: endpoint {
-				remote-endpoint = <&adv7533_out>;
+				remote-endpoint = <&adv7535_out>;
 			};
 		};
 	};
@@ -107,6 +107,13 @@
 		enable-active-high;
 	};
 
+	reg_vext_3v3: regulator-vext-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VEXT_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
 	sound {
 		compatible = "simple-audio-card";
 		simple-audio-card,name = "wm8960-audio";
@@ -364,7 +371,7 @@
 				regulator-always-on;
 			};
 
-			BUCK5 {
+			reg_buck5: BUCK5 {
 				regulator-name = "BUCK5";
 				regulator-min-microvolt = <1650000>;
 				regulator-max-microvolt = <1950000>;
@@ -415,14 +422,16 @@
 
 	hdmi@3d {
 		compatible = "adi,adv7535";
-		reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>;
-		reg-names = "main", "cec", "edid", "packet";
+		reg = <0x3d>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
 		adi,dsi-lanes = <4>;
-		adi,input-depth = <8>;
-		adi,input-colorspace = "rgb";
-		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
+		avdd-supply = <&reg_buck5>;
+		dvdd-supply = <&reg_buck5>;
+		pvdd-supply = <&reg_buck5>;
+		a2vdd-supply = <&reg_buck5>;
+		v3p3-supply = <&reg_vext_3v3>;
+		v1p2-supply = <&reg_buck5>;
 
 		ports {
 			#address-cells = <1>;
@@ -431,7 +440,7 @@
 			port@0 {
 				reg = <0>;
 
-				adv7533_in: endpoint {
+				adv7535_in: endpoint {
 					remote-endpoint = <&dsi_out>;
 				};
 			};
@@ -439,7 +448,7 @@
 			port@1 {
 				reg = <1>;
 
-				adv7533_out: endpoint {
+				adv7535_out: endpoint {
 					remote-endpoint = <&hdmi_connector_in>;
 				};
 			};
@@ -524,7 +533,7 @@
 			reg = <1>;
 
 			dsi_out: endpoint {
-				remote-endpoint = <&adv7533_in>;
+				remote-endpoint = <&adv7535_in>;
 				data-lanes = <1 2 3 4>;
 			};
 		};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
index c8640cac3edc..00a240484c25 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
@@ -19,6 +19,30 @@
 		stdout-path = &uart1;
 	};
 
+	backlight_lvds: backlight {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_lvds1>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <11>;
+		enable-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>;
+		num-interpolated-steps = <2>;
+		power-supply = <&reg_lvds1_reg_en>;
+		pwms = <&pwm3 0 50000 0>;
+	};
+
+	panel1_lvds: panel-lvds {
+		compatible = "edt,etml1010g3dra";
+		backlight = <&backlight_lvds>;
+		power-supply = <&reg_vcc_3v3_sw>;
+
+		port {
+			panel1_in: endpoint {
+				remote-endpoint = <&ldb_lvds_ch1>;
+			};
+		};
+	};
+
 	reg_can1_stby: regulator-can1-stby {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -39,6 +63,15 @@
 		regulator-name = "can2-stby";
 	};
 
+	reg_lvds1_reg_en: regulator-lvds1 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio1 9 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <1200000>;
+		regulator-min-microvolt = <1200000>;
+		regulator-name = "lvds1_reg_en";
+	};
+
 	reg_usb1_vbus: regulator-usb1-vbus {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -61,6 +94,13 @@
 		startup-delay-us = <100>;
 		off-on-delay-us = <12000>;
 	};
+
+	reg_vcc_3v3_sw: regulator-vcc-3v3-sw {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_3V3_SW";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
 };
 
 &eqos {
@@ -135,10 +175,41 @@
 	};
 };
 
+&lcdif2 {
+	status = "okay";
+};
+
+&lvds_bridge {
+	status = "okay";
+
+	ports {
+		port@2 {
+			ldb_lvds_ch1: endpoint {
+				remote-endpoint = <&panel1_in>;
+			};
+		};
+	};
+};
+
 &snvs_pwrkey {
 	status = "okay";
 };
 
+&pwm3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_pwm3>;
+};
+
+&rv3028 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_rtc>;
+	interrupt-parent = <&gpio4>;
+	interrupts = <19 IRQ_TYPE_LEVEL_LOW>;
+	wakeup-source;
+	trickle-resistor-ohms = <3000>;
+};
+
 /* debug console */
 &uart1 {
 	pinctrl-names = "default";
@@ -239,12 +310,12 @@
 			MX8MP_IOMUXC_ENET_RD3__ENET_QOS_RGMII_RD3		0x90
 			MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x90
 			MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL		0x90
-			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0		0x16
-			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1		0x16
-			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2		0x16
-			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3		0x16
-			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL		0x16
-			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x16
+			MX8MP_IOMUXC_ENET_TD0__ENET_QOS_RGMII_TD0		0x12
+			MX8MP_IOMUXC_ENET_TD1__ENET_QOS_RGMII_TD1		0x12
+			MX8MP_IOMUXC_ENET_TD2__ENET_QOS_RGMII_TD2		0x12
+			MX8MP_IOMUXC_ENET_TD3__ENET_QOS_RGMII_TD3		0x12
+			MX8MP_IOMUXC_ENET_TX_CTL__ENET_QOS_RGMII_TX_CTL		0x12
+			MX8MP_IOMUXC_ENET_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x12
 			MX8MP_IOMUXC_SAI1_MCLK__GPIO4_IO20			0x10
 		>;
 	};
@@ -289,16 +360,34 @@
 		>;
 	};
 
+	pinctrl_lvds1: lvds1grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SD2_WP__GPIO2_IO20		0x12
+		>;
+	};
+
+	pinctrl_pwm3: pwm3grp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SPDIF_TX__PWM3_OUT		0x12
+		>;
+	};
+
 	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
 		fsl,pins = <
 			MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x40
 		>;
 	};
 
+	pinctrl_rtc: rtcgrp {
+		fsl,pins = <
+			MX8MP_IOMUXC_SAI1_TXD7__GPIO4_IO19	0x1C0
+		>;
+	};
+
 	pinctrl_uart1: uart1grp {
 		fsl,pins = <
-			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX	0x40
-			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX	0x40
+			MX8MP_IOMUXC_UART1_RXD__UART1_DCE_RX	0x140
+			MX8MP_IOMUXC_UART1_TXD__UART1_DCE_TX	0x140
 		>;
 	};
 
@@ -319,7 +408,7 @@
 
 	pinctrl_usdhc2_pins: usdhc2-gpiogrp {
 		fsl,pins = <
-			MX8MP_IOMUXC_SD2_CD_B__GPIO2_IO12	0x1c4
+			MX8MP_IOMUXC_SD2_CD_B__GPIO2_IO12	0x40
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
index c976c3b6cbc6..e6ffa6a6b68b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
@@ -175,7 +175,6 @@
 	rv3028: rtc@52 {
 		compatible = "microcrystal,rv3028";
 		reg = <0x52>;
-		trickle-resistor-ohms = <3000>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index a2d5d19b2de0..86d3da36e4f3 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -184,6 +184,13 @@
 		enable-active-high;
 	};
 
+	reg_vcc_1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_1V8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
 	reg_vcc_3v3: regulator-3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "VCC_3V3";
@@ -480,7 +487,7 @@
 		clock-names = "mclk";
 		clocks = <&audio_blk_ctrl IMX8MP_CLK_AUDIOMIX_SAI3_MCLK1>;
 		reset-gpios = <&gpio4 29 GPIO_ACTIVE_LOW>;
-		iov-supply = <&reg_vcc_3v3>;
+		iov-supply = <&reg_vcc_1v8>;
 		ldoin-supply = <&reg_vcc_3v3>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
index 0e8d0f3c7ea8..e7bf032265e0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi
@@ -63,8 +63,15 @@
 &ecspi2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_spi2>;
-	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
+	cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>,
+		   <&gpio1 10 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	tpm@1 {
+		compatible = "tcg,tpm_tis-spi";
+		reg = <0x1>;
+		spi-max-frequency = <36000000>;
+	};
 };
 
 &gpio4 {
@@ -228,6 +235,7 @@
 			MX8MP_IOMUXC_ECSPI2_MOSI__ECSPI2_MOSI	0x140
 			MX8MP_IOMUXC_ECSPI2_MISO__ECSPI2_MISO	0x140
 			MX8MP_IOMUXC_ECSPI2_SS0__GPIO5_IO13	0x140
+			MX8MP_IOMUXC_GPIO1_IO10__GPIO1_IO10	0x140
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
index c3305f0d4001..faa17cbbe2fd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
@@ -552,7 +552,7 @@
 				regulator-name = "On-module +V3.3_ADC (LDO4)";
 			};
 
-			LDO5 {
+			reg_vdd_sdio: LDO5 {
 				regulator-max-microvolt = <3300000>;
 				regulator-min-microvolt = <1800000>;
 				regulator-name = "On-module +V3.3_1.8_SD (LDO5)";
@@ -885,6 +885,7 @@
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
 	pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>;
 	vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&reg_vdd_sdio>;
 };
 
 /* On-module eMMC */
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 76c73daf546b..bfc5c81a5bd4 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1636,8 +1636,10 @@
 					 <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT>,
 					 <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>;
 				clock-names = "pclk", "wrap", "phy", "axi";
-				assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM1_PIX>;
-				assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>;
+				assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM1_PIX>,
+						  <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF>;
+				assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>,
+							 <&clk IMX8MP_CLK_24M>;
 				assigned-clock-rates = <500000000>;
 				power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_MIPI_CSI2_1>;
 				status = "disabled";
@@ -1670,8 +1672,10 @@
 					 <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT>,
 					 <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>;
 				clock-names = "pclk", "wrap", "phy", "axi";
-				assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM2_PIX>;
-				assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>;
+				assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM1_PIX>,
+						  <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF>;
+				assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>,
+							 <&clk IMX8MP_CLK_24M>;
 				assigned-clock-rates = <266000000>;
 				power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_MIPI_CSI2_2>;
 				status = "disabled";
@@ -1820,7 +1824,7 @@
 					compatible = "fsl,imx8mp-ldb";
 					reg = <0x5c 0x4>, <0x128 0x4>;
 					reg-names = "ldb", "lvds";
-					clocks = <&clk IMX8MP_CLK_MEDIA_LDB>;
+					clocks = <&clk IMX8MP_CLK_MEDIA_LDB_ROOT>;
 					clock-names = "ldb";
 					assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>;
 					assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
index b302daca4ce6..0165f3a25985 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq-mba8mx.dts
@@ -28,18 +28,6 @@
 		id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>;
 	};
 
-	pcie0_refclk: pcie0-refclk {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
-	};
-
-	pcie1_refclk: pcie1-refclk {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
-	};
-
 	reg_otg_vbus: regulator-otg-vbus {
 		compatible = "regulator-fixed";
 		pinctrl-names = "default";
@@ -103,23 +91,24 @@
 	gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
 };
 
+/* PCIe slot on X36 */
 &pcie0 {
 	reset-gpio = <&expander0 14 GPIO_ACTIVE_LOW>;
 	clocks = <&clk IMX8MQ_CLK_PCIE1_ROOT>,
-		 <&pcie0_refclk>,
-		 <&clk IMX8MQ_CLK_PCIE1_PHY>,
+		 <&pcieclk 3>,
+		 <&pcieclk 2>,
 		 <&clk IMX8MQ_CLK_PCIE1_AUX>;
 	status = "okay";
 };
 
 /*
- * miniPCIe, also usable for cards with USB. Therefore configure the reset as
+ * miniPCIe on X28, also usable for cards with USB. Therefore configure the reset as
  * static gpio hog.
  */
 &pcie1 {
 	clocks = <&clk IMX8MQ_CLK_PCIE2_ROOT>,
-		 <&pcie1_refclk>,
-		 <&clk IMX8MQ_CLK_PCIE2_PHY>,
+		 <&pcieclk 1>,
+		 <&pcieclk 0>,
 		 <&clk IMX8MQ_CLK_PCIE2_AUX>;
 	status = "okay";
 };
@@ -171,6 +160,7 @@
 };
 
 &usb3_phy1 {
+	vbus-supply = <&reg_hub_vbus>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval-v1.2.dts b/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval-v1.2.dts
new file mode 100644
index 000000000000..8466a8204ed0
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval-v1.2.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8qm-apalis.dtsi"
+#include "imx8-apalis-eval-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX8QM/QP on Apalis Evaluation Board V1.2";
+	compatible = "toradex,apalis-imx8-eval-v1.2",
+		     "toradex,apalis-imx8",
+		     "fsl,imx8qm";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval.dts b/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval.dts
index 5ab0921eb599..b0ebf6d05450 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis-eval.dts
@@ -6,7 +6,7 @@
 /dts-v1/;
 
 #include "imx8qm-apalis.dtsi"
-#include "imx8-apalis-eval.dtsi"
+#include "imx8-apalis-eval-v1.1.dtsi"
 
 / {
 	model = "Toradex Apalis iMX8QM/QP on Apalis Evaluation Board";
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval-v1.2.dts b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval-v1.2.dts
new file mode 100644
index 000000000000..92c0ae0c0337
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval-v1.2.dts
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-or-later OR MIT
+/*
+ * Copyright 2024 Toradex
+ */
+
+/dts-v1/;
+
+#include "imx8qm-apalis-v1.1.dtsi"
+#include "imx8-apalis-eval-v1.2.dtsi"
+
+/ {
+	model = "Toradex Apalis iMX8QM V1.1 on Apalis Evaluation Board V1.2";
+	compatible = "toradex,apalis-imx8-v1.1-eval-v1.2",
+		     "toradex,apalis-imx8-v1.1",
+		     "fsl,imx8qm";
+};
+
+/* Apalis MMC1 */
+&usdhc2 {
+	/delete-property/ no-1-8-v;
+};
+
+/* Apalis SD1 */
+&usdhc3 {
+	/delete-property/ no-1-8-v;
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval.dts b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval.dts
index c8ff75831556..c998e542f93c 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qm-apalis-v1.1-eval.dts
@@ -6,7 +6,7 @@
 /dts-v1/;
 
 #include "imx8qm-apalis-v1.1.dtsi"
-#include "imx8-apalis-eval.dtsi"
+#include "imx8-apalis-eval-v1.1.dtsi"
 
 / {
 	model = "Toradex Apalis iMX8QM V1.1 on Apalis Evaluation Board";
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
index 6d50838ad17d..77ac0efdfaad 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
@@ -41,6 +41,18 @@
 	};
 };
 
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-frequency = <100000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_i2c1>;
+	pinctrl-1 = <&pinctrl_i2c1_gpio>;
+	scl-gpios = <&lsio_gpio0 14 GPIO_ACTIVE_HIGH>;
+	sda-gpios = <&lsio_gpio0 15 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
 &lpuart0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_lpuart0>;
@@ -104,6 +116,20 @@
 };
 
 &iomuxc {
+	pinctrl_i2c1: i2c1grp {
+		fsl,pins = <
+			IMX8QM_GPT0_CLK_DMA_I2C1_SCL 0x0600004c
+			IMX8QM_GPT0_CAPTURE_DMA_I2C1_SDA 0x0600004c
+		>;
+	};
+
+	pinctrl_i2c1_gpio: i2c1gpio-grp {
+		fsl,pins = <
+			IMX8QM_GPT0_CLK_LSIO_GPIO0_IO14		0xc600004c
+			IMX8QM_GPT0_CAPTURE_LSIO_GPIO0_IO15	0xc600004c
+		>;
+	};
+
 	pinctrl_fec1: fec1grp {
 		fsl,pins = <
 			IMX8QM_ENET0_MDC_CONN_ENET0_MDC				0x06000020
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-conn.dtsi
index ec1639174e2e..545e175c88b3 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-conn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-conn.dtsi
@@ -6,20 +6,25 @@
 
 &fec1 {
 	compatible = "fsl,imx8qm-fec", "fsl,imx6sx-fec";
+	iommus = <&smmu 0x12 0x7f80>;
 };
 
 &fec2 {
 	compatible = "fsl,imx8qm-fec", "fsl,imx6sx-fec";
+	iommus = <&smmu 0x12 0x7f80>;
 };
 
 &usdhc1 {
 	compatible = "fsl,imx8qm-usdhc", "fsl,imx8qxp-usdhc", "fsl,imx7d-usdhc";
+	iommus = <&smmu 0x11 0x7f80>;
 };
 
 &usdhc2 {
 	compatible = "fsl,imx8qm-usdhc", "fsl,imx8qxp-usdhc", "fsl,imx7d-usdhc";
+	iommus = <&smmu 0x11 0x7f80>;
 };
 
 &usdhc3 {
 	compatible = "fsl,imx8qm-usdhc", "fsl,imx8qxp-usdhc", "fsl,imx7d-usdhc";
+	iommus = <&smmu 0x11 0x7f80>;
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
index 69cb8676732e..11626fae5f97 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
@@ -17,6 +17,32 @@
 		power-domains = <&pd IMX_SC_R_UART_4>;
 	};
 
+	i2c4: i2c@5a840000 {
+		compatible = "fsl,imx8qm-lpi2c", "fsl,imx7ulp-lpi2c";
+		reg = <0x5a840000 0x4000>;
+		interrupts = <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-parent = <&gic>;
+		clocks = <&i2c4_lpcg 0>,
+			 <&i2c4_lpcg 1>;
+		clock-names = "per", "ipg";
+		assigned-clocks = <&clk IMX_SC_R_I2C_4 IMX_SC_PM_CLK_PER>;
+		assigned-clock-rates = <24000000>;
+		power-domains = <&pd IMX_SC_R_I2C_4>;
+		status = "disabled";
+	};
+
+	i2c4_lpcg: clock-controller@5ac40000 {
+		compatible = "fsl,imx8qxp-lpcg";
+		reg = <0x5ac40000 0x10000>;
+		#clock-cells = <1>;
+		clocks = <&clk IMX_SC_R_I2C_4 IMX_SC_PM_CLK_PER>,
+			 <&dma_ipg_clk>;
+		clock-indices = <IMX_LPCG_CLK_0>, <IMX_LPCG_CLK_4>;
+		clock-output-names = "i2c4_lpcg_clk",
+				     "i2c4_lpcg_ipg_clk";
+		power-domains = <&pd IMX_SC_R_I2C_4>;
+	};
+
 	can1_lpcg: clock-controller@5ace0000 {
 		compatible = "fsl,imx8qxp-lpcg";
 		reg = <0x5ace0000 0x10000>;
@@ -96,15 +122,30 @@
 	status = "okay";
 };
 
+/* It is eDMA1 in 8QM RM, but 8QXP it is eDMA3 */
 &edma3 {
+	reg = <0x5a9f0000 0x210000>;
+	dma-channels = <10>;
+	interrupts = <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 432 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 433 IRQ_TYPE_LEVEL_HIGH>;
 	power-domains = <&pd IMX_SC_R_DMA_1_CH0>,
-		     <&pd IMX_SC_R_DMA_1_CH1>,
-		     <&pd IMX_SC_R_DMA_1_CH2>,
-		     <&pd IMX_SC_R_DMA_1_CH3>,
-		     <&pd IMX_SC_R_DMA_1_CH4>,
-		     <&pd IMX_SC_R_DMA_1_CH5>,
-		     <&pd IMX_SC_R_DMA_1_CH6>,
-		     <&pd IMX_SC_R_DMA_1_CH7>;
+			<&pd IMX_SC_R_DMA_1_CH1>,
+			<&pd IMX_SC_R_DMA_1_CH2>,
+			<&pd IMX_SC_R_DMA_1_CH3>,
+			<&pd IMX_SC_R_DMA_1_CH4>,
+			<&pd IMX_SC_R_DMA_1_CH5>,
+			<&pd IMX_SC_R_DMA_1_CH6>,
+			<&pd IMX_SC_R_DMA_1_CH7>,
+			<&pd IMX_SC_R_DMA_1_CH8>,
+			<&pd IMX_SC_R_DMA_1_CH9>;
 };
 
 &flexcan1 {
diff --git a/arch/arm64/boot/dts/freescale/imx8qm.dtsi b/arch/arm64/boot/dts/freescale/imx8qm.dtsi
index 31744fc1ab08..b3d01677b70c 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm.dtsi
@@ -265,6 +265,47 @@
 			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; /* Hypervisor */
 	};
 
+	smmu: iommu@51400000 {
+		compatible = "arm,mmu-500";
+		interrupt-parent = <&gic>;
+		reg = <0 0x51400000 0 0x40000>;
+		#global-interrupts = <1>;
+		#iommu-cells = <2>;
+		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	system-controller {
 		compatible = "fsl,imx-scu";
 		mbox-names = "tx0",
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp-mba8xx.dts b/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp-mba8xx.dts
new file mode 100644
index 000000000000..7d2e98bf8bc5
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp-mba8xx.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+/dts-v1/;
+
+#include "imx8qxp-tqma8xqp.dtsi"
+#include "mba8xx.dtsi"
+
+/ {
+	model = "TQ-Systems i.MX8QXP TQMa8XQP on MBa8Xx";
+	compatible = "tq,imx8qxp-tqma8xqp-mba8xx", "tq,imx8qxp-tqma8xqp", "fsl,imx8qxp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp.dtsi
new file mode 100644
index 000000000000..b14040bf4ddd
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-tqma8xqp.dtsi
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+#include "imx8qxp.dtsi"
+#include "tqma8xx.dtsi"
+
+/ {
+	model = "TQ-Systems i.MX8QXP TQMa8XQP";
+	compatible = "tq,imx8qxp-tqma8xqp", "fsl,imx8qxp";
+};
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
index 958267b33340..10e16d84c0c3 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qxp.dtsi
@@ -260,6 +260,13 @@
 			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>; /* Hypervisor */
 	};
 
+	clk_dummy: clock-dummy {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+		clock-output-names = "clk_dummy";
+	};
+
 	xtal32k: clock-xtal32k {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
@@ -310,6 +317,7 @@
 	/* sorted in register address */
 	#include "imx8-ss-img.dtsi"
 	#include "imx8-ss-vpu.dtsi"
+	#include "imx8-ss-gpu0.dtsi"
 	#include "imx8-ss-adma.dtsi"
 	#include "imx8-ss-conn.dtsi"
 	#include "imx8-ss-ddr.dtsi"
diff --git a/arch/arm64/boot/dts/freescale/imx8ulp-evk.dts b/arch/arm64/boot/dts/freescale/imx8ulp-evk.dts
index 69dd8e31027c..24bb253b938d 100644
--- a/arch/arm64/boot/dts/freescale/imx8ulp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8ulp-evk.dts
@@ -37,7 +37,7 @@
 			no-map;
 		};
 
-		rsc_table: rsc-table@1fff8000{
+		rsc_table: rsc-table@1fff8000 {
 			reg = <0 0x1fff8000 0 0x1000>;
 			no-map;
 		};
diff --git a/arch/arm64/boot/dts/freescale/imx93-phyboard-segin.dts b/arch/arm64/boot/dts/freescale/imx93-phyboard-segin.dts
new file mode 100644
index 000000000000..85fb188b057f
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx93-phyboard-segin.dts
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 PHYTEC Messtechnik GmbH
+ * Author: Wadim Egorov <w.egorov@phytec.de>, Christoph Stoidner <c.stoidner@phytec.de>
+ * Copyright (C) 2024 Mathieu Othacehe <m.othacehe@gmail.com>
+ *
+ * Product homepage:
+ * phyBOARD-Segin carrier board is reused for the i.MX93 design.
+ * https://www.phytec.eu/en/produkte/single-board-computer/phyboard-segin-imx6ul/
+ */
+/dts-v1/;
+
+#include "imx93-phycore-som.dtsi"
+
+/{
+	model = "PHYTEC phyBOARD-Segin-i.MX93";
+	compatible = "phytec,imx93-phyboard-segin", "phytec,imx93-phycore-som",
+		     "fsl,imx93";
+
+	chosen {
+		stdout-path = &lpuart1;
+	};
+
+	reg_usdhc2_vmmc: regulator-usdhc2 {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 7 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usdhc2_vmmc>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "VCC_SD";
+	};
+};
+
+/* Console */
+&lpuart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+/* eMMC */
+&usdhc1 {
+	no-1-8-v;
+};
+
+/* SD-Card */
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2_default>, <&pinctrl_usdhc2_cd>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_cd>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>;
+	bus-width = <4>;
+	cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
+	no-mmc;
+	no-sdio;
+	vmmc-supply = <&reg_usdhc2_vmmc>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX93_PAD_UART1_RXD__LPUART1_RX		0x31e
+			MX93_PAD_UART1_TXD__LPUART1_TX		0x30e
+		>;
+	};
+
+	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
+		fsl,pins = <
+			MX93_PAD_SD2_RESET_B__GPIO3_IO07	0x31e
+		>;
+	};
+
+	pinctrl_usdhc2_cd: usdhc2cdgrp {
+		fsl,pins = <
+			MX93_PAD_SD2_CD_B__GPIO3_IO00		0x31e
+		>;
+	};
+
+	pinctrl_usdhc2_default: usdhc2grp {
+		fsl,pins = <
+			MX93_PAD_SD2_CLK__USDHC2_CLK		0x179e
+			MX93_PAD_SD2_CMD__USDHC2_CMD		0x139e
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x138e
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x138e
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x138e
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x139e
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT	0x51e
+		>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2grp {
+		fsl,pins = <
+			MX93_PAD_SD2_CLK__USDHC2_CLK            0x179e
+			MX93_PAD_SD2_CMD__USDHC2_CMD            0x139e
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0        0x138e
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1        0x138e
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2        0x139e
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3        0x139e
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT    0x51e
+		>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2grp {
+		fsl,pins = <
+			MX93_PAD_SD2_CLK__USDHC2_CLK            0x178e
+			MX93_PAD_SD2_CMD__USDHC2_CMD            0x139e
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0        0x139e
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1        0x139e
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2        0x139e
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3        0x139e
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT    0x51e
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx93-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx93-phycore-som.dtsi
new file mode 100644
index 000000000000..88c2657b50e6
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx93-phycore-som.dtsi
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (C) 2023 PHYTEC Messtechnik GmbH
+ * Author: Wadim Egorov <w.egorov@phytec.de>, Christoph Stoidner <c.stoidner@phytec.de>
+ * Copyright (C) 2024 Mathieu Othacehe <m.othacehe@gmail.com>
+ *
+ * Product homepage:
+ * https://www.phytec.eu/en/produkte/system-on-modules/phycore-imx-91-93/
+ */
+
+#include <dt-bindings/leds/common.h>
+
+#include "imx93.dtsi"
+
+/{
+	model = "PHYTEC phyCORE-i.MX93";
+	compatible = "phytec,imx93-phycore-som", "fsl,imx93";
+
+	reserved-memory {
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			alloc-ranges = <0 0x80000000 0 0x40000000>;
+			size = <0 0x10000000>;
+			linux,cma-default;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_leds>;
+
+		led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+};
+
+/* Ethernet */
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_fec>;
+	phy-mode = "rmii";
+	phy-handle = <&ethphy1>;
+	fsl,magic-packet;
+	assigned-clocks = <&clk IMX93_CLK_ENET_TIMER1>,
+			  <&clk IMX93_CLK_ENET_REF>,
+			  <&clk IMX93_CLK_ENET_REF_PHY>;
+	assigned-clock-parents = <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>,
+				 <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>,
+				 <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>;
+	assigned-clock-rates = <100000000>, <50000000>, <50000000>;
+	status = "okay";
+
+	mdio: mdio {
+		clock-frequency = <5000000>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy1: ethernet-phy@1 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <1>;
+		};
+	};
+};
+
+/* eMMC */
+&usdhc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	bus-width = <8>;
+	non-removable;
+	status = "okay";
+};
+
+/* Watchdog */
+&wdog3 {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_fec: fecgrp {
+		fsl,pins = <
+			MX93_PAD_ENET2_MDC__ENET1_MDC			0x50e
+			MX93_PAD_ENET2_MDIO__ENET1_MDIO			0x502
+			MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0		0x57e
+			MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1		0x57e
+			MX93_PAD_ENET2_RXC__ENET1_RX_ER			0x5fe
+			MX93_PAD_ENET2_RX_CTL__ENET1_RGMII_RX_CTL	0x57e
+			MX93_PAD_ENET2_TD0__ENET1_RGMII_TD0		0x50e
+			MX93_PAD_ENET2_TD1__ENET1_RGMII_TD1		0x50e
+			MX93_PAD_ENET2_TX_CTL__ENET1_RGMII_TX_CTL	0x50e
+			MX93_PAD_ENET2_TD2__ENET1_TX_CLK		0x4000050e
+		>;
+	};
+
+	pinctrl_leds: ledsgrp {
+		fsl,pins = <
+			MX93_PAD_I2C1_SDA__GPIO1_IO01		0x31e
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX93_PAD_SD1_CLK__USDHC1_CLK		0x179e
+			MX93_PAD_SD1_CMD__USDHC1_CMD		0x1386
+			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x138e
+			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x1386
+			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x138e
+			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x1386
+			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x1386
+			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x1386
+			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x1386
+			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x1386
+			MX93_PAD_SD1_STROBE__USDHC1_STROBE	0x179e
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
index f6e422dc2663..9d2328c185c9 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
@@ -122,10 +122,8 @@
 
 	/* protectable identification memory (part of M24C64-D @57) */
 	eeprom@5f {
-		compatible = "st,24c64", "atmel,24c64";
+		compatible = "atmel,24c64d-wl";
 		reg = <0x5f>;
-		size = <32>;
-		pagesize = <32>;
 		vcc-supply = <&reg_v3v3>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx93-var-som-symphony.dts b/arch/arm64/boot/dts/freescale/imx93-var-som-symphony.dts
new file mode 100644
index 000000000000..576d6982a4a0
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx93-var-som-symphony.dts
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2021 NXP
+ * Copyright 2023 Variscite Ltd.
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/leds/common.h>
+#include "imx93-var-som.dtsi"
+
+/{
+	model = "Variscite VAR-SOM-MX93 on Symphony evaluation board";
+	compatible = "variscite,var-som-mx93-symphony",
+		     "variscite,var-som-mx93", "fsl,imx93";
+
+	aliases {
+		ethernet0 = &eqos;
+		ethernet1 = &fec;
+	};
+
+	chosen {
+		stdout-path = &lpuart1;
+	};
+
+	/*
+	 * Needed only for Symphony <= v1.5
+	 */
+	reg_fec_phy: regulator-fec-phy {
+		compatible = "regulator-fixed";
+		regulator-name = "fec-phy";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-enable-ramp-delay = <20000>;
+		gpio = <&pca9534 7 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	reg_usdhc2_vmmc: regulator-usdhc2 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usdhc2_vmmc>;
+		regulator-name = "VSD_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio2 18 GPIO_ACTIVE_HIGH>;
+		off-on-delay-us = <20000>;
+		enable-active-high;
+	};
+
+	reg_vref_1v8: regulator-adc-vref {
+		compatible = "regulator-fixed";
+		regulator-name = "vref_1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		ethosu_mem: ethosu-region@88000000 {
+			compatible = "shared-dma-pool";
+			reusable;
+			reg = <0x0 0x88000000 0x0 0x8000000>;
+		};
+
+		vdev0vring0: vdev0vring0@87ee0000 {
+			reg = <0 0x87ee0000 0 0x8000>;
+			no-map;
+		};
+
+		vdev0vring1: vdev0vring1@87ee8000 {
+			reg = <0 0x87ee8000 0 0x8000>;
+			no-map;
+		};
+
+		vdev1vring0: vdev1vring0@87ef0000 {
+			reg = <0 0x87ef0000 0 0x8000>;
+			no-map;
+		};
+
+		vdev1vring1: vdev1vring1@87ef8000 {
+			reg = <0 0x87ef8000 0 0x8000>;
+			no-map;
+		};
+
+		rsc_table: rsc-table@2021f000 {
+			reg = <0 0x2021f000 0 0x1000>;
+			no-map;
+		};
+
+		vdevbuffer: vdevbuffer@87f00000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x87f00000 0 0x100000>;
+			no-map;
+		};
+
+		ele_reserved: ele-reserved@87de0000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x87de0000 0 0x100000>;
+			no-map;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		key-back {
+			label = "Back";
+			gpios = <&pca9534 1 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_BACK>;
+		};
+
+		key-home {
+			label = "Home";
+			gpios = <&pca9534 2 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_HOME>;
+		};
+
+		key-menu {
+			label = "Menu";
+			gpios = <&pca9534 3 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_MENU>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&pca9534 0 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+};
+
+/* Use external instead of internal RTC*/
+&bbnsm_rtc {
+	status = "disabled";
+};
+
+&eqos {
+	mdio {
+		ethphy1: ethernet-phy@5 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <5>;
+			qca,disable-smarteee;
+			eee-broken-1000t;
+			reset-gpios = <&pca9534 5 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <10000>;
+			reset-deassert-us = <20000>;
+			vddio-supply = <&vddio1>;
+
+			vddio1: vddio-regulator {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+			};
+		};
+	};
+};
+
+&fec {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_fec>;
+	phy-mode = "rgmii";
+	phy-handle = <&ethphy1>;
+	phy-supply = <&reg_fec_phy>;
+	status = "okay";
+};
+
+&flexcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexcan1>;
+	status = "okay";
+};
+
+&lpi2c1 {
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "sleep", "gpio";
+	pinctrl-0 = <&pinctrl_lpi2c1>;
+	pinctrl-1 = <&pinctrl_lpi2c1_gpio>;
+	pinctrl-2 = <&pinctrl_lpi2c1_gpio>;
+	scl-gpios = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+	sda-gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+
+	/* DS1337 RTC module */
+	rtc@68 {
+		compatible = "dallas,ds1337";
+		reg = <0x68>;
+	};
+};
+
+&lpi2c5 {
+	clock-frequency = <400000>;
+	pinctrl-names = "default", "sleep", "gpio";
+	pinctrl-0 = <&pinctrl_lpi2c5>;
+	pinctrl-1 = <&pinctrl_lpi2c5_gpio>;
+	pinctrl-2 = <&pinctrl_lpi2c5_gpio>;
+	scl-gpios = <&gpio2 23 GPIO_ACTIVE_HIGH>;
+	sda-gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+
+	pca9534: gpio@20 {
+		compatible = "nxp,pca9534";
+		reg = <0x20>;
+		gpio-controller;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pca9534>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <26 IRQ_TYPE_EDGE_FALLING>;
+		#gpio-cells = <2>;
+		wakeup-source;
+	};
+};
+
+/* Console */
+&lpuart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart1>;
+	status = "okay";
+};
+
+/* J18.7, J18.9 */
+&lpuart6 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart6>;
+	status = "okay";
+};
+
+/* SD */
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	cd-gpios = <&gpio3 00 GPIO_ACTIVE_LOW>;
+	vmmc-supply = <&reg_usdhc2_vmmc>;
+	bus-width = <4>;
+	status = "okay";
+	no-sdio;
+	no-mmc;
+};
+
+/* Watchdog */
+&wdog3 {
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_fec: fecgrp {
+		fsl,pins = <
+			MX93_PAD_ENET2_RD0__ENET1_RGMII_RD0		0x57e
+			MX93_PAD_ENET2_RD1__ENET1_RGMII_RD1		0x57e
+			MX93_PAD_ENET2_RD2__ENET1_RGMII_RD2		0x57e
+			MX93_PAD_ENET2_RD3__ENET1_RGMII_RD3		0x57e
+			MX93_PAD_ENET2_RXC__ENET1_RGMII_RXC		0x5fe
+			MX93_PAD_ENET2_RX_CTL__ENET1_RGMII_RX_CTL	0x57e
+			MX93_PAD_ENET2_TD0__ENET1_RGMII_TD0		0x57e
+			MX93_PAD_ENET2_TD1__ENET1_RGMII_TD1		0x57e
+			MX93_PAD_ENET2_TD2__ENET1_RGMII_TD2		0x57e
+			MX93_PAD_ENET2_TD3__ENET1_RGMII_TD3		0x57e
+			MX93_PAD_ENET2_TXC__ENET1_RGMII_TXC		0x5fe
+			MX93_PAD_ENET2_TX_CTL__ENET1_RGMII_TX_CTL	0x57e
+		>;
+	};
+
+	pinctrl_flexcan1: flexcan1grp {
+		fsl,pins = <
+			MX93_PAD_PDM_CLK__CAN1_TX                       0x139e
+			MX93_PAD_PDM_BIT_STREAM0__CAN1_RX               0x139e
+		>;
+	};
+
+	pinctrl_lpi2c1: lpi2c1grp {
+		fsl,pins = <
+			MX93_PAD_I2C1_SCL__LPI2C1_SCL			0x40000b9e
+			MX93_PAD_I2C1_SDA__LPI2C1_SDA			0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c1_gpio: lpi2c1gpiogrp {
+		fsl,pins = <
+			MX93_PAD_I2C1_SCL__GPIO1_IO00			0x31e
+			MX93_PAD_I2C1_SDA__GPIO1_IO01			0x31e
+		>;
+	};
+
+	pinctrl_lpi2c5: lpi2c5grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO23__LPI2C5_SCL			0x40000b9e
+			MX93_PAD_GPIO_IO22__LPI2C5_SDA			0x40000b9e
+		>;
+	};
+
+	pinctrl_lpi2c5_gpio: lpi2c5gpiogrp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO23__GPIO2_IO23			0x31e
+			MX93_PAD_GPIO_IO22__GPIO2_IO22			0x31e
+		>;
+	};
+
+	pinctrl_pca9534: pca9534grp {
+		fsl,pins = <
+			MX93_PAD_CCM_CLKO1__GPIO3_IO26		0x31e
+		>;
+	};
+
+	pinctrl_uart1: uart1grp {
+		fsl,pins = <
+			MX93_PAD_UART1_RXD__LPUART1_RX			0x31e
+			MX93_PAD_UART1_TXD__LPUART1_TX			0x31e
+		>;
+	};
+
+	pinctrl_uart6: uart6grp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO05__LPUART6_RX			0x31e
+			MX93_PAD_GPIO_IO04__LPUART6_TX			0x31e
+		>;
+	};
+
+	pinctrl_reg_usdhc2_vmmc: regusdhc2vmmcgrp {
+		fsl,pins = <
+			MX93_PAD_GPIO_IO18__GPIO2_IO18		0x31e
+		>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <
+			MX93_PAD_SD2_CLK__USDHC2_CLK		0x15fe
+			MX93_PAD_SD2_CMD__USDHC2_CMD		0x13fe
+			MX93_PAD_SD2_DATA0__USDHC2_DATA0	0x13fe
+			MX93_PAD_SD2_DATA1__USDHC2_DATA1	0x13fe
+			MX93_PAD_SD2_DATA2__USDHC2_DATA2	0x13fe
+			MX93_PAD_SD2_DATA3__USDHC2_DATA3	0x13fe
+			MX93_PAD_SD2_VSELECT__USDHC2_VSELECT	0x51e
+		>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <
+			MX93_PAD_SD2_CD_B__GPIO3_IO00		0x31e
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx93-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx93-var-som.dtsi
new file mode 100644
index 000000000000..783938245e4f
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/imx93-var-som.dtsi
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright 2022 NXP
+ * Copyright 2023 Variscite Ltd.
+ */
+
+/dts-v1/;
+
+#include "imx93.dtsi"
+
+/{
+	model = "Variscite VAR-SOM-MX93 module";
+	compatible = "variscite,var-som-mx93", "fsl,imx93";
+
+	mmc_pwrseq: mmc-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		post-power-on-delay-ms = <100>;
+		power-off-delay-us = <10000>;
+		reset-gpios = <&gpio4 14 GPIO_ACTIVE_LOW>,	/* WIFI_RESET */
+			      <&gpio3 7 GPIO_ACTIVE_LOW>;	/* WIFI_PWR_EN */
+	};
+
+	reg_eqos_phy: regulator-eqos-phy {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_eqos_phy>;
+		regulator-name = "eth_phy_pwr";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		startup-delay-us = <100000>;
+		regulator-always-on;
+	};
+};
+
+&eqos {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_eqos>;
+	phy-mode = "rgmii";
+	phy-handle = <&ethphy0>;
+	status = "okay";
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		clock-frequency = <1000000>;
+
+		ethphy0: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <0>;
+			eee-broken-1000t;
+		};
+	};
+};
+
+/* eMMC */
+&usdhc1 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	pinctrl-1 = <&pinctrl_usdhc1>;
+	pinctrl-2 = <&pinctrl_usdhc1>;
+	bus-width = <8>;
+	non-removable;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_eqos: eqosgrp {
+		fsl,pins = <
+			MX93_PAD_ENET1_MDC__ENET_QOS_MDC			0x57e
+			MX93_PAD_ENET1_MDIO__ENET_QOS_MDIO			0x57e
+			MX93_PAD_ENET1_RD0__ENET_QOS_RGMII_RD0			0x57e
+			MX93_PAD_ENET1_RD1__ENET_QOS_RGMII_RD1			0x57e
+			MX93_PAD_ENET1_RD2__ENET_QOS_RGMII_RD2			0x57e
+			MX93_PAD_ENET1_RD3__ENET_QOS_RGMII_RD3			0x57e
+			MX93_PAD_ENET1_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK	0x5fe
+			MX93_PAD_ENET1_RX_CTL__ENET_QOS_RGMII_RX_CTL		0x57e
+			MX93_PAD_ENET1_TD0__ENET_QOS_RGMII_TD0			0x57e
+			MX93_PAD_ENET1_TD1__ENET_QOS_RGMII_TD1			0x57e
+			MX93_PAD_ENET1_TD2__ENET_QOS_RGMII_TD2			0x57e
+			MX93_PAD_ENET1_TD3__ENET_QOS_RGMII_TD3			0x57e
+			MX93_PAD_ENET1_TXC__CCM_ENET_QOS_CLOCK_GENERATE_TX_CLK	0x5fe
+			MX93_PAD_ENET1_TX_CTL__ENET_QOS_RGMII_TX_CTL		0x57e
+		>;
+	};
+
+	pinctrl_reg_eqos_phy: regeqosgrp {
+		fsl,pins = <
+			MX93_PAD_UART2_TXD__GPIO1_IO07			0x51e
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			MX93_PAD_SD1_CLK__USDHC1_CLK		0x15fe
+			MX93_PAD_SD1_CMD__USDHC1_CMD		0x13fe
+			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x13fe
+			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x13fe
+			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x13fe
+			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x13fe
+			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x13fe
+			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x13fe
+			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x13fe
+			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x13fe
+			MX93_PAD_SD1_STROBE__USDHC1_STROBE	0x15fe
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index 8f2e7c42ad6e..601c94e1fac8 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -294,7 +294,7 @@
 				status = "disabled";
 			};
 
-			i3c1: i3c-master@44330000 {
+			i3c1: i3c@44330000 {
 				compatible = "silvaco,i3c-master-v1";
 				reg = <0x44330000 0x10000>;
 				interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
@@ -671,7 +671,7 @@
 				status = "disabled";
 			};
 
-			i3c2: i3c-master@42520000 {
+			i3c2: i3c@42520000 {
 				compatible = "silvaco,i3c-master-v1";
 				reg = <0x42520000 0x10000>;
 				interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/freescale/mba8mx.dtsi b/arch/arm64/boot/dts/freescale/mba8mx.dtsi
index e2bc53b8d39a..427467df42bf 100644
--- a/arch/arm64/boot/dts/freescale/mba8mx.dtsi
+++ b/arch/arm64/boot/dts/freescale/mba8mx.dtsi
@@ -29,6 +29,12 @@
 		stdout-path = &uart3;
 	};
 
+	clk_xtal25: clk-xtal25 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+	};
+
 	gpio-keys {
 		compatible = "gpio-keys";
 		pinctrl-names = "default";
@@ -100,12 +106,6 @@
 		};
 	};
 
-	pcie0_refclk: pcie0-refclk {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <100000000>;
-	};
-
 	reg_12v: regulator-12v {
 		compatible = "regulator-fixed";
 		regulator-name = "MBA8MX_12V";
@@ -219,7 +219,7 @@
 			line-name = "BOOT_CFG_OE#";
 		};
 
-		rst-usb-hub-hog {
+		rst_usb_hub_hog: rst-usb-hub-hog {
 			gpio-hog;
 			gpios = <13 0>;
 			output-high;
@@ -264,6 +264,13 @@
 		pagesize = <16>;
 		vcc-supply = <&reg_vcc_3v3>;
 	};
+
+	pcieclk: clk@68 {
+		compatible = "renesas,9fgv0441";
+		reg = <0x68>;
+		clocks = <&clk_xtal25>;
+		#clock-cells = <1>;
+	};
 };
 
 &i2c3 {
diff --git a/arch/arm64/boot/dts/freescale/mba8xx.dtsi b/arch/arm64/boot/dts/freescale/mba8xx.dtsi
new file mode 100644
index 000000000000..276d1683b03b
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/mba8xx.dtsi
@@ -0,0 +1,554 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/net/ti-dp83867.h>
+
+/ {
+	adc {
+		compatible = "iio-hwmon";
+		io-channels = <&adc0 0>, <&adc0 1>, <&adc0 2>, <&adc0 3>;
+	};
+
+	aliases {
+		rtc0 = &pcf85063;
+		rtc1 = &rtc;
+	};
+
+	backlight_lvds: backlight-lvds {
+		compatible = "pwm-backlight";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_bl_lvds>;
+		pwms = <&adma_pwm 0 5000000 0>;
+		brightness-levels = <0 4 8 16 32 64 128 255>;
+		default-brightness-level = <7>;
+		power-supply = <&reg_12v0>;
+		enable-gpios = <&lsio_gpio1 30 GPIO_ACTIVE_HIGH>;
+		status = "disabled";
+	};
+
+	chosen {
+		stdout-path = &lpuart1;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_gpiobuttons>;
+		autorepeat;
+
+		switch-a {
+			label = "switcha";
+			linux,code = <BTN_0>;
+			gpios = <&lsio_gpio1 13 GPIO_ACTIVE_LOW>;
+		};
+
+		switch-b {
+			label = "switchb";
+			linux,code = <BTN_1>;
+			gpios = <&lsio_gpio1 14 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			gpios = <&expander 1 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "default-on";
+		};
+
+		led2 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&expander 2 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+		};
+	};
+
+	/* TODO LVDS panels */
+
+	reg_12v0: regulator-12v0 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_12V";
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+		gpio = <&expander 6 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	reg_pcie_1v5: regulator-pcie-1v5 {
+		compatible = "regulator-fixed";
+		regulator-name = "MBA8XX_PCIE_1V5";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_pcie_1v5>;
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		gpio = <&lsio_gpio0 30 GPIO_ACTIVE_HIGH>;
+		startup-delay-us = <1000>;
+		enable-active-high;
+	};
+
+	reg_pcie_3v3: regulator-pcie-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "MBA8XX_PCIE_3V3";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_pcie_3v3>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&lsio_gpio0 31 GPIO_ACTIVE_HIGH>;
+		startup-delay-us = <1000>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	reg_3v3_mb: regulator-usdhc2-vmmc {
+		compatible = "regulator-fixed";
+		regulator-name = "V_3V3_MB";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	sound {
+		compatible = "fsl,imx-audio-tlv320aic32x4";
+		model = "tqm-tlv320aic32";
+		audio-codec = <&tlv320aic3x04>;
+		ssi-controller = <&sai1>;
+	};
+};
+
+&adc0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_adc0>;
+	vref-supply = <&reg_1v8>;
+	#io-channel-cells = <1>;
+	status = "okay";
+};
+
+&adma_pwm {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_admapwm>;
+};
+
+&fec1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_fec1>;
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethphy0>;
+	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@0 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <0>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_ethphy0>;
+			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+			ti,dp83867-rxctrl-strap-quirk;
+			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+			reset-gpios = <&lsio_gpio3 2 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <500000>;
+			reset-deassert-us = <50000>;
+			enet-phy-lane-no-swap;
+			interrupt-parent = <&lsio_gpio3>;
+			interrupts = <0 IRQ_TYPE_EDGE_FALLING>;
+		};
+
+		ethphy3: ethernet-phy@3 {
+			compatible = "ethernet-phy-ieee802.3-c22";
+			reg = <3>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_ethphy3>;
+			ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+			ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+			ti,dp83867-rxctrl-strap-quirk;
+			ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
+			reset-gpios = <&lsio_gpio3 3 GPIO_ACTIVE_LOW>;
+			reset-assert-us = <500000>;
+			reset-deassert-us = <50000>;
+			enet-phy-lane-no-swap;
+			interrupt-parent = <&lsio_gpio3>;
+			interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
+		};
+	};
+};
+
+&fec2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_fec2>;
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethphy3>;
+	status = "okay";
+};
+
+&flexcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_can0>;
+	xceiver-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&flexcan2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_can1>;
+	xceiver-supply = <&reg_3v3>;
+	status = "okay";
+};
+
+&i2c1 {
+	tlv320aic3x04: audio-codec@18 {
+		compatible = "ti,tlv320aic32x4";
+		reg = <0x18>;
+		clocks = <&mclkout0_lpcg 0>;
+		clock-names = "mclk";
+		iov-supply = <&reg_1v8>;
+		ldoin-supply = <&reg_3v3>;
+	};
+
+	se97b_1c: temperature-sensor@1c {
+		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
+		reg = <0x1c>;
+	};
+
+	at24c02_54: eeprom@54 {
+		compatible = "nxp,se97b", "atmel,24c02";
+		reg = <0x54>;
+		pagesize = <16>;
+		vcc-supply = <&reg_3v3>;
+	};
+
+	expander: gpio@70 {
+		compatible = "nxp,pca9538";
+		reg = <0x70>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pca9538>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-parent = <&lsio_gpio4>;
+		interrupts = <19 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		vcc-supply = <&reg_1v8>;
+
+		gpio-line-names = "", "LED_A",
+				  "LED_B", "",
+				  "DSI_EN", "USB_RESET#",
+				  "V_12V_EN", "PCIE_DIS#";
+	};
+};
+
+&i2c2 {
+	clock-frequency = <100000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_lpi2c2>;
+	pinctrl-1 = <&pinctrl_lpi2c2gpio>;
+	scl-gpios = <&lsio_gpio1 31 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&lsio_gpio2 0 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	status = "okay";
+};
+
+/* TODO LDB */
+
+&lpspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi1>;
+	cs-gpios = <&lsio_gpio0 27 GPIO_ACTIVE_LOW>, <&lsio_gpio0 29 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&lpspi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi2>;
+	cs-gpios = <&lsio_gpio1 0 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&lpspi3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_spi3>;
+	num-cs = <2>;
+	cs-gpios = <&lsio_gpio0 16 GPIO_ACTIVE_LOW>;
+	status = "okay";
+};
+
+&lpuart1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lpuart1>;
+	status = "okay";
+};
+
+&lpuart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lpuart3>;
+	status = "okay";
+};
+
+&lsio_gpio3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_lsgpio3>;
+	gpio-line-names = "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "X4_15",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "",
+			  "", "", "", "";
+};
+
+/* TODO: Mini-PCIe */
+
+&sai1 {
+	assigned-clocks = <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_PLL>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_SLV_BUS>,
+			  <&clk IMX_SC_R_AUDIO_PLL_0 IMX_SC_PM_CLK_MST_BUS>,
+			  <&sai1_lpcg 0>;
+	assigned-clock-rates = <786432000>, <49152000>, <12288000>, <49152000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_sai1>;
+	status = "okay";
+};
+
+&usbotg1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_usbotg1>;
+	srp-disable;
+	hnp-disable;
+	adp-disable;
+	power-active-high;
+	over-current-active-low;
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&usbotg3 {
+	status = "okay";
+};
+
+&usbotg3_cdns3 {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&usbphy1 {
+	status = "okay";
+};
+
+&usb3_phy {
+	status = "okay";
+};
+
+&usdhc2 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc2>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-1 = <&pinctrl_usdhc2_100mhz>, <&pinctrl_usdhc2_gpio>;
+	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
+	bus-width = <4>;
+	cd-gpios = <&lsio_gpio4 22 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&lsio_gpio4 21 GPIO_ACTIVE_HIGH>;
+	vmmc-supply = <&reg_3v3_mb>;
+	no-1-8-v;
+	no-sdio;
+	no-mmc;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_adc0: adc0grp {
+		fsl,pins = <IMX8QXP_ADC_IN0_ADMA_ADC_IN0	0x02000060>,
+			   <IMX8QXP_ADC_IN1_ADMA_ADC_IN1	0x02000060>,
+			   <IMX8QXP_ADC_IN2_ADMA_ADC_IN2	0x02000060>,
+			   <IMX8QXP_ADC_IN3_ADMA_ADC_IN3	0x02000060>;
+	};
+
+	pinctrl_admapwm: admapwmgrp {
+		fsl,pins = <IMX8QXP_SPI0_CS1_ADMA_LCD_PWM0_OUT	0x00000021>;
+	};
+
+	pinctrl_bl_lvds: bllvdsgrp {
+		fsl,pins = <IMX8QXP_MIPI_DSI1_I2C0_SDA_LSIO_GPIO1_IO30	0x00000021>;
+	};
+
+	pinctrl_can0: can0grp {
+		fsl,pins = <IMX8QXP_UART0_RX_ADMA_FLEXCAN0_RX		0x00000021>,
+			   <IMX8QXP_UART0_TX_ADMA_FLEXCAN0_TX		0x00000021>;
+	};
+
+	pinctrl_can1: can1grp {
+		fsl,pins = <IMX8QXP_UART2_RX_ADMA_FLEXCAN1_RX		0x00000021>,
+			   <IMX8QXP_UART2_TX_ADMA_FLEXCAN1_TX		0x00000021>;
+	};
+
+	pinctrl_ethphy0: ethphy0grp {
+		fsl,pins = <IMX8QXP_CSI_EN_LSIO_GPIO3_IO02		0x00000040>,
+			   <IMX8QXP_CSI_PCLK_LSIO_GPIO3_IO00		0x00000040>;
+	};
+
+	pinctrl_ethphy3: ethphy3grp {
+		fsl,pins = <IMX8QXP_CSI_RESET_LSIO_GPIO3_IO03		0x00000040>,
+			   <IMX8QXP_CSI_MCLK_LSIO_GPIO3_IO01		0x00000040>;
+	};
+
+	pinctrl_fec1: fec1grp {
+		fsl,pins = <IMX8QXP_ENET0_MDC_CONN_ENET0_MDC			0x06000041>,
+			   <IMX8QXP_ENET0_MDIO_CONN_ENET0_MDIO			0x06000041>,
+			   <IMX8QXP_ENET0_RGMII_TX_CTL_CONN_ENET0_RGMII_TX_CTL	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_TXC_CONN_ENET0_RGMII_TXC	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_TXD0_CONN_ENET0_RGMII_TXD0	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_TXD1_CONN_ENET0_RGMII_TXD1	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_TXD2_CONN_ENET0_RGMII_TXD2	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_TXD3_CONN_ENET0_RGMII_TXD3	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RX_CTL_CONN_ENET0_RGMII_RX_CTL	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RXC_CONN_ENET0_RGMII_RXC	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RXD0_CONN_ENET0_RGMII_RXD0	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RXD1_CONN_ENET0_RGMII_RXD1	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RXD2_CONN_ENET0_RGMII_RXD2	0x00000040>,
+			   <IMX8QXP_ENET0_RGMII_RXD3_CONN_ENET0_RGMII_RXD3	0x00000040>;
+	};
+
+	pinctrl_fec2: fec2grp {
+		fsl,pins = <IMX8QXP_ESAI0_SCKR_CONN_ENET1_RGMII_TX_CTL		0x00000040>,
+			   <IMX8QXP_ESAI0_FSR_CONN_ENET1_RGMII_TXC		0x00000040>,
+			   <IMX8QXP_ESAI0_TX4_RX1_CONN_ENET1_RGMII_TXD0		0x00000040>,
+			   <IMX8QXP_ESAI0_TX5_RX0_CONN_ENET1_RGMII_TXD1		0x00000040>,
+			   <IMX8QXP_ESAI0_FST_CONN_ENET1_RGMII_TXD2		0x00000040>,
+			   <IMX8QXP_ESAI0_SCKT_CONN_ENET1_RGMII_TXD3		0x00000040>,
+			   <IMX8QXP_ESAI0_TX0_CONN_ENET1_RGMII_RXC		0x00000040>,
+			   <IMX8QXP_SPDIF0_TX_CONN_ENET1_RGMII_RX_CTL		0x00000040>,
+			   <IMX8QXP_SPDIF0_RX_CONN_ENET1_RGMII_RXD0		0x00000040>,
+			   <IMX8QXP_ESAI0_TX3_RX2_CONN_ENET1_RGMII_RXD1		0x00000040>,
+			   <IMX8QXP_ESAI0_TX2_RX3_CONN_ENET1_RGMII_RXD2		0x00000040>,
+			   <IMX8QXP_ESAI0_TX1_CONN_ENET1_RGMII_RXD3		0x00000040>;
+	};
+
+	pinctrl_gpiobuttons: gpiobuttonsgrp {
+		fsl,pins = <IMX8QXP_ADC_IN5_LSIO_GPIO1_IO13	0x00000020>,
+			   <IMX8QXP_ADC_IN4_LSIO_GPIO1_IO14	0x00000020>;
+	};
+
+	pinctrl_lpi2c2: lpi2c2grp {
+		fsl,pins = <IMX8QXP_MIPI_DSI1_GPIO0_00_ADMA_I2C2_SCL	0x06000021>,
+			   <IMX8QXP_MIPI_DSI1_GPIO0_01_ADMA_I2C2_SDA	0x06000021>;
+	};
+
+	pinctrl_lpi2c2gpio: lpi2c2gpiogrp {
+		fsl,pins = <IMX8QXP_MIPI_DSI1_GPIO0_00_LSIO_GPIO1_IO31	0x06000021>,
+			   <IMX8QXP_MIPI_DSI1_GPIO0_01_LSIO_GPIO2_IO00	0x06000021>;
+	};
+
+	pinctrl_lpuart1: lpuart1grp {
+		fsl,pins = <IMX8QXP_UART1_RX_ADMA_UART1_RX	0x06000020>,
+			   <IMX8QXP_UART1_TX_ADMA_UART1_TX	0x06000020>;
+	};
+
+	pinctrl_lpuart3: lpuart3grp {
+		fsl,pins = <IMX8QXP_FLEXCAN2_RX_ADMA_UART3_RX	0x06000020>,
+			   <IMX8QXP_FLEXCAN2_TX_ADMA_UART3_TX	0x06000020>;
+	};
+
+	pinctrl_lsgpio3: lsgpio3grp {
+		fsl,pins = <IMX8QXP_QSPI0A_SS1_B_LSIO_GPIO3_IO15	0x00000021>;
+	};
+
+	pinctrl_pca9538: pca9538grp {
+		fsl,pins = <IMX8QXP_USDHC1_RESET_B_LSIO_GPIO4_IO19	0x00000020>;
+	};
+
+	pinctrl_pcieb: pcieagrp {
+		fsl,pins = <IMX8QXP_PCIE_CTRL0_PERST_B_LSIO_GPIO4_IO00	0x06000041>,
+			   <IMX8QXP_PCIE_CTRL0_CLKREQ_B_LSIO_GPIO4_IO01	0x06000041>,
+			   <IMX8QXP_PCIE_CTRL0_WAKE_B_LSIO_GPIO4_IO02	0x04000041>;
+	};
+
+	pinctrl_reg_pcie_1v5: regpcie1v5grp {
+		fsl,pins = <IMX8QXP_SAI1_RXC_LSIO_GPIO0_IO30	0x00000021>;
+	};
+
+	pinctrl_reg_pcie_3v3: regpcie3v3grp {
+		fsl,pins = <IMX8QXP_SAI1_RXFS_LSIO_GPIO0_IO31	0x00000021>;
+	};
+
+	pinctrl_sai1: sai1grp {
+		fsl,pins = <IMX8QXP_MCLK_OUT0_ADMA_ACM_MCLK_OUT0	0x06000041>,
+			   <IMX8QXP_FLEXCAN0_RX_ADMA_SAI1_TXC		0x06000041>,
+			   <IMX8QXP_FLEXCAN0_TX_ADMA_SAI1_TXFS		0x06000041>,
+			   <IMX8QXP_FLEXCAN1_RX_ADMA_SAI1_TXD		0x06000041>,
+			   <IMX8QXP_FLEXCAN1_TX_ADMA_SAI1_RXD		0x06000041>;
+	};
+
+	pinctrl_spi1: spi1grp {
+		fsl,pins = <IMX8QXP_SAI0_TXC_ADMA_SPI1_SDI	0x00000041>,
+			   <IMX8QXP_SAI0_TXD_ADMA_SPI1_SDO	0x00000041>,
+			   <IMX8QXP_SAI0_TXFS_ADMA_SPI1_SCK	0x00000041>,
+			   <IMX8QXP_SAI0_RXD_LSIO_GPIO0_IO27	0x00000021>,
+			   <IMX8QXP_SAI1_RXD_LSIO_GPIO0_IO29	0x00000021>;
+	};
+
+	pinctrl_spi2: spi2grp {
+		fsl,pins = <IMX8QXP_SPI2_SCK_ADMA_SPI2_SCK	0x00000041>,
+			   <IMX8QXP_SPI2_SDI_ADMA_SPI2_SDI	0x00000041>,
+			   <IMX8QXP_SPI2_SDO_ADMA_SPI2_SDO	0x00000041>,
+			   <IMX8QXP_SPI2_CS0_LSIO_GPIO1_IO00	0x00000021>;
+	};
+
+	pinctrl_spi3: spi3grp {
+		fsl,pins = <IMX8QXP_SPI3_SCK_ADMA_SPI3_SCK	0x00000041>,
+			   <IMX8QXP_SPI3_SDI_ADMA_SPI3_SDI	0x00000041>,
+			   <IMX8QXP_SPI3_SDO_ADMA_SPI3_SDO	0x00000041>,
+			   <IMX8QXP_SPI3_CS0_LSIO_GPIO0_IO16	0x00000021>,
+			   <IMX8QXP_SPI3_CS1_ADMA_SPI3_CS1	0x00000021>;
+	};
+
+	pinctrl_usbotg1: usbotg1grp {
+		fsl,pins = <IMX8QXP_USB_SS3_TC0_CONN_USB_OTG1_PWR	0x00000021>,
+			   <IMX8QXP_USB_SS3_TC2_CONN_USB_OTG1_OC	0x00000021>;
+	};
+
+	pinctrl_usdhc2_gpio: usdhc2gpiogrp {
+		fsl,pins = <IMX8QXP_USDHC1_WP_LSIO_GPIO4_IO21		0x00000021>,
+			   <IMX8QXP_USDHC1_CD_B_LSIO_GPIO4_IO22		0x00000021>;
+	};
+
+	pinctrl_usdhc2: usdhc2grp {
+		fsl,pins = <IMX8QXP_USDHC1_CLK_CONN_USDHC1_CLK		0x06000041>,
+			   <IMX8QXP_USDHC1_CMD_CONN_USDHC1_CMD		0x00000021>,
+			   <IMX8QXP_USDHC1_DATA0_CONN_USDHC1_DATA0	0x00000021>,
+			   <IMX8QXP_USDHC1_DATA1_CONN_USDHC1_DATA1	0x00000021>,
+			   <IMX8QXP_USDHC1_DATA2_CONN_USDHC1_DATA2	0x00000021>,
+			   <IMX8QXP_USDHC1_DATA3_CONN_USDHC1_DATA3	0x00000021>,
+			   <IMX8QXP_USDHC1_VSELECT_CONN_USDHC1_VSELECT	0x00000021>;
+	};
+
+	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
+		fsl,pins = <IMX8QXP_USDHC1_CLK_CONN_USDHC1_CLK		0x06000040>,
+			   <IMX8QXP_USDHC1_CMD_CONN_USDHC1_CMD		0x00000020>,
+			   <IMX8QXP_USDHC1_DATA0_CONN_USDHC1_DATA0	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA1_CONN_USDHC1_DATA1	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA2_CONN_USDHC1_DATA2	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA3_CONN_USDHC1_DATA3	0x00000020>,
+			   <IMX8QXP_USDHC1_VSELECT_CONN_USDHC1_VSELECT	0x00000020>;
+	};
+
+	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
+		fsl,pins = <IMX8QXP_USDHC1_CLK_CONN_USDHC1_CLK		0x06000040>,
+			   <IMX8QXP_USDHC1_CMD_CONN_USDHC1_CMD		0x00000020>,
+			   <IMX8QXP_USDHC1_DATA0_CONN_USDHC1_DATA0	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA1_CONN_USDHC1_DATA1	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA2_CONN_USDHC1_DATA2	0x00000020>,
+			   <IMX8QXP_USDHC1_DATA3_CONN_USDHC1_DATA3	0x00000020>,
+			   <IMX8QXP_USDHC1_VSELECT_CONN_USDHC1_VSELECT	0x00000020>;
+	};
+};
diff --git a/arch/arm64/boot/dts/freescale/tqma8xx.dtsi b/arch/arm64/boot/dts/freescale/tqma8xx.dtsi
new file mode 100644
index 000000000000..d98469a7c47c
--- /dev/null
+++ b/arch/arm64/boot/dts/freescale/tqma8xx.dtsi
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: (GPL-2.0-or-later OR X11)
+/*
+ * Copyright 2018-2023 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
+ */
+
+/ {
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0 0x40000000>;
+	};
+
+	reg_1v8: regulator-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_1V8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	reg_3v3: regulator-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "V_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/*
+		 * global autoconfigured region for contiguous allocations
+		 * must not exceed memory size and region
+		 */
+		linux,cma {
+			compatible = "shared-dma-pool";
+			reusable;
+			size = <0 0x20000000>;
+			alloc-ranges = <0 0x96000000 0 0x30000000>;
+			linux,cma-default;
+		};
+	};
+};
+
+/* TQMa8Xx only uses industrial grade, reduce trip points accordingly */
+&cpu_alert0 {
+	temperature = <95000>;
+};
+
+&cpu_crit0 {
+	temperature = <100000>;
+};
+/* end of temperature grade adjustments */
+
+&flexspi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_flexspi0>;
+	status = "okay";
+
+	flash0: flash@0 {
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "jedec,spi-nor";
+		spi-max-frequency = <66000000>;
+		spi-tx-bus-width = <1>;
+		spi-rx-bus-width = <4>;
+	};
+};
+
+/* TODO GPU */
+
+&i2c1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clock-frequency = <100000>;
+	pinctrl-names = "default", "gpio";
+	pinctrl-0 = <&pinctrl_lpi2c1>;
+	pinctrl-1 = <&pinctrl_lpi2c1gpio>;
+	scl-gpios = <&lsio_gpio1 27 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	sda-gpios = <&lsio_gpio1 28 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
+	status = "okay";
+
+	se97: temperature-sensor@1b {
+		compatible = "nxp,se97b", "jedec,jc-42.4-temp";
+		reg = <0x1b>;
+	};
+
+	pcf85063: rtc@51 {
+		compatible = "nxp,pcf85063a";
+		reg = <0x51>;
+		quartz-load-femtofarads = <7000>;
+	};
+
+	at24c02: eeprom@53 {
+		compatible = "nxp,se97b", "atmel,24c02";
+		reg = <0x53>;
+		pagesize = <16>;
+		read-only;
+		vcc-supply = <&reg_3v3>;
+	};
+
+	m24c64: eeprom@57 {
+		compatible = "atmel,24c64";
+		reg = <0x57>;
+		pagesize = <32>;
+		vcc-supply = <&reg_3v3>;
+	};
+};
+
+&mu_m0 {
+	status = "okay";
+};
+
+&mu1_m0 {
+	status = "okay";
+};
+
+&thermal_zones {
+	pmic_thermal: pmic-thermal {
+		polling-delay-passive = <250>;
+		polling-delay = <2000>;
+		thermal-sensors = <&tsens IMX_SC_R_PMIC_0>;
+
+		trips {
+			pmic_alert0: trip0 {
+				temperature = <110000>;
+				hysteresis = <2000>;
+				type = "passive";
+			};
+
+			pmic_crit0: trip1 {
+				temperature = <125000>;
+				hysteresis = <2000>;
+				type = "critical";
+			};
+		};
+
+		cooling-maps {
+			map0 {
+				trip = <&pmic_alert0>;
+				cooling-device =
+					<&A35_0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+					<&A35_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+					<&A35_2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+					<&A35_3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+			};
+		};
+	};
+};
+
+&usdhc1 {
+	pinctrl-names = "default", "state_100mhz", "state_200mhz";
+	pinctrl-0 = <&pinctrl_usdhc1>;
+	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
+	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
+	vqmmc-supply = <&reg_1v8>;
+	vmmc-supply = <&reg_3v3>;
+	bus-width = <8>;
+	non-removable;
+	no-sdio;
+	no-sd;
+	status = "okay";
+};
+
+&vpu {
+	compatible = "nxp,imx8qxp-vpu";
+	status = "okay";
+};
+
+&vpu_core0 {
+	memory-region = <&decoder_boot>, <&decoder_rpc>;
+	status = "okay";
+};
+
+&vpu_core1 {
+	memory-region = <&encoder_boot>, <&encoder_rpc>;
+	status = "okay";
+};
+
+&iomuxc {
+	pinctrl_flexspi0: flexspi0grp {
+		fsl,pins = <
+			IMX8QXP_QSPI0A_DATA0_LSIO_QSPI0A_DATA0	0x0600004d
+			IMX8QXP_QSPI0A_DATA1_LSIO_QSPI0A_DATA1	0x0600004d
+			IMX8QXP_QSPI0A_DATA2_LSIO_QSPI0A_DATA2	0x0600004d
+			IMX8QXP_QSPI0A_DATA3_LSIO_QSPI0A_DATA3	0x0600004d
+			IMX8QXP_QSPI0A_DQS_LSIO_QSPI0A_DQS	0x0600004d
+			IMX8QXP_QSPI0A_SS0_B_LSIO_QSPI0A_SS0_B	0x0600004d
+			IMX8QXP_QSPI0A_SCLK_LSIO_QSPI0A_SCLK	0x0600004d
+			IMX8QXP_QSPI0B_SCLK_LSIO_QSPI0B_SCLK	0x0600004d
+			IMX8QXP_QSPI0B_DATA0_LSIO_QSPI0B_DATA0	0x0600004d
+			IMX8QXP_QSPI0B_DATA1_LSIO_QSPI0B_DATA1	0x0600004d
+			IMX8QXP_QSPI0B_DATA2_LSIO_QSPI0B_DATA2	0x0600004d
+			IMX8QXP_QSPI0B_DATA3_LSIO_QSPI0B_DATA3	0x0600004d
+			IMX8QXP_QSPI0B_DQS_LSIO_QSPI0B_DQS	0x0600004d
+			IMX8QXP_QSPI0B_SS0_B_LSIO_QSPI0B_SS0_B	0x0600004d
+			IMX8QXP_QSPI0B_SS1_B_LSIO_QSPI0B_SS1_B	0x0600004d
+		>;
+	};
+
+	pinctrl_lpi2c1: lpi2c1grp {
+		fsl,pins = <
+			IMX8QXP_MIPI_DSI0_GPIO0_00_ADMA_I2C1_SCL	0x06000021
+			IMX8QXP_MIPI_DSI0_GPIO0_01_ADMA_I2C1_SDA	0x06000021
+		>;
+	};
+
+	pinctrl_lpi2c1gpio: lpi2c1gpiogrp {
+		fsl,pins = <
+			IMX8QXP_MIPI_DSI0_GPIO0_00_LSIO_GPIO1_IO27	0x06000021
+			IMX8QXP_MIPI_DSI0_GPIO0_01_LSIO_GPIO1_IO28	0x06000021
+		>;
+	};
+
+	pinctrl_usdhc1: usdhc1grp {
+		fsl,pins = <
+			IMX8QXP_EMMC0_CLK_CONN_EMMC0_CLK	0x06000041
+			IMX8QXP_EMMC0_CMD_CONN_EMMC0_CMD	0x00000021
+			IMX8QXP_EMMC0_DATA0_CONN_EMMC0_DATA0	0x00000021
+			IMX8QXP_EMMC0_DATA1_CONN_EMMC0_DATA1	0x00000021
+			IMX8QXP_EMMC0_DATA2_CONN_EMMC0_DATA2	0x00000021
+			IMX8QXP_EMMC0_DATA3_CONN_EMMC0_DATA3	0x00000021
+			IMX8QXP_EMMC0_DATA4_CONN_EMMC0_DATA4	0x00000021
+			IMX8QXP_EMMC0_DATA5_CONN_EMMC0_DATA5	0x00000021
+			IMX8QXP_EMMC0_DATA6_CONN_EMMC0_DATA6	0x00000021
+			IMX8QXP_EMMC0_DATA7_CONN_EMMC0_DATA7	0x00000021
+			IMX8QXP_EMMC0_STROBE_CONN_EMMC0_STROBE	0x00000041
+		>;
+	};
+
+	pinctrl_usdhc1_100mhz: usdhc1-100mhzgrp {
+		fsl,pins = <
+			IMX8QXP_EMMC0_CLK_CONN_EMMC0_CLK	0x06000040
+			IMX8QXP_EMMC0_CMD_CONN_EMMC0_CMD	0x00000020
+			IMX8QXP_EMMC0_DATA0_CONN_EMMC0_DATA0	0x00000020
+			IMX8QXP_EMMC0_DATA1_CONN_EMMC0_DATA1	0x00000020
+			IMX8QXP_EMMC0_DATA2_CONN_EMMC0_DATA2	0x00000020
+			IMX8QXP_EMMC0_DATA3_CONN_EMMC0_DATA3	0x00000020
+			IMX8QXP_EMMC0_DATA4_CONN_EMMC0_DATA4	0x00000020
+			IMX8QXP_EMMC0_DATA5_CONN_EMMC0_DATA5	0x00000020
+			IMX8QXP_EMMC0_DATA6_CONN_EMMC0_DATA6	0x00000020
+			IMX8QXP_EMMC0_DATA7_CONN_EMMC0_DATA7	0x00000020
+			IMX8QXP_EMMC0_STROBE_CONN_EMMC0_STROBE	0x00000040
+		>;
+	};
+
+	pinctrl_usdhc1_200mhz: usdhc1-200mhzgrp {
+		fsl,pins = <
+			IMX8QXP_EMMC0_CLK_CONN_EMMC0_CLK	0x06000040
+			IMX8QXP_EMMC0_CMD_CONN_EMMC0_CMD	0x00000020
+			IMX8QXP_EMMC0_DATA0_CONN_EMMC0_DATA0	0x00000020
+			IMX8QXP_EMMC0_DATA1_CONN_EMMC0_DATA1	0x00000020
+			IMX8QXP_EMMC0_DATA2_CONN_EMMC0_DATA2	0x00000020
+			IMX8QXP_EMMC0_DATA3_CONN_EMMC0_DATA3	0x00000020
+			IMX8QXP_EMMC0_DATA4_CONN_EMMC0_DATA4	0x00000020
+			IMX8QXP_EMMC0_DATA5_CONN_EMMC0_DATA5	0x00000020
+			IMX8QXP_EMMC0_DATA6_CONN_EMMC0_DATA6	0x00000020
+			IMX8QXP_EMMC0_DATA7_CONN_EMMC0_DATA7	0x00000020
+			IMX8QXP_EMMC0_STROBE_CONN_EMMC0_STROBE	0x00000040
+		>;
+	};
+};
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
index d66d425e45b7..1162978329c1 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex5.dtsi
@@ -202,7 +202,7 @@
 			status = "disabled";
 		};
 
-		i3c0: i3c-master@10da0000 {
+		i3c0: i3c@10da0000 {
 			compatible = "snps,dw-i3c-master-1.00a";
 			reg = <0x10da0000 0x1000>;
 			#address-cells = <3>;
@@ -212,7 +212,7 @@
 			status = "disabled";
 		};
 
-		i3c1: i3c-master@10da1000 {
+		i3c1: i3c@10da1000 {
 			compatible = "snps,dw-i3c-master-1.00a";
 			reg = <0x10da1000 0x1000>;
 			#address-cells = <3>;
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 48ec4ebec0a8..b864ffa74ea8 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -126,7 +126,6 @@
 	amba {
 		#address-cells = <2>;
 		#size-cells = <1>;
-		#interrupt-cells = <3>;
 
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
diff --git a/arch/arm64/boot/dts/lg/lg1313.dtsi b/arch/arm64/boot/dts/lg/lg1313.dtsi
index 3869460aa5dc..996fb39bb50c 100644
--- a/arch/arm64/boot/dts/lg/lg1313.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1313.dtsi
@@ -126,7 +126,6 @@
 	amba {
 		#address-cells = <2>;
 		#size-cells = <1>;
-		#interrupt-cells = <3>;
 
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
index b5e042b8e929..5591939e057b 100644
--- a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
@@ -77,7 +77,6 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
-		dma-ranges;
 
 		internal-regs@7f000000 {
 			#address-cells = <1>;
@@ -204,6 +203,30 @@
 			};
 		};
 
+		mmc_dma: bus@80500000 {
+				compatible = "simple-bus";
+				ranges;
+				#address-cells = <0x2>;
+				#size-cells = <0x2>;
+				reg = <0x0 0x80500000 0x0 0x100000>;
+				dma-ranges = <0x0 0x0 0x2 0x0 0x0 0x80000000>;
+				dma-coherent;
+
+				sdhci: mmc@805c0000 {
+					compatible = "marvell,ac5-sdhci",
+						     "marvell,armada-ap806-sdhci";
+					reg = <0x0 0x805c0000 0x0 0x1000>;
+					interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+					clocks = <&emmc_clock>, <&cnm_clock>;
+					clock-names = "core", "axi";
+					bus-width = <8>;
+					non-removable;
+					mmc-ddr-1_8v;
+					mmc-hs200-1_8v;
+					mmc-hs400-1_8v;
+				};
+		};
+
 		/*
 		 * Dedicated section for devices behind 32bit controllers so we
 		 * can configure specific DMA mapping for them
@@ -335,5 +358,11 @@
 			#clock-cells = <0>;
 			clock-frequency = <400000000>;
 		};
+
+		emmc_clock: emmc-clock {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <400000000>;
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx35xx-rd.dts b/arch/arm64/boot/dts/marvell/ac5-98dx35xx-rd.dts
index f0ebdb84eec9..0c973d7a215a 100644
--- a/arch/arm64/boot/dts/marvell/ac5-98dx35xx-rd.dts
+++ b/arch/arm64/boot/dts/marvell/ac5-98dx35xx-rd.dts
@@ -99,3 +99,7 @@
 		};
 	};
 };
+
+&sdhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index e300145ad1a6..1cc3fa1c354d 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -431,14 +431,14 @@
 			crypto: crypto@90000 {
 				compatible = "inside-secure,safexcel-eip97ies";
 				reg = <0x90000 0x20000>;
-				interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+				interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				interrupt-names = "mem", "ring0", "ring1",
-						  "ring2", "ring3", "eip";
+					     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "ring0", "ring1", "ring2",
+						  "ring3", "eip", "mem";
 				clocks = <&nb_periph_clk 15>;
 			};
 
diff --git a/arch/arm64/boot/dts/marvell/armada-ap807.dtsi b/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
index 4a23f65d475f..a3328d05fc94 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap807.dtsi
@@ -33,3 +33,6 @@
 		     "marvell,armada-ap806-sdhci"; /* Backward compatibility */
 };
 
+&ap_thermal {
+	compatible = "marvell,armada-ap807-thermal";
+};
diff --git a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
index 2c920e22cec2..7ec7c789d87e 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap80x.dtsi
@@ -138,7 +138,6 @@
 
 			odmi: odmi@300000 {
 				compatible = "marvell,odmi-controller";
-				interrupt-controller;
 				msi-controller;
 				marvell,odmi-frames = <4>;
 				reg = <0x300000 0x4000>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
index 4ec1aae0a3a9..7e595ac80043 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
@@ -511,14 +511,14 @@
 		CP11X_LABEL(crypto): crypto@800000 {
 			compatible = "inside-secure,safexcel-eip197b";
 			reg = <0x800000 0x200000>;
-			interrupts = <87 IRQ_TYPE_LEVEL_HIGH>,
-				<88 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <88 IRQ_TYPE_LEVEL_HIGH>,
 				<89 IRQ_TYPE_LEVEL_HIGH>,
 				<90 IRQ_TYPE_LEVEL_HIGH>,
 				<91 IRQ_TYPE_LEVEL_HIGH>,
-				<92 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "mem", "ring0", "ring1",
-				"ring2", "ring3", "eip";
+				<92 IRQ_TYPE_LEVEL_HIGH>,
+				<87 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ring0", "ring1", "ring2", "ring3",
+					  "eip", "mem";
 			clock-names = "core", "reg";
 			clocks = <&CP11X_LABEL(clk) 1 26>,
 				 <&CP11X_LABEL(clk) 1 17>;
diff --git a/arch/arm64/boot/dts/mediatek/Makefile b/arch/arm64/boot/dts/mediatek/Makefile
index 1e6f91731e92..37b4ca3a87c9 100644
--- a/arch/arm64/boot/dts/mediatek/Makefile
+++ b/arch/arm64/boot/dts/mediatek/Makefile
@@ -8,6 +8,8 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt6797-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt6797-x20-dev.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7622-rfb1.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7622-bananapi-bpi-r64.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt7981b-xiaomi-ax3000t.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-acelink-ew-7886cax.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-emmc.dtbo
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-nand.dtbo
@@ -15,6 +17,7 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-nor.dtbo
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-bananapi-bpi-r3-sd.dtbo
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986a-rfb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt7986b-rfb.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt7988a-bananapi-bpi-r4.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8167-pumpkin.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-elm.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-elm-hana.dtb
@@ -49,6 +52,16 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-kodama-sku32.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku0.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-kukui-krane-sku176.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8183-pumpkin.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393216.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393217.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-magneton-sku393218.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-rusty-sku196608.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-steelix-sku131072.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-steelix-sku131073.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-tentacool-sku327681.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-tentacool-sku327683.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-tentacruel-sku262144.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-corsola-tentacruel-sku262148.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8186-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8188-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8192-asurada-hayato-r1.dtb
@@ -63,4 +76,5 @@ dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-demo.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8195-evb.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8365-evk.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-genio-1200-evk.dtb
+dtb-$(CONFIG_ARCH_MEDIATEK) += mt8395-radxa-nio-12l.dtb
 dtb-$(CONFIG_ARCH_MEDIATEK) += mt8516-pumpkin.dtb
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
index fffdb7bbf889..0c38f7b51763 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
@@ -43,12 +43,12 @@
 
 	extcon_usb: extcon_iddig {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pio 12 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pio 12 GPIO_ACTIVE_HIGH>;
 	};
 
 	extcon_usb1: extcon_iddig1 {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pio 14 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pio 14 GPIO_ACTIVE_HIGH>;
 	};
 
 	usb_p0_vbus: regulator-usb-p0-vbus {
diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
index ed1a9d319415..6d218caa198c 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
@@ -261,7 +261,7 @@
 		#clock-cells = <1>;
 	};
 
-	syscfg_pctl_a: syscfg_pctl_a@10005000 {
+	syscfg_pctl_a: syscon@10005000 {
 		compatible = "mediatek,mt2712-pctl-a-syscfg", "syscon";
 		reg = <0 0x10005000 0 0x1000>;
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt6797.dtsi b/arch/arm64/boot/dts/mediatek/mt6797.dtsi
index c3677d77e0a4..0e9d11b4585b 100644
--- a/arch/arm64/boot/dts/mediatek/mt6797.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt6797.dtsi
@@ -117,7 +117,7 @@
 		#clock-cells = <1>;
 	};
 
-	infrasys: infracfg_ao@10001000 {
+	infrasys: syscon@10001000 {
 		compatible = "mediatek,mt6797-infracfg", "syscon";
 		reg = <0 0x10001000 0 0x1000>;
 		#clock-cells = <1>;
@@ -452,19 +452,19 @@
 		#clock-cells = <1>;
 	};
 
-	imgsys: imgsys_config@15000000  {
+	imgsys: syscon@15000000  {
 		compatible = "mediatek,mt6797-imgsys", "syscon";
 		reg = <0 0x15000000 0 0x1000>;
 		#clock-cells = <1>;
 	};
 
-	vdecsys: vdec_gcon@16000000 {
+	vdecsys: syscon@16000000 {
 		compatible = "mediatek,mt6797-vdecsys", "syscon";
 		reg = <0 0x16000000 0 0x10000>;
 		#clock-cells = <1>;
 	};
 
-	vencsys: venc_gcon@17000000 {
+	vencsys: syscon@17000000 {
 		compatible = "mediatek,mt6797-vencsys", "syscon";
 		reg = <0 0x17000000 0 0x1000>;
 		#clock-cells = <1>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
index a1f42048dcc7..224bb289660c 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
@@ -75,6 +75,7 @@
 
 	memory@40000000 {
 		reg = <0 0x40000000 0 0x40000000>;
+		device_type = "memory";
 	};
 
 	reg_1p8v: regulator-1p8v {
@@ -185,6 +186,18 @@
 					label = "lan3";
 				};
 
+				port@5 {
+					reg = <5>;
+					ethernet = <&gmac1>;
+					phy-mode = "rgmii";
+
+					fixed-link {
+						speed = <1000>;
+						full-duplex;
+						pause;
+					};
+				};
+
 				port@6 {
 					reg = <6>;
 					label = "cpu";
diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
index 2dc1bdc74e21..41629769bdc8 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
@@ -57,6 +57,7 @@
 
 	memory@40000000 {
 		reg = <0 0x40000000 0 0x20000000>;
+		device_type = "memory";
 	};
 
 	reg_1p8v: regulator-1p8v {
@@ -117,6 +118,18 @@
 		};
 	};
 
+	gmac1: mac@1 {
+		compatible = "mediatek,eth-mac";
+		reg = <1>;
+		phy-mode = "rgmii";
+
+		fixed-link {
+			speed = <1000>;
+			full-duplex;
+			pause;
+		};
+	};
+
 	mdio-bus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -155,6 +168,18 @@
 					label = "wan";
 				};
 
+				port@5 {
+					reg = <5>;
+					ethernet = <&gmac1>;
+					phy-mode = "rgmii";
+
+					fixed-link {
+						speed = <1000>;
+						full-duplex;
+						pause;
+					};
+				};
+
 				port@6 {
 					reg = <6>;
 					label = "cpu";
diff --git a/arch/arm64/boot/dts/mediatek/mt7981b-xiaomi-ax3000t.dts b/arch/arm64/boot/dts/mediatek/mt7981b-xiaomi-ax3000t.dts
new file mode 100644
index 000000000000..a314c3e05e50
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt7981b-xiaomi-ax3000t.dts
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+
+/dts-v1/;
+
+#include "mt7981b.dtsi"
+
+/ {
+	compatible = "xiaomi,ax3000t", "mediatek,mt7981b";
+	model = "Xiaomi AX3000T";
+
+	memory@40000000 {
+		reg = <0 0x40000000 0 0x10000000>;
+		device_type = "memory";
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt7981b.dtsi b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi
new file mode 100644
index 000000000000..4feff3d1c5f4
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+
+#include <dt-bindings/clock/mediatek,mt7981-clk.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "mediatek,mt7981b";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a53";
+			reg = <0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a53";
+			reg = <0x1>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+	};
+
+	oscillator-40m {
+		compatible = "fixed-clock";
+		clock-frequency = <40000000>;
+		clock-output-names = "clkxtal";
+		#clock-cells = <0>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		method = "smc";
+	};
+
+	soc {
+		compatible = "simple-bus";
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		gic: interrupt-controller@c000000 {
+			compatible = "arm,gic-v3";
+			reg = <0 0x0c000000 0 0x40000>,  /* GICD */
+			      <0 0x0c080000 0 0x200000>; /* GICR */
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+		};
+
+		infracfg: clock-controller@10001000 {
+			compatible = "mediatek,mt7981-infracfg", "syscon";
+			reg = <0 0x10001000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clock-controller@1001b000 {
+			compatible = "mediatek,mt7981-topckgen", "syscon";
+			reg = <0 0x1001b000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clock-controller@1001e000 {
+			compatible = "mediatek,mt7981-apmixedsys";
+			reg = <0 0x1001e000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		pwm@10048000 {
+			compatible = "mediatek,mt7981-pwm";
+			reg = <0 0x10048000 0 0x1000>;
+			clocks = <&infracfg CLK_INFRA_PWM_STA>,
+				<&infracfg CLK_INFRA_PWM_HCK>,
+				<&infracfg CLK_INFRA_PWM1_CK>,
+				<&infracfg CLK_INFRA_PWM2_CK>,
+				<&infracfg CLK_INFRA_PWM3_CK>;
+			clock-names = "top", "main", "pwm1", "pwm2", "pwm3";
+			#pwm-cells = <2>;
+		};
+
+		clock-controller@15000000 {
+			compatible = "mediatek,mt7981-ethsys", "syscon";
+			reg = <0 0x15000000 0 0x1000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-acelink-ew-7886cax.dts b/arch/arm64/boot/dts/mediatek/mt7986a-acelink-ew-7886cax.dts
new file mode 100644
index 000000000000..08b3b0827436
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-acelink-ew-7886cax.dts
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+
+/dts-v1/;
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+
+#include "mt7986a.dtsi"
+
+/ {
+	compatible = "acelink,ew-7886cax", "mediatek,mt7986a";
+	model = "Acelink EW-7886CAX";
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@40000000 {
+		reg = <0 0x40000000 0 0x20000000>;
+		device_type = "memory";
+	};
+
+	keys {
+		compatible = "gpio-keys";
+
+		key-restart {
+			label = "Reset";
+			gpios = <&pio 7 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_RESTART>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_RED>;
+			gpios = <&pio 18 GPIO_ACTIVE_HIGH>;
+		};
+
+		led-1 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&pio 19 GPIO_ACTIVE_HIGH>;
+		};
+
+		led-2 {
+			function = LED_FUNCTION_STATUS;
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&pio 20 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&crypto {
+	status = "okay";
+};
+
+&eth {
+	status = "okay";
+
+	mac@1 {
+		compatible = "mediatek,eth-mac";
+		reg = <1>;
+		phy-mode = "2500base-x";
+		phy-handle = <&phy6>;
+		nvmem-cells = <&macaddr>;
+		nvmem-cell-names = "mac-address";
+	};
+
+	mdio-bus {
+		reset-gpios = <&pio 6 GPIO_ACTIVE_LOW>;
+		reset-delay-us = <50000>;
+		reset-post-delay-us = <20000>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy6: phy@6 {
+			compatible = "ethernet-phy-ieee802.3-c45";
+			reg = <6>;
+		};
+	};
+};
+
+&pcie_phy {
+	status = "okay";
+};
+
+&spi0 {
+	status = "okay";
+
+	flash@0 {
+		compatible = "spi-nand";
+		reg = <0>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		spi-max-frequency = <52000000>;
+		spi-rx-bus-width = <4>;
+		spi-tx-bus-width = <4>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				reg = <0x0 0x100000>;
+				label = "bootloader";
+				read-only;
+			};
+
+			partition@100000 {
+				reg = <0x100000 0x80000>;
+				label = "u-boot-env";
+			};
+
+			partition@180000 {
+				compatible = "nvmem-cells";
+				reg = <0x180000 0x200000>;
+				label = "factory";
+				read-only;
+
+				nvmem-layout {
+					compatible = "fixed-layout";
+					#address-cells = <1>;
+					#size-cells = <1>;
+
+					eeprom: eeprom@0 {
+						reg = <0x0 0x1000>;
+					};
+
+					macaddr: macaddr@4 {
+						reg = <0x4 0x6>;
+					};
+				};
+			};
+
+			partition@380000 {
+				reg = <0x380000 0x200000>;
+				label = "fip";
+			};
+
+			partition@580000 {
+				reg = <0x580000 0x4000000>;
+				label = "ubi";
+			};
+		};
+	};
+};
+
+&trng {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&watchdog {
+	status = "okay";
+};
+
+&wifi {
+	nvmem-cells = <&eeprom>;
+	nvmem-cell-names = "eeprom";
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nand.dtso b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nand.dtso
index 543c13385d6e..7b97c5c91bd0 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nand.dtso
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nand.dtso
@@ -15,7 +15,7 @@
 		__overlay__ {
 			#address-cells = <1>;
 			#size-cells = <0>;
-			spi_nand: spi_nand@0 {
+			spi_nand: flash@0 {
 				compatible = "spi-nand";
 				reg = <0>;
 				spi-max-frequency = <10000000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
index d06d4af43cbf..e04b1c0c0ebb 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
@@ -43,7 +43,7 @@
 		#cooling-cells = <2>;
 		/* cooling level (0, 1, 2) - pwm inverted */
 		cooling-levels = <255 96 0>;
-		pwms = <&pwm 0 10000 0>;
+		pwms = <&pwm 0 10000>;
 		status = "okay";
 	};
 
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts
index 3ef371ca254e..5d8e3d3f6c20 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts
@@ -65,6 +65,18 @@
 		};
 	};
 
+	gmac1: mac@1 {
+		compatible = "mediatek,eth-mac";
+		reg = <1>;
+		phy-mode = "rgmii";
+
+		fixed-link {
+			speed = <1000>;
+			full-duplex;
+			pause;
+		};
+	};
+
 	mdio: mdio-bus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -237,12 +249,13 @@
 	pinctrl-0 = <&spi_flash_pins>;
 	cs-gpios = <0>, <0>;
 	status = "okay";
-	spi_nand: spi_nand@0 {
+
+	spi_nand: flash@0 {
 		compatible = "spi-nand";
 		reg = <0>;
 		spi-max-frequency = <10000000>;
-		spi-tx-buswidth = <4>;
-		spi-rx-buswidth = <4>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 	};
 };
 
@@ -287,6 +300,18 @@
 			label = "lan4";
 		};
 
+		port@5 {
+			reg = <5>;
+			ethernet = <&gmac1>;
+			phy-mode = "rgmii";
+
+			fixed-link {
+				speed = <1000>;
+				full-duplex;
+				pause;
+			};
+		};
+
 		port@6 {
 			reg = <6>;
 			label = "cpu";
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
index fc751e049953..b3f416b9a7a4 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
@@ -16,49 +16,49 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
-	clk40m: oscillator-40m {
-		compatible = "fixed-clock";
-		clock-frequency = <40000000>;
-		#clock-cells = <0>;
-		clock-output-names = "clkxtal";
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
 		cpu0: cpu@0 {
-			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			enable-method = "psci";
 			reg = <0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
 			#cooling-cells = <2>;
 		};
 
 		cpu1: cpu@1 {
-			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			enable-method = "psci";
 			reg = <0x1>;
+			device_type = "cpu";
+			enable-method = "psci";
 			#cooling-cells = <2>;
 		};
 
 		cpu2: cpu@2 {
-			device_type = "cpu";
 			compatible = "arm,cortex-a53";
-			enable-method = "psci";
 			reg = <0x2>;
+			device_type = "cpu";
+			enable-method = "psci";
 			#cooling-cells = <2>;
 		};
 
 		cpu3: cpu@3 {
-			device_type = "cpu";
-			enable-method = "psci";
 			compatible = "arm,cortex-a53";
 			reg = <0x3>;
+			device_type = "cpu";
+			enable-method = "psci";
 			#cooling-cells = <2>;
 		};
 	};
 
+	clk40m: oscillator-40m {
+		compatible = "fixed-clock";
+		clock-frequency = <40000000>;
+		#clock-cells = <0>;
+		clock-output-names = "clkxtal";
+	};
+
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
@@ -121,38 +121,30 @@
 
 	};
 
-	timer {
-		compatible = "arm,armv8-timer";
-		interrupt-parent = <&gic>;
-		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
-			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
-			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
-			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
-	};
-
 	soc {
-		#address-cells = <2>;
-		#size-cells = <2>;
 		compatible = "simple-bus";
 		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
 
 		gic: interrupt-controller@c000000 {
 			compatible = "arm,gic-v3";
-			#interrupt-cells = <3>;
-			interrupt-parent = <&gic>;
-			interrupt-controller;
 			reg = <0 0x0c000000 0 0x10000>,  /* GICD */
 			      <0 0x0c080000 0 0x80000>,  /* GICR */
 			      <0 0x0c400000 0 0x2000>,   /* GICC */
 			      <0 0x0c410000 0 0x1000>,   /* GICH */
 			      <0 0x0c420000 0 0x2000>;   /* GICV */
+			interrupt-parent = <&gic>;
 			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
 		};
 
 		infracfg: infracfg@10001000 {
 			compatible = "mediatek,mt7986-infracfg", "syscon";
 			reg = <0 0x10001000 0 0x1000>;
 			#clock-cells = <1>;
+			#reset-cells = <1>;
 		};
 
 		wed_pcie: wed-pcie@10003000 {
@@ -202,6 +194,19 @@
 			#interrupt-cells = <2>;
 		};
 
+		pwm: pwm@10048000 {
+			compatible = "mediatek,mt7986-pwm";
+			reg = <0 0x10048000 0 0x1000>;
+			#pwm-cells = <2>;
+			interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&topckgen CLK_TOP_PWM_SEL>,
+				 <&infracfg CLK_INFRA_PWM_STA>,
+				 <&infracfg CLK_INFRA_PWM1_CK>,
+				 <&infracfg CLK_INFRA_PWM2_CK>;
+			clock-names = "top", "main", "pwm1", "pwm2";
+			status = "disabled";
+		};
+
 		sgmiisys0: syscon@10060000 {
 			compatible = "mediatek,mt7986-sgmiisys_0",
 				     "syscon";
@@ -234,26 +239,11 @@
 				     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "ring0", "ring1", "ring2", "ring3";
 			clocks = <&infracfg CLK_INFRA_EIP97_CK>;
-			clock-names = "infra_eip97_ck";
 			assigned-clocks = <&topckgen CLK_TOP_EIP_B_SEL>;
 			assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>;
 			status = "disabled";
 		};
 
-		pwm: pwm@10048000 {
-			compatible = "mediatek,mt7986-pwm";
-			reg = <0 0x10048000 0 0x1000>;
-			#clock-cells = <1>;
-			#pwm-cells = <2>;
-			interrupts = <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&topckgen CLK_TOP_PWM_SEL>,
-				 <&infracfg CLK_INFRA_PWM_STA>,
-				 <&infracfg CLK_INFRA_PWM1_CK>,
-				 <&infracfg CLK_INFRA_PWM2_CK>;
-			clock-names = "top", "main", "pwm1", "pwm2";
-			status = "disabled";
-		};
-
 		uart0: serial@11002000 {
 			compatible = "mediatek,mt7986-uart",
 				     "mediatek,mt6577-uart";
@@ -311,9 +301,9 @@
 
 		spi0: spi@1100a000 {
 			compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm";
+			reg = <0 0x1100a000 0 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			reg = <0 0x1100a000 0 0x100>;
 			interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&topckgen CLK_TOP_MPLL_D2>,
 				 <&topckgen CLK_TOP_SPI_SEL>,
@@ -325,9 +315,9 @@
 
 		spi1: spi@1100b000 {
 			compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm";
+			reg = <0 0x1100b000 0 0x100>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			reg = <0 0x1100b000 0 0x100>;
 			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&topckgen CLK_TOP_MPLL_D2>,
 				 <&topckgen CLK_TOP_SPIM_MST_SEL>,
@@ -337,6 +327,21 @@
 			status = "disabled";
 		};
 
+		thermal: thermal@1100c800 {
+			compatible = "mediatek,mt7986-thermal";
+			reg = <0 0x1100c800 0 0x800>;
+			interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&infracfg CLK_INFRA_THERM_CK>,
+				 <&infracfg CLK_INFRA_ADC_26M_CK>,
+				 <&infracfg CLK_INFRA_ADC_FRC_CK>;
+			clock-names = "therm", "auxadc", "adc_32k";
+			nvmem-cells = <&thermal_calibration>;
+			nvmem-cell-names = "calibration-data";
+			#thermal-sensor-cells = <1>;
+			mediatek,auxadc = <&auxadc>;
+			mediatek,apmixedsys = <&apmixedsys>;
+		};
+
 		auxadc: adc@1100d000 {
 			compatible = "mediatek,mt7986-auxadc";
 			reg = <0 0x1100d000 0 0x1000>;
@@ -388,39 +393,23 @@
 			status = "disabled";
 		};
 
-		thermal: thermal@1100c800 {
-			#thermal-sensor-cells = <1>;
-			compatible = "mediatek,mt7986-thermal";
-			reg = <0 0x1100c800 0 0x800>;
-			interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&infracfg CLK_INFRA_THERM_CK>,
-				 <&infracfg CLK_INFRA_ADC_26M_CK>,
-				 <&infracfg CLK_INFRA_ADC_FRC_CK>;
-			clock-names = "therm", "auxadc", "adc_32k";
-			mediatek,auxadc = <&auxadc>;
-			mediatek,apmixedsys = <&apmixedsys>;
-			nvmem-cells = <&thermal_calibration>;
-			nvmem-cell-names = "calibration-data";
-		};
-
 		pcie: pcie@11280000 {
 			compatible = "mediatek,mt7986-pcie",
 				     "mediatek,mt8192-pcie";
+			reg = <0x00 0x11280000 0x00 0x4000>;
+			reg-names = "pcie-mac";
+			ranges = <0x82000000 0x00 0x20000000 0x00
+				  0x20000000 0x00 0x10000000>;
 			device_type = "pci";
 			#address-cells = <3>;
 			#size-cells = <2>;
-			reg = <0x00 0x11280000 0x00 0x4000>;
-			reg-names = "pcie-mac";
 			interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 			bus-range = <0x00 0xff>;
-			ranges = <0x82000000 0x00 0x20000000 0x00
-				  0x20000000 0x00 0x10000000>;
 			clocks = <&infracfg CLK_INFRA_IPCIE_PIPE_CK>,
 				 <&infracfg CLK_INFRA_IPCIE_CK>,
 				 <&infracfg CLK_INFRA_IPCIER_CK>,
 				 <&infracfg CLK_INFRA_IPCIEB_CK>;
 			clock-names = "pl_250m", "tl_26m", "peri_26m", "top_133m";
-			status = "disabled";
 
 			phys = <&pcie_port PHY_TYPE_PCIE>;
 			phy-names = "pcie-phy";
@@ -431,6 +420,8 @@
 					<0 0 0 2 &pcie_intc 1>,
 					<0 0 0 3 &pcie_intc 2>,
 					<0 0 0 4 &pcie_intc 3>;
+			status = "disabled";
+
 			pcie_intc: interrupt-controller {
 				#address-cells = <0>;
 				#interrupt-cells = <1>;
@@ -441,9 +432,9 @@
 		pcie_phy: t-phy {
 			compatible = "mediatek,mt7986-tphy",
 				     "mediatek,generic-tphy-v2";
+			ranges;
 			#address-cells = <2>;
 			#size-cells = <2>;
-			ranges;
 			status = "disabled";
 
 			pcie_port: pcie-phy@11c00000 {
@@ -468,9 +459,9 @@
 		usb_phy: t-phy@11e10000 {
 			compatible = "mediatek,mt7986-tphy",
 				     "mediatek,generic-tphy-v2";
+			ranges = <0 0 0x11e10000 0x1700>;
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0 0 0x11e10000 0x1700>;
 			status = "disabled";
 
 			u2port0: usb-phy@0 {
@@ -498,11 +489,11 @@
 		};
 
 		ethsys: syscon@15000000 {
-			 #address-cells = <1>;
-			 #size-cells = <1>;
 			 compatible = "mediatek,mt7986-ethsys",
 				      "syscon";
 			 reg = <0 0x15000000 0 0x1000>;
+			 #address-cells = <1>;
+			 #size-cells = <1>;
 			 #clock-cells = <1>;
 			 #reset-cells = <1>;
 		};
@@ -533,20 +524,6 @@
 			mediatek,wo-ccif = <&wo_ccif1>;
 		};
 
-		wo_ccif0: syscon@151a5000 {
-			compatible = "mediatek,mt7986-wo-ccif", "syscon";
-			reg = <0 0x151a5000 0 0x1000>;
-			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
-		wo_ccif1: syscon@151ad000 {
-			compatible = "mediatek,mt7986-wo-ccif", "syscon";
-			reg = <0 0x151ad000 0 0x1000>;
-			interrupt-parent = <&gic>;
-			interrupts = <GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH>;
-		};
-
 		eth: ethernet@15100000 {
 			compatible = "mediatek,mt7986-eth";
 			reg = <0 0x15100000 0 0x80000>;
@@ -579,26 +556,40 @@
 					  <&topckgen CLK_TOP_SGM_325M_SEL>;
 			assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>,
 						 <&apmixedsys CLK_APMIXED_SGMPLL>;
+			#reset-cells = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 			mediatek,ethsys = <&ethsys>;
 			mediatek,sgmiisys = <&sgmiisys0>, <&sgmiisys1>;
 			mediatek,wed-pcie = <&wed_pcie>;
 			mediatek,wed = <&wed0>, <&wed1>;
-			#reset-cells = <1>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 		};
 
+		wo_ccif0: syscon@151a5000 {
+			compatible = "mediatek,mt7986-wo-ccif", "syscon";
+			reg = <0 0x151a5000 0 0x1000>;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		wo_ccif1: syscon@151ad000 {
+			compatible = "mediatek,mt7986-wo-ccif", "syscon";
+			reg = <0 0x151ad000 0 0x1000>;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
 		wifi: wifi@18000000 {
 			compatible = "mediatek,mt7986-wmac";
+			reg = <0 0x18000000 0 0x1000000>,
+			      <0 0x10003000 0 0x1000>,
+			      <0 0x11d10000 0 0x1000>;
 			resets = <&watchdog MT7986_TOPRGU_CONSYS_SW_RST>;
 			reset-names = "consys";
 			clocks = <&topckgen CLK_TOP_CONN_MCUSYS_SEL>,
 				 <&topckgen CLK_TOP_AP2CNN_HOST_SEL>;
 			clock-names = "mcu", "ap2conn";
-			reg = <0 0x18000000 0 0x1000000>,
-			      <0 0x10003000 0 0x1000>,
-			      <0 0x11d10000 0 0x1000>;
 			interrupts = <GIC_SPI 213 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 214 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 215 IRQ_TYPE_LEVEL_HIGH>,
@@ -646,4 +637,13 @@
 			};
 		};
 	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts
index dde190442e38..58f77d932429 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts
@@ -45,6 +45,18 @@
 		};
 	};
 
+	gmac1: mac@1 {
+		compatible = "mediatek,eth-mac";
+		reg = <1>;
+		phy-mode = "rgmii";
+
+		fixed-link {
+			speed = <1000>;
+			full-duplex;
+			pause;
+		};
+	};
+
 	mdio: mdio-bus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -83,6 +95,18 @@
 					label = "lan4";
 				};
 
+				port@5 {
+					reg = <5>;
+					ethernet = <&gmac1>;
+					phy-mode = "rgmii";
+
+					fixed-link {
+						speed = <1000>;
+						full-duplex;
+						pause;
+					};
+				};
+
 				port@6 {
 					reg = <6>;
 					label = "cpu";
@@ -152,12 +176,13 @@
 	pinctrl-0 = <&spi_flash_pins>;
 	cs-gpios = <0>, <0>;
 	status = "okay";
-	spi_nand: spi_nand@0 {
+
+	spi_nand: flash@0 {
 		compatible = "spi-nand";
 		reg = <0>;
 		spi-max-frequency = <10000000>;
-		spi-tx-buswidth = <4>;
-		spi-rx-buswidth = <4>;
+		spi-tx-bus-width = <4>;
+		spi-rx-bus-width = <4>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts
new file mode 100644
index 000000000000..efc4ad0b08b8
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt7988a-bananapi-bpi-r4.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+
+/dts-v1/;
+
+#include "mt7988a.dtsi"
+
+/ {
+	compatible = "bananapi,bpi-r4", "mediatek,mt7988a";
+	model = "Banana Pi BPI-R4";
+	chassis-type = "embedded";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt7988a.dtsi b/arch/arm64/boot/dts/mediatek/mt7988a.dtsi
new file mode 100644
index 000000000000..bba97de4fb44
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt7988a.dtsi
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	compatible = "mediatek,mt7988a";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a73";
+			reg = <0x0>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a73";
+			reg = <0x1>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		cpu@2 {
+			compatible = "arm,cortex-a73";
+			reg = <0x2>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+
+		cpu@3 {
+			compatible = "arm,cortex-a73";
+			reg = <0x3>;
+			device_type = "cpu";
+			enable-method = "psci";
+		};
+	};
+
+	oscillator-40m {
+		compatible = "fixed-clock";
+		clock-frequency = <40000000>;
+		#clock-cells = <0>;
+		clock-output-names = "clkxtal";
+	};
+
+	pmu {
+		compatible = "arm,cortex-a73-pmu";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	psci {
+		compatible = "arm,psci-0.2";
+		method = "smc";
+	};
+
+	soc {
+		compatible = "simple-bus";
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		gic: interrupt-controller@c000000 {
+			compatible = "arm,gic-v3";
+			reg = <0 0x0c000000 0 0x40000>,  /* GICD */
+			      <0 0x0c080000 0 0x200000>, /* GICR */
+			      <0 0x0c400000 0 0x2000>,   /* GICC */
+			      <0 0x0c410000 0 0x1000>,   /* GICH */
+			      <0 0x0c420000 0 0x2000>;   /* GICV */
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+		};
+
+		clock-controller@10001000 {
+			compatible = "mediatek,mt7988-infracfg", "syscon";
+			reg = <0 0x10001000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clock-controller@1001b000 {
+			compatible = "mediatek,mt7988-topckgen", "syscon";
+			reg = <0 0x1001b000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		watchdog: watchdog@1001c000 {
+			compatible = "mediatek,mt7988-wdt";
+			reg = <0 0x1001c000 0 0x1000>;
+			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+			#reset-cells = <1>;
+		};
+
+		clock-controller@1001e000 {
+			compatible = "mediatek,mt7988-apmixedsys";
+			reg = <0 0x1001e000 0 0x1000>;
+			#clock-cells = <1>;
+		};
+
+		clock-controller@11f40000 {
+			compatible = "mediatek,mt7988-xfi-pll";
+			reg = <0 0x11f40000 0 0x1000>;
+			resets = <&watchdog 16>;
+			#clock-cells = <1>;
+		};
+
+		clock-controller@15000000 {
+			compatible = "mediatek,mt7988-ethsys", "syscon";
+			reg = <0 0x15000000 0 0x1000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
+		clock-controller@15031000 {
+			compatible = "mediatek,mt7988-ethwarp";
+			reg = <0 0x15031000 0 0x1000>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+			     <GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm-hana-rev7.dts b/arch/arm64/boot/dts/mediatek/mt8173-elm-hana-rev7.dts
index 256f245ac01d..1c9fc791bdfc 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-elm-hana-rev7.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-elm-hana-rev7.dts
@@ -14,7 +14,7 @@
 
 &cpu_thermal {
 	trips {
-		cpu_crit: cpu_crit0 {
+		cpu_crit: cpu-crit0 {
 			temperature = <100000>;
 			type = "critical";
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
index 8d614ac2c58e..6d962d437e02 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173-elm.dtsi
@@ -1135,7 +1135,7 @@
 			compatible = "mediatek,mt6397-rtc";
 		};
 
-		syscfg_pctl_pmic: syscfg_pctl_pmic@c000 {
+		syscfg_pctl_pmic: syscon@c000 {
 			compatible = "mediatek,mt6397-pctl-pmic-syscfg",
 				     "syscon";
 			reg = <0 0x0000c000 0 0x0108>;
@@ -1155,6 +1155,7 @@
 		spi-max-frequency = <12000000>;
 		interrupts-extended = <&pio 0 IRQ_TYPE_LEVEL_LOW>;
 		google,cros-ec-spi-msg-delay = <500>;
+		wakeup-source;
 
 		i2c_tunnel: i2c-tunnel0 {
 			compatible = "google,cros-ec-i2c-tunnel";
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 0e5c628d1ec3..3fab21f59d18 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -41,7 +41,7 @@
 
 	extcon_usb: extcon_iddig {
 		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&pio 16 GPIO_ACTIVE_HIGH>;
+		id-gpios = <&pio 16 GPIO_ACTIVE_HIGH>;
 	};
 
 	usb_p1_vbus: regulator-usb-p1 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index cac4cd0a0320..3458be7f7f61 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -222,14 +222,14 @@
 		};
 	};
 
-	pmu_a53 {
+	pmu-a53 {
 		compatible = "arm,cortex-a53-pmu";
 		interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_LOW>,
 			     <GIC_SPI 9 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-affinity = <&cpu0>, <&cpu1>;
 	};
 
-	pmu_a72 {
+	pmu-a72 {
 		compatible = "arm,cortex-a72-pmu";
 		interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_LOW>,
 			     <GIC_SPI 13 IRQ_TYPE_LEVEL_LOW>;
@@ -286,7 +286,7 @@
 					type = "passive";
 				};
 
-				cpu_crit: cpu_crit0 {
+				cpu_crit: cpu-crit0 {
 					temperature = <115000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -318,7 +318,7 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
-		vpu_dma_reserved: vpu_dma_mem_region@b7000000 {
+		vpu_dma_reserved: vpu-dma-mem@b7000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0xb7000000 0 0x500000>;
 			alignment = <0x1000>;
@@ -366,7 +366,7 @@
 			#reset-cells = <1>;
 		};
 
-		syscfg_pctl_a: syscfg_pctl_a@10005000 {
+		syscfg_pctl_a: syscon@10005000 {
 			compatible = "mediatek,mt8173-pctl-a-syscfg", "syscon";
 			reg = <0 0x10005000 0 0x1000>;
 		};
@@ -590,6 +590,15 @@
 			reg = <0 0x10206000 0 0x1000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			socinfo-data1@40 {
+				reg = <0x040 0x4>;
+			};
+
+			socinfo-data2@44 {
+				reg = <0x044 0x4>;
+			};
+
 			thermal_calibration: calib@528 {
 				reg = <0x528 0xc>;
 			};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
index b6a9830af269..bfb9e42c8aca 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi
@@ -360,6 +360,10 @@
 };
 
 &cros_ec {
+	cbas {
+		compatible = "google,cros-cbas";
+	};
+
 	keyboard-controller {
 		compatible = "google,cros-ec-keyb-switches";
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
index 306c95166f3f..5c1bf6a1e475 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi
@@ -339,6 +339,10 @@
 };
 
 &cros_ec {
+	cbas {
+		compatible = "google,cros-cbas";
+	};
+
 	keyboard-controller {
 		compatible = "google,cros-ec-keyb-switches";
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
index 382e4c6d7191..0f5fa893a774 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi
@@ -343,6 +343,10 @@
 };
 
 &cros_ec {
+	cbas {
+		compatible = "google,cros-cbas";
+	};
+
 	keyboard-controller {
 		compatible = "google,cros-ec-keyb-switches";
 	};
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index 1b3396b1cee3..6bd7424ef66c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -924,6 +924,7 @@
 		interrupts-extended = <&pio 151 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&ec_ap_int_odl>;
+		wakeup-source;
 
 		i2c_tunnel: i2c-tunnel {
 			compatible = "google,cros-ec-i2c-tunnel";
@@ -937,10 +938,6 @@
 			google,usb-port-id = <0>;
 		};
 
-		cbas {
-			compatible = "google,cros-cbas";
-		};
-
 		typec {
 			compatible = "google,cros-ec-typec";
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
index 76449b4cf236..333c516af490 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts
@@ -33,7 +33,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		scp_mem_reserved: scp_mem_region@50000000 {
+		scp_mem_reserved: scp-mem@50000000 {
 			compatible = "shared-dma-pool";
 			reg = <0 0x50000000 0 0x2900000>;
 			no-map;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
index 920ee415ef5f..93dfbf130231 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
@@ -1585,6 +1585,15 @@
 			reg = <0 0x11f10000 0 0x1000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			socinfo-data1@4c {
+				reg = <0x04c 0x4>;
+			};
+
+			socinfo-data2@60 {
+				reg = <0x060 0x4>;
+			};
+
 			thermal_calibration: calib@180 {
 				reg = <0x180 0xc>;
 			};
@@ -1955,7 +1964,7 @@
 			power-domains = <&spm MT8183_POWER_DOMAIN_VENC>;
 		};
 
-		venc_jpg: venc_jpg@17030000 {
+		venc_jpg: jpeg-encoder@17030000 {
 			compatible = "mediatek,mt8183-jpgenc", "mediatek,mtk-jpgenc";
 			reg = <0 0x17030000 0 0x1000>;
 			interrupts = <GIC_SPI 249 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-krabby.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola-krabby.dtsi
new file mode 100644
index 000000000000..7c971198fa95
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-krabby.dtsi
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	aliases {
+		i2c4 = &i2c4;
+	};
+};
+
+&dsi_out {
+	remote-endpoint = <&ps8640_in>;
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+
+	edp-bridge@8 {
+		compatible = "parade,ps8640";
+		reg = <0x8>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ps8640_pins>;
+		powerdown-gpios = <&pio 96 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&pio 98 GPIO_ACTIVE_LOW>;
+		vdd12-supply = <&mt6366_vrf12_reg>;
+		vdd33-supply = <&mt6366_vcn33_reg>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				ps8640_in: endpoint {
+					remote-endpoint = <&dsi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				ps8640_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+
+		aux-bus {
+			panel {
+				compatible = "edp-panel";
+				power-supply = <&pp3300_disp_x>;
+				backlight = <&backlight_lcd0>;
+
+				port {
+					panel_in: endpoint {
+						remote-endpoint = <&ps8640_out>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&i2c1 {
+	i2c-scl-internal-delay-ns = <10000>;
+
+	touchscreen: touchscreen@10 {
+		compatible = "hid-over-i2c";
+		reg = <0x10>;
+		interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen_pins>;
+		post-power-on-delay-ms = <10>;
+		hid-descr-addr = <0x0001>;
+		vdd-supply = <&pp3300_s3>;
+	};
+};
+
+&i2c4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c4_pins>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	proximity@28 {
+		compatible = "semtech,sx9324";
+		reg = <0x28>;
+		#io-channel-cells = <1>;
+		interrupts-extended = <&pio 5 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&sar_sensor_pins>;
+		vdd-supply = <&mt6366_vio18_reg>;
+		svdd-supply = <&mt6366_vio18_reg>;
+	};
+};
+
+&pio {
+	i2c4_pins: i2c4-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO136__FUNC_SDA4>,
+				 <PINMUX_GPIO135__FUNC_SCL4>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	ps8640_pins: ps8640-pins {
+		pins-pwrdn-rst {
+			pinmux = <PINMUX_GPIO96__FUNC_GPIO96>,
+				 <PINMUX_GPIO98__FUNC_GPIO98>;
+			output-low;
+		};
+	};
+
+	sar_sensor_pins: sar-sensor-pins {
+		pins-irq {
+			pinmux = <PINMUX_GPIO5__FUNC_GPIO5>;
+			input-enable;
+			bias-pull-up;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393216.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393216.dts
new file mode 100644
index 000000000000..c9673381ad3b
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393216.dts
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Magneton board";
+	compatible = "google,steelix-sku393219", "google,steelix-sku393216",
+		     "google,steelix", "mediatek,mt8186";
+	chassis-type = "laptop";
+};
+
+&gpio_keys {
+	status = "disabled";
+};
+
+&i2c1 {
+	touchscreen@10 {
+		compatible = "hid-over-i2c";
+		reg = <0x10>;
+		interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen_pins>;
+		vdd-supply = <&pp3300_s3>;
+		post-power-on-delay-ms = <350>;
+		hid-descr-addr = <0x0001>;
+	};
+};
+
+&touchscreen {
+	status = "disabled";
+};
+
+&usb_c1 {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393217.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393217.dts
new file mode 100644
index 000000000000..28e3bbe56421
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393217.dts
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Magneton board";
+	compatible = "google,steelix-sku393220", "google,steelix-sku393217",
+		     "google,steelix", "mediatek,mt8186";
+	chassis-type = "laptop";
+};
+
+&gpio_keys {
+	status = "disabled";
+};
+
+&i2c1 {
+	touchscreen@40 {
+		compatible = "hid-over-i2c";
+		reg = <0x40>;
+		interrupts-extended = <&pio 12 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen_pins>;
+		vdd-supply = <&pp3300_s3>;
+		post-power-on-delay-ms = <450>;
+		hid-descr-addr = <0x0001>;
+	};
+};
+
+&touchscreen {
+	status = "disabled";
+};
+
+&usb_c1 {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393218.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393218.dts
new file mode 100644
index 000000000000..332894218f07
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-magneton-sku393218.dts
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Magneton board";
+	compatible = "google,steelix-sku393221", "google,steelix-sku393218",
+		     "google,steelix", "mediatek,mt8186";
+	chassis-type = "laptop";
+};
+
+&gpio_keys {
+	status = "disabled";
+};
+
+&touchscreen {
+	status = "disabled";
+};
+
+&usb_c1 {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-rusty-sku196608.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-rusty-sku196608.dts
new file mode 100644
index 000000000000..731b0d60228d
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-rusty-sku196608.dts
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Rusty board";
+	compatible = "google,steelix-sku196609", "google,steelix-sku196608",
+		     "google,steelix", "mediatek,mt8186";
+	chassis-type = "laptop";
+};
+
+&gpio_keys {
+	status = "disabled";
+};
+
+&i2c1 {
+	status = "disabled";
+};
+
+&touchscreen {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131072.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131072.dts
new file mode 100644
index 000000000000..eae17bca8585
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131072.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Steelix board";
+	compatible = "google,steelix-sku131072", "google,steelix",
+		     "mediatek,mt8186";
+	chassis-type = "convertible";
+};
+
+&mt6366codec {
+	mediatek,dmic-mode = <0>; /* two-wire */
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131073.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131073.dts
new file mode 100644
index 000000000000..a55375b95d0d
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix-sku131073.dts
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-steelix.dtsi"
+
+/ {
+	model = "Google Steelix board";
+	compatible = "google,steelix-sku131073", "google,steelix",
+		     "mediatek,mt8186";
+	chassis-type = "convertible";
+};
+
+&mt6366codec {
+	mediatek,dmic-mode = <1>; /* one-wire */
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix.dtsi
new file mode 100644
index 000000000000..e74e886a00cb
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-steelix.dtsi
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+
+/{
+	pp1000_edpbrdg: regulator-pp1000-edpbrdg {
+		compatible = "regulator-fixed";
+		regulator-name = "pp1000_edpbrdg";
+		pinctrl-names = "default";
+		pinctrl-0 = <&en_pp1000_edpbrdg>;
+		enable-active-high;
+		regulator-boot-on;
+		gpio = <&pio 29 GPIO_ACTIVE_HIGH>;
+		vin-supply = <&pp3300_z2>;
+	};
+
+	pp1800_edpbrdg_dx: regulator-pp1800-edpbrdg-dx {
+		compatible = "regulator-fixed";
+		regulator-name = "pp1800_edpbrdg_dx";
+		pinctrl-names = "default";
+		pinctrl-0 = <&en_pp1800_edpbrdg>;
+		enable-active-high;
+		regulator-boot-on;
+		gpio = <&pio 30 GPIO_ACTIVE_HIGH>;
+		vin-supply = <&mt6366_vio18_reg>;
+	};
+
+	pp3300_edp_dx: regulator-pp3300-edp-dx {
+		compatible = "regulator-fixed";
+		regulator-name = "pp3300_edp_dx";
+		pinctrl-names = "default";
+		pinctrl-0 = <&en_pp3300_edpbrdg>;
+		enable-active-high;
+		regulator-boot-on;
+		gpio = <&pio 31 GPIO_ACTIVE_HIGH>;
+		vin-supply = <&pp3300_z2>;
+	};
+};
+
+&dsi_out {
+	remote-endpoint = <&anx7625_in>;
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+
+	anx_bridge: anx7625@58 {
+		compatible = "analogix,anx7625";
+		reg = <0x58>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&anx7625_pins>;
+		enable-gpios = <&pio 96 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&pio 98 GPIO_ACTIVE_HIGH>;
+		vdd10-supply = <&pp1000_edpbrdg>;
+		vdd18-supply = <&pp1800_edpbrdg_dx>;
+		vdd33-supply = <&pp3300_edp_dx>;
+		analogix,lane0-swing = /bits/ 8 <0x70 0x30>;
+		analogix,lane1-swing = /bits/ 8 <0x70 0x30>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				anx7625_in: endpoint {
+					remote-endpoint = <&dsi_out>;
+					data-lanes = <0 1 2 3>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				anx7625_out: endpoint {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+
+		aux-bus {
+			panel: panel {
+				compatible = "edp-panel";
+				power-supply = <&pp3300_disp_x>;
+				backlight = <&backlight_lcd0>;
+
+				port {
+					panel_in: endpoint {
+						remote-endpoint = <&anx7625_out>;
+					};
+				};
+			};
+		};
+	};
+};
+
+&i2c1 {
+	touchscreen: touchscreen@5d {
+		compatible = "goodix,gt7375p";
+		reg = <0x5d>;
+		interrupts-extended = <&pio 12 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&touchscreen_pins>;
+		reset-gpios = <&pio 60 GPIO_ACTIVE_LOW>;
+		vdd-supply = <&pp3300_s3>;
+		goodix,no-reset-during-suspend;
+	};
+};
+
+&i2c2 {
+	i2c-scl-internal-delay-ns = <22000>;
+
+	/* second source component */
+	trackpad@2c {
+		compatible = "hid-over-i2c";
+		reg = <0x2c>;
+		hid-descr-addr = <0x20>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_LOW>;
+		vdd-supply = <&pp3300_s3>;
+		wakeup-source;
+	};
+};
+
+&keyboard_controller {
+	function-row-physmap = <
+		MATRIX_KEY(0x00, 0x02, 0)	/* T1 */
+		MATRIX_KEY(0x03, 0x02, 0)	/* T2 */
+		MATRIX_KEY(0x02, 0x02, 0)	/* T3 */
+		MATRIX_KEY(0x01, 0x02, 0)	/* T4 */
+		MATRIX_KEY(0x03, 0x04, 0)	/* T5 */
+		MATRIX_KEY(0x02, 0x04, 0)	/* T6 */
+		MATRIX_KEY(0x01, 0x04, 0)	/* T7 */
+		MATRIX_KEY(0x02, 0x09, 0)	/* T8 */
+		MATRIX_KEY(0x01, 0x09, 0)	/* T9 */
+		MATRIX_KEY(0x00, 0x04, 0)	/* T10 */
+	>;
+
+	linux,keymap = <
+		MATRIX_KEY(0x00, 0x02, KEY_BACK)
+		MATRIX_KEY(0x03, 0x02, KEY_REFRESH)
+		MATRIX_KEY(0x02, 0x02, KEY_ZOOM)
+		MATRIX_KEY(0x01, 0x02, KEY_SCALE)
+		MATRIX_KEY(0x03, 0x04, KEY_BRIGHTNESSDOWN)
+		MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSUP)
+		MATRIX_KEY(0x01, 0x04, KEY_MICMUTE)
+		MATRIX_KEY(0x02, 0x09, KEY_MUTE)
+		MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN)
+		MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP)
+		CROS_STD_MAIN_KEYMAP
+	>;
+};
+
+&pio {
+	anx7625_pins: anx7625-pins {
+		pins-int {
+			pinmux = <PINMUX_GPIO9__FUNC_GPIO9>;
+			input-enable;
+			bias-disable;
+		};
+
+		pins-reset {
+			pinmux = <PINMUX_GPIO98__FUNC_GPIO98>;
+			output-low;
+		};
+
+		pins-power-en {
+			pinmux = <PINMUX_GPIO96__FUNC_GPIO96>;
+			output-low;
+		};
+	};
+
+	en_pp1000_edpbrdg: pp1000-edpbrdg-en-pins {
+		pins-vreg-en {
+			pinmux = <PINMUX_GPIO29__FUNC_GPIO29>;
+			output-low;
+		};
+	};
+
+	en_pp1800_edpbrdg: pp1800-edpbrdg-en-pins {
+		pins-vreg-en {
+			pinmux = <PINMUX_GPIO30__FUNC_GPIO30>;
+			output-low;
+		};
+	};
+
+	en_pp3300_edpbrdg: pp3300-edpbrdg-en-pins {
+		pins-vreg-en {
+			pinmux = <PINMUX_GPIO31__FUNC_GPIO31>;
+			output-low;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327681.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327681.dts
new file mode 100644
index 000000000000..9bb64353ca65
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327681.dts
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-krabby.dtsi"
+
+/ {
+	model = "Google Tentacool board";
+	compatible = "google,tentacruel-sku327681", "google,tentacruel", "mediatek,mt8186";
+	chassis-type = "laptop";
+};
+
+/* Tentacool omits the pen. */
+&gpio_keys {
+	status = "disabled";
+};
+
+/* Tentacool omits the touchscreen; nothing else is on i2c1. */
+&i2c1 {
+	status = "disabled";
+};
+
+&keyboard_controller {
+	function-row-physmap = <
+		MATRIX_KEY(0x00, 0x02, 0)	/* T1 */
+		MATRIX_KEY(0x03, 0x02, 0)	/* T2 */
+		MATRIX_KEY(0x02, 0x02, 0)	/* T3 */
+		MATRIX_KEY(0x01, 0x02, 0)	/* T4 */
+		MATRIX_KEY(0x03, 0x04, 0)	/* T5 */
+		MATRIX_KEY(0x02, 0x04, 0)	/* T6 */
+		MATRIX_KEY(0x01, 0x04, 0)	/* T7 */
+		MATRIX_KEY(0x02, 0x09, 0)	/* T8 */
+		MATRIX_KEY(0x01, 0x09, 0)	/* T9 */
+		MATRIX_KEY(0x00, 0x04, 0)	/* T10 */
+	>;
+
+	linux,keymap = <
+		MATRIX_KEY(0x00, 0x02, KEY_BACK)
+		MATRIX_KEY(0x03, 0x02, KEY_REFRESH)
+		MATRIX_KEY(0x02, 0x02, KEY_ZOOM)
+		MATRIX_KEY(0x01, 0x02, KEY_SCALE)
+		MATRIX_KEY(0x03, 0x04, KEY_SYSRQ)
+		MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSDOWN)
+		MATRIX_KEY(0x01, 0x04, KEY_BRIGHTNESSUP)
+		MATRIX_KEY(0x02, 0x09, KEY_MUTE)
+		MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN)
+		MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP)
+		CROS_STD_MAIN_KEYMAP
+	>;
+};
+
+/* Tentacool omits the touchscreen. */
+&touchscreen {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327683.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327683.dts
new file mode 100644
index 000000000000..c3ae6f9616c8
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacool-sku327683.dts
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+#include "mt8186-corsola-tentacool-sku327681.dts"
+
+/ {
+	compatible = "google,tentacruel-sku327683", "google,tentacruel", "mediatek,mt8186";
+};
+
+/* This variant replaces only the trackpad controller. */
+&i2c2 {
+	/delete-node/ trackpad@15;
+
+	trackpad@15 {
+		compatible = "hid-over-i2c";
+		reg = <0x15>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_LOW>;
+		hid-descr-addr = <0x0001>;
+		vdd-supply = <&pp3300_s3>;
+		wakeup-source;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262144.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262144.dts
new file mode 100644
index 000000000000..26d3451a5e47
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262144.dts
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2022 Google LLC
+ */
+
+/dts-v1/;
+#include "mt8186-corsola-krabby.dtsi"
+
+/ {
+	model = "Google Tentacruel board";
+	compatible = "google,tentacruel-sku262147", "google,tentacruel-sku262146",
+		     "google,tentacruel-sku262145", "google,tentacruel-sku262144",
+		     "google,tentacruel", "mediatek,mt8186";
+	chassis-type = "convertible";
+};
+
+&keyboard_controller {
+	function-row-physmap = <
+		MATRIX_KEY(0x00, 0x02, 0)	/* T1 */
+		MATRIX_KEY(0x03, 0x02, 0)	/* T2 */
+		MATRIX_KEY(0x02, 0x02, 0)	/* T3 */
+		MATRIX_KEY(0x01, 0x02, 0)	/* T4 */
+		MATRIX_KEY(0x03, 0x04, 0)	/* T5 */
+		MATRIX_KEY(0x02, 0x04, 0)	/* T6 */
+		MATRIX_KEY(0x01, 0x04, 0)	/* T7 */
+		MATRIX_KEY(0x02, 0x09, 0)	/* T8 */
+		MATRIX_KEY(0x01, 0x09, 0)	/* T9 */
+		MATRIX_KEY(0x00, 0x04, 0)	/* T10 */
+	>;
+
+	linux,keymap = <
+		MATRIX_KEY(0x00, 0x02, KEY_BACK)
+		MATRIX_KEY(0x03, 0x02, KEY_REFRESH)
+		MATRIX_KEY(0x02, 0x02, KEY_ZOOM)
+		MATRIX_KEY(0x01, 0x02, KEY_SCALE)
+		MATRIX_KEY(0x03, 0x04, KEY_SYSRQ)
+		MATRIX_KEY(0x02, 0x04, KEY_BRIGHTNESSDOWN)
+		MATRIX_KEY(0x01, 0x04, KEY_BRIGHTNESSUP)
+		MATRIX_KEY(0x02, 0x09, KEY_MUTE)
+		MATRIX_KEY(0x01, 0x09, KEY_VOLUMEDOWN)
+		MATRIX_KEY(0x00, 0x04, KEY_VOLUMEUP)
+		CROS_STD_MAIN_KEYMAP
+	>;
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262148.dts b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262148.dts
new file mode 100644
index 000000000000..447b57b12b41
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola-tentacruel-sku262148.dts
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright 2023 Google LLC
+ */
+
+#include "mt8186-corsola-tentacruel-sku262144.dts"
+
+/ {
+	compatible = "google,tentacruel-sku262151", "google,tentacruel-sku262150",
+		     "google,tentacruel-sku262149", "google,tentacruel-sku262148",
+		     "google,tentacruel", "mediatek,mt8186";
+};
+
+/* This variant replaces only the trackpad controller. */
+&i2c2 {
+	/delete-node/ trackpad@15;
+
+	trackpad@15 {
+		compatible = "hid-over-i2c";
+		reg = <0x15>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_LOW>;
+		hid-descr-addr = <0x0001>;
+		vdd-supply = <&pp3300_s3>;
+		wakeup-source;
+	};
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
new file mode 100644
index 000000000000..3dea28f1d806
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
@@ -0,0 +1,1681 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2022 MediaTek Inc.
+ */
+/dts-v1/;
+#include "mt8186.dtsi"
+#include <dt-bindings/pinctrl/mt8186-pinfunc.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/input/gpio-keys.h>
+#include <dt-bindings/regulator/mediatek,mt6397-regulator.h>
+
+/ {
+	aliases {
+		i2c0 = &i2c0;
+		i2c1 = &i2c1;
+		i2c2 = &i2c2;
+		i2c3 = &i2c3;
+		i2c5 = &i2c5;
+		mmc0 = &mmc0;
+		mmc1 = &mmc1;
+		serial0 = &uart0;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		/* The size should be filled in by the bootloader. */
+		reg = <0 0x40000000 0 0>;
+	};
+
+	backlight_lcd0: backlight-lcd0 {
+		compatible = "pwm-backlight";
+		pwms = <&pwm0 0 500000>;
+		power-supply = <&ppvar_sys>;
+		enable-gpios = <&pio 152 0>;
+		brightness-levels = <0 1023>;
+		num-interpolated-steps = <1023>;
+		default-brightness-level = <576>;
+	};
+
+	bt-sco-codec {
+		compatible = "linux,bt-sco";
+		#sound-dai-cells = <0>;
+	};
+
+	dmic-codec {
+		compatible = "dmic-codec";
+		#sound-dai-cells = <0>;
+		num-channels = <2>;
+		wakeup-delay-ms = <50>;
+	};
+
+	gpio_keys: gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pen_eject>;
+
+		pen_insert: pen-insert-switch {
+			label = "Pen Insert";
+			/* Insert = low, eject = high */
+			gpios = <&pio 18 GPIO_ACTIVE_LOW>;
+			wakeup-event-action = <EV_ACT_DEASSERTED>;
+			wakeup-source;
+			linux,code = <SW_PEN_INSERTED>;
+			linux,input-type = <EV_SW>;
+		};
+	};
+
+	pp1800_dpbrdg_dx: regulator-pp1800-dpbrdg-dx {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&en_pp1800_dpbrdg>;
+		gpios = <&pio 39 GPIO_ACTIVE_HIGH>;
+		regulator-name = "pp1800_dpbrdg_dx";
+		enable-active-high;
+		vin-supply = <&mt6366_vio18_reg>;
+	};
+
+	pp3300_disp_x: regulator-pp3300-disp-x {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&edp_panel_fixed_pins>;
+		gpios = <&pio 153 GPIO_ACTIVE_HIGH>;
+		regulator-name = "pp3300_disp_x";
+		enable-active-high;
+		regulator-boot-on;
+		vin-supply = <&pp3300_z2>;
+	};
+
+	/* system wide LDO 3.3V power rail */
+	pp3300_z5: regulator-pp3300-ldo-z5 {
+		compatible = "regulator-fixed";
+		regulator-name = "pp3300_ldo_z5";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&ppvar_sys>;
+	};
+
+	/* separately switched 3.3V power rail */
+	pp3300_s3: regulator-pp3300-s3 {
+		compatible = "regulator-fixed";
+		regulator-name = "pp3300_s3";
+		/* automatically sequenced by PMIC EXT_PMIC_EN2 */
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&pp3300_z2>;
+	};
+
+	/* system wide 3.3V power rail */
+	pp3300_z2: regulator-pp3300-z2 {
+		compatible = "regulator-fixed";
+		regulator-name = "pp3300_z2";
+		/* EN pin tied to pp4200_z2, which is controlled by EC */
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&ppvar_sys>;
+	};
+
+	/* system wide 4.2V power rail */
+	pp4200_z2: regulator-pp4200-z2 {
+		compatible = "regulator-fixed";
+		regulator-name = "pp4200_z2";
+		/* controlled by EC */
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <4200000>;
+		regulator-max-microvolt = <4200000>;
+		vin-supply = <&ppvar_sys>;
+	};
+
+	/* system wide switching 5.0V power rail */
+	pp5000_z2: regulator-pp5000-z2 {
+		compatible = "regulator-fixed";
+		regulator-name = "pp5000_z2";
+		/* controlled by EC */
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&ppvar_sys>;
+	};
+
+	/* system wide semi-regulated power rail from battery or USB */
+	ppvar_sys: regulator-ppvar-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "ppvar_sys";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		adsp_dma_mem: memory@61000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x61000000 0 0x100000>;
+			no-map;
+		};
+
+		adsp_mem: memory@60000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x60000000 0 0xA00000>;
+			no-map;
+		};
+
+		scp_mem: memory@50000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x50000000 0 0x10a0000>;
+			no-map;
+		};
+	};
+
+	sound: sound {
+		compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound";
+		pinctrl-names = "aud_clk_mosi_off",
+				"aud_clk_mosi_on",
+				"aud_clk_miso_off",
+				"aud_clk_miso_on",
+				"aud_dat_miso_off",
+				"aud_dat_miso_on",
+				"aud_dat_mosi_off",
+				"aud_dat_mosi_on",
+				"aud_gpio_i2s0_off",
+				"aud_gpio_i2s0_on",
+				"aud_gpio_i2s1_off",
+				"aud_gpio_i2s1_on",
+				"aud_gpio_i2s2_off",
+				"aud_gpio_i2s2_on",
+				"aud_gpio_i2s3_off",
+				"aud_gpio_i2s3_on",
+				"aud_gpio_pcm_off",
+				"aud_gpio_pcm_on",
+				"aud_gpio_dmic_sec";
+		pinctrl-0 = <&aud_clk_mosi_off>;
+		pinctrl-1 = <&aud_clk_mosi_on>;
+		pinctrl-2 = <&aud_clk_miso_off>;
+		pinctrl-3 = <&aud_clk_miso_on>;
+		pinctrl-4 = <&aud_dat_miso_off>;
+		pinctrl-5 = <&aud_dat_miso_on>;
+		pinctrl-6 = <&aud_dat_mosi_off>;
+		pinctrl-7 = <&aud_dat_mosi_on>;
+		pinctrl-8 = <&aud_gpio_i2s0_off>;
+		pinctrl-9 = <&aud_gpio_i2s0_on>;
+		pinctrl-10 = <&aud_gpio_i2s1_off>;
+		pinctrl-11 = <&aud_gpio_i2s1_on>;
+		pinctrl-12 = <&aud_gpio_i2s2_off>;
+		pinctrl-13 = <&aud_gpio_i2s2_on>;
+		pinctrl-14 = <&aud_gpio_i2s3_off>;
+		pinctrl-15 = <&aud_gpio_i2s3_on>;
+		pinctrl-16 = <&aud_gpio_pcm_off>;
+		pinctrl-17 = <&aud_gpio_pcm_on>;
+		pinctrl-18 = <&aud_gpio_dmic_sec>;
+		mediatek,adsp = <&adsp>;
+		mediatek,platform = <&afe>;
+
+		playback-codecs {
+			sound-dai = <&it6505dptx>, <&rt1019p>;
+		};
+
+		headset-codec {
+			sound-dai = <&rt5682s 0>;
+		};
+	};
+
+	rt1019p: speaker-codec {
+		compatible = "realtek,rt1019p";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rt1019p_pins_default>;
+		#sound-dai-cells = <0>;
+		sdb-gpios = <&pio 150 GPIO_ACTIVE_HIGH>;
+	};
+
+	usb_p1_vbus: regulator-usb-p1-vbus {
+		compatible = "regulator-fixed";
+		gpio = <&pio 148 GPIO_ACTIVE_HIGH>;
+		regulator-name = "vbus1";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		enable-active-high;
+		vin-supply = <&pp5000_z2>;
+	};
+
+	wifi_pwrseq: wifi-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_enable_pin>;
+		post-power-on-delay-ms = <50>;
+		reset-gpios = <&pio 54 GPIO_ACTIVE_LOW>;
+	};
+
+	wifi_wakeup: wifi-wakeup {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_wakeup_pin>;
+
+		wowlan-event {
+			label = "Wake on WiFi";
+			gpios = <&pio 7 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_WAKEUP>;
+			wakeup-source;
+		};
+	};
+};
+
+&adsp {
+	memory-region = <&adsp_dma_mem>, <&adsp_mem>;
+	status = "okay";
+};
+
+&afe {
+	status = "okay";
+};
+
+&cci {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu0 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu1 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu2 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu3 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu4 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu5 {
+	proc-supply = <&mt6366_vproc12_reg>;
+};
+
+&cpu6 {
+	proc-supply = <&mt6366_vproc11_reg>;
+};
+
+&cpu7 {
+	proc-supply = <&mt6366_vproc11_reg>;
+};
+
+&dpi {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&dpi_pins_default>;
+	pinctrl-1 = <&dpi_pins_sleep>;
+	status = "okay";
+};
+
+&dpi_out {
+	remote-endpoint = <&it6505_in>;
+};
+
+&dsi0 {
+	status = "okay";
+};
+
+&gic {
+	mediatek,broken-save-restore-fw;
+};
+
+&gpu {
+	mali-supply = <&mt6366_vgpu_reg>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+	status = "okay";
+};
+
+&i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	clock-frequency = <400000>;
+	i2c-scl-internal-delay-ns = <8000>;
+	status = "okay";
+};
+
+&i2c2 {
+	pinctrl-names = "default";
+	/*
+	 * Trackpad pin put here to work around second source components
+	 * sharing the pinmux in steelix designs.
+	 */
+	pinctrl-0 = <&i2c2_pins>, <&trackpad_pin>;
+	clock-frequency = <400000>;
+	i2c-scl-internal-delay-ns = <10000>;
+	status = "okay";
+
+	trackpad@15 {
+		compatible = "elan,ekth3000";
+		reg = <0x15>;
+		interrupts-extended = <&pio 11 IRQ_TYPE_LEVEL_LOW>;
+		vcc-supply = <&pp3300_s3>;
+		wakeup-source;
+	};
+};
+
+&i2c3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_pins>;
+	clock-frequency = <100000>;
+	status = "okay";
+
+	it6505dptx: dp-bridge@5c {
+		compatible = "ite,it6505";
+		reg = <0x5c>;
+		interrupts-extended = <&pio 8 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&it6505_pins>;
+		#sound-dai-cells = <0>;
+		ovdd-supply = <&mt6366_vsim2_reg>;
+		pwr18-supply = <&pp1800_dpbrdg_dx>;
+		reset-gpios = <&pio 177 GPIO_ACTIVE_HIGH>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				it6505_in: endpoint {
+					link-frequencies = /bits/ 64 <150000000>;
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+			};
+		};
+	};
+};
+
+&i2c5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_pins>;
+	status = "okay";
+
+	rt5682s: codec@1a {
+		compatible = "realtek,rt5682s";
+		reg = <0x1a>;
+		interrupts-extended = <&pio 17 IRQ_TYPE_EDGE_BOTH>;
+		#sound-dai-cells = <1>;
+		AVDD-supply = <&mt6366_vio18_reg>;
+		DBVDD-supply = <&mt6366_vio18_reg>;
+		LDO1-IN-supply = <&mt6366_vio18_reg>;
+		MICVDD-supply = <&pp3300_z2>;
+		realtek,jd-src = <1>;
+	};
+};
+
+&mfg0 {
+	domain-supply = <&mt6366_vsram_gpu_reg>;
+};
+
+&mfg1 {
+	domain-supply = <&mt6366_vgpu_reg>;
+};
+
+&mipi_tx0 {
+	status = "okay";
+};
+
+&mmc0 {
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_pins_default>;
+	pinctrl-1 = <&mmc0_pins_uhs>;
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	non-removable;
+	cap-mmc-highspeed;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	supports-cqe;
+	no-sd;
+	no-sdio;
+	cap-mmc-hw-reset;
+	hs400-ds-delay = <0x11814>;
+	mediatek,hs400-ds-dly3 = <0x14>;
+	vmmc-supply = <&mt6366_vemc_reg>;
+	vqmmc-supply = <&mt6366_vio18_reg>;
+	status = "okay";
+};
+
+&mmc1 {
+	pinctrl-names = "default", "state_uhs", "state_eint";
+	pinctrl-0 = <&mmc1_pins_default>;
+	pinctrl-1 = <&mmc1_pins_uhs>;
+	pinctrl-2 = <&mmc1_pins_eint>;
+	/delete-property/ interrupts;
+	interrupt-names = "msdc", "sdio_wakeup";
+	interrupts-extended = <&gic GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH 0>,
+			      <&pio 87 IRQ_TYPE_LEVEL_LOW>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	bus-width = <4>;
+	max-frequency = <200000000>;
+	cap-sd-highspeed;
+	sd-uhs-sdr104;
+	sd-uhs-sdr50;
+	keep-power-in-suspend;
+	wakeup-source;
+	cap-sdio-irq;
+	no-mmc;
+	no-sd;
+	non-removable;
+	vmmc-supply = <&pp3300_s3>;
+	vqmmc-supply = <&mt6366_vio18_reg>;
+	mmc-pwrseq = <&wifi_pwrseq>;
+	status = "okay";
+
+	bluetooth@2 {
+		compatible = "mediatek,mt7921s-bluetooth";
+		reg = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&bt_pins_reset>;
+		reset-gpios = <&pio 155 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&nor_flash {
+	assigned-clock-parents = <&topckgen CLK_TOP_MAINPLL_D7_D4>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&nor_pins_default>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <39000000>;
+	};
+};
+
+&pio {
+	/* 185 lines */
+	gpio-line-names = "TP",
+			  "TP",
+			  "TP",
+			  "I2S0_HP_DI",
+			  "I2S3_DP_SPKR_DO",
+			  "SAR_INT_ODL",
+			  "BT_WAKE_AP_ODL",
+			  "WIFI_INT_ODL",
+			  "DPBRDG_INT_ODL",
+			  "EDPBRDG_INT_ODL",
+			  "EC_AP_HPD_OD",
+			  "TCHPAD_INT_ODL",
+			  "TCHSCR_INT_1V8_ODL",
+			  "EC_AP_INT_ODL",
+			  "EC_IN_RW_ODL",
+			  "GSC_AP_INT_ODL",
+			  /* AP_FLASH_WP_L is crossystem ABI. Rev1 schematics call it AP_WP_ODL. */
+			  "AP_FLASH_WP_L",
+			  "HP_INT_ODL",
+			  "PEN_EJECT_OD",
+			  "WCAM_PWDN_L",
+			  "WCAM_RST_L",
+			  "UCAM_SEN_EN",
+			  "UCAM_RST_L",
+			  "LTE_RESET_L",
+			  "LTE_SAR_DETECT_L",
+			  "I2S2_DP_SPK_MCK",
+			  "I2S2_DP_SPKR_BCK",
+			  "I2S2_DP_SPKR_LRCK",
+			  "I2S2_DP_SPKR_DI (TP)",
+			  "EN_PP1000_EDPBRDG",
+			  "EN_PP1800_EDPBRDG",
+			  "EN_PP3300_EDPBRDG",
+			  "UART_GSC_TX_AP_RX",
+			  "UART_AP_TX_GSC_RX",
+			  "UART_DBGCON_TX_ADSP_RX",
+			  "UART_ADSP_TX_DBGCON_RX",
+			  "EN_PP1000_DPBRDG",
+			  "TCHSCR_REPORT_DISABLE",
+			  "EN_PP3300_DPBRDG",
+			  "EN_PP1800_DPBRDG",
+			  "SPI_AP_CLK_EC",
+			  "SPI_AP_CS_EC_L",
+			  "SPI_AP_DO_EC_DI",
+			  "SPI_AP_DI_EC_DO",
+			  "SPI_AP_CLK_GSC",
+			  "SPI_AP_CS_GSC_L",
+			  "SPI_AP_DO_GSC_DI",
+			  "SPI_AP_DI_GSC_DO",
+			  "UART_DBGCON_TX_SCP_RX",
+			  "UART_SCP_TX_DBGCON_RX",
+			  "EN_PP1200_CAM_X",
+			  "EN_PP2800A_VCM_X",
+			  "EN_PP2800A_UCAM_X",
+			  "EN_PP2800A_WCAM_X",
+			  "WLAN_MODULE_RST_L",
+			  "EN_PP1200_UCAM_X",
+			  "I2S1_HP_DO",
+			  "I2S1_HP_BCK",
+			  "I2S1_HP_LRCK",
+			  "I2S1_HP_MCK",
+			  "TCHSCR_RST_1V8_L",
+			  "SPI_AP_CLK_ROM",
+			  "SPI_AP_CS_ROM_L",
+			  "SPI_AP_DO_ROM_DI",
+			  "SPI_AP_DI_ROM_DO",
+			  "NC",
+			  "NC",
+			  "EMMC_STRB",
+			  "EMMC_CLK",
+			  "EMMC_CMD",
+			  "EMMC_RST_L",
+			  "EMMC_DATA0",
+			  "EMMC_DATA1",
+			  "EMMC_DATA2",
+			  "EMMC_DATA3",
+			  "EMMC_DATA4",
+			  "EMMC_DATA5",
+			  "EMMC_DATA6",
+			  "EMMC_DATA7",
+			  "AP_KPCOL0",
+			  "NC",
+			  "NC",
+			  "NC",
+			  "TP",
+			  "SDIO_CLK",
+			  "SDIO_CMD",
+			  "SDIO_DATA0",
+			  "SDIO_DATA1",
+			  "SDIO_DATA2",
+			  "SDIO_DATA3",
+			  "NC",
+			  "NC",
+			  "NC",
+			  "NC",
+			  "NC",
+			  "NC",
+			  "EDPBRDG_PWREN",
+			  "BL_PWM_1V8",
+			  "EDPBRDG_RST_L",
+			  "MIPI_DPI_CLK",
+			  "MIPI_DPI_VSYNC",
+			  "MIPI_DPI_HSYNC",
+			  "MIPI_DPI_DE",
+			  "MIPI_DPI_D0",
+			  "MIPI_DPI_D1",
+			  "MIPI_DPI_D2",
+			  "MIPI_DPI_D3",
+			  "MIPI_DPI_D4",
+			  "MIPI_DPI_D5",
+			  "MIPI_DPI_D6",
+			  "MIPI_DPI_DA7",
+			  "MIPI_DPI_D8",
+			  "MIPI_DPI_D9",
+			  "MIPI_DPI_D10",
+			  "MIPI_DPI_D11",
+			  "PCM_BT_CLK",
+			  "PCM_BT_SYNC",
+			  "PCM_BT_DI",
+			  "PCM_BT_DO",
+			  "JTAG_TMS_TP",
+			  "JTAG_TCK_TP",
+			  "JTAG_TDI_TP",
+			  "JTAG_TDO_TP",
+			  "JTAG_TRSTN_TP",
+			  "CLK_24M_WCAM",
+			  "CLK_24M_UCAM",
+			  "UCAM_DET_ODL",
+			  "AP_I2C_EDPBRDG_SCL_1V8",
+			  "AP_I2C_EDPBRDG_SDA_1V8",
+			  "AP_I2C_TCHSCR_SCL_1V8",
+			  "AP_I2C_TCHSCR_SDA_1V8",
+			  "AP_I2C_TCHPAD_SCL_1V8",
+			  "AP_I2C_TCHPAD_SDA_1V8",
+			  "AP_I2C_DPBRDG_SCL_1V8",
+			  "AP_I2C_DPBRDG_SDA_1V8",
+			  "AP_I2C_WLAN_SCL_1V8",
+			  "AP_I2C_WLAN_SDA_1V8",
+			  "AP_I2C_AUD_SCL_1V8",
+			  "AP_I2C_AUD_SDA_1V8",
+			  "AP_I2C_TPM_SCL_1V8",
+			  "AP_I2C_UCAM_SDA_1V8",
+			  "AP_I2C_UCAM_SCL_1V8",
+			  "AP_I2C_UCAM_SDA_1V8",
+			  "AP_I2C_WCAM_SCL_1V8",
+			  "AP_I2C_WCAM_SDA_1V8",
+			  "SCP_I2C_SENSOR_SCL_1V8",
+			  "SCP_I2C_SENSOR_SDA_1V8",
+			  "AP_EC_WARM_RST_REQ",
+			  "AP_XHCI_INIT_DONE",
+			  "USB3_HUB_RST_L",
+			  "EN_SPKR",
+			  "BEEP_ON",
+			  "AP_EDP_BKLTEN",
+			  "EN_PP3300_DISP_X",
+			  "EN_PP3300_SDBRDG_X",
+			  "BT_KILL_1V8_L",
+			  "WIFI_KILL_1V8_L",
+			  "PWRAP_SPI0_CSN",
+			  "PWRAP_SPI0_CK",
+			  "PWRAP_SPI0_MO",
+			  "PWRAP_SPI0_MI",
+			  "SRCLKENA0",
+			  "SRCLKENA1",
+			  "SCP_VREQ_VAO",
+			  "AP_RTC_CLK32K",
+			  "AP_PMIC_WDTRST_L",
+			  "AUD_CLK_MOSI",
+			  "AUD_SYNC_MOSI",
+			  "AUD_DAT_MOSI0",
+			  "AUD_DAT_MOSI1",
+			  "AUD_CLK_MISO",
+			  "AUD_SYNC_MISO",
+			  "AUD_DAT_MISO0",
+			  "AUD_DAT_MISO1",
+			  "NC",
+			  "NC",
+			  "DPBRDG_PWREN",
+			  "DPBRDG_RST_L",
+			  "LTE_W_DISABLE_L",
+			  "LTE_SAR_DETECT_L",
+			  "EN_PP3300_LTE_X",
+			  "LTE_PWR_OFF_L",
+			  "LTE_RESET_L",
+			  "TP",
+			  "TP";
+
+	aud_clk_mosi_off: aud-clk-mosi-off-pins {
+		pins-clk-sync {
+			pinmux = <PINMUX_GPIO166__FUNC_GPIO166>,
+				 <PINMUX_GPIO167__FUNC_GPIO167>;
+			input-enable;
+			bias-pull-down;
+		};
+	};
+
+	aud_clk_mosi_on: aud-clk-mosi-on-pins {
+		pins-clk-sync {
+			pinmux = <PINMUX_GPIO166__FUNC_AUD_CLK_MOSI>,
+				 <PINMUX_GPIO167__FUNC_AUD_SYNC_MOSI>;
+		};
+	};
+
+	aud_clk_miso_off: aud-clk-miso-off-pins {
+		pins-clk-sync {
+			pinmux = <PINMUX_GPIO170__FUNC_GPIO170>,
+				 <PINMUX_GPIO171__FUNC_GPIO171>;
+			input-enable;
+			bias-pull-down;
+		};
+	};
+
+	aud_clk_miso_on: aud-clk-miso-on-pins {
+		pins-clk-sync {
+			pinmux = <PINMUX_GPIO170__FUNC_AUD_CLK_MISO>,
+				 <PINMUX_GPIO171__FUNC_AUD_SYNC_MISO>;
+		};
+	};
+
+	aud_dat_mosi_off: aud-dat-mosi-off-pins {
+		pins-dat {
+			pinmux = <PINMUX_GPIO168__FUNC_GPIO168>,
+				 <PINMUX_GPIO169__FUNC_GPIO169>;
+			input-enable;
+			bias-pull-down;
+		};
+	};
+
+	aud_dat_mosi_on: aud-dat-mosi-on-pins {
+		pins-dat {
+			pinmux = <PINMUX_GPIO168__FUNC_AUD_DAT_MOSI0>,
+				 <PINMUX_GPIO169__FUNC_AUD_DAT_MOSI1>;
+		};
+	};
+
+	aud_dat_miso_off: aud-dat-miso-off-pins {
+		pins-dat {
+			pinmux = <PINMUX_GPIO172__FUNC_GPIO172>,
+				 <PINMUX_GPIO173__FUNC_GPIO173>;
+			input-enable;
+			bias-pull-down;
+		};
+	};
+
+	aud_dat_miso_on: aud-dat-miso-on-pins {
+		pins-dat {
+			pinmux = <PINMUX_GPIO172__FUNC_AUD_DAT_MISO0>,
+				 <PINMUX_GPIO173__FUNC_AUD_DAT_MISO1>;
+			input-schmitt-enable;
+			bias-disable;
+		};
+	};
+
+	aud_gpio_i2s0_off: aud-gpio-i2s0-off-pins {
+		pins-sdata {
+			pinmux = <PINMUX_GPIO3__FUNC_GPIO3>;
+		};
+	};
+
+	aud_gpio_i2s0_on: aud-gpio-i2s0-on-pins {
+		pins-sdata {
+			pinmux = <PINMUX_GPIO3__FUNC_I2S0_DI>;
+		};
+	};
+
+	aud_gpio_i2s1_off: aud-gpio-i2s-off-pins {
+		pins-clk-sdata {
+			pinmux = <PINMUX_GPIO56__FUNC_GPIO56>,
+				 <PINMUX_GPIO57__FUNC_GPIO57>,
+				 <PINMUX_GPIO58__FUNC_GPIO58>,
+				 <PINMUX_GPIO59__FUNC_GPIO59>;
+			output-low;
+		};
+	};
+
+	aud_gpio_i2s1_on: aud-gpio-i2s1-on-pins {
+		pins-clk-sdata {
+			pinmux = <PINMUX_GPIO56__FUNC_I2S1_DO>,
+				 <PINMUX_GPIO57__FUNC_I2S1_BCK>,
+				 <PINMUX_GPIO58__FUNC_I2S1_LRCK>,
+				 <PINMUX_GPIO59__FUNC_I2S1_MCK>;
+		};
+	};
+
+	aud_gpio_i2s2_off: aud-gpio-i2s2-off-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO26__FUNC_GPIO26>,
+				 <PINMUX_GPIO27__FUNC_GPIO27>;
+			output-low;
+		};
+	};
+
+	aud_gpio_i2s2_on: aud-gpio-i2s2-on-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO26__FUNC_I2S2_BCK>,
+				 <PINMUX_GPIO27__FUNC_I2S2_LRCK>;
+			drive-strength = <4>;
+		};
+	};
+
+	aud_gpio_i2s3_off: aud-gpio-i2s3-off-pins {
+		pins-sdata {
+			pinmux = <PINMUX_GPIO4__FUNC_GPIO4>;
+			output-low;
+		};
+	};
+
+	aud_gpio_i2s3_on: aud-gpio-i2s3-on-pins {
+		pins-sdata {
+			pinmux = <PINMUX_GPIO4__FUNC_I2S3_DO>;
+			drive-strength = <4>;
+		};
+	};
+
+	aud_gpio_pcm_off: aud-gpio-pcm-off-pins {
+		pins-clk-sdata {
+			pinmux = <PINMUX_GPIO115__FUNC_GPIO115>,
+				 <PINMUX_GPIO116__FUNC_GPIO116>,
+				 <PINMUX_GPIO117__FUNC_GPIO117>,
+				 <PINMUX_GPIO118__FUNC_GPIO118>;
+			output-low;
+		};
+	};
+
+	aud_gpio_pcm_on: aud-gpio-pcm-on-pins {
+		pins-clk-sdata {
+			pinmux = <PINMUX_GPIO115__FUNC_PCM_CLK>,
+				 <PINMUX_GPIO116__FUNC_PCM_SYNC>,
+				 <PINMUX_GPIO117__FUNC_PCM_DI>,
+				 <PINMUX_GPIO118__FUNC_PCM_DO>;
+		};
+	};
+
+	aud_gpio_dmic_sec: aud-gpio-dmic-sec-pins {
+		pins {
+			pinmux = <PINMUX_GPIO23__FUNC_GPIO23>;
+			output-low;
+		};
+	};
+
+	bt_pins_reset: bt-reset-pins {
+		pins-bt-reset {
+			pinmux = <PINMUX_GPIO155__FUNC_GPIO155>;
+			output-high;
+		};
+	};
+
+	dpi_pins_sleep: dpi-sleep-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO103__FUNC_GPIO103>,
+				 <PINMUX_GPIO104__FUNC_GPIO104>,
+				 <PINMUX_GPIO105__FUNC_GPIO105>,
+				 <PINMUX_GPIO106__FUNC_GPIO106>,
+				 <PINMUX_GPIO107__FUNC_GPIO107>,
+				 <PINMUX_GPIO108__FUNC_GPIO108>,
+				 <PINMUX_GPIO109__FUNC_GPIO109>,
+				 <PINMUX_GPIO110__FUNC_GPIO110>,
+				 <PINMUX_GPIO111__FUNC_GPIO111>,
+				 <PINMUX_GPIO112__FUNC_GPIO112>,
+				 <PINMUX_GPIO113__FUNC_GPIO113>,
+				 <PINMUX_GPIO114__FUNC_GPIO114>,
+				 <PINMUX_GPIO101__FUNC_GPIO101>,
+				 <PINMUX_GPIO100__FUNC_GPIO100>,
+				 <PINMUX_GPIO102__FUNC_GPIO102>,
+				 <PINMUX_GPIO99__FUNC_GPIO99>;
+			drive-strength = <10>;
+			output-low;
+		};
+	};
+
+	dpi_pins_default: dpi-default-pins {
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO103__FUNC_DPI_DATA0>,
+				 <PINMUX_GPIO104__FUNC_DPI_DATA1>,
+				 <PINMUX_GPIO105__FUNC_DPI_DATA2>,
+				 <PINMUX_GPIO106__FUNC_DPI_DATA3>,
+				 <PINMUX_GPIO107__FUNC_DPI_DATA4>,
+				 <PINMUX_GPIO108__FUNC_DPI_DATA5>,
+				 <PINMUX_GPIO109__FUNC_DPI_DATA6>,
+				 <PINMUX_GPIO110__FUNC_DPI_DATA7>,
+				 <PINMUX_GPIO111__FUNC_DPI_DATA8>,
+				 <PINMUX_GPIO112__FUNC_DPI_DATA9>,
+				 <PINMUX_GPIO113__FUNC_DPI_DATA10>,
+				 <PINMUX_GPIO114__FUNC_DPI_DATA11>,
+				 <PINMUX_GPIO101__FUNC_DPI_HSYNC>,
+				 <PINMUX_GPIO100__FUNC_DPI_VSYNC>,
+				 <PINMUX_GPIO102__FUNC_DPI_DE>,
+				 <PINMUX_GPIO99__FUNC_DPI_PCLK>;
+			drive-strength = <10>;
+		};
+	};
+
+	ec_ap_int: cros-ec-int-pins {
+		pins-ec-ap-int-odl {
+			pinmux = <PINMUX_GPIO13__FUNC_GPIO13>;
+			input-enable;
+		};
+	};
+
+	edp_panel_fixed_pins: edp-panel-fixed-pins {
+		pins-vreg-en {
+			pinmux = <PINMUX_GPIO153__FUNC_GPIO153>;
+			output-high;
+		};
+	};
+
+	en_pp1800_dpbrdg: en-pp1800-dpbrdg-pins {
+		pins-vreg-en {
+			pinmux = <PINMUX_GPIO39__FUNC_GPIO39>;
+			output-low;
+		};
+	};
+
+	gsc_int: gsc-int-pins {
+		pins-gsc-ap-int-odl {
+			pinmux = <PINMUX_GPIO15__FUNC_GPIO15>;
+			input-enable;
+		};
+	};
+
+	i2c0_pins: i2c0-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO128__FUNC_SDA0>,
+				 <PINMUX_GPIO127__FUNC_SCL0>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	i2c1_pins: i2c1-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO130__FUNC_SDA1>,
+				 <PINMUX_GPIO129__FUNC_SCL1>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO132__FUNC_SDA2>,
+				 <PINMUX_GPIO131__FUNC_SCL2>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	i2c3_pins: i2c3-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO134__FUNC_SDA3>,
+				 <PINMUX_GPIO133__FUNC_SCL3>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	i2c5_pins: i2c5-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO138__FUNC_SDA5>,
+				 <PINMUX_GPIO137__FUNC_SCL5>;
+			bias-disable;
+			drive-strength = <4>;
+			input-enable;
+		};
+	};
+
+	it6505_pins: it6505-pins {
+		pins-hpd {
+			pinmux = <PINMUX_GPIO10__FUNC_GPIO10>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pins-int {
+			pinmux = <PINMUX_GPIO8__FUNC_GPIO8>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pins-reset {
+			pinmux = <PINMUX_GPIO177__FUNC_GPIO177>;
+			output-low;
+			bias-pull-up;
+		};
+	};
+
+	mmc0_pins_default: mmc0-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO68__FUNC_MSDC0_CLK>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO71__FUNC_MSDC0_DAT0>,
+				 <PINMUX_GPIO72__FUNC_MSDC0_DAT1>,
+				 <PINMUX_GPIO73__FUNC_MSDC0_DAT2>,
+				 <PINMUX_GPIO74__FUNC_MSDC0_DAT3>,
+				 <PINMUX_GPIO75__FUNC_MSDC0_DAT4>,
+				 <PINMUX_GPIO76__FUNC_MSDC0_DAT5>,
+				 <PINMUX_GPIO77__FUNC_MSDC0_DAT6>,
+				 <PINMUX_GPIO78__FUNC_MSDC0_DAT7>,
+				 <PINMUX_GPIO69__FUNC_MSDC0_CMD>;
+			input-enable;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO70__FUNC_MSDC0_RSTB>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc0_pins_uhs: mmc0-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO68__FUNC_MSDC0_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO71__FUNC_MSDC0_DAT0>,
+				 <PINMUX_GPIO72__FUNC_MSDC0_DAT1>,
+				 <PINMUX_GPIO73__FUNC_MSDC0_DAT2>,
+				 <PINMUX_GPIO74__FUNC_MSDC0_DAT3>,
+				 <PINMUX_GPIO75__FUNC_MSDC0_DAT4>,
+				 <PINMUX_GPIO76__FUNC_MSDC0_DAT5>,
+				 <PINMUX_GPIO77__FUNC_MSDC0_DAT6>,
+				 <PINMUX_GPIO78__FUNC_MSDC0_DAT7>,
+				 <PINMUX_GPIO69__FUNC_MSDC0_CMD>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+
+		pins-ds {
+			pinmux = <PINMUX_GPIO67__FUNC_MSDC0_DSL>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO70__FUNC_MSDC0_RSTB>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc1_pins_default: mmc1-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO84__FUNC_MSDC1_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO86__FUNC_MSDC1_DAT0>,
+				 <PINMUX_GPIO87__FUNC_MSDC1_DAT1>,
+				 <PINMUX_GPIO88__FUNC_MSDC1_DAT2>,
+				 <PINMUX_GPIO89__FUNC_MSDC1_DAT3>,
+				 <PINMUX_GPIO85__FUNC_MSDC1_CMD>;
+			input-enable;
+			drive-strength = <6>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc1_pins_uhs: mmc1-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO84__FUNC_MSDC1_CLK>;
+			drive-strength = <6>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO86__FUNC_MSDC1_DAT0>,
+				 <PINMUX_GPIO87__FUNC_MSDC1_DAT1>,
+				 <PINMUX_GPIO88__FUNC_MSDC1_DAT2>,
+				 <PINMUX_GPIO89__FUNC_MSDC1_DAT3>,
+				 <PINMUX_GPIO85__FUNC_MSDC1_CMD>;
+			input-enable;
+			drive-strength = <8>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	mmc1_pins_eint: mmc1-eint-pins {
+		pins-dat1 {
+			pinmux = <PINMUX_GPIO87__FUNC_GPIO87>;
+			input-enable;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+		};
+	};
+
+	nor_pins_default: nor-default-pins {
+		pins-clk-dat {
+			pinmux = <PINMUX_GPIO63__FUNC_SPINOR_IO0>,
+				 <PINMUX_GPIO61__FUNC_SPINOR_CK>,
+				 <PINMUX_GPIO64__FUNC_SPINOR_IO1>;
+			drive-strength = <6>;
+			bias-pull-down;
+		};
+
+		pins-cs-dat {
+			pinmux = <PINMUX_GPIO62__FUNC_SPINOR_CS>,
+				 <PINMUX_GPIO65__FUNC_SPINOR_IO2>,
+				 <PINMUX_GPIO66__FUNC_SPINOR_IO3>;
+			drive-strength = <6>;
+			bias-pull-up;
+		};
+	};
+
+	pen_eject: pen-eject-pins {
+		pins {
+			pinmux = <PINMUX_GPIO18__FUNC_GPIO18>;
+			input-enable;
+			/* External pull-up. */
+			bias-disable;
+		};
+	};
+
+	pwm0_pin: disp-pwm-pins {
+		pins {
+			pinmux = <PINMUX_GPIO97__FUNC_DISP_PWM>;
+			output-high;
+		};
+	};
+
+	rt1019p_pins_default: rt1019p-default-pins {
+		pins-sdb {
+			pinmux = <PINMUX_GPIO150__FUNC_GPIO150>;
+			output-low;
+		};
+	};
+
+	scp_pins: scp-default-pins {
+		pins-scp-uart {
+			pinmux = <PINMUX_GPIO48__FUNC_TP_URXD2_AO>,
+				 <PINMUX_GPIO49__FUNC_TP_UTXD2_AO>;
+		};
+	};
+
+	spi1_pins: spi1-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO40__FUNC_SPI1_CLK_A>,
+				 <PINMUX_GPIO41__FUNC_SPI1_CSB_A>,
+				 <PINMUX_GPIO42__FUNC_SPI1_MO_A>,
+				 <PINMUX_GPIO43__FUNC_SPI1_MI_A>;
+			bias-disable;
+			input-enable;
+		};
+	};
+
+	spi2_pins: spi2-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO44__FUNC_SPI2_CLK_A>,
+				 <PINMUX_GPIO45__FUNC_GPIO45>,
+				 <PINMUX_GPIO46__FUNC_SPI2_MO_A>,
+				 <PINMUX_GPIO47__FUNC_SPI2_MI_A>;
+			bias-disable;
+			input-enable;
+		};
+	};
+
+	spmi_pins: spmi-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO183__FUNC_SPMI_SCL>,
+				 <PINMUX_GPIO184__FUNC_SPMI_SDA>;
+		};
+	};
+
+	touchscreen_pins: touchscreen-pins {
+		pins-irq {
+			pinmux = <PINMUX_GPIO12__FUNC_GPIO12>;
+			input-enable;
+			bias-pull-up;
+		};
+
+		pins-reset {
+			pinmux = <PINMUX_GPIO60__FUNC_GPIO60>;
+			output-high;
+		};
+
+		pins-report-sw {
+			pinmux = <PINMUX_GPIO37__FUNC_GPIO37>;
+			output-low;
+		};
+	};
+
+	trackpad_pin: trackpad-default-pins {
+		pins-int-n {
+			pinmux = <PINMUX_GPIO11__FUNC_GPIO11>;
+			input-enable;
+			bias-disable; /* pulled externally */
+		};
+	};
+
+	wifi_enable_pin: wifi-enable-pins {
+		pins-wifi-enable {
+			pinmux = <PINMUX_GPIO54__FUNC_GPIO54>;
+		};
+	};
+
+	wifi_wakeup_pin: wifi-wakeup-pins {
+		pins-wifi-wakeup {
+			pinmux = <PINMUX_GPIO7__FUNC_GPIO7>;
+			input-enable;
+		};
+	};
+};
+
+&pwm0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm0_pin>;
+	status = "okay";
+};
+
+&pwrap {
+	pmic {
+		compatible = "mediatek,mt6366", "mediatek,mt6358";
+		interrupt-controller;
+		interrupts-extended = <&pio 201 IRQ_TYPE_LEVEL_HIGH>;
+		#interrupt-cells = <2>;
+
+		mt6366codec: codec {
+			compatible = "mediatek,mt6366-sound", "mediatek,mt6358-sound";
+			Avdd-supply = <&mt6366_vaud28_reg>;
+			mediatek,dmic-mode = <1>; /* one-wire */
+		};
+
+		mt6366_regulators: regulators {
+			compatible = "mediatek,mt6366-regulator", "mediatek,mt6358-regulator";
+			vsys-ldo1-supply = <&pp4200_z2>;
+			vsys-ldo2-supply = <&pp4200_z2>;
+			vsys-ldo3-supply = <&pp4200_z2>;
+			vsys-vcore-supply = <&pp4200_z2>;
+			vsys-vdram1-supply = <&pp4200_z2>;
+			vsys-vgpu-supply = <&pp4200_z2>;
+			vsys-vmodem-supply = <&pp4200_z2>;
+			vsys-vpa-supply = <&pp4200_z2>;
+			vsys-vproc11-supply = <&pp4200_z2>;
+			vsys-vproc12-supply = <&pp4200_z2>;
+			vsys-vs1-supply = <&pp4200_z2>;
+			vsys-vs2-supply = <&pp4200_z2>;
+			vs1-ldo1-supply = <&mt6366_vs1_reg>;
+			vs2-ldo1-supply = <&mt6366_vdram1_reg>;
+			vs2-ldo2-supply = <&mt6366_vs2_reg>;
+			vs2-ldo3-supply = <&mt6366_vs2_reg>;
+
+			vcore {
+				regulator-name = "pp0750_dvdd_core";
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <800000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <200>;
+				regulator-allowed-modes = <MT6397_BUCK_MODE_AUTO
+							   MT6397_BUCK_MODE_FORCE_PWM>;
+				regulator-always-on;
+			};
+
+			mt6366_vdram1_reg: vdram1 {
+				regulator-name = "pp1125_emi_vdd2";
+				regulator-min-microvolt = <1125000>;
+				regulator-max-microvolt = <1125000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <0>;
+				regulator-allowed-modes = <MT6397_BUCK_MODE_AUTO
+							   MT6397_BUCK_MODE_FORCE_PWM>;
+				regulator-always-on;
+			};
+
+			mt6366_vgpu_reg: vgpu {
+				/*
+				 * Called "ppvar_dvdd_gpu" in the schematic.
+				 * Called "ppvar_dvdd_vgpu" here to match
+				 * regulator coupling requirements.
+				 */
+				regulator-name = "ppvar_dvdd_vgpu";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <200>;
+				regulator-allowed-modes = <MT6397_BUCK_MODE_AUTO
+							   MT6397_BUCK_MODE_FORCE_PWM>;
+				regulator-coupled-with = <&mt6366_vsram_gpu_reg>;
+				regulator-coupled-max-spread = <10000>;
+			};
+
+			mt6366_vproc11_reg: vproc11 {
+				regulator-name = "ppvar_dvdd_proc_bc_mt6366";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <200>;
+				regulator-allowed-modes = <MT6397_BUCK_MODE_AUTO
+							   MT6397_BUCK_MODE_FORCE_PWM>;
+				regulator-always-on;
+			};
+
+			mt6366_vproc12_reg: vproc12 {
+				regulator-name = "ppvar_dvdd_proc_lc";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <200>;
+				regulator-allowed-modes = <MT6397_BUCK_MODE_AUTO
+							   MT6397_BUCK_MODE_FORCE_PWM>;
+				regulator-always-on;
+			};
+
+			mt6366_vs1_reg: vs1 {
+				regulator-name = "pp2000_vs1";
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <0>;
+				regulator-always-on;
+			};
+
+			mt6366_vs2_reg: vs2 {
+				regulator-name = "pp1350_vs2";
+				regulator-min-microvolt = <1350000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <0>;
+				regulator-always-on;
+			};
+
+			va12 {
+				regulator-name = "pp1200_va12";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-enable-ramp-delay = <270>;
+				regulator-always-on;
+			};
+
+			mt6366_vaud28_reg: vaud28 {
+				regulator-name = "pp2800_vaud28";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vaux18_reg: vaux18 {
+				regulator-name = "pp1840_vaux18";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1840000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vbif28_reg: vbif28 {
+				regulator-name = "pp2800_vbif28";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vcn18_reg: vcn18 {
+				regulator-name = "pp1800_vcn18_x";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vcn28_reg: vcn28 {
+				regulator-name = "pp2800_vcn28_x";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vefuse_reg: vefuse {
+				regulator-name = "pp1800_vefuse";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vfe28_reg: vfe28 {
+				regulator-name = "pp2800_vfe28_x";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vemc_reg: vemc {
+				regulator-name = "pp3000_vemc";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <60>;
+			};
+
+			mt6366_vibr_reg: vibr {
+				regulator-name = "pp2800_vibr_x";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <60>;
+			};
+
+			mt6366_vio18_reg: vio18 {
+				regulator-name = "pp1800_vio18_s3";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <2700>;
+				regulator-always-on;
+			};
+
+			mt6366_vio28_reg: vio28 {
+				regulator-name = "pp2800_vio28_x";
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			mt6366_vm18_reg: vm18 {
+				regulator-name = "pp1800_emi_vdd1";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1840000>;
+				regulator-enable-ramp-delay = <325>;
+				regulator-always-on;
+			};
+
+			mt6366_vmc_reg: vmc {
+				regulator-name = "pp3000_vmc";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <60>;
+			};
+
+			mt6366_vmddr_reg: vmddr {
+				regulator-name = "pm0750_emi_vmddr";
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <750000>;
+				regulator-enable-ramp-delay = <325>;
+				regulator-always-on;
+			};
+
+			mt6366_vmch_reg: vmch {
+				regulator-name = "pp3000_vmch";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-enable-ramp-delay = <60>;
+			};
+
+			mt6366_vcn33_reg: vcn33 {
+				regulator-name = "pp3300_vcn33_x";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-enable-ramp-delay = <270>;
+			};
+
+			vdram2 {
+				regulator-name = "pp0600_emi_vddq";
+				regulator-min-microvolt = <600000>;
+				regulator-max-microvolt = <600000>;
+				regulator-enable-ramp-delay = <3300>;
+				regulator-always-on;
+			};
+
+			mt6366_vrf12_reg: vrf12 {
+				regulator-name = "pp1200_vrf12_x";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-enable-ramp-delay = <120>;
+			};
+
+			mt6366_vrf18_reg: vrf18 {
+				regulator-name = "pp1800_vrf18_x";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-enable-ramp-delay = <120>;
+			};
+
+			vsim1 {
+				regulator-name = "pp1860_vsim1_x";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1860000>;
+				regulator-enable-ramp-delay = <540>;
+			};
+
+			mt6366_vsim2_reg: vsim2 {
+				regulator-name = "pp2760_vsim2_x";
+				regulator-min-microvolt = <2700000>;
+				regulator-max-microvolt = <2760000>;
+				regulator-enable-ramp-delay = <540>;
+			};
+
+			mt6366_vsram_gpu_reg: vsram-gpu {
+				regulator-name = "pp0900_dvdd_sram_gpu";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <240>;
+				regulator-coupled-with = <&mt6366_vgpu_reg>;
+				regulator-coupled-max-spread = <10000>;
+			};
+
+			mt6366_vsram_others_reg: vsram-others {
+				regulator-name = "pp0900_dvdd_sram_core";
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <240>;
+				regulator-always-on;
+			};
+
+			mt6366_vsram_proc11_reg: vsram-proc11 {
+				regulator-name = "pp0900_dvdd_sram_bc";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1120000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <240>;
+				regulator-always-on;
+			};
+
+			mt6366_vsram_proc12_reg: vsram-proc12 {
+				regulator-name = "pp0900_dvdd_sram_lc";
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1120000>;
+				regulator-ramp-delay = <6250>;
+				regulator-enable-ramp-delay = <240>;
+				regulator-always-on;
+			};
+
+			vusb {
+				regulator-name = "pp3070_vusb";
+				regulator-min-microvolt = <3000000>;
+				regulator-max-microvolt = <3070000>;
+				regulator-enable-ramp-delay = <270>;
+				regulator-always-on;
+			};
+
+			vxo22 {
+				regulator-name = "pp2240_vxo22";
+				regulator-min-microvolt = <2200000>;
+				regulator-max-microvolt = <2240000>;
+				regulator-enable-ramp-delay = <120>;
+				/* Feeds DCXO internally */
+				regulator-always-on;
+			};
+		};
+
+		rtc {
+			compatible = "mediatek,mt6366-rtc", "mediatek,mt6358-rtc";
+		};
+	};
+};
+
+&scp {
+	pinctrl-names = "default";
+	pinctrl-0 = <&scp_pins>;
+	firmware-name = "mediatek/mt8186/scp.img";
+	memory-region = <&scp_mem>;
+	status = "okay";
+
+	cros-ec-rpmsg {
+		compatible = "google,cros-ec-rpmsg";
+		mediatek,rpmsg-name = "cros-ec-rpmsg";
+	};
+};
+
+&spi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi1_pins>;
+	mediatek,pad-select = <0>;
+	status = "okay";
+
+	cros_ec: ec@0 {
+		compatible = "google,cros-ec-spi";
+		reg = <0>;
+		interrupts-extended = <&pio 13 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ec_ap_int>;
+		spi-max-frequency = <1000000>;
+
+		i2c_tunnel: i2c-tunnel {
+			compatible = "google,cros-ec-i2c-tunnel";
+			google,remote-bus = <1>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+
+		typec {
+			compatible = "google,cros-ec-typec";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			usb_c0: connector@0 {
+				compatible = "usb-c-connector";
+				reg = <0>;
+				label = "left";
+				power-role = "dual";
+				data-role = "host";
+				try-power-role = "source";
+			};
+
+			usb_c1: connector@1 {
+				compatible = "usb-c-connector";
+				reg = <1>;
+				label = "right";
+				power-role = "dual";
+				data-role = "host";
+				try-power-role = "source";
+			};
+		};
+	};
+};
+
+&spi2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2_pins>;
+	cs-gpios = <&pio 45 GPIO_ACTIVE_LOW>;
+	mediatek,pad-select = <0>;
+	status = "okay";
+
+	tpm@0 {
+		compatible = "google,cr50";
+		reg = <0>;
+		interrupts-extended = <&pio 15 IRQ_TYPE_EDGE_RISING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&gsc_int>;
+		spi-max-frequency = <1000000>;
+	};
+};
+
+&ssusb0 {
+	status = "okay";
+};
+
+&ssusb1 {
+	status = "okay";
+};
+
+&u3phy0 {
+	status = "okay";
+};
+
+&u3phy1 {
+	status = "okay";
+};
+
+&uart0 {
+	status = "okay";
+};
+
+&usb_host0 {
+	vbus-supply = <&pp3300_s3>;
+	status = "okay";
+};
+
+&usb_host1 {
+	vbus-supply = <&usb_p1_vbus>;
+	status = "okay";
+};
+
+&watchdog {
+	mediatek,reset-by-toprgu;
+};
+
+#include <arm/cros-ec-keyboard.dtsi>
+#include <arm/cros-ec-sbs.dtsi>
diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
index 2fec6fd1c1a7..4763ed5dc86c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
@@ -931,11 +931,17 @@
 
 				power-domain@MT8186_POWER_DOMAIN_SSUSB {
 					reg = <MT8186_POWER_DOMAIN_SSUSB>;
+					clocks = <&topckgen CLK_TOP_USB_TOP>,
+						 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>;
+					clock-names = "sys_ck", "ref_ck";
 					#power-domain-cells = <0>;
 				};
 
 				power-domain@MT8186_POWER_DOMAIN_SSUSB_P1 {
 					reg = <MT8186_POWER_DOMAIN_SSUSB_P1>;
+					clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>,
+						 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>;
+					clock-names = "sys_ck", "ref_ck";
 					#power-domain-cells = <0>;
 				};
 
@@ -1061,7 +1067,7 @@
 						reg = <MT8186_POWER_DOMAIN_VENC>;
 						clocks = <&topckgen CLK_TOP_VENC>,
 							 <&vencsys CLK_VENC_CKE1_VENC>;
-						clock-names = "venc0", "larb";
+						clock-names = "venc0", "subsys-larb";
 						mediatek,infracfg = <&infracfg_ao>;
 						#power-domain-cells = <0>;
 					};
@@ -1530,8 +1536,9 @@
 			clocks = <&topckgen CLK_TOP_USB_TOP>,
 				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>,
 				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_HCLK>,
-				 <&infracfg_ao CLK_INFRA_AO_ICUSB>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck";
+				 <&infracfg_ao CLK_INFRA_AO_ICUSB>,
+				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck";
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH 0>;
 			phys = <&u2port0 PHY_TYPE_USB2>;
 			power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB>;
@@ -1595,8 +1602,9 @@
 			clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>,
 				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>,
 				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_HCLK>,
-				 <&clk26m>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck";
+				 <&clk26m>,
+				 <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_XHCI>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck";
 			interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH 0>;
 			phys = <&u2port1 PHY_TYPE_USB2>, <&u3port1 PHY_TYPE_USB3>;
 			power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB_P1>;
@@ -1672,6 +1680,10 @@
 				reg = <0x59c 0x4>;
 				bits = <0 3>;
 			};
+
+			socinfo-data1@7a0 {
+				reg = <0x7a0 0x4>;
+			};
 		};
 
 		mipi_tx0: dsi-phy@11cc0000 {
@@ -1959,6 +1971,43 @@
 			power-domains = <&spm MT8186_POWER_DOMAIN_IMG2>;
 		};
 
+		video_decoder: video-decoder@16000000 {
+			compatible = "mediatek,mt8186-vcodec-dec";
+			reg = <0 0x16000000 0 0x1000>;
+			ranges;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>;
+			iommus = <&iommu_mm IOMMU_PORT_L4_HW_VDEC_MC_EXT>;
+			mediatek,scp = <&scp>;
+
+			vcodec_core: video-codec@16025000 {
+				compatible = "mediatek,mtk-vcodec-core";
+				reg = <0 0x16025000 0 0x1000>;
+				interrupts = <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH 0>;
+				iommus = <&iommu_mm IOMMU_PORT_L4_HW_VDEC_MC_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_UFO_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_PP_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_PRED_RD_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_PRED_WR_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_PPWRAP_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_TILE_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_VLD_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_VLD2_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_AVC_MV_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_UFO_ENC_EXT>,
+					 <&iommu_mm IOMMU_PORT_L4_HW_VDEC_RG_CTRL_DMA_EXT>;
+				clocks = <&topckgen CLK_TOP_VDEC>,
+					 <&vdecsys CLK_VDEC_CKEN>,
+					 <&vdecsys CLK_VDEC_LARB1_CKEN>,
+					 <&topckgen CLK_TOP_UNIVPLL_D3>;
+				clock-names = "vdec-sel", "vdec-soc-vdec", "vdec", "vdec-top";
+				assigned-clocks = <&topckgen CLK_TOP_VDEC>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D3>;
+				power-domains = <&spm MT8186_POWER_DOMAIN_VDEC>;
+			};
+		};
+
 		larb4: smi@1602e000 {
 			compatible = "mediatek,mt8186-smi-larb";
 			reg = <0 0x1602e000 0 0x1000>;
@@ -1993,6 +2042,40 @@
 			power-domains = <&spm MT8186_POWER_DOMAIN_VENC>;
 		};
 
+		venc: video-encoder@17020000 {
+			compatible = "mediatek,mt8186-vcodec-enc", "mediatek,mt8183-vcodec-enc";
+			reg = <0 0x17020000 0 0x2000>;
+			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH 0>;
+			iommus = <&iommu_mm IOMMU_PORT_L7_VENC_RCPU>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_REC>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_BSDMA>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_SV_COMV>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_RD_COMV>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_CUR_LUMA>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_CUR_CHROMA>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_REF_LUMA>,
+				 <&iommu_mm IOMMU_PORT_L7_VENC_REF_CHROMA>;
+			clocks = <&vencsys CLK_VENC_CKE1_VENC>;
+			clock-names = "venc_sel";
+			assigned-clocks = <&topckgen CLK_TOP_VENC>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D3>;
+			power-domains = <&spm MT8186_POWER_DOMAIN_VENC>;
+			mediatek,scp = <&scp>;
+		};
+
+		jpgenc: jpeg-encoder@17030000 {
+			compatible = "mediatek,mt8186-jpgenc", "mediatek,mtk-jpgenc";
+			reg = <0 0x17030000 0 0x10000>;
+			interrupts = <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH 0>;
+			clocks = <&vencsys CLK_VENC_CKE2_JPGENC>;
+			clock-names = "jpgenc";
+			iommus = <&iommu_mm IOMMU_PORT_L7_JPGENC_Y_RDMA>,
+				 <&iommu_mm IOMMU_PORT_L7_JPGENC_C_RDMA>,
+				 <&iommu_mm IOMMU_PORT_L7_JPGENC_Q_TABLE>,
+				 <&iommu_mm IOMMU_PORT_L7_JPGENC_BSDMA>;
+			power-domains = <&spm MT8186_POWER_DOMAIN_VENC>;
+		};
+
 		camsys: clock-controller@1a000000 {
 			compatible = "mediatek,mt8186-camsys";
 			reg = <0 0x1a000000 0 0x1000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
index d87aab8d7a79..9b738f6a5d21 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
@@ -1332,14 +1332,11 @@
 		spi-max-frequency = <3000000>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&cros_ec_int>;
+		wakeup-source;
 
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		base_detection: cbas {
-			compatible = "google,cros-cbas";
-		};
-
 		cros_ec_pwm: pwm {
 			compatible = "google,cros-ec-pwm";
 			#pwm-cells = <1>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
index 6dd32dbfb832..05e401670bce 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
@@ -1164,6 +1164,14 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
+			socinfo-data1@44 {
+				reg = <0x044 0x4>;
+			};
+
+			socinfo-data2@50 {
+				reg = <0x050 0x4>;
+			};
+
 			lvts_e_data1: data1@1c0 {
 				reg = <0x1c0 0x58>;
 			};
@@ -1814,7 +1822,7 @@
 			mediatek,scp = <&scp>;
 			power-domains = <&spm MT8192_POWER_DOMAIN_VENC>;
 			clocks = <&vencsys CLK_VENC_SET1_VENC>;
-			clock-names = "venc-set1";
+			clock-names = "venc_sel";
 			assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>;
 			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D4>;
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts
index 2d5e8f371b6d..a82d716f10d4 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts
@@ -23,3 +23,7 @@
 &ts_10 {
 	status = "okay";
 };
+
+&watchdog {
+	/delete-property/ mediatek,disable-extrst;
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts
index 2586c32ce6e6..2fe20e0dad83 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts
@@ -43,3 +43,7 @@
 &ts_10 {
 	status = "okay";
 };
+
+&watchdog {
+	/delete-property/ mediatek,disable-extrst;
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts
index f54f9477b99d..dd294ca98194 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts
@@ -44,3 +44,7 @@
 &ts_10 {
 	status = "okay";
 };
+
+&watchdog {
+	/delete-property/ mediatek,disable-extrst;
+};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index 3c6079edda19..f94c07f8b933 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -1149,6 +1149,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&cros_ec_int>;
 		spi-max-frequency = <3000000>;
+		wakeup-source;
 
 		keyboard-backlight {
 			compatible = "google,cros-kbd-led-backlight";
@@ -1291,11 +1292,32 @@
 	status = "okay";
 };
 
+/*
+ * For the USB Type-C ports the role and alternate modes switching is
+ * done by the EC so we set dr_mode to host to avoid interfering.
+ */
+&ssusb0 {
+	dr_mode = "host";
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb2 {
+	dr_mode = "host";
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb3 {
+	dr_mode = "host";
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
 &xhci0 {
 	status = "okay";
 
 	rx-fifo-depth = <3072>;
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
 
@@ -1309,8 +1331,6 @@
 
 &xhci2 {
 	status = "okay";
-
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
 
@@ -1319,7 +1339,6 @@
 
 	/* MT7921's USB Bluetooth has issues with USB2 LPM */
 	usb2-lpm-disable;
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	vbus-supply = <&usb_vbus>;
 };
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
index 69c7f3954ae5..b82f7176b4a1 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
@@ -128,6 +128,7 @@
 		compatible = "mediatek,mt6360";
 		reg = <0x34>;
 		interrupt-controller;
+		#interrupt-cells = <1>;
 		interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>;
 		interrupt-names = "IRQB";
 
@@ -528,8 +529,22 @@
 	status = "okay";
 };
 
-&xhci0 {
+&ssusb0 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb2 {
 	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb3 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&xhci0 {
 	vbus-supply = <&otg_vbus_regulator>;
 	status = "okay";
 };
@@ -540,11 +555,9 @@
 };
 
 &xhci2 {
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	status = "okay";
 };
 
 &xhci3 {
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-evb.dts b/arch/arm64/boot/dts/mediatek/mt8195-evb.dts
index 690dc7717f2c..341b6e074139 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-evb.dts
@@ -160,6 +160,18 @@
 	status = "okay";
 };
 
+&ssusb0 {
+	status = "okay";
+};
+
+&ssusb2 {
+	status = "okay";
+};
+
+&ssusb3 {
+	status = "okay";
+};
+
 &xhci0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index b9101662ce40..ea6dc220e1cc 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -1347,29 +1347,40 @@
 			};
 		};
 
-		xhci0: usb@11200000 {
-			compatible = "mediatek,mt8195-xhci",
-				     "mediatek,mtk-xhci";
-			reg = <0 0x11200000 0 0x1000>,
-			      <0 0x11203e00 0 0x0100>;
+		ssusb0: usb@11201000 {
+			compatible = "mediatek,mt8195-mtu3", "mediatek,mtu3";
+			reg = <0 0x11201000 0 0x2dff>, <0 0x11203e00 0 0x0100>;
 			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port0 PHY_TYPE_USB2>,
-			       <&u3port0 PHY_TYPE_USB3>;
-			assigned-clocks = <&topckgen CLK_TOP_USB_TOP>,
-					  <&topckgen CLK_TOP_SSUSB_XHCI>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			ranges = <0 0 0 0x11200000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH 0>;
 			clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB>,
 				 <&topckgen CLK_TOP_SSUSB_REF>,
-				 <&apmixedsys CLK_APMIXED_USB1PLL>,
-				 <&clk26m>,
 				 <&infracfg_ao CLK_INFRA_AO_SSUSB_XHCI>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck",
-				      "xhci_ck";
-			mediatek,syscon-wakeup = <&pericfg 0x400 103>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			phys = <&u2port0 PHY_TYPE_USB2>, <&u3port0 PHY_TYPE_USB3>;
 			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x400 103>;
 			status = "disabled";
+
+			xhci0: usb@0 {
+				compatible = "mediatek,mt8195-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_USB_TOP>,
+						  <&topckgen CLK_TOP_SSUSB_XHCI>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
+							 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB>,
+					 <&topckgen CLK_TOP_SSUSB_REF>,
+					 <&apmixedsys CLK_APMIXED_USB1PLL>,
+					 <&clk26m>,
+					 <&infracfg_ao CLK_INFRA_AO_SSUSB_XHCI>;
+				clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck";
+				status = "disabled";
+			};
 		};
 
 		mmc0: mmc@11230000 {
@@ -1450,52 +1461,68 @@
 			status = "disabled";
 		};
 
-		xhci2: usb@112a0000 {
-			compatible = "mediatek,mt8195-xhci",
-				     "mediatek,mtk-xhci";
-			reg = <0 0x112a0000 0 0x1000>,
-			      <0 0x112a3e00 0 0x0100>;
+		ssusb2: usb@112a1000 {
+			compatible = "mediatek,mt8195-mtu3", "mediatek,mtu3";
+			reg = <0 0x112a1000 0 0x2dff>, <0 0x112a3e00 0 0x0100>;
 			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 533 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port2 PHY_TYPE_USB2>;
-			assigned-clocks = <&topckgen CLK_TOP_USB_TOP_2P>,
-					  <&topckgen CLK_TOP_SSUSB_XHCI_2P>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			ranges = <0 0 0 0x112a0000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 532 IRQ_TYPE_LEVEL_HIGH 0>;
+			assigned-clocks = <&topckgen CLK_TOP_USB_TOP_2P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
 			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_2P_BUS>,
 				 <&topckgen CLK_TOP_SSUSB_P2_REF>,
-				 <&clk26m>,
-				 <&clk26m>,
 				 <&pericfg_ao CLK_PERI_AO_SSUSB_2P_XHCI>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck",
-				      "xhci_ck";
-			mediatek,syscon-wakeup = <&pericfg 0x400 105>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			phys = <&u2port2 PHY_TYPE_USB2>;
 			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x400 105>;
 			status = "disabled";
+
+			xhci2: usb@0 {
+				compatible = "mediatek,mt8195-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 533 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_2P>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_2P_XHCI>;
+				clock-names = "sys_ck";
+				status = "disabled";
+			};
 		};
 
-		xhci3: usb@112b0000 {
-			compatible = "mediatek,mt8195-xhci",
-				     "mediatek,mtk-xhci";
-			reg = <0 0x112b0000 0 0x1000>,
-			      <0 0x112b3e00 0 0x0100>;
+		ssusb3: usb@112b1000 {
+			compatible = "mediatek,mt8195-mtu3", "mediatek,mtu3";
+			reg = <0 0x112b1000 0 0x2dff>, <0 0x112b3e00 0 0x0100>;
 			reg-names = "mac", "ippc";
-			interrupts = <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH 0>;
-			phys = <&u2port3 PHY_TYPE_USB2>;
-			assigned-clocks = <&topckgen CLK_TOP_USB_TOP_3P>,
-					  <&topckgen CLK_TOP_SSUSB_XHCI_3P>;
-			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>,
-						 <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+			ranges = <0 0 0 0x112b0000 0 0x3f00>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			interrupts = <GIC_SPI 535 IRQ_TYPE_LEVEL_HIGH 0>;
+			assigned-clocks = <&topckgen CLK_TOP_USB_TOP_3P>;
+			assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
 			clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_3P_BUS>,
 				 <&topckgen CLK_TOP_SSUSB_P3_REF>,
-				 <&clk26m>,
-				 <&clk26m>,
 				 <&pericfg_ao CLK_PERI_AO_SSUSB_3P_XHCI>;
-			clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck",
-				      "xhci_ck";
-			mediatek,syscon-wakeup = <&pericfg 0x400 106>;
+			clock-names = "sys_ck", "ref_ck", "mcu_ck";
+			phys = <&u2port3 PHY_TYPE_USB2>;
 			wakeup-source;
+			mediatek,syscon-wakeup = <&pericfg 0x400 106>;
 			status = "disabled";
+
+			xhci3: usb@0 {
+				compatible = "mediatek,mt8195-xhci", "mediatek,mtk-xhci";
+				reg = <0 0 0 0x1000>;
+				reg-names = "mac";
+				interrupts = <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH 0>;
+				assigned-clocks = <&topckgen CLK_TOP_SSUSB_XHCI_3P>;
+				assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D5_D4>;
+				clocks = <&pericfg_ao CLK_PERI_AO_SSUSB_3P_XHCI>;
+				clock-names = "sys_ck";
+				status = "disabled";
+			};
 		};
 
 		pcie0: pcie@112f0000 {
@@ -1701,6 +1728,9 @@
 			svs_calib_data: svs-calib@580 {
 				reg = <0x580 0x64>;
 			};
+			socinfo-data1@7a0 {
+				reg = <0x7a0 0x4>;
+			};
 		};
 
 		u3phy2: t-phy@11c40000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
index 7fc515a07c65..1558649f633c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8395-genio-1200-evk.dts
@@ -880,6 +880,21 @@
 	status = "disabled";
 };
 
+&ssusb0 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb2 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&ssusb3 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
 &xhci0 {
 	status = "okay";
 };
@@ -890,11 +905,9 @@
 };
 
 &xhci2 {
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	status = "okay";
 };
 
 &xhci3 {
-	vusb33-supply = <&mt6359_vusb_ldo_reg>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
new file mode 100644
index 000000000000..e5d9b671a405
--- /dev/null
+++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
@@ -0,0 +1,825 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (C) 2023 Radxa Limited
+ * Copyright (C) 2024 Collabora Ltd.
+ *                    AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
+ */
+
+#include "mt8195.dtsi"
+#include "mt6359.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/pinctrl/mt8195-pinfunc.h>
+#include <dt-bindings/regulator/mediatek,mt6360-regulator.h>
+#include <dt-bindings/spmi/spmi.h>
+#include <dt-bindings/usb/pd.h>
+
+/ {
+	model = "Radxa NIO 12L";
+	chassis-type = "embedded";
+	compatible = "radxa,nio-12l", "mediatek,mt8395", "mediatek,mt8195";
+
+	aliases {
+		i2c0 = &i2c2;
+		i2c1 = &i2c3;
+		i2c2 = &i2c4;
+		i2c3 = &i2c0;
+		i2c4 = &i2c1;
+		ethernet0 = &eth;
+		serial0 = &uart0;
+		serial1 = &uart1;
+		spi0 = &spi1;
+		spi1 = &spi2;
+	};
+
+	chosen {
+		stdout-path = "serial0:921600n8";
+	};
+
+	firmware {
+		optee {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+	};
+
+	memory@40000000 {
+		device_type = "memory";
+		reg = <0 0x40000000 0x1 0x0>;
+	};
+
+	wifi_vreg: regulator-wifi-3v3-en {
+		compatible = "regulator-fixed";
+		regulator-name = "wifi_3v3_en";
+		regulator-always-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		enable-active-high;
+		gpio = <&pio 67 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&wifi_vreg_pins>;
+		vin-supply = <&vsys>;
+	};
+
+	/* system wide switching 5.0V power rail */
+	vsys: regulator-vsys {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_vsys>;
+	};
+
+	vsys_buck: regulator-vsys-buck {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys_buck";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_vsys>;
+	};
+
+	/* Rail from power-only "TYPE C DC" port */
+	vcc5v0_vsys: regulator-vcc5v0-sys {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/*
+		 * 12 MiB reserved for OP-TEE (BL32)
+		 * +-----------------------+ 0x43e0_0000
+		 * |      SHMEM 2MiB       |
+		 * +-----------------------+ 0x43c0_0000
+		 * |        | TA_RAM  8MiB |
+		 * + TZDRAM +--------------+ 0x4340_0000
+		 * |        | TEE_RAM 2MiB |
+		 * +-----------------------+ 0x4320_0000
+		 */
+		optee_reserved: optee@43200000 {
+			reg = <0 0x43200000 0 0xc00000>;
+			no-map;
+		};
+
+		scp_mem: memory@50000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x50000000 0 0x2900000>;
+			no-map;
+		};
+
+		vpu_mem: memory@53000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x53000000 0 0x1400000>; /* 20 MB */
+		};
+
+		/* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+		bl31_secmon_mem: memory@54600000 {
+			reg = <0 0x54600000 0x0 0x200000>;
+			no-map;
+		};
+
+		afe_mem: memory@60000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x60000000 0 0x1100000>;
+			no-map;
+		};
+
+		apu_mem: memory@62000000 {
+			compatible = "shared-dma-pool";
+			reg = <0 0x62000000 0 0x1400000>; /* 20 MB */
+		};
+	};
+};
+
+&eth {
+	phy-mode = "rgmii-rxid";
+	phy-handle = <&rgmii_phy>;
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&eth_default_pins>;
+	pinctrl-1 = <&eth_sleep_pins>;
+	mediatek,tx-delay-ps = <2030>;
+	mediatek,mac-wol;
+	snps,reset-gpio = <&pio 93 GPIO_ACTIVE_HIGH>;
+	snps,reset-delays-us = <0 20000 100000>;
+	status = "okay";
+
+	mdio {
+		rgmii_phy: ethernet-phy@1 {
+			compatible = "ethernet-phy-id001c.c916";
+			reg = <0x1>;
+		};
+	};
+};
+
+&gpu {
+	mali-supply = <&mt6315_7_vbuck1>;
+	status = "okay";
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&i2c2_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	typec-mux@48 {
+		compatible = "ite,it5205";
+		reg = <0x48>;
+
+		mode-switch;
+		orientation-switch;
+
+		vcc-supply = <&mt6359_vibr_ldo_reg>;
+
+		port {
+			it5205_sbu_mux: endpoint {
+				remote-endpoint = <&typec_con_mux>;
+			};
+		};
+	};
+};
+
+&i2c4 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&i2c4_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	/* I2C4 exposed at 39-pins MIPI-LCD connector */
+};
+
+&i2c6 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&i2c6_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	mt6360: pmic@34 {
+		compatible = "mediatek,mt6360";
+		reg = <0x34>;
+		interrupts-extended = <&pio 101 IRQ_TYPE_EDGE_FALLING>;
+		interrupt-names = "IRQB";
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		pinctrl-0 = <&mt6360_pins>;
+
+		charger {
+			compatible = "mediatek,mt6360-chg";
+			richtek,vinovp-microvolt = <14500000>;
+
+			otg_vbus_regulator: usb-otg-vbus-regulator {
+				regulator-name = "usb-otg-vbus";
+				regulator-min-microvolt = <4425000>;
+				regulator-max-microvolt = <5825000>;
+			};
+		};
+
+		regulator {
+			compatible = "mediatek,mt6360-regulator";
+			LDO_VIN1-supply = <&vsys_buck>;
+			LDO_VIN3-supply = <&mt6360_buck2>;
+
+			mt6360_buck1: buck1 {
+				regulator-name = "emi_vdd2";
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP
+							   MT6360_OPMODE_ULP>;
+				regulator-always-on;
+			};
+
+			mt6360_buck2: buck2 {
+				regulator-name = "emi_vddq";
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP
+							   MT6360_OPMODE_ULP>;
+				regulator-always-on;
+			};
+
+			mt6360_ldo1: ldo1 {
+				regulator-name = "ext_lcd_3v3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+				regulator-always-on;
+			};
+
+			mt6360_ldo2: ldo2 {
+				regulator-name = "panel1_p1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+			};
+
+			mt6360_ldo3: ldo3 {
+				regulator-name = "vmc_pmu";
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3600000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+			};
+
+			mt6360_ldo5: ldo5 {
+				regulator-name = "vmch_pmu";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+				regulator-always-on;
+			};
+
+			mt6360_ldo6: ldo6 {
+				regulator-name = "mt6360_ldo6"; /* Test point */
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <2100000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+			};
+
+			mt6360_ldo7: ldo7 {
+				regulator-name = "emi_vmddr_en";
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <2100000>;
+				regulator-allowed-modes = <MT6360_OPMODE_NORMAL
+							   MT6360_OPMODE_LP>;
+				regulator-always-on;
+			};
+		};
+
+		typec {
+			compatible = "mediatek,mt6360-tcpc";
+			interrupts-extended = <&pio 100 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-names = "PD_IRQB";
+
+			connector {
+				compatible = "usb-c-connector";
+				label = "USB-C";
+				data-role = "dual";
+				op-sink-microwatt = <10000000>;
+				power-role = "dual";
+				try-power-role = "sink";
+
+				source-pdos = <PDO_FIXED(5000, 1000,
+							 PDO_FIXED_DUAL_ROLE |
+							 PDO_FIXED_DATA_SWAP)>;
+				sink-pdos = <PDO_FIXED(5000, 3000,
+						       PDO_FIXED_DUAL_ROLE |
+						       PDO_FIXED_DATA_SWAP)>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						typec_con_hs: endpoint {
+							remote-endpoint = <&mtu3_hs0_role_sw>;
+						};
+					};
+
+					port@2 {
+						reg = <2>;
+						typec_con_mux: endpoint {
+							remote-endpoint = <&it5205_sbu_mux>;
+						};
+					};
+				};
+			};
+		};
+	};
+};
+
+/* MMC0 Controller: eMMC (HS400). Power lines are shared with UFS! */
+&mmc0 {
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_default_pins>;
+	pinctrl-1 = <&mmc0_uhs_pins>;
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	hs400-ds-delay = <0x14c11>;
+	cap-mmc-highspeed;
+	cap-mmc-hw-reset;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	no-sdio;
+	no-sd;
+	non-removable;
+	vmmc-supply = <&mt6359_vemc_1_ldo_reg>;
+	vqmmc-supply = <&mt6359_vufs_ldo_reg>;
+	status = "okay";
+};
+
+/* MMC1 Controller: MicroSD card slot */
+&mmc1 {
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc1_default_pins>, <&mmc1_pins_detect>;
+	pinctrl-1 = <&mmc1_default_pins>;
+	bus-width = <4>;
+	max-frequency = <200000000>;
+	cap-sd-highspeed;
+	cd-gpios = <&pio 129 GPIO_ACTIVE_LOW>;
+	no-mmc;
+	no-sdio;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	vmmc-supply = <&mt6360_ldo5>;
+	vqmmc-supply = <&mt6360_ldo3>;
+	status = "okay";
+};
+
+&mt6359_vaud18_ldo_reg {
+	regulator-always-on;
+};
+
+&mt6359_vbbck_ldo_reg {
+	regulator-always-on;
+};
+
+/* For USB Hub */
+&mt6359_vcamio_ldo_reg {
+	regulator-always-on;
+};
+
+&mt6359_vcn33_2_bt_ldo_reg {
+	regulator-min-microvolt = <3300000>;
+	regulator-max-microvolt = <3300000>;
+};
+
+&mt6359_vcore_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vgpu11_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vproc1_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vproc2_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vpu_buck_reg {
+	regulator-always-on;
+};
+
+&mt6359_vrf12_ldo_reg {
+	regulator-always-on;
+};
+
+&mt6359_vsram_md_ldo_reg {
+	regulator-always-on;
+};
+
+/* for GPU SRAM */
+&mt6359_vsram_others_ldo_reg {
+	regulator-min-microvolt = <750000>;
+	regulator-max-microvolt = <750000>;
+};
+
+&pio {
+	eth_default_pins: eth-default-pins {
+		pins-cc {
+			pinmux = <PINMUX_GPIO85__FUNC_GBE_TXC>,
+				 <PINMUX_GPIO86__FUNC_GBE_RXC>,
+				 <PINMUX_GPIO87__FUNC_GBE_RXDV>,
+				 <PINMUX_GPIO88__FUNC_GBE_TXEN>;
+			drive-strength = <8>;
+		};
+
+		pins-mdio {
+			pinmux = <PINMUX_GPIO89__FUNC_GBE_MDC>,
+				 <PINMUX_GPIO90__FUNC_GBE_MDIO>;
+			input-enable;
+		};
+
+		pins-power {
+			pinmux = <PINMUX_GPIO91__FUNC_GPIO91>,
+				 <PINMUX_GPIO92__FUNC_GPIO92>;
+			output-high;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO93__FUNC_GPIO93>;
+		};
+
+		pins-rxd {
+			pinmux = <PINMUX_GPIO81__FUNC_GBE_RXD3>,
+				 <PINMUX_GPIO82__FUNC_GBE_RXD2>,
+				 <PINMUX_GPIO83__FUNC_GBE_RXD1>,
+				 <PINMUX_GPIO84__FUNC_GBE_RXD0>;
+		};
+
+		pins-txd {
+			pinmux = <PINMUX_GPIO77__FUNC_GBE_TXD3>,
+				 <PINMUX_GPIO78__FUNC_GBE_TXD2>,
+				 <PINMUX_GPIO79__FUNC_GBE_TXD1>,
+				 <PINMUX_GPIO80__FUNC_GBE_TXD0>;
+			drive-strength = <8>;
+		};
+	};
+
+	eth_sleep_pins: eth-sleep-pins {
+		pins-cc {
+			pinmux = <PINMUX_GPIO85__FUNC_GPIO85>,
+				 <PINMUX_GPIO86__FUNC_GPIO86>,
+				 <PINMUX_GPIO87__FUNC_GPIO87>,
+				 <PINMUX_GPIO88__FUNC_GPIO88>;
+		};
+
+		pins-mdio {
+			pinmux = <PINMUX_GPIO89__FUNC_GPIO89>,
+				 <PINMUX_GPIO90__FUNC_GPIO90>;
+			bias-disable;
+			input-disable;
+		};
+
+		pins-rxd {
+			pinmux = <PINMUX_GPIO81__FUNC_GPIO81>,
+				 <PINMUX_GPIO82__FUNC_GPIO82>,
+				 <PINMUX_GPIO83__FUNC_GPIO83>,
+				 <PINMUX_GPIO84__FUNC_GPIO84>;
+		};
+
+		pins-txd {
+			pinmux = <PINMUX_GPIO77__FUNC_GPIO77>,
+				 <PINMUX_GPIO78__FUNC_GPIO78>,
+				 <PINMUX_GPIO79__FUNC_GPIO79>,
+				 <PINMUX_GPIO80__FUNC_GPIO80>;
+		};
+	};
+
+	i2c2_pins: i2c2-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO12__FUNC_SDA2>,
+				 <PINMUX_GPIO13__FUNC_SCL2>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_111>;
+			drive-strength = <6>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c4_pins: i2c4-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO16__FUNC_SDA4>,
+				 <PINMUX_GPIO17__FUNC_SCL4>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_111>;
+			drive-strength-microamp = <1000>;
+		};
+	};
+
+	i2c6_pins: i2c6-pins {
+		pins {
+			pinmux = <PINMUX_GPIO25__FUNC_SDA6>,
+				 <PINMUX_GPIO26__FUNC_SCL6>;
+			bias-pull-up = <MTK_PULL_SET_RSEL_111>;
+		};
+	};
+
+	mmc0_default_pins: mmc0-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO122__FUNC_MSDC0_CLK>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+			drive-strength = <6>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO126__FUNC_MSDC0_DAT0>,
+				 <PINMUX_GPIO125__FUNC_MSDC0_DAT1>,
+				 <PINMUX_GPIO124__FUNC_MSDC0_DAT2>,
+				 <PINMUX_GPIO123__FUNC_MSDC0_DAT3>,
+				 <PINMUX_GPIO119__FUNC_MSDC0_DAT4>,
+				 <PINMUX_GPIO118__FUNC_MSDC0_DAT5>,
+				 <PINMUX_GPIO117__FUNC_MSDC0_DAT6>,
+				 <PINMUX_GPIO116__FUNC_MSDC0_DAT7>,
+				 <PINMUX_GPIO121__FUNC_MSDC0_CMD>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+			drive-strength = <6>;
+			input-enable;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO120__FUNC_MSDC0_RSTB>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+			drive-strength = <6>;
+		};
+	};
+
+	mmc0_uhs_pins: mmc0-uhs-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO122__FUNC_MSDC0_CLK>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+			drive-strength = <8>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO126__FUNC_MSDC0_DAT0>,
+				 <PINMUX_GPIO125__FUNC_MSDC0_DAT1>,
+				 <PINMUX_GPIO124__FUNC_MSDC0_DAT2>,
+				 <PINMUX_GPIO123__FUNC_MSDC0_DAT3>,
+				 <PINMUX_GPIO119__FUNC_MSDC0_DAT4>,
+				 <PINMUX_GPIO118__FUNC_MSDC0_DAT5>,
+				 <PINMUX_GPIO117__FUNC_MSDC0_DAT6>,
+				 <PINMUX_GPIO116__FUNC_MSDC0_DAT7>,
+				 <PINMUX_GPIO121__FUNC_MSDC0_CMD>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+			drive-strength = <8>;
+			input-enable;
+		};
+
+		pins-ds {
+			pinmux = <PINMUX_GPIO127__FUNC_MSDC0_DSL>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+			drive-strength = <8>;
+		};
+
+		pins-rst {
+			pinmux = <PINMUX_GPIO120__FUNC_MSDC0_RSTB>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+			drive-strength = <8>;
+		};
+	};
+
+	mmc1_default_pins: mmc1-default-pins {
+		pins-clk {
+			pinmux = <PINMUX_GPIO111__FUNC_MSDC1_CLK>;
+			bias-pull-down = <MTK_PUPD_SET_R1R0_10>;
+			drive-strength = <8>;
+		};
+
+		pins-cmd-dat {
+			pinmux = <PINMUX_GPIO110__FUNC_MSDC1_CMD>,
+				 <PINMUX_GPIO112__FUNC_MSDC1_DAT0>,
+				 <PINMUX_GPIO113__FUNC_MSDC1_DAT1>,
+				 <PINMUX_GPIO114__FUNC_MSDC1_DAT2>,
+				 <PINMUX_GPIO115__FUNC_MSDC1_DAT3>;
+			bias-pull-up = <MTK_PUPD_SET_R1R0_01>;
+			drive-strength = <8>;
+			input-enable;
+		};
+	};
+
+	mmc1_pins_detect: mmc1-detect-pins {
+		pins-insert {
+			pinmux = <PINMUX_GPIO129__FUNC_GPIO129>;
+			bias-pull-up;
+		};
+	};
+
+	mt6360_pins: mt6360-pins {
+		pins-irq {
+			pinmux = <PINMUX_GPIO100__FUNC_GPIO100>,
+				 <PINMUX_GPIO101__FUNC_GPIO101>;
+			input-enable;
+			bias-pull-up;
+		};
+	};
+
+	pcie0_default_pins: pcie0-default-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO19__FUNC_WAKEN>,
+				 <PINMUX_GPIO20__FUNC_PERSTN>,
+				 <PINMUX_GPIO21__FUNC_CLKREQN>;
+			bias-pull-up;
+		};
+	};
+
+	pcie1_default_pins: pcie1-default-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO0__FUNC_PERSTN_1>,
+				 <PINMUX_GPIO1__FUNC_CLKREQN_1>,
+				 <PINMUX_GPIO2__FUNC_WAKEN_1>;
+			bias-disable;
+		};
+	};
+
+	spi1_pins: spi1-default-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO136__FUNC_SPIM1_CSB>,
+				 <PINMUX_GPIO137__FUNC_SPIM1_CLK>,
+				 <PINMUX_GPIO138__FUNC_SPIM1_MO>,
+				 <PINMUX_GPIO139__FUNC_SPIM1_MI>;
+			bias-disable;
+		};
+	};
+
+	spi2_pins: spi2-default-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO140__FUNC_SPIM2_CSB>,
+				 <PINMUX_GPIO141__FUNC_SPIM2_CLK>,
+				 <PINMUX_GPIO142__FUNC_SPIM2_MO>,
+				 <PINMUX_GPIO143__FUNC_SPIM2_MI>;
+			bias-disable;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO98__FUNC_UTXD0>,
+				 <PINMUX_GPIO99__FUNC_URXD0>;
+		};
+	};
+
+	uart1_pins: uart1-pins {
+		pins-bus {
+			pinmux = <PINMUX_GPIO102__FUNC_UTXD1>,
+				 <PINMUX_GPIO103__FUNC_URXD1>;
+		};
+	};
+
+	wifi_vreg_pins: wifi-vreg-pins {
+		pins-wifi-pmu-en {
+			pinmux = <PINMUX_GPIO65__FUNC_GPIO65>;
+			output-high;
+		};
+
+		pins-wifi-vreg-en {
+			pinmux = <PINMUX_GPIO67__FUNC_GPIO67>;
+		};
+	};
+};
+
+&pcie0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie0_default_pins>;
+	status = "okay";
+};
+
+&pcie1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie1_default_pins>;
+	status = "okay";
+};
+
+&pmic {
+	interrupts-extended = <&pio 222 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&scp {
+	memory-region = <&scp_mem>;
+	status = "okay";
+};
+
+&spi1 {
+	/* Exposed at 40 pin connector */
+	pinctrl-0 = <&spi1_pins>;
+	pinctrl-names = "default";
+	mediatek,pad-select = <0>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+};
+
+&spi2 {
+	/* Exposed at 40 pin connector */
+	pinctrl-0 = <&spi2_pins>;
+	pinctrl-names = "default";
+	mediatek,pad-select = <0>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "okay";
+};
+
+&spmi {
+	#address-cells = <2>;
+	#size-cells = <0>;
+
+	mt6315_6: pmic@6 {
+		compatible = "mediatek,mt6315-regulator";
+		reg = <0x6 SPMI_USID>;
+
+		regulators {
+			mt6315_6_vbuck1: vbuck1 {
+				regulator-compatible = "vbuck1";
+				regulator-name = "Vbcpu";
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1193750>;
+				regulator-enable-ramp-delay = <256>;
+				regulator-allowed-modes = <0 1 2>;
+				regulator-always-on;
+			};
+		};
+	};
+
+	mt6315_7: pmic@7 {
+		compatible = "mediatek,mt6315-regulator";
+		reg = <0x7 SPMI_USID>;
+
+		regulators {
+			mt6315_7_vbuck1: vbuck1 {
+				regulator-compatible = "vbuck1";
+				regulator-name = "Vgpu";
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1193750>;
+				regulator-enable-ramp-delay = <256>;
+				regulator-allowed-modes = <0 1 2>;
+			};
+		};
+	};
+};
+
+&uart0 {
+	/* Exposed at 40 pin connector */
+	pinctrl-0 = <&uart0_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&uart1 {
+	/* Exposed at 40 pin connector */
+	pinctrl-0 = <&uart1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&ssusb0 {
+	role-switch-default-mode = "host";
+	usb-role-switch;
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+
+	port {
+		mtu3_hs0_role_sw: endpoint {
+			remote-endpoint = <&typec_con_hs>;
+		};
+	};
+};
+
+&ssusb2 {
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	status = "okay";
+};
+
+&xhci0 {
+	vbus-supply = <&otg_vbus_regulator>;
+	status = "okay";
+};
+
+&xhci1 {
+	/* MT7921's USB Bluetooth has issues with USB2 LPM */
+	usb2-lpm-disable;
+	vusb33-supply = <&mt6359_vusb_ldo_reg>;
+	vbus-supply = <&vsys>;
+	status = "okay";
+};
+
+&xhci2 {
+	vbus-supply = <&vsys>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
index bbc2e9bef08d..14d58859bb55 100644
--- a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts
@@ -762,6 +762,7 @@
 			interrupt-parent = <&gpio>;
 			interrupts = <TEGRA_GPIO(C, 7) IRQ_TYPE_LEVEL_LOW>;
 			reg = <0>;
+			wakeup-source;
 
 			google,cros-ec-spi-msg-delay = <2000>;
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
index 5b59c1986e9b..e8b296d9e0d3 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
@@ -53,6 +53,56 @@
 			status = "okay";
 		};
 
+		i2c@c240000 {
+			status = "okay";
+
+			power-sensor@40 {
+				compatible = "ti,ina3221";
+				reg = <0x40>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				input@0 {
+					reg = <0x0>;
+					label = "GPU";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@1 {
+					reg = <0x1>;
+					label = "CPU";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@2 {
+					reg = <0x2>;
+					label = "SOC";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+			};
+
+			power-sensor@41 {
+				compatible = "ti,ina3221";
+				reg = <0x41>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				input@0 {
+					reg = <0x0>;
+					label = "CV";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@1 {
+					reg = <0x1>;
+					label = "VDDRQ";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@2 {
+					reg = <0x2>;
+					label = "SYS5V";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+			};
+		};
+
 		serial@3110000 {
 			status = "okay";
 		};
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts b/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts
index 64a3398fe7a6..c32876699a43 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts
@@ -2062,8 +2062,15 @@
 
 			ports {
 				usb2-0 {
-					mode = "host";
+					mode = "otg";
+					usb-role-switch;
 					status = "okay";
+
+					port {
+						hs_typec_p0: endpoint {
+							remote-endpoint = <&hs_ucsi_ccg_p0>;
+						};
+					};
 				};
 
 				usb2-1 {
@@ -2094,6 +2101,14 @@
 			};
 		};
 
+		usb@3550000 {
+			status = "okay";
+
+			phys = <&{/bus@0/padctl@3520000/pads/usb2/lanes/usb2-0}>,
+			       <&{/bus@0/padctl@3520000/pads/usb3/lanes/usb3-2}>;
+			phy-names = "usb2-0", "usb3-0";
+		};
+
 		usb@3610000 {
 			status = "okay";
 
@@ -2106,6 +2121,40 @@
 			phy-names = "usb2-0", "usb2-1", "usb2-3", "usb3-0", "usb3-2", "usb3-3";
 		};
 
+		i2c@c240000 {
+			typec@8 {
+				compatible = "cypress,cypd4226";
+				reg = <0x08>;
+				interrupt-parent = <&gpio_aon>;
+				interrupts = <TEGRA194_AON_GPIO(BB, 2) IRQ_TYPE_LEVEL_LOW>;
+				firmware-name = "nvidia,jetson-agx-xavier";
+				status = "okay";
+
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				ccg_typec_con0: connector@0 {
+					compatible = "usb-c-connector";
+					reg = <0>;
+					label = "USB-C";
+					data-role = "dual";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							hs_ucsi_ccg_p0: endpoint {
+								remote-endpoint = <&hs_typec_p0>;
+							};
+						};
+					};
+				};
+			};
+		};
+
 		i2c@c250000 {
 			status = "okay";
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi
index 58f190b0f868..59860d19f0f6 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi
@@ -50,6 +50,33 @@
 			status = "okay";
 		};
 
+		i2c@c250000 {
+			status = "okay";
+
+			power-sensor@40 {
+				compatible = "ti,ina3221";
+				reg = <0x40>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				input@0 {
+					reg = <0x0>;
+					label = "VDD_IN";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@1 {
+					reg = <0x1>;
+					label = "VDD_CPU_GPU_CV";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+				input@2 {
+					reg = <0x2>;
+					label = "VDD_SOC";
+					shunt-resistor-micro-ohms = <5000>;
+				};
+			};
+		};
+
 		serial@3100000 {
 			status = "okay";
 		};
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3701.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3701.dtsi
index db6ef711674a..320c8e9b06b4 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3701.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3701.dtsi
@@ -3,6 +3,11 @@
 / {
 	compatible = "nvidia,p3701", "nvidia,tegra234";
 
+	aliases {
+		mmc0 = "/bus@0/mmc@3460000";
+		mmc1 = "/bus@0/mmc@3400000";
+	};
+
 	bus@0 {
 		aconnect@2900000 {
 			status = "okay";
@@ -12,1970 +17,22 @@
 
 				i2s@2901000 {
 					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							i2s1_cif: endpoint {
-								remote-endpoint = <&xbar_i2s1>;
-							};
-						};
-
-						i2s1_port: port@1 {
-							reg = <1>;
-
-							i2s1_dap: endpoint {
-								dai-format = "i2s";
-								/* placeholder for external codec */
-							};
-						};
-					};
 				};
 
 				i2s@2901100 {
 					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							i2s2_cif: endpoint {
-								remote-endpoint = <&xbar_i2s2>;
-							};
-						};
-
-						i2s2_port: port@1 {
-							reg = <1>;
-
-							i2s2_dap: endpoint {
-								dai-format = "i2s";
-								/* placeholder for external codec */
-							};
-						};
-					};
 				};
 
 				i2s@2901300 {
 					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							i2s4_cif: endpoint {
-								remote-endpoint = <&xbar_i2s4>;
-							};
-						};
-
-						i2s4_port: port@1 {
-							reg = <1>;
-
-							i2s4_dap: endpoint {
-								dai-format = "i2s";
-								/* placeholder for external codec */
-							};
-						};
-					};
 				};
 
 				i2s@2901500 {
 					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							i2s6_cif: endpoint {
-								remote-endpoint = <&xbar_i2s6>;
-							};
-						};
-
-						i2s6_port: port@1 {
-							reg = <1>;
-
-							i2s6_dap: endpoint {
-								dai-format = "i2s";
-								/* placeholder for external codec */
-							};
-						};
-					};
-				};
-
-				sfc@2902000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							sfc1_cif_in: endpoint {
-								remote-endpoint = <&xbar_sfc1_in>;
-							};
-						};
-
-						sfc1_out_port: port@1 {
-							reg = <1>;
-
-							sfc1_cif_out: endpoint {
-								remote-endpoint = <&xbar_sfc1_out>;
-							};
-						};
-					};
-				};
-
-				sfc@2902200 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							sfc2_cif_in: endpoint {
-								remote-endpoint = <&xbar_sfc2_in>;
-							};
-						};
-
-						sfc2_out_port: port@1 {
-							reg = <1>;
-
-							sfc2_cif_out: endpoint {
-								remote-endpoint = <&xbar_sfc2_out>;
-							};
-						};
-					};
-				};
-
-				sfc@2902400 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							sfc3_cif_in: endpoint {
-								remote-endpoint = <&xbar_sfc3_in>;
-							};
-						};
-
-						sfc3_out_port: port@1 {
-							reg = <1>;
-
-							sfc3_cif_out: endpoint {
-								remote-endpoint = <&xbar_sfc3_out>;
-							};
-						};
-					};
-				};
-
-				sfc@2902600 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							sfc4_cif_in: endpoint {
-								remote-endpoint = <&xbar_sfc4_in>;
-							};
-						};
-
-						sfc4_out_port: port@1 {
-							reg = <1>;
-
-							sfc4_cif_out: endpoint {
-								remote-endpoint = <&xbar_sfc4_out>;
-							};
-						};
-					};
-				};
-
-				amx@2903000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							amx1_in1: endpoint {
-								remote-endpoint = <&xbar_amx1_in1>;
-							};
-						};
-
-						port@1 {
-							reg = <1>;
-
-							amx1_in2: endpoint {
-								remote-endpoint = <&xbar_amx1_in2>;
-							};
-						};
-
-						port@2 {
-							reg = <2>;
-
-							amx1_in3: endpoint {
-								remote-endpoint = <&xbar_amx1_in3>;
-							};
-						};
-
-						port@3 {
-							reg = <3>;
-
-							amx1_in4: endpoint {
-								remote-endpoint = <&xbar_amx1_in4>;
-							};
-						};
-
-						amx1_out_port: port@4 {
-							reg = <4>;
-
-							amx1_out: endpoint {
-								remote-endpoint = <&xbar_amx1_out>;
-							};
-						};
-					};
-				};
-
-				amx@2903100 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							amx2_in1: endpoint {
-								remote-endpoint = <&xbar_amx2_in1>;
-							};
-						};
-
-						port@1 {
-							reg = <1>;
-
-							amx2_in2: endpoint {
-								remote-endpoint = <&xbar_amx2_in2>;
-							};
-						};
-
-						port@2 {
-							reg = <2>;
-
-							amx2_in3: endpoint {
-								remote-endpoint = <&xbar_amx2_in3>;
-							};
-						};
-
-						port@3 {
-							reg = <3>;
-
-							amx2_in4: endpoint {
-								remote-endpoint = <&xbar_amx2_in4>;
-							};
-						};
-
-						amx2_out_port: port@4 {
-							reg = <4>;
-
-							amx2_out: endpoint {
-								remote-endpoint = <&xbar_amx2_out>;
-							};
-						};
-					};
-				};
-
-				amx@2903200 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							amx3_in1: endpoint {
-								remote-endpoint = <&xbar_amx3_in1>;
-							};
-						};
-
-						port@1 {
-							reg = <1>;
-
-							amx3_in2: endpoint {
-								remote-endpoint = <&xbar_amx3_in2>;
-							};
-						};
-
-						port@2 {
-							reg = <2>;
-
-							amx3_in3: endpoint {
-								remote-endpoint = <&xbar_amx3_in3>;
-							};
-						};
-
-						port@3 {
-							reg = <3>;
-
-							amx3_in4: endpoint {
-								remote-endpoint = <&xbar_amx3_in4>;
-							};
-						};
-
-						amx3_out_port: port@4 {
-							reg = <4>;
-
-							amx3_out: endpoint {
-								remote-endpoint = <&xbar_amx3_out>;
-							};
-						};
-					};
-				};
-
-				amx@2903300 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							amx4_in1: endpoint {
-								remote-endpoint = <&xbar_amx4_in1>;
-							};
-						};
-
-						port@1 {
-							reg = <1>;
-
-							amx4_in2: endpoint {
-								remote-endpoint = <&xbar_amx4_in2>;
-							};
-						};
-
-						port@2 {
-							reg = <2>;
-
-							amx4_in3: endpoint {
-								remote-endpoint = <&xbar_amx4_in3>;
-							};
-						};
-
-						port@3 {
-							reg = <3>;
-
-							amx4_in4: endpoint {
-								remote-endpoint = <&xbar_amx4_in4>;
-							};
-						};
-
-						amx4_out_port: port@4 {
-							reg = <4>;
-
-							amx4_out: endpoint {
-								remote-endpoint = <&xbar_amx4_out>;
-							};
-						};
-					};
-				};
-
-				adx@2903800 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							adx1_in: endpoint {
-								remote-endpoint = <&xbar_adx1_in>;
-							};
-						};
-
-						adx1_out1_port: port@1 {
-							reg = <1>;
-
-							adx1_out1: endpoint {
-								remote-endpoint = <&xbar_adx1_out1>;
-							};
-						};
-
-						adx1_out2_port: port@2 {
-							reg = <2>;
-
-							adx1_out2: endpoint {
-								remote-endpoint = <&xbar_adx1_out2>;
-							};
-						};
-
-						adx1_out3_port: port@3 {
-							reg = <3>;
-
-							adx1_out3: endpoint {
-								remote-endpoint = <&xbar_adx1_out3>;
-							};
-						};
-
-						adx1_out4_port: port@4 {
-							reg = <4>;
-
-							adx1_out4: endpoint {
-								remote-endpoint = <&xbar_adx1_out4>;
-							};
-						};
-					};
-				};
-
-				adx@2903900 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							adx2_in: endpoint {
-								remote-endpoint = <&xbar_adx2_in>;
-							};
-						};
-
-						adx2_out1_port: port@1 {
-							reg = <1>;
-
-							adx2_out1: endpoint {
-								remote-endpoint = <&xbar_adx2_out1>;
-							};
-						};
-
-						adx2_out2_port: port@2 {
-							reg = <2>;
-
-							adx2_out2: endpoint {
-								remote-endpoint = <&xbar_adx2_out2>;
-							};
-						};
-
-						adx2_out3_port: port@3 {
-							reg = <3>;
-
-							adx2_out3: endpoint {
-								remote-endpoint = <&xbar_adx2_out3>;
-							};
-						};
-
-						adx2_out4_port: port@4 {
-							reg = <4>;
-
-							adx2_out4: endpoint {
-								remote-endpoint = <&xbar_adx2_out4>;
-							};
-						};
-					};
-				};
-
-				adx@2903a00 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							adx3_in: endpoint {
-								remote-endpoint = <&xbar_adx3_in>;
-							};
-						};
-
-						adx3_out1_port: port@1 {
-							reg = <1>;
-
-							adx3_out1: endpoint {
-								remote-endpoint = <&xbar_adx3_out1>;
-							};
-						};
-
-						adx3_out2_port: port@2 {
-							reg = <2>;
-
-							adx3_out2: endpoint {
-								remote-endpoint = <&xbar_adx3_out2>;
-							};
-						};
-
-						adx3_out3_port: port@3 {
-							reg = <3>;
-
-							adx3_out3: endpoint {
-								remote-endpoint = <&xbar_adx3_out3>;
-							};
-						};
-
-						adx3_out4_port: port@4 {
-							reg = <4>;
-
-							adx3_out4: endpoint {
-								remote-endpoint = <&xbar_adx3_out4>;
-							};
-						};
-					};
-				};
-
-				adx@2903b00 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							adx4_in: endpoint {
-								remote-endpoint = <&xbar_adx4_in>;
-							};
-						};
-
-						adx4_out1_port: port@1 {
-							reg = <1>;
-
-							adx4_out1: endpoint {
-								remote-endpoint = <&xbar_adx4_out1>;
-							};
-						};
-
-						adx4_out2_port: port@2 {
-							reg = <2>;
-
-							adx4_out2: endpoint {
-								remote-endpoint = <&xbar_adx4_out2>;
-							};
-						};
-
-						adx4_out3_port: port@3 {
-							reg = <3>;
-
-							adx4_out3: endpoint {
-								remote-endpoint = <&xbar_adx4_out3>;
-							};
-						};
-
-						adx4_out4_port: port@4 {
-							reg = <4>;
-
-							adx4_out4: endpoint {
-								remote-endpoint = <&xbar_adx4_out4>;
-							};
-						};
-					};
 				};
 
 				dmic@2904200 {
 					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							dmic3_cif: endpoint {
-								remote-endpoint = <&xbar_dmic3>;
-							};
-						};
-
-						dmic3_port: port@1 {
-							reg = <1>;
-
-							dmic3_dap: endpoint {
-								/* placeholder for external codec */
-							};
-						};
-					};
-				};
-
-				processing-engine@2908000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0x0>;
-
-							ope1_cif_in_ep: endpoint {
-								remote-endpoint = <&xbar_ope1_in_ep>;
-							};
-						};
-
-						ope1_out_port: port@1 {
-							reg = <0x1>;
-
-							ope1_cif_out_ep: endpoint {
-								remote-endpoint = <&xbar_ope1_out_ep>;
-							};
-						};
-					};
-				};
-
-				mvc@290a000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							mvc1_cif_in: endpoint {
-								remote-endpoint = <&xbar_mvc1_in>;
-							};
-						};
-
-						mvc1_out_port: port@1 {
-							reg = <1>;
-
-							mvc1_cif_out: endpoint {
-								remote-endpoint = <&xbar_mvc1_out>;
-							};
-						};
-					};
-				};
-
-				mvc@290a200 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0>;
-
-							mvc2_cif_in: endpoint {
-								remote-endpoint = <&xbar_mvc2_in>;
-							};
-						};
-
-						mvc2_out_port: port@1 {
-							reg = <1>;
-
-							mvc2_cif_out: endpoint {
-								remote-endpoint = <&xbar_mvc2_out>;
-							};
-						};
-					};
-				};
-
-				amixer@290bb00 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0x0>;
-
-							mix_in1: endpoint {
-								remote-endpoint = <&xbar_mix_in1>;
-							};
-						};
-
-						port@1 {
-							reg = <0x1>;
-
-							mix_in2: endpoint {
-								remote-endpoint = <&xbar_mix_in2>;
-							};
-						};
-
-						port@2 {
-							reg = <0x2>;
-
-							mix_in3: endpoint {
-								remote-endpoint = <&xbar_mix_in3>;
-							};
-						};
-
-						port@3 {
-							reg = <0x3>;
-
-							mix_in4: endpoint {
-								remote-endpoint = <&xbar_mix_in4>;
-							};
-						};
-
-						port@4 {
-							reg = <0x4>;
-
-							mix_in5: endpoint {
-								remote-endpoint = <&xbar_mix_in5>;
-							};
-						};
-
-						port@5 {
-							reg = <0x5>;
-
-							mix_in6: endpoint {
-								remote-endpoint = <&xbar_mix_in6>;
-							};
-						};
-
-						port@6 {
-							reg = <0x6>;
-
-							mix_in7: endpoint {
-								remote-endpoint = <&xbar_mix_in7>;
-							};
-						};
-
-						port@7 {
-							reg = <0x7>;
-
-							mix_in8: endpoint {
-								remote-endpoint = <&xbar_mix_in8>;
-							};
-						};
-
-						port@8 {
-							reg = <0x8>;
-
-							mix_in9: endpoint {
-								remote-endpoint = <&xbar_mix_in9>;
-							};
-						};
-
-						port@9 {
-							reg = <0x9>;
-
-							mix_in10: endpoint {
-								remote-endpoint = <&xbar_mix_in10>;
-							};
-						};
-
-						mix_out1_port: port@a {
-							reg = <0xa>;
-
-							mix_out1: endpoint {
-								remote-endpoint = <&xbar_mix_out1>;
-							};
-						};
-
-						mix_out2_port: port@b {
-							reg = <0xb>;
-
-							mix_out2: endpoint {
-								remote-endpoint = <&xbar_mix_out2>;
-							};
-						};
-
-						mix_out3_port: port@c {
-							reg = <0xc>;
-
-							mix_out3: endpoint {
-								remote-endpoint = <&xbar_mix_out3>;
-							};
-						};
-
-						mix_out4_port: port@d {
-							reg = <0xd>;
-
-							mix_out4: endpoint {
-								remote-endpoint = <&xbar_mix_out4>;
-							};
-						};
-
-						mix_out5_port: port@e {
-							reg = <0xe>;
-
-							mix_out5: endpoint {
-								remote-endpoint = <&xbar_mix_out5>;
-							};
-						};
-					};
-				};
-
-				admaif@290f000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						admaif0_port: port@0 {
-							reg = <0x0>;
-
-							admaif0: endpoint {
-								remote-endpoint = <&xbar_admaif0>;
-							};
-						};
-
-						admaif1_port: port@1 {
-							reg = <0x1>;
-
-							admaif1: endpoint {
-								remote-endpoint = <&xbar_admaif1>;
-							};
-						};
-
-						admaif2_port: port@2 {
-							reg = <0x2>;
-
-							admaif2: endpoint {
-								remote-endpoint = <&xbar_admaif2>;
-							};
-						};
-
-						admaif3_port: port@3 {
-							reg = <0x3>;
-
-							admaif3: endpoint {
-								remote-endpoint = <&xbar_admaif3>;
-							};
-						};
-
-						admaif4_port: port@4 {
-							reg = <0x4>;
-
-							admaif4: endpoint {
-								remote-endpoint = <&xbar_admaif4>;
-							};
-						};
-
-						admaif5_port: port@5 {
-							reg = <0x5>;
-
-							admaif5: endpoint {
-								remote-endpoint = <&xbar_admaif5>;
-							};
-						};
-
-						admaif6_port: port@6 {
-							reg = <0x6>;
-
-							admaif6: endpoint {
-								remote-endpoint = <&xbar_admaif6>;
-							};
-						};
-
-						admaif7_port: port@7 {
-							reg = <0x7>;
-
-							admaif7: endpoint {
-								remote-endpoint = <&xbar_admaif7>;
-							};
-						};
-
-						admaif8_port: port@8 {
-							reg = <0x8>;
-
-							admaif8: endpoint {
-								remote-endpoint = <&xbar_admaif8>;
-							};
-						};
-
-						admaif9_port: port@9 {
-							reg = <0x9>;
-
-							admaif9: endpoint {
-								remote-endpoint = <&xbar_admaif9>;
-							};
-						};
-
-						admaif10_port: port@a {
-							reg = <0xa>;
-
-							admaif10: endpoint {
-								remote-endpoint = <&xbar_admaif10>;
-							};
-						};
-
-						admaif11_port: port@b {
-							reg = <0xb>;
-
-							admaif11: endpoint {
-								remote-endpoint = <&xbar_admaif11>;
-							};
-						};
-
-						admaif12_port: port@c {
-							reg = <0xc>;
-
-							admaif12: endpoint {
-								remote-endpoint = <&xbar_admaif12>;
-							};
-						};
-
-						admaif13_port: port@d {
-							reg = <0xd>;
-
-							admaif13: endpoint {
-								remote-endpoint = <&xbar_admaif13>;
-							};
-						};
-
-						admaif14_port: port@e {
-							reg = <0xe>;
-
-							admaif14: endpoint {
-								remote-endpoint = <&xbar_admaif14>;
-							};
-						};
-
-						admaif15_port: port@f {
-							reg = <0xf>;
-
-							admaif15: endpoint {
-								remote-endpoint = <&xbar_admaif15>;
-							};
-						};
-
-						admaif16_port: port@10 {
-							reg = <0x10>;
-
-							admaif16: endpoint {
-								remote-endpoint = <&xbar_admaif16>;
-							};
-						};
-
-						admaif17_port: port@11 {
-							reg = <0x11>;
-
-							admaif17: endpoint {
-								remote-endpoint = <&xbar_admaif17>;
-							};
-						};
-
-						admaif18_port: port@12 {
-							reg = <0x12>;
-
-							admaif18: endpoint {
-								remote-endpoint = <&xbar_admaif18>;
-							};
-						};
-
-						admaif19_port: port@13 {
-							reg = <0x13>;
-
-							admaif19: endpoint {
-								remote-endpoint = <&xbar_admaif19>;
-							};
-						};
-					};
-				};
-
-				asrc@2910000 {
-					status = "okay";
-
-					ports {
-						#address-cells = <1>;
-						#size-cells = <0>;
-
-						port@0 {
-							reg = <0x0>;
-
-							asrc_in1_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in1_ep>;
-							};
-						};
-
-						port@1 {
-							reg = <0x1>;
-
-							asrc_in2_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in2_ep>;
-							};
-						};
-
-						port@2 {
-							reg = <0x2>;
-
-							asrc_in3_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in3_ep>;
-							};
-						};
-
-						port@3 {
-							reg = <0x3>;
-
-							asrc_in4_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in4_ep>;
-							};
-						};
-
-						port@4 {
-							reg = <0x4>;
-
-							asrc_in5_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in5_ep>;
-							};
-						};
-
-						port@5 {
-							reg = <0x5>;
-
-							asrc_in6_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in6_ep>;
-							};
-						};
-
-						port@6 {
-							reg = <0x6>;
-
-							asrc_in7_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_in7_ep>;
-							};
-						};
-
-						asrc_out1_port: port@7 {
-							reg = <0x7>;
-
-							asrc_out1_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out1_ep>;
-							};
-						};
-
-						asrc_out2_port: port@8 {
-							reg = <0x8>;
-
-							asrc_out2_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out2_ep>;
-							};
-						};
-
-						asrc_out3_port: port@9 {
-							reg = <0x9>;
-
-							asrc_out3_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out3_ep>;
-							};
-						};
-
-						asrc_out4_port: port@a {
-							reg = <0xa>;
-
-							asrc_out4_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out4_ep>;
-							};
-						};
-
-						asrc_out5_port: port@b {
-							reg = <0xb>;
-
-							asrc_out5_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out5_ep>;
-							};
-						};
-
-						asrc_out6_port:	port@c {
-							reg = <0xc>;
-
-							asrc_out6_ep: endpoint {
-								remote-endpoint = <&xbar_asrc_out6_ep>;
-							};
-						};
-					};
-				};
-
-				ports {
-					#address-cells = <1>;
-					#size-cells = <0>;
-
-					port@0 {
-						reg = <0x0>;
-
-						xbar_admaif0: endpoint {
-							remote-endpoint = <&admaif0>;
-						};
-					};
-
-					port@1 {
-						reg = <0x1>;
-
-						xbar_admaif1: endpoint {
-							remote-endpoint = <&admaif1>;
-						};
-					};
-
-					port@2 {
-						reg = <0x2>;
-
-						xbar_admaif2: endpoint {
-							remote-endpoint = <&admaif2>;
-						};
-					};
-
-					port@3 {
-						reg = <0x3>;
-
-						xbar_admaif3: endpoint {
-							remote-endpoint = <&admaif3>;
-						};
-					};
-
-					port@4 {
-						reg = <0x4>;
-
-						xbar_admaif4: endpoint {
-							remote-endpoint = <&admaif4>;
-						};
-					};
-
-					port@5 {
-						reg = <0x5>;
-
-						xbar_admaif5: endpoint {
-							remote-endpoint = <&admaif5>;
-						};
-					};
-
-					port@6 {
-						reg = <0x6>;
-
-						xbar_admaif6: endpoint {
-							remote-endpoint = <&admaif6>;
-						};
-					};
-
-					port@7 {
-						reg = <0x7>;
-
-						xbar_admaif7: endpoint {
-							remote-endpoint = <&admaif7>;
-						};
-					};
-
-					port@8 {
-						reg = <0x8>;
-
-						xbar_admaif8: endpoint {
-							remote-endpoint = <&admaif8>;
-						};
-					};
-
-					port@9 {
-						reg = <0x9>;
-
-						xbar_admaif9: endpoint {
-							remote-endpoint = <&admaif9>;
-						};
-					};
-
-					port@a {
-						reg = <0xa>;
-
-						xbar_admaif10: endpoint {
-							remote-endpoint = <&admaif10>;
-						};
-					};
-
-					port@b {
-						reg = <0xb>;
-
-						xbar_admaif11: endpoint {
-							remote-endpoint = <&admaif11>;
-						};
-					};
-
-					port@c {
-						reg = <0xc>;
-
-						xbar_admaif12: endpoint {
-							remote-endpoint = <&admaif12>;
-						};
-					};
-
-					port@d {
-						reg = <0xd>;
-
-						xbar_admaif13: endpoint {
-							remote-endpoint = <&admaif13>;
-						};
-					};
-
-					port@e {
-						reg = <0xe>;
-
-						xbar_admaif14: endpoint {
-							remote-endpoint = <&admaif14>;
-						};
-					};
-
-					port@f {
-						reg = <0xf>;
-
-						xbar_admaif15: endpoint {
-							remote-endpoint = <&admaif15>;
-						};
-					};
-
-					port@10 {
-						reg = <0x10>;
-
-						xbar_admaif16: endpoint {
-							remote-endpoint = <&admaif16>;
-						};
-					};
-
-					port@11 {
-						reg = <0x11>;
-
-						xbar_admaif17: endpoint {
-							remote-endpoint = <&admaif17>;
-						};
-					};
-
-					port@12 {
-						reg = <0x12>;
-
-						xbar_admaif18: endpoint {
-							remote-endpoint = <&admaif18>;
-						};
-					};
-
-					port@13 {
-						reg = <0x13>;
-
-						xbar_admaif19: endpoint {
-							remote-endpoint = <&admaif19>;
-						};
-					};
-
-					xbar_i2s1_port: port@14 {
-						reg = <0x14>;
-
-						xbar_i2s1: endpoint {
-							remote-endpoint = <&i2s1_cif>;
-						};
-					};
-
-					xbar_i2s2_port: port@15 {
-						reg = <0x15>;
-
-						xbar_i2s2: endpoint {
-							remote-endpoint = <&i2s2_cif>;
-						};
-					};
-
-					xbar_i2s4_port: port@17 {
-						reg = <0x17>;
-
-						xbar_i2s4: endpoint {
-							remote-endpoint = <&i2s4_cif>;
-						};
-					};
-
-					xbar_i2s6_port: port@19 {
-						reg = <0x19>;
-
-						xbar_i2s6: endpoint {
-							remote-endpoint = <&i2s6_cif>;
-						};
-					};
-
-					xbar_dmic3_port: port@1c {
-						reg = <0x1c>;
-
-						xbar_dmic3: endpoint {
-							remote-endpoint = <&dmic3_cif>;
-						};
-					};
-
-					xbar_sfc1_in_port: port@20 {
-						reg = <0x20>;
-
-						xbar_sfc1_in: endpoint {
-							remote-endpoint = <&sfc1_cif_in>;
-						};
-					};
-
-					port@21 {
-						reg = <0x21>;
-
-						xbar_sfc1_out: endpoint {
-							remote-endpoint = <&sfc1_cif_out>;
-						};
-					};
-
-					xbar_sfc2_in_port: port@22 {
-						reg = <0x22>;
-
-						xbar_sfc2_in: endpoint {
-							remote-endpoint = <&sfc2_cif_in>;
-						};
-					};
-
-					port@23 {
-						reg = <0x23>;
-
-						xbar_sfc2_out: endpoint {
-							remote-endpoint = <&sfc2_cif_out>;
-						};
-					};
-
-					xbar_sfc3_in_port: port@24 {
-						reg = <0x24>;
-
-						xbar_sfc3_in: endpoint {
-							remote-endpoint = <&sfc3_cif_in>;
-						};
-					};
-
-					port@25 {
-						reg = <0x25>;
-
-						xbar_sfc3_out: endpoint {
-							remote-endpoint = <&sfc3_cif_out>;
-						};
-					};
-
-					xbar_sfc4_in_port: port@26 {
-						reg = <0x26>;
-
-						xbar_sfc4_in: endpoint {
-							remote-endpoint = <&sfc4_cif_in>;
-						};
-					};
-
-					port@27 {
-						reg = <0x27>;
-
-						xbar_sfc4_out: endpoint {
-							remote-endpoint = <&sfc4_cif_out>;
-						};
-					};
-
-					xbar_mvc1_in_port: port@28 {
-						reg = <0x28>;
-
-						xbar_mvc1_in: endpoint {
-							remote-endpoint = <&mvc1_cif_in>;
-						};
-					};
-
-					port@29 {
-						reg = <0x29>;
-
-						xbar_mvc1_out: endpoint {
-							remote-endpoint = <&mvc1_cif_out>;
-						};
-					};
-
-					xbar_mvc2_in_port: port@2a {
-						reg = <0x2a>;
-
-						xbar_mvc2_in: endpoint {
-							remote-endpoint = <&mvc2_cif_in>;
-						};
-					};
-
-					port@2b {
-						reg = <0x2b>;
-
-						xbar_mvc2_out: endpoint {
-							remote-endpoint = <&mvc2_cif_out>;
-						};
-					};
-
-					xbar_amx1_in1_port: port@2c {
-						reg = <0x2c>;
-
-						xbar_amx1_in1: endpoint {
-							remote-endpoint = <&amx1_in1>;
-						};
-					};
-
-					xbar_amx1_in2_port: port@2d {
-						reg = <0x2d>;
-
-						xbar_amx1_in2: endpoint {
-							remote-endpoint = <&amx1_in2>;
-						};
-					};
-
-					xbar_amx1_in3_port: port@2e {
-						reg = <0x2e>;
-
-						xbar_amx1_in3: endpoint {
-							remote-endpoint = <&amx1_in3>;
-						};
-					};
-
-					xbar_amx1_in4_port: port@2f {
-						reg = <0x2f>;
-
-						xbar_amx1_in4: endpoint {
-							remote-endpoint = <&amx1_in4>;
-						};
-					};
-
-					port@30 {
-						reg = <0x30>;
-
-						xbar_amx1_out: endpoint {
-							remote-endpoint = <&amx1_out>;
-						};
-					};
-
-					xbar_amx2_in1_port: port@31 {
-						reg = <0x31>;
-
-						xbar_amx2_in1: endpoint {
-							remote-endpoint = <&amx2_in1>;
-						};
-					};
-
-					xbar_amx2_in2_port: port@32 {
-						reg = <0x32>;
-
-						xbar_amx2_in2: endpoint {
-							remote-endpoint = <&amx2_in2>;
-						};
-					};
-
-					xbar_amx2_in3_port: port@33 {
-						reg = <0x33>;
-
-						xbar_amx2_in3: endpoint {
-							remote-endpoint = <&amx2_in3>;
-						};
-					};
-
-					xbar_amx2_in4_port: port@34 {
-						reg = <0x34>;
-
-						xbar_amx2_in4: endpoint {
-							remote-endpoint = <&amx2_in4>;
-						};
-					};
-
-					port@35 {
-						reg = <0x35>;
-
-						xbar_amx2_out: endpoint {
-							remote-endpoint = <&amx2_out>;
-						};
-					};
-
-					xbar_amx3_in1_port: port@36 {
-						reg = <0x36>;
-
-						xbar_amx3_in1: endpoint {
-							remote-endpoint = <&amx3_in1>;
-						};
-					};
-
-					xbar_amx3_in2_port: port@37 {
-						reg = <0x37>;
-
-						xbar_amx3_in2: endpoint {
-							remote-endpoint = <&amx3_in2>;
-						};
-					};
-
-					xbar_amx3_in3_port: port@38 {
-						reg = <0x38>;
-
-						xbar_amx3_in3: endpoint {
-							remote-endpoint = <&amx3_in3>;
-						};
-					};
-
-					xbar_amx3_in4_port: port@39 {
-						reg = <0x39>;
-
-						xbar_amx3_in4: endpoint {
-							remote-endpoint = <&amx3_in4>;
-						};
-					};
-
-					port@3a {
-						reg = <0x3a>;
-
-						xbar_amx3_out: endpoint {
-							remote-endpoint = <&amx3_out>;
-						};
-					};
-
-					xbar_amx4_in1_port: port@3b {
-						reg = <0x3b>;
-
-						xbar_amx4_in1: endpoint {
-							remote-endpoint = <&amx4_in1>;
-						};
-					};
-
-					xbar_amx4_in2_port: port@3c {
-						reg = <0x3c>;
-
-						xbar_amx4_in2: endpoint {
-							remote-endpoint = <&amx4_in2>;
-						};
-					};
-
-					xbar_amx4_in3_port: port@3d {
-						reg = <0x3d>;
-
-						xbar_amx4_in3: endpoint {
-							remote-endpoint = <&amx4_in3>;
-						};
-					};
-
-					xbar_amx4_in4_port: port@3e {
-						reg = <0x3e>;
-
-						xbar_amx4_in4: endpoint {
-							remote-endpoint = <&amx4_in4>;
-						};
-					};
-
-					port@3f {
-						reg = <0x3f>;
-
-						xbar_amx4_out: endpoint {
-							remote-endpoint = <&amx4_out>;
-						};
-					};
-
-					xbar_adx1_in_port: port@40 {
-						reg = <0x40>;
-
-						xbar_adx1_in: endpoint {
-							remote-endpoint = <&adx1_in>;
-						};
-					};
-
-					port@41 {
-						reg = <0x41>;
-
-						xbar_adx1_out1: endpoint {
-							remote-endpoint = <&adx1_out1>;
-						};
-					};
-
-					port@42 {
-						reg = <0x42>;
-
-						xbar_adx1_out2: endpoint {
-							remote-endpoint = <&adx1_out2>;
-						};
-					};
-
-					port@43 {
-						reg = <0x43>;
-
-						xbar_adx1_out3: endpoint {
-							remote-endpoint = <&adx1_out3>;
-						};
-					};
-
-					port@44 {
-						reg = <0x44>;
-
-						xbar_adx1_out4: endpoint {
-							remote-endpoint = <&adx1_out4>;
-						};
-					};
-
-					xbar_adx2_in_port: port@45 {
-						reg = <0x45>;
-
-						xbar_adx2_in: endpoint {
-							remote-endpoint = <&adx2_in>;
-						};
-					};
-
-					port@46 {
-						reg = <0x46>;
-
-						xbar_adx2_out1: endpoint {
-							remote-endpoint = <&adx2_out1>;
-						};
-					};
-
-					port@47 {
-						reg = <0x47>;
-
-						xbar_adx2_out2: endpoint {
-							remote-endpoint = <&adx2_out2>;
-						};
-					};
-
-					port@48 {
-						reg = <0x48>;
-
-						xbar_adx2_out3: endpoint {
-							remote-endpoint = <&adx2_out3>;
-						};
-					};
-
-					port@49 {
-						reg = <0x49>;
-
-						xbar_adx2_out4: endpoint {
-							remote-endpoint = <&adx2_out4>;
-						};
-					};
-
-					xbar_adx3_in_port: port@4a {
-						reg = <0x4a>;
-
-						xbar_adx3_in: endpoint {
-							remote-endpoint = <&adx3_in>;
-						};
-					};
-
-					port@4b {
-						reg = <0x4b>;
-
-						xbar_adx3_out1: endpoint {
-							remote-endpoint = <&adx3_out1>;
-						};
-					};
-
-					port@4c {
-						reg = <0x4c>;
-
-						xbar_adx3_out2: endpoint {
-							remote-endpoint = <&adx3_out2>;
-						};
-					};
-
-					port@4d {
-						reg = <0x4d>;
-
-						xbar_adx3_out3: endpoint {
-							remote-endpoint = <&adx3_out3>;
-						};
-					};
-
-					port@4e {
-						reg = <0x4e>;
-
-						xbar_adx3_out4: endpoint {
-							remote-endpoint = <&adx3_out4>;
-						};
-					};
-
-					xbar_adx4_in_port: port@4f {
-						reg = <0x4f>;
-
-						xbar_adx4_in: endpoint {
-							remote-endpoint = <&adx4_in>;
-						};
-					};
-
-					port@50 {
-						reg = <0x50>;
-
-						xbar_adx4_out1: endpoint {
-							remote-endpoint = <&adx4_out1>;
-						};
-					};
-
-					port@51 {
-						reg = <0x51>;
-
-						xbar_adx4_out2: endpoint {
-							remote-endpoint = <&adx4_out2>;
-						};
-					};
-
-					port@52 {
-						reg = <0x52>;
-
-						xbar_adx4_out3: endpoint {
-							remote-endpoint = <&adx4_out3>;
-						};
-					};
-
-					port@53 {
-						reg = <0x53>;
-
-						xbar_adx4_out4: endpoint {
-							remote-endpoint = <&adx4_out4>;
-						};
-					};
-
-					xbar_mix_in1_port: port@54 {
-						reg = <0x54>;
-
-						xbar_mix_in1: endpoint {
-							remote-endpoint = <&mix_in1>;
-						};
-					};
-
-					xbar_mix_in2_port: port@55 {
-						reg = <0x55>;
-
-						xbar_mix_in2: endpoint {
-							remote-endpoint = <&mix_in2>;
-						};
-					};
-
-					xbar_mix_in3_port: port@56 {
-						reg = <0x56>;
-
-						xbar_mix_in3: endpoint {
-							remote-endpoint = <&mix_in3>;
-						};
-					};
-
-					xbar_mix_in4_port: port@57 {
-						reg = <0x57>;
-
-						xbar_mix_in4: endpoint {
-							remote-endpoint = <&mix_in4>;
-						};
-					};
-
-					xbar_mix_in5_port: port@58 {
-						reg = <0x58>;
-
-						xbar_mix_in5: endpoint {
-							remote-endpoint = <&mix_in5>;
-						};
-					};
-
-					xbar_mix_in6_port: port@59 {
-						reg = <0x59>;
-
-						xbar_mix_in6: endpoint {
-							remote-endpoint = <&mix_in6>;
-						};
-					};
-
-					xbar_mix_in7_port: port@5a {
-						reg = <0x5a>;
-
-						xbar_mix_in7: endpoint {
-							remote-endpoint = <&mix_in7>;
-						};
-					};
-
-					xbar_mix_in8_port: port@5b {
-						reg = <0x5b>;
-
-						xbar_mix_in8: endpoint {
-							remote-endpoint = <&mix_in8>;
-						};
-					};
-
-					xbar_mix_in9_port: port@5c {
-						reg = <0x5c>;
-
-						xbar_mix_in9: endpoint {
-							remote-endpoint = <&mix_in9>;
-						};
-					};
-
-					xbar_mix_in10_port: port@5d {
-						reg = <0x5d>;
-
-						xbar_mix_in10: endpoint {
-							remote-endpoint = <&mix_in10>;
-						};
-					};
-
-					port@5e {
-						reg = <0x5e>;
-
-						xbar_mix_out1: endpoint {
-							remote-endpoint = <&mix_out1>;
-						};
-					};
-
-					port@5f {
-						reg = <0x5f>;
-
-						xbar_mix_out2: endpoint {
-							remote-endpoint = <&mix_out2>;
-						};
-					};
-
-					port@60 {
-						reg = <0x60>;
-
-						xbar_mix_out3: endpoint {
-							remote-endpoint = <&mix_out3>;
-						};
-					};
-
-					port@61 {
-						reg = <0x61>;
-
-						xbar_mix_out4: endpoint {
-							remote-endpoint = <&mix_out4>;
-						};
-					};
-
-					port@62 {
-						reg = <0x62>;
-
-						xbar_mix_out5: endpoint {
-							remote-endpoint = <&mix_out5>;
-						};
-					};
-
-					xbar_asrc_in1_port: port@63 {
-						reg = <0x63>;
-
-						xbar_asrc_in1_ep: endpoint {
-							remote-endpoint = <&asrc_in1_ep>;
-						};
-					};
-
-					port@64 {
-						reg = <0x64>;
-
-						xbar_asrc_out1_ep: endpoint {
-							remote-endpoint = <&asrc_out1_ep>;
-						};
-					};
-
-					xbar_asrc_in2_port: port@65 {
-						reg = <0x65>;
-
-						xbar_asrc_in2_ep: endpoint {
-							remote-endpoint = <&asrc_in2_ep>;
-						};
-					};
-
-					port@66 {
-						reg = <0x66>;
-
-						xbar_asrc_out2_ep: endpoint {
-							remote-endpoint = <&asrc_out2_ep>;
-						};
-					};
-
-					xbar_asrc_in3_port: port@67 {
-						reg = <0x67>;
-
-						xbar_asrc_in3_ep: endpoint {
-							remote-endpoint = <&asrc_in3_ep>;
-						};
-					};
-
-					port@68 {
-						reg = <0x68>;
-
-						xbar_asrc_out3_ep: endpoint {
-							remote-endpoint = <&asrc_out3_ep>;
-						};
-					};
-
-					xbar_asrc_in4_port: port@69 {
-						reg = <0x69>;
-
-						xbar_asrc_in4_ep: endpoint {
-							remote-endpoint = <&asrc_in4_ep>;
-						};
-					};
-
-					port@6a {
-						reg = <0x6a>;
-
-						xbar_asrc_out4_ep: endpoint {
-							remote-endpoint = <&asrc_out4_ep>;
-						};
-					};
-
-					xbar_asrc_in5_port: port@6b {
-						reg = <0x6b>;
-
-						xbar_asrc_in5_ep: endpoint {
-							remote-endpoint = <&asrc_in5_ep>;
-						};
-					};
-
-					port@6c {
-						reg = <0x6c>;
-
-						xbar_asrc_out5_ep: endpoint {
-							remote-endpoint = <&asrc_out5_ep>;
-						};
-					};
-
-					xbar_asrc_in6_port: port@6d {
-						reg = <0x6d>;
-
-						xbar_asrc_in6_ep: endpoint {
-							remote-endpoint = <&asrc_in6_ep>;
-						};
-					};
-
-					port@6e {
-						reg = <0x6e>;
-
-						xbar_asrc_out6_ep: endpoint {
-							remote-endpoint = <&asrc_out6_ep>;
-						};
-					};
-
-					xbar_asrc_in7_port: port@6f {
-						reg = <0x6f>;
-
-						xbar_asrc_in7_ep: endpoint {
-							remote-endpoint = <&asrc_in7_ep>;
-						};
-					};
-
-					xbar_ope1_in_port: port@70 {
-						reg = <0x70>;
-
-						xbar_ope1_in_ep: endpoint {
-							remote-endpoint = <&ope1_cif_in_ep>;
-						};
-					};
-
-					port@71 {
-						reg = <0x71>;
-
-						xbar_ope1_out_ep: endpoint {
-							remote-endpoint = <&ope1_cif_out_ep>;
-						};
-					};
 				};
 			};
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
index ea13c4a7027c..69db584253da 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts
@@ -12,7 +12,6 @@
 	compatible = "nvidia,p3737-0000+p3701-0000", "nvidia,p3701-0000", "nvidia,tegra234";
 
 	aliases {
-		mmc3 = "/bus@0/mmc@3460000";
 		serial0 = &tcu;
 		serial1 = &uarta;
 	};
@@ -175,7 +174,7 @@
 			status = "okay";
 
 			phy-handle = <&mgbe0_phy>;
-			phy-mode = "usxgmii";
+			phy-mode = "10gbase-r";
 
 			mdio {
 				#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3767-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3767-0000.dtsi
deleted file mode 100644
index baf4f69e410d..000000000000
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3767-0000.dtsi
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include "tegra234-p3767.dtsi"
-
-/ {
-	compatible = "nvidia,p3767-0000", "nvidia,tegra234";
-	model = "NVIDIA Jetson Orin NX";
-
-	bus@0 {
-		hda@3510000 {
-			nvidia,model = "NVIDIA Jetson Orin NX HDA";
-		};
-	};
-};
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3767-0005.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3767-0005.dtsi
deleted file mode 100644
index 232fa95ef4ae..000000000000
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3767-0005.dtsi
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include "tegra234-p3767.dtsi"
-
-/ {
-	compatible = "nvidia,p3767-0005", "nvidia,tegra234";
-	model = "NVIDIA Jetson Orin Nano";
-
-	bus@0 {
-		hda@3510000 {
-			nvidia,model = "NVIDIA Jetson Orin Nano HDA";
-		};
-	};
-};
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi
index 59c14ded5e9f..84db7132e8fc 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3767.dtsi
@@ -5,7 +5,35 @@
 / {
 	compatible = "nvidia,p3767", "nvidia,tegra234";
 
+	aliases {
+		mmc0 = "/bus@0/mmc@3400000";
+	};
+
 	bus@0 {
+		aconnect@2900000 {
+			status = "okay";
+
+			ahub@2900800 {
+				status = "okay";
+
+				i2s@2901100 {
+					status = "okay";
+				};
+
+				i2s@2901300 {
+					status = "okay";
+				};
+			};
+
+			dma-controller@2930000 {
+				status = "okay";
+			};
+
+			interrupt-controller@2a40000 {
+				status = "okay";
+			};
+		};
+
 		i2c@3160000 {
 			status = "okay";
 
@@ -127,6 +155,64 @@
 		vin-supply = <&vdd_5v0_sys>;
 	};
 
+	sound {
+		compatible = "nvidia,tegra186-audio-graph-card";
+		status = "okay";
+
+		dais = /* ADMAIF (FE) Ports */
+		       <&admaif0_port>, <&admaif1_port>, <&admaif2_port>, <&admaif3_port>,
+		       <&admaif4_port>, <&admaif5_port>, <&admaif6_port>, <&admaif7_port>,
+		       <&admaif8_port>, <&admaif9_port>, <&admaif10_port>, <&admaif11_port>,
+		       <&admaif12_port>, <&admaif13_port>, <&admaif14_port>, <&admaif15_port>,
+		       <&admaif16_port>, <&admaif17_port>, <&admaif18_port>, <&admaif19_port>,
+		       /* XBAR Ports */
+		       <&xbar_i2s2_port>, <&xbar_i2s4_port>,
+		       <&xbar_sfc1_in_port>, <&xbar_sfc2_in_port>,
+		       <&xbar_sfc3_in_port>, <&xbar_sfc4_in_port>,
+		       <&xbar_mvc1_in_port>, <&xbar_mvc2_in_port>,
+		       <&xbar_amx1_in1_port>, <&xbar_amx1_in2_port>,
+		       <&xbar_amx1_in3_port>, <&xbar_amx1_in4_port>,
+		       <&xbar_amx2_in1_port>, <&xbar_amx2_in2_port>,
+		       <&xbar_amx2_in3_port>, <&xbar_amx2_in4_port>,
+		       <&xbar_amx3_in1_port>, <&xbar_amx3_in2_port>,
+		       <&xbar_amx3_in3_port>, <&xbar_amx3_in4_port>,
+		       <&xbar_amx4_in1_port>, <&xbar_amx4_in2_port>,
+		       <&xbar_amx4_in3_port>, <&xbar_amx4_in4_port>,
+		       <&xbar_adx1_in_port>, <&xbar_adx2_in_port>,
+		       <&xbar_adx3_in_port>, <&xbar_adx4_in_port>,
+		       <&xbar_mix_in1_port>, <&xbar_mix_in2_port>,
+		       <&xbar_mix_in3_port>, <&xbar_mix_in4_port>,
+		       <&xbar_mix_in5_port>, <&xbar_mix_in6_port>,
+		       <&xbar_mix_in7_port>, <&xbar_mix_in8_port>,
+		       <&xbar_mix_in9_port>, <&xbar_mix_in10_port>,
+		       <&xbar_asrc_in1_port>, <&xbar_asrc_in2_port>,
+		       <&xbar_asrc_in3_port>, <&xbar_asrc_in4_port>,
+		       <&xbar_asrc_in5_port>, <&xbar_asrc_in6_port>,
+		       <&xbar_asrc_in7_port>,
+		       <&xbar_ope1_in_port>,
+		       /* HW accelerators */
+		       <&sfc1_out_port>, <&sfc2_out_port>,
+		       <&sfc3_out_port>, <&sfc4_out_port>,
+		       <&mvc1_out_port>, <&mvc2_out_port>,
+		       <&amx1_out_port>, <&amx2_out_port>,
+		       <&amx3_out_port>, <&amx4_out_port>,
+		       <&adx1_out1_port>, <&adx1_out2_port>,
+		       <&adx1_out3_port>, <&adx1_out4_port>,
+		       <&adx2_out1_port>, <&adx2_out2_port>,
+		       <&adx2_out3_port>, <&adx2_out4_port>,
+		       <&adx3_out1_port>, <&adx3_out2_port>,
+		       <&adx3_out3_port>, <&adx3_out4_port>,
+		       <&adx4_out1_port>, <&adx4_out2_port>,
+		       <&adx4_out3_port>, <&adx4_out4_port>,
+		       <&mix_out1_port>, <&mix_out2_port>, <&mix_out3_port>,
+		       <&mix_out4_port>, <&mix_out5_port>,
+		       <&asrc_out1_port>, <&asrc_out2_port>, <&asrc_out3_port>,
+		       <&asrc_out4_port>, <&asrc_out5_port>, <&asrc_out6_port>,
+		       <&ope1_out_port>,
+		       /* BE I/O Ports */
+		       <&i2s2_port>, <&i2s4_port>;
+	};
+
 	thermal-zones {
 		tj-thermal {
 			polling-delay = <1000>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0000.dts
index 61b0e69d3d20..1607ee14216f 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0000.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0000.dts
@@ -4,7 +4,7 @@
 #include <dt-bindings/input/linux-event-codes.h>
 #include <dt-bindings/input/gpio-keys.h>
 
-#include "tegra234-p3767-0000.dtsi"
+#include "tegra234-p3767.dtsi"
 #include "tegra234-p3768-0000.dtsi"
 
 / {
@@ -37,7 +37,6 @@
 
 		hda@3510000 {
 			nvidia,model = "NVIDIA Jetson Orin NX HDA";
-			status = "okay";
 		};
 
 		padctl@3520000 {
@@ -85,6 +84,10 @@
 		enable-active-high;
 	};
 
+	sound {
+		label = "NVIDIA Jetson Orin NX APE";
+	};
+
 	thermal-zones {
 		tj-thermal {
 			cooling-maps {
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0005.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0005.dts
index 9e9bb9ca8be4..dc2d4bef1e83 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0005.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-p3768-0000+p3767-0005.dts
@@ -4,17 +4,27 @@
 #include <dt-bindings/input/linux-event-codes.h>
 #include <dt-bindings/input/gpio-keys.h>
 
-#include "tegra234-p3767-0005.dtsi"
+#include "tegra234-p3767.dtsi"
 #include "tegra234-p3768-0000.dtsi"
 
 / {
 	compatible = "nvidia,p3768-0000+p3767-0005", "nvidia,p3767-0005", "nvidia,tegra234";
 	model = "NVIDIA Jetson Orin Nano Developer Kit";
 
+	bus@0 {
+		hda@3510000 {
+			nvidia,model = "NVIDIA Jetson Orin Nano HDA";
+		};
+	};
+
 	pwm-fan {
 		cooling-levels = <0 88 187 255>;
 	};
 
+	sound {
+		label = "NVIDIA Jetson Orin Nano APE";
+	};
+
 	thermal-zones {
 		tj-thermal {
 			cooling-maps {
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
index 9f3e9f30c3f7..292e28376eec 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
+++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
@@ -8,7 +8,6 @@
 	compatible = "nvidia,tegra234-vdk", "nvidia,tegra234";
 
 	aliases {
-		mmc3 = "/bus@0/mmc@3460000";
 		serial0 = &uarta;
 	};
 
diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
index 3f16595d099c..78cbfdd98dd1 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -200,6 +200,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S1";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s1_cif: endpoint {
+								remote-endpoint = <&xbar_i2s1>;
+							};
+						};
+
+						i2s1_port: port@1 {
+							reg = <1>;
+
+							i2s1_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_i2s2: i2s@2901100 {
@@ -214,6 +236,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S2";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s2_cif: endpoint {
+								remote-endpoint = <&xbar_i2s2>;
+							};
+						};
+
+						i2s2_port: port@1 {
+							reg = <1>;
+
+							i2s2_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_i2s3: i2s@2901200 {
@@ -228,6 +272,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S3";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s3_cif: endpoint {
+								remote-endpoint = <&xbar_i2s3>;
+							};
+						};
+
+						i2s3_port: port@1 {
+							reg = <1>;
+
+							i2s3_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_i2s4: i2s@2901300 {
@@ -242,6 +308,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S4";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s4_cif: endpoint {
+								remote-endpoint = <&xbar_i2s4>;
+							};
+						};
+
+						i2s4_port: port@1 {
+							reg = <1>;
+
+							i2s4_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_i2s5: i2s@2901400 {
@@ -256,6 +344,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S5";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s5_cif: endpoint {
+								remote-endpoint = <&xbar_i2s5>;
+							};
+						};
+
+						i2s5_port: port@1 {
+							reg = <1>;
+
+							i2s5_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_i2s6: i2s@2901500 {
@@ -270,6 +380,28 @@
 					assigned-clock-rates = <1536000>;
 					sound-name-prefix = "I2S6";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							i2s6_cif: endpoint {
+								remote-endpoint = <&xbar_i2s6>;
+							};
+						};
+
+						i2s6_port: port@1 {
+							reg = <1>;
+
+							i2s6_dap: endpoint {
+								dai-format = "i2s";
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_sfc1: sfc@2902000 {
@@ -277,7 +409,27 @@
 						     "nvidia,tegra210-sfc";
 					reg = <0x0 0x2902000 0x0 0x200>;
 					sound-name-prefix = "SFC1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							sfc1_cif_in: endpoint {
+								remote-endpoint = <&xbar_sfc1_in>;
+							};
+						};
+
+						sfc1_out_port: port@1 {
+							reg = <1>;
+
+							sfc1_cif_out: endpoint {
+								remote-endpoint = <&xbar_sfc1_out>;
+							};
+						};
+					};
 				};
 
 				tegra_sfc2: sfc@2902200 {
@@ -285,7 +437,27 @@
 						     "nvidia,tegra210-sfc";
 					reg = <0x0 0x2902200 0x0 0x200>;
 					sound-name-prefix = "SFC2";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							sfc2_cif_in: endpoint {
+								remote-endpoint = <&xbar_sfc2_in>;
+							};
+						};
+
+						sfc2_out_port: port@1 {
+							reg = <1>;
+
+							sfc2_cif_out: endpoint {
+								remote-endpoint = <&xbar_sfc2_out>;
+							};
+						};
+					};
 				};
 
 				tegra_sfc3: sfc@2902400 {
@@ -293,7 +465,27 @@
 						     "nvidia,tegra210-sfc";
 					reg = <0x0 0x2902400 0x0 0x200>;
 					sound-name-prefix = "SFC3";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							sfc3_cif_in: endpoint {
+								remote-endpoint = <&xbar_sfc3_in>;
+							};
+						};
+
+						sfc3_out_port: port@1 {
+							reg = <1>;
+
+							sfc3_cif_out: endpoint {
+								remote-endpoint = <&xbar_sfc3_out>;
+							};
+						};
+					};
 				};
 
 				tegra_sfc4: sfc@2902600 {
@@ -301,7 +493,27 @@
 						     "nvidia,tegra210-sfc";
 					reg = <0x0 0x2902600 0x0 0x200>;
 					sound-name-prefix = "SFC4";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							sfc4_cif_in: endpoint {
+								remote-endpoint = <&xbar_sfc4_in>;
+							};
+						};
+
+						sfc4_out_port: port@1 {
+							reg = <1>;
+
+							sfc4_cif_out: endpoint {
+								remote-endpoint = <&xbar_sfc4_out>;
+							};
+						};
+					};
 				};
 
 				tegra_amx1: amx@2903000 {
@@ -309,7 +521,51 @@
 						     "nvidia,tegra194-amx";
 					reg = <0x0 0x2903000 0x0 0x100>;
 					sound-name-prefix = "AMX1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							amx1_in1: endpoint {
+								remote-endpoint = <&xbar_amx1_in1>;
+							};
+						};
+
+						port@1 {
+							reg = <1>;
+
+							amx1_in2: endpoint {
+								remote-endpoint = <&xbar_amx1_in2>;
+							};
+						};
+
+						port@2 {
+							reg = <2>;
+
+							amx1_in3: endpoint {
+								remote-endpoint = <&xbar_amx1_in3>;
+							};
+						};
+
+						port@3 {
+							reg = <3>;
+
+							amx1_in4: endpoint {
+								remote-endpoint = <&xbar_amx1_in4>;
+							};
+						};
+
+						amx1_out_port: port@4 {
+							reg = <4>;
+
+							amx1_out: endpoint {
+								remote-endpoint = <&xbar_amx1_out>;
+							};
+						};
+					};
 				};
 
 				tegra_amx2: amx@2903100 {
@@ -317,7 +573,51 @@
 						     "nvidia,tegra194-amx";
 					reg = <0x0 0x2903100 0x0 0x100>;
 					sound-name-prefix = "AMX2";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							amx2_in1: endpoint {
+								remote-endpoint = <&xbar_amx2_in1>;
+							};
+						};
+
+						port@1 {
+							reg = <1>;
+
+							amx2_in2: endpoint {
+								remote-endpoint = <&xbar_amx2_in2>;
+							};
+						};
+
+						port@2 {
+							reg = <2>;
+
+							amx2_in3: endpoint {
+								remote-endpoint = <&xbar_amx2_in3>;
+							};
+						};
+
+						port@3 {
+							reg = <3>;
+
+							amx2_in4: endpoint {
+								remote-endpoint = <&xbar_amx2_in4>;
+							};
+						};
+
+						amx2_out_port: port@4 {
+							reg = <4>;
+
+							amx2_out: endpoint {
+								remote-endpoint = <&xbar_amx2_out>;
+							};
+						};
+					};
 				};
 
 				tegra_amx3: amx@2903200 {
@@ -325,7 +625,51 @@
 						     "nvidia,tegra194-amx";
 					reg = <0x0 0x2903200 0x0 0x100>;
 					sound-name-prefix = "AMX3";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							amx3_in1: endpoint {
+								remote-endpoint = <&xbar_amx3_in1>;
+							};
+						};
+
+						port@1 {
+							reg = <1>;
+
+							amx3_in2: endpoint {
+								remote-endpoint = <&xbar_amx3_in2>;
+							};
+						};
+
+						port@2 {
+							reg = <2>;
+
+							amx3_in3: endpoint {
+								remote-endpoint = <&xbar_amx3_in3>;
+							};
+						};
+
+						port@3 {
+							reg = <3>;
+
+							amx3_in4: endpoint {
+								remote-endpoint = <&xbar_amx3_in4>;
+							};
+						};
+
+						amx3_out_port: port@4 {
+							reg = <4>;
+
+							amx3_out: endpoint {
+								remote-endpoint = <&xbar_amx3_out>;
+							};
+						};
+					};
 				};
 
 				tegra_amx4: amx@2903300 {
@@ -333,7 +677,51 @@
 						     "nvidia,tegra194-amx";
 					reg = <0x0 0x2903300 0x0 0x100>;
 					sound-name-prefix = "AMX4";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							amx4_in1: endpoint {
+								remote-endpoint = <&xbar_amx4_in1>;
+							};
+						};
+
+						port@1 {
+							reg = <1>;
+
+							amx4_in2: endpoint {
+								remote-endpoint = <&xbar_amx4_in2>;
+							};
+						};
+
+						port@2 {
+							reg = <2>;
+
+							amx4_in3: endpoint {
+								remote-endpoint = <&xbar_amx4_in3>;
+							};
+						};
+
+						port@3 {
+							reg = <3>;
+
+							amx4_in4: endpoint {
+								remote-endpoint = <&xbar_amx4_in4>;
+							};
+						};
+
+						amx4_out_port: port@4 {
+							reg = <4>;
+
+							amx4_out: endpoint {
+								remote-endpoint = <&xbar_amx4_out>;
+							};
+						};
+					};
 				};
 
 				tegra_adx1: adx@2903800 {
@@ -341,7 +729,51 @@
 						     "nvidia,tegra210-adx";
 					reg = <0x0 0x2903800 0x0 0x100>;
 					sound-name-prefix = "ADX1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							adx1_in: endpoint {
+								remote-endpoint = <&xbar_adx1_in>;
+							};
+						};
+
+						adx1_out1_port: port@1 {
+							reg = <1>;
+
+							adx1_out1: endpoint {
+								remote-endpoint = <&xbar_adx1_out1>;
+							};
+						};
+
+						adx1_out2_port: port@2 {
+							reg = <2>;
+
+							adx1_out2: endpoint {
+								remote-endpoint = <&xbar_adx1_out2>;
+							};
+						};
+
+						adx1_out3_port: port@3 {
+							reg = <3>;
+
+							adx1_out3: endpoint {
+								remote-endpoint = <&xbar_adx1_out3>;
+							};
+						};
+
+						adx1_out4_port: port@4 {
+							reg = <4>;
+
+							adx1_out4: endpoint {
+								remote-endpoint = <&xbar_adx1_out4>;
+							};
+						};
+					};
 				};
 
 				tegra_adx2: adx@2903900 {
@@ -349,7 +781,51 @@
 						     "nvidia,tegra210-adx";
 					reg = <0x0 0x2903900 0x0 0x100>;
 					sound-name-prefix = "ADX2";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							adx2_in: endpoint {
+								remote-endpoint = <&xbar_adx2_in>;
+							};
+						};
+
+						adx2_out1_port: port@1 {
+							reg = <1>;
+
+							adx2_out1: endpoint {
+								remote-endpoint = <&xbar_adx2_out1>;
+							};
+						};
+
+						adx2_out2_port: port@2 {
+							reg = <2>;
+
+							adx2_out2: endpoint {
+								remote-endpoint = <&xbar_adx2_out2>;
+							};
+						};
+
+						adx2_out3_port: port@3 {
+							reg = <3>;
+
+							adx2_out3: endpoint {
+								remote-endpoint = <&xbar_adx2_out3>;
+							};
+						};
+
+						adx2_out4_port: port@4 {
+							reg = <4>;
+
+							adx2_out4: endpoint {
+								remote-endpoint = <&xbar_adx2_out4>;
+							};
+						};
+					};
 				};
 
 				tegra_adx3: adx@2903a00 {
@@ -357,7 +833,51 @@
 						     "nvidia,tegra210-adx";
 					reg = <0x0 0x2903a00 0x0 0x100>;
 					sound-name-prefix = "ADX3";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							adx3_in: endpoint {
+								remote-endpoint = <&xbar_adx3_in>;
+							};
+						};
+
+						adx3_out1_port: port@1 {
+							reg = <1>;
+
+							adx3_out1: endpoint {
+								remote-endpoint = <&xbar_adx3_out1>;
+							};
+						};
+
+						adx3_out2_port: port@2 {
+							reg = <2>;
+
+							adx3_out2: endpoint {
+								remote-endpoint = <&xbar_adx3_out2>;
+							};
+						};
+
+						adx3_out3_port: port@3 {
+							reg = <3>;
+
+							adx3_out3: endpoint {
+								remote-endpoint = <&xbar_adx3_out3>;
+							};
+						};
+
+						adx3_out4_port: port@4 {
+							reg = <4>;
+
+							adx3_out4: endpoint {
+								remote-endpoint = <&xbar_adx3_out4>;
+							};
+						};
+					};
 				};
 
 				tegra_adx4: adx@2903b00 {
@@ -365,7 +885,51 @@
 						     "nvidia,tegra210-adx";
 					reg = <0x0 0x2903b00 0x0 0x100>;
 					sound-name-prefix = "ADX4";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							adx4_in: endpoint {
+								remote-endpoint = <&xbar_adx4_in>;
+							};
+						};
+
+						adx4_out1_port: port@1 {
+							reg = <1>;
+
+							adx4_out1: endpoint {
+								remote-endpoint = <&xbar_adx4_out1>;
+							};
+						};
+
+						adx4_out2_port: port@2 {
+							reg = <2>;
+
+							adx4_out2: endpoint {
+								remote-endpoint = <&xbar_adx4_out2>;
+							};
+						};
+
+						adx4_out3_port: port@3 {
+							reg = <3>;
+
+							adx4_out3: endpoint {
+								remote-endpoint = <&xbar_adx4_out3>;
+							};
+						};
+
+						adx4_out4_port: port@4 {
+							reg = <4>;
+
+							adx4_out4: endpoint {
+								remote-endpoint = <&xbar_adx4_out4>;
+							};
+						};
+					};
 				};
 
 
@@ -380,6 +944,27 @@
 					assigned-clock-rates = <3072000>;
 					sound-name-prefix = "DMIC1";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dmic1_cif: endpoint {
+								remote-endpoint = <&xbar_dmic1>;
+							};
+						};
+
+						dmic1_port: port@1 {
+							reg = <1>;
+
+							dmic1_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_dmic2: dmic@2904100 {
@@ -393,6 +978,27 @@
 					assigned-clock-rates = <3072000>;
 					sound-name-prefix = "DMIC2";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dmic2_cif: endpoint {
+								remote-endpoint = <&xbar_dmic2>;
+							};
+						};
+
+						dmic2_port: port@1 {
+							reg = <1>;
+
+							dmic2_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_dmic3: dmic@2904200 {
@@ -406,6 +1012,27 @@
 					assigned-clock-rates = <3072000>;
 					sound-name-prefix = "DMIC3";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dmic3_cif: endpoint {
+								remote-endpoint = <&xbar_dmic3>;
+							};
+						};
+
+						dmic3_port: port@1 {
+							reg = <1>;
+
+							dmic3_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_dmic4: dmic@2904300 {
@@ -419,6 +1046,27 @@
 					assigned-clock-rates = <3072000>;
 					sound-name-prefix = "DMIC4";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dmic4_cif: endpoint {
+								remote-endpoint = <&xbar_dmic4>;
+							};
+						};
+
+						dmic4_port: port@1 {
+							reg = <1>;
+
+							dmic4_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_dspk1: dspk@2905000 {
@@ -432,6 +1080,27 @@
 					assigned-clock-rates = <12288000>;
 					sound-name-prefix = "DSPK1";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dspk1_cif: endpoint {
+								remote-endpoint = <&xbar_dspk1>;
+							};
+						};
+
+						dspk1_port: port@1 {
+							reg = <1>;
+
+							dspk1_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_dspk2: dspk@2905100 {
@@ -445,6 +1114,27 @@
 					assigned-clock-rates = <12288000>;
 					sound-name-prefix = "DSPK2";
 					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							dspk2_cif: endpoint {
+								remote-endpoint = <&xbar_dspk2>;
+							};
+						};
+
+						dspk2_port: port@1 {
+							reg = <1>;
+
+							dspk2_dap: endpoint {
+								/* placeholder for external codec */
+							};
+						};
+					};
 				};
 
 				tegra_ope1: processing-engine@2908000 {
@@ -452,7 +1142,6 @@
 						     "nvidia,tegra210-ope";
 					reg = <0x0 0x2908000 0x0 0x100>;
 					sound-name-prefix = "OPE1";
-					status = "disabled";
 
 					#address-cells = <2>;
 					#size-cells = <2>;
@@ -469,6 +1158,29 @@
 							     "nvidia,tegra210-mbdrc";
 						reg = <0x0 0x2908200 0x0 0x200>;
 					};
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0x0>;
+
+							ope1_cif_in_ep: endpoint {
+								remote-endpoint =
+									<&xbar_ope1_in_ep>;
+							};
+						};
+
+						ope1_out_port: port@1 {
+							reg = <0x1>;
+
+							ope1_cif_out_ep: endpoint {
+								remote-endpoint =
+									<&xbar_ope1_out_ep>;
+							};
+						};
+					};
 				};
 
 				tegra_mvc1: mvc@290a000 {
@@ -476,7 +1188,27 @@
 						     "nvidia,tegra210-mvc";
 					reg = <0x0 0x290a000 0x0 0x200>;
 					sound-name-prefix = "MVC1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							mvc1_cif_in: endpoint {
+								remote-endpoint = <&xbar_mvc1_in>;
+							};
+						};
+
+						mvc1_out_port: port@1 {
+							reg = <1>;
+
+							mvc1_cif_out: endpoint {
+								remote-endpoint = <&xbar_mvc1_out>;
+							};
+						};
+					};
 				};
 
 				tegra_mvc2: mvc@290a200 {
@@ -484,7 +1216,27 @@
 						     "nvidia,tegra210-mvc";
 					reg = <0x0 0x290a200 0x0 0x200>;
 					sound-name-prefix = "MVC2";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0>;
+
+							mvc2_cif_in: endpoint {
+								remote-endpoint = <&xbar_mvc2_in>;
+							};
+						};
+
+						mvc2_out_port: port@1 {
+							reg = <1>;
+
+							mvc2_cif_out: endpoint {
+								remote-endpoint = <&xbar_mvc2_out>;
+							};
+						};
+					};
 				};
 
 				tegra_amixer: amixer@290bb00 {
@@ -492,7 +1244,131 @@
 						     "nvidia,tegra210-amixer";
 					reg = <0x0 0x290bb00 0x0 0x800>;
 					sound-name-prefix = "MIXER1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0x0>;
+
+							mix_in1: endpoint {
+								remote-endpoint = <&xbar_mix_in1>;
+							};
+						};
+
+						port@1 {
+							reg = <0x1>;
+
+							mix_in2: endpoint {
+								remote-endpoint = <&xbar_mix_in2>;
+							};
+						};
+
+						port@2 {
+							reg = <0x2>;
+
+							mix_in3: endpoint {
+								remote-endpoint = <&xbar_mix_in3>;
+							};
+						};
+
+						port@3 {
+							reg = <0x3>;
+
+							mix_in4: endpoint {
+								remote-endpoint = <&xbar_mix_in4>;
+							};
+						};
+
+						port@4 {
+							reg = <0x4>;
+
+							mix_in5: endpoint {
+								remote-endpoint = <&xbar_mix_in5>;
+							};
+						};
+
+						port@5 {
+							reg = <0x5>;
+
+							mix_in6: endpoint {
+								remote-endpoint = <&xbar_mix_in6>;
+							};
+						};
+
+						port@6 {
+							reg = <0x6>;
+
+							mix_in7: endpoint {
+								remote-endpoint = <&xbar_mix_in7>;
+							};
+						};
+
+						port@7 {
+							reg = <0x7>;
+
+							mix_in8: endpoint {
+								remote-endpoint = <&xbar_mix_in8>;
+							};
+						};
+
+						port@8 {
+							reg = <0x8>;
+
+							mix_in9: endpoint {
+								remote-endpoint = <&xbar_mix_in9>;
+							};
+						};
+
+						port@9 {
+							reg = <0x9>;
+
+							mix_in10: endpoint {
+								remote-endpoint = <&xbar_mix_in10>;
+							};
+						};
+
+						mix_out1_port: port@a {
+							reg = <0xa>;
+
+							mix_out1: endpoint {
+								remote-endpoint = <&xbar_mix_out1>;
+							};
+						};
+
+						mix_out2_port: port@b {
+							reg = <0xb>;
+
+							mix_out2: endpoint {
+								remote-endpoint = <&xbar_mix_out2>;
+							};
+						};
+
+						mix_out3_port: port@c {
+							reg = <0xc>;
+
+							mix_out3: endpoint {
+								remote-endpoint = <&xbar_mix_out3>;
+							};
+						};
+
+						mix_out4_port: port@d {
+							reg = <0xd>;
+
+							mix_out4: endpoint {
+								remote-endpoint = <&xbar_mix_out4>;
+							};
+						};
+
+						mix_out5_port: port@e {
+							reg = <0xe>;
+
+							mix_out5: endpoint {
+								remote-endpoint = <&xbar_mix_out5>;
+							};
+						};
+					};
 				};
 
 				tegra_admaif: admaif@290f000 {
@@ -543,7 +1419,171 @@
 							<&mc TEGRA234_MEMORY_CLIENT_APEDMAW &emc>;
 					interconnect-names = "dma-mem", "write";
 					iommus = <&smmu_niso0 TEGRA234_SID_APE>;
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						admaif0_port: port@0 {
+							reg = <0x0>;
+
+							admaif0: endpoint {
+								remote-endpoint = <&xbar_admaif0>;
+							};
+						};
+
+						admaif1_port: port@1 {
+							reg = <0x1>;
+
+							admaif1: endpoint {
+								remote-endpoint = <&xbar_admaif1>;
+							};
+						};
+
+						admaif2_port: port@2 {
+							reg = <0x2>;
+
+							admaif2: endpoint {
+								remote-endpoint = <&xbar_admaif2>;
+							};
+						};
+
+						admaif3_port: port@3 {
+							reg = <0x3>;
+
+							admaif3: endpoint {
+								remote-endpoint = <&xbar_admaif3>;
+							};
+						};
+
+						admaif4_port: port@4 {
+							reg = <0x4>;
+
+							admaif4: endpoint {
+								remote-endpoint = <&xbar_admaif4>;
+							};
+						};
+
+						admaif5_port: port@5 {
+							reg = <0x5>;
+
+							admaif5: endpoint {
+								remote-endpoint = <&xbar_admaif5>;
+							};
+						};
+
+						admaif6_port: port@6 {
+							reg = <0x6>;
+
+							admaif6: endpoint {
+								remote-endpoint = <&xbar_admaif6>;
+							};
+						};
+
+						admaif7_port: port@7 {
+							reg = <0x7>;
+
+							admaif7: endpoint {
+								remote-endpoint = <&xbar_admaif7>;
+							};
+						};
+
+						admaif8_port: port@8 {
+							reg = <0x8>;
+
+							admaif8: endpoint {
+								remote-endpoint = <&xbar_admaif8>;
+							};
+						};
+
+						admaif9_port: port@9 {
+							reg = <0x9>;
+
+							admaif9: endpoint {
+								remote-endpoint = <&xbar_admaif9>;
+							};
+						};
+
+						admaif10_port: port@a {
+							reg = <0xa>;
+
+							admaif10: endpoint {
+								remote-endpoint = <&xbar_admaif10>;
+							};
+						};
+
+						admaif11_port: port@b {
+							reg = <0xb>;
+
+							admaif11: endpoint {
+								remote-endpoint = <&xbar_admaif11>;
+							};
+						};
+
+						admaif12_port: port@c {
+							reg = <0xc>;
+
+							admaif12: endpoint {
+								remote-endpoint = <&xbar_admaif12>;
+							};
+						};
+
+						admaif13_port: port@d {
+							reg = <0xd>;
+
+							admaif13: endpoint {
+								remote-endpoint = <&xbar_admaif13>;
+							};
+						};
+
+						admaif14_port: port@e {
+							reg = <0xe>;
+
+							admaif14: endpoint {
+								remote-endpoint = <&xbar_admaif14>;
+							};
+						};
+
+						admaif15_port: port@f {
+							reg = <0xf>;
+
+							admaif15: endpoint {
+								remote-endpoint = <&xbar_admaif15>;
+							};
+						};
+
+						admaif16_port: port@10 {
+							reg = <0x10>;
+
+							admaif16: endpoint {
+								remote-endpoint = <&xbar_admaif16>;
+							};
+						};
+
+						admaif17_port: port@11 {
+							reg = <0x11>;
+
+							admaif17: endpoint {
+								remote-endpoint = <&xbar_admaif17>;
+							};
+						};
+
+						admaif18_port: port@12 {
+							reg = <0x12>;
+
+							admaif18: endpoint {
+								remote-endpoint = <&xbar_admaif18>;
+							};
+						};
+
+						admaif19_port: port@13 {
+							reg = <0x13>;
+
+							admaif19: endpoint {
+								remote-endpoint = <&xbar_admaif19>;
+							};
+						};
+					};
 				};
 
 				tegra_asrc: asrc@2910000 {
@@ -551,7 +1591,1045 @@
 						     "nvidia,tegra186-asrc";
 					reg = <0x0 0x2910000 0x0 0x2000>;
 					sound-name-prefix = "ASRC1";
-					status = "disabled";
+
+					ports {
+						#address-cells = <1>;
+						#size-cells = <0>;
+
+						port@0 {
+							reg = <0x0>;
+
+							asrc_in1_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in1_ep>;
+							};
+						};
+
+						port@1 {
+							reg = <0x1>;
+
+							asrc_in2_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in2_ep>;
+							};
+						};
+
+						port@2 {
+							reg = <0x2>;
+
+							asrc_in3_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in3_ep>;
+							};
+						};
+
+						port@3 {
+							reg = <0x3>;
+
+							asrc_in4_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in4_ep>;
+							};
+						};
+
+						port@4 {
+							reg = <0x4>;
+
+							asrc_in5_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in5_ep>;
+							};
+						};
+
+						port@5 {
+							reg = <0x5>;
+
+							asrc_in6_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in6_ep>;
+							};
+						};
+
+						port@6 {
+							reg = <0x6>;
+
+							asrc_in7_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_in7_ep>;
+							};
+						};
+
+						asrc_out1_port: port@7 {
+							reg = <0x7>;
+
+							asrc_out1_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out1_ep>;
+							};
+						};
+
+						asrc_out2_port: port@8 {
+							reg = <0x8>;
+
+							asrc_out2_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out2_ep>;
+							};
+						};
+
+						asrc_out3_port: port@9 {
+							reg = <0x9>;
+
+							asrc_out3_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out3_ep>;
+							};
+						};
+
+						asrc_out4_port: port@a {
+							reg = <0xa>;
+
+							asrc_out4_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out4_ep>;
+							};
+						};
+
+						asrc_out5_port: port@b {
+							reg = <0xb>;
+
+							asrc_out5_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out5_ep>;
+							};
+						};
+
+						asrc_out6_port:	port@c {
+							reg = <0xc>;
+
+							asrc_out6_ep: endpoint {
+								remote-endpoint =
+									<&xbar_asrc_out6_ep>;
+							};
+						};
+					};
+				};
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0x0>;
+
+						xbar_admaif0: endpoint {
+							remote-endpoint = <&admaif0>;
+						};
+					};
+
+					port@1 {
+						reg = <0x1>;
+
+						xbar_admaif1: endpoint {
+							remote-endpoint = <&admaif1>;
+						};
+					};
+
+					port@2 {
+						reg = <0x2>;
+
+						xbar_admaif2: endpoint {
+							remote-endpoint = <&admaif2>;
+						};
+					};
+
+					port@3 {
+						reg = <0x3>;
+
+						xbar_admaif3: endpoint {
+							remote-endpoint = <&admaif3>;
+						};
+					};
+
+					port@4 {
+						reg = <0x4>;
+
+						xbar_admaif4: endpoint {
+							remote-endpoint = <&admaif4>;
+						};
+					};
+
+					port@5 {
+						reg = <0x5>;
+
+						xbar_admaif5: endpoint {
+							remote-endpoint = <&admaif5>;
+						};
+					};
+
+					port@6 {
+						reg = <0x6>;
+
+						xbar_admaif6: endpoint {
+							remote-endpoint = <&admaif6>;
+						};
+					};
+
+					port@7 {
+						reg = <0x7>;
+
+						xbar_admaif7: endpoint {
+							remote-endpoint = <&admaif7>;
+						};
+					};
+
+					port@8 {
+						reg = <0x8>;
+
+						xbar_admaif8: endpoint {
+							remote-endpoint = <&admaif8>;
+						};
+					};
+
+					port@9 {
+						reg = <0x9>;
+
+						xbar_admaif9: endpoint {
+							remote-endpoint = <&admaif9>;
+						};
+					};
+
+					port@a {
+						reg = <0xa>;
+
+						xbar_admaif10: endpoint {
+							remote-endpoint = <&admaif10>;
+						};
+					};
+
+					port@b {
+						reg = <0xb>;
+
+						xbar_admaif11: endpoint {
+							remote-endpoint = <&admaif11>;
+						};
+					};
+
+					port@c {
+						reg = <0xc>;
+
+						xbar_admaif12: endpoint {
+							remote-endpoint = <&admaif12>;
+						};
+					};
+
+					port@d {
+						reg = <0xd>;
+
+						xbar_admaif13: endpoint {
+							remote-endpoint = <&admaif13>;
+						};
+					};
+
+					port@e {
+						reg = <0xe>;
+
+						xbar_admaif14: endpoint {
+							remote-endpoint = <&admaif14>;
+						};
+					};
+
+					port@f {
+						reg = <0xf>;
+
+						xbar_admaif15: endpoint {
+							remote-endpoint = <&admaif15>;
+						};
+					};
+
+					port@10 {
+						reg = <0x10>;
+
+						xbar_admaif16: endpoint {
+							remote-endpoint = <&admaif16>;
+						};
+					};
+
+					port@11 {
+						reg = <0x11>;
+
+						xbar_admaif17: endpoint {
+							remote-endpoint = <&admaif17>;
+						};
+					};
+
+					port@12 {
+						reg = <0x12>;
+
+						xbar_admaif18: endpoint {
+							remote-endpoint = <&admaif18>;
+						};
+					};
+
+					port@13 {
+						reg = <0x13>;
+
+						xbar_admaif19: endpoint {
+							remote-endpoint = <&admaif19>;
+						};
+					};
+
+					xbar_i2s1_port: port@14 {
+						reg = <0x14>;
+
+						xbar_i2s1: endpoint {
+							remote-endpoint = <&i2s1_cif>;
+						};
+					};
+
+					xbar_i2s2_port: port@15 {
+						reg = <0x15>;
+
+						xbar_i2s2: endpoint {
+							remote-endpoint = <&i2s2_cif>;
+						};
+					};
+
+					xbar_i2s3_port: port@16 {
+						reg = <0x16>;
+
+						xbar_i2s3: endpoint {
+							remote-endpoint = <&i2s3_cif>;
+						};
+					};
+
+					xbar_i2s4_port: port@17 {
+						reg = <0x17>;
+
+						xbar_i2s4: endpoint {
+							remote-endpoint = <&i2s4_cif>;
+						};
+					};
+
+					xbar_i2s5_port: port@18 {
+						reg = <0x18>;
+
+						xbar_i2s5: endpoint {
+							remote-endpoint = <&i2s5_cif>;
+						};
+					};
+
+					xbar_i2s6_port: port@19 {
+						reg = <0x19>;
+
+						xbar_i2s6: endpoint {
+							remote-endpoint = <&i2s6_cif>;
+						};
+					};
+
+					xbar_dmic1_port: port@1a {
+						reg = <0x1a>;
+
+						xbar_dmic1: endpoint {
+							remote-endpoint = <&dmic1_cif>;
+						};
+					};
+
+					xbar_dmic2_port: port@1b {
+						reg = <0x1b>;
+
+						xbar_dmic2: endpoint {
+							remote-endpoint = <&dmic2_cif>;
+						};
+					};
+
+					xbar_dmic3_port: port@1c {
+						reg = <0x1c>;
+
+						xbar_dmic3: endpoint {
+							remote-endpoint = <&dmic3_cif>;
+						};
+					};
+
+					xbar_dmic4_port: port@1d {
+						reg = <0x1d>;
+
+						xbar_dmic4: endpoint {
+							remote-endpoint = <&dmic4_cif>;
+						};
+					};
+
+					xbar_dspk1_port: port@1e {
+						reg = <0x1e>;
+
+						xbar_dspk1: endpoint {
+							remote-endpoint = <&dspk1_cif>;
+						};
+					};
+
+					xbar_dspk2_port: port@1f {
+						reg = <0x1f>;
+
+						xbar_dspk2: endpoint {
+							remote-endpoint = <&dspk2_cif>;
+						};
+					};
+
+					xbar_sfc1_in_port: port@20 {
+						reg = <0x20>;
+
+						xbar_sfc1_in: endpoint {
+							remote-endpoint = <&sfc1_cif_in>;
+						};
+					};
+
+					port@21 {
+						reg = <0x21>;
+
+						xbar_sfc1_out: endpoint {
+							remote-endpoint = <&sfc1_cif_out>;
+						};
+					};
+
+					xbar_sfc2_in_port: port@22 {
+						reg = <0x22>;
+
+						xbar_sfc2_in: endpoint {
+							remote-endpoint = <&sfc2_cif_in>;
+						};
+					};
+
+					port@23 {
+						reg = <0x23>;
+
+						xbar_sfc2_out: endpoint {
+							remote-endpoint = <&sfc2_cif_out>;
+						};
+					};
+
+					xbar_sfc3_in_port: port@24 {
+						reg = <0x24>;
+
+						xbar_sfc3_in: endpoint {
+							remote-endpoint = <&sfc3_cif_in>;
+						};
+					};
+
+					port@25 {
+						reg = <0x25>;
+
+						xbar_sfc3_out: endpoint {
+							remote-endpoint = <&sfc3_cif_out>;
+						};
+					};
+
+					xbar_sfc4_in_port: port@26 {
+						reg = <0x26>;
+
+						xbar_sfc4_in: endpoint {
+							remote-endpoint = <&sfc4_cif_in>;
+						};
+					};
+
+					port@27 {
+						reg = <0x27>;
+
+						xbar_sfc4_out: endpoint {
+							remote-endpoint = <&sfc4_cif_out>;
+						};
+					};
+
+					xbar_mvc1_in_port: port@28 {
+						reg = <0x28>;
+
+						xbar_mvc1_in: endpoint {
+							remote-endpoint = <&mvc1_cif_in>;
+						};
+					};
+
+					port@29 {
+						reg = <0x29>;
+
+						xbar_mvc1_out: endpoint {
+							remote-endpoint = <&mvc1_cif_out>;
+						};
+					};
+
+					xbar_mvc2_in_port: port@2a {
+						reg = <0x2a>;
+
+						xbar_mvc2_in: endpoint {
+							remote-endpoint = <&mvc2_cif_in>;
+						};
+					};
+
+					port@2b {
+						reg = <0x2b>;
+
+						xbar_mvc2_out: endpoint {
+							remote-endpoint = <&mvc2_cif_out>;
+						};
+					};
+
+					xbar_amx1_in1_port: port@2c {
+						reg = <0x2c>;
+
+						xbar_amx1_in1: endpoint {
+							remote-endpoint = <&amx1_in1>;
+						};
+					};
+
+					xbar_amx1_in2_port: port@2d {
+						reg = <0x2d>;
+
+						xbar_amx1_in2: endpoint {
+							remote-endpoint = <&amx1_in2>;
+						};
+					};
+
+					xbar_amx1_in3_port: port@2e {
+						reg = <0x2e>;
+
+						xbar_amx1_in3: endpoint {
+							remote-endpoint = <&amx1_in3>;
+						};
+					};
+
+					xbar_amx1_in4_port: port@2f {
+						reg = <0x2f>;
+
+						xbar_amx1_in4: endpoint {
+							remote-endpoint = <&amx1_in4>;
+						};
+					};
+
+					port@30 {
+						reg = <0x30>;
+
+						xbar_amx1_out: endpoint {
+							remote-endpoint = <&amx1_out>;
+						};
+					};
+
+					xbar_amx2_in1_port: port@31 {
+						reg = <0x31>;
+
+						xbar_amx2_in1: endpoint {
+							remote-endpoint = <&amx2_in1>;
+						};
+					};
+
+					xbar_amx2_in2_port: port@32 {
+						reg = <0x32>;
+
+						xbar_amx2_in2: endpoint {
+							remote-endpoint = <&amx2_in2>;
+						};
+					};
+
+					xbar_amx2_in3_port: port@33 {
+						reg = <0x33>;
+
+						xbar_amx2_in3: endpoint {
+							remote-endpoint = <&amx2_in3>;
+						};
+					};
+
+					xbar_amx2_in4_port: port@34 {
+						reg = <0x34>;
+
+						xbar_amx2_in4: endpoint {
+							remote-endpoint = <&amx2_in4>;
+						};
+					};
+
+					port@35 {
+						reg = <0x35>;
+
+						xbar_amx2_out: endpoint {
+							remote-endpoint = <&amx2_out>;
+						};
+					};
+
+					xbar_amx3_in1_port: port@36 {
+						reg = <0x36>;
+
+						xbar_amx3_in1: endpoint {
+							remote-endpoint = <&amx3_in1>;
+						};
+					};
+
+					xbar_amx3_in2_port: port@37 {
+						reg = <0x37>;
+
+						xbar_amx3_in2: endpoint {
+							remote-endpoint = <&amx3_in2>;
+						};
+					};
+
+					xbar_amx3_in3_port: port@38 {
+						reg = <0x38>;
+
+						xbar_amx3_in3: endpoint {
+							remote-endpoint = <&amx3_in3>;
+						};
+					};
+
+					xbar_amx3_in4_port: port@39 {
+						reg = <0x39>;
+
+						xbar_amx3_in4: endpoint {
+							remote-endpoint = <&amx3_in4>;
+						};
+					};
+
+					port@3a {
+						reg = <0x3a>;
+
+						xbar_amx3_out: endpoint {
+							remote-endpoint = <&amx3_out>;
+						};
+					};
+
+					xbar_amx4_in1_port: port@3b {
+						reg = <0x3b>;
+
+						xbar_amx4_in1: endpoint {
+							remote-endpoint = <&amx4_in1>;
+						};
+					};
+
+					xbar_amx4_in2_port: port@3c {
+						reg = <0x3c>;
+
+						xbar_amx4_in2: endpoint {
+							remote-endpoint = <&amx4_in2>;
+						};
+					};
+
+					xbar_amx4_in3_port: port@3d {
+						reg = <0x3d>;
+
+						xbar_amx4_in3: endpoint {
+							remote-endpoint = <&amx4_in3>;
+						};
+					};
+
+					xbar_amx4_in4_port: port@3e {
+						reg = <0x3e>;
+
+						xbar_amx4_in4: endpoint {
+							remote-endpoint = <&amx4_in4>;
+						};
+					};
+
+					port@3f {
+						reg = <0x3f>;
+
+						xbar_amx4_out: endpoint {
+							remote-endpoint = <&amx4_out>;
+						};
+					};
+
+					xbar_adx1_in_port: port@40 {
+						reg = <0x40>;
+
+						xbar_adx1_in: endpoint {
+							remote-endpoint = <&adx1_in>;
+						};
+					};
+
+					port@41 {
+						reg = <0x41>;
+
+						xbar_adx1_out1: endpoint {
+							remote-endpoint = <&adx1_out1>;
+						};
+					};
+
+					port@42 {
+						reg = <0x42>;
+
+						xbar_adx1_out2: endpoint {
+							remote-endpoint = <&adx1_out2>;
+						};
+					};
+
+					port@43 {
+						reg = <0x43>;
+
+						xbar_adx1_out3: endpoint {
+							remote-endpoint = <&adx1_out3>;
+						};
+					};
+
+					port@44 {
+						reg = <0x44>;
+
+						xbar_adx1_out4: endpoint {
+							remote-endpoint = <&adx1_out4>;
+						};
+					};
+
+					xbar_adx2_in_port: port@45 {
+						reg = <0x45>;
+
+						xbar_adx2_in: endpoint {
+							remote-endpoint = <&adx2_in>;
+						};
+					};
+
+					port@46 {
+						reg = <0x46>;
+
+						xbar_adx2_out1: endpoint {
+							remote-endpoint = <&adx2_out1>;
+						};
+					};
+
+					port@47 {
+						reg = <0x47>;
+
+						xbar_adx2_out2: endpoint {
+							remote-endpoint = <&adx2_out2>;
+						};
+					};
+
+					port@48 {
+						reg = <0x48>;
+
+						xbar_adx2_out3: endpoint {
+							remote-endpoint = <&adx2_out3>;
+						};
+					};
+
+					port@49 {
+						reg = <0x49>;
+
+						xbar_adx2_out4: endpoint {
+							remote-endpoint = <&adx2_out4>;
+						};
+					};
+
+					xbar_adx3_in_port: port@4a {
+						reg = <0x4a>;
+
+						xbar_adx3_in: endpoint {
+							remote-endpoint = <&adx3_in>;
+						};
+					};
+
+					port@4b {
+						reg = <0x4b>;
+
+						xbar_adx3_out1: endpoint {
+							remote-endpoint = <&adx3_out1>;
+						};
+					};
+
+					port@4c {
+						reg = <0x4c>;
+
+						xbar_adx3_out2: endpoint {
+							remote-endpoint = <&adx3_out2>;
+						};
+					};
+
+					port@4d {
+						reg = <0x4d>;
+
+						xbar_adx3_out3: endpoint {
+							remote-endpoint = <&adx3_out3>;
+						};
+					};
+
+					port@4e {
+						reg = <0x4e>;
+
+						xbar_adx3_out4: endpoint {
+							remote-endpoint = <&adx3_out4>;
+						};
+					};
+
+					xbar_adx4_in_port: port@4f {
+						reg = <0x4f>;
+
+						xbar_adx4_in: endpoint {
+							remote-endpoint = <&adx4_in>;
+						};
+					};
+
+					port@50 {
+						reg = <0x50>;
+
+						xbar_adx4_out1: endpoint {
+							remote-endpoint = <&adx4_out1>;
+						};
+					};
+
+					port@51 {
+						reg = <0x51>;
+
+						xbar_adx4_out2: endpoint {
+							remote-endpoint = <&adx4_out2>;
+						};
+					};
+
+					port@52 {
+						reg = <0x52>;
+
+						xbar_adx4_out3: endpoint {
+							remote-endpoint = <&adx4_out3>;
+						};
+					};
+
+					port@53 {
+						reg = <0x53>;
+
+						xbar_adx4_out4: endpoint {
+							remote-endpoint = <&adx4_out4>;
+						};
+					};
+
+					xbar_mix_in1_port: port@54 {
+						reg = <0x54>;
+
+						xbar_mix_in1: endpoint {
+							remote-endpoint = <&mix_in1>;
+						};
+					};
+
+					xbar_mix_in2_port: port@55 {
+						reg = <0x55>;
+
+						xbar_mix_in2: endpoint {
+							remote-endpoint = <&mix_in2>;
+						};
+					};
+
+					xbar_mix_in3_port: port@56 {
+						reg = <0x56>;
+
+						xbar_mix_in3: endpoint {
+							remote-endpoint = <&mix_in3>;
+						};
+					};
+
+					xbar_mix_in4_port: port@57 {
+						reg = <0x57>;
+
+						xbar_mix_in4: endpoint {
+							remote-endpoint = <&mix_in4>;
+						};
+					};
+
+					xbar_mix_in5_port: port@58 {
+						reg = <0x58>;
+
+						xbar_mix_in5: endpoint {
+							remote-endpoint = <&mix_in5>;
+						};
+					};
+
+					xbar_mix_in6_port: port@59 {
+						reg = <0x59>;
+
+						xbar_mix_in6: endpoint {
+							remote-endpoint = <&mix_in6>;
+						};
+					};
+
+					xbar_mix_in7_port: port@5a {
+						reg = <0x5a>;
+
+						xbar_mix_in7: endpoint {
+							remote-endpoint = <&mix_in7>;
+						};
+					};
+
+					xbar_mix_in8_port: port@5b {
+						reg = <0x5b>;
+
+						xbar_mix_in8: endpoint {
+							remote-endpoint = <&mix_in8>;
+						};
+					};
+
+					xbar_mix_in9_port: port@5c {
+						reg = <0x5c>;
+
+						xbar_mix_in9: endpoint {
+							remote-endpoint = <&mix_in9>;
+						};
+					};
+
+					xbar_mix_in10_port: port@5d {
+						reg = <0x5d>;
+
+						xbar_mix_in10: endpoint {
+							remote-endpoint = <&mix_in10>;
+						};
+					};
+
+					port@5e {
+						reg = <0x5e>;
+
+						xbar_mix_out1: endpoint {
+							remote-endpoint = <&mix_out1>;
+						};
+					};
+
+					port@5f {
+						reg = <0x5f>;
+
+						xbar_mix_out2: endpoint {
+							remote-endpoint = <&mix_out2>;
+						};
+					};
+
+					port@60 {
+						reg = <0x60>;
+
+						xbar_mix_out3: endpoint {
+							remote-endpoint = <&mix_out3>;
+						};
+					};
+
+					port@61 {
+						reg = <0x61>;
+
+						xbar_mix_out4: endpoint {
+							remote-endpoint = <&mix_out4>;
+						};
+					};
+
+					port@62 {
+						reg = <0x62>;
+
+						xbar_mix_out5: endpoint {
+							remote-endpoint = <&mix_out5>;
+						};
+					};
+
+					xbar_asrc_in1_port: port@63 {
+						reg = <0x63>;
+
+						xbar_asrc_in1_ep: endpoint {
+							remote-endpoint = <&asrc_in1_ep>;
+						};
+					};
+
+					port@64 {
+						reg = <0x64>;
+
+						xbar_asrc_out1_ep: endpoint {
+							remote-endpoint = <&asrc_out1_ep>;
+						};
+					};
+
+					xbar_asrc_in2_port: port@65 {
+						reg = <0x65>;
+
+						xbar_asrc_in2_ep: endpoint {
+							remote-endpoint = <&asrc_in2_ep>;
+						};
+					};
+
+					port@66 {
+						reg = <0x66>;
+
+						xbar_asrc_out2_ep: endpoint {
+							remote-endpoint = <&asrc_out2_ep>;
+						};
+					};
+
+					xbar_asrc_in3_port: port@67 {
+						reg = <0x67>;
+
+						xbar_asrc_in3_ep: endpoint {
+							remote-endpoint = <&asrc_in3_ep>;
+						};
+					};
+
+					port@68 {
+						reg = <0x68>;
+
+						xbar_asrc_out3_ep: endpoint {
+							remote-endpoint = <&asrc_out3_ep>;
+						};
+					};
+
+					xbar_asrc_in4_port: port@69 {
+						reg = <0x69>;
+
+						xbar_asrc_in4_ep: endpoint {
+							remote-endpoint = <&asrc_in4_ep>;
+						};
+					};
+
+					port@6a {
+						reg = <0x6a>;
+
+						xbar_asrc_out4_ep: endpoint {
+							remote-endpoint = <&asrc_out4_ep>;
+						};
+					};
+
+					xbar_asrc_in5_port: port@6b {
+						reg = <0x6b>;
+
+						xbar_asrc_in5_ep: endpoint {
+							remote-endpoint = <&asrc_in5_ep>;
+						};
+					};
+
+					port@6c {
+						reg = <0x6c>;
+
+						xbar_asrc_out5_ep: endpoint {
+							remote-endpoint = <&asrc_out5_ep>;
+						};
+					};
+
+					xbar_asrc_in6_port: port@6d {
+						reg = <0x6d>;
+
+						xbar_asrc_in6_ep: endpoint {
+							remote-endpoint = <&asrc_in6_ep>;
+						};
+					};
+
+					port@6e {
+						reg = <0x6e>;
+
+						xbar_asrc_out6_ep: endpoint {
+							remote-endpoint = <&asrc_out6_ep>;
+						};
+					};
+
+					xbar_asrc_in7_port: port@6f {
+						reg = <0x6f>;
+
+						xbar_asrc_in7_ep: endpoint {
+							remote-endpoint = <&asrc_in7_ep>;
+						};
+					};
+
+					xbar_ope1_in_port: port@70 {
+						reg = <0x70>;
+
+						xbar_ope1_in_ep: endpoint {
+							remote-endpoint = <&ope1_cif_in_ep>;
+						};
+					};
+
+					port@71 {
+						reg = <0x71>;
+
+						xbar_ope1_out_ep: endpoint {
+							remote-endpoint = <&ope1_cif_out_ep>;
+						};
+					};
 				};
 			};
 
@@ -1459,8 +3537,16 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBEAWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEA>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>;
 			status = "disabled";
+
+			snps,axi-config = <&mgbe0_axi_setup>;
+
+			mgbe0_axi_setup: stmmac-axi-config {
+				snps,blen = <256 128 64 32>;
+				snps,rd_osr_lmt = <63>;
+				snps,wr_osr_lmt = <63>;
+			};
 		};
 
 		ethernet@6900000 {
@@ -1493,8 +3579,16 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBEBWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF1>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>;
 			status = "disabled";
+
+			snps,axi-config = <&mgbe1_axi_setup>;
+
+			mgbe1_axi_setup: stmmac-axi-config {
+				snps,blen = <256 128 64 32>;
+				snps,rd_osr_lmt = <63>;
+				snps,wr_osr_lmt = <63>;
+			};
 		};
 
 		ethernet@6a00000 {
@@ -1527,8 +3621,16 @@
 					<&mc TEGRA234_MEMORY_CLIENT_MGBECWR &emc>;
 			interconnect-names = "dma-mem", "write";
 			iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF2>;
-			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>;
+			power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBED>;
 			status = "disabled";
+
+			snps,axi-config = <&mgbe2_axi_setup>;
+
+			mgbe2_axi_setup: stmmac-axi-config {
+				snps,blen = <256 128 64 32>;
+				snps,rd_osr_lmt = <63>;
+				snps,wr_osr_lmt = <63>;
+			};
 		};
 
 		ethernet@6b00000 {
diff --git a/arch/arm64/boot/dts/qcom/Makefile b/arch/arm64/boot/dts/qcom/Makefile
index 39889d5f8e12..7d40ec5e7d21 100644
--- a/arch/arm64/boot/dts/qcom/Makefile
+++ b/arch/arm64/boot/dts/qcom/Makefile
@@ -23,6 +23,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= ipq9574-rdp433.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= ipq9574-rdp449.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= ipq9574-rdp453.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= ipq9574-rdp454.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= msm8216-samsung-fortuna3g.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-acer-a1-724.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-alcatel-idol347.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-asus-z00l.dtb
@@ -35,11 +36,14 @@ dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-a3u-eur.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-a5u-eur.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-e5.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-e7.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-gprimeltecan.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-grandmax.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-grandprimelte.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-gt510.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-gt58.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-j5.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-j5x.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-rossa.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-samsung-serranove.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-thwc-uf896.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= msm8916-thwc-ufi001c.dtb
@@ -210,6 +214,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= sm6125-sony-xperia-seine-pdx201.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm6125-xiaomi-laurel-sprout.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm6350-sony-xperia-lena-pdx213.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm6375-sony-xperia-murray-pdx225.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= sm7125-xiaomi-curtana.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm7125-xiaomi-joyeuse.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm7225-fairphone-fp4.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8150-hdk.dtb
@@ -233,6 +238,7 @@ dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-hdk.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-qrd.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-sony-xperia-nagara-pdx223.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8450-sony-xperia-nagara-pdx224.dtb
+dtb-$(CONFIG_ARCH_QCOM)	+= sm8550-hdk.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8550-mtp.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8550-qrd.dtb
 dtb-$(CONFIG_ARCH_QCOM)	+= sm8650-mtp.dtb
diff --git a/arch/arm64/boot/dts/qcom/apq8016-sbc-d3-camera-mezzanine.dts b/arch/arm64/boot/dts/qcom/apq8016-sbc-d3-camera-mezzanine.dts
index c08b4be5cc7e..f9cbf8c1d689 100644
--- a/arch/arm64/boot/dts/qcom/apq8016-sbc-d3-camera-mezzanine.dts
+++ b/arch/arm64/boot/dts/qcom/apq8016-sbc-d3-camera-mezzanine.dts
@@ -9,7 +9,7 @@
 #include "apq8016-sbc.dts"
 
 / {
-	camera_vdddo_1v8: camera-vdddo-1v8 {
+	camera_vdddo_1v8: regulator-camera-vdddo {
 		compatible = "regulator-fixed";
 		regulator-name = "camera_vdddo";
 		regulator-min-microvolt = <1800000>;
@@ -17,7 +17,7 @@
 		regulator-always-on;
 	};
 
-	camera_vdda_2v8: camera-vdda-2v8 {
+	camera_vdda_2v8: regulator-camera-vdda {
 		compatible = "regulator-fixed";
 		regulator-name = "camera_vdda";
 		regulator-min-microvolt = <2800000>;
@@ -25,7 +25,7 @@
 		regulator-always-on;
 	};
 
-	camera_vddd_1v5: camera-vddd-1v5 {
+	camera_vddd_1v5: regulator-camera-vddd {
 		compatible = "regulator-fixed";
 		regulator-name = "camera_vddd";
 		regulator-min-microvolt = <1500000>;
@@ -53,7 +53,7 @@
 };
 
 &cci_i2c0 {
-	camera_rear@3b {
+	camera@3b {
 		compatible = "ovti,ov5640";
 		reg = <0x3b>;
 
diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
index 42e2e48b2bc3..770d9c2fb456 100644
--- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
@@ -320,8 +320,12 @@
 			compatible = "qcom,ipq5332-dwc3", "qcom,dwc3";
 			reg = <0x08af8800 0x400>;
 
-			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq";
+			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 53 IRQ_TYPE_EDGE_BOTH>,
+				     <GIC_SPI 52 IRQ_TYPE_EDGE_BOTH>;
+			interrupt-names = "pwr_event",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq";
 
 			clocks = <&gcc GCC_USB0_MASTER_CLK>,
 				 <&gcc GCC_SNOC_USB_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
index 5e1277fea725..4e29adea570a 100644
--- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
@@ -9,6 +9,7 @@
 #include <dt-bindings/clock/qcom,gcc-ipq6018.h>
 #include <dt-bindings/reset/qcom,gcc-ipq6018.h>
 #include <dt-bindings/clock/qcom,apss-ipq.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	#address-cells = <2>;
@@ -43,6 +44,7 @@
 			clock-names = "cpu";
 			operating-points-v2 = <&cpu_opp_table>;
 			cpu-supply = <&ipq6018_s2>;
+			#cooling-cells = <2>;
 		};
 
 		CPU1: cpu@1 {
@@ -55,6 +57,7 @@
 			clock-names = "cpu";
 			operating-points-v2 = <&cpu_opp_table>;
 			cpu-supply = <&ipq6018_s2>;
+			#cooling-cells = <2>;
 		};
 
 		CPU2: cpu@2 {
@@ -67,6 +70,7 @@
 			clock-names = "cpu";
 			operating-points-v2 = <&cpu_opp_table>;
 			cpu-supply = <&ipq6018_s2>;
+			#cooling-cells = <2>;
 		};
 
 		CPU3: cpu@3 {
@@ -79,6 +83,7 @@
 			clock-names = "cpu";
 			operating-points-v2 = <&cpu_opp_table>;
 			cpu-supply = <&ipq6018_s2>;
+			#cooling-cells = <2>;
 		};
 
 		L2_0: l2-cache {
@@ -330,6 +335,16 @@
 			clock-names = "core";
 		};
 
+		tsens: thermal-sensor@4a9000 {
+			compatible = "qcom,ipq6018-tsens", "qcom,ipq8074-tsens";
+			reg = <0x0 0x004a9000 0x0 0x1000>,
+			      <0x0 0x004a8000 0x0 0x1000>;
+			interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "combined";
+			#qcom,sensors = <16>;
+			#thermal-sensor-cells = <1>;
+		};
+
 		cryptobam: dma-controller@704000 {
 			compatible = "qcom,bam-v1.7.0";
 			reg = <0x0 0x00704000 0x0 0x20000>;
@@ -418,6 +433,12 @@
 					  <&gcc GCC_USB1_MOCK_UTMI_CLK>;
 			assigned-clock-rates = <133330000>,
 					       <24000000>;
+
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy";
+
 			resets = <&gcc GCC_USB1_BCR>;
 			status = "disabled";
 
@@ -578,6 +599,21 @@
 			status = "disabled";
 		};
 
+		blsp1_i2c6: i2c@78ba000 {
+			compatible = "qcom,i2c-qup-v2.2.1";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x078ba000 0x0 0x600>;
+			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&gcc GCC_BLSP1_QUP6_I2C_APPS_CLK>,
+			       <&gcc GCC_BLSP1_AHB_CLK>;
+			clock-names = "core", "iface";
+			clock-frequency = <400000>;
+			dmas = <&blsp_dma 22>, <&blsp_dma 23>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
 		qpic_bam: dma-controller@7984000 {
 			compatible = "qcom,bam-v1.7.0";
 			reg = <0x0 0x07984000 0x0 0x1a000>;
@@ -630,6 +666,13 @@
 					       <133330000>,
 					       <24000000>;
 
+			interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "ss_phy_irq";
+
 			resets = <&gcc GCC_USB0_BCR>;
 			status = "disabled";
 
@@ -830,10 +873,10 @@
 
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 0 0 75 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 0 0 78 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 0 0 79 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 0 0 83 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>,
 				 <&gcc GCC_PCIE0_AXI_M_CLK>,
@@ -867,6 +910,122 @@
 		};
 	};
 
+	thermal-zones {
+		nss-top-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 4>;
+
+			trips {
+				nss-top-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		nss-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 5>;
+
+			trips {
+				nss-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		wcss-phya0-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 7>;
+
+			trips {
+				wcss-phya0-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		wcss-phya1-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 8>;
+
+			trips {
+				wcss-phya1-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 13>;
+
+			trips {
+				cpu-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+
+				cpu_alert: cpu-passive {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "passive";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu_alert>;
+					cooling-device = <&CPU0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&CPU1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&CPU2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							 <&CPU3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		lpass-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 14>;
+
+			trips {
+				lpass-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
+		ddrss-top-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens 15>;
+
+			trips {
+				ddrss-top-critical {
+					temperature = <125000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
index cf295bed3299..e5b89753aa5c 100644
--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
@@ -252,6 +252,8 @@
 			clocks = <&gcc GCC_MDIO_AHB_CLK>;
 			clock-names = "gcc_mdio_ahb_clk";
 
+			clock-frequency = <6250000>;
+
 			status = "disabled";
 		};
 
@@ -627,6 +629,13 @@
 						<133330000>,
 						<19200000>;
 
+			interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "ss_phy_irq";
+
 			power-domains = <&gcc USB0_GDSC>;
 
 			resets = <&gcc GCC_USB0_BCR>;
@@ -669,6 +678,13 @@
 						<133330000>,
 						<19200000>;
 
+			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "ss_phy_irq";
+
 			power-domains = <&gcc USB1_GDSC>;
 
 			resets = <&gcc GCC_USB1_BCR>;
@@ -814,13 +830,13 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 142
+			interrupt-map = <0 0 0 1 &intc 0 0 142
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 143
+					<0 0 0 2 &intc 0 0 143
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 144
+					<0 0 0 3 &intc 0 0 144
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 145
+					<0 0 0 4 &intc 0 0 145
 					 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE1_AXI_CLK>,
@@ -876,13 +892,13 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 75
+			interrupt-map = <0 0 0 1 &intc 0 0 75
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 78
+					<0 0 0 2 &intc 0 0 78
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 79
+					<0 0 0 3 &intc 0 0 79
 					 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 83
+					<0 0 0 4 &intc 0 0 83
 					 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_SYS_NOC_PCIE0_AXI_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/ipq9574.dtsi b/arch/arm64/boot/dts/qcom/ipq9574.dtsi
index 5f83ee42a719..7f2e5cbf3bbb 100644
--- a/arch/arm64/boot/dts/qcom/ipq9574.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq9574.dtsi
@@ -321,8 +321,10 @@
 
 		sdhc_1: mmc@7804000 {
 			compatible = "qcom,ipq9574-sdhci", "qcom,sdhci-msm-v5";
-			reg = <0x07804000 0x1000>, <0x07805000 0x1000>;
-			reg-names = "hc", "cqhci";
+			reg = <0x07804000 0x1000>,
+			      <0x07805000 0x1000>,
+			      <0x07808000 0x2000>;
+			reg-names = "hc", "cqhci", "ice";
 
 			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
@@ -330,9 +332,11 @@
 
 			clocks = <&gcc GCC_SDCC1_AHB_CLK>,
 				 <&gcc GCC_SDCC1_APPS_CLK>,
-				 <&xo_board_clk>;
-			clock-names = "iface", "core", "xo";
+				 <&xo_board_clk>,
+				 <&gcc GCC_SDCC1_ICE_CORE_CLK>;
+			clock-names = "iface", "core", "xo", "ice";
 			non-removable;
+			supports-cqe;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/msm8216-samsung-fortuna3g.dts b/arch/arm64/boot/dts/qcom/msm8216-samsung-fortuna3g.dts
new file mode 100644
index 000000000000..366914be7d53
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8216-samsung-fortuna3g.dts
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/dts-v1/;
+
+#include "msm8916-samsung-fortuna-common.dtsi"
+
+/ {
+	model = "Samsung Galaxy Grand Prime (SM-G530H)";
+	compatible = "samsung,fortuna3g", "qcom,msm8916";
+	chassis-type = "handset";
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-fortuna-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-fortuna-common.dtsi
new file mode 100644
index 000000000000..c2800ad2dd5b
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-fortuna-common.dtsi
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "msm8916-pm8916.dtsi"
+#include "msm8916-modem-qdsp6.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	aliases {
+		mmc0 = &sdhc_1; /* eMMC */
+		mmc1 = &sdhc_2; /* SD card */
+		serial0 = &blsp_uart2;
+	};
+
+	chosen {
+		stdout-path = "serial0";
+	};
+
+	reserved-memory {
+		/* Additional memory used by Samsung firmware modifications */
+		tz-apps@85a00000 {
+			reg = <0x0 0x85a00000 0x0 0x600000>;
+			no-map;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&gpio_keys_default>;
+		pinctrl-names = "default";
+
+		label = "GPIO Buttons";
+
+		button-volume-up {
+			label = "Volume Up";
+			gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_VOLUMEUP>;
+		};
+
+		button-home {
+			label = "Home";
+			gpios = <&tlmm 109 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_HOMEPAGE>;
+		};
+	};
+
+	haptic {
+		compatible = "regulator-haptic";
+		haptic-supply = <&reg_motor_vdd>;
+		min-microvolt = <3300000>;
+		max-microvolt = <3300000>;
+	};
+
+	reg_motor_vdd: regulator-motor-vdd {
+		compatible = "regulator-fixed";
+		regulator-name = "motor_vdd";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpio = <&tlmm 72 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-0 = <&motor_en_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_i2c1 {
+	status = "okay";
+
+	muic: extcon@25 {
+		compatible = "siliconmitus,sm5502-muic";
+		reg = <0x25>;
+		interrupts-extended = <&tlmm 12 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-0 = <&muic_int_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_i2c4 {
+	status = "okay";
+
+	fuel-gauge@35 {
+		compatible = "richtek,rt5033-battery";
+		reg = <0x35>;
+
+		interrupts-extended = <&tlmm 121 IRQ_TYPE_EDGE_FALLING>;
+
+		pinctrl-0 = <&fg_alert_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&blsp_uart2 {
+	status = "okay";
+};
+
+&mpss_mem {
+	reg = <0x0 0x86800000 0x0 0x5000000>;
+};
+
+&pm8916_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+	status = "okay";
+};
+
+&pm8916_rpm_regulators {
+	pm8916_l17: l17 {
+		regulator-min-microvolt = <2850000>;
+		regulator-max-microvolt = <2850000>;
+	};
+};
+
+&sdhc_1 {
+	status = "okay";
+};
+
+&sdhc_2 {
+	pinctrl-0 = <&sdc2_default &sdc2_cd_default>;
+	pinctrl-1 = <&sdc2_sleep &sdc2_cd_default>;
+	pinctrl-names = "default", "sleep";
+
+	cd-gpios = <&tlmm 38 GPIO_ACTIVE_LOW>;
+
+	status = "okay";
+};
+
+&sound {
+	model = "msm8916-1mic";
+	audio-routing =
+		"AMIC1", "MIC BIAS External1",
+		"AMIC2", "MIC BIAS Internal2",
+		"AMIC3", "MIC BIAS External1";
+};
+
+&usb {
+	extcon = <&muic>, <&muic>;
+	status = "okay";
+};
+
+&usb_hs_phy {
+	extcon = <&muic>;
+};
+
+&venus {
+	status = "okay";
+};
+
+&venus_mem {
+	status = "okay";
+};
+
+&wcnss {
+	status = "okay";
+};
+
+&wcnss_iris {
+	compatible = "qcom,wcn3620";
+};
+
+&wcnss_mem {
+	status = "okay";
+};
+
+&tlmm {
+	fg_alert_default: fg-alert-default-state {
+		pins = "gpio121";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	gpio_keys_default: gpio-keys-default-state {
+		pins = "gpio107", "gpio109";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-pull-up;
+	};
+
+	motor_en_default: motor-en-default-state {
+		pins = "gpio72";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	muic_int_default: muic-int-default-state {
+		pins = "gpio12";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+
+	sdc2_cd_default: sdc2-cd-default-state {
+		pins = "gpio38";
+		function = "gpio";
+		drive-strength = <2>;
+		bias-disable;
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-gprimeltecan.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-gprimeltecan.dts
new file mode 100644
index 000000000000..9d65fa58ba92
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-gprimeltecan.dts
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/dts-v1/;
+
+#include "msm8916-samsung-fortuna-common.dtsi"
+
+/ {
+	model = "Samsung Galaxy Grand Prime (SM-G530W)";
+	compatible = "samsung,gprimeltecan", "qcom,msm8916";
+	chassis-type = "handset";
+
+	reserved-memory {
+		/* Firmware for gprimeltecan needs more space */
+		/delete-node/ tz-apps@85a00000;
+
+		/* Additional memory used by Samsung firmware modifications */
+		tz-apps@85500000 {
+			reg = <0x0 0x85500000 0x0 0xb00000>;
+			no-map;
+		};
+	};
+};
+
+&mpss_mem {
+	/* Firmware for gprimeltecan needs more space */
+	reg = <0x0 0x86800000 0x0 0x5400000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-grandprimelte.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-grandprimelte.dts
new file mode 100644
index 000000000000..a66ce4b13547
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-grandprimelte.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/dts-v1/;
+
+#include "msm8916-samsung-fortuna-common.dtsi"
+
+/ {
+	model = "Samsung Galaxy Grand Prime (SM-G530FZ)";
+	compatible = "samsung,grandprimelte", "qcom,msm8916";
+	chassis-type = "handset";
+};
+
+&mpss_mem {
+	/* Firmware for grandprimelte needs more space */
+	reg = <0x0 0x86800000 0x0 0x5400000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa-common.dtsi b/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa-common.dtsi
new file mode 100644
index 000000000000..42843771ae2a
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa-common.dtsi
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "msm8916-samsung-fortuna-common.dtsi"
+
+/* SM5504 MUIC instead of SM5502 */
+/delete-node/ &muic;
+
+&blsp_i2c1 {
+	muic: extcon@14 {
+		compatible = "siliconmitus,sm5504-muic";
+		reg = <0x14>;
+		interrupts-extended = <&tlmm 12 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-0 = <&muic_int_default>;
+		pinctrl-names = "default";
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa.dts b/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa.dts
new file mode 100644
index 000000000000..ebaa13c6b016
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/msm8916-samsung-rossa.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/dts-v1/;
+
+#include "msm8916-samsung-rossa-common.dtsi"
+
+/ {
+	model = "Samsung Galaxy Core Prime LTE";
+	compatible = "samsung,rossa", "qcom,msm8916";
+	chassis-type = "handset";
+};
+
+&mpss_mem {
+	/* Firmware for rossa needs more space */
+	reg = <0x0 0x86800000 0x0 0x5800000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi
index e423c57ddd41..cedff4166bfb 100644
--- a/arch/arm64/boot/dts/qcom/msm8916.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi
@@ -1785,6 +1785,8 @@
 			power-domains = <&gcc OXILI_GDSC>;
 			operating-points-v2 = <&gpu_opp_table>;
 			iommus = <&gpu_iommu 1>, <&gpu_iommu 2>;
+			#cooling-cells = <2>;
+
 			status = "disabled";
 
 			gpu_opp_table: opp-table {
@@ -2688,6 +2690,13 @@
 
 			thermal-sensors = <&tsens 2>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				gpu_alert0: trip-point0 {
 					temperature = <75000>;
diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi
index 82d85ff61045..dd45975682b2 100644
--- a/arch/arm64/boot/dts/qcom/msm8939.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi
@@ -1427,6 +1427,8 @@
 			power-domains = <&gcc OXILI_GDSC>;
 			operating-points-v2 = <&opp_table>;
 			iommus = <&gpu_iommu 1>, <&gpu_iommu 2>;
+			#cooling-cells = <2>;
+
 			status = "disabled";
 
 			opp_table: opp-table {
@@ -2456,6 +2458,13 @@
 
 			thermal-sensors = <&tsens 3>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				gpu_alert0: trip-point0 {
 					temperature = <75000>;
@@ -2463,7 +2472,7 @@
 					type = "passive";
 				};
 
-				gpu_crit: gpu_crit {
+				gpu_crit: gpu-crit {
 					temperature = <95000>;
 					hysteresis = <2000>;
 					type = "critical";
diff --git a/arch/arm64/boot/dts/qcom/msm8953.dtsi b/arch/arm64/boot/dts/qcom/msm8953.dtsi
index ad2f8cf9c966..f1011bb641c6 100644
--- a/arch/arm64/boot/dts/qcom/msm8953.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8953.dtsi
@@ -859,6 +859,8 @@
 				      "vsync",
 				      "core";
 
+			resets = <&gcc GCC_MDSS_BCR>;
+
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -1044,6 +1046,125 @@
 			};
 		};
 
+		gpu: gpu@1c00000 {
+			compatible = "qcom,adreno-506.0", "qcom,adreno";
+			reg = <0x01c00000 0x40000>;
+			reg-names = "kgsl_3d0_reg_memory";
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&gcc GCC_OXILI_GFX3D_CLK>,
+				 <&gcc GCC_OXILI_AHB_CLK>,
+				 <&gcc GCC_BIMC_GFX_CLK>,
+				 <&gcc GCC_BIMC_GPU_CLK>,
+				 <&gcc GCC_OXILI_TIMER_CLK>,
+				 <&gcc GCC_OXILI_AON_CLK>;
+			clock-names = "core",
+				      "iface",
+				      "mem_iface",
+				      "alt_mem_iface",
+				      "rbbmtimer",
+				      "alwayson";
+			power-domains = <&gcc OXILI_GX_GDSC>;
+
+			iommus = <&gpu_iommu 0>;
+			operating-points-v2 = <&gpu_opp_table>;
+
+			#cooling-cells = <2>;
+
+			status = "disabled";
+
+			zap-shader {
+				memory-region = <&zap_shader_region>;
+			};
+
+			gpu_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-19200000 {
+					opp-hz = /bits/ 64 <19200000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_min_svs>;
+				};
+
+				opp-133300000 {
+					opp-hz = /bits/ 64 <133300000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_min_svs>;
+				};
+
+				opp-216000000 {
+					opp-hz = /bits/ 64 <216000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_low_svs>;
+				};
+
+				opp-320000000 {
+					opp-hz = /bits/ 64 <320000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_svs>;
+				};
+
+				opp-400000000 {
+					opp-hz = /bits/ 64 <400000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_svs_plus>;
+				};
+
+				opp-510000000 {
+					opp-hz = /bits/ 64 <510000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_nom>;
+				};
+
+				opp-560000000 {
+					opp-hz = /bits/ 64 <560000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_nom_plus>;
+				};
+
+				/*
+				 * This opp is only available on msm8953 and
+				 * sdm632, the max for sdm450 is 600MHz.
+				 */
+				opp-650000000 {
+					opp-hz = /bits/ 64 <650000000>;
+					opp-supported-hw = <0xff>;
+					required-opps = <&rpmpd_opp_turbo>;
+				};
+			};
+		};
+
+		gpu_iommu: iommu@1c48000 {
+			compatible = "qcom,msm8953-iommu", "qcom,msm-iommu-v2";
+			ranges = <0 0x01c48000 0x8000>;
+
+			clocks = <&gcc GCC_OXILI_AHB_CLK>,
+				 <&gcc GCC_BIMC_GFX_CLK>;
+			clock-names = "iface", "bus";
+
+			power-domains = <&gcc OXILI_CX_GDSC>;
+
+			qcom,iommu-secure-id = <18>;
+
+			#address-cells = <1>;
+			#iommu-cells = <1>;
+			#size-cells = <1>;
+
+			/* gfx3d_user */
+			iommu-ctx@0 {
+				compatible = "qcom,msm-iommu-v2-ns";
+				reg = <0x0000 0x1000>;
+				interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+			};
+
+			/* gfx3d_secure */
+			iommu-ctx@2000 {
+				compatible = "qcom,msm-iommu-v2-sec";
+				reg = <0x2000 0x1000>;
+				interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>;
+			};
+		};
+
 		apps_iommu: iommu@1e20000 {
 			compatible = "qcom,msm8953-iommu", "qcom,msm-iommu-v1";
 			ranges = <0 0x01e20000 0x20000>;
@@ -1160,9 +1281,12 @@
 			#size-cells = <1>;
 			ranges;
 
-			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "ss_phy_irq";
 
 			clocks = <&gcc GCC_USB_PHY_CFG_AHB_CLK>,
 				 <&gcc GCC_USB30_MASTER_CLK>,
@@ -2012,6 +2136,33 @@
 				};
 			};
 		};
+
+		gpu-thermal {
+			polling-delay-passive = <250>;
+			polling-delay = <1000>;
+			thermal-sensors = <&tsens0 15>;
+
+			trips {
+				gpu_alert: trip-point0 {
+					temperature = <70000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				gpu_crit: crit {
+					temperature = <90000>;
+					hysteresis = <2000>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi
index cbc84459a5ae..10cd244dea4f 100644
--- a/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8994-msft-lumia-octagon.dtsi
@@ -377,7 +377,7 @@
 &blsp2_i2c1 {
 	status = "okay";
 
-	sideinteraction: ad7147_captouch@2c {
+	sideinteraction: touch@2c {
 		compatible = "ad,ad7147_captouch";
 		reg = <0x2c>;
 
diff --git a/arch/arm64/boot/dts/qcom/msm8994-sony-xperia-kitakami.dtsi b/arch/arm64/boot/dts/qcom/msm8994-sony-xperia-kitakami.dtsi
index 9dbde79f26a2..0163d41f95f8 100644
--- a/arch/arm64/boot/dts/qcom/msm8994-sony-xperia-kitakami.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8994-sony-xperia-kitakami.dtsi
@@ -79,7 +79,7 @@
 			pmsg-size = <0x80000>;
 		};
 
-		fb_region: fb_region@40000000 {
+		fb_region: fb@40000000 {
 			reg = <0 0x40000000 0 0x1000000>;
 			no-map;
 		};
diff --git a/arch/arm64/boot/dts/qcom/msm8994.dtsi b/arch/arm64/boot/dts/qcom/msm8994.dtsi
index 8295bf1b219d..695e541832ad 100644
--- a/arch/arm64/boot/dts/qcom/msm8994.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8994.dtsi
@@ -233,7 +233,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		dfps_data_mem: dfps_data_mem@3400000 {
+		dfps_data_mem: dfps-data@3400000 {
 			reg = <0 0x03400000 0 0x1000>;
 			no-map;
 		};
@@ -243,7 +243,7 @@
 			no-map;
 		};
 
-		smem_mem: smem_region@6a00000 {
+		smem_mem: smem@6a00000 {
 			reg = <0 0x06a00000 0 0x200000>;
 			no-map;
 		};
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 8d41ed261adf..1601e46549e7 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -457,25 +457,6 @@
 		};
 	};
 
-	mpm: interrupt-controller {
-		compatible = "qcom,mpm";
-		qcom,rpm-msg-ram = <&apss_mpm>;
-		interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>;
-		mboxes = <&apcs_glb 1>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-		#power-domain-cells = <0>;
-		interrupt-parent = <&intc>;
-		qcom,mpm-pin-count = <96>;
-		qcom,mpm-pin-map = <2 184>,  /* TSENS1 upper_lower_int */
-				   <52 243>, /* DWC3_PRI ss_phy_irq */
-				   <79 347>, /* DWC3_PRI hs_phy_irq */
-				   <80 352>, /* DWC3_SEC hs_phy_irq */
-				   <81 347>, /* QUSB2_PHY_PRI DP+DM */
-				   <82 352>, /* QUSB2_PHY_SEC DP+DM */
-				   <87 326>; /* SPMI */
-	};
-
 	psci {
 		compatible = "arm,psci-1.0";
 		method = "smc";
@@ -765,15 +746,8 @@
 		};
 
 		rpm_msg_ram: sram@68000 {
-			compatible = "qcom,rpm-msg-ram", "mmio-sram";
+			compatible = "qcom,rpm-msg-ram";
 			reg = <0x00068000 0x6000>;
-			#address-cells = <1>;
-			#size-cells = <1>;
-			ranges = <0 0x00068000 0x7000>;
-
-			apss_mpm: sram@1b8 {
-				reg = <0x1b8 0x48>;
-			};
 		};
 
 		qfprom@74000 {
@@ -782,12 +756,12 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			qusb2p_hstx_trim: hstx_trim@24e {
+			qusb2p_hstx_trim: hstx-trim@24e {
 				reg = <0x24e 0x2>;
 				bits = <5 4>;
 			};
 
-			qusb2s_hstx_trim: hstx_trim@24f {
+			qusb2s_hstx_trim: hstx-trim@24f {
 				reg = <0x24f 0x1>;
 				bits = <1 4>;
 			};
@@ -856,8 +830,8 @@
 			reg = <0x004ad000 0x1000>, /* TM */
 			      <0x004ac000 0x1000>; /* SROT */
 			#qcom,sensors = <8>;
-			interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>,
-					      <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "uplow", "critical";
 			#thermal-sensor-cells = <1>;
 		};
@@ -1363,7 +1337,6 @@
 			interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 			gpio-controller;
 			gpio-ranges = <&tlmm 0 0 150>;
-			wakeup-parent = <&mpm>;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -1891,7 +1864,7 @@
 			      <0x0400a000 0x002100>;
 			reg-names = "core", "chnls", "obsrvr", "intr", "cnfg";
 			interrupt-names = "periph_irq";
-			interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>;
 			qcom,ee = <0>;
 			qcom,channel = <0>;
 			#address-cells = <2>;
@@ -2104,7 +2077,7 @@
 				<0 0>,
 				<0 0>,
 				<150000000 300000000>,
-				<0 0>,
+				<75000000 150000000>,
 				<0 0>,
 				<0 0>,
 				<0 0>,
@@ -2123,8 +2096,8 @@
 			compatible = "qcom,msm8996-qmp-ufs-phy";
 			reg = <0x00627000 0x1000>;
 
-			clocks = <&gcc GCC_UFS_CLKREF_CLK>;
-			clock-names = "ref";
+			clocks = <&rpmcc RPM_SMD_LN_BB_CLK>, <&gcc GCC_UFS_CLKREF_CLK>;
+			clock-names = "ref", "qref";
 
 			resets = <&ufshc 0>;
 			reset-names = "ufsphy";
@@ -3052,8 +3025,8 @@
 			#size-cells = <1>;
 			ranges;
 
-			interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>,
-					      <&mpm 52 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "hs_phy_irq", "ss_phy_irq";
 
 			clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>,
@@ -3408,8 +3381,12 @@
 			#size-cells = <1>;
 			ranges;
 
-			interrupts = <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq";
+			interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "hs_phy_irq";
 
 			clocks = <&gcc GCC_PERIPH_NOC_USB20_AHB_CLK>,
 				<&gcc GCC_USB20_MASTER_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index 2793cc22d381..4dfe2d09ac28 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -1047,12 +1047,12 @@
 			compatible = "qcom,msm8998-qmp-ufs-phy";
 			reg = <0x01da7000 0x1000>;
 
-			clock-names =
-				"ref",
-				"ref_aux";
-			clocks =
-				<&gcc GCC_UFS_CLKREF_CLK>,
-				<&gcc GCC_UFS_PHY_AUX_CLK>;
+			clocks = <&rpmcc RPM_SMD_LN_BB_CLK1>,
+				 <&gcc GCC_UFS_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_CLKREF_CLK>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			reset-names = "ufsphy";
 			resets = <&ufshc 0>;
@@ -1072,6 +1072,11 @@
 			reg = <0x01f60000 0x20000>;
 		};
 
+		tcsr_regs_2: syscon@1fc0000 {
+			compatible = "qcom,msm8998-tcsr", "syscon";
+			reg = <0x01fc0000 0x26000>;
+		};
+
 		tlmm: pinctrl@3400000 {
 			compatible = "qcom,msm8998-pinctrl";
 			reg = <0x03400000 0xc00000>;
@@ -2132,9 +2137,12 @@
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <120000000>;
 
-			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB_30_GDSC>;
 
@@ -2174,6 +2182,8 @@
 			reset-names = "phy",
 				      "phy_phy";
 
+			qcom,tcsr-reg = <&tcsr_regs_2 0xb244>;
+
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/pm2250.dtsi b/arch/arm64/boot/dts/qcom/pm4125.dtsi
index 5f1d15db5c99..cf8c822e80ce 100644
--- a/arch/arm64/boot/dts/qcom/pm2250.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm4125.dtsi
@@ -19,7 +19,7 @@
 			compatible = "qcom,pm8916-pon";
 			reg = <0x800>;
 
-			pm2250_pwrkey: pwrkey {
+			pm4125_pwrkey: pwrkey {
 				compatible = "qcom,pm8941-pwrkey";
 				interrupts-extended = <&spmi_bus 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
 				linux,code = <KEY_POWER>;
@@ -27,7 +27,7 @@
 				bias-pull-up;
 			};
 
-			pm2250_resin: resin {
+			pm4125_resin: resin {
 				compatible = "qcom,pm8941-resin";
 				interrupts-extended = <&spmi_bus 0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>;
 				debounce = <15625>;
@@ -36,6 +36,36 @@
 			};
 		};
 
+		pm4125_vbus: usb-vbus-regulator@1100 {
+			compatible = "qcom,pm4125-vbus-reg", "qcom,pm8150b-vbus-reg";
+			reg = <0x1100>;
+			status = "disabled";
+		};
+
+		pm4125_typec: typec@1500 {
+			compatible = "qcom,pm4125-typec", "qcom,pmi632-typec";
+			reg = <0x1500>;
+			interrupts = <0x0 0x15 0x00 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x15 0x01 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x15 0x02 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x15 0x03 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x15 0x04 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x15 0x05 IRQ_TYPE_EDGE_RISING>,
+				     <0x0 0x15 0x06 IRQ_TYPE_EDGE_BOTH>,
+				     <0x0 0x15 0x07 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "or-rid-detect-change",
+					  "vpd-detect",
+					  "cc-state-change",
+					  "vconn-oc",
+					  "vbus-change",
+					  "attach-detach",
+					  "legacy-cable-detect",
+					  "try-snk-src-detect";
+			vdd-vbus-supply = <&pm4125_vbus>;
+
+			status = "disabled";
+		};
+
 		rtc@6000 {
 			compatible = "qcom,pm8941-rtc";
 			reg = <0x6000>, <0x6100>;
@@ -43,11 +73,11 @@
 			interrupts-extended = <&spmi_bus 0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>;
 		};
 
-		pm2250_gpios: gpio@c000 {
+		pm4125_gpios: gpio@c000 {
 			compatible = "qcom,pm2250-gpio", "qcom,spmi-gpio";
 			reg = <0xc000>;
 			gpio-controller;
-			gpio-ranges = <&pm2250_gpios 0 0 10>;
+			gpio-ranges = <&pm4125_gpios 0 0 10>;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm64/boot/dts/qcom/pmi632.dtsi b/arch/arm64/boot/dts/qcom/pmi632.dtsi
index 4eb79e0ce40a..94d53b1cf6c8 100644
--- a/arch/arm64/boot/dts/qcom/pmi632.dtsi
+++ b/arch/arm64/boot/dts/qcom/pmi632.dtsi
@@ -45,6 +45,36 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
+		pmi632_vbus: usb-vbus-regulator@1100 {
+			compatible = "qcom,pmi632-vbus-reg", "qcom,pm8150b-vbus-reg";
+			reg = <0x1100>;
+			status = "disabled";
+		};
+
+		pmi632_typec: typec@1500 {
+			compatible = "qcom,pmi632-typec";
+			reg = <0x1500>;
+			interrupts = <0x2 0x15 0x00 IRQ_TYPE_EDGE_RISING>,
+				     <0x2 0x15 0x01 IRQ_TYPE_EDGE_BOTH>,
+				     <0x2 0x15 0x02 IRQ_TYPE_EDGE_RISING>,
+				     <0x2 0x15 0x03 IRQ_TYPE_EDGE_BOTH>,
+				     <0x2 0x15 0x04 IRQ_TYPE_EDGE_RISING>,
+				     <0x2 0x15 0x05 IRQ_TYPE_EDGE_RISING>,
+				     <0x2 0x15 0x06 IRQ_TYPE_EDGE_BOTH>,
+				     <0x2 0x15 0x07 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "or-rid-detect-change",
+					  "vpd-detect",
+					  "cc-state-change",
+					  "vconn-oc",
+					  "vbus-change",
+					  "attach-detach",
+					  "legacy-cable-detect",
+					  "try-snk-src-detect";
+			vdd-vbus-supply = <&pmi632_vbus>;
+
+			status = "disabled";
+		};
+
 		pmi632_temp: temp-alarm@2400 {
 			compatible = "qcom,spmi-temp-alarm";
 			reg = <0x2400>;
@@ -127,6 +157,11 @@
 			status = "disabled";
 		};
 
+		pmi632_pbs_client3: pbs@7400 {
+			compatible = "qcom,pmi632-pbs", "qcom,pbs";
+			reg = <0x7400>;
+		};
+
 		pmi632_sdam_7: nvram@b600 {
 			compatible = "qcom,spmi-sdam";
 			reg = <0xb600>;
@@ -155,6 +190,10 @@
 		pmi632_lpg: pwm {
 			compatible = "qcom,pmi632-lpg";
 
+			nvmem = <&pmi632_sdam_7>;
+			nvmem-names = "lpg_chan_sdam";
+			qcom,pbs = <&pmi632_pbs_client3>;
+
 			#address-cells = <1>;
 			#size-cells = <0>;
 			#pwm-cells = <2>;
diff --git a/arch/arm64/boot/dts/qcom/qcm2290.dtsi b/arch/arm64/boot/dts/qcom/qcm2290.dtsi
index 0911fb08ed63..89beac833d43 100644
--- a/arch/arm64/boot/dts/qcom/qcm2290.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcm2290.dtsi
@@ -442,6 +442,11 @@
 			#hwlock-cells = <1>;
 		};
 
+		tcsr_regs: syscon@3c0000 {
+			compatible = "qcom,qcm2290-tcsr", "syscon";
+			reg = <0x0 0x003c0000 0x0 0x40000>;
+		};
+
 		tlmm: pinctrl@500000 {
 			compatible = "qcom,qcm2290-tlmm";
 			reg = <0x0 0x00500000 0x0 0x300000>;
@@ -690,6 +695,8 @@
 
 			#phy-cells = <0>;
 
+			qcom,tcsr-reg = <&tcsr_regs 0xb244>;
+
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
index 176898c9dbbd..4ff9fc24e50e 100644
--- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
+++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
@@ -71,6 +71,41 @@
 		};
 	};
 
+	pmic-glink {
+		compatible = "qcom,qcm6490-pmic-glink", "qcom,pmic-glink";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		connector@0 {
+			compatible = "usb-c-connector";
+			reg = <0>;
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					pmic_glink_hs_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					pmic_glink_ss_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_ss>;
+					};
+				};
+			};
+		};
+	};
+
 	reserved-memory {
 		cont_splash_mem: cont-splash@e1000000 {
 			reg = <0x0 0xe1000000 0x0 0x2300000>;
@@ -82,6 +117,11 @@
 			no-map;
 		};
 
+		removed_mem: removed@c0000000 {
+			reg = <0x0 0xc0000000 0x0 0x5100000>;
+			no-map;
+		};
+
 		rmtfs_mem: memory@f8500000 {
 			compatible = "qcom,rmtfs-mem";
 			reg = <0x0 0xf8500000 0x0 0x600000>;
@@ -886,7 +926,16 @@
 };
 
 &usb_1_dwc3 {
-	dr_mode = "peripheral";
+	dr_mode = "otg";
+	usb-role-switch;
+};
+
+&usb_1_dwc3_hs {
+	remote-endpoint = <&pmic_glink_hs_in>;
+};
+
+&usb_1_dwc3_ss {
+	remote-endpoint = <&pmic_glink_ss_in>;
 };
 
 &usb_1_hsphy {
@@ -915,6 +964,11 @@
 	status = "okay";
 };
 
+&venus {
+	firmware-name = "qcom/qcm6490/fairphone5/venus.mbn";
+	status = "okay";
+};
+
 &wifi {
 	qcom,ath11k-calibration-variant = "Fairphone_5";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
index 03e97e27d16d..e4bfad50a669 100644
--- a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
+++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
@@ -5,8 +5,14 @@
 
 /dts-v1/;
 
+/* PM7250B is configured to use SID8/9 */
+#define PM7250B_SID 8
+#define PM7250B_SID1 9
+
+#include <dt-bindings/leds/common.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 #include "sc7280.dtsi"
+#include "pm7250b.dtsi"
 #include "pm7325.dtsi"
 #include "pm8350c.dtsi"
 #include "pmk8350.dtsi"
@@ -109,7 +115,7 @@
 			no-map;
 		};
 
-		trusted_apps_mem: trusted_apps@c1800000 {
+		trusted_apps_mem: trusted-apps@c1800000 {
 			reg = <0x0 0xc1800000 0x0 0x1c00000>;
 			no-map;
 		};
@@ -123,8 +129,8 @@
 	vph_pwr: vph-pwr-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vph_pwr";
-		regulator-min-microvolt = <2500000>;
-		regulator-max-microvolt = <4350000>;
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
 	};
 };
 
@@ -415,6 +421,33 @@
 	};
 };
 
+&pm8350c_pwm {
+	status = "okay";
+
+	multi-led {
+		color = <LED_COLOR_ID_RGB>;
+		function = LED_FUNCTION_STATUS;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		led@1 {
+			reg = <1>;
+			color = <LED_COLOR_ID_RED>;
+		};
+
+		led@2 {
+			reg = <2>;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+
+		led@3 {
+			reg = <3>;
+			color = <LED_COLOR_ID_BLUE>;
+		};
+	};
+};
+
 &qupv3_id_0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index 2f2eeaf2e945..a05d0234f7fc 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -675,6 +675,14 @@
 			assigned-clocks = <&gcc GCC_USB20_MOCK_UTMI_CLK>,
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
+
+			interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 319 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "qusb2_phy";
+
 			status = "disabled";
 
 			usb3_dwc3: usb@7580000 {
@@ -704,6 +712,14 @@
 			assigned-clocks = <&gcc GCC_USB20_MOCK_UTMI_CLK>,
 					  <&gcc GCC_USB_HS_SYSTEM_CLK>;
 			assigned-clock-rates = <19200000>, <133333333>;
+
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 318 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "qusb2_phy";
+
 			status = "disabled";
 
 			usb@78c0000 {
diff --git a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
index 8bb7d13d85f6..97824c769ba3 100644
--- a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
+++ b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
@@ -110,7 +110,7 @@
 			no-map;
 		};
 
-		trusted_apps_mem: trusted_apps@c1800000 {
+		trusted_apps_mem: trusted-apps@c1800000 {
 			reg = <0x0 0xc1800000 0x0 0x1c00000>;
 			no-map;
 		};
@@ -124,8 +124,8 @@
 	vph_pwr: vph-pwr-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vph_pwr";
-		regulator-min-microvolt = <2500000>;
-		regulator-max-microvolt = <4350000>;
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
 	};
 };
 
@@ -413,6 +413,23 @@
 	};
 };
 
+&gcc {
+	protected-clocks = <GCC_CFG_NOC_LPASS_CLK>,
+			   <GCC_MSS_CFG_AHB_CLK>,
+			   <GCC_MSS_GPLL0_MAIN_DIV_CLK_SRC>,
+			   <GCC_MSS_OFFLINE_AXI_CLK>,
+			   <GCC_MSS_Q6SS_BOOT_CLK_SRC>,
+			   <GCC_MSS_Q6_MEMNOC_AXI_CLK>,
+			   <GCC_MSS_SNOC_AXI_CLK>,
+			   <GCC_QSPI_CNOC_PERIPH_AHB_CLK>,
+			   <GCC_QSPI_CORE_CLK>,
+			   <GCC_QSPI_CORE_CLK_SRC>,
+			   <GCC_SEC_CTRL_CLK_SRC>,
+			   <GCC_WPSS_AHB_BDG_MST_CLK>,
+			   <GCC_WPSS_AHB_CLK>,
+			   <GCC_WPSS_RSCP_CLK>;
+};
+
 &qupv3_id_0 {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
index aa53b6af6d9c..6e9dd0312adc 100644
--- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
+++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
@@ -7,7 +7,7 @@
 
 #include <dt-bindings/leds/common.h>
 #include "qcm2290.dtsi"
-#include "pm2250.dtsi"
+#include "pm4125.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. Robotics RB1";
@@ -177,6 +177,24 @@
 	};
 };
 
+&CPU_PD0 {
+	/delete-property/ power-domains;
+};
+
+&CPU_PD1 {
+	/delete-property/ power-domains;
+};
+
+&CPU_PD2 {
+	/delete-property/ power-domains;
+};
+
+&CPU_PD3 {
+	/delete-property/ power-domains;
+};
+
+/delete-node/ &CLUSTER_PD;
+
 &gpi_dma0 {
 	status = "okay";
 };
@@ -226,7 +244,7 @@
 };
 
 &mdss_dsi0 {
-	vdda-supply = <&pm2250_l5>;
+	vdda-supply = <&pm4125_l5>;
 	status = "okay";
 };
 
@@ -239,7 +257,7 @@
 	status = "okay";
 };
 
-&pm2250_resin {
+&pm4125_resin {
 	linux,code = <KEY_VOLUMEDOWN>;
 	status = "okay";
 };
@@ -263,23 +281,23 @@
 		compatible = "qcom,rpm-pm2250-regulators";
 		vdd_s3-supply = <&vph_pwr>;
 		vdd_s4-supply = <&vph_pwr>;
-		vdd_l1_l2_l3_l5_l6_l7_l8_l9_l10_l11_l12-supply = <&pm2250_s3>;
+		vdd_l1_l2_l3_l5_l6_l7_l8_l9_l10_l11_l12-supply = <&pm4125_s3>;
 		vdd_l4_l17_l18_l19_l20_l21_l22-supply = <&vph_pwr>;
-		vdd_l13_l14_l15_l16-supply = <&pm2250_s4>;
+		vdd_l13_l14_l15_l16-supply = <&pm4125_s4>;
 
 		/*
 		 * S1 - VDD_APC
 		 * S2 - VDD_CX
 		 */
 
-		pm2250_s3: s3 {
+		pm4125_s3: s3 {
 			/* 0.4V-1.6625V -> 1.3V (Power tree requirements) */
 			regulator-min-microvolt = <1352000>;
 			regulator-max-microvolt = <1352000>;
 			regulator-boot-on;
 		};
 
-		pm2250_s4: s4 {
+		pm4125_s4: s4 {
 			/* 1.2V-2.35V -> 2.05V (Power tree requirements) */
 			regulator-min-microvolt = <2072000>;
 			regulator-max-microvolt = <2072000>;
@@ -288,7 +306,7 @@
 
 		/* L1 - VDD_MX */
 
-		pm2250_l2: l2 {
+		pm4125_l2: l2 {
 			/* LPDDR4X VDD2 */
 			regulator-min-microvolt = <1136000>;
 			regulator-max-microvolt = <1136000>;
@@ -296,7 +314,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l3: l3 {
+		pm4125_l3: l3 {
 			/* LPDDR4X VDDQ */
 			regulator-min-microvolt = <616000>;
 			regulator-max-microvolt = <616000>;
@@ -304,14 +322,14 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l4: l4 {
+		pm4125_l4: l4 {
 			/* max = 3.05V -> max = 2.7 to disable 3V signaling (SDHCI2) */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <2700000>;
 			regulator-allow-set-load;
 		};
 
-		pm2250_l5: l5 {
+		pm4125_l5: l5 {
 			/* CSI/DSI */
 			regulator-min-microvolt = <1232000>;
 			regulator-max-microvolt = <1232000>;
@@ -319,7 +337,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l6: l6 {
+		pm4125_l6: l6 {
 			/* DRAM PLL */
 			regulator-min-microvolt = <928000>;
 			regulator-max-microvolt = <928000>;
@@ -327,7 +345,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l7: l7 {
+		pm4125_l7: l7 {
 			/* Wi-Fi CX/MX */
 			regulator-min-microvolt = <664000>;
 			regulator-max-microvolt = <664000>;
@@ -338,20 +356,20 @@
 		 * L9 - VDD_LPI_MX
 		 */
 
-		pm2250_l10: l10 {
+		pm4125_l10: l10 {
 			/* Wi-Fi RFA */
 			regulator-min-microvolt = <1304000>;
 			regulator-max-microvolt = <1304000>;
 		};
 
-		pm2250_l11: l11 {
+		pm4125_l11: l11 {
 			/* GPS RF1 */
 			regulator-min-microvolt = <1000000>;
 			regulator-max-microvolt = <1000000>;
 			regulator-boot-on;
 		};
 
-		pm2250_l12: l12 {
+		pm4125_l12: l12 {
 			/* USB PHYs */
 			regulator-min-microvolt = <928000>;
 			regulator-max-microvolt = <928000>;
@@ -359,7 +377,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l13: l13 {
+		pm4125_l13: l13 {
 			/* USB/QFPROM/PLLs */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -367,7 +385,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l14: l14 {
+		pm4125_l14: l14 {
 			/* SDHCI1 VQMMC */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -376,7 +394,7 @@
 			regulator-always-on;
 		};
 
-		pm2250_l15: l15 {
+		pm4125_l15: l15 {
 			/* WCD/DSI/BT VDDIO */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -385,38 +403,38 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l16: l16 {
+		pm4125_l16: l16 {
 			/* GPS RF2 */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 			regulator-boot-on;
 		};
 
-		pm2250_l17: l17 {
+		pm4125_l17: l17 {
 			regulator-min-microvolt = <3000000>;
 			regulator-max-microvolt = <3000000>;
 		};
 
-		pm2250_l18: l18 {
+		pm4125_l18: l18 {
 			/* VDD_PXn */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 		};
 
-		pm2250_l19: l19 {
+		pm4125_l19: l19 {
 			/* VDD_PXn */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
 		};
 
-		pm2250_l20: l20 {
+		pm4125_l20: l20 {
 			/* SDHCI1 VMMC */
 			regulator-min-microvolt = <2400000>;
 			regulator-max-microvolt = <3600000>;
 			regulator-allow-set-load;
 		};
 
-		pm2250_l21: l21 {
+		pm4125_l21: l21 {
 			/* SDHCI2 VMMC */
 			regulator-min-microvolt = <2960000>;
 			regulator-max-microvolt = <3300000>;
@@ -424,7 +442,7 @@
 			regulator-boot-on;
 		};
 
-		pm2250_l22: l22 {
+		pm4125_l22: l22 {
 			/* Wi-Fi */
 			regulator-min-microvolt = <3312000>;
 			regulator-max-microvolt = <3312000>;
@@ -433,8 +451,8 @@
 };
 
 &sdhc_1 {
-	vmmc-supply = <&pm2250_l20>;
-	vqmmc-supply = <&pm2250_l14>;
+	vmmc-supply = <&pm4125_l20>;
+	vqmmc-supply = <&pm4125_l14>;
 	pinctrl-0 = <&sdc1_state_on>;
 	pinctrl-1 = <&sdc1_state_off>;
 	pinctrl-names = "default", "sleep";
@@ -446,8 +464,8 @@
 };
 
 &sdhc_2 {
-	vmmc-supply = <&pm2250_l21>;
-	vqmmc-supply = <&pm2250_l4>;
+	vmmc-supply = <&pm4125_l21>;
+	vqmmc-supply = <&pm4125_l4>;
 	cd-gpios = <&tlmm 88 GPIO_ACTIVE_LOW>;
 	pinctrl-0 = <&sdc2_state_on &sd_det_in_on>;
 	pinctrl-1 = <&sdc2_state_off &sd_det_in_off>;
@@ -518,8 +536,8 @@
 };
 
 &usb_qmpphy {
-	vdda-phy-supply = <&pm2250_l12>;
-	vdda-pll-supply = <&pm2250_l13>;
+	vdda-phy-supply = <&pm4125_l12>;
+	vdda-pll-supply = <&pm4125_l13>;
 	status = "okay";
 };
 
@@ -528,17 +546,17 @@
 };
 
 &usb_hsphy {
-	vdd-supply = <&pm2250_l12>;
-	vdda-pll-supply = <&pm2250_l13>;
-	vdda-phy-dpdm-supply = <&pm2250_l21>;
+	vdd-supply = <&pm4125_l12>;
+	vdda-pll-supply = <&pm4125_l13>;
+	vdda-phy-dpdm-supply = <&pm4125_l21>;
 	status = "okay";
 };
 
 &wifi {
-	vdd-0.8-cx-mx-supply = <&pm2250_l7>;
-	vdd-1.8-xo-supply = <&pm2250_l13>;
-	vdd-1.3-rfa-supply = <&pm2250_l10>;
-	vdd-3.3-ch0-supply = <&pm2250_l22>;
+	vdd-0.8-cx-mx-supply = <&pm4125_l7>;
+	vdd-1.8-xo-supply = <&pm4125_l13>;
+	vdd-1.3-rfa-supply = <&pm4125_l10>;
+	vdd-3.3-ch0-supply = <&pm4125_l22>;
 	qcom,ath10k-calibration-variant = "Thundercomm_RB1";
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
index 7c19f874fa71..696d6d43c56b 100644
--- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
@@ -6,8 +6,10 @@
 /dts-v1/;
 
 #include <dt-bindings/leds/common.h>
+#include <dt-bindings/usb/pd.h>
 #include "sm4250.dtsi"
 #include "pm6125.dtsi"
+#include "pmi632.dtsi"
 
 / {
 	model = "Qualcomm Technologies, Inc. QRB4210 RB2";
@@ -256,6 +258,46 @@
 	};
 };
 
+&pmi632_typec {
+	status = "okay";
+
+	connector {
+		compatible = "usb-c-connector";
+
+		power-role = "dual";
+		data-role = "dual";
+		self-powered;
+
+		typec-power-opmode = "default";
+		pd-disable;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				pmi632_hs_in: endpoint {
+					remote-endpoint = <&usb_dwc3_hs>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				pmi632_ss_in: endpoint {
+					remote-endpoint = <&usb_qmpphy_out>;
+				};
+			};
+		};
+	};
+};
+
+&pmi632_vbus {
+	regulator-min-microamp = <500000>;
+	regulator-max-microamp = <3000000>;
+	status = "okay";
+};
+
 &pon_pwrkey {
 	status = "okay";
 };
@@ -607,8 +649,8 @@
 	status = "okay";
 };
 
-&usb_dwc3 {
-	maximum-speed = "super-speed";
+&usb_dwc3_hs {
+	remote-endpoint = <&pmi632_hs_in>;
 };
 
 &usb_hsphy {
@@ -626,6 +668,10 @@
 	status = "okay";
 };
 
+&usb_qmpphy_out {
+	remote-endpoint = <&pmi632_ss_in>;
+};
+
 &wifi {
 	vdd-0.8-cx-mx-supply = <&vreg_l8a_0p664>;
 	vdd-1.8-xo-supply = <&vreg_l16a_1p3>;
diff --git a/arch/arm64/boot/dts/qcom/sa8295p-adp.dts b/arch/arm64/boot/dts/qcom/sa8295p-adp.dts
index fd253942e5e5..78e933c42c31 100644
--- a/arch/arm64/boot/dts/qcom/sa8295p-adp.dts
+++ b/arch/arm64/boot/dts/qcom/sa8295p-adp.dts
@@ -108,6 +108,13 @@
 			};
 		};
 	};
+
+	reserved-memory {
+		gpu_mem: gpu-mem@8bf00000 {
+			reg = <0 0x8bf00000 0 0x2000>;
+			no-map;
+		};
+	};
 };
 
 &apps_rsc {
@@ -266,6 +273,48 @@
 	status = "okay";
 };
 
+&i2c12 {
+	pinctrl-0 = <&qup1_i2c4_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	vdd_gfx: regulator@39 {
+		compatible = "maxim,max20411";
+		reg = <0x39>;
+
+		regulator-min-microvolt = <800000>;
+		regulator-max-microvolt = <800000>;
+
+		enable-gpios = <&pmm8540a_gpios 2 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&max20411_en>;
+		pinctrl-names = "default";
+	};
+};
+
+&gpucc {
+	vdd-gfx-supply = <&vdd_gfx>;
+	status = "okay";
+};
+
+&gmu {
+	status = "okay";
+};
+
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		memory-region = <&gpu_mem>;
+		firmware-name = "qcom/sa8295p/a690_zap.mbn";
+	};
+};
+
+&gpu_smmu {
+	status = "okay";
+};
+
 &mdss0 {
 	status = "okay";
 };
@@ -476,6 +525,10 @@
 	status = "okay";
 };
 
+&qup1 {
+	status = "okay";
+};
+
 &qup2 {
 	status = "okay";
 };
@@ -636,6 +689,14 @@
 
 /* PINCTRL */
 
+&pmm8540a_gpios {
+	max20411_en: max20411-en-state {
+		pins = "gpio2";
+		function = "normal";
+		output-enable;
+	};
+};
+
 &tlmm {
 	pcie2a_default: pcie2a-default-state {
 		clkreq-n-pins {
@@ -728,4 +789,11 @@
 			bias-pull-up;
 		};
 	};
+
+	qup1_i2c4_state: qup1-i2c4-state {
+		pins = "gpio0", "gpio1";
+		function = "qup12";
+		drive-strength = <2>;
+		bias-pull-up;
+	};
 };
diff --git a/arch/arm64/boot/dts/qcom/sa8540p-ride.dts b/arch/arm64/boot/dts/qcom/sa8540p-ride.dts
index b04f72ec097c..177b9dad6ff7 100644
--- a/arch/arm64/boot/dts/qcom/sa8540p-ride.dts
+++ b/arch/arm64/boot/dts/qcom/sa8540p-ride.dts
@@ -376,14 +376,14 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie2a_default>;
 
-	status = "okay";
+	status = "disabled";
 };
 
 &pcie2a_phy {
 	vdda-phy-supply = <&vreg_l11a>;
 	vdda-pll-supply = <&vreg_l3a>;
 
-	status = "okay";
+	status = "disabled";
 };
 
 &pcie3a {
diff --git a/arch/arm64/boot/dts/qcom/sa8540p.dtsi b/arch/arm64/boot/dts/qcom/sa8540p.dtsi
index 96b2c59ad02b..23888029cc11 100644
--- a/arch/arm64/boot/dts/qcom/sa8540p.dtsi
+++ b/arch/arm64/boot/dts/qcom/sa8540p.dtsi
@@ -168,6 +168,9 @@
 };
 
 &gpucc {
+	/* SA8295P and SA8540P doesn't provide gfx.lvl */
+	/delete-property/ power-domains;
+
 	status = "disabled";
 };
 
diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
index a7eaca33d326..231cea1f0fa8 100644
--- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
@@ -356,13 +356,18 @@
 			no-map;
 		};
 
+		ddr_training_checksum: ddr-training-checksum@908c0000 {
+			reg = <0x0 0x908c0000 0x0 0x1000>;
+			no-map;
+		};
+
 		reserved_mem: reserved@908f0000 {
-			reg = <0x0 0x908f0000 0x0 0xf000>;
+			reg = <0x0 0x908f0000 0x0 0xe000>;
 			no-map;
 		};
 
-		secdata_apss_mem: secdata-apss@908ff000 {
-			reg = <0x0 0x908ff000 0x0 0x1000>;
+		secdata_apss_mem: secdata-apss@908fe000 {
+			reg = <0x0 0x908fe000 0x0 0x2000>;
 			no-map;
 		};
 
@@ -373,8 +378,43 @@
 			hwlocks = <&tcsr_mutex 3>;
 		};
 
-		cpucp_fw_mem: cpucp-fw@90b00000 {
-			reg = <0x0 0x90b00000 0x0 0x100000>;
+		tz_sail_mailbox_mem: tz-sail-mailbox@90c00000 {
+			reg = <0x0 0x90c00000 0x0 0x100000>;
+			no-map;
+		};
+
+		sail_mailbox_mem: sail-ss@90d00000 {
+			reg = <0x0 0x90d00000 0x0 0x100000>;
+			no-map;
+		};
+
+		sail_ota_mem: sail-ss@90e00000 {
+			reg = <0x0 0x90e00000 0x0 0x300000>;
+			no-map;
+		};
+
+		aoss_backup_mem: aoss-backup@91b00000 {
+			reg = <0x0 0x91b00000 0x0 0x40000>;
+			no-map;
+		};
+
+		cpucp_backup_mem: cpucp-backup@91b40000 {
+			reg = <0x0 0x91b40000 0x0 0x40000>;
+			no-map;
+		};
+
+		tz_config_backup_mem: tz-config-backup@91b80000 {
+			reg = <0x0 0x91b80000 0x0 0x10000>;
+			no-map;
+		};
+
+		ddr_training_data_mem: ddr-training-data@91b90000 {
+			reg = <0x0 0x91b90000 0x0 0x10000>;
+			no-map;
+		};
+
+		cdt_data_backup_mem: cdt-data-backup@91ba0000 {
+			reg = <0x0 0x91ba0000 0x0 0x1000>;
 			no-map;
 		};
 
@@ -433,13 +473,43 @@
 			no-map;
 		};
 
+		audio_mdf_mem: audio-mdf-region@ae000000 {
+			reg = <0x0 0xae000000 0x0 0x1000000>;
+			no-map;
+		};
+
+		firmware_mem: firmware-region@b0000000 {
+			reg = <0x0 0xb0000000 0x0 0x800000>;
+			no-map;
+		};
+
 		hyptz_reserved_mem: hyptz-reserved@beb00000 {
 			reg = <0x0 0xbeb00000 0x0 0x11500000>;
 			no-map;
 		};
 
-		tz_stat_mem: tz-stat@d0000000 {
-			reg = <0x0 0xd0000000 0x0 0x100000>;
+		scmi_mem: scmi-region@d0000000 {
+			reg = <0x0 0xd0000000 0x0 0x40000>;
+			no-map;
+		};
+
+		firmware_logs_mem: firmware-logs@d0040000 {
+			reg = <0x0 0xd0040000 0x0 0x10000>;
+			no-map;
+		};
+
+		firmware_audio_mem: firmware-audio@d0050000 {
+			reg = <0x0 0xd0050000 0x0 0x4000>;
+			no-map;
+		};
+
+		firmware_reserved_mem: firmware-reserved@d0054000 {
+			reg = <0x0 0xd0054000 0x0 0x9c000>;
+			no-map;
+		};
+
+		firmware_quantum_test_mem: firmware-quantum-test@d00f0000 {
+			reg = <0x0 0xd00f0000 0x0 0x10000>;
 			no-map;
 		};
 
@@ -453,8 +523,23 @@
 			no-map;
 		};
 
-		trusted_apps_mem: trusted-apps@d1800000 {
-			reg = <0x0 0xd1800000 0x0 0x3900000>;
+		deepsleep_backup_mem: deepsleep-backup@d1800000 {
+			reg = <0x0 0xd1800000 0x0 0x100000>;
+			no-map;
+		};
+
+		trusted_apps_mem: trusted-apps@d1900000 {
+			reg = <0x0 0xd1900000 0x0 0x3800000>;
+			no-map;
+		};
+
+		tz_stat_mem: tz-stat@db100000 {
+			reg = <0x0 0xdb100000 0x0 0x100000>;
+			no-map;
+		};
+
+		cpucp_fw_mem: cpucp-fw@db200000 {
+			reg = <0x0 0xdb200000 0x0 0x100000>;
 			no-map;
 		};
 	};
@@ -1615,10 +1700,12 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 287 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 261 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 12 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
 					  "ss_phy_irq";
@@ -1702,10 +1789,12 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 7 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 13 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
 					  "ss_phy_irq";
@@ -1765,9 +1854,11 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 443 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
 			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq";
 
@@ -2394,8 +2485,9 @@
 			      <0x0 0x23016000 0x0 0x100>;
 			reg-names = "stmmaceth", "rgmii";
 
-			interrupts = <GIC_SPI 929 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "macirq";
+			interrupts = <GIC_SPI 929 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 781 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq", "sfty";
 
 			clocks = <&gcc GCC_EMAC1_AXI_CLK>,
 				 <&gcc GCC_EMAC1_SLV_AHB_CLK>,
@@ -2427,8 +2519,9 @@
 			      <0x0 0x23056000 0x0 0x100>;
 			reg-names = "stmmaceth", "rgmii";
 
-			interrupts = <GIC_SPI 946 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "macirq";
+			interrupts = <GIC_SPI 946 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 782 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "macirq", "sfty";
 
 			clocks = <&gcc GCC_EMAC0_AXI_CLK>,
 				 <&gcc GCC_EMAC0_SLV_AHB_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
index 46aaeba28604..f3a6da8b2890 100644
--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
@@ -649,6 +649,7 @@ ap_ec_spi: &spi6 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&ap_ec_int_l>;
 		spi-max-frequency = <3000000>;
+		wakeup-source;
 
 		cros_ec_pwm: pwm {
 			compatible = "google,cros-ec-pwm";
diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index 4dcaa15caef2..2b481e20ae38 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -817,7 +817,7 @@
 				bits = <1 3>;
 			};
 
-			gpu_speed_bin: gpu_speed_bin@1d2 {
+			gpu_speed_bin: gpu-speed-bin@1d2 {
 				reg = <0x1d2 0x2>;
 				bits = <5 8>;
 			};
@@ -1532,6 +1532,76 @@
 			qcom,bcm-voters = <&apps_bcm_voter>;
 		};
 
+		ufs_mem_hc: ufshc@1d84000 {
+			compatible = "qcom,sc7180-ufshc", "qcom,ufshc",
+				     "jedec,ufs-2.0";
+			reg = <0 0x01d84000 0 0x3000>;
+			interrupts = <GIC_SPI 265 IRQ_TYPE_LEVEL_HIGH>;
+			phys = <&ufs_mem_phy>;
+			phy-names = "ufsphy";
+			lanes-per-direction = <1>;
+			#reset-cells = <1>;
+			resets = <&gcc GCC_UFS_PHY_BCR>;
+			reset-names = "rst";
+
+			power-domains = <&gcc UFS_PHY_GDSC>;
+
+			iommus = <&apps_smmu 0xa0 0x0>;
+
+			clock-names = "core_clk",
+				      "bus_aggr_clk",
+				      "iface_clk",
+				      "core_clk_unipro",
+				      "ref_clk",
+				      "tx_lane0_sync_clk",
+				      "rx_lane0_sync_clk";
+			clocks = <&gcc GCC_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_AGGRE_UFS_PHY_AXI_CLK>,
+				 <&gcc GCC_UFS_PHY_AHB_CLK>,
+				 <&gcc GCC_UFS_PHY_UNIPRO_CORE_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>,
+				 <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>;
+			freq-table-hz = <50000000 200000000>,
+					<0 0>,
+					<0 0>,
+					<37500000 150000000>,
+					<0 0>,
+					<0 0>,
+					<0 0>;
+
+			interconnects = <&aggre1_noc MASTER_UFS_MEM QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_UFS_MEM_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "ufs-ddr", "cpu-ufs";
+
+			qcom,ice = <&ice>;
+
+			status = "disabled";
+		};
+
+		ufs_mem_phy: phy@1d87000 {
+			compatible = "qcom,sc7180-qmp-ufs-phy",
+				     "qcom,sm7150-qmp-ufs-phy";
+			reg = <0 0x01d87000 0 0x1000>;
+			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+			clock-names = "ref", "ref_aux";
+			power-domains = <&gcc UFS_PHY_GDSC>;
+			resets = <&ufs_mem_hc 0>;
+			reset-names = "ufsphy";
+			#phy-cells = <0>;
+			status = "disabled";
+		};
+
+		ice: crypto@1d90000 {
+			compatible = "qcom,sc7180-inline-crypto-engine",
+				     "qcom,inline-crypto-engine";
+			reg = <0 0x01d90000 0 0x8000>;
+			clocks = <&gcc GCC_UFS_PHY_ICE_CORE_CLK>;
+		};
+
 		ipa: ipa@1e40000 {
 			compatible = "qcom,sc7180-ipa";
 
@@ -2964,12 +3034,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 			required-opps = <&rpmhpd_opp_nom>;
diff --git a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
index c4d00a81da39..cecb3e89f7f7 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi
@@ -18,6 +18,7 @@
  */
 
 /delete-node/ &cdsp_mem;
+/delete-node/ &domain_idle_states;
 /delete-node/ &gpu_zap_mem;
 /delete-node/ &gpu_zap_shader;
 /delete-node/ &hyp_mem;
@@ -26,6 +27,18 @@
 /delete-node/ &sec_apps_mem;
 
 / {
+	cpus {
+		domain_idle_states: domain-idle-states {
+			CLUSTER_SLEEP_0: cluster-sleep-0 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x40003444>;
+				entry-latency-us = <2752>;
+				exit-latency-us = <6562>;
+				min-residency-us = <9926>;
+			};
+		};
+	};
+
 	reserved-memory {
 		camera_mem: memory@8ad00000 {
 			reg = <0x0 0x8ad00000 0x0 0x500000>;
@@ -39,6 +52,10 @@
 	};
 };
 
+&CLUSTER_PD {
+	domain-idle-states = <&CLUSTER_SLEEP_0>;
+};
+
 &lpass_aon {
 	status = "okay";
 };
@@ -119,6 +136,17 @@
 	dma-coherent;
 };
 
+&venus {
+	iommus = <&apps_smmu 0x2180 0x20>,
+		 <&apps_smmu 0x2184 0x20>;
+
+	status = "okay";
+
+	video-firmware {
+		iommus = <&apps_smmu 0x21a2 0x0>;
+	};
+};
+
 &watchdog {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi b/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi
index 9ea6636125ad..2ba4ea60cb14 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-herobrine.dtsi
@@ -548,6 +548,7 @@ ap_ec_spi: &spi10 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&ap_ec_int_l>;
 		spi-max-frequency = <3000000>;
+		wakeup-source;
 
 		cros_ec_pwm: pwm {
 			compatible = "google,cros-ec-pwm";
diff --git a/arch/arm64/boot/dts/qcom/sc7280-idp-ec-h1.dtsi b/arch/arm64/boot/dts/qcom/sc7280-idp-ec-h1.dtsi
index ebae545c587c..fbfac7534d3c 100644
--- a/arch/arm64/boot/dts/qcom/sc7280-idp-ec-h1.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280-idp-ec-h1.dtsi
@@ -19,6 +19,7 @@ ap_ec_spi: &spi10 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&ap_ec_int_l>;
 		spi-max-frequency = <3000000>;
+		wakeup-source;
 
 		cros_ec_pwm: pwm {
 			compatible = "google,cros-ec-pwm";
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index 83b5b76ba179..7e7f0f0fb41b 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -202,6 +202,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_0>;
 			operating-points-v2 = <&cpu0_opp_table>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 0>;
@@ -229,6 +231,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_100>;
 			operating-points-v2 = <&cpu0_opp_table>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 0>;
@@ -251,6 +255,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_200>;
 			operating-points-v2 = <&cpu0_opp_table>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 0>;
@@ -273,6 +279,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_300>;
 			operating-points-v2 = <&cpu0_opp_table>;
+			capacity-dmips-mhz = <1024>;
+			dynamic-power-coefficient = <100>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 0>;
@@ -295,6 +303,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_400>;
 			operating-points-v2 = <&cpu4_opp_table>;
+			capacity-dmips-mhz = <1946>;
+			dynamic-power-coefficient = <520>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 1>;
@@ -317,6 +327,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_500>;
 			operating-points-v2 = <&cpu4_opp_table>;
+			capacity-dmips-mhz = <1946>;
+			dynamic-power-coefficient = <520>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 1>;
@@ -339,6 +351,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_600>;
 			operating-points-v2 = <&cpu4_opp_table>;
+			capacity-dmips-mhz = <1946>;
+			dynamic-power-coefficient = <520>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 1>;
@@ -361,6 +375,8 @@
 			power-domain-names = "psci";
 			next-level-cache = <&L2_700>;
 			operating-points-v2 = <&cpu7_opp_table>;
+			capacity-dmips-mhz = <1985>;
+			dynamic-power-coefficient = <552>;
 			interconnects = <&gem_noc MASTER_APPSS_PROC 3 &mc_virt SLAVE_EBI1 3>,
 					<&epss_l3 MASTER_EPSS_L3_APPS &epss_l3 SLAVE_EPSS_L3_SHARED>;
 			qcom,freq-domain = <&cpufreq_hw 2>;
@@ -453,15 +469,29 @@
 			};
 		};
 
-		domain-idle-states {
-			CLUSTER_SLEEP_0: cluster-sleep-0 {
+		domain_idle_states: domain-idle-states {
+			CLUSTER_SLEEP_APSS_OFF: cluster-sleep-0 {
 				compatible = "domain-idle-state";
-				idle-state-name = "cluster-power-down";
-				arm,psci-suspend-param = <0x40003444>;
+				arm,psci-suspend-param = <0x41000044>;
+				entry-latency-us = <2752>;
+				exit-latency-us = <3048>;
+				min-residency-us = <6118>;
+			};
+
+			CLUSTER_SLEEP_CX_RET: cluster-sleep-1 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x41001344>;
 				entry-latency-us = <3263>;
+				exit-latency-us = <4562>;
+				min-residency-us = <8467>;
+			};
+
+			CLUSTER_SLEEP_LLCC_OFF: cluster-sleep-2 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x4100b344>;
+				entry-latency-us = <3638>;
 				exit-latency-us = <6562>;
-				min-residency-us = <9926>;
-				local-timer-stop;
+				min-residency-us = <9826>;
 			};
 		};
 	};
@@ -872,7 +902,7 @@
 
 		CLUSTER_PD: power-domain-cluster {
 			#power-domain-cells = <0>;
-			domain-idle-states = <&CLUSTER_SLEEP_0>;
+			domain-idle-states = <&CLUSTER_SLEEP_APSS_OFF &CLUSTER_SLEEP_CX_RET &CLUSTER_SLEEP_LLCC_OFF>;
 		};
 	};
 
@@ -966,7 +996,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			gpu_speed_bin: gpu_speed_bin@1e9 {
+			gpu_speed_bin: gpu-speed-bin@1e9 {
 				reg = <0x1e9 0x2>;
 				bits = <5 8>;
 			};
@@ -2178,8 +2208,16 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0", "msi1", "msi2", "msi3",
+					  "msi4", "msi5", "msi6", "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>,
@@ -2345,6 +2383,8 @@
 				 <&apps_smmu 0x4e6 0x0011>;
 			qcom,ee = <0>;
 			qcom,controlled-remotely;
+			num-channels = <16>;
+			qcom,num-ees = <4>;
 		};
 
 		crypto: crypto@1dfa000 {
@@ -2648,6 +2688,31 @@
 			status = "disabled";
 		};
 
+		slimbam: dma-controller@3a84000 {
+			compatible = "qcom,bam-v1.7.0";
+			reg = <0 0x03a84000 0 0x20000>;
+			interrupts = <GIC_SPI 164 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			qcom,controlled-remotely;
+			num-channels  = <31>;
+			qcom,ee = <1>;
+			qcom,num-ees = <2>;
+			iommus = <&apps_smmu 0x1826 0x0>;
+			status = "disabled";
+		};
+
+		slim: slim-ngd@3ac0000 {
+			compatible = "qcom,slim-ngd-v1.5.0";
+			reg = <0 0x03ac0000 0 0x2c000>;
+			interrupts = <GIC_SPI 163 IRQ_TYPE_LEVEL_HIGH>;
+			dmas = <&slimbam 3>, <&slimbam 4>;
+			dma-names = "rx", "tx";
+			iommus = <&apps_smmu 0x1826 0x0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		lpass_hm: clock-controller@3c00000 {
 			compatible = "qcom,sc7280-lpasshm";
 			reg = <0 0x03c00000 0 0x28>;
@@ -3582,10 +3647,12 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 241 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 13 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq";
 
@@ -4035,11 +4102,13 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq",
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
 					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
 					  "ss_phy_irq";
@@ -4065,6 +4134,25 @@
 				phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
 				phy-names = "usb2-phy", "usb3-phy";
 				maximum-speed = "super-speed";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						usb_1_dwc3_hs: endpoint {
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						usb_1_dwc3_ss: endpoint {
+						};
+					};
+				};
 			};
 		};
 
@@ -4091,10 +4179,11 @@
 					<&mmss_noc MASTER_VIDEO_P0 0 &mc_virt SLAVE_EBI1 0>;
 			interconnect-names = "cpu-cfg", "video-mem";
 
-			iommus = <&apps_smmu 0x2180 0x20>,
-				 <&apps_smmu 0x2184 0x20>;
+			iommus = <&apps_smmu 0x2180 0x20>;
 			memory-region = <&video_mem>;
 
+			status = "disabled";
+
 			video-decoder {
 				compatible = "venus-decoder";
 			};
@@ -4103,10 +4192,6 @@
 				compatible = "venus-encoder";
 			};
 
-			video-firmware {
-				iommus = <&apps_smmu 0x21a2 0x0>;
-			};
-
 			venus_opp_table: opp-table {
 				compatible = "operating-points-v2";
 
diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
index 0430d99091e3..32afc78d5b76 100644
--- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
@@ -290,7 +290,7 @@
 			BIG_CPU_SLEEP_0: cpu-sleep-1-0 {
 				compatible = "arm,idle-state";
 				arm,psci-suspend-param = <0x40000004>;
-				entry-latency-us = <241>;
+				entry-latency-us = <2411>;
 				exit-latency-us = <1461>;
 				min-residency-us = <4488>;
 				local-timer-stop;
@@ -298,7 +298,15 @@
 		};
 
 		domain-idle-states {
-			CLUSTER_SLEEP_0: cluster-sleep-0 {
+			CLUSTER_SLEEP_APSS_OFF: cluster-sleep-0 {
+				compatible = "domain-idle-state";
+				arm,psci-suspend-param = <0x41000044>;
+				entry-latency-us = <3300>;
+				exit-latency-us = <3300>;
+				min-residency-us = <6000>;
+			};
+
+			CLUSTER_SLEEP_AOSS_SLEEP: cluster-sleep-1 {
 				compatible = "domain-idle-state";
 				arm,psci-suspend-param = <0x4100a344>;
 				entry-latency-us = <3263>;
@@ -582,7 +590,7 @@
 
 		CLUSTER_PD: power-domain-cpu-cluster0 {
 			#power-domain-cells = <0>;
-			domain-idle-states = <&CLUSTER_SLEEP_0>;
+			domain-idle-states = <&CLUSTER_SLEEP_APSS_OFF &CLUSTER_SLEEP_AOSS_SLEEP>;
 		};
 	};
 
@@ -782,6 +790,7 @@
 			clock-names = "bi_tcxo",
 				      "bi_tcxo_ao",
 				      "sleep_clk";
+			power-domains = <&rpmhpd SC8180X_CX>;
 		};
 
 		qupv3_id_0: geniqup@8c0000 {
@@ -1708,8 +1717,22 @@
 			ranges = <0x01000000 0x0 0x60200000 0x0 0x60200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1805,8 +1828,22 @@
 			ranges = <0x01000000 0x0 0x40200000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1903,8 +1940,22 @@
 			ranges = <0x01000000 0x0 0x68200000 0x0 0x68200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x68300000 0x0 0x68300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 755 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 756 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 755 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 754 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 753 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 752 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 751 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 750 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 749 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 747 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2001,8 +2052,22 @@
 			ranges = <0x01000000 0x0 0x70200000 0x0 0x70200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 671 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 672 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 671 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 670 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 669 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 668 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 667 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 666 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 665 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 663 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2131,9 +2196,11 @@
 			reg = <0 0x01d87000 0 0x1000>;
 
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_MEM_CLKREF_EN>;
 			clock-names = "ref",
-				      "ref_aux";
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -2173,6 +2240,8 @@
 			interconnect-names = "gfx-mem";
 
 			qcom,gmu = <&gmu>;
+			#cooling-cells = <2>;
+
 			status = "disabled";
 
 			gpu_opp_table: opp-table {
@@ -2692,9 +2761,15 @@
 			interrupt-controller;
 			#interrupt-cells = <1>;
 
-			interconnects = <&mmss_noc MASTER_MDP_PORT0 0 &mc_virt SLAVE_EBI_CH0 0>,
-					<&mmss_noc MASTER_MDP_PORT1 0 &mc_virt SLAVE_EBI_CH0 0>;
-			interconnect-names = "mdp0-mem", "mdp1-mem";
+			interconnects = <&mmss_noc MASTER_MDP_PORT0 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>,
+					<&mmss_noc MASTER_MDP_PORT1 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_AMPSS_M0 QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "mdp0-mem",
+					     "mdp1-mem",
+					     "cpu-cfg";
 
 			iommus = <&apps_smmu 0x800 0x420>;
 
@@ -2723,10 +2798,8 @@
 					      "rot",
 					      "lut";
 
-				assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>,
-						  <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
-				assigned-clock-rates = <460000000>,
-						       <19200000>;
+				assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				assigned-clock-rates = <19200000>;
 
 				operating-points-v2 = <&mdp_opp_table>;
 				power-domains = <&rpmhpd SC8180X_MMCX>;
@@ -3184,7 +3257,7 @@
 				 <&dispcc DISP_CC_MDSS_AHB_CLK>;
 			clock-names = "aux", "cfg_ahb";
 
-			power-domains = <&dispcc MDSS_GDSC>;
+			power-domains = <&rpmhpd SC8180X_MX>;
 
 			#clock-cells = <1>;
 			#phy-cells = <0>;
@@ -3210,6 +3283,7 @@
 				      "edp_phy_pll_link_clk",
 				      "edp_phy_pll_vco_div_clk";
 			power-domains = <&rpmhpd SC8180X_MMCX>;
+			required-opps = <&rpmhpd_opp_low_svs>;
 			#clock-cells = <1>;
 			#reset-cells = <1>;
 			#power-domain-cells = <1>;
@@ -3248,7 +3322,7 @@
 
 		aoss_qmp: power-controller@c300000 {
 			compatible = "qcom,sc8180x-aoss-qmp", "qcom,aoss-qmp";
-			reg = <0x0 0x0c300000 0x0 0x100000>;
+			reg = <0x0 0x0c300000 0x0 0x400>;
 			interrupts = <GIC_SPI 389 IRQ_TYPE_EDGE_RISING>;
 			mboxes = <&apss_shared 0>;
 
@@ -3256,6 +3330,11 @@
 			#power-domain-cells = <1>;
 		};
 
+		sram@c3f0000 {
+			compatible = "qcom,rpmh-stats";
+			reg = <0x0 0x0c3f0000 0x0 0x400>;
+		};
+
 		spmi_bus: spmi@c440000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0x0 0x0c440000 0x0 0x0001100>,
@@ -3880,8 +3959,15 @@
 
 			thermal-sensors = <&tsens0 15>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				trip-point0 {
+				gpu_top_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
@@ -4030,8 +4116,15 @@
 
 			thermal-sensors = <&tsens1 11>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				trip-point0 {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
index ffc4406422ae..41215567b3ae 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts
@@ -563,6 +563,8 @@
 };
 
 &pcie4 {
+	max-link-speed = <2>;
+
 	perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>;
 	wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>;
 
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
index def3976bd5bb..15ae94c1602d 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
@@ -6,10 +6,8 @@
 
 /dts-v1/;
 
-#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h>
-#include <dt-bindings/iio/qcom,spmi-adc7-pmk8350.h>
-#include <dt-bindings/iio/qcom,spmi-adc7-pmr735a.h>
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/gpio-keys.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/leds/common.h>
@@ -722,6 +720,8 @@
 };
 
 &pcie4 {
+	max-link-speed = <2>;
+
 	perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>;
 	wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>;
 
@@ -853,27 +853,6 @@
 };
 
 &pmk8280_vadc {
-	status = "okay";
-
-	channel@3 {
-		reg = <PMK8350_ADC7_DIE_TEMP>;
-		qcom,pre-scaling = <1 1>;
-		label = "pmk8350_die_temp";
-	};
-
-	channel@44 {
-		reg = <PMK8350_ADC7_AMUX_THM1_100K_PU>;
-		qcom,hw-settle-time = <200>;
-		qcom,ratiometric;
-		label = "pmk8350_xo_therm";
-	};
-
-	channel@103 {
-		reg = <PM8350_ADC7_DIE_TEMP(1)>;
-		qcom,pre-scaling = <1 1>;
-		label = "pmc8280_1_die_temp";
-	};
-
 	channel@144 {
 		reg = <PM8350_ADC7_AMUX_THM1_100K_PU(1)>;
 		qcom,hw-settle-time = <200>;
@@ -902,12 +881,6 @@
 		label = "sys_therm4";
 	};
 
-	channel@303 {
-		reg = <PM8350_ADC7_DIE_TEMP(3)>;
-		qcom,pre-scaling = <1 1>;
-		label = "pmc8280_2_die_temp";
-	};
-
 	channel@344 {
 		reg = <PM8350_ADC7_AMUX_THM1_100K_PU(3)>;
 		qcom,hw-settle-time = <200>;
@@ -935,12 +908,6 @@
 		qcom,ratiometric;
 		label = "sys_therm8";
 	};
-
-	channel@403 {
-		reg = <PMR735A_ADC7_DIE_TEMP>;
-		qcom,pre-scaling = <1 1>;
-		label = "pmr735a_die_temp";
-	};
 };
 
 &qup0 {
@@ -1202,7 +1169,7 @@
 };
 
 &vamacro {
-	pinctrl-0 = <&dmic01_default>, <&dmic02_default>;
+	pinctrl-0 = <&dmic01_default>, <&dmic23_default>;
 	pinctrl-names = "default";
 
 	vdd-micb-supply = <&vreg_s10b>;
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
index 80ee12ded4f4..945de77911de 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
@@ -3,6 +3,9 @@
  * Copyright (c) 2022, Linaro Limited
  */
 
+#include <dt-bindings/iio/qcom,spmi-adc7-pm8350.h>
+#include <dt-bindings/iio/qcom,spmi-adc7-pmk8350.h>
+#include <dt-bindings/iio/qcom,spmi-adc7-pmr735a.h>
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/spmi/spmi.h>
@@ -84,7 +87,37 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			#io-channel-cells = <1>;
-			status = "disabled";
+
+			channel@3 {
+				reg = <PMK8350_ADC7_DIE_TEMP>;
+				qcom,pre-scaling = <1 1>;
+				label = "pmk8350_die_temp";
+			};
+
+			channel@44 {
+				reg = <PMK8350_ADC7_AMUX_THM1_100K_PU>;
+				qcom,hw-settle-time = <200>;
+				qcom,ratiometric;
+				label = "pmk8350_xo_therm";
+			};
+
+			channel@103 {
+				reg = <PM8350_ADC7_DIE_TEMP(1)>;
+				qcom,pre-scaling = <1 1>;
+				label = "pmc8280_1_die_temp";
+			};
+
+			channel@303 {
+				reg = <PM8350_ADC7_DIE_TEMP(3)>;
+				qcom,pre-scaling = <1 1>;
+				label = "pmc8280_2_die_temp";
+			};
+
+			channel@403 {
+				reg = <PMR735A_ADC7_DIE_TEMP>;
+				qcom,pre-scaling = <1 1>;
+				label = "pmr735a_die_temp";
+			};
 		};
 
 		pmk8280_adc_tm: adc-tm@3400 {
@@ -126,6 +159,8 @@
 			compatible = "qcom,spmi-temp-alarm";
 			reg = <0xa00>;
 			interrupts-extended = <&spmi_bus 0x1 0xa 0x0 IRQ_TYPE_EDGE_BOTH>;
+			io-channels = <&pmk8280_vadc PM8350_ADC7_DIE_TEMP(1)>;
+			io-channel-names = "thermal";
 			#thermal-sensor-cells = <0>;
 		};
 
@@ -178,6 +213,8 @@
 			compatible = "qcom,spmi-temp-alarm";
 			reg = <0xa00>;
 			interrupts-extended = <&spmi_bus 0x2 0xa 0x0 IRQ_TYPE_EDGE_BOTH>;
+			io-channels = <&pmk8280_vadc PM8350_ADC7_DIE_TEMP(3)>;
+			io-channel-names = "thermal";
 			#thermal-sensor-cells = <0>;
 		};
 
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
index febf28356ff8..a5b194813079 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
@@ -2257,9 +2257,12 @@
 			compatible = "qcom,sc8280xp-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
-			clocks = <&gcc GCC_UFS_CARD_CLKREF_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
-			clock-names = "ref", "ref_aux";
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_CARD_CLKREF_CLK>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			power-domains = <&gcc UFS_PHY_GDSC>;
 
@@ -2319,9 +2322,12 @@
 			compatible = "qcom,sc8280xp-qmp-ufs-phy";
 			reg = <0 0x01da7000 0 0x1000>;
 
-			clocks = <&gcc GCC_UFS_1_CARD_CLKREF_CLK>,
-				 <&gcc GCC_UFS_CARD_PHY_AUX_CLK>;
-			clock-names = "ref", "ref_aux";
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_CARD_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_1_CARD_CLKREF_CLK>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			power-domains = <&gcc UFS_CARD_GDSC>;
 
@@ -2978,7 +2984,7 @@
 				};
 			};
 
-			dmic02_default: dmic02-default-state {
+			dmic23_default: dmic23-default-state {
 				clk-pins {
 					pins = "gpio8";
 					function = "dmic2_clk";
@@ -2994,7 +3000,7 @@
 				};
 			};
 
-			dmic02_sleep: dmic02-sleep-state {
+			dmic23_sleep: dmic23-sleep-state {
 				clk-pins {
 					pins = "gpio8";
 					function = "dmic2_clk";
@@ -3451,6 +3457,404 @@
 			};
 		};
 
+		cci0: cci@ac4a000 {
+			compatible = "qcom,sc8280xp-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4a000 0 0x1000>;
+
+			interrupts = <GIC_SPI 460 IRQ_TYPE_EDGE_RISING>;
+
+			clocks = <&camcc CAMCC_CAMNOC_AXI_CLK>,
+				 <&camcc CAMCC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAMCC_CPAS_AHB_CLK>,
+				 <&camcc CAMCC_CCI_0_CLK>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci";
+
+			power-domains = <&camcc TITAN_TOP_GDSC>;
+
+			pinctrl-0 = <&cci0_default>;
+			pinctrl-1 = <&cci0_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci0_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci0_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		cci1: cci@ac4b000 {
+			compatible = "qcom,sc8280xp-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4b000 0 0x1000>;
+
+			interrupts = <GIC_SPI 271 IRQ_TYPE_EDGE_RISING>;
+
+			clocks = <&camcc CAMCC_CAMNOC_AXI_CLK>,
+				 <&camcc CAMCC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAMCC_CPAS_AHB_CLK>,
+				 <&camcc CAMCC_CCI_1_CLK>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci";
+
+			power-domains = <&camcc TITAN_TOP_GDSC>;
+
+			pinctrl-0 = <&cci1_default>;
+			pinctrl-1 = <&cci1_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci1_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci1_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		cci2: cci@ac4c000 {
+			compatible = "qcom,sc8280xp-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4c000 0 0x1000>;
+
+			interrupts = <GIC_SPI 651 IRQ_TYPE_EDGE_RISING>;
+
+			clocks = <&camcc CAMCC_CAMNOC_AXI_CLK>,
+				 <&camcc CAMCC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAMCC_CPAS_AHB_CLK>,
+				 <&camcc CAMCC_CCI_2_CLK>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci";
+			power-domains = <&camcc TITAN_TOP_GDSC>;
+
+			pinctrl-0 = <&cci2_default>;
+			pinctrl-1 = <&cci2_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci2_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci2_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		cci3: cci@ac4d000 {
+			compatible = "qcom,sc8280xp-cci", "qcom,msm8996-cci";
+			reg = <0 0x0ac4d000 0 0x1000>;
+
+			interrupts = <GIC_SPI 650 IRQ_TYPE_EDGE_RISING>;
+
+			clocks = <&camcc CAMCC_CAMNOC_AXI_CLK>,
+				 <&camcc CAMCC_SLOW_AHB_CLK_SRC>,
+				 <&camcc CAMCC_CPAS_AHB_CLK>,
+				 <&camcc CAMCC_CCI_3_CLK>;
+			clock-names = "camnoc_axi",
+				      "slow_ahb_src",
+				      "cpas_ahb",
+				      "cci";
+
+			power-domains = <&camcc TITAN_TOP_GDSC>;
+
+			pinctrl-0 = <&cci3_default>;
+			pinctrl-1 = <&cci3_sleep>;
+			pinctrl-names = "default", "sleep";
+
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+
+			cci3_i2c0: i2c-bus@0 {
+				reg = <0>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+
+			cci3_i2c1: i2c-bus@1 {
+				reg = <1>;
+				clock-frequency = <1000000>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+		camss: camss@ac5a000 {
+			compatible = "qcom,sc8280xp-camss";
+
+			reg = <0 0x0ac5a000 0 0x2000>,
+			      <0 0x0ac5c000 0 0x2000>,
+			      <0 0x0ac65000 0 0x2000>,
+			      <0 0x0ac67000 0 0x2000>,
+			      <0 0x0acaf000 0 0x4000>,
+			      <0 0x0acb3000 0 0x1000>,
+			      <0 0x0acb6000 0 0x4000>,
+			      <0 0x0acba000 0 0x1000>,
+			      <0 0x0acbd000 0 0x4000>,
+			      <0 0x0acc1000 0 0x1000>,
+			      <0 0x0acc4000 0 0x4000>,
+			      <0 0x0acc8000 0 0x1000>,
+			      <0 0x0accb000 0 0x4000>,
+			      <0 0x0accf000 0 0x1000>,
+			      <0 0x0acd2000 0 0x4000>,
+			      <0 0x0acd6000 0 0x1000>,
+			      <0 0x0acd9000 0 0x4000>,
+			      <0 0x0acdd000 0 0x1000>,
+			      <0 0x0ace0000 0 0x4000>,
+			      <0 0x0ace4000 0 0x1000>;
+			reg-names = "csiphy2",
+				    "csiphy3",
+				    "csiphy0",
+				    "csiphy1",
+				    "vfe0",
+				    "csid0",
+				    "vfe1",
+				    "csid1",
+				    "vfe2",
+				    "csid2",
+				    "vfe_lite0",
+				    "csid0_lite",
+				    "vfe_lite1",
+				    "csid1_lite",
+				    "vfe_lite2",
+				    "csid2_lite",
+				    "vfe_lite3",
+				    "csid3_lite",
+				    "vfe3",
+				    "csid3";
+
+			interrupts = <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 448 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 464 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 465 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 466 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 467 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 468 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 477 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 640 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 641 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 758 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 759 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 760 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 761 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 762 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 764 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "csid1_lite",
+					  "vfe_lite1",
+					  "csiphy3",
+					  "csid0",
+					  "vfe0",
+					  "csid1",
+					  "vfe1",
+					  "csid0_lite",
+					  "vfe_lite0",
+					  "csiphy0",
+					  "csiphy1",
+					  "csiphy2",
+					  "csid2",
+					  "vfe2",
+					  "csid3_lite",
+					  "csid2_lite",
+					  "vfe_lite3",
+					  "vfe_lite2",
+					  "csid3",
+					  "vfe3";
+
+			power-domains = <&camcc IFE_0_GDSC>,
+					<&camcc IFE_1_GDSC>,
+					<&camcc IFE_2_GDSC>,
+					<&camcc IFE_3_GDSC>,
+					<&camcc TITAN_TOP_GDSC>;
+			power-domain-names = "ife0",
+					     "ife1",
+					     "ife2",
+					     "ife3",
+					     "top";
+
+			clocks = <&camcc CAMCC_CAMNOC_AXI_CLK>,
+				 <&camcc CAMCC_CPAS_AHB_CLK>,
+				 <&camcc CAMCC_CSIPHY0_CLK>,
+				 <&camcc CAMCC_CSI0PHYTIMER_CLK>,
+				 <&camcc CAMCC_CSIPHY1_CLK>,
+				 <&camcc CAMCC_CSI1PHYTIMER_CLK>,
+				 <&camcc CAMCC_CSIPHY2_CLK>,
+				 <&camcc CAMCC_CSI2PHYTIMER_CLK>,
+				 <&camcc CAMCC_CSIPHY3_CLK>,
+				 <&camcc CAMCC_CSI3PHYTIMER_CLK>,
+				 <&camcc CAMCC_IFE_0_AXI_CLK>,
+				 <&camcc CAMCC_IFE_0_CLK>,
+				 <&camcc CAMCC_IFE_0_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_0_CSID_CLK>,
+				 <&camcc CAMCC_IFE_1_AXI_CLK>,
+				 <&camcc CAMCC_IFE_1_CLK>,
+				 <&camcc CAMCC_IFE_1_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_1_CSID_CLK>,
+				 <&camcc CAMCC_IFE_2_AXI_CLK>,
+				 <&camcc CAMCC_IFE_2_CLK>,
+				 <&camcc CAMCC_IFE_2_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_2_CSID_CLK>,
+				 <&camcc CAMCC_IFE_3_AXI_CLK>,
+				 <&camcc CAMCC_IFE_3_CLK>,
+				 <&camcc CAMCC_IFE_3_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_3_CSID_CLK>,
+				 <&camcc CAMCC_IFE_LITE_0_CLK>,
+				 <&camcc CAMCC_IFE_LITE_0_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_LITE_0_CSID_CLK>,
+				 <&camcc CAMCC_IFE_LITE_1_CLK>,
+				 <&camcc CAMCC_IFE_LITE_1_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_LITE_1_CSID_CLK>,
+				 <&camcc CAMCC_IFE_LITE_2_CLK>,
+				 <&camcc CAMCC_IFE_LITE_2_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_LITE_2_CSID_CLK>,
+				 <&camcc CAMCC_IFE_LITE_3_CLK>,
+				 <&camcc CAMCC_IFE_LITE_3_CPHY_RX_CLK>,
+				 <&camcc CAMCC_IFE_LITE_3_CSID_CLK>,
+				 <&gcc GCC_CAMERA_HF_AXI_CLK>,
+				 <&gcc GCC_CAMERA_SF_AXI_CLK>;
+			clock-names = "camnoc_axi",
+				      "cpas_ahb",
+				      "csiphy0",
+				      "csiphy0_timer",
+				      "csiphy1",
+				      "csiphy1_timer",
+				      "csiphy2",
+				      "csiphy2_timer",
+				      "csiphy3",
+				      "csiphy3_timer",
+				      "vfe0_axi",
+				      "vfe0",
+				      "vfe0_cphy_rx",
+				      "vfe0_csid",
+				      "vfe1_axi",
+				      "vfe1",
+				      "vfe1_cphy_rx",
+				      "vfe1_csid",
+				      "vfe2_axi",
+				      "vfe2",
+				      "vfe2_cphy_rx",
+				      "vfe2_csid",
+				      "vfe3_axi",
+				      "vfe3",
+				      "vfe3_cphy_rx",
+				      "vfe3_csid",
+				      "vfe_lite0",
+				      "vfe_lite0_cphy_rx",
+				      "vfe_lite0_csid",
+				      "vfe_lite1",
+				      "vfe_lite1_cphy_rx",
+				      "vfe_lite1_csid",
+				      "vfe_lite2",
+				      "vfe_lite2_cphy_rx",
+				      "vfe_lite2_csid",
+				      "vfe_lite3",
+				      "vfe_lite3_cphy_rx",
+				      "vfe_lite3_csid",
+				      "gcc_axi_hf",
+				      "gcc_axi_sf";
+
+			iommus = <&apps_smmu 0x2000 0x4e0>,
+				 <&apps_smmu 0x2020 0x4e0>,
+				 <&apps_smmu 0x2040 0x4e0>,
+				 <&apps_smmu 0x2060 0x4e0>,
+				 <&apps_smmu 0x2080 0x4e0>,
+				 <&apps_smmu 0x20e0 0x4e0>,
+				 <&apps_smmu 0x20c0 0x4e0>,
+				 <&apps_smmu 0x20a0 0x4e0>,
+				 <&apps_smmu 0x2400 0x4e0>,
+				 <&apps_smmu 0x2420 0x4e0>,
+				 <&apps_smmu 0x2440 0x4e0>,
+				 <&apps_smmu 0x2460 0x4e0>,
+				 <&apps_smmu 0x2480 0x4e0>,
+				 <&apps_smmu 0x24e0 0x4e0>,
+				 <&apps_smmu 0x24c0 0x4e0>,
+				 <&apps_smmu 0x24a0 0x4e0>;
+
+			interconnects = <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_CAMERA_CFG 0>,
+					<&mmss_noc MASTER_CAMNOC_HF 0 &mc_virt SLAVE_EBI1 0>,
+					<&mmss_noc MASTER_CAMNOC_SF 0 &mc_virt SLAVE_EBI1 0>,
+					<&mmss_noc MASTER_CAMNOC_ICP 0 &mc_virt SLAVE_EBI1 0>;
+			interconnect-names = "cam_ahb",
+					     "cam_hf_mnoc",
+					     "cam_sf_mnoc",
+					     "cam_sf_icp_mnoc";
+
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				port@1 {
+					reg = <1>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				port@2 {
+					reg = <2>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+
+				port@3 {
+					reg = <3>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+				};
+			};
+		};
+
 		camcc: clock-controller@ad00000 {
 			compatible = "qcom,sc8280xp-camcc";
 			reg = <0 0x0ad00000 0 0x20000>;
@@ -4011,6 +4415,28 @@
 			interrupt-controller;
 		};
 
+		tsens2: thermal-sensor@c251000 {
+			compatible = "qcom,sc8280xp-tsens", "qcom,tsens-v2";
+			reg = <0 0x0c251000 0 0x1ff>,
+			      <0 0x0c224000 0 0x8>;
+			#qcom,sensors = <11>;
+			interrupts-extended = <&pdc 122 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 124 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
+		tsens3: thermal-sensor@c252000 {
+			compatible = "qcom,sc8280xp-tsens", "qcom,tsens-v2";
+			reg = <0 0x0c252000 0 0x1ff>,
+			      <0 0x0c225000 0 0x8>;
+			#qcom,sensors = <5>;
+			interrupts-extended = <&pdc 123 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 125 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "uplow", "critical";
+			#thermal-sensor-cells = <1>;
+		};
+
 		tsens0: thermal-sensor@c263000 {
 			compatible = "qcom,sc8280xp-tsens", "qcom,tsens-v2";
 			reg = <0 0x0c263000 0 0x1ff>, /* TM */
@@ -4076,6 +4502,150 @@
 			#interrupt-cells = <2>;
 			gpio-ranges = <&tlmm 0 0 230>;
 			wakeup-parent = <&pdc>;
+
+			cci0_default: cci0-default-state {
+				cci0_i2c0_default: cci0-i2c0-default-pins {
+					/* cci_i2c_sda0, cci_i2c_scl0 */
+					pins = "gpio113", "gpio114";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				cci0_i2c1_default: cci0-i2c1-default-pins {
+					/* cci_i2c_sda1, cci_i2c_scl1 */
+					pins = "gpio115", "gpio116";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			cci0_sleep: cci0-sleep-state {
+				cci0_i2c0_sleep: cci0-i2c0-sleep-pins {
+					/* cci_i2c_sda0, cci_i2c_scl0 */
+					pins = "gpio113", "gpio114";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				cci0_i2c1_sleep: cci0-i2c1-sleep-pins {
+					/* cci_i2c_sda1, cci_i2c_scl1 */
+					pins = "gpio115", "gpio116";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+			};
+
+			cci1_default: cci1-default-state {
+				cci1_i2c0_default: cci1-i2c0-default-pins {
+					/* cci_i2c_sda2, cci_i2c_scl2 */
+					pins = "gpio10","gpio11";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				cci1_i2c1_default: cci1-i2c1-default-pins {
+					/* cci_i2c_sda3, cci_i2c_scl3 */
+					pins = "gpio123","gpio124";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			cci1_sleep: cci1-sleep-state {
+				cci1_i2c0_sleep: cci1-i2c0-sleep-pins {
+					/* cci_i2c_sda2, cci_i2c_scl2 */
+					pins = "gpio10","gpio11";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				cci1_i2c1_sleep: cci1-i2c1-sleep-pins {
+					/* cci_i2c_sda3, cci_i2c_scl3 */
+					pins = "gpio123","gpio124";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+			};
+
+			cci2_default: cci2-default-state {
+				cci2_i2c0_default: cci2-i2c0-default-pins {
+					/* cci_i2c_sda4, cci_i2c_scl4 */
+					pins = "gpio117","gpio118";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				cci2_i2c1_default: cci2-i2c1-default-pins {
+					/* cci_i2c_sda5, cci_i2c_scl5 */
+					pins = "gpio12","gpio13";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			cci2_sleep: cci2-sleep-state {
+				cci2_i2c0_sleep: cci2-i2c0-sleep-pins {
+					/* cci_i2c_sda4, cci_i2c_scl4 */
+					pins = "gpio117","gpio118";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				cci2_i2c1_sleep: cci2-i2c1-sleep-pins {
+					/* cci_i2c_sda5, cci_i2c_scl5 */
+					pins = "gpio12","gpio13";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+			};
+
+			cci3_default: cci3-default-state {
+				cci3_i2c0_default: cci3-i2c0-default-pins {
+					/* cci_i2c_sda6, cci_i2c_scl6 */
+					pins = "gpio145","gpio146";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+
+				cci3_i2c1_default: cci3-i2c1-default-pins {
+					/* cci_i2c_sda7, cci_i2c_scl7 */
+					pins = "gpio164","gpio165";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-up;
+				};
+			};
+
+			cci3_sleep: cci3-sleep-state {
+				cci3_i2c0_sleep: cci3-i2c0-sleep-pins {
+					/* cci_i2c_sda6, cci_i2c_scl6 */
+					pins = "gpio145","gpio146";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+
+				cci3_i2c1_sleep: cci3-i2c1-sleep-pins {
+					/* cci_i2c_sda7, cci_i2c_scl7 */
+					pins = "gpio164","gpio165";
+					function = "cci_i2c";
+					drive-strength = <2>;
+					bias-pull-down;
+				};
+			};
 		};
 
 		apps_smmu: iommu@15000000 {
@@ -5212,6 +5782,21 @@
 			};
 		};
 
+		gpu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens2 2>;
+
+			trips {
+				gpu-crit {
+					temperature = <110000>;
+					hysteresis = <1000>;
+					type = "critical";
+				};
+			};
+		};
+
 		mem-thermal {
 			polling-delay-passive = <250>;
 			polling-delay = <1000>;
diff --git a/arch/arm64/boot/dts/qcom/sda660-inforce-ifc6560.dts b/arch/arm64/boot/dts/qcom/sda660-inforce-ifc6560.dts
index 2ed39d402d3f..702ab49bbc59 100644
--- a/arch/arm64/boot/dts/qcom/sda660-inforce-ifc6560.dts
+++ b/arch/arm64/boot/dts/qcom/sda660-inforce-ifc6560.dts
@@ -461,3 +461,8 @@
 	dr_mode = "peripheral";
 	extcon = <&extcon_usb>;
 };
+
+&usb3_qmpphy {
+	vdda-phy-supply = <&vreg_l1b_0p925>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/qcom/sdm450-motorola-ali.dts b/arch/arm64/boot/dts/qcom/sdm450-motorola-ali.dts
index 362be5719dd2..e27f3c5d5bba 100644
--- a/arch/arm64/boot/dts/qcom/sdm450-motorola-ali.dts
+++ b/arch/arm64/boot/dts/qcom/sdm450-motorola-ali.dts
@@ -4,7 +4,7 @@
  */
 /dts-v1/;
 
-#include "msm8953.dtsi"
+#include "sdm450.dtsi"
 #include "pm8953.dtsi"
 #include "pmi8950.dtsi"
 
diff --git a/arch/arm64/boot/dts/qcom/sdm450.dtsi b/arch/arm64/boot/dts/qcom/sdm450.dtsi
new file mode 100644
index 000000000000..b222aeb459a3
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sdm450.dtsi
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Copyright (c) 2023, Luca Weiss <luca@z3ntu.xyz> */
+
+#include "msm8953.dtsi"
+
+&gpu_opp_table {
+	/delete-node/ opp-650000000;
+
+	opp-600000000 {
+		opp-hz = /bits/ 64 <600000000>;
+		opp-supported-hw = <0xff>;
+		required-opps = <&rpmpd_opp_turbo>;
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/sdm630-sony-xperia-nile.dtsi b/arch/arm64/boot/dts/qcom/sdm630-sony-xperia-nile.dtsi
index 87d0293c728d..819a5f8825e7 100644
--- a/arch/arm64/boot/dts/qcom/sdm630-sony-xperia-nile.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm630-sony-xperia-nile.dtsi
@@ -241,6 +241,16 @@
 	};
 };
 
+&pm660l_wled {
+	status = "okay";
+
+	qcom,switching-freq = <800>;
+	qcom,ovp-millivolt = <29600>;
+	qcom,current-boost-limit = <970>;
+	qcom,current-limit-microamp = <17500>;
+	qcom,num-strings = <2>;
+};
+
 &pon_pwrkey {
 	status = "okay";
 };
@@ -658,10 +668,16 @@
 };
 
 &usb3 {
+	qcom,select-utmi-as-pipe-clk;
+
 	status = "okay";
 };
 
 &usb3_dwc3 {
+	maximum-speed = "high-speed";
+	phys = <&qusb2phy0>;
+	phy-names = "usb2-phy";
+
 	dr_mode = "peripheral";
 	extcon = <&extcon_usb>;
 };
diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi
index 513fe5e76b68..f5921b80ef94 100644
--- a/arch/arm64/boot/dts/qcom/sdm630.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi
@@ -13,6 +13,7 @@
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/thermal/thermal.h>
 #include <dt-bindings/soc/qcom,apr.h>
 
 / {
@@ -1100,6 +1101,7 @@
 			interconnect-names = "gfx-mem";
 
 			operating-points-v2 = <&gpu_sdm630_opp_table>;
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -1281,12 +1283,16 @@
 					  <&gcc GCC_USB30_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <120000000>;
 
-			interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB_30_GDSC>;
-			qcom,select-utmi-as-pipe-clk;
 
 			resets = <&gcc GCC_USB_30_BCR>;
 
@@ -1297,17 +1303,38 @@
 				snps,dis_u2_susphy_quirk;
 				snps,dis_enblslpm_quirk;
 
-				/*
-				 * SDM630 technically supports USB3 but I
-				 * haven't seen any devices making use of it.
-				 */
-				maximum-speed = "high-speed";
-				phys = <&qusb2phy0>;
-				phy-names = "usb2-phy";
+				phys = <&qusb2phy0>, <&usb3_qmpphy>;
+				phy-names = "usb2-phy", "usb3-phy";
 				snps,hird-threshold = /bits/ 8 <0>;
 			};
 		};
 
+		usb3_qmpphy: phy@c010000 {
+			compatible = "qcom,sdm660-qmp-usb3-phy";
+			reg = <0x0c010000 0x1000>;
+
+			clocks = <&gcc GCC_USB3_PHY_AUX_CLK>,
+				 <&gcc GCC_USB3_CLKREF_CLK>,
+				 <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>,
+				 <&gcc GCC_USB3_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "cfg_ahb",
+				      "pipe";
+			clock-output-names = "usb3_phy_pipe_clk_src";
+			#clock-cells = <0>;
+			#phy-cells = <0>;
+
+			resets = <&gcc GCC_USB3_PHY_BCR>,
+				 <&gcc GCC_USB3PHY_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_phy";
+
+			qcom,tcsr-reg = <&tcsr_regs_1 0x6b244>;
+
+			status = "disabled";
+		};
+
 		qusb2phy0: phy@c012000 {
 			compatible = "qcom,sdm660-qusb2-phy";
 			reg = <0x0c012000 0x180>;
@@ -1463,8 +1490,12 @@
 					  <&gcc GCC_USB20_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <60000000>;
 
-			interrupts = <GIC_SPI 348 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq";
+			interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 348 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "hs_phy_irq";
 
 			qcom,select-utmi-as-pipe-clk;
 
@@ -2551,6 +2582,13 @@
 
 			thermal-sensors = <&tsens 8>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert0>;
+					cooling-device = <&adreno_gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				gpu_alert0: trip-point0 {
 					temperature = <90000>;
diff --git a/arch/arm64/boot/dts/qcom/sdm632.dtsi b/arch/arm64/boot/dts/qcom/sdm632.dtsi
index 645b9f6a801f..95b025ea260b 100644
--- a/arch/arm64/boot/dts/qcom/sdm632.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm632.dtsi
@@ -79,3 +79,11 @@
 	compatible = "qcom,kryo250";
 	capacity-dmips-mhz = <1980>;
 };
+
+&gpu_opp_table {
+	opp-725000000 {
+		opp-hz = /bits/ 64 <725000000>;
+		opp-supported-hw = <0xff>;
+		required-opps = <&rpmpd_opp_turbo>;
+	};
+};
diff --git a/arch/arm64/boot/dts/qcom/sdm660-xiaomi-lavender.dts b/arch/arm64/boot/dts/qcom/sdm660-xiaomi-lavender.dts
index 3c47410ba94c..7167f75bced3 100644
--- a/arch/arm64/boot/dts/qcom/sdm660-xiaomi-lavender.dts
+++ b/arch/arm64/boot/dts/qcom/sdm660-xiaomi-lavender.dts
@@ -413,10 +413,16 @@
 };
 
 &usb3 {
+	qcom,select-utmi-as-pipe-clk;
+
 	status = "okay";
 };
 
 &usb3_dwc3 {
+	maximum-speed = "high-speed";
+	phys = <&qusb2phy0>;
+	phy-names = "usb2-phy";
+
 	dr_mode = "peripheral";
 	extcon = <&extcon_usb>;
 };
diff --git a/arch/arm64/boot/dts/qcom/sdm670.dtsi b/arch/arm64/boot/dts/qcom/sdm670.dtsi
index 4d7b77a23159..80e81c4233b3 100644
--- a/arch/arm64/boot/dts/qcom/sdm670.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm670.dtsi
@@ -1320,12 +1320,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
index 0ab5e8f53ac9..e8276db9eabb 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi
@@ -852,6 +852,7 @@ ap_ts_i2c: &i2c14 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&ec_ap_int_l>;
 		spi-max-frequency = <3000000>;
+		wakeup-source;
 
 		cros_ec_pwm: pwm {
 			compatible = "google,cros-ec-pwm";
diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
index ab6220456513..1f517328199b 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
+++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
@@ -580,7 +580,7 @@
 &pcie0 {
 	status = "okay";
 	perst-gpios = <&tlmm 35 GPIO_ACTIVE_LOW>;
-	enable-gpio = <&tlmm 134 GPIO_ACTIVE_HIGH>;
+	wake-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>;
 
 	vddpe-3v3-supply = <&pcie0_3p3v_dual>;
 
diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
index e821103d49c0..46e25c53829a 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi
@@ -508,13 +508,13 @@
 };
 
 &q6afedai {
-	qi2s@22 {
-		reg = <22>;
+	dai@22 {
+		reg = <QUATERNARY_MI2S_RX>;
 		qcom,sd-lines = <1>;
 	};
 
-	qi2s@23 {
-		reg = <23>;
+	dai@23 {
+		reg = <QUATERNARY_MI2S_TX>;
 		qcom,sd-lines = <0>;
 	};
 };
diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts
index fbb8655653fb..486ce175e6bc 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts
+++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts
@@ -60,7 +60,7 @@
 	};
 
 	reserved-memory {
-		framebuffer_region@9d400000 {
+		framebuffer@9d400000 {
 			reg = <0x0 0x9d400000 0x0 (1080 * 2160 * 4)>;
 			no-map;
 		};
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index c2244824355a..2f20be99ee7e 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -2639,10 +2639,12 @@
 			compatible = "qcom,sdm845-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_MEM_CLKREF_CLK>;
 			clock-names = "ref",
-				      "ref_aux";
-			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -3366,8 +3368,8 @@
 
 			qcom,qmp = <&aoss_qmp>;
 
-			power-domains = <&rpmhpd SDM845_CX>,
-					<&rpmhpd SDM845_MX>;
+			power-domains = <&rpmhpd SDM845_LCX>,
+					<&rpmhpd SDM845_LMX>;
 			power-domain-names = "lcx", "lmx";
 
 			memory-region = <&slpi_mem>;
@@ -4058,12 +4060,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc_intc 6 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
@@ -4109,12 +4115,16 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <150000000>;
 
-			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc_intc 7 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_SEC_GDSC>;
 
@@ -4760,6 +4770,7 @@
 			operating-points-v2 = <&gpu_opp_table>;
 
 			qcom,gmu = <&gmu>;
+			#cooling-cells = <2>;
 
 			interconnects = <&mem_noc MASTER_GFX3D 0 &mem_noc SLAVE_EBI1 0>;
 			interconnect-names = "gfx-mem";
@@ -5568,7 +5579,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster0_crit: cluster0_crit {
+				cluster0_crit: cluster0-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -5588,7 +5599,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster1_crit: cluster1_crit {
+				cluster1_crit: cluster1-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -5602,8 +5613,15 @@
 
 			thermal-sensors = <&tsens0 11>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu1_alert0: trip-point0 {
+				gpu_top_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
@@ -5617,8 +5635,15 @@
 
 			thermal-sensors = <&tsens0 12>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu2_alert0: trip-point0 {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/sm4450.dtsi b/arch/arm64/boot/dts/qcom/sm4450.dtsi
index 3e7ae3bebbe0..603c962661cc 100644
--- a/arch/arm64/boot/dts/qcom/sm4450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm4450.dtsi
@@ -17,7 +17,7 @@
 
 	chosen { };
 
-	clocks{
+	clocks {
 		xo_board: xo-board {
 			compatible = "fixed-clock";
 			clock-frequency = <76800000>;
diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi
index 160e098f1075..aca0a87092e4 100644
--- a/arch/arm64/boot/dts/qcom/sm6115.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi
@@ -14,6 +14,7 @@
 #include <dt-bindings/interconnect/qcom,sm6115.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	interrupt-parent = <&intc>;
@@ -614,6 +615,11 @@
 			#hwlock-cells = <1>;
 		};
 
+		tcsr_regs: syscon@3c0000 {
+			compatible = "qcom,sm6115-tcsr", "syscon";
+			reg = <0x0 0x003c0000 0x0 0x40000>;
+		};
+
 		tlmm: pinctrl@500000 {
 			compatible = "qcom,sm6115-tlmm";
 			reg = <0x0 0x00500000 0x0 0x400000>,
@@ -878,8 +884,31 @@
 			clock-output-names = "usb3_phy_pipe_clk_src";
 
 			#phy-cells = <0>;
+			orientation-switch;
+
+			qcom,tcsr-reg = <&tcsr_regs 0xb244>;
 
 			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					usb_qmpphy_out: endpoint {
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					usb_qmpphy_usb_ss_in: endpoint {
+						remote-endpoint = <&usb_dwc3_ss>;
+					};
+				};
+			};
 		};
 
 		system_noc: interconnect@1880000 {
@@ -1194,8 +1223,12 @@
 			compatible = "qcom,sm6115-qmp-ufs-phy";
 			reg = <0x0 0x04807000 0x0 0x1000>;
 
-			clocks = <&gcc GCC_UFS_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
-			clock-names = "ref", "ref_aux";
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_CLKREF_CLK>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -1304,6 +1337,9 @@
 						 &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>,
 						<&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG
 						 &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>;
+				interconnect-names = "qup-core",
+						     "qup-config",
+						     "qup-memory";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -1586,9 +1622,14 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <66666667>;
 
-			interrupts = <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "hs_phy_irq",
+					  "ss_phy_irq";
 
 			resets = <&gcc GCC_USB30_PRIM_BCR>;
 			power-domains = <&gcc GCC_USB30_PRIM_GDSC>;
@@ -1600,7 +1641,6 @@
 			interconnect-names = "usb-ddr",
 					     "apps-usb";
 
-			qcom,select-utmi-as-pipe-clk;
 			status = "disabled";
 
 			usb_dwc3: usb@4e00000 {
@@ -1615,6 +1655,28 @@
 				snps,has-lpm-erratum;
 				snps,hird-threshold = /bits/ 8 <0x10>;
 				snps,usb3_lpm_capable;
+
+				usb-role-switch;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						usb_dwc3_hs: endpoint {
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						usb_dwc3_ss: endpoint {
+							remote-endpoint = <&usb_qmpphy_usb_ss_in>;
+						};
+					};
+				};
 			};
 		};
 
@@ -1646,6 +1708,7 @@
 
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -3085,7 +3148,7 @@
 					type = "passive";
 				};
 
-				cpu4_crit: cpu_crit {
+				cpu4_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3111,7 +3174,7 @@
 					type = "passive";
 				};
 
-				cpu5_crit: cpu_crit {
+				cpu5_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3137,7 +3200,7 @@
 					type = "passive";
 				};
 
-				cpu6_crit: cpu_crit {
+				cpu6_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3163,7 +3226,7 @@
 					type = "passive";
 				};
 
-				cpu7_crit: cpu_crit {
+				cpu7_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3189,7 +3252,7 @@
 					type = "passive";
 				};
 
-				cpu45_crit: cpu_crit {
+				cpu45_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3215,7 +3278,7 @@
 					type = "passive";
 				};
 
-				cpu67_crit: cpu_crit {
+				cpu67_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3241,7 +3304,7 @@
 					type = "passive";
 				};
 
-				cpu0123_crit: cpu_crit {
+				cpu0123_crit: cpu-crit {
 					temperature = <110000>;
 					hysteresis = <1000>;
 					type = "critical";
@@ -3294,8 +3357,15 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens0 15>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				trip-point0 {
+				gpu_alert0: trip-point0 {
 					temperature = <115000>;
 					hysteresis = <5000>;
 					type = "passive";
@@ -3304,7 +3374,7 @@
 				trip-point1 {
 					temperature = <125000>;
 					hysteresis = <1000>;
-					type = "passive";
+					type = "critical";
 				};
 			};
 		};
diff --git a/arch/arm64/boot/dts/qcom/sm6125.dtsi b/arch/arm64/boot/dts/qcom/sm6125.dtsi
index 1dd3a4056e26..98ab08356088 100644
--- a/arch/arm64/boot/dts/qcom/sm6125.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6125.dtsi
@@ -812,10 +812,12 @@
 			compatible = "qcom,sm6125-qmp-ufs-phy";
 			reg = <0x04807000 0xdb8>;
 
-			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+			clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_MEM_CLKREF_CLK>;
 			clock-names = "ref",
-				      "ref_aux";
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -1185,9 +1187,14 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <66666667>;
 
-			interrupts = <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 260 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq";
+			interrupt-names = "pwr_event",
+					  "qusb2_phy",
+					  "hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 			qcom,select-utmi-as-pipe-clk;
diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi
index 43cffe8e1247..24bcec3366ef 100644
--- a/arch/arm64/boot/dts/qcom/sm6350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi
@@ -19,6 +19,7 @@
 #include <dt-bindings/phy/phy-qcom-qmp.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
 #include <dt-bindings/soc/qcom,rpmh-rsc.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	interrupt-parent = <&intc>;
@@ -1189,10 +1190,12 @@
 			compatible = "qcom,sm6350-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_MEM_CLKREF_CLK>;
 			clock-names = "ref",
-				      "ref_aux";
-			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -1325,10 +1328,11 @@
 			qcom,gmu = <&gmu>;
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
-			zap-shader {
+			gpu_zap_shader: zap-shader {
 				memory-region = <&pil_gpu_mem>;
 			};
 
@@ -1439,8 +1443,6 @@
 
 			operating-points-v2 = <&gmu_opp_table>;
 
-			status = "disabled";
-
 			gmu_opp_table: opp-table {
 				compatible = "operating-points-v2";
 
@@ -1830,12 +1832,15 @@
 				      "mock_utmi";
 
 			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
-
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
@@ -1966,6 +1971,13 @@
 			interrupt-controller;
 			#interrupt-cells = <1>;
 
+			interconnects = <&mmss_noc MASTER_MDP_PORT0 QCOM_ICC_TAG_ALWAYS
+					 &clk_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_AMPSS_M0 QCOM_ICC_TAG_ACTIVE_ONLY
+					 &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>;
+			interconnect-names = "mdp0-mem",
+					     "cpu-cfg";
+
 			clocks = <&gcc GCC_DISP_AHB_CLK>,
 				 <&gcc GCC_DISP_AXI_CLK>,
 				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
@@ -2698,6 +2710,569 @@
 		};
 	};
 
+	thermal-zones {
+		aoss0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 0>;
+
+			trips {
+				aoss0-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		aoss1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 0>;
+
+			trips {
+				aoss1-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		audio-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 2>;
+
+			trips {
+				audio-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		camera-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 5>;
+
+			trips {
+				camera-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpu0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 1>;
+
+			trips {
+				cpu0_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu0-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu0_alert0>;
+					cooling-device = <&CPU0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 2>;
+
+			trips {
+				cpu1_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu1-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu1_alert0>;
+					cooling-device = <&CPU1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu2-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 3>;
+
+			trips {
+				cpu2_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu2-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu2_alert0>;
+					cooling-device = <&CPU2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu3-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 4>;
+
+			trips {
+				cpu3_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu3-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu3_alert0>;
+					cooling-device = <&CPU3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu4-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 5>;
+
+			trips {
+				cpu4_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu4-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu4_alert0>;
+					cooling-device = <&CPU4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu5-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 6>;
+
+			trips {
+				cpu5_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu5-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu5_alert0>;
+					cooling-device = <&CPU5 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu6-left-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 9>;
+
+			trips {
+				cpu6_left_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu6-left-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu6_left_alert0>;
+					cooling-device = <&CPU6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu6-right-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 10>;
+
+			trips {
+				cpu6_right_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu6-right-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu6_right_alert0>;
+					cooling-device = <&CPU6 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu7-left-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 11>;
+
+			trips {
+				cpu7_left_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7-left-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu7_left_alert0>;
+					cooling-device = <&CPU7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpu7-right-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 12>;
+
+			trips {
+				cpu7_right_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				cpu7-right-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&cpu7_right_alert0>;
+					cooling-device = <&CPU7 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		cpuss0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 7>;
+
+			trips {
+				cpuss0-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cpuss1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 8>;
+
+			trips {
+				cpuss1-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		cwlan-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 1>;
+
+			trips {
+				cwlan-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		ddr-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 3>;
+
+			trips {
+				ddr-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		gpuss0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 13>;
+
+			trips {
+				gpuss0_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				gpuss0-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&gpuss0_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		gpuss1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens0 14>;
+
+			trips {
+				gpuss1_alert0: trip-point0 {
+					temperature = <95000>;
+					hysteresis = <2000>;
+					type = "passive";
+				};
+
+				gpuss1-crit {
+					temperature = <115000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+
+			cooling-maps {
+				map0 {
+					trip = <&gpuss1_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+		};
+
+		modem-core0-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 6>;
+
+			trips {
+				modem-core0-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem-core1-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 7>;
+
+			trips {
+				modem-core1-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem-scl-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 9>;
+
+			trips {
+				modem-scl-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		modem-vec-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 8>;
+
+			trips {
+				modem-vec-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		npu-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 10>;
+
+			trips {
+				npu-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		q6-hvx-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 4>;
+
+			trips {
+				q6-hvx-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+
+		video-thermal {
+			polling-delay-passive = <0>;
+			polling-delay = <0>;
+
+			thermal-sensors = <&tsens1 11>;
+
+			trips {
+				video-crit {
+					temperature = <125000>;
+					hysteresis = <0>;
+					type = "critical";
+				};
+			};
+		};
+	};
+
 	timer {
 		compatible = "arm,armv8-timer";
 		clock-frequency = <19200000>;
diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi
index 7ac8bf26dda3..4386f8a9c636 100644
--- a/arch/arm64/boot/dts/qcom/sm6375.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi
@@ -1431,13 +1431,15 @@
 			assigned-clock-rates = <19200000>, <133333333>;
 
 			interrupts-extended = <&intc GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
-					      <&mpm 12 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>,
+					      <&mpm 94 IRQ_TYPE_EDGE_BOTH>,
 					      <&mpm 93 IRQ_TYPE_EDGE_BOTH>,
-					      <&mpm 94 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&mpm 12 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
diff --git a/arch/arm64/boot/dts/qcom/sm7125-xiaomi-common.dtsi b/arch/arm64/boot/dts/qcom/sm7125-xiaomi-common.dtsi
index e55cd83c19b8..29289fa41b13 100644
--- a/arch/arm64/boot/dts/qcom/sm7125-xiaomi-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm7125-xiaomi-common.dtsi
@@ -152,6 +152,9 @@
 			regulator-min-microvolt = <824000>;
 			regulator-max-microvolt = <928000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
 		};
 
 		vreg_l5a_2p7: ldo5 {
@@ -188,6 +191,9 @@
 			regulator-min-microvolt = <1696000>;
 			regulator-max-microvolt = <1952000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
 		};
 
 		vreg_l13a_1p8: ldo13 {
@@ -230,6 +236,9 @@
 			regulator-min-microvolt = <2696000>;
 			regulator-max-microvolt = <3304000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
 		};
 	};
 
@@ -258,6 +267,9 @@
 			regulator-min-microvolt = <1144000>;
 			regulator-max-microvolt = <1304000>;
 			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
 		};
 
 		vreg_l4c_1p8: ldo4 {
@@ -398,6 +410,20 @@
 	};
 };
 
+&ufs_mem_hc {
+	vcc-supply = <&vreg_l19a_3p0>;
+	vcc-max-microamp = <600000>;
+	vccq2-supply = <&vreg_l12a_1p8>;
+	vccq2-max-microamp = <600000>;
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l4a_0p88>;
+	vdda-pll-supply = <&vreg_l3c_1p23>;
+	status = "okay";
+};
+
 &usb_1 {
 	qcom,select-utmi-as-pipe-clk;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/qcom/sm7125-xiaomi-curtana.dts b/arch/arm64/boot/dts/qcom/sm7125-xiaomi-curtana.dts
new file mode 100644
index 000000000000..12f517a8492c
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm7125-xiaomi-curtana.dts
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023, Joe Mason <buddyjojo06@outlook.com>
+ */
+
+/dts-v1/;
+
+#include "sm7125-xiaomi-common.dtsi"
+
+/ {
+	model = "Xiaomi Redmi Note 9S";
+	compatible = "xiaomi,curtana", "qcom,sm7125";
+
+	/* required for bootloader to select correct board */
+	qcom,board-id = <0x20022 1>;
+};
diff --git a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts
index ade619805519..bc67e8c1fe4d 100644
--- a/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts
+++ b/arch/arm64/boot/dts/qcom/sm7225-fairphone-fp4.dts
@@ -68,6 +68,14 @@
 		};
 	};
 
+	/* Dummy regulator until PM6150L has LCDB VSP/VSN support */
+	lcdb_dummy: regulator-lcdb-dummy {
+		compatible = "regulator-fixed";
+		regulator-name = "lcdb_dummy";
+		regulator-min-microvolt = <5500000>;
+		regulator-max-microvolt = <5500000>;
+	};
+
 	reserved-memory {
 		/*
 		 * The rmtfs memory region in downstream is 'dynamically allocated'
@@ -116,7 +124,7 @@
 };
 
 &adsp {
-	firmware-name = "qcom/sm7225/fairphone4/adsp.mdt";
+	firmware-name = "qcom/sm7225/fairphone4/adsp.mbn";
 	status = "okay";
 };
 
@@ -361,7 +369,7 @@
 };
 
 &cdsp {
-	firmware-name = "qcom/sm7225/fairphone4/cdsp.mdt";
+	firmware-name = "qcom/sm7225/fairphone4/cdsp.mbn";
 	status = "okay";
 };
 
@@ -373,6 +381,14 @@
 	status = "okay";
 };
 
+&gpu {
+	status = "okay";
+};
+
+&gpu_zap_shader {
+	firmware-name = "qcom/sm7225/fairphone4/a615_zap.mbn";
+};
+
 &i2c0 {
 	clock-frequency = <400000>;
 	status = "okay";
@@ -400,12 +416,49 @@
 &ipa {
 	qcom,gsi-loader = "self";
 	memory-region = <&pil_ipa_fw_mem>;
-	firmware-name = "qcom/sm7225/fairphone4/ipa_fws.mdt";
+	firmware-name = "qcom/sm7225/fairphone4/ipa_fws.mbn";
+	status = "okay";
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dsi0 {
+	vdda-supply = <&vreg_l22a>;
+	status = "okay";
+
+	panel@0 {
+		compatible = "djn,9a-3r063-1102b";
+		reg = <0>;
+
+		backlight = <&pm6150l_wled>;
+		reset-gpios = <&pm6150l_gpios 9 GPIO_ACTIVE_LOW>;
+
+		vdd1-supply = <&vreg_l1e>;
+		vsn-supply = <&lcdb_dummy>;
+		vsp-supply = <&lcdb_dummy>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&mdss_dsi0_out>;
+			};
+		};
+	};
+};
+
+&mdss_dsi0_out {
+	data-lanes = <0 1 2 3>;
+	remote-endpoint = <&panel_in>;
+};
+
+&mdss_dsi0_phy {
+	vdds-supply = <&vreg_l18a>;
 	status = "okay";
 };
 
 &mpss {
-	firmware-name = "qcom/sm7225/fairphone4/modem.mdt";
+	firmware-name = "qcom/sm7225/fairphone4/modem.mbn";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index 761a6757dc26..a35c0852b5a1 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -967,7 +967,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			gpu_speed_bin: gpu_speed_bin@133 {
+			gpu_speed_bin: gpu-speed-bin@133 {
 				reg = <0x133 0x1>;
 				bits = <5 3>;
 			};
@@ -1843,8 +1843,22 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1858,14 +1872,16 @@
 				 <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
 				 <&gcc GCC_PCIE_0_SLV_AXI_CLK>,
 				 <&gcc GCC_PCIE_0_SLV_Q2A_AXI_CLK>,
-				 <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>;
+				 <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>;
 			clock-names = "pipe",
 				      "aux",
 				      "cfg",
 				      "bus_master",
 				      "bus_slave",
 				      "slave_q2a",
-				      "tbu";
+				      "tbu",
+				      "ref";
 
 			iommu-map = <0x0   &apps_smmu 0x1d80 0x1>,
 				    <0x100 &apps_smmu 0x1d81 0x1>;
@@ -1879,7 +1895,7 @@
 			phy-names = "pciephy";
 
 			perst-gpios = <&tlmm 35 GPIO_ACTIVE_HIGH>;
-			enable-gpio = <&tlmm 37 GPIO_ACTIVE_HIGH>;
+			wake-gpios = <&tlmm 37 GPIO_ACTIVE_HIGH>;
 
 			pinctrl-names = "default";
 			pinctrl-0 = <&pcie0_default_state>;
@@ -1934,8 +1950,22 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_EDGE_RISING>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1949,14 +1979,16 @@
 				 <&gcc GCC_PCIE_1_MSTR_AXI_CLK>,
 				 <&gcc GCC_PCIE_1_SLV_AXI_CLK>,
 				 <&gcc GCC_PCIE_1_SLV_Q2A_AXI_CLK>,
-				 <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>;
+				 <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>;
 			clock-names = "pipe",
 				      "aux",
 				      "cfg",
 				      "bus_master",
 				      "bus_slave",
 				      "slave_q2a",
-				      "tbu";
+				      "tbu",
+				      "ref";
 
 			assigned-clocks = <&gcc GCC_PCIE_1_AUX_CLK>;
 			assigned-clock-rates = <19200000>;
@@ -2063,10 +2095,12 @@
 			compatible = "qcom,sm8150-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_MEM_CLKREF_CLK>;
 			clock-names = "ref",
-				      "ref_aux";
-			clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				      "ref_aux",
+				      "qref";
 
 			power-domains = <&gcc UFS_PHY_GDSC>;
 
@@ -2198,6 +2232,7 @@
 
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -2428,7 +2463,7 @@
 				bias-disable;
 			};
 
-			qup_spi6_default: qup-spi6_default-state {
+			qup_spi6_default: qup-spi6-default-state {
 				pins = "gpio4", "gpio5", "gpio6", "gpio7";
 				function = "qup6";
 				drive-strength = <6>;
@@ -2442,7 +2477,7 @@
 				bias-disable;
 			};
 
-			qup_spi7_default: qup-spi7_default-state {
+			qup_spi7_default: qup-spi7-default-state {
 				pins = "gpio98", "gpio99", "gpio100", "gpio101";
 				function = "qup7";
 				drive-strength = <6>;
@@ -3573,12 +3608,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 8 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 9 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 6 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
@@ -3645,12 +3684,16 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 7 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 10 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq", "ss_phy_irq",
-					  "dm_hs_phy_irq", "dp_hs_phy_irq";
+					      <&pdc 7 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_SEC_GDSC>;
 
@@ -5067,7 +5110,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster0_crit: cluster0_crit {
+				cluster0_crit: cluster0-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -5087,7 +5130,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster1_crit: cluster1_crit {
+				cluster1_crit: cluster1-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -5101,8 +5144,15 @@
 
 			thermal-sensors = <&tsens0 15>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu1_alert0: trip-point0 {
+				gpu_top_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
@@ -5281,8 +5331,15 @@
 
 			thermal-sensors = <&tsens1 11>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu2_alert0: trip-point0 {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
index 946365f15a59..6f54f50a70b0 100644
--- a/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250-xiaomi-elish-common.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: BSD-3-Clause
 /*
- * Copyright (c) 2022, 2023 Jianhua Lu <lujianhua000@gmail.com>
+ * Copyright (c) 2022-2024 Jianhua Lu <lujianhua000@gmail.com>
  */
 
 #include <dt-bindings/arm/qcom,ids.h>
@@ -551,6 +551,7 @@
 		vddio-supply = <&vreg_l14a_1p88>;
 		reset-gpios = <&tlmm 75 GPIO_ACTIVE_LOW>;
 		backlight = <&backlight>;
+		rotation = <90>;
 
 		status = "disabled";
 
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 760501c1301a..39bd8f0eba1e 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -975,7 +975,7 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 
-			gpu_speed_bin: gpu_speed_bin@19b {
+			gpu_speed_bin: gpu-speed-bin@19b {
 				reg = <0x19b 0x1>;
 				bits = <5 3>;
 			};
@@ -2152,8 +2152,14 @@
 				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi0", "msi1", "msi2", "msi3",
-					  "msi4", "msi5", "msi6", "msi7";
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2248,8 +2254,22 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2349,8 +2369,22 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x64200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x64300000 0x0 0x64300000 0x0 0x3d00000>;
 
-			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 261 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 262 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 264 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 288 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 289 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 290 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2506,10 +2540,12 @@
 			compatible = "qcom,sm8250-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
-			clock-names = "ref",
-				      "ref_aux";
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_1X_CLKREF_EN>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -2888,6 +2924,7 @@
 
 			nvmem-cells = <&gpu_speed_bin>;
 			nvmem-cell-names = "speed_bin";
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -4128,14 +4165,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 			wakeup-source;
@@ -4197,14 +4236,16 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 16 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 13 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 16 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_SEC_GDSC>;
 			wakeup-source;
@@ -6757,7 +6798,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster0_crit: cluster0_crit {
+				cluster0_crit: cluster0-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -6777,7 +6818,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster1_crit: cluster1_crit {
+				cluster1_crit: cluster1-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -6791,8 +6832,15 @@
 
 			thermal-sensors = <&tsens0 15>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu1_alert0: trip-point0 {
+				gpu_top_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
@@ -6926,8 +6974,15 @@
 
 			thermal-sensors = <&tsens1 8>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu2_alert0: trip-point0 {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <2000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
index e78c83a897c2..a5e7dbbd8c6c 100644
--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
@@ -1526,8 +1526,14 @@
 				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi0", "msi1", "msi2", "msi3",
-					  "msi4", "msi5", "msi6", "msi7";
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1611,8 +1617,22 @@
 			ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
 				 <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1726,10 +1746,12 @@
 			compatible = "qcom,sm8350-qmp-ufs-phy";
 			reg = <0 0x01d87000 0 0x1000>;
 
-			clock-names = "ref",
-				      "ref_aux";
 			clocks = <&rpmhcc RPMH_CXO_CLK>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&gcc GCC_UFS_1_CLKREF_EN>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -1847,6 +1869,7 @@
 			operating-points-v2 = <&gpu_opp_table>;
 
 			qcom,gmu = <&gmu>;
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -2312,14 +2335,16 @@
 					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
@@ -2385,14 +2410,16 @@
 					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
 			assigned-clock-rates = <19200000>, <200000000>;
 
-			interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 16 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts-extended = <&intc GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 13 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 12 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 16 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_SEC_GDSC>;
 
@@ -4165,7 +4192,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster0_crit: cluster0_crit {
+				cluster0_crit: cluster0-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -4185,7 +4212,7 @@
 					hysteresis = <2000>;
 					type = "hot";
 				};
-				cluster1_crit: cluster1_crit {
+				cluster1_crit: cluster1-crit {
 					temperature = <110000>;
 					hysteresis = <2000>;
 					type = "critical";
@@ -4214,8 +4241,15 @@
 
 			thermal-sensors = <&tsens1 1>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu1_alert0: trip-point0 {
+				gpu_top_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <1000>;
 					type = "hot";
@@ -4229,8 +4263,15 @@
 
 			thermal-sensors = <&tsens1 2>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
-				gpu2_alert0: trip-point0 {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <90000>;
 					hysteresis = <1000>;
 					type = "hot";
diff --git a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
index a20d5d76af35..0786cff07b89 100644
--- a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
+++ b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts
@@ -938,8 +938,8 @@
 			"TX DMIC3", "MIC BIAS1",
 			"TX SWR_INPUT0", "ADC1_OUTPUT",
 			"TX SWR_INPUT1", "ADC2_OUTPUT",
-			"TX SWR_INPUT2", "ADC3_OUTPUT",
-			"TX SWR_INPUT3", "ADC4_OUTPUT";
+			"TX SWR_INPUT0", "ADC3_OUTPUT",
+			"TX SWR_INPUT1", "ADC4_OUTPUT";
 
 	wcd-playback-dai-link {
 		link-name = "WCD Playback";
@@ -1147,7 +1147,7 @@
 };
 
 &vamacro {
-	pinctrl-0 = <&dmic01_default>, <&dmic02_default>;
+	pinctrl-0 = <&dmic01_default>, <&dmic23_default>;
 	pinctrl-names = "default";
 	vdd-micb-supply = <&vreg_s10b_1p8>;
 	qcom,dmic-sample-rate = <600000>;
diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi
index 01e4dfc4babd..b86be34a912b 100644
--- a/arch/arm64/boot/dts/qcom/sm8450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi
@@ -1028,6 +1028,12 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&qup_uart20_default>;
 				interrupts = <GIC_SPI 587 IRQ_TYPE_LEVEL_HIGH>;
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				status = "disabled";
 			};
 
@@ -1420,6 +1426,12 @@
 				pinctrl-names = "default";
 				pinctrl-0 = <&qup_uart7_tx>, <&qup_uart7_rx>;
 				interrupts = <GIC_SPI 608 IRQ_TYPE_LEVEL_HIGH>;
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
+						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
+				interconnect-names = "qup-core",
+						     "qup-config";
 				status = "disabled";
 			};
 		};
@@ -1772,8 +1784,22 @@
 			msi-map = <0x0 &gic_its 0x5981 0x1>,
 				  <0x100 &gic_its 0x5980 0x1>;
 			msi-map-mask = <0xff00>;
-			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1881,8 +1907,22 @@
 			msi-map = <0x0 &gic_its 0x5a01 0x1>,
 				  <0x100 &gic_its 0x5a00 0x1>;
 			msi-map-mask = <0xff00>;
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -2038,6 +2078,7 @@
 			operating-points-v2 = <&gpu_opp_table>;
 
 			qcom,gmu = <&gmu>;
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -3934,7 +3975,7 @@
 				};
 			};
 
-			dmic02_default: dmic02-default-state {
+			dmic23_default: dmic23-default-state {
 				clk-pins {
 					pins = "gpio8";
 					function = "dmic2_clk";
@@ -4485,13 +4526,15 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 
@@ -4890,6 +4933,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens0 14>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_top_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -4909,7 +4959,7 @@
 					type = "passive";
 				};
 
-				gpu0_tj_cfg: tj-cfg {
+				gpu_top_alert0: trip-point0 {
 					temperature = <95000>;
 					hysteresis = <5000>;
 					type = "passive";
@@ -4922,6 +4972,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens0 15>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu_bottom_alert0>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -4941,7 +4998,7 @@
 					type = "passive";
 				};
 
-				gpu1_tj_cfg: tj-cfg {
+				gpu_bottom_alert0: trip-point0 {
 					temperature = <95000>;
 					hysteresis = <5000>;
 					type = "passive";
diff --git a/arch/arm64/boot/dts/qcom/sm8550-hdk.dts b/arch/arm64/boot/dts/qcom/sm8550-hdk.dts
new file mode 100644
index 000000000000..12d60a0ee095
--- /dev/null
+++ b/arch/arm64/boot/dts/qcom/sm8550-hdk.dts
@@ -0,0 +1,1306 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Copyright (c) 2024 Linaro Limited
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+#include "sm8550.dtsi"
+#include "pm8010.dtsi"
+#include "pm8550.dtsi"
+#include "pm8550b.dtsi"
+#define PMK8550VE_SID 5
+#include "pm8550ve.dtsi"
+#include "pm8550vs.dtsi"
+#include "pmk8550.dtsi"
+#include "pmr735d_a.dtsi"
+
+/ {
+	model = "Qualcomm Technologies, Inc. SM8550 HDK";
+	compatible = "qcom,sm8550-hdk", "qcom,sm8550";
+	chassis-type = "embedded";
+
+	aliases {
+		serial0 = &uart7;
+		serial1 = &uart14;
+	};
+
+	wcd938x: audio-codec {
+		compatible = "qcom,wcd9385-codec";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&wcd_default>;
+
+		qcom,micbias1-microvolt = <1800000>;
+		qcom,micbias2-microvolt = <1800000>;
+		qcom,micbias3-microvolt = <1800000>;
+		qcom,micbias4-microvolt = <1800000>;
+		qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>;
+		qcom,mbhc-headset-vthreshold-microvolt = <1700000>;
+		qcom,mbhc-headphone-vthreshold-microvolt = <50000>;
+		qcom,rx-device = <&wcd_rx>;
+		qcom,tx-device = <&wcd_tx>;
+
+		reset-gpios = <&tlmm 108 GPIO_ACTIVE_LOW>;
+
+		vdd-buck-supply = <&vreg_l15b_1p8>;
+		vdd-rxtx-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l15b_1p8>;
+		vdd-mic-bias-supply = <&vreg_bob1>;
+
+		#sound-dai-cells = <1>;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
+	hdmi-out {
+		compatible = "hdmi-connector";
+		type = "a";
+
+		port {
+			hdmi_connector_out: endpoint {
+				remote-endpoint = <&lt9611_out>;
+			};
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&volume_up_n>;
+		pinctrl-names = "default";
+
+		key-volume-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			gpios = <&pm8550_gpios 6 GPIO_ACTIVE_LOW>;
+			debounce-interval = <15>;
+			linux,can-disable;
+			wakeup-source;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-0 {
+			function = LED_FUNCTION_BLUETOOTH;
+			color = <LED_COLOR_ID_BLUE>;
+			gpios = <&tlmm 159 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "bluetooth-power";
+			default-state = "off";
+		};
+
+		led-1 {
+			function = LED_FUNCTION_INDICATOR;
+			color = <LED_COLOR_ID_GREEN>;
+			gpios = <&tlmm 160 GPIO_ACTIVE_HIGH>;
+			default-state = "off";
+			panic-indicator;
+		};
+
+		led-2 {
+			function = LED_FUNCTION_WLAN;
+			color = <LED_COLOR_ID_ORANGE>;
+			gpios = <&tlmm 162 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "phy0tx";
+			default-state = "off";
+		};
+	};
+
+	pmic-glink {
+		compatible = "qcom,sm8550-pmic-glink", "qcom,pmic-glink";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		orientation-gpios = <&tlmm 11 GPIO_ACTIVE_HIGH>;
+
+		connector@0 {
+			compatible = "usb-c-connector";
+			reg = <0>;
+			power-role = "dual";
+			data-role = "dual";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+
+					pmic_glink_hs_in: endpoint {
+						remote-endpoint = <&usb_1_dwc3_hs>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+
+					pmic_glink_ss_in: endpoint {
+						remote-endpoint = <&usb_dp_qmpphy_out>;
+					};
+				};
+
+				port@2 {
+					reg = <2>;
+
+					pmic_glink_sbu: endpoint {
+						remote-endpoint = <&fsa4480_sbu_mux>;
+					};
+				};
+			};
+		};
+	};
+
+	lt9611_1v2: regulator-lt9611-1v2 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "LT9611_1V2";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+
+		vin-supply = <&vph_pwr>;
+		gpio = <&tlmm 152 GPIO_ACTIVE_HIGH>;
+
+		enable-active-high;
+	};
+
+	lt9611_3v3: regulator-lt9611-3v3 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "LT9611_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		vin-supply = <&vreg_bob_3v3>;
+		gpio = <&tlmm 6 GPIO_ACTIVE_HIGH>;
+
+		enable-active-high;
+	};
+
+	vph_pwr: regulator-vph-pwr {
+		compatible = "regulator-fixed";
+
+		regulator-name = "vph_pwr";
+		regulator-min-microvolt = <3700000>;
+		regulator-max-microvolt = <3700000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vreg_bob_3v3: regulator-vreg-bob-3v3 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "VREG_BOB_3P3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		vin-supply = <&vph_pwr>;
+	};
+
+	sound {
+		compatible = "qcom,sm8550-sndcard", "qcom,sm8450-sndcard";
+		model = "SM8550-HDK";
+		audio-routing = "SpkrLeft IN", "WSA_SPK1 OUT",
+				"SpkrRight IN", "WSA_SPK2 OUT",
+				"IN1_HPHL", "HPHL_OUT",
+				"IN2_HPHR", "HPHR_OUT",
+				"AMIC1", "MIC BIAS1",
+				"AMIC2", "MIC BIAS2",
+				"AMIC5", "MIC BIAS4",
+				"TX SWR_INPUT0", "ADC1_OUTPUT",
+				"TX SWR_INPUT1", "ADC2_OUTPUT",
+				"TX SWR_INPUT1", "ADC4_OUTPUT";
+
+		wcd-playback-dai-link {
+			link-name = "WCD Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wcd-capture-dai-link {
+			link-name = "WCD Capture";
+
+			cpu {
+				sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>;
+			};
+
+			codec {
+				sound-dai = <&wcd938x 1>, <&swr2 0>, <&lpass_txmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wsa-dai-link {
+			link-name = "WSA Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&north_spkr>, <&south_spkr>, <&swr0 0>, <&lpass_wsamacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		va-dai-link {
+			link-name = "VA Capture";
+
+			cpu {
+				sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>;
+			};
+
+			codec {
+				sound-dai = <&lpass_vamacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+	};
+};
+
+&apps_rsc {
+	regulators-0 {
+		compatible = "qcom,pm8550-rpmh-regulators";
+
+		vdd-bob1-supply = <&vph_pwr>;
+		vdd-bob2-supply = <&vph_pwr>;
+		vdd-l1-l4-l10-supply = <&vreg_s6g_1p86>;
+		vdd-l2-l13-l14-supply = <&vreg_bob1>;
+		vdd-l3-supply = <&vreg_s4g_1p25>;
+		vdd-l5-l16-supply = <&vreg_bob1>;
+		vdd-l6-l7-supply = <&vreg_bob1>;
+		vdd-l8-l9-supply = <&vreg_bob1>;
+		vdd-l11-supply = <&vreg_s4g_1p25>;
+		vdd-l12-supply = <&vreg_s6g_1p86>;
+		vdd-l15-supply = <&vreg_s6g_1p86>;
+		vdd-l17-supply = <&vreg_bob2>;
+
+		qcom,pmic-id = "b";
+
+		vreg_bob1: bob1 {
+			regulator-name = "vreg_bob1";
+			regulator-min-microvolt = <3296000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_bob2: bob2 {
+			regulator-name = "vreg_bob2";
+			regulator-min-microvolt = <2720000>;
+			regulator-max-microvolt = <3960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1b_1p8: ldo1 {
+			regulator-name = "vreg_l1b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2b_3p0: ldo2 {
+			regulator-name = "vreg_l2b_3p0";
+			regulator-min-microvolt = <3008000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5b_3p1: ldo5 {
+			regulator-name = "vreg_l5b_3p1";
+			regulator-min-microvolt = <3104000>;
+			regulator-max-microvolt = <3104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6b_1p8: ldo6 {
+			regulator-name = "vreg_l6b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7b_1p8: ldo7 {
+			regulator-name = "vreg_l7b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l8b_1p8: ldo8 {
+			regulator-name = "vreg_l8b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l9b_2p9: ldo9 {
+			regulator-name = "vreg_l9b_2p9";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <3008000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l11b_1p2: ldo11 {
+			regulator-name = "vreg_l11b_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l12b_1p8: ldo12 {
+			regulator-name = "vreg_l12b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l13b_3p0: ldo13 {
+			regulator-name = "vreg_l13b_3p0";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l14b_3p2: ldo14 {
+			regulator-name = "vreg_l14b_3p2";
+			regulator-min-microvolt = <3200000>;
+			regulator-max-microvolt = <3200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l15b_1p8: ldo15 {
+			regulator-name = "vreg_l15b_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l16b_2p8: ldo16 {
+			regulator-name = "vreg_l16b_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l17b_2p5: ldo17 {
+			regulator-name = "vreg_l17b_2p5";
+			regulator-min-microvolt = <2504000>;
+			regulator-max-microvolt = <2504000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-1 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s4g_1p25>;
+		vdd-l2-supply = <&vreg_s4e_0p95>;
+		vdd-l3-supply = <&vreg_s4e_0p95>;
+
+		qcom,pmic-id = "c";
+
+		vreg_l3c_0p9: ldo3 {
+			regulator-name = "vreg_l3c_0p9";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-2 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s4e_0p95>;
+		vdd-l2-supply = <&vreg_s4e_0p95>;
+		vdd-l3-supply = <&vreg_s4e_0p95>;
+
+		qcom,pmic-id = "d";
+
+		vreg_l1d_0p88: ldo1 {
+			regulator-name = "vreg_l1d_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <920000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		/* ldo2 supplies SM8550 VDD_LPI_MX */
+	};
+
+	regulators-3 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s4e_0p95>;
+		vdd-l2-supply = <&vreg_s4e_0p95>;
+		vdd-l3-supply = <&vreg_s4g_1p25>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "e";
+
+		vreg_s4e_0p95: smps4 {
+			regulator-name = "vreg_s4e_0p95";
+			regulator-min-microvolt = <904000>;
+			regulator-max-microvolt = <984000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s5e_1p08: smps5 {
+			regulator-name = "vreg_s5e_1p08";
+			regulator-min-microvolt = <1080000>;
+			regulator-max-microvolt = <1120000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1e_0p88: ldo1 {
+			regulator-name = "vreg_l1e_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <880000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2e_0p9: ldo2 {
+			regulator-name = "vreg_l2e_0p9";
+			regulator-min-microvolt = <904000>;
+			regulator-max-microvolt = <970000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3e_1p2: ldo3 {
+			regulator-name = "vreg_l3e_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-4 {
+		compatible = "qcom,pm8550ve-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s4e_0p95>;
+		vdd-l2-supply = <&vreg_s4e_0p95>;
+		vdd-l3-supply = <&vreg_s4e_0p95>;
+		vdd-s4-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "f";
+
+		vreg_s4f_0p5: smps4 {
+			regulator-name = "vreg_s4f_0p5";
+			regulator-min-microvolt = <500000>;
+			regulator-max-microvolt = <700000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1f_0p9: ldo1 {
+			regulator-name = "vreg_l1f_0p9";
+			regulator-min-microvolt = <912000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2f_0p88: ldo2 {
+			regulator-name = "vreg_l2f_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3f_0p88: ldo3 {
+			regulator-name = "vreg_l3f_0p88";
+			regulator-min-microvolt = <880000>;
+			regulator-max-microvolt = <912000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-5 {
+		compatible = "qcom,pm8550vs-rpmh-regulators";
+
+		vdd-l1-supply = <&vreg_s4g_1p25>;
+		vdd-l2-supply = <&vreg_s4g_1p25>;
+		vdd-l3-supply = <&vreg_s4g_1p25>;
+		vdd-s1-supply = <&vph_pwr>;
+		vdd-s2-supply = <&vph_pwr>;
+		vdd-s3-supply = <&vph_pwr>;
+		vdd-s4-supply = <&vph_pwr>;
+		vdd-s5-supply = <&vph_pwr>;
+		vdd-s6-supply = <&vph_pwr>;
+
+		qcom,pmic-id = "g";
+
+		vreg_s1g_1p25: smps1 {
+			regulator-name = "vreg_s1g_1p25";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s2g_0p85: smps2 {
+			regulator-name = "vreg_s2g_0p85";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s3g_0p8: smps3 {
+			regulator-name = "vreg_s3g_0p8";
+			regulator-min-microvolt = <300000>;
+			regulator-max-microvolt = <1004000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s4g_1p25: smps4 {
+			regulator-name = "vreg_s4g_1p25";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1352000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s5g_0p85: smps5 {
+			regulator-name = "vreg_s5g_0p85";
+			regulator-min-microvolt = <500000>;
+			regulator-max-microvolt = <1004000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_s6g_1p86: smps6 {
+			regulator-name = "vreg_s6g_1p86";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l1g_1p2: ldo1 {
+			regulator-name = "vreg_l1g_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3g_1p2: ldo3 {
+			regulator-name = "vreg_l3g_1p2";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-6 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p25>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p86>;
+		vdd-l6-supply = <&vreg_s6g_1p86>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		qcom,pmic-id = "m";
+
+		vreg_l1m_1p056: ldo1 {
+			regulator-name = "vreg_l1m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2m_1p056: ldo2 {
+			regulator-name = "vreg_l2m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3m_2p8: ldo3 {
+			regulator-name = "vreg_l3m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4m_2p8: ldo4 {
+			regulator-name = "vreg_l4m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5m_1p8: ldo5 {
+			regulator-name = "vreg_l5m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6m_1p8: ldo6 {
+			regulator-name = "vreg_l6m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7m_2p9: ldo7 {
+			regulator-name = "vreg_l7m_2p9";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2904000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+
+		vdd-l1-l2-supply = <&vreg_s4g_1p25>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6g_1p86>;
+		vdd-l6-supply = <&vreg_bob1>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		qcom,pmic-id = "n";
+
+		vreg_l1n_1p1: ldo1 {
+			regulator-name = "vreg_l1n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2n_1p1: ldo2 {
+			regulator-name = "vreg_l2n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3n_2p8: ldo3 {
+			regulator-name = "vreg_l3n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3000000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4n_2p8: ldo4 {
+			regulator-name = "vreg_l4n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5n_1p8: ldo5 {
+			regulator-name = "vreg_l5n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6n_3p3: ldo6 {
+			regulator-name = "vreg_l6n_3p3";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7n_2p96: ldo7 {
+			regulator-name = "vreg_l7n_2p96";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	lt9611_codec: hdmi-bridge@2b {
+		compatible = "lontium,lt9611uxc";
+		reg = <0x2b>;
+
+		interrupts-extended = <&tlmm 8 IRQ_TYPE_EDGE_FALLING>;
+
+		reset-gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
+
+		vdd-supply = <&lt9611_1v2>;
+		vcc-supply = <&lt9611_3v3>;
+
+		pinctrl-0 = <&lt9611_irq_pin>, <&lt9611_rst_pin>;
+		pinctrl-names = "default";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lt9611_a: endpoint {
+					remote-endpoint = <&mdss_dsi0_out>;
+				};
+			};
+
+			port@2 {
+				reg = <2>;
+
+				lt9611_out: endpoint {
+					remote-endpoint = <&hdmi_connector_out>;
+				};
+			};
+		};
+	};
+};
+
+&i2c_hub_2 {
+	status = "okay";
+
+	typec-mux@42 {
+		compatible = "fcs,fsa4480";
+		reg = <0x42>;
+
+		vcc-supply = <&vreg_bob1>;
+
+		mode-switch;
+		orientation-switch;
+
+		port {
+			fsa4480_sbu_mux: endpoint {
+				remote-endpoint = <&pmic_glink_sbu>;
+			};
+		};
+	};
+};
+
+&i2c_master_hub_0 {
+	status = "okay";
+};
+
+&ipa {
+	qcom,gsi-loader = "self";
+	memory-region = <&ipa_fw_mem>;
+	firmware-name = "qcom/sm8550/ipa_fws.mbn";
+	status = "okay";
+};
+
+&gpi_dma1 {
+	status = "okay";
+};
+
+&gpu {
+	status = "okay";
+
+	zap-shader {
+		firmware-name = "qcom/sm8550/a740_zap.mbn";
+	};
+};
+
+&lpass_tlmm {
+	spkr_1_sd_n_active: spkr-1-sd-n-active-state {
+		pins = "gpio17";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+
+	spkr_2_sd_n_active: spkr-2-sd-n-active-state {
+		pins = "gpio18";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dsi0 {
+	vdda-supply = <&vreg_l3e_1p2>;
+	status = "okay";
+};
+
+&mdss_dsi0_out {
+	remote-endpoint = <&lt9611_a>;
+	data-lanes = <0 1 2 3>;
+};
+
+&mdss_dsi0_phy {
+	vdds-supply = <&vreg_l1e_0p88>;
+	status = "okay";
+};
+
+&mdss_dp0 {
+	status = "okay";
+};
+
+&mdss_dp0_out {
+	remote-endpoint = <&usb_dp_qmpphy_dp_in>;
+	data-lanes = <0 1>;
+};
+
+&pcie0 {
+	wake-gpios = <&tlmm 96 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 94 GPIO_ACTIVE_LOW>;
+
+	pinctrl-0 = <&pcie0_default_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&pcie0_phy {
+	vdda-phy-supply = <&vreg_l1e_0p88>;
+	vdda-pll-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&pcie1 {
+	wake-gpios = <&tlmm 99 GPIO_ACTIVE_HIGH>;
+	perst-gpios = <&tlmm 97 GPIO_ACTIVE_LOW>;
+
+	pinctrl-0 = <&pcie1_default_state>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&pcie1_phy {
+	vdda-phy-supply = <&vreg_l3c_0p9>;
+	vdda-pll-supply = <&vreg_l3e_1p2>;
+	vdda-qref-supply = <&vreg_l1e_0p88>;
+
+	status = "okay";
+};
+
+&pcie_1_phy_aux_clk {
+	clock-frequency = <1000>;
+};
+
+&pm8550_gpios {
+	sdc2_card_det_n: sdc2-card-det-state {
+		pins = "gpio12";
+		function = "normal";
+		input-enable;
+		output-disable;
+		bias-pull-up;
+		power-source = <1>; /* 1.8 V */
+	};
+
+	volume_up_n: volume-up-n-state {
+		pins = "gpio6";
+		function = "normal";
+		power-source = <1>;
+		bias-pull-up;
+		input-enable;
+	};
+};
+
+/* The RGB signals are routed to 3 separate LEDs on the HDK8550 */
+&pm8550_pwm {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	status = "okay";
+
+	led@1 {
+		reg = <1>;
+		function = LED_FUNCTION_STATUS;
+		color = <LED_COLOR_ID_RED>;
+		default-state = "off";
+	};
+
+	led@2 {
+		reg = <2>;
+		function = LED_FUNCTION_STATUS;
+		color = <LED_COLOR_ID_GREEN>;
+		default-state = "off";
+	};
+
+	led@3 {
+		reg = <3>;
+		function = LED_FUNCTION_STATUS;
+		color = <LED_COLOR_ID_BLUE>;
+		default-state = "off";
+	};
+};
+
+&pm8550b_eusb2_repeater {
+	vdd18-supply = <&vreg_l15b_1p8>;
+	vdd3-supply = <&vreg_l5b_3p1>;
+};
+
+&pon_pwrkey {
+	status = "okay";
+};
+
+&pon_resin {
+	linux,code = <KEY_VOLUMEDOWN>;
+
+	status = "okay";
+};
+
+&qupv3_id_0 {
+	status = "okay";
+};
+
+&qupv3_id_1 {
+	status = "okay";
+};
+
+&remoteproc_adsp {
+	firmware-name = "qcom/sm8550/adsp.mbn",
+			"qcom/sm8550/adsp_dtb.mbn";
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/sm8550/cdsp.mbn",
+			"qcom/sm8550/cdsp_dtb.mbn";
+	status = "okay";
+};
+
+&remoteproc_mpss {
+	firmware-name = "qcom/sm8550/modem.mbn",
+			"qcom/sm8550/modem_dtb.mbn";
+	status = "okay";
+};
+
+&sdhc_2 {
+	cd-gpios = <&pm8550_gpios 12 GPIO_ACTIVE_HIGH>;
+
+	pinctrl-0 = <&sdc2_default>, <&sdc2_card_det_n>;
+	pinctrl-1 = <&sdc2_sleep>, <&sdc2_card_det_n>;
+	pinctrl-names = "default", "sleep";
+
+	vmmc-supply = <&vreg_l9b_2p9>;
+	vqmmc-supply = <&vreg_l8b_1p8>;
+
+	bus-width = <4>;
+	no-sdio;
+	no-mmc;
+
+	status = "okay";
+};
+
+&sleep_clk {
+	clock-frequency = <32000>;
+};
+
+&swr0 {
+	status = "okay";
+
+	/* WSA8845, Speaker North */
+	north_spkr: speaker@0,0 {
+		compatible = "sdw20217020400";
+		reg = <0 0>;
+
+		pinctrl-0 = <&spkr_1_sd_n_active>;
+		pinctrl-names = "default";
+
+		powerdown-gpios = <&lpass_tlmm 17 GPIO_ACTIVE_LOW>;
+
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l15b_1p8>;
+
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrLeft";
+	};
+
+	/* WSA8845, Speaker South */
+	south_spkr: speaker@0,1 {
+		compatible = "sdw20217020400";
+		reg = <0 1>;
+
+		pinctrl-0 = <&spkr_2_sd_n_active>;
+		pinctrl-names = "default";
+
+		powerdown-gpios = <&lpass_tlmm 18 GPIO_ACTIVE_LOW>;
+
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l15b_1p8>;
+
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrRight";
+	};
+};
+
+&swr1 {
+	status = "okay";
+
+	/* WCD9385 RX */
+	wcd_rx: codec@0,4 {
+		compatible = "sdw20217010d00";
+		reg = <0 4>;
+
+		/*
+		 * WCD9385 RX Port 1 (HPH_L/R)      <=> SWR1 Port 1 (HPH_L/R)
+		 * WCD9385 RX Port 2 (CLSH)         <=> SWR1 Port 2 (CLSH)
+		 * WCD9385 RX Port 3 (COMP_L/R)     <=> SWR1 Port 3 (COMP_L/R)
+		 * WCD9385 RX Port 4 (LO)           <=> SWR1 Port 4 (LO)
+		 * WCD9385 RX Port 5 (DSD_L/R)      <=> SWR1 Port 5 (DSD_L/R)
+		 */
+		qcom,rx-port-mapping = <1 2 3 4 5>;
+	};
+};
+
+&swr2 {
+	status = "okay";
+
+	/* WCD9385 TX */
+	wcd_tx: codec@0,3 {
+		compatible = "sdw20217010d00";
+		reg = <0 3>;
+
+		/*
+		 * WCD9385 TX Port 1 (ADC1,2)             <=> SWR2 Port 2 (TX SWR_INPUT 0,1,2,3)
+		 * WCD9385 TX Port 2 (ADC3,4)             <=> SWR2 Port 2 (TX SWR_INPUT 0,1,2,3)
+		 * WCD9385 TX Port 3 (DMIC0,1,2,3 & MBHC) <=> SWR2 Port 3 (TX SWR_INPUT 4,5,6,7)
+		 * WCD9385 TX Port 4 (DMIC4,5,6,7)        <=> SWR2 Port 4 (TX SWR_INPUT 8,9,10,11)
+		 */
+		qcom,tx-port-mapping = <2 2 3 4>;
+	};
+};
+
+&tlmm {
+	/* Reserved I/Os for NFC */
+	gpio-reserved-ranges = <32 8>;
+
+	bt_default: bt-default-state {
+		bt-en-pins {
+			pins = "gpio81";
+			function = "gpio";
+			drive-strength = <16>;
+			bias-disable;
+		};
+
+		sw-ctrl-pins {
+			pins = "gpio82";
+			function = "gpio";
+			bias-pull-down;
+		};
+	};
+
+	lt9611_irq_pin: lt9611-irq-state {
+		pins = "gpio8";
+		function = "gpio";
+		bias-disable;
+	};
+
+	lt9611_rst_pin: lt9611-rst-state {
+		pins = "gpio7";
+		function = "gpio";
+		output-high;
+	};
+
+	wcd_default: wcd-reset-n-active-state {
+		pins = "gpio108";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
+&uart7 {
+	status = "okay";
+};
+
+&uart14 {
+	status = "okay";
+
+	bluetooth {
+		compatible = "qcom,wcn7850-bt";
+
+		vddio-supply = <&vreg_l15b_1p8>;
+		vddaon-supply = <&vreg_s4e_0p95>;
+		vdddig-supply = <&vreg_s4e_0p95>;
+		vddrfa0p8-supply = <&vreg_s4e_0p95>;
+		vddrfa1p2-supply = <&vreg_s4g_1p25>;
+		vddrfa1p9-supply = <&vreg_s6g_1p86>;
+
+		max-speed = <3200000>;
+
+		enable-gpios = <&tlmm 81 GPIO_ACTIVE_HIGH>;
+		swctrl-gpios = <&tlmm 82 GPIO_ACTIVE_HIGH>;
+
+		pinctrl-0 = <&bt_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&ufs_mem_hc {
+	reset-gpios = <&tlmm 210 GPIO_ACTIVE_LOW>;
+
+	vcc-supply = <&vreg_l17b_2p5>;
+	vcc-max-microamp = <1300000>;
+	vccq-supply = <&vreg_l1g_1p2>;
+	vccq-max-microamp = <1200000>;
+	vdd-hba-supply = <&vreg_l3g_1p2>;
+
+	status = "okay";
+};
+
+&ufs_mem_phy {
+	vdda-phy-supply = <&vreg_l1d_0p88>;
+	vdda-pll-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1 {
+	status = "okay";
+};
+
+&usb_1_dwc3 {
+	dr_mode = "otg";
+	usb-role-switch;
+};
+
+&usb_1_dwc3_hs {
+	remote-endpoint = <&pmic_glink_hs_in>;
+};
+
+&usb_1_dwc3_ss {
+	remote-endpoint = <&usb_dp_qmpphy_usb_ss_in>;
+};
+
+&usb_1_hsphy {
+	vdd-supply = <&vreg_l1e_0p88>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	phys = <&pm8550b_eusb2_repeater>;
+
+	status = "okay";
+};
+
+&usb_dp_qmpphy {
+	vdda-phy-supply = <&vreg_l3e_1p2>;
+	vdda-pll-supply = <&vreg_l3f_0p88>;
+
+	orientation-switch;
+
+	status = "okay";
+};
+
+&usb_dp_qmpphy_dp_in {
+	remote-endpoint = <&mdss_dp0_out>;
+};
+
+&usb_dp_qmpphy_out {
+	remote-endpoint = <&pmic_glink_ss_in>;
+};
+
+&usb_dp_qmpphy_usb_ss_in {
+	remote-endpoint = <&usb_1_dwc3_ss>;
+};
+
+&xo_board {
+	clock-frequency = <76800000>;
+};
diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
index c1135ad5fa69..3d4ad5aac70f 100644
--- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
+++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts
@@ -106,14 +106,21 @@
 				"SpkrRight IN", "WSA_SPK2 OUT",
 				"IN1_HPHL", "HPHL_OUT",
 				"IN2_HPHR", "HPHR_OUT",
+				"AMIC1", "MIC BIAS1",
 				"AMIC2", "MIC BIAS2",
+				"AMIC3", "MIC BIAS3",
+				"AMIC4", "MIC BIAS3",
+				"AMIC5", "MIC BIAS4",
 				"VA DMIC0", "MIC BIAS1",
 				"VA DMIC1", "MIC BIAS1",
 				"VA DMIC2", "MIC BIAS3",
 				"TX DMIC0", "MIC BIAS1",
 				"TX DMIC1", "MIC BIAS2",
 				"TX DMIC2", "MIC BIAS3",
-				"TX SWR_ADC1", "ADC2_OUTPUT";
+				"TX SWR_INPUT0", "ADC1_OUTPUT",
+				"TX SWR_INPUT1", "ADC2_OUTPUT",
+				"TX SWR_INPUT0", "ADC3_OUTPUT",
+				"TX SWR_INPUT1", "ADC4_OUTPUT";
 
 		wcd-playback-dai-link {
 			link-name = "WCD Playback";
@@ -874,7 +881,7 @@
 	wcd_tx: codec@0,3 {
 		compatible = "sdw20217010d00";
 		reg = <0 3>;
-		qcom,tx-port-mapping = <1 1 2 3>;
+		qcom,tx-port-mapping = <2 2 3 4>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
index d401d63e5c4d..92f015017418 100644
--- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
+++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts
@@ -124,14 +124,21 @@
 				"SpkrRight IN", "WSA_SPK2 OUT",
 				"IN1_HPHL", "HPHL_OUT",
 				"IN2_HPHR", "HPHR_OUT",
+				"AMIC1", "MIC BIAS1",
 				"AMIC2", "MIC BIAS2",
+				"AMIC3", "MIC BIAS3",
+				"AMIC4", "MIC BIAS3",
+				"AMIC5", "MIC BIAS4",
 				"VA DMIC0", "MIC BIAS1",
 				"VA DMIC1", "MIC BIAS1",
 				"VA DMIC2", "MIC BIAS3",
 				"TX DMIC0", "MIC BIAS1",
 				"TX DMIC1", "MIC BIAS2",
 				"TX DMIC2", "MIC BIAS3",
-				"TX SWR_ADC1", "ADC2_OUTPUT";
+				"TX SWR_INPUT0", "ADC1_OUTPUT",
+				"TX SWR_INPUT1", "ADC2_OUTPUT",
+				"TX SWR_INPUT0", "ADC3_OUTPUT",
+				"TX SWR_INPUT1", "ADC4_OUTPUT";
 
 		wcd-playback-dai-link {
 			link-name = "WCD Playback";
@@ -724,6 +731,10 @@
 		 <&usb_dp_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
 };
 
+&gpi_dma1 {
+	status = "okay";
+};
+
 &gpu {
 	status = "okay";
 
@@ -960,6 +971,30 @@
 	};
 };
 
+&spi4 {
+	status = "okay";
+
+	touchscreen@0 {
+		compatible = "goodix,gt9916";
+		reg = <0>;
+
+		interrupt-parent = <&tlmm>;
+		interrupts = <25 IRQ_TYPE_LEVEL_LOW>;
+
+		reset-gpios = <&tlmm 24 GPIO_ACTIVE_LOW>;
+
+		avdd-supply = <&vreg_l14b_3p2>;
+
+		spi-max-frequency = <1000000>;
+
+		touchscreen-size-x = <1080>;
+		touchscreen-size-y = <2400>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&ts_irq>, <&ts_reset>;
+	};
+};
+
 &swr1 {
 	status = "okay";
 
@@ -978,7 +1013,7 @@
 	wcd_tx: codec@0,3 {
 		compatible = "sdw20217010d00";
 		reg = <0 3>;
-		qcom,tx-port-mapping = <1 1 2 3>;
+		qcom,tx-port-mapping = <2 2 3 4>;
 	};
 };
 
@@ -1028,6 +1063,20 @@
 		bias-pull-down;
 	};
 
+	ts_irq: ts-irq-state {
+		pins = "gpio25";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+
+	ts_reset: ts-reset-state {
+		pins = "gpio24";
+		function = "gpio";
+		drive-strength = <8>;
+		bias-pull-up;
+	};
+
 	wcd_default: wcd-reset-n-active-state {
 		pins = "gpio108";
 		function = "gpio";
diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi
index ee1ba5a8c8fc..3904348075f6 100644
--- a/arch/arm64/boot/dts/qcom/sm8550.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi
@@ -1713,9 +1713,22 @@
 			linux,pci-domain = <0>;
 			num-lanes = <2>;
 
-			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
-
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1742,6 +1755,9 @@
 					<&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_0 0>;
 			interconnect-names = "pcie-mem", "cpu-pcie";
 
+			/* Entries are reversed due to the unusual ITS DeviceID encoding */
+			msi-map = <0x0 &gic_its 0x1401 0x1>,
+				  <0x100 &gic_its 0x1400 0x1>;
 			iommu-map = <0x0   &apps_smmu 0x1400 0x1>,
 				    <0x100 &apps_smmu 0x1401 0x1>;
 
@@ -1804,9 +1820,22 @@
 			linux,pci-domain = <1>;
 			num-lanes = <2>;
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
-
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
 			interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
@@ -1838,6 +1867,9 @@
 					<&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_1 0>;
 			interconnect-names = "pcie-mem", "cpu-pcie";
 
+			/* Entries are reversed due to the unusual ITS DeviceID encoding */
+			msi-map = <0x0 &gic_its 0x1481 0x1>,
+				  <0x100 &gic_its 0x1480 0x1>;
 			iommu-map = <0x0   &apps_smmu 0x1480 0x1>,
 				    <0x100 &apps_smmu 0x1481 0x1>;
 
@@ -1907,9 +1939,12 @@
 		ufs_mem_phy: phy@1d80000 {
 			compatible = "qcom,sm8550-qmp-ufs-phy";
 			reg = <0x0 0x01d80000 0x0 0x2000>;
-			clocks = <&tcsr TCSR_UFS_CLKREF_EN>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
-			clock-names = "ref", "ref_aux";
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&tcsr TCSR_UFS_CLKREF_EN>;
+			clock-names = "ref",
+				      "ref_aux",
+				      "qref";
 
 			power-domains = <&gcc UFS_MEM_PHY_GDSC>;
 
@@ -1940,6 +1975,7 @@
 			iommus = <&apps_smmu 0x60 0x0>;
 			dma-coherent;
 
+			operating-points-v2 = <&ufs_opp_table>;
 			interconnects = <&aggre1_noc MASTER_UFS_MEM 0 &mc_virt SLAVE_EBI1 0>,
 					<&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_UFS_MEM_CFG 0>;
 
@@ -1960,18 +1996,49 @@
 				 <&gcc GCC_UFS_PHY_TX_SYMBOL_0_CLK>,
 				 <&gcc GCC_UFS_PHY_RX_SYMBOL_0_CLK>,
 				 <&gcc GCC_UFS_PHY_RX_SYMBOL_1_CLK>;
-			freq-table-hz =
-				<75000000 300000000>,
-				<0 0>,
-				<0 0>,
-				<75000000 300000000>,
-				<100000000 403000000>,
-				<0 0>,
-				<0 0>,
-				<0 0>;
 			qcom,ice = <&ice>;
 
 			status = "disabled";
+
+			ufs_opp_table: opp-table {
+				compatible = "operating-points-v2";
+
+				opp-75000000 {
+					opp-hz = /bits/ 64 <75000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <75000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>;
+					required-opps = <&rpmhpd_opp_low_svs>;
+				};
+
+				opp-150000000 {
+					opp-hz = /bits/ 64 <150000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <150000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>;
+					required-opps = <&rpmhpd_opp_svs>;
+				};
+
+				opp-300000000 {
+					opp-hz = /bits/ 64 <300000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <300000000>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>,
+						 /bits/ 64 <0>;
+					required-opps = <&rpmhpd_opp_nom>;
+				};
+			};
 		};
 
 		ice: crypto@1d88000 {
@@ -2012,6 +2079,7 @@
 			operating-points-v2 = <&gpu_opp_table>;
 
 			qcom,gmu = <&gmu>;
+			#cooling-cells = <2>;
 
 			status = "disabled";
 
@@ -2507,7 +2575,7 @@
 				};
 			};
 
-			dmic02_default: dmic02-default-state {
+			dmic23_default: dmic23-default-state {
 				clk-pins {
 					pins = "gpio8";
 					function = "dmic2_clk";
@@ -3133,13 +3201,15 @@
 			assigned-clock-rates = <19200000>, <200000000>;
 
 			interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
-					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>,
+					      <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>,
 					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
-					      <&pdc 14 IRQ_TYPE_EDGE_BOTH>;
-			interrupt-names = "hs_phy_irq",
-					  "ss_phy_irq",
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "hs_phy_irq",
+					  "dp_hs_phy_irq",
 					  "dm_hs_phy_irq",
-					  "dp_hs_phy_irq";
+					  "ss_phy_irq";
 
 			power-domains = <&gcc USB30_PRIM_GDSC>;
 			required-opps = <&rpmhpd_opp_nom>;
@@ -3248,7 +3318,7 @@
 		spmi_bus: spmi@c400000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0 0x0c400000 0 0x3000>,
-			      <0 0x0c500000 0 0x4000000>,
+			      <0 0x0c500000 0 0x400000>,
 			      <0 0x0c440000 0 0x80000>,
 			      <0 0x0c4c0000 0 0x20000>,
 			      <0 0x0c42d000 0 0x4000>;
@@ -4254,6 +4324,7 @@
 						reg = <3>;
 						iommus = <&apps_smmu 0x1003 0x80>,
 							 <&apps_smmu 0x1063 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@4 {
@@ -4261,6 +4332,7 @@
 						reg = <4>;
 						iommus = <&apps_smmu 0x1004 0x80>,
 							 <&apps_smmu 0x1064 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@5 {
@@ -4268,6 +4340,7 @@
 						reg = <5>;
 						iommus = <&apps_smmu 0x1005 0x80>,
 							 <&apps_smmu 0x1065 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@6 {
@@ -4275,6 +4348,7 @@
 						reg = <6>;
 						iommus = <&apps_smmu 0x1006 0x80>,
 							 <&apps_smmu 0x1066 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@7 {
@@ -4282,6 +4356,7 @@
 						reg = <7>;
 						iommus = <&apps_smmu 0x1007 0x80>,
 							 <&apps_smmu 0x1067 0x0>;
+						dma-coherent;
 					};
 				};
 
@@ -4388,6 +4463,7 @@
 						iommus = <&apps_smmu 0x1961 0x0>,
 							 <&apps_smmu 0x0c01 0x20>,
 							 <&apps_smmu 0x19c1 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@2 {
@@ -4396,6 +4472,7 @@
 						iommus = <&apps_smmu 0x1962 0x0>,
 							 <&apps_smmu 0x0c02 0x20>,
 							 <&apps_smmu 0x19c2 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@3 {
@@ -4404,6 +4481,7 @@
 						iommus = <&apps_smmu 0x1963 0x0>,
 							 <&apps_smmu 0x0c03 0x20>,
 							 <&apps_smmu 0x19c3 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@4 {
@@ -4412,6 +4490,7 @@
 						iommus = <&apps_smmu 0x1964 0x0>,
 							 <&apps_smmu 0x0c04 0x20>,
 							 <&apps_smmu 0x19c4 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@5 {
@@ -4420,6 +4499,7 @@
 						iommus = <&apps_smmu 0x1965 0x0>,
 							 <&apps_smmu 0x0c05 0x20>,
 							 <&apps_smmu 0x19c5 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@6 {
@@ -4428,6 +4508,7 @@
 						iommus = <&apps_smmu 0x1966 0x0>,
 							 <&apps_smmu 0x0c06 0x20>,
 							 <&apps_smmu 0x19c6 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@7 {
@@ -4436,6 +4517,7 @@
 						iommus = <&apps_smmu 0x1967 0x0>,
 							 <&apps_smmu 0x0c07 0x20>,
 							 <&apps_smmu 0x19c7 0x10>;
+						dma-coherent;
 					};
 
 					compute-cb@8 {
@@ -4444,6 +4526,7 @@
 						iommus = <&apps_smmu 0x1968 0x0>,
 							 <&apps_smmu 0x0c08 0x20>,
 							 <&apps_smmu 0x19c8 0x10>;
+						dma-coherent;
 					};
 
 					/* note: secure cb9 in downstream */
@@ -5304,6 +5387,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 1>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu0_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5336,6 +5426,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 2>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu1_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5368,6 +5465,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 3>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu2_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5400,6 +5504,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 4>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu3_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5432,6 +5543,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 5>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu4_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5464,6 +5582,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 6>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu5_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5496,6 +5621,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 7>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu6_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
@@ -5528,6 +5660,13 @@
 			polling-delay = <0>;
 			thermal-sensors = <&tsens2 8>;
 
+			cooling-maps {
+				map0 {
+					trip = <&gpu7_junction_config>;
+					cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
+			};
+
 			trips {
 				thermal-engine-config {
 					temperature = <125000>;
diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
index 9d916edb1c73..4450273f9667 100644
--- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
+++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts
@@ -66,6 +66,29 @@
 		};
 	};
 
+	sound {
+		compatible = "qcom,sm8650-sndcard", "qcom,sm8450-sndcard";
+		model = "SM8650-MTP";
+		audio-routing = "SpkrLeft IN", "WSA_SPK1 OUT",
+				"SpkrRight IN", "WSA_SPK2 OUT";
+
+		wsa-dai-link {
+			link-name = "WSA Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&left_spkr>, <&right_spkr>, <&swr0 0>, <&lpass_wsamacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+	};
+
 	vph_pwr: vph-pwr-regulator {
 		compatible = "regulator-fixed";
 
@@ -428,6 +451,138 @@
 						   RPMH_REGULATOR_MODE_HPM>;
 		};
 	};
+
+	regulators-6 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "m";
+
+		vdd-l1-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6c_1p8>;
+		vdd-l6-supply = <&vreg_bob1>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1m_1p1: ldo1 {
+			regulator-name = "vreg_l1m_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2m_1p056: ldo2 {
+			regulator-name = "vreg_l2m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3m_2p8: ldo3 {
+			regulator-name = "vreg_l3m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4m_2p8: ldo4 {
+			regulator-name = "vreg_l4m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5m_1p8: ldo5 {
+			regulator-name = "vreg_l5m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6m_2p8: ldo6 {
+			regulator-name = "vreg_l6m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7m_2p96: ldo7 {
+			regulator-name = "vreg_l7m_2p96";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "n";
+
+		vdd-l1-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-l4-supply = <&vreg_s6c_1p8>;
+		vdd-l5-supply = <&vreg_bob2>;
+		vdd-l6-supply = <&vreg_bob2>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1n_1p1: ldo1 {
+			regulator-name = "vreg_l1n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2n_1p056: ldo2 {
+			regulator-name = "vreg_l2n_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3n_1p8: ldo3 {
+			regulator-name = "vreg_l3n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4n_1p8: ldo4 {
+			regulator-name = "vreg_l4n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5n_2p8: ldo5 {
+			regulator-name = "vreg_l5n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6n_2p8: ldo6 {
+			regulator-name = "vreg_l6n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7n_3p3: ldo7 {
+			regulator-name = "vreg_l7n_3p3";
+			regulator-min-microvolt = <3304000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
 };
 
 &dispcc {
@@ -622,7 +777,7 @@
 
 &tlmm {
 	/* Reserved I/Os for NFC */
-	gpio-reserved-ranges = <32 8>;
+	gpio-reserved-ranges = <32 8>, <74 1>;
 
 	disp0_reset_n_active: disp0-reset-n-active-state {
 		pins = "gpio133";
diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
index 592a67a47c78..b07cac2e5bc8 100644
--- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
+++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts
@@ -77,9 +77,83 @@
 					reg = <1>;
 
 					pmic_glink_ss_in: endpoint {
-						remote-endpoint = <&usb_1_dwc3_ss>;
+						remote-endpoint = <&redriver_ss_out>;
 					};
 				};
+
+				port@2 {
+					reg = <2>;
+
+					pmic_glink_sbu: endpoint {
+						remote-endpoint = <&wcd_usbss_sbu_mux>;
+				    };
+				};
+			};
+		};
+	};
+
+	sound {
+		compatible = "qcom,sm8650-sndcard", "qcom,sm8450-sndcard";
+		model = "SM8650-QRD";
+		audio-routing = "SpkrLeft IN", "WSA_SPK1 OUT",
+				"SpkrRight IN", "WSA_SPK2 OUT",
+				"IN1_HPHL", "HPHL_OUT",
+				"IN2_HPHR", "HPHR_OUT",
+				"AMIC1", "MIC BIAS1",
+				"AMIC2", "MIC BIAS2",
+				"AMIC3", "MIC BIAS3",
+				"AMIC4", "MIC BIAS3",
+				"AMIC5", "MIC BIAS4",
+				"TX SWR_INPUT0", "ADC1_OUTPUT",
+				"TX SWR_INPUT1", "ADC2_OUTPUT",
+				"TX SWR_INPUT2", "ADC3_OUTPUT",
+				"TX SWR_INPUT3", "ADC4_OUTPUT";
+
+		wcd-playback-dai-link {
+			link-name = "WCD Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&wcd939x 0>, <&swr1 0>, <&lpass_rxmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wcd-capture-dai-link {
+			link-name = "WCD Capture";
+
+			cpu {
+				sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>;
+			};
+
+			codec {
+				sound-dai = <&wcd939x 1>, <&swr2 0>, <&lpass_txmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wsa-dai-link {
+			link-name = "WSA Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&left_spkr>, <&right_spkr>, <&swr0 0>, <&lpass_wsamacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
 			};
 		};
 	};
@@ -94,6 +168,41 @@
 		regulator-always-on;
 		regulator-boot-on;
 	};
+
+	wcd939x: audio-codec {
+		compatible = "qcom,wcd9395-codec", "qcom,wcd9390-codec";
+
+		pinctrl-0 = <&wcd_default>;
+		pinctrl-names = "default";
+
+		qcom,micbias1-microvolt = <1800000>;
+		qcom,micbias2-microvolt = <1800000>;
+		qcom,micbias3-microvolt = <1800000>;
+		qcom,micbias4-microvolt = <1800000>;
+		qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>;
+		qcom,mbhc-headset-vthreshold-microvolt = <1700000>;
+		qcom,mbhc-headphone-vthreshold-microvolt = <50000>;
+		qcom,rx-device = <&wcd_rx>;
+		qcom,tx-device = <&wcd_tx>;
+
+		reset-gpios = <&tlmm 107 GPIO_ACTIVE_LOW>;
+
+		vdd-buck-supply = <&vreg_l15b_1p8>;
+		vdd-rxtx-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l15b_1p8>;
+		vdd-mic-bias-supply = <&vreg_bob1>;
+
+		#sound-dai-cells = <1>;
+
+		mode-switch;
+		orientation-switch;
+
+		port {
+			wcd_codec_headset_in: endpoint {
+				remote-endpoint = <&wcd_usbss_headset_out>;
+			};
+		};
+	};
 };
 
 &apps_rsc {
@@ -436,6 +545,138 @@
 						   RPMH_REGULATOR_MODE_HPM>;
 		};
 	};
+
+	regulators-6 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "m";
+
+		vdd-l1-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-l4-supply = <&vreg_bob2>;
+		vdd-l5-supply = <&vreg_s6c_1p8>;
+		vdd-l6-supply = <&vreg_bob1>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1m_1p1: ldo1 {
+			regulator-name = "vreg_l1m_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2m_1p056: ldo2 {
+			regulator-name = "vreg_l2m_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3m_2p8: ldo3 {
+			regulator-name = "vreg_l3m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4m_2p8: ldo4 {
+			regulator-name = "vreg_l4m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5m_1p8: ldo5 {
+			regulator-name = "vreg_l5m_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6m_2p8: ldo6 {
+			regulator-name = "vreg_l6m_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7m_2p96: ldo7 {
+			regulator-name = "vreg_l7m_2p96";
+			regulator-min-microvolt = <2960000>;
+			regulator-max-microvolt = <2960000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
+
+	regulators-7 {
+		compatible = "qcom,pm8010-rpmh-regulators";
+		qcom,pmic-id = "n";
+
+		vdd-l1-l2-supply = <&vreg_s1c_1p2>;
+		vdd-l3-l4-supply = <&vreg_s6c_1p8>;
+		vdd-l5-supply = <&vreg_bob2>;
+		vdd-l6-supply = <&vreg_bob2>;
+		vdd-l7-supply = <&vreg_bob1>;
+
+		vreg_l1n_1p1: ldo1 {
+			regulator-name = "vreg_l1n_1p1";
+			regulator-min-microvolt = <1104000>;
+			regulator-max-microvolt = <1104000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l2n_1p056: ldo2 {
+			regulator-name = "vreg_l2n_1p056";
+			regulator-min-microvolt = <1056000>;
+			regulator-max-microvolt = <1056000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+			regulator-allowed-modes = <RPMH_REGULATOR_MODE_LPM
+						   RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l3n_1p8: ldo3 {
+			regulator-name = "vreg_l3n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l4n_1p8: ldo4 {
+			regulator-name = "vreg_l4n_1p8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l5n_2p8: ldo5 {
+			regulator-name = "vreg_l5n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l6n_2p8: ldo6 {
+			regulator-name = "vreg_l6n_2p8";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+
+		vreg_l7n_3p3: ldo7 {
+			regulator-name = "vreg_l7n_3p3";
+			regulator-min-microvolt = <3304000>;
+			regulator-max-microvolt = <3304000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+		};
+	};
 };
 
 &dispcc {
@@ -446,6 +687,78 @@
 	status = "okay";
 };
 
+&i2c3 {
+       status = "okay";
+
+       wcd_usbss: typec-mux@e {
+		compatible = "qcom,wcd9395-usbss", "qcom,wcd9390-usbss";
+		reg = <0xe>;
+
+		vdd-supply = <&vreg_l15b_1p8>;
+		reset-gpios = <&tlmm 152 GPIO_ACTIVE_HIGH>;
+
+		mode-switch;
+		orientation-switch;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				wcd_usbss_sbu_mux: endpoint {
+					remote-endpoint = <&pmic_glink_sbu>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				wcd_usbss_headset_out: endpoint {
+					remote-endpoint = <&wcd_codec_headset_in>;
+				};
+			};
+		};
+       };
+};
+
+&i2c6 {
+	status = "okay";
+
+	typec-mux@1c {
+		compatible = "onnn,nb7vpq904m";
+		reg = <0x1c>;
+
+		vcc-supply = <&vreg_l15b_1p8>;
+
+		retimer-switch;
+		orientation-switch;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				redriver_ss_out: endpoint {
+					remote-endpoint = <&pmic_glink_ss_in>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				redriver_ss_in: endpoint {
+					data-lanes = <3 2 1 0>;
+					remote-endpoint = <&usb_dp_qmpphy_out>;
+				};
+			};
+		};
+	};
+};
+
 &ipa {
 	qcom,gsi-loader = "self";
 	memory-region = <&ipa_fw_mem>;
@@ -453,6 +766,16 @@
 	status = "okay";
 };
 
+&lpass_tlmm {
+	spkr_1_sd_n_active: spkr-1-sd-n-active-state {
+		pins = "gpio21";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
 &mdss {
 	status = "okay";
 };
@@ -495,6 +818,15 @@
 	status = "okay";
 };
 
+&mdss_dp0 {
+	status = "okay";
+};
+
+&mdss_dp0_out {
+	data-lanes = <0 1>;
+	remote-endpoint = <&usb_dp_qmpphy_dp_in>;
+};
+
 &mdss_mdp {
 	status = "okay";
 };
@@ -600,6 +932,11 @@
 	status = "okay";
 };
 
+&qup_i2c3_data_clk {
+	/* Use internal I2C pull-up */
+	bias-pull-up = <2200>;
+};
+
 &qupv3_id_0 {
 	status = "okay";
 };
@@ -657,9 +994,77 @@
 	};
 };
 
+&swr0 {
+	status = "okay";
+
+	/* WSA8845, Speaker Left */
+	left_spkr: speaker@0,0 {
+		compatible = "sdw20217020400";
+		reg = <0 0>;
+		pinctrl-0 = <&spkr_1_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&lpass_tlmm 21 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrLeft";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l3c_1p2>;
+	};
+
+	/* WSA8845, Speaker Right */
+	right_spkr: speaker@0,1 {
+		compatible = "sdw20217020400";
+		reg = <0 1>;
+		pinctrl-0 = <&spkr_2_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&tlmm 77 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "SpkrRight";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l3c_1p2>;
+	};
+};
+
+&swr1 {
+	status = "okay";
+
+	/* WCD9395 RX */
+	wcd_rx: codec@0,4 {
+		compatible = "sdw20217010e00";
+		reg = <0 4>;
+
+		/*
+		 * WCD9395 RX Port 1 (HPH_L/R)      <=> SWR1 Port 1 (HPH_L/R)
+		 * WCD9395 RX Port 2 (CLSH)         <=> SWR1 Port 2 (CLSH)
+		 * WCD9395 RX Port 3 (COMP_L/R)     <=> SWR1 Port 3 (COMP_L/R)
+		 * WCD9395 RX Port 4 (LO)           <=> SWR1 Port 4 (LO)
+		 * WCD9395 RX Port 5 (DSD_L/R)      <=> SWR1 Port 5 (DSD_L/R)
+		 * WCD9395 RX Port 6 (HIFI_PCM_L/R) <=> SWR1 Port 9 (HIFI_PCM_L/R)
+		 */
+		qcom,rx-port-mapping = <1 2 3 4 5 9>;
+	};
+};
+
+&swr2 {
+	status = "okay";
+
+	/* WCD9395 TX */
+	wcd_tx: codec@0,3 {
+		compatible = "sdw20217010e00";
+		reg = <0 3>;
+
+		/*
+		 * WCD9395 TX Port 1 (ADC1,2,3,4)         <=> SWR2 Port 2 (TX SWR_INPUT 0,1,2,3)
+		 * WCD9395 TX Port 2 (ADC3,4 & DMIC0,1)   <=> SWR2 Port 2 (TX SWR_INPUT 0,1,2,3)
+		 * WCD9395 TX Port 3 (DMIC0,1,2,3 & MBHC) <=> SWR2 Port 3 (TX SWR_INPUT 4,5,6,7)
+		 * WCD9395 TX Port 4 (DMIC4,5,6,7)        <=> SWR2 Port 4 (TX SWR_INPUT 8,9,10,11)
+		 */
+		qcom,tx-port-mapping = <2 2 3 4>;
+	};
+};
+
 &tlmm {
 	/* Reserved I/Os for NFC */
-	gpio-reserved-ranges = <32 8>;
+	gpio-reserved-ranges = <32 8>, <74 1>;
 
 	bt_default: bt-default-state {
 		bt-en-pins {
@@ -704,6 +1109,14 @@
 		bias-pull-down;
 	};
 
+	spkr_2_sd_n_active: spkr-2-sd-n-active-state {
+		pins = "gpio77";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+
 	ts_irq: ts-irq-state {
 		pins = "gpio161";
 		function = "gpio";
@@ -718,6 +1131,14 @@
 		drive-strength = <8>;
 		bias-pull-up;
 	};
+
+	wcd_default: wcd-reset-n-active-state {
+		pins = "gpio107";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
 };
 
 &uart14 {
@@ -787,7 +1208,7 @@
 };
 
 &usb_1_dwc3_ss {
-	remote-endpoint = <&pmic_glink_ss_in>;
+	remote-endpoint = <&usb_dp_qmpphy_usb_ss_in>;
 };
 
 &usb_1_hsphy {
@@ -803,9 +1224,23 @@
 	vdda-phy-supply = <&vreg_l3i_1p2>;
 	vdda-pll-supply = <&vreg_l3g_0p91>;
 
+	orientation-switch;
+
 	status = "okay";
 };
 
+&usb_dp_qmpphy_dp_in {
+	remote-endpoint = <&mdss_dp0_out>;
+};
+
+&usb_dp_qmpphy_out {
+	remote-endpoint = <&redriver_ss_in>;
+};
+
+&usb_dp_qmpphy_usb_ss_in {
+	remote-endpoint = <&usb_1_dwc3_ss>;
+};
+
 &xo_board {
 	clock-frequency = <76800000>;
 };
diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi
index 2df77123a8c7..ba72d8f38420 100644
--- a/arch/arm64/boot/dts/qcom/sm8650.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi
@@ -525,6 +525,11 @@
 			no-map;
 		};
 
+		qlink_logging_mem: qlink-logging@84800000 {
+			reg = <0 0x84800000 0 0x200000>;
+			no-map;
+		};
+
 		mpss_dsm_mem: mpss-dsm@86b00000 {
 			reg = <0 0x86b00000 0 0x4900000>;
 			no-map;
@@ -1228,7 +1233,7 @@
 				clocks = <&gcc GCC_QUPV3_WRAP2_S6_CLK>;
 				clock-names = "se";
 
-				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
 						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
 						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
 						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
@@ -1250,7 +1255,7 @@
 				clocks = <&gcc GCC_QUPV3_WRAP2_S7_CLK>;
 				clock-names = "se";
 
-				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
 						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
 						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
 						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
@@ -2213,8 +2218,22 @@
 			      <0 0x60100000 0 0x100000>;
 			reg-names = "parf", "dbi", "elbi", "atu", "config";
 
-			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 
 			clocks = <&gcc GCC_PCIE_0_AUX_CLK>,
 				 <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
@@ -2255,6 +2274,11 @@
 			interrupt-map-mask = <0 0 0 0x7>;
 			#interrupt-cells = <1>;
 
+			/* Entries are reversed due to the unusual ITS DeviceID encoding */
+			msi-map = <0x0 &gic_its 0x1401 0x1>,
+				  <0x100 &gic_its 0x1400 0x1>;
+			msi-map-mask = <0xff00>;
+
 			linux,pci-domain = <0>;
 			num-lanes = <2>;
 			bus-range = <0 0xff>;
@@ -2317,8 +2341,22 @@
 				    "atu",
 				    "config";
 
-			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "msi";
+			interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 309 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 312 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 313 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 314 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
 
 			clocks = <&gcc GCC_PCIE_1_AUX_CLK>,
 				 <&gcc GCC_PCIE_1_CFG_AHB_CLK>,
@@ -2364,6 +2402,11 @@
 			interrupt-map-mask = <0 0 0 0x7>;
 			#interrupt-cells = <1>;
 
+			/* Entries are reversed due to the unusual ITS DeviceID encoding */
+			msi-map = <0x0 &gic_its 0x1481 0x1>,
+				  <0x100 &gic_its 0x1480 0x1>;
+			msi-map-mask = <0xff00>;
+
 			linux,pci-domain = <1>;
 			num-lanes = <2>;
 			bus-range = <0 0xff>;
@@ -2448,10 +2491,12 @@
 			compatible = "qcom,sm8650-qmp-ufs-phy";
 			reg = <0 0x01d80000 0 0x2000>;
 
-			clocks = <&tcsr TCSR_UFS_CLKREF_EN>,
-				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+				 <&tcsr TCSR_UFS_CLKREF_EN>;
 			clock-names = "ref",
-				      "ref_aux";
+				      "ref_aux",
+				      "qref";
 
 			resets = <&ufs_mem_hc 0>;
 			reset-names = "ufsphy";
@@ -2627,7 +2672,8 @@
 					     "mss";
 
 			memory-region = <&mpss_mem>, <&q6_mpss_dtb_mem>,
-					<&mpss_dsm_mem>, <&mpss_dsm_mem_2>;
+					<&mpss_dsm_mem>, <&mpss_dsm_mem_2>,
+					<&qlink_logging_mem>;
 
 			qcom,qmp = <&aoss_qmp>;
 
@@ -2919,7 +2965,7 @@
 				};
 			};
 
-			dmic02_default: dmic02-default-state {
+			dmic23_default: dmic23-default-state {
 				clk-pins {
 					pins = "gpio8";
 					function = "dmic2_clk";
@@ -3703,7 +3749,7 @@
 		spmi_bus: spmi@c400000 {
 			compatible = "qcom,spmi-pmic-arb";
 			reg = <0 0x0c400000 0 0x3000>,
-			      <0 0x0c500000 0 0x4000000>,
+			      <0 0x0c500000 0 0x400000>,
 			      <0 0x0c440000 0 0x80000>,
 			      <0 0x0c4c0000 0 0x20000>,
 			      <0 0x0c42d000 0 0x4000>;
@@ -4808,6 +4854,7 @@
 
 						iommus = <&apps_smmu 0x1003 0x80>,
 							 <&apps_smmu 0x1043 0x20>;
+						dma-coherent;
 					};
 
 					compute-cb@4 {
@@ -4816,6 +4863,7 @@
 
 						iommus = <&apps_smmu 0x1004 0x80>,
 							 <&apps_smmu 0x1044 0x20>;
+						dma-coherent;
 					};
 
 					compute-cb@5 {
@@ -4824,6 +4872,7 @@
 
 						iommus = <&apps_smmu 0x1005 0x80>,
 							 <&apps_smmu 0x1045 0x20>;
+						dma-coherent;
 					};
 
 					compute-cb@6 {
@@ -4832,6 +4881,7 @@
 
 						iommus = <&apps_smmu 0x1006 0x80>,
 							 <&apps_smmu 0x1046 0x20>;
+						dma-coherent;
 					};
 
 					compute-cb@7 {
@@ -4841,6 +4891,7 @@
 						iommus = <&apps_smmu 0x1007 0x40>,
 							 <&apps_smmu 0x1067 0x0>,
 							 <&apps_smmu 0x1087 0x0>;
+						dma-coherent;
 					};
 				};
 
@@ -4961,6 +5012,7 @@
 						iommus = <&apps_smmu 0x1961 0x0>,
 							 <&apps_smmu 0x0c01 0x20>,
 							 <&apps_smmu 0x19c1 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@2 {
@@ -4970,6 +5022,7 @@
 						iommus = <&apps_smmu 0x1962 0x0>,
 							 <&apps_smmu 0x0c02 0x20>,
 							 <&apps_smmu 0x19c2 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@3 {
@@ -4979,6 +5032,7 @@
 						iommus = <&apps_smmu 0x1963 0x0>,
 							 <&apps_smmu 0x0c03 0x20>,
 							 <&apps_smmu 0x19c3 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@4 {
@@ -4988,6 +5042,7 @@
 						iommus = <&apps_smmu 0x1964 0x0>,
 							 <&apps_smmu 0x0c04 0x20>,
 							 <&apps_smmu 0x19c4 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@5 {
@@ -4997,6 +5052,7 @@
 						iommus = <&apps_smmu 0x1965 0x0>,
 							 <&apps_smmu 0x0c05 0x20>,
 							 <&apps_smmu 0x19c5 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@6 {
@@ -5006,6 +5062,7 @@
 						iommus = <&apps_smmu 0x1966 0x0>,
 							 <&apps_smmu 0x0c06 0x20>,
 							 <&apps_smmu 0x19c6 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@7 {
@@ -5015,6 +5072,7 @@
 						iommus = <&apps_smmu 0x1967 0x0>,
 							 <&apps_smmu 0x0c07 0x20>,
 							 <&apps_smmu 0x19c7 0x0>;
+						dma-coherent;
 					};
 
 					compute-cb@8 {
@@ -5024,6 +5082,7 @@
 						iommus = <&apps_smmu 0x1968 0x0>,
 							 <&apps_smmu 0x0c08 0x20>,
 							 <&apps_smmu 0x19c8 0x0>;
+						dma-coherent;
 					};
 				};
 			};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
index 7532d8eca2de..6a0a54532e5f 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
@@ -18,10 +18,124 @@
 		serial0 = &uart21;
 	};
 
+	wcd938x: audio-codec {
+		compatible = "qcom,wcd9385-codec";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&wcd_default>;
+
+		qcom,micbias1-microvolt = <1800000>;
+		qcom,micbias2-microvolt = <1800000>;
+		qcom,micbias3-microvolt = <1800000>;
+		qcom,micbias4-microvolt = <1800000>;
+		qcom,mbhc-buttons-vthreshold-microvolt = <75000 150000 237000 500000 500000 500000 500000 500000>;
+		qcom,mbhc-headset-vthreshold-microvolt = <1700000>;
+		qcom,mbhc-headphone-vthreshold-microvolt = <50000>;
+		qcom,rx-device = <&wcd_rx>;
+		qcom,tx-device = <&wcd_tx>;
+
+		reset-gpios = <&tlmm 191 GPIO_ACTIVE_LOW>;
+
+		vdd-buck-supply = <&vreg_l15b_1p8>;
+		vdd-rxtx-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l15b_1p8>;
+		vdd-mic-bias-supply = <&vreg_bob1>;
+
+		#sound-dai-cells = <1>;
+	};
+
 	chosen {
 		stdout-path = "serial0:115200n8";
 	};
 
+	sound {
+		compatible = "qcom,x1e80100-sndcard";
+		model = "X1E80100-CRD";
+		audio-routing = "WooferLeft IN", "WSA WSA_SPK1 OUT",
+				"TwitterLeft IN", "WSA WSA_SPK2 OUT",
+				"WooferRight IN", "WSA2 WSA_SPK2 OUT",
+				"TwitterRight IN", "WSA2 WSA_SPK2 OUT",
+				"IN1_HPHL", "HPHL_OUT",
+				"IN2_HPHR", "HPHR_OUT",
+				"AMIC2", "MIC BIAS2",
+				"VA DMIC0", "MIC BIAS3",
+				"VA DMIC1", "MIC BIAS3",
+				"VA DMIC2", "MIC BIAS1",
+				"VA DMIC3", "MIC BIAS1",
+				"VA DMIC0", "VA MIC BIAS3",
+				"VA DMIC1", "VA MIC BIAS3",
+				"VA DMIC2", "VA MIC BIAS1",
+				"VA DMIC3", "VA MIC BIAS1",
+				"TX SWR_INPUT1", "ADC2_OUTPUT";
+
+		wcd-playback-dai-link {
+			link-name = "WCD Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai RX_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&wcd938x 0>, <&swr1 0>, <&lpass_rxmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wcd-capture-dai-link {
+			link-name = "WCD Capture";
+
+			cpu {
+				sound-dai = <&q6apmbedai TX_CODEC_DMA_TX_3>;
+			};
+
+			codec {
+				sound-dai = <&wcd938x 1>, <&swr2 0>, <&lpass_txmacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		wsa-dai-link {
+			link-name = "WSA Playback";
+
+			cpu {
+				sound-dai = <&q6apmbedai WSA_CODEC_DMA_RX_0>;
+			};
+
+			codec {
+				sound-dai = <&left_woofer>, <&left_tweeter>,
+					    <&swr0 0>, <&lpass_wsamacro 0>,
+					    <&right_woofer>, <&right_tweeter>,
+					    <&swr3 0>, <&lpass_wsa2macro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+
+		va-dai-link {
+			link-name = "VA Capture";
+
+			cpu {
+				sound-dai = <&q6apmbedai VA_CODEC_DMA_TX_0>;
+			};
+
+			codec {
+				sound-dai = <&lpass_vamacro 0>;
+			};
+
+			platform {
+				sound-dai = <&q6apm>;
+			};
+		};
+	};
+
 	vph_pwr: vph-pwr-regulator {
 		compatible = "regulator-fixed";
 
@@ -401,10 +515,251 @@
 	};
 };
 
+&i2c0 {
+	clock-frequency = <400000>;
+
+	status = "okay";
+
+	touchpad@15 {
+		compatible = "hid-over-i2c";
+		reg = <0x15>;
+
+		hid-descr-addr = <0x1>;
+		interrupts-extended = <&tlmm 3 IRQ_TYPE_LEVEL_LOW>;
+
+		pinctrl-0 = <&tpad_default>;
+		pinctrl-names = "default";
+
+		wakeup-source;
+	};
+
+	keyboard@3a {
+		compatible = "hid-over-i2c";
+		reg = <0x3a>;
+
+		hid-descr-addr = <0x1>;
+		interrupts-extended = <&tlmm 67 IRQ_TYPE_LEVEL_LOW>;
+
+		pinctrl-0 = <&kybd_default>;
+		pinctrl-names = "default";
+
+		wakeup-source;
+	};
+};
+
+&i2c8 {
+	clock-frequency = <400000>;
+
+	status = "okay";
+
+	touchscreen@10 {
+		compatible = "hid-over-i2c";
+		reg = <0x10>;
+
+		hid-descr-addr = <0x1>;
+		interrupts-extended = <&tlmm 51 IRQ_TYPE_LEVEL_LOW>;
+
+		pinctrl-0 = <&ts0_default>;
+		pinctrl-names = "default";
+	};
+};
+
+&lpass_tlmm {
+	spkr_01_sd_n_active: spkr-01-sd-n-active-state {
+		pins = "gpio12";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+
+	spkr_23_sd_n_active: spkr-23-sd-n-active-state {
+		pins = "gpio13";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
+};
+
+&lpass_vamacro {
+	pinctrl-0 = <&dmic01_default>, <&dmic23_default>;
+	pinctrl-names = "default";
+
+	vdd-micb-supply = <&vreg_l1b_1p8>;
+	qcom,dmic-sample-rate = <4800000>;
+};
+
+&mdss {
+	status = "okay";
+};
+
+&mdss_dp3 {
+	compatible = "qcom,x1e80100-dp";
+	/delete-property/ #sound-dai-cells;
+
+	data-lanes = <0 1 2 3>;
+
+	status = "okay";
+
+	aux-bus {
+		panel {
+			compatible = "edp-panel";
+			power-supply = <&vreg_edp_3p3>;
+
+			port {
+				edp_panel_in: endpoint {
+					remote-endpoint = <&mdss_dp3_out>;
+				};
+			};
+		};
+	};
+
+	ports {
+		port@1 {
+			reg = <1>;
+			mdss_dp3_out: endpoint {
+				remote-endpoint = <&edp_panel_in>;
+			};
+		};
+	};
+};
+
+&mdss_dp3_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l2j_1p2>;
+
+	status = "okay";
+};
+
+&pcie4 {
+	status = "okay";
+};
+
+&pcie4_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&pcie6a {
+	status = "okay";
+};
+
+&pcie6a_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l2j_1p2>;
+
+	status = "okay";
+};
+
+&qupv3_0 {
+	status = "okay";
+};
+
+&qupv3_1 {
+	status = "okay";
+};
+
 &qupv3_2 {
 	status = "okay";
 };
 
+&remoteproc_adsp {
+	firmware-name = "qcom/x1e80100/adsp.mbn",
+			"qcom/x1e80100/adsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/x1e80100/cdsp.mbn",
+			"qcom/x1e80100/cdsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&swr0 {
+	status = "okay";
+
+	/* WSA8845, Left Woofer */
+	left_woofer: speaker@0,0 {
+		compatible = "sdw20217020400";
+		reg = <0 0>;
+		pinctrl-0 = <&spkr_01_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "WooferLeft";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l12b_1p2>;
+	};
+
+	/* WSA8845, Left Tweeter */
+	left_tweeter: speaker@0,1 {
+		compatible = "sdw20217020400";
+		reg = <0 1>;
+		/* pinctrl in left_woofer node because of sharing the GPIO*/
+		powerdown-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "TwitterLeft";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l12b_1p2>;
+	};
+};
+
+&swr1 {
+	status = "okay";
+
+	/* WCD9385 RX */
+	wcd_rx: codec@0,4 {
+		compatible = "sdw20217010d00";
+		reg = <0 4>;
+		qcom,rx-port-mapping = <1 2 3 4 5>;
+	};
+};
+
+&swr2 {
+	status = "okay";
+
+	/* WCD9385 TX */
+	wcd_tx: codec@0,3 {
+		compatible = "sdw20217010d00";
+		reg = <0 3>;
+		qcom,tx-port-mapping = <1 1 2 3>;
+	};
+};
+
+&swr3 {
+	status = "okay";
+
+	/* WSA8845, Right Woofer */
+	right_woofer: speaker@0,0 {
+		compatible = "sdw20217020400";
+		reg = <0 0>;
+		pinctrl-0 = <&spkr_23_sd_n_active>;
+		pinctrl-names = "default";
+		powerdown-gpios = <&lpass_tlmm 13 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "WooferRight";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l12b_1p2>;
+	};
+
+	/* WSA8845, Right Tweeter */
+	right_tweeter: speaker@0,1 {
+		compatible = "sdw20217020400";
+		reg = <0 1>;
+		/* pinctrl in right_woofer node because of sharing the GPIO*/
+		powerdown-gpios = <&lpass_tlmm 13 GPIO_ACTIVE_LOW>;
+		#sound-dai-cells = <0>;
+		sound-name-prefix = "TwitterRight";
+		vdd-1p8-supply = <&vreg_l15b_1p8>;
+		vdd-io-supply = <&vreg_l12b_1p2>;
+	};
+};
+
 &tlmm {
 	gpio-reserved-ranges = <34 2>, /* Unused */
 			       <44 4>, /* SPI (TPM) */
@@ -416,9 +771,104 @@
 		drive-strength = <16>;
 		bias-disable;
 	};
+
+	kybd_default: kybd-default-state {
+		pins = "gpio67";
+		function = "gpio";
+		bias-disable;
+	};
+
+	tpad_default: tpad-default-state {
+		pins = "gpio3";
+		function = "gpio";
+		bias-disable;
+	};
+
+	ts0_default: ts0-default-state {
+		int-n-pins {
+			pins = "gpio51";
+			function = "gpio";
+			bias-disable;
+		};
+
+		reset-n-pins {
+			pins = "gpio48";
+			function = "gpio";
+			output-high;
+			drive-strength = <16>;
+		};
+	};
+
+	wcd_default: wcd-reset-n-active-state {
+		pins = "gpio191";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+		output-low;
+	};
 };
 
 &uart21 {
 	compatible = "qcom,geni-debug-uart";
 	status = "okay";
 };
+
+&usb_1_ss0_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss0_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss0 {
+	status = "okay";
+};
+
+&usb_1_ss0_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
+
+&usb_1_ss1_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss1_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss1 {
+	status = "okay";
+};
+
+&usb_1_ss1_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
+
+&usb_1_ss2_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss2_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss2 {
+	status = "okay";
+};
+
+&usb_1_ss2_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
index a37ad9475c90..e76d29053d79 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
@@ -5,6 +5,7 @@
 
 /dts-v1/;
 
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/regulator/qcom,rpmh-regulator.h>
 
 #include "x1e80100.dtsi"
@@ -31,6 +32,23 @@
 		regulator-always-on;
 		regulator-boot-on;
 	};
+
+	vreg_edp_3p3: regulator-edp-3p3 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "VREG_EDP_3P3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpio = <&tlmm 70 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+
+		pinctrl-0 = <&edp_reg_en>;
+		pinctrl-names = "default";
+
+		regulator-always-on;
+		regulator-boot-on;
+	};
 };
 
 &apps_rsc {
@@ -243,7 +261,7 @@
 		qcom,pmic-id = "e";
 
 		vdd-l2-supply = <&vreg_s1f_0p7>;
-		vdd-l3-supply = <&vph_pwr>;
+		vdd-l3-supply = <&vreg_s5j_1p2>;
 
 		vreg_l2e_0p8: ldo2 {
 			regulator-name = "vreg_l2e_0p8";
@@ -349,7 +367,7 @@
 		qcom,pmic-id = "j";
 
 		vdd-l1-supply = <&vreg_s1f_0p7>;
-		vdd-l2-supply = <&vph_pwr>;
+		vdd-l2-supply = <&vreg_s5j_1p2>;
 		vdd-l3-supply = <&vreg_s1f_0p7>;
 		vdd-s5-supply = <&vph_pwr>;
 
@@ -383,17 +401,170 @@
 	};
 };
 
+&mdss {
+	status = "okay";
+};
+
+&mdss_dp3 {
+	compatible = "qcom,x1e80100-dp";
+	/delete-property/ #sound-dai-cells;
+
+	data-lanes = <0 1 2 3>;
+
+	status = "okay";
+
+	aux-bus {
+		panel {
+			compatible = "edp-panel";
+			power-supply = <&vreg_edp_3p3>;
+
+			port {
+				edp_panel_in: endpoint {
+					remote-endpoint = <&mdss_dp3_out>;
+				};
+			};
+		};
+	};
+
+	ports {
+		port@1 {
+			reg = <1>;
+			mdss_dp3_out: endpoint {
+				remote-endpoint = <&edp_panel_in>;
+			};
+		};
+	};
+};
+
+&mdss_dp3_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l2j_1p2>;
+
+	status = "okay";
+};
+
+&pcie4 {
+	status = "okay";
+};
+
+&pcie4_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&pcie6a {
+	status = "okay";
+};
+
+&pcie6a_phy {
+	vdda-phy-supply = <&vreg_l3j_0p8>;
+	vdda-pll-supply = <&vreg_l2j_1p2>;
+
+	status = "okay";
+};
+
+&qupv3_0 {
+	status = "okay";
+};
+
+&qupv3_1 {
+	status = "okay";
+};
+
 &qupv3_2 {
 	status = "okay";
 };
 
+&remoteproc_adsp {
+	firmware-name = "qcom/x1e80100/adsp.mbn",
+			"qcom/x1e80100/adsp_dtb.mbn";
+
+	status = "okay";
+};
+
+&remoteproc_cdsp {
+	firmware-name = "qcom/x1e80100/cdsp.mbn",
+			"qcom/x1e80100/cdsp_dtb.mbn";
+
+	status = "okay";
+};
+
 &tlmm {
 	gpio-reserved-ranges = <33 3>, /* Unused */
 			       <44 4>, /* SPI (TPM) */
 			       <238 1>; /* UFS Reset */
+
+	edp_reg_en: edp-reg-en-state {
+		pins = "gpio70";
+		function = "gpio";
+		drive-strength = <16>;
+		bias-disable;
+	};
 };
 
 &uart21 {
 	compatible = "qcom,geni-debug-uart";
 	status = "okay";
 };
+
+&usb_1_ss0_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss0_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss0 {
+	status = "okay";
+};
+
+&usb_1_ss0_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
+
+&usb_1_ss1_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss1_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss1 {
+	status = "okay";
+};
+
+&usb_1_ss1_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
+
+&usb_1_ss2_hsphy {
+	vdd-supply = <&vreg_l2e_0p8>;
+	vdda12-supply = <&vreg_l3e_1p2>;
+
+	status = "okay";
+};
+
+&usb_1_ss2_qmpphy {
+	status = "okay";
+};
+
+&usb_1_ss2 {
+	status = "okay";
+};
+
+&usb_1_ss2_dwc3 {
+	dr_mode = "host";
+	usb-role-switch;
+};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
index 6f75fc342ceb..8e517f76189e 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -4,14 +4,20 @@
  */
 
 #include <dt-bindings/clock/qcom,rpmh.h>
+#include <dt-bindings/clock/qcom,x1e80100-dispcc.h>
 #include <dt-bindings/clock/qcom,x1e80100-gcc.h>
+#include <dt-bindings/clock/qcom,x1e80100-tcsr.h>
 #include <dt-bindings/dma/qcom-gpi.h>
 #include <dt-bindings/interconnect/qcom,icc.h>
 #include <dt-bindings/interconnect/qcom,x1e80100-rpmh.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/mailbox/qcom-ipcc.h>
+#include <dt-bindings/phy/phy-qcom-qmp.h>
 #include <dt-bindings/power/qcom,rpmhpd.h>
 #include <dt-bindings/power/qcom-rpmpd.h>
+#include <dt-bindings/soc/qcom,gpr.h>
 #include <dt-bindings/soc/qcom,rpmh-rsc.h>
+#include <dt-bindings/sound/qcom,q6dsp-lpass-ports.h>
 
 / {
 	interrupt-parent = <&intc>;
@@ -395,16 +401,24 @@
 		CLUSTER_PD0: power-domain-cpu-cluster0 {
 			#power-domain-cells = <0>;
 			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+			power-domains = <&SYSTEM_PD>;
 		};
 
 		CLUSTER_PD1: power-domain-cpu-cluster1 {
 			#power-domain-cells = <0>;
 			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+			power-domains = <&SYSTEM_PD>;
 		};
 
 		CLUSTER_PD2: power-domain-cpu-cluster2 {
 			#power-domain-cells = <0>;
 			domain-idle-states = <&CLUSTER_CL4>, <&CLUSTER_CL5>;
+			power-domains = <&SYSTEM_PD>;
+		};
+
+		SYSTEM_PD: power-domain-system {
+			#power-domain-cells = <0>;
+			/* TODO: system-wide idle states */
 		};
 	};
 
@@ -662,6 +676,58 @@
 		};
 	};
 
+	smp2p-adsp {
+		compatible = "qcom,smp2p";
+
+		interrupts-extended = <&ipcc IPCC_CLIENT_LPASS
+					     IPCC_MPROC_SIGNAL_SMP2P
+					     IRQ_TYPE_EDGE_RISING>;
+
+		mboxes = <&ipcc IPCC_CLIENT_LPASS
+				IPCC_MPROC_SIGNAL_SMP2P>;
+
+		qcom,smem = <443>, <429>;
+		qcom,local-pid = <0>;
+		qcom,remote-pid = <2>;
+
+		smp2p_adsp_out: master-kernel {
+			qcom,entry-name = "master-kernel";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		smp2p_adsp_in: slave-kernel {
+			qcom,entry-name = "slave-kernel";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+
+	smp2p-cdsp {
+		compatible = "qcom,smp2p";
+
+		interrupts-extended = <&ipcc IPCC_CLIENT_CDSP
+					     IPCC_MPROC_SIGNAL_SMP2P
+					     IRQ_TYPE_EDGE_RISING>;
+
+		mboxes = <&ipcc IPCC_CLIENT_CDSP
+				IPCC_MPROC_SIGNAL_SMP2P>;
+
+		qcom,smem = <94>, <432>;
+		qcom,local-pid = <0>;
+		qcom,remote-pid = <5>;
+
+		smp2p_cdsp_out: master-kernel {
+			qcom,entry-name = "master-kernel";
+			#qcom,smem-state-cells = <1>;
+		};
+
+		smp2p_cdsp_in: slave-kernel {
+			qcom,entry-name = "slave-kernel";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+		};
+	};
+
 	soc: soc@0 {
 		compatible = "simple-bus";
 
@@ -677,13 +743,13 @@
 			clocks = <&bi_tcxo_div2>,
 				 <&sleep_clk>,
 				 <0>,
+				 <&pcie4_phy>,
 				 <0>,
+				 <&pcie6a_phy>,
 				 <0>,
-				 <0>,
-				 <0>,
-				 <0>,
-				 <0>,
-				 <0>;
+				 <&usb_1_ss0_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
+				 <&usb_1_ss1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
+				 <&usb_1_ss2_qmpphy QMP_USB43DP_USB3_PIPE_CLK>;
 
 			power-domains = <&rpmhpd RPMHPD_CX>;
 			#clock-cells = <1>;
@@ -691,6 +757,17 @@
 			#power-domain-cells = <1>;
 		};
 
+		ipcc: mailbox@408000 {
+			compatible = "qcom,x1e80100-ipcc", "qcom,ipcc";
+			reg = <0 0x00408000 0 0x1000>;
+
+			interrupts = <GIC_SPI 229 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-controller;
+			#interrupt-cells = <3>;
+
+			#mbox-cells = <2>;
+		};
+
 		gpi_dma2: dma-controller@800000 {
 			compatible = "qcom,x1e80100-gpi-dma", "qcom,sm6350-gpi-dma";
 			reg = <0 0x00800000 0 0x60000>;
@@ -1139,7 +1216,7 @@
 				clocks = <&gcc GCC_QUPV3_WRAP2_S5_CLK>;
 				clock-names = "se";
 
-				interconnects =	<&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
+				interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS
 						 &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>,
 						<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
 						 &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>;
@@ -2428,6 +2505,126 @@
 			};
 		};
 
+		usb_1_ss0_hsphy: phy@fd3000 {
+			compatible = "qcom,x1e80100-snps-eusb2-phy",
+				     "qcom,sm8550-snps-eusb2-phy";
+			reg = <0 0x00fd3000 0 0x154>;
+			#phy-cells = <0>;
+
+			clocks = <&tcsr TCSR_USB2_1_CLKREF_EN>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_PRIM_BCR>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss0_qmpphy: phy@fd5000 {
+			compatible = "qcom,x1e80100-qmp-usb3-dp-phy";
+			reg = <0 0x00fd5000 0 0x4000>;
+
+			clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "usb3_pipe";
+
+			power-domains = <&gcc GCC_USB_0_PHY_GDSC>;
+
+			resets = <&gcc GCC_USB3_PHY_PRIM_BCR>,
+				 <&gcc GCC_USB4_0_DP0_PHY_PRIM_BCR>;
+			reset-names = "phy",
+				      "common";
+
+			#clock-cells = <1>;
+			#phy-cells = <1>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss1_hsphy: phy@fd9000 {
+			compatible = "qcom,x1e80100-snps-eusb2-phy",
+				     "qcom,sm8550-snps-eusb2-phy";
+			reg = <0 0x00fd9000 0 0x154>;
+			#phy-cells = <0>;
+
+			clocks = <&tcsr TCSR_USB2_1_CLKREF_EN>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_SEC_BCR>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss1_qmpphy: phy@fda000 {
+			compatible = "qcom,x1e80100-qmp-usb3-dp-phy";
+			reg = <0 0x00fda000 0 0x4000>;
+
+			clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "usb3_pipe";
+
+			power-domains = <&gcc GCC_USB_1_PHY_GDSC>;
+
+			resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
+				 <&gcc GCC_USB4_1_DP0_PHY_SEC_BCR>;
+			reset-names = "phy",
+				      "common";
+
+			#clock-cells = <1>;
+			#phy-cells = <1>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss2_hsphy: phy@fde000 {
+			compatible = "qcom,x1e80100-snps-eusb2-phy",
+				     "qcom,sm8550-snps-eusb2-phy";
+			reg = <0 0x00fde000 0 0x154>;
+			#phy-cells = <0>;
+
+			clocks = <&tcsr TCSR_USB2_1_CLKREF_EN>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_TERT_BCR>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss2_qmpphy: phy@fdf000 {
+			compatible = "qcom,x1e80100-qmp-usb3-dp-phy";
+			reg = <0 0x00fdf000 0 0x4000>;
+
+			clocks = <&gcc GCC_USB3_TERT_PHY_AUX_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_USB3_TERT_PHY_COM_AUX_CLK>,
+				 <&gcc GCC_USB3_TERT_PHY_PIPE_CLK>;
+			clock-names = "aux",
+				      "ref",
+				      "com_aux",
+				      "usb3_pipe";
+
+			power-domains = <&gcc GCC_USB_2_PHY_GDSC>;
+
+			resets = <&gcc GCC_USB3_PHY_TERT_BCR>,
+				 <&gcc GCC_USB4_2_DP0_PHY_TERT_BCR>;
+			reset-names = "phy",
+				      "common";
+
+			#clock-cells = <1>;
+			#phy-cells = <1>;
+
+			status = "disabled";
+		};
+
 		cnoc_main: interconnect@1500000 {
 			compatible = "qcom,x1e80100-cnoc-main";
 			reg = <0 0x1500000 0 0x14400>;
@@ -2536,12 +2733,258 @@
 			#interconnect-cells = <2>;
 		};
 
+		pcie6a: pci@1bf8000 {
+			device_type = "pci";
+			compatible = "qcom,pcie-x1e80100";
+			reg = <0 0x01bf8000 0 0x3000>,
+			      <0 0x70000000 0 0xf1d>,
+			      <0 0x70000f20 0 0xa8>,
+			      <0 0x70001000 0 0x1000>,
+			      <0 0x70100000 0 0x100000>;
+			reg-names = "parf",
+				    "dbi",
+				    "elbi",
+				    "atu",
+				    "config";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges = <0x01000000 0 0x00000000 0 0x70200000 0 0x100000>,
+				 <0x02000000 0 0x70300000 0 0x70300000 0 0x3d00000>;
+			bus-range = <0 0xff>;
+
+			dma-coherent;
+
+			linux,pci-domain = <7>;
+			num-lanes = <2>;
+
+			interrupts = <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 774 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 837 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 838 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 839 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 840 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 841 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 842 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
+
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0 0 0 0x7>;
+			interrupt-map = <0 0 0 1 &intc 0 0 0 843 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &intc 0 0 0 844 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &intc 0 0 0 845 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &intc 0 0 0 772 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&gcc GCC_PCIE_6A_AUX_CLK>,
+				 <&gcc GCC_PCIE_6A_CFG_AHB_CLK>,
+				 <&gcc GCC_PCIE_6A_MSTR_AXI_CLK>,
+				 <&gcc GCC_PCIE_6A_SLV_AXI_CLK>,
+				 <&gcc GCC_PCIE_6A_SLV_Q2A_AXI_CLK>,
+				 <&gcc GCC_CFG_NOC_PCIE_ANOC_SOUTH_AHB_CLK>,
+				 <&gcc GCC_CNOC_PCIE_SOUTH_SF_AXI_CLK>;
+			clock-names = "aux",
+				      "cfg",
+				      "bus_master",
+				      "bus_slave",
+				      "slave_q2a",
+				      "noc_aggr",
+				      "cnoc_sf_axi";
+
+			assigned-clocks = <&gcc GCC_PCIE_6A_AUX_CLK>;
+			assigned-clock-rates = <19200000>;
+
+			interconnects = <&pcie_south_anoc MASTER_PCIE_6A QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc_main SLAVE_PCIE_6A QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "pcie-mem",
+					     "cpu-pcie";
+
+			resets = <&gcc GCC_PCIE_6A_BCR>,
+				 <&gcc GCC_PCIE_6A_LINK_DOWN_BCR>;
+			reset-names = "pci",
+				      "link_down";
+
+			power-domains = <&gcc GCC_PCIE_6A_GDSC>;
+
+			phys = <&pcie6a_phy>;
+			phy-names = "pciephy";
+
+			status = "disabled";
+		};
+
+		pcie6a_phy: phy@1bfc000 {
+			compatible = "qcom,x1e80100-qmp-gen4x2-pcie-phy";
+			reg = <0 0x01bfc000 0 0x2000>;
+
+			clocks = <&gcc GCC_PCIE_6A_PHY_AUX_CLK>,
+				 <&gcc GCC_PCIE_6A_CFG_AHB_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_PCIE_6A_PHY_RCHNG_CLK>,
+				 <&gcc GCC_PCIE_6A_PIPE_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb",
+				      "ref",
+				      "rchng",
+				      "pipe";
+
+			resets = <&gcc GCC_PCIE_6A_PHY_BCR>,
+				 <&gcc GCC_PCIE_6A_NOCSR_COM_PHY_BCR>;
+			reset-names = "phy",
+				      "phy_nocsr";
+
+			assigned-clocks = <&gcc GCC_PCIE_6A_PHY_RCHNG_CLK>;
+			assigned-clock-rates = <100000000>;
+
+			power-domains = <&gcc GCC_PCIE_6_PHY_GDSC>;
+
+			#clock-cells = <0>;
+			clock-output-names = "pcie6a_pipe_clk";
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		pcie4: pci@1c08000 {
+			device_type = "pci";
+			compatible = "qcom,pcie-x1e80100";
+			reg = <0 0x01c08000 0 0x3000>,
+			      <0 0x7c000000 0 0xf1d>,
+			      <0 0x7c000f40 0 0xa8>,
+			      <0 0x7c001000 0 0x1000>,
+			      <0 0x7c100000 0 0x100000>,
+			      <0 0x01c0b000 0 0x1000>;
+			reg-names = "parf",
+			            "dbi",
+				    "elbi",
+				    "atu",
+				    "config",
+				    "mhi";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			ranges = <0x01000000 0 0x00000000 0 0x7c200000 0 0x100000>,
+				 <0x02000000 0 0x7c300000 0 0x7c300000 0 0x3d00000>;
+			bus-range = <0x00 0xff>;
+
+			dma-coherent;
+
+			linux,pci-domain = <5>;
+			num-lanes = <2>;
+
+			interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "msi0",
+					  "msi1",
+					  "msi2",
+					  "msi3",
+					  "msi4",
+					  "msi5",
+					  "msi6",
+					  "msi7";
+
+			#interrupt-cells = <1>;
+			interrupt-map-mask = <0 0 0 0x7>;
+			interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &intc 0 0 0 150 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &intc 0 0 0 151 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &intc 0 0 0 152 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&gcc GCC_PCIE_4_AUX_CLK>,
+				 <&gcc GCC_PCIE_4_CFG_AHB_CLK>,
+				 <&gcc GCC_PCIE_4_MSTR_AXI_CLK>,
+				 <&gcc GCC_PCIE_4_SLV_AXI_CLK>,
+				 <&gcc GCC_PCIE_4_SLV_Q2A_AXI_CLK>,
+				 <&gcc GCC_CFG_NOC_PCIE_ANOC_NORTH_AHB_CLK>,
+				 <&gcc GCC_CNOC_PCIE_NORTH_SF_AXI_CLK>;
+			clock-names = "aux",
+				      "cfg",
+				      "bus_master",
+				      "bus_slave",
+				      "slave_q2a",
+				      "noc_aggr",
+				      "cnoc_sf_axi";
+
+			assigned-clocks = <&gcc GCC_PCIE_4_AUX_CLK>;
+			assigned-clock-rates = <19200000>;
+
+			interconnects = <&pcie_south_anoc MASTER_PCIE_4 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &cnoc_main SLAVE_PCIE_4 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "pcie-mem",
+					     "cpu-pcie";
+
+			resets = <&gcc GCC_PCIE_4_BCR>,
+				 <&gcc GCC_PCIE_4_LINK_DOWN_BCR>;
+			reset-names = "pci",
+				      "link_down";
+
+			power-domains = <&gcc GCC_PCIE_4_GDSC>;
+
+			phys = <&pcie4_phy>;
+			phy-names = "pciephy";
+
+			status = "disabled";
+		};
+
+		pcie4_phy: phy@1c0e000 {
+			compatible = "qcom,x1e80100-qmp-gen3x2-pcie-phy";
+			reg = <0 0x01c0e000 0 0x2000>;
+
+			clocks = <&gcc GCC_PCIE_4_AUX_CLK>,
+				 <&gcc GCC_PCIE_4_CFG_AHB_CLK>,
+				 <&rpmhcc RPMH_CXO_CLK>,
+				 <&gcc GCC_PCIE_4_PHY_RCHNG_CLK>,
+				 <&gcc GCC_PCIE_4_PIPE_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb",
+				      "ref",
+				      "rchng",
+				      "pipe";
+
+			resets = <&gcc GCC_PCIE_4_PHY_BCR>;
+			reset-names = "phy";
+
+			assigned-clocks = <&gcc GCC_PCIE_4_PHY_RCHNG_CLK>;
+			assigned-clock-rates = <100000000>;
+
+			power-domains = <&gcc GCC_PCIE_4_PHY_GDSC>;
+
+			#clock-cells = <0>;
+			clock-output-names = "pcie4_pipe_clk";
+
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
 		tcsr_mutex: hwlock@1f40000 {
 			compatible = "qcom,tcsr-mutex";
 			reg = <0 0x01f40000 0 0x20000>;
 			#hwlock-cells = <1>;
 		};
 
+		tcsr: clock-controller@1fc0000 {
+			compatible = "qcom,x1e80100-tcsr", "syscon";
+			reg = <0 0x01fc0000 0 0x30000>;
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+		};
+
 		gem_noc: interconnect@26400000 {
 			compatible = "qcom,x1e80100-gem-noc";
 			reg = <0 0x26400000 0 0x311200>;
@@ -2560,6 +3003,331 @@
 			#interconnect-cells = <2>;
 		};
 
+		lpass_wsa2macro: codec@6aa0000 {
+			compatible = "qcom,x1e80100-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro";
+			reg = <0 0x06aa0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_WSA2_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "wsa2-mclk";
+			#sound-dai-cells = <1>;
+			sound-name-prefix = "WSA2";
+		};
+
+		swr3: soundwire@6ab0000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06ab0000 0 0x10000>;
+			clocks = <&lpass_wsa2macro>;
+			clock-names = "iface";
+			interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>;
+			label = "WSA2";
+
+			pinctrl-0 = <&wsa2_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <9>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x07 0x1f 0x3f 0x07 0x1f 0x3f 0xc8 0xff 0xff 0x0f 0x0f 0xff 0x31f>;
+			qcom,ports-offset1 =		/bits/ 8 <0x01 0x03 0x05 0x02 0x04 0x15 0x00 0xff 0xff 0x06 0x0d 0xff 0x00>;
+			qcom,ports-offset2 =		/bits/ 8 <0xff 0x07 0x1f 0xff 0x07 0x1f 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x18>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0x00 0x01 0x01 0x00 0x01 0x01 0x00 0x00 0x00 0x01 0x01 0x00 0x00>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_rxmacro: codec@6ac0000 {
+			compatible = "qcom,x1e80100-lpass-rx-macro", "qcom,sm8550-lpass-rx-macro";
+			reg = <0 0x06ac0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_RX_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		swr1: soundwire@6ad0000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06ad0000 0 0x10000>;
+			clocks = <&lpass_rxmacro>;
+			clock-names = "iface";
+			interrupts = <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
+			label = "RX";
+
+			pinctrl-0 = <&rx_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <1>;
+			qcom,dout-ports = <11>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x03 0x1f 0x1f 0x07 0x00 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-offset1 =		/bits/ 8 <0x00 0x00 0x0b 0x01 0x00 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x0b 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0x03 0x00 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0x06 0x0f 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-word-length =	/bits/ 8 <0x01 0x07 0x04 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0x00 0x01 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0x01 0x00 0x00 0x00 0x00 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_txmacro: codec@6ae0000 {
+			compatible = "qcom,x1e80100-lpass-tx-macro", "qcom,sm8550-lpass-tx-macro";
+			reg = <0 0x06ae0000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+		};
+
+		lpass_wsamacro: codec@6b00000 {
+			compatible = "qcom,x1e80100-lpass-wsa-macro", "qcom,sm8550-lpass-wsa-macro";
+			reg = <0 0x06b00000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_WSA_CORE_TX_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&lpass_vamacro>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec",
+				      "fsgen";
+
+			#clock-cells = <0>;
+			clock-output-names = "mclk";
+			#sound-dai-cells = <1>;
+			sound-name-prefix = "WSA";
+		};
+
+		swr0: soundwire@6b10000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06b10000 0 0x10000>;
+			clocks = <&lpass_wsamacro>;
+			clock-names = "iface";
+			interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+			label = "WSA";
+
+			pinctrl-0 = <&wsa_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <9>;
+
+			qcom,ports-sinterval =		/bits/ 16 <0x07 0x1f 0x3f 0x07 0x1f 0x3f 0xc8 0xff 0xff 0x0f 0x0f 0xff 0x31f>;
+			qcom,ports-offset1 =		/bits/ 8 <0x01 0x03 0x05 0x02 0x04 0x15 0x00 0xff 0xff 0x06 0x0d 0xff 0x00>;
+			qcom,ports-offset2 =		/bits/ 8 <0xff 0x07 0x1f 0xff 0x07 0x1f 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x0f>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0x08 0xff 0xff 0xff 0xff 0xff 0x18>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0x00 0x01 0x01 0x00 0x01 0x01 0x00 0x00 0x00 0x01 0x01 0x00 0x00>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		swr2: soundwire@6d30000 {
+			compatible = "qcom,soundwire-v2.0.0";
+			reg = <0 0x06d30000 0 0x10000>;
+			clocks = <&lpass_txmacro>;
+			clock-names = "iface";
+			interrupts = <GIC_SPI 496 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 520 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "core", "wakeup";
+			label = "TX";
+
+			pinctrl-0 = <&tx_swr_active>;
+			pinctrl-names = "default";
+
+			qcom,din-ports = <4>;
+			qcom,dout-ports = <1>;
+
+			qcom,ports-sinterval-low =	/bits/ 8 <0x00 0x01 0x03 0x03 0x00>;
+			qcom,ports-offset1 =		/bits/ 8 <0x00 0x01 0x02 0x00 0x00>;
+			qcom,ports-offset2 =		/bits/ 8 <0x00 0x00 0x00 0x00 0xff>;
+			qcom,ports-hstart =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-hstop =		/bits/ 8 <0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-word-length =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-pack-mode =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-block-group-count =	/bits/ 8 <0xff 0xff 0xff 0xff 0xff>;
+			qcom,ports-lane-control =	/bits/ 8 <0xff 0x00 0x00 0x01 0xff>;
+
+			#address-cells = <2>;
+			#size-cells = <0>;
+			#sound-dai-cells = <1>;
+			status = "disabled";
+		};
+
+		lpass_vamacro: codec@6d44000 {
+			compatible = "qcom,x1e80100-lpass-va-macro", "qcom,sm8550-lpass-va-macro";
+			reg = <0 0x06d44000 0 0x1000>;
+			clocks = <&q6prmcc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+			clock-names = "mclk",
+				      "macro",
+				      "dcodec";
+
+			#clock-cells = <0>;
+			clock-output-names = "fsgen";
+			#sound-dai-cells = <1>;
+		};
+
+		lpass_tlmm: pinctrl@6e80000 {
+			compatible = "qcom,x1e80100-lpass-lpi-pinctrl", "qcom,sm8550-lpass-lpi-pinctrl";
+			reg = <0 0x06e80000 0 0x20000>,
+			      <0 0x07250000 0 0x10000>;
+
+			clocks = <&q6prmcc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+				 <&q6prmcc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+			clock-names = "core", "audio";
+
+			gpio-controller;
+			#gpio-cells = <2>;
+			gpio-ranges = <&lpass_tlmm 0 0 23>;
+
+			tx_swr_active: tx-swr-active-state {
+				clk-pins {
+					pins = "gpio0";
+					function = "swr_tx_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio1", "gpio2";
+					function = "swr_tx_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			rx_swr_active: rx-swr-active-state {
+				clk-pins {
+					pins = "gpio3";
+					function = "swr_rx_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio4", "gpio5";
+					function = "swr_rx_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			dmic01_default: dmic01-default-state {
+				clk-pins {
+					pins = "gpio6";
+					function = "dmic1_clk";
+					drive-strength = <8>;
+					output-high;
+				};
+
+				data-pins {
+					pins = "gpio7";
+					function = "dmic1_data";
+					drive-strength = <8>;
+					input-enable;
+				};
+			};
+
+			dmic23_default: dmic23-default-state {
+				clk-pins {
+					pins = "gpio8";
+					function = "dmic2_clk";
+					drive-strength = <8>;
+					output-high;
+				};
+
+				data-pins {
+					pins = "gpio9";
+					function = "dmic2_data";
+					drive-strength = <8>;
+					input-enable;
+				};
+			};
+
+			wsa_swr_active: wsa-swr-active-state {
+				clk-pins {
+					pins = "gpio10";
+					function = "wsa_swr_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio11";
+					function = "wsa_swr_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+
+			wsa2_swr_active: wsa2-swr-active-state {
+				clk-pins {
+					pins = "gpio15";
+					function = "wsa2_swr_clk";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-disable;
+				};
+
+				data-pins {
+					pins = "gpio16";
+					function = "wsa2_swr_data";
+					drive-strength = <2>;
+					slew-rate = <1>;
+					bias-bus-hold;
+				};
+			};
+		};
+
 		lpass_ag_noc: interconnect@7e40000 {
 			compatible = "qcom,x1e80100-lpass-ag-noc";
 			reg = <0 0x7e40000 0 0xE080>;
@@ -2587,6 +3355,849 @@
 			#interconnect-cells = <2>;
 		};
 
+		usb_2_hsphy: phy@88e0000 {
+			compatible = "qcom,x1e80100-snps-eusb2-phy",
+				     "qcom,sm8550-snps-eusb2-phy";
+			reg = <0 0x088e0000 0 0x154>;
+			#phy-cells = <0>;
+
+			clocks = <&tcsr TCSR_USB2_2_CLKREF_EN>;
+			clock-names = "ref";
+
+			resets = <&gcc GCC_QUSB2PHY_USB20_HS_BCR>;
+
+			status = "disabled";
+		};
+
+		usb_1_ss2: usb@a0f8800 {
+			compatible = "qcom,x1e80100-dwc3", "qcom,dwc3";
+			reg = <0 0x0a0f8800 0 0x400>;
+
+			clocks = <&gcc GCC_CFG_NOC_USB3_TERT_AXI_CLK>,
+				 <&gcc GCC_USB30_TERT_MASTER_CLK>,
+				 <&gcc GCC_AGGRE_USB3_TERT_AXI_CLK>,
+				 <&gcc GCC_USB30_TERT_SLEEP_CLK>,
+				 <&gcc GCC_USB30_TERT_MOCK_UTMI_CLK>,
+				 <&gcc GCC_AGGRE_USB_NOC_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_NORTH_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_SOUTH_AXI_CLK>,
+				 <&gcc GCC_SYS_NOC_USB_AXI_CLK>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi",
+				      "noc_aggr",
+				      "noc_aggr_north",
+				      "noc_aggr_south",
+				      "noc_sys";
+
+			assigned-clocks = <&gcc GCC_USB30_TERT_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_TERT_MASTER_CLK>;
+			assigned-clock-rates = <19200000>,
+					       <200000000>;
+
+			interrupts-extended = <&intc GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 58 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 57 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 10 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
+
+			power-domains = <&gcc GCC_USB30_TERT_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			resets = <&gcc GCC_USB30_TERT_BCR>;
+
+			interconnects = <&usb_south_anoc MASTER_USB3_2 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_USB3_2 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
+
+			wakeup-source;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			usb_1_ss2_dwc3: usb@a000000 {
+				compatible = "snps,dwc3";
+				reg = <0 0x0a000000 0 0xcd00>;
+
+				interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+
+				iommus = <&apps_smmu 0x14a0 0x0>;
+
+				phys = <&usb_1_ss2_hsphy>,
+				       <&usb_1_ss2_qmpphy QMP_USB43DP_USB3_PHY>;
+				phy-names = "usb2-phy",
+				            "usb3-phy";
+
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
+				snps,usb3_lpm_capable;
+
+				dma-coherent;
+
+				port {
+					usb_1_ss2_role_switch: endpoint {
+					};
+				};
+			};
+		};
+
+		usb_2: usb@a2f8800 {
+			compatible = "qcom,x1e80100-dwc3", "qcom,dwc3";
+			reg = <0 0x0a2f8800 0 0x400>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			clocks = <&gcc GCC_CFG_NOC_USB2_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB20_MASTER_CLK>,
+				 <&gcc GCC_AGGRE_USB2_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB20_SLEEP_CLK>,
+				 <&gcc GCC_USB20_MOCK_UTMI_CLK>,
+				 <&gcc GCC_AGGRE_USB_NOC_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_NORTH_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_SOUTH_AXI_CLK>,
+				 <&gcc GCC_SYS_NOC_USB_AXI_CLK>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi",
+				      "noc_aggr",
+				      "noc_aggr_north",
+				      "noc_aggr_south",
+				      "noc_sys";
+
+			assigned-clocks = <&gcc GCC_USB20_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB20_MASTER_CLK>;
+			assigned-clock-rates = <19200000>, <200000000>;
+
+			interrupts-extended = <&intc GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 50 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 49 IRQ_TYPE_EDGE_BOTH>;
+			interrupt-names = "pwr_event",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq";
+
+			power-domains = <&gcc GCC_USB20_PRIM_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			resets = <&gcc GCC_USB20_PRIM_BCR>;
+
+			interconnects = <&usb_north_anoc MASTER_USB2 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_USB2 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
+
+			wakeup-source;
+
+			status = "disabled";
+
+			usb_2_dwc3: usb@a200000 {
+				compatible = "snps,dwc3";
+				reg = <0 0x0a200000 0 0xcd00>;
+				interrupts = <GIC_SPI 241 IRQ_TYPE_LEVEL_HIGH>;
+				iommus = <&apps_smmu 0x14e0 0x0>;
+				phys = <&usb_2_hsphy>;
+				phy-names = "usb2-phy";
+				maximum-speed = "high-speed";
+
+				port {
+					usb_2_role_switch: endpoint {
+					};
+				};
+			};
+		};
+
+		usb_1_ss0: usb@a6f8800 {
+			compatible = "qcom,x1e80100-dwc3", "qcom,dwc3";
+			reg = <0 0x0a6f8800 0 0x400>;
+
+			clocks = <&gcc GCC_CFG_NOC_USB3_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB30_PRIM_MASTER_CLK>,
+				 <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>,
+				 <&gcc GCC_USB30_PRIM_SLEEP_CLK>,
+				 <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+				 <&gcc GCC_AGGRE_USB_NOC_AXI_CLK>,
+				 <&gcc GCC_CFG_NOC_USB_ANOC_NORTH_AHB_CLK>,
+				 <&gcc GCC_CFG_NOC_USB_ANOC_SOUTH_AHB_CLK>,
+				 <&gcc GCC_SYS_NOC_USB_AXI_CLK>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi",
+				      "noc_aggr",
+				      "noc_aggr_north",
+				      "noc_aggr_south",
+				      "noc_sys";
+
+			assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_PRIM_MASTER_CLK>;
+			assigned-clock-rates = <19200000>,
+					       <200000000>;
+
+			interrupts-extended = <&intc GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 61 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 15 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 17 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
+
+			power-domains = <&gcc GCC_USB30_PRIM_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			resets = <&gcc GCC_USB30_PRIM_BCR>;
+
+			wakeup-source;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			usb_1_ss0_dwc3: usb@a600000 {
+				compatible = "snps,dwc3";
+				reg = <0 0x0a600000 0 0xcd00>;
+
+				interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+
+				iommus = <&apps_smmu 0x1420 0x0>;
+
+				phys = <&usb_1_ss0_hsphy>,
+				       <&usb_1_ss0_qmpphy QMP_USB43DP_USB3_PHY>;
+				phy-names = "usb2-phy",
+					    "usb3-phy";
+
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
+				snps,usb3_lpm_capable;
+
+				dma-coherent;
+
+				port {
+					usb_1_ss0_role_switch: endpoint {
+					};
+				};
+			};
+		};
+
+		usb_1_ss1: usb@a8f8800 {
+			compatible = "qcom,x1e80100-dwc3", "qcom,dwc3";
+			reg = <0 0x0a8f8800 0 0x400>;
+
+			clocks = <&gcc GCC_CFG_NOC_USB3_SEC_AXI_CLK>,
+				 <&gcc GCC_USB30_SEC_MASTER_CLK>,
+				 <&gcc GCC_AGGRE_USB3_SEC_AXI_CLK>,
+				 <&gcc GCC_USB30_SEC_SLEEP_CLK>,
+				 <&gcc GCC_USB30_SEC_MOCK_UTMI_CLK>,
+				 <&gcc GCC_AGGRE_USB_NOC_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_NORTH_AXI_CLK>,
+				 <&gcc GCC_AGGRE_NOC_USB_SOUTH_AXI_CLK>,
+				 <&gcc GCC_SYS_NOC_USB_AXI_CLK>;
+			clock-names = "cfg_noc",
+				      "core",
+				      "iface",
+				      "sleep",
+				      "mock_utmi",
+				      "noc_aggr",
+				      "noc_aggr_north",
+				      "noc_aggr_south",
+				      "noc_sys";
+
+			assigned-clocks = <&gcc GCC_USB30_SEC_MOCK_UTMI_CLK>,
+					  <&gcc GCC_USB30_SEC_MASTER_CLK>;
+			assigned-clock-rates = <19200000>,
+					       <200000000>;
+
+			interrupts-extended = <&intc GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>,
+					      <&pdc 60 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 11 IRQ_TYPE_EDGE_BOTH>,
+					      <&pdc 47 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "pwr_event",
+					  "dp_hs_phy_irq",
+					  "dm_hs_phy_irq",
+					  "ss_phy_irq";
+
+			power-domains = <&gcc GCC_USB30_SEC_GDSC>;
+			required-opps = <&rpmhpd_opp_nom>;
+
+			resets = <&gcc GCC_USB30_SEC_BCR>;
+
+			interconnects = <&usb_south_anoc MASTER_USB3_1 QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
+					 &config_noc SLAVE_USB3_1 QCOM_ICC_TAG_ALWAYS>;
+			interconnect-names = "usb-ddr",
+					     "apps-usb";
+
+			wakeup-source;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			usb_1_ss1_dwc3: usb@a800000 {
+				compatible = "snps,dwc3";
+				reg = <0 0x0a800000 0 0xcd00>;
+
+				interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+
+				iommus = <&apps_smmu 0x1460 0x0>;
+
+				phys = <&usb_1_ss1_hsphy>,
+				       <&usb_1_ss1_qmpphy QMP_USB43DP_USB3_PHY>;
+				phy-names = "usb2-phy",
+					    "usb3-phy";
+
+				snps,dis_u2_susphy_quirk;
+				snps,dis_enblslpm_quirk;
+				snps,usb3_lpm_capable;
+
+				dma-coherent;
+
+				port {
+					usb_1_ss1_role_switch: endpoint {
+					};
+				};
+			};
+		};
+
+		mdss: display-subsystem@ae00000 {
+			compatible = "qcom,x1e80100-mdss";
+			reg = <0 0x0ae00000 0 0x1000>;
+			reg-names = "mdss";
+
+			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+
+			clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&gcc GCC_DISP_HF_AXI_CLK>,
+				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
+
+			resets = <&dispcc DISP_CC_MDSS_CORE_BCR>;
+
+			interconnects = <&mmss_noc MASTER_MDP QCOM_ICC_TAG_ALWAYS
+					 &gem_noc SLAVE_LLCC QCOM_ICC_TAG_ALWAYS>,
+					<&mc_virt MASTER_LLCC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+					<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ACTIVE_ONLY
+					 &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ACTIVE_ONLY>;
+			interconnect-names = "mdp0-mem",
+					     "mdp1-mem",
+					     "cpu-cfg";
+
+			power-domains = <&dispcc MDSS_GDSC>;
+
+			iommus = <&apps_smmu 0x1c00 0x2>;
+
+			interrupt-controller;
+			#interrupt-cells = <1>;
+
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+
+			status = "disabled";
+
+			mdss_mdp: display-controller@ae01000 {
+				compatible = "qcom,x1e80100-dpu";
+				reg = <0 0x0ae01000 0 0x8f000>,
+				      <0 0x0aeb0000 0 0x2008>;
+				reg-names = "mdp",
+					    "vbif";
+
+				interrupts-extended = <&mdss 0>;
+
+				clocks = <&gcc GCC_DISP_HF_AXI_CLK>,
+					 <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_LUT_CLK>,
+					 <&dispcc DISP_CC_MDSS_MDP_CLK>,
+					 <&dispcc DISP_CC_MDSS_VSYNC_CLK>;
+				clock-names = "nrt_bus",
+					      "iface",
+					      "lut",
+					      "core",
+					      "vsync";
+
+				operating-points-v2 = <&mdp_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_intf0_out: endpoint {
+							remote-endpoint = <&mdss_dp0_in>;
+						};
+					};
+
+					port@4 {
+						reg = <4>;
+
+						mdss_intf4_out: endpoint {
+							remote-endpoint = <&mdss_dp1_in>;
+						};
+					};
+
+					port@5 {
+						reg = <5>;
+
+						mdss_intf5_out: endpoint {
+							remote-endpoint = <&mdss_dp3_in>;
+						};
+					};
+
+					port@6 {
+						reg = <6>;
+
+						mdss_intf6_out: endpoint {
+							remote-endpoint = <&mdss_dp2_in>;
+						};
+					};
+				};
+
+				mdp_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-200000000 {
+						opp-hz = /bits/ 64 <200000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-325000000 {
+						opp-hz = /bits/ 64 <325000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-375000000 {
+						opp-hz = /bits/ 64 <375000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-514000000 {
+						opp-hz = /bits/ 64 <514000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+
+					opp-575000000 {
+						opp-hz = /bits/ 64 <575000000>;
+						required-opps = <&rpmhpd_opp_nom_l1>;
+					};
+				};
+			};
+
+			mdss_dp0: displayport-controller@ae90000 {
+				compatible = "qcom,x1e80100-dp";
+				reg = <0 0xae90000 0 0x200>,
+				      <0 0xae90200 0 0x200>,
+				      <0 0xae90400 0 0x600>,
+				      <0 0xae91000 0 0x400>,
+				      <0 0xae91400 0 0x400>;
+
+				interrupts-extended = <&mdss 12>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX0_PIXEL0_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX0_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC>;
+				assigned-clock-parents = <&usb_1_ss0_qmpphy QMP_USB43DP_DP_LINK_CLK>,
+							 <&usb_1_ss0_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>;
+
+				operating-points-v2 = <&mdss_dp0_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&usb_1_ss0_qmpphy QMP_USB43DP_DP_PHY>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dp0_in: endpoint {
+							remote-endpoint = <&mdss_intf0_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dp0_out: endpoint {
+						};
+					};
+				};
+
+				mdss_dp0_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-160000000 {
+						opp-hz = /bits/ 64 <160000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dp1: displayport-controller@ae98000 {
+				compatible = "qcom,x1e80100-dp";
+				reg = <0 0xae98000 0 0x200>,
+				      <0 0xae98200 0 0x200>,
+				      <0 0xae98400 0 0x600>,
+				      <0 0xae99000 0 0x400>,
+				      <0 0xae99400 0 0x400>;
+
+				interrupts-extended = <&mdss 13>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX1_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX1_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX1_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX1_PIXEL0_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX1_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC>;
+				assigned-clock-parents = <&usb_1_ss1_qmpphy QMP_USB43DP_DP_LINK_CLK>,
+							 <&usb_1_ss1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>;
+
+				operating-points-v2 = <&mdss_dp1_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&usb_1_ss1_qmpphy QMP_USB43DP_DP_PHY>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dp1_in: endpoint {
+							remote-endpoint = <&mdss_intf4_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+
+						mdss_dp1_out: endpoint {
+						};
+					};
+				};
+
+				mdss_dp1_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-160000000 {
+						opp-hz = /bits/ 64 <160000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dp2: displayport-controller@ae9a000 {
+				compatible = "qcom,x1e80100-dp";
+				reg = <0 0xae9a000 0 0x200>,
+				      <0 0xae9a200 0 0x200>,
+				      <0 0xae9a400 0 0x600>,
+				      <0 0xae9b000 0 0x400>,
+				      <0 0xae9b400 0 0x400>;
+
+				interrupts-extended = <&mdss 14>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX2_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX2_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX2_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX2_PIXEL0_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX2_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dp2_phy 0>,
+							 <&mdss_dp2_phy 1>;
+
+				operating-points-v2 = <&mdss_dp2_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&mdss_dp2_phy>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+						mdss_dp2_in: endpoint {
+							remote-endpoint = <&mdss_intf6_out>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+					};
+				};
+
+				mdss_dp2_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-160000000 {
+						opp-hz = /bits/ 64 <160000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+			mdss_dp3: displayport-controller@aea0000 {
+				compatible = "qcom,x1e80100-dp";
+				reg = <0 0xaea0000 0 0x200>,
+				      <0 0xaea0200 0 0x200>,
+				      <0 0xaea0400 0 0x600>,
+				      <0 0xaea1000 0 0x400>,
+				      <0 0xaea1400 0 0x400>;
+
+				interrupts-extended = <&mdss 15>;
+
+				clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX3_AUX_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX3_LINK_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX3_LINK_INTF_CLK>,
+					 <&dispcc DISP_CC_MDSS_DPTX3_PIXEL0_CLK>;
+				clock-names = "core_iface",
+					      "core_aux",
+					      "ctrl_link",
+					      "ctrl_link_iface",
+					      "stream_pixel";
+
+				assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX3_LINK_CLK_SRC>,
+						  <&dispcc DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC>;
+				assigned-clock-parents = <&mdss_dp3_phy 0>,
+							 <&mdss_dp3_phy 1>;
+
+				operating-points-v2 = <&mdss_dp3_opp_table>;
+
+				power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+				phys = <&mdss_dp3_phy>;
+				phy-names = "dp";
+
+				#sound-dai-cells = <0>;
+
+				status = "disabled";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					port@0 {
+						reg = <0>;
+
+						mdss_dp3_in: endpoint {
+							remote-endpoint = <&mdss_intf5_out>;
+
+							link-frequencies = /bits/ 64 <8100000000>;
+						};
+					};
+
+					port@1 {
+						reg = <1>;
+					};
+				};
+
+				mdss_dp3_opp_table: opp-table {
+					compatible = "operating-points-v2";
+
+					opp-160000000 {
+						opp-hz = /bits/ 64 <160000000>;
+						required-opps = <&rpmhpd_opp_low_svs>;
+					};
+
+					opp-270000000 {
+						opp-hz = /bits/ 64 <270000000>;
+						required-opps = <&rpmhpd_opp_svs>;
+					};
+
+					opp-540000000 {
+						opp-hz = /bits/ 64 <540000000>;
+						required-opps = <&rpmhpd_opp_svs_l1>;
+					};
+
+					opp-810000000 {
+						opp-hz = /bits/ 64 <810000000>;
+						required-opps = <&rpmhpd_opp_nom>;
+					};
+				};
+			};
+
+		};
+
+		mdss_dp2_phy: phy@aec2a00 {
+			compatible = "qcom,x1e80100-dp-phy";
+			reg = <0 0x0aec2a00 0 0x19c>,
+			      <0 0x0aec2200 0 0xec>,
+			      <0 0x0aec2600 0 0xec>,
+			      <0 0x0aec2000 0 0x1c8>;
+
+			clocks = <&dispcc DISP_CC_MDSS_DPTX2_AUX_CLK>,
+				 <&dispcc DISP_CC_MDSS_AHB_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb";
+
+			power-domains = <&rpmhpd RPMHPD_MX>;
+
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		mdss_dp3_phy: phy@aec5a00 {
+			compatible = "qcom,x1e80100-dp-phy";
+			reg = <0 0x0aec5a00 0 0x19c>,
+			      <0 0x0aec5200 0 0xec>,
+			      <0 0x0aec5600 0 0xec>,
+			      <0 0x0aec5000 0 0x1c8>;
+
+			clocks = <&dispcc DISP_CC_MDSS_DPTX3_AUX_CLK>,
+				 <&dispcc DISP_CC_MDSS_AHB_CLK>;
+			clock-names = "aux",
+				      "cfg_ahb";
+
+			power-domains = <&rpmhpd RPMHPD_MX>;
+
+			#clock-cells = <1>;
+			#phy-cells = <0>;
+
+			status = "disabled";
+		};
+
+		dispcc: clock-controller@af00000 {
+			compatible = "qcom,x1e80100-dispcc";
+			reg = <0 0x0af00000 0 0x20000>;
+			clocks = <&bi_tcxo_div2>,
+				 <&bi_tcxo_ao_div2>,
+				 <&gcc GCC_DISP_AHB_CLK>,
+				 <&sleep_clk>,
+				 <0>, /* dsi0 */
+				 <0>,
+				 <0>, /* dsi1 */
+				 <0>,
+				 <&usb_1_ss0_qmpphy QMP_USB43DP_DP_LINK_CLK>, /* dp0 */
+				 <&usb_1_ss0_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+				 <&usb_1_ss1_qmpphy QMP_USB43DP_DP_LINK_CLK>, /* dp1 */
+				 <&usb_1_ss1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+				 <&mdss_dp2_phy 0>, /* dp2 */
+				 <&mdss_dp2_phy 1>,
+				 <&mdss_dp3_phy 0>, /* dp3 */
+				 <&mdss_dp3_phy 1>;
+			power-domains = <&rpmhpd RPMHPD_MMCX>;
+			required-opps = <&rpmhpd_opp_low_svs>;
+			#clock-cells = <1>;
+			#reset-cells = <1>;
+			#power-domain-cells = <1>;
+		};
+
 		pdc: interrupt-controller@b220000 {
 			compatible = "qcom,x1e80100-pdc", "qcom,pdc";
 			reg = <0 0x0b220000 0 0x30000>, <0 0x174000f0 0 0x64>;
@@ -2599,6 +4210,18 @@
 			interrupt-controller;
 		};
 
+		aoss_qmp: power-management@c300000 {
+			compatible = "qcom,x1e80100-aoss-qmp", "qcom,aoss-qmp";
+			reg = <0 0x0c300000 0 0x400>;
+			interrupt-parent = <&ipcc>;
+			interrupts-extended = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP
+						     IRQ_TYPE_EDGE_RISING>;
+			mboxes = <&ipcc IPCC_CLIENT_AOP IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+			#clock-cells = <0>;
+		};
+
+
 		tlmm: pinctrl@f100000 {
 			compatible = "qcom,x1e80100-tlmm";
 			reg = <0 0x0f100000 0 0xf00000>;
@@ -3170,7 +4793,7 @@
 				/* TX, RX */
 				pins = "gpio86", "gpio87";
 				function = "qup2_se5";
-				drive-strength= <2>;
+				drive-strength = <2>;
 				bias-disable;
 			};
 		};
@@ -3315,7 +4938,6 @@
 			      <0 0x17510000 0 0x10000>,
 			      <0 0x17520000 0 0x10000>;
 			reg-names = "drv-0", "drv-1", "drv-2";
-			qcom,drv-count = <3>;
 
 			interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
@@ -3326,6 +4948,7 @@
 					  <WAKE_TCS      2>, <CONTROL_TCS   0>;
 
 			label = "apps_rsc";
+			power-domains = <&SYSTEM_PD>;
 
 			apps_bcm_voter: bcm-voter {
 				compatible = "qcom,bcm-voter";
@@ -3514,6 +5137,144 @@
 				    "llcc_broadcast_base";
 			interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
 		};
+
+		remoteproc_adsp: remoteproc@30000000 {
+			compatible = "qcom,x1e80100-adsp-pas";
+			reg = <0 0x30000000 0 0x100>;
+
+			interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog",
+					  "fatal",
+					  "ready",
+					  "handover",
+					  "stop-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			power-domains = <&rpmhpd RPMHPD_LCX>,
+					<&rpmhpd RPMHPD_LMX>;
+			power-domain-names = "lcx",
+					     "lmx";
+
+			interconnects = <&lpass_lpicx_noc MASTER_LPASS_PROC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+
+			memory-region = <&adspslpi_mem>,
+					<&q6_adsp_dtb_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&smp2p_adsp_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_LPASS
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+				mboxes = <&ipcc IPCC_CLIENT_LPASS
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				label = "lpass";
+				qcom,remote-pid = <2>;
+
+				gpr {
+					compatible = "qcom,gpr";
+					qcom,glink-channels = "adsp_apps";
+					qcom,domain = <GPR_DOMAIN_ID_ADSP>;
+					qcom,intents = <512 20>;
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					q6apm: service@1 {
+						compatible = "qcom,q6apm";
+						reg = <GPR_APM_MODULE_IID>;
+						#sound-dai-cells = <0>;
+						qcom,protection-domain = "avs/audio",
+									 "msm/adsp/audio_pd";
+
+						q6apmbedai: bedais {
+							compatible = "qcom,q6apm-lpass-dais";
+							#sound-dai-cells = <1>;
+						};
+
+						q6apmdai: dais {
+							compatible = "qcom,q6apm-dais";
+							iommus = <&apps_smmu 0x1001 0x80>,
+								 <&apps_smmu 0x1061 0x0>;
+						};
+					};
+
+					q6prm: service@2 {
+						compatible = "qcom,q6prm";
+						reg = <GPR_PRM_MODULE_IID>;
+						qcom,protection-domain = "avs/audio",
+									 "msm/adsp/audio_pd";
+
+						q6prmcc: clock-controller {
+							compatible = "qcom,q6prm-lpass-clocks";
+							#clock-cells = <2>;
+						};
+					};
+				};
+			};
+		};
+
+		remoteproc_cdsp: remoteproc@32300000 {
+			compatible = "qcom,x1e80100-cdsp-pas";
+			reg = <0 0x32300000 0 0x1400000>;
+
+			interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>,
+					      <&smp2p_cdsp_in 3 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "wdog",
+					  "fatal",
+					  "ready",
+					  "handover",
+					  "stop-ack";
+
+			clocks = <&rpmhcc RPMH_CXO_CLK>;
+			clock-names = "xo";
+
+			power-domains = <&rpmhpd RPMHPD_CX>,
+					<&rpmhpd RPMHPD_MXC>,
+					<&rpmhpd RPMHPD_NSP>;
+			power-domain-names = "cx",
+					     "mxc",
+					     "nsp";
+
+			interconnects = <&nsp_noc MASTER_CDSP_PROC QCOM_ICC_TAG_ALWAYS
+					 &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>;
+
+			memory-region = <&cdsp_mem>,
+					<&q6_cdsp_dtb_mem>;
+
+			qcom,qmp = <&aoss_qmp>;
+
+			qcom,smem-states = <&smp2p_cdsp_out 0>;
+			qcom,smem-state-names = "stop";
+
+			status = "disabled";
+
+			glink-edge {
+				interrupts-extended = <&ipcc IPCC_CLIENT_CDSP
+							     IPCC_MPROC_SIGNAL_GLINK_QMP
+							     IRQ_TYPE_EDGE_RISING>;
+				mboxes = <&ipcc IPCC_CLIENT_CDSP
+						IPCC_MPROC_SIGNAL_GLINK_QMP>;
+
+				label = "cdsp";
+				qcom,remote-pid = <5>;
+			};
+		};
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/renesas/Makefile b/arch/arm64/boot/dts/renesas/Makefile
index 8ea68d582710..5f3e0e61d78d 100644
--- a/arch/arm64/boot/dts/renesas/Makefile
+++ b/arch/arm64/boot/dts/renesas/Makefile
@@ -82,10 +82,15 @@ dtb-$(CONFIG_ARCH_R8A779F0) += r8a779f0-spider.dtb
 dtb-$(CONFIG_ARCH_R8A779F0) += r8a779f4-s4sk.dtb
 
 dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk.dtb
+dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-cpu.dtb
 dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-ard-audio-da7212.dtbo
 r8a779g0-white-hawk-ard-audio-da7212-dtbs := r8a779g0-white-hawk.dtb r8a779g0-white-hawk-ard-audio-da7212.dtbo
 dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g0-white-hawk-ard-audio-da7212.dtb
 
+dtb-$(CONFIG_ARCH_R8A779G0) += r8a779g2-white-hawk-single.dtb
+
+dtb-$(CONFIG_ARCH_R8A779H0) += r8a779h0-gray-hawk-single.dtb
+
 dtb-$(CONFIG_ARCH_R8A77951) += r8a779m1-salvator-xs.dtb
 r8a779m1-salvator-xs-panel-aa104xd12-dtbs := r8a779m1-salvator-xs.dtb salvator-panel-aa104xd12.dtbo
 dtb-$(CONFIG_ARCH_R8A77951) += r8a779m1-salvator-xs-panel-aa104xd12.dtb
@@ -103,7 +108,10 @@ r8a779m5-salvator-xs-panel-aa104xd12-dtbs := r8a779m5-salvator-xs.dtb salvator-p
 dtb-$(CONFIG_ARCH_R8A77965) += r8a779m5-salvator-xs-panel-aa104xd12.dtb
 
 dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043u11-smarc.dtb
+dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043u11-smarc-cru-csi-ov5645.dtbo
 dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043-smarc-pmod.dtbo
+r9a07g043u11-smarc-cru-csi-ov5645-dtbs := r9a07g043u11-smarc.dtb r9a07g043u11-smarc-cru-csi-ov5645.dtbo
+dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043u11-smarc-cru-csi-ov5645.dtb
 r9a07g043u11-smarc-pmod-dtbs := r9a07g043u11-smarc.dtb r9a07g043-smarc-pmod.dtbo
 dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043u11-smarc-pmod.dtb
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
index 95b0a1f6debf..a8a44fe5e83b 100644
--- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi
@@ -529,6 +529,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
@@ -541,7 +542,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
@@ -554,7 +557,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
@@ -568,6 +573,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
@@ -581,6 +587,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a774b1.dtsi b/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
index 786660fcdea4..4fff511e994c 100644
--- a/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774b1.dtsi
@@ -413,6 +413,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774B1_PD_ALWAYS_ON>;
@@ -425,7 +426,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774B1_PD_ALWAYS_ON>;
@@ -438,7 +441,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774B1_PD_ALWAYS_ON>;
@@ -452,6 +457,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774B1_PD_ALWAYS_ON>;
@@ -465,6 +471,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774B1_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
index eed94ffed7c1..1ef43d78c3a5 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
@@ -384,6 +384,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
@@ -396,7 +397,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
@@ -409,7 +412,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
@@ -423,6 +428,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
@@ -436,6 +442,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
index 175e5d296da6..be55ae83944c 100644
--- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
@@ -593,6 +593,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774E1_PD_ALWAYS_ON>;
@@ -605,7 +606,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774E1_PD_ALWAYS_ON>;
@@ -618,7 +621,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774E1_PD_ALWAYS_ON>;
@@ -632,6 +637,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774E1_PD_ALWAYS_ON>;
@@ -645,6 +651,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A774E1_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77951.dtsi b/arch/arm64/boot/dts/renesas/r8a77951.dtsi
index a4260d9291ba..bea4edd17d53 100644
--- a/arch/arm64/boot/dts/renesas/r8a77951.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77951.dtsi
@@ -614,6 +614,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
@@ -626,7 +627,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
@@ -639,7 +642,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
@@ -653,6 +658,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
@@ -666,6 +672,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77960.dtsi b/arch/arm64/boot/dts/renesas/r8a77960.dtsi
index a631ead171b2..7846fea8e40d 100644
--- a/arch/arm64/boot/dts/renesas/r8a77960.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77960.dtsi
@@ -578,6 +578,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
@@ -590,7 +591,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
@@ -603,7 +606,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
@@ -617,6 +622,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
@@ -630,6 +636,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77961.dtsi b/arch/arm64/boot/dts/renesas/r8a77961.dtsi
index 7254912a241f..58f9286a5ab5 100644
--- a/arch/arm64/boot/dts/renesas/r8a77961.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77961.dtsi
@@ -578,6 +578,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77961_PD_ALWAYS_ON>;
@@ -590,7 +591,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77961_PD_ALWAYS_ON>;
@@ -603,7 +606,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77961_PD_ALWAYS_ON>;
@@ -617,6 +622,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77961_PD_ALWAYS_ON>;
@@ -630,6 +636,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77961_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
index e57b9027066e..692940662d38 100644
--- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
@@ -449,6 +449,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
@@ -461,7 +462,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
@@ -474,7 +477,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
@@ -488,6 +493,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
@@ -501,6 +507,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77970.dtsi b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
index ed6e2e47c604..d2d3cecc76d5 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77970.dtsi
@@ -328,6 +328,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
@@ -340,7 +341,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
@@ -353,7 +356,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
@@ -367,6 +372,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
@@ -380,6 +386,7 @@
 			interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77970_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
index 5ed2daaca1f0..c0ba110c74d6 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
@@ -357,6 +357,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
@@ -369,7 +370,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
@@ -382,7 +385,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
@@ -395,7 +400,9 @@
 			reg = <0 0xe6fe0000 0 0x30>;
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
@@ -408,7 +415,9 @@
 			reg = <0 0xffc00000 0 0x30>;
 			interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
index 8c2b28342387..37063e3f4e1b 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
@@ -415,6 +415,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
@@ -427,7 +428,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
@@ -440,7 +443,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
@@ -454,6 +459,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
@@ -467,6 +473,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77995.dtsi b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
index 8cf6473c63d3..89990dd8ebf7 100644
--- a/arch/arm64/boot/dts/renesas/r8a77995.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77995.dtsi
@@ -336,6 +336,7 @@
 			interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 125>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
@@ -348,7 +349,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 124>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
@@ -361,7 +364,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 123>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
@@ -375,6 +380,7 @@
 			interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 132 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 122>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
@@ -388,6 +394,7 @@
 			interrupts = <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 121>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A77995_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
index 4e67a0356497..cfa70b441e32 100644
--- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
@@ -370,6 +370,7 @@
 			interrupts = <GIC_SPI 512 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 513 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 514 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 713>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779A0_PD_ALWAYS_ON>;
@@ -382,7 +383,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 504 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 505 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 506 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 506 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 507 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 714>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779A0_PD_ALWAYS_ON>;
@@ -395,7 +398,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 508 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 509 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 510 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 510 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 511 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 715>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779A0_PD_ALWAYS_ON>;
@@ -408,7 +413,9 @@
 			reg = <0 0xe6fe0000 0 0x30>;
 			interrupts = <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 716>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779A0_PD_ALWAYS_ON>;
@@ -421,7 +428,9 @@
 			reg = <0 0xffc00000 0 0x30>;
 			interrupts = <GIC_SPI 476 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 477 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 717>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779A0_PD_ALWAYS_ON>;
@@ -658,7 +667,7 @@
 		avb0: ethernet@e6800000 {
 			compatible = "renesas,etheravb-r8a779a0",
 				     "renesas,etheravb-rcar-gen4";
-			reg = <0 0xe6800000 0 0x800>;
+			reg = <0 0xe6800000 0 0x1000>;
 			interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 257 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 258 IRQ_TYPE_LEVEL_HIGH>,
@@ -706,7 +715,7 @@
 		avb1: ethernet@e6810000 {
 			compatible = "renesas,etheravb-r8a779a0",
 				     "renesas,etheravb-rcar-gen4";
-			reg = <0 0xe6810000 0 0x800>;
+			reg = <0 0xe6810000 0 0x1000>;
 			interrupts = <GIC_SPI 281 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 283 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
index 7fb4989cce8a..72cf30341fc4 100644
--- a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
@@ -501,6 +501,7 @@
 			interrupts = <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 476 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 713>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>;
@@ -513,7 +514,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 477 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 480 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 714>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>;
@@ -526,7 +529,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 481 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 482 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 483 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 483 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 484 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 715>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>;
@@ -539,7 +544,9 @@
 			reg = <0 0xe6fe0000 0 0x30>;
 			interrupts = <GIC_SPI 485 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 716>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>;
@@ -552,7 +559,9 @@
 			reg = <0 0xffc00000 0 0x30>;
 			interrupts = <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 492 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 717>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779F0_PD_ALWAYS_ON>;
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dts b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dts
new file mode 100644
index 000000000000..c8b1bb50a8cf
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dts
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the standalone R-Car V4H White Hawk CPU board
+ *
+ * Copyright (C) 2023 Glider bv
+ */
+
+/dts-v1/;
+#include "r8a779g0-white-hawk-cpu.dtsi"
+
+/ {
+	model = "Renesas White Hawk CPU board based on r8a779g0";
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
index 913f70fe6c5c..b1fe1aedc27d 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-cpu.dtsi
@@ -1,378 +1,14 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
- * Device Tree Source for the White Hawk CPU board
+ * Device Tree Source for the R-Car V4H White Hawk CPU board
  *
  * Copyright (C) 2022 Renesas Electronics Corp.
  */
 
 #include "r8a779g0.dtsi"
-
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/input/input.h>
-#include <dt-bindings/leds/common.h>
+#include "white-hawk-cpu-common.dtsi"
 
 / {
 	model = "Renesas White Hawk CPU board";
 	compatible = "renesas,white-hawk-cpu", "renesas,r8a779g0";
-
-	aliases {
-		ethernet0 = &avb0;
-		serial0 = &hscif0;
-	};
-
-	chosen {
-		bootargs = "ignore_loglevel rw root=/dev/nfs ip=on";
-		stdout-path = "serial0:921600n8";
-	};
-
-	keys {
-		compatible = "gpio-keys";
-
-		pinctrl-0 = <&keys_pins>;
-		pinctrl-names = "default";
-
-		key-1 {
-			gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_1>;
-			label = "SW47";
-			wakeup-source;
-			debounce-interval = <20>;
-		};
-
-		key-2 {
-			gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_2>;
-			label = "SW48";
-			wakeup-source;
-			debounce-interval = <20>;
-		};
-
-		key-3 {
-			gpios = <&gpio5 2 GPIO_ACTIVE_LOW>;
-			linux,code = <KEY_3>;
-			label = "SW49";
-			wakeup-source;
-			debounce-interval = <20>;
-		};
-	};
-
-	leds {
-		compatible = "gpio-leds";
-
-		led-1 {
-			gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
-			color = <LED_COLOR_ID_GREEN>;
-			function = LED_FUNCTION_INDICATOR;
-			function-enumerator = <1>;
-		};
-
-		led-2 {
-			gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
-			color = <LED_COLOR_ID_GREEN>;
-			function = LED_FUNCTION_INDICATOR;
-			function-enumerator = <2>;
-		};
-
-		led-3 {
-			gpios = <&gpio7 2 GPIO_ACTIVE_HIGH>;
-			color = <LED_COLOR_ID_GREEN>;
-			function = LED_FUNCTION_INDICATOR;
-			function-enumerator = <3>;
-		};
-	};
-
-	memory@48000000 {
-		device_type = "memory";
-		/* first 128MB is reserved for secure area. */
-		reg = <0x0 0x48000000 0x0 0x78000000>;
-	};
-
-	memory@480000000 {
-		device_type = "memory";
-		reg = <0x4 0x80000000 0x0 0x80000000>;
-	};
-
-	memory@600000000 {
-		device_type = "memory";
-		reg = <0x6 0x00000000 0x1 0x00000000>;
-	};
-
-	mini-dp-con {
-		compatible = "dp-connector";
-		label = "CN5";
-		type = "mini";
-
-		port {
-			mini_dp_con_in: endpoint {
-				remote-endpoint = <&sn65dsi86_out>;
-			};
-		};
-	};
-
-	reg_1p2v: regulator-1p2v {
-		compatible = "regulator-fixed";
-		regulator-name = "fixed-1.2V";
-		regulator-min-microvolt = <1200000>;
-		regulator-max-microvolt = <1200000>;
-		regulator-boot-on;
-		regulator-always-on;
-	};
-
-	reg_1p8v: regulator-1p8v {
-		compatible = "regulator-fixed";
-		regulator-name = "fixed-1.8V";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-		regulator-boot-on;
-		regulator-always-on;
-	};
-
-	reg_3p3v: regulator-3p3v {
-		compatible = "regulator-fixed";
-		regulator-name = "fixed-3.3V";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-boot-on;
-		regulator-always-on;
-	};
-
-	sn65dsi86_refclk: clk-x6 {
-		compatible = "fixed-clock";
-		#clock-cells = <0>;
-		clock-frequency = <38400000>;
-	};
-};
-
-&avb0 {
-	pinctrl-0 = <&avb0_pins>;
-	pinctrl-names = "default";
-	phy-handle = <&phy0>;
-	tx-internal-delay-ps = <2000>;
-	status = "okay";
-
-	phy0: ethernet-phy@0 {
-		compatible = "ethernet-phy-id0022.1622",
-			     "ethernet-phy-ieee802.3-c22";
-		rxc-skew-ps = <1500>;
-		reg = <0>;
-		interrupt-parent = <&gpio7>;
-		interrupts = <5 IRQ_TYPE_LEVEL_LOW>;
-		reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
-	};
-};
-
-&dsi0 {
-	status = "okay";
-
-	ports {
-		port@1 {
-			dsi0_out: endpoint {
-				remote-endpoint = <&sn65dsi86_in>;
-				data-lanes = <1 2 3 4>;
-			};
-		};
-	};
-};
-
-&du {
-	status = "okay";
-};
-
-&extal_clk {
-	clock-frequency = <16666666>;
-};
-
-&extalr_clk {
-	clock-frequency = <32768>;
-};
-
-&hscif0 {
-	pinctrl-0 = <&hscif0_pins>;
-	pinctrl-names = "default";
-
-	status = "okay";
-};
-
-&i2c0 {
-	pinctrl-0 = <&i2c0_pins>;
-	pinctrl-names = "default";
-
-	status = "okay";
-	clock-frequency = <400000>;
-
-	io_expander_a: gpio@20 {
-		compatible = "onnn,pca9654";
-		reg = <0x20>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
-		gpio-controller;
-		#gpio-cells = <2>;
-		interrupt-controller;
-		#interrupt-cells = <2>;
-	};
-
-	eeprom@50 {
-		compatible = "rohm,br24g01", "atmel,24c01";
-		label = "cpu-board";
-		reg = <0x50>;
-		pagesize = <8>;
-	};
-};
-
-&i2c1 {
-	pinctrl-0 = <&i2c1_pins>;
-	pinctrl-names = "default";
-
-	status = "okay";
-	clock-frequency = <400000>;
-
-	bridge@2c {
-		compatible = "ti,sn65dsi86";
-		reg = <0x2c>;
-
-		clocks = <&sn65dsi86_refclk>;
-		clock-names = "refclk";
-
-		interrupt-parent = <&intc_ex>;
-		interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
-
-		enable-gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>;
-
-		vccio-supply = <&reg_1p8v>;
-		vpll-supply = <&reg_1p8v>;
-		vcca-supply = <&reg_1p2v>;
-		vcc-supply = <&reg_1p2v>;
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@0 {
-				reg = <0>;
-				sn65dsi86_in: endpoint {
-					remote-endpoint = <&dsi0_out>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-				sn65dsi86_out: endpoint {
-					remote-endpoint = <&mini_dp_con_in>;
-				};
-			};
-		};
-	};
-};
-
-&mmc0 {
-	pinctrl-0 = <&mmc_pins>;
-	pinctrl-1 = <&mmc_pins>;
-	pinctrl-names = "default", "state_uhs";
-
-	vmmc-supply = <&reg_3p3v>;
-	vqmmc-supply = <&reg_1p8v>;
-	mmc-hs200-1_8v;
-	mmc-hs400-1_8v;
-	bus-width = <8>;
-	no-sd;
-	no-sdio;
-	non-removable;
-	full-pwr-cycle-in-suspend;
-	status = "okay";
-};
-
-&pfc {
-	pinctrl-0 = <&scif_clk_pins>;
-	pinctrl-names = "default";
-
-	avb0_pins: avb0 {
-		mux {
-			groups = "avb0_link", "avb0_mdio", "avb0_rgmii",
-				 "avb0_txcrefclk";
-			function = "avb0";
-		};
-
-		pins_mdio {
-			groups = "avb0_mdio";
-			drive-strength = <21>;
-		};
-
-		pins_mii {
-			groups = "avb0_rgmii";
-			drive-strength = <21>;
-		};
-
-	};
-	hscif0_pins: hscif0 {
-		groups = "hscif0_data";
-		function = "hscif0";
-	};
-
-	i2c0_pins: i2c0 {
-		groups = "i2c0";
-		function = "i2c0";
-	};
-
-	i2c1_pins: i2c1 {
-		groups = "i2c1";
-		function = "i2c1";
-	};
-
-	keys_pins: keys {
-		pins = "GP_5_0", "GP_5_1", "GP_5_2";
-		bias-pull-up;
-	};
-
-	mmc_pins: mmc {
-		groups = "mmc_data8", "mmc_ctrl", "mmc_ds";
-		function = "mmc";
-		power-source = <1800>;
-	};
-
-	qspi0_pins: qspi0 {
-		groups = "qspi0_ctrl", "qspi0_data4";
-		function = "qspi0";
-	};
-
-	scif_clk_pins: scif_clk {
-		groups = "scif_clk";
-		function = "scif_clk";
-	};
-};
-
-&rpc {
-	pinctrl-0 = <&qspi0_pins>;
-	pinctrl-names = "default";
-
-	status = "okay";
-
-	flash@0 {
-		compatible = "spansion,s25fs512s", "jedec,spi-nor";
-		reg = <0>;
-		spi-max-frequency = <40000000>;
-		spi-rx-bus-width = <4>;
-
-		partitions {
-			compatible = "fixed-partitions";
-			#address-cells = <1>;
-			#size-cells = <1>;
-
-			boot@0 {
-				reg = <0x0 0x1200000>;
-				read-only;
-			};
-			user@1200000 {
-				reg = <0x1200000 0x2e00000>;
-			};
-		};
-	};
-};
-
-&rwdt {
-	timeout-sec = <60>;
-	status = "okay";
-};
-
-&scif_clk {
-	clock-frequency = <24000000>;
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk.dts b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk.dts
index eff1ef6e2cc8..784d4e8b204c 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk.dts
@@ -1,69 +1,15 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
- * Device Tree Source for the White Hawk CPU and BreakOut boards
+ * Device Tree Source for the R-Car V4H White Hawk CPU and BreakOut boards
  *
  * Copyright (C) 2022 Renesas Electronics Corp.
  */
 
 /dts-v1/;
 #include "r8a779g0-white-hawk-cpu.dtsi"
-#include "r8a779g0-white-hawk-csi-dsi.dtsi"
-#include "r8a779g0-white-hawk-ethernet.dtsi"
+#include "white-hawk-common.dtsi"
 
 / {
 	model = "Renesas White Hawk CPU and Breakout boards based on r8a779g0";
 	compatible = "renesas,white-hawk-breakout", "renesas,white-hawk-cpu", "renesas,r8a779g0";
-
-	can_transceiver0: can-phy0 {
-		compatible = "nxp,tjr1443";
-		#phy-cells = <0>;
-		enable-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
-		max-bitrate = <5000000>;
-	};
-};
-
-&can_clk {
-	clock-frequency = <40000000>;
-};
-
-&canfd {
-	pinctrl-0 = <&canfd0_pins>, <&canfd1_pins>, <&can_clk_pins>;
-	pinctrl-names = "default";
-
-	status = "okay";
-
-	channel0 {
-		status = "okay";
-		phys = <&can_transceiver0>;
-	};
-
-	channel1 {
-		status = "okay";
-	};
-};
-
-&i2c0 {
-	eeprom@51 {
-		compatible = "rohm,br24g01", "atmel,24c01";
-		label = "breakout-board";
-		reg = <0x51>;
-		pagesize = <8>;
-	};
-};
-
-&pfc {
-	can_clk_pins: can-clk {
-		groups = "can_clk";
-		function = "can_clk";
-	};
-
-	canfd0_pins: canfd0 {
-		groups = "canfd0_data";
-		function = "canfd0";
-	};
-
-	canfd1_pins: canfd1 {
-		groups = "canfd1_data";
-		function = "canfd1";
-	};
 };
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
index d3d25e077c5d..9bc542bc6169 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
@@ -161,11 +161,6 @@
 		};
 	};
 
-	psci {
-		compatible = "arm,psci-1.0", "arm,psci-0.2";
-		method = "smc";
-	};
-
 	extal_clk: extal {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
@@ -185,13 +180,24 @@
 		interrupts-extended = <&gic GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
 	};
 
-	/* External SCIF clock - to be overridden by boards that provide it */
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2";
+		method = "smc";
+	};
+
+	/* External SCIF clocks - to be overridden by boards that provide them */
 	scif_clk: scif {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <0>;
 	};
 
+	scif_clk2: scif2 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -479,6 +485,7 @@
 			interrupts = <GIC_SPI 289 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 290 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 291 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2";
 			clocks = <&cpg CPG_MOD 713>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
@@ -491,7 +498,9 @@
 			reg = <0 0xe6fc0000 0 0x30>;
 			interrupts = <GIC_SPI 292 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 293 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 294 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 294 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 295 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 714>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
@@ -504,7 +513,9 @@
 			reg = <0 0xe6fd0000 0 0x30>;
 			interrupts = <GIC_SPI 296 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 297 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 298 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 299 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 715>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
@@ -517,7 +528,9 @@
 			reg = <0 0xe6fe0000 0 0x30>;
 			interrupts = <GIC_SPI 300 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 301 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 302 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 303 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 716>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
@@ -530,7 +543,9 @@
 			reg = <0 0xffc00000 0 0x30>;
 			interrupts = <GIC_SPI 304 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 305 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "tuni0", "tuni1", "tuni2", "ticpi2";
 			clocks = <&cpg CPG_MOD 717>;
 			clock-names = "fck";
 			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
@@ -681,7 +696,7 @@
 			interrupts = <GIC_SPI 248 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 516>,
 				 <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>,
-				 <&scif_clk>;
+				 <&scif_clk2>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac0 0x35>, <&dmac0 0x34>,
 			       <&dmac1 0x35>, <&dmac1 0x34>;
@@ -761,7 +776,7 @@
 		avb0: ethernet@e6800000 {
 			compatible = "renesas,etheravb-r8a779g0",
 				     "renesas,etheravb-rcar-gen4";
-			reg = <0 0xe6800000 0 0x800>;
+			reg = <0 0xe6800000 0 0x1000>;
 			interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>,
@@ -808,7 +823,7 @@
 		avb1: ethernet@e6810000 {
 			compatible = "renesas,etheravb-r8a779g0",
 				     "renesas,etheravb-rcar-gen4";
-			reg = <0 0xe6810000 0 0x800>;
+			reg = <0 0xe6810000 0 0x1000>;
 			interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 362 IRQ_TYPE_LEVEL_HIGH>,
@@ -1057,7 +1072,7 @@
 			interrupts = <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&cpg CPG_MOD 705>,
 				 <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>,
-				 <&scif_clk>;
+				 <&scif_clk2>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			dmas = <&dmac0 0x59>, <&dmac0 0x58>,
 			       <&dmac1 0x59>, <&dmac1 0x58>;
@@ -1777,6 +1792,37 @@
 			};
 		};
 
+		mmc0: mmc@ee140000 {
+			compatible = "renesas,sdhi-r8a779g0",
+				     "renesas,rcar-gen4-sdhi";
+			reg = <0 0xee140000 0 0x2000>;
+			interrupts = <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 706>,
+				 <&cpg CPG_CORE R8A779G0_CLK_SD0H>;
+			clock-names = "core", "clkh";
+			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
+			resets = <&cpg 706>;
+			max-frequency = <200000000>;
+			iommus = <&ipmmu_ds0 32>;
+			status = "disabled";
+		};
+
+		rpc: spi@ee200000 {
+			compatible = "renesas,r8a779g0-rpc-if",
+				     "renesas,rcar-gen4-rpc-if";
+			reg = <0 0xee200000 0 0x200>,
+			      <0 0x08000000 0 0x04000000>,
+			      <0 0xee208000 0 0x100>;
+			reg-names = "regs", "dirmap", "wbuf";
+			interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 629>;
+			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
+			resets = <&cpg 629>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		ipmmu_rt0: iommu@ee480000 {
 			compatible = "renesas,ipmmu-r8a779g0",
 				     "renesas,rcar-gen4-ipmmu-vmsa";
@@ -1886,37 +1932,6 @@
 			#iommu-cells = <1>;
 		};
 
-		mmc0: mmc@ee140000 {
-			compatible = "renesas,sdhi-r8a779g0",
-				     "renesas,rcar-gen4-sdhi";
-			reg = <0 0xee140000 0 0x2000>;
-			interrupts = <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&cpg CPG_MOD 706>,
-				 <&cpg CPG_CORE R8A779G0_CLK_SD0H>;
-			clock-names = "core", "clkh";
-			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
-			resets = <&cpg 706>;
-			max-frequency = <200000000>;
-			iommus = <&ipmmu_ds0 32>;
-			status = "disabled";
-		};
-
-		rpc: spi@ee200000 {
-			compatible = "renesas,r8a779g0-rpc-if",
-				     "renesas,rcar-gen4-rpc-if";
-			reg = <0 0xee200000 0 0x200>,
-			      <0 0x08000000 0 0x04000000>,
-			      <0 0xee208000 0 0x100>;
-			reg-names = "regs", "dirmap", "wbuf";
-			interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&cpg CPG_MOD 629>;
-			power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>;
-			resets = <&cpg 629>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-			status = "disabled";
-		};
-
 		gic: interrupt-controller@f1000000 {
 			compatible = "arm,gic-v3";
 			#interrupt-cells = <3>;
diff --git a/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts
new file mode 100644
index 000000000000..2f79e5a61248
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the R-Car V4H ES2.0 White Hawk Single board
+ *
+ * Copyright (C) 2023 Glider bv
+ */
+
+/dts-v1/;
+#include "r8a779g2.dtsi"
+#include "white-hawk-cpu-common.dtsi"
+#include "white-hawk-common.dtsi"
+
+/ {
+	model = "Renesas White Hawk Single board based on r8a779g2";
+	compatible = "renesas,white-hawk-single", "renesas,r8a779g2",
+		     "renesas,r8a779g0";
+};
+
+&hscif0 {
+	uart-has-rtscts;
+};
+
+&hscif0_pins {
+	groups = "hscif0_data", "hscif0_ctrl";
+	function = "hscif0";
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a779g2.dtsi b/arch/arm64/boot/dts/renesas/r8a779g2.dtsi
new file mode 100644
index 000000000000..e08f531843e2
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a779g2.dtsi
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the R-Car V4H (R8A779G2) SoC
+ *
+ * Copyright (C) 2023 Glider bv
+ */
+
+#include "r8a779g0.dtsi"
+
+/ {
+	compatible = "renesas,r8a779g2", "renesas,r8a779g0";
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts
new file mode 100644
index 000000000000..bc8616a56c03
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the R-Car V4M Gray Hawk Single board
+ *
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ * Copyright (C) 2024 Glider bv
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+
+#include "r8a779h0.dtsi"
+
+/ {
+	model = "Renesas Gray Hawk Single board based on r8a779h0";
+	compatible = "renesas,gray-hawk-single", "renesas,r8a779h0";
+
+	aliases {
+		serial0 = &hscif0;
+		ethernet0 = &avb0;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel";
+		stdout-path = "serial0:921600n8";
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x78000000>;
+	};
+
+	memory@480000000 {
+		device_type = "memory";
+		reg = <0x4 0x80000000 0x1 0x80000000>;
+	};
+
+	reg_1p8v: regulator-1p8v {
+			compatible = "regulator-fixed";
+			regulator-name = "fixed-1.8V";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-boot-on;
+			regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3p3v {
+			compatible = "regulator-fixed";
+			regulator-name = "fixed-3.3V";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-boot-on;
+			regulator-always-on;
+	};
+};
+
+&avb0 {
+	pinctrl-0 = <&avb0_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy0>;
+	tx-internal-delay-ps = <2000>;
+	status = "okay";
+
+	phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0022.1622",
+			     "ethernet-phy-ieee802.3-c22";
+		rxc-skew-ps = <1500>;
+		reg = <0>;
+		interrupt-parent = <&gpio7>;
+		interrupts = <5 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&extal_clk {
+	clock-frequency = <16666666>;
+};
+
+&extalr_clk {
+	clock-frequency = <32768>;
+};
+
+&hscif0 {
+	pinctrl-0 = <&hscif0_pins>;
+	pinctrl-names = "default";
+
+	uart-has-rtscts;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+	clock-frequency = <400000>;
+
+	eeprom@50 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "cpu-board";
+		reg = <0x50>;
+		pagesize = <8>;
+	};
+
+	eeprom@51 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "breakout-board";
+		reg = <0x51>;
+		pagesize = <8>;
+	};
+
+	eeprom@52 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "csi-dsi-sub-board-id";
+		reg = <0x52>;
+		pagesize = <8>;
+	};
+
+	eeprom@53 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "ethernet-sub-board-id";
+		reg = <0x53>;
+		pagesize = <8>;
+	};
+};
+
+&mmc0 {
+	pinctrl-0 = <&mmc_pins>;
+	pinctrl-1 = <&mmc_pins>;
+	pinctrl-names = "default", "state_uhs";
+
+	vmmc-supply = <&reg_3p3v>;
+	vqmmc-supply = <&reg_1p8v>;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	bus-width = <8>;
+	no-sd;
+	no-sdio;
+	non-removable;
+	full-pwr-cycle-in-suspend;
+	status = "okay";
+};
+
+&pfc {
+	pinctrl-0 = <&scif_clk_pins>;
+	pinctrl-names = "default";
+
+	avb0_pins: avb0 {
+		mux {
+			groups = "avb0_link", "avb0_mdio", "avb0_rgmii",
+				 "avb0_txcrefclk";
+			function = "avb0";
+		};
+
+		pins_mdio {
+			groups = "avb0_mdio";
+			drive-strength = <21>;
+		};
+
+		pins_mii {
+			groups = "avb0_rgmii";
+			drive-strength = <21>;
+		};
+	};
+
+	hscif0_pins: hscif0 {
+		groups = "hscif0_data", "hscif0_ctrl";
+		function = "hscif0";
+	};
+
+	i2c0_pins: i2c0 {
+		groups = "i2c0";
+		function = "i2c0";
+	};
+
+	mmc_pins: mmc {
+		groups = "mmc_data8", "mmc_ctrl", "mmc_ds";
+		function = "mmc";
+		power-source = <1800>;
+	};
+
+	qspi0_pins: qspi0 {
+		groups = "qspi0_ctrl", "qspi0_data4";
+		function = "qspi0";
+	};
+
+	scif_clk_pins: scif-clk {
+		groups = "scif_clk";
+		function = "scif_clk";
+	};
+};
+
+&rpc {
+	pinctrl-0 = <&qspi0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	flash@0 {
+		compatible = "spansion,s25fs512s", "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <40000000>;
+		spi-rx-bus-width = <4>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			boot@0 {
+				reg = <0x0 0x1200000>;
+				read-only;
+			};
+			user@1200000 {
+				reg = <0x1200000 0x2e00000>;
+			};
+		};
+	};
+};
+
+&rwdt {
+	timeout-sec = <60>;
+	status = "okay";
+};
+
+&scif_clk {
+	clock-frequency = <24000000>;
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
new file mode 100644
index 000000000000..11885729181b
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
@@ -0,0 +1,664 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the R-Car V4M (R8A779H0) SoC
+ *
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#include <dt-bindings/clock/renesas,r8a779h0-cpg-mssr.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/power/renesas,r8a779h0-sysc.h>
+
+/ {
+	compatible = "renesas,r8a779h0";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cluster0_opp: opp-table-0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp-500000000 {
+			opp-hz = /bits/ 64 <500000000>;
+			opp-microvolt = <825000>;
+			clock-latency-ns = <500000>;
+		};
+		opp-1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <825000>;
+			clock-latency-ns = <500000>;
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&a76_0>;
+				};
+				core1 {
+					cpu = <&a76_1>;
+				};
+				core2 {
+					cpu = <&a76_2>;
+				};
+				core3 {
+					cpu = <&a76_3>;
+				};
+			};
+		};
+
+		a76_0: cpu@0 {
+			compatible = "arm,cortex-a76";
+			reg = <0>;
+			device_type = "cpu";
+			power-domains = <&sysc R8A779H0_PD_A1E0D0C0>;
+			next-level-cache = <&L3_CA76>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&cpg CPG_CORE R8A779H0_CLK_ZC0>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		a76_1: cpu@100 {
+			compatible = "arm,cortex-a76";
+			reg = <0x100>;
+			device_type = "cpu";
+			power-domains = <&sysc R8A779H0_PD_A1E0D0C1>;
+			next-level-cache = <&L3_CA76>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&cpg CPG_CORE R8A779H0_CLK_ZC1>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		a76_2: cpu@200 {
+			compatible = "arm,cortex-a76";
+			reg = <0x200>;
+			device_type = "cpu";
+			power-domains = <&sysc R8A779H0_PD_A1E0D0C2>;
+			next-level-cache = <&L3_CA76>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&cpg CPG_CORE R8A779H0_CLK_ZC2>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		a76_3: cpu@300 {
+			compatible = "arm,cortex-a76";
+			reg = <0x300>;
+			device_type = "cpu";
+			power-domains = <&sysc R8A779H0_PD_A1E0D0C3>;
+			next-level-cache = <&L3_CA76>;
+			enable-method = "psci";
+			cpu-idle-states = <&CPU_SLEEP_0>;
+			clocks = <&cpg CPG_CORE R8A779H0_CLK_ZC3>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		idle-states {
+			entry-method = "psci";
+
+			CPU_SLEEP_0: cpu-sleep-0 {
+				compatible = "arm,idle-state";
+				arm,psci-suspend-param = <0x0010000>;
+				local-timer-stop;
+				entry-latency-us = <400>;
+				exit-latency-us = <500>;
+				min-residency-us = <4000>;
+			};
+		};
+
+		L3_CA76: cache-controller {
+			compatible = "cache";
+			power-domains = <&sysc R8A779H0_PD_A2E0D0>;
+			cache-unified;
+			cache-level = <3>;
+		};
+	};
+
+	extal_clk: extal-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	extalr_clk: extalr-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		/* This value must be overridden by the board */
+		clock-frequency = <0>;
+	};
+
+	pmu-a76 {
+		compatible = "arm,cortex-a76-pmu";
+		interrupts-extended = <&gic GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>;
+	};
+
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2";
+		method = "smc";
+	};
+
+	/* External SCIF clock - to be overridden by boards that provide it */
+	scif_clk: scif-clk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
+	soc: soc {
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		rwdt: watchdog@e6020000 {
+			compatible = "renesas,r8a779h0-wdt",
+				     "renesas,rcar-gen4-wdt";
+			reg = <0 0xe6020000 0 0x0c>;
+			interrupts = <GIC_SPI 330 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 907>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 907>;
+			status = "disabled";
+		};
+
+		pfc: pinctrl@e6050000 {
+			compatible = "renesas,pfc-r8a779h0";
+			reg = <0 0xe6050000 0 0x16c>, <0 0xe6050800 0 0x16c>,
+			      <0 0xe6058000 0 0x16c>, <0 0xe6058800 0 0x16c>,
+			      <0 0xe6060000 0 0x16c>, <0 0xe6060800 0 0x16c>,
+			      <0 0xe6061000 0 0x16c>, <0 0xe6061800 0 0x16c>;
+		};
+
+		gpio0: gpio@e6050180 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6050180 0 0x54>;
+			interrupts = <GIC_SPI 619 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 0 19>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 915>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 915>;
+		};
+
+		gpio1: gpio@e6050980 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6050980 0 0x54>;
+			interrupts = <GIC_SPI 623 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 32 30>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 915>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 915>;
+		};
+
+		gpio2: gpio@e6058180 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6058180 0 0x54>;
+			interrupts = <GIC_SPI 627 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 64 20>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 916>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 916>;
+		};
+
+		gpio3: gpio@e6058980 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6058980 0 0x54>;
+			interrupts = <GIC_SPI 631 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 96 32>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 916>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 916>;
+		};
+
+		gpio4: gpio@e6060180 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6060180 0 0x54>;
+			interrupts = <GIC_SPI 635 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 128 25>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 917>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 917>;
+		};
+
+		gpio5: gpio@e6060980 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6060980 0 0x54>;
+			interrupts = <GIC_SPI 639 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 160 21>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 917>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 917>;
+		};
+
+		gpio6: gpio@e6061180 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6061180 0 0x54>;
+			interrupts = <GIC_SPI 643 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 192 21>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 917>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 917>;
+		};
+
+		gpio7: gpio@e6061980 {
+			compatible = "renesas,gpio-r8a779h0",
+				     "renesas,rcar-gen4-gpio";
+			reg = <0 0xe6061980 0 0x54>;
+			interrupts = <GIC_SPI 647 IRQ_TYPE_LEVEL_HIGH>;
+			#gpio-cells = <2>;
+			gpio-controller;
+			gpio-ranges = <&pfc 0 224 21>;
+			#interrupt-cells = <2>;
+			interrupt-controller;
+			clocks = <&cpg CPG_MOD 917>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 917>;
+		};
+
+		cpg: clock-controller@e6150000 {
+			compatible = "renesas,r8a779h0-cpg-mssr";
+			reg = <0 0xe6150000 0 0x4000>;
+			clocks = <&extal_clk>, <&extalr_clk>;
+			clock-names = "extal", "extalr";
+			#clock-cells = <2>;
+			#power-domain-cells = <0>;
+			#reset-cells = <1>;
+		};
+
+		rst: reset-controller@e6160000 {
+			compatible = "renesas,r8a779h0-rst";
+			reg = <0 0xe6160000 0 0x4000>;
+		};
+
+		sysc: system-controller@e6180000 {
+			compatible = "renesas,r8a779h0-sysc";
+			reg = <0 0xe6180000 0 0x4000>;
+			#power-domain-cells = <1>;
+		};
+
+		i2c0: i2c@e6500000 {
+			compatible = "renesas,i2c-r8a779h0",
+				     "renesas,rcar-gen4-i2c";
+			reg = <0 0xe6500000 0 0x40>;
+			interrupts = <GIC_SPI 610 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 518>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 518>;
+			dmas = <&dmac1 0x91>, <&dmac1 0x90>,
+			       <&dmac2 0x91>, <&dmac2 0x90>;
+			dma-names = "tx", "rx", "tx", "rx";
+			i2c-scl-internal-delay-ns = <110>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c1: i2c@e6508000 {
+			compatible = "renesas,i2c-r8a779h0",
+				     "renesas,rcar-gen4-i2c";
+			reg = <0 0xe6508000 0 0x40>;
+			interrupts = <GIC_SPI 611 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 519>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 519>;
+			dmas = <&dmac1 0x93>, <&dmac1 0x92>,
+			       <&dmac2 0x93>, <&dmac2 0x92>;
+			dma-names = "tx", "rx", "tx", "rx";
+			i2c-scl-internal-delay-ns = <110>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c2: i2c@e6510000 {
+			compatible = "renesas,i2c-r8a779h0",
+				     "renesas,rcar-gen4-i2c";
+			reg = <0 0xe6510000 0 0x40>;
+			interrupts = <GIC_SPI 612 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 520>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 520>;
+			dmas = <&dmac1 0x95>, <&dmac1 0x94>,
+			       <&dmac2 0x95>, <&dmac2 0x94>;
+			dma-names = "tx", "rx", "tx", "rx";
+			i2c-scl-internal-delay-ns = <110>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		i2c3: i2c@e66d0000 {
+			compatible = "renesas,i2c-r8a779h0",
+				     "renesas,rcar-gen4-i2c";
+			reg = <0 0xe66d0000 0 0x40>;
+			interrupts = <GIC_SPI 613 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 521>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 521>;
+			dmas = <&dmac1 0x97>, <&dmac1 0x96>,
+			       <&dmac2 0x97>, <&dmac2 0x96>;
+			dma-names = "tx", "rx", "tx", "rx";
+			i2c-scl-internal-delay-ns = <110>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		hscif0: serial@e6540000 {
+			compatible = "renesas,hscif-r8a779h0",
+				     "renesas,rcar-gen4-hscif", "renesas,hscif";
+			reg = <0 0xe6540000 0 0x60>;
+			interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 514>,
+				 <&cpg CPG_CORE R8A779H0_CLK_SASYNCPERD1>,
+				 <&scif_clk>;
+			clock-names = "fck", "brg_int", "scif_clk";
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 514>;
+			dmas = <&dmac1 0x31>, <&dmac1 0x30>,
+			       <&dmac2 0x31>, <&dmac2 0x30>;
+			dma-names = "tx", "rx", "tx", "rx";
+			status = "disabled";
+		};
+
+		avb0: ethernet@e6800000 {
+			compatible = "renesas,etheravb-r8a779h0",
+				     "renesas,etheravb-rcar-gen4";
+			reg = <0 0xe6800000 0 0x1000>;
+			interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 344 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 345 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 346 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 348 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 349 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 350 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 352 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 354 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 356 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 358 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 359 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15",
+					  "ch16", "ch17", "ch18", "ch19",
+					  "ch20", "ch21", "ch22", "ch23",
+					  "ch24";
+			clocks = <&cpg CPG_MOD 211>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A779H0_PD_C4>;
+			resets = <&cpg 211>;
+			phy-mode = "rgmii";
+			rx-internal-delay-ps = <0>;
+			tx-internal-delay-ps = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		avb1: ethernet@e6810000 {
+			compatible = "renesas,etheravb-r8a779h0",
+				     "renesas,etheravb-rcar-gen4";
+			reg = <0 0xe6810000 0 0x1000>;
+			interrupts = <GIC_SPI 360 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 361 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 362 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 363 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 364 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 365 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 366 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 368 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 372 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 373 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 375 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 377 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 378 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 380 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 382 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 384 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15",
+					  "ch16", "ch17", "ch18", "ch19",
+					  "ch20", "ch21", "ch22", "ch23",
+					  "ch24";
+			clocks = <&cpg CPG_MOD 212>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A779H0_PD_C4>;
+			resets = <&cpg 212>;
+			phy-mode = "rgmii";
+			rx-internal-delay-ps = <0>;
+			tx-internal-delay-ps = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		avb2: ethernet@e6820000 {
+			compatible = "renesas,etheravb-r8a779h0",
+				     "renesas,etheravb-rcar-gen4";
+			reg = <0 0xe6820000 0 0x1000>;
+			interrupts = <GIC_SPI 385 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 387 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 388 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 389 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 390 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 391 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 392 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 393 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 394 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 395 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 396 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 397 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 398 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 399 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 400 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 401 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 402 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 403 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 404 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 405 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 406 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 407 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 408 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "ch0", "ch1", "ch2", "ch3",
+					  "ch4", "ch5", "ch6", "ch7",
+					  "ch8", "ch9", "ch10", "ch11",
+					  "ch12", "ch13", "ch14", "ch15",
+					  "ch16", "ch17", "ch18", "ch19",
+					  "ch20", "ch21", "ch22", "ch23",
+					  "ch24";
+			clocks = <&cpg CPG_MOD 213>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A779H0_PD_C4>;
+			resets = <&cpg 213>;
+			phy-mode = "rgmii";
+			rx-internal-delay-ps = <0>;
+			tx-internal-delay-ps = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		dmac1: dma-controller@e7350000 {
+			compatible = "renesas,dmac-r8a779h0",
+				     "renesas,rcar-gen4-dmac";
+			reg = <0 0xe7350000 0 0x1000>,
+			      <0 0xe7300000 0 0x10000>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3", "ch4",
+					  "ch5", "ch6", "ch7", "ch8", "ch9",
+					  "ch10", "ch11", "ch12", "ch13",
+					  "ch14", "ch15";
+			clocks = <&cpg CPG_MOD 709>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 709>;
+			#dma-cells = <1>;
+			dma-channels = <16>;
+		};
+
+		dmac2: dma-controller@e7351000 {
+			compatible = "renesas,dmac-r8a779h0",
+				     "renesas,rcar-gen4-dmac";
+			reg = <0 0xe7351000 0 0x1000>,
+			      <0 0xe7310000 0 0x10000>;
+			interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 104 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 107 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "error",
+					  "ch0", "ch1", "ch2", "ch3", "ch4",
+					  "ch5", "ch6", "ch7";
+			clocks = <&cpg CPG_MOD 710>;
+			clock-names = "fck";
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 710>;
+			#dma-cells = <1>;
+			dma-channels = <8>;
+		};
+
+		mmc0: mmc@ee140000 {
+			compatible = "renesas,sdhi-r8a779h0",
+				     "renesas,rcar-gen4-sdhi";
+			reg = <0 0xee140000 0 0x2000>;
+			interrupts = <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 706>,
+				 <&cpg CPG_CORE R8A779H0_CLK_SD0H>;
+			clock-names = "core", "clkh";
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 706>;
+			max-frequency = <200000000>;
+			status = "disabled";
+		};
+
+		rpc: spi@ee200000 {
+			compatible = "renesas,r8a779h0-rpc-if",
+				     "renesas,rcar-gen4-rpc-if";
+			reg = <0 0xee200000 0 0x200>,
+			      <0 0x08000000 0 0x04000000>,
+			      <0 0xee208000 0 0x100>;
+			reg-names = "regs", "dirmap", "wbuf";
+			interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 629>;
+			power-domains = <&sysc R8A779H0_PD_ALWAYS_ON>;
+			resets = <&cpg 629>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
+		gic: interrupt-controller@f1000000 {
+			compatible = "arm,gic-v3";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			reg = <0x0 0xf1000000 0 0x20000>,
+			      <0x0 0xf1060000 0 0x110000>;
+			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		prr: chipid@fff00044 {
+			compatible = "renesas,prr";
+			reg = <0 0xfff00044 0 4>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+				      <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+				      <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+				      <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
+				      <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
index 2ab231572d95..964b0a475eee 100644
--- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
@@ -61,6 +61,75 @@
 &soc {
 	interrupt-parent = <&gic>;
 
+	cru: video@10830000 {
+		compatible = "renesas,r9a07g043-cru", "renesas,rzg2l-cru";
+		reg = <0 0x10830000 0 0x400>;
+		clocks = <&cpg CPG_MOD R9A07G043_CRU_VCLK>,
+			 <&cpg CPG_MOD R9A07G043_CRU_PCLK>,
+			 <&cpg CPG_MOD R9A07G043_CRU_ACLK>;
+		clock-names = "video", "apb", "axi";
+		interrupts = <SOC_PERIPHERAL_IRQ(167) IRQ_TYPE_LEVEL_HIGH>,
+			     <SOC_PERIPHERAL_IRQ(168) IRQ_TYPE_LEVEL_HIGH>,
+			     <SOC_PERIPHERAL_IRQ(169) IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "image_conv", "image_conv_err", "axi_mst_err";
+		resets = <&cpg R9A07G043_CRU_PRESETN>,
+			 <&cpg R9A07G043_CRU_ARESETN>;
+		reset-names = "presetn", "aresetn";
+		power-domains = <&cpg>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@1 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				reg = <1>;
+				crucsi2: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&csi2cru>;
+				};
+			};
+		};
+	};
+
+	csi2: csi2@10830400 {
+		compatible = "renesas,r9a07g043-csi2", "renesas,rzg2l-csi2";
+		reg = <0 0x10830400 0 0xfc00>;
+		interrupts = <SOC_PERIPHERAL_IRQ(166) IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cpg CPG_MOD R9A07G043_CRU_SYSCLK>,
+			 <&cpg CPG_MOD R9A07G043_CRU_VCLK>,
+			 <&cpg CPG_MOD R9A07G043_CRU_PCLK>;
+		clock-names = "system", "video", "apb";
+		resets = <&cpg R9A07G043_CRU_PRESETN>,
+			 <&cpg R9A07G043_CRU_CMN_RSTB>;
+		reset-names = "presetn", "cmn-rstb";
+		power-domains = <&cpg>;
+		status = "disabled";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+			};
+
+			port@1 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <1>;
+
+				csi2cru: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&crucsi2>;
+				};
+			};
+		};
+	};
+
 	irqc: interrupt-controller@110a0000 {
 		compatible = "renesas,r9a07g043u-irqc",
 			     "renesas,rzg2l-irqc";
@@ -109,7 +178,13 @@
 			     <SOC_PERIPHERAL_IRQ(473) IRQ_TYPE_LEVEL_HIGH>,
 			     <SOC_PERIPHERAL_IRQ(474) IRQ_TYPE_LEVEL_HIGH>,
 			     <SOC_PERIPHERAL_IRQ(475) IRQ_TYPE_LEVEL_HIGH>,
-			     <SOC_PERIPHERAL_IRQ(25) IRQ_TYPE_EDGE_RISING>;
+			     <SOC_PERIPHERAL_IRQ(25) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(34) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(35) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(36) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(37) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(38) IRQ_TYPE_EDGE_RISING>,
+			     <SOC_PERIPHERAL_IRQ(39) IRQ_TYPE_EDGE_RISING>;
 		interrupt-names = "nmi",
 				  "irq0", "irq1", "irq2", "irq3",
 				  "irq4", "irq5", "irq6", "irq7",
@@ -121,7 +196,9 @@
 				  "tint20", "tint21", "tint22", "tint23",
 				  "tint24", "tint25", "tint26", "tint27",
 				  "tint28", "tint29", "tint30", "tint31",
-				  "bus-err";
+				  "bus-err", "ec7tie1-0", "ec7tie2-0",
+				  "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1",
+				  "ec7tiovf-1";
 		clocks = <&cpg CPG_MOD R9A07G043_IA55_CLK>,
 			<&cpg CPG_MOD R9A07G043_IA55_PCLK>;
 		clock-names = "clk", "pclk";
diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u11-smarc-cru-csi-ov5645.dtso b/arch/arm64/boot/dts/renesas/r9a07g043u11-smarc-cru-csi-ov5645.dtso
new file mode 100644
index 000000000000..b41bb4b31a26
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/r9a07g043u11-smarc-cru-csi-ov5645.dtso
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device Tree overlay for the RZ/G2UL SMARC EVK with OV5645 camera
+ * connected to CSI and CRU enabled.
+ *
+ * Copyright (C) 2024 Renesas Electronics Corp.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
+
+#define OV5645_PARENT_I2C i2c0
+#include "rz-smarc-cru-csi-ov5645.dtsi"
+
+&ov5645 {
+	enable-gpios = <&pinctrl RZG2L_GPIO(4, 4) GPIO_ACTIVE_HIGH>;
+	reset-gpios = <&pinctrl RZG2L_GPIO(0, 1) GPIO_ACTIVE_LOW>;
+};
diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
index 66f68fc2b241..9f00b75d2bd0 100644
--- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
@@ -793,6 +793,22 @@
 			reset-names = "rst", "arst", "prst";
 			power-domains = <&cpg>;
 			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dsi0_in: endpoint {
+						remote-endpoint = <&du_out_dsi>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+				};
+			};
 		};
 
 		vspd: vsp@10870000 {
@@ -820,6 +836,36 @@
 			resets = <&cpg R9A07G044_LCDC_RESET_N>;
 		};
 
+		du: display@10890000 {
+			compatible = "renesas,r9a07g044-du";
+			reg = <0 0x10890000 0 0x10000>;
+			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A07G044_LCDC_CLK_A>,
+				 <&cpg CPG_MOD R9A07G044_LCDC_CLK_P>,
+				 <&cpg CPG_MOD R9A07G044_LCDC_CLK_D>;
+			clock-names = "aclk", "pclk", "vclk";
+			power-domains = <&cpg>;
+			resets = <&cpg R9A07G044_LCDC_RESET_N>;
+			renesas,vsps = <&vspd 0>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					du_out_dsi: endpoint {
+						remote-endpoint = <&dsi0_in>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+				};
+			};
+		};
+
 		cpg: clock-controller@11010000 {
 			compatible = "renesas,r9a07g044-cpg";
 			reg = <0 0x11010000 0 0x10000>;
@@ -905,7 +951,27 @@
 				     <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 25 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 34 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 35 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 36 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 37 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 38 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 39 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3",
+					  "irq4", "irq5", "irq6", "irq7",
+					  "tint0", "tint1", "tint2", "tint3",
+					  "tint4", "tint5", "tint6", "tint7",
+					  "tint8", "tint9", "tint10", "tint11",
+					  "tint12", "tint13", "tint14", "tint15",
+					  "tint16", "tint17", "tint18", "tint19",
+					  "tint20", "tint21", "tint22", "tint23",
+					  "tint24", "tint25", "tint26", "tint27",
+					  "tint28", "tint29", "tint30", "tint31",
+					  "bus-err", "ec7tie1-0", "ec7tie2-0",
+					  "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1",
+					  "ec7tiovf-1";
 			clocks = <&cpg CPG_MOD R9A07G044_IA55_CLK>,
 				 <&cpg CPG_MOD R9A07G044_IA55_PCLK>;
 			clock-names = "clk", "pclk";
diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
index 1f1d481dc783..53d8905f367a 100644
--- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
@@ -798,6 +798,22 @@
 			reset-names = "rst", "arst", "prst";
 			power-domains = <&cpg>;
 			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dsi0_in: endpoint {
+						remote-endpoint = <&du_out_dsi>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+				};
+			};
 		};
 
 		vspd: vsp@10870000 {
@@ -826,6 +842,37 @@
 			resets = <&cpg R9A07G054_LCDC_RESET_N>;
 		};
 
+		du: display@10890000 {
+			compatible = "renesas,r9a07g054-du",
+				     "renesas,r9a07g044-du";
+			reg = <0 0x10890000 0 0x10000>;
+			interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A07G054_LCDC_CLK_A>,
+				 <&cpg CPG_MOD R9A07G054_LCDC_CLK_P>,
+				 <&cpg CPG_MOD R9A07G054_LCDC_CLK_D>;
+			clock-names = "aclk", "pclk", "vclk";
+			power-domains = <&cpg>;
+			resets = <&cpg R9A07G054_LCDC_RESET_N>;
+			renesas,vsps = <&vspd 0>;
+			status = "disabled";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					du_out_dsi: endpoint {
+						remote-endpoint = <&dsi0_in>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+				};
+			};
+		};
+
 		cpg: clock-controller@11010000 {
 			compatible = "renesas,r9a07g054-cpg";
 			reg = <0 0x11010000 0 0x10000>;
@@ -912,7 +959,27 @@
 				     <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 25 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 34 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 35 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 36 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 37 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 38 IRQ_TYPE_EDGE_RISING>,
+				     <GIC_SPI 39 IRQ_TYPE_EDGE_RISING>;
+			interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3",
+					  "irq4", "irq5", "irq6", "irq7",
+					  "tint0", "tint1", "tint2", "tint3",
+					  "tint4", "tint5", "tint6", "tint7",
+					  "tint8", "tint9", "tint10", "tint11",
+					  "tint12", "tint13", "tint14", "tint15",
+					  "tint16", "tint17", "tint18", "tint19",
+					  "tint20", "tint21", "tint22", "tint23",
+					  "tint24", "tint25", "tint26", "tint27",
+					  "tint28", "tint29", "tint30", "tint31",
+					  "bus-err", "ec7tie1-0", "ec7tie2-0",
+					  "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1",
+					  "ec7tiovf-1";
 			clocks = <&cpg CPG_MOD R9A07G054_IA55_CLK>,
 				 <&cpg CPG_MOD R9A07G054_IA55_PCLK>;
 			clock-names = "clk", "pclk";
diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
index 5facfad96158..f5f3f4f4c8d6 100644
--- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
@@ -42,6 +42,11 @@
 		clock-frequency = <0>;
 	};
 
+	psci {
+		compatible = "arm,psci-1.0", "arm,psci-0.2";
+		method = "smc";
+	};
+
 	soc: soc {
 		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
@@ -152,7 +157,10 @@
 				     <GIC_SPI 458 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 459 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 460 IRQ_TYPE_LEVEL_HIGH>,
-				     <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+				     <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "nmi",
 					  "irq0", "irq1", "irq2", "irq3",
 					  "irq4", "irq5", "irq6", "irq7",
@@ -164,7 +172,8 @@
 					  "tint20", "tint21", "tint22", "tint23",
 					  "tint24", "tint25", "tint26", "tint27",
 					  "tint28", "tint29", "tint30", "tint31",
-					  "bus-err";
+					  "bus-err", "ec7tie1-0", "ec7tie2-0",
+					  "ec7tiovf-0";
 			clocks = <&cpg CPG_MOD R9A08G045_IA55_CLK>,
 				 <&cpg CPG_MOD R9A08G045_IA55_PCLK>;
 			clock-names = "clk", "pclk";
@@ -264,6 +273,20 @@
 			      <0x0 0x12440000 0 0x60000>;
 			interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
 		};
+
+		wdt0: watchdog@12800800 {
+			compatible = "renesas,r9a08g045-wdt", "renesas,rzg2l-wdt";
+			reg = <0 0x12800800 0 0x400>;
+			clocks = <&cpg CPG_MOD R9A08G045_WDT0_PCLK>,
+				 <&cpg CPG_MOD R9A08G045_WDT0_CLK>;
+			clock-names = "pclk", "oscclk";
+			interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "wdt", "perrout";
+			resets = <&cpg R9A08G045_WDT0_PRESETN>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
 	};
 
 	timer {
diff --git a/arch/arm64/boot/dts/renesas/rzg2l-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg2l-smarc.dtsi
index 37807f1bda4d..887dffe14910 100644
--- a/arch/arm64/boot/dts/renesas/rzg2l-smarc.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2l-smarc.dtsi
@@ -40,17 +40,7 @@
 	status = "okay";
 
 	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-			dsi0_in: endpoint {
-			};
-		};
-
 		port@1 {
-			reg = <1>;
 			dsi0_out: endpoint {
 				data-lanes = <1 2 3 4>;
 				remote-endpoint = <&adv7535_in>;
@@ -59,6 +49,10 @@
 	};
 };
 
+&du {
+	status = "okay";
+};
+
 &i2c1 {
 	adv7535: hdmi@3d {
 		compatible = "adi,adv7535";
diff --git a/arch/arm64/boot/dts/renesas/rzg2lc-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg2lc-smarc.dtsi
index 859bc8745e66..f21508640b6e 100644
--- a/arch/arm64/boot/dts/renesas/rzg2lc-smarc.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2lc-smarc.dtsi
@@ -56,17 +56,7 @@
 	status = "okay";
 
 	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-			dsi0_in: endpoint {
-			};
-		};
-
 		port@1 {
-			reg = <1>;
 			dsi0_out: endpoint {
 				data-lanes = <1 2 3 4>;
 				remote-endpoint = <&adv7535_in>;
@@ -75,6 +65,10 @@
 	};
 };
 
+&du {
+	status = "okay";
+};
+
 &i2c1 {
 	adv7535: hdmi@3d {
 		compatible = "adi,adv7535";
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
index f062d4ad78b7..acac4666ae59 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
@@ -193,12 +193,14 @@
 #endif
 
 &pinctrl {
+#if SW_CONFIG3 == SW_ON
 	eth0-phy-irq-hog {
 		gpio-hog;
 		gpios = <RZG2L_GPIO(12, 0) GPIO_ACTIVE_LOW>;
 		input;
 		line-name = "eth0-phy-irq";
 	};
+#endif
 
 	eth0_pins: eth0 {
 		txc {
@@ -234,12 +236,14 @@
 		};
 	};
 
+#if SW_CONFIG3 == SW_ON
 	eth1-phy-irq-hog {
 		gpio-hog;
 		gpios = <RZG2L_GPIO(12, 1) GPIO_ACTIVE_LOW>;
 		input;
 		line-name = "eth1-phy-irq";
 	};
+#endif
 
 	eth1_pins: eth1 {
 		txc {
@@ -336,3 +340,8 @@
 		};
 	};
 };
+
+&wdt0 {
+	timeout-sec = <60>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
index 214520137230..deb2ad37bb2e 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc.dtsi
@@ -6,6 +6,7 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
 #include <dt-bindings/pinctrl/rzg2l-pinctrl.h>
 
 / {
@@ -14,6 +15,37 @@
 		mmc1 = &sdhi1;
 	};
 
+	keys {
+		compatible = "gpio-keys";
+
+		key-1 {
+			interrupts = <RZG2L_GPIO(18, 0) IRQ_TYPE_EDGE_FALLING>;
+			interrupt-parent = <&pinctrl>;
+			linux,code = <KEY_1>;
+			label = "USER_SW1";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+
+		key-2 {
+			interrupts = <RZG2L_GPIO(0, 1) IRQ_TYPE_EDGE_FALLING>;
+			interrupt-parent = <&pinctrl>;
+			linux,code = <KEY_2>;
+			label = "USER_SW2";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+
+		key-3 {
+			interrupts = <RZG2L_GPIO(0, 3) IRQ_TYPE_EDGE_FALLING>;
+			interrupt-parent = <&pinctrl>;
+			linux,code = <KEY_3>;
+			label = "USER_SW3";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+	};
+
 	vcc_sdhi1: regulator-vcc-sdhi1 {
 		compatible = "regulator-fixed";
 		regulator-name = "SDHI1 Vcc";
@@ -35,6 +67,27 @@
 };
 
 &pinctrl {
+	key-1-gpio-hog {
+		gpio-hog;
+		gpios = <RZG2L_GPIO(18, 0) GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "key-1-gpio-irq";
+	};
+
+	key-2-gpio-hog {
+		gpio-hog;
+		gpios = <RZG2L_GPIO(0, 1) GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "key-2-gpio-irq";
+	};
+
+	key-3-gpio-hog {
+		gpio-hog;
+		gpios = <RZG2L_GPIO(0, 3) GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "key-3-gpio-irq";
+	};
+
 	scif0_pins: scif0 {
 		pinmux = <RZG2L_PORT_PINMUX(6, 3, 1)>, /* RXD */
 			 <RZG2L_PORT_PINMUX(6, 4, 1)>; /* TXD */
diff --git a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
index 3885ef3454ff..431b37bf5661 100644
--- a/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb-kf.dtsi
@@ -32,39 +32,40 @@
 		};
 	};
 
-	accel_3v3: regulator-acc-3v3 {
+	reg_t1p8v: regulator-t1p8v {
 		compatible = "regulator-fixed";
-		regulator-name = "accel-3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-	};
-
-	hdmi_1v8: regulator-hdmi-1v8 {
-		compatible = "regulator-fixed";
-		regulator-name = "hdmi-1v8";
+		regulator-name = "T1.8V";
 		regulator-min-microvolt = <1800000>;
 		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
 	};
 
-	hdmi_3v3: regulator-hdmi-3v3 {
+	pcie_1v5: regulator-pcie-1v5 {
 		compatible = "regulator-fixed";
-		regulator-name = "hdmi-3v3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
+		regulator-name = "pcie-1v5";
+		regulator-min-microvolt = <1500000>;
+		regulator-max-microvolt = <1500000>;
+		gpio = <&gpio_exp_77 15 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
 	};
 
-	snd_3p3v: regulator-snd_3p3v {
+	pcie_3v3: regulator-pcie-3v3 {
 		compatible = "regulator-fixed";
-		regulator-name = "snd-3.3v";
+		regulator-name = "pcie-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		gpio = <&gpio_exp_77 14 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
 	};
 
-	snd_vcc5v: regulator-snd_vcc5v {
+	reg_5v: regulator-5v {
 		compatible = "regulator-fixed";
-		regulator-name = "snd-vcc5v";
+		regulator-name = "fixed-5V";
 		regulator-min-microvolt = <5000000>;
 		regulator-max-microvolt = <5000000>;
+		regulator-boot-on;
+		regulator-always-on;
 	};
 
 	wlan_en: regulator-wlan_en {
@@ -157,11 +158,11 @@
 
 				pd-gpios = <&gpio_exp_75 5 GPIO_ACTIVE_LOW>;
 
-				avdd-supply = <&hdmi_1v8>;
-				dvdd-supply = <&hdmi_1v8>;
-				pvdd-supply = <&hdmi_1v8>;
-				dvdd-3v-supply = <&hdmi_3v3>;
-				bgvdd-supply = <&hdmi_1v8>;
+				avdd-supply = <&reg_t1p8v>;
+				dvdd-supply = <&reg_t1p8v>;
+				pvdd-supply = <&reg_t1p8v>;
+				dvdd-3v-supply = <&reg_3p3v>;
+				bgvdd-supply = <&reg_t1p8v>;
 
 				adi,input-depth = <8>;
 				adi,input-colorspace = "rgb";
@@ -198,8 +199,8 @@
 				compatible = "st,lsm9ds0-imu";
 				reg = <0x1d>;
 
-				vdd-supply = <&accel_3v3>;
-				vddio-supply = <&accel_3v3>;
+				vdd-supply = <&reg_3p3v>;
+				vddio-supply = <&reg_3p3v>;
 			};
 
 			pcm3168a: audio-codec@44 {
@@ -209,20 +210,20 @@
 				clocks = <&clksndsel>;
 				clock-names = "scki";
 
-				VDD1-supply = <&snd_3p3v>;
-				VDD2-supply = <&snd_3p3v>;
-				VCCAD1-supply = <&snd_vcc5v>;
-				VCCAD2-supply = <&snd_vcc5v>;
-				VCCDA1-supply = <&snd_vcc5v>;
-				VCCDA2-supply = <&snd_vcc5v>;
+				VDD1-supply = <&reg_3p3v>;
+				VDD2-supply = <&reg_3p3v>;
+				VCCAD1-supply = <&reg_5v>;
+				VCCAD2-supply = <&reg_5v>;
+				VCCDA1-supply = <&reg_5v>;
+				VCCDA2-supply = <&reg_5v>;
 			};
 
 			gyroscope@6b {
 				compatible = "st,lsm9ds0-gyro";
 				reg = <0x6b>;
 
-				vdd-supply = <&accel_3v3>;
-				vddio-supply = <&accel_3v3>;
+				vdd-supply = <&reg_3p3v>;
+				vddio-supply = <&reg_3p3v>;
 			};
 		};
 	};
@@ -234,6 +235,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <8 IRQ_TYPE_EDGE_FALLING>;
 
@@ -294,6 +296,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <4 IRQ_TYPE_EDGE_FALLING>;
 	};
@@ -314,6 +317,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio7>;
 		interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
 	};
@@ -324,6 +328,7 @@
 		gpio-controller;
 		#gpio-cells = <2>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 		interrupt-parent = <&gpio5>;
 		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
 	};
@@ -344,6 +349,9 @@
 
 &pciec1 {
 	status = "okay";
+
+	vpcie1v5-supply = <&pcie_1v5>;
+	vpcie3v3-supply = <&pcie_3v3>;
 };
 
 &pfc {
@@ -413,6 +421,13 @@
 	pinctrl-names = "default";
 
 	status = "okay";
+
+	gnss {
+		compatible = "u-blox,neo-m8";
+		reset-gpios = <&gpio_exp_75 6 GPIO_ACTIVE_LOW>;
+		vcc-supply = <&reg_3p3v>;
+		current-speed = <9600>;
+	};
 };
 
 &sdhi3 {
diff --git a/arch/arm64/boot/dts/renesas/white-hawk-common.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-common.dtsi
new file mode 100644
index 000000000000..c99086edadca
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/white-hawk-common.dtsi
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the common parts shared by the White Hawk BreakOut
+ * and White Hawk Single boards
+ *
+ * Copyright (C) 2022 Renesas Electronics Corp.
+ */
+
+#include "white-hawk-csi-dsi.dtsi"
+#include "white-hawk-ethernet.dtsi"
+
+/ {
+	can_transceiver0: can-phy0 {
+		compatible = "nxp,tjr1443";
+		#phy-cells = <0>;
+		enable-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
+		max-bitrate = <5000000>;
+	};
+};
+
+&can_clk {
+	clock-frequency = <40000000>;
+};
+
+&canfd {
+	pinctrl-0 = <&canfd0_pins>, <&canfd1_pins>, <&can_clk_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	channel0 {
+		status = "okay";
+		phys = <&can_transceiver0>;
+	};
+
+	channel1 {
+		status = "okay";
+	};
+};
+
+&i2c0 {
+	eeprom@51 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "breakout-board";
+		reg = <0x51>;
+		pagesize = <8>;
+	};
+};
+
+&pfc {
+	can_clk_pins: can-clk {
+		groups = "can_clk";
+		function = "can_clk";
+	};
+
+	canfd0_pins: canfd0 {
+		groups = "canfd0_data";
+		function = "canfd0";
+	};
+
+	canfd1_pins: canfd1 {
+		groups = "canfd1_data";
+		function = "canfd1";
+	};
+};
diff --git a/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi
new file mode 100644
index 000000000000..8ac17370ff36
--- /dev/null
+++ b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * Device Tree Source for the common parts shared by the White Hawk CPU and
+ * White Hawk Single boards
+ *
+ * Copyright (C) 2022 Renesas Electronics Corp.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	aliases {
+		ethernet0 = &avb0;
+		serial0 = &hscif0;
+	};
+
+	chosen {
+		bootargs = "ignore_loglevel rw root=/dev/nfs ip=on";
+		stdout-path = "serial0:921600n8";
+	};
+
+	sn65dsi86_refclk: clk-x6 {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <38400000>;
+	};
+
+	keys {
+		compatible = "gpio-keys";
+
+		pinctrl-0 = <&keys_pins>;
+		pinctrl-names = "default";
+
+		key-1 {
+			gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_1>;
+			label = "SW47";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+
+		key-2 {
+			gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_2>;
+			label = "SW48";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+
+		key-3 {
+			gpios = <&gpio5 2 GPIO_ACTIVE_LOW>;
+			linux,code = <KEY_3>;
+			label = "SW49";
+			wakeup-source;
+			debounce-interval = <20>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led-1 {
+			gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_INDICATOR;
+			function-enumerator = <1>;
+		};
+
+		led-2 {
+			gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_INDICATOR;
+			function-enumerator = <2>;
+		};
+
+		led-3 {
+			gpios = <&gpio7 2 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_INDICATOR;
+			function-enumerator = <3>;
+		};
+	};
+
+	memory@48000000 {
+		device_type = "memory";
+		/* first 128MB is reserved for secure area. */
+		reg = <0x0 0x48000000 0x0 0x78000000>;
+	};
+
+	memory@480000000 {
+		device_type = "memory";
+		reg = <0x4 0x80000000 0x0 0x80000000>;
+	};
+
+	memory@600000000 {
+		device_type = "memory";
+		reg = <0x6 0x00000000 0x1 0x00000000>;
+	};
+
+	mini-dp-con {
+		compatible = "dp-connector";
+		label = "CN5";
+		type = "mini";
+
+		port {
+			mini_dp_con_in: endpoint {
+				remote-endpoint = <&sn65dsi86_out>;
+			};
+		};
+	};
+
+	reg_1p2v: regulator-1p2v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.2V";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	reg_1p8v: regulator-1p8v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-1.8V";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+
+	reg_3p3v: regulator-3p3v {
+		compatible = "regulator-fixed";
+		regulator-name = "fixed-3.3V";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		regulator-always-on;
+	};
+};
+
+&avb0 {
+	pinctrl-0 = <&avb0_pins>;
+	pinctrl-names = "default";
+	phy-handle = <&phy0>;
+	tx-internal-delay-ps = <2000>;
+	status = "okay";
+
+	phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0022.1622",
+			     "ethernet-phy-ieee802.3-c22";
+		rxc-skew-ps = <1500>;
+		reg = <0>;
+		interrupt-parent = <&gpio7>;
+		interrupts = <5 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&dsi0 {
+	status = "okay";
+
+	ports {
+		port@1 {
+			dsi0_out: endpoint {
+				remote-endpoint = <&sn65dsi86_in>;
+				data-lanes = <1 2 3 4>;
+			};
+		};
+	};
+};
+
+&du {
+	status = "okay";
+};
+
+&extal_clk {
+	clock-frequency = <16666666>;
+};
+
+&extalr_clk {
+	clock-frequency = <32768>;
+};
+
+&hscif0 {
+	pinctrl-0 = <&hscif0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-0 = <&i2c0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+	clock-frequency = <400000>;
+
+	io_expander_a: gpio@20 {
+		compatible = "onnn,pca9654";
+		reg = <0x20>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	eeprom@50 {
+		compatible = "rohm,br24g01", "atmel,24c01";
+		label = "cpu-board";
+		reg = <0x50>;
+		pagesize = <8>;
+	};
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+	clock-frequency = <400000>;
+
+	bridge@2c {
+		compatible = "ti,sn65dsi86";
+		reg = <0x2c>;
+
+		clocks = <&sn65dsi86_refclk>;
+		clock-names = "refclk";
+
+		interrupt-parent = <&intc_ex>;
+		interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+		enable-gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>;
+
+		vccio-supply = <&reg_1p8v>;
+		vpll-supply = <&reg_1p8v>;
+		vcca-supply = <&reg_1p2v>;
+		vcc-supply = <&reg_1p2v>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				sn65dsi86_in: endpoint {
+					remote-endpoint = <&dsi0_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				sn65dsi86_out: endpoint {
+					remote-endpoint = <&mini_dp_con_in>;
+				};
+			};
+		};
+	};
+};
+
+&mmc0 {
+	pinctrl-0 = <&mmc_pins>;
+	pinctrl-1 = <&mmc_pins>;
+	pinctrl-names = "default", "state_uhs";
+
+	vmmc-supply = <&reg_3p3v>;
+	vqmmc-supply = <&reg_1p8v>;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	bus-width = <8>;
+	no-sd;
+	no-sdio;
+	non-removable;
+	full-pwr-cycle-in-suspend;
+	status = "okay";
+};
+
+&pfc {
+	pinctrl-0 = <&scif_clk_pins>;
+	pinctrl-names = "default";
+
+	avb0_pins: avb0 {
+		mux {
+			groups = "avb0_link", "avb0_mdio", "avb0_rgmii",
+				 "avb0_txcrefclk";
+			function = "avb0";
+		};
+
+		pins_mdio {
+			groups = "avb0_mdio";
+			drive-strength = <21>;
+		};
+
+		pins_mii {
+			groups = "avb0_rgmii";
+			drive-strength = <21>;
+		};
+
+	};
+
+	hscif0_pins: hscif0 {
+		groups = "hscif0_data";
+		function = "hscif0";
+	};
+
+	i2c0_pins: i2c0 {
+		groups = "i2c0";
+		function = "i2c0";
+	};
+
+	i2c1_pins: i2c1 {
+		groups = "i2c1";
+		function = "i2c1";
+	};
+
+	keys_pins: keys {
+		pins = "GP_5_0", "GP_5_1", "GP_5_2";
+		bias-pull-up;
+	};
+
+	mmc_pins: mmc {
+		groups = "mmc_data8", "mmc_ctrl", "mmc_ds";
+		function = "mmc";
+		power-source = <1800>;
+	};
+
+	qspi0_pins: qspi0 {
+		groups = "qspi0_ctrl", "qspi0_data4";
+		function = "qspi0";
+	};
+
+	scif_clk_pins: scif_clk {
+		groups = "scif_clk";
+		function = "scif_clk";
+	};
+};
+
+&rpc {
+	pinctrl-0 = <&qspi0_pins>;
+	pinctrl-names = "default";
+
+	status = "okay";
+
+	flash@0 {
+		compatible = "spansion,s25fs512s", "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <40000000>;
+		spi-rx-bus-width = <4>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			boot@0 {
+				reg = <0x0 0x1200000>;
+				read-only;
+			};
+			user@1200000 {
+				reg = <0x1200000 0x2e00000>;
+			};
+		};
+	};
+};
+
+&rwdt {
+	timeout-sec = <60>;
+	status = "okay";
+};
+
+&scif_clk {
+	clock-frequency = <24000000>;
+};
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-csi-dsi.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi
index f8537f7ea4de..3006b0a64f41 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-csi-dsi.dtsi
+++ b/arch/arm64/boot/dts/renesas/white-hawk-csi-dsi.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
- * Device Tree Source for the R-Car V4H White Hawk CSI/DSI sub-board
+ * Device Tree Source for the White Hawk CSI/DSI sub-board
  *
  * Copyright (C) 2022 Glider bv
  */
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-ethernet.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi
index 4f411f95c674..a218fda337cf 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g0-white-hawk-ethernet.dtsi
+++ b/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
- * Device Tree Source for the R-Car V4H White Hawk RAVB/Ethernet(1000Base-T1)
+ * Device Tree Source for the White Hawk RAVB/Ethernet(1000Base-T1)
  * sub-board
  *
  * Copyright (C) 2022 Glider bv
diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile
index a7b30e11beaf..f906a868b71a 100644
--- a/arch/arm64/boot/dts/rockchip/Makefile
+++ b/arch/arm64/boot/dts/rockchip/Makefile
@@ -71,6 +71,8 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-rockpro64.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-sapphire.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399-sapphire-excavator.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3399pro-rock-pi-n10.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg-arc-d.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg-arc-s.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg353p.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg353ps.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg353v.dtb
@@ -78,6 +80,9 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg353vs.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-anbernic-rg503.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinenote-v1.1.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinenote-v1.2.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinetab2-v0.1.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinetab2-v2.0.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-rgb10max3.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-rgb30.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-rk2023.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-powkiddy-x55.dtb
@@ -98,11 +103,13 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-lubancat-2.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-nanopi-r5c.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-nanopi-r5s.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-odroid-m1.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-qnap-ts433.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-radxa-e25.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-roc-pc.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-rock-3a.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-coolpi-cm5-evb.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-io.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6a-wifi.dtbo
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-edgeble-neu6b-io.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-evb1-v10.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-jaguar.dtb
@@ -110,9 +117,13 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-nanopc-t6.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-orangepi-5-plus.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-quartzpro64.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-rock-5b.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-tiger-haikou.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-toybrick-x0.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588-turing-rk1.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-coolpi-4b.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-indiedroid-nova.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-khadas-edge2.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-nanopi-r6s.dtb
+dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-nanopi-r6c.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-rock-5a.dtb
 dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3588s-orangepi-5.dtb
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index 16798eb77077..ae398acdcf45 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -227,6 +227,7 @@
 
 &uart5 {
 	pinctrl-0 = <&uart5_xfer>;
+	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index 12397755830b..bb1aea82e666 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -347,6 +347,12 @@
 	};
 };
 
+&pmu_io_domains {
+	pmuio1-supply = <&vcc_3v3>;
+	pmuio2-supply = <&vcc_3v3>;
+	status = "okay";
+};
+
 &saradc {
 	vref-supply = <&vcc_1v8>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index d0905515399b..9137dd76e72c 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -631,6 +631,7 @@
 		clock-names = "spiclk", "apb_pclk";
 		dmas = <&dmac 12>, <&dmac 13>;
 		dma-names = "tx", "rx";
+		num-cs = <2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>;
 		#address-cells = <1>;
@@ -646,6 +647,7 @@
 		clock-names = "spiclk", "apb_pclk";
 		dmas = <&dmac 14>, <&dmac 15>;
 		dma-names = "tx", "rx";
+		num-cs = <2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>;
 		#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
index 3cda6c627b68..f09d60bbe6c4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
@@ -148,7 +148,7 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
 	clock_in_out = "input";
-	phy-handle = <&rtl8211e>;
+	phy-handle = <&rtl8211>;
 	phy-mode = "rgmii";
 	phy-supply = <&vcc_io>;
 	pinctrl-names = "default";
@@ -165,7 +165,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		rtl8211e: ethernet-phy@1 {
+		rtl8211: ethernet-phy@1 {
 			reg = <1>;
 			pinctrl-0 = <&eth_phy_int_pin>, <&eth_phy_reset_pin>;
 			pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index fb5dcf6e9327..b6f045069ee2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -488,7 +488,6 @@
 	pwm3: pwm@ff1b0030 {
 		compatible = "rockchip,rk3328-pwm";
 		reg = <0x0 0xff1b0030 0x0 0x10>;
-		interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_PWM>, <&cru PCLK_PWM>;
 		clock-names = "pwm", "pclk";
 		pinctrl-names = "default";
@@ -745,11 +744,20 @@
 		status = "disabled";
 
 		ports {
-			hdmi_in: port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi_in: port@0 {
+				reg = <0>;
+
 				hdmi_in_vop: endpoint {
 					remote-endpoint = <&vop_out_hdmi>;
 				};
 			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
+			};
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
index 9e3aec4440bd..dfb2a0bdea5b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
@@ -22,9 +22,6 @@
 		ethernet0 = &gmac;
 		mmc0 = &sdmmc;
 		mmc1 = &sdhci;
-		spi1 = &spi1;
-		spi2 = &spi2;
-		spi5 = &spi5;
 	};
 
 	avdd_0v9_s0: avdd-0v9-s0 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
index e7551449e718..e26e2d86279c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-orangepi.dts
@@ -14,7 +14,7 @@
 
 / {
 	model = "Orange Pi RK3399 Board";
-	compatible = "rockchip,rk3399-orangepi", "rockchip,rk3399";
+	compatible = "xunlong,rk3399-orangepi", "rockchip,rk3399";
 
 	aliases {
 		ethernet0 = &gmac;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
index 18a98c4648ea..2c3984a880af 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
@@ -273,11 +273,12 @@
 
 &uart0 {
 	pinctrl-names = "default";
-	pinctrl-0 = <&uart0_xfer &uart0_cts &uart0_rts>;
+	pinctrl-0 = <&uart0_xfer>;
 	status = "okay";
 };
 
 &uart2 {
+	rts-gpios = <&gpio2 RK_PC3 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4a.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4a.dts
index d5df8939a658..c68f45849c44 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4a.dts
@@ -19,6 +19,6 @@
 	flash@0 {
 		compatible = "jedec,spi-nor";
 		reg = <0>;
-		spi-max-frequency = <10000000>;
+		spi-max-frequency = <108000000>;
 	};
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4b.dts
index bee6d7588302..6ea3180e57ca 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4b.dts
@@ -37,7 +37,7 @@
 	flash@0 {
 		compatible = "jedec,spi-nor";
 		reg = <0>;
-		spi-max-frequency = <10000000>;
+		spi-max-frequency = <108000000>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4c.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4c.dts
index de2ebe4cb4f3..5274938bf1b8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4c.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4c.dts
@@ -49,7 +49,7 @@
 	flash@0 {
 		compatible = "jedec,spi-nor";
 		reg = <0>;
-		spi-max-frequency = <10000000>;
+		spi-max-frequency = <108000000>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 6e12c5a920ca..9d5f5b083e3c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -38,6 +38,12 @@
 		serial2 = &uart2;
 		serial3 = &uart3;
 		serial4 = &uart4;
+		spi0 = &spi0;
+		spi1 = &spi1;
+		spi2 = &spi2;
+		spi3 = &spi3;
+		spi4 = &spi4;
+		spi5 = &spi5;
 	};
 
 	cpus {
@@ -45,7 +51,7 @@
 		#size-cells = <0>;
 
 		cpu-map {
-			cluster0 {
+			cluster0 {	/* Cortex-A53 */
 				core0 {
 					cpu = <&cpu_l0>;
 				};
@@ -60,7 +66,7 @@
 				};
 			};
 
-			cluster1 {
+			cluster1 {	/* Cortex-A72 */
 				core0 {
 					cpu = <&cpu_b0>;
 				};
@@ -80,6 +86,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <100>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_cache_l>;
 		};
 
 		cpu_l1: cpu@1 {
@@ -92,6 +105,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <100>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_cache_l>;
 		};
 
 		cpu_l2: cpu@2 {
@@ -104,6 +124,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <100>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_cache_l>;
 		};
 
 		cpu_l3: cpu@3 {
@@ -116,6 +143,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <100>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0x8000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <128>;
+			next-level-cache = <&l2_cache_l>;
 		};
 
 		cpu_b0: cpu@100 {
@@ -128,6 +162,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <436>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0xC000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_b>;
 
 			thermal-idle {
 				#cooling-cells = <2>;
@@ -146,6 +187,13 @@
 			#cooling-cells = <2>; /* min followed by max */
 			dynamic-power-coefficient = <436>;
 			cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>;
+			i-cache-size = <0xC000>;
+			i-cache-line-size = <64>;
+			i-cache-sets = <256>;
+			d-cache-size = <0x8000>;
+			d-cache-line-size = <64>;
+			d-cache-sets = <256>;
+			next-level-cache = <&l2_cache_b>;
 
 			thermal-idle {
 				#cooling-cells = <2>;
@@ -154,6 +202,24 @@
 			};
 		};
 
+		l2_cache_l: l2-cache-cluster0 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+			cache-size = <0x80000>;
+			cache-line-size = <64>;
+			cache-sets = <512>;
+		};
+
+		l2_cache_b: l2-cache-cluster1 {
+			compatible = "cache";
+			cache-level = <2>;
+			cache-unified;
+			cache-size = <0x100000>;
+			cache-line-size = <64>;
+			cache-sets = <1024>;
+		};
+
 		idle-states {
 			entry-method = "psci";
 
@@ -1956,6 +2022,7 @@
 	hdmi: hdmi@ff940000 {
 		compatible = "rockchip,rk3399-dw-hdmi";
 		reg = <0x0 0xff940000 0x0 0x20000>;
+		reg-io-width = <4>;
 		interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>;
 		clocks = <&cru PCLK_HDMI_CTRL>,
 			 <&cru SCLK_HDMI_SFR>,
@@ -1964,13 +2031,16 @@
 			 <&cru PLL_VPLL>;
 		clock-names = "iahb", "isfr", "cec", "grf", "ref";
 		power-domains = <&power RK3399_PD_HDCP>;
-		reg-io-width = <4>;
 		rockchip,grf = <&grf>;
 		#sound-dai-cells = <0>;
 		status = "disabled";
 
 		ports {
-			hdmi_in: port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			hdmi_in: port@0 {
+				reg = <0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
@@ -1983,6 +2053,10 @@
 					remote-endpoint = <&vopl_out_hdmi>;
 				};
 			};
+
+			hdmi_out: port@1 {
+				reg = <1>;
+			};
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-d.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-d.dts
new file mode 100644
index 000000000000..ab83e8a61615
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-d.dts
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3566-anbernic-rg-arc.dtsi"
+
+/ {
+	model = "Anbernic RG ARC-D";
+	compatible = "anbernic,rg-arc-d", "rockchip,rk3566";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc0;
+		mmc2 = &sdmmc1;
+		mmc3 = &sdmmc2;
+	};
+};
+
+&i2c2 {
+	pinctrl-0 = <&i2c2m1_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+
+	touchscreen@14 {
+		compatible = "goodix,gt927";
+		reg = <0x14>;
+		interrupt-parent = <&gpio4>;
+		interrupts = <RK_PB1 IRQ_TYPE_EDGE_FALLING>;
+		irq-gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&touch_int>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio4 RK_PA6 GPIO_ACTIVE_HIGH>;
+		touchscreen-inverted-y;
+		touchscreen-size-x = <640>;
+		touchscreen-size-y = <480>;
+	};
+};
+
+&pinctrl {
+	touchscreen {
+		touch_int: touch_int {
+			rockchip,pins = <4 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
+
+&sdhci {
+	bus-width = <8>;
+	mmc-hs200-1_8v;
+	non-removable;
+	pinctrl-0 = <&emmc_bus8>, <&emmc_clk>, <&emmc_cmd>,
+		    <&emmc_datastrobe>, <&emmc_rstnout>;
+	pinctrl-names = "default";
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-s.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-s.dts
new file mode 100644
index 000000000000..6264a8c78d0b
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc-s.dts
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3566-anbernic-rg-arc.dtsi"
+
+/ {
+	model = "Anbernic RG ARC-S";
+	compatible = "anbernic,rg-arc-s", "rockchip,rk3566";
+
+	aliases {
+		mmc1 = &sdmmc0;
+		mmc2 = &sdmmc1;
+		mmc3 = &sdmmc2;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc.dtsi
new file mode 100644
index 000000000000..a4a60e4a53d4
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg-arc.dtsi
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3566-anbernic-rgxx3.dtsi"
+
+/ {
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&vcc_sys>;
+		pwms = <&pwm4 0 25000 0>;
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		charge-full-design-microamp-hours = <3472000>;
+		charge-term-current-microamp = <300000>;
+		constant-charge-current-max-microamp = <2000000>;
+		constant-charge-voltage-max-microvolt = <4200000>;
+		factory-internal-resistance-micro-ohms = <117000>;
+		voltage-max-design-microvolt = <4172000>;
+		voltage-min-design-microvolt = <3400000>;
+
+		ocv-capacity-celsius = <20>;
+		ocv-capacity-table-0 =	<4172000 100>, <4054000 95>, <3984000 90>, <3926000 85>,
+					<3874000 80>, <3826000 75>, <3783000 70>, <3746000 65>,
+					<3714000 60>, <3683000 55>, <3650000 50>, <3628000 45>,
+					<3612000 40>, <3600000 35>, <3587000 30>, <3571000 25>,
+					<3552000 20>, <3525000 15>, <3492000 10>, <3446000 5>,
+					<3400000 0>;
+	};
+
+	/* Channels reversed for both headphones and speakers. */
+	sound {
+		compatible = "simple-audio-card";
+		pinctrl-0 = <&hp_det>;
+		pinctrl-names = "default";
+		simple-audio-card,name = "rk817_ext";
+		simple-audio-card,aux-devs = <&spk_amp>;
+		simple-audio-card,format = "i2s";
+		simple-audio-card,hp-det-gpio = <&gpio4 RK_PC6 GPIO_ACTIVE_HIGH>;
+		simple-audio-card,mclk-fs = <256>;
+		simple-audio-card,widgets =
+			"Microphone", "Mic Jack",
+			"Headphone", "Headphones",
+			"Speaker", "Internal Speakers";
+		simple-audio-card,routing =
+			"MICL", "Mic Jack",
+			"Headphones", "HPOL",
+			"Headphones", "HPOR",
+			"Internal Speakers", "Speaker Amp OUTL",
+			"Internal Speakers", "Speaker Amp OUTR",
+			"Speaker Amp INL", "HPOL",
+			"Speaker Amp INR", "HPOR";
+		simple-audio-card,pin-switches = "Internal Speakers";
+
+		simple-audio-card,codec {
+			sound-dai = <&rk817>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s1_8ch>;
+		};
+	};
+
+	spk_amp: audio-amplifier {
+		compatible = "simple-audio-amplifier";
+		enable-gpios = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>;
+		pinctrl-0 = <&spk_amp_enable_h>;
+		pinctrl-names = "default";
+		sound-name-prefix = "Speaker Amp";
+	};
+};
+
+&cru {
+	assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>,
+			  <&pmucru PLL_PPLL>, <&cru PLL_VPLL>;
+	assigned-clock-rates = <32768>, <1200000000>,
+			       <200000000>, <128000000>;
+};
+
+&dsi_dphy0 {
+	status = "okay";
+};
+
+&dsi0 {
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	ports {
+		dsi0_in: port@0 {
+			reg = <0>;
+			dsi0_in_vp1: endpoint {
+				remote-endpoint = <&vp1_out_dsi0>;
+			};
+		};
+
+		dsi0_out: port@1 {
+			reg = <1>;
+			mipi_out_panel: endpoint {
+				remote-endpoint = <&mipi_in_panel>;
+			};
+		};
+	};
+
+	panel: panel@0 {
+		compatible = "anbernic,rg-arc-panel", "sitronix,st7701";
+		reg = <0>;
+		backlight = <&backlight>;
+		IOVCC-supply = <&vcc3v3_lcd0_n>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_rst>;
+		reset-gpios = <&gpio4 RK_PA0 GPIO_ACTIVE_HIGH>;
+		rotation = <90>;
+		VCC-supply = <&vcc3v3_lcd0_n>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+/*
+ * Device uses a non-standard six button layout for a gamepad with X,
+ * Y, and Z on the top row of buttons and A, B, and C under the bottom
+ * row.
+ */
+&gpio_keys_control {
+	button-a {
+		gpios = <&gpio3 RK_PC3 GPIO_ACTIVE_LOW>;
+		label = "A";
+		linux,code = <BTN_A>;
+	};
+
+	button-b {
+		gpios = <&gpio3 RK_PC2 GPIO_ACTIVE_LOW>;
+		label = "B";
+		linux,code = <BTN_B>;
+	};
+
+	button-c {
+		gpios = <&gpio3 RK_PA2 GPIO_ACTIVE_LOW>;
+		label = "C";
+		linux,code = <BTN_C>;
+	};
+
+	button-left {
+		gpios = <&gpio3 RK_PA6 GPIO_ACTIVE_LOW>;
+		label = "DPAD-LEFT";
+		linux,code = <BTN_DPAD_LEFT>;
+	};
+
+	button-r1 {
+		gpios = <&gpio3 RK_PB4 GPIO_ACTIVE_LOW>;
+		label = "TR";
+		linux,code = <BTN_TR>;
+	};
+
+	button-r2 {
+		gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_LOW>;
+		label = "TR2";
+		linux,code = <BTN_TR2>;
+	};
+
+	button-right {
+		gpios = <&gpio3 RK_PA5 GPIO_ACTIVE_LOW>;
+		label = "DPAD-RIGHT";
+		linux,code = <BTN_DPAD_RIGHT>;
+	};
+
+	button-x {
+		gpios = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
+		label = "X";
+		linux,code = <BTN_X>;
+	};
+
+	button-y {
+		gpios = <&gpio3 RK_PC1 GPIO_ACTIVE_LOW>;
+		label = "Y";
+		linux,code = <BTN_Y>;
+	};
+
+	button-z {
+		gpios = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>;
+		label = "Z";
+		linux,code = <BTN_Z>;
+	};
+};
+
+&pinctrl {
+	audio-amplifier {
+		spk_amp_enable_h: spk-amp-enable-h {
+			rockchip,pins =
+				<4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	gpio-lcd {
+		lcd_rst: lcd-rst {
+			rockchip,pins =
+				<4 RK_PA0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	headphone {
+		hp_det: hp-det {
+			rockchip,pins =
+				<4 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&rk817 {
+	rk817_charger: charger {
+		monitored-battery = <&battery>;
+		rockchip,resistor-sense-micro-ohms = <10000>;
+		rockchip,sleep-enter-current-microamp = <300000>;
+		rockchip,sleep-filter-current-microamp = <100000>;
+	};
+};
+
+&vp1 {
+	vp1_out_dsi0: endpoint@ROCKCHIP_VOP2_EP_MIPI0 {
+		reg = <ROCKCHIP_VOP2_EP_MIPI0>;
+		remote-endpoint = <&dsi0_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi
index 2a2821f4c580..63a18ff36cea 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353x.dtsi
@@ -8,11 +8,73 @@
 #include "rk3566-anbernic-rgxx3.dtsi"
 
 / {
+	adc-joystick {
+		compatible = "adc-joystick";
+		io-channels = <&adc_mux 0>,
+			      <&adc_mux 1>,
+			      <&adc_mux 2>,
+			      <&adc_mux 3>;
+		pinctrl-0 = <&joy_mux_en>;
+		pinctrl-names = "default";
+		poll-interval = <60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		axis@0 {
+			reg = <0>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_X>;
+		};
+
+		axis@1 {
+			reg = <1>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_RX>;
+		};
+
+		axis@2 {
+			reg = <2>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_Y>;
+		};
+
+		axis@3 {
+			reg = <3>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_RY>;
+		};
+	};
+
+	adc_mux: adc-mux {
+		compatible = "io-channel-mux";
+		channels = "left_x", "right_x", "left_y", "right_y";
+		#io-channel-cells = <1>;
+		io-channels = <&saradc 3>;
+		io-channel-names = "parent";
+		mux-controls = <&gpio_mux>;
+		settle-time-us = <100>;
+	};
+
 	backlight: backlight {
 		compatible = "pwm-backlight";
 		power-supply = <&vcc_sys>;
 		pwms = <&pwm4 0 25000 0>;
 	};
+
+	gpio_mux: mux-controller {
+		compatible = "gpio-mux";
+		mux-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_LOW>,
+			    <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>;
+		#mux-control-cells = <0>;
+	};
 };
 
 &cru {
@@ -83,6 +145,18 @@
 		linux,code = <BTN_DPAD_RIGHT>;
 	};
 
+	button-thumbl {
+		gpios = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>;
+		label = "THUMBL";
+		linux,code = <BTN_THUMBL>;
+	};
+
+	button-thumbr {
+		gpios = <&gpio3 RK_PA2 GPIO_ACTIVE_LOW>;
+		label = "THUMBR";
+		linux,code = <BTN_THUMBR>;
+	};
+
 	button-y {
 		gpios = <&gpio3 RK_PC1 GPIO_ACTIVE_LOW>;
 		label = "WEST";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts
index c763c7f3b1b3..94e6dd61a2db 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg503.dts
@@ -17,6 +17,61 @@
 		mmc2 = &sdmmc2;
 	};
 
+	adc-joystick {
+		compatible = "adc-joystick";
+		io-channels = <&adc_mux 0>,
+			      <&adc_mux 1>,
+			      <&adc_mux 2>,
+			      <&adc_mux 3>;
+		pinctrl-0 = <&joy_mux_en>;
+		pinctrl-names = "default";
+		poll-interval = <60>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		axis@0 {
+			reg = <0>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_X>;
+		};
+
+		axis@1 {
+			reg = <1>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_RX>;
+		};
+
+		axis@2 {
+			reg = <2>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <15 1023>;
+			linux,code = <ABS_Y>;
+		};
+
+		axis@3 {
+			reg = <3>;
+			abs-flat = <32>;
+			abs-fuzz = <32>;
+			abs-range = <1023 15>;
+			linux,code = <ABS_RY>;
+		};
+	};
+
+	adc_mux: adc-mux {
+		compatible = "io-channel-mux";
+		channels = "left_x", "right_x", "left_y", "right_y";
+		#io-channel-cells = <1>;
+		io-channels = <&saradc 3>;
+		io-channel-names = "parent";
+		mux-controls = <&gpio_mux>;
+		settle-time-us = <100>;
+	};
+
 	battery: battery {
 		compatible = "simple-battery";
 		charge-full-design-microamp-hours = <3472000>;
@@ -36,6 +91,13 @@
 					<3400000 0>;
 	};
 
+	gpio_mux: mux-controller {
+		compatible = "gpio-mux";
+		mux-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_LOW>,
+			    <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>;
+		#mux-control-cells = <0>;
+	};
+
 	gpio_spi: spi {
 		compatible = "spi-gpio";
 		pinctrl-names = "default";
@@ -174,6 +236,18 @@
 		linux,code = <BTN_DPAD_RIGHT>;
 	};
 
+	button-thumbl {
+		gpios = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>;
+		label = "THUMBL";
+		linux,code = <BTN_THUMBL>;
+	};
+
+	button-thumbr {
+		gpios = <&gpio3 RK_PA2 GPIO_ACTIVE_LOW>;
+		label = "THUMBR";
+		linux,code = <BTN_THUMBR>;
+	};
+
 	button-y {
 		gpios = <&gpio3 RK_PC2 GPIO_ACTIVE_LOW>;
 		label = "WEST";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rgxx3.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rgxx3.dtsi
index 8cbf3d9a4f22..18b8c2e7befa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rgxx3.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rgxx3.dtsi
@@ -14,51 +14,6 @@
 		stdout-path = "serial2:1500000n8";
 	};
 
-	adc-joystick {
-		compatible = "adc-joystick";
-		io-channels = <&adc_mux 0>,
-			      <&adc_mux 1>,
-			      <&adc_mux 2>,
-			      <&adc_mux 3>;
-		pinctrl-0 = <&joy_mux_en>;
-		pinctrl-names = "default";
-		poll-interval = <60>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		axis@0 {
-			reg = <0>;
-			abs-flat = <32>;
-			abs-fuzz = <32>;
-			abs-range = <1023 15>;
-			linux,code = <ABS_X>;
-		};
-
-		axis@1 {
-			reg = <1>;
-			abs-flat = <32>;
-			abs-fuzz = <32>;
-			abs-range = <15 1023>;
-			linux,code = <ABS_RX>;
-		};
-
-		axis@2 {
-			reg = <2>;
-			abs-flat = <32>;
-			abs-fuzz = <32>;
-			abs-range = <15 1023>;
-			linux,code = <ABS_Y>;
-		};
-
-		axis@3 {
-			reg = <3>;
-			abs-flat = <32>;
-			abs-fuzz = <32>;
-			abs-range = <1023 15>;
-			linux,code = <ABS_RY>;
-		};
-	};
-
 	adc_keys: adc-keys {
 		compatible = "adc-keys";
 		io-channels = <&saradc 0>;
@@ -77,16 +32,6 @@
 		};
 	};
 
-	adc_mux: adc-mux {
-		compatible = "io-channel-mux";
-		channels = "left_x", "right_x", "left_y", "right_y";
-		#io-channel-cells = <1>;
-		io-channels = <&saradc 3>;
-		io-channel-names = "parent";
-		mux-controls = <&gpio_mux>;
-		settle-time-us = <100>;
-	};
-
 	gpio_keys_control: gpio-keys-control {
 		compatible = "gpio-keys";
 		pinctrl-0 = <&btn_pins_ctrl>;
@@ -128,18 +73,6 @@
 			linux,code = <BTN_START>;
 		};
 
-		button-thumbl {
-			gpios = <&gpio3 RK_PA1 GPIO_ACTIVE_LOW>;
-			label = "THUMBL";
-			linux,code = <BTN_THUMBL>;
-		};
-
-		button-thumbr {
-			gpios = <&gpio3 RK_PA2 GPIO_ACTIVE_LOW>;
-			label = "THUMBR";
-			linux,code = <BTN_THUMBR>;
-		};
-
 		button-up {
 			gpios = <&gpio3 RK_PA3 GPIO_ACTIVE_LOW>;
 			label = "DPAD-UP";
@@ -172,13 +105,6 @@
 		};
 	};
 
-	gpio_mux: mux-controller {
-		compatible = "gpio-mux";
-		mux-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_LOW>,
-			    <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>;
-		#mux-control-cells = <0>;
-	};
-
 	hdmi-con {
 		compatible = "hdmi-connector";
 		ddc-i2c-bus = <&i2c5>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v0.1.dts b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v0.1.dts
new file mode 100644
index 000000000000..5fe6ca5da9d3
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v0.1.dts
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include "rk3566-pinetab2.dtsi"
+
+/ {
+	model = "Pine64 PineTab2 v0.1";
+	compatible = "pine64,pinetab2-v0.1", "pine64,pinetab2", "rockchip,rk3566";
+};
+
+&lcd {
+	reset-gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_LOW>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&lcd_pwren_h &lcd0_rst_l>;
+};
+
+&pinctrl {
+	lcd0 {
+		lcd0_rst_l: lcd0-rst-l {
+			rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&sdmmc1 {
+	vmmc-supply = <&vcc3v3_sys>;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v2.0.dts b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v2.0.dts
new file mode 100644
index 000000000000..9349541cbbd0
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2-v2.0.dts
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include "rk3566-pinetab2.dtsi"
+
+/ {
+	model = "Pine64 PineTab2 v2.0";
+	compatible = "pine64,pinetab2-v2.0", "pine64,pinetab2", "rockchip,rk3566";
+};
+
+&gpio_keys {
+	pinctrl-0 = <&kb_id_det>, <&hall_int_l>;
+
+	event-hall-sensor {
+		debounce-interval = <20>;
+		gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_LOW>;
+		label = "Hall Sensor";
+		linux,code = <SW_LID>;
+		linux,input-type = <EV_SW>;
+		wakeup-event-action = <EV_ACT_DEASSERTED>;
+		wakeup-source;
+	};
+};
+
+&lcd {
+	reset-gpios = <&gpio0 RK_PC6 GPIO_ACTIVE_LOW>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&lcd_pwren_h &lcd0_rst_l>;
+};
+
+&pinctrl {
+	lcd0 {
+		lcd0_rst_l: lcd0-rst-l {
+			rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hall {
+		hall_int_l: hall-int-l {
+			rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&sdmmc1 {
+	vmmc-supply = <&vcc_sys>;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi
new file mode 100644
index 000000000000..db40281eafbe
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi
@@ -0,0 +1,943 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/gpio-keys.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/soc/rockchip,vop2.h>
+#include <dt-bindings/usb/pd.h>
+#include "rk3566.dtsi"
+
+/ {
+	chassis-type = "tablet";
+
+	aliases {
+		mmc0 = &sdhci;
+		mmc1 = &sdmmc0;
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <25>;
+
+		button-vol-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			press-threshold-microvolt = <297500>;
+		};
+
+		button-vol-down {
+			label = "Volume Down";
+			linux,code = <KEY_VOLUMEDOWN>;
+			press-threshold-microvolt = <1750>;
+		};
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		pwms = <&pwm4 0 25000 0>;
+		brightness-levels = <20 220>;
+		num-interpolated-steps = <200>;
+		default-brightness-level = <100>;
+		power-supply = <&vcc_sys>;
+	};
+
+	battery: battery {
+		compatible = "simple-battery";
+		charge-full-design-microamp-hours = <6000000>;
+		charge-term-current-microamp = <300000>;
+		constant-charge-current-max-microamp = <2000000>;
+		constant-charge-voltage-max-microvolt = <4300000>;
+		voltage-max-design-microvolt = <4350000>;
+		voltage-min-design-microvolt = <3400000>;
+
+		ocv-capacity-celsius = <20>;
+		ocv-capacity-table-0 = <4322000 100>, <4250000 95>, <4192000 90>, <4136000 85>,
+				       <4080000 80>, <4022000 75>, <3972000 70>, <3928000 65>,
+				       <3885000 60>, <3833000 55>, <3798000 50>, <3780000 45>,
+				       <3776000 40>, <3773000 35>, <3755000 30>, <3706000 25>,
+				       <3640000 20>, <3589000 15>, <3535000 10>, <3492000 5>,
+				       <3400000 0>;
+	};
+
+	gpio_keys: gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&kb_id_det>;
+
+		tablet-mode-switch {
+			debounce-interval = <20>;
+			gpios = <&gpio4 RK_PA4 GPIO_ACTIVE_HIGH>;
+			label = "Tablet Mode";
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_TABLET_MODE>;
+		};
+	};
+
+	hdmi-connector {
+		compatible = "hdmi-connector";
+		type = "d";
+
+		port {
+			hdmi_con_in: endpoint {
+				remote-endpoint = <&hdmi_out_con>;
+			};
+		};
+	};
+
+	led-0 {
+		compatible = "regulator-led";
+		vled-supply = <&vcc5v0_flashled>;
+		color = <LED_COLOR_ID_WHITE>;
+		function = LED_FUNCTION_FLASH;
+	};
+
+	rk817-sound {
+		compatible = "simple-audio-card";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hp_det_l>;
+		simple-audio-card,format = "i2s";
+		simple-audio-card,name = "rk817_ext";
+		simple-audio-card,mclk-fs = <256>;
+
+		simple-audio-card,widgets =
+			"Microphone", "Mic Jack",
+			"Headphone", "Headphones",
+			"Speaker", "Internal Speakers";
+
+		simple-audio-card,routing =
+			"MICR", "Mic Jack",
+			"Headphones", "HPOL",
+			"Headphones", "HPOR",
+			"Internal Speakers", "Speaker Amplifier OUTL",
+			"Internal Speakers", "Speaker Amplifier OUTR",
+			"Speaker Amplifier INL", "HPOL",
+			"Speaker Amplifier INR", "HPOR";
+		simple-audio-card,hp-det-gpio = <&gpio4 RK_PC6 GPIO_ACTIVE_LOW>;
+		simple-audio-card,aux-devs = <&speaker_amp>;
+		simple-audio-card,pin-switches = "Internal Speakers";
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s1_8ch>;
+		};
+
+		simple-audio-card,codec {
+			sound-dai = <&rk817>;
+		};
+	};
+
+	speaker_amp: speaker-amplifier {
+		compatible = "simple-audio-amplifier";
+		pinctrl-names = "default";
+		pinctrl-0 = <&spk_ctl>;
+		enable-gpios = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>;
+		sound-name-prefix = "Speaker Amplifier";
+		VCC-supply = <&vcc_bat>;
+	};
+
+	vcc_3v3: vcc-3v3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vcc3v3_minipcie: vcc3v3-minipcie-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC3 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie_pwren_h>;
+		regulator-name = "vcc3v3_minipcie";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_sys>;
+	};
+
+	vcc3v3_sd: vcc3v3-sd-regulator {
+		compatible = "regulator-fixed";
+		gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&sdmmc_pwren_l>;
+		regulator-name = "vcc3v3_sd";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
+	vcc5v0_flashled: vcc5v0-flashled-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PA5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&flash_led_en_h>;
+		regulator-name = "vcc5v0_flashled";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v_midu>;
+	};
+
+	vcc5v0_usb_host0: vcc5v0-usb-host0-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC4 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_host_pwren1_h>;
+		regulator-name = "vcc5v0_usb_host0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v_midu>;
+	};
+
+	vcc5v0_usb_host2: vcc5v0-usb-host2-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&usb_host_pwren2_h>;
+		regulator-name = "vcc5v0_usb_host2";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v_midu>;
+	};
+
+	vcc_bat: vcc-bat-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_bat";
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vcc_sys: vcc-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_bat>;
+	};
+
+	vdd1v2_dvp: vdd1v2-dvp-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd1v2_dvp";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		vin-supply = <&vcc_3v3>;
+	};
+};
+
+&combphy1 {
+	status = "okay";
+};
+
+&combphy2 {
+	status = "okay";
+};
+
+&cpu0 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu1 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu2 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cpu3 {
+	cpu-supply = <&vdd_cpu>;
+};
+
+&cru {
+	assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>,
+			  <&pmucru PLL_PPLL>, <&cru PLL_VPLL>;
+	assigned-clock-rates = <32768>, <1200000000>, <200000000>, <500000000>;
+	assigned-clock-parents = <&pmucru CLK_RTC32K_FRAC>;
+};
+
+&csi_dphy {
+	status = "okay";
+};
+
+&dsi0 {
+	status = "okay";
+	clock-master;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	lcd: panel@0 {
+		compatible = "boe,th101mb31ig002-28a";
+		reg = <0>;
+		backlight = <&backlight>;
+		enable-gpios = <&gpio0 RK_PC7 GPIO_ACTIVE_HIGH>;
+		rotation = <90>;
+		power-supply = <&vcc_3v3>;
+
+		port@0 {
+			panel_in_dsi: endpoint@0 {
+				remote-endpoint = <&dsi0_out_con>;
+			};
+		};
+	};
+};
+
+&dsi0_in {
+	dsi0_in_vp1: endpoint {
+		remote-endpoint = <&vp1_out_dsi0>;
+	};
+};
+
+&dsi0_out {
+	dsi0_out_con: endpoint {
+		remote-endpoint = <&panel_in_dsi>;
+	};
+};
+
+&dsi_dphy0 {
+	status = "okay";
+};
+
+&gpu {
+	mali-supply = <&vdd_gpu_npu>;
+	status = "okay";
+};
+
+&hdmi {
+	avdd-0v9-supply = <&vdda_0v9_p>;
+	avdd-1v8-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&hdmi_in {
+	hdmi_in_vp0: endpoint {
+		remote-endpoint = <&vp0_out_hdmi>;
+	};
+};
+
+&hdmi_out {
+	hdmi_out_con: endpoint {
+		remote-endpoint = <&hdmi_con_in>;
+	};
+};
+
+&hdmi_sound {
+	status = "okay";
+};
+
+&i2c0 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu";
+		regulator-min-microvolt = <800000>;
+		regulator-max-microvolt = <1150000>;
+		regulator-ramp-delay = <2300>;
+		regulator-always-on;
+		regulator-boot-on;
+		vin-supply = <&vcc_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	rk817: pmic@20 {
+		compatible = "rockchip,rk817";
+		reg = <0x20>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>;
+		assigned-clocks = <&cru I2S1_MCLKOUT_TX>;
+		assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>;
+		clock-names = "mclk";
+		clocks = <&cru I2S1_MCLKOUT_TX>;
+		clock-output-names = "rk808-clkout1", "rk808-clkout2";
+		#clock-cells = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int_l>, <&i2s1m0_mclk>;
+		rockchip,system-power-controller;
+		#sound-dai-cells = <0>;
+		wakeup-source;
+
+		vcc1-supply = <&vcc_sys>;
+		vcc2-supply = <&vcc_sys>;
+		vcc3-supply = <&vcc_sys>;
+		vcc4-supply = <&vcc_sys>;
+		vcc5-supply = <&vcc_sys>;
+		vcc6-supply = <&vcc_sys>;
+		vcc7-supply = <&vcc_sys>;
+		vcc8-supply = <&vcc_sys>;
+		vcc9-supply = <&vcc5v_midu>;
+
+		regulators {
+			vdd_logic: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_logic";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_gpu_npu: DCDC_REG2 {
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-ramp-delay = <6001>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vdd_gpu_npu";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc_ddr";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc3v3_sys: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-initial-mode = <0x2>;
+				regulator-name = "vcc3v3_sys";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca1v8_pmu: LDO_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcca1v8_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vdda_0v9_p: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda_0v9_p";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda0v9_pmu: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <900000>;
+				regulator-name = "vdda0v9_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vccio_acodec: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_acodec";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc3v3_pmu: LDO_REG6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc3v3_pmu";
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_1v8: LDO_REG7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc1v8_dvp: LDO_REG8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc1v8_dvp";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc2v8_dvp: LDO_REG9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2800000>;
+				regulator-max-microvolt = <2800000>;
+				regulator-name = "vcc2v8_dvp";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc5v_midu: BOOST {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-name = "boost";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vbus: OTG_SWITCH {
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5000000>;
+				regulator-name = "otg_switch";
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+
+		charger {
+			monitored-battery = <&battery>;
+			rockchip,resistor-sense-micro-ohms = <10000>;
+			rockchip,sleep-enter-current-microamp = <300000>;
+			rockchip,sleep-filter-current-microamp = <100000>;
+		};
+	};
+};
+
+&i2c1 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	touchscreen@5d {
+		compatible = "goodix,gt911";
+		reg = <0x5d>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB0 IRQ_TYPE_EDGE_FALLING>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&tp_int_l_pmuio2>, <&tp_rst_l_pmuio2>;
+		AVDD28-supply = <&vcc3v3_pmu>;
+		VDDIO-supply = <&vcca1v8_pmu>;
+		irq-gpios = <&gpio0 RK_PB0 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>;
+	};
+};
+
+&i2c2 {
+	clock-frequency = <400000>;
+	pinctrl-0 = <&i2c2m1_xfer>;
+	status = "okay";
+
+	vcm@c {
+		compatible = "dongwoon,dw9714";
+		reg = <0x0c>;
+		vcc-supply = <&vcc1v8_dvp>;
+	};
+
+	camera@36 {
+		compatible = "ovti,ov5648";
+		reg = <0x36>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&camerab_pdn_l &camerab_rst_l>;
+
+		clocks = <&cru CLK_CIF_OUT>;
+		assigned-clocks = <&cru CLK_CIF_OUT>;
+		assigned-clock-rates = <24000000>;
+
+		avdd-supply = <&vcc2v8_dvp>;
+		dvdd-supply = <&vdd1v2_dvp>;
+		dovdd-supply = <&vcc1v8_dvp>;
+		powerdown-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_LOW>;
+
+		port {
+			endpoint {
+				data-lanes = <1 2>;
+				remote-endpoint = <0>;
+				link-frequencies = /bits/ 64 <210000000 168000000>;
+			};
+		};
+	};
+};
+
+&i2c5 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	accelerometer@18 {
+		compatible = "silan,sc7a20";
+		reg = <0x18>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <RK_PA2 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&gsensor_int_l>;
+		st,drdy-int-pin = <1>;
+		vdd-supply = <&vcc_1v8>;
+		vddio-supply = <&vcc_1v8>;
+		mount-matrix = "1", "0", "0",
+			       "0", "0", "1",
+			       "0", "1", "0";
+	};
+};
+
+&i2s0_8ch {
+	status = "okay";
+};
+
+&i2s1_8ch {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2s1m0_sclktx
+		     &i2s1m0_lrcktx
+		     &i2s1m0_sdi0
+		     &i2s1m0_sdo0>;
+	rockchip,trcm-sync-tx-only;
+	status = "okay";
+};
+
+&pcie2x1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie_reset_h>;
+	reset-gpios = <&gpio1 RK_PB2 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_minipcie>;
+	status = "okay";
+};
+
+&pinctrl {
+	camerab {
+		camerab_pdn_l: camerab-pdn-l {
+			rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		camerab_rst_l: camerab-rst-l {
+			rockchip,pins = <4 RK_PB1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	cameraf {
+		cameraf_pdn_l: cameraf-pdn-l {
+			rockchip,pins = <4 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		cameraf_rst_l: cameraf-rst-l {
+			rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	flash {
+		flash_led_en_h: flash-led-en-h {
+			rockchip,pins = <4 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	fspi {
+		fspi_dual_io_pins: fspi-dual-io-pins {
+			rockchip,pins =
+				/* fspi_clk */
+				<1 RK_PD0 1 &pcfg_pull_none>,
+				/* fspi_cs0n */
+				<1 RK_PD3 1 &pcfg_pull_none>,
+				/* fspi_d0 */
+				<1 RK_PD1 1 &pcfg_pull_none>,
+				/* fspi_d1 */
+				<1 RK_PD2 1 &pcfg_pull_none>;
+		};
+	};
+
+	gsensor {
+		gsensor_int_l: gsensor-int-l {
+			rockchip,pins = <3 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	kb {
+		kb_id_det: kb-id-det {
+			rockchip,pins = <4 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	lcd {
+		lcd_pwren_h: lcd-pwren-h {
+			rockchip,pins = <0 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie {
+		pcie_pwren_h: pcie-pwren-h {
+			rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie_reset_h: pcie-reset-h {
+			rockchip,pins = <1 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pmic {
+		pmic_int_l: pmic-int-l {
+			rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdmmc {
+		sdmmc_pwren_l: sdmmc-pwren-l {
+			rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	sound {
+		hp_det_l: hp-det-l {
+			rockchip,pins = <4 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		spk_ctl: spk-ctl {
+			rockchip,pins = <4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	tp {
+		tp_int_l_pmuio2: tp-int-l-pmuio2 {
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+
+		tp_rst_l_pmuio2: tp-rst-l-pmuio2 {
+			rockchip,pins = <0 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		usbcc_int_l: usbcc-int-l {
+			rockchip,pins = <0 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usb_host_pwren1_h: usb-host-pwren1-h {
+			rockchip,pins = <4 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		usb_host_pwren2_h: usb-host-pwren2-h {
+			rockchip,pins = <4 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	wifi {
+		host_wake_wl: host-wake-wl {
+			rockchip,pins = <0 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		wifi_wake_host_h: wifi-wake-host-h {
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
+		};
+	};
+};
+
+&pmu_io_domains {
+	pmuio1-supply = <&vcc3v3_pmu>;
+	pmuio2-supply = <&vcca1v8_pmu>;
+	vccio1-supply = <&vccio_acodec>;
+	vccio2-supply = <&vcc_1v8>;
+	vccio3-supply = <&vccio_sd>;
+	vccio4-supply = <&vcc_1v8>;
+	vccio5-supply = <&vcc_1v8>;
+	vccio6-supply = <&vcc1v8_dvp>;
+	vccio7-supply = <&vcc_3v3>;
+	status = "okay";
+};
+
+&pwm4 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	max-frequency = <200000000>;
+	mmc-hs200-1_8v;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8
+		     &emmc_clk
+		     &emmc_cmd
+		     &emmc_datastrobe
+		     &emmc_rstnout>;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_1v8>;
+	status = "okay";
+};
+
+&sdmmc0 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc0_bus4
+		     &sdmmc0_clk
+		     &sdmmc0_cmd
+		     &sdmmc0_det>;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc3v3_sd>;
+	vqmmc-supply = <&vccio_sd>;
+	status = "okay";
+};
+
+&sdmmc1 {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	cap-sdio-irq;
+	keep-power-in-suspend;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&sdmmc1_bus4
+		     &sdmmc1_cmd
+		     &sdmmc1_clk>;
+	sd-uhs-sdr104;
+	vqmmc-supply = <&vcca1v8_pmu>;
+	status = "okay";
+};
+
+&sfc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&fspi_dual_io_pins>;
+	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		spi-max-frequency = <100000000>;
+		spi-rx-bus-width = <2>;
+		spi-tx-bus-width = <1>;
+	};
+};
+
+&tsadc {
+	rockchip,hw-tshut-mode = <1>;
+	rockchip,hw-tshut-polarity = <0>;
+	status = "okay";
+};
+
+&uart2 {
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host0_xhci {
+	status = "okay";
+};
+
+&usb_host1_xhci {
+	status = "okay";
+};
+
+&usb2phy0 {
+	status = "okay";
+};
+
+&usb2phy0_host {
+	phy-supply = <&vcc5v0_usb_host0>;
+	status = "okay";
+};
+
+&usb2phy0_otg {
+	status = "okay";
+};
+
+&usb2phy1 {
+	status = "okay";
+};
+
+&usb2phy1_otg {
+	phy-supply = <&vcc5v0_usb_host2>;
+	status = "okay";
+};
+
+&vop {
+	assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>;
+	assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>;
+	status = "okay";
+};
+
+&vop_mmu {
+	status = "okay";
+};
+
+&vp0 {
+	vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 {
+		reg = <ROCKCHIP_VOP2_EP_HDMI0>;
+		remote-endpoint = <&hdmi_in_vp0>;
+	};
+};
+
+&vp1 {
+	vp1_out_dsi0: endpoint@ROCKCHIP_VOP2_EP_MIPI0 {
+		reg = <ROCKCHIP_VOP2_EP_MIPI0>;
+		remote-endpoint = <&dsi0_in_vp1>;
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb10max3.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb10max3.dts
new file mode 100644
index 000000000000..e5a474e681dd
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb10max3.dts
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/linux-event-codes.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3566-powkiddy-rk2023.dtsi"
+
+/ {
+	model = "Powkiddy RGB10MAX3";
+	compatible = "powkiddy,rgb10max3", "rockchip,rk3566";
+};
+
+&bluetooth {
+	compatible = "realtek,rtl8723ds-bt";
+};
+
+&cru {
+	assigned-clocks = <&pmucru CLK_RTC_32K>, <&cru PLL_GPLL>,
+			  <&pmucru PLL_PPLL>, <&cru PLL_VPLL>;
+	assigned-clock-rates = <32768>, <1200000000>,
+			       <200000000>, <126400000>;
+};
+
+&dsi0 {
+	panel: panel@0 {
+		compatible = "powkiddy,rgb10max3-panel";
+		reg = <0>;
+		backlight = <&backlight>;
+		iovcc-supply = <&vcc3v3_lcd0_n>;
+		pinctrl-0 = <&lcd_rst>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio4 RK_PA0 GPIO_ACTIVE_LOW>;
+		rotation = <270>;
+		vcc-supply = <&vcc3v3_lcd0_n>;
+
+		port {
+			mipi_in_panel: endpoint {
+				remote-endpoint = <&mipi_out_panel>;
+			};
+		};
+	};
+};
+
+&green_led {
+	default-state = "on";
+	function = LED_FUNCTION_POWER;
+};
+
+&i2c0 {
+	vdd_cpu: regulator@40 {
+		compatible = "fcs,fan53555";
+		reg = <0x40>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1390000>;
+		regulator-name = "vdd_cpu";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_sys>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&leds {
+	amber_led: led-2 {
+		color = <LED_COLOR_ID_AMBER>;
+		function = LED_FUNCTION_CHARGING;
+		max-brightness = <255>;
+		pwms = <&pwm0 0 25000 0>;
+	};
+};
+
+&pwm0 {
+	pinctrl-0 = <&pwm0m1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&red_led {
+	default-state = "off";
+	function = LED_FUNCTION_STATUS;
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
index 0ac64f043b80..1f567a14ac84 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rgb30.dts
@@ -37,3 +37,21 @@
 		};
 	};
 };
+
+&i2c0 {
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1390000>;
+		regulator-name = "vdd_cpu";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_sys>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts
index ba32d0793dca..bc9933d9e262 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dts
@@ -36,3 +36,21 @@
 		};
 	};
 };
+
+&i2c0 {
+	vdd_cpu: regulator@1c {
+		compatible = "tcs,tcs4525";
+		reg = <0x1c>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <712500>;
+		regulator-max-microvolt = <1390000>;
+		regulator-name = "vdd_cpu";
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc_sys>;
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi
index 0fa8f06f94cd..3ab751a01cb2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-powkiddy-rk2023.dtsi
@@ -614,22 +614,6 @@
 			rockchip,sleep-filter-current-microamp = <100000>;
 		};
 	};
-
-	vdd_cpu: regulator@1c {
-		compatible = "tcs,tcs4525";
-		reg = <0x1c>;
-		fcs,suspend-voltage-selector = <1>;
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <712500>;
-		regulator-max-microvolt = <1390000>;
-		regulator-name = "vdd_cpu";
-		regulator-ramp-delay = <2300>;
-		vin-supply = <&vcc_sys>;
-		regulator-state-mem {
-			regulator-off-in-suspend;
-		};
-	};
 };
 
 &i2c5 {
@@ -805,7 +789,7 @@
 	uart-has-rtscts;
 	status = "okay";
 
-	bluetooth {
+	bluetooth: bluetooth {
 		compatible = "realtek,rtl8821cs-bt", "realtek,rtl8723bs-bt";
 		device-wake-gpios = <&gpio4 4 GPIO_ACTIVE_HIGH>;
 		enable-gpios = <&gpio4 3 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
index f9127ddfbb7d..7b5f3904ef61 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
@@ -13,7 +13,7 @@
 
 / {
 	model = "Bananapi-R2 Pro (RK3568) DDR4 Board";
-	compatible = "rockchip,rk3568-bpi-r2pro", "rockchip,rk3568";
+	compatible = "sinovoip,rk3568-bpi-r2pro", "rockchip,rk3568";
 
 	aliases {
 		ethernet0 = &gmac0;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
new file mode 100644
index 000000000000..6a998166003c
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2021 Rockchip Electronics Co., Ltd.
+ * Copyright (c) 2024 Uwe Kleine-König
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include "rk3568.dtsi"
+
+/ {
+	model = "Qnap TS-433-4G NAS System 4-Bay";
+	compatible = "qnap,ts433", "rockchip,rk3568";
+};
+
+&gmac0 {
+	assigned-clocks = <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0>;
+	assigned-clock-parents = <&cru SCLK_GMAC0_RGMII_SPEED>, <&cru CLK_MAC0_2TOP>;
+	assigned-clock-rates = <0>, <125000000>;
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy0>;
+	phy-mode = "rgmii";
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_tx_bus2
+		     &gmac0_rx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus>;
+	rx_delay = <0x2f>;
+	tx_delay = <0x3c>;
+	status = "okay";
+};
+
+&i2c0 {
+	pmic@20 {
+		compatible = "rockchip,rk809";
+		reg = <0x20>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
+	};
+};
+
+&i2c1 {
+	status = "okay";
+
+	rtc@51 {
+		compatible = "microcrystal,rv8263";
+		reg = <0x51>;
+		wakeup-source;
+	};
+};
+
+&mdio0 {
+	rgmii_phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x0>;
+	};
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+&pcie3x1 {
+	/* The downstream dts has: rockchip,bifurcation, XXX: find out what this is about */
+	reset-gpios = <&gpio0 RK_PC7 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	max-frequency = <200000000>;
+	non-removable;
+	status = "okay";
+};
+
+/*
+ * Pins available on CN3 connector at TTL voltage level (3V3).
+ * ,_  _.
+ * |1234|  1=TX 2=VCC
+ * `----'  3=RX 4=GND
+ */
+&uart2 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
index c19c0f1b3778..92f96ec01385 100644
--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
@@ -597,6 +597,7 @@
 		compatible = "rockchip,rk3568-vpu";
 		reg = <0x0 0xfdea0000 0x0 0x800>;
 		interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "vdpu";
 		clocks = <&cru ACLK_VPU>, <&cru HCLK_VPU>;
 		clock-names = "aclk", "hclk";
 		iommus = <&vdpu_mmu>;
@@ -1123,7 +1124,7 @@
 		dmas = <&dmac1 4>, <&dmac1 5>;
 		dma-names = "tx", "rx";
 		resets = <&cru SRST_M_I2S2_2CH>;
-		reset-names = "m";
+		reset-names = "tx-m";
 		rockchip,grf = <&grf>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2s2m0_sclktx
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
index d4c70835e0fe..a4946cdc3bb3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-evb.dts
@@ -72,7 +72,7 @@
 		vin-supply = <&vcc3v3_sys>;
 	};
 
-	vcc5v0_usb30_host: vcc5v0-usb30-host-regulator {
+	vcc5v0_usb_host1: vcc5v0_usb_host2: vcc5v0-usb-host-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "vcc5v0_host";
 		regulator-boot-on;
@@ -114,6 +114,7 @@
 	status = "okay";
 };
 
+/* Standard pcie */
 &pcie3x2 {
 	reset-gpios = <&gpio3 RK_PB0 GPIO_ACTIVE_HIGH>;
 	vpcie3v3-supply = <&vcc3v3_sys>;
@@ -122,6 +123,7 @@
 
 /* M.2 M-Key ssd */
 &pcie3x4 {
+	num-lanes = <2>;
 	reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>;
 	vpcie3v3-supply = <&vcc3v3_sys>;
 	status = "okay";
@@ -188,12 +190,12 @@
 };
 
 &u2phy2_host {
-	phy-supply = <&vcc5v0_usb30_host>;
+	phy-supply = <&vcc5v0_usb_host1>;
 	status = "okay";
 };
 
 &u2phy3_host {
-	phy-supply = <&vcc5v0_usb30_host>;
+	phy-supply = <&vcc5v0_usb_host2>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
index 0b02f4d6e003..cce1c8e83587 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
@@ -16,8 +16,8 @@
 
 	aliases {
 		mmc0 = &sdhci;
-		mmc1 = &sdio;
-		mmc2 = &sdmmc;
+		mmc1 = &sdmmc;
+		mmc2 = &sdio;
 		serial2 = &uart2;
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi
new file mode 100644
index 000000000000..c0d4a15323e2
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-common.dtsi
@@ -0,0 +1,466 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Edgeble AI Technologies Pvt. Ltd.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+
+/ {
+	aliases {
+		mmc0 = &sdhci;
+	};
+
+	gpio-leds {
+		compatible = "gpio-leds";
+
+		led_user: led-0 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_HEARTBEAT;
+			gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+			pinctrl-names = "default";
+			pinctrl-0 = <&led_user_en>;
+		};
+	};
+
+	vcc12v_dcin: vcc12v-dcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc12v_dcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&pinctrl {
+	leds {
+		led_user_en: led_user_en {
+			rockchip,pins = <0 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&sdhci {
+	bus-width = <8>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	status = "okay";
+};
+
+&spi2 {
+	status = "okay";
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		spi-max-frequency = <1000000>;
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PA7 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-name = "vdd_gpu_s0";
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-name = "vdd_log_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-name = "vdd_vdenc_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-name = "vdd_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-name = "vdd2_ddr_s3";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-name = "vdd_2v0_pldo_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-name = "vcc_3v3_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-name = "vddq_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-name = "vcc_1v8_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-name = "avcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-name = "vcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-name = "avdd_1v2_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_3v3_s0: pldo-reg4 {
+				regulator-name = "vcc_3v3_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-name = "vccio_sd_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-name = "pldo6_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-name = "vdd_0v75_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_ddr_pll_s0: nldo-reg2 {
+				regulator-name = "vdd_ddr_pll_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-name = "avdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v85_s0: nldo-reg4 {
+				regulator-name = "vdd_0v85_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-name = "vdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
index be6a4f4f90f6..46d5e21d4d27 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dts
@@ -6,18 +6,10 @@
 /dts-v1/;
 #include "rk3588.dtsi"
 #include "rk3588-edgeble-neu6a.dtsi"
+#include "rk3588-edgeble-neu6a-io.dtsi"
 
 / {
 	model = "Edgeble Neu6A IO Board";
 	compatible = "edgeble,neural-compute-module-6a-io",
 		     "edgeble,neural-compute-module-6a", "rockchip,rk3588";
-
-	chosen {
-		stdout-path = "serial2:1500000n8";
-	};
-};
-
-&uart2 {
-	pinctrl-0 = <&uart2m0_xfer>;
-	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi
new file mode 100644
index 000000000000..963e880ccc12
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-io.dtsi
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Edgeble AI Technologies Pvt. Ltd.
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	vcc3v3_pcie2x1l0: vcc3v3-pcie2x1l0-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_pcie2x1l0";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <5000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc3v3_pcie3x2: vcc3v3-pcie3x2-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio2 RK_PC4 GPIO_ACTIVE_HIGH>; /* PCIE_4G_PWEN */
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie3x2_vcc3v3_en>;
+		regulator-name = "vcc3v3_pcie3x2";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <5000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc3v3_pcie3x4: vcc3v3-pcie3x4-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio2 RK_PC5 GPIO_ACTIVE_HIGH>; /* PCIE30x4_PWREN_H */
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie3x4_vcc3v3_en>;
+		regulator-name = "vcc3v3_pcie3x4";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <5000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_host: vcc5v0-host-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio3 RK_PC7 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5v0_host_en>;
+		regulator-name = "vcc5v0_host";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-boot-on;
+		regulator-always-on;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&combphy1_ps {
+	status = "okay";
+};
+
+&i2c6 {
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		pinctrl-names = "default";
+		pinctrl-0 = <&hym8563_int>;
+		wakeup-source;
+	};
+};
+
+/* ETH */
+&pcie2x1l0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie2_0_rst>;
+	reset-gpios = <&gpio4 RK_PA5 GPIO_ACTIVE_HIGH>; /* PCIE20_1_PERST_L */
+	vpcie3v3-supply = <&vcc3v3_pcie2x1l0>;
+	status = "okay";
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+/* B-Key and E-Key */
+&pcie3x2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie3x2_rst>;
+	reset-gpios = <&gpio4 RK_PB6 GPIO_ACTIVE_HIGH>; /* PCIE30X4_PERSTn_M1_L */
+	vpcie3v3-supply = <&vcc3v3_pcie3x2>;
+	status = "okay";
+};
+
+/* M-Key */
+&pcie3x4 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie3x4_rst>;
+	reset-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; /* PCIE30X2_PERSTn_M1_L */
+	vpcie3v3-supply = <&vcc3v3_pcie3x4>;
+	status = "okay";
+};
+
+&pinctrl {
+	pcie2 {
+		pcie2_0_rst: pcie2-0-rst {
+			rockchip,pins = <4 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	pcie3 {
+		pcie3x2_rst: pcie3x2-rst {
+			rockchip,pins = <4 RK_PB6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie3x2_vcc3v3_en: pcie3x2-vcc3v3-en {
+			rockchip,pins = <2 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie3x4_rst: pcie3x4-rst {
+			rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie3x4_vcc3v3_en: pcie3x4-vcc3v3-en {
+			rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hym8563 {
+		hym8563_int: hym8563-int {
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	usb {
+		vcc5v0_host_en: vcc5v0-host-en {
+			rockchip,pins = <3 RK_PC7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+/* FAN */
+&pwm2 {
+	pinctrl-0 = <&pwm2m1_pins>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&sata0 {
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-mmc-highspeed;
+	cap-sd-highspeed;
+	disable-wp;
+	no-sdio;
+	no-mmc;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
+
+/* RS232 */
+&uart6 {
+	pinctrl-0 = <&uart6m0_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+/* RS485 */
+&uart7 {
+	pinctrl-0 = <&uart7m2_xfer>;
+	pinctrl-names = "default";
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	/* connected to USB hub, which is powered by vcc5v0_sys */
+	phy-supply = <&vcc5v0_sys>;
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy3_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-wifi.dtso b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-wifi.dtso
new file mode 100644
index 000000000000..e9a3855e8752
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a-wifi.dtso
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2022 Edgeble AI Technologies Pvt. Ltd.
+ *
+ * DT-overlay for Edgeble On-SoM WiFi6/BT M.2 1216 modules,
+ * - AW-XM548NF
+ * - Intel 8260D2W
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+
+&{/} {
+	vcc3v3_pcie2x1l1: vcc3v3-pcie2x1l1-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; /* WIFI_3V3_EN */
+		pinctrl-names = "default";
+		pinctrl-0 = <&pcie2_1_vcc3v3_en>;
+		regulator-name = "vcc3v3_pcie2x1l1";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <50000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+/* WiFi6 */
+&pcie2x1l1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie2_1_rst>;
+	reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; /* PCIE20_2_WIFI_PERSTn */
+	vpcie3v3-supply = <&vcc3v3_pcie2x1l1>;
+	status = "okay";
+};
+
+&pinctrl {
+	pcie2 {
+		pcie2_1_rst: pcie2-1-rst {
+			rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		pcie2_1_vcc3v3_en: pcie2-1-vcc-en {
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a.dtsi
index 727580aaa105..4c76a00b41eb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6a.dtsi
@@ -3,29 +3,8 @@
  * Copyright (c) 2022 Edgeble AI Technologies Pvt. Ltd.
  */
 
+#include "rk3588-edgeble-neu6a-common.dtsi"
+
 / {
 	compatible = "edgeble,neural-compute-module-6a", "rockchip,rk3588";
-
-	aliases {
-		mmc0 = &sdhci;
-	};
-
-	vcc12v_dcin: vcc12v-dcin-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc12v_dcin";
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <12000000>;
-		regulator-max-microvolt = <12000000>;
-	};
-};
-
-&sdhci {
-	bus-width = <8>;
-	no-sdio;
-	no-sd;
-	non-removable;
-	mmc-hs400-1_8v;
-	mmc-hs400-enhanced-strobe;
-	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
index 070baeb63431..0d6f1be69ac8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b-io.dts
@@ -6,84 +6,10 @@
 /dts-v1/;
 #include "rk3588j.dtsi"
 #include "rk3588-edgeble-neu6b.dtsi"
+#include "rk3588-edgeble-neu6a-io.dtsi"
 
 / {
 	model = "Edgeble Neu6B IO Board";
 	compatible = "edgeble,neural-compute-module-6a-io",
 		     "edgeble,neural-compute-module-6b", "rockchip,rk3588";
-
-	chosen {
-		stdout-path = "serial2:1500000n8";
-	};
-};
-
-&combphy0_ps {
-	status = "okay";
-};
-
-&i2c6 {
-	status = "okay";
-
-	hym8563: rtc@51 {
-		compatible = "haoyu,hym8563";
-		reg = <0x51>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
-		#clock-cells = <0>;
-		clock-output-names = "hym8563";
-		pinctrl-names = "default";
-		pinctrl-0 = <&hym8563_int>;
-		wakeup-source;
-	};
-};
-
-&pinctrl {
-	hym8563 {
-		hym8563_int: hym8563-int {
-			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
-		};
-	};
-};
-
-/* FAN */
-&pwm2 {
-	pinctrl-0 = <&pwm2m1_pins>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-&sata0 {
-	status = "okay";
-};
-
-&sdmmc {
-	bus-width = <4>;
-	cap-mmc-highspeed;
-	cap-sd-highspeed;
-	disable-wp;
-	no-sdio;
-	no-mmc;
-	sd-uhs-sdr104;
-	vmmc-supply = <&vcc_3v3_s3>;
-	vqmmc-supply = <&vccio_sd_s0>;
-	status = "okay";
-};
-
-&uart2 {
-	pinctrl-0 = <&uart2m0_xfer>;
-	status = "okay";
-};
-
-/* RS232 */
-&uart6 {
-	pinctrl-0 = <&uart6m0_xfer>;
-	pinctrl-names = "default";
-	status = "okay";
-};
-
-/* RS485 */
-&uart7 {
-	pinctrl-0 = <&uart7m2_xfer>;
-	pinctrl-names = "default";
-	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b.dtsi
index 017559bba37f..c4634bc09fb4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-edgeble-neu6b.dtsi
@@ -3,387 +3,8 @@
  * Copyright (c) 2023 Edgeble AI Technologies Pvt. Ltd.
  */
 
+#include "rk3588-edgeble-neu6a-common.dtsi"
+
 / {
 	compatible = "edgeble,neural-compute-module-6b", "rockchip,rk3588";
-
-	aliases {
-		mmc0 = &sdhci;
-	};
-
-	vcc12v_dcin: vcc12v-dcin-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc12v_dcin";
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <12000000>;
-		regulator-max-microvolt = <12000000>;
-	};
-
-	vcc5v0_sys: vcc5v0-sys-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc5v0_sys";
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <5000000>;
-		regulator-max-microvolt = <5000000>;
-		vin-supply = <&vcc12v_dcin>;
-	};
-
-	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
-		compatible = "regulator-fixed";
-		regulator-name = "vcc_1v1_nldo_s3";
-		regulator-always-on;
-		regulator-boot-on;
-		regulator-min-microvolt = <1100000>;
-		regulator-max-microvolt = <1100000>;
-		vin-supply = <&vcc5v0_sys>;
-	};
-};
-
-&cpu_l0 {
-	cpu-supply = <&vdd_cpu_lit_s0>;
-};
-
-&cpu_l1 {
-	cpu-supply = <&vdd_cpu_lit_s0>;
-};
-
-&cpu_l2 {
-	cpu-supply = <&vdd_cpu_lit_s0>;
-};
-
-&cpu_l3 {
-	cpu-supply = <&vdd_cpu_lit_s0>;
-};
-
-&sdhci {
-	bus-width = <8>;
-	no-sdio;
-	no-sd;
-	non-removable;
-	mmc-hs400-1_8v;
-	mmc-hs400-enhanced-strobe;
-	status = "okay";
-};
-
-&spi2 {
-	status = "okay";
-	assigned-clocks = <&cru CLK_SPI2>;
-	assigned-clock-rates = <200000000>;
-	num-cs = <1>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
-
-	pmic@0 {
-		compatible = "rockchip,rk806";
-		spi-max-frequency = <1000000>;
-		reg = <0x0>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <RK_PA7 IRQ_TYPE_LEVEL_LOW>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
-			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
-
-		vcc1-supply = <&vcc5v0_sys>;
-		vcc2-supply = <&vcc5v0_sys>;
-		vcc3-supply = <&vcc5v0_sys>;
-		vcc4-supply = <&vcc5v0_sys>;
-		vcc5-supply = <&vcc5v0_sys>;
-		vcc6-supply = <&vcc5v0_sys>;
-		vcc7-supply = <&vcc5v0_sys>;
-		vcc8-supply = <&vcc5v0_sys>;
-		vcc9-supply = <&vcc5v0_sys>;
-		vcc10-supply = <&vcc5v0_sys>;
-		vcc11-supply = <&vcc_2v0_pldo_s3>;
-		vcc12-supply = <&vcc5v0_sys>;
-		vcc13-supply = <&vcc_1v1_nldo_s3>;
-		vcc14-supply = <&vcc_1v1_nldo_s3>;
-		vcca-supply = <&vcc5v0_sys>;
-
-		gpio-controller;
-		#gpio-cells = <2>;
-
-		rk806_dvs1_null: dvs1-null-pins {
-			pins = "gpio_pwrctrl2";
-			function = "pin_fun0";
-		};
-
-		rk806_dvs2_null: dvs2-null-pins {
-			pins = "gpio_pwrctrl2";
-			function = "pin_fun0";
-		};
-
-		rk806_dvs3_null: dvs3-null-pins {
-			pins = "gpio_pwrctrl3";
-			function = "pin_fun0";
-		};
-
-		regulators {
-			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
-				regulator-name = "vdd_gpu_s0";
-				regulator-boot-on;
-				regulator-min-microvolt = <550000>;
-				regulator-max-microvolt = <950000>;
-				regulator-ramp-delay = <12500>;
-				regulator-enable-ramp-delay = <400>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
-				regulator-name = "vdd_cpu_lit_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <550000>;
-				regulator-max-microvolt = <950000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vdd_log_s0: dcdc-reg3 {
-				regulator-name = "vdd_log_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <675000>;
-				regulator-max-microvolt = <750000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-					regulator-suspend-microvolt = <750000>;
-				};
-			};
-
-			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
-				regulator-name = "vdd_vdenc_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <550000>;
-				regulator-max-microvolt = <950000>;
-				regulator-init-microvolt = <750000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vdd_ddr_s0: dcdc-reg5 {
-				regulator-name = "vdd_ddr_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <675000>;
-				regulator-max-microvolt = <900000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-					regulator-suspend-microvolt = <850000>;
-				};
-			};
-
-			vdd2_ddr_s3: dcdc-reg6 {
-				regulator-name = "vdd2_ddr_s3";
-				regulator-always-on;
-				regulator-boot-on;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-				};
-			};
-
-			vcc_2v0_pldo_s3: dcdc-reg7 {
-				regulator-name = "vdd_2v0_pldo_s3";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <2000000>;
-				regulator-max-microvolt = <2000000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <2000000>;
-				};
-			};
-
-			vcc_3v3_s3: dcdc-reg8 {
-				regulator-name = "vcc_3v3_s3";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <3300000>;
-				};
-			};
-
-			vddq_ddr_s0: dcdc-reg9 {
-				regulator-name = "vddq_ddr_s0";
-				regulator-always-on;
-				regulator-boot-on;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vcc_1v8_s3: dcdc-reg10 {
-				regulator-name = "vcc_1v8_s3";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <1800000>;
-				};
-			};
-
-			avcc_1v8_s0: pldo-reg1 {
-				regulator-name = "avcc_1v8_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vcc_1v8_s0: pldo-reg2 {
-				regulator-name = "vcc_1v8_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-					regulator-suspend-microvolt = <1800000>;
-				};
-			};
-
-			avdd_1v2_s0: pldo-reg3 {
-				regulator-name = "avdd_1v2_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <1200000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vcc_3v3_s0: pldo-reg4 {
-				regulator-name = "vcc_3v3_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vccio_sd_s0: pldo-reg5 {
-				regulator-name = "vccio_sd_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3300000>;
-				regulator-ramp-delay = <12500>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			pldo6_s3: pldo-reg6 {
-				regulator-name = "pldo6_s3";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <1800000>;
-				};
-			};
-
-			vdd_0v75_s3: nldo-reg1 {
-				regulator-name = "vdd_0v75_s3";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <750000>;
-				regulator-max-microvolt = <750000>;
-
-				regulator-state-mem {
-					regulator-on-in-suspend;
-					regulator-suspend-microvolt = <750000>;
-				};
-			};
-
-			vdd_ddr_pll_s0: nldo-reg2 {
-				regulator-name = "vdd_ddr_pll_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <850000>;
-				regulator-max-microvolt = <850000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-					regulator-suspend-microvolt = <850000>;
-				};
-			};
-
-			avdd_0v75_s0: nldo-reg3 {
-				regulator-name = "avdd_0v75_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <750000>;
-				regulator-max-microvolt = <750000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vdd_0v85_s0: nldo-reg4 {
-				regulator-name = "vdd_0v85_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <850000>;
-				regulator-max-microvolt = <850000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-
-			vdd_0v75_s0: nldo-reg5 {
-				regulator-name = "vdd_0v75_s0";
-				regulator-always-on;
-				regulator-boot-on;
-				regulator-min-microvolt = <750000>;
-				regulator-max-microvolt = <750000>;
-
-				regulator-state-mem {
-					regulator-off-in-suspend;
-				};
-			};
-		};
-	};
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
index ac7c677b0fb9..de30c2632b8e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-evb1-v10.dts
@@ -448,6 +448,7 @@
 			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
 		pinctrl-names = "default";
 		spi-max-frequency = <1000000>;
+		system-power-controller;
 
 		vcc1-supply = <&vcc5v0_sys>;
 		vcc2-supply = <&vcc5v0_sys>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
index 4ce70fb75a30..39d65002add1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
@@ -62,7 +62,6 @@
 		compatible = "gpio-leds";
 		pinctrl-names = "default";
 		pinctrl-0 = <&led1_pin>;
-		status = "okay";
 
 		/* LED1 on PCB */
 		led-1 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
index d7722772ecd8..ad8e36a339dc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts
@@ -159,6 +159,29 @@
 		regulator-max-microvolt = <3300000>;
 		vin-supply = <&vcc5v0_sys>;
 	};
+
+	vcc3v3_sd_s0: vcc3v3-sd-s0-regulator {
+		compatible = "regulator-fixed";
+		enable-active-low;
+		gpio = <&gpio4 RK_PA5 GPIO_ACTIVE_LOW>;
+		regulator-boot-on;
+		regulator-max-microvolt = <3300000>;
+		regulator-min-microvolt = <3300000>;
+		regulator-name = "vcc3v3_sd_s0";
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vdd_4g_3v3: vdd-4g-3v3-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PC6 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pin_4g_lte_pwren>;
+		regulator-name = "vdd_4g_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
 };
 
 &combphy0_ps {
@@ -189,19 +212,19 @@
 	cpu-supply = <&vdd_cpu_lit_s0>;
 };
 
-&cpu_b0{
+&cpu_b0 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
 
-&cpu_b1{
+&cpu_b1 {
 	cpu-supply = <&vdd_cpu_big0_s0>;
 };
 
-&cpu_b2{
+&cpu_b2 {
 	cpu-supply = <&vdd_cpu_big1_s0>;
 };
 
-&cpu_b3{
+&cpu_b3 {
 	cpu-supply = <&vdd_cpu_big1_s0>;
 };
 
@@ -504,6 +527,10 @@
 	};
 
 	usb {
+		pin_4g_lte_pwren: 4g-lte-pwren {
+			rockchip,pins = <4 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
 		typec5v_pwren: typec5v-pwren {
 			rockchip,pins = <1 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
@@ -539,11 +566,12 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	no-mmc;
 	no-sdio;
 	sd-uhs-sdr104;
-	vmmc-supply = <&vcc_3v3_s3>;
+	vmmc-supply = <&vcc3v3_sd_s0>;
 	vqmmc-supply = <&vccio_sd_s0>;
 	status = "okay";
 };
@@ -884,6 +912,7 @@
 };
 
 &u2phy2_host {
+	phy-supply = <&vdd_4g_3v3>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index 3e660ff6cd5f..1b606ea5b6cf 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -444,7 +444,6 @@
 &sdmmc {
 	bus-width = <4>;
 	cap-sd-highspeed;
-	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	max-frequency = <150000000>;
 	no-sdio;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
index 87a0abf95f7d..67414d72e2b6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
@@ -429,7 +429,6 @@
 &sdmmc {
 	bus-width = <4>;
 	cap-sd-highspeed;
-	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	max-frequency = <150000000>;
 	no-sdio;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
index a0e303c3a1dc..1fe8b2a0ed75 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
@@ -58,6 +58,13 @@
 		#cooling-cells = <2>;
 	};
 
+	rfkill {
+		compatible = "rfkill-gpio";
+		label = "rfkill-pcie-wlan";
+		radio-type = "wlan";
+		shutdown-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>;
+	};
+
 	vcc3v3_pcie2x1l0: vcc3v3-pcie2x1l0-regulator {
 		compatible = "regulator-fixed";
 		enable-active-high;
@@ -371,7 +378,6 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
-	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	sd-uhs-sdr104;
 	vmmc-supply = <&vcc_3v3_s3>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts
new file mode 100644
index 000000000000..d672198c6b64
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger-haikou.dts
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Theobroma Systems Design und Consulting GmbH
+ */
+
+/dts-v1/;
+#include <dt-bindings/input/input.h>
+#include "rk3588-tiger.dtsi"
+
+/ {
+	model = "Theobroma Systems RK3588-Q7 SoM on Haikou devkit";
+	compatible = "tsd,rk3588-tiger-haikou", "tsd,rk3588-tiger", "rockchip,rk3588";
+
+	aliases {
+		ethernet0 = &gmac0;
+		mmc1 = &sdmmc;
+	};
+
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
+	dc_12v: dc-12v-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "dc_12v";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&haikou_keys_pin>;
+
+		button-batlow-n {
+			label = "BATLOW#";
+			linux,code = <KEY_BATTERY>;
+			gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_LOW>;
+		};
+
+		button-slp-btn-n {
+			label = "SLP_BTN#";
+			linux,code = <KEY_SLEEP>;
+			gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>;
+		};
+
+		button-wake-n {
+			label = "WAKE#";
+			linux,code = <KEY_WAKEUP>;
+			gpios = <&gpio3 RK_PC6 GPIO_ACTIVE_LOW>;
+			wakeup-source;
+		};
+
+		switch-lid-btn-n {
+			label = "LID_BTN#";
+			linux,code = <SW_LID>;
+			linux,input-type = <EV_SW>;
+			gpios = <&gpio3 RK_PD5 GPIO_ACTIVE_LOW>;
+		};
+	};
+
+	i2s3-sound {
+		compatible = "simple-audio-card";
+		simple-audio-card,format = "i2s";
+		simple-audio-card,name = "Haikou,I2S-codec";
+		simple-audio-card,mclk-fs = <512>;
+		simple-audio-card,frame-master = <&sgtl5000_codec>;
+		simple-audio-card,bitclock-master = <&sgtl5000_codec>;
+
+		sgtl5000_codec: simple-audio-card,codec {
+			sound-dai = <&sgtl5000>;
+		};
+
+		simple-audio-card,cpu {
+			sound-dai = <&i2s3_2ch>;
+		};
+	};
+
+	sgtl5000_clk: sgtl5000-oscillator  {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24576000>;
+	};
+
+	vcc3v3_baseboard: vcc3v3-baseboard-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_baseboard";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&dc_12v>;
+	};
+
+	vcc3v3_low_noise: vcc3v3-low-noise-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc3v3_low_noise";
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc5v0_usb>;
+	};
+
+	vcc5v0_baseboard: vcc5v0-baseboard-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_baseboard";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_12v>;
+	};
+
+	vcc5v0_usb: vcc5v0-usb-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usb";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&dc_12v>;
+	};
+
+	vddd_audio_1v6: vddd-audio-1v6-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vddd_audio_1v6";
+		regulator-boot-on;
+		regulator-min-microvolt = <1600000>;
+		regulator-max-microvolt = <1600000>;
+		vin-supply = <&vcc5v0_usb>;
+	};
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+&gmac0 {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+
+	eeprom@50 {
+		reg = <0x50>;
+		compatible = "atmel,24c01";
+		pagesize = <8>;
+		size = <128>;
+		vcc-supply = <&vcc3v3_baseboard>;
+	};
+};
+
+&i2c5 {
+	clock-frequency = <400000>;
+	status = "okay";
+
+	sgtl5000: codec@a {
+		compatible = "fsl,sgtl5000";
+		reg = <0x0a>;
+		clocks = <&sgtl5000_clk>;
+		#sound-dai-cells = <0>;
+		VDDA-supply = <&vcc3v3_low_noise>;
+		VDDIO-supply = <&vcc3v3_baseboard>;
+		VDDD-supply = <&vddd_audio_1v6>;
+	};
+};
+
+&i2c8 {
+	status = "okay";
+};
+
+&i2s3_2ch {
+	status = "okay";
+};
+
+&pcie30phy {
+	status = "okay";
+};
+
+&pcie3x4 {
+	vpcie3v3-supply = <&vcc3v3_baseboard>;
+	status = "okay";
+};
+
+&pinctrl {
+	haikou {
+		haikou_keys_pin: haikou-keys-pin {
+			rockchip,pins =
+				/* BATLOW# */
+				<3 RK_PB5 RK_FUNC_GPIO &pcfg_pull_up>,
+				/* SLP_BTN# */
+				<4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_up>,
+				/* WAKE# */
+				<3 RK_PC6 RK_FUNC_GPIO &pcfg_pull_up>,
+				/* LID_BTN */
+				<3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+};
+
+&sdmmc {
+	/* while the same pin, sdmmc_det does not detect card changes */
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
+	disable-wp;
+	pinctrl-0 = <&sdmmc_bus4 &sdmmc_cmd &sdmmc_clk>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc3v3_baseboard>;
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy3_host {
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m2_xfer>;
+	status = "okay";
+};
+
+&uart5 {
+	rts-gpios = <&gpio3 RK_PB3 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+/* host0 on Q7_USB_P2, lower usb3 port */
+&usb_host0_ehci {
+	status = "okay";
+};
+
+/* host0 on Q7_USB_P2, lower usb3 port */
+&usb_host0_ohci {
+	status = "okay";
+};
+
+/* host1 on Q7_USB_P3, usb2 port */
+&usb_host1_ehci {
+	status = "okay";
+};
+
+/* host1 on Q7_USB_P3, usb2 port */
+&usb_host1_ohci {
+	status = "okay";
+};
+
+/* host2 on Q7_USB_P2, lower usb3 port */
+&usb_host2_xhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
new file mode 100644
index 000000000000..1eb2543a5fde
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2023 Theobroma Systems Design und Consulting GmbH
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3588.dtsi"
+
+/ {
+	compatible = "tsd,rk3588-tiger", "rockchip,rk3588";
+
+	aliases {
+		mmc0 = &sdhci;
+		rtc0 = &rtc_twi;
+	};
+
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		pinctrl-0 = <&emmc_reset>;
+		pinctrl-names = "default";
+		reset-gpios = <&gpio2 RK_PA3 GPIO_ACTIVE_HIGH>;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&module_led_pin>;
+
+		/* Named LED1 on the board */
+		led-1 {
+			gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_HIGH>;
+			function = LED_FUNCTION_HEARTBEAT;
+			linux,default-trigger = "heartbeat";
+			color = <LED_COLOR_ID_AMBER>;
+		};
+	};
+
+	/*
+	 * 100MHz reference clock for PCIe peripherals from PI6C557-05BLE
+	 * clock generator.
+	 * The clock output is gated via the OE pin on the clock generator.
+	 * This is modeled as a fixed-clock plus a gpio-gate-clock.
+	 */
+	pcie_refclk_gen: pcie-refclk-gen-clock {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <1000000000>;
+	};
+
+	pcie_refclk: pcie-refclk-clock {
+		compatible = "gpio-gate-clock";
+		clocks = <&pcie_refclk_gen>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>; /* PCIE30X4_CLKREQN_M1_L */
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc_1v2_s3: vcc-1v2-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v2_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_baseboard>;
+	};
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii";
+	phy-supply = <&vcc_1v2_s3>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_rx_bus2
+		     &gmac0_tx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus
+		     &eth0_pins
+		     &eth_reset>;
+	tx_delay = <0x10>;
+	rx_delay = <0x10>;
+	snps,reset-gpio = <&gpio4 RK_PC3 GPIO_ACTIVE_LOW>;
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 100000>;
+};
+
+&i2c1 {
+	pinctrl-0 = <&i2c1m0_xfer>;
+};
+
+&i2c1m0_xfer {
+	rockchip,pins =
+		/* i2c1_scl_m0 */
+		<0 RK_PB5 9 &pcfg_pull_none_drv_level_0>,
+		/* i2c1_sda_m0 */
+		<0 RK_PB6 9 &pcfg_pull_none_drv_level_0>;
+};
+
+&i2c2 {
+	pinctrl-0 = <&i2c2m3_xfer>;
+	status = "okay";
+};
+
+&i2c2m3_xfer {
+	rockchip,pins =
+		/* i2c2_scl_m3 */
+		<1 RK_PC5 9 &pcfg_pull_none_drv_level_0>,
+		/* i2c2_sda_m3 */
+		<1 RK_PC4 9 &pcfg_pull_none_drv_level_0>;
+};
+
+&i2c3 {
+	pinctrl-0 = <&i2c3m0_xfer>;
+};
+
+&i2c4 {
+	pinctrl-0 = <&i2c4m4_xfer>;
+	status = "okay";
+
+	vdd_npu_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_npu_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c5 {
+	pinctrl-0 = <&i2c5m1_xfer>;
+};
+
+&i2c5m1_xfer {
+	rockchip,pins =
+		/* i2c5_scl_m1 */
+		<4 RK_PB6 9 &pcfg_pull_none_drv_level_0>,
+		/* i2c5_sda_m1 */
+		<4 RK_PB7 9 &pcfg_pull_none_drv_level_0>;
+};
+
+&i2c6 {
+	/*
+	 * Mule-ATtiny can handle up to Fast mode Plus (1MHz) on I2C bus,
+	 * but SOC can handle only up to (400kHz).
+	 */
+	clock-frequency = <400000>;
+	status = "okay";
+
+	fan@18 {
+		compatible = "ti,amc6821";
+		reg = <0x18>;
+	};
+
+	rtc_twi: rtc@6f {
+		compatible = "isil,isl1208";
+		reg = <0x6f>;
+	};
+};
+
+&i2c6m0_xfer {
+	rockchip,pins =
+		/* i2c6_scl_m0 */
+		<0 RK_PD0 9 &pcfg_pull_none_drv_level_0>,
+		/* i2c6_sda_m0 */
+		<0 RK_PC7 9 &pcfg_pull_none_drv_level_0>;
+};
+
+&i2c7 {
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c7m0_xfer {
+	rockchip,pins =
+		/* i2c7_scl_m0 */
+		<1 RK_PD0 9 &pcfg_pull_none_drv_level_0>,
+		/* i2c7_sda_m0 */
+		<1 RK_PD1 9 &pcfg_pull_none_drv_level_0>;
+};
+
+&i2c8 {
+	pinctrl-0 = <&i2c8m2_xfer>;
+};
+
+&mdio0 {
+	rgmii_phy: ethernet-phy@6 {
+		/* KSZ9031 or KSZ9131 */
+		compatible = "ethernet-phy-ieee802.3-c22";
+		reg = <0x6>;
+		clocks = <&cru REFCLKO25M_ETH0_OUT>;
+	};
+};
+
+&pcie3x4 {
+	/*
+	 * The board has a gpio-controlled "pcie_refclk" generator,
+	 * so add it to the list of clocks.
+	 */
+	clocks = <&cru ACLK_PCIE_4L_MSTR>, <&cru ACLK_PCIE_4L_SLV>,
+		 <&cru ACLK_PCIE_4L_DBI>, <&cru PCLK_PCIE_4L>,
+		 <&cru CLK_PCIE_AUX0>, <&cru CLK_PCIE4L_PIPE>,
+		 <&pcie_refclk>;
+	clock-names = "aclk_mst", "aclk_slv",
+		      "aclk_dbi", "pclk",
+		      "aux", "pipe",
+		      "ref";
+	reset-gpios = <&gpio3 RK_PB6 GPIO_ACTIVE_HIGH>;
+};
+
+&pinctrl {
+	emmc {
+		emmc_reset: emmc-reset {
+			rockchip,pins = <2 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	ethernet {
+		eth_reset: eth-reset {
+			rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	leds {
+		module_led_pin: module-led-pin {
+			rockchip,pins = <1 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	mmc-ddr-1_8v;
+	mmc-hs200-1_8v;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	mmc-pwrseq = <&emmc_pwrseq>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
+	supports-cqe;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vcc_1v8_s3>;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	max-frequency = <150000000>;
+	vqmmc-supply = <&vccio_sd_s0>;
+};
+
+&spi0 {
+	pinctrl-0 = <&spi0m1_cs0 &spi0m1_cs1 &spi0m3_pins>;
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		system-power-controller;
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: dcdc-reg1 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: dcdc-reg2 {
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-name = "vdd_log_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: dcdc-reg4 {
+				regulator-name = "vdd_vdenc_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-name = "vdd_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-name = "vdd2_ddr_s3";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-name = "vcc_2v0_pldo_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-name = "vcc_3v3_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-name = "vddq_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-name = "vcc_1v8_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vcca_1v8_s0: pldo-reg1 {
+				regulator-name = "vcca_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-name = "vcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdda_1v2_s0: pldo-reg3 {
+				regulator-name = "vdda_1v2_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcca_3v3_s0: pldo-reg4 {
+				regulator-name = "vcca_3v3_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-name = "vccio_sd_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-name = "pldo6_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-name = "vdd_0v75_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdda_ddr_pll_s0: nldo-reg2 {
+				regulator-name = "vdda_ddr_pll_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdda_0v75_s0: nldo-reg3 {
+				regulator-name = "vdda_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdda_0v85_s0: nldo-reg4 {
+				regulator-name = "vdda_0v85_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-name = "vdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+/* Mule-ATtiny UPDI */
+&uart4 {
+	pinctrl-0 = <&uart4m2_xfer>;
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
new file mode 100644
index 000000000000..9090c5c99f2a
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
@@ -0,0 +1,688 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2024 Rockchip Electronics Co., Ltd.
+ *
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include <dt-bindings/pinctrl/rockchip.h>
+#include "rk3588.dtsi"
+
+/ {
+	model = "Rockchip Toybrick TB-RK3588X Board";
+	compatible = "rockchip,rk3588-toybrick-x0", "rockchip,rk3588";
+
+	aliases {
+		mmc0 = &sdhci;
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 1>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		button-vol-up {
+			label = "Volume Up";
+			linux,code = <KEY_VOLUMEUP>;
+			press-threshold-microvolt = <17000>;
+		};
+
+		button-vol-down {
+			label = "Volume Down";
+			linux,code = <KEY_VOLUMEDOWN>;
+			press-threshold-microvolt = <417000>;
+		};
+
+		button-menu {
+			label = "Menu";
+			linux,code = <KEY_MENU>;
+			press-threshold-microvolt = <890000>;
+		};
+
+		button-escape {
+			label = "Escape";
+			linux,code = <KEY_ESC>;
+			press-threshold-microvolt = <1235000>;
+		};
+	};
+
+	backlight: backlight {
+		compatible = "pwm-backlight";
+		power-supply = <&vcc12v_dcin>;
+		pwms = <&pwm2 0 25000 0>;
+	};
+
+	pcie20_avdd0v85: pcie20-avdd0v85-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "pcie20_avdd0v85";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <850000>;
+		regulator-max-microvolt = <850000>;
+		vin-supply = <&vdd_0v85_s0>;
+	};
+
+	pcie20_avdd1v8: pcie20-avdd1v8-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "pcie20_avdd1v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&avcc_1v8_s0>;
+	};
+
+	pcie30_avdd0v75: pcie30-avdd0v75-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "pcie30_avdd0v75";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <750000>;
+		regulator-max-microvolt = <750000>;
+		vin-supply = <&avdd_0v75_s0>;
+	};
+
+	pcie30_avdd1v8: pcie30-avdd1v8-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "pcie30_avdd1v8";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		vin-supply = <&avcc_1v8_s0>;
+	};
+
+	vcc12v_dcin: vcc12v-dcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc12v_dcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <12000000>;
+		regulator-max-microvolt = <12000000>;
+	};
+
+	vcc5v0_host: vcc5v0-host-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpio = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5v0_host_en>;
+		regulator-name = "vcc5v0_host";
+		regulator-boot-on;
+		regulator-always-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usb>;
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usbdcin: vcc5v0-usbdcin-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usbdcin";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc12v_dcin>;
+	};
+
+	vcc5v0_usb: vcc5v0-usb-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usb";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usbdcin>;
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac0 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy>;
+	phy-mode = "rgmii-rxid";
+	pinctrl-0 = <&gmac0_miim
+		     &gmac0_tx_bus2
+		     &gmac0_rx_bus2
+		     &gmac0_rgmii_clk
+		     &gmac0_rgmii_bus>;
+	pinctrl-names = "default";
+	rx_delay = <0x00>;
+	tx_delay = <0x43>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PD4 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&hym8563_int>;
+		wakeup-source;
+	};
+};
+
+&mdio0 {
+	rgmii_phy: ethernet-phy@1 {
+		/* RTL8211F */
+		compatible = "ethernet-phy-id001c.c916";
+		reg = <0x1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtl8211f_rst>;
+		reset-assert-us = <20000>;
+		reset-deassert-us = <100000>;
+		reset-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pinctrl {
+	rtl8211f {
+		rtl8211f_rst: rtl8211f-rst {
+			rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+	};
+
+	hym8563 {
+		hym8563_int: hym8563-int {
+			rockchip,pins = <0 RK_PD4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	usb {
+		vcc5v0_host_en: vcc5v0-host-en {
+			rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&pwm2 {
+	status = "okay";
+};
+
+&saradc {
+	vref-supply = <&vcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	mmc-hs400-1_8v;
+	mmc-hs400-enhanced-strobe;
+	no-sdio;
+	no-sd;
+	non-removable;
+	status = "okay";
+};
+
+&spi2 {
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	num-cs = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	status = "okay";
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		reg = <0x0>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+		spi-max-frequency = <1000000>;
+		system-power-controller;
+
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-name = "vdd_gpu_s0";
+				regulator-boot-on;
+				regulator-enable-ramp-delay = <400>;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-name = "vdd_cpu_lit_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-name = "vdd_log_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-name = "vdd_vdenc_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-init-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-name = "vdd_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-name = "vdd2_ddr_s3";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-name = "vdd_2v0_pldo_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-name = "vcc_3v3_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-name = "vddq_ddr_s0";
+				regulator-always-on;
+				regulator-boot-on;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-name = "vcc_1v8_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-name = "avcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-name = "vcc_1v8_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-name = "avdd_1v2_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_3v3_s0: pldo-reg4 {
+				regulator-name = "vcc_3v3_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-name = "vccio_sd_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-name = "pldo6_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-name = "vdd_0v75_s3";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_ddr_pll_s0: nldo-reg2 {
+				regulator-name = "vdd_ddr_pll_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-name = "avdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <837500>;
+				regulator-max-microvolt = <837500>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v85_s0: nldo-reg4 {
+				regulator-name = "vdd_0v85_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-name = "vdd_0v75_s0";
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&u2phy3 {
+	status = "okay";
+};
+
+&u2phy3_host {
+	phy-supply = <&vcc5v0_host>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
+
+&usb_host1_ehci {
+	status = "okay";
+};
+
+&usb_host1_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
index ef4f058c20ff..e037bf9db75a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts
@@ -19,8 +19,8 @@
 
 	aliases {
 		mmc0 = &sdhci;
-		mmc1 = &sdio;
-		mmc2 = &sdmmc;
+		mmc1 = &sdmmc;
+		mmc2 = &sdio;
 	};
 
 	analog-sound {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
index dc677f29a9c7..ce8119cbb824 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
@@ -141,6 +141,10 @@
 	status = "okay";
 };
 
+&combphy2_psu {
+	status = "okay";
+};
+
 &cpu_l0 {
 	cpu-supply = <&vdd_cpu_lit_s0>;
 };
@@ -195,13 +199,13 @@
 
 &gpio1 {
 	gpio-line-names = /* GPIO1 A0-A7 */
-			  "HEADER_27_3v3", "HEADER_28_3v3", "", "",
+			  "HEADER_27_3v3", "", "", "",
 			  "HEADER_29_1v8", "", "HEADER_7_1v8", "",
 			  /* GPIO1 B0-B7 */
 			  "", "HEADER_31_1v8", "HEADER_33_1v8", "",
 			  "HEADER_11_1v8", "HEADER_13_1v8", "", "",
 			  /* GPIO1 C0-C7 */
-			  "", "", "", "",
+			  "", "HEADER_28_3v3", "", "",
 			  "", "", "", "",
 			  /* GPIO1 D0-D7 */
 			  "", "", "", "",
@@ -225,11 +229,11 @@
 
 &gpio4 {
 	gpio-line-names = /* GPIO4 A0-A7 */
-			  "", "", "HEADER_37_3v3", "HEADER_32_3v3",
-			  "HEADER_36_3v3", "", "HEADER_35_3v3", "HEADER_38_3v3",
+			  "", "", "HEADER_37_3v3", "HEADER_8_3v3",
+			  "HEADER_10_3v3", "", "HEADER_32_3v3", "HEADER_35_3v3",
 			  /* GPIO4 B0-B7 */
 			  "", "", "", "HEADER_40_3v3",
-			  "HEADER_8_3v3", "HEADER_10_3v3", "", "",
+			  "HEADER_38_3v3", "HEADER_36_3v3", "", "",
 			  /* GPIO4 C0-C7 */
 			  "", "", "", "",
 			  "", "", "", "",
@@ -842,3 +846,7 @@
 &usb_host1_ohci {
 	status = "okay";
 };
+
+&usb_host2_xhci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6c.dts b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6c.dts
new file mode 100644
index 000000000000..497bbb57071f
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6c.dts
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include "rk3588s-nanopi-r6s.dts"
+
+/ {
+	model = "FriendlyElec NanoPi R6C";
+	compatible = "friendlyarm,nanopi-r6c", "rockchip,rk3588s";
+};
+
+&lan2_led {
+	label = "user_led";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6s.dts b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6s.dts
new file mode 100644
index 000000000000..4fa644ae510c
--- /dev/null
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6s.dts
@@ -0,0 +1,764 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+/dts-v1/;
+
+#include <dt-bindings/pinctrl/rockchip.h>
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/input/input.h>
+#include "rk3588s.dtsi"
+
+/ {
+	model = "FriendlyElec NanoPi R6S";
+	compatible = "friendlyarm,nanopi-r6s", "rockchip,rk3588s";
+
+	aliases {
+		ethernet0 = &gmac1;
+		mmc0 = &sdmmc;
+		mmc1 = &sdhci;
+	};
+
+	chosen {
+		stdout-path = "serial2:1500000n8";
+	};
+
+	adc-keys {
+		compatible = "adc-keys";
+		io-channels = <&saradc 0>;
+		io-channel-names = "buttons";
+		keyup-threshold-microvolt = <1800000>;
+		poll-interval = <100>;
+
+		button-maskrom {
+			label = "Maskrom";
+			linux,code = <KEY_VENDOR>;
+			press-threshold-microvolt = <1800>;
+		};
+	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		pinctrl-names = "default";
+		pinctrl-0 = <&key1_pin>;
+
+		button-user {
+			label = "User";
+			linux,code = <BTN_1>;
+			gpios = <&gpio1 RK_PC0 GPIO_ACTIVE_LOW>;
+			debounce-interval = <50>;
+		};
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		sys_led: led-0 {
+			label = "sys_led";
+			gpios = <&gpio1 RK_PC1 GPIO_ACTIVE_HIGH>;
+			linux,default-trigger = "heartbeat";
+			pinctrl-names = "default";
+			pinctrl-0 = <&sys_led_pin>;
+		};
+
+		wan_led: led-1 {
+			label = "wan_led";
+			gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&wan_led_pin>;
+		};
+
+		lan1_led: led-2 {
+			label = "lan1_led";
+			gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&lan1_led_pin>;
+		};
+
+		lan2_led: led-3 {
+			label = "lan2_led";
+			gpios = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&lan2_led_pin>;
+		};
+	};
+
+	vcc5v0_sys: vcc5v0-sys-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_sys";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
+	vcc_1v1_nldo_s3: vcc-1v1-nldo-s3-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_1v1_nldo_s3";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc_3v3_s0: vcc-3v3-s0-regulator {
+		compatible = "regulator-fixed";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-name = "vcc_3v3_s0";
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc_3v3_sd_s0: vcc-3v3-sd-s0-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&sd_s0_pwr>;
+		regulator-name = "vcc_3v3_sd_s0";
+		regulator-boot-on;
+		regulator-max-microvolt = <3000000>;
+		regulator-min-microvolt = <3000000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc_3v3_pcie20: vcc3v3-pcie20-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc_3v3_pcie20";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		vin-supply = <&vcc_3v3_s3>;
+	};
+
+	vcc5v0_usb: vcc5v0-usb-regulator {
+		compatible = "regulator-fixed";
+		regulator-name = "vcc5v0_usb";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_sys>;
+	};
+
+	vcc5v0_usb_otg0: vcc5v0-usb-otg0-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio1 RK_PD2 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&typec5v_pwren>;
+		regulator-name = "vcc5v0_usb_otg0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usb>;
+	};
+
+	vcc5v0_host_20: vcc5v0-host-20-regulator {
+		compatible = "regulator-fixed";
+		enable-active-high;
+		gpios = <&gpio4 RK_PB5 GPIO_ACTIVE_HIGH>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&vcc5v0_host20_en>;
+		regulator-name = "vcc5v0_host_20";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vcc5v0_usb>;
+	};
+};
+
+&combphy0_ps {
+	status = "okay";
+};
+
+&combphy2_psu {
+	status = "okay";
+};
+
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big0_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big1_s0>;
+};
+
+&cpu_l0 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&gmac1 {
+	clock_in_out = "output";
+	phy-handle = <&rgmii_phy1>;
+	phy-mode = "rgmii-rxid";
+	pinctrl-0 = <&gmac1_miim
+		     &gmac1_tx_bus2
+		     &gmac1_rx_bus2
+		     &gmac1_rgmii_clk
+		     &gmac1_rgmii_bus>;
+	pinctrl-names = "default";
+	tx_delay = <0x42>;
+	status = "okay";
+};
+
+&i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0m2_xfer>;
+	status = "okay";
+
+	vdd_cpu_big0_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big0_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+
+	vdd_cpu_big1_s0: regulator@43 {
+		compatible = "rockchip,rk8603", "rockchip,rk8602";
+		reg = <0x43>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_cpu_big1_s0";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <1050000>;
+		regulator-ramp-delay = <2300>;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c2 {
+	status = "okay";
+
+	vdd_npu_s0: regulator@42 {
+		compatible = "rockchip,rk8602";
+		reg = <0x42>;
+		fcs,suspend-voltage-selector = <1>;
+		regulator-name = "vdd_npu_s0";
+		regulator-min-microvolt = <550000>;
+		regulator-max-microvolt = <950000>;
+		regulator-ramp-delay = <2300>;
+		regulator-boot-on;
+		regulator-always-on;
+		vin-supply = <&vcc5v0_sys>;
+
+		regulator-state-mem {
+			regulator-off-in-suspend;
+		};
+	};
+};
+
+&i2c6 {
+	clock-frequency = <200000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c6m0_xfer>;
+	status = "okay";
+
+	hym8563: rtc@51 {
+		compatible = "haoyu,hym8563";
+		reg = <0x51>;
+		#clock-cells = <0>;
+		clock-output-names = "hym8563";
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtc_int>;
+		interrupt-parent = <&gpio0>;
+		interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>;
+		wakeup-source;
+	};
+};
+
+&mdio1 {
+	rgmii_phy1: ethernet-phy@1 {
+		compatible = "ethernet-phy-id001c.c916";
+		reg = <0x1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtl8211f_rst>;
+		reset-assert-us = <20000>;
+		reset-deassert-us = <100000>;
+		reset-gpios = <&gpio3 RK_PB7 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&pcie2x1l1 {
+	reset-gpios = <&gpio1 RK_PA7 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc_3v3_pcie20>;
+	status = "okay";
+};
+
+&pcie2x1l2 {
+	reset-gpios = <&gpio3 RK_PD1 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc_3v3_pcie20>;
+	status = "okay";
+};
+
+&pinctrl {
+	gpio-key {
+		key1_pin: key1-pin {
+			rockchip,pins = <1 RK_PC0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	gpio-leds {
+		sys_led_pin: sys-led-pin {
+			rockchip,pins =
+				<1 RK_PC1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		wan_led_pin: wan-led-pin {
+			rockchip,pins =
+				<1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		lan1_led_pin: lan1-led-pin {
+			rockchip,pins =
+				<1 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		lan2_led_pin: lan2-led-pin {
+			rockchip,pins =
+				<1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	hym8563 {
+		rtc_int: rtc-int {
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	sdmmc {
+		sd_s0_pwr: sd-s0-pwr {
+			rockchip,pins = <4 RK_PB4 RK_FUNC_GPIO &pcfg_pull_up>;
+		};
+	};
+
+	usb {
+		typec5v_pwren: typec5v-pwren {
+			rockchip,pins = <1 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+
+		vcc5v0_host20_en: vcc5v0-host20-en {
+			rockchip,pins = <4 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
+	rtl8211f {
+		rtl8211f_rst: rtl8211f-rst {
+			rockchip,pins = <3 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+};
+
+&saradc {
+	vref-supply = <&avcc_1v8_s0>;
+	status = "okay";
+};
+
+&sdhci {
+	bus-width = <8>;
+	no-sdio;
+	no-sd;
+	non-removable;
+	mmc-hs200-1_8v;
+	status = "okay";
+};
+
+&sdmmc {
+	bus-width = <4>;
+	cap-sd-highspeed;
+	disable-wp;
+	max-frequency = <150000000>;
+	no-mmc;
+	no-sdio;
+	sd-uhs-sdr104;
+	vmmc-supply = <&vcc_3v3_sd_s0>;
+	vqmmc-supply = <&vccio_sd_s0>;
+	status = "okay";
+};
+
+&spi2 {
+	status = "okay";
+	assigned-clocks = <&cru CLK_SPI2>;
+	assigned-clock-rates = <200000000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi2m2_cs0 &spi2m2_pins>;
+	num-cs = <1>;
+
+	pmic@0 {
+		compatible = "rockchip,rk806";
+		spi-max-frequency = <1000000>;
+		reg = <0x0>;
+
+		interrupt-parent = <&gpio0>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
+			    <&rk806_dvs2_null>, <&rk806_dvs3_null>;
+
+		system-power-controller;
+
+		vcc1-supply = <&vcc5v0_sys>;
+		vcc2-supply = <&vcc5v0_sys>;
+		vcc3-supply = <&vcc5v0_sys>;
+		vcc4-supply = <&vcc5v0_sys>;
+		vcc5-supply = <&vcc5v0_sys>;
+		vcc6-supply = <&vcc5v0_sys>;
+		vcc7-supply = <&vcc5v0_sys>;
+		vcc8-supply = <&vcc5v0_sys>;
+		vcc9-supply = <&vcc5v0_sys>;
+		vcc10-supply = <&vcc5v0_sys>;
+		vcc11-supply = <&vcc_2v0_pldo_s3>;
+		vcc12-supply = <&vcc5v0_sys>;
+		vcc13-supply = <&vcc_1v1_nldo_s3>;
+		vcc14-supply = <&vcc_1v1_nldo_s3>;
+		vcca-supply = <&vcc5v0_sys>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		rk806_dvs1_null: dvs1-null-pins {
+			pins = "gpio_pwrctrl1";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs2_null: dvs2-null-pins {
+			pins = "gpio_pwrctrl2";
+			function = "pin_fun0";
+		};
+
+		rk806_dvs3_null: dvs3-null-pins {
+			pins = "gpio_pwrctrl3";
+			function = "pin_fun0";
+		};
+
+		regulators {
+			vdd_gpu_s0: vdd_gpu_mem_s0: dcdc-reg1 {
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_gpu_s0";
+				regulator-enable-ramp-delay = <400>;
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_cpu_lit_s0: vdd_cpu_lit_mem_s0: dcdc-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_cpu_lit_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_log_s0: dcdc-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <750000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_log_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			vdd_vdenc_s0: vdd_vdenc_mem_s0: dcdc-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <550000>;
+				regulator-max-microvolt = <950000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_vdenc_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_ddr_s0: dcdc-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <675000>;
+				regulator-max-microvolt = <900000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			vdd2_ddr_s3: dcdc-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vdd2_ddr_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+				};
+			};
+
+			vcc_2v0_pldo_s3: dcdc-reg7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <2000000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vdd_2v0_pldo_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <2000000>;
+				};
+			};
+
+			vcc_3v3_s3: dcdc-reg8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_3v3_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <3300000>;
+				};
+			};
+
+			vddq_ddr_s0: dcdc-reg9 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vddq_ddr_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vcc_1v8_s3: dcdc-reg10 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avcc_1v8_s0: pldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "avcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vcc_1v8_s0: pldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_1v8_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			avdd_1v2_s0: pldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-name = "avdd_1v2_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			avcc_3v3_s0: pldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "avcc_3v3_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vccio_sd_s0: pldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-ramp-delay = <12500>;
+				regulator-name = "vccio_sd_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			pldo6_s3: pldo-reg6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "pldo6_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <1800000>;
+				};
+			};
+
+			vdd_0v75_s3: nldo-reg1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s3";
+
+				regulator-state-mem {
+					regulator-on-in-suspend;
+					regulator-suspend-microvolt = <750000>;
+				};
+			};
+
+			avdd_ddr_pll_s0: nldo-reg2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "avdd_ddr_pll_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+					regulator-suspend-microvolt = <850000>;
+				};
+			};
+
+			avdd_0v75_s0: nldo-reg3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "avdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			avdd_0v85_s0: nldo-reg4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <850000>;
+				regulator-name = "avdd_0v85_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+
+			vdd_0v75_s0: nldo-reg5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <750000>;
+				regulator-name = "vdd_0v75_s0";
+
+				regulator-state-mem {
+					regulator-off-in-suspend;
+				};
+			};
+		};
+	};
+};
+
+&tsadc {
+	status = "okay";
+};
+
+&u2phy2 {
+	status = "okay";
+};
+
+&u2phy2_host {
+	phy-supply = <&vcc5v0_host_20>;
+	status = "okay";
+};
+
+&uart2 {
+	pinctrl-0 = <&uart2m0_xfer>;
+	status = "okay";
+};
+
+&usb_host0_ehci {
+	status = "okay";
+};
+
+&usb_host0_ohci {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
index 2002fd0221fa..00afb90d4eb1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-rock-5a.dts
@@ -366,7 +366,6 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
-	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	max-frequency = <150000000>;
 	no-sdio;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
index 36b1b7acfe6a..87b83c87bd55 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi
@@ -519,6 +519,7 @@
 	vo1_grf: syscon@fd5a8000 {
 		compatible = "rockchip,rk3588-vo-grf", "syscon";
 		reg = <0x0 0xfd5a8000 0x0 0x100>;
+		clocks = <&cru PCLK_VO1GRF>;
 	};
 
 	php_grf: syscon@fd5b0000 {
@@ -586,6 +587,11 @@
 		};
 	};
 
+	hdptxphy0_grf: syscon@fd5e0000 {
+		compatible = "rockchip,rk3588-hdptxphy-grf", "syscon";
+		reg = <0x0 0xfd5e0000 0x0 0x100>;
+	};
+
 	ioc: syscon@fd5f0000 {
 		compatible = "rockchip,rk3588-ioc", "syscon";
 		reg = <0x0 0xfd5f0000 0x0 0x10000>;
@@ -1704,7 +1710,6 @@
 		dmas = <&dmac1 0>, <&dmac1 1>;
 		dma-names = "tx", "rx";
 		power-domains = <&power RK3588_PD_AUDIO>;
-		rockchip,trcm-sync-tx-only;
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2s2m1_lrck
 			     &i2s2m1_sclk
@@ -1725,7 +1730,6 @@
 		dmas = <&dmac1 2>, <&dmac1 3>;
 		dma-names = "tx", "rx";
 		power-domains = <&power RK3588_PD_AUDIO>;
-		rockchip,trcm-sync-tx-only;
 		pinctrl-names = "default";
 		pinctrl-0 = <&i2s3_lrck
 			     &i2s3_sclk
@@ -2360,6 +2364,22 @@
 		#dma-cells = <1>;
 	};
 
+	hdptxphy_hdmi0: phy@fed60000 {
+		compatible = "rockchip,rk3588-hdptx-phy";
+		reg = <0x0 0xfed60000 0x0 0x2000>;
+		clocks = <&cru CLK_USB2PHY_HDPTXRXPHY_REF>, <&cru PCLK_HDPTX0>;
+		clock-names = "ref", "apb";
+		#phy-cells = <0>;
+		resets = <&cru SRST_HDPTX0>, <&cru SRST_P_HDPTX0>,
+			 <&cru SRST_HDPTX0_INIT>, <&cru SRST_HDPTX0_CMN>,
+			 <&cru SRST_HDPTX0_LANE>, <&cru SRST_HDPTX0_ROPLL>,
+			 <&cru SRST_HDPTX0_LCPLL>;
+		reset-names = "phy", "apb", "init", "cmn", "lane", "ropll",
+			      "lcpll";
+		rockchip,grf = <&hdptxphy0_grf>;
+		status = "disabled";
+	};
+
 	combphy0_ps: phy@fee00000 {
 		compatible = "rockchip,rk3588-naneng-combphy";
 		reg = <0x0 0xfee00000 0x0 0x100>;
diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi
index 96859d098ef8..5dd4f3580a60 100644
--- a/arch/arm64/boot/dts/st/stm32mp251.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi
@@ -52,6 +52,18 @@
 			compatible = "fixed-clock";
 			clock-frequency = <200000000>;
 		};
+
+		ck_icn_p_vdec: ck-icn-p-vdec {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <200000000>;
+		};
+
+		ck_icn_p_venc: ck-icn-p-venc {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+			clock-frequency = <200000000>;
+		};
 	};
 
 	firmware {
diff --git a/arch/arm64/boot/dts/st/stm32mp255.dtsi b/arch/arm64/boot/dts/st/stm32mp255.dtsi
index e6fa596211f5..17f197c5b22b 100644
--- a/arch/arm64/boot/dts/st/stm32mp255.dtsi
+++ b/arch/arm64/boot/dts/st/stm32mp255.dtsi
@@ -6,4 +6,21 @@
 #include "stm32mp253.dtsi"
 
 / {
+	soc@0 {
+		rifsc: rifsc-bus@42080000 {
+			vdec: vdec@480d0000 {
+				compatible = "st,stm32mp25-vdec";
+				reg = <0x480d0000 0x3c8>;
+				interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&ck_icn_p_vdec>;
+			};
+
+			venc: venc@480e0000 {
+				compatible = "st,stm32mp25-venc";
+				reg = <0x480e0000 0x800>;
+				interrupts = <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>;
+				clocks = <&ck_icn_ls_mcu>;
+			};
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/tesla/fsd.dtsi b/arch/arm64/boot/dts/tesla/fsd.dtsi
index aaffb50b8b60..047a83cee603 100644
--- a/arch/arm64/boot/dts/tesla/fsd.dtsi
+++ b/arch/arm64/boot/dts/tesla/fsd.dtsi
@@ -601,6 +601,7 @@
 			clocks = <&clock_peric PERIC_PCLK_UART0>,
 				 <&clock_peric PERIC_SCLK_UART0>;
 			clock-names = "uart", "clk_uart_baud0";
+			samsung,uart-fifosize = <64>;
 			status = "disabled";
 		};
 
@@ -613,6 +614,7 @@
 			clocks = <&clock_peric PERIC_PCLK_UART1>,
 				 <&clock_peric PERIC_SCLK_UART1>;
 			clock-names = "uart", "clk_uart_baud0";
+			samsung,uart-fifosize = <64>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile
index 52c1dc910308..9a722c2473fb 100644
--- a/arch/arm64/boot/dts/ti/Makefile
+++ b/arch/arm64/boot/dts/ti/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Make file to build device tree binaries for boards based on
 # Texas Instruments Inc processors
@@ -22,6 +22,7 @@ dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dahlia.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-dev.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-mallow.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am625-verdin-wifi-yavia.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am62x-phyboard-lyra-gpio-fan.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am62-lp-sk.dtb
 
 # Boards with AM62Ax SoC
@@ -37,7 +38,15 @@ dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-csi2-imx219.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am62x-sk-hdmi-audio.dtbo
 
 # Boards with AM64x SoC
+k3-am642-hummingboard-t-pcie-dtbs := \
+	k3-am642-hummingboard-t.dtb k3-am642-hummingboard-t-pcie.dtbo
+k3-am642-hummingboard-t-usb3-dtbs := \
+	k3-am642-hummingboard-t.dtb k3-am642-hummingboard-t-usb3.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am642-evm.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am642-evm-icssg1-dualemac.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am642-hummingboard-t.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am642-hummingboard-t-pcie.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am642-hummingboard-t-usb3.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-phyboard-electra-rdk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am642-tqma64xxl-mbax4xxl.dtb
@@ -45,18 +54,24 @@ dtb-$(CONFIG_ARCH_K3) += k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo
 
 # Boards with AM65x SoC
-k3-am654-gp-evm-dtbs := k3-am654-base-board.dtb k3-am654-base-board-rocktech-rk101-panel.dtbo
+k3-am654-gp-evm-dtbs := k3-am654-base-board.dtb \
+	k3-am654-base-board-rocktech-rk101-panel.dtbo \
+	k3-am654-pcie-usb3.dtbo
 k3-am654-evm-dtbs := k3-am654-base-board.dtb k3-am654-icssg2.dtbo
-k3-am654-idk-dtbs := k3-am654-evm.dtb k3-am654-idk.dtbo
+k3-am654-idk-dtbs := k3-am654-evm.dtb k3-am654-idk.dtbo k3-am654-pcie-usb2.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-am6528-iot2050-basic.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am6528-iot2050-basic-pg2.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am6548-iot2050-advanced.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am6548-iot2050-advanced-m2.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am6548-iot2050-advanced-pg2.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am6548-iot2050-advanced-sm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am654-base-board.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am654-gp-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am654-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-am654-idk.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-am654-base-board-rocktech-rk101-panel.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am654-pcie-usb2.dtbo
+dtb-$(CONFIG_ARCH_K3) += k3-am654-pcie-usb3.dtbo
 
 # Boards with J7200 SoC
 k3-j7200-evm-dtbs := k3-j7200-common-proc-board.dtb k3-j7200-evm-quad-port-eth-exp.dtbo
@@ -69,6 +84,7 @@ dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-gesi-exp-board.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-evm-pcie0-ep.dtbo
 dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk.dtb
+dtb-$(CONFIG_ARCH_K3) += k3-j721e-sk-csi2-dual-imx219.dtbo
 
 # Boards with J721s2 SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am68-sk-base-board.dtb
@@ -78,6 +94,9 @@ k3-j721s2-evm-dtbs := k3-j721s2-common-proc-board.dtb k3-j721s2-evm-gesi-exp-boa
 dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j721s2-evm-pcie1-ep.dtbo
 
+# Boards with J722s SoC
+dtb-$(CONFIG_ARCH_K3) += k3-j722s-evm.dtb
+
 # Boards with J784s4 SoC
 dtb-$(CONFIG_ARCH_K3) += k3-am69-sk.dtb
 dtb-$(CONFIG_ARCH_K3) += k3-j784s4-evm.dtb
@@ -87,6 +106,8 @@ k3-am625-beagleplay-csi2-ov5640-dtbs := k3-am625-beagleplay.dtb \
 	k3-am625-beagleplay-csi2-ov5640.dtbo
 k3-am625-beagleplay-csi2-tevi-ov5640-dtbs := k3-am625-beagleplay.dtb \
 	k3-am625-beagleplay-csi2-tevi-ov5640.dtbo
+k3-am625-phyboard-lyra-gpio-fan-dtbs := k3-am625-phyboard-lyra-rdk.dtb \
+	k3-am62x-phyboard-lyra-gpio-fan.dtbo
 k3-am625-sk-csi2-imx219-dtbs := k3-am625-sk.dtb \
 	k3-am62x-sk-csi2-imx219.dtbo
 k3-am625-sk-csi2-ov5640-dtbs := k3-am625-sk.dtb \
@@ -101,12 +122,27 @@ k3-am62a7-sk-csi2-ov5640-dtbs := k3-am62a7-sk.dtb \
 	k3-am62x-sk-csi2-ov5640.dtbo
 k3-am62a7-sk-csi2-tevi-ov5640-dtbs := k3-am62a7-sk.dtb \
 	k3-am62x-sk-csi2-tevi-ov5640.dtbo
+k3-am62a7-sk-hdmi-audio-dtbs := k3-am62a7-sk.dtb k3-am62x-sk-hdmi-audio.dtbo
+k3-am62p5-sk-csi2-imx219-dtbs := k3-am62p5-sk.dtb \
+	k3-am62x-sk-csi2-imx219.dtbo
+k3-am62p5-sk-csi2-ov5640-dtbs := k3-am62p5-sk.dtb \
+	k3-am62x-sk-csi2-ov5640.dtbo
+k3-am62p5-sk-csi2-tevi-ov5640-dtbs := k3-am62p5-sk.dtb \
+	k3-am62x-sk-csi2-tevi-ov5640.dtbo
+k3-am642-evm-icssg1-dualemac-dtbs := \
+	k3-am642-evm.dtb k3-am642-evm-icssg1-dualemac.dtbo
 k3-am642-tqma64xxl-mbax4xxl-sdcard-dtbs := \
 	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-sdcard.dtbo
 k3-am642-tqma64xxl-mbax4xxl-wlan-dtbs := \
 	k3-am642-tqma64xxl-mbax4xxl.dtb k3-am64-tqma64xxl-mbax4xxl-wlan.dtbo
+k3-am68-sk-base-board-csi2-dual-imx219-dtbs := k3-am68-sk-base-board.dtb \
+	k3-j721e-sk-csi2-dual-imx219.dtbo
+k3-am69-sk-csi2-dual-imx219-dtbs := k3-am69-sk.dtb \
+	k3-j721e-sk-csi2-dual-imx219.dtbo
 k3-j721e-evm-pcie0-ep-dtbs := k3-j721e-common-proc-board.dtb \
 	k3-j721e-evm-pcie0-ep.dtbo
+k3-j721e-sk-csi2-dual-imx219-dtbs := k3-j721e-sk.dtb \
+	k3-j721e-sk-csi2-dual-imx219.dtbo
 k3-j721s2-evm-pcie1-ep-dtbs := k3-j721s2-common-proc-board.dtb \
 	k3-j721s2-evm-pcie1-ep.dtbo
 dtb- += k3-am625-beagleplay-csi2-ov5640.dtb \
@@ -118,9 +154,17 @@ dtb- += k3-am625-beagleplay-csi2-ov5640.dtb \
 	k3-am62-lp-sk-hdmi-audio.dtb \
 	k3-am62a7-sk-csi2-imx219.dtb \
 	k3-am62a7-sk-csi2-ov5640.dtb \
+	k3-am62a7-sk-hdmi-audio.dtb \
+	k3-am62p5-sk-csi2-imx219.dtb \
+	k3-am62p5-sk-csi2-ov5640.dtb \
+	k3-am62p5-sk-csi2-tevi-ov5640.dtb \
+	k3-am642-evm-icssg1-dualemac.dtb \
 	k3-am642-tqma64xxl-mbax4xxl-sdcard.dtb \
 	k3-am642-tqma64xxl-mbax4xxl-wlan.dtb \
+	k3-am68-sk-base-board-csi2-dual-imx219-dtbs \
+	k3-am69-sk-csi2-dual-imx219-dtbs \
 	k3-j721e-evm-pcie0-ep.dtb \
+	k3-j721e-sk-csi2-dual-imx219-dtbs \
 	k3-j721s2-evm-pcie1-ep.dtb
 
 # Enable support for device-tree overlays
@@ -128,7 +172,12 @@ DTC_FLAGS_k3-am625-beagleplay += -@
 DTC_FLAGS_k3-am625-sk += -@
 DTC_FLAGS_k3-am62-lp-sk += -@
 DTC_FLAGS_k3-am62a7-sk += -@
+DTC_FLAGS_k3-am62p5-sk += -@
+DTC_FLAGS_k3-am642-evm += -@
 DTC_FLAGS_k3-am642-tqma64xxl-mbax4xxl += -@
 DTC_FLAGS_k3-am6548-iot2050-advanced-m2 += -@
+DTC_FLAGS_k3-am68-sk-base-board += -@
+DTC_FLAGS_k3-am69-sk += -@
 DTC_FLAGS_k3-j721e-common-proc-board += -@
+DTC_FLAGS_k3-j721e-sk += -@
 DTC_FLAGS_k3-j721s2-common-proc-board += -@
diff --git a/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts b/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts
index 5e6feb8cd125..c4149059a4c5 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62-lp-sk.dts
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * AM62x LP SK: https://www.ti.com/tool/SK-AM62-LP
  *
- * Copyright (C) 2021-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
index 464b7565d085..e9cffca073ef 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM625 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_main {
@@ -42,9 +42,8 @@
 		};
 	};
 
-	main_conf: syscon@100000 {
-		compatible = "syscon", "simple-mfd";
-		reg = <0x00 0x00100000 0x00 0x20000>;
+	main_conf: bus@100000 {
+		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x0 0x00 0x00100000 0x20000>;
@@ -559,10 +558,9 @@
 		clock-names = "clk_ahb", "clk_xin";
 		assigned-clocks = <&k3_clks 57 6>;
 		assigned-clock-parents = <&k3_clks 57 8>;
+		bus-width = <8>;
 		mmc-ddr-1_8v;
 		mmc-hs200-1_8v;
-		ti,trm-icp = <0x2>;
-		bus-width = <8>;
 		ti,clkbuf-sel = <0x7>;
 		ti,otap-del-sel-legacy = <0x0>;
 		ti,otap-del-sel-mmc-hs = <0x0>;
@@ -580,7 +578,8 @@
 		power-domains = <&k3_pds 58 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 58 5>, <&k3_clks 58 6>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,trm-icp = <0x2>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
 		ti,otap-del-sel-legacy = <0x8>;
 		ti,otap-del-sel-sd-hs = <0x0>;
 		ti,otap-del-sel-sdr12 = <0x0>;
@@ -592,8 +591,6 @@
 		ti,itap-del-sel-sd-hs = <0x1>;
 		ti,itap-del-sel-sdr12 = <0xa>;
 		ti,itap-del-sel-sdr25 = <0x1>;
-		ti,clkbuf-sel = <0x7>;
-		bus-width = <4>;
 		status = "disabled";
 	};
 
@@ -604,7 +601,8 @@
 		power-domains = <&k3_pds 184 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 184 5>, <&k3_clks 184 6>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,trm-icp = <0x2>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
 		ti,otap-del-sel-legacy = <0x8>;
 		ti,otap-del-sel-sd-hs = <0x0>;
 		ti,otap-del-sel-sdr12 = <0x0>;
@@ -616,7 +614,6 @@
 		ti,itap-del-sel-sd-hs = <0xa>;
 		ti,itap-del-sel-sdr12 = <0xa>;
 		ti,itap-del-sel-sdr25 = <0x1>;
-		ti,clkbuf-sel = <0x7>;
 		status = "disabled";
 	};
 
@@ -640,6 +637,8 @@
 			interrupt-names = "host", "peripheral";
 			maximum-speed = "high-speed";
 			dr_mode = "otg";
+			snps,usb2-gadget-lpm-disable;
+			snps,usb2-lpm-disable;
 		};
 	};
 
@@ -663,6 +662,8 @@
 			interrupt-names = "host", "peripheral";
 			maximum-speed = "high-speed";
 			dr_mode = "otg";
+			snps,usb2-gadget-lpm-disable;
+			snps,usb2-lpm-disable;
 		};
 	};
 
@@ -779,9 +780,10 @@
 		      <0x00 0x30207000 0x00 0x1000>, /* ovr1 */
 		      <0x00 0x30208000 0x00 0x1000>, /* ovr2 */
 		      <0x00 0x3020a000 0x00 0x1000>, /* vp1: Used for OLDI */
-		      <0x00 0x3020b000 0x00 0x1000>; /* vp2: Used as DPI Out */
+		      <0x00 0x3020b000 0x00 0x1000>, /* vp2: Used as DPI Out */
+		      <0x00 0x30201000 0x00 0x1000>; /* common1 */
 		reg-names = "common", "vidl1", "vid",
-			    "ovr1", "ovr2", "vp1", "vp2";
+			    "ovr1", "ovr2", "vp1", "vp2", "common1";
 		power-domains = <&k3_pds 186 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 186 6>,
 			 <&dss_vp1_clk>,
diff --git a/arch/arm64/boot/dts/ti/k3-am62-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62-mcu.dtsi
index 0e0b234581c6..e66d486ef1f2 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-mcu.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM625 SoC Family MCU Domain peripherals
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu {
diff --git a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
index aa43e7407eee..43488cc8bcb1 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-phycore-som.dtsi
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2022 - 2023 PHYTEC Messtechnik GmbH
+ * Copyright (C) 2022-2024 PHYTEC Messtechnik GmbH
  * Author: Wadim Egorov <w.egorov@phytec.de>
  *
  * Product homepage:
@@ -317,7 +317,6 @@
 &sdhci0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc0_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	non-removable;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/ti/k3-am62-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-am62-thermal.dtsi
index a358757e26f0..12ba833002a1 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
index bf6d27e70bc4..6c4cec8728e4 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
@@ -185,7 +185,6 @@
 
 /* Verdin SD_1 */
 &sdhci1 {
-	ti,driver-strength-ohm = <33>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
index 680071688dcb..be62648e7818 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dev.dtsi
@@ -206,7 +206,6 @@
 
 /* Verdin SD_1 */
 &sdhci1 {
-	ti,driver-strength-ohm = <33>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi
index 17b93534f658..77b1beb638ad 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-mallow.dtsi
@@ -127,6 +127,16 @@
 		    <&pinctrl_qspi1_cs2_gpio>;
 	cs-gpios = <0>, <&main_gpio0 12 GPIO_ACTIVE_LOW>;
 	status = "okay";
+
+	tpm@1 {
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
+		reg = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_qspi1_dqs_gpio>;
+		interrupt-parent = <&main_gpio1>;
+		interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+		spi-max-frequency = <18500000>;
+	};
 };
 
 /* Verdin UART_3 */
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-wifi.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-wifi.dtsi
index a6808b10c7b2..4768ef42c4fc 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-wifi.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-wifi.dtsi
@@ -26,7 +26,6 @@
 	mmc-pwrseq = <&wifi_pwrseq>;
 	non-removable;
 	ti,fails-without-test-cd;
-	ti,driver-strength-ohm = <50>;
 	vmmc-supply = <&reg_3v3>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
index 6a06724b6d16..e8d8857ad51f 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
@@ -42,6 +42,22 @@
 		usb1 = &usb1;
 	};
 
+	connector {
+		compatible = "gpio-usb-b-connector", "usb-b-connector";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb0_id>;
+		id-gpios = <&main_gpio1 19 GPIO_ACTIVE_HIGH>;
+		label = "USB_1";
+		self-powered;
+		vbus-supply = <&reg_usb0_vbus>;
+
+		port {
+			usb_dr_connector: endpoint {
+				remote-endpoint = <&usb0_ep>;
+			};
+		};
+	};
+
 	verdin_gpio_keys: gpio-keys {
 		compatible = "gpio-keys";
 		pinctrl-names = "default";
@@ -151,6 +167,18 @@
 		vin-supply = <&reg_sd_3v3_1v8>;
 	};
 
+	reg_usb0_vbus: regulator-usb0-vbus {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_usb0_en>;
+		enable-active-high;
+		/* Verdin USB_1_EN (SODIMM 155) */
+		gpio = <&main_gpio1 50 GPIO_ACTIVE_HIGH>;
+		regulator-max-microvolt = <5000000>;
+		regulator-min-microvolt = <5000000>;
+		regulator-name = "USB_1_EN";
+	};
+
 	reserved-memory {
 		#address-cells = <2>;
 		#size-cells = <2>;
@@ -436,6 +464,13 @@
 		>;
 	};
 
+	/* Verdin USB_1_EN */
+	pinctrl_usb0_en: main-gpio1-50-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x0254, PIN_INPUT, 7) /* (C20) USB0_DRVVBUS.GPIO1_50 */ /* SODIMM 155 */
+		>;
+	};
+
 	/* On-module I2C - PMIC_I2C */
 	pinctrl_i2c0: main-i2c0-default-pins {
 		pinctrl-single,pins = <
@@ -660,13 +695,6 @@
 		>;
 	};
 
-	/* Verdin USB_1 */
-	pinctrl_usb0: main-usb0-default-pins {
-		pinctrl-single,pins = <
-			AM62X_IOPAD(0x0254, PIN_OUTPUT, 0) /* (C20) USB0_DRVVBUS */ /* SODIMM 155 */
-		>;
-	};
-
 	/* Verdin USB_2 */
 	pinctrl_usb1: main-usb1-default-pins {
 		pinctrl-single,pins = <
@@ -1013,7 +1041,7 @@
 		"",
 		"",
 		"SODIMM_17",
-		"", /* 50 */
+		"SODIMM_155", /* 50 */
 		"",
 		"",
 		"",
@@ -1118,7 +1146,7 @@
 				regulator-always-on;
 				regulator-boot-on;
 				regulator-max-microvolt = <850000>;
-				regulator-min-microvolt = <850000>;
+				regulator-min-microvolt = <750000>;
 				regulator-name = "+VDD_CORE (PMIC BUCK1)";
 			};
 
@@ -1407,7 +1435,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdhci0>;
 	non-removable;
-	ti,driver-strength-ohm = <50>;
 	status = "okay";
 };
 
@@ -1416,7 +1443,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdhci1>;
 	disable-wp;
-	ti,driver-strength-ohm = <50>;
 	vmmc-supply = <&reg_sdhc1_vmmc>;
 	vqmmc-supply = <&reg_sdhc1_vqmmc>;
 	status = "disabled";
@@ -1428,11 +1454,16 @@
 	status = "disabled";
 };
 
-/* TODO: role swich using ID pin */
 &usb0 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_usb0>, <&pinctrl_usb0_id>;
+	adp-disable;
+	usb-role-switch;
 	status = "disabled";
+
+	port {
+		usb0_ep: endpoint {
+			remote-endpoint = <&usb_dr_connector>;
+		};
+	};
 };
 
 /* Verdin USB_2 */
diff --git a/arch/arm64/boot/dts/ti/k3-am62-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62-wakeup.dtsi
index fef76f52a52e..23ce1bfda8d6 100644
--- a/arch/arm64/boot/dts/ti/k3-am62-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62-wakeup.dtsi
@@ -1,10 +1,12 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM625 SoC Family Wakeup Domain peripherals
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
+#include <dt-bindings/bus/ti-sysc.h>
+
 &cbass_wakeup {
 	wkup_conf: syscon@43000000 {
 		bootph-all;
@@ -21,14 +23,34 @@
 		};
 	};
 
-	wkup_uart0: serial@2b300000 {
-		compatible = "ti,am64-uart", "ti,am654-uart";
-		reg = <0x00 0x2b300000 0x00 0x100>;
-		interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+	target-module@2b300050 {
+		compatible = "ti,sysc-omap2", "ti,sysc";
+		reg = <0x00 0x2b300050 0x00 0x4>,
+		      <0x00 0x2b300054 0x00 0x4>,
+		      <0x00 0x2b300058 0x00 0x4>;
+		reg-names = "rev", "sysc", "syss";
+		ti,sysc-mask = <(SYSC_OMAP2_ENAWAKEUP |
+				 SYSC_OMAP2_SOFTRESET |
+				 SYSC_OMAP2_AUTOIDLE)>;
+		ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+				<SYSC_IDLE_NO>,
+				<SYSC_IDLE_SMART>,
+				<SYSC_IDLE_SMART_WKUP>;
+		ti,syss-mask = <1>;
+		ti,no-reset-on-init;
 		power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 114 0>;
-		clock-names = "fclk";
-		status = "disabled";
+		clock-names = "fck";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x00 0x2b300000 0x100000>;
+
+		wkup_uart0: serial@0 {
+			compatible = "ti,am64-uart", "ti,am654-uart";
+			reg = <0x0 0x100>;
+			interrupts = <GIC_SPI 186 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
 	};
 
 	wkup_i2c0: i2c@2b200000 {
diff --git a/arch/arm64/boot/dts/ti/k3-am62.dtsi b/arch/arm64/boot/dts/ti/k3-am62.dtsi
index f1e15206e1ce..f0781f2bea29 100644
--- a/arch/arm64/boot/dts/ti/k3-am62.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62 SoC Family
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso
index 5e80ca7033ba..3b4643b7d19c 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-ov5640.dtso
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * ALINX AN5641 & Digilent PCam 5C - OV5640 camera module
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso
index 5e1cbbc27c8f..81a2763d43c6 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay-csi2-tevi-ov5640.dtso
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Technexion TEVI-OV5640-*-RPI - OV5640 camera module
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
index eadbdd9ffe37..a34e0df2ab86 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * https://beagleplay.org/
  *
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
- * Copyright (C) 2022-2023 Robert Nelson, BeagleBoard.org Foundation
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Robert Nelson, BeagleBoard.org Foundation
  */
 
 /dts-v1/;
@@ -29,7 +29,6 @@
 		i2c3 = &main_i2c3;
 		i2c4 = &wkup_i2c0;
 		i2c5 = &mcu_i2c0;
-		mdio-gpio0 = &mdio0;
 		mmc0 = &sdhci0;
 		mmc1 = &sdhci1;
 		mmc2 = &sdhci2;
@@ -231,27 +230,6 @@
 		};
 	};
 
-	/* Workaround for errata i2329 - just use mdio bitbang */
-	mdio0: mdio {
-		compatible = "virtual,mdio-gpio";
-		pinctrl-names = "default";
-		pinctrl-0 = <&mdio0_pins_default>;
-		gpios = <&main_gpio0 86 GPIO_ACTIVE_HIGH>, /* MDC */
-			<&main_gpio0 85 GPIO_ACTIVE_HIGH>; /* MDIO */
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpsw3g_phy0: ethernet-phy@0 {
-			reg = <0>;
-		};
-
-		cpsw3g_phy1: ethernet-phy@1 {
-			reg = <1>;
-			reset-gpios = <&main_gpio1 5 GPIO_ACTIVE_LOW>;
-			reset-assert-us = <25>;
-			reset-deassert-us = <60000>; /* T2 */
-		};
-	};
 };
 
 &main_pmx0 {
@@ -312,8 +290,8 @@
 
 	mdio0_pins_default: mdio0-default-pins {
 		pinctrl-single,pins = <
-			AM62X_IOPAD(0x0160, PIN_OUTPUT, 7) /* (AD24) MDIO0_MDC.GPIO0_86 */
-			AM62X_IOPAD(0x015c, PIN_INPUT, 7) /* (AB22) MDIO0_MDIO.GPIO0_85 */
+			AM62X_IOPAD(0x0160, PIN_OUTPUT, 0) /* (AD24) MDIO0_MDC */
+			AM62X_IOPAD(0x015c, PIN_INPUT, 0) /* (AB22) MDIO0_MDIO */
 		>;
 	};
 
@@ -573,11 +551,13 @@
 };
 
 &usbss0 {
+	bootph-all;
 	ti,vbus-divider;
 	status = "okay";
 };
 
 &usb0 {
+	bootph-all;
 	dr_mode = "peripheral";
 };
 
@@ -611,8 +591,20 @@
 };
 
 &cpsw3g_mdio {
-	/* Workaround for errata i2329 - Use mdio bitbang */
-	status = "disabled";
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mdio0_pins_default>;
+
+	cpsw3g_phy0: ethernet-phy@0 {
+		reg = <0>;
+	};
+
+	cpsw3g_phy1: ethernet-phy@1 {
+		reg = <1>;
+		reset-gpios = <&main_gpio1 5 GPIO_ACTIVE_LOW>;
+		reset-assert-us = <25>;
+		reset-deassert-us = <60000>; /* T2 */
+	};
 };
 
 &main_gpio0 {
@@ -827,7 +819,6 @@
 	bootph-all;
 	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	status = "okay";
 };
@@ -840,7 +831,6 @@
 
 	vmmc-supply = <&vdd_3v3_sd>;
 	vqmmc-supply = <&vdd_sd_dv>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	cd-gpios = <&main_gpio1 48 GPIO_ACTIVE_LOW>;
 	cd-debounce-delay-ms = <100>;
@@ -852,12 +842,10 @@
 	vmmc-supply = <&wlan_en>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&wifi_pins_default>, <&wifi_32k_clk>;
-	bus-width = <4>;
 	non-removable;
 	ti,fails-without-test-cd;
 	cap-power-off-card;
 	keep-power-in-suspend;
-	ti,driver-strength-ohm = <50>;
 	assigned-clocks = <&k3_clks 157 158>;
 	assigned-clock-parents = <&k3_clks 157 160>;
 	#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
index 4bc0134c987d..a83a90497857 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2022 - 2023 PHYTEC Messtechnik GmbH
+ * Copyright (C) 2022-2024 PHYTEC Messtechnik GmbH
  * Author: Wadim Egorov <w.egorov@phytec.de>
  *
  * Product homepage:
@@ -222,6 +222,7 @@
 	cpsw3g_phy3: ethernet-phy@3 {
 		compatible = "ethernet-phy-id2000.a231", "ethernet-phy-ieee802.3-c22";
 		reg = <3>;
+		ti,clk-output-sel = <DP83867_CLK_O_SEL_OFF>;
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
 		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
 	};
@@ -333,7 +334,6 @@
 	vqmmc-supply = <&vddshv5_sdio>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	no-1-8-v;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/ti/k3-am625-sk.dts b/arch/arm64/boot/dts/ti/k3-am625-sk.dts
index b18092497c9a..ae81ebb39d02 100644
--- a/arch/arm64/boot/dts/ti/k3-am625-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am625-sk.dts
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * AM625 SK: https://www.ti.com/lit/zip/sprr448
  *
- * Copyright (C) 2021-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am625.dtsi b/arch/arm64/boot/dts/ti/k3-am625.dtsi
index 4193c2b3eed6..4014add6320d 100644
--- a/arch/arm64/boot/dts/ti/k3-am625.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am625.dtsi
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM625 SoC family in Quad core configuration
  *
  * TRM: https://www.ti.com/lit/pdf/spruiv7
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
index f0b8c9ab1459..aa1e057082f0 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62A SoC Family Main Domain peripherals
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_main {
@@ -42,9 +42,8 @@
 		};
 	};
 
-	main_conf: syscon@100000 {
-		compatible = "ti,j721e-system-controller", "syscon", "simple-mfd";
-		reg = <0x00 0x00100000 0x00 0x20000>;
+	main_conf: bus@100000 {
+		compatible = "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x00 0x00 0x00100000 0x20000>;
@@ -536,6 +535,24 @@
 		status = "disabled";
 	};
 
+	sdhci0: mmc@fa10000 {
+		compatible = "ti,am62-sdhci";
+		reg = <0x00 0xfa10000 0x00 0x260>, <0x00 0xfa18000 0x00 0x134>;
+		interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
+		power-domains = <&k3_pds 57 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 57 5>, <&k3_clks 57 6>;
+		clock-names = "clk_ahb", "clk_xin";
+		assigned-clocks = <&k3_clks 57 6>;
+		assigned-clock-parents = <&k3_clks 57 8>;
+		bus-width = <8>;
+		mmc-hs200-1_8v;
+		ti,clkbuf-sel = <0x7>;
+		ti,otap-del-sel-legacy = <0x0>;
+		ti,otap-del-sel-mmc-hs = <0x0>;
+		ti,otap-del-sel-hs200 = <0x6>;
+		status = "disabled";
+	};
+
 	sdhci1: mmc@fa00000 {
 		compatible = "ti,am62-sdhci";
 		reg = <0x00 0xfa00000 0x00 0x260>, <0x00 0xfa08000 0x00 0x134>;
@@ -543,7 +560,8 @@
 		power-domains = <&k3_pds 58 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 58 5>, <&k3_clks 58 6>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,trm-icp = <0x2>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
 		ti,otap-del-sel-legacy = <0x0>;
 		ti,otap-del-sel-sd-hs = <0x0>;
 		ti,otap-del-sel-sdr12 = <0xf>;
@@ -555,8 +573,30 @@
 		ti,itap-del-sel-sd-hs = <0x0>;
 		ti,itap-del-sel-sdr12 = <0x0>;
 		ti,itap-del-sel-sdr25 = <0x0>;
-		ti,clkbuf-sel = <0x7>;
+		no-1-8-v;
+		status = "disabled";
+	};
+
+	sdhci2: mmc@fa20000 {
+		compatible = "ti,am62-sdhci";
+		reg = <0x00 0xfa20000 0x00 0x260>, <0x00 0xfa28000 0x00 0x134>;
+		interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
+		power-domains = <&k3_pds 184 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 184 5>, <&k3_clks 184 6>;
+		clock-names = "clk_ahb", "clk_xin";
 		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
+		ti,otap-del-sel-legacy = <0x0>;
+		ti,otap-del-sel-sd-hs = <0x0>;
+		ti,otap-del-sel-sdr12 = <0xf>;
+		ti,otap-del-sel-sdr25 = <0xf>;
+		ti,otap-del-sel-sdr50 = <0xc>;
+		ti,otap-del-sel-sdr104 = <0x6>;
+		ti,otap-del-sel-ddr50 = <0x9>;
+		ti,itap-del-sel-legacy = <0x0>;
+		ti,itap-del-sel-sd-hs = <0x0>;
+		ti,itap-del-sel-sdr12 = <0x0>;
+		ti,itap-del-sel-sdr25 = <0x0>;
 		no-1-8-v;
 		status = "disabled";
 	};
@@ -985,4 +1025,30 @@
 		power-domains = <&k3_pds 185 TI_SCI_PD_EXCLUSIVE>;
 		status = "disabled";
 	};
+
+	dss: dss@30200000 {
+		compatible = "ti,am62a7-dss";
+		reg = <0x00 0x30200000 0x00 0x1000>, /* common */
+		      <0x00 0x30202000 0x00 0x1000>, /* vidl1 */
+		      <0x00 0x30206000 0x00 0x1000>, /* vid */
+		      <0x00 0x30207000 0x00 0x1000>, /* ovr1 */
+		      <0x00 0x30208000 0x00 0x1000>, /* ovr2 */
+		      <0x00 0x3020a000 0x00 0x1000>, /* vp1: Tied OFF in the SoC */
+		      <0x00 0x3020b000 0x00 0x1000>, /* vp2: Used as DPI Out */
+		      <0x00 0x30201000 0x00 0x1000>; /* common1 */
+		reg-names = "common", "vidl1", "vid",
+			    "ovr1", "ovr2", "vp1", "vp2", "common1";
+		power-domains = <&k3_pds 186 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 186 6>,
+			 <&k3_clks 186 0>,
+			 <&k3_clks 186 2>;
+		clock-names = "fck", "vp1", "vp2";
+		interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+		status = "disabled";
+
+		dss_ports: ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
index a6d16a94088c..8c36e56f4138 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-mcu.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM625 SoC Family MCU Domain peripherals
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu {
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-thermal.dtsi
index 85ce545633ea..c7486fb2a5b4 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi
index 4e8279fa01e1..f7bec484705a 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62A SoC Family Wakeup Domain peripherals
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_wakeup {
diff --git a/arch/arm64/boot/dts/ti/k3-am62a.dtsi b/arch/arm64/boot/dts/ti/k3-am62a.dtsi
index 61a210ecd5ff..b1b884600293 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62A SoC Family
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
index 7b7142586295..f241637a5642 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * AM62A SK: https://www.ti.com/lit/zip/sprr459
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -20,6 +20,7 @@
 		serial0 = &wkup_uart0;
 		serial2 = &main_uart0;
 		serial3 = &main_uart1;
+		mmc0 = &sdhci0;
 		mmc1 = &sdhci1;
 	};
 
@@ -132,6 +133,18 @@
 		clock-frequency = <12288000>;
 	};
 
+	hdmi0: connector-hdmi {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&sii9022_out>;
+			};
+		};
+	};
+
 	codec_audio: sound {
 		compatible = "simple-audio-card";
 		simple-audio-card,name = "AM62Ax-SKEVM";
@@ -181,6 +194,39 @@
 };
 
 &main_pmx0 {
+	main_dss0_pins_default: main-dss0-default-pins {
+		pinctrl-single,pins = <
+			AM62AX_IOPAD(0x100, PIN_OUTPUT, 0) /* (V17) VOUT0_VSYNC */
+			AM62AX_IOPAD(0x0f8, PIN_OUTPUT, 0) /* (T18) VOUT0_HSYNC */
+			AM62AX_IOPAD(0x104, PIN_OUTPUT, 0) /* (AA22) VOUT0_PCLK */
+			AM62AX_IOPAD(0x0fc, PIN_OUTPUT, 0) /* (U17) VOUT0_DE */
+			AM62AX_IOPAD(0x0b8, PIN_OUTPUT, 0) /* (U22) VOUT0_DATA0 */
+			AM62AX_IOPAD(0x0bc, PIN_OUTPUT, 0) /* (U21) VOUT0_DATA1 */
+			AM62AX_IOPAD(0x0c0, PIN_OUTPUT, 0) /* (U20) VOUT0_DATA2 */
+			AM62AX_IOPAD(0x0c4, PIN_OUTPUT, 0) /* (U19) VOUT0_DATA3 */
+			AM62AX_IOPAD(0x0c8, PIN_OUTPUT, 0) /* (T19) VOUT0_DATA4 */
+			AM62AX_IOPAD(0x0cc, PIN_OUTPUT, 0) /* (U18) VOUT0_DATA5 */
+			AM62AX_IOPAD(0x0d0, PIN_OUTPUT, 0) /* (V22) VOUT0_DATA6 */
+			AM62AX_IOPAD(0x0d4, PIN_OUTPUT, 0) /* (V21) VOUT0_DATA7 */
+			AM62AX_IOPAD(0x0d8, PIN_OUTPUT, 0) /* (V19) VOUT0_DATA8 */
+			AM62AX_IOPAD(0x0dc, PIN_OUTPUT, 0) /* (V18) VOUT0_DATA9 */
+			AM62AX_IOPAD(0x0e0, PIN_OUTPUT, 0) /* (W22) VOUT0_DATA10 */
+			AM62AX_IOPAD(0x0e4, PIN_OUTPUT, 0) /* (W21) VOUT0_DATA11 */
+			AM62AX_IOPAD(0x0e8, PIN_OUTPUT, 0) /* (W20) VOUT0_DATA12 */
+			AM62AX_IOPAD(0x0ec, PIN_OUTPUT, 0) /* (W19) VOUT0_DATA13 */
+			AM62AX_IOPAD(0x0f0, PIN_OUTPUT, 0) /* (Y21) VOUT0_DATA14 */
+			AM62AX_IOPAD(0x0f4, PIN_OUTPUT, 0) /* (Y22) VOUT0_DATA15 */
+			AM62AX_IOPAD(0x05c, PIN_OUTPUT, 1) /* (P22) GPMC0_AD8.VOUT0_DATA16 */
+			AM62AX_IOPAD(0x060, PIN_OUTPUT, 1) /* (R19) GPMC0_AD9.VOUT0_DATA17 */
+			AM62AX_IOPAD(0x064, PIN_OUTPUT, 1) /* (R20) GPMC0_AD10.VOUT0_DATA18 */
+			AM62AX_IOPAD(0x068, PIN_OUTPUT, 1) /* (R22) GPMC0_AD11.VOUT0_DATA19 */
+			AM62AX_IOPAD(0x06c, PIN_OUTPUT, 1) /* (T22) GPMC0_AD12.VOUT0_DATA20 */
+			AM62AX_IOPAD(0x070, PIN_OUTPUT, 1) /* (R21) GPMC0_AD13.VOUT0_DATA21 */
+			AM62AX_IOPAD(0x074, PIN_OUTPUT, 1) /* (T20) GPMC0_AD14.VOUT0_DATA22 */
+			AM62AX_IOPAD(0x078, PIN_OUTPUT, 1) /* (T21) GPMC0_AD15.VOUT0_DATA23 */
+		>;
+	};
+
 	main_uart0_pins_default: main-uart0-default-pins {
 		pinctrl-single,pins = <
 			AM62AX_IOPAD(0x1c8, PIN_INPUT, 0) /* (E14) UART0_RXD */
@@ -218,6 +264,22 @@
 		>;
 	};
 
+	main_mmc0_pins_default: main-mmc0-default-pins {
+		pinctrl-single,pins = <
+			AM62AX_IOPAD(0x220, PIN_INPUT, 0) /* (Y3) MMC0_CMD */
+			AM62AX_IOPAD(0x218, PIN_INPUT, 0) /* (AB1) MMC0_CLKLB */
+			AM62AX_IOPAD(0x21c, PIN_INPUT, 0) /* (AB1) MMC0_CLK */
+			AM62AX_IOPAD(0x214, PIN_INPUT, 0) /* (AA2) MMC0_DAT0 */
+			AM62AX_IOPAD(0x210, PIN_INPUT_PULLUP, 0) /* (AA1) MMC0_DAT1 */
+			AM62AX_IOPAD(0x20c, PIN_INPUT_PULLUP, 0) /* (AA3) MMC0_DAT2 */
+			AM62AX_IOPAD(0x208, PIN_INPUT_PULLUP, 0) /* (Y4) MMC0_DAT3 */
+			AM62AX_IOPAD(0x204, PIN_INPUT_PULLUP, 0) /* (AB2) MMC0_DAT4 */
+			AM62AX_IOPAD(0x200, PIN_INPUT_PULLUP, 0) /* (AC1) MMC0_DAT5 */
+			AM62AX_IOPAD(0x1fc, PIN_INPUT_PULLUP, 0) /* (AD2) MMC0_DAT6 */
+			AM62AX_IOPAD(0x1f8, PIN_INPUT_PULLUP, 0) /* (AC2) MMC0_DAT7 */
+		>;
+	};
+
 	main_mmc1_pins_default: main-mmc1-default-pins {
 		pinctrl-single,pins = <
 			AM62AX_IOPAD(0x23c, PIN_INPUT, 0) /* (A21) MMC1_CMD */
@@ -466,6 +528,36 @@
 				  "CSI_EN", "AUTO_100M_1000M_CONFIG",
 				  "CSI_VLDO_SEL", "SoC_WLAN_SDIO_RST";
 	};
+
+	sii9022: bridge-hdmi@3b {
+		compatible = "sil,sii9022";
+		reg = <0x3b>;
+		interrupt-parent = <&exp1>;
+		interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
+		#sound-dai-cells = <0>;
+		sil,i2s-data-lanes = < 0 >;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				sii9022_in: endpoint {
+					remote-endpoint = <&dpi1_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				sii9022_out: endpoint {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
 };
 
 &main_i2c2 {
@@ -475,13 +567,21 @@
 	clock-frequency = <400000>;
 };
 
+&sdhci0 {
+	/* eMMC */
+	status = "okay";
+	non-removable;
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mmc0_pins_default>;
+	disable-wp;
+};
+
 &sdhci1 {
 	/* SD/MMC */
 	status = "okay";
 	vmmc-supply = <&vdd_mmc1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
@@ -583,3 +683,20 @@
 	tx-num-evt = <32>;
 	rx-num-evt = <32>;
 };
+
+&dss {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_dss0_pins_default>;
+};
+
+&dss_ports {
+	/* VP2: DPI Output */
+	port@1 {
+		reg = <1>;
+
+		dpi1_out: endpoint {
+			remote-endpoint = <&sii9022_in>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62a7.dtsi b/arch/arm64/boot/dts/ti/k3-am62a7.dtsi
index 58f1c43edcf8..f86a23404e6d 100644
--- a/arch/arm64/boot/dts/ti/k3-am62a7.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62a7.dtsi
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62A7 SoC family in Quad core configuration
  *
  * TRM: https://www.ti.com/lit/zip/spruj16
  *
- * Copyright (C) 2020-2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
index 4c51bae06b57..7337a9e13535 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree file for the AM62P main domain peripherals
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_main {
@@ -158,6 +158,43 @@
 		};
 	};
 
+	dmss_csi: bus@4e000000 {
+		compatible = "simple-bus";
+		ranges = <0x00 0x4e000000 0x00 0x4e000000 0x00 0x408000>;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dma-ranges;
+		ti,sci-dev-id = <198>;
+
+		inta_main_dmss_csi: interrupt-controller@4e400000 {
+			compatible = "ti,sci-inta";
+			reg = <0x00 0x4e400000 0x00 0x8000>;
+			#interrupt-cells = <0>;
+			interrupt-controller;
+			interrupt-parent = <&gic500>;
+			msi-controller;
+			power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <200>;
+			ti,interrupt-ranges = <0 237 8>;
+			ti,unmapped-event-sources = <&main_bcdma_csi>;
+		};
+
+		main_bcdma_csi: dma-controller@4e230000 {
+			compatible = "ti,am62a-dmss-bcdma-csirx";
+			reg = <0x00 0x4e230000 0x00 0x100>,
+			      <0x00 0x4e180000 0x00 0x8000>,
+			      <0x00 0x4e100000 0x00 0x10000>;
+			reg-names = "gcfg", "rchanrt", "ringrt";
+			#dma-cells = <3>;
+			msi-parent = <&inta_main_dmss_csi>;
+			power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+			ti,sci = <&dmsc>;
+			ti,sci-dev-id = <199>;
+			ti,sci-rm-range-rchan = <0x21>;
+		};
+	};
+
 	dmsc: system-controller@44043000 {
 		compatible = "ti,k2g-sci";
 		ti,host-id = <12>;
@@ -534,7 +571,21 @@
 		clock-names = "clk_ahb", "clk_xin";
 		assigned-clocks = <&k3_clks 57 2>;
 		assigned-clock-parents = <&k3_clks 57 4>;
-		ti,otap-del-sel-legacy = <0x0>;
+		bus-width = <8>;
+		mmc-ddr-1_8v;
+		mmc-hs200-1_8v;
+		mmc-hs400-1_8v;
+		ti,clkbuf-sel = <0x7>;
+		ti,strobe-sel = <0x77>;
+		ti,trm-icp = <0x8>;
+		ti,otap-del-sel-legacy = <0x1>;
+		ti,otap-del-sel-mmc-hs = <0x1>;
+		ti,otap-del-sel-ddr52 = <0x6>;
+		ti,otap-del-sel-hs200 = <0x8>;
+		ti,otap-del-sel-hs400 = <0x5>;
+		ti,itap-del-sel-legacy = <0x10>;
+		ti,itap-del-sel-mmc-hs = <0xa>;
+		ti,itap-del-sel-ddr52 = <0x3>;
 		status = "disabled";
 	};
 
@@ -545,7 +596,19 @@
 		power-domains = <&k3_pds 58 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 58 5>, <&k3_clks 58 6>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,otap-del-sel-legacy = <0x8>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
+		ti,otap-del-sel-legacy = <0x0>;
+		ti,otap-del-sel-sd-hs = <0x0>;
+		ti,otap-del-sel-sdr12 = <0xf>;
+		ti,otap-del-sel-sdr25 = <0xf>;
+		ti,otap-del-sel-sdr50 = <0xc>;
+		ti,otap-del-sel-ddr50 = <0x9>;
+		ti,otap-del-sel-sdr104 = <0x6>;
+		ti,itap-del-sel-legacy = <0x0>;
+		ti,itap-del-sel-sd-hs = <0x0>;
+		ti,itap-del-sel-sdr12 = <0x0>;
+		ti,itap-del-sel-sdr25 = <0x0>;
 		status = "disabled";
 	};
 
@@ -556,7 +619,19 @@
 		power-domains = <&k3_pds 184 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 184 5>, <&k3_clks 184 6>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,otap-del-sel-legacy = <0x8>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
+		ti,otap-del-sel-legacy = <0x0>;
+		ti,otap-del-sel-sd-hs = <0x0>;
+		ti,otap-del-sel-sdr12 = <0xf>;
+		ti,otap-del-sel-sdr25 = <0xf>;
+		ti,otap-del-sel-sdr50 = <0xc>;
+		ti,otap-del-sel-ddr50 = <0x9>;
+		ti,otap-del-sel-sdr104 = <0x6>;
+		ti,itap-del-sel-legacy = <0x0>;
+		ti,itap-del-sel-sd-hs = <0x0>;
+		ti,itap-del-sel-sdr12 = <0x0>;
+		ti,itap-del-sel-sdr25 = <0x0>;
 		status = "disabled";
 	};
 
@@ -891,4 +966,73 @@
 		power-domains = <&k3_pds 192 TI_SCI_PD_EXCLUSIVE>;
 		status = "disabled";
 	};
+
+	ti_csi2rx0: ticsi2rx@30102000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x30102000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x5000 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 182 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@30101000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x30101000 0x00 0x1000>;
+			clocks = <&k3_clks 182 0>, <&k3_clks 182 3>, <&k3_clks 182 0>,
+				<&k3_clks 182 0>, <&k3_clks 182 4>, <&k3_clks 182 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@30110000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x30110000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 185 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	vpu: video-codec@30210000 {
+		compatible = "ti,j721s2-wave521c", "cnm,wave521c";
+		reg = <0x00 0x30210000 0x00 0x10000>;
+		interrupts = <GIC_SPI 225 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&k3_clks 204 2>;
+		power-domains = <&k3_pds 204 TI_SCI_PD_EXCLUSIVE>;
+	};
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi
index c4b0b91d70cf..b973b550eb9d 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree file for the AM62P MCU domain peripherals
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu {
@@ -187,6 +187,8 @@
 		ranges = <0x79000000 0x00 0x79000000 0x8000>,
 			 <0x79020000 0x00 0x79020000 0x8000>;
 		power-domains = <&k3_pds 7 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
 		mcu_r5fss0_core0: r5f@79000000 {
 			compatible = "ti,am62-r5f";
 			reg = <0x79000000 0x00008000>,
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-thermal.dtsi
index 85ce545633ea..c7486fb2a5b4 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi
index 19f42b39394e..a84756c336d0 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree file for the AM62P wakeup domain peripherals
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_wakeup {
@@ -78,6 +78,7 @@
 		ranges = <0x78000000 0x00 0x78000000 0x8000>,
 			 <0x78100000 0x00 0x78100000 0x8000>;
 		power-domains = <&k3_pds 119 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
 
 		wkup_r5fss0_core0: r5f@78000000 {
 			compatible = "ti,am62-r5f";
diff --git a/arch/arm64/boot/dts/ti/k3-am62p.dtsi b/arch/arm64/boot/dts/ti/k3-am62p.dtsi
index 84ffe7b9dcaf..94babc412575 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM62P SoC Family
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/gpio/gpio.h>
@@ -71,7 +71,7 @@
 			 <0x00 0x43600000 0x00 0x43600000 0x00 0x00010000>, /* SA3 sproxy data */
 			 <0x00 0x44043000 0x00 0x44043000 0x00 0x00000fe0>, /* TI SCI DEBUG */
 			 <0x00 0x44860000 0x00 0x44860000 0x00 0x00040000>, /* SA3 sproxy config */
-			 <0x00 0x48000000 0x00 0x48000000 0x00 0x06400000>, /* DMSS */
+			 <0x00 0x48000000 0x00 0x48000000 0x00 0x06408000>, /* DMSS */
 			 <0x00 0x60000000 0x00 0x60000000 0x00 0x08000000>, /* FSS0 DAT1 */
 			 <0x00 0x70000000 0x00 0x70000000 0x00 0x00010000>, /* OCSRAM */
 			 <0x01 0x00000000 0x01 0x00000000 0x00 0x00310000>, /* A53 PERIPHBASE */
diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
index 1773c05f752c..e86f34e835c1 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree file for the AM62P5-SK
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Schematics: https://www.ti.com/lit/zip/sprr487
  */
@@ -413,6 +413,7 @@
 	status = "okay";
 	ti,driver-strength-ohm = <50>;
 	disable-wp;
+	bootph-all;
 };
 
 &sdhci1 {
@@ -422,9 +423,7 @@
 	vqmmc-supply = <&vddshv_sdio>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
-	no-1-8-v;
 	bootph-all;
 };
 
@@ -445,6 +444,10 @@
 };
 
 &cpsw3g_mdio {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mdio1_pins_default>;
+	status = "okay";
+
 	cpsw3g_phy0: ethernet-phy@0 {
 		reg = <0>;
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
diff --git a/arch/arm64/boot/dts/ti/k3-am62p5.dtsi b/arch/arm64/boot/dts/ti/k3-am62p5.dtsi
index 50147bb63e03..41f479dca455 100644
--- a/arch/arm64/boot/dts/ti/k3-am62p5.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62p5.dtsi
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree file for the AM62P5 SoC family (quad core)
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * TRM: https://www.ti.com/lit/pdf/spruj83
  */
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra-gpio-fan.dtso b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra-gpio-fan.dtso
new file mode 100644
index 000000000000..f0b2fd4165a7
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am62x-phyboard-lyra-gpio-fan.dtso
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2024 PHYTEC America LLC
+ * Author: Garrett Giordano <ggiordano@phytec.com>
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/thermal/thermal.h>
+#include "k3-pinctrl.h"
+
+&{/} {
+	fan: gpio-fan {
+		compatible = "gpio-fan";
+		gpio-fan,speed-map = <0 0 8600 1>;
+		gpios = <&main_gpio0 40 GPIO_ACTIVE_LOW>;
+		#cooling-cells = <2>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&gpio_fan_pins_default>;
+	};
+};
+
+&main_pmx0 {
+	gpio_fan_pins_default: gpio-fan-default-pins {
+		pinctrl-single,pins = <
+			AM62X_IOPAD(0x0a4, PIN_OUTPUT, 7) /* (M22) GPMC0_DIR.GPIO0_40 */
+		>;
+	};
+};
+
+&thermal_zones {
+	main0_thermal: main0-thermal {
+		trips {
+			main0_thermal_trip0: main0-thermal-trip {
+				temperature = <65000>;  /* millicelsius */
+				hysteresis = <2000>;    /* millicelsius */
+				type = "active";
+			};
+		};
+
+		cooling-maps {
+			map0 {
+				trip = <&main0_thermal_trip0>;
+				cooling-device = <&fan THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
index 33768c02d8eb..3c45782ab2b7 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Common dtsi for AM62x SK and derivatives
  *
- * Copyright (C) 2021-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/leds/common.h>
@@ -411,7 +411,6 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc0_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
@@ -421,7 +420,6 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
@@ -460,6 +458,7 @@
 };
 
 &usbss0 {
+	bootph-all;
 	status = "okay";
 	ti,vbus-divider;
 };
@@ -470,6 +469,7 @@
 };
 
 &usb0 {
+	bootph-all;
 	#address-cells = <1>;
 	#size-cells = <0>;
 	usb-role-switch;
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso
index 6f4cd73c2f43..76ca02127f95 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-imx219.dtso
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * IMX219 (RPi v2) Camera Module
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso
index 9323a4b38389..ccc7f5e43184 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-ov5640.dtso
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * ALINX AN5641 & Digilent PCam 5C - OV5640 camera module
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso
index dcaa33a4c8d3..4eaf9d757dd0 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-csi2-tevi-ov5640.dtso
@@ -1,7 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Technexion TEVI-OV5640-*-RPI - OV5640 camera module
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-hdmi-audio.dtso b/arch/arm64/boot/dts/ti/k3-am62x-sk-hdmi-audio.dtso
index 43a0ddc123e5..18c3082f68e6 100644
--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-hdmi-audio.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-hdmi-audio.dtso
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * Audio playback via HDMI for AM625-SK and AM62-LP SK.
  *
@@ -6,7 +6,7 @@
  * AM625 SK: https://www.ti.com/tool/SK-AM62
  * AM62-LP SK: https://www.ti.com/tool/SK-AM62-LP
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
index e348114f42e0..6f9aa5e02138 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM642 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/phy/phy-cadence.h>
@@ -51,10 +51,11 @@
 			reg = <0x00000014 0x4>;
 		};
 
-		serdes_ln_ctrl: mux-controller {
-			compatible = "mmio-mux";
+		serdes_ln_ctrl: mux-controller@4080 {
+			compatible = "reg-mux";
+			reg = <0x4080 0x4>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4080 0x3>; /* SERDES0 lane0 select */
+			mux-reg-masks = <0x0 0x3>; /* SERDES0 lane0 select */
 		};
 
 		phy_gmii_sel: phy@4044 {
@@ -626,13 +627,18 @@
 		power-domains = <&k3_pds 57 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 57 0>, <&k3_clks 57 1>;
 		clock-names = "clk_ahb", "clk_xin";
+		bus-width = <8>;
 		mmc-ddr-1_8v;
 		mmc-hs200-1_8v;
+		ti,clkbuf-sel = <0x7>;
 		ti,trm-icp = <0x2>;
 		ti,otap-del-sel-legacy = <0x0>;
 		ti,otap-del-sel-mmc-hs = <0x0>;
 		ti,otap-del-sel-ddr52 = <0x6>;
 		ti,otap-del-sel-hs200 = <0x7>;
+		ti,itap-del-sel-legacy = <0x10>;
+		ti,itap-del-sel-mmc-hs = <0xa>;
+		ti,itap-del-sel-ddr52 = <0x3>;
 		status = "disabled";
 	};
 
@@ -643,15 +649,19 @@
 		power-domains = <&k3_pds 58 TI_SCI_PD_EXCLUSIVE>;
 		clocks = <&k3_clks 58 3>, <&k3_clks 58 4>;
 		clock-names = "clk_ahb", "clk_xin";
-		ti,trm-icp = <0x2>;
+		bus-width = <4>;
+		ti,clkbuf-sel = <0x7>;
 		ti,otap-del-sel-legacy = <0x0>;
-		ti,otap-del-sel-sd-hs = <0xf>;
+		ti,otap-del-sel-sd-hs = <0x0>;
 		ti,otap-del-sel-sdr12 = <0xf>;
 		ti,otap-del-sel-sdr25 = <0xf>;
 		ti,otap-del-sel-sdr50 = <0xc>;
 		ti,otap-del-sel-sdr104 = <0x6>;
 		ti,otap-del-sel-ddr50 = <0x9>;
-		ti,clkbuf-sel = <0x7>;
+		ti,itap-del-sel-legacy = <0x0>;
+		ti,itap-del-sel-sd-hs = <0x0>;
+		ti,itap-del-sel-sdr12 = <0x0>;
+		ti,itap-del-sel-sdr25 = <0x0>;
 		status = "disabled";
 	};
 
@@ -1041,25 +1051,6 @@
 		status = "disabled";
 	};
 
-	pcie0_ep: pcie-ep@f102000 {
-		compatible = "ti,am64-pcie-ep", "ti,j721e-pcie-ep";
-		reg = <0x00 0x0f102000 0x00 0x1000>,
-		      <0x00 0x0f100000 0x00 0x400>,
-		      <0x00 0x0d000000 0x00 0x00800000>,
-		      <0x00 0x68000000 0x00 0x08000000>;
-		reg-names = "intd_cfg", "user_cfg", "reg", "mem";
-		interrupt-names = "link_state";
-		interrupts = <GIC_SPI 203 IRQ_TYPE_EDGE_RISING>;
-		ti,syscon-pcie-ctrl = <&main_conf 0x4070>;
-		max-link-speed = <2>;
-		num-lanes = <1>;
-		power-domains = <&k3_pds 114 TI_SCI_PD_EXCLUSIVE>;
-		clocks = <&k3_clks 114 0>;
-		clock-names = "fck";
-		max-functions = /bits/ 8 <1>;
-		status = "disabled";
-	};
-
 	epwm0: pwm@23000000 {
 		compatible = "ti,am64-epwm", "ti,am3352-ehrpwm";
 		#pwm-cells = <3>;
@@ -1244,6 +1235,18 @@
 			};
 		};
 
+		icssg0_iep0: iep@2e000 {
+			compatible = "ti,am654-icss-iep";
+			reg = <0x2e000 0x1000>;
+			clocks = <&icssg0_iepclk_mux>;
+		};
+
+		icssg0_iep1: iep@2f000 {
+			compatible = "ti,am654-icss-iep";
+			reg = <0x2f000 0x1000>;
+			clocks = <&icssg0_iepclk_mux>;
+		};
+
 		icssg0_mii_rt: mii-rt@32000 {
 			compatible = "ti,pruss-mii", "syscon";
 			reg = <0x32000 0x100>;
@@ -1385,6 +1388,18 @@
 			};
 		};
 
+		icssg1_iep0: iep@2e000 {
+			compatible = "ti,am654-icss-iep";
+			reg = <0x2e000 0x1000>;
+			clocks = <&icssg1_iepclk_mux>;
+		};
+
+		icssg1_iep1: iep@2f000 {
+			compatible = "ti,am654-icss-iep";
+			reg = <0x2f000 0x1000>;
+			clocks = <&icssg1_iepclk_mux>;
+		};
+
 		icssg1_mii_rt: mii-rt@32000 {
 			compatible = "ti,pruss-mii", "syscon";
 			reg = <0x32000 0x100>;
diff --git a/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi
index b9508072bebb..ec17285869da 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-mcu.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM64 SoC Family MCU Domain peripherals
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu {
diff --git a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
index 1678e74cb750..125e507966fb 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-phycore-som.dtsi
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2021 PHYTEC America, LLC - https://www.phytec.com
+ * Copyright (C) 2021-2024 PHYTEC America, LLC - https://www.phytec.com
  * Author: Matt McKee <mmckee@phytec.com>
  *
- * Copyright (C) 2022 PHYTEC Messtechnik GmbH
+ * Copyright (C) 2022-2024 PHYTEC Messtechnik GmbH
  * Author: Wadim Egorov <w.egorov@phytec.de>
  *
  * Product homepage:
@@ -318,3 +318,10 @@
 	disable-wp;
 	keep-power-in-suspend;
 };
+
+&tscadc0 {
+	status = "okay";
+	adc {
+		ti,adc-channels = <0 1 2 3 4 5 6 7>;
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am64-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-am64-thermal.dtsi
index 036db56ba797..b1cd5542428c 100644
--- a/arch/arm64/boot/dts/ti/k3-am64-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-am64.dtsi b/arch/arm64/boot/dts/ti/k3-am64.dtsi
index 0187c42aed4f..74e56cc68d46 100644
--- a/arch/arm64/boot/dts/ti/k3-am64.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am64.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM642 SoC Family
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac.dtso b/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac.dtso
new file mode 100644
index 000000000000..af2fd3e7448b
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-evm-icssg1-dualemac.dtso
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/**
+ * DT overlay for enabling 2nd ICSSG1 port on AM642 EVM
+ *
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include "k3-pinctrl.h"
+
+&{/} {
+	aliases {
+		ethernet1 = "/icssg1-eth/ethernet-ports/port@1";
+	};
+
+	mdio-mux-2 {
+		compatible = "mdio-mux-multiplexer";
+		mux-controls = <&mdio_mux>;
+		mdio-parent-bus = <&icssg1_mdio>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		mdio@0 {
+			reg = <0x0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			icssg1_phy2: ethernet-phy@3 {
+				reg = <3>;
+				tx-internal-delay-ps = <250>;
+				rx-internal-delay-ps = <2000>;
+			};
+		};
+	};
+};
+
+&main_pmx0 {
+	icssg1_rgmii2_pins_default: icssg1-rgmii2-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0108, PIN_INPUT, 2) /* (W11) PRG1_PRU1_GPO0.RGMII2_RD0 */
+			AM64X_IOPAD(0x010c, PIN_INPUT, 2) /* (V11) PRG1_PRU1_GPO1.RGMII2_RD1 */
+			AM64X_IOPAD(0x0110, PIN_INPUT, 2) /* (AA12) PRG1_PRU1_GPO2.RGMII2_RD2 */
+			AM64X_IOPAD(0x0114, PIN_INPUT, 2) /* (Y12) PRG1_PRU1_GPO3.RGMII2_RD3 */
+			AM64X_IOPAD(0x0120, PIN_INPUT, 2) /* (U11) PRG1_PRU1_GPO6.RGMII2_RXC */
+			AM64X_IOPAD(0x0118, PIN_INPUT, 2) /* (W12) PRG1_PRU1_GPO4.RGMII2_RX_CTL */
+			AM64X_IOPAD(0x0134, PIN_OUTPUT, 2) /* (AA10) PRG1_PRU1_GPO11.RGMII2_TD0 */
+			AM64X_IOPAD(0x0138, PIN_OUTPUT, 2) /* (V10) PRG1_PRU1_GPO12.RGMII2_TD1 */
+			AM64X_IOPAD(0x013c, PIN_OUTPUT, 2) /* (U10) PRG1_PRU1_GPO13.RGMII2_TD2 */
+			AM64X_IOPAD(0x0140, PIN_OUTPUT, 2) /* (AA11) PRG1_PRU1_GPO14.RGMII2_TD3 */
+			AM64X_IOPAD(0x0148, PIN_OUTPUT, 2) /* (Y10) PRG1_PRU1_GPO16.RGMII2_TXC */
+			AM64X_IOPAD(0x0144, PIN_OUTPUT, 2) /* (Y11) PRG1_PRU1_GPO15.RGMII2_TX_CTL */
+		>;
+	};
+};
+
+&cpsw3g {
+	pinctrl-0 = <&rgmii1_pins_default>;
+};
+
+&cpsw_port2 {
+	status = "disabled";
+};
+
+&mdio_mux_1 {
+	status = "disabled";
+};
+
+&icssg1_eth {
+	pinctrl-0 = <&icssg1_rgmii1_pins_default>, <&icssg1_rgmii2_pins_default>;
+};
+
+&icssg1_emac1 {
+	status = "okay";
+	phy-handle = <&icssg1_phy2>;
+	phy-mode = "rgmii-id";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-evm.dts b/arch/arm64/boot/dts/ti/k3-am642-evm.dts
index 8c5651d2cf5d..53fe1d065ddb 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-evm.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -32,6 +32,7 @@
 		mmc1 = &sdhci1;
 		ethernet0 = &cpsw_port1;
 		ethernet1 = &cpsw_port2;
+		ethernet2 = &icssg1_emac0;
 	};
 
 	memory@80000000 {
@@ -198,7 +199,7 @@
 		mux-gpios = <&exp1 12 GPIO_ACTIVE_HIGH>;
 	};
 
-	mdio-mux-1 {
+	mdio_mux_1: mdio-mux-1 {
 		compatible = "mdio-mux-multiplexer";
 		mux-controls = <&mdio_mux>;
 		mdio-parent-bus = <&cpsw3g_mdio>;
@@ -229,6 +230,64 @@
 		max-bitrate = <5000000>;
 		standby-gpios = <&exp1 9 GPIO_ACTIVE_HIGH>;
 	};
+
+	icssg1_eth: icssg1-eth {
+		compatible = "ti,am642-icssg-prueth";
+		pinctrl-names = "default";
+		pinctrl-0 = <&icssg1_rgmii1_pins_default>;
+		sram = <&oc_sram>;
+		ti,prus = <&pru1_0>, <&rtu1_0>, <&tx_pru1_0>, <&pru1_1>, <&rtu1_1>, <&tx_pru1_1>;
+		firmware-name = "ti-pruss/am64x-sr2-pru0-prueth-fw.elf",
+				"ti-pruss/am64x-sr2-rtu0-prueth-fw.elf",
+				"ti-pruss/am64x-sr2-txpru0-prueth-fw.elf",
+				"ti-pruss/am64x-sr2-pru1-prueth-fw.elf",
+				"ti-pruss/am64x-sr2-rtu1-prueth-fw.elf",
+				"ti-pruss/am64x-sr2-txpru1-prueth-fw.elf";
+
+		ti,pruss-gp-mux-sel = <2>,	/* MII mode */
+				      <2>,
+				      <2>,
+				      <2>,	/* MII mode */
+				      <2>,
+				      <2>;
+		ti,mii-g-rt = <&icssg1_mii_g_rt>;
+		ti,mii-rt = <&icssg1_mii_rt>;
+		ti,iep = <&icssg1_iep0>,  <&icssg1_iep1>;
+		interrupt-parent = <&icssg1_intc>;
+		interrupts = <24 0 2>, <25 1 3>;
+		interrupt-names = "tx_ts0", "tx_ts1";
+		dmas = <&main_pktdma 0xc200 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc201 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc202 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc203 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc204 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc205 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc206 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc207 15>, /* egress slice 1 */
+		       <&main_pktdma 0x4200 15>, /* ingress slice 0 */
+		       <&main_pktdma 0x4201 15>; /* ingress slice 1 */
+		dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+			    "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+			    "rx0", "rx1";
+
+		ethernet-ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			icssg1_emac0: port@0 {
+				reg = <0>;
+				phy-handle = <&icssg1_phy1>;
+				phy-mode = "rgmii-id";
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+			};
+			icssg1_emac1: port@1 {
+				reg = <1>;
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				status = "disabled";
+			};
+		};
+	};
 };
 
 &main_pmx0 {
@@ -383,6 +442,30 @@
 			AM64X_IOPAD(0x0030, PIN_OUTPUT_PULLUP, 7) /* (L18) OSPI0_CSN1.GPIO0_12 */
 		>;
 	};
+
+	icssg1_mdio1_pins_default: icssg1-mdio1-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x015c, PIN_OUTPUT, 0) /* (Y6) PRG1_MDIO0_MDC */
+			AM64X_IOPAD(0x0158, PIN_INPUT, 0) /* (AA6) PRG1_MDIO0_MDIO */
+		>;
+	};
+
+	icssg1_rgmii1_pins_default: icssg1-rgmii1-default-pins{
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x00b8, PIN_INPUT, 2) /* (Y7) PRG1_PRU0_GPO0.PRG1_RGMII1_RD0 */
+			AM64X_IOPAD(0x00bc, PIN_INPUT, 2) /* (U8) PRG1_PRU0_GPO1.PRG1_RGMII1_RD1 */
+			AM64X_IOPAD(0x00c0, PIN_INPUT, 2) /* (W8) PRG1_PRU0_GPO2.PRG1_RGMII1_RD2 */
+			AM64X_IOPAD(0x00c4, PIN_INPUT, 2) /* (V8) PRG1_PRU0_GPO3.PRG1_RGMII1_RD3 */
+			AM64X_IOPAD(0x00d0, PIN_INPUT, 2) /* (AA7) PRG1_PRU0_GPO6.PRG1_RGMII1_RXC */
+			AM64X_IOPAD(0x00c8, PIN_INPUT, 2) /* (Y8) PRG1_PRU0_GPO4.PRG1_RGMII1_RX_CTL */
+			AM64X_IOPAD(0x00e4, PIN_INPUT, 2) /* (AA8) PRG1_PRU0_GPO11.PRG1_RGMII1_TD0 */
+			AM64X_IOPAD(0x00e8, PIN_INPUT, 2) /* (U9) PRG1_PRU0_GPO12.PRG1_RGMII1_TD1 */
+			AM64X_IOPAD(0x00ec, PIN_INPUT, 2) /* (W9) PRG1_PRU0_GPO13.PRG1_RGMII1_TD2 */
+			AM64X_IOPAD(0x00f0, PIN_INPUT, 2) /* (AA9) PRG1_PRU0_GPO14.PRG1_RGMII1_TD3 */
+			AM64X_IOPAD(0x00f8, PIN_INPUT, 2) /* (V9) PRG1_PRU0_GPO16.PRG1_RGMII1_TXC */
+			AM64X_IOPAD(0x00f4, PIN_INPUT, 2) /* (Y9) PRG1_PRU0_GPO15.PRG1_RGMII1_TX_CTL */
+		>;
+	};
 };
 
 &main_uart0 {
@@ -494,10 +577,10 @@
 /* eMMC */
 &sdhci0 {
 	status = "okay";
-	bus-width = <8>;
 	non-removable;
 	ti,driver-strength-ohm = <50>;
 	disable-wp;
+	bootph-all;
 };
 
 /* SD/MMC */
@@ -506,9 +589,7 @@
 	status = "okay";
 	vmmc-supply = <&vdd_mmc1>;
 	pinctrl-names = "default";
-	bus-width = <4>;
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
@@ -660,25 +741,25 @@
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster4>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster4>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
@@ -705,12 +786,6 @@
 	num-lanes = <1>;
 };
 
-&pcie0_ep {
-	phys = <&serdes0_pcie_link>;
-	phy-names = "pcie-phy";
-	num-lanes = <1>;
-};
-
 &ecap0 {
 	status = "okay";
 	/* PWM is available on Pin 1 of header J12 */
@@ -731,3 +806,15 @@
 	pinctrl-0 = <&main_mcan1_pins_default>;
 	phys = <&transceiver2>;
 };
+
+&icssg1_mdio {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&icssg1_mdio1_pins_default>;
+
+	icssg1_phy1: ethernet-phy@f {
+		reg = <0xf>;
+		tx-internal-delay-ps = <250>;
+		rx-internal-delay-ps = <2000>;
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso
new file mode 100644
index 000000000000..bd9a5caf20da
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-pcie.dtso
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2023 Josua Mayer <josua@solid-run.com>
+ *
+ * Overlay for SolidRun AM642 HummingBoard-T to enable PCI-E.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/phy/phy.h>
+
+#include "k3-serdes.h"
+
+&pcie0_rc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie0_default_pins>;
+	reset-gpios = <&main_gpio1 15 GPIO_ACTIVE_HIGH>;
+	phys = <&serdes0_link>;
+	phy-names = "pcie-phy";
+	num-lanes = <1>;
+	status = "okay";
+};
+
+&serdes0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	serdes0_link: phy@0 {
+		reg = <0>;
+		cdns,num-lanes = <1>;
+		cdns,phy-type = <PHY_TYPE_PCIE>;
+		#phy-cells = <0>;
+		resets = <&serdes_wiz0 1>;
+	};
+};
+
+&serdes_ln_ctrl {
+	idle-states = <AM64_SERDES0_LANE0_PCIE0>;
+};
+
+&serdes_mux {
+	idle-state = <1>;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso
new file mode 100644
index 000000000000..ffcc3bd3c7bc
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t-usb3.dtso
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2023 Josua Mayer <josua@solid-run.com>
+ *
+ * Overlay for SolidRun AM642 HummingBoard-T to enable USB-3.1.
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/phy/phy.h>
+
+#include "k3-serdes.h"
+
+&serdes0 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	serdes0_link: phy@0 {
+		reg = <0>;
+		cdns,num-lanes = <1>;
+		cdns,phy-type = <PHY_TYPE_USB3>;
+		#phy-cells = <0>;
+		resets = <&serdes_wiz0 1>;
+	};
+};
+
+&serdes_ln_ctrl {
+	idle-states = <AM64_SERDES0_LANE0_USB>;
+};
+
+&serdes_mux {
+	idle-state = <0>;
+};
+
+&usbss0 {
+	/delete-property/ ti,usb2-only;
+};
+
+&usb0 {
+	maximum-speed = "super-speed";
+	phys = <&serdes0_link>;
+	phy-names = "cdns3,usb3-phy";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts
new file mode 100644
index 000000000000..234d76e4e944
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2023 Josua Mayer <josua@solid-run.com>
+ *
+ * DTS for SolidRun AM642 HummingBoard-T,
+ * running on Cortex A53.
+ *
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/leds/common.h>
+#include <dt-bindings/phy/phy.h>
+
+#include "k3-am642.dtsi"
+#include "k3-am642-sr-som.dtsi"
+
+/ {
+	model = "SolidRun AM642 HummingBoard-T";
+	compatible = "solidrun,am642-hummingboard-t", "solidrun,am642-sr-som", "ti,am642";
+
+	aliases {
+		serial5 = &main_uart3;
+	};
+
+	leds {
+		compatible = "gpio-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&leds_default_pins>;
+
+		/* D24 */
+		led1: led-1 {
+			label = "led1";
+			gpios = <&main_gpio0 29 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+
+		/* D25 */
+		led2: led-2 {
+			label = "led2";
+			gpios = <&main_gpio0 30 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+
+		/* D26 */
+		led3: led-3 {
+			label = "led3";
+			gpios = <&main_gpio0 33 GPIO_ACTIVE_HIGH>;
+			color = <LED_COLOR_ID_GREEN>;
+		};
+	};
+
+	regulator-m2-3v3 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&regulator_pcie_3v3_default_pins>;
+		regulator-name = "m2-3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		gpio = <&main_gpio1 17 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
+	};
+
+	regulator-vpp-1v8 {
+		compatible = "regulator-fixed";
+		pinctrl-names = "default";
+		pinctrl-0 = <&regulator_vpp_1v8_default_pins>;
+		regulator-name = "vpp-1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		gpio = <&main_gpio1 78 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+	};
+
+	serdes_mux: mux-controller {
+		compatible = "gpio-mux";
+		pinctrl-names = "default";
+		pinctrl-0 = <&serdes_mux_default_pins>;
+		#mux-control-cells = <0>;
+		/*
+		 * Mux has 2 IOs:
+		 * - select: 0 = USB-3 (M2); 1 = PCIE (M1)
+		 * - shutdown: 0 = active; 1 = disabled (high impedance)
+		 */
+		mux-gpios = <&main_gpio1 40 GPIO_ACTIVE_HIGH>, <&main_gpio1 41 GPIO_ACTIVE_HIGH>;
+		/* default disabled */
+		idle-state = <2>;
+	};
+};
+
+&main_gpio0 {
+	m2-reset-hog {
+		gpio-hog;
+		gpios = <12 GPIO_ACTIVE_LOW>;
+		output-low; /* deasserted */
+		line-name = "m2-reset";
+	};
+
+	m1-m2-w-disable1-hog {
+		gpio-hog;
+		gpios = <32 GPIO_ACTIVE_LOW>;
+		output-low; /* deasserted */
+		line-name = "m1-m2-pcie-w-disable1";
+	};
+
+	m1-m2-w-disable2-hog {
+		gpio-hog;
+		gpios = <34 GPIO_ACTIVE_LOW>;
+		output-low; /* deasserted */
+		line-name = "m1-m2-pcie-w-disable2";
+	};
+};
+
+&main_gpio1 {
+	m1-pcie-clkreq0-hog {
+		gpio-hog;
+		gpios = <11 GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "m1-pcie-clkreq0";
+	};
+
+	m2-pcie-clkreq-hog {
+		gpio-hog;
+		gpios = <35 GPIO_ACTIVE_LOW>;
+		input;
+		line-name = "m2-pcie-clkreq";
+	};
+};
+
+&main_i2c0 {
+	pinctrl-0 = <&main_i2c0_default_pins>, <&main_i2c0_int_default_pins>;
+
+	humidity-sensor@41 {
+		compatible = "ti,hdc2010";
+		reg = <0x41>;
+		interrupt-parent = <&main_gpio0>;
+		interrupts = <37 IRQ_TYPE_EDGE_FALLING>;
+	};
+
+	light-sensor@44 {
+		compatible = "ti,opt3001";
+		reg = <0x44>;
+		interrupt-parent = <&main_gpio0>;
+		interrupts = <37 IRQ_TYPE_EDGE_FALLING>;
+	};
+
+	/* charger@6a */
+};
+
+&main_i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c1_default_pins>;
+	status = "okay";
+
+	rtc@69 {
+		compatible = "abracon,abx80x";
+		reg = <0x69>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&rtc_int_default_pins>;
+		abracon,tc-diode = "schottky";
+		abracon,tc-resistor = <3>;
+		interrupt-parent = <&main_gpio0>;
+		interrupts = <44 IRQ_TYPE_EDGE_FALLING>;
+	};
+};
+
+&main_mcan0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mcan0_default_pins>;
+	status = "okay";
+
+	can-transceiver {
+		max-bitrate = <8000000>;
+	};
+};
+
+&main_mcan1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mcan1_default_pins>;
+	status = "okay";
+
+	can-transceiver {
+		max-bitrate = <8000000>;
+	};
+};
+
+&main_pmx0 {
+	leds_default_pins: leds-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0074, PIN_OUTPUT, 7) /* GPMC0_AD14.GPIO0_29 */
+			AM64X_IOPAD(0x0078, PIN_OUTPUT, 7) /* GPMC0_AD15.GPIO0_30 */
+			AM64X_IOPAD(0x0088, PIN_OUTPUT, 7) /* GPMC0_OEn_REn.GPIO0_33 */
+		>;
+	};
+
+	main_i2c0_int_default_pins: main-i2c0-int-default-pins {
+		pinctrl-single,pins = <
+			/* external pull-up on Carrier */
+			AM64X_IOPAD(0x0098, PIN_INPUT, 7) /* GPMC0_WAIT0.GPIO0_37 */
+		>;
+	};
+
+	main_i2c1_default_pins: main-i2c1-default-pins {
+		pinctrl-single,pins = <
+			/* external pull-up on SoM */
+			AM64X_IOPAD(0x0268, PIN_INPUT, 0) /* I2C1_SCL.I2C1_SCL */
+			AM64X_IOPAD(0x026c, PIN_INPUT, 0) /* I2C1_SDA.I2C1_SDA */
+		>;
+	};
+
+	main_mcan0_default_pins: main-mcan0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0254, PIN_INPUT, 0) /* MCAN0_RX.MCAN0_RX */
+			AM64X_IOPAD(0x0250, PIN_OUTPUT, 0) /* MCAN0_TX.MCAN0_TX */
+		>;
+	};
+
+	main_mcan1_default_pins: main-mcan1-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x025c, PIN_INPUT, 0) /* MCAN1_RX.MCAN1_RX */
+			AM64X_IOPAD(0x0258, PIN_OUTPUT, 0) /* MCAN1_TX.MCAN1_TX */
+		>;
+	};
+
+	main_uart3_default_pins: main-uart3-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x016c, PIN_INPUT, 10) /* PRG0_PRU0_GPO3.UART3_CTSn */
+			AM64X_IOPAD(0x0170, PIN_OUTPUT, 10) /* PRG0_PRU0_GPO4.UART3_TXD */
+			AM64X_IOPAD(0x0174, PIN_OUTPUT, 10) /* PRG0_PRU0_GPO5.UART3_RTSn */
+			AM64X_IOPAD(0x01ac, PIN_INPUT, 10) /* PRG0_PRU0_GPO19.UART3_RXD */
+		>;
+	};
+
+	pcie0_default_pins: pcie0-default-pins {
+		pinctrl-single,pins = <
+			/* connector M2 RESET */
+			AM64X_IOPAD(0x0030, PIN_OUTPUT, 7) /* OSPI0_CSn1.GPIO0_12 */
+			/* connectors M1 & M2 W_DISABLE1 */
+			AM64X_IOPAD(0x0084, PIN_OUTPUT, 7) /* GPMC0_ADVN_ALE.GPIO0_32 */
+			/* connectors M1 & M2 W_DISABLE2 */
+			AM64X_IOPAD(0x008c, PIN_OUTPUT, 7) /* GPMC0_WEN.GPIO0_34 */
+			/* connectors M1 & M2 PERST0 (PCI Reset) */
+			AM64X_IOPAD(0x019c, PIN_OUTPUT, 7) /* PRG0_PRU0_GPO15.GPIO1_15 */
+			/* connector M1 CLKREQ0 */
+			AM64X_IOPAD(0x018c, PIN_INPUT, 7) /* PRG0_PRU0_GPO11.GPIO1_11 */
+			/* connector M2 CLKREQ0 */
+			AM64X_IOPAD(0x01ec, PIN_INPUT, 7) /* PRG0_PRU1_GPO15.GPIO1_35 */
+		>;
+	};
+
+	regulator_pcie_3v3_default_pins: regulator-pcie-3v3-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x01a4, PIN_OUTPUT, 7) /* PRG0_PRU0_GPO17.GPIO1_17 */
+		>;
+	};
+
+	regulator_vpp_1v8_default_pins: regulator-vpp-1v8-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x029c, PIN_OUTPUT, 7) /* MMC1_SDWP.GPIO1_78 */
+		>;
+	};
+
+	rtc_int_default_pins: rtc-int-default-pins {
+		pinctrl-single,pins = <
+			/* external pull-up on Carrier */
+			AM64X_IOPAD(0x00b4, PIN_INPUT, 7) /* GPMC0_CSn3.GPIO0_44 */
+		>;
+	};
+
+	serdes_mux_default_pins: serdes-mux-default-pins {
+		pinctrl-single,pins = <
+			/* SEL, 10k pull-down on carrier, 2.2k pullup on SoM */
+			AM64X_IOPAD(0x0200, PIN_OUTPUT, 7) /* PRG0_MDIO0_MDIO.GPIO1_40 */
+			/* EN */
+			AM64X_IOPAD(0x0204, PIN_OUTPUT, 7) /* PRG0_MDIO0_MDC.GPIO1_41 */
+		>;
+	};
+};
+
+&main_uart3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_uart3_default_pins>;
+	uart-has-rtscts;
+	rs485-rts-active-low;
+	linux,rs485-enabled-at-boot-time;
+	status = "okay";
+};
+
+&usb0 {
+	dr_mode = "host";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
index 53b64e55413f..8237b8c815b8 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2021 PHYTEC America, LLC - https://www.phytec.com
+ * Copyright (C) 2021-2024 PHYTEC America, LLC - https://www.phytec.com
  * Author: Matt McKee <mmckee@phytec.com>
  *
- * Copyright (C) 2022 PHYTEC Messtechnik GmbH
+ * Copyright (C) 2022-2024 PHYTEC Messtechnik GmbH
  * Author: Wadim Egorov <w.egorov@phytec.de>
  *
  * Product homepage:
@@ -159,6 +159,15 @@
 		>;
 	};
 
+	main_spi0_pins_default: main-spi0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x020c, PIN_OUTPUT, 7)	/* (C13) SPI0_CS1.GPIO1_43 */
+			AM64X_IOPAD(0x0210, PIN_INPUT, 0)	/* (D13) SPI0_CLK */
+			AM64X_IOPAD(0x0214, PIN_OUTPUT, 0)	/* (A13) SPI0_D0 */
+			AM64X_IOPAD(0x0218, PIN_INPUT, 0)	/* (A14) SPI0_D1 */
+		>;
+	};
+
 	main_uart0_pins_default: main-uart0-default-pins {
 		pinctrl-single,pins = <
 			AM64X_IOPAD(0x0230, PIN_INPUT, 0)	/* (D15) UART0_RXD */
@@ -248,6 +257,20 @@
 	phys = <&can_tc2>;
 };
 
+&main_spi0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_spi0_pins_default>;
+	cs-gpios = <0>, <&main_gpio1 43 GPIO_ACTIVE_LOW>;
+	ti,pindir-d0-out-d1-in;
+
+	tpm@1 {
+		compatible = "infineon,slb9670", "tcg,tpm_tis-spi";
+		reg = <1>;
+		spi-max-frequency = <10000000>;
+	};
+};
+
 &main_uart0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -269,7 +292,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_mmc1_pins_default>;
 	bus-width = <4>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 	no-1-8-v;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am642-sk.dts b/arch/arm64/boot/dts/ti/k3-am642-sk.dts
index 1dddd6fc1a0d..67cd41bf806e 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-sk.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -469,9 +469,7 @@
 	status = "okay";
 	vmmc-supply = <&vdd_mmc1>;
 	pinctrl-names = "default";
-	bus-width = <4>;
 	pinctrl-0 = <&main_mmc1_pins_default>;
-	ti,driver-strength-ohm = <50>;
 	disable-wp;
 };
 
@@ -646,25 +644,25 @@
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster4>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster4>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am642-sr-som.dtsi b/arch/arm64/boot/dts/ti/k3-am642-sr-som.dtsi
new file mode 100644
index 000000000000..c19d0b8bbf0f
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am642-sr-som.dtsi
@@ -0,0 +1,594 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2023 Josua Mayer <josua@solid-run.com>
+ *
+ */
+
+#include <dt-bindings/net/ti-dp83869.h>
+
+/ {
+	model = "SolidRun AM642 SoM";
+	compatible = "solidrun,am642-sr-som", "ti,am642";
+
+	aliases {
+		ethernet0 = &cpsw_port1;
+		ethernet1 = &icssg1_emac0;
+		ethernet2 = &icssg1_emac1;
+		mmc0 = &sdhci0;
+		mmc1 = &sdhci1;
+		serial2 = &main_uart0;
+	};
+
+	chosen {
+		/* SoC default UART console */
+		stdout-path = "serial2:115200n8";
+	};
+
+	/* PRU Ethernet Controller */
+	ethernet {
+		compatible = "ti,am642-icssg-prueth";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pru_rgmii1_default_pins>, <&pru_rgmii2_default_pins>;
+
+		sram = <&oc_sram>;
+		ti,prus = <&pru1_0>, <&rtu1_0>, <&tx_pru1_0>, <&pru1_1>, <&rtu1_1>, <&tx_pru1_1>;
+		firmware-name = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-rtu0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-txpru0-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-pru1-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-rtu1-prueth-fw.elf",
+				"ti-pruss/am65x-sr2-txpru1-prueth-fw.elf";
+
+		/* configure internal pinmux for mii mode */
+		ti,pruss-gp-mux-sel = <2>, <2>, <2>, <2>, <2>, <2>;
+
+		ti,mii-g-rt = <&icssg1_mii_g_rt>;
+		ti,mii-rt = <&icssg1_mii_rt>;
+		ti,iep = <&icssg1_iep0>, <&icssg1_iep1>;
+
+		/*
+		 * Configure icssg interrupt controller to map pru-internal
+		 * interrupts 8/9 via channels 0/1 to host interrupts 0/1.
+		 *
+		 * For details see interrupt controller documentation:
+		 * Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
+		 */
+		interrupt-parent = <&icssg1_intc>;
+		interrupts = <24 0 2>, <25 1 3>;
+		interrupt-names = "tx_ts0", "tx_ts1";
+
+		dmas = <&main_pktdma 0xc200 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc201 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc202 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc203 15>, /* egress slice 0 */
+		       <&main_pktdma 0xc204 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc205 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc206 15>, /* egress slice 1 */
+		       <&main_pktdma 0xc207 15>, /* egress slice 1 */
+		       <&main_pktdma 0x4200 15>, /* ingress slice 0 */
+		       <&main_pktdma 0x4201 15>; /* ingress slice 1 */
+		dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+			    "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+			    "rx0", "rx1";
+
+		ethernet-ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			icssg1_emac0: port@0 {
+				reg = <0>;
+				ti,syscon-rgmii-delay = <&main_conf 0x4110>;
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				phy-handle = <&ethernet_phy2>;
+				phy-mode = "rgmii-id";
+			};
+
+			icssg1_emac1: port@1 {
+				reg = <1>;
+				ti,syscon-rgmii-delay = <&main_conf 0x4114>;
+				/* Filled in by bootloader */
+				local-mac-address = [00 00 00 00 00 00];
+				phy-handle = <&ethernet_phy1>;
+				phy-mode = "rgmii-id";
+			};
+		};
+	};
+
+	/* DDR16SS0:
+	 * - Bank 1 @ 0x080000000-0x0FFFFFFFF: max. 2GB in 32-bit address space
+	 * - Bank 2 @ 0x880000000-0x9FFFFFFFF: max. 6GB in 64-bit address space
+	 */
+	memory@80000000 {
+		reg = <0x00000000 0x80000000 0x00000000 0x80000000>,
+		      <0x00000008 0x80000000 0x00000001 0x80000000>;
+		device_type = "memory";
+	};
+
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		secure_ddr: optee@9e800000 {
+			reg = <0x00 0x9e800000 0x00 0x01800000>; /* for OP-TEE */
+			no-map;
+		};
+
+		main_r5fss0_core0_dma_memory_region: r5f-dma-memory@a0000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core0_memory_region: r5f-memory@a0100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_dma_memory_region: r5f-dma-memory@a1000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss0_core1_memory_region: r5f-memory@a1100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa1100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_dma_memory_region: r5f-dma-memory@a2000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core0_memory_region: r5f-memory@a2100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa2100000 0x00 0xf00000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_dma_memory_region: r5f-dma-memory@a3000000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3000000 0x00 0x100000>;
+			no-map;
+		};
+
+		main_r5fss1_core1_memory_region: r5f-memory@a3100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa3100000 0x00 0xf00000>;
+			no-map;
+		};
+	};
+
+	vdd_mmc0: regulator-vdd-mmc0 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd-mmc0";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&cpsw3g {
+	pinctrl-names = "default";
+	pinctrl-0 = <&rgmii1_default_pins>;
+};
+
+&cpsw3g_mdio {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mdio0_default_pins>;
+	status = "okay";
+
+	ethernet_phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id2000.a0f1";
+		reg = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ethernet_phy0_default_pins>;
+		ti,clk-output-sel = <DP83869_CLK_O_SEL_REF_CLK>;
+		ti,op-mode = <DP83869_RGMII_COPPER_ETHERNET>;
+		/*
+		 * Disable interrupts because ISR never clears 0x0040
+		 *
+		 * interrupt-parent = <&main_gpio1>;
+		 * interrupts = <70 IRQ_TYPE_LEVEL_LOW>;
+		 */
+		/*
+		 * Disable HW Reset because clock signal is daisy-chained
+		 *
+		 * reset-gpios = <&main_gpio0 84 GPIO_ACTIVE_LOW>;
+		 * reset-assert-us = <1>;
+		 * reset-deassert-us = <30>;
+		 */
+	};
+};
+
+&cpsw_port1 {
+	phy-mode = "rgmii-id";
+	phy-handle = <&ethernet_phy0>;
+};
+
+&cpsw_port2 {
+	status = "disabled";
+};
+
+&icssg1_mdio {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pru1_mdio0_default_pins>;
+	status = "okay";
+
+	ethernet_phy1: ethernet-phy@3 {
+		compatible = "ethernet-phy-id2000.a0f1";
+		reg = <3>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ethernet_phy1_default_pins>;
+		ti,clk-output-sel = <DP83869_CLK_O_SEL_REF_CLK>;
+		ti,op-mode = <DP83869_RGMII_COPPER_ETHERNET>;
+		/*
+		 * Disable interrupts because ISR never clears 0x0040
+		 *
+		 * interrupt-parent = <&main_gpio1>;
+		 * interrupts = <70 IRQ_TYPE_LEVEL_LOW>;
+		 */
+		/*
+		 * Disable HW Reset because clock signal is daisy-chained
+		 *
+		 * reset-gpios = <&main_gpio0 20 GPIO_ACTIVE_LOW>;
+		 * reset-assert-us = <1>;
+		 * reset-deassert-us = <30>;
+		 */
+	};
+
+	ethernet_phy2: ethernet-phy@f {
+		compatible = "ethernet-phy-id2000.a0f1";
+		reg = <0xf>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ethernet_phy2_default_pins>;
+		ti,op-mode = <DP83869_RGMII_COPPER_ETHERNET>;
+		/*
+		 * Disable interrupts because ISR never clears 0x0040
+		 *
+		 * interrupt-parent = <&main_gpio1>;
+		 * interrupts = <70 IRQ_TYPE_LEVEL_LOW>;
+		 */
+		/*
+		 * Disable HW Reset because clock signal is daisy-chained
+		 *
+		 * reset-gpios = <&main_gpio0 52 GPIO_ACTIVE_LOW>;
+		 * reset-assert-us = <1>;
+		 * reset-deassert-us = <30>;
+		 */
+	};
+};
+
+&mailbox0_cluster2 {
+	status = "okay";
+
+	mbox_main_r5fss0_core0: mbox-main-r5fss0-core0 {
+		ti,mbox-rx = <0 0 2>;
+		ti,mbox-tx = <1 0 2>;
+	};
+
+	mbox_main_r5fss0_core1: mbox-main-r5fss0-core1 {
+		ti,mbox-rx = <2 0 2>;
+		ti,mbox-tx = <3 0 2>;
+	};
+};
+
+&mailbox0_cluster4 {
+	status = "okay";
+
+	mbox_main_r5fss1_core0: mbox-main-r5fss1-core0 {
+		ti,mbox-rx = <0 0 2>;
+		ti,mbox-tx = <1 0 2>;
+	};
+
+	mbox_main_r5fss1_core1: mbox-main-r5fss1-core1 {
+		ti,mbox-rx = <2 0 2>;
+		ti,mbox-tx = <3 0 2>;
+	};
+};
+
+&main_i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c0_default_pins>;
+	status = "okay";
+
+	som_eeprom: eeprom@50 {
+		compatible = "atmel,24c01";
+		reg = <0x50>;
+		pagesize = <8>;
+	};
+};
+
+&main_pmx0 {
+	/* hog global functions */
+	pinctrl-names = "default";
+	pinctrl-0 = <&ethernet_phy_default_pins>;
+
+	ethernet_phy_default_pins: ethernet-phy-default-pins {
+		pinctrl-single,pins = <
+			/* interrupt / power-down, external pull-up on SoM */
+			AM64X_IOPAD(0x0278, PIN_INPUT, 7) /* EXTINTn.GPIO1_70 */
+		>;
+	};
+
+	ethernet_phy0_default_pins: ethernet-phy0-default-pins {
+		pinctrl-single,pins = <
+			/* reset */
+			AM64X_IOPAD(0x0154, PIN_OUTPUT, 7) /* PRG1_PRU1_GPO19.GPIO0_84 */
+			/* reference clock */
+			AM64X_IOPAD(0x0274, PIN_OUTPUT, 5) /* EXT_REFCLK1.CLKOUT0 */
+		>;
+	};
+
+	ethernet_phy1_default_pins: ethernet-phy1-default-pins {
+		pinctrl-single,pins = <
+			/* reset */
+			AM64X_IOPAD(0x0150, PIN_OUTPUT, 7) /* PRG1_PRU1_GPO18.GPIO0_20 */
+			/* led0, external pull-down on SoM */
+			AM64X_IOPAD(0x0128, PIN_INPUT, 7) /* PRG1_PRU1_GPO8.GPIO0_73 */
+			/* led1/rxer */
+			AM64X_IOPAD(0x011c, PIN_INPUT, 7) /* PRG1_PRU1_GPO5.GPIO0_70 */
+		>;
+	};
+
+	ethernet_phy2_default_pins: ethernet-phy2-default-pins {
+		pinctrl-single,pins = <
+			/* reset */
+			AM64X_IOPAD(0x00d4, PIN_OUTPUT, 7) /* PRG1_PRU0_GPO7.GPIO0_52 */
+			/* led0, external pull-down on SoM */
+			AM64X_IOPAD(0x00d8, PIN_INPUT, 7) /* PRG1_PRU0_GPO8.GPIO0_53 */
+			/* led1/rxer */
+			AM64X_IOPAD(0x00cc, PIN_INPUT, 7) /* PRG1_PRU0_GPO5.GPIO0_50 */
+		>;
+	};
+
+	main_i2c0_default_pins: main-i2c0-default-pins {
+		pinctrl-single,pins = <
+			/* external pull-up on SoM */
+			AM64X_IOPAD(0x0260, PIN_INPUT, 0) /* I2C0_SCL.I2C0_SCL */
+			AM64X_IOPAD(0x0264, PIN_INPUT, 0) /* I2C0_SDA.I2C0_SDA */
+		>;
+	};
+
+	/*
+	 * main_mmc0_default_pins: main-mmc0-default-pins
+	 *
+	 * MMC0_CMD: no padconfig
+	 * MMC0_CLK: no padconfig, external pull-up on SoM
+	 * MMC0_DAT0: no padconfig
+	 * MMC0_DAT1: no padconfig
+	 * MMC0_DAT2: no padconfig
+	 * MMC0_DAT3: no padconfig
+	 * MMC0_DAT4: no padconfig
+	 * MMC0_DAT5: no padconfig
+	 * MMC0_DAT6: no padconfig
+	 * MMC0_DAT7: no padconfig
+	 * MMC0_DS: no padconfig, external pull-down on SoM
+	 */
+
+	main_mmc1_default_pins: main-mmc1-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0294, PIN_INPUT_PULLUP, 0) /* (J19) MMC1_CMD */
+			AM64X_IOPAD(0x028c, PIN_INPUT, 0) /* MMC1_CLK.MMC1_CLK */
+			AM64X_IOPAD(0x0288, PIN_INPUT_PULLUP, 0) /* MMC1_DAT0.MMC1_DAT0 */
+			AM64X_IOPAD(0x0284, PIN_INPUT_PULLUP, 0) /* MMC1_DAT1.MMC1_DAT1 */
+			AM64X_IOPAD(0x0280, PIN_INPUT_PULLUP, 0) /* MMC1_DAT2.MMC1_DAT2 */
+			AM64X_IOPAD(0x027c, PIN_INPUT_PULLUP, 0) /* MMC1_DAT3.MMC1_DAT3 */
+			/* external pull-down on SoM & Carrier */
+			AM64X_IOPAD(0x0298, PIN_INPUT_PULLUP, 0) /* MMC1_SDCD.MMC1_SDCD */
+			AM64X_IOPAD(0x0290, PIN_INPUT, 0) /* MMC1_CLKLB: clock loopback */
+		>;
+	};
+
+	main_uart0_default_pins: main-uart0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0230, PIN_INPUT, 0) /* UART0_RXD.UART0_RXD */
+			AM64X_IOPAD(0x0234, PIN_OUTPUT, 0) /* UART0_TXD.UART0_TXD */
+		>;
+	};
+
+	mdio0_default_pins: mdio0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x01fc, PIN_OUTPUT, 4) /* PRG0_PRU1_GPO19.MDIO0_MDC */
+			AM64X_IOPAD(0x01f8, PIN_INPUT, 4) /* PRG0_PRU1_GPO18.MDIO0_MDIO */
+		>;
+	};
+
+	ospi0_default_pins: ospi0-default-pins {
+		pinctrl-single,pins = <
+			/* external pull-down on SoM */
+			AM64X_IOPAD(0x0000, PIN_OUTPUT, 0) /* OSPI0_CLK.OSPI0_CLK */
+			AM64X_IOPAD(0x0008, PIN_OUTPUT, 0) /* OSPI0_DQS.OSPI0_DQS */
+			/* external pull-up on SoM */
+			AM64X_IOPAD(0x002c, PIN_OUTPUT, 0) /* OSPI0_CSn0.OSPI0_CSn0 */
+			AM64X_IOPAD(0x000c, PIN_INPUT, 0) /* OSPI0_D0.OSPI0_D0 */
+			AM64X_IOPAD(0x0010, PIN_INPUT, 0) /* OSPI0_D1.OSPI0_D1 */
+			AM64X_IOPAD(0x0014, PIN_INPUT, 0) /* OSPI0_D2.OSPI0_D2 */
+			AM64X_IOPAD(0x0018, PIN_INPUT, 0) /* OSPI0_D3.OSPI0_D3 */
+			AM64X_IOPAD(0x001c, PIN_INPUT, 0) /* OSPI0_D4.OSPI0_D4 */
+			AM64X_IOPAD(0x0020, PIN_INPUT, 0) /* OSPI0_D5.OSPI0_D5 */
+			AM64X_IOPAD(0x0024, PIN_INPUT, 0) /* OSPI0_D6.OSPI0_D6 */
+			AM64X_IOPAD(0x0028, PIN_INPUT, 0) /* OSPI0_D7.OSPI0_D7 */
+		>;
+	};
+
+	ospi0_flash0_default_pins: ospi0-flash0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0034, PIN_OUTPUT, 7) /* OSPI0_CSn2.GPIO0_13 */
+			AM64X_IOPAD(0x0038, PIN_INPUT, 7) /* OSPI0_CSn3.GPIO0_14 */
+		>;
+	};
+
+	pru1_mdio0_default_pins: pru1-mdio0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x015c, PIN_OUTPUT, 0) /* PRG1_MDIO0_MDC.PRG1_MDIO0_MDC */
+			AM64X_IOPAD(0x0158, PIN_INPUT, 0) /* PRG1_MDIO0_MDIO.PRG1_MDIO0_MDIO */
+		>;
+	};
+
+	pru_rgmii1_default_pins: pru-rgmii1-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x00b8, PIN_INPUT, 2) /* (Y7) PRG1_PRU0_GPO0.PRG1_RGMII1_RD0 */
+			AM64X_IOPAD(0x00bc, PIN_INPUT, 2) /* (U8) PRG1_PRU0_GPO1.PRG1_RGMII1_RD1 */
+			AM64X_IOPAD(0x00c0, PIN_INPUT, 2) /* (W8) PRG1_PRU0_GPO2.PRG1_RGMII1_RD2 */
+			AM64X_IOPAD(0x00c4, PIN_INPUT, 2) /* (V8) PRG1_PRU0_GPO3.PRG1_RGMII1_RD3 */
+			AM64X_IOPAD(0x00d0, PIN_INPUT, 2) /* (AA7) PRG1_PRU0_GPO6.PRG1_RGMII1_RXC */
+			AM64X_IOPAD(0x00c8, PIN_INPUT, 2) /* (Y8) PRG1_PRU0_GPO4.PRG1_RGMII1_RX_CTL */
+			AM64X_IOPAD(0x00e4, PIN_OUTPUT, 2) /* (AA8) PRG1_PRU0_GPO11.PRG1_RGMII1_TD0 */
+			AM64X_IOPAD(0x00e8, PIN_OUTPUT, 2) /* (U9) PRG1_PRU0_GPO12.PRG1_RGMII1_TD1 */
+			AM64X_IOPAD(0x00ec, PIN_OUTPUT, 2) /* (W9) PRG1_PRU0_GPO13.PRG1_RGMII1_TD2 */
+			AM64X_IOPAD(0x00f0, PIN_OUTPUT, 2) /* (AA9) PRG1_PRU0_GPO14.PRG1_RGMII1_TD3 */
+			AM64X_IOPAD(0x00f8, PIN_INPUT, 2) /* (V9) PRG1_PRU0_GPO16.PRG1_RGMII1_TXC */
+			AM64X_IOPAD(0x00f4, PIN_OUTPUT, 2) /* (Y9) PRG1_PRU0_GPO15.PRG1_RGMII1_TX_CTL */
+		>;
+	};
+
+	pru_rgmii2_default_pins: pru-rgmii2-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x0108, PIN_INPUT, 2) /* PRG1_PRU1_GPO0.RGMII2_RD0 */
+			AM64X_IOPAD(0x010c, PIN_INPUT, 2) /* PRG1_PRU1_GPO1.RGMII2_RD1 */
+			AM64X_IOPAD(0x0110, PIN_INPUT, 2) /* PRG1_PRU1_GPO2.RGMII2_RD2 */
+			AM64X_IOPAD(0x0114, PIN_INPUT, 2) /* PRG1_PRU1_GPO3.RGMII2_RD3 */
+			AM64X_IOPAD(0x0120, PIN_INPUT, 2) /* PRG1_PRU1_GPO6.RGMII2_RXC */
+			AM64X_IOPAD(0x0118, PIN_INPUT, 2) /* PRG1_PRU1_GPO4.RGMII2_RX_CTL */
+			AM64X_IOPAD(0x0134, PIN_OUTPUT, 2) /* PRG1_PRU1_GPO11.RGMII2_TD0 */
+			AM64X_IOPAD(0x0138, PIN_OUTPUT, 2) /* PRG1_PRU1_GPO12.RGMII2_TD1 */
+			AM64X_IOPAD(0x013c, PIN_OUTPUT, 2) /* PRG1_PRU1_GPO13.RGMII2_TD2 */
+			AM64X_IOPAD(0x0140, PIN_OUTPUT, 2) /* PRG1_PRU1_GPO14.RGMII2_TD3 */
+			AM64X_IOPAD(0x0148, PIN_INPUT, 2) /* PRG1_PRU1_GPO16.RGMII2_TXC */
+			AM64X_IOPAD(0x0144, PIN_OUTPUT, 2) /* PRG1_PRU1_GPO15.RGMII2_TX_CTL */
+		>;
+	};
+
+	rgmii1_default_pins: rgmii1-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x01cc, PIN_INPUT, 4) /* PRG0_PRU1_GPO7.RGMII1_RD0 */
+			AM64X_IOPAD(0x01d4, PIN_INPUT, 4) /* PRG0_PRU1_GPO9.RGMII1_RD1 */
+			AM64X_IOPAD(0x01d8, PIN_INPUT, 4) /* PRG0_PRU1_GPO10.RGMII1_RD2 */
+			AM64X_IOPAD(0x01f4, PIN_INPUT, 4) /* PRG0_PRU1_GPO17.RGMII1_RD3 */
+			AM64X_IOPAD(0x0188, PIN_INPUT, 4) /* PRG0_PRU0_GPO10.RGMII1_RXC */
+			AM64X_IOPAD(0x0184, PIN_INPUT, 4) /* PRG0_PRU0_GPO9.RGMII1_RX_CTL */
+			AM64X_IOPAD(0x0124, PIN_OUTPUT, 4) /* PRG1_PRU1_GPO7.RGMII1_TD0 */
+			AM64X_IOPAD(0x012c, PIN_OUTPUT, 4) /* PRG1_PRU1_GPO9.RGMII1_TD1 */
+			AM64X_IOPAD(0x0130, PIN_OUTPUT, 4) /* PRG1_PRU1_GPO10.RGMII1_TD2 */
+			AM64X_IOPAD(0x014c, PIN_OUTPUT, 4) /* PRG1_PRU1_GPO17.RGMII1_TD3 */
+			AM64X_IOPAD(0x00e0, PIN_INPUT, 4) /* PRG1_PRU0_GPO10.RGMII1_TXC */
+			AM64X_IOPAD(0x00dc, PIN_OUTPUT, 4) /* PRG1_PRU0_GPO9.RGMII1_TX_CTL */
+		>;
+	};
+
+	usb0_default_pins: usb0-default-pins {
+		pinctrl-single,pins = <
+			AM64X_IOPAD(0x02a8, PIN_OUTPUT, 0) /* USB0_DRVVBUS.USB0_DRVVBUS */
+		>;
+	};
+};
+
+&main_r5fss0_core0 {
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core0>;
+	memory-region = <&main_r5fss0_core0_dma_memory_region>,
+			<&main_r5fss0_core0_memory_region>;
+};
+
+&main_r5fss0_core1 {
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss0_core1>;
+	memory-region = <&main_r5fss0_core1_dma_memory_region>,
+			<&main_r5fss0_core1_memory_region>;
+};
+
+&main_r5fss1_core0 {
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core0>;
+	memory-region = <&main_r5fss1_core0_dma_memory_region>,
+			<&main_r5fss1_core0_memory_region>;
+};
+
+&main_r5fss1_core1 {
+	mboxes = <&mailbox0_cluster4 &mbox_main_r5fss1_core1>;
+	memory-region = <&main_r5fss1_core1_dma_memory_region>,
+			<&main_r5fss1_core1_memory_region>;
+};
+
+/* SoC default UART console */
+&main_uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_uart0_default_pins>;
+	status = "okay";
+};
+
+&ospi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ospi0_default_pins>;
+	num-cs = <1>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&ospi0_flash0_default_pins>;
+		spi-tx-bus-width = <8>;
+		spi-rx-bus-width = <8>;
+		spi-max-frequency = <200000000>;
+		cdns,tshsl-ns = <50>;
+		cdns,tsd2d-ns = <50>;
+		cdns,tchsh-ns = <4>;
+		cdns,tslch-ns = <4>;
+		cdns,read-delay = <0>;
+		interrupt-parent = <&main_gpio0>;
+		interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
+		reset-gpios = <&main_gpio0 13 GPIO_ACTIVE_LOW>;
+	};
+};
+
+&sdhci0 {
+	/* mmc0 pins have no padconfig */
+	bus-width = <8>;
+	ti,driver-strength-ohm = <50>;
+	disable-wp;
+	non-removable;
+	cap-mmc-hw-reset;
+	no-sd;
+	/*
+	 * MMC controller supports switching between 1.8V and 3.3V signalling.
+	 * However MMC0 (unlike MMC1) does not integrate an LDO.
+	 * Explicitly link a regulator node for indicating to the driver which
+	 * voltages are actually usable.
+	 */
+	vqmmc-supply = <&vdd_mmc0>;
+	status = "okay";
+};
+
+/*
+ * microSD is on carrier - however since SoC can boot from it,
+ * configure it just in case.
+ */
+&sdhci1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mmc1_default_pins>;
+	bus-width = <4>;
+	ti,driver-strength-ohm = <50>;
+	disable-wp;
+	status = "okay";
+};
+
+/*
+ * USB settings are a carrier choice - however since SoC can boot from it,
+ * configure as USB-2.0 OTG here, keeping USB-3 serdes disabled.
+ */
+&usb0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_default_pins>;
+	dr_mode = "otg";
+	maximum-speed = "high-speed";
+};
+
+&usbss0 {
+	ti,vbus-divider;
+	ti,usb2-only;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
index 55102d35cecc..1f4dc5ad1696 100644
--- a/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
+++ b/arch/arm64/boot/dts/ti/k3-am642-tqma64xxl-mbax4xxl.dts
@@ -422,7 +422,6 @@
 	cd-gpios = <&main_gpio1 77 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	no-mmc;
-	ti,driver-strength-ohm = <50>;
 	ti,fails-without-test-cd;
 	/* Enabled by overlay */
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am642.dtsi b/arch/arm64/boot/dts/ti/k3-am642.dtsi
index 7a6eedea3aae..8589ee55ef09 100644
--- a/arch/arm64/boot/dts/ti/k3-am642.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am642.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM642 SoC family in Dual core configuration
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-arduino-connector.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-arduino-connector.dtsi
new file mode 100644
index 000000000000..7ff0abd7c62e
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-arduino-connector.dtsi
@@ -0,0 +1,768 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Siemens AG, 2018-2023
+ *
+ * Authors:
+ *   Le Jin <le.jin@siemens.com>
+ *   Jan Kiszka <jan.kiszka@siemens.com>
+ *
+ * Common bits for IOT2050 variants with Arduino connector
+ */
+
+&wkup_pmx0 {
+	pinctrl-names =
+		"default",
+		"d0-uart0-rxd",  "d0-gpio",  "d0-gpio-pullup",  "d0-gpio-pulldown",
+		"d1-uart0-txd",  "d1-gpio",  "d1-gpio-pullup",  "d1-gpio-pulldown",
+		"d2-uart0-ctsn", "d2-gpio",  "d2-gpio-pullup",  "d2-gpio-pulldown",
+		"d3-uart0-rtsn", "d3-gpio",  "d3-gpio-pullup",  "d3-gpio-pulldown",
+		"d10-spi0-cs0",  "d10-gpio", "d10-gpio-pullup", "d10-gpio-pulldown",
+		"d11-spi0-d0",   "d11-gpio", "d11-gpio-pullup", "d11-gpio-pulldown",
+		"d12-spi0-d1",   "d12-gpio", "d12-gpio-pullup", "d12-gpio-pulldown",
+		"d13-spi0-clk",  "d13-gpio", "d13-gpio-pullup", "d13-gpio-pulldown",
+		"a0-gpio", "a0-gpio-pullup", "a0-gpio-pulldown",
+		"a1-gpio", "a1-gpio-pullup", "a1-gpio-pulldown",
+		"a2-gpio", "a2-gpio-pullup", "a2-gpio-pulldown",
+		"a3-gpio", "a3-gpio-pullup", "a3-gpio-pulldown",
+		"a4-gpio", "a4-gpio-pullup", "a4-gpio-pulldown",
+		"a5-gpio", "a5-gpio-pullup", "a5-gpio-pulldown";
+
+	pinctrl-0 = <&d0_uart0_rxd>;
+	pinctrl-1 = <&d0_uart0_rxd>;
+	pinctrl-2 = <&d0_gpio>;
+	pinctrl-3 = <&d0_gpio_pullup>;
+	pinctrl-4 = <&d0_gpio_pulldown>;
+	pinctrl-5 = <&d1_uart0_txd>;
+	pinctrl-6 = <&d1_gpio>;
+	pinctrl-7 = <&d1_gpio_pullup>;
+	pinctrl-8 = <&d1_gpio_pulldown>;
+	pinctrl-9 = <&d2_uart0_ctsn>;
+	pinctrl-10 = <&d2_gpio>;
+	pinctrl-11 = <&d2_gpio_pullup>;
+	pinctrl-12 = <&d2_gpio_pulldown>;
+	pinctrl-13 = <&d3_uart0_rtsn>;
+	pinctrl-14 = <&d3_gpio>;
+	pinctrl-15 = <&d3_gpio_pullup>;
+	pinctrl-16 = <&d3_gpio_pulldown>;
+	pinctrl-17 = <&d10_spi0_cs0>;
+	pinctrl-18 = <&d10_gpio>;
+	pinctrl-19 = <&d10_gpio_pullup>;
+	pinctrl-20 = <&d10_gpio_pulldown>;
+	pinctrl-21 = <&d11_spi0_d0>;
+	pinctrl-22 = <&d11_gpio>;
+	pinctrl-23 = <&d11_gpio_pullup>;
+	pinctrl-24 = <&d11_gpio_pulldown>;
+	pinctrl-25 = <&d12_spi0_d1>;
+	pinctrl-26 = <&d12_gpio>;
+	pinctrl-27 = <&d12_gpio_pullup>;
+	pinctrl-28 = <&d12_gpio_pulldown>;
+	pinctrl-29 = <&d13_spi0_clk>;
+	pinctrl-30 = <&d13_gpio>;
+	pinctrl-31 = <&d13_gpio_pullup>;
+	pinctrl-32 = <&d13_gpio_pulldown>;
+	pinctrl-33 = <&a0_gpio>;
+	pinctrl-34 = <&a0_gpio_pullup>;
+	pinctrl-35 = <&a0_gpio_pulldown>;
+	pinctrl-36 = <&a1_gpio>;
+	pinctrl-37 = <&a1_gpio_pullup>;
+	pinctrl-38 = <&a1_gpio_pulldown>;
+	pinctrl-39 = <&a2_gpio>;
+	pinctrl-40 = <&a2_gpio_pullup>;
+	pinctrl-41 = <&a2_gpio_pulldown>;
+	pinctrl-42 = <&a3_gpio>;
+	pinctrl-43 = <&a3_gpio_pullup>;
+	pinctrl-44 = <&a3_gpio_pulldown>;
+	pinctrl-45 = <&a4_gpio>;
+	pinctrl-46 = <&a4_gpio_pullup>;
+	pinctrl-47 = <&a4_gpio_pulldown>;
+	pinctrl-48 = <&a5_gpio>;
+	pinctrl-49 = <&a5_gpio_pullup>;
+	pinctrl-50 = <&a5_gpio_pulldown>;
+
+	d0_uart0_rxd: d0-uart0-rxd-pins {
+		pinctrl-single,pins = <
+			/* (P4) MCU_UART0_RXD */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 4)
+		>;
+	};
+
+	d0_gpio: d0-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 7)
+		>;
+	};
+
+	d0_gpio_pullup: d0-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d0_gpio_pulldown: d0-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d1_uart0_txd: d1-uart0-txd-pins {
+		pinctrl-single,pins = <
+			/* (P5) MCU_UART0_TXD */
+			AM65X_WKUP_IOPAD(0x0048, PIN_OUTPUT, 4)
+		>;
+	};
+
+	d1_gpio: d1-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
+		>;
+	};
+
+	d1_gpio_pullup: d1-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
+		>;
+	};
+
+	d1_gpio_pulldown: d1-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d2_uart0_ctsn: d2-uart0-ctsn-pins {
+		pinctrl-single,pins = <
+			/* (P1) MCU_UART0_CTSn */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 4)
+		>;
+	};
+
+	d2_gpio: d2-gpio-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
+		>;
+	};
+
+	d2_gpio_pullup: d2-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
+		>;
+	};
+
+	d2_gpio_pulldown: d2-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (P5) WKUP_GPIO0_31 */
+			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d3_uart0_rtsn: d3-uart0-rtsn-pins {
+		pinctrl-single,pins = <
+			/* (N3) MCU_UART0_RTSn */
+			AM65X_WKUP_IOPAD(0x0054, PIN_OUTPUT, 4)
+		>;
+	};
+
+	d3_gpio: d3-gpio-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
+		>;
+	};
+
+	d3_gpio_pullup: d3-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
+		>;
+	};
+
+	d3_gpio_pulldown: d3-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (N3) WKUP_GPIO0_33 */
+			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d10_spi0_cs0: d10-spi0-cs0-pins {
+		pinctrl-single,pins = <
+			/* (Y4) MCU_SPI0_CS0 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_OUTPUT, 0)
+		>;
+	};
+
+	d10_gpio: d10-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
+		>;
+	};
+
+	d10_gpio_pullup: d10-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
+		>;
+	};
+
+	d10_gpio_pulldown: d10-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y4) WKUP_GPIO0_51 */
+			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d11_spi0_d0: d11-spi0-d0-pins {
+		pinctrl-single,pins = <
+			/* (Y3) MCU_SPI0_D0 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 0)
+		>;
+	};
+
+	d11_gpio: d11-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
+		>;
+	};
+
+	d11_gpio_pullup: d11-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
+		>;
+	};
+
+	d11_gpio_pulldown: d11-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y3) WKUP_GPIO0_49 */
+			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d12_spi0_d1: d12-spi0-d1-pins {
+		pinctrl-single,pins = <
+			/* (Y2) MCU_SPI0_D1 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 0)
+		>;
+	};
+
+	d12_gpio: d12-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d12_gpio_pullup: d12-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d12_gpio_pulldown: d12-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y2) WKUP_GPIO0_50 */
+			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d13_spi0_clk: d13-spi0-clk-pins {
+		pinctrl-single,pins = <
+			/* (Y1) MCU_SPI0_CLK */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 0)
+		>;
+	};
+
+	d13_gpio: d13-gpio-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
+		>;
+	};
+
+	d13_gpio_pullup: d13-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
+		>;
+	};
+
+	d13_gpio_pulldown: d13-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (Y1) WKUP_GPIO0_48 */
+			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a0_gpio: a0-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	a0_gpio_pullup: a0-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	a0_gpio_pulldown: a0-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L6) WKUP_GPIO0_45 */
+			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a1_gpio: a1-gpio-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
+		>;
+	};
+
+	a1_gpio_pullup: a1-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
+		>;
+	};
+
+	a1_gpio_pulldown: a1-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (M6) WKUP_GPIO0_44 */
+			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a2_gpio: a2-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
+		>;
+	};
+
+	a2_gpio_pullup: a2-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
+		>;
+	};
+
+	a2_gpio_pulldown: a2-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L5) WKUP_GPIO0_43 */
+			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a3_gpio: a3-gpio-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
+		>;
+	};
+
+	a3_gpio_pullup: a3-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
+		>;
+	};
+
+	a3_gpio_pulldown: a3-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (M5) WKUP_GPIO0_39 */
+			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a4_gpio: a4-gpio-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
+		>;
+	};
+
+	a4_gpio_pullup: a4-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
+		>;
+	};
+
+	a4_gpio_pulldown: a4-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (L2) WKUP_GPIO0_42 */
+			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	a5_gpio: a5-gpio-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT, 7)
+		>;
+	};
+
+	a5_gpio_pullup: a5-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	a5_gpio_pulldown: a5-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (N5) WKUP_GPIO0_35 */
+			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	wkup_i2c0_pins_default: wkup-i2c0-default-pins {
+		pinctrl-single,pins = <
+			/* (AC7) WKUP_I2C0_SCL */
+			AM65X_WKUP_IOPAD(0x00e0, PIN_INPUT,  0)
+			/* (AD6) WKUP_I2C0_SDA */
+			AM65X_WKUP_IOPAD(0x00e4, PIN_INPUT,  0)
+		>;
+	};
+
+	arduino_i2c_aio_switch_pins_default: arduino-i2c-aio-switch-default-pins {
+		pinctrl-single,pins = <
+			/* (R2) WKUP_GPIO0_21 */
+			AM65X_WKUP_IOPAD(0x0024, PIN_OUTPUT, 7)
+		>;
+	};
+
+	arduino_io_oe_pins_default: arduino-io-oe-default-pins {
+		pinctrl-single,pins = <
+			/* (N4) WKUP_GPIO0_34 */
+			AM65X_WKUP_IOPAD(0x0058, PIN_OUTPUT, 7)
+			/* (M2) WKUP_GPIO0_36 */
+			AM65X_WKUP_IOPAD(0x0060, PIN_OUTPUT, 7)
+			/* (M3) WKUP_GPIO0_37 */
+			AM65X_WKUP_IOPAD(0x0064, PIN_OUTPUT, 7)
+			/* (M4) WKUP_GPIO0_38 */
+			AM65X_WKUP_IOPAD(0x0068, PIN_OUTPUT, 7)
+			/* (M1) WKUP_GPIO0_41 */
+			AM65X_WKUP_IOPAD(0x0074, PIN_OUTPUT, 7)
+		>;
+	};
+};
+
+&main_pmx0 {
+	pinctrl-names =
+		"default",
+		"d4-ehrpwm0-a", "d4-gpio", "d4-gpio-pullup", "d4-gpio-pulldown",
+		"d5-ehrpwm1-a", "d5-gpio", "d5-gpio-pullup", "d5-gpio-pulldown",
+		"d6-ehrpwm2-a", "d6-gpio", "d6-gpio-pullup", "d6-gpio-pulldown",
+		"d7-ehrpwm3-a", "d7-gpio", "d7-gpio-pullup", "d7-gpio-pulldown",
+		"d8-ehrpwm4-a", "d8-gpio", "d8-gpio-pullup", "d8-gpio-pulldown",
+		"d9-ehrpwm5-a", "d9-gpio", "d9-gpio-pullup", "d9-gpio-pulldown";
+
+	pinctrl-0 = <&d4_ehrpwm0_a>;
+	pinctrl-1 = <&d4_ehrpwm0_a>;
+	pinctrl-2 = <&d4_gpio>;
+	pinctrl-3 = <&d4_gpio_pullup>;
+	pinctrl-4 = <&d4_gpio_pulldown>;
+
+	pinctrl-5 = <&d5_ehrpwm1_a>;
+	pinctrl-6 = <&d5_gpio>;
+	pinctrl-7 = <&d5_gpio_pullup>;
+	pinctrl-8 = <&d5_gpio_pulldown>;
+
+	pinctrl-9 = <&d6_ehrpwm2_a>;
+	pinctrl-10 = <&d6_gpio>;
+	pinctrl-11 = <&d6_gpio_pullup>;
+	pinctrl-12 = <&d6_gpio_pulldown>;
+
+	pinctrl-13 = <&d7_ehrpwm3_a>;
+	pinctrl-14 = <&d7_gpio>;
+	pinctrl-15 = <&d7_gpio_pullup>;
+	pinctrl-16 = <&d7_gpio_pulldown>;
+
+	pinctrl-17 = <&d8_ehrpwm4_a>;
+	pinctrl-18 = <&d8_gpio>;
+	pinctrl-19 = <&d8_gpio_pullup>;
+	pinctrl-20 = <&d8_gpio_pulldown>;
+
+	pinctrl-21 = <&d9_ehrpwm5_a>;
+	pinctrl-22 = <&d9_gpio>;
+	pinctrl-23 = <&d9_gpio_pullup>;
+	pinctrl-24 = <&d9_gpio_pulldown>;
+
+	d4_ehrpwm0_a: d4-ehrpwm0-a-pins {
+		pinctrl-single,pins = <
+			/* (AG18) EHRPWM0_A */
+			AM65X_IOPAD(0x0084, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d4_gpio: d4-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT, 7)
+		>;
+	};
+
+	d4_gpio_pullup: d4-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d4_gpio_pulldown: d4-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AG18) GPIO0_33 */
+			AM65X_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d5_ehrpwm1_a: d5-ehrpwm1-a-pins {
+		pinctrl-single,pins = <
+			/* (AF17) EHRPWM1_A */
+			AM65X_IOPAD(0x008C, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d5_gpio: d5-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT, 7)
+		>;
+	};
+
+	d5_gpio_pullup: d5-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d5_gpio_pulldown: d5-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AF17) GPIO0_35 */
+			AM65X_IOPAD(0x008C, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d6_ehrpwm2_a: d6-ehrpwm2-a-pins {
+		pinctrl-single,pins = <
+			/* (AH16) EHRPWM2_A */
+			AM65X_IOPAD(0x0098, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d6_gpio: d6-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT, 7)
+		>;
+	};
+
+	d6_gpio_pullup: d6-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d6_gpio_pulldown: d6-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AH16) GPIO0_38 */
+			AM65X_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d7_ehrpwm3_a: d7-ehrpwm3-a-pins {
+		pinctrl-single,pins = <
+			/* (AH15) EHRPWM3_A */
+			AM65X_IOPAD(0x00AC, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d7_gpio: d7-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT, 7)
+		>;
+	};
+
+	d7_gpio_pullup: d7-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d7_gpio_pulldown: d7-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AH15) GPIO0_43 */
+			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d8_ehrpwm4_a: d8-ehrpwm4-a-pins {
+		pinctrl-single,pins = <
+			/* (AG15) EHRPWM4_A */
+			AM65X_IOPAD(0x00C0, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d8_gpio: d8-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT, 7)
+		>;
+	};
+
+	d8_gpio_pullup: d8-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d8_gpio_pulldown: d8-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AG15) GPIO0_48 */
+			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+
+	d9_ehrpwm5_a: d9-ehrpwm5-a-pins {
+		pinctrl-single,pins = <
+			/* (AD15) EHRPWM5_A */
+			AM65X_IOPAD(0x00CC, PIN_OUTPUT, 5)
+		>;
+	};
+
+	d9_gpio: d9-gpio-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT, 7)
+		>;
+	};
+
+	d9_gpio_pullup: d9-gpio-pullup-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLUP, 7)
+		>;
+	};
+
+	d9_gpio_pulldown: d9-gpio-pulldown-pins {
+		pinctrl-single,pins = <
+			/* (AD15) GPIO0_51 */
+			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLDOWN, 7)
+		>;
+	};
+};
+
+&main_gpio0 {
+	gpio-line-names =
+		"main_gpio0-base", "", "", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "", "", "", "",
+		"", "", "", "", "", "", "", "", "", "",
+		"", "", "", "IO4", "", "IO5", "", "", "IO6", "",
+		"", "", "", "IO7", "", "", "", "", "IO8", "",
+		"", "IO9";
+};
+
+&wkup_gpio0 {
+	pinctrl-names = "default";
+	pinctrl-0 =
+		<&arduino_i2c_aio_switch_pins_default>,
+		<&arduino_io_oe_pins_default>,
+		<&push_button_pins_default>,
+		<&db9_com_mode_pins_default>;
+	gpio-line-names =
+		/* 0..9 */
+		"wkup_gpio0-base", "", "", "", "UART0-mode1", "UART0-mode0",
+		"UART0-enable", "UART0-terminate", "", "WIFI-disable",
+		/* 10..19 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 20..29 */
+		"", "A4A5-I2C-mux", "", "", "", "USER-button", "", "", "","IO0",
+		/* 30..39 */
+		"IO1", "IO2", "", "IO3", "IO17-direction", "A5",
+		"IO16-direction", "IO15-direction", "IO14-direction", "A3",
+		/* 40..49 */
+		"", "IO18-direction", "A4", "A2", "A1", "A0", "", "", "IO13",
+		"IO11",
+		/* 50..51 */
+		"IO12", "IO10";
+};
+
+&wkup_i2c0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&wkup_i2c0_pins_default>;
+	clock-frequency = <400000>;
+};
+
+&mcu_i2c0 {
+	/* D4200 */
+	pcal9535_1: gpio@20 {
+		compatible = "nxp,pcal9535";
+		reg = <0x20>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-line-names =
+			"A0-pull", "A1-pull", "A2-pull", "A3-pull", "A4-pull",
+			"A5-pull", "", "",
+			"IO14-enable", "IO15-enable", "IO16-enable",
+			"IO17-enable", "IO18-enable", "IO19-enable";
+	};
+
+	/* D4201 */
+	pcal9535_2: gpio@21 {
+		compatible = "nxp,pcal9535";
+		reg = <0x21>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-line-names =
+			"IO0-direction", "IO1-direction", "IO2-direction",
+			"IO3-direction", "IO4-direction", "IO5-direction",
+			"IO6-direction", "IO7-direction",
+			"IO8-direction", "IO9-direction", "IO10-direction",
+			"IO11-direction", "IO12-direction", "IO13-direction",
+			"IO19-direction";
+	};
+
+	/* D4202 */
+	pcal9535_3: gpio@25 {
+		compatible = "nxp,pcal9535";
+		reg = <0x25>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		gpio-line-names =
+			"IO0-pull", "IO1-pull", "IO2-pull", "IO3-pull",
+			"IO4-pull", "IO5-pull", "IO6-pull", "IO7-pull",
+			"IO8-pull", "IO9-pull", "IO10-pull", "IO11-pull",
+			"IO12-pull", "IO13-pull";
+	};
+};
+
+&mcu_uart0 {
+	status = "okay";
+};
+
+&tscadc1 {
+	status = "okay";
+	adc {
+		ti,adc-channels = <0 1 2 3 4 5>;
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
index 1d1979859583..c50a585dd638 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg1.dtsi
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2021-2023
  *
@@ -8,10 +8,7 @@
  * Common bits of the IOT2050 Basic and Advanced variants, PG1
  */
 
-&dss {
-	assigned-clocks = <&k3_clks 67 2>;
-	assigned-clock-parents = <&k3_clks 67 5>;
-};
+#include "k3-am65-iot2050-dp.dtsi"
 
 &serdes0 {
 	status = "disabled";
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
index e9b57b87e42e..e2584a5efe34 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common-pg2.dtsi
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) Siemens AG, 2021
+ * Copyright (c) Siemens AG, 2021-2023
  *
  * Authors:
  *   Chao Zeng <chao.zeng@siemens.com>
@@ -9,6 +9,11 @@
  * Common bits of the IOT2050 Basic and Advanced variants, PG2
  */
 
+&mcu_r5fss0 {
+	/* lock-step mode not supported on PG2 boards */
+	ti,cluster-mode = <0>;
+};
+
 &main_pmx0 {
 	cp2102n_reset_pin_default: cp2102n-reset-default-pins {
 		pinctrl-single,pins = <
@@ -33,21 +38,3 @@
 	/* Workaround needed to get DP clock of 154Mhz */
 	assigned-clocks = <&k3_clks 67 0>;
 };
-
-&serdes0 {
-	assigned-clocks = <&k3_clks 153 4>, <&serdes0 AM654_SERDES_CMU_REFCLK>;
-	assigned-clock-parents = <&k3_clks 153 7>, <&k3_clks 153 4>;
-};
-
-&dwc3_0 {
-	assigned-clock-parents = <&k3_clks 151 4>,  /* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
-				 <&k3_clks 151 8>;  /* set PIPE3_TXB_CLK to WIZ8B2M4VSB */
-	phys = <&serdes0 PHY_TYPE_USB3 0>;
-	phy-names = "usb3-phy";
-};
-
-&usb0 {
-	maximum-speed = "super-speed";
-	snps,dis-u1-entry-quirk;
-	snps,dis-u2-entry-quirk;
-};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
index 61a634afaa4f..ef34b851e178 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-common.dtsi
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) Siemens AG, 2018-2021
+ * Copyright (c) Siemens AG, 2018-2024
  *
  * Authors:
  *   Le Jin <le.jin@siemens.com>
@@ -9,6 +9,7 @@
  * Common bits of the IOT2050 Basic and Advanced variants, PG1 and PG2
  */
 
+#include <dt-bindings/leds/common.h>
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/net/ti-dp83867.h>
 
@@ -75,6 +76,12 @@
 			alignment = <0x1000>;
 			no-map;
 		};
+
+		/* To reserve the power-on(PON) reason for watchdog reset */
+		wdt_reset_memory_region: wdt-memory@a2200000 {
+			reg = <0x00 0xa2200000 0x00 0x1000>;
+			no-map;
+		};
 	};
 
 	leds {
@@ -82,28 +89,46 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&leds_pins_default>;
 
-		status-led-red {
+		led-0 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_STATUS;
+			label = "status-led-red";
 			gpios = <&wkup_gpio0 32 GPIO_ACTIVE_HIGH>;
 			panic-indicator;
 		};
 
-		status-led-green {
+		led-1 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_STATUS;
+			label = "status-led-green";
 			gpios = <&wkup_gpio0 24 GPIO_ACTIVE_HIGH>;
 		};
 
-		user-led1-red {
+		led-2 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_INDICATOR;
+			label = "user-led1-red";
 			gpios = <&pcal9535_3 14 GPIO_ACTIVE_HIGH>;
 		};
 
-		user-led1-green {
+		led-3 {
+			color = <LED_COLOR_ID_GREEN>;
+			function = LED_FUNCTION_INDICATOR;
+			label = "user-led1-green";
 			gpios = <&pcal9535_2 15 GPIO_ACTIVE_HIGH>;
 		};
 
-		user-led2-red {
+		led-4 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_INDICATOR;
+			label = "user-led2-red";
 			gpios = <&wkup_gpio0 17 GPIO_ACTIVE_HIGH>;
 		};
 
-		user-led2-green {
+		led-5 {
+			color = <LED_COLOR_ID_RED>;
+			function = LED_FUNCTION_INDICATOR;
+			label = "user-led2-green";
 			gpios = <&wkup_gpio0 22 GPIO_ACTIVE_HIGH>;
 		};
 	};
@@ -186,434 +211,6 @@
 };
 
 &wkup_pmx0 {
-	pinctrl-names =
-		"default",
-		"d0-uart0-rxd",  "d0-gpio",  "d0-gpio-pullup",  "d0-gpio-pulldown",
-		"d1-uart0-txd",  "d1-gpio",  "d1-gpio-pullup",  "d1-gpio-pulldown",
-		"d2-uart0-ctsn", "d2-gpio",  "d2-gpio-pullup",  "d2-gpio-pulldown",
-		"d3-uart0-rtsn", "d3-gpio",  "d3-gpio-pullup",  "d3-gpio-pulldown",
-		"d10-spi0-cs0",  "d10-gpio", "d10-gpio-pullup", "d10-gpio-pulldown",
-		"d11-spi0-d0",   "d11-gpio", "d11-gpio-pullup", "d11-gpio-pulldown",
-		"d12-spi0-d1",   "d12-gpio", "d12-gpio-pullup", "d12-gpio-pulldown",
-		"d13-spi0-clk",  "d13-gpio", "d13-gpio-pullup", "d13-gpio-pulldown",
-		"a0-gpio", "a0-gpio-pullup", "a0-gpio-pulldown",
-		"a1-gpio", "a1-gpio-pullup", "a1-gpio-pulldown",
-		"a2-gpio", "a2-gpio-pullup", "a2-gpio-pulldown",
-		"a3-gpio", "a3-gpio-pullup", "a3-gpio-pulldown",
-		"a4-gpio", "a4-gpio-pullup", "a4-gpio-pulldown",
-		"a5-gpio", "a5-gpio-pullup", "a5-gpio-pulldown";
-
-	pinctrl-0 = <&d0_uart0_rxd>;
-	pinctrl-1 = <&d0_uart0_rxd>;
-	pinctrl-2 = <&d0_gpio>;
-	pinctrl-3 = <&d0_gpio_pullup>;
-	pinctrl-4 = <&d0_gpio_pulldown>;
-	pinctrl-5 = <&d1_uart0_txd>;
-	pinctrl-6 = <&d1_gpio>;
-	pinctrl-7 = <&d1_gpio_pullup>;
-	pinctrl-8 = <&d1_gpio_pulldown>;
-	pinctrl-9 = <&d2_uart0_ctsn>;
-	pinctrl-10 = <&d2_gpio>;
-	pinctrl-11 = <&d2_gpio_pullup>;
-	pinctrl-12 = <&d2_gpio_pulldown>;
-	pinctrl-13 = <&d3_uart0_rtsn>;
-	pinctrl-14 = <&d3_gpio>;
-	pinctrl-15 = <&d3_gpio_pullup>;
-	pinctrl-16 = <&d3_gpio_pulldown>;
-	pinctrl-17 = <&d10_spi0_cs0>;
-	pinctrl-18 = <&d10_gpio>;
-	pinctrl-19 = <&d10_gpio_pullup>;
-	pinctrl-20 = <&d10_gpio_pulldown>;
-	pinctrl-21 = <&d11_spi0_d0>;
-	pinctrl-22 = <&d11_gpio>;
-	pinctrl-23 = <&d11_gpio_pullup>;
-	pinctrl-24 = <&d11_gpio_pulldown>;
-	pinctrl-25 = <&d12_spi0_d1>;
-	pinctrl-26 = <&d12_gpio>;
-	pinctrl-27 = <&d12_gpio_pullup>;
-	pinctrl-28 = <&d12_gpio_pulldown>;
-	pinctrl-29 = <&d13_spi0_clk>;
-	pinctrl-30 = <&d13_gpio>;
-	pinctrl-31 = <&d13_gpio_pullup>;
-	pinctrl-32 = <&d13_gpio_pulldown>;
-	pinctrl-33 = <&a0_gpio>;
-	pinctrl-34 = <&a0_gpio_pullup>;
-	pinctrl-35 = <&a0_gpio_pulldown>;
-	pinctrl-36 = <&a1_gpio>;
-	pinctrl-37 = <&a1_gpio_pullup>;
-	pinctrl-38 = <&a1_gpio_pulldown>;
-	pinctrl-39 = <&a2_gpio>;
-	pinctrl-40 = <&a2_gpio_pullup>;
-	pinctrl-41 = <&a2_gpio_pulldown>;
-	pinctrl-42 = <&a3_gpio>;
-	pinctrl-43 = <&a3_gpio_pullup>;
-	pinctrl-44 = <&a3_gpio_pulldown>;
-	pinctrl-45 = <&a4_gpio>;
-	pinctrl-46 = <&a4_gpio_pullup>;
-	pinctrl-47 = <&a4_gpio_pulldown>;
-	pinctrl-48 = <&a5_gpio>;
-	pinctrl-49 = <&a5_gpio_pullup>;
-	pinctrl-50 = <&a5_gpio_pulldown>;
-
-	d0_uart0_rxd: d0-uart0-rxd-pins {
-		pinctrl-single,pins = <
-			/* (P4) MCU_UART0_RXD */
-			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 4)
-		>;
-	};
-
-	d0_gpio: d0-gpio-pins {
-		pinctrl-single,pins = <
-			/* (P4) WKUP_GPIO0_29 */
-			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 7)
-		>;
-	};
-
-	d0_gpio_pullup: d0-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (P4) WKUP_GPIO0_29 */
-			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d0_gpio_pulldown: d0-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (P4) WKUP_GPIO0_29 */
-			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d1_uart0_txd: d1-uart0-txd-pins {
-		pinctrl-single,pins = <
-			/* (P5) MCU_UART0_TXD */
-			AM65X_WKUP_IOPAD(0x0048, PIN_OUTPUT, 4)
-		>;
-	};
-
-	d1_gpio: d1-gpio-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_30 */
-			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
-		>;
-	};
-
-	d1_gpio_pullup: d1-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_30 */
-			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)
-		>;
-	};
-
-	d1_gpio_pulldown: d1-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_30 */
-			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d2_uart0_ctsn: d2-uart0-ctsn-pins {
-		pinctrl-single,pins = <
-			/* (P1) MCU_UART0_CTSn */
-			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 4)
-		>;
-	};
-
-	d2_gpio: d2-gpio-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_31 */
-			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
-		>;
-	};
-
-	d2_gpio_pullup: d2-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_31 */
-			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT, 7)
-		>;
-	};
-
-	d2_gpio_pulldown: d2-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (P5) WKUP_GPIO0_31 */
-			AM65X_WKUP_IOPAD(0x004C, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d3_uart0_rtsn: d3-uart0-rtsn-pins {
-		pinctrl-single,pins = <
-			/* (N3) MCU_UART0_RTSn */
-			AM65X_WKUP_IOPAD(0x0054, PIN_OUTPUT, 4)
-		>;
-	};
-
-	d3_gpio: d3-gpio-pins {
-		pinctrl-single,pins = <
-			/* (N3) WKUP_GPIO0_33 */
-			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
-		>;
-	};
-
-	d3_gpio_pullup: d3-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (N3) WKUP_GPIO0_33 */
-			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT, 7)
-		>;
-	};
-
-	d3_gpio_pulldown: d3-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (N3) WKUP_GPIO0_33 */
-			AM65X_WKUP_IOPAD(0x0054, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d10_spi0_cs0: d10-spi0-cs0-pins {
-		pinctrl-single,pins = <
-			/* (Y4) MCU_SPI0_CS0 */
-			AM65X_WKUP_IOPAD(0x009c, PIN_OUTPUT, 0)
-		>;
-	};
-
-	d10_gpio: d10-gpio-pins {
-		pinctrl-single,pins = <
-			/* (Y4) WKUP_GPIO0_51 */
-			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
-		>;
-	};
-
-	d10_gpio_pullup: d10-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (Y4) WKUP_GPIO0_51 */
-			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT, 7)
-		>;
-	};
-
-	d10_gpio_pulldown: d10-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (Y4) WKUP_GPIO0_51 */
-			AM65X_WKUP_IOPAD(0x009c, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d11_spi0_d0: d11-spi0-d0-pins {
-		pinctrl-single,pins = <
-			/* (Y3) MCU_SPI0_D0 */
-			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 0)
-		>;
-	};
-
-	d11_gpio: d11-gpio-pins {
-		pinctrl-single,pins = <
-			/* (Y3) WKUP_GPIO0_49 */
-			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
-		>;
-	};
-
-	d11_gpio_pullup: d11-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (Y3) WKUP_GPIO0_49 */
-			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT, 7)
-		>;
-	};
-
-	d11_gpio_pulldown: d11-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (Y3) WKUP_GPIO0_49 */
-			AM65X_WKUP_IOPAD(0x0094, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d12_spi0_d1: d12-spi0-d1-pins {
-		pinctrl-single,pins = <
-			/* (Y2) MCU_SPI0_D1 */
-			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 0)
-		>;
-	};
-
-	d12_gpio: d12-gpio-pins {
-		pinctrl-single,pins = <
-			/* (Y2) WKUP_GPIO0_50 */
-			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
-		>;
-	};
-
-	d12_gpio_pullup: d12-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (Y2) WKUP_GPIO0_50 */
-			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT, 7)
-		>;
-	};
-
-	d12_gpio_pulldown: d12-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (Y2) WKUP_GPIO0_50 */
-			AM65X_WKUP_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d13_spi0_clk: d13-spi0-clk-pins {
-		pinctrl-single,pins = <
-			/* (Y1) MCU_SPI0_CLK */
-			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 0)
-		>;
-	};
-
-	d13_gpio: d13-gpio-pins {
-		pinctrl-single,pins = <
-			/* (Y1) WKUP_GPIO0_48 */
-			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
-		>;
-	};
-
-	d13_gpio_pullup: d13-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (Y1) WKUP_GPIO0_48 */
-			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT, 7)
-		>;
-	};
-
-	d13_gpio_pulldown: d13-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (Y1) WKUP_GPIO0_48 */
-			AM65X_WKUP_IOPAD(0x0090, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a0_gpio: a0-gpio-pins {
-		pinctrl-single,pins = <
-			/* (L6) WKUP_GPIO0_45 */
-			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
-		>;
-	};
-
-	a0_gpio_pullup: a0-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (L6) WKUP_GPIO0_45 */
-			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT, 7)
-		>;
-	};
-
-	a0_gpio_pulldown: a0-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (L6) WKUP_GPIO0_45 */
-			AM65X_WKUP_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a1_gpio: a1-gpio-pins {
-		pinctrl-single,pins = <
-			/* (M6) WKUP_GPIO0_44 */
-			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
-		>;
-	};
-
-	a1_gpio_pullup: a1-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (M6) WKUP_GPIO0_44 */
-			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT, 7)
-		>;
-	};
-
-	a1_gpio_pulldown: a1-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (M6) WKUP_GPIO0_44 */
-			AM65X_WKUP_IOPAD(0x0080, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a2_gpio: a2-gpio-pins {
-		pinctrl-single,pins = <
-			/* (L5) WKUP_GPIO0_43 */
-			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
-		>;
-	};
-
-	a2_gpio_pullup: a2-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (L5) WKUP_GPIO0_43 */
-			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT, 7)
-		>;
-	};
-
-	a2_gpio_pulldown: a2-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (L5) WKUP_GPIO0_43 */
-			AM65X_WKUP_IOPAD(0x007C, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a3_gpio: a3-gpio-pins {
-		pinctrl-single,pins = <
-			/* (M5) WKUP_GPIO0_39 */
-			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
-		>;
-	};
-
-	a3_gpio_pullup: a3-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (M5) WKUP_GPIO0_39 */
-			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT, 7)
-		>;
-	};
-
-	a3_gpio_pulldown: a3-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (M5) WKUP_GPIO0_39 */
-			AM65X_WKUP_IOPAD(0x006C, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a4_gpio: a4-gpio-pins {
-		pinctrl-single,pins = <
-			/* (L2) WKUP_GPIO0_42 */
-			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
-		>;
-	};
-
-	a4_gpio_pullup: a4-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (L2) WKUP_GPIO0_42 */
-			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT, 7)
-		>;
-	};
-
-	a4_gpio_pulldown: a4-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (L2) WKUP_GPIO0_42 */
-			AM65X_WKUP_IOPAD(0x0078, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	a5_gpio: a5-gpio-pins {
-		pinctrl-single,pins = <
-			/* (N5) WKUP_GPIO0_35 */
-			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT, 7)
-		>;
-	};
-
-	a5_gpio_pullup: a5-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (N5) WKUP_GPIO0_35 */
-			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	a5_gpio_pulldown: a5-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (N5) WKUP_GPIO0_35 */
-			AM65X_WKUP_IOPAD(0x005C, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	wkup_i2c0_pins_default: wkup-i2c0-default-pins {
-		pinctrl-single,pins = <
-			/* (AC7) WKUP_I2C0_SCL */
-			AM65X_WKUP_IOPAD(0x00e0, PIN_INPUT,  0)
-			/* (AD6) WKUP_I2C0_SDA */
-			AM65X_WKUP_IOPAD(0x00e4, PIN_INPUT,  0)
-		>;
-	};
-
 	mcu_i2c0_pins_default: mcu-i2c0-default-pins {
 		pinctrl-single,pins = <
 			/* (AD8) MCU_I2C0_SCL */
@@ -623,13 +220,6 @@
 		>;
 	};
 
-	arduino_i2c_aio_switch_pins_default: arduino-i2c-aio-switch-default-pins {
-		pinctrl-single,pins = <
-			/* (R2) WKUP_GPIO0_21 */
-			AM65X_WKUP_IOPAD(0x0024, PIN_OUTPUT, 7)
-		>;
-	};
-
 	push_button_pins_default: push-button-default-pins {
 		pinctrl-single,pins = <
 			/* (T1) MCU_OSPI1_CLK.WKUP_GPIO0_25 */
@@ -637,22 +227,6 @@
 		>;
 	};
 
-
-	arduino_io_oe_pins_default: arduino-io-oe-default-pins {
-		pinctrl-single,pins = <
-			/* (N4) WKUP_GPIO0_34 */
-			AM65X_WKUP_IOPAD(0x0058, PIN_OUTPUT, 7)
-			/* (M2) WKUP_GPIO0_36 */
-			AM65X_WKUP_IOPAD(0x0060, PIN_OUTPUT, 7)
-			/* (M3) WKUP_GPIO0_37 */
-			AM65X_WKUP_IOPAD(0x0064, PIN_OUTPUT, 7)
-			/* (M4) WKUP_GPIO0_38 */
-			AM65X_WKUP_IOPAD(0x0068, PIN_OUTPUT, 7)
-			/* (M1) WKUP_GPIO0_41 */
-			AM65X_WKUP_IOPAD(0x0074, PIN_OUTPUT, 7)
-		>;
-	};
-
 	mcu_fss0_ospi0_pins_default: mcu-fss0-ospi0-default-pins {
 		pinctrl-single,pins = <
 			/* (V1) MCU_OSPI0_CLK */
@@ -716,214 +290,6 @@
 };
 
 &main_pmx0 {
-	pinctrl-names =
-		"default",
-		"d4-ehrpwm0-a", "d4-gpio", "d4-gpio-pullup", "d4-gpio-pulldown",
-		"d5-ehrpwm1-a", "d5-gpio", "d5-gpio-pullup", "d5-gpio-pulldown",
-		"d6-ehrpwm2-a", "d6-gpio", "d6-gpio-pullup", "d6-gpio-pulldown",
-		"d7-ehrpwm3-a", "d7-gpio", "d7-gpio-pullup", "d7-gpio-pulldown",
-		"d8-ehrpwm4-a", "d8-gpio", "d8-gpio-pullup", "d8-gpio-pulldown",
-		"d9-ehrpwm5-a", "d9-gpio", "d9-gpio-pullup", "d9-gpio-pulldown";
-
-	pinctrl-0 = <&d4_ehrpwm0_a>;
-	pinctrl-1 = <&d4_ehrpwm0_a>;
-	pinctrl-2 = <&d4_gpio>;
-	pinctrl-3 = <&d4_gpio_pullup>;
-	pinctrl-4 = <&d4_gpio_pulldown>;
-
-	pinctrl-5 = <&d5_ehrpwm1_a>;
-	pinctrl-6 = <&d5_gpio>;
-	pinctrl-7 = <&d5_gpio_pullup>;
-	pinctrl-8 = <&d5_gpio_pulldown>;
-
-	pinctrl-9 = <&d6_ehrpwm2_a>;
-	pinctrl-10 = <&d6_gpio>;
-	pinctrl-11 = <&d6_gpio_pullup>;
-	pinctrl-12 = <&d6_gpio_pulldown>;
-
-	pinctrl-13 = <&d7_ehrpwm3_a>;
-	pinctrl-14 = <&d7_gpio>;
-	pinctrl-15 = <&d7_gpio_pullup>;
-	pinctrl-16 = <&d7_gpio_pulldown>;
-
-	pinctrl-17 = <&d8_ehrpwm4_a>;
-	pinctrl-18 = <&d8_gpio>;
-	pinctrl-19 = <&d8_gpio_pullup>;
-	pinctrl-20 = <&d8_gpio_pulldown>;
-
-	pinctrl-21 = <&d9_ehrpwm5_a>;
-	pinctrl-22 = <&d9_gpio>;
-	pinctrl-23 = <&d9_gpio_pullup>;
-	pinctrl-24 = <&d9_gpio_pulldown>;
-
-	d4_ehrpwm0_a: d4-ehrpwm0-a-pins {
-		pinctrl-single,pins = <
-			/* (AG18) EHRPWM0_A */
-			AM65X_IOPAD(0x0084, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d4_gpio: d4-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AG18) GPIO0_33 */
-			AM65X_IOPAD(0x0084, PIN_INPUT, 7)
-		>;
-	};
-
-	d4_gpio_pullup: d4-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AG18) GPIO0_33 */
-			AM65X_IOPAD(0x0084, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d4_gpio_pulldown: d4-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AG18) GPIO0_33 */
-			AM65X_IOPAD(0x0084, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d5_ehrpwm1_a: d5-ehrpwm1-a-pins {
-		pinctrl-single,pins = <
-			/* (AF17) EHRPWM1_A */
-			AM65X_IOPAD(0x008C, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d5_gpio: d5-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AF17) GPIO0_35 */
-			AM65X_IOPAD(0x008C, PIN_INPUT, 7)
-		>;
-	};
-
-	d5_gpio_pullup: d5-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AF17) GPIO0_35 */
-			AM65X_IOPAD(0x008C, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d5_gpio_pulldown: d5-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AF17) GPIO0_35 */
-			AM65X_IOPAD(0x008C, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d6_ehrpwm2_a: d6-ehrpwm2-a-pins {
-		pinctrl-single,pins = <
-			/* (AH16) EHRPWM2_A */
-			AM65X_IOPAD(0x0098, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d6_gpio: d6-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AH16) GPIO0_38 */
-			AM65X_IOPAD(0x0098, PIN_INPUT, 7)
-		>;
-	};
-
-	d6_gpio_pullup: d6-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AH16) GPIO0_38 */
-			AM65X_IOPAD(0x0098, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d6_gpio_pulldown: d6-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AH16) GPIO0_38 */
-			AM65X_IOPAD(0x0098, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d7_ehrpwm3_a: d7-ehrpwm3-a-pins {
-		pinctrl-single,pins = <
-			/* (AH15) EHRPWM3_A */
-			AM65X_IOPAD(0x00AC, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d7_gpio: d7-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AH15) GPIO0_43 */
-			AM65X_IOPAD(0x00AC, PIN_INPUT, 7)
-		>;
-	};
-
-	d7_gpio_pullup: d7-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AH15) GPIO0_43 */
-			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d7_gpio_pulldown: d7-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AH15) GPIO0_43 */
-			AM65X_IOPAD(0x00AC, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d8_ehrpwm4_a: d8-ehrpwm4-a-pins {
-		pinctrl-single,pins = <
-			/* (AG15) EHRPWM4_A */
-			AM65X_IOPAD(0x00C0, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d8_gpio: d8-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AG15) GPIO0_48 */
-			AM65X_IOPAD(0x00C0, PIN_INPUT, 7)
-		>;
-	};
-
-	d8_gpio_pullup: d8-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AG15) GPIO0_48 */
-			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d8_gpio_pulldown: d8-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AG15) GPIO0_48 */
-			AM65X_IOPAD(0x00C0, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
-	d9_ehrpwm5_a: d9-ehrpwm5-a-pins {
-		pinctrl-single,pins = <
-			/* (AD15) EHRPWM5_A */
-			AM65X_IOPAD(0x00CC, PIN_OUTPUT, 5)
-		>;
-	};
-
-	d9_gpio: d9-gpio-pins {
-		pinctrl-single,pins = <
-			/* (AD15) GPIO0_51 */
-			AM65X_IOPAD(0x00CC, PIN_INPUT, 7)
-		>;
-	};
-
-	d9_gpio_pullup: d9-gpio-pullup-pins {
-		pinctrl-single,pins = <
-			/* (AD15) GPIO0_51 */
-			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLUP, 7)
-		>;
-	};
-
-	d9_gpio_pulldown: d9-gpio-pulldown-pins {
-		pinctrl-single,pins = <
-			/* (AD15) GPIO0_51 */
-			AM65X_IOPAD(0x00CC, PIN_INPUT_PULLDOWN, 7)
-		>;
-	};
-
 	main_pcie_enable_pins_default: main-pcie-enable-default-pins {
 		pinctrl-single,pins = <
 			AM65X_IOPAD(0x01c4, PIN_INPUT_PULLUP, 7)  /* (AH13) GPIO1_17 */
@@ -971,45 +337,6 @@
 		>;
 	};
 
-	dss_vout1_pins_default: dss-vout1-default-pins {
-		pinctrl-single,pins = <
-			AM65X_IOPAD(0x0000, PIN_OUTPUT, 1)  /* VOUT1_DATA0 */
-			AM65X_IOPAD(0x0004, PIN_OUTPUT, 1)  /* VOUT1_DATA1 */
-			AM65X_IOPAD(0x0008, PIN_OUTPUT, 1)  /* VOUT1_DATA2 */
-			AM65X_IOPAD(0x000c, PIN_OUTPUT, 1)  /* VOUT1_DATA3 */
-			AM65X_IOPAD(0x0010, PIN_OUTPUT, 1)  /* VOUT1_DATA4 */
-			AM65X_IOPAD(0x0014, PIN_OUTPUT, 1)  /* VOUT1_DATA5 */
-			AM65X_IOPAD(0x0018, PIN_OUTPUT, 1)  /* VOUT1_DATA6 */
-			AM65X_IOPAD(0x001c, PIN_OUTPUT, 1)  /* VOUT1_DATA7 */
-			AM65X_IOPAD(0x0020, PIN_OUTPUT, 1)  /* VOUT1_DATA8 */
-			AM65X_IOPAD(0x0024, PIN_OUTPUT, 1)  /* VOUT1_DATA9 */
-			AM65X_IOPAD(0x0028, PIN_OUTPUT, 1)  /* VOUT1_DATA10 */
-			AM65X_IOPAD(0x002c, PIN_OUTPUT, 1)  /* VOUT1_DATA11 */
-			AM65X_IOPAD(0x0030, PIN_OUTPUT, 1)  /* VOUT1_DATA12 */
-			AM65X_IOPAD(0x0034, PIN_OUTPUT, 1)  /* VOUT1_DATA13 */
-			AM65X_IOPAD(0x0038, PIN_OUTPUT, 1)  /* VOUT1_DATA14 */
-			AM65X_IOPAD(0x003c, PIN_OUTPUT, 1)  /* VOUT1_DATA15 */
-			AM65X_IOPAD(0x0040, PIN_OUTPUT, 1)  /* VOUT1_DATA16 */
-			AM65X_IOPAD(0x0044, PIN_OUTPUT, 1)  /* VOUT1_DATA17 */
-			AM65X_IOPAD(0x0048, PIN_OUTPUT, 1)  /* VOUT1_DATA18 */
-			AM65X_IOPAD(0x004c, PIN_OUTPUT, 1)  /* VOUT1_DATA19 */
-			AM65X_IOPAD(0x0050, PIN_OUTPUT, 1)  /* VOUT1_DATA20 */
-			AM65X_IOPAD(0x0054, PIN_OUTPUT, 1)  /* VOUT1_DATA21 */
-			AM65X_IOPAD(0x0058, PIN_OUTPUT, 1)  /* VOUT1_DATA22 */
-			AM65X_IOPAD(0x005c, PIN_OUTPUT, 1)  /* VOUT1_DATA23 */
-			AM65X_IOPAD(0x0060, PIN_OUTPUT, 1)  /* VOUT1_VSYNC */
-			AM65X_IOPAD(0x0064, PIN_OUTPUT, 1)  /* VOUT1_HSYNC */
-			AM65X_IOPAD(0x0068, PIN_OUTPUT, 1)  /* VOUT1_PCLK */
-			AM65X_IOPAD(0x006c, PIN_OUTPUT, 1)  /* VOUT1_DE */
-		>;
-	};
-
-	dp_pins_default: dp-default-pins {
-		pinctrl-single,pins = <
-			AM65X_IOPAD(0x0078, PIN_OUTPUT, 7)  /* (AF18) DP rst_n */
-		>;
-	};
-
 	main_i2c2_pins_default: main-i2c2-default-pins {
 		pinctrl-single,pins = <
 			AM65X_IOPAD(0x0074, PIN_INPUT,  5)  /* (T27) I2C2_SCL */
@@ -1082,57 +409,11 @@
 	pinctrl-0 = <&main_uart1_pins_default>;
 };
 
-&mcu_uart0 {
-	status = "okay";
-};
-
-&main_gpio0 {
-	gpio-line-names =
-		"main_gpio0-base", "", "", "", "", "", "", "", "", "",
-		"", "", "", "", "", "", "", "", "", "",
-		"", "", "", "", "", "", "", "", "", "",
-		"", "", "", "IO4", "", "IO5", "", "", "IO6", "",
-		"", "", "", "IO7", "", "", "", "", "IO8", "",
-		"", "IO9";
-};
-
 &main_gpio1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_pcie_enable_pins_default>;
 };
 
-&wkup_gpio0 {
-	pinctrl-names = "default";
-	pinctrl-0 =
-		<&arduino_i2c_aio_switch_pins_default>,
-		<&arduino_io_oe_pins_default>,
-		<&push_button_pins_default>,
-		<&db9_com_mode_pins_default>;
-	gpio-line-names =
-		/* 0..9 */
-		"wkup_gpio0-base", "", "", "", "UART0-mode1", "UART0-mode0",
-		"UART0-enable", "UART0-terminate", "", "WIFI-disable",
-		/* 10..19 */
-		"", "", "", "", "", "", "", "", "", "",
-		/* 20..29 */
-		"", "A4A5-I2C-mux", "", "", "", "USER-button", "", "", "","IO0",
-		/* 30..39 */
-		"IO1", "IO2", "", "IO3", "IO17-direction", "A5",
-		"IO16-direction", "IO15-direction", "IO14-direction", "A3",
-		/* 40..49 */
-		"", "IO18-direction", "A4", "A2", "A1", "A0", "", "", "IO13",
-		"IO11",
-		/* 50..51 */
-		"IO12", "IO10";
-};
-
-&wkup_i2c0 {
-	status = "okay";
-	pinctrl-names = "default";
-	pinctrl-0 = <&wkup_i2c0_pins_default>;
-	clock-frequency = <400000>;
-};
-
 &mcu_i2c0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -1150,47 +431,6 @@
 		ti,vsel1-state-high;
 		ti,enable-vout-discharge;
 	};
-
-	/* D4200 */
-	pcal9535_1: gpio@20 {
-		compatible = "nxp,pcal9535";
-		reg = <0x20>;
-		#gpio-cells = <2>;
-		gpio-controller;
-		gpio-line-names =
-			"A0-pull", "A1-pull", "A2-pull", "A3-pull", "A4-pull",
-			"A5-pull", "", "",
-			"IO14-enable", "IO15-enable", "IO16-enable",
-			"IO17-enable", "IO18-enable", "IO19-enable";
-	};
-
-	/* D4201 */
-	pcal9535_2: gpio@21 {
-		compatible = "nxp,pcal9535";
-		reg = <0x21>;
-		#gpio-cells = <2>;
-		gpio-controller;
-		gpio-line-names =
-			"IO0-direction", "IO1-direction", "IO2-direction",
-			"IO3-direction", "IO4-direction", "IO5-direction",
-			"IO6-direction", "IO7-direction",
-			"IO8-direction", "IO9-direction", "IO10-direction",
-			"IO11-direction", "IO12-direction", "IO13-direction",
-			"IO19-direction";
-	};
-
-	/* D4202 */
-	pcal9535_3: gpio@25 {
-		compatible = "nxp,pcal9535";
-		reg = <0x25>;
-		#gpio-cells = <2>;
-		gpio-controller;
-		gpio-line-names =
-			"IO0-pull", "IO1-pull", "IO2-pull", "IO3-pull",
-			"IO4-pull", "IO5-pull", "IO6-pull", "IO7-pull",
-			"IO8-pull", "IO9-pull", "IO10-pull", "IO11-pull",
-			"IO12-pull", "IO13-pull";
-	};
 };
 
 &main_i2c0 {
@@ -1233,32 +473,6 @@
 
 	#address-cells = <1>;
 	#size-cells = <0>;
-
-	edp-bridge@f {
-		compatible = "toshiba,tc358767";
-		reg = <0x0f>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&dp_pins_default>;
-		reset-gpios = <&main_gpio0 30 GPIO_ACTIVE_HIGH>;
-
-		clock-names = "ref";
-		clocks = <&dp_refclk>;
-
-		toshiba,hpd-pin = <0>;
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@1 {
-				reg = <1>;
-
-				bridge_in: endpoint {
-					remote-endpoint = <&dpi_out>;
-				};
-			};
-		};
-	};
 };
 
 &mcu_cpsw {
@@ -1292,13 +506,6 @@
 	ti,pindir-d0-out-d1-in;
 };
 
-&tscadc1 {
-	status = "okay";
-	adc {
-		ti,adc-channels = <0 1 2 3 4 5>;
-	};
-};
-
 &ospi0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -1364,26 +571,6 @@
 	};
 };
 
-&dss {
-	pinctrl-names = "default";
-	pinctrl-0 = <&dss_vout1_pins_default>;
-
-	assigned-clocks = <&k3_clks 67 2>;
-	assigned-clock-parents = <&k3_clks 67 5>;
-};
-
-&dss_ports {
-	#address-cells = <1>;
-	#size-cells = <0>;
-	port@1 {
-		reg = <1>;
-
-		dpi_out: endpoint {
-			remote-endpoint = <&bridge_in>;
-		};
-	};
-};
-
 &pcie1_rc {
 	status = "okay";
 	pinctrl-names = "default";
@@ -1418,13 +605,17 @@
 &mcu_r5fss0_core0 {
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 };
 
 &mcu_r5fss0_core1 {
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
-	mboxes = <&mailbox0_cluster1>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_mcu_r5fss0_core1>;
+};
+
+&mcu_rti1 {
+	memory-region = <&wdt_reset_memory_region>;
 };
 
 &icssg0_mdio {
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-dp.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-dp.dtsi
new file mode 100644
index 000000000000..984cc80913bc
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-dp.dtsi
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Siemens AG, 2024
+ *
+ * Authors:
+ *   Jan Kiszka <jan.kiszka@siemens.com>
+ *
+ * Common bits for IOT2050 variants with Display Port
+ */
+
+&main_pmx0 {
+	dss_vout1_pins_default: dss-vout1-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x0000, PIN_OUTPUT, 1)  /* VOUT1_DATA0 */
+			AM65X_IOPAD(0x0004, PIN_OUTPUT, 1)  /* VOUT1_DATA1 */
+			AM65X_IOPAD(0x0008, PIN_OUTPUT, 1)  /* VOUT1_DATA2 */
+			AM65X_IOPAD(0x000c, PIN_OUTPUT, 1)  /* VOUT1_DATA3 */
+			AM65X_IOPAD(0x0010, PIN_OUTPUT, 1)  /* VOUT1_DATA4 */
+			AM65X_IOPAD(0x0014, PIN_OUTPUT, 1)  /* VOUT1_DATA5 */
+			AM65X_IOPAD(0x0018, PIN_OUTPUT, 1)  /* VOUT1_DATA6 */
+			AM65X_IOPAD(0x001c, PIN_OUTPUT, 1)  /* VOUT1_DATA7 */
+			AM65X_IOPAD(0x0020, PIN_OUTPUT, 1)  /* VOUT1_DATA8 */
+			AM65X_IOPAD(0x0024, PIN_OUTPUT, 1)  /* VOUT1_DATA9 */
+			AM65X_IOPAD(0x0028, PIN_OUTPUT, 1)  /* VOUT1_DATA10 */
+			AM65X_IOPAD(0x002c, PIN_OUTPUT, 1)  /* VOUT1_DATA11 */
+			AM65X_IOPAD(0x0030, PIN_OUTPUT, 1)  /* VOUT1_DATA12 */
+			AM65X_IOPAD(0x0034, PIN_OUTPUT, 1)  /* VOUT1_DATA13 */
+			AM65X_IOPAD(0x0038, PIN_OUTPUT, 1)  /* VOUT1_DATA14 */
+			AM65X_IOPAD(0x003c, PIN_OUTPUT, 1)  /* VOUT1_DATA15 */
+			AM65X_IOPAD(0x0040, PIN_OUTPUT, 1)  /* VOUT1_DATA16 */
+			AM65X_IOPAD(0x0044, PIN_OUTPUT, 1)  /* VOUT1_DATA17 */
+			AM65X_IOPAD(0x0048, PIN_OUTPUT, 1)  /* VOUT1_DATA18 */
+			AM65X_IOPAD(0x004c, PIN_OUTPUT, 1)  /* VOUT1_DATA19 */
+			AM65X_IOPAD(0x0050, PIN_OUTPUT, 1)  /* VOUT1_DATA20 */
+			AM65X_IOPAD(0x0054, PIN_OUTPUT, 1)  /* VOUT1_DATA21 */
+			AM65X_IOPAD(0x0058, PIN_OUTPUT, 1)  /* VOUT1_DATA22 */
+			AM65X_IOPAD(0x005c, PIN_OUTPUT, 1)  /* VOUT1_DATA23 */
+			AM65X_IOPAD(0x0060, PIN_OUTPUT, 1)  /* VOUT1_VSYNC */
+			AM65X_IOPAD(0x0064, PIN_OUTPUT, 1)  /* VOUT1_HSYNC */
+			AM65X_IOPAD(0x0068, PIN_OUTPUT, 1)  /* VOUT1_PCLK */
+			AM65X_IOPAD(0x006c, PIN_OUTPUT, 1)  /* VOUT1_DE */
+		>;
+	};
+
+	dp_pins_default: dp-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x0078, PIN_OUTPUT, 7)  /* (AF18) DP rst_n */
+		>;
+	};
+};
+
+&main_i2c3 {
+	edp-bridge@f {
+		compatible = "toshiba,tc358767";
+		reg = <0x0f>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&dp_pins_default>;
+		reset-gpios = <&main_gpio0 30 GPIO_ACTIVE_HIGH>;
+
+		clock-names = "ref";
+		clocks = <&dp_refclk>;
+
+		toshiba,hpd-pin = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@1 {
+				reg = <1>;
+
+				bridge_in: endpoint {
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+		};
+	};
+};
+
+&dss {
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_vout1_pins_default>;
+
+	assigned-clocks = <&k3_clks 67 2>;
+	assigned-clock-parents = <&k3_clks 67 5>;
+};
+
+&dss_ports {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	port@1 {
+		reg = <1>;
+
+		dpi_out: endpoint {
+			remote-endpoint = <&bridge_in>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-iot2050-usb3.dtsi b/arch/arm64/boot/dts/ti/k3-am65-iot2050-usb3.dtsi
new file mode 100644
index 000000000000..e5bd7c301b12
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am65-iot2050-usb3.dtsi
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Siemens AG, 2024
+ *
+ * Authors:
+ *   Jan Kiszka <jan.kiszka@siemens.com>
+ *
+ * Common bits for IOT2050 variants with USB3 support
+ */
+
+&serdes0 {
+	assigned-clocks = <&k3_clks 153 4>, <&serdes0 AM654_SERDES_CMU_REFCLK>;
+	assigned-clock-parents = <&k3_clks 153 7>, <&k3_clks 153 4>;
+};
+
+&dwc3_0 {
+	assigned-clock-parents = <&k3_clks 151 4>,  /* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
+				 <&k3_clks 151 8>;  /* set PIPE3_TXB_CLK to WIZ8B2M4VSB */
+	phys = <&serdes0 PHY_TYPE_USB3 0>;
+	phy-names = "usb3-phy";
+};
+
+&usb0 {
+	maximum-speed = "super-speed";
+	snps,dis-u1-entry-quirk;
+	snps,dis-u2-entry-quirk;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
index fcea54465636..ff857117d719 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM6 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2016-2018 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 #include <dt-bindings/phy/phy-am654-serdes.h>
 
@@ -886,20 +886,6 @@
 		status = "disabled";
 	};
 
-	pcie0_ep: pcie-ep@5500000 {
-		compatible = "ti,am654-pcie-ep";
-		reg = <0x0 0x5500000 0x0 0x1000>, <0x0 0x5501000 0x0 0x1000>, <0x0 0x10000000 0x0 0x8000000>, <0x0 0x5506000 0x0 0x1000>;
-		reg-names = "app", "dbics", "addr_space", "atu";
-		power-domains = <&k3_pds 120 TI_SCI_PD_EXCLUSIVE>;
-		ti,syscon-pcie-mode = <&scm_conf 0x4060>;
-		num-ib-windows = <16>;
-		num-ob-windows = <16>;
-		max-link-speed = <2>;
-		dma-coherent;
-		interrupts = <GIC_SPI 340 IRQ_TYPE_EDGE_RISING>;
-		status = "disabled";
-	};
-
 	pcie1_rc: pcie@5600000 {
 		compatible = "ti,am654-pcie-rc";
 		reg = <0x0 0x5600000 0x0 0x1000>, <0x0 0x5601000 0x0 0x1000>, <0x0 0x18000000 0x0 0x2000>, <0x0 0x5606000 0x0 0x1000>;
@@ -921,20 +907,6 @@
 		status = "disabled";
 	};
 
-	pcie1_ep: pcie-ep@5600000 {
-		compatible = "ti,am654-pcie-ep";
-		reg = <0x0 0x5600000 0x0 0x1000>, <0x0 0x5601000 0x0 0x1000>, <0x0 0x18000000 0x0 0x4000000>, <0x0 0x5606000 0x0 0x1000>;
-		reg-names = "app", "dbics", "addr_space", "atu";
-		power-domains = <&k3_pds 121 TI_SCI_PD_EXCLUSIVE>;
-		ti,syscon-pcie-mode = <&scm_conf 0x4070>;
-		num-ib-windows = <16>;
-		num-ob-windows = <16>;
-		max-link-speed = <2>;
-		dma-coherent;
-		interrupts = <GIC_SPI 355 IRQ_TYPE_EDGE_RISING>;
-		status = "disabled";
-	};
-
 	mcasp0: mcasp@2b00000 {
 		compatible = "ti,am33xx-mcasp-audio";
 		reg = <0x0 0x02b00000 0x0 0x2000>,
@@ -1019,9 +991,10 @@
 		      <0x0 0x04a07000 0x0 0x1000>, /* ovr1 */
 		      <0x0 0x04a08000 0x0 0x1000>, /* ovr2 */
 		      <0x0 0x04a0a000 0x0 0x1000>, /* vp1 */
-		      <0x0 0x04a0b000 0x0 0x1000>; /* vp2 */
+		      <0x0 0x04a0b000 0x0 0x1000>, /* vp2 */
+		      <0x0 0x04a01000 0x0 0x1000>; /* common1 */
 		reg-names = "common", "vidl1", "vid",
-			"ovr1", "ovr2", "vp1", "vp2";
+			"ovr1", "ovr2", "vp1", "vp2", "common1";
 
 		ti,am65x-oldi-io-ctrl = <&dss_oldi_io_ctrl>;
 
@@ -1050,6 +1023,13 @@
 		};
 	};
 
+	gpu: gpu@7000000 {
+		compatible = "ti,am6548-gpu", "img,powervr-sgx544";
+		reg = <0x0 0x7000000 0x0 0x10000>;
+		interrupts = <GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>;
+		power-domains = <&k3_pds 65 TI_SCI_PD_EXCLUSIVE>;
+	};
+
 	ehrpwm0: pwm@3000000 {
 		compatible = "ti,am654-ehrpwm", "ti,am3352-ehrpwm";
 		#pwm-cells = <3>;
diff --git a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
index ecd7356f3315..6ff3ccc39fb4 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-mcu.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM6 SoC Family MCU Domain peripherals
  *
- * Copyright (C) 2016-2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu {
diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
index f037b36243ce..37527890ddea 100644
--- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM6 SoC Family Wakeup Domain peripherals
  *
- * Copyright (C) 2016-2018 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_wakeup {
diff --git a/arch/arm64/boot/dts/ti/k3-am65.dtsi b/arch/arm64/boot/dts/ti/k3-am65.dtsi
index 4d7b6155a76b..c59baebc5a25 100644
--- a/arch/arm64/boot/dts/ti/k3-am65.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am65.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM6 SoC Family
  *
- * Copyright (C) 2016-2018 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/gpio/gpio.h>
diff --git a/arch/arm64/boot/dts/ti/k3-am652.dtsi b/arch/arm64/boot/dts/ti/k3-am652.dtsi
index 0f22e00faa90..cbb3caaf82c3 100644
--- a/arch/arm64/boot/dts/ti/k3-am652.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am652.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM65 SoC family in Dual core configuration
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include "k3-am65.dtsi"
diff --git a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
index 1d6cddb11991..eed6fe70d297 100644
--- a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-common.dtsi
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2021
  *
@@ -11,6 +11,7 @@
 
 #include "k3-am652.dtsi"
 #include "k3-am65-iot2050-common.dtsi"
+#include "k3-am65-iot2050-arduino-connector.dtsi"
 
 / {
 	memory@80000000 {
@@ -40,8 +41,3 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&main_uart0_pins_default>;
 };
-
-&mcu_r5fss0 {
-	/* lock-step mode not supported on Basic boards */
-	ti,cluster-mode = <0>;
-};
diff --git a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-pg2.dts b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-pg2.dts
index c62549a4b436..c1faf9497b63 100644
--- a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-pg2.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic-pg2.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2021
  *
@@ -17,6 +17,8 @@
 
 #include "k3-am6528-iot2050-basic-common.dtsi"
 #include "k3-am65-iot2050-common-pg2.dtsi"
+#include "k3-am65-iot2050-dp.dtsi"
+#include "k3-am65-iot2050-usb3.dtsi"
 
 / {
 	compatible = "siemens,iot2050-basic-pg2", "ti,am654";
diff --git a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic.dts b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic.dts
index 87928ff28214..29a31891b3db 100644
--- a/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6528-iot2050-basic.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2021
  *
@@ -22,3 +22,8 @@
 	compatible = "siemens,iot2050-basic", "ti,am654";
 	model = "SIMATIC IOT2050 Basic";
 };
+
+&mcu_r5fss0 {
+	/* lock-step mode not supported on this board */
+	ti,cluster-mode = <0>;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board-rocktech-rk101-panel.dtso b/arch/arm64/boot/dts/ti/k3-am654-base-board-rocktech-rk101-panel.dtso
index 3be92c39ecba..364c57b3b3a0 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-base-board-rocktech-rk101-panel.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am654-base-board-rocktech-rk101-panel.dtso
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * OLDI-LCD1EVM Rocktech integrated panel and touch DT overlay for AM654-EVM.
  * Panel Link: https://www.digimax.it/en/tft-lcd/20881-RK101II01D-CT
  * AM654 LCD EVM: https://www.ti.com/tool/TMDSLCD1EVM
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
index 822c288d2797..aba0c52b1213 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am654-base-board.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2016-2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -531,13 +531,13 @@
 &mcu_r5fss0_core0 {
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 };
 
 &mcu_r5fss0_core1 {
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
-	mboxes = <&mailbox0_cluster1>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_mcu_r5fss0_core1>;
 };
 
 &ospi0 {
diff --git a/arch/arm64/boot/dts/ti/k3-am654-icssg2.dtso b/arch/arm64/boot/dts/ti/k3-am654-icssg2.dtso
index ec8cf20ca3ac..0a6e75265ba9 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-icssg2.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am654-icssg2.dtso
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT overlay for IDK application board on AM654 EVM
  *
- * Copyright (C) 2018-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2018-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am654-idk.dtso b/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
index 150428dfce6f..8bdb87fcbde0 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
+++ b/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT overlay for IDK application board on AM654 EVM
  *
- * Copyright (C) 2018-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2018-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-am654-industrial-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-am654-industrial-thermal.dtsi
index 9021c738056b..de5a2ed907a7 100644
--- a/arch/arm64/boot/dts/ti/k3-am654-industrial-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am654-industrial-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-am654-pcie-usb2.dtso b/arch/arm64/boot/dts/ti/k3-am654-pcie-usb2.dtso
new file mode 100644
index 000000000000..c3cb752f8cd7
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am654-pcie-usb2.dtso
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/**
+ * DT overlay for SERDES personality card: 2lane PCIe + USB2.0 Host on AM654 EVM
+ *
+ * Copyright (C) 2018-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/phy/phy-am654-serdes.h>
+#include "k3-pinctrl.h"
+
+&serdes0 {
+	assigned-clocks = <&k3_clks 153 4>,
+			  <&serdes0 AM654_SERDES_CMU_REFCLK>,
+			  <&serdes0 AM654_SERDES_RO_REFCLK>;
+	assigned-clock-parents = <&k3_clks 153 8>,
+				 <&k3_clks 153 4>,
+				 <&k3_clks 153 4>;
+	status = "okay";
+};
+
+&serdes1 {
+	assigned-clocks = <&serdes1 AM654_SERDES_CMU_REFCLK>;
+	assigned-clock-parents = <&serdes0 AM654_SERDES_RO_REFCLK>;
+	status = "okay";
+};
+
+&pcie0_rc {
+	num-lanes = <2>;
+	phys = <&serdes0 PHY_TYPE_PCIE 1>, <&serdes1 PHY_TYPE_PCIE 1>;
+	phy-names = "pcie-phy0", "pcie-phy1";
+	reset-gpios = <&pca9555 5 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&main_pmx0 {
+       usb0_pins_default: usb0-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x02bc, PIN_OUTPUT, 0) /* (AD9) USB0_DRVVBUS */
+		>;
+	};
+};
+
+&dwc3_0 {
+	status = "okay";
+};
+
+&usb0_phy {
+	status = "okay";
+};
+
+&usb0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_pins_default>;
+	dr_mode = "host";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am654-pcie-usb3.dtso b/arch/arm64/boot/dts/ti/k3-am654-pcie-usb3.dtso
new file mode 100644
index 000000000000..333e423e8bb6
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am654-pcie-usb3.dtso
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/**
+ * DT overlay for SERDES personality card: 1lane PCIe + USB3.0 DRD on AM654 EVM
+ *
+ * Copyright (C) 2018-2024 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/phy/phy-am654-serdes.h>
+
+#include "k3-pinctrl.h"
+
+&serdes1 {
+	status = "okay";
+};
+
+&pcie1_rc {
+	num-lanes = <1>;
+	phys = <&serdes1 PHY_TYPE_PCIE 0>;
+	phy-names = "pcie-phy0";
+	reset-gpios = <&pca9555 5 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&main_pmx0 {
+	usb0_pins_default: usb0-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x02bc, PIN_OUTPUT, 0) /* (AD9) USB0_DRVVBUS */
+		>;
+	};
+};
+
+&serdes0 {
+	status = "okay";
+	assigned-clocks = <&k3_clks 153 4>, <&serdes0 AM654_SERDES_CMU_REFCLK>;
+	assigned-clock-parents = <&k3_clks 153 7>, <&k3_clks 153 4>;
+};
+
+&dwc3_0 {
+	status = "okay";
+	assigned-clock-parents = <&k3_clks 151 4>,      /* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
+	<&k3_clks 151 8>;      /* set PIPE3_TXB_CLK to WIZ8B2M4VSB */
+	phys = <&serdes0 PHY_TYPE_USB3 0>;
+	phy-names = "usb3-phy";
+};
+
+&usb0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&usb0_pins_default>;
+	dr_mode = "host";
+	maximum-speed = "super-speed";
+	snps,dis-u1-entry-quirk;
+	snps,dis-u2-entry-quirk;
+};
+
+&usb0_phy {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am654.dtsi b/arch/arm64/boot/dts/ti/k3-am654.dtsi
index 888567b921f0..bb77c8454734 100644
--- a/arch/arm64/boot/dts/ti/k3-am654.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am654.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for AM6 SoC family in Quad core configuration
  *
- * Copyright (C) 2016-2018 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include "k3-am65.dtsi"
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
index 3864ec54e371..ae842b85b70d 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-common.dtsi
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2021
  *
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
index bd6f2e696e94..cc619bbec181 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-m2.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2023
  *
@@ -15,17 +15,14 @@
 
 #include "k3-am6548-iot2050-advanced-common.dtsi"
 #include "k3-am65-iot2050-common-pg2.dtsi"
+#include "k3-am65-iot2050-arduino-connector.dtsi"
+#include "k3-am65-iot2050-dp.dtsi"
 
 / {
 	compatible = "siemens,iot2050-advanced-m2", "ti,am654";
 	model = "SIMATIC IOT2050 Advanced M2";
 };
 
-&mcu_r5fss0 {
-	/* lock-step mode not supported on this board */
-	ti,cluster-mode = <0>;
-};
-
 &main_pmx0 {
 	main_bkey_pcie_reset: main-bkey-pcie-reset-default-pins {
 		pinctrl-single,pins = <
@@ -96,16 +93,3 @@
 &pcie1_rc {
 	status = "disabled";
 };
-
-&dwc3_0 {
-	assigned-clock-parents = <&k3_clks 151 4>,  /* set REF_CLK to 20MHz i.e. PER0_PLL/48 */
-				 <&k3_clks 151 9>;  /* set PIPE3_TXB_CLK to CLK_12M_RC/256 (for HS only) */
-	/delete-property/ phys;
-	/delete-property/ phy-names;
-};
-
-&usb0 {
-	maximum-speed = "high-speed";
-	/delete-property/ snps,dis-u1-entry-quirk;
-	/delete-property/ snps,dis-u2-entry-quirk;
-};
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-pg2.dts b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-pg2.dts
index f00dc86d01b9..ec721275e8e2 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-pg2.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-pg2.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) Siemens AG, 2018-2021
+ * Copyright (c) Siemens AG, 2018-2023
  *
  * Authors:
  *   Le Jin <le.jin@siemens.com>
@@ -17,13 +17,11 @@
 
 #include "k3-am6548-iot2050-advanced-common.dtsi"
 #include "k3-am65-iot2050-common-pg2.dtsi"
+#include "k3-am65-iot2050-arduino-connector.dtsi"
+#include "k3-am65-iot2050-dp.dtsi"
+#include "k3-am65-iot2050-usb3.dtsi"
 
 / {
 	compatible = "siemens,iot2050-advanced-pg2", "ti,am654";
 	model = "SIMATIC IOT2050 Advanced PG2";
 };
-
-&mcu_r5fss0 {
-	/* lock-step mode not supported on this board */
-	ti,cluster-mode = <0>;
-};
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-sm.dts b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-sm.dts
new file mode 100644
index 000000000000..b829f4bcab69
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced-sm.dts
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Siemens AG, 2023
+ *
+ * Authors:
+ *   Baocheng Su <baocheng.su@siemens.com>
+ *   Chao Zeng <chao.zeng@siemens.com>
+ *   Huaqian Li <huaqian.li@siemens.com>
+ *
+ * AM6548-based (quad-core) IOT2050 SM variant, Product Generation 2
+ * 4 GB RAM, 16 GB eMMC, USB-serial converter on connector X30
+ *
+ * Product homepage:
+ * https://new.siemens.com/global/en/products/automation/pc-based/iot-gateways/simatic-iot2050.html
+ */
+
+/dts-v1/;
+
+#include "k3-am6548-iot2050-advanced-common.dtsi"
+#include "k3-am65-iot2050-common-pg2.dtsi"
+
+/ {
+	compatible = "siemens,iot2050-advanced-sm", "ti,am654";
+	model = "SIMATIC IOT2050 Advanced SM";
+
+	memory@80000000 {
+		device_type = "memory";
+		/* 4G RAM */
+		reg = <0x00000000 0x80000000 0x00000000 0x80000000>,
+		      <0x00000008 0x80000000 0x00000000 0x80000000>;
+	};
+
+	aliases {
+		spi1 = &main_spi0;
+	};
+
+	leds {
+		pinctrl-0 = <&leds_pins_default>, <&user1_led_pins>;
+
+		led-2 {
+			gpios = <&wkup_gpio0 52 GPIO_ACTIVE_HIGH>;
+		};
+
+		led-3 {
+			gpios = <&wkup_gpio0 53 GPIO_ACTIVE_HIGH>;
+		};
+	};
+};
+
+&main_pmx0 {
+	main_pcie_enable_pins_default: main-pcie-enable-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x01d8, PIN_OUTPUT, 7)  /* (AH12) GPIO1_22 */
+		>;
+	};
+
+	main_spi0_pins: main-spi0-default-pins  {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x01c4, PIN_INPUT, 0) /* (AH13) SPI0_CLK */
+			AM65X_IOPAD(0x01c8, PIN_INPUT, 0) /* (AE13) SPI0_D0 */
+			AM65X_IOPAD(0x01cc, PIN_INPUT, 0) /* (AD13) SPI0_D1 */
+			AM65X_IOPAD(0x01bc, PIN_OUTPUT, 0) /* (AG13) SPI0_CS0 */
+		>;
+	};
+};
+
+&main_pmx1 {
+	asic_spi_mux_ctrl_pin: asic-spi-mux-ctrl-default-pins {
+		pinctrl-single,pins = <
+			AM65X_IOPAD(0x0010, PIN_OUTPUT, 7)  /* (D21) GPIO1_86 */
+		>;
+	};
+};
+
+&wkup_pmx0 {
+	user1_led_pins: user1-led-default-pins {
+		pinctrl-single,pins = <
+			/* (AB1) WKUP_UART0_RXD:WKUP_GPIO0_52, as USER 1 led red */
+			AM65X_WKUP_IOPAD(0x00a0, PIN_OUTPUT, 7)
+			/* (AB5) WKUP_UART0_TXD:WKUP_GPIO0_53, as USER 1 led green */
+			AM65X_WKUP_IOPAD(0x00a4, PIN_OUTPUT, 7)
+		>;
+	};
+
+	soc_asic_pins: soc-asic-default-pins {
+		pinctrl-single,pins = <
+			AM65X_WKUP_IOPAD(0x0044, PIN_INPUT, 7)  /* (P4) WKUP_GPIO0_29 */
+			AM65X_WKUP_IOPAD(0x0048, PIN_INPUT, 7)  /* (P5) WKUP_GPIO0_30 */
+			AM65X_WKUP_IOPAD(0x004c, PIN_INPUT, 7)  /* (P1) WKUP_GPIO0_31 */
+		>;
+	};
+};
+
+&main_gpio0 {
+	gpio-line-names = "main_gpio0-base";
+};
+
+&main_gpio1 {
+	pinctrl-names = "default";
+	pinctrl-0 =
+		<&cp2102n_reset_pin_default>,
+		<&main_pcie_enable_pins_default>,
+		<&asic_spi_mux_ctrl_pin>;
+	gpio-line-names =
+		/* 0..9 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 10..19 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 20..29 */
+		"", "", "", "", "CP2102N-RESET", "", "", "", "", "",
+		/* 30..39 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 40..49 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 50..59 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 60..69 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 70..79 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 80..86 */
+		"", "", "", "", "", "", "ASIC-spi-mux-ctrl";
+};
+
+&wkup_gpio0 {
+	pinctrl-names = "default";
+	pinctrl-0 =
+		<&push_button_pins_default>,
+		<&db9_com_mode_pins_default>,
+		<&soc_asic_pins>;
+	gpio-line-names =
+		/* 0..9 */
+		"wkup_gpio0-base", "", "", "", "UART0-mode1", "UART0-mode0",
+		"UART0-enable", "UART0-terminate", "", "WIFI-disable",
+		/* 10..19 */
+		"", "", "", "", "", "", "", "", "", "",
+		/* 20..29 */
+		"", "", "", "", "", "USER-button", "", "", "","ASIC-gpio-0",
+		/* 30..31 */
+		"ASIC-gpio-1", "ASIC-gpio-2";
+};
+
+&main_spi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_spi0_pins>;
+
+	#address-cells = <1>;
+	#size-cells= <0>;
+};
+
+&mcu_spi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_spi0_pins_default>;
+};
+
+&main_i2c3 {
+	accelerometer: lsm6dso@6a {
+		compatible = "st,lsm6dso";
+		reg = <0x6a>;
+	};
+};
+
+&dss {
+	status = "disabled";
+};
+
+&serdes0 {
+	assigned-clocks = <&k3_clks 153 4>, <&serdes0 AM654_SERDES_CMU_REFCLK>;
+	assigned-clock-parents = <&k3_clks 153 8>, <&k3_clks 153 4>;
+};
+
+&serdes1 {
+	status = "disabled";
+};
+
+&pcie0_rc {
+	pinctrl-names = "default";
+	pinctrl-0 = <&minipcie_pins_default>;
+
+	num-lanes = <1>;
+	phys = <&serdes0 PHY_TYPE_PCIE 1>;
+	phy-names = "pcie-phy0";
+	reset-gpios = <&wkup_gpio0 27 GPIO_ACTIVE_HIGH>;
+	status = "okay";
+};
+
+&pcie1_rc {
+	status = "disabled";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced.dts b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced.dts
index 077f165bdc68..649652a540ef 100644
--- a/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced.dts
+++ b/arch/arm64/boot/dts/ti/k3-am6548-iot2050-advanced.dts
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) Siemens AG, 2018-2021
  *
@@ -17,6 +17,7 @@
 
 #include "k3-am6548-iot2050-advanced-common.dtsi"
 #include "k3-am65-iot2050-common-pg1.dtsi"
+#include "k3-am65-iot2050-arduino-connector.dtsi"
 
 / {
 	compatible = "siemens,iot2050-advanced", "ti,am654";
diff --git a/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
index d0cfdeac21fb..d743f023cdd9 100644
--- a/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-am68-sk-base-board.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Base Board: https://www.ti.com/lit/zip/SPRR463
  */
@@ -169,6 +169,13 @@
 			};
 		};
 	};
+
+	csi_mux: mux-controller {
+		compatible = "gpio-mux";
+		#mux-state-cells = <1>;
+		mux-gpios = <&exp3 1 GPIO_ACTIVE_HIGH>;
+		idle-state = <0>;
+	};
 };
 
 &main_pmx0 {
@@ -186,6 +193,13 @@
 		>;
 	};
 
+	main_i2c1_pins_default: main-i2c1-default-pins {
+		pinctrl-single,pins = <
+			J721S2_IOPAD(0x0ac, PIN_INPUT, 13) /* (AC25) MCASP0_AXR15.I2C1_SCL */
+			J721S2_IOPAD(0x0b0, PIN_INPUT, 13) /* (AD26) MCASP1_AXR3.I2C1_SDA */
+		>;
+	};
+
 	main_mmc1_pins_default: main-mmc1-default-pins {
 		pinctrl-single,pins = <
 			J721S2_IOPAD(0x104, PIN_INPUT, 0) /* (P23) MMC1_CLK */
@@ -431,6 +445,42 @@
 	};
 };
 
+&main_i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c1_pins_default>;
+	status = "okay";
+
+	exp3: gpio@20 {
+		compatible = "ti,tca6408";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "CSI_VIO_SEL", "CSI_SEL_FPC_EXPn",
+				  "IO_EXP_CSI2_EXP_RSTz","CSI0_B_GPIO1",
+				  "CSI1_B_GPIO1";
+	};
+
+	i2c-mux@70 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x70>;
+
+		cam0_i2c: i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+		};
+
+		cam1_i2c: i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+		};
+
+	};
+};
+
 &main_i2c4 {
 	status = "okay";
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/ti/k3-am68-sk-som.dtsi b/arch/arm64/boot/dts/ti/k3-am68-sk-som.dtsi
index 20861a0a46b0..0f4a5da0ebc4 100644
--- a/arch/arm64/boot/dts/ti/k3-am68-sk-som.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-am68-sk-som.dtsi
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -209,51 +209,51 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
 
 &c71_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_1>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_1>;
 	memory-region = <&c71_1_dma_memory_region>,
 			<&c71_1_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk.dts b/arch/arm64/boot/dts/ti/k3-am69-sk.dts
index 8da591579868..50de2a448a3a 100644
--- a/arch/arm64/boot/dts/ti/k3-am69-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-am69-sk.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Design Files: https://www.ti.com/lit/zip/SPRR466
  * TRM: https://www.ti.com/lit/zip/spruj52
@@ -33,6 +33,7 @@
 
 	memory@80000000 {
 		device_type = "memory";
+		bootph-all;
 		/* 32G RAM */
 		reg = <0x00 0x80000000 0x00 0x80000000>,
 		      <0x08 0x80000000 0x07 0x80000000>;
@@ -321,6 +322,38 @@
 			};
 		};
 	};
+
+	csi_mux: mux-controller {
+		compatible = "gpio-mux";
+		#mux-state-cells = <1>;
+		mux-gpios = <&exp2 1 GPIO_ACTIVE_HIGH>;
+		idle-state = <0>;
+	};
+
+	transceiver1: can-phy0 {
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+	};
+
+	transceiver2: can-phy1 {
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+	};
+
+	transceiver3: can-phy2 {
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+	};
+
+	transceiver4: can-phy3 {
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+	};
+
 };
 
 &main_pmx0 {
@@ -340,6 +373,13 @@
 		>;
 	};
 
+	main_i2c1_pins_default: main-i2c1-default-pins {
+		pinctrl-single,pins = <
+			J784S4_IOPAD(0x0ac, PIN_INPUT_PULLUP, 13) /* (AE34) MCASP0_AXR15.I2C1_SCL */
+			J784S4_IOPAD(0x0b0, PIN_INPUT_PULLUP, 13) /* (AL33) MCASP1_AXR3.I2C1_SDA */
+		>;
+	};
+
 	main_mmc1_pins_default: main-mmc1-default-pins {
 		bootph-all;
 		pinctrl-single,pins = <
@@ -429,6 +469,40 @@
 			J784S4_IOPAD(0x000, PIN_INPUT, 7) /* (AN35) EXTINTN.GPIO0_0 */
 		>;
 	};
+
+	main_mcan6_pins_default: main-mcan6-default-pins {
+		pinctrl-single,pins = <
+			J784S4_IOPAD(0x098, PIN_INPUT, 0) /* (AH36) MCAN6_RX */
+			J784S4_IOPAD(0x094, PIN_OUTPUT, 0) /* (AG35) MCAN6_TX */
+		>;
+	};
+
+	main_mcan7_pins_default: main-mcan7-default-pins {
+		pinctrl-single,pins = <
+			J784S4_IOPAD(0x0A0, PIN_INPUT, 0) /* (AD34) MCAN7_RX */
+			J784S4_IOPAD(0x09C, PIN_OUTPUT, 0) /* (AF35) MCAN7_TX */
+		>;
+	};
+
+};
+
+&wkup_pmx0 {
+	bootph-all;
+	mcu_fss0_ospi0_pins_default: mcu-fss0-ospi0-default-pins {
+		pinctrl-single,pins = <
+			J784S4_WKUP_IOPAD(0x000, PIN_OUTPUT, 0) /* (E32) MCU_OSPI0_CLK */
+			J784S4_WKUP_IOPAD(0x02c, PIN_OUTPUT, 0) /* (A32) MCU_OSPI0_CSn0 */
+			J784S4_WKUP_IOPAD(0x00c, PIN_INPUT, 0) /* (B33) MCU_OSPI0_D0 */
+			J784S4_WKUP_IOPAD(0x010, PIN_INPUT, 0) /* (B32) MCU_OSPI0_D1 */
+			J784S4_WKUP_IOPAD(0x014, PIN_INPUT, 0) /* (C33) MCU_OSPI0_D2 */
+			J784S4_WKUP_IOPAD(0x018, PIN_INPUT, 0) /* (C35) MCU_OSPI0_D3 */
+			J784S4_WKUP_IOPAD(0x01c, PIN_INPUT, 0) /* (D33) MCU_OSPI0_D4 */
+			J784S4_WKUP_IOPAD(0x020, PIN_INPUT, 0) /* (D34) MCU_OSPI0_D5 */
+			J784S4_WKUP_IOPAD(0x024, PIN_INPUT, 0) /* (E34) MCU_OSPI0_D6 */
+			J784S4_WKUP_IOPAD(0x028, PIN_INPUT, 0) /* (E33) MCU_OSPI0_D7 */
+			J784S4_WKUP_IOPAD(0x008, PIN_INPUT, 0) /* (C34) MCU_OSPI0_DQS */
+		>;
+	};
 };
 
 &wkup_pmx2 {
@@ -525,6 +599,21 @@
 			J784S4_WKUP_IOPAD(0x090, PIN_INPUT, 7) /* (H37) WKUP_GPIO0_14 */
 		>;
 	};
+
+	mcu_mcan0_pins_default: mcu-mcan0-default-pins {
+		pinctrl-single,pins = <
+			J784S4_WKUP_IOPAD(0x054, PIN_INPUT, 0) /* (F38) MCU_MCAN0_RX */
+			J784S4_WKUP_IOPAD(0x050, PIN_OUTPUT, 0) /* (K33) MCU_MCAN0_TX */
+		>;
+	};
+
+	mcu_mcan1_pins_default: mcu-mcan1-default-pins {
+		pinctrl-single,pins = <
+			J784S4_WKUP_IOPAD(0x06c, PIN_INPUT, 0) /* (K36) WKUP_GPIO0_5.MCU_MCAN1_RX */
+			J784S4_WKUP_IOPAD(0x068, PIN_OUTPUT, 0)/* (H35) WKUP_GPIO0_4.MCU_MCAN1_TX */
+		>;
+	};
+
 };
 
 &wkup_pmx3 {
@@ -646,7 +735,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pmic_irq_pins_default>;
 		interrupt-parent = <&wkup_gpio0>;
-		interrupts = <39 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <83 IRQ_TYPE_EDGE_FALLING>;
 		gpio-controller;
 		#gpio-cells = <2>;
 		ti,primary-pmic;
@@ -774,6 +863,42 @@
 	};
 };
 
+&main_i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c1_pins_default>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	exp2: gpio@21 {
+		compatible = "ti,tca6408";
+		reg = <0x21>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "CSI_VIO_SEL", "CSI_MUX_SEL_2", "CSI2_RSTz",
+				  "IO_EXP_CAM0_GPIO1", "IO_EXP_CAM1_GPIO1";
+	};
+
+	i2c-mux@70 {
+		compatible = "nxp,pca9543";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0x70>;
+
+		cam0_i2c: i2c@0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0>;
+		};
+
+		cam1_i2c: i2c@1 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+		};
+
+	};
+};
+
 &main_sdhci0 {
 	bootph-all;
 	/* eMMC */
@@ -822,77 +947,77 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &main_r5fss2_core0 {
-	mboxes = <&mailbox0_cluster3>, <&mbox_main_r5fss2_core0>;
+	mboxes = <&mailbox0_cluster3 &mbox_main_r5fss2_core0>;
 	memory-region = <&main_r5fss2_core0_dma_memory_region>,
 			<&main_r5fss2_core0_memory_region>;
 };
 
 &main_r5fss2_core1 {
-	mboxes = <&mailbox0_cluster3>, <&mbox_main_r5fss2_core1>;
+	mboxes = <&mailbox0_cluster3 &mbox_main_r5fss2_core1>;
 	memory-region = <&main_r5fss2_core1_dma_memory_region>,
 			<&main_r5fss2_core1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
 
 &c71_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_1>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_1>;
 	memory-region = <&c71_1_dma_memory_region>,
 			<&c71_1_memory_region>;
 };
 
 &c71_2 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster5>, <&mbox_c71_2>;
+	mboxes = <&mailbox0_cluster5 &mbox_c71_2>;
 	memory-region = <&c71_2_dma_memory_region>,
 			<&c71_2_memory_region>;
 };
 
 &c71_3 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster5>, <&mbox_c71_3>;
+	mboxes = <&mailbox0_cluster5 &mbox_c71_3>;
 	memory-region = <&c71_3_dma_memory_region>,
 			<&c71_3_memory_region>;
 };
@@ -918,13 +1043,9 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&dss_vout0_pins_default>;
 	assigned-clocks = <&k3_clks 218 2>,
-			  <&k3_clks 218 5>,
-			  <&k3_clks 218 14>,
-			  <&k3_clks 218 18>;
+			  <&k3_clks 218 5>;
 	assigned-clock-parents = <&k3_clks 218 3>,
-				 <&k3_clks 218 7>,
-				 <&k3_clks 218 16>,
-				 <&k3_clks 218 22>;
+				 <&k3_clks 218 7>;
 };
 
 &serdes_wiz4 {
@@ -992,3 +1113,93 @@
 		};
 	};
 };
+
+&mcu_mcan0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_mcan0_pins_default>;
+	phys = <&transceiver1>;
+};
+
+&mcu_mcan1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_mcan1_pins_default>;
+	phys = <&transceiver2>;
+};
+
+&main_mcan6 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mcan6_pins_default>;
+	phys = <&transceiver3>;
+};
+
+&main_mcan7 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mcan7_pins_default>;
+	phys = <&transceiver4>;
+};
+
+&ospi0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_fss0_ospi0_pins_default>;
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-tx-bus-width = <8>;
+		spi-rx-bus-width = <8>;
+		spi-max-frequency = <25000000>;
+		cdns,tshsl-ns = <60>;
+		cdns,tsd2d-ns = <60>;
+		cdns,tchsh-ns = <60>;
+		cdns,tslch-ns = <60>;
+		cdns,read-delay = <4>;
+
+		partitions {
+			bootph-all;
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "ospi.tiboot3";
+				reg = <0x0 0x100000>;
+			};
+
+			partition@100000 {
+				label = "ospi.tispl";
+				reg = <0x100000 0x200000>;
+			};
+
+			partition@300000 {
+				label = "ospi.u-boot";
+				reg = <0x300000 0x400000>;
+			};
+
+			partition@700000 {
+				label = "ospi.env";
+				reg = <0x700000 0x40000>;
+			};
+
+			partition@740000 {
+				label = "ospi.env.backup";
+				reg = <0x740000 0x40000>;
+			};
+
+			partition@800000 {
+				label = "ospi.rootfs";
+				reg = <0x800000 0x37c0000>;
+			};
+
+			partition@3fc0000 {
+				bootph-pre-ram;
+				label = "ospi.phypattern";
+				reg = <0x3fc0000 0x40000>;
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts
index cee2b4b0eb87..6593c5da82c0 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -88,27 +88,56 @@
 		states = <1800000 0x0>,
 			 <3300000 0x1>;
 	};
+
+	transceiver1: can-phy1 {
+		compatible = "ti,tcan1043";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&mcu_mcan0_gpio_pins_default>;
+		standby-gpios = <&wkup_gpio0 58 GPIO_ACTIVE_LOW>;
+		enable-gpios = <&wkup_gpio0 0 GPIO_ACTIVE_HIGH>;
+	};
+
+	transceiver2: can-phy2 {
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&mcu_mcan1_gpio_pins_default>;
+		standby-gpios = <&wkup_gpio0 2 GPIO_ACTIVE_HIGH>;
+	};
+
+	transceiver3: can-phy3 {
+		compatible = "ti,tcan1043";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+		standby-gpios = <&exp2 7 GPIO_ACTIVE_LOW>;
+		enable-gpios = <&exp2 6 GPIO_ACTIVE_HIGH>;
+		mux-states = <&mux0 1>;
+	};
 };
 
 &wkup_pmx0 {
+};
+
+&wkup_pmx2 {
 	mcu_uart0_pins_default: mcu-uart0-default-pins {
 		pinctrl-single,pins = <
-			J721E_WKUP_IOPAD(0xf4, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */
-			J721E_WKUP_IOPAD(0xf0, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */
-			J721E_WKUP_IOPAD(0xf8, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */
-			J721E_WKUP_IOPAD(0xfc, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */
+			J721E_WKUP_IOPAD(0x90, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */
+			J721E_WKUP_IOPAD(0x94, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */
+			J721E_WKUP_IOPAD(0x8c, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */
+			J721E_WKUP_IOPAD(0x88, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */
 		>;
 	};
 
 	wkup_uart0_pins_default: wkup-uart0-default-pins {
 		pinctrl-single,pins = <
-			J721E_WKUP_IOPAD(0xb0, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */
-			J721E_WKUP_IOPAD(0xb4, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */
+			J721E_WKUP_IOPAD(0x48, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */
+			J721E_WKUP_IOPAD(0x4c, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */
 		>;
 	};
-};
 
-&wkup_pmx2 {
 	mcu_cpsw_pins_default: mcu-cpsw-default-pins {
 		pinctrl-single,pins = <
 			J721E_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */
@@ -138,6 +167,33 @@
 			J721E_WKUP_IOPAD(0x0030, PIN_INPUT, 0) /* (L4) MCU_MDIO0_MDIO */
 		>;
 	};
+
+	mcu_mcan0_pins_default: mcu-mcan0-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x54, PIN_INPUT, 0) /* (A17) MCU_MCAN0_RX */
+			J721E_WKUP_IOPAD(0x50, PIN_OUTPUT, 0) /* (A16) MCU_MCAN0_TX */
+		>;
+	};
+
+	mcu_mcan1_pins_default: mcu-mcan1-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x6c, PIN_INPUT, 0) /* (B16) WKUP_GPIO0_5.MCU_MCAN1_RX */
+			J721E_WKUP_IOPAD(0x68, PIN_OUTPUT, 0) /* (D13) WKUP_GPIO0_4.MCU_MCAN1_TX */
+		>;
+	};
+
+	mcu_mcan0_gpio_pins_default: mcu-mcan0-gpio-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x58, PIN_INPUT, 7) /* (B18) WKUP_GPIO0_0 */
+			J721E_WKUP_IOPAD(0x40, PIN_INPUT, 7) /* (B17) MCU_SPI0_D1 */
+		>;
+	};
+
+	mcu_mcan1_gpio_pins_default: mcu-mcan1-gpio-default-pins {
+		pinctrl-single,pins = <
+			J721E_WKUP_IOPAD(0x60, PIN_INPUT, 7) /* (D14) WKUP_GPIO0_2 */
+		>;
+	};
 };
 
 &main_pmx0 {
@@ -189,6 +245,13 @@
 			J721E_IOPAD(0xd0, PIN_OUTPUT, 7) /* (T5) SPI0_D1.GPIO0_55 */
 		>;
 	};
+
+	main_mcan3_pins_default: main-mcan3-default-pins {
+		pinctrl-single,pins = <
+			J721E_IOPAD(0x3c, PIN_INPUT, 0) /* (W16) MCAN3_RX */
+			J721E_IOPAD(0x38, PIN_OUTPUT, 0) /* (Y21) MCAN3_TX */
+		>;
+	};
 };
 
 &main_pmx1 {
@@ -210,7 +273,6 @@
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&mcu_uart0_pins_default>;
-	clock-frequency = <96000000>;
 };
 
 &main_uart0 {
@@ -382,15 +444,30 @@
 };
 
 &pcie1_rc {
+	status = "okay";
 	reset-gpios = <&exp1 2 GPIO_ACTIVE_HIGH>;
 	phys = <&serdes0_pcie_link>;
 	phy-names = "pcie-phy";
 	num-lanes = <2>;
 };
 
-&pcie1_ep {
-	phys = <&serdes0_pcie_link>;
-	phy-names = "pcie-phy";
-	num-lanes = <2>;
-	status = "disabled";
+&mcu_mcan0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_mcan0_pins_default>;
+	phys = <&transceiver1>;
+};
+
+&mcu_mcan1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcu_mcan1_pins_default>;
+	phys = <&transceiver2>;
+};
+
+&main_mcan3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mcan3_pins_default>;
+	phys = <&transceiver3>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-evm-quad-port-eth-exp.dtso b/arch/arm64/boot/dts/ti/k3-j7200-evm-quad-port-eth-exp.dtso
index 32d905235ed7..6432ca08ee8e 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-evm-quad-port-eth-exp.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j7200-evm-quad-port-eth-exp.dtso
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for CPSW5G in QSGMII mode using J7 Quad Port ETH EXP Add-On Ethernet Card with
  * J7200 board.
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
index da67bf8fe703..657f9cc9f4ea 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J7200 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 / {
@@ -33,10 +33,11 @@
 		ranges = <0x00 0x00 0x00100000 0x1c000>;
 
 		serdes_ln_ctrl: mux-controller@4080 {
-			compatible = "mmio-mux";
+			compatible = "reg-mux";
+			reg = <0x4080 0x20>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4080 0x3>, <0x4084 0x3>, /* SERDES0 lane0/1 select */
-					<0x4088 0x3>, <0x408c 0x3>; /* SERDES0 lane2/3 select */
+			mux-reg-masks = <0x0 0x3>, <0x4 0x3>, /* SERDES0 lane0/1 select */
+					<0x8 0x3>, <0xc 0x3>; /* SERDES0 lane2/3 select */
 		};
 
 		cpsw0_phy_gmii_sel: phy@4044 {
@@ -47,9 +48,10 @@
 		};
 
 		usb_serdes_mux: mux-controller@4000 {
-			compatible = "mmio-mux";
+			compatible = "reg-mux";
+			reg = <0x4000 0x4>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4000 0x8000000>; /* USB0 to SERDES0 lane 1/3 mux */
+			mux-reg-masks = <0x0 0x8000000>; /* USB0 to SERDES0 lane 1/3 mux */
 		};
 	};
 
@@ -399,7 +401,7 @@
 
 	/* TIMERIO pad input CTRLMMR_TIMER*_CTRL registers */
 	main_timerio_input: pinctrl@104200 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		reg = <0x0 0x104200 0x0 0x50>;
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
@@ -408,7 +410,7 @@
 
 	/* TIMERIO pad output CTCTRLMMR_TIMERIO*_CTRL registers */
 	main_timerio_output: pinctrl@104280 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		reg = <0x0 0x104280 0x0 0x20>;
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
@@ -416,7 +418,7 @@
 	};
 
 	main_pmx0: pinctrl@11c000 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x11c000 0x00 0x10c>;
 		#pinctrl-cells = <1>;
@@ -425,7 +427,7 @@
 	};
 
 	main_pmx1: pinctrl@11c11c {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x11c11c 0x00 0xc>;
 		#pinctrl-cells = <1>;
@@ -770,26 +772,7 @@
 		ranges = <0x01000000 0x0 0x18001000  0x00 0x18001000  0x0 0x0010000>,
 			 <0x02000000 0x0 0x18011000  0x00 0x18011000  0x0 0x7fef000>;
 		dma-ranges = <0x02000000 0x0 0x0 0x0 0x0 0x10000 0x0>;
-	};
-
-	pcie1_ep: pcie-ep@2910000 {
-		compatible = "ti,j7200-pcie-ep", "ti,j721e-pcie-ep";
-		reg = <0x00 0x02910000 0x00 0x1000>,
-		      <0x00 0x02917000 0x00 0x400>,
-		      <0x00 0x0d800000 0x00 0x00800000>,
-		      <0x00 0x18000000 0x00 0x08000000>;
-		reg-names = "intd_cfg", "user_cfg", "reg", "mem";
-		interrupt-names = "link_state";
-		interrupts = <GIC_SPI 330 IRQ_TYPE_EDGE_RISING>;
-		ti,syscon-pcie-ctrl = <&scm_conf 0x4074>;
-		max-link-speed = <3>;
-		num-lanes = <4>;
-		power-domains = <&k3_pds 240 TI_SCI_PD_EXCLUSIVE>;
-		clocks = <&k3_clks 240 6>;
-		clock-names = "fck";
-		max-functions = /bits/ 8 <6>;
-		max-virtual-functions = /bits/ 8 <4 4 4 4 0 0>;
-		dma-coherent;
+		status = "disabled";
 	};
 
 	usbss0: cdns-usb@4104000 {
@@ -895,6 +878,276 @@
 		status = "disabled";
 	};
 
+	main_mcan0: can@2701000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02701000 0x00 0x200>,
+		      <0x00 0x02708000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 156 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 156 0>, <&k3_clks 156 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan1: can@2711000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02711000 0x00 0x200>,
+		      <0x00 0x02718000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 158 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 158 0>, <&k3_clks 158 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan2: can@2721000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02721000 0x00 0x200>,
+		      <0x00 0x02728000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 160 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 160 0>, <&k3_clks 160 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan3: can@2731000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02731000 0x00 0x200>,
+		      <0x00 0x02738000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 161 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 161 0>, <&k3_clks 161 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan4: can@2741000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02741000 0x00 0x200>,
+		      <0x00 0x02748000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 162 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 162 0>, <&k3_clks 162 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan5: can@2751000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02751000 0x00 0x200>,
+		      <0x00 0x02758000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 163 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 163 0>, <&k3_clks 163 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan6: can@2761000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02761000 0x00 0x200>,
+		      <0x00 0x02768000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 164 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 164 0>, <&k3_clks 164 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan7: can@2771000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02771000 0x00 0x200>,
+		      <0x00 0x02778000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 165 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 165 0>, <&k3_clks 165 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan8: can@2781000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02781000 0x00 0x200>,
+		      <0x00 0x02788000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 166 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 166 0>, <&k3_clks 166 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 576 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 577 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan9: can@2791000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02791000 0x00 0x200>,
+		      <0x00 0x02798000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 167 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 167 0>, <&k3_clks 167 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 579 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 580 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan10: can@27a1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x027a1000 0x00 0x200>,
+		      <0x00 0x027a8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 168 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 168 0>, <&k3_clks 168 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 582 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 583 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan11: can@27b1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x027b1000 0x00 0x200>,
+		      <0x00 0x027b8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 169 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 169 0>, <&k3_clks 169 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 585 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 586 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan12: can@27c1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x027c1000 0x00 0x200>,
+		      <0x00 0x027c8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 170 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 170 0>, <&k3_clks 170 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 588 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 589 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan13: can@27d1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x027d1000 0x00 0x200>,
+		      <0x00 0x027d8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 171 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 171 0>, <&k3_clks 171 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 591 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 592 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan14: can@2681000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02681000 0x00 0x200>,
+		      <0x00 0x02688000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 150 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 150 0>, <&k3_clks 150 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 594 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 595 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan15: can@2691000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x02691000 0x00 0x200>,
+		      <0x00 0x02698000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 151 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 151 0>, <&k3_clks 151 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 597 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 598 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan16: can@26a1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x026a1000 0x00 0x200>,
+		      <0x00 0x026a8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 152 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 152 0>, <&k3_clks 152 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 784 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 785 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	main_mcan17: can@26b1000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x026b1000 0x00 0x200>,
+		      <0x00 0x026b8000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 153 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 153 0>, <&k3_clks 153 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 787 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 788 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
 	main_spi0: spi@2100000 {
 		compatible = "ti,am654-mcspi","ti,omap4-mcspi";
 		reg = <0x00 0x02100000 0x00 0x400>;
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
index 60b26374ae0c..7cf21c99956e 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-mcu-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J7200 SoC Family MCU/WAKEUP Domain peripherals
  *
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu_wakeup {
@@ -192,7 +192,7 @@
 
 	/* MCU_TIMERIO pad input CTRLMMR_MCU_TIMER*_CTRL registers */
 	mcu_timerio_input: pinctrl@40f04200 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		reg = <0x0 0x40f04200 0x0 0x28>;
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
@@ -202,7 +202,7 @@
 
 	/* MCU_TIMERIO pad output CTRLMMR_MCU_TIMERIO*_CTRL registers */
 	mcu_timerio_output: pinctrl@40f04280 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		reg = <0x0 0x40f04280 0x0 0x28>;
 		#pinctrl-cells = <1>;
 		pinctrl-single,register-width = <32>;
@@ -211,7 +211,7 @@
 	};
 
 	wkup_pmx0: pinctrl@4301c000 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x4301c000 0x00 0x34>;
 		#pinctrl-cells = <1>;
@@ -220,7 +220,7 @@
 	};
 
 	wkup_pmx1: pinctrl@4301c038 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x4301c038 0x00 0x8>;
 		#pinctrl-cells = <1>;
@@ -229,7 +229,7 @@
 	};
 
 	wkup_pmx2: pinctrl@4301c068 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x4301c068 0x00 0xec>;
 		#pinctrl-cells = <1>;
@@ -238,7 +238,7 @@
 	};
 
 	wkup_pmx3: pinctrl@4301c174 {
-		compatible = "pinctrl-single";
+		compatible = "ti,j7200-padconf", "pinctrl-single";
 		/* Proxy 0 addressing */
 		reg = <0x00 0x4301c174 0x00 0x20>;
 		#pinctrl-cells = <1>;
@@ -518,17 +518,18 @@
 		status = "disabled";
 	};
 
-	fss: syscon@47000000 {
-		compatible = "syscon", "simple-mfd";
+	fss: bus@47000000 {
+		compatible = "simple-bus";
 		reg = <0x00 0x47000000 0x00 0x100>;
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
 
-		hbmc_mux: hbmc-mux {
-			compatible = "mmio-mux";
+		hbmc_mux: mux-controller@47000004 {
+			compatible = "reg-mux";
+			reg = <0x00 0x47000004 0x00 0x4>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4 0x2>; /* HBMC select */
+			mux-reg-masks = <0x0 0x2>; /* HBMC select */
 		};
 
 		hbmc: hyperbus@47034000 {
@@ -655,4 +656,34 @@
 		ti,esm-pins = <95>;
 		bootph-pre-ram;
 	};
+
+	mcu_mcan0: can@40528000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x40528000 0x00 0x200>,
+		      <0x00 0x40500000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 172 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 172 0>, <&k3_clks 172 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 832 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 833 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
+
+	mcu_mcan1: can@40568000 {
+		compatible = "bosch,m_can";
+		reg = <0x00 0x40568000 0x00 0x200>,
+		      <0x00 0x40540000 0x00 0x8000>;
+		reg-names = "m_can", "message_ram";
+		power-domains = <&k3_pds 173 TI_SCI_PD_EXCLUSIVE>;
+		clocks = <&k3_clks 173 0>, <&k3_clks 173 2>;
+		clock-names = "hclk", "cclk";
+		interrupts = <GIC_SPI 835 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 836 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "int0", "int1";
+		bosch,mram-cfg = <0x0 128 64 64 64 64 32 32>;
+		status = "disabled";
+	};
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
index ea47f10d393a..7e6a584ac6f0 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-som-p0.dtsi
@@ -1,10 +1,12 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
 
+#include <dt-bindings/gpio/gpio.h>
+
 #include "k3-j7200.dtsi"
 
 / {
@@ -80,6 +82,25 @@
 			no-map;
 		};
 	};
+
+	mux0: mux-controller {
+		compatible = "gpio-mux";
+		#mux-state-cells = <1>;
+		mux-gpios = <&exp_som 1 GPIO_ACTIVE_HIGH>;
+	};
+
+	mux1: mux-controller {
+		compatible = "gpio-mux";
+		#mux-state-cells = <1>;
+		mux-gpios = <&exp_som 2 GPIO_ACTIVE_HIGH>;
+	};
+
+	transceiver0: can-phy0 {
+		/* standby pin has been grounded by default */
+		compatible = "ti,tcan1042";
+		#phy-cells = <0>;
+		max-bitrate = <5000000>;
+	};
 };
 
 &wkup_pmx0 {
@@ -142,6 +163,13 @@
 			J721E_IOPAD(0xd8, PIN_INPUT_PULLUP, 0) /* (W2) I2C0_SDA */
 		>;
 	};
+
+	main_mcan0_pins_default: main-mcan0-default-pins {
+		pinctrl-single,pins = <
+			J721E_IOPAD(0x24, PIN_INPUT, 0) /* (V20) MCAN0_RX */
+			J721E_IOPAD(0x20, PIN_OUTPUT, 0) /* (V18) MCAN0_TX */
+		>;
+	};
 };
 
 &hbmc {
@@ -222,25 +250,25 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
@@ -478,3 +506,10 @@
 		};
 	};
 };
+
+&main_mcan0 {
+	status = "okay";
+	pinctrl-0 = <&main_mcan0_pins_default>;
+	pinctrl-names = "default";
+	phys = <&transceiver0>;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j7200-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-j7200-thermal.dtsi
index e7e3a643a6f0..2d22a95a6fdb 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-j7200.dtsi b/arch/arm64/boot/dts/ti/k3-j7200.dtsi
index ef73e6d7e858..d411911fdf71 100644
--- a/arch/arm64/boot/dts/ti/k3-j7200.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j7200.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J7200 SoC Family
  *
- * Copyright (C) 2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2020-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/irq.h>
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
index 2f954729f353..a2925555fe81 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * https://beagleboard.org/ai-64
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
- * Copyright (C) 2022 Jason Kridner, BeagleBoard.org Foundation
- * Copyright (C) 2022 Robert Nelson, BeagleBoard.org Foundation
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Jason Kridner, BeagleBoard.org Foundation
+ * Copyright (C) 2022-2024 Robert Nelson, BeagleBoard.org Foundation
  */
 
 /dts-v1/;
@@ -936,58 +936,58 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &c66_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_0>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_0>;
 	memory-region = <&c66_0_dma_memory_region>,
 			<&c66_0_memory_region>;
 };
 
 &c66_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_1>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_1>;
 	memory-region = <&c66_1_dma_memory_region>,
 			<&c66_1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
index fe5207ac7d85..8230d53cd696 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2019 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2019-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Product Link: https://www.ti.com/tool/J721EXCPXEVM
  */
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-evm-gesi-exp-board.dtso b/arch/arm64/boot/dts/ti/k3-j721e-evm-gesi-exp-board.dtso
index 6a7d37575da1..f84aa9f94547 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-evm-gesi-exp-board.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j721e-evm-gesi-exp-board.dtso
@@ -1,11 +1,11 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for CPSW9G in RGMII mode using J7 GESI EXP BRD board with
  * J721E board.
  *
  * GESI Board Product Link: https://www.ti.com/tool/J7EXPCXEVM
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso
index 0c82a13b65a4..4062709d6579 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j721e-evm-pcie0-ep.dtso
@@ -1,11 +1,11 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for enabling PCIE0 instance in Endpoint Configuration with the
  * J7 common processor board.
  *
  * J7 Common Processor Board Product Link: https://www.ti.com/tool/J721EXCPXEVM
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-evm-quad-port-eth-exp.dtso b/arch/arm64/boot/dts/ti/k3-j721e-evm-quad-port-eth-exp.dtso
index d4c51ffc3d6b..8376fa4b6ee1 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-evm-quad-port-eth-exp.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j721e-evm-quad-port-eth-exp.dtso
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for CPSW9G in QSGMII mode using J7 Quad Port ETH EXP Add-On Ethernet Card with
  * J721E board.
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index 2569b4c08ffb..c7eafbc862f9 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721E SoC Family Main Domain peripherals
  *
- * Copyright (C) 2016-2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/phy/phy-ti.h>
@@ -45,15 +45,15 @@
 		ranges = <0x0 0x0 0x00100000 0x1c000>;
 
 		serdes_ln_ctrl: mux-controller@4080 {
-			compatible = "mmio-mux";
-			reg = <0x00004080 0x50>;
+			compatible = "reg-mux";
+			reg = <0x4080 0x50>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4080 0x3>, <0x4084 0x3>, /* SERDES0 lane0/1 select */
-					<0x4090 0x3>, <0x4094 0x3>, /* SERDES1 lane0/1 select */
-					<0x40a0 0x3>, <0x40a4 0x3>, /* SERDES2 lane0/1 select */
-					<0x40b0 0x3>, <0x40b4 0x3>, /* SERDES3 lane0/1 select */
-					<0x40c0 0x3>, <0x40c4 0x3>, <0x40c8 0x3>, <0x40cc 0x3>;
-					/* SERDES4 lane0/1/2/3 select */
+			mux-reg-masks = <0x0 0x3>, <0x4 0x3>, /* SERDES0 lane0/1 select */
+					<0x10 0x3>, <0x14 0x3>, /* SERDES1 lane0/1 select */
+					<0x20 0x3>, <0x24 0x3>, /* SERDES2 lane0/1 select */
+					<0x30 0x3>, <0x34 0x3>, /* SERDES3 lane0/1 select */
+					<0x40 0x3>, <0x44 0x3>, /* SERDES4 lane0/1 select */
+					<0x48 0x3>, <0x4c 0x3>; /* SERDES4 lane2/3 select */
 			idle-states = <J721E_SERDES0_LANE0_PCIE0_LANE0>, <J721E_SERDES0_LANE1_PCIE0_LANE1>,
 				      <J721E_SERDES1_LANE0_PCIE1_LANE0>, <J721E_SERDES1_LANE1_PCIE1_LANE1>,
 				      <J721E_SERDES2_LANE0_PCIE2_LANE0>, <J721E_SERDES2_LANE1_PCIE2_LANE1>,
@@ -70,10 +70,11 @@
 		};
 
 		usb_serdes_mux: mux-controller@4000 {
-			compatible = "mmio-mux";
+			compatible = "reg-mux";
+			reg = <0x4000 0x20>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4000 0x8000000>, /* USB0 to SERDES0/3 mux */
-					<0x4010 0x8000000>; /* USB1 to SERDES1/2 mux */
+			mux-reg-masks = <0x0 0x8000000>, /* USB0 to SERDES0/3 mux */
+					<0x10 0x8000000>; /* USB1 to SERDES1/2 mux */
 		};
 
 		ehrpwm_tbclk: clock-controller@4140 {
@@ -572,6 +573,128 @@
 		pinctrl-single,function-mask = <0x0000001f>;
 	};
 
+	ti_csi2rx0: ticsi2rx@4500000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x0 0x4500000 0x0 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_udmap 0x4940>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 26 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@4504000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x0 0x4504000 0x0 0x1000>;
+			clocks = <&k3_clks 26 2>, <&k3_clks 26 0>, <&k3_clks 26 2>,
+				<&k3_clks 26 2>, <&k3_clks 26 3>, <&k3_clks 26 3>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx1: ticsi2rx@4510000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x0 0x4510000 0x0 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_udmap 0x4960>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 27 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx1: csi-bridge@4514000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x0 0x4514000 0x0 0x1000>;
+			clocks = <&k3_clks 27 2>, <&k3_clks 27 0>, <&k3_clks 27 2>,
+				 <&k3_clks 27 2>, <&k3_clks 27 3>, <&k3_clks 27 3>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				      "pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy1>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi1_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi1_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi1_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi1_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi1_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@4580000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x0 0x4580000 0x0 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 147 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy1: phy@4590000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x0 0x4590000 0x0 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 148 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
 	serdes_wiz0: wiz@5000000 {
 		compatible = "ti,j721e-wiz-16g";
 		#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
index a74912d9e4da..4618b697fbc4 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721E SoC Family MCU/WAKEUP Domain peripherals
  *
- * Copyright (C) 2016-2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu_wakeup {
@@ -353,9 +353,9 @@
 
 		hbmc_mux: mux-controller@47000004 {
 			compatible = "reg-mux";
-			reg = <0x00 0x47000004 0x00 0x2>;
+			reg = <0x00 0x47000004 0x00 0x4>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4 0x2>; /* HBMC select */
+			mux-reg-masks = <0x0 0x2>; /* HBMC select */
 		};
 
 		hbmc: hyperbus@47034000 {
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk-csi2-dual-imx219.dtso b/arch/arm64/boot/dts/ti/k3-j721e-sk-csi2-dual-imx219.dtso
new file mode 100644
index 000000000000..47bb5480b5b0
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-j721e-sk-csi2-dual-imx219.dtso
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/**
+ * DT Overlay for dual RPi Camera V2.1 (Sony IMX219) interfaced with CSI2
+ * on J721E SK, AM68 SK or AM69-SK board.
+ * https://datasheets.raspberrypi.org/camera/camera-v2-schematic.pdf
+ *
+ * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+/dts-v1/;
+/plugin/;
+
+#include <dt-bindings/gpio/gpio.h>
+#include "k3-pinctrl.h"
+
+&{/} {
+	clk_imx219_fixed: imx219-xclk {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+	};
+};
+
+&csi_mux {
+	idle-state = <1>;
+};
+
+/* CAM0 I2C */
+&cam0_i2c {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	imx219_0: imx219-0@10 {
+		compatible = "sony,imx219";
+		reg = <0x10>;
+
+		clocks = <&clk_imx219_fixed>;
+		clock-names = "xclk";
+
+		port {
+			csi2_cam0: endpoint {
+				remote-endpoint = <&csi2rx0_in_sensor>;
+				link-frequencies = /bits/ 64 <456000000>;
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+/* CAM1 I2C */
+&cam1_i2c {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	imx219_1: imx219-1@10 {
+		compatible = "sony,imx219";
+		reg = <0x10>;
+
+		clocks = <&clk_imx219_fixed>;
+		clock-names = "xclk";
+
+		port {
+			csi2_cam1: endpoint {
+				remote-endpoint = <&csi2rx1_in_sensor>;
+				link-frequencies = /bits/ 64 <456000000>;
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+	};
+};
+
+
+&cdns_csi2rx0 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi0_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx0_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam0>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+
+		csi0_port1: port@1 {
+			reg = <1>;
+			status = "disabled";
+		};
+
+		csi0_port2: port@2 {
+			reg = <2>;
+			status = "disabled";
+		};
+
+		csi0_port3: port@3 {
+			reg = <3>;
+			status = "disabled";
+		};
+
+		csi0_port4: port@4 {
+			reg = <4>;
+			status = "disabled";
+		};
+	};
+};
+
+&dphy0 {
+	status = "okay";
+};
+
+&ti_csi2rx0 {
+	status = "okay";
+};
+
+&cdns_csi2rx1 {
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		csi1_port0: port@0 {
+			reg = <0>;
+			status = "okay";
+
+			csi2rx1_in_sensor: endpoint {
+				remote-endpoint = <&csi2_cam1>;
+				bus-type = <4>; /* CSI2 DPHY. */
+				clock-lanes = <0>;
+				data-lanes = <1 2>;
+			};
+		};
+
+		csi1_port1: port@1 {
+			reg = <1>;
+			status = "disabled";
+		};
+
+		csi1_port2: port@2 {
+			reg = <2>;
+			status = "disabled";
+		};
+
+		csi1_port3: port@3 {
+			reg = <3>;
+			status = "disabled";
+		};
+
+		csi1_port4: port@4 {
+			reg = <4>;
+			status = "disabled";
+		};
+	};
+};
+
+&dphy1 {
+	status = "okay";
+};
+
+&ti_csi2rx1 {
+	status = "okay";
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
index 188dfe291a32..0c4575ad8d7c 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * J721E SK URL: https://www.ti.com/tool/SK-TDA4VM
  */
@@ -286,6 +286,15 @@
 			};
 		};
 	};
+
+	csi_mux: mux-controller {
+		compatible = "gpio-mux";
+		#mux-state-cells = <1>;
+		mux-gpios = <&main_gpio0 88 GPIO_ACTIVE_HIGH>;
+		idle-state = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&main_csi_mux_sel_pins_default>;
+	};
 };
 
 &main_pmx0 {
@@ -352,6 +361,12 @@
 		>;
 	};
 
+	main_csi_mux_sel_pins_default: main-csi-mux-sel-default-pins {
+		pinctrl-single,pins = <
+			J721E_IOPAD(0x164, PIN_OUTPUT, 7) /* (V29) RGMII5_TD2 */
+		>;
+	};
+
 	dp0_pins_default: dp0-default-pins {
 		pinctrl-single,pins = <
 			J721E_IOPAD(0x1c4, PIN_INPUT, 5) /* SPI0_CS1.DP0_HPD */
@@ -574,7 +589,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&pmic_irq_pins_default>;
 		interrupt-parent = <&wkup_gpio0>;
-		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
 		gpio-controller;
 		#gpio-cells = <2>;
 		ti,primary-pmic;
@@ -651,7 +666,7 @@
 		reg = <0x4c>;
 		system-power-controller;
 		interrupt-parent = <&wkup_gpio0>;
-		interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
 		gpio-controller;
 		#gpio-cells = <2>;
 		buck1234-supply = <&vsys_3v3>;
@@ -858,14 +873,14 @@
 		reg = <0x70>;
 
 		/* CSI0 I2C */
-		i2c@0 {
+		cam0_i2c: i2c@0 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0>;
 		};
 
 		/* CSI1 I2C */
-		i2c@1 {
+		cam1_i2c: i2c@1 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <1>;
@@ -1168,58 +1183,58 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &c66_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_0>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_0>;
 	memory-region = <&c66_0_dma_memory_region>,
 			<&c66_0_memory_region>;
 };
 
 &c66_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_1>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_1>;
 	memory-region = <&c66_1_dma_memory_region>,
 			<&c66_1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
index a75611eec791..1fae6495db07 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-som-p0.dtsi
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2019-2020 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2019-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Product Link: https://www.ti.com/tool/J721EXSOMXEVM
  */
@@ -549,58 +549,58 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &c66_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_0>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_0>;
 	memory-region = <&c66_0_dma_memory_region>,
 			<&c66_0_memory_region>;
 };
 
 &c66_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster3>, <&mbox_c66_1>;
+	mboxes = <&mailbox0_cluster3 &mbox_c66_1>;
 	memory-region = <&c66_1_dma_memory_region>,
 			<&c66_1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-thermal.dtsi
index c2523279001b..927f7614ae7a 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721e.dtsi b/arch/arm64/boot/dts/ti/k3-j721e.dtsi
index a200810df54a..5a72c518ceb6 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721E SoC Family
  *
- * Copyright (C) 2016-2019 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2016-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/interrupt-controller/irq.h>
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts
index c6b85bbf9a17..c5a0b7cbb14f 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Common Processor Board: https://www.ti.com/tool/J721EXCPXEVM
  */
@@ -147,6 +147,13 @@
 		>;
 	};
 
+	main_i2c5_pins_default: main-i2c5-default-pins {
+		pinctrl-single,pins = <
+			J721S2_IOPAD(0x01c, PIN_INPUT, 8) /* (Y24) MCAN15_TX.I2C5_SCL */
+			J721S2_IOPAD(0x018, PIN_INPUT, 8) /* (W23) MCAN14_RX.I2C5_SDA */
+		>;
+	};
+
 	main_mmc1_pins_default: main-mmc1-default-pins {
 		pinctrl-single,pins = <
 			J721S2_IOPAD(0x104, PIN_INPUT, 0) /* (P23) MMC1_CLK */
@@ -190,8 +197,6 @@
 &wkup_pmx2 {
 	wkup_uart0_pins_default: wkup-uart0-default-pins {
 		pinctrl-single,pins = <
-			J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (E25) WKUP_GPIO0_6.WKUP_UART0_CTSn */
-			J721S2_WKUP_IOPAD(0x074, PIN_OUTPUT, 0) /* (F28) WKUP_GPIO0_7.WKUP_UART0_RTSn */
 			J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (D28) WKUP_UART0_RXD */
 			J721S2_WKUP_IOPAD(0x04c, PIN_OUTPUT, 0) /* (D27) WKUP_UART0_TXD */
 		>;
@@ -356,6 +361,24 @@
 	};
 };
 
+&main_i2c5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c5_pins_default>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	exp5: gpio@20 {
+		compatible = "ti,tca6408";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "CSI2_EXP_RSTZ", "CSI2_EXP_A_GPIO0",
+				  "CSI2_EXP_A_GPIO1", "CSI2_EXP_A_GPIO2",
+				  "CSI2_EXP_B_GPIO1", "CSI2_EXP_B_GPIO2",
+				  "CSI2_EXP_B_GPIO3", "CSI2_EXP_B_GPIO4";
+	};
+};
+
 &main_sdhci0 {
 	/* eMMC */
 	status = "okay";
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-evm-gesi-exp-board.dtso b/arch/arm64/boot/dts/ti/k3-j721s2-evm-gesi-exp-board.dtso
index b78feea31b54..1be28283c7d9 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-evm-gesi-exp-board.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-evm-gesi-exp-board.dtso
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for MAIN CPSW2G using GESI Expansion Board with J7 common processor board.
  *
  * GESI Board Product Link: https://www.ti.com/tool/J7EXPCXEVM
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso b/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso
index 43568eb67d93..5ff390915b75 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-evm-pcie1-ep.dtso
@@ -1,11 +1,11 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /**
  * DT Overlay for enabling PCIE1 instance in Endpoint Configuration with the
  * J7 common processor board.
  *
  * J7 Common Processor Board Product Link: https://www.ti.com/tool/J721EXCPXEVM
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
index ea7f2b2ab165..b70c8615e3c1 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721S2 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/phy/phy-cadence.h>
@@ -45,7 +45,7 @@
 		ranges = <0x00 0x00 0x00104000 0x18000>;
 
 		usb_serdes_mux: mux-controller@0 {
-			compatible = "mmio-mux";
+			compatible = "reg-mux";
 			reg = <0x0 0x4>;
 			#mux-control-cells = <1>;
 			mux-reg-masks = <0x0 0x8000000>; /* USB0 to SERDES0 lane 1/3 mux */
@@ -58,11 +58,11 @@
 		};
 
 		serdes_ln_ctrl: mux-controller@80 {
-			compatible = "mmio-mux";
+			compatible = "reg-mux";
 			reg = <0x80 0x10>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x80 0x3>, <0x84 0x3>, /* SERDES0 lane0/1 select */
-					<0x88 0x3>, <0x8c 0x3>; /* SERDES0 lane2/3 select */
+			mux-reg-masks = <0x0 0x3>, <0x4 0x3>, /* SERDES0 lane0/1 select */
+					<0x8 0x3>, <0xc 0x3>; /* SERDES0 lane2/3 select */
 		};
 
 		ehrpwm_tbclk: clock-controller@140 {
@@ -716,6 +716,14 @@
 		status = "disabled";
 	};
 
+	vpu: video-codec@4210000 {
+		compatible = "ti,j721s2-wave521c", "cnm,wave521c";
+		reg = <0x00 0x4210000 0x00 0x10000>;
+		interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&k3_clks 179 2>;
+		power-domains = <&k3_pds 179 TI_SCI_PD_EXCLUSIVE>;
+	};
+
 	main_sdhci0: mmc@4f80000 {
 		compatible = "ti,j721e-sdhci-8bit";
 		reg = <0x00 0x04f80000 0x00 0x1000>,
@@ -1122,7 +1130,6 @@
 			ti,sci-dev-id = <225>;
 			ti,sci-rm-range-rchan = <0x21>;
 			ti,sci-rm-range-tchan = <0x22>;
-			status = "disabled";
 		};
 
 		cpts@310d0000 {
@@ -1233,6 +1240,128 @@
 		};
 	};
 
+	ti_csi2rx0: ticsi2rx@4500000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x04500000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x4940 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 38 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@4504000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x04504000 0x00 0x1000>;
+			clocks = <&k3_clks 38 3>, <&k3_clks 38 1>, <&k3_clks 38 3>,
+				<&k3_clks 38 3>, <&k3_clks 38 4>, <&k3_clks 38 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx1: ticsi2rx@4510000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x04510000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x4960 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 39 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx1: csi-bridge@4514000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x04514000 0x00 0x1000>;
+			clocks = <&k3_clks 39 3>, <&k3_clks 39 1>, <&k3_clks 39 3>,
+				<&k3_clks 39 3>, <&k3_clks 39 4>, <&k3_clks 39 4>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy1>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi1_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi1_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi1_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi1_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi1_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@4580000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x04580000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 152 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy1: phy@4590000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x04590000 0x00 0x1100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 153 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
 	serdes_wiz0: wiz@5060000 {
 		compatible = "ti,j721s2-wiz-10g";
 		#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
index 80aa33c58a45..eaf7f709440e 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721S2 SoC Family MCU/WAKEUP Domain peripherals
  *
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu_wakeup {
@@ -663,7 +663,7 @@
 		compatible = "ti,j7200-vtm";
 		reg = <0x00 0x42040000 0x0 0x350>,
 		      <0x00 0x42050000 0x0 0x350>;
-		power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>;
+		power-domains = <&k3_pds 180 TI_SCI_PD_SHARED>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
index da3237b23b63..623c8421525d 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-som-p0.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * SoM: https://www.ti.com/lit/zip/sprr439
  *
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 /dts-v1/;
@@ -504,51 +504,51 @@
 };
 
 &mcu_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core0>;
 	memory-region = <&mcu_r5fss0_core0_dma_memory_region>,
 			<&mcu_r5fss0_core0_memory_region>;
 };
 
 &mcu_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster0>, <&mbox_mcu_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster0 &mbox_mcu_r5fss0_core1>;
 	memory-region = <&mcu_r5fss0_core1_dma_memory_region>,
 			<&mcu_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss0_core0 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core0>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core0>;
 	memory-region = <&main_r5fss0_core0_dma_memory_region>,
 			<&main_r5fss0_core0_memory_region>;
 };
 
 &main_r5fss0_core1 {
-	mboxes = <&mailbox0_cluster1>, <&mbox_main_r5fss0_core1>;
+	mboxes = <&mailbox0_cluster1 &mbox_main_r5fss0_core1>;
 	memory-region = <&main_r5fss0_core1_dma_memory_region>,
 			<&main_r5fss0_core1_memory_region>;
 };
 
 &main_r5fss1_core0 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core0>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core0>;
 	memory-region = <&main_r5fss1_core0_dma_memory_region>,
 			<&main_r5fss1_core0_memory_region>;
 };
 
 &main_r5fss1_core1 {
-	mboxes = <&mailbox0_cluster2>, <&mbox_main_r5fss1_core1>;
+	mboxes = <&mailbox0_cluster2 &mbox_main_r5fss1_core1>;
 	memory-region = <&main_r5fss1_core1_dma_memory_region>,
 			<&main_r5fss1_core1_memory_region>;
 };
 
 &c71_0 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_0>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_0>;
 	memory-region = <&c71_0_dma_memory_region>,
 			<&c71_0_memory_region>;
 };
 
 &c71_1 {
 	status = "okay";
-	mboxes = <&mailbox0_cluster4>, <&mbox_c71_1>;
+	mboxes = <&mailbox0_cluster4 &mbox_c71_1>;
 	memory-region = <&c71_1_dma_memory_region>,
 			<&c71_1_memory_region>;
 };
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-thermal.dtsi
index f7b1a15b8fa0..e3ef61c1658f 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-j721s2.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2.dtsi
index 1f636acd4eee..be4502fe1c9d 100644
--- a/arch/arm64/boot/dts/ti/k3-j721s2.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721s2.dtsi
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J721S2 SoC Family
  *
  * TRM (SPRUJ28 NOVEMBER 2021): https://www.ti.com/lit/pdf/spruj28
  *
- * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2021-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  */
 
diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
new file mode 100644
index 000000000000..cee3a8661d5e
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts
@@ -0,0 +1,383 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Device Tree file for the J722S EVM
+ * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
+ *
+ * Schematics: https://www.ti.com/lit/zip/sprr495
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/net/ti-dp83867.h>
+#include "k3-j722s.dtsi"
+
+/ {
+	compatible = "ti,j722s-evm", "ti,j722s";
+	model = "Texas Instruments J722S EVM";
+
+	aliases {
+		serial0 = &wkup_uart0;
+		serial2 = &main_uart0;
+		mmc0 = &sdhci0;
+		mmc1 = &sdhci1;
+	};
+
+	chosen {
+		stdout-path = &main_uart0;
+	};
+
+	memory@80000000 {
+		/* 8G RAM */
+		reg = <0x00000000 0x80000000 0x00000000 0x80000000>,
+		      <0x00000008 0x80000000 0x00000001 0x80000000>;
+		device_type = "memory";
+		bootph-pre-ram;
+	};
+
+	reserved_memory: reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		secure_tfa_ddr: tfa@9e780000 {
+			reg = <0x00 0x9e780000 0x00 0x80000>;
+			no-map;
+		};
+
+		secure_ddr: optee@9e800000 {
+			reg = <0x00 0x9e800000 0x00 0x01800000>;
+			no-map;
+		};
+
+		wkup_r5fss0_core0_memory_region: r5f-memory@a0100000 {
+			compatible = "shared-dma-pool";
+			reg = <0x00 0xa0100000 0x00 0xf00000>;
+			no-map;
+		};
+
+	};
+
+	vmain_pd: regulator-0 {
+		/* TPS65988 PD CONTROLLER OUTPUT */
+		compatible = "regulator-fixed";
+		regulator-name = "vmain_pd";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		regulator-always-on;
+		regulator-boot-on;
+		bootph-all;
+	};
+
+	vsys_5v0: regulator-vsys5v0 {
+		/* Output of LM5140 */
+		compatible = "regulator-fixed";
+		regulator-name = "vsys_5v0";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+		vin-supply = <&vmain_pd>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vdd_mmc1: regulator-mmc1 {
+		/* TPS22918DBVR */
+		compatible = "regulator-fixed";
+		regulator-name = "vdd_mmc1";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		enable-active-high;
+		gpio = <&exp1 15 GPIO_ACTIVE_HIGH>;
+		bootph-all;
+	};
+
+	vdd_sd_dv: regulator-TLV71033 {
+		compatible = "regulator-gpio";
+		regulator-name = "tlv71033";
+		pinctrl-names = "default";
+		pinctrl-0 = <&vdd_sd_dv_pins_default>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-boot-on;
+		vin-supply = <&vsys_5v0>;
+		gpios = <&main_gpio0 70 GPIO_ACTIVE_HIGH>;
+		states = <1800000 0x0>,
+			 <3300000 0x1>;
+	};
+
+	vsys_io_1v8: regulator-vsys-io-1v8 {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys_io_1v8";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+
+	vsys_io_1v2: regulator-vsys-io-1v2 {
+		compatible = "regulator-fixed";
+		regulator-name = "vsys_io_1v2";
+		regulator-min-microvolt = <1200000>;
+		regulator-max-microvolt = <1200000>;
+		regulator-always-on;
+		regulator-boot-on;
+	};
+};
+
+&main_pmx0 {
+
+	main_i2c0_pins_default: main-i2c0-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x01e0, PIN_INPUT_PULLUP, 0) /* (D23) I2C0_SCL */
+			J722S_IOPAD(0x01e4, PIN_INPUT_PULLUP, 0) /* (B22) I2C0_SDA */
+		>;
+		bootph-all;
+	};
+
+	main_uart0_pins_default: main-uart0-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x01c8, PIN_INPUT, 0)	/* (A22) UART0_RXD */
+			J722S_IOPAD(0x01cc, PIN_OUTPUT, 0)	/* (B22) UART0_TXD */
+		>;
+		bootph-all;
+	};
+
+	vdd_sd_dv_pins_default: vdd-sd-dv-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x0120, PIN_INPUT, 7) /* (F27) MMC2_CMD.GPIO0_70 */
+		>;
+		bootph-all;
+	};
+
+	main_mmc1_pins_default: main-mmc1-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x023c, PIN_INPUT, 0) /* (H22) MMC1_CMD */
+			J722S_IOPAD(0x0234, PIN_OUTPUT, 0) /* (H24) MMC1_CLK */
+			J722S_IOPAD(0x0230, PIN_INPUT, 0) /* (H23) MMC1_DAT0 */
+			J722S_IOPAD(0x022c, PIN_INPUT_PULLUP, 0) /* (H20) MMC1_DAT1 */
+			J722S_IOPAD(0x0228, PIN_INPUT_PULLUP, 0) /* (J23) MMC1_DAT2 */
+			J722S_IOPAD(0x0224, PIN_INPUT_PULLUP, 0) /* (H25) MMC1_DAT3 */
+			J722S_IOPAD(0x0240, PIN_INPUT, 0) /* (B24) MMC1_SDCD */
+		>;
+		bootph-all;
+	};
+
+	mdio_pins_default: mdio-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x0160, PIN_OUTPUT, 0) /* (AC24) MDIO0_MDC */
+			J722S_IOPAD(0x015c, PIN_INPUT, 0) /* (AD25) MDIO0_MDIO */
+		>;
+	};
+
+	ospi0_pins_default: ospi0-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x0000, PIN_OUTPUT, 0) /* (L24) OSPI0_CLK */
+			J722S_IOPAD(0x002c, PIN_OUTPUT, 0) /* (K26) OSPI0_CSn0 */
+			J722S_IOPAD(0x000c, PIN_INPUT, 0) /* (K27) OSPI0_D0 */
+			J722S_IOPAD(0x0010, PIN_INPUT, 0) /* (L27) OSPI0_D1 */
+			J722S_IOPAD(0x0014, PIN_INPUT, 0) /* (L26) OSPI0_D2 */
+			J722S_IOPAD(0x0018, PIN_INPUT, 0) /* (L25) OSPI0_D3 */
+			J722S_IOPAD(0x001c, PIN_INPUT, 0) /* (L21) OSPI0_D4 */
+			J722S_IOPAD(0x0020, PIN_INPUT, 0) /* (M26) OSPI0_D5 */
+			J722S_IOPAD(0x0024, PIN_INPUT, 0) /* (N27) OSPI0_D6 */
+			J722S_IOPAD(0x0028, PIN_INPUT, 0) /* (M27) OSPI0_D7 */
+			J722S_IOPAD(0x0008, PIN_INPUT, 0) /* (L22) OSPI0_DQS */
+		>;
+		bootph-all;
+	};
+
+	rgmii1_pins_default: rgmii1-default-pins {
+		pinctrl-single,pins = <
+			J722S_IOPAD(0x014c, PIN_INPUT, 0) /* (AC25) RGMII1_RD0 */
+			J722S_IOPAD(0x0150, PIN_INPUT, 0) /* (AD27) RGMII1_RD1 */
+			J722S_IOPAD(0x0154, PIN_INPUT, 0) /* (AE24) RGMII1_RD2 */
+			J722S_IOPAD(0x0158, PIN_INPUT, 0) /* (AE26) RGMII1_RD3 */
+			J722S_IOPAD(0x0148, PIN_INPUT, 0) /* (AE27) RGMII1_RXC */
+			J722S_IOPAD(0x0144, PIN_INPUT, 0) /* (AD23) RGMII1_RX_CTL */
+			J722S_IOPAD(0x0134, PIN_OUTPUT, 0) /* (AF27) RGMII1_TD0 */
+			J722S_IOPAD(0x0138, PIN_OUTPUT, 0) /* (AE23) RGMII1_TD1 */
+			J722S_IOPAD(0x013c, PIN_OUTPUT, 0) /* (AG25) RGMII1_TD2 */
+			J722S_IOPAD(0x0140, PIN_OUTPUT, 0) /* (AF24) RGMII1_TD3 */
+			J722S_IOPAD(0x0130, PIN_OUTPUT, 0) /* (AG26) RGMII1_TXC */
+			J722S_IOPAD(0x012c, PIN_OUTPUT, 0) /* (AF25) RGMII1_TX_CTL */
+		>;
+	};
+};
+
+&cpsw3g {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&rgmii1_pins_default>;
+};
+
+&cpsw3g_mdio {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mdio_pins_default>;
+
+	cpsw3g_phy0: ethernet-phy@0 {
+		reg = <0>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_00_NS>;
+		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+		ti,min-output-impedance;
+	};
+};
+
+&cpsw_port1 {
+	phy-mode = "rgmii-rxid";
+	phy-handle = <&cpsw3g_phy0>;
+};
+
+&cpsw_port2 {
+	status = "disabled";
+};
+
+&main_gpio1 {
+	status = "okay";
+};
+
+&main_uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_uart0_pins_default>;
+	status = "okay";
+	bootph-all;
+};
+
+&mcu_pmx0 {
+
+	wkup_uart0_pins_default: wkup-uart0-default-pins {
+		pinctrl-single,pins = <
+			J722S_MCU_IOPAD(0x02c, PIN_INPUT, 0)	/* (C7) WKUP_UART0_CTSn */
+			J722S_MCU_IOPAD(0x030, PIN_OUTPUT, 0)	/* (C6) WKUP_UART0_RTSn */
+			J722S_MCU_IOPAD(0x024, PIN_INPUT, 0)	/* (D8) WKUP_UART0_RXD */
+			J722S_MCU_IOPAD(0x028, PIN_OUTPUT, 0)	/* (D7) WKUP_UART0_TXD */
+		>;
+		bootph-all;
+	};
+
+	wkup_i2c0_pins_default: wkup-i2c0-default-pins {
+		pinctrl-single,pins = <
+			J722S_MCU_IOPAD(0x04c, PIN_INPUT_PULLUP, 0)	/* (C7) WKUP_I2C0_SCL */
+			J722S_MCU_IOPAD(0x050, PIN_INPUT_PULLUP, 0)	/* (C6) WKUP_I2C1_SDA */
+		>;
+		bootph-all;
+	};
+};
+
+&wkup_uart0 {
+	/* WKUP UART0 is used by Device Manager firmware */
+	pinctrl-names = "default";
+	pinctrl-0 = <&wkup_uart0_pins_default>;
+	status = "reserved";
+	bootph-all;
+};
+
+&wkup_i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&wkup_i2c0_pins_default>;
+	clock-frequency = <400000>;
+	status = "okay";
+	bootph-all;
+};
+
+&main_i2c0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c0_pins_default>;
+	clock-frequency = <400000>;
+	status = "okay";
+	bootph-all;
+
+	exp1: gpio@23 {
+		compatible = "ti,tca6424";
+		reg = <0x23>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "TRC_MUX_SEL", "OSPI/ONAND_MUX_SEL",
+				  "MCASP1_FET_SEL", "CTRL_PM_I2C_OE#",
+				  "CSI_VIO_SEL", "USB2.0_MUX_SEL",
+				  "CSI01_MUX_SEL_2", "CSI23_MUX_SEL_2",
+				  "LMK1_OE1", "LMK1_OE0",
+				  "LMK2_OE0", "LMK2_OE1",
+				  "GPIO_RGMII1_RST#", "GPIO_AUD_RSTn",
+				  "GPIO_eMMC_RSTn", "GPIO_uSD_PWR_EN",
+				  "USER_LED2", "MCAN0_STB",
+				  "PCIe0_1L_RC_RSTz", "PCIe0_1L_PRSNT#",
+				  "ENET1_EXP_SPARE2", "ENET1_EXP_PWRDN",
+				  "PD_I2ENET1_I2CMUX_SELC_IRQ", "ENET1_EXP_RESETZ";
+	};
+};
+
+&ospi0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&ospi0_pins_default>;
+	status = "okay";
+
+	flash@0 {
+		compatible = "jedec,spi-nor";
+		reg = <0x0>;
+		spi-tx-bus-width = <8>;
+		spi-rx-bus-width = <8>;
+		spi-max-frequency = <25000000>;
+		cdns,tshsl-ns = <60>;
+		cdns,tsd2d-ns = <60>;
+		cdns,tchsh-ns = <60>;
+		cdns,tslch-ns = <60>;
+		cdns,read-delay = <4>;
+		bootph-all;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "ospi.tiboot3";
+				reg = <0x00 0x80000>;
+			};
+
+			partition@80000 {
+				label = "ospi.tispl";
+				reg = <0x80000 0x200000>;
+			};
+
+			partition@280000 {
+				label = "ospi.u-boot";
+				reg = <0x280000 0x400000>;
+			};
+
+			partition@680000 {
+				label = "ospi.env";
+				reg = <0x680000 0x40000>;
+			};
+
+			partition@6c0000 {
+				label = "ospi.env.backup";
+				reg = <0x6c0000 0x40000>;
+			};
+
+			partition@800000 {
+				label = "ospi.rootfs";
+				reg = <0x800000 0x37c0000>;
+			};
+
+			partition@3fc0000 {
+				label = "ospi.phypattern";
+				reg = <0x3fc0000 0x40000>;
+			};
+		};
+	};
+
+};
+
+&sdhci1 {
+	/* SD/MMC */
+	vmmc-supply = <&vdd_mmc1>;
+	vqmmc-supply = <&vdd_sd_dv>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_mmc1_pins_default>;
+	ti,driver-strength-ohm = <50>;
+	disable-wp;
+	no-1-8-v;
+	status = "okay";
+	bootph-all;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j722s.dtsi b/arch/arm64/boot/dts/ti/k3-j722s.dtsi
new file mode 100644
index 000000000000..c75744edb143
--- /dev/null
+++ b/arch/arm64/boot/dts/ti/k3-j722s.dtsi
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Device Tree Source for J722S SoC Family
+ *
+ * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
+
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/soc/ti,sci_pm_domain.h>
+
+#include "k3-am62p5.dtsi"
+
+/ {
+	model = "Texas Instruments K3 J722S SoC";
+	compatible = "ti,j722s";
+
+	cbass_main: bus@f0000 {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+
+		ranges = <0x00 0x000f0000 0x00 0x000f0000 0x00 0x00030000>, /* Main MMRs */
+			 <0x00 0x00420000 0x00 0x00420000 0x00 0x00001000>, /* ESM0 */
+			 <0x00 0x00600000 0x00 0x00600000 0x00 0x00001100>, /* GPIO */
+			 <0x00 0x00703000 0x00 0x00703000 0x00 0x00000200>, /* USB0 debug trace */
+			 <0x00 0x0070c000 0x00 0x0070c000 0x00 0x00000200>, /* USB1 debug trace */
+			 <0x00 0x00a40000 0x00 0x00a40000 0x00 0x00000800>, /* Timesync router */
+			 <0x00 0x01000000 0x00 0x01000000 0x00 0x01b28400>, /* First peripheral window */
+			 <0x00 0x08000000 0x00 0x08000000 0x00 0x00200000>, /* Main CPSW */
+			 <0x00 0x0d000000 0x00 0x0d000000 0x00 0x00800000>, /* PCIE_0 */
+			 <0x00 0x0e000000 0x00 0x0e000000 0x00 0x01d20000>, /* Second peripheral window */
+			 <0x00 0x0fd80000 0x00 0x0fd80000 0x00 0x00080000>, /* GPU */
+			 <0x00 0x0fd20000 0x00 0x0fd20000 0x00 0x00000100>, /* JPEGENC0_CORE */
+			 <0x00 0x0fd20200 0x00 0x0fd20200 0x00 0x00000200>, /* JPEGENC0_CORE_MMU */
+			 <0x00 0x20000000 0x00 0x20000000 0x00 0x0a008000>, /* Third peripheral window */
+			 <0x00 0x30040000 0x00 0x30040000 0x00 0x00080000>, /* PRUSS-M */
+			 <0x00 0x301C0000 0x00 0x301C0000 0x00 0x00001000>, /* DPHY-TX */
+			 <0x00 0x30101000 0x00 0x30101000 0x00 0x00080100>, /* CSI window */
+			 <0x00 0x30200000 0x00 0x30200000 0x00 0x00010000>, /* DSS */
+			 <0x00 0x30210000 0x00 0x30210000 0x00 0x00010000>, /* VPU */
+			 <0x00 0x30220000 0x00 0x30220000 0x00 0x00010000>, /* DSS1 */
+			 <0x00 0x30270000 0x00 0x30270000 0x00 0x00010000>, /* DSI-base1 */
+			 <0x00 0x30500000 0x00 0x30500000 0x00 0x00100000>, /* DSI-base2 */
+			 <0x00 0x31000000 0x00 0x31000000 0x00 0x00050000>, /* USB0 DWC3 Core window */
+			 <0x00 0x31200000 0x00 0x31200000 0x00 0x00040000>, /* USB1 DWC3 Core window */
+			 <0x00 0x40900000 0x00 0x40900000 0x00 0x00030000>, /* SA3UL */
+			 <0x00 0x43600000 0x00 0x43600000 0x00 0x00010000>, /* SA3 sproxy data */
+			 <0x00 0x44043000 0x00 0x44043000 0x00 0x00000fe0>, /* TI SCI DEBUG */
+			 <0x00 0x44860000 0x00 0x44860000 0x00 0x00040000>, /* SA3 sproxy config */
+			 <0x00 0x48000000 0x00 0x48000000 0x00 0x06408000>, /* DMSS */
+			 <0x00 0x60000000 0x00 0x60000000 0x00 0x08000000>, /* FSS0 DAT1 */
+			 <0x00 0x68000000 0x00 0x68000000 0x00 0x08000000>, /* PCIe0 DAT0 */
+			 <0x00 0x70000000 0x00 0x70000000 0x00 0x00040000>, /* OCSRAM */
+			 <0x00 0x78400000 0x00 0x78400000 0x00 0x00008000>, /* MAIN R5FSS0 ATCM */
+			 <0x00 0x78500000 0x00 0x78500000 0x00 0x00008000>, /* MAIN R5FSS0 BTCM */
+			 <0x00 0x7e000000 0x00 0x7e000000 0x00 0x00200000>, /* C7X_0 L2SRAM */
+			 <0x00 0x7e200000 0x00 0x7e200000 0x00 0x00200000>, /* C7X_1 L2SRAM */
+			 <0x01 0x00000000 0x01 0x00000000 0x00 0x00310000>, /* A53 PERIPHBASE */
+			 <0x05 0x00000000 0x05 0x00000000 0x01 0x00000000>, /* FSS0 DAT3 */
+			 <0x06 0x00000000 0x06 0x00000000 0x01 0x00000000>, /* PCIe0 DAT1 */
+
+			 /* MCU Domain Range */
+			 <0x00 0x04000000 0x00 0x04000000 0x00 0x01ff1400>,
+			 <0x00 0x79000000 0x00 0x79000000 0x00 0x00008000>,
+			 <0x00 0x79020000 0x00 0x79020000 0x00 0x00008000>,
+			 <0x00 0x79100000 0x00 0x79100000 0x00 0x00040000>,
+			 <0x00 0x79140000 0x00 0x79140000 0x00 0x00040000>,
+
+			 /* Wakeup Domain Range */
+			 <0x00 0x00b00000 0x00 0x00b00000 0x00 0x00002400>,
+			 <0x00 0x2b000000 0x00 0x2b000000 0x00 0x00300400>,
+			 <0x00 0x43000000 0x00 0x43000000 0x00 0x00020000>,
+			 <0x00 0x78000000 0x00 0x78000000 0x00 0x00008000>,
+			 <0x00 0x78100000 0x00 0x78100000 0x00 0x00008000>;
+	};
+};
+
+/* Main domain overrides */
+
+&inta_main_dmss {
+	ti,interrupt-ranges = <7 71 21>;
+};
+
+&oc_sram {
+	reg = <0x00 0x70000000 0x00 0x40000>;
+	ranges = <0x00 0x00 0x70000000 0x40000>;
+};
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
index f34b92acc56d..81fd7afac8c5 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts
@@ -1,6 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  * EVM Board Schematics: https://www.ti.com/lit/zip/sprr458
  */
@@ -31,6 +31,7 @@
 
 	memory@80000000 {
 		device_type = "memory";
+		bootph-all;
 		/* 32G RAM */
 		reg = <0x00 0x80000000 0x00 0x80000000>,
 		      <0x08 0x80000000 0x07 0x80000000>;
@@ -296,6 +297,13 @@
 		>;
 	};
 
+	main_i2c5_pins_default: main-i2c5-default-pins {
+		pinctrl-single,pins = <
+			J784S4_IOPAD(0x01c, PIN_INPUT, 8) /* (AG34) MCAN15_TX.I2C5_SCL */
+			J784S4_IOPAD(0x018, PIN_INPUT, 8) /* (AK36) MCAN14_RX.I2C5_SDA */
+		>;
+	};
+
 	main_mmc1_pins_default: main-mmc1-default-pins {
 		bootph-all;
 		pinctrl-single,pins = <
@@ -335,8 +343,6 @@
 	wkup_uart0_pins_default: wkup-uart0-default-pins {
 		bootph-all;
 		pinctrl-single,pins = <
-			J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (L37) WKUP_GPIO0_6.WKUP_UART0_CTSn */
-			J721S2_WKUP_IOPAD(0x074, PIN_INPUT, 0) /* (L36) WKUP_GPIO0_7.WKUP_UART0_RTSn */
 			J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (K35) WKUP_UART0_RXD */
 			J721S2_WKUP_IOPAD(0x04c, PIN_INPUT, 0) /* (K34) WKUP_UART0_TXD */
 		>;
@@ -760,6 +766,24 @@
 	};
 };
 
+&main_i2c5 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&main_i2c5_pins_default>;
+	clock-frequency = <400000>;
+	status = "okay";
+
+	exp5: gpio@20 {
+		compatible = "ti,tca6408";
+		reg = <0x20>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-line-names = "CSI2_EXP_RSTZ", "CSI2_EXP_A_GPIO0",
+				  "CSI2_EXP_A_GPIO1", "CSI2_EXP_A_GPIO3",
+				  "CSI2_EXP_B_GPIO1", "CSI2_EXP_B_GPIO2",
+				  "CSI2_EXP_B_GPIO3", "CSI2_EXP_B_GPIO4";
+	};
+};
+
 &main_sdhci0 {
 	bootph-all;
 	/* eMMC */
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
index f2b720ed1e4f..b67c37460a73 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J784S4 SoC Family Main Domain peripherals
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #include <dt-bindings/mux/mux.h>
@@ -52,12 +52,12 @@
 			compatible = "reg-mux";
 			reg = <0x00004080 0x30>;
 			#mux-control-cells = <1>;
-			mux-reg-masks = <0x4080 0x3>, <0x4084 0x3>, /* SERDES0 lane0/1 select */
-					<0x4088 0x3>, <0x408c 0x3>, /* SERDES0 lane2/3 select */
-					<0x4090 0x3>, <0x4094 0x3>, /* SERDES1 lane0/1 select */
-					<0x4098 0x3>, <0x409c 0x3>, /* SERDES1 lane2/3 select */
-					<0x40a0 0x3>, <0x40a4 0x3>, /* SERDES2 lane0/1 select */
-					<0x40a8 0x3>, <0x40ac 0x3>; /* SERDES2 lane2/3 select */
+			mux-reg-masks = <0x0 0x3>, <0x4 0x3>, /* SERDES0 lane0/1 select */
+					<0x8 0x3>, <0xc 0x3>, /* SERDES0 lane2/3 select */
+					<0x10 0x3>, <0x14 0x3>, /* SERDES1 lane0/1 select */
+					<0x18 0x3>, <0x1c 0x3>, /* SERDES1 lane2/3 select */
+					<0x20 0x3>, <0x24 0x3>, /* SERDES2 lane0/1 select */
+					<0x28 0x3>, <0x2c 0x3>; /* SERDES2 lane2/3 select */
 			idle-states = <J784S4_SERDES0_LANE0_PCIE1_LANE0>,
 				      <J784S4_SERDES0_LANE1_PCIE1_LANE1>,
 				      <J784S4_SERDES0_LANE2_IP3_UNUSED>,
@@ -662,6 +662,204 @@
 		status = "disabled";
 	};
 
+	ti_csi2rx0: ticsi2rx@4500000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x04500000 0x00 0x00001000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x4940 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 72 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx0: csi-bridge@4504000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x04504000 0x00 0x00001000>;
+			clocks = <&k3_clks 72 2>, <&k3_clks 72 0>, <&k3_clks 72 2>,
+				<&k3_clks 72 2>, <&k3_clks 72 3>, <&k3_clks 72 3>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy0>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi0_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi0_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi0_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi0_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi0_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx1: ticsi2rx@4510000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x04510000 0x00 0x1000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x4960 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 73 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx1: csi-bridge@4514000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x04514000 0x00 0x00001000>;
+			clocks = <&k3_clks 73 2>, <&k3_clks 73 0>, <&k3_clks 73 2>,
+				<&k3_clks 73 2>, <&k3_clks 73 3>, <&k3_clks 73 3>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy1>;
+			phy-names = "dphy";
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi1_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi1_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi1_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi1_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi1_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	ti_csi2rx2: ticsi2rx@4520000 {
+		compatible = "ti,j721e-csi2rx-shim";
+		reg = <0x00 0x04520000 0x00 0x00001000>;
+		ranges;
+		#address-cells = <2>;
+		#size-cells = <2>;
+		dmas = <&main_bcdma_csi 0 0x4980 0>;
+		dma-names = "rx0";
+		power-domains = <&k3_pds 74 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+
+		cdns_csi2rx2: csi-bridge@4524000 {
+			compatible = "ti,j721e-csi2rx", "cdns,csi2rx";
+			reg = <0x00 0x04524000 0x00 0x00001000>;
+			clocks = <&k3_clks 74 2>, <&k3_clks 74 0>, <&k3_clks 74 2>,
+				<&k3_clks 74 2>, <&k3_clks 74 3>, <&k3_clks 74 3>;
+			clock-names = "sys_clk", "p_clk", "pixel_if0_clk",
+				"pixel_if1_clk", "pixel_if2_clk", "pixel_if3_clk";
+			phys = <&dphy2>;
+			phy-names = "dphy";
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				csi2_port0: port@0 {
+					reg = <0>;
+					status = "disabled";
+				};
+
+				csi2_port1: port@1 {
+					reg = <1>;
+					status = "disabled";
+				};
+
+				csi2_port2: port@2 {
+					reg = <2>;
+					status = "disabled";
+				};
+
+				csi2_port3: port@3 {
+					reg = <3>;
+					status = "disabled";
+				};
+
+				csi2_port4: port@4 {
+					reg = <4>;
+					status = "disabled";
+				};
+			};
+		};
+	};
+
+	dphy0: phy@4580000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x04580000 0x00 0x00001100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 212 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy1: phy@4590000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x04590000 0x00 0x00001100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 213 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	dphy2: phy@45a0000 {
+		compatible = "cdns,dphy-rx";
+		reg = <0x00 0x045a0000 0x00 0x00001100>;
+		#phy-cells = <0>;
+		power-domains = <&k3_pds 214 TI_SCI_PD_EXCLUSIVE>;
+		status = "disabled";
+	};
+
+	vpu0: video-codec@4210000 {
+		compatible = "ti,j721s2-wave521c", "cnm,wave521c";
+		reg = <0x00 0x4210000 0x00 0x10000>;
+		interrupts = <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&k3_clks 241 2>;
+		power-domains = <&k3_pds 241 TI_SCI_PD_EXCLUSIVE>;
+	};
+
+	vpu1: video-codec@4220000 {
+		compatible = "ti,j721s2-wave521c", "cnm,wave521c";
+		reg = <0x00 0x4220000 0x00 0x10000>;
+		interrupts = <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&k3_clks 242 2>;
+		power-domains = <&k3_pds 242 TI_SCI_PD_EXCLUSIVE>;
+	};
+
 	main_sdhci0: mmc@4f80000 {
 		compatible = "ti,j721e-sdhci-8bit";
 		reg = <0x00 0x04f80000 0x00 0x1000>,
@@ -1224,7 +1422,6 @@
 			ti,sci-dev-id = <281>;
 			ti,sci-rm-range-rchan = <0x21>;
 			ti,sci-rm-range-tchan = <0x22>;
-			status = "disabled";
 		};
 
 		cpts@310d0000 {
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
index 3902a921d7e5..77a8d99139ec 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J784S4 SoC Family MCU/WAKEUP Domain peripherals
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 &cbass_mcu_wakeup {
@@ -628,7 +628,7 @@
 		compatible = "ti,j7200-vtm";
 		reg = <0x00 0x42040000 0x00 0x350>,
 		      <0x00 0x42050000 0x00 0x350>;
-		power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>;
+		power-domains = <&k3_pds 243 TI_SCI_PD_SHARED>;
 		#thermal-sensor-cells = <1>;
 	};
 
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-thermal.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-thermal.dtsi
index f7b1a15b8fa0..e3ef61c1658f 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4-thermal.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4-thermal.dtsi
@@ -1,4 +1,7 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
+ */
 
 #include <dt-bindings/thermal/thermal.h>
 
diff --git a/arch/arm64/boot/dts/ti/k3-j784s4.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4.dtsi
index 4398c3a463e1..6e2e92ffe745 100644
--- a/arch/arm64/boot/dts/ti/k3-j784s4.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j784s4.dtsi
@@ -1,10 +1,10 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Device Tree Source for J784S4 SoC Family
  *
  * TRM (SPRUJ43 JULY 2022): https://www.ti.com/lit/zip/spruj52
  *
- * Copyright (C) 2022 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2022-2024 Texas Instruments Incorporated - https://www.ti.com/
  *
  */
 
@@ -235,6 +235,8 @@
 		ranges = <0x00 0x00100000 0x00 0x00100000 0x00 0x00020000>, /* ctrl mmr */
 			 <0x00 0x00600000 0x00 0x00600000 0x00 0x00031100>, /* GPIO */
 			 <0x00 0x01000000 0x00 0x01000000 0x00 0x0d000000>, /* Most peripherals */
+			 <0x00 0x04210000 0x00 0x04210000 0x00 0x00010000>, /* VPU0 */
+			 <0x00 0x04220000 0x00 0x04220000 0x00 0x00010000>, /* VPU1 */
 			 <0x00 0x0d000000 0x00 0x0d000000 0x00 0x01000000>, /* PCIe Core*/
 			 <0x00 0x10000000 0x00 0x10000000 0x00 0x08000000>, /* PCIe0 DAT0 */
 			 <0x00 0x18000000 0x00 0x18000000 0x00 0x08000000>, /* PCIe1 DAT0 */
diff --git a/arch/arm64/boot/dts/ti/k3-pinctrl.h b/arch/arm64/boot/dts/ti/k3-pinctrl.h
index 2a4e0e084d69..4cd2df467d0b 100644
--- a/arch/arm64/boot/dts/ti/k3-pinctrl.h
+++ b/arch/arm64/boot/dts/ti/k3-pinctrl.h
@@ -1,9 +1,9 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 /*
  * This header provides constants for pinctrl bindings for TI's K3 SoC
  * family.
  *
- * Copyright (C) 2018-2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2018-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 #ifndef DTS_ARM64_TI_K3_PINCTRL_H
 #define DTS_ARM64_TI_K3_PINCTRL_H
@@ -59,6 +59,9 @@
 #define J721S2_IOPAD(pa, val, muxmode)		(((pa) & 0x1fff)) ((val) | (muxmode))
 #define J721S2_WKUP_IOPAD(pa, val, muxmode)	(((pa) & 0x1fff)) ((val) | (muxmode))
 
+#define J722S_IOPAD(pa, val, muxmode)		(((pa) & 0x1fff)) ((val) | (muxmode))
+#define J722S_MCU_IOPAD(pa, val, muxmode)	(((pa) & 0x1fff)) ((val) | (muxmode))
+
 #define J784S4_IOPAD(pa, val, muxmode)		(((pa) & 0x1fff)) ((val) | (muxmode))
 #define J784S4_WKUP_IOPAD(pa, val, muxmode)	(((pa) & 0x1fff)) ((val) | (muxmode))
 
diff --git a/arch/arm64/boot/dts/ti/k3-serdes.h b/arch/arm64/boot/dts/ti/k3-serdes.h
index 21b4886c47ba..a011ad893b44 100644
--- a/arch/arm64/boot/dts/ti/k3-serdes.h
+++ b/arch/arm64/boot/dts/ti/k3-serdes.h
@@ -1,8 +1,8 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 /*
  * This header provides constants for SERDES MUX for TI SoCs
  *
- * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/
+ * Copyright (C) 2023-2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef DTS_ARM64_TI_K3_SERDES_H
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
index ccaca29200bb..dd4569e7bd95 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi
@@ -230,18 +230,30 @@
 
 &uart0 {
 	clocks = <&zynqmp_clk UART0_REF>, <&zynqmp_clk LPD_LSBUS>;
+	assigned-clocks = <&zynqmp_clk UART0_REF>;
 };
 
 &uart1 {
 	clocks = <&zynqmp_clk UART1_REF>, <&zynqmp_clk LPD_LSBUS>;
+	assigned-clocks = <&zynqmp_clk UART1_REF>;
 };
 
-&dwc3_0 {
+&usb0 {
 	clocks = <&zynqmp_clk USB0_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>;
+	assigned-clocks = <&zynqmp_clk USB0_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>;
 };
 
-&dwc3_1 {
+&dwc3_0 {
+	clocks = <&zynqmp_clk USB3_DUAL_REF>;
+};
+
+&usb1 {
 	clocks = <&zynqmp_clk USB1_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>;
+	assigned-clocks = <&zynqmp_clk USB1_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>;
+};
+
+&dwc3_1 {
+	clocks = <&zynqmp_clk USB3_DUAL_REF>;
 };
 
 &watchdog0 {
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
index 92f4190d564d..d7535a77b45e 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revA.dtso
@@ -139,7 +139,7 @@
 	bus-width = <4>;
 };
 
-&gem3 { /* required by spec */
+&gem3 {
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gem3_default>;
@@ -166,9 +166,28 @@
 	};
 };
 
-&pinctrl0 { /* required by spec */
+&pinctrl0 {
 	status = "okay";
 
+	pinctrl_gpio0_default: gpio0-default {
+                conf {
+                        groups = "gpio0_38_grp";
+                        bias-pull-up;
+                        power-source = <IO_STANDARD_LVCMOS18>;
+                };
+
+                mux {
+                        groups = "gpio0_38_grp";
+                        function = "gpio0";
+                };
+
+                conf-tx {
+                        pins = "MIO38";
+                        bias-disable;
+                        output-enable;
+                };
+        };
+
 	pinctrl_uart1_default: uart1-default {
 		conf {
 			groups = "uart1_9_grp";
@@ -185,6 +204,7 @@
 		conf-tx {
 			pins = "MIO36";
 			bias-disable;
+			output-enable;
 		};
 
 		mux {
@@ -207,7 +227,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		conf {
 			groups = "gpio0_24_grp", "gpio0_25_grp";
 			slew-rate = <SLEW_RATE_SLOW>;
@@ -236,6 +256,7 @@
 		conf-bootstrap {
 			pins = "MIO71", "MIO73", "MIO75";
 			bias-disable;
+			output-enable;
 			low-power-disable;
 		};
 
@@ -243,6 +264,7 @@
 			pins = "MIO64", "MIO65", "MIO66",
 				"MIO67", "MIO68", "MIO69";
 			bias-disable;
+			output-enable;
 			low-power-enable;
 		};
 
@@ -251,6 +273,7 @@
 			slew-rate = <SLEW_RATE_SLOW>;
 			power-source = <IO_STANDARD_LVCMOS18>;
 			bias-disable;
+			output-enable;
 		};
 
 		mux-mdio {
@@ -281,6 +304,7 @@
 			pins = "MIO54", "MIO56", "MIO57", "MIO58", "MIO59",
 			"MIO60", "MIO61", "MIO62", "MIO63";
 			bias-disable;
+			output-enable;
 			drive-strength = <4>;
 			slew-rate = <SLEW_RATE_SLOW>;
 		};
@@ -319,6 +343,12 @@
 	};
 };
 
+&gpio {
+        status = "okay";
+        pinctrl-names = "default";
+        pinctrl-0 = <&pinctrl_gpio0_default>;
+};
+
 &uart1 {
 	status = "okay";
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
index f88b71f5b07a..a7b8fffad499 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-sck-kv-g-revB.dtso
@@ -94,6 +94,7 @@
 	pinctrl-0 = <&pinctrl_usb0_default>;
 	phy-names = "usb3-phy";
 	phys = <&psgtr 2 PHY_TYPE_USB3 0 1>;
+	assigned-clock-rates = <250000000>, <20000000>;
 };
 
 &dwc3_0 {
@@ -122,7 +123,7 @@
 	bus-width = <4>;
 };
 
-&gem3 { /* required by spec */
+&gem3 {
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gem3_default>;
@@ -149,9 +150,28 @@
 	};
 };
 
-&pinctrl0 { /* required by spec */
+&pinctrl0 {
 	status = "okay";
 
+	pinctrl_gpio0_default: gpio0-default {
+		conf {
+			groups = "gpio0_38_grp";
+			bias-pull-up;
+			power-source = <IO_STANDARD_LVCMOS18>;
+		};
+
+		mux {
+			groups = "gpio0_38_grp";
+			function = "gpio0";
+		};
+
+		conf-tx {
+			pins = "MIO38";
+			bias-disable;
+			output-enable;
+		};
+	};
+
 	pinctrl_uart1_default: uart1-default {
 		conf {
 			groups = "uart1_9_grp";
@@ -168,6 +188,7 @@
 		conf-tx {
 			pins = "MIO36";
 			bias-disable;
+			output-enable;
 		};
 
 		mux {
@@ -190,7 +211,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		conf {
 			groups = "gpio0_24_grp", "gpio0_25_grp";
 			slew-rate = <SLEW_RATE_SLOW>;
@@ -219,6 +240,7 @@
 		conf-bootstrap {
 			pins = "MIO71", "MIO73", "MIO75";
 			bias-disable;
+			output-enable;
 			low-power-disable;
 		};
 
@@ -226,6 +248,7 @@
 			pins = "MIO64", "MIO65", "MIO66",
 				"MIO67", "MIO68", "MIO69";
 			bias-disable;
+			output-enable;
 			low-power-enable;
 		};
 
@@ -234,6 +257,7 @@
 			slew-rate = <SLEW_RATE_SLOW>;
 			power-source = <IO_STANDARD_LVCMOS18>;
 			bias-disable;
+			output-enable;
 		};
 
 		mux-mdio {
@@ -264,6 +288,7 @@
 			pins = "MIO54", "MIO56", "MIO57", "MIO58", "MIO59",
 			"MIO60", "MIO61", "MIO62", "MIO63";
 			bias-disable;
+			output-enable;
 			drive-strength = <4>;
 			slew-rate = <SLEW_RATE_SLOW>;
 		};
@@ -302,6 +327,12 @@
 	};
 };
 
+&gpio {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_gpio0_default>;
+};
+
 &uart1 {
 	status = "okay";
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
index 73491626e01e..6aff22d43361 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm015-dc1.dts
@@ -148,7 +148,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_36_grp", "gpio0_37_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
index f767708fb50d..1850325e1d6c 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm016-dc2.dts
@@ -219,7 +219,7 @@
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_6_grp", "gpio0_7_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
index b1857e17ab7e..53aa3dca1dca 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zc1751-xm019-dc5.dts
@@ -125,7 +125,7 @@
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_74_grp", "gpio0_75_grp";
 			function = "gpio0";
@@ -152,7 +152,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_76_grp", "gpio0_77_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
index 52f998c22538..c5945067cd57 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
@@ -275,7 +275,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_4_grp", "gpio0_5_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu102-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu102-revA.dts
index 84952c14f021..ad8f23a0ec67 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu102-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu102-revA.dts
@@ -603,7 +603,7 @@
 				reg = <0x5d>;
 				temperature-stability = <50>; /* copy from zc702 */
 				factory-fout = <156250000>;
-				clock-frequency = <148500000>;
+				clock-frequency = <156250000>;
 				clock-output-names = "si570_mgt";
 			};
 		};
@@ -689,7 +689,7 @@
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_14_grp", "gpio0_15_grp";
 			function = "gpio0";
@@ -716,7 +716,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_16_grp", "gpio0_17_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revA.dts
index 5084ddcee00f..b1eca1bb6a63 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revA.dts
@@ -272,7 +272,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_16_grp", "gpio0_17_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revC.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revC.dts
index b273bd1d920a..ddc74d963a05 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revC.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu104-revC.dts
@@ -284,7 +284,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_16_grp", "gpio0_17_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu106-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu106-revA.dts
index 50c384aa253e..7beedd730f94 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu106-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu106-revA.dts
@@ -605,7 +605,7 @@
 				reg = <0x5d>;
 				temperature-stability = <50>; /* copy from zc702 */
 				factory-fout = <156250000>;
-				clock-frequency = <148500000>;
+				clock-frequency = <156250000>;
 				clock-output-names = "si570_mgt";
 			};
 		};
@@ -700,7 +700,7 @@
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_14_grp", "gpio0_15_grp";
 			function = "gpio0";
@@ -727,7 +727,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_16_grp", "gpio0_17_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu111-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu111-revA.dts
index 617cb0405a7d..b67ff7ecf3c3 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu111-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu111-revA.dts
@@ -589,7 +589,7 @@
 		};
 	};
 
-	pinctrl_i2c0_gpio: i2c0-gpio {
+	pinctrl_i2c0_gpio: i2c0-gpio-grp {
 		mux {
 			groups = "gpio0_14_grp", "gpio0_15_grp";
 			function = "gpio0";
@@ -616,7 +616,7 @@
 		};
 	};
 
-	pinctrl_i2c1_gpio: i2c1-gpio {
+	pinctrl_i2c1_gpio: i2c1-gpio-grp {
 		mux {
 			groups = "gpio0_16_grp", "gpio0_17_grp";
 			function = "gpio0";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu1275-revA.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu1275-revA.dts
index c406017b0348..a38c2baeba6c 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu1275-revA.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu1275-revA.dts
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * dts file for Xilinx ZynqMP ZC1275
+ * dts file for Xilinx ZynqMP ZCU1275
  *
  * (C) Copyright 2017 - 2021, Xilinx, Inc.
  *
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index eaba466804bc..25d20d803230 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -24,6 +24,13 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	options {
+		u-boot {
+			compatible = "u-boot,config";
+			bootscr-address = /bits/ 64 <0x20000000>;
+		};
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -180,13 +187,18 @@
 	};
 
 	firmware {
+		optee: optee  {
+			compatible = "linaro,optee-tz";
+			method = "smc";
+		};
+
 		zynqmp_firmware: zynqmp-firmware {
 			compatible = "xlnx,zynqmp-firmware";
 			#power-domain-cells = <1>;
 			method = "smc";
 			bootph-all;
 
-			zynqmp_power: zynqmp-power {
+			zynqmp_power: power-management {
 				bootph-all;
 				compatible = "xlnx,zynqmp-power";
 				interrupt-parent = <&gic>;
@@ -281,6 +293,7 @@
 			interrupt-parent = <&gic>;
 			tx-fifo-depth = <0x40>;
 			rx-fifo-depth = <0x40>;
+			resets = <&zynqmp_reset ZYNQMP_RESET_CAN0>;
 			power-domains = <&zynqmp_firmware PD_CAN_0>;
 		};
 
@@ -293,6 +306,7 @@
 			interrupt-parent = <&gic>;
 			tx-fifo-depth = <0x40>;
 			rx-fifo-depth = <0x40>;
+			resets = <&zynqmp_reset ZYNQMP_RESET_CAN1>;
 			power-domains = <&zynqmp_firmware PD_CAN_1>;
 		};
 
@@ -326,7 +340,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14e8>;
+			/* iommus = <&smmu 0x14e8>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -339,7 +353,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14e9>;
+			/* iommus = <&smmu 0x14e9>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -352,7 +366,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14ea>;
+			/* iommus = <&smmu 0x14ea>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -365,7 +379,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14eb>;
+			/* iommus = <&smmu 0x14eb>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -378,7 +392,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14ec>;
+			/* iommus = <&smmu 0x14ec>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -391,7 +405,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14ed>;
+			/* iommus = <&smmu 0x14ed>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -404,7 +418,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14ee>;
+			/* iommus = <&smmu 0x14ee>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -417,7 +431,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <128>;
-			iommus = <&smmu 0x14ef>;
+			/* iommus = <&smmu 0x14ef>; */
 			power-domains = <&zynqmp_firmware PD_GDMA>;
 		};
 
@@ -462,7 +476,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x868>;
+			/* iommus = <&smmu 0x868>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -475,7 +489,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x869>;
+			/* iommus = <&smmu 0x869>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -488,7 +502,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86a>;
+			/* iommus = <&smmu 0x86a>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -501,7 +515,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86b>;
+			/* iommus = <&smmu 0x86b>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -514,7 +528,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86c>;
+			/* iommus = <&smmu 0x86c>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -527,7 +541,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86d>;
+			/* iommus = <&smmu 0x86d>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -540,7 +554,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86e>;
+			/* iommus = <&smmu 0x86e>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -553,7 +567,7 @@
 			clock-names = "clk_main", "clk_apb";
 			#dma-cells = <1>;
 			xlnx,bus-width = <64>;
-			iommus = <&smmu 0x86f>;
+			/* iommus = <&smmu 0x86f>; */
 			power-domains = <&zynqmp_firmware PD_ADMA>;
 		};
 
@@ -573,7 +587,7 @@
 			interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			iommus = <&smmu 0x872>;
+			/* iommus = <&smmu 0x872>; */
 			power-domains = <&zynqmp_firmware PD_NAND>;
 		};
 
@@ -585,7 +599,7 @@
 				     <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0b0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			iommus = <&smmu 0x874>;
+			/* iommus = <&smmu 0x874>; */
 			power-domains = <&zynqmp_firmware PD_ETH_0>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM0>;
 			reset-names = "gem0_rst";
@@ -599,7 +613,7 @@
 				     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0c0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			iommus = <&smmu 0x875>;
+			/* iommus = <&smmu 0x875>; */
 			power-domains = <&zynqmp_firmware PD_ETH_1>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>;
 			reset-names = "gem1_rst";
@@ -613,7 +627,7 @@
 				     <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0d0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			iommus = <&smmu 0x876>;
+			/* iommus = <&smmu 0x876>; */
 			power-domains = <&zynqmp_firmware PD_ETH_2>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM2>;
 			reset-names = "gem2_rst";
@@ -627,7 +641,7 @@
 				     <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff0e0000 0x0 0x1000>;
 			clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
-			iommus = <&smmu 0x877>;
+			/* iommus = <&smmu 0x877>; */
 			power-domains = <&zynqmp_firmware PD_ETH_3>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_GEM3>;
 			reset-names = "gem3_rst";
@@ -689,7 +703,7 @@
 			msi-parent = <&pcie>;
 			reg = <0x0 0xfd0e0000 0x0 0x1000>,
 			      <0x0 0xfd480000 0x0 0x1000>,
-			      <0x80 0x00000000 0x0 0x1000000>;
+			      <0x80 0x00000000 0x0 0x10000000>;
 			reg-names = "breg", "pcireg", "cfg";
 			ranges = <0x02000000 0x00000000 0xe0000000 0x00000000 0xe0000000 0x00000000 0x10000000>,/* non-prefetchable memory */
 				 <0x43000000 0x00000006 0x00000000 0x00000006 0x00000000 0x00000002 0x00000000>;/* prefetchable memory */
@@ -699,7 +713,7 @@
 					<0x0 0x0 0x0 0x2 &pcie_intc 0x2>,
 					<0x0 0x0 0x0 0x3 &pcie_intc 0x3>,
 					<0x0 0x0 0x0 0x4 &pcie_intc 0x4>;
-			iommus = <&smmu 0x4d0>;
+			/* iommus = <&smmu 0x4d0>; */
 			power-domains = <&zynqmp_firmware PD_PCIE>;
 			pcie_intc: legacy-interrupt-controller {
 				interrupt-controller;
@@ -720,7 +734,7 @@
 			      <0x0 0xc0000000 0x0 0x8000000>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			iommus = <&smmu 0x873>;
+			/* iommus = <&smmu 0x873>; */
 			power-domains = <&zynqmp_firmware PD_QSPI>;
 		};
 
@@ -752,8 +766,7 @@
 			interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
 			power-domains = <&zynqmp_firmware PD_SATA>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_SATA>;
-			iommus = <&smmu 0x4c0>, <&smmu 0x4c1>,
-				 <&smmu 0x4c2>, <&smmu 0x4c3>;
+			/* iommus = <&smmu 0x4c0>, <&smmu 0x4c1>, <&smmu 0x4c2>, <&smmu 0x4c3>; */
 		};
 
 		sdhci0: mmc@ff160000 {
@@ -764,7 +777,7 @@
 			interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff160000 0x0 0x1000>;
 			clock-names = "clk_xin", "clk_ahb";
-			iommus = <&smmu 0x870>;
+			/* iommus = <&smmu 0x870>; */
 			#clock-cells = <1>;
 			clock-output-names = "clk_out_sd0", "clk_in_sd0";
 			power-domains = <&zynqmp_firmware PD_SD_0>;
@@ -779,7 +792,7 @@
 			interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x0 0xff170000 0x0 0x1000>;
 			clock-names = "clk_xin", "clk_ahb";
-			iommus = <&smmu 0x871>;
+			/* iommus = <&smmu 0x871>; */
 			#clock-cells = <1>;
 			clock-output-names = "clk_out_sd1", "clk_in_sd1";
 			power-domains = <&zynqmp_firmware PD_SD_1>;
@@ -912,6 +925,7 @@
 			status = "disabled";
 			compatible = "xlnx,zynqmp-dwc3";
 			reg = <0x0 0xff9d0000 0x0 0x100>;
+			clock-names = "bus_clk", "ref_clk";
 			power-domains = <&zynqmp_firmware PD_USB_0>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_USB0_CORERESET>,
 				 <&zynqmp_reset ZYNQMP_RESET_USB0_HIBERRESET>,
@@ -922,14 +936,15 @@
 
 			dwc3_0: usb@fe200000 {
 				compatible = "snps,dwc3";
+				status = "disabled";
 				reg = <0x0 0xfe200000 0x0 0x40000>;
 				interrupt-parent = <&gic>;
 				interrupt-names = "host", "peripheral", "otg";
 				interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
-				clock-names = "bus_early", "ref";
-				iommus = <&smmu 0x860>;
+				clock-names = "ref";
+				/* iommus = <&smmu 0x860>; */
 				snps,quirk-frame-length-adjustment = <0x20>;
 				snps,resume-hs-terminations;
 				/* dma-coherent; */
@@ -942,6 +957,7 @@
 			status = "disabled";
 			compatible = "xlnx,zynqmp-dwc3";
 			reg = <0x0 0xff9e0000 0x0 0x100>;
+			clock-names = "bus_clk", "ref_clk";
 			power-domains = <&zynqmp_firmware PD_USB_1>;
 			resets = <&zynqmp_reset ZYNQMP_RESET_USB1_CORERESET>,
 				 <&zynqmp_reset ZYNQMP_RESET_USB1_HIBERRESET>,
@@ -951,14 +967,15 @@
 
 			dwc3_1: usb@fe300000 {
 				compatible = "snps,dwc3";
+				status = "disabled";
 				reg = <0x0 0xfe300000 0x0 0x40000>;
 				interrupt-parent = <&gic>;
 				interrupt-names = "host", "peripheral", "otg";
 				interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
-				clock-names = "bus_early", "ref";
-				iommus = <&smmu 0x861>;
+				clock-names = "ref";
+				/* iommus = <&smmu 0x861>; */
 				snps,quirk-frame-length-adjustment = <0x20>;
 				snps,resume-hs-terminations;
 				/* dma-coherent; */
@@ -1018,6 +1035,7 @@
 			interrupt-parent = <&gic>;
 			clock-names = "axi_clk";
 			power-domains = <&zynqmp_firmware PD_DP>;
+			/* iommus = <&smmu 0xce4>; */
 			#dma-cells = <1>;
 		};
 
@@ -1032,6 +1050,7 @@
 			reg-names = "dp", "blend", "av_buf", "aud";
 			interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-parent = <&gic>;
+			/* iommus = <&smmu 0xce3>; */
 			clock-names = "dp_apb_clk", "dp_aud_clk",
 				      "dp_vtc_pixel_clk_in";
 			power-domains = <&zynqmp_firmware PD_DP>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index e6cf3e5d63c3..ed69b4636d0f 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -251,6 +251,9 @@ CONFIG_RASPBERRYPI_FIRMWARE=y
 CONFIG_INTEL_STRATIX10_SERVICE=y
 CONFIG_INTEL_STRATIX10_RSU=m
 CONFIG_MTK_ADSP_IPC=m
+CONFIG_GOOGLE_FIRMWARE=y
+CONFIG_GOOGLE_CBMEM=m
+CONFIG_GOOGLE_COREBOOT_TABLE=m
 CONFIG_EFI_CAPSULE_LOADER=y
 CONFIG_IMX_SCU=y
 CONFIG_QCOM_QSEECOM=y
@@ -432,6 +435,7 @@ CONFIG_MOUSE_ELAN_I2C=m
 CONFIG_INPUT_TOUCHSCREEN=y
 CONFIG_TOUCHSCREEN_ATMEL_MXT=m
 CONFIG_TOUCHSCREEN_GOODIX=m
+CONFIG_TOUCHSCREEN_GOODIX_BERLIN_SPI=m
 CONFIG_TOUCHSCREEN_ELAN=m
 CONFIG_TOUCHSCREEN_EDT_FT5X06=m
 CONFIG_INPUT_MISC=y
@@ -620,6 +624,7 @@ CONFIG_PINCTRL_SM8350_LPASS_LPI=m
 CONFIG_PINCTRL_SM8450_LPASS_LPI=m
 CONFIG_PINCTRL_SC8280XP_LPASS_LPI=m
 CONFIG_PINCTRL_SM8550_LPASS_LPI=m
+CONFIG_PINCTRL_SM8650_LPASS_LPI=m
 CONFIG_GPIO_ALTERA=m
 CONFIG_GPIO_DAVINCI=y
 CONFIG_GPIO_DWAPB=y
@@ -632,6 +637,7 @@ CONFIG_GPIO_SYSCON=y
 CONFIG_GPIO_UNIPHIER=y
 CONFIG_GPIO_VISCONTI=y
 CONFIG_GPIO_WCD934X=m
+CONFIG_GPIO_VF610=y
 CONFIG_GPIO_XGENE=y
 CONFIG_GPIO_XGENE_SB=y
 CONFIG_GPIO_MAX732X=y
@@ -752,6 +758,7 @@ CONFIG_REGULATOR_HI6421V530=y
 CONFIG_REGULATOR_HI655X=y
 CONFIG_REGULATOR_MAX77620=y
 CONFIG_REGULATOR_MAX8973=y
+CONFIG_REGULATOR_MAX20411=m
 CONFIG_REGULATOR_MP8859=y
 CONFIG_REGULATOR_MT6315=m
 CONFIG_REGULATOR_MT6357=y
@@ -792,13 +799,16 @@ CONFIG_USB_VIDEO_CLASS=m
 CONFIG_V4L_PLATFORM_DRIVERS=y
 CONFIG_SDR_PLATFORM_DRIVERS=y
 CONFIG_V4L_MEM2MEM_DRIVERS=y
+CONFIG_VIDEO_AMPHION_VPU=m
 CONFIG_VIDEO_CADENCE_CSI2RX=m
 CONFIG_VIDEO_MEDIATEK_JPEG=m
 CONFIG_VIDEO_MEDIATEK_VCODEC=m
+CONFIG_VIDEO_WAVE_VPU=m
 CONFIG_VIDEO_IMX7_CSI=m
 CONFIG_VIDEO_IMX_MIPI_CSIS=m
 CONFIG_VIDEO_IMX8_ISI=m
 CONFIG_VIDEO_IMX8_ISI_M2M=y
+CONFIG_VIDEO_IMX8_JPEG=m
 CONFIG_VIDEO_QCOM_CAMSS=m
 CONFIG_VIDEO_QCOM_VENUS=m
 CONFIG_VIDEO_RCAR_ISP=m
@@ -861,6 +871,7 @@ CONFIG_DRM_PANEL_RAYDIUM_RM67191=m
 CONFIG_DRM_PANEL_SITRONIX_ST7703=m
 CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m
 CONFIG_DRM_PANEL_VISIONOX_VTDR6130=m
+CONFIG_DRM_FSL_LDB=m
 CONFIG_DRM_LONTIUM_LT8912B=m
 CONFIG_DRM_LONTIUM_LT9611=m
 CONFIG_DRM_LONTIUM_LT9611UXC=m
@@ -992,6 +1003,8 @@ CONFIG_SND_SOC_TLV320AIC32X4_I2C=m
 CONFIG_SND_SOC_TLV320AIC3X_I2C=m
 CONFIG_SND_SOC_WCD9335=m
 CONFIG_SND_SOC_WCD934X=m
+CONFIG_SND_SOC_WCD939X=m
+CONFIG_SND_SOC_WCD939X_SDW=m
 CONFIG_SND_SOC_WM8524=m
 CONFIG_SND_SOC_WM8904=m
 CONFIG_SND_SOC_WM8960=m
@@ -1032,6 +1045,7 @@ CONFIG_USB_CDNS_SUPPORT=m
 CONFIG_USB_CDNS3=m
 CONFIG_USB_CDNS3_GADGET=y
 CONFIG_USB_CDNS3_HOST=y
+CONFIG_USB_CDNS3_IMX=m
 CONFIG_USB_MTU3=y
 CONFIG_USB_MUSB_HDRC=y
 CONFIG_USB_MUSB_SUNXI=y
@@ -1049,6 +1063,7 @@ CONFIG_USB_QCOM_EUD=m
 CONFIG_USB_HSIC_USB3503=y
 CONFIG_USB_ONBOARD_HUB=m
 CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_MXS_PHY=m
 CONFIG_USB_GADGET=y
 CONFIG_USB_RENESAS_USBHS_UDC=m
 CONFIG_USB_RZV2M_USB3DRD=y
@@ -1079,6 +1094,7 @@ CONFIG_TYPEC_HD3SS3220=m
 CONFIG_TYPEC_MUX_FSA4480=m
 CONFIG_TYPEC_MUX_GPIO_SBU=m
 CONFIG_TYPEC_MUX_NB7VPQ904M=m
+CONFIG_TYPEC_MUX_WCD939X_USBSS=m
 CONFIG_TYPEC_DP_ALTMODE=m
 CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=32
@@ -1242,7 +1258,11 @@ CONFIG_COMMON_CLK_MT8192_SCP_ADSP=y
 CONFIG_COMMON_CLK_MT8192_VDECSYS=y
 CONFIG_COMMON_CLK_MT8192_VENCSYS=y
 CONFIG_COMMON_CLK_QCOM=y
+CONFIG_CLK_X1E80100_CAMCC=m
+CONFIG_CLK_X1E80100_DISPCC=m
 CONFIG_CLK_X1E80100_GCC=y
+CONFIG_CLK_X1E80100_GPUCC=m
+CONFIG_CLK_X1E80100_TCSRCC=y
 CONFIG_QCOM_A53PLL=y
 CONFIG_QCOM_CLK_APCS_MSM8916=y
 CONFIG_QCOM_CLK_APCC_MSM8996=y
@@ -1265,6 +1285,7 @@ CONFIG_MSM_MMCC_8998=m
 CONFIG_QCM_GCC_2290=y
 CONFIG_QCM_DISPCC_2290=m
 CONFIG_QCS_GCC_404=y
+CONFIG_QDU_GCC_1000=y
 CONFIG_SC_CAMCC_8280XP=m
 CONFIG_SC_DISPCC_8280XP=m
 CONFIG_SA_GCC_8775P=y
@@ -1366,6 +1387,7 @@ CONFIG_QCOM_STATS=m
 CONFIG_QCOM_WCNSS_CTRL=m
 CONFIG_QCOM_APR=m
 CONFIG_QCOM_ICC_BWMON=m
+CONFIG_QCOM_PBS=m
 CONFIG_ARCH_R8A77995=y
 CONFIG_ARCH_R8A77990=y
 CONFIG_ARCH_R8A77951=y
@@ -1377,6 +1399,7 @@ CONFIG_ARCH_R8A77980=y
 CONFIG_ARCH_R8A77970=y
 CONFIG_ARCH_R8A779A0=y
 CONFIG_ARCH_R8A779G0=y
+CONFIG_ARCH_R8A779H0=y
 CONFIG_ARCH_R8A774C0=y
 CONFIG_ARCH_R8A774E1=y
 CONFIG_ARCH_R8A774A1=y
@@ -1410,6 +1433,7 @@ CONFIG_EXTCON_USBC_CROS_EC=y
 CONFIG_RENESAS_RPCIF=m
 CONFIG_IIO=y
 CONFIG_EXYNOS_ADC=y
+CONFIG_IMX8QXP_ADC=m
 CONFIG_IMX93_ADC=m
 CONFIG_MAX9611=m
 CONFIG_MEDIATEK_MT6577_AUXADC=m
@@ -1461,6 +1485,7 @@ CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_CADENCE_TORRENT=m
 CONFIG_PHY_CADENCE_DPHY_RX=m
 CONFIG_PHY_CADENCE_SIERRA=m
+CONFIG_PHY_CADENCE_SALVO=m
 CONFIG_PHY_MIXEL_MIPI_DPHY=m
 CONFIG_PHY_FSL_IMX8M_PCIE=y
 CONFIG_PHY_HI6220_USB=y
@@ -1490,6 +1515,7 @@ CONFIG_PHY_ROCKCHIP_INNO_USB2=y
 CONFIG_PHY_ROCKCHIP_INNO_DSIDPHY=m
 CONFIG_PHY_ROCKCHIP_NANENG_COMBO_PHY=m
 CONFIG_PHY_ROCKCHIP_PCIE=m
+CONFIG_PHY_ROCKCHIP_SAMSUNG_HDPTX=m
 CONFIG_PHY_ROCKCHIP_SNPS_PCIE3=y
 CONFIG_PHY_ROCKCHIP_TYPEC=y
 CONFIG_PHY_SAMSUNG_UFS=y
@@ -1550,8 +1576,9 @@ CONFIG_INTERCONNECT_QCOM=y
 CONFIG_INTERCONNECT_QCOM_MSM8916=m
 CONFIG_INTERCONNECT_QCOM_MSM8996=m
 CONFIG_INTERCONNECT_QCOM_OSM_L3=m
-CONFIG_INTERCONNECT_QCOM_QCM2290=m
+CONFIG_INTERCONNECT_QCOM_QCM2290=y
 CONFIG_INTERCONNECT_QCOM_QCS404=m
+CONFIG_INTERCONNECT_QCOM_QDU1000=y
 CONFIG_INTERCONNECT_QCOM_SA8775P=y
 CONFIG_INTERCONNECT_QCOM_SC7180=y
 CONFIG_INTERCONNECT_QCOM_SC7280=y
@@ -1560,7 +1587,7 @@ CONFIG_INTERCONNECT_QCOM_SC8280XP=y
 CONFIG_INTERCONNECT_QCOM_SDM845=y
 CONFIG_INTERCONNECT_QCOM_SDX75=y
 CONFIG_INTERCONNECT_QCOM_SM8150=m
-CONFIG_INTERCONNECT_QCOM_SM8250=m
+CONFIG_INTERCONNECT_QCOM_SM8250=y
 CONFIG_INTERCONNECT_QCOM_SM8350=m
 CONFIG_INTERCONNECT_QCOM_SM8450=y
 CONFIG_INTERCONNECT_QCOM_SM8550=y
@@ -1571,8 +1598,7 @@ CONFIG_RZ_MTU3_CNT=m
 CONFIG_HTE=y
 CONFIG_HTE_TEGRA194=y
 CONFIG_HTE_TEGRA194_TEST=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_BTRFS_FS=m
 CONFIG_BTRFS_FS_POSIX_ACL=y
@@ -1590,6 +1616,7 @@ CONFIG_CONFIGFS_FS=y
 CONFIG_EFIVAR_FS=y
 CONFIG_UBIFS_FS=m
 CONFIG_SQUASHFS=y
+CONFIG_PSTORE_RAM=m
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_NFS_V4_1=y
diff --git a/arch/arm64/configs/virt.config b/arch/arm64/configs/virt.config
index c47c36f8f67b..2d1d2ce7ae2a 100644
--- a/arch/arm64/configs/virt.config
+++ b/arch/arm64/configs/virt.config
@@ -14,6 +14,7 @@
 # CONFIG_ARCH_BERLIN is not set
 # CONFIG_ARCH_BRCMSTB is not set
 # CONFIG_ARCH_EXYNOS is not set
+# CONFIG_ARCH_SPARX5 is not set
 # CONFIG_ARCH_K3 is not set
 # CONFIG_ARCH_LAYERSCAPE is not set
 # CONFIG_ARCH_LG1K is not set
@@ -23,14 +24,17 @@
 # CONFIG_ARCH_MESON is not set
 # CONFIG_ARCH_MVEBU is not set
 # CONFIG_ARCH_NXP is not set
+# CONFIG_ARCH_MA35 is not set
 # CONFIG_ARCH_MXC is not set
 # CONFIG_ARCH_NPCM is not set
 # CONFIG_ARCH_QCOM is not set
+# CONFIG_ARCH_REALTEK is not set
 # CONFIG_ARCH_RENESAS is not set
 # CONFIG_ARCH_ROCKCHIP is not set
 # CONFIG_ARCH_S32 is not set
 # CONFIG_ARCH_SEATTLE is not set
 # CONFIG_ARCH_INTEL_SOCFPGA is not set
+# CONFIG_ARCH_STM32 is not set
 # CONFIG_ARCH_SYNQUACER is not set
 # CONFIG_ARCH_TEGRA is not set
 # CONFIG_ARCH_TESLA_FSD is not set
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index bac4cabef607..467ac2f768ac 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_request *req)
 			src += blocks * AES_BLOCK_SIZE;
 		}
 		if (nbytes && walk.nbytes == walk.total) {
+			u8 buf[AES_BLOCK_SIZE];
+			u8 *d = dst;
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+
 			neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds,
 					     nbytes, walk.iv);
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				memcpy(d, dst, nbytes);
+
 			nbytes = 0;
 		}
 		kernel_neon_end();
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 210bb43cff2c..d328f549b1a6 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
 	:
 	: [cpucap] "i" (cpucap)
@@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	if (!cpucap_is_possible(cpucap))
 		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
 	:
 	: [cpucap] "i" (cpucap)
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 21c824edf8ce..bd8d4ca81a48 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -83,7 +83,7 @@ struct arm64_ftr_bits {
  * to full-0 denotes that this field has no override
  *
  * A @mask field set to full-0 with the corresponding @val field set
- * to full-1 denotes thath this field has an invalid override.
+ * to full-1 denotes that this field has an invalid override.
  */
 struct arm64_ftr_override {
 	u64		val;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 7c7493cb571f..52f076afeb96 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
 #define ARM_CPU_IMP_HISI		0x48
 #define ARM_CPU_IMP_APPLE		0x61
 #define ARM_CPU_IMP_AMPERE		0xC0
+#define ARM_CPU_IMP_MICROSOFT		0x6D
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -135,6 +136,8 @@
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 50e5f25d3024..b67b89c54e1c 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -62,13 +62,13 @@ static inline void cpacr_restore(unsigned long cpacr)
  * When we defined the maximum SVE vector length we defined the ABI so
  * that the maximum vector length included all the reserved for future
  * expansion bits in ZCR rather than those just currently defined by
- * the architecture. While SME follows a similar pattern the fact that
- * it includes a square matrix means that any allocations that attempt
- * to cover the maximum potential vector length (such as happen with
- * the regset used for ptrace) end up being extremely large. Define
- * the much lower actual limit for use in such situations.
+ * the architecture.  Using this length to allocate worst size buffers
+ * results in excessively large allocations, and this effect is even
+ * more pronounced for SME due to ZA.  Define more suitable VLs for
+ * these situations.
  */
-#define SME_VQ_MAX	16
+#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1)
+#define SME_VQ_MAX	((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1)
 
 struct task_struct;
 
@@ -386,6 +386,7 @@ extern void sme_alloc(struct task_struct *task, bool flush);
 extern unsigned int sme_get_vl(void);
 extern int sme_set_current_vl(unsigned long arg);
 extern int sme_get_current_vl(void);
+extern void sme_suspend_exit(void);
 
 /*
  * Return how many bytes of memory are required to store the full SME
@@ -421,6 +422,7 @@ static inline int sme_max_vl(void) { return 0; }
 static inline int sme_max_virtualisable_vl(void) { return 0; }
 static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
 static inline int sme_get_current_vl(void) { return -EINVAL; }
+static inline void sme_suspend_exit(void) { }
 
 static inline size_t sme_state_size(struct task_struct const *task)
 {
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45d22..6aafbb789991 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop					\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
@@ -35,7 +35,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
diff --git a/arch/arm64/include/asm/page-def.h b/arch/arm64/include/asm/page-def.h
index 2403f7b4cdbf..792e9fe881dc 100644
--- a/arch/arm64/include/asm/page-def.h
+++ b/arch/arm64/include/asm/page-def.h
@@ -11,7 +11,7 @@
 #include <linux/const.h>
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define PAGE_SHIFT		CONFIG_PAGE_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index b4ae32109932..4305995c8f82 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -17,9 +17,6 @@
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>
-#ifdef CONFIG_COMPAT_VDSO
-#include <generated/vdso32-offsets.h>
-#endif
 
 #define VDSO_SYMBOL(base, name)						   \
 ({									   \
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index e5d03a7039b4..467cb7117273 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -77,9 +77,9 @@ obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS)	+= patch-scs.o
 # We need to prevent the SCS patching code from patching itself. Using
 # -mbranch-protection=none here to avoid the patchable PAC opcodes from being
 # generated triggers an issue with full LTO on Clang, which stops emitting PAC
-# instructions altogether. So instead, omit the unwind tables used by the
-# patching code, so it will not be able to locate its own PAC instructions.
-CFLAGS_patch-scs.o			+= -fno-asynchronous-unwind-tables -fno-unwind-tables
+# instructions altogether. So disable LTO as well for the compilation unit.
+CFLAGS_patch-scs.o			+= -mbranch-protection=none
+CFLAGS_REMOVE_patch-scs.o		+= $(CC_FLAGS_LTO)
 
 # Force dependency (vdso*-wrap.S includes vdso.so through incbin)
 $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 967c7c7a4e7d..76b8dd37092a 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -374,6 +374,7 @@ static const struct midr_range erratum_1463225[] = {
 static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2139208
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2119858
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -387,6 +388,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 static const struct midr_range tsb_flush_fail_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2067961
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2054223
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -399,6 +401,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
 static struct midr_range trbe_write_out_of_range_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2253138
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2224489
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a5dc6f764195..f27acca550d5 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1311,6 +1311,22 @@ void __init sme_setup(void)
 		get_sme_default_vl());
 }
 
+void sme_suspend_exit(void)
+{
+	u64 smcr = 0;
+
+	if (!system_supports_sme())
+		return;
+
+	if (system_supports_fa64())
+		smcr |= SMCR_ELx_FA64;
+	if (system_supports_sme2())
+		smcr |= SMCR_ELx_EZT0;
+
+	write_sysreg_s(smcr, SYS_SMCR_EL1);
+	write_sysreg_s(0, SYS_SMPRI_EL1);
+}
+
 #endif /* CONFIG_ARM64_SME */
 
 static void sve_init_regs(void)
@@ -1635,7 +1651,7 @@ void fpsimd_preserve_current_state(void)
 void fpsimd_signal_preserve_current_state(void)
 {
 	fpsimd_preserve_current_state();
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(current);
 }
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index dc6cf0e37194..e3bef38fc2e2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1500,7 +1500,8 @@ static const struct user_regset aarch64_regsets[] = {
 #ifdef CONFIG_ARM64_SVE
 	[REGSET_SVE] = { /* Scalable Vector Extension */
 		.core_note_type = NT_ARM_SVE,
-		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX,
+					      SVE_PT_REGS_SVE),
 				  SVE_VQ_BYTES),
 		.size = SVE_VQ_BYTES,
 		.align = SVE_VQ_BYTES,
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0e8beb3349ea..425b1bc17a3f 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 		vl = task_get_sme_vl(current);
 		vq = sve_vq_from_vl(vl);
 		flags |= SVE_SIG_FLAG_SM;
-	} else if (test_thread_flag(TIF_SVE)) {
+	} else if (current->thread.fp_type == FP_STATE_SVE) {
 		vq = sve_vq_from_vl(vl);
 	}
 
@@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 	if (system_supports_sve() || system_supports_sme()) {
 		unsigned int vq = 0;
 
-		if (add_all || test_thread_flag(TIF_SVE) ||
+		if (add_all || current->thread.fp_type == FP_STATE_SVE ||
 		    thread_sm_enabled(&current->thread)) {
 			int vl = max(sve_max_vl(), sme_max_vl());
 
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 7f88028a00c0..b2a60e0bcfd2 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -247,7 +247,7 @@ struct kunwind_consume_entry_data {
 	void *cookie;
 };
 
-static bool
+static __always_inline bool
 arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
 {
 	struct kunwind_consume_entry_data *data = cookie;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index eca4d0435211..eaaff94329cd 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -12,6 +12,7 @@
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
 #include <asm/exec.h>
+#include <asm/fpsimd.h>
 #include <asm/mte.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -80,6 +81,8 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	spectre_v4_enable_mitigation(NULL);
 
+	sme_suspend_exit();
+
 	/* Restore additional feature-specific configuration */
 	ptrauth_suspend_exit();
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 5562daf38a22..89b6e7840002 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -69,10 +69,7 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = {
 /*
  * The vDSO data page.
  */
-static union {
-	struct vdso_data	data[CS_BASES];
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
 struct vdso_data *vdso_data = vdso_data_store.data;
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 2266fcdff78a..f5f80fdce0fe 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -127,9 +127,6 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
 targets += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
-include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 # Strip rule for vdso.so
 $(obj)/vdso.so: OBJCOPYFLAGS := -S
 $(obj)/vdso.so: $(obj)/vdso32.so.dbg FORCE
@@ -166,9 +163,3 @@ quiet_cmd_vdsoas = AS32    $@
 
 quiet_cmd_vdsomunge = MUNGE   $@
       cmd_vdsomunge = $(obj)/$(munge) $< $@
-
-# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
-gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
-quiet_cmd_vdsosym = VDSOSYM $@
-# The AArch64 nm should be able to read an AArch32 binary
-      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 6c3c8ca73e7f..27ca89b628a0 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -3,7 +3,6 @@
 # KVM configuration
 #
 
-source "virt/lib/Kconfig"
 source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c651df904fe3..ab9d05fcf98b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1419,7 +1419,6 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
 				 level + 1);
 	if (ret) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
-		mm_ops->put_page(pgtable);
 		return ERR_PTR(ret);
 	}
 
@@ -1502,7 +1501,6 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 	if (!stage2_try_break_pte(ctx, mmu)) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
-		mm_ops->put_page(childp);
 		return -EAGAIN;
 	}
 
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 8350fb8fee0b..b7be96a53597 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void)
 		 hyp_mem_base);
 }
 
+static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
+{
+	if (host_kvm->arch.pkvm.handle) {
+		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
+					  host_kvm->arch.pkvm.handle));
+	}
+
+	host_kvm->arch.pkvm.handle = 0;
+	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+}
+
 /*
  * Allocates and donates memory for hypervisor VM structs at EL2.
  *
@@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
 	return 0;
 
 destroy_vm:
-	pkvm_destroy_hyp_vm(host_kvm);
+	__pkvm_destroy_hyp_vm(host_kvm);
 	return ret;
 free_vm:
 	free_pages_exact(hyp_vm, hyp_vm_sz);
@@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm)
 {
 	int ret = 0;
 
-	mutex_lock(&host_kvm->lock);
+	mutex_lock(&host_kvm->arch.config_lock);
 	if (!host_kvm->arch.pkvm.handle)
 		ret = __pkvm_create_hyp_vm(host_kvm);
-	mutex_unlock(&host_kvm->lock);
+	mutex_unlock(&host_kvm->arch.config_lock);
 
 	return ret;
 }
 
 void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 {
-	if (host_kvm->arch.pkvm.handle) {
-		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
-					  host_kvm->arch.pkvm.handle));
-	}
-
-	host_kvm->arch.pkvm.handle = 0;
-	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+	mutex_lock(&host_kvm->arch.config_lock);
+	__pkvm_destroy_hyp_vm(host_kvm);
+	mutex_unlock(&host_kvm->arch.config_lock);
 }
 
 int pkvm_init_host_vm(struct kvm *host_kvm)
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index e2764d0ffa9f..28a93074eca1 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 		}
 
 		irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
+
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 		irq->pending_latch = pendmask & (1U << bit_nr);
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -1432,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
 
 	for (i = 0; i < irq_count; i++) {
 		irq = vgic_get_irq(kvm, NULL, intids[i]);
+		if (!irq)
+			continue;
 
 		update_affinity(irq, vcpu2);
 
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index cf2a6fd7dff8..9c2723ab1c94 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -89,6 +89,7 @@ config CSKY
 	select HAVE_KPROBES if !CPU_CK610
 	select HAVE_KPROBES_ON_FTRACE if !CPU_CK610
 	select HAVE_KRETPROBES if !CPU_CK610
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
index 98a3f4b168bd..ef2e37a10a0f 100644
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop32					\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
@@ -29,7 +29,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	bsr32		%l[label]		\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
diff --git a/arch/csky/include/asm/page.h b/arch/csky/include/asm/page.h
index 4a0502e324a6..0ca6c408c07f 100644
--- a/arch/csky/include/asm/page.h
+++ b/arch/csky/include/asm/page.h
@@ -10,7 +10,7 @@
 /*
  * PAGE_SHIFT determines the page size: 4KB
  */
-#define PAGE_SHIFT	12
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE - 1))
 #define THREAD_SIZE	(PAGE_SIZE * 2)
@@ -82,11 +82,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 	return __pa(kaddr) >> PAGE_SHIFT;
 }
 
-static inline void * pfn_to_virt(unsigned long pfn)
-{
-	return (void *)((unsigned long)__va(pfn) << PAGE_SHIFT);
-}
-
 #define MAP_NR(x)	PFN_DOWN((unsigned long)(x) - PAGE_OFFSET - \
 				 PHYS_OFFSET_OFFSET)
 #define virt_to_page(x)	(mem_map + MAP_NR(x))
diff --git a/arch/csky/include/asm/vdso.h b/arch/csky/include/asm/vdso.h
index bdce581b5fcb..181a15edafe8 100644
--- a/arch/csky/include/asm/vdso.h
+++ b/arch/csky/include/asm/vdso.h
@@ -5,11 +5,6 @@
 
 #include <linux/types.h>
 
-#ifndef GENERIC_TIME_VSYSCALL
-struct vdso_data {
-};
-#endif
-
 /*
  * The VDSO symbols are mapped into Linux so we can just use regular symbol
  * addressing to get their offsets in userspace.  The symbols are mapped at an
diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c
index 8e42352cbf12..92dbbf3e0205 100644
--- a/arch/csky/kernel/smp.c
+++ b/arch/csky/kernel/smp.c
@@ -152,10 +152,6 @@ void arch_irq_work_raise(void)
 }
 #endif
 
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 }
diff --git a/arch/csky/kernel/vdso.c b/arch/csky/kernel/vdso.c
index 16c20d64d165..2ca886e4a458 100644
--- a/arch/csky/kernel/vdso.c
+++ b/arch/csky/kernel/vdso.c
@@ -8,25 +8,15 @@
 #include <linux/slab.h>
 
 #include <asm/page.h>
-#ifdef GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
-#else
-#include <asm/vdso.h>
-#endif
 
 extern char vdso_start[], vdso_end[];
 
 static unsigned int vdso_pages;
 static struct page **vdso_pagelist;
 
-/*
- * The vDSO data page.
- */
-static union {
-	struct vdso_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
 static int __init vdso_init(void)
 {
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index a880ee067d2e..1414052e7d6b 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -8,6 +8,10 @@ config HEXAGON
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_NO_PREEMPT
 	select DMA_GLOBAL_POOL
+	select HAVE_PAGE_SIZE_4KB
+	select HAVE_PAGE_SIZE_16KB
+	select HAVE_PAGE_SIZE_64KB
+	select HAVE_PAGE_SIZE_256KB
 	# Other pending projects/to-do items.
 	# select HAVE_REGS_AND_STACK_ACCESS_API
 	# select HAVE_HW_BREAKPOINT if PERF_EVENTS
@@ -120,26 +124,6 @@ config NR_CPUS
 	  This is purely to save memory - each supported CPU adds
 	  approximately eight kilobytes to the kernel image.
 
-choice
-	prompt "Kernel page size"
-	default PAGE_SIZE_4KB
-	help
-	  Changes the default page size; use with caution.
-
-config PAGE_SIZE_4KB
-	bool "4KB"
-
-config PAGE_SIZE_16KB
-	bool "16KB"
-
-config PAGE_SIZE_64KB
-	bool "64KB"
-
-config PAGE_SIZE_256KB
-	bool "256KB"
-
-endchoice
-
 source "kernel/Kconfig.hz"
 
 endmenu
diff --git a/arch/hexagon/include/asm/page.h b/arch/hexagon/include/asm/page.h
index 10f1bc07423c..8a6af57274c2 100644
--- a/arch/hexagon/include/asm/page.h
+++ b/arch/hexagon/include/asm/page.h
@@ -13,27 +13,22 @@
 /*  This is probably not the most graceful way to handle this.  */
 
 #ifdef CONFIG_PAGE_SIZE_4KB
-#define PAGE_SHIFT 12
 #define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_4KB
 #endif
 
 #ifdef CONFIG_PAGE_SIZE_16KB
-#define PAGE_SHIFT 14
 #define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_16KB
 #endif
 
 #ifdef CONFIG_PAGE_SIZE_64KB
-#define PAGE_SHIFT 16
 #define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_64KB
 #endif
 
 #ifdef CONFIG_PAGE_SIZE_256KB
-#define PAGE_SHIFT 18
 #define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_256KB
 #endif
 
 #ifdef CONFIG_PAGE_SIZE_1MB
-#define PAGE_SHIFT 20
 #define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_1MB
 #endif
 
@@ -50,6 +45,7 @@
 #define HVM_HUGEPAGE_SIZE 0x5
 #endif
 
+#define PAGE_SHIFT CONFIG_PAGE_SHIFT
 #define PAGE_SIZE  (1UL << PAGE_SHIFT)
 #define PAGE_MASK  (~((1 << PAGE_SHIFT) - 1))
 
@@ -133,12 +129,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 	return __pa(kaddr) >> PAGE_SHIFT;
 }
 
-static inline void *pfn_to_virt(unsigned long pfn)
-{
-	return (void *)((unsigned long)__va(pfn) << PAGE_SHIFT);
-}
-
-
 #define page_to_virt(page)	__va(page_to_phys(page))
 
 #include <asm/mem-layout.h>
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index 608884bc3396..65e1fdf9fdb2 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -114,10 +114,6 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 	local_irq_restore(flags);
 }
 
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 /*
  * interrupts should already be disabled from the VM
  * SP should already be correct; need to set THREADINFO_REG
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 10959e6c3583..b274784c2e26 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -12,6 +12,7 @@ config LOONGARCH
 	select ARCH_DISABLE_KASAN_INLINE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_FORTIFY_SOURCE
@@ -99,6 +100,7 @@ config LOONGARCH
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
+	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -225,15 +227,6 @@ config MACH_LOONGSON64
 config FIX_EARLYCON_MEM
 	def_bool y
 
-config PAGE_SIZE_4KB
-	bool
-
-config PAGE_SIZE_16KB
-	bool
-
-config PAGE_SIZE_64KB
-	bool
-
 config PGTABLE_2LEVEL
 	bool
 
@@ -286,7 +279,7 @@ choice
 
 config 4KB_3LEVEL
 	bool "4KB with 3 levels"
-	select PAGE_SIZE_4KB
+	select HAVE_PAGE_SIZE_4KB
 	select PGTABLE_3LEVEL
 	help
 	  This option selects 4KB page size with 3 level page tables, which
@@ -294,7 +287,7 @@ config 4KB_3LEVEL
 
 config 4KB_4LEVEL
 	bool "4KB with 4 levels"
-	select PAGE_SIZE_4KB
+	select HAVE_PAGE_SIZE_4KB
 	select PGTABLE_4LEVEL
 	help
 	  This option selects 4KB page size with 4 level page tables, which
@@ -302,7 +295,7 @@ config 4KB_4LEVEL
 
 config 16KB_2LEVEL
 	bool "16KB with 2 levels"
-	select PAGE_SIZE_16KB
+	select HAVE_PAGE_SIZE_16KB
 	select PGTABLE_2LEVEL
 	help
 	  This option selects 16KB page size with 2 level page tables, which
@@ -310,7 +303,7 @@ config 16KB_2LEVEL
 
 config 16KB_3LEVEL
 	bool "16KB with 3 levels"
-	select PAGE_SIZE_16KB
+	select HAVE_PAGE_SIZE_16KB
 	select PGTABLE_3LEVEL
 	help
 	  This option selects 16KB page size with 3 level page tables, which
@@ -318,7 +311,7 @@ config 16KB_3LEVEL
 
 config 64KB_2LEVEL
 	bool "64KB with 2 levels"
-	select PAGE_SIZE_64KB
+	select HAVE_PAGE_SIZE_64KB
 	select PGTABLE_2LEVEL
 	help
 	  This option selects 64KB page size with 2 level page tables, which
@@ -326,7 +319,7 @@ config 64KB_2LEVEL
 
 config 64KB_3LEVEL
 	bool "64KB with 3 levels"
-	select PAGE_SIZE_64KB
+	select HAVE_PAGE_SIZE_64KB
 	select PGTABLE_3LEVEL
 	help
 	  This option selects 64KB page size with 3 level page tables, which
@@ -632,23 +625,6 @@ config RANDOMIZE_BASE_MAX_OFFSET
 
 	  This is limited by the size of the lower address memory, 256MB.
 
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL
@@ -667,10 +643,6 @@ config ARCH_SPARSEMEM_ENABLE
 	  or have huge holes in the physical address space for other reasons.
 	  See <file:Documentation/mm/numa.rst> for more.
 
-config ARCH_ENABLE_THP_MIGRATION
-	def_bool y
-	depends on TRANSPARENT_HUGEPAGE
-
 config ARCH_MEMORY_PROBE
 	def_bool y
 	depends on MEMORY_HOTPLUG
diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
index b38071a4d0b0..8aefb0c12672 100644
--- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -60,7 +60,7 @@
 
 	#address-cells = <1>;
 	#size-cells = <0>;
-	eeprom@57{
+	eeprom@57 {
 		compatible = "atmel,24c16";
 		reg = <0x57>;
 		pagesize = <16>;
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
index 132a2d1ea8bc..ed4d32434041 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -78,7 +78,7 @@
 
 	#address-cells = <1>;
 	#size-cells = <0>;
-	eeprom@57{
+	eeprom@57 {
 		compatible = "atmel,24c16";
 		reg = <0x57>;
 		pagesize = <16>;
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index 8de6c4b83a61..49e29b29996f 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+#define MAX_CORE_PIC 256
+
 extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 extern int __init parse_acpi_topology(void);
 
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 3cea299a5ef5..29acfe3de3fa 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop			\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
@@ -35,7 +35,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 63f137ce82a4..afb6fa16b826 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -11,15 +11,7 @@
 /*
  * PAGE_SHIFT determines the page size
  */
-#ifdef CONFIG_PAGE_SIZE_4KB
-#define PAGE_SHIFT	12
-#endif
-#ifdef CONFIG_PAGE_SIZE_16KB
-#define PAGE_SHIFT	14
-#endif
-#ifdef CONFIG_PAGE_SIZE_64KB
-#define PAGE_SHIFT	16
-#endif
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE - 1))
 
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index b6b097bbf866..5cf59c617126 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -29,11 +29,9 @@ int disabled_cpus;
 
 u64 acpi_saved_sp;
 
-#define MAX_CORE_PIC 256
-
 #define PREFIX			"ACPI: "
 
-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
 {
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edf2bba80130..634ef17fd38b 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -357,6 +357,8 @@ void __init platform_init(void)
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
+
+	early_init_fdt_scan_reserved_mem();
 	unflatten_and_copy_device_tree();
 
 #ifdef CONFIG_NUMA
@@ -390,8 +392,6 @@ static void __init arch_mem_init(char **cmdline_p)
 
 	check_kernel_sections_mem();
 
-	early_init_fdt_scan_reserved_mem();
-
 	/*
 	 * In order to reduce the possibility of kernel panic when failed to
 	 * get IO TLB memory under CONFIG_SWIOTLB, it is better to allocate
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 2b49d30eb7c0..aabee0b280fe 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -88,6 +88,73 @@ void show_ipi_list(struct seq_file *p, int prec)
 	}
 }
 
+static inline void set_cpu_core_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_core_setup_map);
+
+	for_each_cpu(i, &cpu_core_setup_map) {
+		if (cpu_data[cpu].package == cpu_data[i].package) {
+			cpumask_set_cpu(i, &cpu_core_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_core_map[i]);
+		}
+	}
+}
+
+static inline void set_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
+
+	for_each_cpu(i, &cpu_sibling_setup_map) {
+		if (cpus_are_siblings(cpu, i)) {
+			cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
+			cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
+		}
+	}
+}
+
+static inline void clear_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	for_each_cpu(i, &cpu_sibling_setup_map) {
+		if (cpus_are_siblings(cpu, i)) {
+			cpumask_clear_cpu(i, &cpu_sibling_map[cpu]);
+			cpumask_clear_cpu(cpu, &cpu_sibling_map[i]);
+		}
+	}
+
+	cpumask_clear_cpu(cpu, &cpu_sibling_setup_map);
+}
+
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	cpumask_clear(&temp_foreign_map);
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpus_are_siblings(i, k))
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	for_each_online_cpu(i)
+		cpumask_andnot(&cpu_foreign_map[i],
+			       &temp_foreign_map, &cpu_sibling_map[i]);
+}
+
 /* Send mailbox buffer via Mail_Send */
 static void csr_mail_send(uint64_t data, int cpu, int mailbox)
 {
@@ -303,6 +370,7 @@ int loongson_cpu_disable(void)
 	numa_remove_cpu(cpu);
 #endif
 	set_cpu_online(cpu, false);
+	clear_cpu_sibling_map(cpu);
 	calculate_cpu_foreign_map();
 	local_irq_save(flags);
 	irq_migrate_all_off_this_cpu();
@@ -337,6 +405,7 @@ void __noreturn arch_cpu_idle_dead(void)
 		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
 	} while (addr == 0);
 
+	local_irq_disable();
 	init_fn = (void *)TO_CACHE(addr);
 	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
 
@@ -379,59 +448,6 @@ static int __init ipi_pm_init(void)
 core_initcall(ipi_pm_init);
 #endif
 
-static inline void set_cpu_sibling_map(int cpu)
-{
-	int i;
-
-	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);
-
-	for_each_cpu(i, &cpu_sibling_setup_map) {
-		if (cpus_are_siblings(cpu, i)) {
-			cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
-			cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
-		}
-	}
-}
-
-static inline void set_cpu_core_map(int cpu)
-{
-	int i;
-
-	cpumask_set_cpu(cpu, &cpu_core_setup_map);
-
-	for_each_cpu(i, &cpu_core_setup_map) {
-		if (cpu_data[cpu].package == cpu_data[i].package) {
-			cpumask_set_cpu(i, &cpu_core_map[cpu]);
-			cpumask_set_cpu(cpu, &cpu_core_map[i]);
-		}
-	}
-}
-
-/*
- * Calculate a new cpu_foreign_map mask whenever a
- * new cpu appears or disappears.
- */
-void calculate_cpu_foreign_map(void)
-{
-	int i, k, core_present;
-	cpumask_t temp_foreign_map;
-
-	/* Re-calculate the mask */
-	cpumask_clear(&temp_foreign_map);
-	for_each_online_cpu(i) {
-		core_present = 0;
-		for_each_cpu(k, &temp_foreign_map)
-			if (cpus_are_siblings(i, k))
-				core_present = 1;
-		if (!core_present)
-			cpumask_set_cpu(i, &temp_foreign_map);
-	}
-
-	for_each_online_cpu(i)
-		cpumask_andnot(&cpu_foreign_map[i],
-			       &temp_foreign_map, &cpu_sibling_map[i]);
-}
-
 /* Preload SMP state for boot cpu */
 void smp_prepare_boot_cpu(void)
 {
diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c
index 14941e4be66d..90dfccb41c14 100644
--- a/arch/loongarch/kernel/vdso.c
+++ b/arch/loongarch/kernel/vdso.c
@@ -21,15 +21,13 @@
 #include <asm/vdso.h>
 #include <vdso/helpers.h>
 #include <vdso/vsyscall.h>
+#include <vdso/datapage.h>
 #include <generated/vdso-offsets.h>
 
 extern char vdso_start[], vdso_end[];
 
 /* Kernel-provided data used by the VDSO. */
-static union {
-	u8 page[PAGE_SIZE];
-	struct vdso_data data[CS_BASES];
-} generic_vdso_data __page_aligned_data;
+static union vdso_data_store generic_vdso_data __page_aligned_data;
 
 static union {
 	u8 page[LOONGARCH_VDSO_DATA_SIZE];
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 27701991886d..36106922b5d7 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -298,74 +298,73 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val)
 	return ret;
 }
 
-static int _kvm_get_cpucfg(int id, u64 *v)
+static int _kvm_get_cpucfg_mask(int id, u64 *v)
 {
-	int ret = 0;
-
-	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
+	if (id < 0 || id >= KVM_MAX_CPUCFG_REGS)
 		return -EINVAL;
 
 	switch (id) {
 	case 2:
-		/* Return CPUCFG2 features which have been supported by KVM */
+		/* CPUCFG2 features unconditionally supported by KVM */
 		*v = CPUCFG2_FP     | CPUCFG2_FPSP  | CPUCFG2_FPDP     |
 		     CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV |
 		     CPUCFG2_LAM;
 		/*
-		 * If LSX is supported by CPU, it is also supported by KVM,
-		 * as we implement it.
+		 * For the ISA extensions listed below, if one is supported
+		 * by the host, then it is also supported by KVM.
 		 */
 		if (cpu_has_lsx)
 			*v |= CPUCFG2_LSX;
-		/*
-		 * if LASX is supported by CPU, it is also supported by KVM,
-		 * as we implement it.
-		 */
 		if (cpu_has_lasx)
 			*v |= CPUCFG2_LASX;
 
-		break;
+		return 0;
 	default:
-		ret = -EINVAL;
-		break;
+		/*
+		 * No restrictions on other valid CPUCFG IDs' values, but
+		 * CPUCFG data is limited to 32 bits as the LoongArch ISA
+		 * manual says (Volume 1, Section 2.2.10.5 "CPUCFG").
+		 */
+		*v = U32_MAX;
+		return 0;
 	}
-	return ret;
 }
 
 static int kvm_check_cpucfg(int id, u64 val)
 {
-	u64 mask;
-	int ret = 0;
-
-	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
-		return -EINVAL;
+	int ret;
+	u64 mask = 0;
 
-	if (_kvm_get_cpucfg(id, &mask))
+	ret = _kvm_get_cpucfg_mask(id, &mask);
+	if (ret)
 		return ret;
 
+	if (val & ~mask)
+		/* Unsupported features and/or the higher 32 bits should not be set */
+		return -EINVAL;
+
 	switch (id) {
 	case 2:
-		/* CPUCFG2 features checking */
-		if (val & ~mask)
-			/* The unsupported features should not be set */
-			ret = -EINVAL;
-		else if (!(val & CPUCFG2_LLFTP))
-			/* The LLFTP must be set, as guest must has a constant timer */
-			ret = -EINVAL;
-		else if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP)))
-			/* Single and double float point must both be set when enable FP */
-			ret = -EINVAL;
-		else if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP))
-			/* FP should be set when enable LSX */
-			ret = -EINVAL;
-		else if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX))
-			/* LSX, FP should be set when enable LASX, and FP has been checked before. */
-			ret = -EINVAL;
-		break;
+		if (!(val & CPUCFG2_LLFTP))
+			/* Guests must have a constant timer */
+			return -EINVAL;
+		if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP)))
+			/* Single and double float point must both be set when FP is enabled */
+			return -EINVAL;
+		if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP))
+			/* LSX architecturally implies FP but val does not satisfy that */
+			return -EINVAL;
+		if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX))
+			/* LASX architecturally implies LSX and FP but val does not satisfy that */
+			return -EINVAL;
+		return 0;
 	default:
-		break;
+		/*
+		 * Values for the other CPUCFG IDs are not being further validated
+		 * besides the mask check above.
+		 */
+		return 0;
 	}
-	return ret;
 }
 
 static int kvm_get_one_reg(struct kvm_vcpu *vcpu,
@@ -566,7 +565,7 @@ static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
 	uint64_t val;
 	uint64_t __user *uaddr = (uint64_t __user *)attr->addr;
 
-	ret = _kvm_get_cpucfg(attr->attr, &val);
+	ret = _kvm_get_cpucfg_mask(attr->attr, &val);
 	if (ret)
 		return ret;
 
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index cc3e81fe0186..c608adc99845 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr)
 		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
 		unsigned long offset = 0;
 
+		if (maddr >= FIXADDR_START)
+			return (void *)(kasan_early_shadow_page);
+
 		maddr &= XRANGE_SHADOW_MASK;
 		switch (xrange) {
 		case XKPRANGE_CC_SEG:
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index c74c9921304f..f597cd08a96b 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,6 +2,7 @@
 # Objects to go into the VDSO.
 
 KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
 # Include the generic Makefile to check the built vdso.
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 4b3e93cac723..7b709453d5e7 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -84,12 +84,15 @@ config MMU
 
 config MMU_MOTOROLA
 	bool
+	select HAVE_PAGE_SIZE_4KB
 
 config MMU_COLDFIRE
+	select HAVE_PAGE_SIZE_8KB
 	bool
 
 config MMU_SUN3
 	bool
+	select HAVE_PAGE_SIZE_8KB
 	depends on MMU && !MMU_MOTOROLA && !MMU_COLDFIRE
 
 config ARCH_SUPPORTS_KEXEC
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 9dcf245c9cbf..c777a129768a 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -30,6 +30,7 @@ config COLDFIRE
 	select GENERIC_CSUM
 	select GPIOLIB
 	select HAVE_LEGACY_CLK
+	select HAVE_PAGE_SIZE_8KB if !MMU
 
 endchoice
 
@@ -45,6 +46,7 @@ config M68000
 	select GENERIC_CSUM
 	select CPU_NO_EFFICIENT_FFS
 	select HAVE_ARCH_HASH
+	select HAVE_PAGE_SIZE_4KB
 	select LEGACY_TIMER_TICK
 	help
 	  The Freescale (was Motorola) 68000 CPU is the first generation of
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 43e39040d3ac..0abcf994ce55 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -15,10 +15,10 @@
 KBUILD_DEFCONFIG := multi_defconfig
 
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+    ifeq ($(CROSS_COMPILE),)
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-)
-	endif
+    endif
 endif
 
 #
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index b4d71fea558f..a6f6607efe79 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -336,7 +336,6 @@ CONFIG_ATA=y
 CONFIG_PATA_GAYLE=y
 CONFIG_PATA_BUDDHA=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -579,12 +578,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 682d8cd3dd3c..0ca1f9f930bc 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -316,7 +316,6 @@ CONFIG_SCSI_SAS_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -536,12 +535,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 15259ced8463..be030659d8d7 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -331,7 +331,6 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_FALCON=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -556,12 +555,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 7395c12caef6..ad8f81fbb630 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -314,7 +314,6 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_BVME6000_SCSI=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -528,12 +527,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 92506bc7f78d..ff253b6accec 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -315,7 +315,6 @@ CONFIG_SCSI_SAS_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -538,12 +537,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 144bc8c0d8b5..f92b866620a7 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -320,7 +320,6 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_PLATFORM=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -555,12 +554,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 07594c729497..bd813beaa8a7 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -363,7 +363,6 @@ CONFIG_PATA_GAYLE=y
 CONFIG_PATA_BUDDHA=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -641,12 +640,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index c34de6c1de20..2237ee0fe433 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -313,7 +313,6 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MVME147_SCSI=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -527,12 +526,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 83bc029d1f33..afb5aa9c5012 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -314,7 +314,6 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_MVME16x_SCSI=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -528,12 +527,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 4f551dac2ed7..e40f7a308966 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -320,7 +320,6 @@ CONFIG_ATA=y
 # CONFIG_ATA_BMDMA is not set
 CONFIG_PATA_FALCON=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -545,12 +544,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index b1bf01182bd3..4df397c0395f 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -310,7 +310,6 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_SUN3_SCSI=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -526,12 +525,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 5c9a3f71f036..aa7719b3947f 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -311,7 +311,6 @@ CONFIG_ISCSI_TCP=m
 CONFIG_ISCSI_BOOT_SYSFS=m
 CONFIG_SUN3X_ESP=y
 CONFIG_MD=y
-CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
@@ -526,12 +525,10 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_AEGIS128=m
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index a708fbd5a844..642fb80c5c4e 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -96,6 +96,9 @@ static const struct block_device_operations nfhd_ops = {
 
 static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= bsize,
+	};
 	struct nfhd_device *dev;
 	int dev_id = id - NFHD_DEV_OFFSET;
 	int err = -ENOMEM;
@@ -117,9 +120,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->disk)
+	dev->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(dev->disk)) {
+		err = PTR_ERR(dev->disk);
 		goto free_dev;
+	}
 
 	dev->disk->major = major_num;
 	dev->disk->first_minor = dev_id * 16;
@@ -128,7 +133,6 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->disk->private_data = dev;
 	sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
 	set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
-	blk_queue_logical_block_size(dev->disk->queue, bsize);
 	err = add_disk(dev->disk);
 	if (err)
 		goto out_cleanup_disk;
diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h
index a5993ad83ed8..8cfb84b49975 100644
--- a/arch/m68k/include/asm/page.h
+++ b/arch/m68k/include/asm/page.h
@@ -7,11 +7,7 @@
 #include <asm/page_offset.h>
 
 /* PAGE_SHIFT determines the page size */
-#if defined(CONFIG_SUN3) || defined(CONFIG_COLDFIRE)
-#define PAGE_SHIFT	13
-#else
-#define PAGE_SHIFT	12
-#endif
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 #define PAGE_OFFSET	(PAGE_OFFSET_RAW)
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 211f338d6235..f18ec02ddeb2 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -31,6 +31,7 @@ config MICROBLAZE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCI
 	select IRQ_DOMAIN
 	select XILINX_INTC
diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h
index 86a4ce07c192..8810f4f1c3b0 100644
--- a/arch/microblaze/include/asm/page.h
+++ b/arch/microblaze/include/asm/page.h
@@ -20,7 +20,7 @@
 #ifdef __KERNEL__
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT		12
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(ASM_CONST(1) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 797ae590ebdb..24bac93affee 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -81,6 +81,9 @@ config MIPS
 	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
+	select HAVE_PAGE_SIZE_4KB if !CPU_LOONGSON2EF && !CPU_LOONGSON64
+	select HAVE_PAGE_SIZE_16KB if !CPU_R3000
+	select HAVE_PAGE_SIZE_64KB if !CPU_R3000
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
@@ -1608,6 +1611,8 @@ config CPU_CAVIUM_OCTEON
 	depends on SYS_HAS_CPU_CAVIUM_OCTEON
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_64BIT_KERNEL
+	select HAVE_PAGE_SIZE_8KB if !MIPS_VA_BITS_48
+	select HAVE_PAGE_SIZE_32KB if !MIPS_VA_BITS_48
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
@@ -2029,59 +2034,6 @@ config ZBOOT_LOAD_ADDRESS
 
 	  This is only used if non-zero.
 
-choice
-	prompt "Kernel page size"
-	default PAGE_SIZE_4KB
-
-config PAGE_SIZE_4KB
-	bool "4kB"
-	depends on !CPU_LOONGSON2EF && !CPU_LOONGSON64
-	help
-	  This option select the standard 4kB Linux page size.  On some
-	  R3000-family processors this is the only available page size.  Using
-	  4kB page size will minimize memory consumption and is therefore
-	  recommended for low memory systems.
-
-config PAGE_SIZE_8KB
-	bool "8kB"
-	depends on CPU_CAVIUM_OCTEON
-	depends on !MIPS_VA_BITS_48
-	help
-	  Using 8kB page size will result in higher performance kernel at
-	  the price of higher memory consumption.  This option is available
-	  only on cnMIPS processors.  Note that you will need a suitable Linux
-	  distribution to support this.
-
-config PAGE_SIZE_16KB
-	bool "16kB"
-	depends on !CPU_R3000
-	help
-	  Using 16kB page size will result in higher performance kernel at
-	  the price of higher memory consumption.  This option is available on
-	  all non-R3000 family processors.  Note that you will need a suitable
-	  Linux distribution to support this.
-
-config PAGE_SIZE_32KB
-	bool "32kB"
-	depends on CPU_CAVIUM_OCTEON
-	depends on !MIPS_VA_BITS_48
-	help
-	  Using 32kB page size will result in higher performance kernel at
-	  the price of higher memory consumption.  This option is available
-	  only on cnMIPS cores.  Note that you will need a suitable Linux
-	  distribution to support this.
-
-config PAGE_SIZE_64KB
-	bool "64kB"
-	depends on !CPU_R3000
-	help
-	  Using 64kB page size will result in higher performance kernel at
-	  the price of higher memory consumption.  This option is available on
-	  all non-R3000 family processor.  Not that at the time of this
-	  writing this option is still high experimental.
-
-endchoice
-
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
 	default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 4044eaf989ac..0921ddda11a4 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	"	.set	pop"
 	: "=&r" (sum), "=&r" (tmp)
 	: "r" (saddr), "r" (daddr),
-	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum));
+	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)
+	: "memory");
 
 	return csum_fold(sum);
 }
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 081be98c71ef..ff5d388502d4 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -39,7 +39,7 @@ extern void jump_label_apply_nops(struct module *mod);
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+	asm goto("1:\t" B_INSN " 2f\n\t"
 		"2:\t.insn\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
@@ -53,7 +53,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
+	asm goto("1:\t" J_INSN " %l[l_yes]\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ef9585d96f6b..4609cb0326cf 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -17,21 +17,7 @@
 /*
  * PAGE_SHIFT determines the page size
  */
-#ifdef CONFIG_PAGE_SIZE_4KB
-#define PAGE_SHIFT	12
-#endif
-#ifdef CONFIG_PAGE_SIZE_8KB
-#define PAGE_SHIFT	13
-#endif
-#ifdef CONFIG_PAGE_SIZE_16KB
-#define PAGE_SHIFT	14
-#endif
-#ifdef CONFIG_PAGE_SIZE_32KB
-#define PAGE_SHIFT	15
-#endif
-#ifdef CONFIG_PAGE_SIZE_64KB
-#define PAGE_SHIFT	16
-#endif
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~((1 << PAGE_SHIFT) - 1))
 
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index daf3cf244ea9..d14d0e37ad02 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
                                            unsigned long val)
 {
 	regs->cp0_epc = val;
+	regs->cp0_cause &= ~CAUSEF_BD;
 }
 
 /* Query offset/name of register from its name/offset */
@@ -154,6 +155,8 @@ static inline long regs_return_value(struct pt_regs *regs)
 }
 
 #define instruction_pointer(regs) ((regs)->cp0_epc)
+extern unsigned long exception_ip(struct pt_regs *regs);
+#define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)
 
 extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h
index cc7b516129a8..afb03d45bcd0 100644
--- a/arch/mips/include/asm/vdso.h
+++ b/arch/mips/include/asm/vdso.h
@@ -50,9 +50,4 @@ extern struct mips_vdso_image vdso_image_o32;
 extern struct mips_vdso_image vdso_image_n32;
 #endif
 
-union mips_vdso_data {
-	struct vdso_data data[CS_BASES];
-	u8 page[PAGE_SIZE];
-};
-
 #endif /* __ASM_VDSO_H */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index d9df543f7e2c..59288c13b581 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -31,6 +31,7 @@
 #include <linux/seccomp.h>
 #include <linux/ftrace.h>
 
+#include <asm/branch.h>
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
@@ -48,6 +49,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+unsigned long exception_ip(struct pt_regs *regs)
+{
+	return exception_epc(regs);
+}
+EXPORT_SYMBOL(exception_ip);
+
 /*
  * Called by kernel/ptrace.c when detaching..
  *
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index f6d40e43f108..dda36fa26307 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -24,7 +24,7 @@
 #include <vdso/vsyscall.h>
 
 /* Kernel-provided data used by the VDSO. */
-static union mips_vdso_data mips_vdso_data __page_aligned_data;
+static union vdso_data_store mips_vdso_data __page_aligned_data;
 struct vdso_data *vdso_data = mips_vdso_data.data;
 
 /*
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 58d9565dc2c7..79d3039b29f1 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -15,6 +15,7 @@ config NIOS2
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_KGDB
+	select HAVE_PAGE_SIZE_4KB
 	select IRQ_DOMAIN
 	select LOCK_MM_AND_FIND_VMA
 	select MODULES_USE_ELF_RELA
diff --git a/arch/nios2/include/asm/page.h b/arch/nios2/include/asm/page.h
index 0ae7d9ce369b..0722f88e63cc 100644
--- a/arch/nios2/include/asm/page.h
+++ b/arch/nios2/include/asm/page.h
@@ -21,7 +21,7 @@
 /*
  * PAGE_SHIFT determines the page size
  */
-#define PAGE_SHIFT	12
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE - 1))
 
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index fd9bb76a610b..3586cda55bde 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -25,6 +25,7 @@ config OPENRISC
 	select GENERIC_CPU_DEVICES
 	select HAVE_PCI
 	select HAVE_UID16
+	select HAVE_PAGE_SIZE_8KB
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/openrisc/include/asm/page.h b/arch/openrisc/include/asm/page.h
index 44fc1fd56717..1d5913f67c31 100644
--- a/arch/openrisc/include/asm/page.h
+++ b/arch/openrisc/include/asm/page.h
@@ -18,7 +18,7 @@
 
 /* PAGE_SHIFT determines the page size */
 
-#define PAGE_SHIFT      13
+#define PAGE_SHIFT      CONFIG_PAGE_SHIFT
 #ifdef __ASSEMBLY__
 #define PAGE_SIZE       (1 << PAGE_SHIFT)
 #else
@@ -77,11 +77,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 	return __pa(kaddr) >> PAGE_SHIFT;
 }
 
-static inline void * pfn_to_virt(unsigned long pfn)
-{
-	return (void *)((unsigned long)__va(pfn) << PAGE_SHIFT);
-}
-
 #define virt_to_page(addr) \
 	(mem_map + (((unsigned long)(addr)-PAGE_OFFSET) >> PAGE_SHIFT))
 
diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c
index 1c5a2d71d675..86da4bc5ee0b 100644
--- a/arch/openrisc/kernel/smp.c
+++ b/arch/openrisc/kernel/smp.c
@@ -57,10 +57,6 @@ static void boot_secondary(unsigned int cpu, struct task_struct *idle)
 	spin_unlock(&boot_lock);
 }
 
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 void __init smp_init_cpus(void)
 {
 	struct device_node *cpu;
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index d14ccc948a29..b180e684fa0d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -25,7 +25,6 @@ config PARISC
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
-	select BUILDTIME_TABLE_SORT
 	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
@@ -274,6 +273,7 @@ choice
 
 config PARISC_PAGE_SIZE_4KB
 	bool "4KB"
+	select HAVE_PAGE_SIZE_4KB
 	help
 	  This lets you select the page size of the kernel.  For best
 	  performance, a page size of 16KB is recommended.  For best
@@ -289,10 +289,12 @@ config PARISC_PAGE_SIZE_4KB
 
 config PARISC_PAGE_SIZE_16KB
 	bool "16KB"
+	select HAVE_PAGE_SIZE_16KB
 	depends on PA8X00 && BROKEN && !KFENCE
 
 config PARISC_PAGE_SIZE_64KB
 	bool "64KB"
+	select HAVE_PAGE_SIZE_64KB
 	depends on PA8X00 && BROKEN && !KFENCE
 
 endchoice
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 920db57b6b4c..316f84f1d15c 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -50,12 +50,12 @@ export CROSS32CC
 
 # Set default cross compiler for kernel build
 ifdef cross_compiling
-	ifeq ($(CROSS_COMPILE),)
+    ifeq ($(CROSS_COMPILE),)
 		CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux
 		CROSS_COMPILE := $(call cc-cross-prefix, \
 			$(foreach a,$(CC_ARCHES), \
 			$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
-	endif
+    endif
 endif
 
 ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 74d17d7e759d..5937d5edaba1 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -576,6 +576,7 @@
 	.section __ex_table,"aw"			!	\
 	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
+	or %r0,%r0,%r0					!	\
 	.previous
 
 
diff --git a/arch/parisc/include/asm/extable.h b/arch/parisc/include/asm/extable.h
new file mode 100644
index 000000000000..4ea23e3d79dc
--- /dev/null
+++ b/arch/parisc/include/asm/extable.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PARISC_EXTABLE_H
+#define __PARISC_EXTABLE_H
+
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+
+/*
+ * The exception table consists of three addresses:
+ *
+ * - A relative address to the instruction that is allowed to fault.
+ * - A relative address at which the program should continue (fixup routine)
+ * - An asm statement which specifies which CPU register will
+ *   receive -EFAULT when an exception happens if the lowest bit in
+ *   the fixup address is set.
+ *
+ * Note: The register specified in the err_opcode instruction will be
+ * modified at runtime if a fault happens. Register %r0 will be ignored.
+ *
+ * Since relative addresses are used, 32bit values are sufficient even on
+ * 64bit kernel.
+ */
+
+struct pt_regs;
+int fixup_exception(struct pt_regs *regs);
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+struct exception_table_entry {
+	int insn;	/* relative address of insn that is allowed to fault. */
+	int fixup;	/* relative address of fixup routine */
+	int err_opcode; /* sample opcode with register which holds error code */
+};
+
+#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\
+	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
+	".word (" #fault_addr " - .), (" #except_addr " - .)\n" \
+	opcode "\n"					   \
+	".previous\n"
+
+/*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT on fault into the register specified by the err_opcode instruction,
+ * and zeroes the target register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_VAR(__err_var)		\
+	int __err_var = 0
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\
+	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register)
+
+static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
+				       struct exception_table_entry *b,
+				       struct exception_table_entry tmp,
+				       int delta)
+{
+	a->fixup = b->fixup + delta;
+	b->fixup = tmp.fixup - delta;
+	a->err_opcode = b->err_opcode;
+	b->err_opcode = tmp.err_opcode;
+}
+#define swap_ex_entry_fixup swap_ex_entry_fixup
+
+#endif
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 94428798b6aa..317ebc5edc9f 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
@@ -29,7 +29,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h
index 0a175ac87698..0f42f5c8e3b6 100644
--- a/arch/parisc/include/asm/kprobes.h
+++ b/arch/parisc/include/asm/kprobes.h
@@ -10,9 +10,10 @@
 #ifndef _PARISC_KPROBES_H
 #define _PARISC_KPROBES_H
 
+#include <asm-generic/kprobes.h>
+
 #ifdef CONFIG_KPROBES
 
-#include <asm-generic/kprobes.h>
 #include <linux/types.h>
 #include <linux/ptrace.h>
 #include <linux/notifier.h>
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 667e703c0e8f..ad4e15d12ed1 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -4,15 +4,7 @@
 
 #include <linux/const.h>
 
-#if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-# define PAGE_SHIFT	12
-#elif defined(CONFIG_PARISC_PAGE_SIZE_16KB)
-# define PAGE_SHIFT	14
-#elif defined(CONFIG_PARISC_PAGE_SIZE_64KB)
-# define PAGE_SHIFT	16
-#else
-# error "unknown default kernel page size"
-#endif
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h
index c822bd0c0e3c..51f40eaf7780 100644
--- a/arch/parisc/include/asm/special_insns.h
+++ b/arch/parisc/include/asm/special_insns.h
@@ -8,7 +8,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%1),%0\n"			\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
@@ -22,7 +23,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%%sr3,%1),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 4165079898d9..88d0ae5769dd 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -7,6 +7,7 @@
  */
 #include <asm/page.h>
 #include <asm/cache.h>
+#include <asm/extable.h>
 
 #include <linux/bug.h>
 #include <linux/string.h>
@@ -26,37 +27,6 @@
 #define STD_USER(sr, x, ptr)	__put_user_asm(sr, "std", x, ptr)
 #endif
 
-/*
- * The exception table contains two values: the first is the relative offset to
- * the address of the instruction that is allowed to fault, and the second is
- * the relative offset to the address of the fixup routine. Since relative
- * addresses are used, 32bit values are sufficient even on 64bit kernel.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-struct exception_table_entry {
-	int insn;	/* relative address of insn that is allowed to fault. */
-	int fixup;	/* relative address of fixup routine */
-};
-
-#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
-	".section __ex_table,\"aw\"\n"			   \
-	".align 4\n"					   \
-	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
-	".previous\n"
-
-/*
- * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
- * (with lowest bit set) for which the fault handler in fixup_exception() will
- * load -EFAULT into %r29 for a read or write fault, and zeroes the target
- * register in case of a read fault in get_user().
- */
-#define ASM_EXCEPTIONTABLE_REG	29
-#define ASM_EXCEPTIONTABLE_VAR(__variable)		\
-	register long __variable __asm__ ("r29") = 0
-#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
-	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
-
 #define __get_user_internal(sr, val, ptr)		\
 ({							\
 	ASM_EXCEPTIONTABLE_VAR(__gu_err);		\
@@ -83,7 +53,7 @@ struct exception_table_entry {
 							\
 	__asm__("1: " ldx " 0(%%sr%2,%3),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
 		: "=r"(__gu_val), "+r"(__gu_err)        \
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -115,8 +85,8 @@ struct exception_table_entry {
 		"1: ldw 0(%%sr%2,%3),%0\n"		\
 		"2: ldw 4(%%sr%2,%3),%R0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1")	\
 		: "=&r"(__gu_tmp.l), "+r"(__gu_err)	\
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -174,7 +144,7 @@ struct exception_table_entry {
 	__asm__ __volatile__ (					\
 		"1: " stx " %1,0(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(x), "i"(sr), "r"(ptr))
 
@@ -186,15 +156,14 @@ struct exception_table_entry {
 		"1: stw %1,0(%%sr%2,%3)\n"			\
 		"2: stw %R1,4(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(__val), "i"(sr), "r"(ptr));		\
 } while (0)
 
 #endif /* !defined(CONFIG_64BIT) */
 
-
 /*
  * Complex access routines -- external declarations
  */
@@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
 #define INLINE_COPY_TO_USER
 #define INLINE_COPY_FROM_USER
 
-struct pt_regs;
-int fixup_exception(struct pt_regs *regs);
-
 #endif /* __PARISC_UACCESS_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 268d90a9325b..422f3e1e6d9c 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init;
 
 struct pdc_cache_info cache_info __ro_after_init;
 #ifndef CONFIG_PA20
-struct pdc_btlb_info btlb_info __ro_after_init;
+struct pdc_btlb_info btlb_info;
 #endif
 
 DEFINE_STATIC_KEY_TRUE(parisc_has_cache);
@@ -264,6 +264,10 @@ parisc_cache_init(void)
 	icache_stride = CAFL_STRIDE(cache_info.ic_conf);
 #undef CAFL_STRIDE
 
+	/* stride needs to be non-zero, otherwise cache flushes will not work */
+	WARN_ON(cache_info.dc_size && dcache_stride == 0);
+	WARN_ON(cache_info.ic_size && icache_stride == 0);
+
 	if ((boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) ==
 						PDC_MODEL_NVA_UNSUPPORTED) {
 		printk(KERN_WARNING "parisc_cache_init: Only equivalent aliasing supported!\n");
@@ -850,7 +854,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fic,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (dcache_stride), "i" (SR_USER));
 	}
@@ -865,7 +869,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fdc,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (icache_stride), "i" (SR_USER));
 	}
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 25f9b9e9d6df..c7ff339732ba 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -742,7 +742,7 @@ parse_tree_node(struct device *parent, int index, struct hardware_path *modpath)
 	};
 
 	if (device_for_each_child(parent, &recurse_data, descend_children))
-		{ /* nothing */ };
+		{ /* nothing */ }
 
 	return d.dev;
 }
@@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
 
 	pr_info("\n");
 
+	/* Prevent hung task messages when printing on serial console */
+	cond_resched();
+
 	pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n",
 		hpa, parisc_hardware_description(&dev->id));
 
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index d1defb9ede70..621a4b386ae4 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -78,7 +78,7 @@ asmlinkage void notrace __hot ftrace_function_trampoline(unsigned long parent,
 #endif
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER)
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	static_key_enable(&ftrace_graph_enable.key);
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e95a977ba5f3..bf73562706b2 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -172,7 +172,6 @@ static int __init processor_probe(struct parisc_device *dev)
 	p->cpu_num = cpu_info.cpu_num;
 	p->cpu_loc = cpu_info.cpu_loc;
 
-	set_cpu_possible(cpuid, true);
 	store_cpu_topology(cpuid);
 
 #ifdef CONFIG_SMP
@@ -474,13 +473,6 @@ static struct parisc_driver cpu_driver __refdata = {
  */
 void __init processor_init(void)
 {
-	unsigned int cpu;
-
 	reset_cpu_topology();
-
-	/* reset possible mask. We will mark those which are possible. */
-	for_each_possible_cpu(cpu)
-		set_cpu_possible(cpu, false);
-
 	register_parisc_driver(&cpu_driver);
 }
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index ce25acfe4889..c520e551a165 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg)
 "2:	ldbs	1(%%sr1,%3), %0\n"
 "	depw	%2, 23, 24, %0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop)
 "	mtctl	%2,11\n"
 "	vshd	%0,%3,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2)
 	: "r" (saddr), "r" (regs->isr) );
 
@@ -189,8 +189,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	mtsar	%%r19\n"
 "	shrpd	%0,%%r20,%%sar,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "=r" (val), "+r" (ret)
 	: "0" (val), "r" (saddr), "r" (regs->isr)
 	: "r19", "r20" );
@@ -209,9 +209,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	vshd	%0,%R0,%0\n"
 "	vshd	%R0,%4,%R0\n"
 "4:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1")
 	: "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1)
 	: "r" (regs->isr) );
     }
@@ -244,8 +244,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg)
 "1:	stb %1, 0(%%sr1, %3)\n"
 "2:	stb %2, 1(%%sr1, %3)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret), "=&r" (temp1)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr) );
 
@@ -285,8 +285,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop)
 "	stw	%%r20,0(%%sr1,%2)\n"
 "	stw	%%r21,4(%%sr1,%2)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -329,10 +329,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "3:	std	%%r20,0(%%sr1,%2)\n"
 "4:	std	%%r21,8(%%sr1,%2)\n"
 "5:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -357,11 +357,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "4:	stw	%%r1,4(%%sr1,%2)\n"
 "5:	stw	%R1,8(%%sr1,%2)\n"
 "6:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r1" );
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 27ae40a443b8..f7e0fee5ee55 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -228,10 +228,8 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 #ifdef CONFIG_IRQSTACKS
 	extern void * const _call_on_stack;
 #endif /* CONFIG_IRQSTACKS */
-	void *ptr;
 
-	ptr = dereference_kernel_function_descriptor(&handle_interruption);
-	if (pc_is_kernel_fn(pc, ptr)) {
+	if (pc_is_kernel_fn(pc, handle_interruption)) {
 		struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
 		dbg("Unwinding through handle_interruption()\n");
 		info->prev_sp = regs->gr[30];
@@ -239,13 +237,13 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 		return 1;
 	}
 
-	if (pc_is_kernel_fn(pc, ret_from_kernel_thread) ||
-	    pc_is_kernel_fn(pc, syscall_exit)) {
+	if (pc == (unsigned long)&ret_from_kernel_thread ||
+	    pc == (unsigned long)&syscall_exit) {
 		info->prev_sp = info->prev_ip = 0;
 		return 1;
 	}
 
-	if (pc_is_kernel_fn(pc, intr_return)) {
+	if (pc == (unsigned long)&intr_return) {
 		struct pt_regs *regs;
 
 		dbg("Found intr_return()\n");
@@ -257,14 +255,14 @@ static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int
 	}
 
 	if (pc_is_kernel_fn(pc, _switch_to) ||
-	    pc_is_kernel_fn(pc, _switch_to_ret)) {
+	    pc == (unsigned long)&_switch_to_ret) {
 		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
 		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
 		return 1;
 	}
 
 #ifdef CONFIG_IRQSTACKS
-	if (pc_is_kernel_fn(pc, _call_on_stack)) {
+	if (pc == (unsigned long)&_call_on_stack) {
 		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
 		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 548051b0b4af..b445e47903cf 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -127,7 +127,7 @@ SECTIONS
 	}
 #endif
 
-	RO_DATA(8)
+	RO_DATA(PAGE_SIZE)
 
 	/* unwind info */
 	. = ALIGN(4);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 2fe5b44986e0..c39de84e98b0 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs)
 		 * Fix up get_user() and put_user().
 		 * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
 		 * bit in the relative address of the fixup routine to indicate
-		 * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with
-		 * -EFAULT to report a userspace access error.
+		 * that the register encoded in the "or %r0,%r0,register"
+		 * opcode should be loaded with -EFAULT to report a userspace
+		 * access error.
 		 */
 		if (fix->fixup & 1) {
-			regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT;
+			int fault_error_reg = fix->err_opcode & 0x1f;
+			if (!WARN_ON(!fault_error_reg))
+				regs->gr[fault_error_reg] = -EFAULT;
+			pr_debug("Unalignment fixup of register %d at %pS\n",
+				fault_error_reg, (void*)regs->iaoq[0]);
 
 			/* zero target register for get_user() */
 			if (parisc_acctyp(0, regs->iir) == VM_READ) {
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b9fc064d38d2..8fad4e5d7ad5 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -212,7 +212,7 @@ config PPC
 	select HAVE_ARCH_HUGE_VMAP		if PPC_RADIX_MMU || PPC_8xx
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
-	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
+	select HAVE_ARCH_KASAN			if PPC32 && PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN			if PPC_RADIX_MMU
 	select HAVE_ARCH_KASAN			if PPC_BOOK3E_64
 	select HAVE_ARCH_KASAN_VMALLOC		if HAVE_ARCH_KASAN
@@ -809,19 +809,23 @@ choice
 config PPC_4K_PAGES
 	bool "4k page size"
 	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+	select HAVE_PAGE_SIZE_4KB
 
 config PPC_16K_PAGES
 	bool "16k page size"
 	depends on 44x || PPC_8xx
+	select HAVE_PAGE_SIZE_16KB
 
 config PPC_64K_PAGES
 	bool "64k page size"
 	depends on 44x || PPC_BOOK3S_64
 	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
+	select HAVE_PAGE_SIZE_64KB
 
 config PPC_256K_PAGES
 	bool "256k page size (Requires non-standard binutils settings)"
 	depends on 44x && !PPC_47x
+	select HAVE_PAGE_SIZE_256KB
 	help
 	  Make the page size 256k.
 
@@ -832,29 +836,6 @@ config PPC_256K_PAGES
 
 endchoice
 
-config PAGE_SIZE_4KB
-	def_bool y
-	depends on PPC_4K_PAGES
-
-config PAGE_SIZE_16KB
-	def_bool y
-	depends on PPC_16K_PAGES
-
-config PAGE_SIZE_64KB
-	def_bool y
-	depends on PPC_64K_PAGES
-
-config PAGE_SIZE_256KB
-	def_bool y
-	depends on PPC_256K_PAGES
-
-config PPC_PAGE_SHIFT
-	int
-	default 18 if PPC_256K_PAGES
-	default 16 if PPC_64K_PAGES
-	default 14 if PPC_16K_PAGES
-	default 12
-
 config THREAD_SHIFT
 	int "Thread shift" if EXPERT
 	range 13 15
@@ -891,7 +872,7 @@ config DATA_SHIFT
 	default 23 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx && PIN_TLB_DATA
 	default 19 if (DEBUG_PAGEALLOC || KFENCE) && PPC_8xx
 	default 24 if STRICT_KERNEL_RWX && PPC_85xx
-	default PPC_PAGE_SHIFT
+	default PAGE_SHIFT
 	help
 	  On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
 	  Smaller is the alignment, greater is the number of necessary DBATs.
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 1ebd2ca97f12..107fc5a48456 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -20,14 +20,6 @@
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
 
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
-		addr += MCOUNT_INSN_SIZE;
-
-	return addr;
-}
-
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp);
 
@@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
 #ifdef CONFIG_FUNCTION_TRACER
 extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
 void ftrace_free_init_tramp(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
 #else
 static inline void ftrace_free_init_tramp(void) { }
+static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
 #endif
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 93ce3ec25387..2f2a86ed2280 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e5fcc79b5bfb..e411e5a70ea3 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -21,7 +21,7 @@
  * page size. When using 64K pages however, whether we are really supporting
  * 64K pages in HW or not is irrelevant to those definitions.
  */
-#define PAGE_SHIFT		CONFIG_PPC_PAGE_SHIFT
+#define PAGE_SHIFT		CONFIG_PAGE_SHIFT
 #define PAGE_SIZE		(ASM_CONST(1) << PAGE_SHIFT)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index 0dbbff59101d..c3cd5b131033 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -32,7 +32,7 @@ typedef struct {
  */
 struct papr_sysparm_buf {
 	__be16 len;
-	char val[PAPR_SYSPARM_MAX_OUTPUT];
+	u8 val[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void);
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index ce2b1b5eebdd..a8b7e8682f5b 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start,
 				void *data);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
+#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \
+				  defined(CONFIG_PPC_POWERNV))
+extern void ppc_iommu_register_device(struct pci_controller *phb);
+extern void ppc_iommu_unregister_device(struct pci_controller *phb);
+#else
+static inline void ppc_iommu_register_device(struct pci_controller *phb) { }
+static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { }
+#endif
+
+
 /* From rtas_pci.h */
 extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7fd09f25452d..bb47af9054a9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -617,6 +617,8 @@
 #endif
 #define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
 #define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE	0x3F3		/* G2_LE HID2 Register */
+#define  HID2_G2_LE_HBE	(1<<18)		/* High BAT Enable (G2_LE) */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 9bb2210c8d44..065ffd1b2f8a 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -69,7 +69,7 @@ enum rtas_function_index {
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE,
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2,
 	RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW,
-	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS,
+	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW,
 	RTAS_FNIDX__IBM_SCAN_LOG_DUMP,
 	RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR,
 	RTAS_FNIDX__IBM_SET_EEH_OPTION,
@@ -164,7 +164,7 @@ typedef struct {
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE         rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE)
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2        rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2)
 #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW          rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW)
-#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS          rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS)
+#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW           rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW)
 #define RTAS_FN_IBM_SCAN_LOG_DUMP                 rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP)
 #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR         rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR)
 #define RTAS_FN_IBM_SET_EEH_OPTION                rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index ea26665f82cf..f43f3a6b0051 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t;
 
 extern char __head_end[];
 extern char __srwx_boundary[];
+extern char __exittext_begin[], __exittext_end[];
 
 /* Patch sites */
 extern s32 patch__call_flush_branch_caches1;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index bf5dde1a4114..15c5691dd218 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
 #define MIN_THREAD_SHIFT	(CONFIG_THREAD_SHIFT + 1)
 #else
 #define MIN_THREAD_SHIFT	CONFIG_THREAD_SHIFT
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f1f9890f50d3..de10437fd206 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -74,7 +74,7 @@ __pu_failed:							\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op " %0,0(%1)	# put_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -83,7 +83,7 @@ __pu_failed:							\
 		: label)
 #else
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -97,7 +97,7 @@ __pu_failed:							\
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -146,7 +146,7 @@ do {								\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op" %0,0(%1)	# get_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -155,7 +155,7 @@ do {								\
 		: label)
 #else
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op"%U1%X1 %0, %1	# get_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -169,7 +169,7 @@ do {								\
 	__get_user_asm_goto(x, addr, label, "ld")
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	lwz%X1 %0, %1\n"			\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
index 9f9a0f267ea5..f733467b1534 100644
--- a/arch/powerpc/include/uapi/asm/papr-sysparm.h
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -14,7 +14,7 @@ enum {
 struct papr_sysparm_io_block {
 	__u32 parameter;
 	__u16 length;
-	char data[PAPR_SYSPARM_MAX_OUTPUT];
+	__u8 data[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 /**
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f29ce3dd6140..bfd3f442e5eb 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
+
+	/*
+	 * This assumes that all cores using __setup_cpu_603 with
+	 * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+	 */
+BEGIN_MMU_FTR_SECTION
+	bl      setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
 	blr
 SYM_FUNC_END(setup_604_hid0)
 
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+	mfspr	r11,SPRN_HID2_G2_LE
+	oris	r11,r11,HID2_G2_LE_HBE@h
+	mtspr	SPRN_HID2_G2_LE,r11
+	sync
+	isync
+	blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
  * erratas we work around here.
  * Moto MPC710CE.pdf describes them, those are errata
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
 	mtcr	r7
 	blr
 _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
index ceb06b109f83..2ae8e9a7b461 100644
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@
 
 #ifdef CONFIG_PPC64
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
-				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+				 PPC_FEATURE_BOOKE)
 #else
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
 				 PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bd863702d812..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
-	std	r11,_NIP(r1)
+	std	r11,_LINK(r1)
+	std	r11,_NIP(r1)	/* Saved LR is also the next instruction */
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
-	std	r11,_LINK(r1)
 	std	r11,_CTR(r1)
 
 	li	r11,\trapnr
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ebe259bdd462..1185efebf032 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1287,20 +1287,22 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
-	int ret = -EINVAL;
 
 	/* At first attach the ownership is already set */
-	if (!domain)
+	if (!domain) {
+		iommu_group_put(grp);
 		return 0;
-
-	if (!grp)
-		return -ENODEV;
+	}
 
 	table_group = iommu_group_get_iommudata(grp);
-	ret = table_group->ops->take_ownership(table_group);
+	/*
+	 * The domain being set to PLATFORM from earlier
+	 * BLOCKED. The table_group ownership has to be released.
+	 */
+	table_group->ops->release_ownership(table_group);
 	iommu_group_put(grp);
 
-	return ret;
+	return 0;
 }
 
 static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
@@ -1312,13 +1314,32 @@ static struct iommu_domain spapr_tce_platform_domain = {
 	.ops = &spapr_tce_platform_domain_ops,
 };
 
-static struct iommu_domain spapr_tce_blocked_domain = {
-	.type = IOMMU_DOMAIN_BLOCKED,
+static int
+spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
+				     struct device *dev)
+{
+	struct iommu_group *grp = iommu_group_get(dev);
+	struct iommu_table_group *table_group;
+	int ret = -EINVAL;
+
 	/*
 	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
 	 * also sets the dma_api ops
 	 */
-	.ops = &spapr_tce_platform_domain_ops,
+	table_group = iommu_group_get_iommudata(grp);
+	ret = table_group->ops->take_ownership(table_group);
+	iommu_group_put(grp);
+
+	return ret;
+}
+
+static const struct iommu_domain_ops spapr_tce_blocked_domain_ops = {
+	.attach_dev = spapr_tce_blocked_iommu_attach_dev,
+};
+
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &spapr_tce_blocked_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
@@ -1339,7 +1360,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
 	struct pci_controller *hose;
 
 	if (!dev_is_pci(dev))
-		return ERR_PTR(-EPERM);
+		return ERR_PTR(-ENODEV);
 
 	pdev = to_pci_dev(dev);
 	hose = pdev->bus->sysdata;
@@ -1388,6 +1409,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
 	NULL,
 };
 
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+	iommu_device_sysfs_add(&phb->iommu, phb->parent,
+				spapr_tce_iommu_groups, "iommu-phb%04x",
+				phb->global_number);
+	iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+				phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+	iommu_device_unregister(&phb->iommu);
+	iommu_device_sysfs_remove(&phb->iommu);
+}
+
 /*
  * This registers IOMMU devices of PHBs. This needs to happen
  * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1398,11 +1434,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
 	struct pci_controller *hose;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
-		iommu_device_sysfs_add(&hose->iommu, hose->parent,
-				       spapr_tce_iommu_groups, "iommu-phb%04x",
-				       hose->global_number);
-		iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
-				      hose->parent);
+		ppc_iommu_register_device(hose);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
index 938e66829eae..d5c48d1b0a31 100644
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
 	 * This allows interrupts to be unmasked without hard disabling, and
 	 * also without new hard interrupts coming in ahead of pending ones.
 	 */
-	asm_volatile_goto(
+	asm goto(
 "1:					\n"
 "		lbz	9,%0(13)	\n"
 "		cmpwi	9,0		\n"
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 7e793b503e29..8064d9c3de86 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
 		.name = "ibm,remove-pe-dma-window",
 	},
-	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = {
-		.name = "ibm,reset-pe-dma-windows",
+	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
+		/*
+		 * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
+		 * "ibm,reset-pe-dma-windows" (plural), but RTAS
+		 * implementations use the singular form in practice.
+		 */
+		.name = "ibm,reset-pe-dma-window",
 	},
 	[RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
 		.name = "ibm,scan-log-dump",
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 693334c20d07..a60e4139214b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -984,7 +984,7 @@ static bool shared_caches __ro_after_init;
 /* cpumask of CPUs with asymmetric SMT dependency */
 static int powerpc_smt_flags(void)
 {
-	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
 
 	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
 		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
@@ -1010,9 +1010,9 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack);
 static int powerpc_shared_cache_flags(void)
 {
 	if (static_branch_unlikely(&splpar_asym_pack))
-		return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING;
+		return SD_SHARE_LLC | SD_ASYM_PACKING;
 
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_SHARE_LLC;
 }
 
 static int powerpc_shared_proc_flags(void)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 82010629cf88..d8d6b4fd9a14 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,10 +27,22 @@
 #include <asm/ftrace.h>
 #include <asm/syscall.h>
 #include <asm/inst.h>
+#include <asm/sections.h>
 
 #define	NUM_FTRACE_TRAMPS	2
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+		addr += MCOUNT_INSN_SIZE;
+
+	return addr;
+}
+
 static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
 {
 	ppc_inst_t op;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 7b85c3b460a3..12fab1803bcf 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -37,6 +37,11 @@
 #define	NUM_FTRACE_TRAMPS	8
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
 static ppc_inst_t
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 1c5970df3233..f420df7888a7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -281,7 +281,9 @@ SECTIONS
 	 * to deal with references from __bug_table
 	 */
 	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		__exittext_begin = .;
 		EXIT_TEXT
+		__exittext_end = .;
 	}
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 52427fc2a33f..0b921704da45 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -391,6 +391,24 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 /* Dummy value used in computing PCR value below */
 #define PCR_ARCH_31    (PCR_ARCH_300 << 1)
 
+static inline unsigned long map_pcr_to_cap(unsigned long pcr)
+{
+	unsigned long cap = 0;
+
+	switch (pcr) {
+	case PCR_ARCH_300:
+		cap = H_GUEST_CAP_POWER9;
+		break;
+	case PCR_ARCH_31:
+		cap = H_GUEST_CAP_POWER10;
+		break;
+	default:
+		break;
+	}
+
+	return cap;
+}
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
 	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0;
@@ -424,11 +442,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 			break;
 		case PVR_ARCH_300:
 			guest_pcr_bit = PCR_ARCH_300;
-			cap = H_GUEST_CAP_POWER9;
 			break;
 		case PVR_ARCH_31:
 			guest_pcr_bit = PCR_ARCH_31;
-			cap = H_GUEST_CAP_POWER10;
 			break;
 		default:
 			return -EINVAL;
@@ -440,6 +456,12 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 		return -EINVAL;
 
 	if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) {
+		/*
+		 * 'arch_compat == 0' would mean the guest should default to
+		 * L1's compatibility. In this case, the guest would pick
+		 * host's PCR and evaluate the corresponding capabilities.
+		 */
+		cap = map_pcr_to_cap(guest_pcr_bit);
 		if (!(cap & nested_capabilities))
 			return -EINVAL;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index 5378eb40b162..8e6f5355f08b 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -138,6 +138,7 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 	vector128 v;
 	int rc, i;
 	u16 iden;
+	u32 arch_compat = 0;
 
 	vcpu = gsm->data;
 
@@ -347,8 +348,23 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 			break;
 		}
 		case KVMPPC_GSID_LOGICAL_PVR:
-			rc = kvmppc_gse_put_u32(gsb, iden,
-						vcpu->arch.vcore->arch_compat);
+			/*
+			 * Though 'arch_compat == 0' would mean the default
+			 * compatibility, arch_compat, being a Guest Wide
+			 * Element, cannot be filled with a value of 0 in GSB
+			 * as this would result into a kernel trap.
+			 * Hence, when `arch_compat == 0`, arch_compat should
+			 * default to L1's PVR.
+			 */
+			if (!vcpu->arch.vcore->arch_compat) {
+				if (cpu_has_feature(CPU_FTR_ARCH_31))
+					arch_compat = PVR_ARCH_31;
+				else if (cpu_has_feature(CPU_FTR_ARCH_300))
+					arch_compat = PVR_ARCH_300;
+			} else {
+				arch_compat = vcpu->arch.vcore->arch_compat;
+			}
+			rc = kvmppc_gse_put_u32(gsb, iden, arch_compat);
 			break;
 		}
 
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..aa9aa11927b2 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
 	if (ret)
 		return ret;
 
+	k_start = k_start & PAGE_MASK;
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 	if (!block)
 		return -ENOMEM;
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index e966b2ad8ecd..b3327a358eb4 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -27,7 +27,7 @@
 
 #include "mpc85xx.h"
 
-void __init mpc8536_ds_pic_init(void)
+static void __init mpc8536_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1b59e45a0c64..19122daadb55 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -21,7 +21,7 @@
 
 #include "mpc85xx.h"
 
-void __init mvme2500_pic_init(void)
+static void __init mvme2500_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0,
 		  MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 10d6f1fa3327..491895ac8bcf 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -24,7 +24,7 @@
 
 #include "mpc85xx.h"
 
-void __init p1010_rdb_pic_init(void)
+static void __init p1010_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0dd786a061a6..adc3a2ee1415 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -370,7 +370,7 @@ exit:
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022ds_set_pixel_clock(unsigned int pixclock)
+static void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022ds_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	switch (port) {
@@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_ds_pic_init(void)
+static void __init p1022_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 25ab6e9c1470..6198299d95b1 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -40,7 +40,7 @@
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022rdk_set_pixel_clock(unsigned int pixclock)
+static void p1022rdk_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022rdk_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	return FSL_DIU_PORT_DVI;
@@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_rdk_pic_init(void)
+static void __init p1022_rdk_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index baa12eff6d5d..60e0b8947ce6 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -8,6 +8,8 @@
 #include <linux/of_irq.h>
 #include <linux/io.h>
 
+#include "socrates_fpga_pic.h"
+
 /*
  * The FPGA supports 9 interrupt sources, which can be routed to 3
  * interrupt request lines of the MPIC. The line to be used can be
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 45f257fc1ade..2582427d8d01 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -37,7 +37,7 @@
 #define MPC85xx_L2CTL_L2I		0x40000000 /* L2 flash invalidate */
 #define MPC85xx_L2CTL_L2SIZ_MASK	0x30000000 /* L2 SRAM size (R/O) */
 
-void __init xes_mpc85xx_pic_init(void)
+static void __init xes_mpc85xx_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 496e16c588aa..e8c4129697b1 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb,
 
 struct iommu_table_ops iommu_table_lpar_multi_ops;
 
-/*
- * iommu_table_setparms_lpar
- *
- * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
- */
-static void iommu_table_setparms_lpar(struct pci_controller *phb,
-				      struct device_node *dn,
-				      struct iommu_table *tbl,
-				      struct iommu_table_group *table_group,
-				      const __be32 *dma_window)
-{
-	unsigned long offset, size, liobn;
-
-	of_parse_dma_window(dn, dma_window, &liobn, &offset, &size);
-
-	iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL,
-				    &iommu_table_lpar_multi_ops);
-
-
-	table_group->tce32_start = offset;
-	table_group->tce32_size = size;
-}
-
 struct iommu_table_ops iommu_table_pseries_ops = {
 	.set = tce_build_pSeries,
 	.clear = tce_free_pSeries,
@@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = {
  * dynamic 64bit DMA window, walking up the device tree.
  */
 static struct device_node *pci_dma_find(struct device_node *dn,
-					const __be32 **dma_window)
+					struct dynamic_dma_window_prop *prop)
 {
-	const __be32 *dw = NULL;
+	const __be32 *default_prop = NULL;
+	const __be32 *ddw_prop = NULL;
+	struct device_node *rdn = NULL;
+	bool default_win = false, ddw_win = false;
 
 	for ( ; dn && PCI_DN(dn); dn = dn->parent) {
-		dw = of_get_property(dn, "ibm,dma-window", NULL);
-		if (dw) {
-			if (dma_window)
-				*dma_window = dw;
-			return dn;
+		default_prop = of_get_property(dn, "ibm,dma-window", NULL);
+		if (default_prop) {
+			rdn = dn;
+			default_win = true;
+		}
+		ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
+		}
+		ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
 		}
-		dw = of_get_property(dn, DIRECT64_PROPNAME, NULL);
-		if (dw)
-			return dn;
-		dw = of_get_property(dn, DMA64_PROPNAME, NULL);
-		if (dw)
-			return dn;
+
+		/* At least found default window, which is the case for normal boot */
+		if (default_win)
+			break;
 	}
 
-	return NULL;
+	/* For PCI devices there will always be a DMA window, either on the device
+	 * or parent bus
+	 */
+	WARN_ON(!(default_win | ddw_win));
+
+	/* caller doesn't want to get DMA window property */
+	if (!prop)
+		return rdn;
+
+	/* parse DMA window property. During normal system boot, only default
+	 * DMA window is passed in OF. But, for kdump, a dedicated adapter might
+	 * have both default and DDW in FDT. In this scenario, DDW takes precedence
+	 * over default window.
+	 */
+	if (ddw_win) {
+		struct dynamic_dma_window_prop *p;
+
+		p = (struct dynamic_dma_window_prop *)ddw_prop;
+		prop->liobn = p->liobn;
+		prop->dma_base = p->dma_base;
+		prop->tce_shift = p->tce_shift;
+		prop->window_shift = p->window_shift;
+	} else if (default_win) {
+		unsigned long offset, size, liobn;
+
+		of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size);
+
+		prop->liobn = cpu_to_be32((u32)liobn);
+		prop->dma_base = cpu_to_be64(offset);
+		prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K);
+		prop->window_shift = cpu_to_be32(order_base_2(size));
+	}
+
+	return rdn;
 }
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
@@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const __be32 *dma_window = NULL;
+	struct dynamic_dma_window_prop prop;
 
 	dn = pci_bus_to_OF_node(bus);
 
 	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
 		 dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 
-	if (dma_window == NULL)
-		pr_debug("  no ibm,dma-window property !\n");
+	/* In PPC architecture, there will always be DMA window on bus or one of the
+	 * parent bus. During reboot, there will be ibm,dma-window property to
+	 * define DMA window. For kdump, there will at least be default window or DDW
+	 * or both.
+	 */
 
 	ppci = PCI_DN(pdn);
 
@@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->table_group) {
 		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
 		tbl = ppci->table_group->tables[0];
-		if (dma_window) {
-			iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
-						  ppci->table_group, dma_window);
 
-			if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
-				panic("Failed to initialize iommu table");
-		}
+		iommu_table_setparms_common(tbl, ppci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name)
 			continue;
 		}
 
+		/* If at the time of system initialization, there are DDWs in OF,
+		 * it means this is during kexec. DDW could be direct or dynamic.
+		 * We will just mark DDWs as "dynamic" since this is kdump path,
+		 * no need to worry about perforance. ddw_list_new_entry() will
+		 * set window->direct = false.
+		 */
 		window = ddw_list_new_entry(pdn, dma64);
 		if (!window) {
 			of_node_put(pdn);
@@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
+	struct dynamic_dma_window_prop prop;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
 
@@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %pOF\n", dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 	if (!pdn || !PCI_DN(pdn)) {
 		printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
 		       "no DMA window found for pci dev=%s dn=%pOF\n",
@@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	if (!pci->table_group) {
 		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
 		tbl = pci->table_group->tables[0];
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
-				pci->table_group, dma_window);
+
+		iommu_table_setparms_common(tbl, pci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		pci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
 
 		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4561667832ed..4e9916bb03d7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);
 
-	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
-		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+	/*
+	 * VPA steal time counters are reported at TB frequency. Hence do a
+	 * conversion to ns before returning
+	 */
+	return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+			be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
 }
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4ba824568119..4448386268d9 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 
 	pseries_msi_allocate_domains(phb);
 
+	ppc_iommu_register_device(phb);
+
 	/* Create EEH devices for the PHB */
 	eeh_phb_pe_create(phb);
 
@@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
+	ppc_iommu_unregister_device(phb);
+
 	pseries_msi_free_domains(phb);
 
 	/* Keep a reference so phb isn't freed yet */
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 5020044400dc..4de57ba52236 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -41,7 +41,7 @@ struct memcons memcons = {
 	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
 };
 
-void memcons_putc(char c)
+static void memcons_putc(char c)
 {
 	char *new_output_pos;
 
@@ -54,7 +54,7 @@ void memcons_putc(char c)
 	memcons.output_pos = new_output_pos;
 }
 
-int memcons_getc_poll(void)
+static int memcons_getc_poll(void)
 {
 	char c;
 	char *new_input_pos;
@@ -77,7 +77,7 @@ int memcons_getc_poll(void)
 	return -1;
 }
 
-int memcons_getc(void)
+static int memcons_getc(void)
 {
 	int c;
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index bffbd869a068..d2c257a0da2a 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -136,6 +136,7 @@ config RISCV
 	select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD
 	select HAVE_MOVE_PMD
 	select HAVE_MOVE_PUD
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -315,7 +316,6 @@ config AS_HAS_OPTION_ARCH
 	# https://reviews.llvm.org/D123515
 	def_bool y
 	depends on $(as-instr, .option arch$(comma) +m)
-	depends on !$(as-instr, .option arch$(comma) -i)
 
 source "arch/riscv/Kconfig.socs"
 source "arch/riscv/Kconfig.errata"
@@ -983,7 +983,19 @@ config RISCV_ISA_FALLBACK
 config BUILTIN_DTB
 	bool "Built-in device tree"
 	depends on OF && NONPORTABLE
-	default y if XIP_KERNEL
+	help
+	  Build a device tree into the Linux image.
+	  This option should be selected if no bootloader is being used.
+	  If unsure, say N.
+
+
+config BUILTIN_DTB_SOURCE
+	string "Built-in device tree source"
+	depends on BUILTIN_DTB
+	help
+	  DTS file path (without suffix, relative to arch/riscv/boot/dts)
+	  for the DTS file that will be used to produce the DTB linked into the
+	  kernel.
 
 endmenu # "Boot options"
 
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index e08e91c49abe..623de5f8a208 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -84,36 +84,4 @@ config SOC_CANAAN
 	help
 	  This enables support for Canaan Kendryte K210 SoC platform hardware.
 
-if ARCH_CANAAN
-
-config ARCH_CANAAN_K210_DTB_BUILTIN
-	def_bool SOC_CANAAN_K210_DTB_BUILTIN
-
-config SOC_CANAAN_K210_DTB_BUILTIN
-	bool "Builtin device tree for the Canaan Kendryte K210"
-	depends on ARCH_CANAAN
-	default y
-	select OF
-	select BUILTIN_DTB
-	help
-	  Build a device tree for the Kendryte K210 into the Linux image.
-	  This option should be selected if no bootloader is being used.
-	  If unsure, say Y.
-
-config ARCH_CANAAN_K210_DTB_SOURCE
-	string
-	default SOC_CANAAN_K210_DTB_SOURCE
-
-config SOC_CANAAN_K210_DTB_SOURCE
-	string "Source file for the Canaan Kendryte K210 builtin DTB"
-	depends on ARCH_CANAAN
-	depends on ARCH_CANAAN_K210_DTB_BUILTIN
-	default "k210_generic"
-	help
-	  Base name (without suffix, relative to arch/riscv/boot/dts/canaan)
-	  for the DTS file that will be used to produce the DTB linked into the
-	  kernel.
-
-endif # ARCH_CANAAN
-
 endmenu # "SoC selection"
diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile
index 72030fd727af..fdae05bbf556 100644
--- a/arch/riscv/boot/dts/Makefile
+++ b/arch/riscv/boot/dts/Makefile
@@ -8,4 +8,4 @@ subdir-y += sophgo
 subdir-y += starfive
 subdir-y += thead
 
-obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix /, $(subdir-y))
+obj-$(CONFIG_BUILTIN_DTB) := $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
diff --git a/arch/riscv/boot/dts/canaan/Makefile b/arch/riscv/boot/dts/canaan/Makefile
index 520623264c87..987d1f0c41f0 100644
--- a/arch/riscv/boot/dts/canaan/Makefile
+++ b/arch/riscv/boot/dts/canaan/Makefile
@@ -5,5 +5,3 @@ dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_bit.dtb
 dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_dock.dtb
 dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_go.dtb
 dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maixduino.dtb
-
-obj-$(CONFIG_ARCH_CANAAN_K210_DTB_BUILTIN) += $(addsuffix .dtb.o, $(CONFIG_ARCH_CANAAN_K210_DTB_SOURCE))
diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile
index 45adc4926e79..e177815bf1a2 100644
--- a/arch/riscv/boot/dts/microchip/Makefile
+++ b/arch/riscv/boot/dts/microchip/Makefile
@@ -4,4 +4,3 @@ dtb-$(CONFIG_ARCH_MICROCHIP_POLARFIRE) += mpfs-m100pfsevp.dtb
 dtb-$(CONFIG_ARCH_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb
 dtb-$(CONFIG_ARCH_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb
 dtb-$(CONFIG_ARCH_MICROCHIP_POLARFIRE) += mpfs-tysom-m.dtb
-obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y))
diff --git a/arch/riscv/boot/dts/sifive/Makefile b/arch/riscv/boot/dts/sifive/Makefile
index 6a5fbd4ed96a..495bf760a909 100644
--- a/arch/riscv/boot/dts/sifive/Makefile
+++ b/arch/riscv/boot/dts/sifive/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_ARCH_SIFIVE) += hifive-unleashed-a00.dtb \
 			     hifive-unmatched-a00.dtb
-obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y))
diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
index 07387f9c135c..72b87b08ab44 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
@@ -123,6 +123,7 @@
 		interrupt-parent = <&gpio>;
 		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
+		#interrupt-cells = <2>;
 
 		onkey {
 			compatible = "dlg,da9063-onkey";
diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
index ead1cc35d88b..81fda312f988 100644
--- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi
+++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi
@@ -6,6 +6,8 @@
 /dts-v1/;
 #include <dt-bindings/interrupt-controller/irq.h>
 
+#include <dt-bindings/reset/sophgo,sg2042-reset.h>
+
 #include "sg2042-cpus.dtsi"
 
 / {
@@ -327,6 +329,12 @@
 			riscv,ndev = <224>;
 		};
 
+		rstgen: reset-controller@7030013000 {
+			compatible = "sophgo,sg2042-reset";
+			reg = <0x00000070 0x30013000 0x00000000 0x0000000c>;
+			#reset-cells = <1>;
+		};
+
 		uart0: serial@7040000000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x00000070 0x40000000 0x00000000 0x00001000>;
@@ -335,6 +343,7 @@
 			clock-frequency = <500000000>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
+			resets = <&rstgen RST_UART0>;
 			status = "disabled";
 		};
 	};
diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi
index c216aaecac53..5d499d8aa804 100644
--- a/arch/riscv/boot/dts/starfive/jh7100.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi
@@ -96,14 +96,14 @@
 			thermal-sensors = <&sfctemp>;
 
 			trips {
-				cpu_alert0 {
+				cpu-alert0 {
 					/* milliCelsius */
 					temperature = <75000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				cpu_crit {
+				cpu-crit {
 					/* milliCelsius */
 					temperature = <90000>;
 					hysteresis = <2000>;
@@ -113,30 +113,34 @@
 		};
 	};
 
-	osc_sys: osc_sys {
+	osc_sys: osc-sys {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
+		clock-output-names = "osc_sys";
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
 	};
 
-	osc_aud: osc_aud {
+	osc_aud: osc-aud {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
+		clock-output-names = "osc_aud";
 		/* This value must be overridden by the board */
 		clock-frequency = <0>;
 	};
 
-	gmac_rmii_ref: gmac_rmii_ref {
+	gmac_rmii_ref: gmac-rmii-ref {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
+		clock-output-names = "gmac_rmii_ref";
 		/* Should be overridden by the board when needed */
 		clock-frequency = <0>;
 	};
 
-	gmac_gr_mii_rxclk: gmac_gr_mii_rxclk {
+	gmac_gr_mii_rxclk: gmac-gr-mii-rxclk {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
+		clock-output-names = "gmac_gr_mii_rxclk";
 		/* Should be overridden by the board when needed */
 		clock-frequency = <0>;
 	};
diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi
index 45213cdf50dc..74ed3b9264d8 100644
--- a/arch/riscv/boot/dts/starfive/jh7110.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi
@@ -237,14 +237,14 @@
 			};
 
 			trips {
-				cpu_alert0: cpu_alert0 {
+				cpu_alert0: cpu-alert0 {
 					/* milliCelsius */
 					temperature = <85000>;
 					hysteresis = <2000>;
 					type = "passive";
 				};
 
-				cpu_crit {
+				cpu-crit {
 					/* milliCelsius */
 					temperature = <100000>;
 					hysteresis = <2000>;
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
index 146c46d0525b..7e75200543f4 100644
--- a/arch/riscv/configs/nommu_k210_defconfig
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -33,6 +33,8 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0"
 CONFIG_CMDLINE_FORCE=y
+CONFIG_BUILTIN_DTB=y
+CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic"
 # CONFIG_SECCOMP is not set
 # CONFIG_STACKPROTECTOR is not set
 # CONFIG_GCC_PLUGINS is not set
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
index 95d8d1808f19..0ba353e9ca71 100644
--- a/arch/riscv/configs/nommu_k210_sdcard_defconfig
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -25,6 +25,8 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro"
 CONFIG_CMDLINE_FORCE=y
+CONFIG_BUILTIN_DTB=y
+CONFIG_BUILTIN_DTB_SOURCE="canaan/k210_generic"
 # CONFIG_SECCOMP is not set
 # CONFIG_STACKPROTECTOR is not set
 # CONFIG_GCC_PLUGINS is not set
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index c20236a0725b..85b2c443823e 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -20,7 +20,7 @@
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 #ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -51,7 +51,7 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
 # ifdef CONFIG_RISCV_ISA_ZBB
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 9ffc35537024..329d8244a9b3 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
 {
 	int num;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
@@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x)
 	if (!x)
 		return 0;
 
-	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+	asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
 				      RISCV_ISA_EXT_ZBB, 1)
 			  : : : : legacy);
 
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index a5b60b54b101..88e6f1499e88 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -53,7 +53,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	    IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
 		unsigned long fold_temp;
 
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 		    :
 		    :
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 5a626ed2c47a..0bd11862b760 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -80,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -103,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");
 
 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 510014051f5d..2468c55933cd 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -424,6 +424,7 @@
 # define CSR_STATUS	CSR_MSTATUS
 # define CSR_IE		CSR_MIE
 # define CSR_TVEC	CSR_MTVEC
+# define CSR_ENVCFG	CSR_MENVCFG
 # define CSR_SCRATCH	CSR_MSCRATCH
 # define CSR_EPC	CSR_MEPC
 # define CSR_CAUSE	CSR_MCAUSE
@@ -448,6 +449,7 @@
 # define CSR_STATUS	CSR_SSTATUS
 # define CSR_IE		CSR_SIE
 # define CSR_TVEC	CSR_STVEC
+# define CSR_ENVCFG	CSR_SENVCFG
 # define CSR_SCRATCH	CSR_SSCRATCH
 # define CSR_EPC	CSR_SEPC
 # define CSR_CAUSE	CSR_SCAUSE
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 329172122952..15055f9df4da 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -25,6 +25,11 @@
 
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #ifndef __ASSEMBLY__
+
+extern void *return_address(unsigned int level);
+
+#define ftrace_return_address(n) return_address(n)
+
 void MCOUNT_NAME(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 4c5b0e929890..22deb7a2a6ec 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -11,6 +11,11 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 }
 #define arch_clear_hugepage_flags arch_clear_hugepage_flags
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+#endif
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 5340f818746b..1f2d2599c655 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -81,6 +81,8 @@
 #define RISCV_ISA_EXT_ZTSO		72
 #define RISCV_ISA_EXT_ZACAS		73
 
+#define RISCV_ISA_EXT_XLINUXENVCFG	127
+
 #define RISCV_ISA_EXT_MAX		128
 #define RISCV_ISA_EXT_INVALID		U32_MAX
 
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0..4a35d787c019 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
@@ -39,7 +39,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 57e887bfa34c..2947423b5082 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -12,7 +12,7 @@
 #include <linux/pfn.h>
 #include <linux/const.h>
 
-#define PAGE_SHIFT	(12)
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE - 1))
 
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index d169a4f41a2e..c80bb9990d32 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -95,7 +95,13 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 		__pud_free(mm, pud);
 }
 
-#define __pud_free_tlb(tlb, pud, addr)  pud_free((tlb)->mm, pud)
+#define __pud_free_tlb(tlb, pud, addr)					\
+do {									\
+	if (pgtable_l4_enabled) {					\
+		pagetable_pud_dtor(virt_to_ptdesc(pud));		\
+		tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud));	\
+	}								\
+} while (0)
 
 #define p4d_alloc_one p4d_alloc_one
 static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -124,7 +130,11 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 		__p4d_free(mm, p4d);
 }
 
-#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
+#define __p4d_free_tlb(tlb, p4d, addr)					\
+do {									\
+	if (pgtable_l5_enabled)						\
+		tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d));	\
+} while (0)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 static inline void sync_kernel_mappings(pgd_t *pgd)
@@ -149,7 +159,11 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
-#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+#define __pmd_free_tlb(tlb, pmd, addr)				\
+do {								\
+	pagetable_pmd_dtor(virt_to_ptdesc(pmd));		\
+	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd));	\
+} while (0)
 
 #endif /* __PAGETABLE_PMD_FOLDED */
 
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index b42017d76924..b99bd66107a6 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -136,7 +136,7 @@ enum napot_cont_order {
  * 10010 - IO   Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable
  */
 #define _PAGE_PMA_THEAD		((1UL << 62) | (1UL << 61) | (1UL << 60))
-#define _PAGE_NOCACHE_THEAD	((1UL < 61) | (1UL << 60))
+#define _PAGE_NOCACHE_THEAD	((1UL << 61) | (1UL << 60))
 #define _PAGE_IO_THEAD		((1UL << 63) | (1UL << 60))
 #define _PAGE_MTMASK_THEAD	(_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 0c94260b5d0c..6066822e7396 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -84,7 +84,7 @@
  * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
  * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
  */
-#define vmemmap		((struct page *)VMEMMAP_START)
+#define vmemmap		((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT))
 
 #define PCI_IO_SIZE      SZ_16M
 #define PCI_IO_END       VMEMMAP_START
@@ -439,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+#define pte_leaf_size(pte)	(pte_napot(pte) ?				\
+					napot_cont_size(napot_cont_order(pte)) :\
+					PAGE_SIZE)
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/asm-generic/pgtable.h
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index f7e8ef2418b9..b1495a7e06ce 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -21,4 +21,9 @@ static inline bool on_thread_stack(void)
 	return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
 }
 
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
 #endif /* _ASM_RISCV_STACKTRACE_H */
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 02f87867389a..491296a335d0 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -14,6 +14,7 @@ struct suspend_context {
 	struct pt_regs regs;
 	/* Saved and restored by high-level functions */
 	unsigned long scratch;
+	unsigned long envcfg;
 	unsigned long tvec;
 	unsigned long ie;
 #ifdef CONFIG_MMU
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1eb5682b2af6..50b63b5c15bd 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 #ifdef CONFIG_MMU
-	if (tlb->fullmm || tlb->need_flush_all)
+	if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
 		flush_tlb_mm(tlb->mm);
 	else
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 928f096dca21..4112cc8d1d69 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -75,6 +75,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h
index 924d01b56c9a..51f6dfe19745 100644
--- a/arch/riscv/include/asm/vmalloc.h
+++ b/arch/riscv/include/asm/vmalloc.h
@@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot)
 	return true;
 }
 
-#ifdef CONFIG_RISCV_ISA_SVNAPOT
-#include <linux/pgtable.h>
+#endif
 
-#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size
-static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end,
-							 u64 pfn, unsigned int max_page_shift)
-{
-	unsigned long map_size = PAGE_SIZE;
-	unsigned long size, order;
-
-	if (!has_svnapot())
-		return map_size;
-
-	for_each_napot_order_rev(order) {
-		if (napot_cont_shift(order) > max_page_shift)
-			continue;
-
-		size = napot_cont_size(order);
-		if (end - addr < size)
-			continue;
-
-		if (!IS_ALIGNED(addr, size))
-			continue;
-
-		if (!IS_ALIGNED(PFN_PHYS(pfn), size))
-			continue;
-
-		map_size = size;
-		break;
-	}
-
-	return map_size;
-}
-
-#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift
-static inline int arch_vmap_pte_supported_shift(unsigned long size)
-{
-	int shift = PAGE_SHIFT;
-	unsigned long order;
-
-	if (!has_svnapot())
-		return shift;
-
-	WARN_ON_ONCE(size >= PMD_SIZE);
-
-	for_each_napot_order_rev(order) {
-		if (napot_cont_size(order) > size)
-			continue;
-
-		if (!IS_ALIGNED(size, napot_cont_size(order)))
-			continue;
-
-		shift = napot_cont_shift(order);
-		break;
-	}
-
-	return shift;
-}
-
-#endif /* CONFIG_RISCV_ISA_SVNAPOT */
-#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
 #endif /* _ASM_RISCV_VMALLOC_H */
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index d6b7a5b95874..7499e88a947c 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -139,6 +139,33 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZIHPM,
 	KVM_RISCV_ISA_EXT_SMSTATEEN,
 	KVM_RISCV_ISA_EXT_ZICOND,
+	KVM_RISCV_ISA_EXT_ZBC,
+	KVM_RISCV_ISA_EXT_ZBKB,
+	KVM_RISCV_ISA_EXT_ZBKC,
+	KVM_RISCV_ISA_EXT_ZBKX,
+	KVM_RISCV_ISA_EXT_ZKND,
+	KVM_RISCV_ISA_EXT_ZKNE,
+	KVM_RISCV_ISA_EXT_ZKNH,
+	KVM_RISCV_ISA_EXT_ZKR,
+	KVM_RISCV_ISA_EXT_ZKSED,
+	KVM_RISCV_ISA_EXT_ZKSH,
+	KVM_RISCV_ISA_EXT_ZKT,
+	KVM_RISCV_ISA_EXT_ZVBB,
+	KVM_RISCV_ISA_EXT_ZVBC,
+	KVM_RISCV_ISA_EXT_ZVKB,
+	KVM_RISCV_ISA_EXT_ZVKG,
+	KVM_RISCV_ISA_EXT_ZVKNED,
+	KVM_RISCV_ISA_EXT_ZVKNHA,
+	KVM_RISCV_ISA_EXT_ZVKNHB,
+	KVM_RISCV_ISA_EXT_ZVKSED,
+	KVM_RISCV_ISA_EXT_ZVKSH,
+	KVM_RISCV_ISA_EXT_ZVKT,
+	KVM_RISCV_ISA_EXT_ZFH,
+	KVM_RISCV_ISA_EXT_ZFHMIN,
+	KVM_RISCV_ISA_EXT_ZIHINTNTL,
+	KVM_RISCV_ISA_EXT_ZVFH,
+	KVM_RISCV_ISA_EXT_ZVFHMIN,
+	KVM_RISCV_ISA_EXT_ZFA,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f71910718053..604d6bf7e476 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE
 CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
@@ -46,6 +47,7 @@ obj-y	+= irq.o
 obj-y	+= process.o
 obj-y	+= ptrace.o
 obj-y	+= reset.o
+obj-y	+= return_address.o
 obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 89920f84d0a3..79a5a35fab96 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -24,6 +24,7 @@
 #include <asm/hwprobe.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
+#include <asm/sbi.h>
 #include <asm/vector.h>
 
 #include "copy-unaligned.h"
@@ -202,6 +203,16 @@ static const unsigned int riscv_zvbb_exts[] = {
 };
 
 /*
+ * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V
+ * privileged ISA, the existence of the CSRs is implied by any extension which
+ * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the
+ * existence of the CSR, and treat it as a subset of those other extensions.
+ */
+static const unsigned int riscv_xlinuxenvcfg_exts[] = {
+	RISCV_ISA_EXT_XLINUXENVCFG
+};
+
+/*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
  *
@@ -250,8 +261,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
 	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
-	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+	__RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts),
+	__RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
@@ -539,6 +550,20 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
 		}
 
 		/*
+		 * "V" in ISA strings is ambiguous in practice: it should mean
+		 * just the standard V-1.0 but vendors aren't well behaved.
+		 * Many vendors with T-Head CPU cores which implement the 0.7.1
+		 * version of the vector specification put "v" into their DTs.
+		 * CPU cores with the ratified spec will contain non-zero
+		 * marchid.
+		 */
+		if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID &&
+		    riscv_cached_marchid(cpu) == 0x0) {
+			this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v];
+			clear_bit(RISCV_ISA_EXT_v, isainfo->isa);
+		}
+
+		/*
 		 * All "okay" hart should have same isa. Set HWCAP based on
 		 * common capabilities of every "okay" hart, in case they don't
 		 * have.
@@ -950,7 +975,7 @@ arch_initcall(check_unaligned_access_all_cpus);
 void riscv_user_isa_enable(void)
 {
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
-		csr_set(CSR_SENVCFG, ENVCFG_CBZE);
+		csr_set(CSR_ENVCFG, ENVCFG_CBZE);
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 8e114f5930ce..0d6225fd3194 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -41,7 +41,7 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
+static DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
 
 static bool __init has_pv_steal_clock(void)
 {
@@ -91,8 +91,8 @@ static int pv_time_cpu_down_prepare(unsigned int cpu)
 static u64 pv_time_steal_clock(int cpu)
 {
 	struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu);
-	u32 sequence;
-	u64 steal;
+	__le32 sequence;
+	__le64 steal;
 
 	/*
 	 * Check the sequence field before and after reading the steal
diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c
new file mode 100644
index 000000000000..c8115ec8fb30
--- /dev/null
+++ b/arch/riscv/kernel/return_address.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This code come from arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2023 SiFive.
+ */
+
+#include <linux/export.h>
+#include <linux/kprobes.h>
+#include <linux/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static bool save_return_addr(void *d, unsigned long pc)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)pc;
+		return false;
+	}
+
+	--data->level;
+
+	return true;
+}
+NOKPROBE_SYMBOL(save_return_addr);
+
+noinline void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+
+	data.level = level + 3;
+	data.addr = NULL;
+
+	arch_stack_walk(save_return_addr, &data, current, NULL);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+
+}
+EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 519b6bd946e5..c4ed7d977f57 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -42,10 +42,6 @@
 
 static DECLARE_COMPLETION(cpu_running);
 
-void __init smp_prepare_boot_cpu(void)
-{
-}
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 239509367e42..299795341e8a 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -15,6 +15,8 @@
 void suspend_save_csrs(struct suspend_context *context)
 {
 	context->scratch = csr_read(CSR_SCRATCH);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
 	context->ie = csr_read(CSR_IE);
 
@@ -36,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context)
 void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, context->scratch);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
 	csr_write(CSR_IE, context->ie);
 
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 2cf76218a5bd..98315b98256d 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -30,14 +30,8 @@ enum rv_vdso_map {
 
 #define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
 
-/*
- * The vDSO data page.
- */
-static union {
-	struct vdso_data	data;
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
 struct __vdso_info {
 	const char *name;
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index fc34557f5356..5f7355e96008 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -42,15 +42,42 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVPBMT),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
+	KVM_ISA_EXT_ARR(ZBC),
+	KVM_ISA_EXT_ARR(ZBKB),
+	KVM_ISA_EXT_ARR(ZBKC),
+	KVM_ISA_EXT_ARR(ZBKX),
 	KVM_ISA_EXT_ARR(ZBS),
+	KVM_ISA_EXT_ARR(ZFA),
+	KVM_ISA_EXT_ARR(ZFH),
+	KVM_ISA_EXT_ARR(ZFHMIN),
 	KVM_ISA_EXT_ARR(ZICBOM),
 	KVM_ISA_EXT_ARR(ZICBOZ),
 	KVM_ISA_EXT_ARR(ZICNTR),
 	KVM_ISA_EXT_ARR(ZICOND),
 	KVM_ISA_EXT_ARR(ZICSR),
 	KVM_ISA_EXT_ARR(ZIFENCEI),
+	KVM_ISA_EXT_ARR(ZIHINTNTL),
 	KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 	KVM_ISA_EXT_ARR(ZIHPM),
+	KVM_ISA_EXT_ARR(ZKND),
+	KVM_ISA_EXT_ARR(ZKNE),
+	KVM_ISA_EXT_ARR(ZKNH),
+	KVM_ISA_EXT_ARR(ZKR),
+	KVM_ISA_EXT_ARR(ZKSED),
+	KVM_ISA_EXT_ARR(ZKSH),
+	KVM_ISA_EXT_ARR(ZKT),
+	KVM_ISA_EXT_ARR(ZVBB),
+	KVM_ISA_EXT_ARR(ZVBC),
+	KVM_ISA_EXT_ARR(ZVFH),
+	KVM_ISA_EXT_ARR(ZVFHMIN),
+	KVM_ISA_EXT_ARR(ZVKB),
+	KVM_ISA_EXT_ARR(ZVKG),
+	KVM_ISA_EXT_ARR(ZVKNED),
+	KVM_ISA_EXT_ARR(ZVKNHA),
+	KVM_ISA_EXT_ARR(ZVKNHB),
+	KVM_ISA_EXT_ARR(ZVKSED),
+	KVM_ISA_EXT_ARR(ZVKSH),
+	KVM_ISA_EXT_ARR(ZVKT),
 };
 
 static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -92,13 +119,40 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_RISCV_ISA_EXT_ZFA:
+	case KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_RISCV_ISA_EXT_ZIHINTNTL:
 	case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_RISCV_ISA_EXT_ZVFHMIN:
+	case KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_RISCV_ISA_EXT_ZVKT:
 		return false;
 	/* Extensions which can be disabled using Smstateen */
 	case KVM_RISCV_ISA_EXT_SSAIA:
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index 01f09fe8c3b0..d8cf9ca28c61 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -26,8 +26,12 @@ void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
 {
 	gpa_t shmem = vcpu->arch.sta.shmem;
 	u64 last_steal = vcpu->arch.sta.last_steal;
-	u32 *sequence_ptr, sequence;
-	u64 *steal_ptr, steal;
+	__le32 __user *sequence_ptr;
+	__le64 __user *steal_ptr;
+	__le32 sequence_le;
+	__le64 steal_le;
+	u32 sequence;
+	u64 steal;
 	unsigned long hva;
 	gfn_t gfn;
 
@@ -47,22 +51,22 @@ void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
 		return;
 	}
 
-	sequence_ptr = (u32 *)(hva + offset_in_page(shmem) +
+	sequence_ptr = (__le32 __user *)(hva + offset_in_page(shmem) +
 			       offsetof(struct sbi_sta_struct, sequence));
-	steal_ptr = (u64 *)(hva + offset_in_page(shmem) +
+	steal_ptr = (__le64 __user *)(hva + offset_in_page(shmem) +
 			    offsetof(struct sbi_sta_struct, steal));
 
-	if (WARN_ON(get_user(sequence, sequence_ptr)))
+	if (WARN_ON(get_user(sequence_le, sequence_ptr)))
 		return;
 
-	sequence = le32_to_cpu(sequence);
+	sequence = le32_to_cpu(sequence_le);
 	sequence += 1;
 
 	if (WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr)))
 		return;
 
-	if (!WARN_ON(get_user(steal, steal_ptr))) {
-		steal = le64_to_cpu(steal);
+	if (!WARN_ON(get_user(steal_le, steal_ptr))) {
+		steal = le64_to_cpu(steal_le);
 		vcpu->arch.sta.last_steal = READ_ONCE(current->sched_info.run_delay);
 		steal += vcpu->arch.sta.last_steal - last_steal;
 		WARN_ON(put_user(cpu_to_le64(steal), steal_ptr));
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index af3df5274ccb..74af3ab520b6 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -53,7 +53,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -170,7 +170,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
@@ -178,7 +178,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 				  : no_zbb);
 
 #ifdef CONFIG_32BIT
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 16	\n\
 			andi	%[offset], %[offset], 1		\n\
@@ -193,7 +193,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
 
 		return (unsigned short)csum;
 #else /* !CONFIG_32BIT */
-		asm_volatile_goto(".option push			\n\
+		asm_goto_output(".option push			\n\
 		.option arch,+zbb				\n\
 			rori	%[fold_temp], %[csum], 32	\n\
 			add	%[csum], %[fold_temp], %[csum]	\n\
@@ -257,7 +257,7 @@ do_csum_no_alignment(const unsigned char *buff, int len)
 		 * support, so nop when Zbb is available and jump when Zbb is
 		 * not available.
 		 */
-		asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+		asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
 					      RISCV_ISA_EXT_ZBB, 1)
 				  :
 				  :
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 431596c0e20e..5ef2a6891158 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	return pte;
 }
 
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		return P4D_SIZE - PUD_SIZE;
+#endif
+	case PMD_SIZE:
+		return PUD_SIZE - PMD_SIZE;
+	case napot_cont_size(NAPOT_CONT64KB_ORDER):
+		return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+	default:
+		break;
+	}
+
+	return 0UL;
+}
+
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
@@ -177,13 +197,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 	return entry;
 }
 
+static void clear_flush(struct mm_struct *mm,
+			unsigned long addr,
+			pte_t *ptep,
+			unsigned long pgsize,
+			unsigned long ncontig)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		ptep_get_and_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
 void set_huge_pte_at(struct mm_struct *mm,
 		     unsigned long addr,
 		     pte_t *ptep,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift;
+	unsigned long hugepage_shift, pgsize;
 	int i, pte_num;
 
 	if (sz >= PGDIR_SIZE)
@@ -198,7 +241,22 @@ void set_huge_pte_at(struct mm_struct *mm,
 		hugepage_shift = PAGE_SHIFT;
 
 	pte_num = sz >> hugepage_shift;
-	for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
+	pgsize = 1 << hugepage_shift;
+
+	if (!pte_present(pte)) {
+		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+			set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	if (!pte_napot(pte)) {
+		set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+	for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
 		set_pte_at(mm, addr, ptep, pte);
 }
 
@@ -306,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		pte_clear(mm, addr, ptep);
 }
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	unsigned long order;
 
@@ -334,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init);
 
 #else
 
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
 {
 	return false;
 }
@@ -351,7 +409,7 @@ int pmd_huge(pmd_t pmd)
 	return pmd_leaf(pmd);
 }
 
-bool __init arch_hugetlb_valid_size(unsigned long size)
+static bool __hugetlb_valid_size(unsigned long size)
 {
 	if (size == HPAGE_SIZE)
 		return true;
@@ -363,6 +421,18 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 		return false;
 }
 
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	return __hugetlb_valid_size(size);
+}
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	return __hugetlb_valid_size(huge_page_size(h));
+}
+#endif
+
 #ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 32cad6a65ccd..fa34cf55037b 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1385,6 +1385,10 @@ void __init misc_mem_init(void)
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 	arch_numa_init();
 	sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* The entire VMEMMAP region has been populated. Flush TLB for this region */
+	local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
 	zone_sizes_init();
 	arch_reserve_crashkernel();
 	memblock_dump_all();
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8d12b26f5ac3..893566e004b7 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,9 +66,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+/* Flush a range of kernel pages without broadcasting */
 void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 static void __ipi_flush_tlb_all(void *info)
@@ -233,4 +234,5 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
 	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
 			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	cpumask_clear(&batch->cpumask);
 }
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index fe565f3a3a91..36e14e7c8f87 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -127,6 +127,7 @@ config S390
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_KERNEL_PMD_MKWRITE
+	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
@@ -199,6 +200,7 @@ config S390
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_NOP_MCOUNT
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -448,7 +450,7 @@ config COMPAT
 	select COMPAT_OLD_SIGACTION
 	select HAVE_UID16
 	depends on MULTIUSER
-	depends on !CC_IS_CLANG
+	depends on !CC_IS_CLANG && !LD_IS_LLD
 	help
 	  Select this option if you want to enable your system kernel to
 	  handle system-calls from ELF binaries for 31 bit ESA.  This option
@@ -582,14 +584,23 @@ config RELOCATABLE
 	help
 	  This builds a kernel image that retains relocation information
 	  so it can be loaded at an arbitrary address.
-	  The kernel is linked as a position-independent executable (PIE)
-	  and contains dynamic relocations which are processed early in the
-	  bootup process.
 	  The relocations make the kernel image about 15% larger (compressed
 	  10%), but are discarded at runtime.
 	  Note: this option exists only for documentation purposes, please do
 	  not remove it.
 
+config PIE_BUILD
+	def_bool CC_IS_CLANG && !$(cc-option,-munaligned-symbols)
+	help
+	  If the compiler is unable to generate code that can manage unaligned
+	  symbols, the kernel is linked as a position-independent executable
+	  (PIE) and includes dynamic relocations that are processed early
+	  during bootup.
+
+	  For kpatch functionality, it is recommended to build the kernel
+	  without the PIE_BUILD option. PIE_BUILD is only enabled when the
+	  compiler lacks proper support for handling unaligned symbols.
+
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image (KASLR)"
 	default y
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 73873e451686..2a58e1864931 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,8 +14,14 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+ifdef CONFIG_PIE_BUILD
 KBUILD_CFLAGS	+= -fPIE
-LDFLAGS_vmlinux	:= -pie
+LDFLAGS_vmlinux	:= -pie -z notext
+else
+KBUILD_CFLAGS	+= $(call cc-option,-munaligned-symbols,)
+LDFLAGS_vmlinux	:= --emit-relocs --discard-none
+extra_tools	:= relocs
+endif
 aflags_dwarf	:= -Wa,-gdwarf-2
 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
 ifndef CONFIG_AS_IS_LLVM
@@ -143,7 +149,7 @@ archheaders:
 
 archprepare:
 	$(Q)$(MAKE) $(build)=$(syscalls) kapi
-	$(Q)$(MAKE) $(build)=$(tools) kapi
+	$(Q)$(MAKE) $(build)=$(tools) kapi $(extra_tools)
 ifeq ($(KBUILD_EXTMOD),)
 # We need to generate vdso-offsets.h before compiling certain files in kernel/.
 # In order to do that, we should use the archprepare target, but we can't since
diff --git a/arch/s390/boot/.gitignore b/arch/s390/boot/.gitignore
index f56591bc0897..f5ef099e2fd3 100644
--- a/arch/s390/boot/.gitignore
+++ b/arch/s390/boot/.gitignore
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 image
 bzImage
+relocs.S
 section_cmp.*
 vmlinux
 vmlinux.lds
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index c7c81e5f9218..294f08a8811a 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -37,7 +37,8 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
 obj-y	:= head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o
 obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o machine_kexec_reloc.o
+obj-y	+= version.o pgm_check_info.o ctype.o ipl_data.o
+obj-y	+= $(if $(CONFIG_PIE_BUILD),machine_kexec_reloc.o,relocs.o)
 obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE))	+= uv.o
 obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 obj-y	+= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
@@ -48,6 +49,9 @@ targets	:= bzImage section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y
 targets	+= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
 targets += vmlinux.bin.zst info.bin syms.bin vmlinux.syms $(obj-all)
+ifndef CONFIG_PIE_BUILD
+targets += relocs.S
+endif
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
 OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all))
@@ -56,9 +60,9 @@ clean-files += vmlinux.map
 
 quiet_cmd_section_cmp = SECTCMP $*
 define cmd_section_cmp
-	s1=`$(OBJDUMP) -t -j "$*" "$<" | sort | \
+	s1=`$(OBJDUMP) -t "$<" | grep "\s$*\s\+" | sort | \
 		sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
-	s2=`$(OBJDUMP) -t -j "$*" "$(word 2,$^)" | sort | \
+	s2=`$(OBJDUMP) -t "$(word 2,$^)" | grep "\s$*\s\+" | sort | \
 		sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \
 	if [ "$$s1" != "$$s2" ]; then \
 		echo "error: section $* differs between $< and $(word 2,$^)" >&2; \
@@ -73,11 +77,12 @@ $(obj)/bzImage: $(obj)/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.b
 $(obj)/section_cmp%: vmlinux $(obj)/vmlinux FORCE
 	$(call if_changed,section_cmp)
 
-LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T
+LDFLAGS_vmlinux-$(CONFIG_LD_ORPHAN_WARN) := --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
+LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS_ALL) FORCE
 	$(call if_changed,ld)
 
-LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T
+LDFLAGS_vmlinux.syms := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(OBJECTS) FORCE
 	$(call if_changed,ld)
 
@@ -93,7 +98,7 @@ OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .
 $(obj)/syms.o: $(obj)/syms.bin FORCE
 	$(call if_changed,objcopy)
 
-OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
+OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=alloc,load
 $(obj)/info.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
@@ -105,6 +110,14 @@ OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+ifndef CONFIG_PIE_BUILD
+CMD_RELOCS=arch/s390/tools/relocs
+quiet_cmd_relocs = RELOCS $@
+	cmd_relocs = $(CMD_RELOCS) $< > $@
+$(obj)/relocs.S: vmlinux FORCE
+	$(call if_changed,relocs)
+endif
+
 suffix-$(CONFIG_KERNEL_GZIP)  := .gz
 suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
 suffix-$(CONFIG_KERNEL_LZ4)  := .lz4
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 222c6886acf6..567d60f78bbc 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -25,9 +25,14 @@ struct vmlinux_info {
 	unsigned long bootdata_size;
 	unsigned long bootdata_preserved_off;
 	unsigned long bootdata_preserved_size;
+#ifdef CONFIG_PIE_BUILD
 	unsigned long dynsym_start;
 	unsigned long rela_dyn_start;
 	unsigned long rela_dyn_end;
+#else
+	unsigned long got_start;
+	unsigned long got_end;
+#endif
 	unsigned long amode31_size;
 	unsigned long init_mm_off;
 	unsigned long swapper_pg_dir_off;
@@ -83,6 +88,7 @@ extern unsigned long vmalloc_size;
 extern int vmalloc_size_set;
 extern char __boot_data_start[], __boot_data_end[];
 extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+extern char __vmlinux_relocs_64_start[], __vmlinux_relocs_64_end[];
 extern char _decompressor_syms_start[], _decompressor_syms_end[];
 extern char _stack_start[], _stack_end[];
 extern char _end[], _decompressor_end[];
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 9cc76e631759..6cf89314209a 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -141,7 +141,8 @@ static void copy_bootdata(void)
 	memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
 }
 
-static void handle_relocs(unsigned long offset)
+#ifdef CONFIG_PIE_BUILD
+static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset)
 {
 	Elf64_Rela *rela_start, *rela_end, *rela;
 	int r_type, r_sym, rc;
@@ -172,6 +173,54 @@ static void handle_relocs(unsigned long offset)
 	}
 }
 
+static void kaslr_adjust_got(unsigned long offset) {}
+static void rescue_relocs(void) {}
+static void free_relocs(void) {}
+#else
+static int *vmlinux_relocs_64_start;
+static int *vmlinux_relocs_64_end;
+
+static void rescue_relocs(void)
+{
+	unsigned long size = __vmlinux_relocs_64_end - __vmlinux_relocs_64_start;
+
+	vmlinux_relocs_64_start = (void *)physmem_alloc_top_down(RR_RELOC, size, 0);
+	vmlinux_relocs_64_end = (void *)vmlinux_relocs_64_start + size;
+	memmove(vmlinux_relocs_64_start, __vmlinux_relocs_64_start, size);
+}
+
+static void free_relocs(void)
+{
+	physmem_free(RR_RELOC);
+}
+
+static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset)
+{
+	int *reloc;
+	long loc;
+
+	/* Adjust R_390_64 relocations */
+	for (reloc = vmlinux_relocs_64_start; reloc < vmlinux_relocs_64_end; reloc++) {
+		loc = (long)*reloc + offset;
+		if (loc < min_addr || loc > max_addr)
+			error("64-bit relocation outside of kernel!\n");
+		*(u64 *)loc += offset;
+	}
+}
+
+static void kaslr_adjust_got(unsigned long offset)
+{
+	u64 *entry;
+
+	/*
+	 * Even without -fPIE, Clang still uses a global offset table for some
+	 * reason. Adjust the GOT entries.
+	 */
+	for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++)
+		*entry += offset;
+}
+#endif
+
 /*
  * Merge information from several sources into a single ident_map_size value.
  * "ident_map_size" represents the upper limit of physical memory we may ever
@@ -299,14 +348,19 @@ static void setup_vmalloc_size(void)
 	vmalloc_size = max(size, vmalloc_size);
 }
 
-static void offset_vmlinux_info(unsigned long offset)
+static void kaslr_adjust_vmlinux_info(unsigned long offset)
 {
 	*(unsigned long *)(&vmlinux.entry) += offset;
 	vmlinux.bootdata_off += offset;
 	vmlinux.bootdata_preserved_off += offset;
+#ifdef CONFIG_PIE_BUILD
 	vmlinux.rela_dyn_start += offset;
 	vmlinux.rela_dyn_end += offset;
 	vmlinux.dynsym_start += offset;
+#else
+	vmlinux.got_start += offset;
+	vmlinux.got_end += offset;
+#endif
 	vmlinux.init_mm_off += offset;
 	vmlinux.swapper_pg_dir_off += offset;
 	vmlinux.invalid_pg_dir_off += offset;
@@ -361,6 +415,7 @@ void startup_kernel(void)
 	detect_physmem_online_ranges(max_physmem_end);
 	save_ipl_cert_comp_list();
 	rescue_initrd(safe_addr, ident_map_size);
+	rescue_relocs();
 
 	if (kaslr_enabled()) {
 		vmlinux_lma = randomize_within_range(vmlinux.image_size + vmlinux.bss_size,
@@ -368,7 +423,7 @@ void startup_kernel(void)
 						     ident_map_size);
 		if (vmlinux_lma) {
 			__kaslr_offset = vmlinux_lma - vmlinux.default_lma;
-			offset_vmlinux_info(__kaslr_offset);
+			kaslr_adjust_vmlinux_info(__kaslr_offset);
 		}
 	}
 	vmlinux_lma = vmlinux_lma ?: vmlinux.default_lma;
@@ -393,18 +448,20 @@ void startup_kernel(void)
 	/*
 	 * The order of the following operations is important:
 	 *
-	 * - handle_relocs() must follow clear_bss_section() to establish static
-	 *   memory references to data in .bss to be used by setup_vmem()
+	 * - kaslr_adjust_relocs() must follow clear_bss_section() to establish
+	 *   static memory references to data in .bss to be used by setup_vmem()
 	 *   (i.e init_mm.pgd)
 	 *
-	 * - setup_vmem() must follow handle_relocs() to be able using
+	 * - setup_vmem() must follow kaslr_adjust_relocs() to be able using
 	 *   static memory references to data in .bss (i.e init_mm.pgd)
 	 *
-	 * - copy_bootdata() must follow setup_vmem() to propagate changes to
-	 *   bootdata made by setup_vmem()
+	 * - copy_bootdata() must follow setup_vmem() to propagate changes
+	 *   to bootdata made by setup_vmem()
 	 */
 	clear_bss_section(vmlinux_lma);
-	handle_relocs(__kaslr_offset);
+	kaslr_adjust_relocs(vmlinux_lma, vmlinux_lma + vmlinux.image_size, __kaslr_offset);
+	kaslr_adjust_got(__kaslr_offset);
+	free_relocs();
 	setup_vmem(asce_limit);
 	copy_bootdata();
 
diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index 389df0e0d9e5..3d7ea585ab99 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -31,6 +31,7 @@ SECTIONS
 		_text = .;	/* Text */
 		*(.text)
 		*(.text.*)
+		INIT_TEXT
 		_etext = . ;
 	}
 	.rodata : {
@@ -39,6 +40,9 @@ SECTIONS
 		*(.rodata.*)
 		_erodata = . ;
 	}
+	.got : {
+		*(.got)
+	}
 	NOTES
 	.data :	{
 		_data = . ;
@@ -106,6 +110,24 @@ SECTIONS
 		_compressed_end = .;
 	}
 
+#ifndef CONFIG_PIE_BUILD
+	/*
+	 * When the kernel is built with CONFIG_KERNEL_UNCOMPRESSED, the entire
+	 * uncompressed vmlinux.bin is positioned in the bzImage decompressor
+	 * image at the default kernel LMA of 0x100000, enabling it to be
+	 * executed in-place. However, the size of .vmlinux.relocs could be
+	 * large enough to cause an overlap with the uncompressed kernel at the
+	 * address 0x100000. To address this issue, .vmlinux.relocs is
+	 * positioned after the .rodata.compressed.
+	 */
+	. = ALIGN(4);
+	.vmlinux.relocs : {
+		__vmlinux_relocs_64_start = .;
+		*(.vmlinux.relocs_64)
+		__vmlinux_relocs_64_end = .;
+	}
+#endif
+
 #define SB_TRAILER_SIZE 32
 	/* Trailer needed for Secure Boot */
 	. += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */
@@ -118,8 +140,34 @@ SECTIONS
 	}
 	_end = .;
 
+	DWARF_DEBUG
+	ELF_DETAILS
+
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the three reserved double words.
+	 */
+	.got.plt : {
+		*(.got.plt)
+	}
+	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+
 	/* Sections to be discarded */
 	/DISCARD/ : {
+		COMMON_DISCARDS
 		*(.eh_frame)
 		*(__ex_table)
 		*(*__ksymtab*)
diff --git a/arch/s390/configs/compat.config b/arch/s390/configs/compat.config
new file mode 100644
index 000000000000..6fd051453ae8
--- /dev/null
+++ b/arch/s390/configs/compat.config
@@ -0,0 +1,3 @@
+# Help: Enable compat support
+CONFIG_COMPAT=y
+CONFIG_COMPAT_32BIT_TIME=y
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index cae2dd34fbb4..4032e6e136ac 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -118,7 +118,6 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
-CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -374,6 +373,7 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -436,9 +436,6 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -637,7 +634,6 @@ CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
-CONFIG_NETFS_SUPPORT=m
 CONFIG_NETFS_STATS=y
 CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
@@ -709,7 +705,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
-CONFIG_INIT_STACK_NONE=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -739,7 +734,6 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
@@ -830,6 +824,8 @@ CONFIG_TEST_LOCKUP=m
 CONFIG_DEBUG_PREEMPT=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
+CONFIG_LOCKDEP_BITS=16
+CONFIG_LOCKDEP_CHAINS_BITS=17
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
 CONFIG_DEBUG_IRQFLAGS=y
@@ -886,4 +882,3 @@ CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_STRING_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
-CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 42b988873e54..d33f814f78b2 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -109,7 +109,6 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
-CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -364,6 +363,7 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -426,9 +426,6 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
-CONFIG_MD_LINEAR=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -622,7 +619,6 @@ CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
 CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
-CONFIG_NETFS_SUPPORT=m
 CONFIG_NETFS_STATS=y
 CONFIG_FSCACHE=y
 CONFIG_CACHEFILES=m
@@ -693,7 +689,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
 CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
-CONFIG_INIT_STACK_NONE=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
@@ -724,11 +719,9 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_AEGIS128=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -815,4 +808,3 @@ CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BPF=m
-CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 30d2a1687665..c51f3ec4eb28 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y
 # CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=2
@@ -64,7 +65,6 @@ CONFIG_ZFCP=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
-CONFIG_INIT_STACK_NONE=y
 # CONFIG_ZLIB_DFLTCC is not set
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c
index ed9959e6f714..f8b0c52e77a4 100644
--- a/arch/s390/crypto/chacha-glue.c
+++ b/arch/s390/crypto/chacha-glue.c
@@ -15,14 +15,14 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 #include "chacha-s390.h"
 
 static void chacha20_crypt_s390(u32 *state, u8 *dst, const u8 *src,
 				unsigned int nbytes, const u32 *key,
 				u32 *counter)
 {
-	struct kernel_fpu vxstate;
+	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
 
 	kernel_fpu_begin(&vxstate, KERNEL_VXR);
 	chacha20_vx(dst, src, nbytes, key, counter);
diff --git a/arch/s390/crypto/chacha-s390.S b/arch/s390/crypto/chacha-s390.S
index 37cb63f25b17..63f3102678c0 100644
--- a/arch/s390/crypto/chacha-s390.S
+++ b/arch/s390/crypto/chacha-s390.S
@@ -8,7 +8,7 @@
 
 #include <linux/linkage.h>
 #include <asm/nospec-insn.h>
-#include <asm/vx-insn.h>
+#include <asm/fpu-insn.h>
 
 #define SP	%r15
 #define FRAME	(16 * 8 + 4 * 8)
diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c
index 017143e9cef7..74f17c905d12 100644
--- a/arch/s390/crypto/crc32-vx.c
+++ b/arch/s390/crypto/crc32-vx.c
@@ -13,8 +13,8 @@
 #include <linux/cpufeature.h>
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
-#include <asm/fpu/api.h>
-
+#include <asm/fpu.h>
+#include "crc32-vx.h"
 
 #define CRC32_BLOCK_SIZE	1
 #define CRC32_DIGEST_SIZE	4
@@ -31,11 +31,6 @@ struct crc_desc_ctx {
 	u32 crc;
 };
 
-/* Prototypes for functions in assembly files */
-u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
-u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
-u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
-
 /*
  * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension
  *
@@ -49,8 +44,8 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
 	static u32 __pure ___fname(u32 crc,				    \
 				unsigned char const *data, size_t datalen)  \
 	{								    \
-		struct kernel_fpu vxstate;				    \
 		unsigned long prealign, aligned, remaining;		    \
+		DECLARE_KERNEL_FPU_ONSTACK16(vxstate);			    \
 									    \
 		if (datalen < VX_MIN_LEN + VX_ALIGN_MASK)		    \
 			return ___crc32_sw(crc, data, datalen);		    \
diff --git a/arch/s390/crypto/crc32-vx.h b/arch/s390/crypto/crc32-vx.h
new file mode 100644
index 000000000000..652c96e1a822
--- /dev/null
+++ b/arch/s390/crypto/crc32-vx.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRC32_VX_S390_H
+#define _CRC32_VX_S390_H
+
+#include <linux/types.h>
+
+u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size);
+
+#endif /* _CRC32_VX_S390_H */
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.c
index 34ee47926891..fed7c9c70d05 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.c
@@ -12,20 +12,17 @@
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
-#include <linux/linkage.h>
-#include <asm/nospec-insn.h>
-#include <asm/vx-insn.h>
+#include <linux/types.h>
+#include <asm/fpu.h>
+#include "crc32-vx.h"
 
 /* Vector register range containing CRC-32 constants */
-#define CONST_R1R2		%v9
-#define CONST_R3R4		%v10
-#define CONST_R5		%v11
-#define CONST_R6		%v12
-#define CONST_RU_POLY		%v13
-#define CONST_CRC_POLY		%v14
-
-	.data
-	.balign	8
+#define CONST_R1R2		9
+#define CONST_R3R4		10
+#define CONST_R5		11
+#define CONST_R6		12
+#define CONST_RU_POLY		13
+#define CONST_CRC_POLY		14
 
 /*
  * The CRC-32 constant block contains reduction constants to fold and
@@ -58,105 +55,74 @@
  *	P'(x) = 0xEDB88320
  */
 
-SYM_DATA_START_LOCAL(constants_CRC_32_BE)
-	.quad		0x08833794c, 0x0e6228b11	# R1, R2
-	.quad		0x0c5b9cd4c, 0x0e8a45605	# R3, R4
-	.quad		0x0f200aa66, 1 << 32		# R5, x32
-	.quad		0x0490d678d, 1			# R6, 1
-	.quad		0x104d101df, 0			# u
-	.quad		0x104C11DB7, 0			# P(x)
-SYM_DATA_END(constants_CRC_32_BE)
-
-	.previous
-
-	GEN_BR_THUNK %r14
-
-	.text
-/*
- * The CRC-32 function(s) use these calling conventions:
- *
- * Parameters:
- *
- *	%r2:	Initial CRC value, typically ~0; and final CRC (return) value.
- *	%r3:	Input buffer pointer, performance might be improved if the
- *		buffer is on a doubleword boundary.
- *	%r4:	Length of the buffer, must be 64 bytes or greater.
+static unsigned long constants_CRC_32_BE[] = {
+	0x08833794c, 0x0e6228b11,	/* R1, R2 */
+	0x0c5b9cd4c, 0x0e8a45605,	/* R3, R4 */
+	0x0f200aa66, 1UL << 32,		/* R5, x32 */
+	0x0490d678d, 1,			/* R6, 1 */
+	0x104d101df, 0,			/* u */
+	0x104C11DB7, 0,			/* P(x) */
+};
+
+/**
+ * crc32_be_vgfm_16 - Compute CRC-32 (BE variant) with vector registers
+ * @crc: Initial CRC value, typically ~0.
+ * @buf: Input buffer pointer, performance might be improved if the
+ *	  buffer is on a doubleword boundary.
+ * @size: Size of the buffer, must be 64 bytes or greater.
  *
  * Register usage:
- *
- *	%r5:	CRC-32 constant pool base pointer.
  *	V0:	Initial CRC value and intermediate constants and results.
  *	V1..V4:	Data for CRC computation.
  *	V5..V8:	Next data chunks that are fetched from the input buffer.
- *
  *	V9..V14: CRC-32 constants.
  */
-SYM_FUNC_START(crc32_be_vgfm_16)
+u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size)
+{
 	/* Load CRC-32 constants */
-	larl	%r5,constants_CRC_32_BE
-	VLM	CONST_R1R2,CONST_CRC_POLY,0,%r5
+	fpu_vlm(CONST_R1R2, CONST_CRC_POLY, &constants_CRC_32_BE);
+	fpu_vzero(0);
 
 	/* Load the initial CRC value into the leftmost word of V0. */
-	VZERO	%v0
-	VLVGF	%v0,%r2,0
+	fpu_vlvgf(0, crc, 0);
 
 	/* Load a 64-byte data chunk and XOR with CRC */
-	VLM	%v1,%v4,0,%r3		/* 64-bytes into V1..V4 */
-	VX	%v1,%v0,%v1		/* V1 ^= CRC */
-	aghi	%r3,64			/* BUF = BUF + 64 */
-	aghi	%r4,-64			/* LEN = LEN - 64 */
-
-	/* Check remaining buffer size and jump to proper folding method */
-	cghi	%r4,64
-	jl	.Lless_than_64bytes
-
-.Lfold_64bytes_loop:
-	/* Load the next 64-byte data chunk into V5 to V8 */
-	VLM	%v5,%v8,0,%r3
+	fpu_vlm(1, 4, buf);
+	fpu_vx(1, 0, 1);
+	buf += 64;
+	size -= 64;
+
+	while (size >= 64) {
+		/* Load the next 64-byte data chunk into V5 to V8 */
+		fpu_vlm(5, 8, buf);
+
+		/*
+		 * Perform a GF(2) multiplication of the doublewords in V1 with
+		 * the reduction constants in V0.  The intermediate result is
+		 * then folded (accumulated) with the next data chunk in V5 and
+		 * stored in V1.  Repeat this step for the register contents
+		 * in V2, V3, and V4 respectively.
+		 */
+		fpu_vgfmag(1, CONST_R1R2, 1, 5);
+		fpu_vgfmag(2, CONST_R1R2, 2, 6);
+		fpu_vgfmag(3, CONST_R1R2, 3, 7);
+		fpu_vgfmag(4, CONST_R1R2, 4, 8);
+		buf += 64;
+		size -= 64;
+	}
 
-	/*
-	 * Perform a GF(2) multiplication of the doublewords in V1 with
-	 * the reduction constants in V0.  The intermediate result is
-	 * then folded (accumulated) with the next data chunk in V5 and
-	 * stored in V1.  Repeat this step for the register contents
-	 * in V2, V3, and V4 respectively.
-	 */
-	VGFMAG	%v1,CONST_R1R2,%v1,%v5
-	VGFMAG	%v2,CONST_R1R2,%v2,%v6
-	VGFMAG	%v3,CONST_R1R2,%v3,%v7
-	VGFMAG	%v4,CONST_R1R2,%v4,%v8
-
-	/* Adjust buffer pointer and length for next loop */
-	aghi	%r3,64			/* BUF = BUF + 64 */
-	aghi	%r4,-64			/* LEN = LEN - 64 */
-
-	cghi	%r4,64
-	jnl	.Lfold_64bytes_loop
-
-.Lless_than_64bytes:
 	/* Fold V1 to V4 into a single 128-bit value in V1 */
-	VGFMAG	%v1,CONST_R3R4,%v1,%v2
-	VGFMAG	%v1,CONST_R3R4,%v1,%v3
-	VGFMAG	%v1,CONST_R3R4,%v1,%v4
-
-	/* Check whether to continue with 64-bit folding */
-	cghi	%r4,16
-	jl	.Lfinal_fold
+	fpu_vgfmag(1, CONST_R3R4, 1, 2);
+	fpu_vgfmag(1, CONST_R3R4, 1, 3);
+	fpu_vgfmag(1, CONST_R3R4, 1, 4);
 
-.Lfold_16bytes_loop:
+	while (size >= 16) {
+		fpu_vl(2, buf);
+		fpu_vgfmag(1, CONST_R3R4, 1, 2);
+		buf += 16;
+		size -= 16;
+	}
 
-	VL	%v2,0,,%r3		/* Load next data chunk */
-	VGFMAG	%v1,CONST_R3R4,%v1,%v2	/* Fold next data chunk */
-
-	/* Adjust buffer pointer and size for folding next data chunk */
-	aghi	%r3,16
-	aghi	%r4,-16
-
-	/* Process remaining data chunks */
-	cghi	%r4,16
-	jnl	.Lfold_16bytes_loop
-
-.Lfinal_fold:
 	/*
 	 * The R5 constant is used to fold a 128-bit value into an 96-bit value
 	 * that is XORed with the next 96-bit input data chunk.  To use a single
@@ -164,7 +130,7 @@ SYM_FUNC_START(crc32_be_vgfm_16)
 	 * form an intermediate 96-bit value (with appended zeros) which is then
 	 * XORed with the intermediate reduction result.
 	 */
-	VGFMG	%v1,CONST_R5,%v1
+	fpu_vgfmg(1, CONST_R5, 1);
 
 	/*
 	 * Further reduce the remaining 96-bit value to a 64-bit value using a
@@ -173,7 +139,7 @@ SYM_FUNC_START(crc32_be_vgfm_16)
 	 * doubleword with R6.	The result is a 64-bit value and is subject to
 	 * the Barret reduction.
 	 */
-	VGFMG	%v1,CONST_R6,%v1
+	fpu_vgfmg(1, CONST_R6, 1);
 
 	/*
 	 * The input values to the Barret reduction are the degree-63 polynomial
@@ -194,20 +160,15 @@ SYM_FUNC_START(crc32_be_vgfm_16)
 	 */
 
 	/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
-	VUPLLF	%v2,%v1
-	VGFMG	%v2,CONST_RU_POLY,%v2
+	fpu_vupllf(2, 1);
+	fpu_vgfmg(2, CONST_RU_POLY, 2);
 
 	/*
 	 * Compute the GF(2) product of the CRC polynomial in VO with T1(x) in
 	 * V2 and XOR the intermediate result, T2(x),  with the value in V1.
 	 * The final result is in the rightmost word of V2.
 	 */
-	VUPLLF	%v2,%v2
-	VGFMAG	%v2,CONST_CRC_POLY,%v2,%v1
-
-.Ldone:
-	VLGVF	%r2,%v2,3
-	BR_EX	%r14
-SYM_FUNC_END(crc32_be_vgfm_16)
-
-.previous
+	fpu_vupllf(2, 2);
+	fpu_vgfmag(2, CONST_CRC_POLY, 2, 1);
+	return fpu_vlgvf(2, 3);
+}
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.c
index 5a819ae09a0b..2f629f394df7 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.c
@@ -13,20 +13,17 @@
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
-#include <linux/linkage.h>
-#include <asm/nospec-insn.h>
-#include <asm/vx-insn.h>
+#include <linux/types.h>
+#include <asm/fpu.h>
+#include "crc32-vx.h"
 
 /* Vector register range containing CRC-32 constants */
-#define CONST_PERM_LE2BE	%v9
-#define CONST_R2R1		%v10
-#define CONST_R4R3		%v11
-#define CONST_R5		%v12
-#define CONST_RU_POLY		%v13
-#define CONST_CRC_POLY		%v14
-
-	.data
-	.balign	8
+#define CONST_PERM_LE2BE	9
+#define CONST_R2R1		10
+#define CONST_R4R3		11
+#define CONST_R5		12
+#define CONST_RU_POLY		13
+#define CONST_CRC_POLY		14
 
 /*
  * The CRC-32 constant block contains reduction constants to fold and
@@ -59,64 +56,43 @@
  *	P'(x) = 0x82F63B78
  */
 
-SYM_DATA_START_LOCAL(constants_CRC_32_LE)
-	.octa		0x0F0E0D0C0B0A09080706050403020100	# BE->LE mask
-	.quad		0x1c6e41596, 0x154442bd4		# R2, R1
-	.quad		0x0ccaa009e, 0x1751997d0		# R4, R3
-	.octa		0x163cd6124				# R5
-	.octa		0x1F7011641				# u'
-	.octa		0x1DB710641				# P'(x) << 1
-SYM_DATA_END(constants_CRC_32_LE)
-
-SYM_DATA_START_LOCAL(constants_CRC_32C_LE)
-	.octa		0x0F0E0D0C0B0A09080706050403020100	# BE->LE mask
-	.quad		0x09e4addf8, 0x740eef02			# R2, R1
-	.quad		0x14cd00bd6, 0xf20c0dfe			# R4, R3
-	.octa		0x0dd45aab8				# R5
-	.octa		0x0dea713f1				# u'
-	.octa		0x105ec76f0				# P'(x) << 1
-SYM_DATA_END(constants_CRC_32C_LE)
-
-	.previous
-
-	GEN_BR_THUNK %r14
-
-	.text
-
-/*
- * The CRC-32 functions use these calling conventions:
- *
- * Parameters:
- *
- *	%r2:	Initial CRC value, typically ~0; and final CRC (return) value.
- *	%r3:	Input buffer pointer, performance might be improved if the
- *		buffer is on a doubleword boundary.
- *	%r4:	Length of the buffer, must be 64 bytes or greater.
+static unsigned long constants_CRC_32_LE[] = {
+	0x0f0e0d0c0b0a0908, 0x0706050403020100,	/* BE->LE mask */
+	0x1c6e41596, 0x154442bd4,		/* R2, R1 */
+	0x0ccaa009e, 0x1751997d0,		/* R4, R3 */
+	0x0, 0x163cd6124,			/* R5 */
+	0x0, 0x1f7011641,			/* u' */
+	0x0, 0x1db710641			/* P'(x) << 1 */
+};
+
+static unsigned long constants_CRC_32C_LE[] = {
+	0x0f0e0d0c0b0a0908, 0x0706050403020100,	/* BE->LE mask */
+	0x09e4addf8, 0x740eef02,		/* R2, R1 */
+	0x14cd00bd6, 0xf20c0dfe,		/* R4, R3 */
+	0x0, 0x0dd45aab8,			/* R5 */
+	0x0, 0x0dea713f1,			/* u' */
+	0x0, 0x105ec76f0			/* P'(x) << 1 */
+};
+
+/**
+ * crc32_le_vgfm_generic - Compute CRC-32 (LE variant) with vector registers
+ * @crc: Initial CRC value, typically ~0.
+ * @buf: Input buffer pointer, performance might be improved if the
+ *	 buffer is on a doubleword boundary.
+ * @size: Size of the buffer, must be 64 bytes or greater.
+ * @constants: CRC-32 constant pool base pointer.
  *
  * Register usage:
- *
- *	%r5:	CRC-32 constant pool base pointer.
- *	V0:	Initial CRC value and intermediate constants and results.
- *	V1..V4:	Data for CRC computation.
- *	V5..V8:	Next data chunks that are fetched from the input buffer.
- *	V9:	Constant for BE->LE conversion and shift operations
- *
+ *	V0:	  Initial CRC value and intermediate constants and results.
+ *	V1..V4:	  Data for CRC computation.
+ *	V5..V8:	  Next data chunks that are fetched from the input buffer.
+ *	V9:	  Constant for BE->LE conversion and shift operations
  *	V10..V14: CRC-32 constants.
  */
-
-SYM_FUNC_START(crc32_le_vgfm_16)
-	larl	%r5,constants_CRC_32_LE
-	j	crc32_le_vgfm_generic
-SYM_FUNC_END(crc32_le_vgfm_16)
-
-SYM_FUNC_START(crc32c_le_vgfm_16)
-	larl	%r5,constants_CRC_32C_LE
-	j	crc32_le_vgfm_generic
-SYM_FUNC_END(crc32c_le_vgfm_16)
-
-SYM_FUNC_START(crc32_le_vgfm_generic)
+static u32 crc32_le_vgfm_generic(u32 crc, unsigned char const *buf, size_t size, unsigned long *constants)
+{
 	/* Load CRC-32 constants */
-	VLM	CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
+	fpu_vlm(CONST_PERM_LE2BE, CONST_CRC_POLY, constants);
 
 	/*
 	 * Load the initial CRC value.
@@ -125,90 +101,73 @@ SYM_FUNC_START(crc32_le_vgfm_generic)
 	 * vector register and is later XORed with the LSB portion
 	 * of the loaded input data.
 	 */
-	VZERO	%v0			/* Clear V0 */
-	VLVGF	%v0,%r2,3		/* Load CRC into rightmost word */
+	fpu_vzero(0);			/* Clear V0 */
+	fpu_vlvgf(0, crc, 3);		/* Load CRC into rightmost word */
 
 	/* Load a 64-byte data chunk and XOR with CRC */
-	VLM	%v1,%v4,0,%r3		/* 64-bytes into V1..V4 */
-	VPERM	%v1,%v1,%v1,CONST_PERM_LE2BE
-	VPERM	%v2,%v2,%v2,CONST_PERM_LE2BE
-	VPERM	%v3,%v3,%v3,CONST_PERM_LE2BE
-	VPERM	%v4,%v4,%v4,CONST_PERM_LE2BE
+	fpu_vlm(1, 4, buf);
+	fpu_vperm(1, 1, 1, CONST_PERM_LE2BE);
+	fpu_vperm(2, 2, 2, CONST_PERM_LE2BE);
+	fpu_vperm(3, 3, 3, CONST_PERM_LE2BE);
+	fpu_vperm(4, 4, 4, CONST_PERM_LE2BE);
+
+	fpu_vx(1, 0, 1);		/* V1 ^= CRC */
+	buf += 64;
+	size -= 64;
+
+	while (size >= 64) {
+		fpu_vlm(5, 8, buf);
+		fpu_vperm(5, 5, 5, CONST_PERM_LE2BE);
+		fpu_vperm(6, 6, 6, CONST_PERM_LE2BE);
+		fpu_vperm(7, 7, 7, CONST_PERM_LE2BE);
+		fpu_vperm(8, 8, 8, CONST_PERM_LE2BE);
+		/*
+		 * Perform a GF(2) multiplication of the doublewords in V1 with
+		 * the R1 and R2 reduction constants in V0.  The intermediate
+		 * result is then folded (accumulated) with the next data chunk
+		 * in V5 and stored in V1. Repeat this step for the register
+		 * contents in V2, V3, and V4 respectively.
+		 */
+		fpu_vgfmag(1, CONST_R2R1, 1, 5);
+		fpu_vgfmag(2, CONST_R2R1, 2, 6);
+		fpu_vgfmag(3, CONST_R2R1, 3, 7);
+		fpu_vgfmag(4, CONST_R2R1, 4, 8);
+		buf += 64;
+		size -= 64;
+	}
 
-	VX	%v1,%v0,%v1		/* V1 ^= CRC */
-	aghi	%r3,64			/* BUF = BUF + 64 */
-	aghi	%r4,-64			/* LEN = LEN - 64 */
-
-	cghi	%r4,64
-	jl	.Lless_than_64bytes
-
-.Lfold_64bytes_loop:
-	/* Load the next 64-byte data chunk into V5 to V8 */
-	VLM	%v5,%v8,0,%r3
-	VPERM	%v5,%v5,%v5,CONST_PERM_LE2BE
-	VPERM	%v6,%v6,%v6,CONST_PERM_LE2BE
-	VPERM	%v7,%v7,%v7,CONST_PERM_LE2BE
-	VPERM	%v8,%v8,%v8,CONST_PERM_LE2BE
-
-	/*
-	 * Perform a GF(2) multiplication of the doublewords in V1 with
-	 * the R1 and R2 reduction constants in V0.  The intermediate result
-	 * is then folded (accumulated) with the next data chunk in V5 and
-	 * stored in V1. Repeat this step for the register contents
-	 * in V2, V3, and V4 respectively.
-	 */
-	VGFMAG	%v1,CONST_R2R1,%v1,%v5
-	VGFMAG	%v2,CONST_R2R1,%v2,%v6
-	VGFMAG	%v3,CONST_R2R1,%v3,%v7
-	VGFMAG	%v4,CONST_R2R1,%v4,%v8
-
-	aghi	%r3,64			/* BUF = BUF + 64 */
-	aghi	%r4,-64			/* LEN = LEN - 64 */
-
-	cghi	%r4,64
-	jnl	.Lfold_64bytes_loop
-
-.Lless_than_64bytes:
 	/*
 	 * Fold V1 to V4 into a single 128-bit value in V1.  Multiply V1 with R3
 	 * and R4 and accumulating the next 128-bit chunk until a single 128-bit
 	 * value remains.
 	 */
-	VGFMAG	%v1,CONST_R4R3,%v1,%v2
-	VGFMAG	%v1,CONST_R4R3,%v1,%v3
-	VGFMAG	%v1,CONST_R4R3,%v1,%v4
-
-	cghi	%r4,16
-	jl	.Lfinal_fold
-
-.Lfold_16bytes_loop:
-
-	VL	%v2,0,,%r3		/* Load next data chunk */
-	VPERM	%v2,%v2,%v2,CONST_PERM_LE2BE
-	VGFMAG	%v1,CONST_R4R3,%v1,%v2	/* Fold next data chunk */
+	fpu_vgfmag(1, CONST_R4R3, 1, 2);
+	fpu_vgfmag(1, CONST_R4R3, 1, 3);
+	fpu_vgfmag(1, CONST_R4R3, 1, 4);
+
+	while (size >= 16) {
+		fpu_vl(2, buf);
+		fpu_vperm(2, 2, 2, CONST_PERM_LE2BE);
+		fpu_vgfmag(1, CONST_R4R3, 1, 2);
+		buf += 16;
+		size -= 16;
+	}
 
-	aghi	%r3,16
-	aghi	%r4,-16
-
-	cghi	%r4,16
-	jnl	.Lfold_16bytes_loop
-
-.Lfinal_fold:
 	/*
 	 * Set up a vector register for byte shifts.  The shift value must
 	 * be loaded in bits 1-4 in byte element 7 of a vector register.
 	 * Shift by 8 bytes: 0x40
 	 * Shift by 4 bytes: 0x20
 	 */
-	VLEIB	%v9,0x40,7
+	fpu_vleib(9, 0x40, 7);
 
 	/*
 	 * Prepare V0 for the next GF(2) multiplication: shift V0 by 8 bytes
 	 * to move R4 into the rightmost doubleword and set the leftmost
 	 * doubleword to 0x1.
 	 */
-	VSRLB	%v0,CONST_R4R3,%v9
-	VLEIG	%v0,1,0
+	fpu_vsrlb(0, CONST_R4R3, 9);
+	fpu_vleig(0, 1, 0);
 
 	/*
 	 * Compute GF(2) product of V1 and V0.	The rightmost doubleword
@@ -216,7 +175,7 @@ SYM_FUNC_START(crc32_le_vgfm_generic)
 	 * multiplied by 0x1 and is then XORed with rightmost product.
 	 * Implicitly, the intermediate leftmost product becomes padded
 	 */
-	VGFMG	%v1,%v0,%v1
+	fpu_vgfmg(1, 0, 1);
 
 	/*
 	 * Now do the final 32-bit fold by multiplying the rightmost word
@@ -231,10 +190,10 @@ SYM_FUNC_START(crc32_le_vgfm_generic)
 	 * rightmost doubleword and the leftmost doubleword is zero to ignore
 	 * the leftmost product of V1.
 	 */
-	VLEIB	%v9,0x20,7		  /* Shift by words */
-	VSRLB	%v2,%v1,%v9		  /* Store remaining bits in V2 */
-	VUPLLF	%v1,%v1			  /* Split rightmost doubleword */
-	VGFMAG	%v1,CONST_R5,%v1,%v2	  /* V1 = (V1 * R5) XOR V2 */
+	fpu_vleib(9, 0x20, 7);		  /* Shift by words */
+	fpu_vsrlb(2, 1, 9);		  /* Store remaining bits in V2 */
+	fpu_vupllf(1, 1);		  /* Split rightmost doubleword */
+	fpu_vgfmag(1, CONST_R5, 1, 2);	  /* V1 = (V1 * R5) XOR V2 */
 
 	/*
 	 * Apply a Barret reduction to compute the final 32-bit CRC value.
@@ -256,20 +215,26 @@ SYM_FUNC_START(crc32_le_vgfm_generic)
 	 */
 
 	/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
-	VUPLLF	%v2,%v1
-	VGFMG	%v2,CONST_RU_POLY,%v2
+	fpu_vupllf(2, 1);
+	fpu_vgfmg(2, CONST_RU_POLY, 2);
 
 	/*
 	 * Compute the GF(2) product of the CRC polynomial with T1(x) in
 	 * V2 and XOR the intermediate result, T2(x), with the value in V1.
 	 * The final result is stored in word element 2 of V2.
 	 */
-	VUPLLF	%v2,%v2
-	VGFMAG	%v2,CONST_CRC_POLY,%v2,%v1
+	fpu_vupllf(2, 2);
+	fpu_vgfmag(2, CONST_CRC_POLY, 2, 1);
+
+	return fpu_vlgvf(2, 2);
+}
 
-.Ldone:
-	VLGVF	%r2,%v2,2
-	BR_EX	%r14
-SYM_FUNC_END(crc32_le_vgfm_generic)
+u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size)
+{
+	return crc32_le_vgfm_generic(crc, buf, size, &constants_CRC_32_LE[0]);
+}
 
-.previous
+u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size)
+{
+	return crc32_le_vgfm_generic(crc, buf, size, &constants_CRC_32C_LE[0]);
+}
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 55ee5567a5ea..99f7e1f2b70a 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -125,20 +125,8 @@ struct s390_pxts_ctx {
 static inline int __paes_keyblob2pkey(struct key_blob *kb,
 				     struct pkey_protkey *pk)
 {
-	int i, ret;
-
-	/* try three times in case of failure */
-	for (i = 0; i < 3; i++) {
-		if (i > 0 && ret == -EAGAIN && in_task())
-			if (msleep_interruptible(1000))
-				return -EINTR;
-		ret = pkey_keyblob2pkey(kb->key, kb->keylen,
-					pk->protkey, &pk->len, &pk->type);
-		if (ret == 0)
-			break;
-	}
-
-	return ret;
+	return pkey_keyblob2pkey(kb->key, kb->keylen,
+				 pk->protkey, &pk->len, &pk->type);
 }
 
 static inline int __paes_convert_key(struct s390_paes_ctx *ctx)
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index 9a2786079e3a..4131f0daa5ea 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -20,8 +20,7 @@
  */
 static void diag0c_fn(void *data)
 {
-	diag_stat_inc(DIAG_STAT_X00C);
-	diag_amode31_ops.diag0c(((void **)data)[smp_processor_id()]);
+	diag0c(((void **)data)[smp_processor_id()]);
 }
 
 /*
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index f5f7e78ddc0c..9fc3f0dae8f0 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -25,7 +25,7 @@
 
 static inline unsigned long __hypfs_sprp_diag304(void *data, unsigned long cmd)
 {
-	union register_pair r1 = { .even = (unsigned long)data, };
+	union register_pair r1 = { .even = virt_to_phys(data), };
 
 	asm volatile("diag %[r1],%[r3],0x304\n"
 		     : [r1] "+&d" (r1.pair)
@@ -74,7 +74,7 @@ static int __hypfs_sprp_ioctl(void __user *user_area)
 	int rc;
 
 	rc = -ENOMEM;
-	data = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	data = (void *)get_zeroed_page(GFP_KERNEL);
 	diag304 = kzalloc(sizeof(*diag304), GFP_KERNEL);
 	if (!data || !diag304)
 		goto out;
diff --git a/arch/s390/include/asm/access-regs.h b/arch/s390/include/asm/access-regs.h
new file mode 100644
index 000000000000..1a6412d9f5ad
--- /dev/null
+++ b/arch/s390/include/asm/access-regs.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 1999, 2024
+ */
+
+#ifndef __ASM_S390_ACCESS_REGS_H
+#define __ASM_S390_ACCESS_REGS_H
+
+#include <linux/instrumented.h>
+#include <asm/sigcontext.h>
+
+struct access_regs {
+	unsigned int regs[NUM_ACRS];
+};
+
+static inline void save_access_regs(unsigned int *acrs)
+{
+	struct access_regs *regs = (struct access_regs *)acrs;
+
+	instrument_write(regs, sizeof(*regs));
+	asm volatile("stamy	0,15,%[regs]"
+		     : [regs] "=QS" (*regs)
+		     :
+		     : "memory");
+}
+
+static inline void restore_access_regs(unsigned int *acrs)
+{
+	struct access_regs *regs = (struct access_regs *)acrs;
+
+	instrument_read(regs, sizeof(*regs));
+	asm volatile("lamy	0,15,%[regs]"
+		     :
+		     : [regs] "QS" (*regs)
+		     : "memory");
+}
+
+#endif /* __ASM_S390_ACCESS_REGS_H */
diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h
index f2240392c708..a92ebbc7aa7a 100644
--- a/arch/s390/include/asm/appldata.h
+++ b/arch/s390/include/asm/appldata.h
@@ -54,13 +54,13 @@ static inline int appldata_asm(struct appldata_parameter_list *parm_list,
 	parm_list->function = fn;
 	parm_list->parlist_length = sizeof(*parm_list);
 	parm_list->buffer_length = length;
-	parm_list->product_id_addr = (unsigned long) id;
+	parm_list->product_id_addr = virt_to_phys(id);
 	parm_list->buffer_addr = virt_to_phys(buffer);
 	diag_stat_inc(DIAG_STAT_X0DC);
 	asm volatile(
 		"	diag	%1,%0,0xdc"
 		: "=d" (ry)
-		: "d" (parm_list), "m" (*parm_list), "m" (*id)
+		: "d" (virt_to_phys(parm_list)), "m" (*parm_list), "m" (*id)
 		: "cc");
 	return ry;
 }
diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h
index a873e873e1ee..56096ae26f29 100644
--- a/arch/s390/include/asm/asm-prototypes.h
+++ b/arch/s390/include/asm/asm-prototypes.h
@@ -3,7 +3,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/ftrace.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 #include <asm-generic/asm-prototypes.h>
 
 __int128_t __ashlti3(__int128_t a, int b);
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index aebe1e22c7be..c500d45fb465 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -14,7 +14,7 @@
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
 		"1:	.asciz	\""__FILE__"\"\n"		\
 		".previous\n"					\
-		".section __bug_table,\"awM\",@progbits,%2\n"	\
+		".section __bug_table,\"aw\"\n"			\
 		"2:	.long	0b-.\n"				\
 		"	.long	1b-.\n"				\
 		"	.short	%0,%1\n"			\
@@ -30,7 +30,7 @@
 #define __EMIT_BUG(x) do {					\
 	asm_inline volatile(					\
 		"0:	mc	0,0\n"				\
-		".section __bug_table,\"awM\",@progbits,%1\n"	\
+		".section __bug_table,\"aw\"\n"			\
 		"1:	.long	0b-.\n"				\
 		"	.short	%0\n"				\
 		"	.org	1b+%1\n"			\
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 69837eec2ff5..b89159591ca0 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -12,36 +12,29 @@
 #ifndef _S390_CHECKSUM_H
 #define _S390_CHECKSUM_H
 
-#include <linux/kasan-checks.h>
+#include <linux/instrumented.h>
 #include <linux/in6.h>
 
-/*
- * Computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit).
- *
- * Returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic.
- *
- * This function must be called with even lengths, except
- * for the last fragment, which may be odd.
- *
- * It's best to have buff aligned on a 32-bit boundary.
- */
-static inline __wsum csum_partial(const void *buff, int len, __wsum sum)
+static inline __wsum cksm(const void *buff, int len, __wsum sum)
 {
 	union register_pair rp = {
-		.even = (unsigned long) buff,
-		.odd = (unsigned long) len,
+		.even = (unsigned long)buff,
+		.odd = (unsigned long)len,
 	};
 
-	kasan_check_read(buff, len);
-	asm volatile(
+	instrument_read(buff, len);
+	asm volatile("\n"
 		"0:	cksm	%[sum],%[rp]\n"
 		"	jo	0b\n"
 		: [sum] "+&d" (sum), [rp] "+&d" (rp.pair) : : "cc", "memory");
 	return sum;
 }
 
+__wsum csum_partial(const void *buff, int len, __wsum sum);
+
+#define _HAVE_ARCH_CSUM_AND_COPY
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
+
 /*
  * Fold a partial checksum without adding pseudo headers.
  */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index bed804137537..20b94220113b 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -44,6 +44,13 @@ enum diag_stat_enum {
 void diag_stat_inc(enum diag_stat_enum nr);
 void diag_stat_inc_norecursion(enum diag_stat_enum nr);
 
+struct hypfs_diag0c_entry;
+
+/*
+ * Diagnose 0c: Pseudo Timer
+ */
+void diag0c(struct hypfs_diag0c_entry *data);
+
 /*
  * Diagnose 10: Release page range
  */
@@ -331,10 +338,10 @@ struct hypfs_diag0c_entry;
  */
 struct diag_ops {
 	int (*diag210)(struct diag210 *addr);
-	int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode);
+	int (*diag26c)(unsigned long rx, unsigned long rx1, enum diag26c_sc subcode);
 	int (*diag14)(unsigned long rx, unsigned long ry1, unsigned long subcode);
 	int (*diag8c)(struct diag8c *addr, struct ccw_dev_id *devno, size_t len);
-	void (*diag0c)(struct hypfs_diag0c_entry *entry);
+	void (*diag0c)(unsigned long rx);
 	void (*diag308_reset)(void);
 };
 
@@ -342,9 +349,9 @@ extern struct diag_ops diag_amode31_ops;
 extern struct diag210 *__diag210_tmp_amode31;
 
 int _diag210_amode31(struct diag210 *addr);
-int _diag26c_amode31(void *req, void *resp, enum diag26c_sc subcode);
+int _diag26c_amode31(unsigned long rx, unsigned long rx1, enum diag26c_sc subcode);
 int _diag14_amode31(unsigned long rx, unsigned long ry1, unsigned long subcode);
-void _diag0c_amode31(struct hypfs_diag0c_entry *entry);
+void _diag0c_amode31(unsigned long rx);
 void _diag308_reset_amode31(void);
 int _diag8c_amode31(struct diag8c *addr, struct ccw_dev_id *devno, size_t len);
 
diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h
index fdd319a622b0..7f5004065e8a 100644
--- a/arch/s390/include/asm/entry-common.h
+++ b/arch/s390/include/asm/entry-common.h
@@ -8,7 +8,7 @@
 #include <linux/processor.h>
 #include <linux/uaccess.h>
 #include <asm/timex.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 #include <asm/pai.h>
 
 #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_GUARDED_STORAGE | _TIF_PER_TRAP)
@@ -41,8 +41,7 @@ static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
 
 static __always_inline void arch_exit_to_user_mode(void)
 {
-	if (test_cpu_flag(CIF_FPU))
-		__load_fpu_regs();
+	load_user_fpu_regs();
 
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
 		debug_user_asce(1);
diff --git a/arch/s390/include/asm/vx-insn-asm.h b/arch/s390/include/asm/fpu-insn-asm.h
index 360f8b36d962..02ccfe46050a 100644
--- a/arch/s390/include/asm/vx-insn-asm.h
+++ b/arch/s390/include/asm/fpu-insn-asm.h
@@ -9,11 +9,11 @@
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
-#ifndef __ASM_S390_VX_INSN_INTERNAL_H
-#define __ASM_S390_VX_INSN_INTERNAL_H
+#ifndef __ASM_S390_FPU_INSN_ASM_H
+#define __ASM_S390_FPU_INSN_ASM_H
 
-#ifndef __ASM_S390_VX_INSN_H
-#error only <asm/vx-insn.h> can be included directly
+#ifndef __ASM_S390_FPU_INSN_H
+#error only <asm/fpu-insn.h> can be included directly
 #endif
 
 #ifdef __ASSEMBLY__
@@ -195,10 +195,26 @@
 /* RXB - Compute most significant bit used vector registers
  *
  * @rxb:	Operand to store computed RXB value
- * @v1:		First vector register designated operand
- * @v2:		Second vector register designated operand
- * @v3:		Third vector register designated operand
- * @v4:		Fourth vector register designated operand
+ * @v1:		Vector register designated operand whose MSB is stored in
+ *		RXB bit 0 (instruction bit 36) and whose remaining bits
+ *		are stored in instruction bits 8-11.
+ * @v2:		Vector register designated operand whose MSB is stored in
+ *		RXB bit 1 (instruction bit 37) and whose remaining bits
+ *		are stored in instruction bits 12-15.
+ * @v3:		Vector register designated operand whose MSB is stored in
+ *		RXB bit 2 (instruction bit 38) and whose remaining bits
+ *		are stored in instruction bits 16-19.
+ * @v4:		Vector register designated operand whose MSB is stored in
+ *		RXB bit 3 (instruction bit 39) and whose remaining bits
+ *		are stored in instruction bits 32-35.
+ *
+ * Note: In most vector instruction formats [1] V1, V2, V3, and V4 directly
+ * correspond to @v1, @v2, @v3, and @v4. But there are exceptions, such as but
+ * not limited to the vector instruction formats VRR-g, VRR-h, VRS-a, VRS-d,
+ * and VSI.
+ *
+ * [1] IBM z/Architecture Principles of Operation, chapter "Program
+ * Execution, section "Instructions", subsection "Instruction Formats".
  */
 .macro	RXB	rxb v1 v2=0 v3=0 v4=0
 	\rxb = 0
@@ -223,6 +239,9 @@
  * @v2:		Second vector register designated operand (for RXB)
  * @v3:		Third vector register designated operand (for RXB)
  * @v4:		Fourth vector register designated operand (for RXB)
+ *
+ * Note: For @v1, @v2, @v3, and @v4 also refer to the RXB macro
+ * description for further details.
  */
 .macro	MRXB	m v1 v2=0 v3=0 v4=0
 	rxb = 0
@@ -238,6 +257,9 @@
  * @v2:		Second vector register designated operand (for RXB)
  * @v3:		Third vector register designated operand (for RXB)
  * @v4:		Fourth vector register designated operand (for RXB)
+ *
+ * Note: For @v1, @v2, @v3, and @v4 also refer to the RXB macro
+ * description for further details.
  */
 .macro	MRXBOPC	m opc v1 v2=0 v3=0 v4=0
 	MRXB	\m, \v1, \v2, \v3, \v4
@@ -350,7 +372,7 @@
 	VX_NUM	v3, \vr
 	.word	0xE700 | (r1 << 4) | (v3&15)
 	.word	(b2 << 12) | (\disp)
-	MRXBOPC	\m, 0x21, v3
+	MRXBOPC	\m, 0x21, 0, v3
 .endm
 .macro	VLGVB	gr, vr, disp, base="%r0"
 	VLGV	\gr, \vr, \disp, \base, 0
@@ -499,6 +521,25 @@
 	VMRL	\vr1, \vr2, \vr3, 3
 .endm
 
+/* VECTOR LOAD WITH LENGTH */
+.macro VLL	v, gr, disp, base
+	VX_NUM	v1, \v
+	GR_NUM	b2, \base
+	GR_NUM	r3, \gr
+	.word	0xE700 | ((v1&15) << 4) | r3
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC 0, 0x37, v1
+.endm
+
+/* VECTOR STORE WITH LENGTH */
+.macro VSTL	v, gr, disp, base
+	VX_NUM	v1, \v
+	GR_NUM	b2, \base
+	GR_NUM	r3, \gr
+	.word	0xE700 | ((v1&15) << 4) | r3
+	.word	(b2 << 12) | (\disp)
+	MRXBOPC 0, 0x3f, v1
+.endm
 
 /* Vector integer instructions */
 
@@ -512,6 +553,16 @@
 	MRXBOPC	0, 0x68, v1, v2, v3
 .endm
 
+/* VECTOR CHECKSUM */
+.macro VCKSM	vr1, vr2, vr3
+	VX_NUM	v1, \vr1
+	VX_NUM	v2, \vr2
+	VX_NUM	v3, \vr3
+	.word	0xE700 | ((v1&15) << 4) | (v2&15)
+	.word	((v3&15) << 12)
+	MRXBOPC 0, 0x66, v1, v2, v3
+.endm
+
 /* VECTOR EXCLUSIVE OR */
 .macro	VX	vr1, vr2, vr3
 	VX_NUM	v1, \vr1
@@ -678,4 +729,4 @@
 .endm
 
 #endif	/* __ASSEMBLY__ */
-#endif	/* __ASM_S390_VX_INSN_INTERNAL_H */
+#endif	/* __ASM_S390_FPU_INSN_ASM_H */
diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h
new file mode 100644
index 000000000000..c1e2e521d9af
--- /dev/null
+++ b/arch/s390/include/asm/fpu-insn.h
@@ -0,0 +1,486 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Support for Floating Point and Vector Instructions
+ *
+ */
+
+#ifndef __ASM_S390_FPU_INSN_H
+#define __ASM_S390_FPU_INSN_H
+
+#include <asm/fpu-insn-asm.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/instrumented.h>
+#include <asm/asm-extable.h>
+
+asm(".include \"asm/fpu-insn-asm.h\"\n");
+
+/*
+ * Various small helper functions, which can and should be used within
+ * kernel fpu code sections. Each function represents only one floating
+ * point or vector instruction (except for helper functions which require
+ * exception handling).
+ *
+ * This allows to use floating point and vector instructions like C
+ * functions, which has the advantage that all supporting code, like
+ * e.g. loops, can be written in easy to read C code.
+ *
+ * Each of the helper functions provides support for code instrumentation,
+ * like e.g. KASAN. Therefore instrumentation is also covered automatically
+ * when using these functions.
+ *
+ * In order to ensure that code generated with the helper functions stays
+ * within kernel fpu sections, which are guarded with kernel_fpu_begin()
+ * and kernel_fpu_end() calls, each function has a mandatory "memory"
+ * barrier.
+ */
+
+static __always_inline void fpu_cefbr(u8 f1, s32 val)
+{
+	asm volatile("cefbr	%[f1],%[val]\n"
+		     :
+		     : [f1] "I" (f1), [val] "d" (val)
+		     : "memory");
+}
+
+static __always_inline unsigned long fpu_cgebr(u8 f2, u8 mode)
+{
+	unsigned long val;
+
+	asm volatile("cgebr	%[val],%[mode],%[f2]\n"
+		     : [val] "=d" (val)
+		     : [f2] "I" (f2), [mode] "I" (mode)
+		     : "memory");
+	return val;
+}
+
+static __always_inline void fpu_debr(u8 f1, u8 f2)
+{
+	asm volatile("debr	%[f1],%[f2]\n"
+		     :
+		     : [f1] "I" (f1), [f2] "I" (f2)
+		     : "memory");
+}
+
+static __always_inline void fpu_ld(unsigned short fpr, freg_t *reg)
+{
+	instrument_read(reg, sizeof(*reg));
+	asm volatile("ld	 %[fpr],%[reg]\n"
+		     :
+		     : [fpr] "I" (fpr), [reg] "Q" (reg->ui)
+		     : "memory");
+}
+
+static __always_inline void fpu_ldgr(u8 f1, u32 val)
+{
+	asm volatile("ldgr	%[f1],%[val]\n"
+		     :
+		     : [f1] "I" (f1), [val] "d" (val)
+		     : "memory");
+}
+
+static __always_inline void fpu_lfpc(unsigned int *fpc)
+{
+	instrument_read(fpc, sizeof(*fpc));
+	asm volatile("lfpc	%[fpc]"
+		     :
+		     : [fpc] "Q" (*fpc)
+		     : "memory");
+}
+
+/**
+ * fpu_lfpc_safe - Load floating point control register safely.
+ * @fpc: new value for floating point control register
+ *
+ * Load floating point control register. This may lead to an exception,
+ * since a saved value may have been modified by user space (ptrace,
+ * signal return, kvm registers) to an invalid value. In such a case
+ * set the floating point control register to zero.
+ */
+static inline void fpu_lfpc_safe(unsigned int *fpc)
+{
+	u32 tmp;
+
+	instrument_read(fpc, sizeof(*fpc));
+	asm volatile("\n"
+		"0:	lfpc	%[fpc]\n"
+		"1:	nopr	%%r7\n"
+		".pushsection .fixup, \"ax\"\n"
+		"2:	lghi	%[tmp],0\n"
+		"	sfpc	%[tmp]\n"
+		"	jg	1b\n"
+		".popsection\n"
+		EX_TABLE(1b, 2b)
+		: [tmp] "=d" (tmp)
+		: [fpc] "Q" (*fpc)
+		: "memory");
+}
+
+static __always_inline void fpu_std(unsigned short fpr, freg_t *reg)
+{
+	instrument_write(reg, sizeof(*reg));
+	asm volatile("std	 %[fpr],%[reg]\n"
+		     : [reg] "=Q" (reg->ui)
+		     : [fpr] "I" (fpr)
+		     : "memory");
+}
+
+static __always_inline void fpu_sfpc(unsigned int fpc)
+{
+	asm volatile("sfpc	%[fpc]"
+		     :
+		     : [fpc] "d" (fpc)
+		     : "memory");
+}
+
+static __always_inline void fpu_stfpc(unsigned int *fpc)
+{
+	instrument_write(fpc, sizeof(*fpc));
+	asm volatile("stfpc	%[fpc]"
+		     : [fpc] "=Q" (*fpc)
+		     :
+		     : "memory");
+}
+
+static __always_inline void fpu_vab(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VAB	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+static __always_inline void fpu_vcksm(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VCKSM	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+static __always_inline void fpu_vesravb(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VESRAVB	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+static __always_inline void fpu_vgfmag(u8 v1, u8 v2, u8 v3, u8 v4)
+{
+	asm volatile("VGFMAG	%[v1],%[v2],%[v3],%[v4]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3), [v4] "I" (v4)
+		     : "memory");
+}
+
+static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VGFMG	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+#ifdef CONFIG_CC_IS_CLANG
+
+static __always_inline void fpu_vl(u8 v1, const void *vxr)
+{
+	instrument_read(vxr, sizeof(__vector128));
+	asm volatile("\n"
+		"	la	1,%[vxr]\n"
+		"	VL	%[v1],0,,1\n"
+		:
+		: [vxr] "R" (*(__vector128 *)vxr),
+		  [v1] "I" (v1)
+		: "memory", "1");
+}
+
+#else /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vl(u8 v1, const void *vxr)
+{
+	instrument_read(vxr, sizeof(__vector128));
+	asm volatile("VL	%[v1],%O[vxr],,%R[vxr]\n"
+		     :
+		     : [vxr] "Q" (*(__vector128 *)vxr),
+		       [v1] "I" (v1)
+		     : "memory");
+}
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vleib(u8 v, s16 val, u8 index)
+{
+	asm volatile("VLEIB	%[v],%[val],%[index]"
+		     :
+		     : [v] "I" (v), [val] "K" (val), [index] "I" (index)
+		     : "memory");
+}
+
+static __always_inline void fpu_vleig(u8 v, s16 val, u8 index)
+{
+	asm volatile("VLEIG	%[v],%[val],%[index]"
+		     :
+		     : [v] "I" (v), [val] "K" (val), [index] "I" (index)
+		     : "memory");
+}
+
+static __always_inline u64 fpu_vlgvf(u8 v, u16 index)
+{
+	u64 val;
+
+	asm volatile("VLGVF	%[val],%[v],%[index]"
+		     : [val] "=d" (val)
+		     : [v] "I" (v), [index] "L" (index)
+		     : "memory");
+	return val;
+}
+
+#ifdef CONFIG_CC_IS_CLANG
+
+static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
+{
+	unsigned int size;
+
+	size = min(index + 1, sizeof(__vector128));
+	instrument_read(vxr, size);
+	asm volatile("\n"
+		"	la	1,%[vxr]\n"
+		"	VLL	%[v1],%[index],0,1\n"
+		:
+		: [vxr] "R" (*(u8 *)vxr),
+		  [index] "d" (index),
+		  [v1] "I" (v1)
+		: "memory", "1");
+}
+
+#else /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
+{
+	unsigned int size;
+
+	size = min(index + 1, sizeof(__vector128));
+	instrument_read(vxr, size);
+	asm volatile("VLL	%[v1],%[index],%O[vxr],%R[vxr]\n"
+		     :
+		     : [vxr] "Q" (*(u8 *)vxr),
+		       [index] "d" (index),
+		       [v1] "I" (v1)
+		     : "memory");
+}
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+#ifdef CONFIG_CC_IS_CLANG
+
+#define fpu_vlm(_v1, _v3, _vxrs)					\
+({									\
+	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
+	struct {							\
+		__vector128 _v[(_v3) - (_v1) + 1];			\
+	} *_v = (void *)(_vxrs);					\
+									\
+	instrument_read(_v, size);					\
+	asm volatile("\n"						\
+		"	la	1,%[vxrs]\n"				\
+		"	VLM	%[v1],%[v3],0,1\n"			\
+		:							\
+		: [vxrs] "R" (*_v),					\
+		  [v1] "I" (_v1), [v3] "I" (_v3)			\
+		: "memory", "1");					\
+	(_v3) - (_v1) + 1;						\
+})
+
+#else /* CONFIG_CC_IS_CLANG */
+
+#define fpu_vlm(_v1, _v3, _vxrs)					\
+({									\
+	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
+	struct {							\
+		__vector128 _v[(_v3) - (_v1) + 1];			\
+	} *_v = (void *)(_vxrs);					\
+									\
+	instrument_read(_v, size);					\
+	asm volatile("VLM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
+		     :							\
+		     : [vxrs] "Q" (*_v),				\
+		       [v1] "I" (_v1), [v3] "I" (_v3)			\
+		     : "memory");					\
+	(_v3) - (_v1) + 1;						\
+})
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vlr(u8 v1, u8 v2)
+{
+	asm volatile("VLR	%[v1],%[v2]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2)
+		     : "memory");
+}
+
+static __always_inline void fpu_vlvgf(u8 v, u32 val, u16 index)
+{
+	asm volatile("VLVGF	%[v],%[val],%[index]"
+		     :
+		     : [v] "I" (v), [val] "d" (val), [index] "L" (index)
+		     : "memory");
+}
+
+static __always_inline void fpu_vn(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VN	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+static __always_inline void fpu_vperm(u8 v1, u8 v2, u8 v3, u8 v4)
+{
+	asm volatile("VPERM	%[v1],%[v2],%[v3],%[v4]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3), [v4] "I" (v4)
+		     : "memory");
+}
+
+static __always_inline void fpu_vrepib(u8 v1, s16 i2)
+{
+	asm volatile("VREPIB	%[v1],%[i2]"
+		     :
+		     : [v1] "I" (v1), [i2] "K" (i2)
+		     : "memory");
+}
+
+static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VSRLB	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+#ifdef CONFIG_CC_IS_CLANG
+
+static __always_inline void fpu_vst(u8 v1, const void *vxr)
+{
+	instrument_write(vxr, sizeof(__vector128));
+	asm volatile("\n"
+		"	la	1,%[vxr]\n"
+		"	VST	%[v1],0,,1\n"
+		: [vxr] "=R" (*(__vector128 *)vxr)
+		: [v1] "I" (v1)
+		: "memory", "1");
+}
+
+#else /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vst(u8 v1, const void *vxr)
+{
+	instrument_write(vxr, sizeof(__vector128));
+	asm volatile("VST	%[v1],%O[vxr],,%R[vxr]\n"
+		     : [vxr] "=Q" (*(__vector128 *)vxr)
+		     : [v1] "I" (v1)
+		     : "memory");
+}
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+#ifdef CONFIG_CC_IS_CLANG
+
+static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
+{
+	unsigned int size;
+
+	size = min(index + 1, sizeof(__vector128));
+	instrument_write(vxr, size);
+	asm volatile("\n"
+		"	la	1,%[vxr]\n"
+		"	VSTL	%[v1],%[index],0,1\n"
+		: [vxr] "=R" (*(u8 *)vxr)
+		: [index] "d" (index), [v1] "I" (v1)
+		: "memory", "1");
+}
+
+#else /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
+{
+	unsigned int size;
+
+	size = min(index + 1, sizeof(__vector128));
+	instrument_write(vxr, size);
+	asm volatile("VSTL	%[v1],%[index],%O[vxr],%R[vxr]\n"
+		     : [vxr] "=Q" (*(u8 *)vxr)
+		     : [index] "d" (index), [v1] "I" (v1)
+		     : "memory");
+}
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+#ifdef CONFIG_CC_IS_CLANG
+
+#define fpu_vstm(_v1, _v3, _vxrs)					\
+({									\
+	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
+	struct {							\
+		__vector128 _v[(_v3) - (_v1) + 1];			\
+	} *_v = (void *)(_vxrs);					\
+									\
+	instrument_write(_v, size);					\
+	asm volatile("\n"						\
+		"	la	1,%[vxrs]\n"				\
+		"	VSTM	%[v1],%[v3],0,1\n"			\
+		: [vxrs] "=R" (*_v)					\
+		: [v1] "I" (_v1), [v3] "I" (_v3)			\
+		: "memory", "1");					\
+	(_v3) - (_v1) + 1;						\
+})
+
+#else /* CONFIG_CC_IS_CLANG */
+
+#define fpu_vstm(_v1, _v3, _vxrs)					\
+({									\
+	unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128);	\
+	struct {							\
+		__vector128 _v[(_v3) - (_v1) + 1];			\
+	} *_v = (void *)(_vxrs);					\
+									\
+	instrument_write(_v, size);					\
+	asm volatile("VSTM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
+		     : [vxrs] "=Q" (*_v)				\
+		     : [v1] "I" (_v1), [v3] "I" (_v3)			\
+		     : "memory");					\
+	(_v3) - (_v1) + 1;						\
+})
+
+#endif /* CONFIG_CC_IS_CLANG */
+
+static __always_inline void fpu_vupllf(u8 v1, u8 v2)
+{
+	asm volatile("VUPLLF	%[v1],%[v2]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2)
+		     : "memory");
+}
+
+static __always_inline void fpu_vx(u8 v1, u8 v2, u8 v3)
+{
+	asm volatile("VX	%[v1],%[v2],%[v3]"
+		     :
+		     : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3)
+		     : "memory");
+}
+
+static __always_inline void fpu_vzero(u8 v)
+{
+	asm volatile("VZERO	%[v]"
+		     :
+		     : [v] "I" (v)
+		     : "memory");
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_S390_FPU_INSN_H */
diff --git a/arch/s390/include/asm/fpu-types.h b/arch/s390/include/asm/fpu-types.h
new file mode 100644
index 000000000000..8d58d5a95399
--- /dev/null
+++ b/arch/s390/include/asm/fpu-types.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * FPU data structures
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_S390_FPU_TYPES_H
+#define _ASM_S390_FPU_TYPES_H
+
+#include <asm/sigcontext.h>
+
+struct fpu {
+	u32 fpc;
+	__vector128 vxrs[__NUM_VXRS] __aligned(8);
+};
+
+struct kernel_fpu_hdr {
+	int	mask;
+	u32	fpc;
+};
+
+struct kernel_fpu {
+	struct kernel_fpu_hdr hdr;
+	__vector128 vxrs[] __aligned(8);
+};
+
+#define KERNEL_FPU_STRUCT(vxr_size)				\
+struct kernel_fpu_##vxr_size {					\
+	struct kernel_fpu_hdr hdr;				\
+	__vector128 vxrs[vxr_size] __aligned(8);		\
+}
+
+KERNEL_FPU_STRUCT(8);
+KERNEL_FPU_STRUCT(16);
+KERNEL_FPU_STRUCT(32);
+
+#define DECLARE_KERNEL_FPU_ONSTACK(vxr_size, name)		\
+	struct kernel_fpu_##vxr_size name __uninitialized
+
+#define DECLARE_KERNEL_FPU_ONSTACK8(name)			\
+	DECLARE_KERNEL_FPU_ONSTACK(8, name)
+
+#define DECLARE_KERNEL_FPU_ONSTACK16(name)			\
+	DECLARE_KERNEL_FPU_ONSTACK(16, name)
+
+#define DECLARE_KERNEL_FPU_ONSTACK32(name)			\
+	DECLARE_KERNEL_FPU_ONSTACK(32, name)
+
+#endif /* _ASM_S390_FPU_TYPES_H */
diff --git a/arch/s390/include/asm/fpu.h b/arch/s390/include/asm/fpu.h
new file mode 100644
index 000000000000..c84cb33913e2
--- /dev/null
+++ b/arch/s390/include/asm/fpu.h
@@ -0,0 +1,295 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * In-kernel FPU support functions
+ *
+ *
+ * Consider these guidelines before using in-kernel FPU functions:
+ *
+ *  1. Use kernel_fpu_begin() and kernel_fpu_end() to enclose all in-kernel
+ *     use of floating-point or vector registers and instructions.
+ *
+ *  2. For kernel_fpu_begin(), specify the vector register range you want to
+ *     use with the KERNEL_VXR_* constants. Consider these usage guidelines:
+ *
+ *     a) If your function typically runs in process-context, use the lower
+ *	  half of the vector registers, for example, specify KERNEL_VXR_LOW.
+ *     b) If your function typically runs in soft-irq or hard-irq context,
+ *	  prefer using the upper half of the vector registers, for example,
+ *	  specify KERNEL_VXR_HIGH.
+ *
+ *     If you adhere to these guidelines, an interrupted process context
+ *     does not require to save and restore vector registers because of
+ *     disjoint register ranges.
+ *
+ *     Also note that the __kernel_fpu_begin()/__kernel_fpu_end() functions
+ *     includes logic to save and restore up to 16 vector registers at once.
+ *
+ *  3. You can nest kernel_fpu_begin()/kernel_fpu_end() by using different
+ *     struct kernel_fpu states.  Vector registers that are in use by outer
+ *     levels are saved and restored.  You can minimize the save and restore
+ *     effort by choosing disjoint vector register ranges.
+ *
+ *  5. To use vector floating-point instructions, specify the KERNEL_FPC
+ *     flag to save and restore floating-point controls in addition to any
+ *     vector register range.
+ *
+ *  6. To use floating-point registers and instructions only, specify the
+ *     KERNEL_FPR flag.  This flag triggers a save and restore of vector
+ *     registers V0 to V15 and floating-point controls.
+ *
+ * Copyright IBM Corp. 2015
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_S390_FPU_H
+#define _ASM_S390_FPU_H
+
+#include <linux/processor.h>
+#include <linux/preempt.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <asm/sigcontext.h>
+#include <asm/fpu-types.h>
+#include <asm/fpu-insn.h>
+#include <asm/facility.h>
+
+static inline bool cpu_has_vx(void)
+{
+	return likely(test_facility(129));
+}
+
+enum {
+	KERNEL_FPC_BIT = 0,
+	KERNEL_VXR_V0V7_BIT,
+	KERNEL_VXR_V8V15_BIT,
+	KERNEL_VXR_V16V23_BIT,
+	KERNEL_VXR_V24V31_BIT,
+};
+
+#define KERNEL_FPC		BIT(KERNEL_FPC_BIT)
+#define KERNEL_VXR_V0V7		BIT(KERNEL_VXR_V0V7_BIT)
+#define KERNEL_VXR_V8V15	BIT(KERNEL_VXR_V8V15_BIT)
+#define KERNEL_VXR_V16V23	BIT(KERNEL_VXR_V16V23_BIT)
+#define KERNEL_VXR_V24V31	BIT(KERNEL_VXR_V24V31_BIT)
+
+#define KERNEL_VXR_LOW		(KERNEL_VXR_V0V7   | KERNEL_VXR_V8V15)
+#define KERNEL_VXR_MID		(KERNEL_VXR_V8V15  | KERNEL_VXR_V16V23)
+#define KERNEL_VXR_HIGH		(KERNEL_VXR_V16V23 | KERNEL_VXR_V24V31)
+
+#define KERNEL_VXR		(KERNEL_VXR_LOW	   | KERNEL_VXR_HIGH)
+#define KERNEL_FPR		(KERNEL_FPC	   | KERNEL_VXR_LOW)
+
+void load_fpu_state(struct fpu *state, int flags);
+void save_fpu_state(struct fpu *state, int flags);
+void __kernel_fpu_begin(struct kernel_fpu *state, int flags);
+void __kernel_fpu_end(struct kernel_fpu *state, int flags);
+
+static __always_inline void save_vx_regs(__vector128 *vxrs)
+{
+	fpu_vstm(0, 15, &vxrs[0]);
+	fpu_vstm(16, 31, &vxrs[16]);
+}
+
+static __always_inline void load_vx_regs(__vector128 *vxrs)
+{
+	fpu_vlm(0, 15, &vxrs[0]);
+	fpu_vlm(16, 31, &vxrs[16]);
+}
+
+static __always_inline void __save_fp_regs(freg_t *fprs, unsigned int offset)
+{
+	fpu_std(0, &fprs[0 * offset]);
+	fpu_std(1, &fprs[1 * offset]);
+	fpu_std(2, &fprs[2 * offset]);
+	fpu_std(3, &fprs[3 * offset]);
+	fpu_std(4, &fprs[4 * offset]);
+	fpu_std(5, &fprs[5 * offset]);
+	fpu_std(6, &fprs[6 * offset]);
+	fpu_std(7, &fprs[7 * offset]);
+	fpu_std(8, &fprs[8 * offset]);
+	fpu_std(9, &fprs[9 * offset]);
+	fpu_std(10, &fprs[10 * offset]);
+	fpu_std(11, &fprs[11 * offset]);
+	fpu_std(12, &fprs[12 * offset]);
+	fpu_std(13, &fprs[13 * offset]);
+	fpu_std(14, &fprs[14 * offset]);
+	fpu_std(15, &fprs[15 * offset]);
+}
+
+static __always_inline void __load_fp_regs(freg_t *fprs, unsigned int offset)
+{
+	fpu_ld(0, &fprs[0 * offset]);
+	fpu_ld(1, &fprs[1 * offset]);
+	fpu_ld(2, &fprs[2 * offset]);
+	fpu_ld(3, &fprs[3 * offset]);
+	fpu_ld(4, &fprs[4 * offset]);
+	fpu_ld(5, &fprs[5 * offset]);
+	fpu_ld(6, &fprs[6 * offset]);
+	fpu_ld(7, &fprs[7 * offset]);
+	fpu_ld(8, &fprs[8 * offset]);
+	fpu_ld(9, &fprs[9 * offset]);
+	fpu_ld(10, &fprs[10 * offset]);
+	fpu_ld(11, &fprs[11 * offset]);
+	fpu_ld(12, &fprs[12 * offset]);
+	fpu_ld(13, &fprs[13 * offset]);
+	fpu_ld(14, &fprs[14 * offset]);
+	fpu_ld(15, &fprs[15 * offset]);
+}
+
+static __always_inline void save_fp_regs(freg_t *fprs)
+{
+	__save_fp_regs(fprs, sizeof(freg_t) / sizeof(freg_t));
+}
+
+static __always_inline void load_fp_regs(freg_t *fprs)
+{
+	__load_fp_regs(fprs, sizeof(freg_t) / sizeof(freg_t));
+}
+
+static __always_inline void save_fp_regs_vx(__vector128 *vxrs)
+{
+	freg_t *fprs = (freg_t *)&vxrs[0].high;
+
+	__save_fp_regs(fprs, sizeof(__vector128) / sizeof(freg_t));
+}
+
+static __always_inline void load_fp_regs_vx(__vector128 *vxrs)
+{
+	freg_t *fprs = (freg_t *)&vxrs[0].high;
+
+	__load_fp_regs(fprs, sizeof(__vector128) / sizeof(freg_t));
+}
+
+static inline void load_user_fpu_regs(void)
+{
+	struct thread_struct *thread = &current->thread;
+
+	if (!thread->ufpu_flags)
+		return;
+	load_fpu_state(&thread->ufpu, thread->ufpu_flags);
+	thread->ufpu_flags = 0;
+}
+
+static __always_inline void __save_user_fpu_regs(struct thread_struct *thread, int flags)
+{
+	save_fpu_state(&thread->ufpu, flags);
+	__atomic_or(flags, &thread->ufpu_flags);
+}
+
+static inline void save_user_fpu_regs(void)
+{
+	struct thread_struct *thread = &current->thread;
+	int mask, flags;
+
+	mask = __atomic_or(KERNEL_FPC | KERNEL_VXR, &thread->kfpu_flags);
+	flags = ~READ_ONCE(thread->ufpu_flags) & (KERNEL_FPC | KERNEL_VXR);
+	if (flags)
+		__save_user_fpu_regs(thread, flags);
+	barrier();
+	WRITE_ONCE(thread->kfpu_flags, mask);
+}
+
+static __always_inline void _kernel_fpu_begin(struct kernel_fpu *state, int flags)
+{
+	struct thread_struct *thread = &current->thread;
+	int mask, uflags;
+
+	mask = __atomic_or(flags, &thread->kfpu_flags);
+	state->hdr.mask = mask;
+	uflags = READ_ONCE(thread->ufpu_flags);
+	if ((uflags & flags) != flags)
+		__save_user_fpu_regs(thread, ~uflags & flags);
+	if (mask & flags)
+		__kernel_fpu_begin(state, flags);
+}
+
+static __always_inline void _kernel_fpu_end(struct kernel_fpu *state, int flags)
+{
+	int mask = state->hdr.mask;
+
+	if (mask & flags)
+		__kernel_fpu_end(state, flags);
+	barrier();
+	WRITE_ONCE(current->thread.kfpu_flags, mask);
+}
+
+void __kernel_fpu_invalid_size(void);
+
+static __always_inline void kernel_fpu_check_size(int flags, unsigned int size)
+{
+	unsigned int cnt = 0;
+
+	if (flags & KERNEL_VXR_V0V7)
+		cnt += 8;
+	if (flags & KERNEL_VXR_V8V15)
+		cnt += 8;
+	if (flags & KERNEL_VXR_V16V23)
+		cnt += 8;
+	if (flags & KERNEL_VXR_V24V31)
+		cnt += 8;
+	if (cnt != size)
+		__kernel_fpu_invalid_size();
+}
+
+#define kernel_fpu_begin(state, flags)					\
+{									\
+	typeof(state) s = (state);					\
+	int _flags = (flags);						\
+									\
+	kernel_fpu_check_size(_flags, ARRAY_SIZE(s->vxrs));		\
+	_kernel_fpu_begin((struct kernel_fpu *)s, _flags);		\
+}
+
+#define kernel_fpu_end(state, flags)					\
+{									\
+	typeof(state) s = (state);					\
+	int _flags = (flags);						\
+									\
+	kernel_fpu_check_size(_flags, ARRAY_SIZE(s->vxrs));		\
+	_kernel_fpu_end((struct kernel_fpu *)s, _flags);		\
+}
+
+static inline void save_kernel_fpu_regs(struct thread_struct *thread)
+{
+	if (!thread->kfpu_flags)
+		return;
+	save_fpu_state(&thread->kfpu, thread->kfpu_flags);
+}
+
+static inline void restore_kernel_fpu_regs(struct thread_struct *thread)
+{
+	if (!thread->kfpu_flags)
+		return;
+	load_fpu_state(&thread->kfpu, thread->kfpu_flags);
+}
+
+static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		fprs[i].ui = vxrs[i].high;
+}
+
+static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
+{
+	int i;
+
+	for (i = 0; i < __NUM_FPRS; i++)
+		vxrs[i].high = fprs[i].ui;
+}
+
+static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	fpregs->pad = 0;
+	fpregs->fpc = fpu->fpc;
+	convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
+}
+
+static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
+{
+	fpu->fpc = fpregs->fpc;
+	convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
+}
+
+#endif /* _ASM_S390_FPU_H */
diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h
deleted file mode 100644
index d6ca8bc6ca68..000000000000
--- a/arch/s390/include/asm/fpu/api.h
+++ /dev/null
@@ -1,126 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * In-kernel FPU support functions
- *
- *
- * Consider these guidelines before using in-kernel FPU functions:
- *
- *  1. Use kernel_fpu_begin() and kernel_fpu_end() to enclose all in-kernel
- *     use of floating-point or vector registers and instructions.
- *
- *  2. For kernel_fpu_begin(), specify the vector register range you want to
- *     use with the KERNEL_VXR_* constants. Consider these usage guidelines:
- *
- *     a) If your function typically runs in process-context, use the lower
- *	  half of the vector registers, for example, specify KERNEL_VXR_LOW.
- *     b) If your function typically runs in soft-irq or hard-irq context,
- *	  prefer using the upper half of the vector registers, for example,
- *	  specify KERNEL_VXR_HIGH.
- *
- *     If you adhere to these guidelines, an interrupted process context
- *     does not require to save and restore vector registers because of
- *     disjoint register ranges.
- *
- *     Also note that the __kernel_fpu_begin()/__kernel_fpu_end() functions
- *     includes logic to save and restore up to 16 vector registers at once.
- *
- *  3. You can nest kernel_fpu_begin()/kernel_fpu_end() by using different
- *     struct kernel_fpu states.  Vector registers that are in use by outer
- *     levels are saved and restored.  You can minimize the save and restore
- *     effort by choosing disjoint vector register ranges.
- *
- *  5. To use vector floating-point instructions, specify the KERNEL_FPC
- *     flag to save and restore floating-point controls in addition to any
- *     vector register range.
- *
- *  6. To use floating-point registers and instructions only, specify the
- *     KERNEL_FPR flag.  This flag triggers a save and restore of vector
- *     registers V0 to V15 and floating-point controls.
- *
- * Copyright IBM Corp. 2015
- * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- */
-
-#ifndef _ASM_S390_FPU_API_H
-#define _ASM_S390_FPU_API_H
-
-#include <linux/preempt.h>
-#include <asm/asm-extable.h>
-#include <asm/fpu/internal.h>
-
-void save_fpu_regs(void);
-void load_fpu_regs(void);
-void __load_fpu_regs(void);
-
-/**
- * sfpc_safe - Set floating point control register safely.
- * @fpc: new value for floating point control register
- *
- * Set floating point control register. This may lead to an exception,
- * since a saved value may have been modified by user space (ptrace,
- * signal return, kvm registers) to an invalid value. In such a case
- * set the floating point control register to zero.
- */
-static inline void sfpc_safe(u32 fpc)
-{
-	asm volatile("\n"
-		"0:	sfpc	%[fpc]\n"
-		"1:	nopr	%%r7\n"
-		".pushsection .fixup, \"ax\"\n"
-		"2:	lghi	%[fpc],0\n"
-		"	jg	0b\n"
-		".popsection\n"
-		EX_TABLE(1b, 2b)
-		: [fpc] "+d" (fpc)
-		: : "memory");
-}
-
-#define KERNEL_FPC		1
-#define KERNEL_VXR_V0V7		2
-#define KERNEL_VXR_V8V15	4
-#define KERNEL_VXR_V16V23	8
-#define KERNEL_VXR_V24V31	16
-
-#define KERNEL_VXR_LOW		(KERNEL_VXR_V0V7|KERNEL_VXR_V8V15)
-#define KERNEL_VXR_MID		(KERNEL_VXR_V8V15|KERNEL_VXR_V16V23)
-#define KERNEL_VXR_HIGH		(KERNEL_VXR_V16V23|KERNEL_VXR_V24V31)
-
-#define KERNEL_VXR		(KERNEL_VXR_LOW|KERNEL_VXR_HIGH)
-#define KERNEL_FPR		(KERNEL_FPC|KERNEL_VXR_LOW)
-
-struct kernel_fpu;
-
-/*
- * Note the functions below must be called with preemption disabled.
- * Do not enable preemption before calling __kernel_fpu_end() to prevent
- * an corruption of an existing kernel FPU state.
- *
- * Prefer using the kernel_fpu_begin()/kernel_fpu_end() pair of functions.
- */
-void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags);
-void __kernel_fpu_end(struct kernel_fpu *state, u32 flags);
-
-
-static inline void kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
-{
-	preempt_disable();
-	state->mask = S390_lowcore.fpu_flags;
-	if (!test_cpu_flag(CIF_FPU))
-		/* Save user space FPU state and register contents */
-		save_fpu_regs();
-	else if (state->mask & flags)
-		/* Save FPU/vector register in-use by the kernel */
-		__kernel_fpu_begin(state, flags);
-	S390_lowcore.fpu_flags |= flags;
-}
-
-static inline void kernel_fpu_end(struct kernel_fpu *state, u32 flags)
-{
-	S390_lowcore.fpu_flags = state->mask;
-	if (state->mask & flags)
-		/* Restore FPU/vector register in-use by the kernel */
-		__kernel_fpu_end(state, flags);
-	preempt_enable();
-}
-
-#endif /* _ASM_S390_FPU_API_H */
diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
deleted file mode 100644
index d511c4cf5afb..000000000000
--- a/arch/s390/include/asm/fpu/internal.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * FPU state and register content conversion primitives
- *
- * Copyright IBM Corp. 2015
- * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- */
-
-#ifndef _ASM_S390_FPU_INTERNAL_H
-#define _ASM_S390_FPU_INTERNAL_H
-
-#include <linux/string.h>
-#include <asm/facility.h>
-#include <asm/fpu/types.h>
-
-static inline bool cpu_has_vx(void)
-{
-	return likely(test_facility(129));
-}
-
-static inline void save_vx_regs(__vector128 *vxrs)
-{
-	asm volatile(
-		"	la	1,%0\n"
-		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
-		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
-		: "=Q" (*(struct vx_array *) vxrs) : : "1");
-}
-
-static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs)
-{
-	int i;
-
-	for (i = 0; i < __NUM_FPRS; i++)
-		fprs[i].ui = vxrs[i].high;
-}
-
-static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
-{
-	int i;
-
-	for (i = 0; i < __NUM_FPRS; i++)
-		vxrs[i].high = fprs[i].ui;
-}
-
-static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
-{
-	fpregs->pad = 0;
-	fpregs->fpc = fpu->fpc;
-	if (cpu_has_vx())
-		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
-	else
-		memcpy((freg_t *)&fpregs->fprs, fpu->fprs,
-		       sizeof(fpregs->fprs));
-}
-
-static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
-{
-	fpu->fpc = fpregs->fpc;
-	if (cpu_has_vx())
-		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
-	else
-		memcpy(fpu->fprs, (freg_t *)&fpregs->fprs,
-		       sizeof(fpregs->fprs));
-}
-
-#endif /* _ASM_S390_FPU_INTERNAL_H */
diff --git a/arch/s390/include/asm/fpu/types.h b/arch/s390/include/asm/fpu/types.h
deleted file mode 100644
index d889e9436865..000000000000
--- a/arch/s390/include/asm/fpu/types.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * FPU data structures
- *
- * Copyright IBM Corp. 2015
- * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
- */
-
-#ifndef _ASM_S390_FPU_TYPES_H
-#define _ASM_S390_FPU_TYPES_H
-
-#include <asm/sigcontext.h>
-
-struct fpu {
-	__u32 fpc;		/* Floating-point control */
-	void *regs;		/* Pointer to the current save area */
-	union {
-		/* Floating-point register save area */
-		freg_t fprs[__NUM_FPRS];
-		/* Vector register save area */
-		__vector128 vxrs[__NUM_VXRS];
-	};
-};
-
-/* VX array structure for address operand constraints in inline assemblies */
-struct vx_array { __vector128 _[__NUM_VXRS]; };
-
-/* In-kernel FPU state structure */
-struct kernel_fpu {
-	u32	    mask;
-	u32	    fpc;
-	union {
-		freg_t fprs[__NUM_FPRS];
-		__vector128 vxrs[__NUM_VXRS];
-	};
-};
-
-#endif /* _ASM_S390_FPU_TYPES_H */
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 895f774bbcc5..bf78cf381dfc 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -25,7 +25,7 @@
  */
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 0,%l[label]\n"
+	asm goto("0:	brcl 0,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
@@ -39,7 +39,7 @@ label:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 15,%l[label]\n"
+	asm goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 52664105a473..95990461888f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -23,7 +23,7 @@
 #include <linux/mmu_notifier.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 #include <asm/isc.h>
 #include <asm/guarded_storage.h>
 
@@ -743,7 +743,6 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *vsie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct gs_cb      *host_gscb;
-	struct fpu	  host_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;
@@ -765,6 +764,8 @@ struct kvm_vcpu_arch {
 	__u64 cputm_start;
 	bool gs_enabled;
 	bool skey_enabled;
+	/* Indicator if the access registers have been loaded from guest */
+	bool acrs_loaded;
 	struct kvm_s390_pv_vcpu pv;
 	union diag318_info diag318_info;
 };
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5dc1b6345006..8c5f16857539 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -157,7 +157,7 @@ struct lowcore {
 	__s32	preempt_count;			/* 0x03a8 */
 	__u32	spinlock_lockval;		/* 0x03ac */
 	__u32	spinlock_index;			/* 0x03b0 */
-	__u32	fpu_flags;			/* 0x03b4 */
+	__u8	pad_0x03b4[0x03b8-0x03b4];	/* 0x03b4 */
 	__u64	percpu_offset;			/* 0x03b8 */
 	__u8	pad_0x03c0[0x03c8-0x03c0];	/* 0x03c0 */
 	__u64	machine_flags;			/* 0x03c8 */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 73b9c3bf377f..ded9548d11d9 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -11,7 +11,7 @@
 #include <linux/const.h>
 #include <asm/types.h>
 
-#define _PAGE_SHIFT	12
+#define _PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define _PAGE_SIZE	(_AC(1, UL) << _PAGE_SHIFT)
 #define _PAGE_MASK	(~(_PAGE_SIZE - 1))
 
diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h
index 7d1888e3dee6..3f609565734b 100644
--- a/arch/s390/include/asm/pai.h
+++ b/arch/s390/include/asm/pai.h
@@ -16,7 +16,7 @@ struct qpaci_info_block {
 	u64 header;
 	struct {
 		u64 : 8;
-		u64 num_cc : 8;	/* # of supported crypto counters */
+		u64 num_cc : 8;		/* # of supported crypto counters */
 		u64 : 9;
 		u64 num_nnpa : 7;	/* # of supported NNPA counters */
 		u64 : 32;
@@ -81,4 +81,5 @@ enum paievt_mode {
 	PAI_MODE_COUNTING,
 };
 
+#define PAI_SAVE_AREA(x)	((x)->hw.event_base)
 #endif
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index e91cd6bbc330..30820a649e6e 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -122,6 +122,7 @@ struct zpci_dev {
 	struct rcu_head rcu;
 	struct hotplug_slot hotplug_slot;
 
+	struct mutex state_lock;	/* protect state changes */
 	enum zpci_state state;
 	u32		fid;		/* function ID, used by sclp */
 	u32		fh;		/* function handle, used by insn's */
@@ -142,7 +143,6 @@ struct zpci_dev {
 	u8		reserved	: 2;
 	unsigned int	devfn;		/* DEVFN part of the RID*/
 
-	struct mutex lock;
 	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
 	u32 uid;			/* user defined id */
 	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
@@ -170,6 +170,7 @@ struct zpci_dev {
 	u64		dma_mask;	/* DMA address space mask */
 
 	/* Function measurement block */
+	struct mutex fmb_lock;
 	struct zpci_fmb *fmb;
 	u16		fmb_update;	/* update interval */
 	u16		fmb_length;
diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h
index 9e41a74fce9a..e747b067f8db 100644
--- a/arch/s390/include/asm/physmem_info.h
+++ b/arch/s390/include/asm/physmem_info.h
@@ -22,6 +22,7 @@ enum reserved_range_type {
 	RR_DECOMPRESSOR,
 	RR_INITRD,
 	RR_VMLINUX,
+	RR_RELOC,
 	RR_AMODE31,
 	RR_IPLREPORT,
 	RR_CERT_COMP_LIST,
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index c0b6e74d899a..7cf00cf8fb0b 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -15,13 +15,11 @@
 #include <linux/bits.h>
 
 #define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
-#define CIF_FPU			3	/* restore FPU registers */
 #define CIF_ENABLED_WAIT	5	/* in enabled wait state */
 #define CIF_MCCK_GUEST		6	/* machine check happening in guest */
 #define CIF_DEDICATED_CPU	7	/* this CPU is dedicated */
 
 #define _CIF_NOHZ_DELAY		BIT(CIF_NOHZ_DELAY)
-#define _CIF_FPU		BIT(CIF_FPU)
 #define _CIF_ENABLED_WAIT	BIT(CIF_ENABLED_WAIT)
 #define _CIF_MCCK_GUEST		BIT(CIF_MCCK_GUEST)
 #define _CIF_DEDICATED_CPU	BIT(CIF_DEDICATED_CPU)
@@ -33,13 +31,12 @@
 #include <linux/cpumask.h>
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
+#include <asm/fpu-types.h>
 #include <asm/cpu.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
-#include <asm/fpu/types.h>
-#include <asm/fpu/internal.h>
 #include <asm/irqflags.h>
 
 typedef long (*sys_call_ptr_t)(struct pt_regs *regs);
@@ -169,6 +166,8 @@ struct thread_struct {
 	unsigned int gmap_write_flag;		/* gmap fault write indication */
 	unsigned int gmap_int_code;		/* int code of last gmap fault */
 	unsigned int gmap_pfault;		/* signal of a pending guest pfault */
+	int ufpu_flags;				/* user fpu flags */
+	int kfpu_flags;				/* kernel fpu flags */
 
 	/* Per-thread information related to debugging */
 	struct per_regs per_user;		/* User specified PER registers */
@@ -184,7 +183,8 @@ struct thread_struct {
 	struct gs_cb *gs_cb;			/* Current guarded storage cb */
 	struct gs_cb *gs_bc_cb;			/* Broadcast guarded storage cb */
 	struct pgm_tdb trap_tdb;		/* Transaction abort diagnose block */
-	struct fpu fpu;				/* FP and VX register save area */
+	struct fpu ufpu;			/* User FP and VX register save area */
+	struct fpu kfpu;			/* Kernel FP and VX register save area */
 };
 
 /* Flag to disable transactions. */
@@ -203,7 +203,6 @@ typedef struct thread_struct thread_struct;
 
 #define INIT_THREAD {							\
 	.ksp = sizeof(init_stack) + (unsigned long) &init_stack,	\
-	.fpu.regs = (void *) init_task.thread.fpu.fprs,			\
 	.last_break = 1,						\
 }
 
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index d28bf8fb2799..788bc4467445 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -203,6 +203,10 @@ static inline int test_and_clear_pt_regs_flag(struct pt_regs *regs, int flag)
 	return ret;
 }
 
+struct task_struct;
+
+void update_cr_regs(struct task_struct *task);
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index 31ec4f545e03..433fde85b14e 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -4,7 +4,6 @@
 
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
-#include <asm/switch_to.h>
 
 struct stack_frame_user {
 	unsigned long back_chain;
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
deleted file mode 100644
index c61b2cc1a8a8..000000000000
--- a/arch/s390/include/asm/switch_to.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 1999, 2009
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#ifndef __ASM_SWITCH_TO_H
-#define __ASM_SWITCH_TO_H
-
-#include <linux/thread_info.h>
-#include <asm/fpu/api.h>
-#include <asm/ptrace.h>
-#include <asm/guarded_storage.h>
-
-extern struct task_struct *__switch_to(void *, void *);
-extern void update_cr_regs(struct task_struct *task);
-
-static inline void save_access_regs(unsigned int *acrs)
-{
-	typedef struct { int _[NUM_ACRS]; } acrstype;
-
-	asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs));
-}
-
-static inline void restore_access_regs(unsigned int *acrs)
-{
-	typedef struct { int _[NUM_ACRS]; } acrstype;
-
-	asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs));
-}
-
-#define switch_to(prev, next, last) do {				\
-	/* save_fpu_regs() sets the CIF_FPU flag, which enforces	\
-	 * a restore of the floating point / vector registers as	\
-	 * soon as the next task returns to user space			\
-	 */								\
-	save_fpu_regs();						\
-	save_access_regs(&prev->thread.acrs[0]);			\
-	save_ri_cb(prev->thread.ri_cb);					\
-	save_gs_cb(prev->thread.gs_cb);					\
-	update_cr_regs(next);						\
-	restore_access_regs(&next->thread.acrs[0]);			\
-	restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);		\
-	restore_gs_cb(next->thread.gs_cb);				\
-	prev = __switch_to(prev, next);					\
-} while (0)
-
-#endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h
index 73ee89142666..0e2b40ef69b0 100644
--- a/arch/s390/include/asm/vdso/data.h
+++ b/arch/s390/include/asm/vdso/data.h
@@ -3,7 +3,6 @@
 #define __S390_ASM_VDSO_DATA_H
 
 #include <linux/types.h>
-#include <vdso/datapage.h>
 
 struct arch_vdso_data {
 	__s64 tod_steering_delta;
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h
deleted file mode 100644
index 8c188f1c6d27..000000000000
--- a/arch/s390/include/asm/vx-insn.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Support for Vector Instructions
- *
- * This wrapper header file allows to use the vector instruction macros in
- * both assembler files as well as in inline assemblies in C files.
- */
-
-#ifndef __ASM_S390_VX_INSN_H
-#define __ASM_S390_VX_INSN_H
-
-#include <asm/vx-insn-asm.h>
-
-#ifndef __ASSEMBLY__
-
-asm(".include \"asm/vx-insn-asm.h\"\n");
-
-#endif /* __ASSEMBLY__ */
-#endif	/* __ASM_S390_VX_INSN_H */
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index 56254fa06f99..4f2669030220 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -166,5 +166,6 @@ int populate_cache_leaves(unsigned int cpu)
 			ci_leaf_init(this_leaf++, pvt, ctype, level, cpu);
 		}
 	}
+	this_cpu_ci->cpu_map_populated = true;
 	return 0;
 }
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index f8fc6c25d051..1942e2a9f8db 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -24,12 +24,12 @@
 #include <linux/tty.h>
 #include <linux/personality.h>
 #include <linux/binfmts.h>
+#include <asm/access-regs.h>
 #include <asm/ucontext.h>
 #include <linux/uaccess.h>
 #include <asm/lowcore.h>
-#include <asm/switch_to.h>
 #include <asm/vdso.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 #include "compat_linux.h"
 #include "compat_ptrace.h"
 #include "entry.h"
@@ -56,7 +56,7 @@ typedef struct
 static void store_sigregs(void)
 {
 	save_access_regs(current->thread.acrs);
-	save_fpu_regs();
+	save_user_fpu_regs();
 }
 
 /* Load registers after signal return */
@@ -79,7 +79,7 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	fpregs_store((_s390_fp_regs *) &user_sregs.fpregs, &current->thread.fpu);
+	fpregs_store((_s390_fp_regs *) &user_sregs.fpregs, &current->thread.ufpu);
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
 		return -EFAULT;
 	return 0;
@@ -113,7 +113,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	fpregs_load((_s390_fp_regs *) &user_sregs.fpregs, &current->thread.fpu);
+	fpregs_load((_s390_fp_regs *)&user_sregs.fpregs, &current->thread.ufpu);
 
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
@@ -136,11 +136,11 @@ static int save_sigregs_ext32(struct pt_regs *regs,
 	/* Save vector registers to signal stack */
 	if (cpu_has_vx()) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			vxrs[i] = current->thread.fpu.vxrs[i].low;
+			vxrs[i] = current->thread.ufpu.vxrs[i].low;
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
 				   sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_to_user(&sregs_ext->vxrs_high,
-				   current->thread.fpu.vxrs + __NUM_VXRS_LOW,
+				   current->thread.ufpu.vxrs + __NUM_VXRS_LOW,
 				   sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 	}
@@ -165,12 +165,12 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 	if (cpu_has_vx()) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
-		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
+		    __copy_from_user(current->thread.ufpu.vxrs + __NUM_VXRS_LOW,
 				     &sregs_ext->vxrs_high,
 				     sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			current->thread.fpu.vxrs[i].low = vxrs[i];
+			current->thread.ufpu.vxrs[i].low = vxrs[i];
 	}
 	return 0;
 }
@@ -184,7 +184,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 	if (get_compat_sigset(&set, (compat_sigset_t __user *)frame->sc.oldmask))
 		goto badframe;
 	set_current_blocked(&set);
-	save_fpu_regs();
+	save_user_fpu_regs();
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
 	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
@@ -207,7 +207,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 	set_current_blocked(&set);
 	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
-	save_fpu_regs();
+	save_user_fpu_regs();
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 5c46c2659305..d09ebb6f5262 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -22,7 +22,7 @@
 #include <asm/ipl.h>
 #include <asm/sclp.h>
 #include <asm/maccess.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 
 #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 92fdc35f028c..8dee9aa0ec95 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -147,11 +147,40 @@ void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr)
 EXPORT_SYMBOL(diag_stat_inc_norecursion);
 
 /*
+ * Diagnose 0c: Pseudo Timer
+ */
+void diag0c(struct hypfs_diag0c_entry *data)
+{
+	diag_stat_inc(DIAG_STAT_X00C);
+	diag_amode31_ops.diag0c(virt_to_phys(data));
+}
+
+/*
  * Diagnose 14: Input spool file manipulation
+ *
+ * The subcode parameter determines the type of the first parameter rx.
+ * Currently used are the following 3 subcommands:
+ * 0x0:   Read the Next Spool File Buffer (Data Record)
+ * 0x28:  Position a Spool File to the Designated Record
+ * 0xfff: Retrieve Next File Descriptor
+ *
+ * For subcommands 0x0 and 0xfff, the value of the first parameter is
+ * a virtual address of a memory buffer and needs virtual to physical
+ * address translation. For other subcommands the rx parameter is not
+ * a virtual address.
  */
 int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
 {
 	diag_stat_inc(DIAG_STAT_X014);
+	switch (subcode) {
+	case 0x0:
+	case 0xfff:
+		rx = virt_to_phys((void *)rx);
+		break;
+	default:
+		/* Do nothing */
+		break;
+	}
 	return diag_amode31_ops.diag14(rx, ry1, subcode);
 }
 EXPORT_SYMBOL(diag14);
@@ -265,6 +294,6 @@ EXPORT_SYMBOL(diag224);
 int diag26c(void *req, void *resp, enum diag26c_sc subcode)
 {
 	diag_stat_inc(DIAG_STAT_X26C);
-	return diag_amode31_ops.diag26c(req, resp, subcode);
+	return diag_amode31_ops.diag26c(virt_to_phys(req), virt_to_phys(resp), subcode);
 }
 EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2345ea332b97..c666271433fb 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -19,8 +19,10 @@
 #include <linux/kernel.h>
 #include <asm/asm-extable.h>
 #include <linux/memblock.h>
+#include <asm/access-regs.h>
 #include <asm/diag.h>
 #include <asm/ebcdic.h>
+#include <asm/fpu.h>
 #include <asm/ipl.h>
 #include <asm/lowcore.h>
 #include <asm/processor.h>
@@ -31,7 +33,6 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
-#include <asm/switch_to.h>
 #include "entry.h"
 
 #define decompressor_handled_param(param)			\
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 49a11f6dd7ae..fc5277eab554 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -24,7 +24,7 @@
 #include <asm/page.h>
 #include <asm/sigp.h>
 #include <asm/irq.h>
-#include <asm/vx-insn.h>
+#include <asm/fpu-insn.h>
 #include <asm/setup.h>
 #include <asm/nmi.h>
 #include <asm/nospec-insn.h>
@@ -171,13 +171,13 @@ _LPP_OFFSET	= __LC_LPP
 	nop	0
 
 /*
- * Scheduler resume function, called by switch_to
- *  gpr2 = (task_struct *) prev
- *  gpr3 = (task_struct *) next
+ * Scheduler resume function, called by __switch_to
+ *  gpr2 = (task_struct *)prev
+ *  gpr3 = (task_struct *)next
  * Returns:
  *  gpr2 = prev
  */
-SYM_FUNC_START(__switch_to)
+SYM_FUNC_START(__switch_to_asm)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
 	lghi	%r4,__TASK_stack
 	lghi	%r1,__TASK_thread
@@ -193,7 +193,7 @@ SYM_FUNC_START(__switch_to)
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40
 	BR_EX	%r14
-SYM_FUNC_END(__switch_to)
+SYM_FUNC_END(__switch_to_asm)
 
 #if IS_ENABLED(CONFIG_KVM)
 /*
@@ -220,8 +220,6 @@ SYM_FUNC_START(__sie64a)
 	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
 	tm	__SIE_PROG20+3(%r14),3		# last exit...
 	jnz	.Lsie_skip
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	jo	.Lsie_skip			# exit if fp/vx regs changed
 	lg	%r14,__SF_SIE_CONTROL_PHYS(%r15)	# get sie block phys addr
 	BPEXIT	__SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
 .Lsie_entry:
@@ -489,16 +487,11 @@ SYM_FUNC_END(psw_idle)
  */
 SYM_CODE_START(mcck_int_handler)
 	BPOFF
-	la	%r1,4095		# validate r1
-	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# validate cpu timer
-	LBEAR	__LC_LAST_BREAK_SAVE_AREA-4095(%r1)		# validate bear
-	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA		# validate gprs
 	lmg	%r8,%r9,__LC_MCK_OLD_PSW
 	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE
 	jo	.Lmcck_panic		# yes -> rest of mcck code invalid
 	TSTMSK	__LC_MCCK_CODE,MCCK_CODE_CR_VALID
 	jno	.Lmcck_panic		# control registers invalid -> panic
-	lctlg	%c0,%c15,__LC_CREGS_SAVE_AREA		# validate ctl regs
 	ptlb
 	lghi	%r14,__LC_CPU_TIMER_SAVE_AREA
 	mvc	__LC_MCCK_ENTER_TIMER(8),0(%r14)
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 9f41853f36b9..21969520f947 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -19,6 +19,7 @@ void mcck_int_handler(void);
 void restart_int_handler(void);
 void early_pgm_check_handler(void);
 
+struct task_struct *__switch_to_asm(struct task_struct *prev, struct task_struct *next);
 void __ret_from_fork(struct task_struct *prev, struct pt_regs *regs);
 void __do_pgm_check(struct pt_regs *regs);
 void __do_syscall(struct pt_regs *regs, int per_trap);
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index a4f3449cc814..fa90bbdc5ef9 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -8,256 +8,186 @@
 #include <linux/kernel.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
-#include <asm/fpu/types.h>
-#include <asm/fpu/api.h>
-#include <asm/vx-insn.h>
+#include <asm/fpu.h>
 
-void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
+void __kernel_fpu_begin(struct kernel_fpu *state, int flags)
 {
+	__vector128 *vxrs = state->vxrs;
+	int mask;
+
 	/*
 	 * Limit the save to the FPU/vector registers already
-	 * in use by the previous context
+	 * in use by the previous context.
 	 */
-	flags &= state->mask;
-
+	flags &= state->hdr.mask;
 	if (flags & KERNEL_FPC)
-		/* Save floating point control */
-		asm volatile("stfpc %0" : "=Q" (state->fpc));
-
+		fpu_stfpc(&state->hdr.fpc);
 	if (!cpu_has_vx()) {
-		if (flags & KERNEL_VXR_V0V7) {
-			/* Save floating-point registers */
-			asm volatile("std 0,%0" : "=Q" (state->fprs[0]));
-			asm volatile("std 1,%0" : "=Q" (state->fprs[1]));
-			asm volatile("std 2,%0" : "=Q" (state->fprs[2]));
-			asm volatile("std 3,%0" : "=Q" (state->fprs[3]));
-			asm volatile("std 4,%0" : "=Q" (state->fprs[4]));
-			asm volatile("std 5,%0" : "=Q" (state->fprs[5]));
-			asm volatile("std 6,%0" : "=Q" (state->fprs[6]));
-			asm volatile("std 7,%0" : "=Q" (state->fprs[7]));
-			asm volatile("std 8,%0" : "=Q" (state->fprs[8]));
-			asm volatile("std 9,%0" : "=Q" (state->fprs[9]));
-			asm volatile("std 10,%0" : "=Q" (state->fprs[10]));
-			asm volatile("std 11,%0" : "=Q" (state->fprs[11]));
-			asm volatile("std 12,%0" : "=Q" (state->fprs[12]));
-			asm volatile("std 13,%0" : "=Q" (state->fprs[13]));
-			asm volatile("std 14,%0" : "=Q" (state->fprs[14]));
-			asm volatile("std 15,%0" : "=Q" (state->fprs[15]));
-		}
+		if (flags & KERNEL_VXR_LOW)
+			save_fp_regs_vx(vxrs);
 		return;
 	}
-
-	/* Test and save vector registers */
-	asm volatile (
-		/*
-		 * Test if any vector register must be saved and, if so,
-		 * test if all register can be saved.
-		 */
-		"	la	1,%[vxrs]\n"	/* load save area */
-		"	tmll	%[m],30\n"	/* KERNEL_VXR */
-		"	jz	7f\n"		/* no work -> done */
-		"	jo	5f\n"		/* -> save V0..V31 */
-		/*
-		 * Test for special case KERNEL_FPU_MID only. In this
-		 * case a vstm V8..V23 is the best instruction
-		 */
-		"	chi	%[m],12\n"	/* KERNEL_VXR_MID */
-		"	jne	0f\n"		/* -> save V8..V23 */
-		"	VSTM	8,23,128,1\n"	/* vstm %v8,%v23,128(%r1) */
-		"	j	7f\n"
-		/* Test and save the first half of 16 vector registers */
-		"0:	tmll	%[m],6\n"	/* KERNEL_VXR_LOW */
-		"	jz	3f\n"		/* -> KERNEL_VXR_HIGH */
-		"	jo	2f\n"		/* 11 -> save V0..V15 */
-		"	brc	2,1f\n"		/* 10 -> save V8..V15 */
-		"	VSTM	0,7,0,1\n"	/* vstm %v0,%v7,0(%r1) */
-		"	j	3f\n"
-		"1:	VSTM	8,15,128,1\n"	/* vstm %v8,%v15,128(%r1) */
-		"	j	3f\n"
-		"2:	VSTM	0,15,0,1\n"	/* vstm %v0,%v15,0(%r1) */
-		/* Test and save the second half of 16 vector registers */
-		"3:	tmll	%[m],24\n"	/* KERNEL_VXR_HIGH */
-		"	jz	7f\n"
-		"	jo	6f\n"		/* 11 -> save V16..V31 */
-		"	brc	2,4f\n"		/* 10 -> save V24..V31 */
-		"	VSTM	16,23,256,1\n"	/* vstm %v16,%v23,256(%r1) */
-		"	j	7f\n"
-		"4:	VSTM	24,31,384,1\n"	/* vstm %v24,%v31,384(%r1) */
-		"	j	7f\n"
-		"5:	VSTM	0,15,0,1\n"	/* vstm %v0,%v15,0(%r1) */
-		"6:	VSTM	16,31,256,1\n"	/* vstm %v16,%v31,256(%r1) */
-		"7:"
-		: [vxrs] "=Q" (*(struct vx_array *) &state->vxrs)
-		: [m] "d" (flags)
-		: "1", "cc");
+	mask = flags & KERNEL_VXR;
+	if (mask == KERNEL_VXR) {
+		vxrs += fpu_vstm(0, 15, vxrs);
+		vxrs += fpu_vstm(16, 31, vxrs);
+		return;
+	}
+	if (mask == KERNEL_VXR_MID) {
+		vxrs += fpu_vstm(8, 23, vxrs);
+		return;
+	}
+	mask = flags & KERNEL_VXR_LOW;
+	if (mask) {
+		if (mask == KERNEL_VXR_LOW)
+			vxrs += fpu_vstm(0, 15, vxrs);
+		else if (mask == KERNEL_VXR_V0V7)
+			vxrs += fpu_vstm(0, 7, vxrs);
+		else
+			vxrs += fpu_vstm(8, 15, vxrs);
+	}
+	mask = flags & KERNEL_VXR_HIGH;
+	if (mask) {
+		if (mask == KERNEL_VXR_HIGH)
+			vxrs += fpu_vstm(16, 31, vxrs);
+		else if (mask == KERNEL_VXR_V16V23)
+			vxrs += fpu_vstm(16, 23, vxrs);
+		else
+			vxrs += fpu_vstm(24, 31, vxrs);
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void __kernel_fpu_end(struct kernel_fpu *state, u32 flags)
+void __kernel_fpu_end(struct kernel_fpu *state, int flags)
 {
+	__vector128 *vxrs = state->vxrs;
+	int mask;
+
 	/*
 	 * Limit the restore to the FPU/vector registers of the
-	 * previous context that have been overwritte by the
-	 * current context
+	 * previous context that have been overwritten by the
+	 * current context.
 	 */
-	flags &= state->mask;
-
+	flags &= state->hdr.mask;
 	if (flags & KERNEL_FPC)
-		/* Restore floating-point controls */
-		asm volatile("lfpc %0" : : "Q" (state->fpc));
-
+		fpu_lfpc(&state->hdr.fpc);
 	if (!cpu_has_vx()) {
-		if (flags & KERNEL_VXR_V0V7) {
-			/* Restore floating-point registers */
-			asm volatile("ld 0,%0" : : "Q" (state->fprs[0]));
-			asm volatile("ld 1,%0" : : "Q" (state->fprs[1]));
-			asm volatile("ld 2,%0" : : "Q" (state->fprs[2]));
-			asm volatile("ld 3,%0" : : "Q" (state->fprs[3]));
-			asm volatile("ld 4,%0" : : "Q" (state->fprs[4]));
-			asm volatile("ld 5,%0" : : "Q" (state->fprs[5]));
-			asm volatile("ld 6,%0" : : "Q" (state->fprs[6]));
-			asm volatile("ld 7,%0" : : "Q" (state->fprs[7]));
-			asm volatile("ld 8,%0" : : "Q" (state->fprs[8]));
-			asm volatile("ld 9,%0" : : "Q" (state->fprs[9]));
-			asm volatile("ld 10,%0" : : "Q" (state->fprs[10]));
-			asm volatile("ld 11,%0" : : "Q" (state->fprs[11]));
-			asm volatile("ld 12,%0" : : "Q" (state->fprs[12]));
-			asm volatile("ld 13,%0" : : "Q" (state->fprs[13]));
-			asm volatile("ld 14,%0" : : "Q" (state->fprs[14]));
-			asm volatile("ld 15,%0" : : "Q" (state->fprs[15]));
-		}
+		if (flags & KERNEL_VXR_LOW)
+			load_fp_regs_vx(vxrs);
 		return;
 	}
-
-	/* Test and restore (load) vector registers */
-	asm volatile (
-		/*
-		 * Test if any vector register must be loaded and, if so,
-		 * test if all registers can be loaded at once.
-		 */
-		"	la	1,%[vxrs]\n"	/* load restore area */
-		"	tmll	%[m],30\n"	/* KERNEL_VXR */
-		"	jz	7f\n"		/* no work -> done */
-		"	jo	5f\n"		/* -> restore V0..V31 */
-		/*
-		 * Test for special case KERNEL_FPU_MID only. In this
-		 * case a vlm V8..V23 is the best instruction
-		 */
-		"	chi	%[m],12\n"	/* KERNEL_VXR_MID */
-		"	jne	0f\n"		/* -> restore V8..V23 */
-		"	VLM	8,23,128,1\n"	/* vlm %v8,%v23,128(%r1) */
-		"	j	7f\n"
-		/* Test and restore the first half of 16 vector registers */
-		"0:	tmll	%[m],6\n"	/* KERNEL_VXR_LOW */
-		"	jz	3f\n"		/* -> KERNEL_VXR_HIGH */
-		"	jo	2f\n"		/* 11 -> restore V0..V15 */
-		"	brc	2,1f\n"		/* 10 -> restore V8..V15 */
-		"	VLM	0,7,0,1\n"	/* vlm %v0,%v7,0(%r1) */
-		"	j	3f\n"
-		"1:	VLM	8,15,128,1\n"	/* vlm %v8,%v15,128(%r1) */
-		"	j	3f\n"
-		"2:	VLM	0,15,0,1\n"	/* vlm %v0,%v15,0(%r1) */
-		/* Test and restore the second half of 16 vector registers */
-		"3:	tmll	%[m],24\n"	/* KERNEL_VXR_HIGH */
-		"	jz	7f\n"
-		"	jo	6f\n"		/* 11 -> restore V16..V31 */
-		"	brc	2,4f\n"		/* 10 -> restore V24..V31 */
-		"	VLM	16,23,256,1\n"	/* vlm %v16,%v23,256(%r1) */
-		"	j	7f\n"
-		"4:	VLM	24,31,384,1\n"	/* vlm %v24,%v31,384(%r1) */
-		"	j	7f\n"
-		"5:	VLM	0,15,0,1\n"	/* vlm %v0,%v15,0(%r1) */
-		"6:	VLM	16,31,256,1\n"	/* vlm %v16,%v31,256(%r1) */
-		"7:"
-		: [vxrs] "=Q" (*(struct vx_array *) &state->vxrs)
-		: [m] "d" (flags)
-		: "1", "cc");
+	mask = flags & KERNEL_VXR;
+	if (mask == KERNEL_VXR) {
+		vxrs += fpu_vlm(0, 15, vxrs);
+		vxrs += fpu_vlm(16, 31, vxrs);
+		return;
+	}
+	if (mask == KERNEL_VXR_MID) {
+		vxrs += fpu_vlm(8, 23, vxrs);
+		return;
+	}
+	mask = flags & KERNEL_VXR_LOW;
+	if (mask) {
+		if (mask == KERNEL_VXR_LOW)
+			vxrs += fpu_vlm(0, 15, vxrs);
+		else if (mask == KERNEL_VXR_V0V7)
+			vxrs += fpu_vlm(0, 7, vxrs);
+		else
+			vxrs += fpu_vlm(8, 15, vxrs);
+	}
+	mask = flags & KERNEL_VXR_HIGH;
+	if (mask) {
+		if (mask == KERNEL_VXR_HIGH)
+			vxrs += fpu_vlm(16, 31, vxrs);
+		else if (mask == KERNEL_VXR_V16V23)
+			vxrs += fpu_vlm(16, 23, vxrs);
+		else
+			vxrs += fpu_vlm(24, 31, vxrs);
+	}
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
-void __load_fpu_regs(void)
+void load_fpu_state(struct fpu *state, int flags)
 {
-	unsigned long *regs = current->thread.fpu.regs;
-	struct fpu *state = &current->thread.fpu;
+	__vector128 *vxrs = &state->vxrs[0];
+	int mask;
 
-	sfpc_safe(state->fpc);
-	if (likely(cpu_has_vx())) {
-		asm volatile("lgr	1,%0\n"
-			     "VLM	0,15,0,1\n"
-			     "VLM	16,31,256,1\n"
-			     :
-			     : "d" (regs)
-			     : "1", "cc", "memory");
-	} else {
-		asm volatile("ld 0,%0" : : "Q" (regs[0]));
-		asm volatile("ld 1,%0" : : "Q" (regs[1]));
-		asm volatile("ld 2,%0" : : "Q" (regs[2]));
-		asm volatile("ld 3,%0" : : "Q" (regs[3]));
-		asm volatile("ld 4,%0" : : "Q" (regs[4]));
-		asm volatile("ld 5,%0" : : "Q" (regs[5]));
-		asm volatile("ld 6,%0" : : "Q" (regs[6]));
-		asm volatile("ld 7,%0" : : "Q" (regs[7]));
-		asm volatile("ld 8,%0" : : "Q" (regs[8]));
-		asm volatile("ld 9,%0" : : "Q" (regs[9]));
-		asm volatile("ld 10,%0" : : "Q" (regs[10]));
-		asm volatile("ld 11,%0" : : "Q" (regs[11]));
-		asm volatile("ld 12,%0" : : "Q" (regs[12]));
-		asm volatile("ld 13,%0" : : "Q" (regs[13]));
-		asm volatile("ld 14,%0" : : "Q" (regs[14]));
-		asm volatile("ld 15,%0" : : "Q" (regs[15]));
+	if (flags & KERNEL_FPC)
+		fpu_lfpc(&state->fpc);
+	if (!cpu_has_vx()) {
+		if (flags & KERNEL_VXR_V0V7)
+			load_fp_regs_vx(state->vxrs);
+		return;
+	}
+	mask = flags & KERNEL_VXR;
+	if (mask == KERNEL_VXR) {
+		fpu_vlm(0, 15, &vxrs[0]);
+		fpu_vlm(16, 31, &vxrs[16]);
+		return;
+	}
+	if (mask == KERNEL_VXR_MID) {
+		fpu_vlm(8, 23, &vxrs[8]);
+		return;
+	}
+	mask = flags & KERNEL_VXR_LOW;
+	if (mask) {
+		if (mask == KERNEL_VXR_LOW)
+			fpu_vlm(0, 15, &vxrs[0]);
+		else if (mask == KERNEL_VXR_V0V7)
+			fpu_vlm(0, 7, &vxrs[0]);
+		else
+			fpu_vlm(8, 15, &vxrs[8]);
+	}
+	mask = flags & KERNEL_VXR_HIGH;
+	if (mask) {
+		if (mask == KERNEL_VXR_HIGH)
+			fpu_vlm(16, 31, &vxrs[16]);
+		else if (mask == KERNEL_VXR_V16V23)
+			fpu_vlm(16, 23, &vxrs[16]);
+		else
+			fpu_vlm(24, 31, &vxrs[24]);
 	}
-	clear_cpu_flag(CIF_FPU);
-}
-
-void load_fpu_regs(void)
-{
-	raw_local_irq_disable();
-	__load_fpu_regs();
-	raw_local_irq_enable();
 }
-EXPORT_SYMBOL(load_fpu_regs);
 
-void save_fpu_regs(void)
+void save_fpu_state(struct fpu *state, int flags)
 {
-	unsigned long flags, *regs;
-	struct fpu *state;
-
-	local_irq_save(flags);
+	__vector128 *vxrs = &state->vxrs[0];
+	int mask;
 
-	if (test_cpu_flag(CIF_FPU))
-		goto out;
-
-	state = &current->thread.fpu;
-	regs = current->thread.fpu.regs;
-
-	asm volatile("stfpc %0" : "=Q" (state->fpc));
-	if (likely(cpu_has_vx())) {
-		asm volatile("lgr	1,%0\n"
-			     "VSTM	0,15,0,1\n"
-			     "VSTM	16,31,256,1\n"
-			     :
-			     : "d" (regs)
-			     : "1", "cc", "memory");
-	} else {
-		asm volatile("std 0,%0" : "=Q" (regs[0]));
-		asm volatile("std 1,%0" : "=Q" (regs[1]));
-		asm volatile("std 2,%0" : "=Q" (regs[2]));
-		asm volatile("std 3,%0" : "=Q" (regs[3]));
-		asm volatile("std 4,%0" : "=Q" (regs[4]));
-		asm volatile("std 5,%0" : "=Q" (regs[5]));
-		asm volatile("std 6,%0" : "=Q" (regs[6]));
-		asm volatile("std 7,%0" : "=Q" (regs[7]));
-		asm volatile("std 8,%0" : "=Q" (regs[8]));
-		asm volatile("std 9,%0" : "=Q" (regs[9]));
-		asm volatile("std 10,%0" : "=Q" (regs[10]));
-		asm volatile("std 11,%0" : "=Q" (regs[11]));
-		asm volatile("std 12,%0" : "=Q" (regs[12]));
-		asm volatile("std 13,%0" : "=Q" (regs[13]));
-		asm volatile("std 14,%0" : "=Q" (regs[14]));
-		asm volatile("std 15,%0" : "=Q" (regs[15]));
+	if (flags & KERNEL_FPC)
+		fpu_stfpc(&state->fpc);
+	if (!cpu_has_vx()) {
+		if (flags & KERNEL_VXR_LOW)
+			save_fp_regs_vx(state->vxrs);
+		return;
+	}
+	mask = flags & KERNEL_VXR;
+	if (mask == KERNEL_VXR) {
+		fpu_vstm(0, 15, &vxrs[0]);
+		fpu_vstm(16, 31, &vxrs[16]);
+		return;
+	}
+	if (mask == KERNEL_VXR_MID) {
+		fpu_vstm(8, 23, &vxrs[8]);
+		return;
+	}
+	mask = flags & KERNEL_VXR_LOW;
+	if (mask) {
+		if (mask == KERNEL_VXR_LOW)
+			fpu_vstm(0, 15, &vxrs[0]);
+		else if (mask == KERNEL_VXR_V0V7)
+			fpu_vstm(0, 7, &vxrs[0]);
+		else
+			fpu_vstm(8, 15, &vxrs[8]);
+	}
+	mask = flags & KERNEL_VXR_HIGH;
+	if (mask) {
+		if (mask == KERNEL_VXR_HIGH)
+			fpu_vstm(16, 31, &vxrs[16]);
+		else if (mask == KERNEL_VXR_V16V23)
+			fpu_vstm(16, 23, &vxrs[16]);
+		else
+			fpu_vstm(24, 31, &vxrs[24]);
 	}
-	set_cpu_flag(CIF_FPU);
-out:
-	local_irq_restore(flags);
 }
-EXPORT_SYMBOL(save_fpu_regs);
+EXPORT_SYMBOL(save_fpu_state);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index ba75f6bee774..1486350a4177 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1941,8 +1941,7 @@ static void dump_reipl_run(struct shutdown_trigger *trigger)
 	    reipl_type == IPL_TYPE_UNKNOWN)
 		os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR;
 	os_info_entry_add(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags));
-	csum = (__force unsigned int)
-	       csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
+	csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0);
 	abs_lc = get_abs_lowcore();
 	abs_lc->ipib = __pa(reipl_block_actual);
 	abs_lc->ipib_checksum = csum;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index aa22ffc16bcd..c5d0c1cf984b 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -13,8 +13,10 @@
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
 #include <linux/debug_locks.h>
+#include <asm/guarded_storage.h>
 #include <asm/pfault.h>
 #include <asm/cio.h>
+#include <asm/fpu.h>
 #include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/ipl.h>
@@ -26,7 +28,6 @@
 #include <asm/os_info.h>
 #include <asm/set_memory.h>
 #include <asm/stacktrace.h>
-#include <asm/switch_to.h>
 #include <asm/nmi.h>
 #include <asm/sclp.h>
 
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 9ad44c26d1a2..c77382a67325 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -23,16 +23,14 @@
 #include <linux/export.h>
 #include <asm/lowcore.h>
 #include <asm/ctlreg.h>
+#include <asm/fpu.h>
 #include <asm/smp.h>
 #include <asm/stp.h>
 #include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
-#include <asm/switch_to.h>
 #include <asm/asm-offsets.h>
 #include <asm/pai.h>
-#include <asm/vx-insn.h>
-#include <asm/fpu/api.h>
 
 struct mcck_struct {
 	unsigned int kill_task : 1;
@@ -204,133 +202,63 @@ void s390_handle_mcck(void)
 	}
 }
 
-/*
- * returns 0 if register contents could be validated
- * returns 1 otherwise
+/**
+ * nmi_registers_valid - verify if registers are valid
+ * @mci: machine check interruption code
+ *
+ * Inspect a machine check interruption code and verify if all required
+ * registers are valid. For some registers the corresponding validity bit is
+ * ignored and the registers are set to the expected value.
+ * Returns true if all registers are valid, otherwise false.
  */
-static int notrace s390_validate_registers(union mci mci)
+static bool notrace nmi_registers_valid(union mci mci)
 {
-	struct mcesa *mcesa;
-	void *fpt_save_area;
 	union ctlreg2 cr2;
-	int kill_task;
-	u64 zero;
-
-	kill_task = 0;
-	zero = 0;
-
-	if (!mci.gr || !mci.fp)
-		kill_task = 1;
-	fpt_save_area = &S390_lowcore.floating_pt_save_area;
-	if (!mci.fc) {
-		kill_task = 1;
-		asm volatile(
-			"	lfpc	%0\n"
-			:
-			: "Q" (zero));
-	} else {
-		asm volatile(
-			"	lfpc	%0\n"
-			:
-			: "Q" (S390_lowcore.fpt_creg_save_area));
-	}
 
-	mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK);
-	if (!cpu_has_vx()) {
-		/* Validate floating point registers */
-		asm volatile(
-			"	ld	0,0(%0)\n"
-			"	ld	1,8(%0)\n"
-			"	ld	2,16(%0)\n"
-			"	ld	3,24(%0)\n"
-			"	ld	4,32(%0)\n"
-			"	ld	5,40(%0)\n"
-			"	ld	6,48(%0)\n"
-			"	ld	7,56(%0)\n"
-			"	ld	8,64(%0)\n"
-			"	ld	9,72(%0)\n"
-			"	ld	10,80(%0)\n"
-			"	ld	11,88(%0)\n"
-			"	ld	12,96(%0)\n"
-			"	ld	13,104(%0)\n"
-			"	ld	14,112(%0)\n"
-			"	ld	15,120(%0)\n"
-			:
-			: "a" (fpt_save_area)
-			: "memory");
-	} else {
-		/* Validate vector registers */
-		union ctlreg0 cr0;
-
-		/*
-		 * The vector validity must only be checked if not running a
-		 * KVM guest. For KVM guests the machine check is forwarded by
-		 * KVM and it is the responsibility of the guest to take
-		 * appropriate actions. The host vector or FPU values have been
-		 * saved by KVM and will be restored by KVM.
-		 */
-		if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST))
-			kill_task = 1;
-		cr0.reg = S390_lowcore.cregs_save_area[0];
-		cr0.afp = cr0.vx = 1;
-		local_ctl_load(0, &cr0.reg);
-		asm volatile(
-			"	la	1,%0\n"
-			"	VLM	0,15,0,1\n"
-			"	VLM	16,31,256,1\n"
-			:
-			: "Q" (*(struct vx_array *)mcesa->vector_save_area)
-			: "1");
-		local_ctl_load(0, &S390_lowcore.cregs_save_area[0]);
-	}
-	/* Validate access registers */
-	asm volatile(
-		"	lam	0,15,0(%0)\n"
-		:
-		: "a" (&S390_lowcore.access_regs_save_area)
-		: "memory");
-	if (!mci.ar)
-		kill_task = 1;
-	/* Validate guarded storage registers */
-	cr2.reg = S390_lowcore.cregs_save_area[2];
-	if (cr2.gse) {
-		if (!mci.gs) {
-			/*
-			 * 2 cases:
-			 * - machine check in kernel or userspace
-			 * - machine check while running SIE (KVM guest)
-			 * For kernel or userspace the userspace values of
-			 * guarded storage control can not be recreated, the
-			 * process must be terminated.
-			 * For SIE the guest values of guarded storage can not
-			 * be recreated. This is either due to a bug or due to
-			 * GS being disabled in the guest. The guest will be
-			 * notified by KVM code and the guests machine check
-			 * handling must take care of this.  The host values
-			 * are saved by KVM and are not affected.
-			 */
-			if (!test_cpu_flag(CIF_MCCK_GUEST))
-				kill_task = 1;
-		} else {
-			load_gs_cb((struct gs_cb *)mcesa->guarded_storage_save_area);
-		}
-	}
 	/*
-	 * The getcpu vdso syscall reads CPU number from the programmable
+	 * The getcpu vdso syscall reads the CPU number from the programmable
 	 * field of the TOD clock. Disregard the TOD programmable register
-	 * validity bit and load the CPU number into the TOD programmable
-	 * field unconditionally.
+	 * validity bit and load the CPU number into the TOD programmable field
+	 * unconditionally.
 	 */
 	set_tod_programmable_field(raw_smp_processor_id());
-	/* Validate clock comparator register */
+	/*
+	 * Set the clock comparator register to the next expected value.
+	 */
 	set_clock_comparator(S390_lowcore.clock_comparator);
-
+	if (!mci.gr || !mci.fp || !mci.fc)
+		return false;
+	/*
+	 * The vector validity must only be checked if not running a
+	 * KVM guest. For KVM guests the machine check is forwarded by
+	 * KVM and it is the responsibility of the guest to take
+	 * appropriate actions. The host vector or FPU values have been
+	 * saved by KVM and will be restored by KVM.
+	 */
+	if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST))
+		return false;
+	if (!mci.ar)
+		return false;
+	/*
+	 * Two cases for guarded storage registers:
+	 * - machine check in kernel or userspace
+	 * - machine check while running SIE (KVM guest)
+	 * For kernel or userspace the userspace values of guarded storage
+	 * control can not be recreated, the process must be terminated.
+	 * For SIE the guest values of guarded storage can not be recreated.
+	 * This is either due to a bug or due to GS being disabled in the
+	 * guest. The guest will be notified by KVM code and the guests machine
+	 * check handling must take care of this. The host values are saved by
+	 * KVM and are not affected.
+	 */
+	cr2.reg = S390_lowcore.cregs_save_area[2];
+	if (cr2.gse && !mci.gs && !test_cpu_flag(CIF_MCCK_GUEST))
+		return false;
 	if (!mci.ms || !mci.pm || !mci.ia)
-		kill_task = 1;
-
-	return kill_task;
+		return false;
+	return true;
 }
-NOKPROBE_SYMBOL(s390_validate_registers);
+NOKPROBE_SYMBOL(nmi_registers_valid);
 
 /*
  * Backup the guest's machine check info to its description block
@@ -428,7 +356,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 			s390_handle_damage();
 		}
 	}
-	if (s390_validate_registers(mci)) {
+	if (!nmi_registers_valid(mci)) {
 		if (!user_mode(regs))
 			s390_handle_damage();
 		/*
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index 6e1824141b29..a801e6bd5341 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -29,7 +29,7 @@ static struct os_info os_info __page_aligned_data;
 u32 os_info_csum(struct os_info *os_info)
 {
 	int size = sizeof(*os_info) - offsetof(struct os_info, version_major);
-	return (__force u32)csum_partial(&os_info->version_major, size, 0);
+	return (__force u32)cksm(&os_info->version_major, size, 0);
 }
 
 /*
@@ -49,7 +49,7 @@ void os_info_entry_add(int nr, void *ptr, u64 size)
 {
 	os_info.entry[nr].addr = __pa(ptr);
 	os_info.entry[nr].size = size;
-	os_info.entry[nr].csum = (__force u32)csum_partial(ptr, size, 0);
+	os_info.entry[nr].csum = (__force u32)cksm(ptr, size, 0);
 	os_info.csum = os_info_csum(&os_info);
 }
 
@@ -98,7 +98,7 @@ static void os_info_old_alloc(int nr, int align)
 		msg = "copy failed";
 		goto fail_free;
 	}
-	csum = (__force u32)csum_partial(buf_align, size, 0);
+	csum = (__force u32)cksm(buf_align, size, 0);
 	if (csum != os_info_old->entry[nr].csum) {
 		msg = "checksum failed";
 		goto fail_free;
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index bf8a672b15a4..823d652e3917 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -98,6 +98,7 @@ static void paicrypt_event_destroy(struct perf_event *event)
 			    event->attr.config, event->cpu,
 			    cpump->active_events, cpump->mode,
 			    refcount_read(&cpump->refcnt));
+	free_page(PAI_SAVE_AREA(event));
 	if (refcount_dec_and_test(&cpump->refcnt)) {
 		debug_sprintf_event(cfm_dbg, 4, "%s page %#lx save %p\n",
 				    __func__, (unsigned long)cpump->page,
@@ -260,6 +261,7 @@ static int paicrypt_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *a = &event->attr;
 	struct paicrypt_map *cpump;
+	int rc = 0;
 
 	/* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */
 	if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type)
@@ -274,10 +276,21 @@ static int paicrypt_event_init(struct perf_event *event)
 	/* Allow only CRYPTO_ALL for sampling. */
 	if (a->sample_period && a->config != PAI_CRYPTO_BASE)
 		return -EINVAL;
+	/* Get a page to store last counter values for sampling */
+	if (a->sample_period) {
+		PAI_SAVE_AREA(event) = get_zeroed_page(GFP_KERNEL);
+		if (!PAI_SAVE_AREA(event)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+	}
 
 	cpump = paicrypt_busy(event);
-	if (IS_ERR(cpump))
-		return PTR_ERR(cpump);
+	if (IS_ERR(cpump)) {
+		free_page(PAI_SAVE_AREA(event));
+		rc = PTR_ERR(cpump);
+		goto out;
+	}
 
 	event->destroy = paicrypt_event_destroy;
 
@@ -293,7 +306,8 @@ static int paicrypt_event_init(struct perf_event *event)
 	}
 
 	static_branch_inc(&pai_key);
-	return 0;
+out:
+	return rc;
 }
 
 static void paicrypt_read(struct perf_event *event)
@@ -310,20 +324,15 @@ static void paicrypt_read(struct perf_event *event)
 
 static void paicrypt_start(struct perf_event *event, int flags)
 {
+	struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+	struct paicrypt_map *cpump = mp->mapptr;
 	u64 sum;
 
-	/* Event initialization sets last_tag to 0. When later on the events
-	 * are deleted and re-added, do not reset the event count value to zero.
-	 * Events are added, deleted and re-added when 2 or more events
-	 * are active at the same time.
-	 */
 	if (!event->attr.sample_period) {	/* Counting */
-		if (!event->hw.last_tag) {
-			event->hw.last_tag = 1;
-			sum = paicrypt_getall(event);	/* Get current value */
-			local64_set(&event->hw.prev_count, sum);
-		}
+		sum = paicrypt_getall(event);	/* Get current value */
+		local64_set(&event->hw.prev_count, sum);
 	} else {				/* Sampling */
+		cpump->event = event;
 		perf_sched_cb_inc(event->pmu);
 	}
 }
@@ -339,7 +348,6 @@ static int paicrypt_add(struct perf_event *event, int flags)
 		WRITE_ONCE(S390_lowcore.ccd, ccd);
 		local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT);
 	}
-	cpump->event = event;
 	if (flags & PERF_EF_START)
 		paicrypt_start(event, PERF_EF_RELOAD);
 	event->hw.state = 0;
@@ -367,23 +375,34 @@ static void paicrypt_del(struct perf_event *event, int flags)
 	}
 }
 
-/* Create raw data and save it in buffer. Returns number of bytes copied.
- * Saves only positive counter entries of the form
+/* Create raw data and save it in buffer. Calculate the delta for each
+ * counter between this invocation and the last invocation.
+ * Returns number of bytes copied.
+ * Saves only entries with positive counter difference of the form
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
 static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page,
-			    bool exclude_user, bool exclude_kernel)
+			    unsigned long *page_old, bool exclude_user,
+			    bool exclude_kernel)
 {
 	int i, outidx = 0;
 
 	for (i = 1; i <= paicrypt_cnt; i++) {
-		u64 val = 0;
+		u64 val = 0, val_old = 0;
 
-		if (!exclude_kernel)
+		if (!exclude_kernel) {
 			val += paicrypt_getctr(page, i, true);
-		if (!exclude_user)
+			val_old += paicrypt_getctr(page_old, i, true);
+		}
+		if (!exclude_user) {
 			val += paicrypt_getctr(page, i, false);
+			val_old += paicrypt_getctr(page_old, i, false);
+		}
+		if (val >= val_old)
+			val -= val_old;
+		else
+			val = (~0ULL - val_old) + val + 1;
 		if (val) {
 			userdata[outidx].num = i;
 			userdata[outidx].value = val;
@@ -426,8 +445,8 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
 
 	overflow = perf_event_overflow(event, &data, &regs);
 	perf_event_update_userpage(event);
-	/* Clear lowcore page after read */
-	memset(cpump->page, 0, PAGE_SIZE);
+	/* Save crypto counter lowcore page after reading event data. */
+	memcpy((void *)PAI_SAVE_AREA(event), cpump->page, PAGE_SIZE);
 	return overflow;
 }
 
@@ -443,6 +462,7 @@ static int paicrypt_have_sample(void)
 	if (!event)		/* No event active */
 		return 0;
 	rawsize = paicrypt_copy(cpump->save, cpump->page,
+				(unsigned long *)PAI_SAVE_AREA(event),
 				cpump->event->attr.exclude_user,
 				cpump->event->attr.exclude_kernel);
 	if (rawsize)			/* No incremented counters */
@@ -694,6 +714,12 @@ static int __init attr_event_init_one(struct attribute **attrs, int num)
 {
 	struct perf_pmu_events_attr *pa;
 
+	/* Index larger than array_size, no counter name available */
+	if (num >= ARRAY_SIZE(paicrypt_ctrnames)) {
+		attrs[num] = NULL;
+		return 0;
+	}
+
 	pa = kzalloc(sizeof(*pa), GFP_KERNEL);
 	if (!pa)
 		return -ENOMEM;
@@ -714,14 +740,13 @@ static int __init attr_event_init(void)
 	struct attribute **attrs;
 	int ret, i;
 
-	attrs = kmalloc_array(ARRAY_SIZE(paicrypt_ctrnames) + 1, sizeof(*attrs),
-			      GFP_KERNEL);
+	attrs = kmalloc_array(paicrypt_cnt + 2, sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
 		return -ENOMEM;
-	for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) {
+	for (i = 0; i <= paicrypt_cnt; i++) {
 		ret = attr_event_init_one(attrs, i);
 		if (ret) {
-			attr_event_free(attrs, i - 1);
+			attr_event_free(attrs, i);
 			return ret;
 		}
 	}
@@ -742,8 +767,10 @@ static int __init paicrypt_init(void)
 	paicrypt_cnt = ib.num_cc;
 	if (paicrypt_cnt == 0)
 		return 0;
-	if (paicrypt_cnt >= PAI_CRYPTO_MAXCTR)
-		paicrypt_cnt = PAI_CRYPTO_MAXCTR - 1;
+	if (paicrypt_cnt >= PAI_CRYPTO_MAXCTR) {
+		pr_err("Too many PMU pai_crypto counters %d\n", paicrypt_cnt);
+		return -E2BIG;
+	}
 
 	rc = attr_event_init();		/* Export known PAI crypto events */
 	if (rc) {
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index af7f2b538c8f..616a25606cd6 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -120,6 +120,7 @@ static void paiext_event_destroy(struct perf_event *event)
 	struct paiext_mapptr *mp = per_cpu_ptr(paiext_root.mapptr, event->cpu);
 	struct paiext_map *cpump = mp->mapptr;
 
+	free_page(PAI_SAVE_AREA(event));
 	mutex_lock(&paiext_reserve_mutex);
 	cpump->event = NULL;
 	if (refcount_dec_and_test(&cpump->refcnt))	/* Last reference gone */
@@ -202,7 +203,6 @@ static int paiext_alloc(struct perf_event_attr *a, struct perf_event *event)
 	}
 
 	rc = 0;
-	cpump->event = event;
 
 undo:
 	if (rc) {
@@ -256,10 +256,18 @@ static int paiext_event_init(struct perf_event *event)
 	/* Prohibit exclude_user event selection */
 	if (a->exclude_user)
 		return -EINVAL;
+	/* Get a page to store last counter values for sampling */
+	if (a->sample_period) {
+		PAI_SAVE_AREA(event) = get_zeroed_page(GFP_KERNEL);
+		if (!PAI_SAVE_AREA(event))
+			return -ENOMEM;
+	}
 
 	rc = paiext_alloc(a, event);
-	if (rc)
+	if (rc) {
+		free_page(PAI_SAVE_AREA(event));
 		return rc;
+	}
 	event->destroy = paiext_event_destroy;
 
 	if (a->sample_period) {
@@ -319,15 +327,15 @@ static void paiext_read(struct perf_event *event)
 
 static void paiext_start(struct perf_event *event, int flags)
 {
+	struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+	struct paiext_map *cpump = mp->mapptr;
 	u64 sum;
 
 	if (!event->attr.sample_period) {	/* Counting */
-		if (!event->hw.last_tag) {
-			event->hw.last_tag = 1;
-			sum = paiext_getall(event);	/* Get current value */
-			local64_set(&event->hw.prev_count, sum);
-		}
+		sum = paiext_getall(event);	/* Get current value */
+		local64_set(&event->hw.prev_count, sum);
 	} else {				/* Sampling */
+		cpump->event = event;
 		perf_sched_cb_inc(event->pmu);
 	}
 }
@@ -346,7 +354,6 @@ static int paiext_add(struct perf_event *event, int flags)
 		debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n",
 				    __func__, S390_lowcore.aicd, pcb->acc);
 	}
-	cpump->event = event;
 	if (flags & PERF_EF_START)
 		paiext_start(event, PERF_EF_RELOAD);
 	event->hw.state = 0;
@@ -384,13 +391,19 @@ static void paiext_del(struct perf_event *event, int flags)
  * 2 bytes: Number of counter
  * 8 bytes: Value of counter
  */
-static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area)
+static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area,
+			  unsigned long *area_old)
 {
 	int i, outidx = 0;
 
 	for (i = 1; i <= paiext_cnt; i++) {
 		u64 val = paiext_getctr(area, i);
+		u64 val_old = paiext_getctr(area_old, i);
 
+		if (val >= val_old)
+			val -= val_old;
+		else
+			val = (~0ULL - val_old) + val + 1;
 		if (val) {
 			userdata[outidx].num = i;
 			userdata[outidx].value = val;
@@ -446,8 +459,9 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
 
 	overflow = perf_event_overflow(event, &data, &regs);
 	perf_event_update_userpage(event);
-	/* Clear lowcore area after read */
-	memset(cpump->area, 0, PAIE1_CTRBLOCK_SZ);
+	/* Save NNPA lowcore area after read in event */
+	memcpy((void *)PAI_SAVE_AREA(event), cpump->area,
+	       PAIE1_CTRBLOCK_SZ);
 	return overflow;
 }
 
@@ -462,7 +476,8 @@ static int paiext_have_sample(void)
 
 	if (!event)
 		return 0;
-	rawsize = paiext_copy(cpump->save, cpump->area);
+	rawsize = paiext_copy(cpump->save, cpump->area,
+			      (unsigned long *)PAI_SAVE_AREA(event));
 	if (rawsize)			/* Incremented counters */
 		rc = paiext_push_sample(rawsize, cpump, event);
 	return rc;
@@ -584,6 +599,12 @@ static int __init attr_event_init_one(struct attribute **attrs, int num)
 {
 	struct perf_pmu_events_attr *pa;
 
+	/* Index larger than array_size, no counter name available */
+	if (num >= ARRAY_SIZE(paiext_ctrnames)) {
+		attrs[num] = NULL;
+		return 0;
+	}
+
 	pa = kzalloc(sizeof(*pa), GFP_KERNEL);
 	if (!pa)
 		return -ENOMEM;
@@ -604,14 +625,13 @@ static int __init attr_event_init(void)
 	struct attribute **attrs;
 	int ret, i;
 
-	attrs = kmalloc_array(ARRAY_SIZE(paiext_ctrnames) + 1, sizeof(*attrs),
-			      GFP_KERNEL);
+	attrs = kmalloc_array(paiext_cnt + 2, sizeof(*attrs), GFP_KERNEL);
 	if (!attrs)
 		return -ENOMEM;
-	for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) {
+	for (i = 0; i <= paiext_cnt; i++) {
 		ret = attr_event_init_one(attrs, i);
 		if (ret) {
-			attr_event_free(attrs, i - 1);
+			attr_event_free(attrs, i);
 			return ret;
 		}
 	}
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 3d93656bd948..a6b058ee4a36 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -5,8 +5,7 @@
 #include <linux/errno.h>
 #include <linux/bug.h>
 #include <asm/ptrace.h>
-#include <asm/fpu/api.h>
-#include <asm/fpu/types.h>
+#include <asm/fpu.h>
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -20,10 +19,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 			return 0;
 
 		idx -= PERF_REG_S390_FP0;
-		if (cpu_has_vx())
-			fp = *(freg_t *)(current->thread.fpu.vxrs + idx);
-		else
-			fp = current->thread.fpu.fprs[idx];
+		fp = *(freg_t *)(current->thread.ufpu.vxrs + idx);
 		return fp.ui;
 	}
 
@@ -65,6 +61,6 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 	 */
 	regs_user->regs = task_pt_regs(current);
 	if (user_mode(regs_user->regs))
-		save_fpu_regs();
+		save_user_fpu_regs();
 	regs_user->abi = perf_reg_abi(current);
 }
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 4e3b366589fb..dd456b475861 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -31,15 +31,19 @@
 #include <linux/init_task.h>
 #include <linux/entry-common.h>
 #include <linux/io.h>
+#include <asm/guarded_storage.h>
+#include <asm/access-regs.h>
+#include <asm/switch_to.h>
 #include <asm/cpu_mf.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/vtimer.h>
 #include <asm/exec.h>
+#include <asm/fpu.h>
 #include <asm/irq.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include <asm/stacktrace.h>
-#include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
 #include <asm/unwind.h>
 #include "entry.h"
@@ -84,13 +88,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	/*
 	 * Save the floating-point or vector register state of the current
-	 * task and set the CIF_FPU flag to lazy restore the FPU register
+	 * task and set the TIF_FPU flag to lazy restore the FPU register
 	 * state when returning to user space.
 	 */
-	save_fpu_regs();
+	save_user_fpu_regs();
 
 	*dst = *src;
-	dst->thread.fpu.regs = dst->thread.fpu.fprs;
+	dst->thread.kfpu_flags = 0;
 
 	/*
 	 * Don't transfer over the runtime instrumentation or the guarded
@@ -186,8 +190,23 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 void execve_tail(void)
 {
-	current->thread.fpu.fpc = 0;
-	asm volatile("sfpc %0" : : "d" (0));
+	current->thread.ufpu.fpc = 0;
+	fpu_sfpc(0);
+}
+
+struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next)
+{
+	save_user_fpu_regs();
+	save_kernel_fpu_regs(&prev->thread);
+	save_access_regs(&prev->thread.acrs[0]);
+	save_ri_cb(prev->thread.ri_cb);
+	save_gs_cb(prev->thread.gs_cb);
+	update_cr_regs(next);
+	restore_kernel_fpu_regs(&next->thread);
+	restore_access_regs(&next->thread.acrs[0]);
+	restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);
+	restore_gs_cb(next->thread.gs_cb);
+	return __switch_to_asm(prev, next);
 }
 
 unsigned long __get_wchan(struct task_struct *p)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index f1897a8bb221..1cfed8b710b8 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -24,13 +24,14 @@
 #include <linux/seccomp.h>
 #include <linux/compat.h>
 #include <trace/syscall.h>
+#include <asm/guarded_storage.h>
+#include <asm/access-regs.h>
 #include <asm/page.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
-#include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
 #include <asm/facility.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 
 #include "entry.h"
 
@@ -246,22 +247,15 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr)
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		tmp = child->thread.fpu.fpc;
+		tmp = child->thread.ufpu.fpc;
 		tmp <<= BITS_PER_LONG - 32;
 
 	} else if (addr < offsetof(struct user, regs.fp_regs) + sizeof(s390_fp_regs)) {
 		/*
-		 * floating point regs. are either in child->thread.fpu
-		 * or the child->thread.fpu.vxrs array
+		 * floating point regs. are in the child->thread.ufpu.vxrs array
 		 */
 		offset = addr - offsetof(struct user, regs.fp_regs.fprs);
-		if (cpu_has_vx())
-			tmp = *(addr_t *)
-			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
-		else
-			tmp = *(addr_t *)
-			       ((addr_t) child->thread.fpu.fprs + offset);
-
+		tmp = *(addr_t *)((addr_t)child->thread.ufpu.vxrs + 2 * offset);
 	} else if (addr < offsetof(struct user, regs.per_info) + sizeof(per_struct)) {
 		/*
 		 * Handle access to the per_info structure.
@@ -395,21 +389,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 */
 		if ((unsigned int)data != 0)
 			return -EINVAL;
-		child->thread.fpu.fpc = data >> (BITS_PER_LONG - 32);
+		child->thread.ufpu.fpc = data >> (BITS_PER_LONG - 32);
 
 	} else if (addr < offsetof(struct user, regs.fp_regs) + sizeof(s390_fp_regs)) {
 		/*
-		 * floating point regs. are either in child->thread.fpu
-		 * or the child->thread.fpu.vxrs array
+		 * floating point regs. are in the child->thread.ufpu.vxrs array
 		 */
 		offset = addr - offsetof(struct user, regs.fp_regs.fprs);
-		if (cpu_has_vx())
-			*(addr_t *)((addr_t)
-				child->thread.fpu.vxrs + 2*offset) = data;
-		else
-			*(addr_t *)((addr_t)
-				child->thread.fpu.fprs + offset) = data;
-
+		*(addr_t *)((addr_t)child->thread.ufpu.vxrs + 2 * offset) = data;
 	} else if (addr < offsetof(struct user, regs.per_info) + sizeof(per_struct)) {
 		/*
 		 * Handle access to the per_info structure.
@@ -622,21 +609,14 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr)
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		tmp = child->thread.fpu.fpc;
+		tmp = child->thread.ufpu.fpc;
 
 	} else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) {
 		/*
-		 * floating point regs. are either in child->thread.fpu
-		 * or the child->thread.fpu.vxrs array
+		 * floating point regs. are in the child->thread.ufpu.vxrs array
 		 */
 		offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs);
-		if (cpu_has_vx())
-			tmp = *(__u32 *)
-			       ((addr_t) child->thread.fpu.vxrs + 2*offset);
-		else
-			tmp = *(__u32 *)
-			       ((addr_t) child->thread.fpu.fprs + offset);
-
+		tmp = *(__u32 *)((addr_t)child->thread.ufpu.vxrs + 2 * offset);
 	} else if (addr < offsetof(struct compat_user, regs.per_info) + sizeof(struct compat_per_struct_kernel)) {
 		/*
 		 * Handle access to the per_info structure.
@@ -748,21 +728,14 @@ static int __poke_user_compat(struct task_struct *child,
 		/*
 		 * floating point control reg. is in the thread structure
 		 */
-		child->thread.fpu.fpc = data;
+		child->thread.ufpu.fpc = data;
 
 	} else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) {
 		/*
-		 * floating point regs. are either in child->thread.fpu
-		 * or the child->thread.fpu.vxrs array
+		 * floating point regs. are in the child->thread.ufpu.vxrs array
 		 */
 		offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs);
-		if (cpu_has_vx())
-			*(__u32 *)((addr_t)
-				child->thread.fpu.vxrs + 2*offset) = tmp;
-		else
-			*(__u32 *)((addr_t)
-				child->thread.fpu.fprs + offset) = tmp;
-
+		*(__u32 *)((addr_t)child->thread.ufpu.vxrs + 2 * offset) = tmp;
 	} else if (addr < offsetof(struct compat_user, regs.per_info) + sizeof(struct compat_per_struct_kernel)) {
 		/*
 		 * Handle access to the per_info structure.
@@ -893,10 +866,10 @@ static int s390_fpregs_get(struct task_struct *target,
 	_s390_fp_regs fp_regs;
 
 	if (target == current)
-		save_fpu_regs();
+		save_user_fpu_regs();
 
-	fp_regs.fpc = target->thread.fpu.fpc;
-	fpregs_store(&fp_regs, &target->thread.fpu);
+	fp_regs.fpc = target->thread.ufpu.fpc;
+	fpregs_store(&fp_regs, &target->thread.ufpu);
 
 	return membuf_write(&to, &fp_regs, sizeof(fp_regs));
 }
@@ -910,22 +883,17 @@ static int s390_fpregs_set(struct task_struct *target,
 	freg_t fprs[__NUM_FPRS];
 
 	if (target == current)
-		save_fpu_regs();
-
-	if (cpu_has_vx())
-		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
-	else
-		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
-
+		save_user_fpu_regs();
+	convert_vx_to_fp(fprs, target->thread.ufpu.vxrs);
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
-		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
+		u32 ufpc[2] = { target->thread.ufpu.fpc, 0 };
 		rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc,
 					0, offsetof(s390_fp_regs, fprs));
 		if (rc)
 			return rc;
 		if (ufpc[1] != 0)
 			return -EINVAL;
-		target->thread.fpu.fpc = ufpc[0];
+		target->thread.ufpu.fpc = ufpc[0];
 	}
 
 	if (rc == 0 && count > 0)
@@ -933,12 +901,7 @@ static int s390_fpregs_set(struct task_struct *target,
 					fprs, offsetof(s390_fp_regs, fprs), -1);
 	if (rc)
 		return rc;
-
-	if (cpu_has_vx())
-		convert_fp_to_vx(target->thread.fpu.vxrs, fprs);
-	else
-		memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs));
-
+	convert_fp_to_vx(target->thread.ufpu.vxrs, fprs);
 	return rc;
 }
 
@@ -988,9 +951,9 @@ static int s390_vxrs_low_get(struct task_struct *target,
 	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
-		save_fpu_regs();
+		save_user_fpu_regs();
 	for (i = 0; i < __NUM_VXRS_LOW; i++)
-		vxrs[i] = target->thread.fpu.vxrs[i].low;
+		vxrs[i] = target->thread.ufpu.vxrs[i].low;
 	return membuf_write(&to, vxrs, sizeof(vxrs));
 }
 
@@ -1005,15 +968,15 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
-		save_fpu_regs();
+		save_user_fpu_regs();
 
 	for (i = 0; i < __NUM_VXRS_LOW; i++)
-		vxrs[i] = target->thread.fpu.vxrs[i].low;
+		vxrs[i] = target->thread.ufpu.vxrs[i].low;
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
 	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			target->thread.fpu.vxrs[i].low = vxrs[i];
+			target->thread.ufpu.vxrs[i].low = vxrs[i];
 
 	return rc;
 }
@@ -1025,8 +988,8 @@ static int s390_vxrs_high_get(struct task_struct *target,
 	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
-		save_fpu_regs();
-	return membuf_write(&to, target->thread.fpu.vxrs + __NUM_VXRS_LOW,
+		save_user_fpu_regs();
+	return membuf_write(&to, target->thread.ufpu.vxrs + __NUM_VXRS_LOW,
 			    __NUM_VXRS_HIGH * sizeof(__vector128));
 }
 
@@ -1040,10 +1003,10 @@ static int s390_vxrs_high_set(struct task_struct *target,
 	if (!cpu_has_vx())
 		return -ENODEV;
 	if (target == current)
-		save_fpu_regs();
+		save_user_fpu_regs();
 
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				target->thread.fpu.vxrs + __NUM_VXRS_LOW, 0, -1);
+				target->thread.ufpu.vxrs + __NUM_VXRS_LOW, 0, -1);
 	return rc;
 }
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d1f3b56e7afc..24ed33f044ec 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -504,12 +504,12 @@ static void __init setup_resources(void)
 	int j;
 	u64 i;
 
-	code_resource.start = (unsigned long) _text;
-	code_resource.end = (unsigned long) _etext - 1;
-	data_resource.start = (unsigned long) _etext;
-	data_resource.end = (unsigned long) _edata - 1;
-	bss_resource.start = (unsigned long) __bss_start;
-	bss_resource.end = (unsigned long) __bss_stop - 1;
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext) - 1;
+	data_resource.start = __pa_symbol(_etext);
+	data_resource.end = __pa_symbol(_edata) - 1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop) - 1;
 
 	for_each_mem_range(i, &start, &end) {
 		res = memblock_alloc(sizeof(*res), 8);
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 43e9661cd715..6c2cb345402f 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -30,8 +30,8 @@
 #include <linux/compat.h>
 #include <asm/ucontext.h>
 #include <linux/uaccess.h>
+#include <asm/access-regs.h>
 #include <asm/lowcore.h>
-#include <asm/switch_to.h>
 #include <asm/vdso.h>
 #include "entry.h"
 
@@ -109,7 +109,7 @@ struct rt_sigframe
 static void store_sigregs(void)
 {
 	save_access_regs(current->thread.acrs);
-	save_fpu_regs();
+	save_user_fpu_regs();
 }
 
 /* Load registers after signal return */
@@ -131,7 +131,7 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	fpregs_store(&user_sregs.fpregs, &current->thread.fpu);
+	fpregs_store(&user_sregs.fpregs, &current->thread.ufpu);
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
 		return -EFAULT;
 	return 0;
@@ -165,7 +165,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
 
-	fpregs_load(&user_sregs.fpregs, &current->thread.fpu);
+	fpregs_load(&user_sregs.fpregs, &current->thread.ufpu);
 
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
@@ -181,11 +181,11 @@ static int save_sigregs_ext(struct pt_regs *regs,
 	/* Save vector registers to signal stack */
 	if (cpu_has_vx()) {
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			vxrs[i] = current->thread.fpu.vxrs[i].low;
+			vxrs[i] = current->thread.ufpu.vxrs[i].low;
 		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
 				   sizeof(sregs_ext->vxrs_low)) ||
 		    __copy_to_user(&sregs_ext->vxrs_high,
-				   current->thread.fpu.vxrs + __NUM_VXRS_LOW,
+				   current->thread.ufpu.vxrs + __NUM_VXRS_LOW,
 				   sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 	}
@@ -202,12 +202,12 @@ static int restore_sigregs_ext(struct pt_regs *regs,
 	if (cpu_has_vx()) {
 		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
 				     sizeof(sregs_ext->vxrs_low)) ||
-		    __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW,
+		    __copy_from_user(current->thread.ufpu.vxrs + __NUM_VXRS_LOW,
 				     &sregs_ext->vxrs_high,
 				     sizeof(sregs_ext->vxrs_high)))
 			return -EFAULT;
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
-			current->thread.fpu.vxrs[i].low = vxrs[i];
+			current->thread.ufpu.vxrs[i].low = vxrs[i];
 	}
 	return 0;
 }
@@ -222,7 +222,7 @@ SYSCALL_DEFINE0(sigreturn)
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
 		goto badframe;
 	set_current_blocked(&set);
-	save_fpu_regs();
+	save_user_fpu_regs();
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
 	if (restore_sigregs_ext(regs, &frame->sregs_ext))
@@ -246,7 +246,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	set_current_blocked(&set);
 	if (restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
-	save_fpu_regs();
+	save_user_fpu_regs();
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index c39d9f0d4b1c..0324649aae0a 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -36,12 +36,13 @@
 #include <linux/sched/task_stack.h>
 #include <linux/crash_dump.h>
 #include <linux/kprobes.h>
+#include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/ctlreg.h>
 #include <asm/pfault.h>
 #include <asm/diag.h>
-#include <asm/switch_to.h>
 #include <asm/facility.h>
+#include <asm/fpu.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index f6f8f498c9be..1b1be3110cfc 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -20,7 +20,7 @@
 #include <asm/sysinfo.h>
 #include <asm/cpcmd.h>
 #include <asm/topology.h>
-#include <asm/fpu/api.h>
+#include <asm/fpu.h>
 
 int topology_max_mnest;
 
@@ -426,9 +426,9 @@ subsys_initcall(create_proc_service_level);
  */
 void s390_adjust_jiffies(void)
 {
+	DECLARE_KERNEL_FPU_ONSTACK16(fpu);
 	struct sysinfo_1_2_2 *info;
 	unsigned long capability;
-	struct kernel_fpu fpu;
 
 	info = (void *) get_zeroed_page(GFP_KERNEL);
 	if (!info)
@@ -447,21 +447,14 @@ void s390_adjust_jiffies(void)
 		 * point division ..
 		 */
 		kernel_fpu_begin(&fpu, KERNEL_FPR);
-		asm volatile(
-			"	sfpc	%3\n"
-			"	l	%0,%1\n"
-			"	tmlh	%0,0xff80\n"
-			"	jnz	0f\n"
-			"	cefbr	%%f2,%0\n"
-			"	j	1f\n"
-			"0:	le	%%f2,%1\n"
-			"1:	cefbr	%%f0,%2\n"
-			"	debr	%%f0,%%f2\n"
-			"	cgebr	%0,5,%%f0\n"
-			: "=&d" (capability)
-			: "Q" (info->capability), "d" (10000000), "d" (0)
-			: "cc"
-			);
+		fpu_sfpc(0);
+		if (info->capability & 0xff800000)
+			fpu_ldgr(2, info->capability);
+		else
+			fpu_cefbr(2, info->capability);
+		fpu_cefbr(0, 10000000);
+		fpu_debr(0, 2);
+		capability = fpu_cgebr(0, 5);
 		kernel_fpu_end(&fpu, KERNEL_FPR);
 	} else
 		/*
diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S
index 14c6d25c035f..c0a70efa2426 100644
--- a/arch/s390/kernel/text_amode31.S
+++ b/arch/s390/kernel/text_amode31.S
@@ -90,7 +90,7 @@ SYM_FUNC_START(_diag26c_amode31)
 SYM_FUNC_END(_diag26c_amode31)
 
 /*
- * void _diag0c_amode31(struct hypfs_diag0c_entry *entry)
+ * void _diag0c_amode31(unsigned long rx)
  */
 SYM_FUNC_START(_diag0c_amode31)
 	sam31
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 14abad953c02..fb9f31f36628 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -251,8 +251,8 @@ static struct clocksource clocksource_tod = {
 	.rating		= 400,
 	.read		= read_tod_clock,
 	.mask		= CLOCKSOURCE_MASK(64),
-	.mult		= 1000,
-	.shift		= 12,
+	.mult		= 4096000,
+	.shift		= 24,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	.vdso_clock_mode = VDSO_CLOCKMODE_TOD,
 };
@@ -716,7 +716,7 @@ out_unlock:
 /*
  * STP subsys sysfs interface functions
  */
-static struct bus_type stp_subsys = {
+static const struct bus_type stp_subsys = {
 	.name		= "stp",
 	.dev_name	= "stp",
 };
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 46dac4540ca8..52578b5cecbd 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -28,8 +28,8 @@
 #include <linux/cpu.h>
 #include <linux/entry-common.h>
 #include <asm/asm-extable.h>
-#include <asm/fpu/api.h>
 #include <asm/vtime.h>
+#include <asm/fpu.h>
 #include "entry.h"
 
 static inline void __user *get_trap_ip(struct pt_regs *regs)
@@ -201,8 +201,8 @@ static void vector_exception(struct pt_regs *regs)
 	}
 
 	/* get vector interrupt code from fpc */
-	save_fpu_regs();
-	vic = (current->thread.fpu.fpc & 0xf00) >> 8;
+	save_user_fpu_regs();
+	vic = (current->thread.ufpu.fpc & 0xf00) >> 8;
 	switch (vic) {
 	case 1: /* invalid vector operation */
 		si_code = FPE_FLTINV;
@@ -227,9 +227,9 @@ static void vector_exception(struct pt_regs *regs)
 
 static void data_exception(struct pt_regs *regs)
 {
-	save_fpu_regs();
-	if (current->thread.fpu.fpc & FPC_DXC_MASK)
-		do_fp_trap(regs, current->thread.fpu.fpc);
+	save_user_fpu_regs();
+	if (current->thread.ufpu.fpc & FPC_DXC_MASK)
+		do_fp_trap(regs, current->thread.ufpu.fpc);
 	else
 		do_trap(regs, SIGILL, ILL_ILLOPN, "data exception");
 }
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index b88345ef8bd9..5b0633ea8d93 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -12,7 +12,6 @@
 #include <linux/kdebug.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm/switch_to.h>
 #include <asm/facility.h>
 #include <asm/kprobes.h>
 #include <asm/dis.h>
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index bbaefd84f15e..a45b3a4c91db 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -25,10 +25,7 @@ extern char vdso32_start[], vdso32_end[];
 
 static struct vm_special_mapping vvar_mapping;
 
-static union {
-	struct vdso_data	data[CS_BASES];
-	u8			page[PAGE_SIZE];
-} vdso_data_store __page_aligned_data;
+static union vdso_data_store vdso_data_store __page_aligned_data;
 
 struct vdso_data *vdso_data = vdso_data_store.data;
 
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index caec7db6f966..b12a274cbb47 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -22,7 +22,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin
 
-LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \
+LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \
 	--hash-style=both --build-id=sha1 -melf_s390 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
index edf5ff1debe1..65b9513a5a0e 100644
--- a/arch/s390/kernel/vdso32/vdso32.lds.S
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -9,7 +9,6 @@
 
 OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
 OUTPUT_ARCH(s390:31-bit)
-ENTRY(_start)
 
 SECTIONS
 {
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index e3c9085f8fa7..ef9832726097 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -25,8 +25,9 @@ KBUILD_AFLAGS_64 += -m64
 
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_64))
+KBUILD_CFLAGS_64 := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_64))
 KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin
-ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \
+ldflags-y := -shared -soname=linux-vdso64.so.1 \
 	     --hash-style=both --build-id=sha1 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index 4461ea151e49..37e2a505e81d 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -9,7 +9,6 @@
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
-ENTRY(_start)
 
 SECTIONS
 {
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index e32ef446f451..48de296e8905 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -59,6 +59,14 @@ SECTIONS
 	} :text = 0x0700
 
 	RO_DATA(PAGE_SIZE)
+	.data.rel.ro : {
+		*(.data.rel.ro .data.rel.ro.*)
+	}
+	.got : {
+		__got_start = .;
+		*(.got)
+		__got_end = .;
+	}
 
 	. = ALIGN(PAGE_SIZE);
 	_sdata = .;		/* Start of data section */
@@ -73,6 +81,9 @@ SECTIONS
 	__end_ro_after_init = .;
 
 	RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
+	.data.rel : {
+		*(.data.rel*)
+	}
 	BOOT_DATA_PRESERVED
 
 	. = ALIGN(8);
@@ -181,6 +192,7 @@ SECTIONS
 
 	PERCPU_SECTION(0x100)
 
+#ifdef CONFIG_PIE_BUILD
 	.dynsym ALIGN(8) : {
 		__dynsym_start = .;
 		*(.dynsym)
@@ -191,6 +203,19 @@ SECTIONS
 		*(.rela*)
 		__rela_dyn_end = .;
 	}
+	.dynamic ALIGN(8) : {
+		*(.dynamic)
+	}
+	.dynstr ALIGN(8) : {
+		*(.dynstr)
+	}
+#endif
+	.hash ALIGN(8) : {
+		*(.hash)
+	}
+	.gnu.hash ALIGN(8) : {
+		*(.gnu.hash)
+	}
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
@@ -214,9 +239,14 @@ SECTIONS
 		QUAD(__boot_data_preserved_start)		/* bootdata_preserved_off */
 		QUAD(__boot_data_preserved_end -
 		     __boot_data_preserved_start)		/* bootdata_preserved_size */
+#ifdef CONFIG_PIE_BUILD
 		QUAD(__dynsym_start)				/* dynsym_start */
 		QUAD(__rela_dyn_start)				/* rela_dyn_start */
 		QUAD(__rela_dyn_end)				/* rela_dyn_end */
+#else
+		QUAD(__got_start)				/* got_start */
+		QUAD(__got_end)					/* got_end */
+#endif
 		QUAD(_eamode31 - _samode31)			/* amode31_size */
 		QUAD(init_mm)
 		QUAD(swapper_pg_dir)
@@ -235,6 +265,30 @@ SECTIONS
 	DWARF_DEBUG
 	ELF_DETAILS
 
+	/*
+	 * Make sure that the .got.plt is either completely empty or it
+	 * contains only the three reserved double words.
+	 */
+	.got.plt : {
+		*(.got.plt)
+	}
+	ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!")
+
+	/*
+	 * Sections that should stay zero sized, which is safer to
+	 * explicitly check instead of blindly discarding.
+	 */
+	.plt : {
+		*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
+	}
+	ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+#ifndef CONFIG_PIE_BUILD
+	.rela.dyn : {
+		*(.rela.*) *(.rela_*)
+	}
+	ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
+#endif
+
 	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 5bfcc50c1a68..ee863566910b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -11,11 +11,11 @@
 #include <linux/err.h>
 #include <linux/pgtable.h>
 #include <linux/bitfield.h>
+#include <asm/access-regs.h>
 #include <asm/fault.h>
 #include <asm/gmap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
-#include <asm/switch_to.h>
 
 union asce {
 	unsigned long val;
@@ -391,7 +391,8 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar,
 	if (ar >= NUM_ACRS)
 		return -EINVAL;
 
-	save_access_regs(vcpu->run->s.regs.acrs);
+	if (vcpu->arch.acrs_loaded)
+		save_access_regs(vcpu->run->s.regs.acrs);
 	alet.val = vcpu->run->s.regs.acrs[ar];
 
 	if (ar == 0 || alet.val == 0) {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fc4007cc067a..dc721d50a942 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -19,13 +19,13 @@
 #include <linux/slab.h>
 #include <linux/bitmap.h>
 #include <linux/vmalloc.h>
+#include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/dis.h>
 #include <linux/uaccess.h>
 #include <asm/sclp.h>
 #include <asm/isc.h>
 #include <asm/gmap.h>
-#include <asm/switch_to.h>
 #include <asm/nmi.h>
 #include <asm/airq.h>
 #include <asm/tpi.h>
@@ -584,7 +584,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 
 	mci.val = mchk->mcic;
 	/* take care of lazy register loading */
-	save_fpu_regs();
+	kvm_s390_fpu_store(vcpu->run);
 	save_access_regs(vcpu->run->s.regs.acrs);
 	if (MACHINE_HAS_GS && vcpu->arch.gs_enabled)
 		save_gs_cb(current->thread.gs_cb);
@@ -648,7 +648,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu,
 	}
 	rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA,
 			     vcpu->run->s.regs.gprs, 128);
-	rc |= put_guest_lc(vcpu, current->thread.fpu.fpc,
+	rc |= put_guest_lc(vcpu, vcpu->run->s.regs.fpc,
 			   (u32 __user *) __LC_FP_CREG_SAVE_AREA);
 	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr,
 			   (u32 __user *) __LC_TOD_PROGREG_SAVE_AREA);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ea63ac769889..b11bb8e780a1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -33,19 +33,19 @@
 #include <linux/pgtable.h>
 #include <linux/mmu_notifier.h>
 
+#include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
 #include <asm/stp.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
-#include <asm/switch_to.h>
 #include <asm/isc.h>
 #include <asm/sclp.h>
 #include <asm/cpacf.h>
 #include <asm/timex.h>
+#include <asm/fpu.h>
 #include <asm/ap.h>
 #include <asm/uv.h>
-#include <asm/fpu/api.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "pci.h"
@@ -3951,6 +3951,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_ARCH0 |
 				    KVM_SYNC_PFAULT |
 				    KVM_SYNC_DIAG318;
+	vcpu->arch.acrs_loaded = false;
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
@@ -4829,8 +4830,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			       vcpu->run->s.regs.gprs,
 			       sizeof(sie_page->pv_grregs));
 		}
-		if (test_cpu_flag(CIF_FPU))
-			load_fpu_regs();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
 		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
@@ -4951,16 +4950,8 @@ static void sync_regs(struct kvm_vcpu *vcpu)
 	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
-	/* save host (userspace) fprs/vrs */
-	save_fpu_regs();
-	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
-	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
-	if (cpu_has_vx())
-		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
-	else
-		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
-	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-
+	vcpu->arch.acrs_loaded = true;
+	kvm_s390_fpu_load(vcpu->run);
 	/* Sync fmt2 only data */
 	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
 		sync_regs_fmt2(vcpu);
@@ -5021,12 +5012,8 @@ static void store_regs(struct kvm_vcpu *vcpu)
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
-	/* Save guest register state */
-	save_fpu_regs();
-	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	/* Restore will be done lazily at return */
-	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
-	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
+	vcpu->arch.acrs_loaded = false;
+	kvm_s390_fpu_store(vcpu->run);
 	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu)))
 		store_regs_fmt2(vcpu);
 }
@@ -5034,6 +5021,7 @@ static void store_regs(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
+	DECLARE_KERNEL_FPU_ONSTACK32(fpu);
 	int rc;
 
 	/*
@@ -5075,6 +5063,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR);
 	sync_regs(vcpu);
 	enable_cpu_timer_accounting(vcpu);
 
@@ -5098,6 +5087,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 	disable_cpu_timer_accounting(vcpu);
 	store_regs(vcpu);
+	kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR);
 
 	kvm_sigset_deactivate(vcpu);
 
@@ -5172,8 +5162,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * switch in the run ioctl. Let's update our copies before we save
 	 * it into the save area
 	 */
-	save_fpu_regs();
-	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
+	kvm_s390_fpu_store(vcpu->run);
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a7ea80cfa445..111eb5c74784 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -20,6 +20,24 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
+static inline void kvm_s390_fpu_store(struct kvm_run *run)
+{
+	fpu_stfpc(&run->s.regs.fpc);
+	if (cpu_has_vx())
+		save_vx_regs((__vector128 *)&run->s.regs.vrs);
+	else
+		save_fp_regs((freg_t *)&run->s.regs.fprs);
+}
+
+static inline void kvm_s390_fpu_load(struct kvm_run *run)
+{
+	fpu_lfpc_safe(&run->s.regs.fpc);
+	if (cpu_has_vx())
+		load_vx_regs((__vector128 *)&run->s.regs.vrs);
+	else
+		load_fp_regs((freg_t *)&run->s.regs.fprs);
+}
+
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & ECB_TE))
 #define TDB_FORMAT1		1
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 621a17fd1a1b..f875a404a0a0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -676,8 +676,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.crypto.pqap_hook) {
 		pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook;
 		ret = pqap_hook(vcpu);
-		if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000)
-			kvm_s390_set_psw_cc(vcpu, 3);
+		if (!ret) {
+			if (vcpu->run->s.regs.gprs[1] & 0x00ff0000)
+				kvm_s390_set_psw_cc(vcpu, 3);
+			else
+				kvm_s390_set_psw_cc(vcpu, 0);
+		}
 		up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem);
 		return ret;
 	}
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index fef42e2a80a2..b2c9f010f0fe 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -18,7 +18,6 @@
 #include <asm/sclp.h>
 #include <asm/nmi.h>
 #include <asm/dis.h>
-#include <asm/fpu/api.h>
 #include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -1149,8 +1148,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	 */
 	vcpu->arch.sie_block->prog0c |= PROG_IN_SIE;
 	barrier();
-	if (test_cpu_flag(CIF_FPU))
-		load_fpu_regs();
 	if (!kvm_s390_vcpu_sie_inhibited(vcpu))
 		rc = sie64a(scb_s, vcpu->run->s.regs.gprs);
 	barrier();
@@ -1235,7 +1232,6 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
 	gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
 	if (IS_ERR(gmap))
 		return PTR_ERR(gmap);
-	gmap->private = vcpu->kvm;
 	vcpu->kvm->stat.gmap_shadow_create++;
 	WRITE_ONCE(vsie_page->gmap, gmap);
 	return 0;
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 7c50eca85ca4..90eac15ea62a 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -4,6 +4,7 @@
 #
 
 lib-y += delay.o string.o uaccess.o find.o spinlock.o tishift.o
+lib-y += csum-partial.o
 obj-y += mem.o xor.o
 lib-$(CONFIG_KPROBES) += probes.o
 lib-$(CONFIG_UPROBES) += probes.o
diff --git a/arch/s390/lib/csum-partial.c b/arch/s390/lib/csum-partial.c
new file mode 100644
index 000000000000..458abd9bac70
--- /dev/null
+++ b/arch/s390/lib/csum-partial.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <asm/checksum.h>
+#include <asm/fpu.h>
+
+/*
+ * Computes the checksum of a memory block at src, length len,
+ * and adds in "sum" (32-bit). If copy is true copies to dst.
+ *
+ * Returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic.
+ *
+ * This function must be called with even lengths, except
+ * for the last fragment, which may be odd.
+ *
+ * It's best to have src and dst aligned on a 64-bit boundary.
+ */
+static __always_inline __wsum csum_copy(void *dst, const void *src, int len, __wsum sum, bool copy)
+{
+	DECLARE_KERNEL_FPU_ONSTACK8(vxstate);
+
+	if (!cpu_has_vx()) {
+		if (copy)
+			memcpy(dst, src, len);
+		return cksm(dst, len, sum);
+	}
+	kernel_fpu_begin(&vxstate, KERNEL_VXR_V16V23);
+	fpu_vlvgf(16, (__force u32)sum, 1);
+	fpu_vzero(17);
+	fpu_vzero(18);
+	fpu_vzero(19);
+	while (len >= 64) {
+		fpu_vlm(20, 23, src);
+		if (copy) {
+			fpu_vstm(20, 23, dst);
+			dst += 64;
+		}
+		fpu_vcksm(16, 20, 16);
+		fpu_vcksm(17, 21, 17);
+		fpu_vcksm(18, 22, 18);
+		fpu_vcksm(19, 23, 19);
+		src += 64;
+		len -= 64;
+	}
+	while (len >= 32) {
+		fpu_vlm(20, 21, src);
+		if (copy) {
+			fpu_vstm(20, 21, dst);
+			dst += 32;
+		}
+		fpu_vcksm(16, 20, 16);
+		fpu_vcksm(17, 21, 17);
+		src += 32;
+		len -= 32;
+	}
+	while (len >= 16) {
+		fpu_vl(20, src);
+		if (copy) {
+			fpu_vst(20, dst);
+			dst += 16;
+		}
+		fpu_vcksm(16, 20, 16);
+		src += 16;
+		len -= 16;
+	}
+	if (len) {
+		fpu_vll(20, len - 1, src);
+		if (copy)
+			fpu_vstl(20, len - 1, dst);
+		fpu_vcksm(16, 20, 16);
+	}
+	fpu_vcksm(18, 19, 18);
+	fpu_vcksm(16, 17, 16);
+	fpu_vcksm(16, 18, 16);
+	sum = (__force __wsum)fpu_vlgvf(16, 1);
+	kernel_fpu_end(&vxstate, KERNEL_VXR_V16V23);
+	return sum;
+}
+
+__wsum csum_partial(const void *buff, int len, __wsum sum)
+{
+	return csum_copy(NULL, buff, len, sum, false);
+}
+EXPORT_SYMBOL(csum_partial);
+
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+	return csum_copy(dst, src, len, 0, true);
+}
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index e41869f5cc95..282fefe107a2 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -136,7 +136,7 @@ dcss_diag(int *func, void *parameter,
 	unsigned long rx, ry;
 	int rc;
 
-	rx = (unsigned long) parameter;
+	rx = virt_to_phys(parameter);
 	ry = (unsigned long) *func;
 
 	diag_stat_inc(DIAG_STAT_X064);
@@ -178,7 +178,7 @@ query_segment_type (struct dcss_segment *seg)
 
 	/* initialize diag input parameters */
 	qin->qopcode = DCSS_FINDSEGA;
-	qin->qoutptr = (unsigned long) qout;
+	qin->qoutptr = virt_to_phys(qout);
 	qin->qoutlen = sizeof(struct qout64);
 	memcpy (qin->qname, seg->dcss_name, 8);
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 6f96b5a71c63..8da39deb56ca 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1691,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 		return ERR_PTR(-ENOMEM);
 	new->mm = parent->mm;
 	new->parent = gmap_get(parent);
+	new->private = parent->private;
 	new->orig_asce = asce;
 	new->edat_level = edat_level;
 	new->initialized = false;
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index fc9a7dc26c5e..b14fc0887654 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -71,6 +71,15 @@ static inline unsigned long mmap_base(unsigned long rnd,
 	return PAGE_ALIGN(STACK_TOP - gap - rnd);
 }
 
+static int get_align_mask(struct file *filp, unsigned long flags)
+{
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
+	if (filp || (flags & MAP_SHARED))
+		return MMAP_ALIGN_MASK << PAGE_SHIFT;
+	return 0;
+}
+
 unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 				     unsigned long len, unsigned long pgoff,
 				     unsigned long flags)
@@ -97,10 +106,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
-	if (filp || (flags & MAP_SHARED))
-		info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
-	else
-		info.align_mask = 0;
+	info.align_mask = get_align_mask(filp, flags);
 	info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 	if (offset_in_page(addr))
@@ -138,10 +144,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	if (filp || (flags & MAP_SHARED))
-		info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT;
-	else
-		info.align_mask = 0;
+	info.align_mask = get_align_mask(filp, flags);
 	info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 676ac74026a8..26afde0d1ed3 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -28,6 +28,7 @@
 #include <linux/jump_label.h>
 #include <linux/pci.h>
 #include <linux/printk.h>
+#include <linux/lockdep.h>
 
 #include <asm/isc.h>
 #include <asm/airq.h>
@@ -252,7 +253,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 /* combine single writes by using store-block insn */
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 {
-       zpci_memcpy_toio(to, from, count);
+	zpci_memcpy_toio(to, from, count * 8);
 }
 
 void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
@@ -730,12 +731,12 @@ EXPORT_SYMBOL_GPL(zpci_disable_device);
  * equivalent to its state during boot when first probing a driver.
  * Consequently after reset the PCI function requires re-initialization via the
  * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors()
- * and enabling the function via e.g.pci_enablde_device_flags().The caller
+ * and enabling the function via e.g. pci_enable_device_flags(). The caller
  * must guard against concurrent reset attempts.
  *
  * In most cases this function should not be called directly but through
  * pci_reset_function() or pci_reset_bus() which handle the save/restore and
- * locking.
+ * locking - asserted by lockdep.
  *
  * Return: 0 on success and an error value otherwise
  */
@@ -744,6 +745,7 @@ int zpci_hot_reset_device(struct zpci_dev *zdev)
 	u8 status;
 	int rc;
 
+	lockdep_assert_held(&zdev->state_lock);
 	zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh);
 	if (zdev_enabled(zdev)) {
 		/* Disables device access, DMAs and IRQs (reset state) */
@@ -806,7 +808,8 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
 	zdev->state =  state;
 
 	kref_init(&zdev->kref);
-	mutex_init(&zdev->lock);
+	mutex_init(&zdev->state_lock);
+	mutex_init(&zdev->fmb_lock);
 	mutex_init(&zdev->kzdev_lock);
 
 	rc = zpci_init_iommu(zdev);
@@ -870,6 +873,10 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
 {
 	int rc;
 
+	lockdep_assert_held(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		return 0;
+
 	if (zdev->zbus->bus)
 		zpci_bus_remove_device(zdev, false);
 
@@ -889,7 +896,7 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
 }
 
 /**
- * zpci_device_reserved() - Mark device as resverved
+ * zpci_device_reserved() - Mark device as reserved
  * @zdev: the zpci_dev that was reserved
  *
  * Handle the case that a given zPCI function was reserved by another system.
@@ -899,8 +906,6 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
  */
 void zpci_device_reserved(struct zpci_dev *zdev)
 {
-	if (zdev->has_hp_slot)
-		zpci_exit_slot(zdev);
 	/*
 	 * Remove device from zpci_list as it is going away. This also
 	 * makes sure we ignore subsequent zPCI events for this device.
@@ -918,6 +923,9 @@ void zpci_release_device(struct kref *kref)
 	struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
 	int ret;
 
+	if (zdev->has_hp_slot)
+		zpci_exit_slot(zdev);
+
 	if (zdev->zbus->bus)
 		zpci_bus_remove_device(zdev, false);
 
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 6dde2263c79d..2cb5043a997d 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -91,9 +91,9 @@ static int pci_perf_show(struct seq_file *m, void *v)
 	if (!zdev)
 		return 0;
 
-	mutex_lock(&zdev->lock);
+	mutex_lock(&zdev->fmb_lock);
 	if (!zdev->fmb) {
-		mutex_unlock(&zdev->lock);
+		mutex_unlock(&zdev->fmb_lock);
 		seq_puts(m, "FMB statistics disabled\n");
 		return 0;
 	}
@@ -130,7 +130,7 @@ static int pci_perf_show(struct seq_file *m, void *v)
 	}
 
 	pci_sw_counter_show(m);
-	mutex_unlock(&zdev->lock);
+	mutex_unlock(&zdev->fmb_lock);
 	return 0;
 }
 
@@ -148,7 +148,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
 	if (rc)
 		return rc;
 
-	mutex_lock(&zdev->lock);
+	mutex_lock(&zdev->fmb_lock);
 	switch (val) {
 	case 0:
 		rc = zpci_fmb_disable_device(zdev);
@@ -157,7 +157,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf,
 		rc = zpci_fmb_enable_device(zdev);
 		break;
 	}
-	mutex_unlock(&zdev->lock);
+	mutex_unlock(&zdev->fmb_lock);
 	return rc ? rc : count;
 }
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 4d9773ef9e0a..dbe95ec5917e 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -267,6 +267,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
 	if (zdev) {
+		mutex_lock(&zdev->state_lock);
 		zpci_update_fh(zdev, ccdf->fh);
 		if (zdev->zbus->bus)
 			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
@@ -294,6 +295,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	}
 	pci_dev_put(pdev);
 no_pdev:
+	if (zdev)
+		mutex_unlock(&zdev->state_lock);
 	zpci_zdev_put(zdev);
 }
 
@@ -326,6 +329,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 
 	zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
+
+	if (existing_zdev)
+		mutex_lock(&zdev->state_lock);
+
 	switch (ccdf->pec) {
 	case 0x0301: /* Reserved|Standby -> Configured */
 		if (!zdev) {
@@ -348,7 +355,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (zdev) {
-			/* The event may have been queued before we confirgured
+			/* The event may have been queued before we configured
 			 * the device.
 			 */
 			if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
@@ -359,7 +366,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		break;
 	case 0x0304: /* Configured -> Standby|Reserved */
 		if (zdev) {
-			/* The event may have been queued before we confirgured
+			/* The event may have been queued before we configured
 			 * the device.:
 			 */
 			if (zdev->state == ZPCI_FN_STATE_CONFIGURED)
@@ -383,8 +390,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	default:
 		break;
 	}
-	if (existing_zdev)
+	if (existing_zdev) {
+		mutex_unlock(&zdev->state_lock);
 		zpci_zdev_put(zdev);
+	}
 }
 
 void zpci_event_availability(void *data)
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 8a7abac51816..a0b872b74fe3 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -49,6 +49,39 @@ static ssize_t mio_enabled_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(mio_enabled);
 
+static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev)
+{
+	u8 status;
+	int ret;
+
+	pci_stop_and_remove_bus_device(pdev);
+	if (zdev_enabled(zdev)) {
+		ret = zpci_disable_device(zdev);
+		/*
+		 * Due to a z/VM vs LPAR inconsistency in the error
+		 * state the FH may indicate an enabled device but
+		 * disable says the device is already disabled don't
+		 * treat it as an error here.
+		 */
+		if (ret == -EINVAL)
+			ret = 0;
+		if (ret)
+			return ret;
+	}
+
+	ret = zpci_enable_device(zdev);
+	if (ret)
+		return ret;
+
+	if (zdev->dma_table) {
+		ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+					 virt_to_phys(zdev->dma_table), &status);
+		if (ret)
+			zpci_disable_device(zdev);
+	}
+	return ret;
+}
+
 static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
@@ -56,7 +89,6 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct zpci_dev *zdev = to_zpci(pdev);
 	int ret = 0;
-	u8 status;
 
 	/* Can't use device_remove_self() here as that would lead us to lock
 	 * the pci_rescan_remove_lock while holding the device' kernfs lock.
@@ -70,6 +102,12 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	 */
 	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
 	WARN_ON_ONCE(!kn);
+
+	/* Device needs to be configured and state must not change */
+	mutex_lock(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		goto out;
+
 	/* device_remove_file() serializes concurrent calls ignoring all but
 	 * the first
 	 */
@@ -82,35 +120,13 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
 	 */
 	pci_lock_rescan_remove();
 	if (pci_dev_is_added(pdev)) {
-		pci_stop_and_remove_bus_device(pdev);
-		if (zdev_enabled(zdev)) {
-			ret = zpci_disable_device(zdev);
-			/*
-			 * Due to a z/VM vs LPAR inconsistency in the error
-			 * state the FH may indicate an enabled device but
-			 * disable says the device is already disabled don't
-			 * treat it as an error here.
-			 */
-			if (ret == -EINVAL)
-				ret = 0;
-			if (ret)
-				goto out;
-		}
-
-		ret = zpci_enable_device(zdev);
-		if (ret)
-			goto out;
-
-		if (zdev->dma_table) {
-			ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-						 virt_to_phys(zdev->dma_table), &status);
-			if (ret)
-				zpci_disable_device(zdev);
-		}
+		ret = _do_recover(pdev, zdev);
 	}
-out:
 	pci_rescan_bus(zdev->zbus->bus);
 	pci_unlock_rescan_remove();
+
+out:
+	mutex_unlock(&zdev->state_lock);
 	if (kn)
 		sysfs_unbreak_active_protection(kn);
 	return ret ? ret : count;
diff --git a/arch/s390/tools/.gitignore b/arch/s390/tools/.gitignore
index ea62f37b79ef..e6af51d9d183 100644
--- a/arch/s390/tools/.gitignore
+++ b/arch/s390/tools/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 gen_facilities
 gen_opcode_table
+relocs
diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile
index f9dd47ff9ac4..f2862364fb42 100644
--- a/arch/s390/tools/Makefile
+++ b/arch/s390/tools/Makefile
@@ -25,3 +25,8 @@ $(kapi)/facility-defs.h: $(obj)/gen_facilities FORCE
 
 $(kapi)/dis-defs.h: $(obj)/gen_opcode_table FORCE
 	$(call filechk,dis-defs.h)
+
+hostprogs	+= relocs
+PHONY		+= relocs
+relocs: $(obj)/relocs
+	@:
diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c
new file mode 100644
index 000000000000..30a732c808f3
--- /dev/null
+++ b/arch/s390/tools/relocs.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <elf.h>
+#include <byteswap.h>
+#define USE_BSD
+#include <endian.h>
+
+#define ELF_BITS 64
+
+#define ELF_MACHINE		EM_S390
+#define ELF_MACHINE_NAME	"IBM S/390"
+#define SHT_REL_TYPE		SHT_RELA
+#define Elf_Rel			Elf64_Rela
+
+#define ELF_CLASS		ELFCLASS64
+#define ELF_ENDIAN		ELFDATA2MSB
+#define ELF_R_SYM(val)		ELF64_R_SYM(val)
+#define ELF_R_TYPE(val)		ELF64_R_TYPE(val)
+#define ELF_ST_TYPE(o)		ELF64_ST_TYPE(o)
+#define ELF_ST_BIND(o)		ELF64_ST_BIND(o)
+#define ELF_ST_VISIBILITY(o)	ELF64_ST_VISIBILITY(o)
+
+#define ElfW(type)		_ElfW(ELF_BITS, type)
+#define _ElfW(bits, type)	__ElfW(bits, type)
+#define __ElfW(bits, type)	Elf##bits##_##type
+
+#define Elf_Addr		ElfW(Addr)
+#define Elf_Ehdr		ElfW(Ehdr)
+#define Elf_Phdr		ElfW(Phdr)
+#define Elf_Shdr		ElfW(Shdr)
+#define Elf_Sym			ElfW(Sym)
+
+static Elf_Ehdr		ehdr;
+static unsigned long	shnum;
+static unsigned int	shstrndx;
+
+struct relocs {
+	uint32_t	*offset;
+	unsigned long	count;
+	unsigned long	size;
+};
+
+static struct relocs relocs64;
+#define FMT PRIu64
+
+struct section {
+	Elf_Shdr	shdr;
+	struct section	*link;
+	Elf_Rel		*reltab;
+};
+
+static struct section *secs;
+
+#if BYTE_ORDER == LITTLE_ENDIAN
+#define le16_to_cpu(val)	(val)
+#define le32_to_cpu(val)	(val)
+#define le64_to_cpu(val)	(val)
+#define be16_to_cpu(val)	bswap_16(val)
+#define be32_to_cpu(val)	bswap_32(val)
+#define be64_to_cpu(val)	bswap_64(val)
+#endif
+
+#if BYTE_ORDER == BIG_ENDIAN
+#define le16_to_cpu(val)	bswap_16(val)
+#define le32_to_cpu(val)	bswap_32(val)
+#define le64_to_cpu(val)	bswap_64(val)
+#define be16_to_cpu(val)	(val)
+#define be32_to_cpu(val)	(val)
+#define be64_to_cpu(val)	(val)
+#endif
+
+static uint16_t elf16_to_cpu(uint16_t val)
+{
+	if (ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+		return le16_to_cpu(val);
+	else
+		return be16_to_cpu(val);
+}
+
+static uint32_t elf32_to_cpu(uint32_t val)
+{
+	if (ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+		return le32_to_cpu(val);
+	else
+		return be32_to_cpu(val);
+}
+
+#define elf_half_to_cpu(x)	elf16_to_cpu(x)
+#define elf_word_to_cpu(x)	elf32_to_cpu(x)
+
+static uint64_t elf64_to_cpu(uint64_t val)
+{
+	return be64_to_cpu(val);
+}
+
+#define elf_addr_to_cpu(x)	elf64_to_cpu(x)
+#define elf_off_to_cpu(x)	elf64_to_cpu(x)
+#define elf_xword_to_cpu(x)	elf64_to_cpu(x)
+
+static void die(char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(1);
+}
+
+static void read_ehdr(FILE *fp)
+{
+	if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+		die("Cannot read ELF header: %s\n", strerror(errno));
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0)
+		die("No ELF magic\n");
+	if (ehdr.e_ident[EI_CLASS] != ELF_CLASS)
+		die("Not a %d bit executable\n", ELF_BITS);
+	if (ehdr.e_ident[EI_DATA] != ELF_ENDIAN)
+		die("ELF endian mismatch\n");
+	if (ehdr.e_ident[EI_VERSION] != EV_CURRENT)
+		die("Unknown ELF version\n");
+
+	/* Convert the fields to native endian */
+	ehdr.e_type	 = elf_half_to_cpu(ehdr.e_type);
+	ehdr.e_machine	 = elf_half_to_cpu(ehdr.e_machine);
+	ehdr.e_version	 = elf_word_to_cpu(ehdr.e_version);
+	ehdr.e_entry	 = elf_addr_to_cpu(ehdr.e_entry);
+	ehdr.e_phoff	 = elf_off_to_cpu(ehdr.e_phoff);
+	ehdr.e_shoff	 = elf_off_to_cpu(ehdr.e_shoff);
+	ehdr.e_flags	 = elf_word_to_cpu(ehdr.e_flags);
+	ehdr.e_ehsize	 = elf_half_to_cpu(ehdr.e_ehsize);
+	ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize);
+	ehdr.e_phnum	 = elf_half_to_cpu(ehdr.e_phnum);
+	ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize);
+	ehdr.e_shnum	 = elf_half_to_cpu(ehdr.e_shnum);
+	ehdr.e_shstrndx  = elf_half_to_cpu(ehdr.e_shstrndx);
+
+	shnum = ehdr.e_shnum;
+	shstrndx = ehdr.e_shstrndx;
+
+	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN))
+		die("Unsupported ELF header type\n");
+	if (ehdr.e_machine != ELF_MACHINE)
+		die("Not for %s\n", ELF_MACHINE_NAME);
+	if (ehdr.e_version != EV_CURRENT)
+		die("Unknown ELF version\n");
+	if (ehdr.e_ehsize != sizeof(Elf_Ehdr))
+		die("Bad Elf header size\n");
+	if (ehdr.e_phentsize != sizeof(Elf_Phdr))
+		die("Bad program header entry\n");
+	if (ehdr.e_shentsize != sizeof(Elf_Shdr))
+		die("Bad section header entry\n");
+
+	if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) {
+		Elf_Shdr shdr;
+
+		if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+			die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+			die("Cannot read initial ELF section header: %s\n", strerror(errno));
+
+		if (shnum == SHN_UNDEF)
+			shnum = elf_xword_to_cpu(shdr.sh_size);
+
+		if (shstrndx == SHN_XINDEX)
+			shstrndx = elf_word_to_cpu(shdr.sh_link);
+	}
+
+	if (shstrndx >= shnum)
+		die("String table index out of bounds\n");
+}
+
+static void read_shdrs(FILE *fp)
+{
+	Elf_Shdr shdr;
+	int i;
+
+	secs = calloc(shnum, sizeof(struct section));
+	if (!secs)
+		die("Unable to allocate %ld section headers\n", shnum);
+
+	if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+		die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1) {
+			die("Cannot read ELF section headers %d/%ld: %s\n",
+			    i, shnum, strerror(errno));
+		}
+
+		sec->shdr.sh_name      = elf_word_to_cpu(shdr.sh_name);
+		sec->shdr.sh_type      = elf_word_to_cpu(shdr.sh_type);
+		sec->shdr.sh_flags     = elf_xword_to_cpu(shdr.sh_flags);
+		sec->shdr.sh_addr      = elf_addr_to_cpu(shdr.sh_addr);
+		sec->shdr.sh_offset    = elf_off_to_cpu(shdr.sh_offset);
+		sec->shdr.sh_size      = elf_xword_to_cpu(shdr.sh_size);
+		sec->shdr.sh_link      = elf_word_to_cpu(shdr.sh_link);
+		sec->shdr.sh_info      = elf_word_to_cpu(shdr.sh_info);
+		sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
+		sec->shdr.sh_entsize   = elf_xword_to_cpu(shdr.sh_entsize);
+
+		if (sec->shdr.sh_link < shnum)
+			sec->link = &secs[sec->shdr.sh_link];
+	}
+
+}
+
+static void read_relocs(FILE *fp)
+{
+	int i, j;
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_REL_TYPE)
+			continue;
+
+		sec->reltab = malloc(sec->shdr.sh_size);
+		if (!sec->reltab)
+			die("malloc of %" FMT " bytes for relocs failed\n", sec->shdr.sh_size);
+
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+			die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+		if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+			die("Cannot read symbol table: %s\n", strerror(errno));
+
+		for (j = 0; j < sec->shdr.sh_size / sizeof(Elf_Rel); j++) {
+			Elf_Rel *rel = &sec->reltab[j];
+
+			rel->r_offset = elf_addr_to_cpu(rel->r_offset);
+			rel->r_info   = elf_xword_to_cpu(rel->r_info);
+#if (SHT_REL_TYPE == SHT_RELA)
+			rel->r_addend = elf_xword_to_cpu(rel->r_addend);
+#endif
+		}
+	}
+}
+
+static void add_reloc(struct relocs *r, uint32_t offset)
+{
+	if (r->count == r->size) {
+		unsigned long newsize = r->size + 50000;
+		void *mem = realloc(r->offset, newsize * sizeof(r->offset[0]));
+
+		if (!mem)
+			die("realloc of %ld entries for relocs failed\n", newsize);
+
+		r->offset = mem;
+		r->size = newsize;
+	}
+	r->offset[r->count++] = offset;
+}
+
+static int do_reloc(struct section *sec, Elf_Rel *rel)
+{
+	unsigned int r_type = ELF64_R_TYPE(rel->r_info);
+	ElfW(Addr) offset = rel->r_offset;
+
+	switch (r_type) {
+	case R_390_NONE:
+	case R_390_PC32:
+	case R_390_PC64:
+	case R_390_PC16DBL:
+	case R_390_PC32DBL:
+	case R_390_PLT32DBL:
+	case R_390_GOTENT:
+	case R_390_GOTPCDBL:
+	case R_390_GOTOFF64:
+		break;
+	case R_390_64:
+		add_reloc(&relocs64, offset);
+		break;
+	default:
+		die("Unsupported relocation type: %d\n", r_type);
+		break;
+	}
+
+	return 0;
+}
+
+static void walk_relocs(void)
+{
+	int i;
+
+	/* Walk through the relocations */
+	for (i = 0; i < shnum; i++) {
+		struct section *sec_applies;
+		int j;
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_REL_TYPE)
+			continue;
+
+		sec_applies = &secs[sec->shdr.sh_info];
+		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
+			continue;
+
+		for (j = 0; j < sec->shdr.sh_size / sizeof(Elf_Rel); j++) {
+			Elf_Rel *rel = &sec->reltab[j];
+
+			do_reloc(sec, rel);
+		}
+	}
+}
+
+static int cmp_relocs(const void *va, const void *vb)
+{
+	const uint32_t *a, *b;
+
+	a = va; b = vb;
+	return (*a == *b) ? 0 : (*a > *b) ? 1 : -1;
+}
+
+static void sort_relocs(struct relocs *r)
+{
+	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+}
+
+static int print_reloc(uint32_t v)
+{
+	return fprintf(stdout, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1;
+}
+
+static void emit_relocs(void)
+{
+	int i;
+
+	walk_relocs();
+	sort_relocs(&relocs64);
+
+	printf(".section \".vmlinux.relocs_64\",\"a\"\n");
+	for (i = 0; i < relocs64.count; i++)
+		print_reloc(relocs64.offset[i]);
+}
+
+static void process(FILE *fp)
+{
+	read_ehdr(fp);
+	read_shdrs(fp);
+	read_relocs(fp);
+	emit_relocs();
+}
+
+static void usage(void)
+{
+	die("relocs vmlinux\n");
+}
+
+int main(int argc, char **argv)
+{
+	unsigned char e_ident[EI_NIDENT];
+	const char *fname;
+	FILE *fp;
+
+	fname = NULL;
+
+	if (argc != 2)
+		usage();
+
+	fname = argv[1];
+
+	fp = fopen(fname, "r");
+	if (!fp)
+		die("Cannot open %s: %s\n", fname, strerror(errno));
+
+	if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT)
+		die("Cannot read %s: %s", fname, strerror(errno));
+
+	rewind(fp);
+
+	process(fp);
+
+	fclose(fp);
+	return 0;
+}
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index 62f4b9edcb98..f780b467e75d 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -9,18 +9,7 @@
 #include <linux/const.h>
 
 /* PAGE_SHIFT determines the page size */
-#if defined(CONFIG_PAGE_SIZE_4KB)
-# define PAGE_SHIFT	12
-#elif defined(CONFIG_PAGE_SIZE_8KB)
-# define PAGE_SHIFT	13
-#elif defined(CONFIG_PAGE_SIZE_16KB)
-# define PAGE_SHIFT	14
-#elif defined(CONFIG_PAGE_SIZE_64KB)
-# define PAGE_SHIFT	16
-#else
-# error "Bogus kernel page size?"
-#endif
-
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 #define PTE_MASK	PAGE_MASK
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index 455311d9a5e9..f32a1963ff0c 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -4,6 +4,9 @@ menu "Memory management options"
 config MMU
         bool "Support for memory management hardware"
 	depends on !CPU_SH2
+	select HAVE_PAGE_SIZE_4KB
+	select HAVE_PAGE_SIZE_8KB if X2TLB
+	select HAVE_PAGE_SIZE_64KB if CPU_SH4
 	default y
 	help
 	  Some SH processors (such as SH-2/SH-2A) lack an MMU. In order to
@@ -13,6 +16,15 @@ config MMU
 	  turning this off will boot the kernel on these machines with the
 	  MMU implicitly switched off.
 
+config NOMMU
+	def_bool !MMU
+	select HAVE_PAGE_SIZE_4KB
+	select HAVE_PAGE_SIZE_8KB
+	select HAVE_PAGE_SIZE_16KB
+	select HAVE_PAGE_SIZE_64KB
+	help
+	  On MMU-less systems, any of these page sizes can be selected
+
 config PAGE_OFFSET
 	hex
 	default "0x80000000" if MMU
@@ -148,36 +160,6 @@ config HAVE_SRAM_POOL
 	select GENERIC_ALLOCATOR
 
 choice
-	prompt "Kernel page size"
-	default PAGE_SIZE_4KB
-
-config PAGE_SIZE_4KB
-	bool "4kB"
-	help
-	  This is the default page size used by all SuperH CPUs.
-
-config PAGE_SIZE_8KB
-	bool "8kB"
-	depends on !MMU || X2TLB
-	help
-	  This enables 8kB pages as supported by SH-X2 and later MMUs.
-
-config PAGE_SIZE_16KB
-	bool "16kB"
-	depends on !MMU
-	help
-	  This enables 16kB pages on MMU-less SH systems.
-
-config PAGE_SIZE_64KB
-	bool "64kB"
-	depends on !MMU || CPU_SH4
-	help
-	  This enables support for 64kB pages, possible on all SH-4
-	  CPUs and later.
-
-endchoice
-
-choice
 	prompt "HugeTLB page size"
 	depends on HUGETLB_PAGE
 	default HUGETLB_PAGE_SIZE_1MB if PAGE_SIZE_64KB
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 204c43cb3d43..7e6bc6fff76b 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -58,6 +58,7 @@ config SPARC32
 	select DMA_DIRECT_REMAP
 	select GENERIC_ATOMIC64
 	select HAVE_UID16
+	select HAVE_PAGE_SIZE_4KB
 	select LOCK_MM_AND_FIND_VMA
 	select OLD_SIGACTION
 	select ZONE_DMA
@@ -75,6 +76,7 @@ config SPARC64
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_PAGE_SIZE_8KB
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING_USER
 	select HAVE_TIF_NOHZ
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index 5f6035936131..2a03daa68f28 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -60,7 +60,7 @@ libs-y                 += arch/sparc/prom/
 libs-y                 += arch/sparc/lib/
 
 drivers-$(CONFIG_PM) += arch/sparc/power/
-drivers-$(CONFIG_FB) += arch/sparc/video/
+drivers-$(CONFIG_FB_CORE) += arch/sparc/video/
 
 boot := arch/sparc/boot
 
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 94eb529dcb77..2718cbea826a 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -10,7 +10,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
@@ -26,7 +26,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes]\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
diff --git a/arch/sparc/include/asm/page_32.h b/arch/sparc/include/asm/page_32.h
index 6be6f683f98f..9977c77374cd 100644
--- a/arch/sparc/include/asm/page_32.h
+++ b/arch/sparc/include/asm/page_32.h
@@ -11,7 +11,7 @@
 
 #include <linux/const.h>
 
-#define PAGE_SHIFT   12
+#define PAGE_SHIFT   CONFIG_PAGE_SHIFT
 #define PAGE_SIZE    (_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK    (~(PAGE_SIZE-1))
 
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index 254dffd85fb1..e9bd24821c93 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -4,8 +4,7 @@
 
 #include <linux/const.h>
 
-#define PAGE_SHIFT   13
-
+#define PAGE_SHIFT   CONFIG_PAGE_SHIFT
 #define PAGE_SIZE    (_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK    (~(PAGE_SIZE-1))
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index f3969a3600db..a0cc9bb41a92 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1206,10 +1206,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 }
 
-void smp_prepare_boot_cpu(void)
-{
-}
-
 void __init smp_setup_processor_id(void)
 {
 	if (tlb_type == spitfire)
diff --git a/arch/sparc/video/Makefile b/arch/sparc/video/Makefile
index 6baddbd58e4d..d4d83f1702c6 100644
--- a/arch/sparc/video/Makefile
+++ b/arch/sparc/video/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-obj-$(CONFIG_FB) += fbdev.o
+obj-$(CONFIG_FB_CORE) += fbdev.o
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index b5e179360534..93a5a8999b07 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -20,6 +20,7 @@ config UML
 	select HAVE_UID16
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_BUGVERBOSE
+	select HAVE_PAGE_SIZE_4KB
 	select NO_DMA if !UML_DMA_EMULATION
 	select OF_EARLY_FLATTREE if OF
 	select GENERIC_IRQ_SHOW
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 82f05f250634..34957dcb88b9 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -115,7 +115,9 @@ archprepare:
 	$(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h
 
 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie)
+ifdef CONFIG_LD_SCRIPT_DYN
+LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie
+endif
 LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib
 
 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 92ee2697ff39..63fc062add70 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -108,8 +108,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 static DEFINE_MUTEX(ubd_lock);
 static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode);
-static void ubd_release(struct gendisk *disk);
 static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
@@ -118,16 +116,11 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 static const struct block_device_operations ubd_blops = {
         .owner		= THIS_MODULE,
-        .open		= ubd_open,
-        .release	= ubd_release,
         .ioctl		= ubd_ioctl,
         .compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= ubd_getgeo,
 };
 
-/* Protected by ubd_lock */
-static struct gendisk *ubd_gendisk[MAX_DEV];
-
 #ifdef CONFIG_BLK_DEV_UBD_SYNC
 #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \
 					 .cl = 1 })
@@ -155,7 +148,6 @@ struct ubd {
 	 * backing or the cow file. */
 	char *file;
 	char *serial;
-	int count;
 	int fd;
 	__u64 size;
 	struct openflags boot_openflags;
@@ -165,7 +157,7 @@ struct ubd {
 	unsigned no_trim:1;
 	struct cow cow;
 	struct platform_device pdev;
-	struct request_queue *queue;
+	struct gendisk *disk;
 	struct blk_mq_tag_set tag_set;
 	spinlock_t lock;
 };
@@ -181,7 +173,6 @@ struct ubd {
 #define DEFAULT_UBD { \
 	.file = 		NULL, \
 	.serial =		NULL, \
-	.count =		0, \
 	.fd =			-1, \
 	.size =			-1, \
 	.boot_openflags =	OPEN_FLAGS, \
@@ -774,8 +765,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 	ubd_dev->fd = fd;
 
 	if(ubd_dev->cow.file != NULL){
-		blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long));
-
 		err = -ENOMEM;
 		ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len);
 		if(ubd_dev->cow.bitmap == NULL){
@@ -797,11 +786,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		if(err < 0) goto error;
 		ubd_dev->cow.fd = err;
 	}
-	if (ubd_dev->no_trim == 0) {
-		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
-	}
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue);
 	return 0;
  error:
 	os_close_file(ubd_dev->fd);
@@ -851,27 +835,6 @@ static const struct attribute_group *ubd_attr_groups[] = {
 	NULL,
 };
 
-static int ubd_disk_register(int major, u64 size, int unit,
-			     struct gendisk *disk)
-{
-	disk->major = major;
-	disk->first_minor = unit << UBD_SHIFT;
-	disk->minors = 1 << UBD_SHIFT;
-	disk->fops = &ubd_blops;
-	set_capacity(disk, size / 512);
-	sprintf(disk->disk_name, "ubd%c", 'a' + unit);
-
-	ubd_devs[unit].pdev.id   = unit;
-	ubd_devs[unit].pdev.name = DRIVER_NAME;
-	ubd_devs[unit].pdev.dev.release = ubd_device_release;
-	dev_set_drvdata(&ubd_devs[unit].pdev.dev, &ubd_devs[unit]);
-	platform_device_register(&ubd_devs[unit].pdev);
-
-	disk->private_data = &ubd_devs[unit];
-	disk->queue = ubd_devs[unit].queue;
-	return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
-}
-
 #define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
 
 static const struct blk_mq_ops ubd_mq_ops = {
@@ -881,18 +844,36 @@ static const struct blk_mq_ops ubd_mq_ops = {
 static int ubd_add(int n, char **error_out)
 {
 	struct ubd *ubd_dev = &ubd_devs[n];
+	struct queue_limits lim = {
+		.max_segments		= MAX_SG,
+		.seg_boundary_mask	= PAGE_SIZE - 1,
+	};
 	struct gendisk *disk;
 	int err = 0;
 
 	if(ubd_dev->file == NULL)
 		goto out;
 
+	if (ubd_dev->cow.file)
+		lim.max_hw_sectors = 8 * sizeof(long);
+	if (!ubd_dev->no_trim) {
+		lim.max_hw_discard_sectors = UBD_MAX_REQUEST;
+		lim.max_write_zeroes_sectors = UBD_MAX_REQUEST;
+	}
+
 	err = ubd_file_size(ubd_dev, &ubd_dev->size);
 	if(err < 0){
 		*error_out = "Couldn't determine size of device's file";
 		goto out;
 	}
 
+	err = ubd_open_dev(ubd_dev);
+	if (err) {
+		pr_err("ubd%c: Can't open \"%s\": errno = %d\n",
+			'a' + n, ubd_dev->file, -err);
+		goto out;
+	}
+
 	ubd_dev->size = ROUND_BLOCK(ubd_dev->size);
 
 	ubd_dev->tag_set.ops = &ubd_mq_ops;
@@ -904,29 +885,43 @@ static int ubd_add(int n, char **error_out)
 
 	err = blk_mq_alloc_tag_set(&ubd_dev->tag_set);
 	if (err)
-		goto out;
+		goto out_close;
 
-	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, ubd_dev);
+	disk = blk_mq_alloc_disk(&ubd_dev->tag_set, &lim, ubd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
-	ubd_dev->queue = disk->queue;
 
-	blk_queue_write_cache(ubd_dev->queue, true, false);
-	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
-	blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
-	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
+	blk_queue_write_cache(disk->queue, true, false);
+	disk->major = UBD_MAJOR;
+	disk->first_minor = n << UBD_SHIFT;
+	disk->minors = 1 << UBD_SHIFT;
+	disk->fops = &ubd_blops;
+	set_capacity(disk, ubd_dev->size / 512);
+	sprintf(disk->disk_name, "ubd%c", 'a' + n);
+	disk->private_data = ubd_dev;
+	set_disk_ro(disk, !ubd_dev->openflags.w);
+
+	ubd_dev->pdev.id = n;
+	ubd_dev->pdev.name = DRIVER_NAME;
+	ubd_dev->pdev.dev.release = ubd_device_release;
+	dev_set_drvdata(&ubd_dev->pdev.dev, ubd_dev);
+	platform_device_register(&ubd_dev->pdev);
+
+	err = device_add_disk(&ubd_dev->pdev.dev, disk, ubd_attr_groups);
 	if (err)
 		goto out_cleanup_disk;
 
-	ubd_gendisk[n] = disk;
 	return 0;
 
 out_cleanup_disk:
 	put_disk(disk);
 out_cleanup_tags:
 	blk_mq_free_tag_set(&ubd_dev->tag_set);
+out_close:
+	ubd_close_dev(ubd_dev);
 out:
 	return err;
 }
@@ -1012,7 +1007,6 @@ static int ubd_id(char **str, int *start_out, int *end_out)
 
 static int ubd_remove(int n, char **error_out)
 {
-	struct gendisk *disk = ubd_gendisk[n];
 	struct ubd *ubd_dev;
 	int err = -ENODEV;
 
@@ -1023,15 +1017,15 @@ static int ubd_remove(int n, char **error_out)
 	if(ubd_dev->file == NULL)
 		goto out;
 
-	/* you cannot remove a open disk */
-	err = -EBUSY;
-	if(ubd_dev->count > 0)
-		goto out;
+	if (ubd_dev->disk) {
+		/* you cannot remove a open disk */
+		err = -EBUSY;
+		if (disk_openers(ubd_dev->disk))
+			goto out;
 
-	ubd_gendisk[n] = NULL;
-	if(disk != NULL){
-		del_gendisk(disk);
-		put_disk(disk);
+		del_gendisk(ubd_dev->disk);
+		ubd_close_dev(ubd_dev);
+		put_disk(ubd_dev->disk);
 	}
 
 	err = 0;
@@ -1153,37 +1147,6 @@ static int __init ubd_driver_init(void){
 
 device_initcall(ubd_driver_init);
 
-static int ubd_open(struct gendisk *disk, blk_mode_t mode)
-{
-	struct ubd *ubd_dev = disk->private_data;
-	int err = 0;
-
-	mutex_lock(&ubd_mutex);
-	if(ubd_dev->count == 0){
-		err = ubd_open_dev(ubd_dev);
-		if(err){
-			printk(KERN_ERR "%s: Can't open \"%s\": errno = %d\n",
-			       disk->disk_name, ubd_dev->file, -err);
-			goto out;
-		}
-	}
-	ubd_dev->count++;
-	set_disk_ro(disk, !ubd_dev->openflags.w);
-out:
-	mutex_unlock(&ubd_mutex);
-	return err;
-}
-
-static void ubd_release(struct gendisk *disk)
-{
-	struct ubd *ubd_dev = disk->private_data;
-
-	mutex_lock(&ubd_mutex);
-	if(--ubd_dev->count == 0)
-		ubd_close_dev(ubd_dev);
-	mutex_unlock(&ubd_mutex);
-}
-
 static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask,
 			  __u64 *cow_offset, unsigned long *bitmap,
 			  __u64 bitmap_offset, unsigned long *bitmap_words,
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 4b6d1b526bc1..66fe06db872f 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
+	asm goto("1: jmp 6f\n"
 		 "2:\n"
 		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			 "((5f-4f) - (2b-1b)),0x90\n"
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
index 84866127d074..9ef9a8aedfa6 100644
--- a/arch/um/include/asm/page.h
+++ b/arch/um/include/asm/page.h
@@ -10,7 +10,7 @@
 #include <linux/const.h>
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 5a83da703e87..6a1f36df6a18 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -28,5 +28,7 @@ obj-y += net/
 
 obj-$(CONFIG_KEXEC_FILE) += purgatory/
 
+obj-y += virt/svm/
+
 # for cleaning
 subdir- += boot tools
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5edec175b9bf..6290a040effa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -147,6 +147,7 @@ config X86
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
 	select GENERIC_CLOCKEVENTS_BROADCAST	if X86_64 || (X86_32 && X86_LOCAL_APIC)
+	select GENERIC_CLOCKEVENTS_BROADCAST_IDLE	if GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
@@ -255,6 +256,7 @@ config X86
 	select HAVE_NOINSTR_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_OBJTOOL			if X86_64
 	select HAVE_OPTPROBES
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
@@ -496,6 +498,15 @@ config X86_CPU_RESCTRL
 
 	  Say N if unsure.
 
+config X86_FRED
+	bool "Flexible Return and Event Delivery"
+	depends on X86_64
+	help
+	  When enabled, try to use Flexible Return and Event Delivery
+	  instead of the legacy SYSCALL/SYSENTER/IDT architecture for
+	  ring transitions and exception/interrupt handling if the
+	  system supports.
+
 if X86_32
 config X86_BIGSMP
 	bool "Support for big SMP systems with more than 8 CPUs"
@@ -1539,19 +1550,6 @@ config AMD_MEM_ENCRYPT
 	  This requires an AMD processor that supports Secure Memory
 	  Encryption (SME).
 
-config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT
-	bool "Activate AMD Secure Memory Encryption (SME) by default"
-	depends on AMD_MEM_ENCRYPT
-	help
-	  Say yes to have system memory encrypted by default if running on
-	  an AMD processor that supports Secure Memory Encryption (SME).
-
-	  If set to Y, then the encryption of system memory can be
-	  deactivated with the mem_encrypt=off command line option.
-
-	  If set to N, then the encryption of system memory can be
-	  activated with the mem_encrypt=on command line option.
-
 # Common NUMA Features
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
@@ -2114,11 +2112,11 @@ config PHYSICAL_START
 	help
 	  This gives the physical address where the kernel is loaded.
 
-	  If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then
-	  bzImage will decompress itself to above physical address and
-	  run from there. Otherwise, bzImage will run from the address where
-	  it has been loaded by the boot loader and will ignore above physical
-	  address.
+	  If the kernel is not relocatable (CONFIG_RELOCATABLE=n) then bzImage
+	  will decompress itself to above physical address and run from there.
+	  Otherwise, bzImage will run from the address where it has been loaded
+	  by the boot loader. The only exception is if it is loaded below the
+	  above physical address, in which case it will relocate itself there.
 
 	  In normal kdump cases one does not have to set/change this option
 	  as now bzImage can be compiled as a completely relocatable image
@@ -2434,6 +2432,18 @@ source "kernel/livepatch/Kconfig"
 
 endmenu
 
+config CC_HAS_NAMED_AS
+	def_bool CC_IS_GCC && GCC_VERSION >= 120100
+
+config USE_X86_SEG_SUPPORT
+	def_bool y
+	depends on CC_HAS_NAMED_AS
+	#
+	# -fsanitize=kernel-address (KASAN) is at the moment incompatible
+	# with named address spaces - see GCC PR sanitizer/111736.
+	#
+	depends on !KASAN
+
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)
 
@@ -2465,12 +2475,12 @@ config CALL_PADDING
 
 config FINEIBT
 	def_bool y
-	depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE
+	depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE
 	select CALL_PADDING
 
 config HAVE_CALL_THUNKS
 	def_bool y
-	depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL
+	depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL
 
 config CALL_THUNKS
 	def_bool n
@@ -2492,7 +2502,7 @@ menuconfig SPECULATION_MITIGATIONS
 
 if SPECULATION_MITIGATIONS
 
-config PAGE_TABLE_ISOLATION
+config MITIGATION_PAGE_TABLE_ISOLATION
 	bool "Remove the kernel mapping in user mode"
 	default y
 	depends on (X86_64 || X86_PAE)
@@ -2503,7 +2513,7 @@ config PAGE_TABLE_ISOLATION
 
 	  See Documentation/arch/x86/pti.rst for more details.
 
-config RETPOLINE
+config MITIGATION_RETPOLINE
 	bool "Avoid speculative indirect branches in kernel"
 	select OBJTOOL if HAVE_OBJTOOL
 	default y
@@ -2513,9 +2523,9 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
-config RETHUNK
+config MITIGATION_RETHUNK
 	bool "Enable return-thunks"
-	depends on RETPOLINE && CC_HAS_RETURN_THUNK
+	depends on MITIGATION_RETPOLINE && CC_HAS_RETURN_THUNK
 	select OBJTOOL if HAVE_OBJTOOL
 	default y if X86_64
 	help
@@ -2524,14 +2534,14 @@ config RETHUNK
 	  Requires a compiler with -mfunction-return=thunk-extern
 	  support for full protection. The kernel may run slower.
 
-config CPU_UNRET_ENTRY
+config MITIGATION_UNRET_ENTRY
 	bool "Enable UNRET on kernel entry"
-	depends on CPU_SUP_AMD && RETHUNK && X86_64
+	depends on CPU_SUP_AMD && MITIGATION_RETHUNK && X86_64
 	default y
 	help
 	  Compile the kernel with support for the retbleed=unret mitigation.
 
-config CALL_DEPTH_TRACKING
+config MITIGATION_CALL_DEPTH_TRACKING
 	bool "Mitigate RSB underflow with call depth tracking"
 	depends on CPU_SUP_INTEL && HAVE_CALL_THUNKS
 	select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
@@ -2551,7 +2561,7 @@ config CALL_DEPTH_TRACKING
 
 config CALL_THUNKS_DEBUG
 	bool "Enable call thunks and call depth tracking debugging"
-	depends on CALL_DEPTH_TRACKING
+	depends on MITIGATION_CALL_DEPTH_TRACKING
 	select FUNCTION_ALIGNMENT_32B
 	default n
 	help
@@ -2562,14 +2572,14 @@ config CALL_THUNKS_DEBUG
 	  Only enable this when you are debugging call thunks as this
 	  creates a noticeable runtime overhead. If unsure say N.
 
-config CPU_IBPB_ENTRY
+config MITIGATION_IBPB_ENTRY
 	bool "Enable IBPB on kernel entry"
 	depends on CPU_SUP_AMD && X86_64
 	default y
 	help
 	  Compile the kernel with support for the retbleed=ibpb mitigation.
 
-config CPU_IBRS_ENTRY
+config MITIGATION_IBRS_ENTRY
 	bool "Enable IBRS on kernel entry"
 	depends on CPU_SUP_INTEL && X86_64
 	default y
@@ -2578,14 +2588,14 @@ config CPU_IBRS_ENTRY
 	  This mitigates both spectre_v2 and retbleed at great cost to
 	  performance.
 
-config CPU_SRSO
+config MITIGATION_SRSO
 	bool "Mitigate speculative RAS overflow on AMD"
-	depends on CPU_SUP_AMD && X86_64 && RETHUNK
+	depends on CPU_SUP_AMD && X86_64 && MITIGATION_RETHUNK
 	default y
 	help
 	  Enable the SRSO mitigation needed on AMD Zen1-4 machines.
 
-config SLS
+config MITIGATION_SLS
 	bool "Mitigate Straight-Line-Speculation"
 	depends on CC_HAS_SLS && X86_64
 	select OBJTOOL if HAVE_OBJTOOL
@@ -2595,7 +2605,7 @@ config SLS
 	  against straight line speculation. The kernel image might be slightly
 	  larger.
 
-config GDS_FORCE_MITIGATION
+config MITIGATION_GDS_FORCE
 	bool "Force GDS Mitigation"
 	depends on CPU_SUP_INTEL
 	default n
@@ -2614,6 +2624,17 @@ config GDS_FORCE_MITIGATION
 
 	  If in doubt, say N.
 
+config MITIGATION_RFDS
+	bool "RFDS Mitigation"
+	depends on CPU_SUP_INTEL
+	default y
+	help
+	  Enable mitigation for Register File Data Sampling (RFDS) by default.
+	  RFDS is a hardware vulnerability which affects Intel Atom CPUs. It
+	  allows unprivileged speculative access to stale data previously
+	  stored in floating point, vector and integer registers.
+	  See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
+
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b9224cf2ee4d..2a7279d80460 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -379,7 +379,7 @@ config X86_CMOV
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1a068de12a56..1eccc2ee45fb 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -22,7 +22,7 @@ RETPOLINE_VDSO_CFLAGS	:= -mretpoline
 endif
 RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 
-ifdef CONFIG_RETHUNK
+ifdef CONFIG_MITIGATION_RETHUNK
 RETHUNK_CFLAGS		:= -mfunction-return=thunk-extern
 RETPOLINE_CFLAGS	+= $(RETHUNK_CFLAGS)
 endif
@@ -53,6 +53,9 @@ REALMODE_CFLAGS += -fno-stack-protector
 REALMODE_CFLAGS += -Wno-address-of-packed-member
 REALMODE_CFLAGS += $(cc_stack_align4)
 REALMODE_CFLAGS += $(CLANG_FLAGS)
+ifdef CONFIG_CC_IS_CLANG
+REALMODE_CFLAGS += -Wno-gnu
+endif
 export REALMODE_CFLAGS
 
 # BITS is used as extension for files which are available in a 32 bit
@@ -112,13 +115,13 @@ ifeq ($(CONFIG_X86_32),y)
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-	ifeq ($(CONFIG_STACKPROTECTOR),y)
-		ifeq ($(CONFIG_SMP),y)
+    ifeq ($(CONFIG_STACKPROTECTOR),y)
+        ifeq ($(CONFIG_SMP),y)
 			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
-		else
+        else
 			KBUILD_CFLAGS += -mstack-protector-guard=global
-		endif
-	endif
+        endif
+    endif
 else
         BITS := 64
         UTS_MACHINE := x86_64
@@ -192,7 +195,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
 # Avoid indirect branches in kernel to deal with Spectre
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
   KBUILD_CFLAGS += $(RETPOLINE_CFLAGS)
   # Additionally, avoid generating expensive indirect jumps which
   # are subject to retpolines for small number of switch cases.
@@ -205,7 +208,7 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
-ifdef CONFIG_SLS
+ifdef CONFIG_MITIGATION_SLS
   KBUILD_CFLAGS += -mharden-sls=all
 endif
 
@@ -296,12 +299,11 @@ install:
 
 vdso-install-$(CONFIG_X86_64)		+= arch/x86/entry/vdso/vdso64.so.dbg
 vdso-install-$(CONFIG_X86_X32_ABI)	+= arch/x86/entry/vdso/vdsox32.so.dbg
-vdso-install-$(CONFIG_X86_32)		+= arch/x86/entry/vdso/vdso32.so.dbg
-vdso-install-$(CONFIG_IA32_EMULATION)	+= arch/x86/entry/vdso/vdso32.so.dbg
+vdso-install-$(CONFIG_COMPAT_32)	+= arch/x86/entry/vdso/vdso32.so.dbg
 
 archprepare: checkbin
 checkbin:
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
 ifeq ($(RETPOLINE_CFLAGS),)
 	@echo "You are building kernel with non-retpoline compiler." >&2
 	@echo "Please update your compiler." >&2
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 18d15d1ce87d..f196b1d1ddf8 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -5,6 +5,8 @@
 #include "../string.h"
 #include "efi.h"
 
+#include <asm/bootparam.h>
+
 #include <linux/numa.h>
 
 /*
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index c1bb180973ea..e162d7f59cc5 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 
+#include <asm/bootparam.h>
+
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
 {
diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c
index 6edd034b0b30..f2e50f9758e6 100644
--- a/arch/x86/boot/compressed/efi.c
+++ b/arch/x86/boot/compressed/efi.c
@@ -7,6 +7,8 @@
 
 #include "misc.h"
 
+#include <asm/bootparam.h>
+
 /**
  * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment.
  *
diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h
index 866c0af8b5b9..b22300970f97 100644
--- a/arch/x86/boot/compressed/efi.h
+++ b/arch/x86/boot/compressed/efi.h
@@ -97,15 +97,6 @@ typedef struct {
 	u32 tables;
 } efi_system_table_32_t;
 
-/* kexec external ABI */
-struct efi_setup_data {
-	u64 fw_vendor;
-	u64 __unused;
-	u64 tables;
-	u64 smbios;
-	u64 reserved[8];
-};
-
 struct efi_unaccepted_memory {
 	u32 version;
 	u32 unit_size;
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index d040080d7edb..909f2a35b60c 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -8,8 +8,8 @@
  * Copyright (C)      2016  Kees Cook
  */
 
-/* No PAGE_TABLE_ISOLATION support needed either: */
-#undef CONFIG_PAGE_TABLE_ISOLATION
+/* No MITIGATION_PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 
 #include "error.h"
 #include "misc.h"
@@ -389,5 +389,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
 
 void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
 {
-	/* Empty handler to ignore NMI during early boot */
+	spurious_nmi_count++;
 }
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b99e08e6815b..408507e305be 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -52,6 +52,7 @@ struct port_io_ops pio_ops;
 
 memptr free_mem_ptr;
 memptr free_mem_end_ptr;
+int spurious_nmi_count;
 
 static char *vidmem;
 static int vidport;
@@ -164,21 +165,34 @@ void __putstr(const char *s)
 	outb(0xff & (pos >> 1), vidport+1);
 }
 
-void __puthex(unsigned long value)
+static noinline void __putnum(unsigned long value, unsigned int base,
+			      int mindig)
 {
-	char alpha[2] = "0";
-	int bits;
+	char buf[8*sizeof(value)+1];
+	char *p;
 
-	for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) {
-		unsigned long digit = (value >> bits) & 0xf;
+	p = buf + sizeof(buf);
+	*--p = '\0';
 
-		if (digit < 0xA)
-			alpha[0] = '0' + digit;
-		else
-			alpha[0] = 'a' + (digit - 0xA);
+	while (mindig-- > 0 || value) {
+		unsigned char digit = value % base;
+		digit += (digit >= 10) ? ('a'-10) : '0';
+		*--p = digit;
 
-		__putstr(alpha);
+		value /= base;
 	}
+
+	__putstr(p);
+}
+
+void __puthex(unsigned long value)
+{
+	__putnum(value, 16, sizeof(value)*2);
+}
+
+void __putdec(unsigned long value)
+{
+	__putnum(value, 10, 1);
 }
 
 #ifdef CONFIG_X86_NEED_RELOCS
@@ -358,6 +372,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
 }
 
 /*
+ * Set the memory encryption xloadflag based on the mem_encrypt= command line
+ * parameter, if provided.
+ */
+static void parse_mem_encrypt(struct setup_header *hdr)
+{
+	int on = cmdline_find_option_bool("mem_encrypt=on");
+	int off = cmdline_find_option_bool("mem_encrypt=off");
+
+	if (on > off)
+		hdr->xloadflags |= XLF_MEM_ENCRYPTION;
+}
+
+/*
  * The compressed kernel image (ZO), has been moved so that its position
  * is against the end of the buffer used to hold the uncompressed kernel
  * image (VO) and the execution environment (.bss, .brk), which makes sure
@@ -387,6 +414,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
 	/* Clear flags intended for solely in-kernel use. */
 	boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG;
 
+	parse_mem_encrypt(&boot_params_ptr->hdr);
+
 	sanitize_boot_params(boot_params_ptr);
 
 	if (boot_params_ptr->screen_info.orig_video_mode == 7) {
@@ -493,6 +522,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
 	/* Disable exception handling before booting the kernel */
 	cleanup_exception_handling();
 
+	if (spurious_nmi_count) {
+		error_putstr("Spurious early NMIs ignored: ");
+		error_putdec(spurious_nmi_count);
+		error_putstr("\n");
+	}
+
 	return output + entry_offset;
 }
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index bc2f0f17fb90..b353a7be380c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -59,12 +59,15 @@ extern char _head[], _end[];
 /* misc.c */
 extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
+extern int spurious_nmi_count;
 void *malloc(int size);
 void free(void *where);
 void __putstr(const char *s);
 void __puthex(unsigned long value);
+void __putdec(unsigned long value);
 #define error_putstr(__x)  __putstr(__x)
 #define error_puthex(__x)  __puthex(__x)
+#define error_putdec(__x)  __putdec(__x)
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 51f957b24ba7..c882e1f67af0 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
+#include <asm/bootparam.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 454acd7a2daf..ec71846d28c9 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -12,6 +12,7 @@
  */
 #include "misc.h"
 
+#include <asm/bootparam.h>
 #include <asm/pgtable_types.h>
 #include <asm/sev.h>
 #include <asm/trapnr.h>
@@ -116,6 +117,9 @@ static bool fault_in_kernel_space(unsigned long address)
 #undef __init
 #define __init
 
+#undef __head
+#define __head
+
 #define __BOOT_COMPRESSED
 
 /* Basic instruction decoding support needed */
@@ -304,6 +308,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	if (result != ES_OK)
 		goto finish;
 
+	result = vc_check_opcode_bytes(&ctxt, exit_code);
+	if (result != ES_OK)
+		goto finish;
+
 	switch (exit_code) {
 	case SVM_EXIT_RDTSC:
 	case SVM_EXIT_RDTSCP:
@@ -365,7 +373,7 @@ static void enforce_vmpl0(void)
 				 MSR_AMD64_SNP_VMPL_SSS |		\
 				 MSR_AMD64_SNP_SECURE_TSC |		\
 				 MSR_AMD64_SNP_VMGEXIT_PARAM |		\
-				 MSR_AMD64_SNP_VMSA_REG_PROTECTION |	\
+				 MSR_AMD64_SNP_VMSA_REG_PROT |		\
 				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
 				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
 				 MSR_AMD64_SNP_RESERVED_MASK)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b2771710ed98..b5c79f43359b 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -106,17 +106,12 @@ extra_header_fields:
 	.word	0				# MinorSubsystemVersion
 	.long	0				# Win32VersionValue
 
-	.long	setup_size + ZO__end + pecompat_vsize
-						# SizeOfImage
+	.long	setup_size + ZO__end		# SizeOfImage
 
 	.long	salign				# SizeOfHeaders
 	.long	0				# CheckSum
 	.word	IMAGE_SUBSYSTEM_EFI_APPLICATION	# Subsystem (EFI application)
-#ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES
 	.word	IMAGE_DLL_CHARACTERISTICS_NX_COMPAT	# DllCharacteristics
-#else
-	.word	0				# DllCharacteristics
-#endif
 #ifdef CONFIG_X86_32
 	.long	0				# SizeOfStackReserve
 	.long	0				# SizeOfStackCommit
@@ -143,7 +138,7 @@ section_table:
 	.ascii	".setup"
 	.byte	0
 	.byte	0
-	.long	setup_size - salign 		# VirtualSize
+	.long	pecompat_fstart - salign 	# VirtualSize
 	.long	salign				# VirtualAddress
 	.long	pecompat_fstart - salign	# SizeOfRawData
 	.long	salign				# PointerToRawData
@@ -156,8 +151,8 @@ section_table:
 #ifdef CONFIG_EFI_MIXED
 	.asciz	".compat"
 
-	.long	8				# VirtualSize
-	.long	setup_size + ZO__end		# VirtualAddress
+	.long	pecompat_fsize			# VirtualSize
+	.long	pecompat_fstart			# VirtualAddress
 	.long	pecompat_fsize			# SizeOfRawData
 	.long	pecompat_fstart			# PointerToRawData
 
@@ -172,17 +167,16 @@ section_table:
 	 * modes this image supports.
 	 */
 	.pushsection ".pecompat", "a", @progbits
-	.balign	falign
-	.set	pecompat_vsize, salign
+	.balign	salign
 	.globl	pecompat_fstart
 pecompat_fstart:
 	.byte	0x1				# Version
 	.byte	8				# Size
 	.word	IMAGE_FILE_MACHINE_I386		# PE machine type
 	.long	setup_size + ZO_efi32_pe_entry	# Entrypoint
+	.byte	0x0				# Sentinel
 	.popsection
 #else
-	.set	pecompat_vsize, 0
 	.set	pecompat_fstart, setup_size
 #endif
 	.ascii	".text"
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 83bb7efad8ae..3a2d1360abb0 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -24,6 +24,9 @@ SECTIONS
 	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }
 
+	.pecompat	: { *(.pecompat) }
+	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
 	. = ALIGN(16);
 	.rodata		: { *(.rodata*) }
 
@@ -36,9 +39,6 @@ SECTIONS
 	. = ALIGN(16);
 	.data		: { *(.data*) }
 
-	.pecompat	: { *(.pecompat) }
-	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
 	.signature	: {
 		setup_sig = .;
 		LONG(0x5a5aaa55)
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index eeec9986570e..d07be9d05cd0 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -14,7 +14,7 @@
 #include <asm/processor.h>
 
 enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
-static u64 cc_mask __ro_after_init;
+u64 cc_mask __ro_after_init;
 
 static bool noinstr intel_cc_platform_has(enum cc_attr attr)
 {
@@ -148,8 +148,3 @@ u64 cc_mkdec(u64 val)
 	}
 }
 EXPORT_SYMBOL_GPL(cc_mkdec);
-
-__init void cc_set_mask(u64 mask)
-{
-	cc_mask = mask;
-}
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 73abbbdd26f8..91801138b10b 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -42,7 +42,7 @@ CONFIG_EFI_STUB=y
 CONFIG_HZ_1000=y
 CONFIG_KEXEC=y
 CONFIG_CRASH_DUMP=y
-# CONFIG_RETHUNK is not set
+# CONFIG_MITIGATION_RETHUNK is not set
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
 CONFIG_PM_TRACE_RTC=y
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index ca2fe186994b..c93e7f5c2a06 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -18,6 +18,9 @@ obj-y				+= vdso/
 obj-y				+= vsyscall/
 
 obj-$(CONFIG_PREEMPTION)	+= thunk_$(BITS).o
+CFLAGS_entry_fred.o		+= -fno-stack-protector
+CFLAGS_REMOVE_entry_fred.o	+= -pg $(CC_FLAGS_FTRACE)
+obj-$(CONFIG_X86_FRED)		+= entry_64_fred.o entry_fred.o
+
 obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
 obj-$(CONFIG_X86_X32_ABI)	+= syscall_x32.o
-
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9f1d94790a54..ea81770629ee 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -65,7 +65,7 @@ For 32-bit we have the following conventions - kernel is built with
  * for assembly code:
  */
 
-.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0
+.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 unwind_hint=1
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -87,14 +87,17 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq	%r13		/* pt_regs->r13 */
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
+
+	.if \unwind_hint
 	UNWIND_HINT_REGS
+	.endif
 
 	.if \save_ret
 	pushq	%rsi		/* return address on top of stack */
 	.endif
 .endm
 
-.macro CLEAR_REGS
+.macro CLEAR_REGS clear_bp=1
 	/*
 	 * Sanitize registers of values that a speculation attack might
 	 * otherwise want to exploit. The lower registers are likely clobbered
@@ -109,7 +112,9 @@ For 32-bit we have the following conventions - kernel is built with
 	xorl	%r10d, %r10d	/* nospec r10 */
 	xorl	%r11d, %r11d	/* nospec r11 */
 	xorl	%ebx,  %ebx	/* nospec rbx */
+	.if \clear_bp
 	xorl	%ebp,  %ebp	/* nospec rbp */
+	.endif
 	xorl	%r12d, %r12d	/* nospec r12 */
 	xorl	%r13d, %r13d	/* nospec r13 */
 	xorl	%r14d, %r14d	/* nospec r14 */
@@ -117,9 +122,9 @@ For 32-bit we have the following conventions - kernel is built with
 
 .endm
 
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0
-	PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret
-	CLEAR_REGS
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1
+	PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint
+	CLEAR_REGS clear_bp=\clear_bp
 .endm
 
 .macro POP_REGS pop_rdi=1
@@ -142,10 +147,10 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 .endm
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 
 /*
- * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
+ * MITIGATION_PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
  * halves:
  */
 #define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
@@ -160,7 +165,7 @@ For 32-bit we have the following conventions - kernel is built with
 
 .macro ADJUST_KERNEL_CR3 reg:req
 	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
-	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+	/* Clear PCID and "MITIGATION_PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
 	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
 .endm
 
@@ -173,7 +178,7 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 
 #define THIS_CPU_user_pcid_flush_mask   \
-	PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+	PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)
 
 .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
 	mov	%cr3, \scratch_reg
@@ -239,17 +244,19 @@ For 32-bit we have the following conventions - kernel is built with
 .Ldone_\@:
 .endm
 
-.macro RESTORE_CR3 scratch_reg:req save_reg:req
+/* Restore CR3 from a kernel context. May restore a user CR3 value. */
+.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 
-	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
-
 	/*
-	 * KERNEL pages can always resume with NOFLUSH as we do
-	 * explicit flushes.
+	 * If CR3 contained the kernel page tables at the paranoid exception
+	 * entry, then there is nothing to restore as CR3 is not modified while
+	 * handling the exception.
 	 */
 	bt	$PTI_USER_PGTABLE_BIT, \save_reg
-	jnc	.Lnoflush_\@
+	jnc	.Lend_\@
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
 
 	/*
 	 * Check if there's a pending flush for the user ASID we're
@@ -257,25 +264,17 @@ For 32-bit we have the following conventions - kernel is built with
 	 */
 	movq	\save_reg, \scratch_reg
 	andq	$(0x7FF), \scratch_reg
-	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
-	jnc	.Lnoflush_\@
-
 	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
-	jmp	.Lwrcr3_\@
+	jc	.Lwrcr3_\@
 
-.Lnoflush_\@:
 	SET_NOFLUSH_BIT \save_reg
 
 .Lwrcr3_\@:
-	/*
-	 * The CR3 write could be avoided when not changing its value,
-	 * but would require a CR3 read *and* a scratch register.
-	 */
 	movq	\save_reg, %cr3
 .Lend_\@:
 .endm
 
-#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=n: */
 
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
 .endm
@@ -285,7 +284,7 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
 .endm
-.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req
 .endm
 
 #endif
@@ -303,7 +302,7 @@ For 32-bit we have the following conventions - kernel is built with
  * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set.
  */
 .macro IBRS_ENTER save_reg
-#ifdef CONFIG_CPU_IBRS_ENTRY
+#ifdef CONFIG_MITIGATION_IBRS_ENTRY
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
 	movl	$MSR_IA32_SPEC_CTRL, %ecx
 
@@ -332,7 +331,7 @@ For 32-bit we have the following conventions - kernel is built with
  * regs. Must be called after the last RET.
  */
 .macro IBRS_EXIT save_reg
-#ifdef CONFIG_CPU_IBRS_ENTRY
+#ifdef CONFIG_MITIGATION_IBRS_ENTRY
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
 	movl	$MSR_IA32_SPEC_CTRL, %ecx
 
@@ -426,3 +425,63 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_X86_64
+
+/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
+.macro THUNK name, func
+SYM_FUNC_START(\name)
+	pushq %rbp
+	movq %rsp, %rbp
+
+	pushq %rdi
+	pushq %rsi
+	pushq %rdx
+	pushq %rcx
+	pushq %rax
+	pushq %r8
+	pushq %r9
+	pushq %r10
+	pushq %r11
+
+	call \func
+
+	popq %r11
+	popq %r10
+	popq %r9
+	popq %r8
+	popq %rax
+	popq %rcx
+	popq %rdx
+	popq %rsi
+	popq %rdi
+	popq %rbp
+	RET
+SYM_FUNC_END(\name)
+	_ASM_NOKPROBE(\name)
+.endm
+
+#else /* CONFIG_X86_32 */
+
+/* put return address in eax (arg1) */
+.macro THUNK name, func, put_ret_addr_in_eax=0
+SYM_CODE_START_NOALIGN(\name)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+
+	.if \put_ret_addr_in_eax
+	/* Place EIP in the arg1 */
+	movl 3*4(%esp), %eax
+	.endif
+
+	call \func
+	popl %edx
+	popl %ecx
+	popl %eax
+	RET
+	_ASM_NOKPROBE(\name)
+SYM_CODE_END(\name)
+	.endm
+
+#endif
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 8c8d38f0cb1d..d9feadffa972 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -6,6 +6,11 @@
 #include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/msr-index.h>
+#include <asm/unwind_hints.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
+
+#include "calling.h"
 
 .pushsection .noinstr.text, "ax"
 
@@ -20,3 +25,24 @@ SYM_FUNC_END(entry_ibpb)
 EXPORT_SYMBOL_GPL(entry_ibpb);
 
 .popsection
+
+/*
+ * Define the VERW operand that is disguised as entry code so that
+ * it can be referenced with KPTI enabled. This ensure VERW can be
+ * used late in exit-to-user path after page tables are switched.
+ */
+.pushsection .entry.text, "ax"
+
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_START_NOALIGN(mds_verw_sel)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	.word __KERNEL_DS
+.align L1_CACHE_BYTES, 0xcc
+SYM_CODE_END(mds_verw_sel);
+/* For KVM */
+EXPORT_SYMBOL_GPL(mds_verw_sel);
+
+.popsection
+
+THUNK warn_thunk_thunk, __warn_thunk
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c73047bf9f4b..d3a814efbff6 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -305,7 +305,7 @@
 .macro CHECK_AND_APPLY_ESPFIX
 #ifdef CONFIG_X86_ESPFIX32
 #define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page + GDT_ESPFIX_OFFSET)
 
 	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
 
@@ -649,10 +649,6 @@ SYM_CODE_START_LOCAL(asm_\cfunc)
 SYM_CODE_END(asm_\cfunc)
 .endm
 
-.macro idtentry_sysvec vector cfunc
-	idtentry \vector asm_\cfunc \cfunc has_error_code=0
-.endm
-
 /*
  * Include the defines which emit the idt entries which are shared
  * shared between 32 and 64 bit and emit the __irqentry_text_* markers
@@ -885,6 +881,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
 	popl	%eax
+	CLEAR_CPU_BUFFERS
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -954,6 +951,7 @@ restore_all_switch_stack:
 
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
+	CLEAR_CPU_BUFFERS
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -1146,6 +1144,7 @@ SYM_CODE_START(asm_exc_nmi)
 
 	/* Not on SYSENTER stack. */
 	call	exc_nmi
+	CLEAR_CPU_BUFFERS
 	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c40f89ab1b4c..8af2a26b24f6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -161,6 +161,7 @@ syscall_return_via_sysret:
 SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretq
 SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -190,7 +191,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary
+	movq	%rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
 #endif
 
 	/*
@@ -247,7 +248,13 @@ SYM_CODE_START(ret_from_fork_asm)
 	 * and unwind should work normally.
 	 */
 	UNWIND_HINT_REGS
+
+#ifdef CONFIG_X86_FRED
+	ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode", \
+		    "jmp asm_fred_exit_user", X86_FEATURE_FRED
+#else
 	jmp	swapgs_restore_regs_and_return_to_usermode
+#endif
 SYM_CODE_END(ret_from_fork_asm)
 .popsection
 
@@ -370,14 +377,6 @@ SYM_CODE_END(\asmsym)
 	idtentry \vector asm_\cfunc \cfunc has_error_code=1
 .endm
 
-/*
- * System vectors which invoke their handlers directly and are not
- * going through the regular common device interrupt handling code.
- */
-.macro idtentry_sysvec vector cfunc
-	idtentry \vector asm_\cfunc \cfunc has_error_code=0
-.endm
-
 /**
  * idtentry_mce_db - Macro to generate entry stubs for #MC and #DB
  * @vector:		Vector number
@@ -562,7 +561,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 #ifdef CONFIG_XEN_PV
 	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 #endif
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
 #endif
 
@@ -573,12 +572,13 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 .Lswapgs_and_iret:
 	swapgs
+	CLEAR_CPU_BUFFERS
 	/* Assert that the IRET frame indicates user mode. */
 	testb	$3, 8(%rsp)
 	jnz	.Lnative_iret
 	ud2
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 .Lpti_restore_regs_and_return_to_usermode:
 	POP_REGS pop_rdi=0
 
@@ -723,6 +723,8 @@ native_irq_return_ldt:
 	 */
 	popq	%rax				/* Restore user RAX */
 
+	CLEAR_CPU_BUFFERS
+
 	/*
 	 * RSP now points to an ordinary IRET frame, except that the page
 	 * is read-only and RSP[31:16] are preloaded with the userspace
@@ -968,14 +970,14 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 	IBRS_EXIT save_reg=%r15
 
 	/*
-	 * The order of operations is important. RESTORE_CR3 requires
+	 * The order of operations is important. PARANOID_RESTORE_CR3 requires
 	 * kernel GSBASE.
 	 *
 	 * NB to anyone to try to optimize this code: this code does
 	 * not execute at all for exceptions from user mode. Those
 	 * exceptions go through error_return instead.
 	 */
-	RESTORE_CR3	scratch_reg=%rax save_reg=%r14
+	PARANOID_RESTORE_CR3 scratch_reg=%rax save_reg=%r14
 
 	/* Handle the three GSBASE cases */
 	ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE
@@ -1096,7 +1098,7 @@ SYM_CODE_END(error_return)
  *
  * Registers:
  *	%r14: Used to save/restore the CR3 of the interrupted context
- *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
+ *	      when MITIGATION_PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
 SYM_CODE_START(asm_exc_nmi)
 	UNWIND_HINT_IRET_ENTRY
@@ -1404,8 +1406,7 @@ end_repeat_nmi:
 	/* Always restore stashed SPEC_CTRL value (see paranoid_entry) */
 	IBRS_EXIT save_reg=%r15
 
-	/* Always restore stashed CR3 value (see paranoid_entry) */
-	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+	PARANOID_RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
 
 	/*
 	 * The above invocation of paranoid_entry stored the GSBASE
@@ -1450,6 +1451,12 @@ nmi_restore:
 	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */
 
 	/*
+	 * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like
+	 * NMI in kernel after user state is restored. For an unprivileged user
+	 * these conditions are hard to meet.
+	 */
+
+	/*
 	 * iretq reads the "iret" frame and exits the NMI stack in a
 	 * single instruction.  We are returning to kernel mode, so this
 	 * cannot result in a fault.  Similarly, we don't need to worry
@@ -1466,6 +1473,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore)
 	UNWIND_HINT_END_OF_STACK
 	ENDBR
 	mov	$-ENOSYS, %eax
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_CODE_END(entry_SYSCALL32_ignore)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index de94e2e84ecc..eabf48c4d4b4 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
 	xorl	%r9d, %r9d
 	xorl	%r10d, %r10d
 	swapgs
+	CLEAR_CPU_BUFFERS
 	sysretl
 SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
new file mode 100644
index 000000000000..a02bc6f3d2e6
--- /dev/null
+++ b/arch/x86/entry/entry_64_fred.S
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The actual FRED entry points.
+ */
+
+#include <linux/export.h>
+
+#include <asm/asm.h>
+#include <asm/fred.h>
+#include <asm/segment.h>
+
+#include "calling.h"
+
+	.code64
+	.section .noinstr.text, "ax"
+
+.macro FRED_ENTER
+	UNWIND_HINT_END_OF_STACK
+	ENDBR
+	PUSH_AND_CLEAR_REGS
+	movq	%rsp, %rdi	/* %rdi -> pt_regs */
+.endm
+
+.macro FRED_EXIT
+	UNWIND_HINT_REGS
+	POP_REGS
+.endm
+
+/*
+ * The new RIP value that FRED event delivery establishes is
+ * IA32_FRED_CONFIG & ~FFFH for events that occur in ring 3.
+ * Thus the FRED ring 3 entry point must be 4K page aligned.
+ */
+	.align 4096
+
+SYM_CODE_START_NOALIGN(asm_fred_entrypoint_user)
+	FRED_ENTER
+	call	fred_entry_from_user
+SYM_INNER_LABEL(asm_fred_exit_user, SYM_L_GLOBAL)
+	FRED_EXIT
+1:	ERETU
+
+	_ASM_EXTABLE_TYPE(1b, asm_fred_entrypoint_user, EX_TYPE_ERETU)
+SYM_CODE_END(asm_fred_entrypoint_user)
+
+/*
+ * The new RIP value that FRED event delivery establishes is
+ * (IA32_FRED_CONFIG & ~FFFH) + 256 for events that occur in
+ * ring 0, i.e., asm_fred_entrypoint_user + 256.
+ */
+	.org asm_fred_entrypoint_user + 256, 0xcc
+SYM_CODE_START_NOALIGN(asm_fred_entrypoint_kernel)
+	FRED_ENTER
+	call	fred_entry_from_kernel
+	FRED_EXIT
+	ERETS
+SYM_CODE_END(asm_fred_entrypoint_kernel)
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+SYM_FUNC_START(asm_fred_entry_from_kvm)
+	push %rbp
+	mov %rsp, %rbp
+
+	UNWIND_HINT_SAVE
+
+	/*
+	 * Both IRQ and NMI from VMX can be handled on current task stack
+	 * because there is no need to protect from reentrancy and the call
+	 * stack leading to this helper is effectively constant and shallow
+	 * (relatively speaking). Do the same when FRED is active, i.e., no
+	 * need to check current stack level for a stack switch.
+	 *
+	 * Emulate the FRED-defined redzone and stack alignment.
+	 */
+	sub $(FRED_CONFIG_REDZONE_AMOUNT << 6), %rsp
+	and $FRED_STACK_FRAME_RSP_MASK, %rsp
+
+	/*
+	 * Start to push a FRED stack frame, which is always 64 bytes:
+	 *
+	 * +--------+-----------------+
+	 * | Bytes  | Usage           |
+	 * +--------+-----------------+
+	 * | 63:56  | Reserved        |
+	 * | 55:48  | Event Data      |
+	 * | 47:40  | SS + Event Info |
+	 * | 39:32  | RSP             |
+	 * | 31:24  | RFLAGS          |
+	 * | 23:16  | CS + Aux Info   |
+	 * |  15:8  | RIP             |
+	 * |   7:0  | Error Code      |
+	 * +--------+-----------------+
+	 */
+	push $0				/* Reserved, must be 0 */
+	push $0				/* Event data, 0 for IRQ/NMI */
+	push %rdi			/* fred_ss handed in by the caller */
+	push %rbp
+	pushf
+	mov $__KERNEL_CS, %rax
+	push %rax
+
+	/*
+	 * Unlike the IDT event delivery, FRED _always_ pushes an error code
+	 * after pushing the return RIP, thus the CALL instruction CANNOT be
+	 * used here to push the return RIP, otherwise there is no chance to
+	 * push an error code before invoking the IRQ/NMI handler.
+	 *
+	 * Use LEA to get the return RIP and push it, then push an error code.
+	 */
+	lea 1f(%rip), %rax
+	push %rax				/* Return RIP */
+	push $0					/* Error code, 0 for IRQ/NMI */
+
+	PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0
+	movq %rsp, %rdi				/* %rdi -> pt_regs */
+	call __fred_entry_from_kvm		/* Call the C entry point */
+	POP_REGS
+	ERETS
+1:
+	/*
+	 * Objtool doesn't understand what ERETS does, this hint tells it that
+	 * yes, we'll reach here and with what stack state. A save/restore pair
+	 * isn't strictly needed, but it's the simplest form.
+	 */
+	UNWIND_HINT_RESTORE
+	pop %rbp
+	RET
+
+SYM_FUNC_END(asm_fred_entry_from_kvm)
+EXPORT_SYMBOL_GPL(asm_fred_entry_from_kvm);
+#endif
diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
new file mode 100644
index 000000000000..ac120cbdaaf2
--- /dev/null
+++ b/arch/x86/entry/entry_fred.c
@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The FRED specific kernel/user entry functions which are invoked from
+ * assembly code and dispatch to the associated handlers.
+ */
+#include <linux/kernel.h>
+#include <linux/kdebug.h>
+#include <linux/nospec.h>
+
+#include <asm/desc.h>
+#include <asm/fred.h>
+#include <asm/idtentry.h>
+#include <asm/syscall.h>
+#include <asm/trapnr.h>
+#include <asm/traps.h>
+
+/* FRED EVENT_TYPE_OTHER vector numbers */
+#define FRED_SYSCALL			1
+#define FRED_SYSENTER			2
+
+static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code)
+{
+	irqentry_state_t irq_state = irqentry_nmi_enter(regs);
+
+	instrumentation_begin();
+
+	/* Panic on events from a high stack level */
+	if (regs->fred_cs.sl > 0) {
+		pr_emerg("PANIC: invalid or fatal FRED event; event type %u "
+			 "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
+			 regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+			 fred_event_data(regs), regs->cs, regs->ip);
+		die("invalid or fatal FRED event", regs, regs->orig_ax);
+		panic("invalid or fatal FRED event");
+	} else {
+		unsigned long flags = oops_begin();
+		int sig = SIGKILL;
+
+		pr_alert("BUG: invalid or fatal FRED event; event type %u "
+			 "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
+			 regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+			 fred_event_data(regs), regs->cs, regs->ip);
+
+		if (__die("Invalid or fatal FRED event", regs, regs->orig_ax))
+			sig = 0;
+
+		oops_end(flags, regs, sig);
+	}
+
+	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
+}
+
+static noinstr void fred_intx(struct pt_regs *regs)
+{
+	switch (regs->fred_ss.vector) {
+	/* Opcode 0xcd, 0x3, NOT INT3 (opcode 0xcc) */
+	case X86_TRAP_BP:
+		return exc_int3(regs);
+
+	/* Opcode 0xcd, 0x4, NOT INTO (opcode 0xce) */
+	case X86_TRAP_OF:
+		return exc_overflow(regs);
+
+#ifdef CONFIG_IA32_EMULATION
+	/* INT80 */
+	case IA32_SYSCALL_VECTOR:
+		if (ia32_enabled())
+			return int80_emulation(regs);
+		fallthrough;
+#endif
+
+	default:
+		return exc_general_protection(regs, 0);
+	}
+}
+
+static __always_inline void fred_other(struct pt_regs *regs)
+{
+	/* The compiler can fold these conditions into a single test */
+	if (likely(regs->fred_ss.vector == FRED_SYSCALL && regs->fred_ss.lm)) {
+		regs->orig_ax = regs->ax;
+		regs->ax = -ENOSYS;
+		do_syscall_64(regs, regs->orig_ax);
+		return;
+	} else if (ia32_enabled() &&
+		   likely(regs->fred_ss.vector == FRED_SYSENTER && !regs->fred_ss.lm)) {
+		regs->orig_ax = regs->ax;
+		regs->ax = -ENOSYS;
+		do_fast_syscall_32(regs);
+		return;
+	} else {
+		exc_invalid_op(regs);
+		return;
+	}
+}
+
+#define SYSVEC(_vector, _function) [_vector - FIRST_SYSTEM_VECTOR] = fred_sysvec_##_function
+
+static idtentry_t sysvec_table[NR_SYSTEM_VECTORS] __ro_after_init = {
+	SYSVEC(ERROR_APIC_VECTOR,		error_interrupt),
+	SYSVEC(SPURIOUS_APIC_VECTOR,		spurious_apic_interrupt),
+	SYSVEC(LOCAL_TIMER_VECTOR,		apic_timer_interrupt),
+	SYSVEC(X86_PLATFORM_IPI_VECTOR,		x86_platform_ipi),
+
+	SYSVEC(RESCHEDULE_VECTOR,		reschedule_ipi),
+	SYSVEC(CALL_FUNCTION_SINGLE_VECTOR,	call_function_single),
+	SYSVEC(CALL_FUNCTION_VECTOR,		call_function),
+	SYSVEC(REBOOT_VECTOR,			reboot),
+
+	SYSVEC(THRESHOLD_APIC_VECTOR,		threshold),
+	SYSVEC(DEFERRED_ERROR_VECTOR,		deferred_error),
+	SYSVEC(THERMAL_APIC_VECTOR,		thermal),
+
+	SYSVEC(IRQ_WORK_VECTOR,			irq_work),
+
+	SYSVEC(POSTED_INTR_VECTOR,		kvm_posted_intr_ipi),
+	SYSVEC(POSTED_INTR_WAKEUP_VECTOR,	kvm_posted_intr_wakeup_ipi),
+	SYSVEC(POSTED_INTR_NESTED_VECTOR,	kvm_posted_intr_nested_ipi),
+};
+
+static bool fred_setup_done __initdata;
+
+void __init fred_install_sysvec(unsigned int sysvec, idtentry_t handler)
+{
+	if (WARN_ON_ONCE(sysvec < FIRST_SYSTEM_VECTOR))
+		return;
+
+	if (WARN_ON_ONCE(fred_setup_done))
+		return;
+
+	if (!WARN_ON_ONCE(sysvec_table[sysvec - FIRST_SYSTEM_VECTOR]))
+		 sysvec_table[sysvec - FIRST_SYSTEM_VECTOR] = handler;
+}
+
+static noinstr void fred_handle_spurious_interrupt(struct pt_regs *regs)
+{
+	spurious_interrupt(regs, regs->fred_ss.vector);
+}
+
+void __init fred_complete_exception_setup(void)
+{
+	unsigned int vector;
+
+	for (vector = 0; vector < FIRST_EXTERNAL_VECTOR; vector++)
+		set_bit(vector, system_vectors);
+
+	for (vector = 0; vector < NR_SYSTEM_VECTORS; vector++) {
+		if (sysvec_table[vector])
+			set_bit(vector + FIRST_SYSTEM_VECTOR, system_vectors);
+		else
+			sysvec_table[vector] = fred_handle_spurious_interrupt;
+	}
+	fred_setup_done = true;
+}
+
+static noinstr void fred_extint(struct pt_regs *regs)
+{
+	unsigned int vector = regs->fred_ss.vector;
+	unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR,
+						NR_SYSTEM_VECTORS);
+
+	if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR))
+		return;
+
+	if (likely(vector >= FIRST_SYSTEM_VECTOR)) {
+		irqentry_state_t state = irqentry_enter(regs);
+
+		instrumentation_begin();
+		sysvec_table[index](regs);
+		instrumentation_end();
+		irqentry_exit(regs, state);
+	} else {
+		common_interrupt(regs, vector);
+	}
+}
+
+static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code)
+{
+	/* Optimize for #PF. That's the only exception which matters performance wise */
+	if (likely(regs->fred_ss.vector == X86_TRAP_PF))
+		return exc_page_fault(regs, error_code);
+
+	switch (regs->fred_ss.vector) {
+	case X86_TRAP_DE: return exc_divide_error(regs);
+	case X86_TRAP_DB: return fred_exc_debug(regs);
+	case X86_TRAP_BR: return exc_bounds(regs);
+	case X86_TRAP_UD: return exc_invalid_op(regs);
+	case X86_TRAP_NM: return exc_device_not_available(regs);
+	case X86_TRAP_DF: return exc_double_fault(regs, error_code);
+	case X86_TRAP_TS: return exc_invalid_tss(regs, error_code);
+	case X86_TRAP_NP: return exc_segment_not_present(regs, error_code);
+	case X86_TRAP_SS: return exc_stack_segment(regs, error_code);
+	case X86_TRAP_GP: return exc_general_protection(regs, error_code);
+	case X86_TRAP_MF: return exc_coprocessor_error(regs);
+	case X86_TRAP_AC: return exc_alignment_check(regs, error_code);
+	case X86_TRAP_XF: return exc_simd_coprocessor_error(regs);
+
+#ifdef CONFIG_X86_MCE
+	case X86_TRAP_MC: return fred_exc_machine_check(regs);
+#endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+	case X86_TRAP_VE: return exc_virtualization_exception(regs);
+#endif
+#ifdef CONFIG_X86_CET
+	case X86_TRAP_CP: return exc_control_protection(regs, error_code);
+#endif
+	default: return fred_bad_type(regs, error_code);
+	}
+
+}
+
+static noinstr void fred_swexc(struct pt_regs *regs, unsigned long error_code)
+{
+	switch (regs->fred_ss.vector) {
+	case X86_TRAP_BP: return exc_int3(regs);
+	case X86_TRAP_OF: return exc_overflow(regs);
+	default: return fred_bad_type(regs, error_code);
+	}
+}
+
+__visible noinstr void fred_entry_from_user(struct pt_regs *regs)
+{
+	unsigned long error_code = regs->orig_ax;
+
+	/* Invalidate orig_ax so that syscall_get_nr() works correctly */
+	regs->orig_ax = -1;
+
+	switch (regs->fred_ss.type) {
+	case EVENT_TYPE_EXTINT:
+		return fred_extint(regs);
+	case EVENT_TYPE_NMI:
+		if (likely(regs->fred_ss.vector == X86_TRAP_NMI))
+			return fred_exc_nmi(regs);
+		break;
+	case EVENT_TYPE_HWEXC:
+		return fred_hwexc(regs, error_code);
+	case EVENT_TYPE_SWINT:
+		return fred_intx(regs);
+	case EVENT_TYPE_PRIV_SWEXC:
+		if (likely(regs->fred_ss.vector == X86_TRAP_DB))
+			return fred_exc_debug(regs);
+		break;
+	case EVENT_TYPE_SWEXC:
+		return fred_swexc(regs, error_code);
+	case EVENT_TYPE_OTHER:
+		return fred_other(regs);
+	default: break;
+	}
+
+	return fred_bad_type(regs, error_code);
+}
+
+__visible noinstr void fred_entry_from_kernel(struct pt_regs *regs)
+{
+	unsigned long error_code = regs->orig_ax;
+
+	/* Invalidate orig_ax so that syscall_get_nr() works correctly */
+	regs->orig_ax = -1;
+
+	switch (regs->fred_ss.type) {
+	case EVENT_TYPE_EXTINT:
+		return fred_extint(regs);
+	case EVENT_TYPE_NMI:
+		if (likely(regs->fred_ss.vector == X86_TRAP_NMI))
+			return fred_exc_nmi(regs);
+		break;
+	case EVENT_TYPE_HWEXC:
+		return fred_hwexc(regs, error_code);
+	case EVENT_TYPE_PRIV_SWEXC:
+		if (likely(regs->fred_ss.vector == X86_TRAP_DB))
+			return fred_exc_debug(regs);
+		break;
+	case EVENT_TYPE_SWEXC:
+		return fred_swexc(regs, error_code);
+	default: break;
+	}
+
+	return fred_bad_type(regs, error_code);
+}
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+__visible noinstr void __fred_entry_from_kvm(struct pt_regs *regs)
+{
+	switch (regs->fred_ss.type) {
+	case EVENT_TYPE_EXTINT:
+		return fred_extint(regs);
+	case EVENT_TYPE_NMI:
+		return fred_exc_nmi(regs);
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+#endif
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 0103e103a657..da37f42f4549 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -4,33 +4,15 @@
  * Copyright 2008 by Steven Rostedt, Red Hat, Inc
  *  (inspired by Andi Kleen's thunk_64.S)
  */
-	#include <linux/export.h>
-	#include <linux/linkage.h>
-	#include <asm/asm.h>
 
-	/* put return address in eax (arg1) */
-	.macro THUNK name, func, put_ret_addr_in_eax=0
-SYM_CODE_START_NOALIGN(\name)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
 
-	.if \put_ret_addr_in_eax
-	/* Place EIP in the arg1 */
-	movl 3*4(%esp), %eax
-	.endif
+#include "calling.h"
 
-	call \func
-	popl %edx
-	popl %ecx
-	popl %eax
-	RET
-	_ASM_NOKPROBE(\name)
-SYM_CODE_END(\name)
-	.endm
-
-	THUNK preempt_schedule_thunk, preempt_schedule
-	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
-	EXPORT_SYMBOL(preempt_schedule_thunk)
-	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
+THUNK preempt_schedule_thunk, preempt_schedule
+THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
+EXPORT_SYMBOL(preempt_schedule_thunk)
+EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
 
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 416b400f39db..119ebdc3d362 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -9,39 +9,6 @@
 #include "calling.h"
 #include <asm/asm.h>
 
-	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
-	.macro THUNK name, func
-SYM_FUNC_START(\name)
-	pushq %rbp
-	movq %rsp, %rbp
-
-	pushq %rdi
-	pushq %rsi
-	pushq %rdx
-	pushq %rcx
-	pushq %rax
-	pushq %r8
-	pushq %r9
-	pushq %r10
-	pushq %r11
-
-	call \func
-
-	popq %r11
-	popq %r10
-	popq %r9
-	popq %r8
-	popq %rax
-	popq %rcx
-	popq %rdx
-	popq %rsi
-	popq %rdi
-	popq %rbp
-	RET
-SYM_FUNC_END(\name)
-	_ASM_NOKPROBE(\name)
-	.endm
-
 THUNK preempt_schedule_thunk, preempt_schedule
 THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
 EXPORT_SYMBOL(preempt_schedule_thunk)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index b1b8dd1608f7..620f6257bbe9 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -3,7 +3,7 @@
 # Building vDSO images for x86.
 #
 
-# Include the generic Makefile to check the built vdso.
+# Include the generic Makefile to check the built vDSO:
 include $(srctree)/lib/vdso/Makefile
 
 # Sanitizer runtimes are unavailable and cannot be linked here.
@@ -18,48 +18,39 @@ OBJECT_FILES_NON_STANDARD	:= y
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT		:= n
 
-VDSO64-$(CONFIG_X86_64)		:= y
-VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
-VDSO32-$(CONFIG_X86_32)		:= y
-VDSO32-$(CONFIG_IA32_EMULATION)	:= y
-
-# files to link into the vdso
+# Files to link into the vDSO:
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
 vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o
 vobjs-$(CONFIG_X86_SGX)	+= vsgx.o
 
-# files to link into kernel
-obj-y					+= vma.o extable.o
-KASAN_SANITIZE_vma.o			:= y
-UBSAN_SANITIZE_vma.o			:= y
-KCSAN_SANITIZE_vma.o			:= y
-OBJECT_FILES_NON_STANDARD_vma.o		:= n
-OBJECT_FILES_NON_STANDARD_extable.o	:= n
+# Files to link into the kernel:
+obj-y						+= vma.o extable.o
+KASAN_SANITIZE_vma.o				:= y
+UBSAN_SANITIZE_vma.o				:= y
+KCSAN_SANITIZE_vma.o				:= y
+
+OBJECT_FILES_NON_STANDARD_vma.o			:= n
+OBJECT_FILES_NON_STANDARD_extable.o		:= n
 
-# vDSO images to build
-vdso_img-$(VDSO64-y)		+= 64
-vdso_img-$(VDSOX32-y)		+= x32
-vdso_img-$(VDSO32-y)		+= 32
+# vDSO images to build:
+obj-$(CONFIG_X86_64)				+= vdso-image-64.o
+obj-$(CONFIG_X86_X32_ABI)			+= vdso-image-x32.o
+obj-$(CONFIG_COMPAT_32)				+= vdso-image-32.o vdso32-setup.o
 
-obj-$(VDSO32-y)				 += vdso32-setup.o
-OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
+OBJECT_FILES_NON_STANDARD_vdso-image-32.o	:= n
+OBJECT_FILES_NON_STANDARD_vdso-image-64.o	:= n
+OBJECT_FILES_NON_STANDARD_vdso32-setup.o	:= n
 
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
-vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F)
+vobjs := $(addprefix $(obj)/, $(vobjs-y))
+vobjs32 := $(addprefix $(obj)/, $(vobjs32-y))
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
 targets += vdso.lds $(vobjs-y)
 targets += vdso32/vdso32.lds $(vobjs32-y)
 
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
-obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
 
 CPPFLAGS_vdso.lds += -P -C
 
@@ -87,7 +78,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
        -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
 ifneq ($(RETPOLINE_VDSO_CFLAGS),)
   CFL += $(RETPOLINE_VDSO_CFLAGS)
 endif
@@ -123,7 +114,7 @@ VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
 vobjx32s-y := $(vobjs-y:.o=-x32.o)
 
 # same thing, but in the output directory
-vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+vobjx32s := $(addprefix $(obj)/, $(vobjx32s-y))
 
 # Convert 64bit object file to x32 for x32 vDSO.
 quiet_cmd_x32 = X32     $@
@@ -164,7 +155,7 @@ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
 
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
 ifneq ($(RETPOLINE_VDSO_CFLAGS),)
   KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
 endif
@@ -190,5 +181,3 @@ GCOV_PROFILE := n
 
 quiet_cmd_vdso_and_check = VDSO    $@
       cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
-
-clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 7645730dc228..6d83ceb7f1ba 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -274,59 +274,6 @@ up_fail:
 	return ret;
 }
 
-#ifdef CONFIG_X86_64
-/*
- * Put the vdso above the (randomized) stack with another randomized
- * offset.  This way there is no hole in the middle of address space.
- * To save memory make sure it is still in the same PTE as the stack
- * top.  This doesn't give that many random bits.
- *
- * Note that this algorithm is imperfect: the distribution of the vdso
- * start address within a PMD is biased toward the end.
- *
- * Only used for the 64-bit and x32 vdsos.
- */
-static unsigned long vdso_addr(unsigned long start, unsigned len)
-{
-	unsigned long addr, end;
-	unsigned offset;
-
-	/*
-	 * Round up the start address.  It can start out unaligned as a result
-	 * of stack start randomization.
-	 */
-	start = PAGE_ALIGN(start);
-
-	/* Round the lowest possible end address up to a PMD boundary. */
-	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
-	if (end >= DEFAULT_MAP_WINDOW)
-		end = DEFAULT_MAP_WINDOW;
-	end -= len;
-
-	if (end > start) {
-		offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1);
-		addr = start + (offset << PAGE_SHIFT);
-	} else {
-		addr = start;
-	}
-
-	/*
-	 * Forcibly align the final address in case we have a hardware
-	 * issue that requires alignment for performance reasons.
-	 */
-	addr = align_vdso_addr(addr);
-
-	return addr;
-}
-
-static int map_vdso_randomized(const struct vdso_image *image)
-{
-	unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
-
-	return map_vdso(image, addr);
-}
-#endif
-
 int map_vdso_once(const struct vdso_image *image, unsigned long addr)
 {
 	struct mm_struct *mm = current->mm;
@@ -369,7 +316,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (!vdso64_enabled)
 		return 0;
 
-	return map_vdso_randomized(&vdso_image_64);
+	return map_vdso(&vdso_image_64, 0);
 }
 
 #ifdef CONFIG_COMPAT
@@ -380,7 +327,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (x32) {
 		if (!vdso64_enabled)
 			return 0;
-		return map_vdso_randomized(&vdso_image_x32);
+		return map_vdso(&vdso_image_x32, 0);
 	}
 #endif
 #ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index e0ca8120aea8..a3c0df11d0e6 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -76,7 +76,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x sp:%lx ax:%lx si:%lx di:%lx\n",
 			   level, current->comm, task_pid_nr(current),
 			   message, regs->ip, regs->cs,
 			   regs->sp, regs->ax, regs->si, regs->di);
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 81f6d8275b6b..69a3b02e50bb 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -579,7 +579,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	if (!x86_pmu.amd_nb_constraints)
 		return;
 
-	nb_id = topology_die_id(cpu);
+	nb_id = topology_amd_node_id(cpu);
 	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	for_each_online_cpu(i) {
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 5bf03c575812..4ccb8fa483e6 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -71,7 +71,7 @@ union amd_uncore_info {
 };
 
 struct amd_uncore {
-	union amd_uncore_info * __percpu info;
+	union amd_uncore_info  __percpu *info;
 	struct amd_uncore_pmu *pmus;
 	unsigned int num_pmus;
 	bool init_done;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3804f21ab049..768d1414897f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -17,6 +17,7 @@
 #include <linux/kvm_host.h>
 
 #include <asm/cpufeature.h>
+#include <asm/debugreg.h>
 #include <asm/hardirq.h>
 #include <asm/intel-family.h>
 #include <asm/intel_pt.h>
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4b50a3a9818a..326c8cd5aa2d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -834,7 +834,7 @@ static int __init cstate_init(void)
 	}
 
 	if (has_cstate_pkg) {
-		if (topology_max_die_per_package() > 1) {
+		if (topology_max_dies_per_package() > 1) {
 			err = perf_pmu_register(&cstate_pkg_pmu,
 						"cstate_die", -1);
 		} else {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d49d661ec0a7..2641ba620f12 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -5,6 +5,7 @@
 #include <linux/sched/clock.h>
 
 #include <asm/cpu_entry_area.h>
+#include <asm/debugreg.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/insn.h>
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 7927c0b832fa..258e2cdf28fa 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1893,7 +1893,7 @@ static int __init intel_uncore_init(void)
 		return -ENODEV;
 
 	__uncore_max_dies =
-		topology_max_packages() * topology_max_die_per_package();
+		topology_max_packages() * topology_max_dies_per_package();
 
 	id = x86_match_cpu(intel_uncore_match);
 	if (!id) {
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 56eea2c66cfb..92da8aaa5966 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1221,8 +1221,8 @@ void nhmex_uncore_cpu_init(void)
 		uncore_nhmex = true;
 	else
 		nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
-	if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (nhmex_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		nhmex_uncore_cbox.num_boxes = topology_num_cores_per_package();
 	uncore_msr_uncores = nhmex_msr_uncores;
 }
 /* end of Nehalem-EX uncore support */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 7fd4334e12a1..9462fd9f3b7a 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -364,8 +364,8 @@ static struct intel_uncore_type *snb_msr_uncores[] = {
 void snb_uncore_cpu_init(void)
 {
 	uncore_msr_uncores = snb_msr_uncores;
-	if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (snb_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		snb_uncore_cbox.num_boxes = topology_num_cores_per_package();
 }
 
 static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
@@ -428,8 +428,8 @@ static struct intel_uncore_type *skl_msr_uncores[] = {
 void skl_uncore_cpu_init(void)
 {
 	uncore_msr_uncores = skl_msr_uncores;
-	if (skl_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		skl_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (skl_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		skl_uncore_cbox.num_boxes = topology_num_cores_per_package();
 	snb_uncore_arb.ops = &skl_uncore_msr_ops;
 }
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index a96496bef678..2eaf0f339849 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1172,8 +1172,8 @@ static struct intel_uncore_type *snbep_msr_uncores[] = {
 
 void snbep_uncore_cpu_init(void)
 {
-	if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (snbep_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		snbep_uncore_cbox.num_boxes = topology_num_cores_per_package();
 	uncore_msr_uncores = snbep_msr_uncores;
 }
 
@@ -1406,7 +1406,7 @@ static int topology_gidnid_map(int nodeid, u32 gidnid)
 	 */
 	for (i = 0; i < 8; i++) {
 		if (nodeid == GIDNIDMAP(gidnid, i)) {
-			if (topology_max_die_per_package() > 1)
+			if (topology_max_dies_per_package() > 1)
 				die_id = i;
 			else
 				die_id = topology_phys_to_logical_pkg(i);
@@ -1845,8 +1845,8 @@ static struct intel_uncore_type *ivbep_msr_uncores[] = {
 
 void ivbep_uncore_cpu_init(void)
 {
-	if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (ivbep_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		ivbep_uncore_cbox.num_boxes = topology_num_cores_per_package();
 	uncore_msr_uncores = ivbep_msr_uncores;
 }
 
@@ -2917,8 +2917,8 @@ static bool hswep_has_limit_sbox(unsigned int device)
 
 void hswep_uncore_cpu_init(void)
 {
-	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (hswep_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		hswep_uncore_cbox.num_boxes = topology_num_cores_per_package();
 
 	/* Detect 6-8 core systems with only two SBOXes */
 	if (hswep_has_limit_sbox(HSWEP_PCU_DID))
@@ -3280,8 +3280,8 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
 
 void bdx_uncore_cpu_init(void)
 {
-	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
-		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	if (bdx_uncore_cbox.num_boxes > topology_num_cores_per_package())
+		bdx_uncore_cbox.num_boxes = topology_num_cores_per_package();
 	uncore_msr_uncores = bdx_msr_uncores;
 
 	/* Detect systems with no SBOXes */
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 8d98d468b976..fb2b1961e5a3 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -674,7 +674,7 @@ static const struct attribute_group *rapl_attr_update[] = {
 
 static int __init init_rapl_pmus(void)
 {
-	int maxdie = topology_max_packages() * topology_max_die_per_package();
+	int maxdie = topology_max_packages() * topology_max_dies_per_package();
 	size_t size;
 
 	size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 96e6c51515f5..edd2f35b2a5e 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -16,6 +16,11 @@
 extern struct boot_params boot_params;
 static struct real_mode_header hv_vtl_real_mode_header;
 
+static bool __init hv_vtl_msi_ext_dest_id(void)
+{
+	return true;
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -26,8 +31,9 @@ void __init hv_vtl_init_platform(void)
 	x86_init.timers.timer_init = x86_init_noop;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+	x86_init.mpparse.find_mptable = x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg = x86_init_noop;
+	x86_init.mpparse.parse_smp_cfg = x86_init_noop;
 
 	x86_platform.get_wallclock = get_rtc_noop;
 	x86_platform.set_wallclock = set_rtc_noop;
@@ -38,6 +44,8 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.legacy.warm_reset = 0;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 0;
+
+	x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id;
 }
 
 static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 7dcbf153ad72..768d73de0d09 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -15,6 +15,7 @@
 #include <asm/io.h>
 #include <asm/coco.h>
 #include <asm/mem_encrypt.h>
+#include <asm/set_memory.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mtrr.h>
@@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 }
 
 /*
+ * When transitioning memory between encrypted and decrypted, the caller
+ * of set_memory_encrypted() or set_memory_decrypted() is responsible for
+ * ensuring that the memory isn't in use and isn't referenced while the
+ * transition is in progress.  The transition has multiple steps, and the
+ * memory is in an inconsistent state until all steps are complete. A
+ * reference while the state is inconsistent could result in an exception
+ * that can't be cleanly fixed up.
+ *
+ * But the Linux kernel load_unaligned_zeropad() mechanism could cause a
+ * stray reference that can't be prevented by the caller, so Linux has
+ * specific code to handle this case. But when the #VC and #VE exceptions
+ * routed to a paravisor, the specific code doesn't work. To avoid this
+ * problem, mark the pages as "not present" while the transition is in
+ * progress. If load_unaligned_zeropad() causes a stray reference, a normal
+ * page fault is generated instead of #VC or #VE, and the page-fault-based
+ * handlers for load_unaligned_zeropad() resolve the reference.  When the
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+{
+	return !set_memory_np(kbuffer, pagecount);
+}
+
+/*
  * hv_vtom_set_host_visibility - Set specified memory visible to host.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
@@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 	enum hv_mem_host_visibility visibility = enc ?
 			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
+	phys_addr_t paddr;
+	void *vaddr;
 	int ret = 0;
 	bool result = true;
 	int i, pfn;
 
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-	if (!pfn_array)
-		return false;
+	if (!pfn_array) {
+		result = false;
+		goto err_set_memory_p;
+	}
 
 	for (i = 0, pfn = 0; i < pagecount; i++) {
-		pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
+		/*
+		 * Use slow_virt_to_phys() because the PRESENT bit has been
+		 * temporarily cleared in the PTEs.  slow_virt_to_phys() works
+		 * without the PRESENT bit while virt_to_hvpfn() or similar
+		 * does not.
+		 */
+		vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE);
+		paddr = slow_virt_to_phys(vaddr);
+		pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT;
 		pfn++;
 
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
@@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 		}
 	}
 
- err_free_pfn_array:
+err_free_pfn_array:
 	kfree(pfn_array);
+
+err_set_memory_p:
+	/*
+	 * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present()
+	 * did. Do this even if there is an error earlier in this function in
+	 * order to avoid leaving the memory range in a "broken" state. Setting
+	 * the PRESENT bits shouldn't fail, but return an error if it does.
+	 */
+	if (set_memory_p(kbuffer, pagecount))
+		result = false;
+
 	return result;
 }
 
 static bool hv_vtom_tlb_flush_required(bool private)
 {
-	return true;
+	/*
+	 * Since hv_vtom_clear_present() marks the PTEs as "not present"
+	 * and flushes the TLB, they can't be in the TLB. That makes the
+	 * flush controlled by this function redundant, so return "false".
+	 */
+	return false;
 }
 
 static bool hv_vtom_cache_flush_required(void)
@@ -608,6 +662,7 @@ void __init hv_vtom_init(void)
 	x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
 	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+	x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
 
 	/* Set WB as the default cache mode. */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9d159b771dc8..94ce0f7c9d3a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -46,6 +46,10 @@ extern void x86_32_probe_apic(void);
 static inline void x86_32_probe_apic(void) { }
 #endif
 
+extern u32 cpuid_to_apicid[];
+
+#define CPU_ACPIID_INVALID	U32_MAX
+
 #ifdef CONFIG_X86_LOCAL_APIC
 
 extern int apic_verbosity;
@@ -54,8 +58,6 @@ extern int local_apic_timer_c2_ok;
 extern bool apic_is_disabled;
 extern unsigned int lapic_timer_period;
 
-extern u32 cpuid_to_apicid[];
-
 extern enum apic_intr_mode_id apic_intr_mode;
 enum apic_intr_mode_id {
 	APIC_PIC,
@@ -169,6 +171,14 @@ extern bool apic_needs_pit(void);
 
 extern void apic_send_IPI_allbutself(unsigned int vector);
 
+extern void topology_register_apic(u32 apic_id, u32 acpi_id, bool present);
+extern void topology_register_boot_apic(u32 apic_id);
+extern int topology_hotplug_apic(u32 apic_id, u32 acpi_id);
+extern void topology_hotunplug_apic(unsigned int cpu);
+extern void topology_apply_cmdline_limits_early(void);
+extern void topology_init_possible_cpus(void);
+extern void topology_reset_possible_cpus_up(void);
+
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
@@ -183,6 +193,8 @@ static inline void apic_intr_mode_init(void) { }
 static inline void lapic_assign_system_vectors(void) { }
 static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
 static inline bool apic_needs_pit(void) { return true; }
+static inline void topology_apply_cmdline_limits_early(void) { }
+static inline void topology_init_possible_cpus(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_X2APIC
@@ -289,16 +301,11 @@ struct apic {
 	/* Probe, setup and smpboot functions */
 	int	(*probe)(void);
 	int	(*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	bool	(*apic_id_registered)(void);
 
-	bool	(*check_apicid_used)(physid_mask_t *map, u32 apicid);
 	void	(*init_apic_ldr)(void);
-	void	(*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
 	u32	(*cpu_present_to_apicid)(int mps_cpu);
-	u32	(*phys_pkg_id)(u32 cpuid_apic, int index_msb);
 
 	u32	(*get_apic_id)(u32 id);
-	u32	(*set_apic_id)(u32 apicid);
 
 	/* wakeup_secondary_cpu */
 	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
@@ -527,7 +534,6 @@ extern int default_apic_id_valid(u32 apicid);
 extern u32 apic_default_calc_apicid(unsigned int cpu);
 extern u32 apic_flat_calc_apicid(unsigned int cpu);
 
-extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
 extern u32 default_cpu_present_to_apicid(int mps_cpu);
 
 void apic_send_nmi_to_offline_cpu(unsigned int cpu);
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index b1a98fa38828..076bf8dee702 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -12,6 +12,7 @@
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
 #include <asm/asm.h>
+#include <asm/fred.h>
 #include <asm/gsseg.h>
 
 #ifndef CONFIG_X86_CMPXCHG64
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index fbcfec4dc4cc..ca8eed1d496a 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -113,6 +113,20 @@
 
 #endif
 
+#ifndef __ASSEMBLY__
+#ifndef __pic__
+static __always_inline __pure void *rip_rel_ptr(void *p)
+{
+	asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p));
+
+	return p;
+}
+#define RIP_REL_REF(var)	(*(typeof(&(var)))rip_rel_ptr(&(var)))
+#else
+#define RIP_REL_REF(var)	(var)
+#endif
+#endif
+
 /*
  * Macros to generate condition code outputs from inline assembly,
  * The output operand must be type "bool".
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 0216f63a366b..fe1e7e3cc844 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -33,7 +33,7 @@
  * Returns:
  *     0 - (index < size)
  */
-static inline unsigned long array_index_mask_nospec(unsigned long index,
+static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
 		unsigned long size)
 {
 	unsigned long mask;
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613..fb7388bbc212 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_COCO_H
 #define _ASM_X86_COCO_H
 
+#include <asm/asm.h>
 #include <asm/types.h>
 
 enum cc_vendor {
@@ -10,13 +11,20 @@ enum cc_vendor {
 	CC_VENDOR_INTEL,
 };
 
+#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
 extern enum cc_vendor cc_vendor;
+extern u64 cc_mask;
+
+static inline void cc_set_mask(u64 mask)
+{
+	RIP_REL_REF(cc_mask) = mask;
+}
 
-#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
-void cc_set_mask(u64 mask);
 u64 cc_mkenc(u64 val);
 u64 cc_mkdec(u64 val);
 #else
+#define cc_vendor (CC_VENDOR_NONE)
+
 static inline u64 cc_mkenc(u64 val)
 {
 	return val;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index f8f9a9b79395..aa30fd8cad7f 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -9,18 +9,10 @@
 #include <linux/percpu.h>
 #include <asm/ibt.h>
 
-#ifdef CONFIG_SMP
-
-extern void prefill_possible_map(void);
-
-#else /* CONFIG_SMP */
-
-static inline void prefill_possible_map(void) {}
-
+#ifndef CONFIG_SMP
 #define cpu_physical_id(cpu)			boot_cpu_physical_apicid
 #define cpu_acpi_id(cpu)			0
 #define safe_smp_processor_id()			0
-
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87..a1273698fc43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto(
+	asm goto(
 		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index fdf723b6f6d0..f0337f7bcf16 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -95,7 +95,7 @@
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC		( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* "" Clear CPU buffers using VERW */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
@@ -324,7 +324,9 @@
 #define X86_FEATURE_FZRM		(12*32+10) /* "" Fast zero-length REP MOVSB */
 #define X86_FEATURE_FSRS		(12*32+11) /* "" Fast short REP STOSB */
 #define X86_FEATURE_FSRC		(12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
+#define X86_FEATURE_FRED		(12*32+17) /* Flexible Return and Event Delivery */
 #define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
+#define X86_FEATURE_WRMSRNS		(12*32+19) /* "" Non-serializing WRMSR */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* Linear Address Masking */
@@ -440,6 +442,7 @@
 #define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
 #define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP		(19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
@@ -503,4 +506,5 @@
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
 #define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index 9bee3e7bf973..6b122a31da06 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -127,6 +127,42 @@ static inline unsigned int cpuid_edx(unsigned int op)
 	return edx;
 }
 
+static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs)
+{
+	regs[CPUID_EAX] = leaf;
+	regs[CPUID_ECX] = subleaf;
+	__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
+}
+
+#define cpuid_subleaf(leaf, subleaf, regs) {		\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, subleaf, (u32 *)(regs));	\
+}
+
+#define cpuid_leaf(leaf, regs) {			\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, 0, (u32 *)(regs));		\
+}
+
+static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf,
+				    enum cpuid_regs_idx regidx, u32 *reg)
+{
+	u32 regs[4];
+
+	__cpuid_read(leaf, subleaf, regs);
+	*reg = regs[regidx];
+}
+
+#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) {		\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg));	\
+}
+
+#define cpuid_leaf_reg(leaf, regidx, reg) {			\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg));	\
+}
+
 static __always_inline bool cpuid_function_is_indexed(u32 function)
 {
 	switch (function) {
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index dd4b67101bb7..bf5953883ec3 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -18,7 +18,7 @@ struct pcpu_hot {
 			struct task_struct	*current_task;
 			int			preempt_count;
 			int			cpu_number;
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 			u64			call_depth;
 #endif
 			unsigned long		top_of_stack;
@@ -37,8 +37,15 @@ static_assert(sizeof(struct pcpu_hot) == 64);
 
 DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
 
+/* const-qualified alias to pcpu_hot, aliased by linker. */
+DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
+			const_pcpu_hot);
+
 static __always_inline struct task_struct *get_current(void)
 {
+	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+		return this_cpu_read_const(const_pcpu_hot.current_task);
+
 	return this_cpu_read_stable(pcpu_hot.current_task);
 }
 
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 0cec92c430cc..fdbbbfec745a 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -5,7 +5,9 @@
 #include <linux/bug.h>
 #include <linux/percpu.h>
 #include <uapi/asm/debugreg.h>
+
 #include <asm/cpufeature.h>
+#include <asm/msr.h>
 
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
@@ -159,4 +161,26 @@ static inline unsigned long amd_get_dr_addr_mask(unsigned int dr)
 }
 #endif
 
+static inline unsigned long get_debugctlmsr(void)
+{
+	unsigned long debugctlmsr = 0;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return 0;
+#endif
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+
+	return debugctlmsr;
+}
+
+static inline void update_debugctlmsr(unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return;
+#endif
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+}
+
 #endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index ab97b22ac04a..62dc9f59ea76 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,6 +46,7 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
@@ -402,8 +403,6 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
 	desc->limit1 = (limit >> 16) & 0xf;
 }
 
-void alloc_intr_gate(unsigned int n, const void *addr);
-
 static inline void init_idt_data(struct idt_data *data, unsigned int n,
 				 const void *addr)
 {
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 702d93fdd10e..da4054fbf533 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -44,32 +44,32 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 # define DISABLE_PTI		0
 #else
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 # define DISABLE_RETPOLINE	0
 #else
 # define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
 				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
 #endif
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 # define DISABLE_RETHUNK	0
 #else
 # define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
 #endif
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 # define DISABLE_UNRET		0
 #else
 # define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
 #endif
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 # define DISABLE_CALL_DEPTH_TRACKING	0
 #else
 # define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
@@ -117,6 +117,18 @@
 #define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
 #endif
 
+#ifdef CONFIG_X86_FRED
+# define DISABLE_FRED	0
+#else
+# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
+#endif
+
+#ifdef CONFIG_KVM_AMD_SEV
+#define DISABLE_SEV_SNP		0
+#else
+#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -133,7 +145,7 @@
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_LAM)
+#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
@@ -141,7 +153,7 @@
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	0
+#define DISABLED_MASK19	(DISABLE_SEV_SNP)
 #define DISABLED_MASK20	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c4555b269a1b..1dc600fa3ba5 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -143,15 +143,6 @@ extern void efi_free_boot_services(void);
 void arch_efi_call_virt_setup(void);
 void arch_efi_call_virt_teardown(void);
 
-/* kexec external ABI */
-struct efi_setup_data {
-	u64 fw_vendor;
-	u64 __unused;
-	u64 tables;
-	u64 smbios;
-	u64 reserved[8];
-};
-
 extern u64 efi_setup;
 
 #ifdef CONFIG_EFI
@@ -418,8 +409,9 @@ extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
 extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap,
 				     void *buf, struct efi_mem_range *mem);
 
-#define arch_ima_efi_boot_mode	\
-	({ extern struct boot_params boot_params; boot_params.secure_boot; })
+extern enum efi_secureboot_mode __x86_ima_efi_boot_mode(void);
+
+#define arch_ima_efi_boot_mode	__x86_ima_efi_boot_mode()
 
 #ifdef CONFIG_EFI_RUNTIME_MAP
 int efi_get_runtime_map_size(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1e16bd5ac781..1fb83d47711f 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -392,5 +392,4 @@ struct va_alignment {
 } ____cacheline_aligned;
 
 extern struct va_alignment va_align;
-extern unsigned long align_vdso_addr(unsigned long);
 #endif /* _ASM_X86_ELF_H */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index ce8f50192ae3..7e523bb3d2d3 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 
 static __always_inline void arch_exit_to_user_mode(void)
 {
-	mds_user_clear_cpu_buffers();
 	amd_clear_divider();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index fe6312045042..7acf0383be80 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,6 +64,8 @@
 #define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
 #define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
-#define EX_TYPE_ZEROPAD			20 /* longword load with zeropad on fault */
+#define	EX_TYPE_ZEROPAD			20 /* longword load with zeropad on fault */
+
+#define	EX_TYPE_ERETU			21
 
 #endif
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index ca6e5e5f16b2..c485f1944c5f 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -37,10 +37,12 @@ extern void fpu_flush_thread(void);
  * The FPU context is only stored/restored for a user task and
  * PF_KTHREAD is used to distinguish between kernel and user threads.
  */
-static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
 {
 	if (cpu_feature_enabled(X86_FEATURE_FPU) &&
-	    !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+	    !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+		struct fpu *old_fpu = &old->thread.fpu;
+
 		save_fpregs_to_fpstate(old_fpu);
 		/*
 		 * The save operation preserved register state, so the
@@ -60,10 +62,10 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  * Delay loading of the complete FPU state until the return to userland.
  * PKRU is handled separately.
  */
-static inline void switch_fpu_finish(void)
+static inline void switch_fpu_finish(struct task_struct *new)
 {
 	if (cpu_feature_enabled(X86_FEATURE_FPU))
-		set_thread_flag(TIF_NEED_FPU_LOAD);
+		set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD);
 }
 
 #endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
new file mode 100644
index 000000000000..e86c7ba32435
--- /dev/null
+++ b/arch/x86/include/asm/fred.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Macros for Flexible Return and Event Delivery (FRED)
+ */
+
+#ifndef ASM_X86_FRED_H
+#define ASM_X86_FRED_H
+
+#include <linux/const.h>
+
+#include <asm/asm.h>
+#include <asm/trapnr.h>
+
+/*
+ * FRED event return instruction opcodes for ERET{S,U}; supported in
+ * binutils >= 2.41.
+ */
+#define ERETS			_ASM_BYTES(0xf2,0x0f,0x01,0xca)
+#define ERETU			_ASM_BYTES(0xf3,0x0f,0x01,0xca)
+
+/*
+ * RSP is aligned to a 64-byte boundary before used to push a new stack frame
+ */
+#define FRED_STACK_FRAME_RSP_MASK	_AT(unsigned long, (~0x3f))
+
+/*
+ * Used for the return address for call emulation during code patching,
+ * and measured in 64-byte cache lines.
+ */
+#define FRED_CONFIG_REDZONE_AMOUNT	1
+#define FRED_CONFIG_REDZONE		(_AT(unsigned long, FRED_CONFIG_REDZONE_AMOUNT) << 6)
+#define FRED_CONFIG_INT_STKLVL(l)	(_AT(unsigned long, l) << 9)
+#define FRED_CONFIG_ENTRYPOINT(p)	_AT(unsigned long, (p))
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_X86_FRED
+#include <linux/kernel.h>
+
+#include <asm/ptrace.h>
+
+struct fred_info {
+	/* Event data: CR2, DR6, ... */
+	unsigned long edata;
+	unsigned long resv;
+};
+
+/* Full format of the FRED stack frame */
+struct fred_frame {
+	struct pt_regs   regs;
+	struct fred_info info;
+};
+
+static __always_inline struct fred_info *fred_info(struct pt_regs *regs)
+{
+	return &container_of(regs, struct fred_frame, regs)->info;
+}
+
+static __always_inline unsigned long fred_event_data(struct pt_regs *regs)
+{
+	return fred_info(regs)->edata;
+}
+
+void asm_fred_entrypoint_user(void);
+void asm_fred_entrypoint_kernel(void);
+void asm_fred_entry_from_kvm(struct fred_ss);
+
+__visible void fred_entry_from_user(struct pt_regs *regs);
+__visible void fred_entry_from_kernel(struct pt_regs *regs);
+__visible void __fred_entry_from_kvm(struct pt_regs *regs);
+
+/* Can be called from noinstr code, thus __always_inline */
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector)
+{
+	struct fred_ss ss = {
+		.ss     =__KERNEL_DS,
+		.type   = type,
+		.vector = vector,
+		.nmi    = type == EVENT_TYPE_NMI,
+		.lm     = 1,
+	};
+
+	asm_fred_entry_from_kvm(ss);
+}
+
+void cpu_init_fred_exceptions(void);
+void fred_complete_exception_setup(void);
+
+#else /* CONFIG_X86_FRED */
+static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; }
+static inline void cpu_init_fred_exceptions(void) { }
+static inline void fred_complete_exception_setup(void) { }
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+#endif /* CONFIG_X86_FRED */
+#endif /* !__ASSEMBLY__ */
+
+#endif /* ASM_X86_FRED_H */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 35cff5f2becf..9e7e8ca8e299 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -6,7 +6,7 @@
 
 #ifdef CONFIG_X86_64
 
-#include <asm/msr-index.h>
+#include <asm/msr.h>
 
 /*
  * Read/write a task's FSBASE or GSBASE. This returns the value that
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b02c3cd3c0f6..edebf1020e04 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,8 +16,6 @@
 
 #include <asm/irq_vectors.h>
 
-#define IRQ_MATRIX_BITS		NR_VECTORS
-
 #ifndef __ASSEMBLY__
 
 #include <linux/percpu.h>
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index c7ef6ea2fa99..4212c00c9708 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -69,7 +69,7 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm);
 
 extern bool __ia32_enabled;
 
-static inline bool ia32_enabled(void)
+static __always_inline bool ia32_enabled(void)
 {
 	return __ia32_enabled;
 }
@@ -81,7 +81,7 @@ static inline void ia32_disable(void)
 
 #else /* !CONFIG_IA32_EMULATION */
 
-static inline bool ia32_enabled(void)
+static __always_inline bool ia32_enabled(void)
 {
 	return IS_ENABLED(CONFIG_X86_32);
 }
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 13639e57e1f8..47d4c04d103d 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -13,15 +13,18 @@
 
 #include <asm/irq_stack.h>
 
+typedef void (*idtentry_t)(struct pt_regs *regs);
+
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
  *		      No error code pushed by hardware
  * @vector:	Vector number (ignored for C)
  * @func:	Function name of the entry point
  *
- * Declares three functions:
+ * Declares four functions:
  * - The ASM entry point: asm_##func
  * - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the FRED event dispatcher (maybe unused)
  * - The C handler called from the ASM entry point
  *
  * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it
@@ -31,6 +34,7 @@
 #define DECLARE_IDTENTRY(vector, func)					\
 	asmlinkage void asm_##func(void);				\
 	asmlinkage void xen_asm_##func(void);				\
+	void fred_##func(struct pt_regs *regs);				\
 	__visible void func(struct pt_regs *regs)
 
 /**
@@ -138,6 +142,17 @@ static __always_inline void __##func(struct pt_regs *regs,		\
 __visible noinstr void func(struct pt_regs *regs)
 
 /**
+ * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points
+ * @func:	Function name of the entry point
+ *
+ * @func is called from the FRED event dispatcher with interrupts disabled.
+ *
+ * See @DEFINE_IDTENTRY_RAW for further details.
+ */
+#define DEFINE_FREDENTRY_RAW(func)					\
+noinstr void fred_##func(struct pt_regs *regs)
+
+/**
  * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points
  *				    Error code pushed by hardware
  * @vector:	Vector number (ignored for C)
@@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector)
 #define DEFINE_IDTENTRY_SYSVEC(func)					\
 static void __##func(struct pt_regs *regs);				\
 									\
+static __always_inline void instr_##func(struct pt_regs *regs)		\
+{									\
+	kvm_set_cpu_l1tf_flush_l1d();					\
+	run_sysvec_on_irqstack_cond(__##func, regs);			\
+}									\
+									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
 	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
-	kvm_set_cpu_l1tf_flush_l1d();					\
-	run_sysvec_on_irqstack_cond(__##func, regs);			\
+	instr_##func (regs);						\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\
 }									\
 									\
+void fred_##func(struct pt_regs *regs)					\
+{									\
+	instr_##func (regs);						\
+}									\
+									\
 static noinline void __##func(struct pt_regs *regs)
 
 /**
@@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs)
 #define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func)				\
 static __always_inline void __##func(struct pt_regs *regs);		\
 									\
-__visible noinstr void func(struct pt_regs *regs)			\
+static __always_inline void instr_##func(struct pt_regs *regs)		\
 {									\
-	irqentry_state_t state = irqentry_enter(regs);			\
-									\
-	instrumentation_begin();					\
 	__irq_enter_raw();						\
 	kvm_set_cpu_l1tf_flush_l1d();					\
 	__##func (regs);						\
 	__irq_exit_raw();						\
+}									\
+									\
+__visible noinstr void func(struct pt_regs *regs)			\
+{									\
+	irqentry_state_t state = irqentry_enter(regs);			\
+									\
+	instrumentation_begin();					\
+	instr_##func (regs);						\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\
 }									\
 									\
+void fred_##func(struct pt_regs *regs)					\
+{									\
+	instr_##func (regs);						\
+}									\
+									\
 static __always_inline void __##func(struct pt_regs *regs)
 
 /**
@@ -410,17 +445,35 @@ __visible noinstr void func(struct pt_regs *regs,			\
 /* C-Code mapping */
 #define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
 #define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
+#define DEFINE_FREDENTRY_NMI		DEFINE_FREDENTRY_RAW
 
 #ifdef CONFIG_X86_64
 #define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
+#define DEFINE_FREDENTRY_MCE		DEFINE_FREDENTRY_RAW
 
 #define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
+#define DEFINE_FREDENTRY_DEBUG		DEFINE_FREDENTRY_RAW
+#endif
+
+void idt_install_sysvec(unsigned int n, const void *function);
+
+#ifdef CONFIG_X86_FRED
+void fred_install_sysvec(unsigned int vector, const idtentry_t function);
+#else
+static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { }
 #endif
 
+#define sysvec_install(vector, function) {				\
+	if (cpu_feature_enabled(X86_FEATURE_FRED))			\
+		fred_install_sysvec(vector, function);			\
+	else								\
+		idt_install_sysvec(vector, asm_##function);		\
+}
+
 #else /* !__ASSEMBLY__ */
 
 /*
@@ -447,7 +500,7 @@ __visible noinstr void func(struct pt_regs *regs,			\
 
 /* System vector entries */
 #define DECLARE_IDTENTRY_SYSVEC(vector, func)				\
-	idtentry_sysvec vector func
+	DECLARE_IDTENTRY(vector, func)
 
 #ifdef CONFIG_X86_64
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
@@ -655,23 +708,36 @@ DECLARE_IDTENTRY(RESCHEDULE_VECTOR,			sysvec_reschedule_ipi);
 DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR,			sysvec_reboot);
 DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR,	sysvec_call_function_single);
 DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR,		sysvec_call_function);
+#else
+# define fred_sysvec_reschedule_ipi			NULL
+# define fred_sysvec_reboot				NULL
+# define fred_sysvec_call_function_single		NULL
+# define fred_sysvec_call_function			NULL
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
 # ifdef CONFIG_X86_MCE_THRESHOLD
 DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR,		sysvec_threshold);
+# else
+# define fred_sysvec_threshold				NULL
 # endif
 
 # ifdef CONFIG_X86_MCE_AMD
 DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR,		sysvec_deferred_error);
+# else
+# define fred_sysvec_deferred_error			NULL
 # endif
 
 # ifdef CONFIG_X86_THERMAL_VECTOR
 DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR,		sysvec_thermal);
+# else
+# define fred_sysvec_thermal				NULL
 # endif
 
 # ifdef CONFIG_IRQ_WORK
 DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR,		sysvec_irq_work);
+# else
+# define fred_sysvec_irq_work				NULL
 # endif
 #endif
 
@@ -679,12 +745,16 @@ DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR,		sysvec_irq_work);
 DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR,		sysvec_kvm_posted_intr_ipi);
 DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR,	sysvec_kvm_posted_intr_wakeup_ipi);
 DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested_ipi);
+#else
+# define fred_sysvec_kvm_posted_intr_ipi		NULL
+# define fred_sysvec_kvm_posted_intr_wakeup_ipi		NULL
+# define fred_sysvec_kvm_posted_intr_nested_ipi		NULL
 #endif
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,		sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 3814a9263d64..294cd2a40818 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -379,7 +379,7 @@ static inline void iosubmit_cmds512(void __iomem *dst, const void *src,
 	const u8 *end = from + count * 64;
 
 	while (from < end) {
-		movdir64b(dst, from);
+		movdir64b_io(dst, from);
 		from += 64;
 	}
 }
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 51c782600e02..0d806513c4b3 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -140,7 +140,6 @@ extern void mask_ioapic_entries(void);
 extern int restore_ioapic_entries(void);
 
 extern void setup_ioapic_ids_from_mpc(void);
-extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
 extern int mp_find_ioapic(u32 gsi);
 extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 2fd52b65deac..3be2451e7bc8 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -10,6 +10,7 @@ extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_merge;
 extern int panic_on_overflow;
+extern bool amd_iommu_snp_en;
 
 #ifdef CONFIG_SWIOTLB
 extern bool x86_swiotlb_enable;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a..cbbef32517f0 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes] # objtool NOPs this \n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		".byte " __stringify(BYTES_NOP5) "\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes]\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index c9f6a6c5de3c..91ca9a9ee3a2 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -25,7 +25,6 @@
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <asm/bootparam.h>
 
 struct kimage;
 
diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h
index 8fa6ac0e2d76..d91b37f5b4bb 100644
--- a/arch/x86/include/asm/kmsan.h
+++ b/arch/x86/include/asm/kmsan.h
@@ -64,6 +64,7 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 {
 	unsigned long x = (unsigned long)addr;
 	unsigned long y = x - __START_KERNEL_map;
+	bool ret;
 
 	/* use the carry flag to determine if x was < __START_KERNEL_map */
 	if (unlikely(x > y)) {
@@ -79,7 +80,21 @@ static inline bool kmsan_virt_addr_valid(void *addr)
 			return false;
 	}
 
-	return pfn_valid(x >> PAGE_SHIFT);
+	/*
+	 * pfn_valid() relies on RCU, and may call into the scheduler on exiting
+	 * the critical section. However, this would result in recursion with
+	 * KMSAN. Therefore, disable preemption here, and re-enable preemption
+	 * below while suppressing reschedules to avoid recursion.
+	 *
+	 * Note, this sacrifices occasionally breaking scheduling guarantees.
+	 * Although, a kernel compiled with KMSAN has already given up on any
+	 * performance guarantees due to being heavily instrumented.
+	 */
+	preempt_disable();
+	ret = pfn_valid(x >> PAGE_SHIFT);
+	preempt_enable_no_resched();
+
+	return ret;
 }
 
 #endif /* !MODULE */
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 378ed944b849..ab24ce207988 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -138,6 +138,7 @@ KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
+KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b5b2d0fde579..18cbde14cf81 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1145,6 +1145,8 @@ struct kvm_hv {
 	unsigned int synic_auto_eoi_used;
 
 	struct kvm_hv_syndbg hv_syndbg;
+
+	bool xsaves_xsavec_checked;
 };
 #endif
 
@@ -1794,6 +1796,7 @@ struct kvm_x86_ops {
 	unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
 
 	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
+	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h
index 511b35069187..f163176d6f7f 100644
--- a/arch/x86/include/asm/kvmclock.h
+++ b/arch/x86/include/asm/kvmclock.h
@@ -4,8 +4,6 @@
 
 #include <linux/percpu.h>
 
-extern struct clocksource kvm_clock;
-
 DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 
 static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 571fe4d2d232..dc31b13b87a0 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -40,27 +40,27 @@
 
 #ifdef __ASSEMBLY__
 
-#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define RET	jmp __x86_return_thunk
-#else /* CONFIG_RETPOLINE */
-#ifdef CONFIG_SLS
+#else /* CONFIG_MITIGATION_RETPOLINE */
+#ifdef CONFIG_MITIGATION_SLS
 #define RET	ret; int3
 #else
 #define RET	ret
 #endif
-#endif /* CONFIG_RETPOLINE */
+#endif /* CONFIG_MITIGATION_RETPOLINE */
 
 #else /* __ASSEMBLY__ */
 
-#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define ASM_RET	"jmp __x86_return_thunk\n\t"
-#else /* CONFIG_RETPOLINE */
-#ifdef CONFIG_SLS
+#else /* CONFIG_MITIGATION_RETPOLINE */
+#ifdef CONFIG_MITIGATION_SLS
 #define ASM_RET	"ret; int3\n\t"
 #else
 #define ASM_RET	"ret\n\t"
 #endif
-#endif /* CONFIG_RETPOLINE */
+#endif /* CONFIG_MITIGATION_RETPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 73dba8b94443..59aa966dc212 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -131,8 +131,20 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
 				 (typeof(l->a.counter) *) old, new);
 }
 
-/* Always has a lock prefix */
-#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+/*
+ * Implement local_xchg using CMPXCHG instruction without the LOCK prefix.
+ * XCHG is expensive due to the implied LOCK prefix.  The processor
+ * cannot prefetch cachelines if XCHG is used.
+ */
+static __always_inline long
+local_xchg(local_t *l, long n)
+{
+	long c = local_read(l);
+
+	do { } while (!local_try_cmpxchg(l, &c, n));
+
+	return c;
+}
 
 /**
  * local_add_unless - add unless the number is already a given value
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 359ada486fa9..f922b682b9b4 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -15,7 +15,8 @@
 #include <linux/init.h>
 #include <linux/cc_platform.h>
 
-#include <asm/bootparam.h>
+#include <asm/asm.h>
+struct boot_params;
 
 #ifdef CONFIG_X86_MEM_ENCRYPT
 void __init mem_encrypt_init(void);
@@ -46,8 +47,8 @@ void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
 
-void __init sme_encrypt_kernel(struct boot_params *bp);
-void __init sme_enable(struct boot_params *bp);
+void sme_encrypt_kernel(struct boot_params *bp);
+void sme_enable(struct boot_params *bp);
 
 int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
 int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
@@ -58,6 +59,11 @@ void __init mem_encrypt_free_decrypted_mem(void);
 
 void __init sev_es_init_vc_handling(void);
 
+static inline u64 sme_get_me_mask(void)
+{
+	return RIP_REL_REF(sme_me_mask);
+}
+
 #define __bss_decrypted __section(".bss..decrypted")
 
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
@@ -75,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
 
-static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
-static inline void __init sme_enable(struct boot_params *bp) { }
+static inline void sme_encrypt_kernel(struct boot_params *bp) { }
+static inline void sme_enable(struct boot_params *bp) { }
 
 static inline void sev_es_init_vc_handling(void) { }
 
@@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en
 
 static inline void mem_encrypt_free_decrypted_mem(void) { }
 
+static inline u64 sme_get_me_mask(void) { return 0; }
+
 #define __bss_decrypted
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
@@ -106,11 +114,6 @@ void add_encrypt_protection_map(void);
 
 extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
 
-static inline u64 sme_get_me_mask(void)
-{
-	return sme_me_mask;
-}
-
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 4b0f98a8d338..c72c7ff78fcd 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_MPSPEC_H
 #define _ASM_X86_MPSPEC_H
 
+#include <linux/types.h>
 
 #include <asm/mpspec_def.h>
 #include <asm/x86_init.h>
@@ -46,70 +47,31 @@ extern int smp_found_config;
 # define smp_found_config 0
 #endif
 
-static inline void get_smp_config(void)
-{
-	x86_init.mpparse.get_smp_config(0);
-}
-
-static inline void early_get_smp_config(void)
-{
-	x86_init.mpparse.get_smp_config(1);
-}
-
-static inline void find_smp_config(void)
-{
-	x86_init.mpparse.find_smp_config();
-}
-
 #ifdef CONFIG_X86_MPPARSE
 extern void e820__memblock_alloc_reserved_mpc_new(void);
 extern int enable_update_mptable;
-extern void default_find_smp_config(void);
-extern void default_get_smp_config(unsigned int early);
+extern void mpparse_find_mptable(void);
+extern void mpparse_parse_early_smp_config(void);
+extern void mpparse_parse_smp_config(void);
 #else
 static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
-#define enable_update_mptable 0
-#define default_find_smp_config x86_init_noop
-#define default_get_smp_config x86_init_uint_noop
+#define enable_update_mptable		0
+#define mpparse_find_mptable		x86_init_noop
+#define mpparse_parse_early_smp_config	x86_init_noop
+#define mpparse_parse_smp_config	x86_init_noop
 #endif
 
-int generic_processor_info(int apicid);
+extern DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC);
 
-#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_LOCAL_APIC)
-
-struct physid_mask {
-	unsigned long mask[PHYSID_ARRAY_SIZE];
-};
-
-typedef struct physid_mask physid_mask_t;
-
-#define physid_set(physid, map)			set_bit(physid, (map).mask)
-#define physid_isset(physid, map)		test_bit(physid, (map).mask)
-
-#define physids_or(dst, src1, src2)					\
-	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
-
-#define physids_clear(map)					\
-	bitmap_zero((map).mask, MAX_LOCAL_APIC)
-
-#define physids_empty(map)					\
-	bitmap_empty((map).mask, MAX_LOCAL_APIC)
-
-static inline void physids_promote(unsigned long physids, physid_mask_t *map)
+static inline void reset_phys_cpu_present_map(u32 apicid)
 {
-	physids_clear(*map);
-	map->mask[0] = physids;
+	bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC);
+	set_bit(apicid, phys_cpu_present_map);
 }
 
-static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
+static inline void copy_phys_cpu_present_map(unsigned long *dst)
 {
-	physids_clear(*map);
-	physid_set(physid, *map);
+	bitmap_copy(dst, phys_cpu_present_map, MAX_LOCAL_APIC);
 }
 
-#define PHYSID_MASK_ALL		{ {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
-#define PHYSID_MASK_NONE	{ {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
-
-extern physid_mask_t phys_cpu_present_map;
-
 #endif /* _ASM_X86_MPSPEC_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index f1bd7b91b3c6..05956bd8bacf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -36,8 +36,19 @@
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
-/* Intel MSRs. Some also available on other CPUs */
+/* FRED MSRs */
+#define MSR_IA32_FRED_RSP0	0x1cc			/* Level 0 stack pointer */
+#define MSR_IA32_FRED_RSP1	0x1cd			/* Level 1 stack pointer */
+#define MSR_IA32_FRED_RSP2	0x1ce			/* Level 2 stack pointer */
+#define MSR_IA32_FRED_RSP3	0x1cf			/* Level 3 stack pointer */
+#define MSR_IA32_FRED_STKLVLS	0x1d0			/* Exception stack levels */
+#define MSR_IA32_FRED_SSP0	MSR_IA32_PL0_SSP	/* Level 0 shadow stack pointer */
+#define MSR_IA32_FRED_SSP1	0x1d1			/* Level 1 shadow stack pointer */
+#define MSR_IA32_FRED_SSP2	0x1d2			/* Level 2 shadow stack pointer */
+#define MSR_IA32_FRED_SSP3	0x1d3			/* Level 3 shadow stack pointer */
+#define MSR_IA32_FRED_CONFIG	0x1d4			/* Entrypoint and interrupt stack level */
 
+/* Intel MSRs. Some also available on other CPUs */
 #define MSR_TEST_CTRL				0x00000033
 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT	29
 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT		BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
@@ -165,6 +176,14 @@
 						 * CPU is not vulnerable to Gather
 						 * Data Sampling (GDS).
 						 */
+#define ARCH_CAP_RFDS_NO		BIT(27)	/*
+						 * Not susceptible to Register
+						 * File Data Sampling.
+						 */
+#define ARCH_CAP_RFDS_CLEAR		BIT(28)	/*
+						 * VERW clears CPU Register
+						 * File.
+						 */
 
 #define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
 						 * IA32_XAPIC_DISABLE_STATUS MSR
@@ -594,34 +613,47 @@
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
-#define MSR_AMD64_SEV_ES_ENABLED_BIT	1
-#define MSR_AMD64_SEV_SNP_ENABLED_BIT	2
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED_BIT	1
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT	2
 #define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
-
-/* SNP feature bits enabled by the hypervisor */
-#define MSR_AMD64_SNP_VTOM			BIT_ULL(3)
-#define MSR_AMD64_SNP_REFLECT_VC		BIT_ULL(4)
-#define MSR_AMD64_SNP_RESTRICTED_INJ		BIT_ULL(5)
-#define MSR_AMD64_SNP_ALT_INJ			BIT_ULL(6)
-#define MSR_AMD64_SNP_DEBUG_SWAP		BIT_ULL(7)
-#define MSR_AMD64_SNP_PREVENT_HOST_IBS		BIT_ULL(8)
-#define MSR_AMD64_SNP_BTB_ISOLATION		BIT_ULL(9)
-#define MSR_AMD64_SNP_VMPL_SSS			BIT_ULL(10)
-#define MSR_AMD64_SNP_SECURE_TSC		BIT_ULL(11)
-#define MSR_AMD64_SNP_VMGEXIT_PARAM		BIT_ULL(12)
-#define MSR_AMD64_SNP_IBS_VIRT			BIT_ULL(14)
-#define MSR_AMD64_SNP_VMSA_REG_PROTECTION	BIT_ULL(16)
-#define MSR_AMD64_SNP_SMT_PROTECTION		BIT_ULL(17)
-
-/* SNP feature bits reserved for future use. */
-#define MSR_AMD64_SNP_RESERVED_BIT13		BIT_ULL(13)
-#define MSR_AMD64_SNP_RESERVED_BIT15		BIT_ULL(15)
-#define MSR_AMD64_SNP_RESERVED_MASK		GENMASK_ULL(63, 18)
+#define MSR_AMD64_SNP_VTOM_BIT		3
+#define MSR_AMD64_SNP_VTOM		BIT_ULL(MSR_AMD64_SNP_VTOM_BIT)
+#define MSR_AMD64_SNP_REFLECT_VC_BIT	4
+#define MSR_AMD64_SNP_REFLECT_VC	BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT)
+#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5
+#define MSR_AMD64_SNP_RESTRICTED_INJ	BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT)
+#define MSR_AMD64_SNP_ALT_INJ_BIT	6
+#define MSR_AMD64_SNP_ALT_INJ		BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT)
+#define MSR_AMD64_SNP_DEBUG_SWAP_BIT	7
+#define MSR_AMD64_SNP_DEBUG_SWAP	BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS	BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT)
+#define MSR_AMD64_SNP_BTB_ISOLATION_BIT	9
+#define MSR_AMD64_SNP_BTB_ISOLATION	BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT)
+#define MSR_AMD64_SNP_VMPL_SSS_BIT	10
+#define MSR_AMD64_SNP_VMPL_SSS		BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT)
+#define MSR_AMD64_SNP_SECURE_TSC_BIT	11
+#define MSR_AMD64_SNP_SECURE_TSC	BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT	12
+#define MSR_AMD64_SNP_VMGEXIT_PARAM	BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT13	BIT_ULL(13)
+#define MSR_AMD64_SNP_IBS_VIRT_BIT	14
+#define MSR_AMD64_SNP_IBS_VIRT		BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT15	BIT_ULL(15)
+#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT	16
+#define MSR_AMD64_SNP_VMSA_REG_PROT	BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT)
+#define MSR_AMD64_SNP_SMT_PROT_BIT	17
+#define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		18
+#define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
+#define MSR_AMD64_RMP_BASE		0xc0010132
+#define MSR_AMD64_RMP_END		0xc0010133
+
 /* AMD Collaborative Processor Performance Control MSRs */
 #define MSR_AMD_CPPC_CAP1		0xc00102b0
 #define MSR_AMD_CPPC_ENABLE		0xc00102b1
@@ -708,8 +740,15 @@
 #define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K8_TOP_MEM2			0xc001001d
 #define MSR_AMD64_SYSCFG		0xc0010010
-#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT	23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG_SNP_EN_BIT	24
+#define MSR_AMD64_SYSCFG_SNP_EN		BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT)
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN	BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT)
+#define MSR_AMD64_SYSCFG_MFDM_BIT	19
+#define MSR_AMD64_SYSCFG_MFDM		BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT)
+
 #define MSR_K8_INT_PENDING_MSG		0xc0010055
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 65ec1965cd28..d642037f9ed5 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,11 +12,13 @@
 #include <uapi/asm/msr.h>
 #include <asm/shared/msr.h>
 
+#include <linux/percpu.h>
+
 struct msr_info {
-	u32 msr_no;
-	struct msr reg;
-	struct msr *msrs;
-	int err;
+	u32			msr_no;
+	struct msr		reg;
+	struct msr __percpu	*msrs;
+	int			err;
 };
 
 struct msr_regs_info {
@@ -97,6 +99,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
 		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
+/*
+ * WRMSRNS behaves exactly like WRMSR with the only difference being
+ * that it is not a serializing instruction by default.
+ */
+static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high)
+{
+	/* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */
+	asm volatile("1: .byte 0x0f,0x01,0xc6\n"
+		     "2:\n"
+		     _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
+		     : : "c" (msr), "a"(low), "d" (high));
+}
+
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
 	u64 __val = __rdmsr((msr));			\
@@ -297,6 +312,11 @@ do {							\
 
 #endif	/* !CONFIG_PARAVIRT_XXL */
 
+static __always_inline void wrmsrns(u32 msr, u64 val)
+{
+	__wrmsrns(msr, val, val >> 32);
+}
+
 /*
  * 64-bit version of wrmsr_safe():
  */
@@ -305,8 +325,8 @@ static inline int wrmsrl_safe(u32 msr, u64 val)
 	return wrmsr_safe(msr, (u32)val,  (u32)(val >> 32));
 }
 
-struct msr *msrs_alloc(void);
-void msrs_free(struct msr *msrs);
+struct msr __percpu *msrs_alloc(void);
+void msrs_free(struct msr __percpu *msrs);
 int msr_set_bit(u32 msr, u8 bit);
 int msr_clear_bit(u32 msr, u8 bit);
 
@@ -315,8 +335,8 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
 int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
 int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
@@ -345,14 +365,14 @@ static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 	return 0;
 }
 static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
-				struct msr *msrs)
+				struct msr __percpu *msrs)
 {
-	rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
+	rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h));
 }
 static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no,
-				struct msr *msrs)
+				struct msr __percpu *msrs)
 {
-	wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
+	wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h));
 }
 static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
 				    u32 *l, u32 *h)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 5c5f1e56c404..41a0ebb699ec 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -14,9 +14,6 @@ extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-struct ctl_table;
-extern int proc_nmi_enabled(struct ctl_table *, int ,
-			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
 #endif /* CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 262e65539f83..fc3a8a3c7ffe 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -59,13 +59,13 @@
 
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 # define CALL_THUNKS_DEBUG_INC_CALLS				\
-	incq	%gs:__x86_call_count;
+	incq	PER_CPU_VAR(__x86_call_count);
 # define CALL_THUNKS_DEBUG_INC_RETS				\
-	incq	%gs:__x86_ret_count;
+	incq	PER_CPU_VAR(__x86_ret_count);
 # define CALL_THUNKS_DEBUG_INC_STUFFS				\
-	incq	%gs:__x86_stuffs_count;
+	incq	PER_CPU_VAR(__x86_stuffs_count);
 # define CALL_THUNKS_DEBUG_INC_CTXSW				\
-	incq	%gs:__x86_ctxsw_count;
+	incq	PER_CPU_VAR(__x86_ctxsw_count);
 #else
 # define CALL_THUNKS_DEBUG_INC_CALLS
 # define CALL_THUNKS_DEBUG_INC_RETS
@@ -73,16 +73,13 @@
 # define CALL_THUNKS_DEBUG_INC_CTXSW
 #endif
 
-#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
+#if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
 
 #include <asm/asm-offsets.h>
 
 #define CREDIT_CALL_DEPTH					\
 	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
 
-#define ASM_CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
@@ -95,20 +92,14 @@
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, %gs:pcpu_hot + X86_call_depth;		\
-	CALL_THUNKS_DEBUG_INC_CALLS
-
-#define ASM_INCREMENT_CALL_DEPTH				\
 	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
 #define CREDIT_CALL_DEPTH
-#define ASM_CREDIT_CALL_DEPTH
 #define RESET_CALL_DEPTH
-#define INCREMENT_CALL_DEPTH
-#define ASM_INCREMENT_CALL_DEPTH
 #define RESET_CALL_DEPTH_FROM_CALL
+#define INCREMENT_CALL_DEPTH
 #endif
 
 /*
@@ -158,7 +149,7 @@
 	jnz	771b;					\
 	/* barrier for jnz misprediction */		\
 	lfence;						\
-	ASM_CREDIT_CALL_DEPTH				\
+	CREDIT_CALL_DEPTH				\
 	CALL_THUNKS_DEBUG_INC_CTXSW
 #else
 /*
@@ -212,7 +203,7 @@
  */
 .macro VALIDATE_UNRET_END
 #if defined(CONFIG_NOINSTR_VALIDATION) && \
-	(defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO))
+	(defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO))
 	ANNOTATE_RETPOLINE_SAFE
 	nop
 #endif
@@ -241,7 +232,7 @@
  * instruction irrespective of kCFI.
  */
 .macro JMP_NOSPEC reg:req
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	__CS_PREFIX \reg
 	jmp	__x86_indirect_thunk_\reg
 #else
@@ -251,7 +242,7 @@
 .endm
 
 .macro CALL_NOSPEC reg:req
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	__CS_PREFIX \reg
 	call	__x86_indirect_thunk_\reg
 #else
@@ -271,7 +262,7 @@
 .Lskip_rsb_\@:
 .endm
 
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 #define CALL_UNTRAIN_RET	"call entry_untrain_ret"
 #else
 #define CALL_UNTRAIN_RET	""
@@ -289,7 +280,7 @@
  * where we have a stack but before any RET instruction.
  */
 .macro __UNTRAIN_RET ibpb_feature, call_depth_insns
-#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
+#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY)
 	VALIDATE_UNRET_END
 	ALTERNATIVE_3 "",						\
 		      CALL_UNTRAIN_RET, X86_FEATURE_UNRET,		\
@@ -309,12 +300,23 @@
 
 
 .macro CALL_DEPTH_ACCOUNT
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 	ALTERNATIVE "",							\
-		    __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+		    __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
 #endif
 .endm
 
+/*
+ * Macro to execute VERW instruction that mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers.
+ */
+.macro CLEAR_CPU_BUFFERS
+	ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
+.endm
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\
@@ -328,19 +330,19 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
 extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 extern void __x86_return_thunk(void);
 #else
 static inline void __x86_return_thunk(void) {}
 #endif
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 extern void retbleed_return_thunk(void);
 #else
 static inline void retbleed_return_thunk(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
 extern void srso_return_thunk(void);
 extern void srso_alias_return_thunk(void);
 #else
@@ -357,7 +359,9 @@ extern void entry_ibpb(void);
 
 extern void (*x86_return_thunk)(void);
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+extern void __warn_thunk(void);
+
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 extern void call_depth_return_thunk(void);
 
 #define CALL_DEPTH_ACCOUNT					\
@@ -371,14 +375,14 @@ DECLARE_PER_CPU(u64, __x86_ret_count);
 DECLARE_PER_CPU(u64, __x86_stuffs_count);
 DECLARE_PER_CPU(u64, __x86_ctxsw_count);
 #endif
-#else /* !CONFIG_CALL_DEPTH_TRACKING */
+#else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
 static inline void call_depth_return_thunk(void) {}
 #define CALL_DEPTH_ACCOUNT ""
 
-#endif /* CONFIG_CALL_DEPTH_TRACKING */
+#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 
 #define GEN(reg) \
 	extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
@@ -399,7 +403,7 @@ static inline void call_depth_return_thunk(void) {}
 
 /*
  * Inline asm uses the %V modifier which is only in newer GCC
- * which is ensured when CONFIG_RETPOLINE is defined.
+ * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
 # define CALL_NOSPEC						\
 	ALTERNATIVE_2(						\
@@ -529,13 +533,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
 DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 
+extern u16 mds_verw_sel;
+
 #include <asm/segment.h>
 
 /**
@@ -562,17 +567,6 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
- *
- * Clear CPU buffers if the corresponding static key is enabled
- */
-static __always_inline void mds_user_clear_cpu_buffers(void)
-{
-	if (static_branch_likely(&mds_user_clear))
-		mds_clear_cpu_buffers();
-}
-
-/**
  * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index d18e5c332cb9..1b93ff80b43b 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -66,10 +66,14 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
  * virt_addr_valid(kaddr) returns true.
  */
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)
 extern bool __virt_addr_valid(unsigned long kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((unsigned long) (kaddr))
 
+static __always_inline void *pfn_to_kaddr(unsigned long pfn)
+{
+	return __va(pfn << PAGE_SHIFT);
+}
+
 static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits)
 {
 	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 86bd4311daf8..9da9c8a2f1df 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -7,7 +7,7 @@
 #include <linux/mem_encrypt.h>
 
 /* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT		12
+#define PAGE_SHIFT		CONFIG_PAGE_SHIFT
 #define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index b40c462b4af3..b3ab80a03365 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -10,7 +10,6 @@
 #include <linux/numa.h>
 #include <asm/io.h>
 #include <asm/memtype.h>
-#include <asm/x86_init.h>
 
 struct pci_sysdata {
 	int		domain;		/* PCI domain */
@@ -124,16 +123,4 @@ cpumask_of_pcibus(const struct pci_bus *bus)
 }
 #endif
 
-struct pci_setup_rom {
-	struct setup_data data;
-	uint16_t vendor;
-	uint16_t devid;
-	uint64_t pcilen;
-	unsigned long segment;
-	unsigned long bus;
-	unsigned long device;
-	unsigned long function;
-	uint8_t romdata[];
-};
-
 #endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 5e01883eb51e..44958ebaf626 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -4,17 +4,21 @@
 
 #ifdef CONFIG_X86_64
 #define __percpu_seg		gs
+#define __percpu_rel		(%rip)
 #else
 #define __percpu_seg		fs
+#define __percpu_rel
 #endif
 
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_SMP
-#define PER_CPU_VAR(var)	%__percpu_seg:var
-#else /* ! SMP */
-#define PER_CPU_VAR(var)	var
-#endif	/* SMP */
+#define __percpu		%__percpu_seg:
+#else
+#define __percpu
+#endif
+
+#define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
 #ifdef CONFIG_X86_64_SMP
 #define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
@@ -24,30 +28,84 @@
 
 #else /* ...!ASSEMBLY */
 
+#include <linux/build_bug.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_CC_HAS_NAMED_AS
+
+#ifdef __CHECKER__
+#define __seg_gs		__attribute__((address_space(__seg_gs)))
+#define __seg_fs		__attribute__((address_space(__seg_fs)))
+#endif
+
+#ifdef CONFIG_X86_64
+#define __percpu_seg_override	__seg_gs
+#else
+#define __percpu_seg_override	__seg_fs
+#endif
+
+#define __percpu_prefix		""
+
+#else /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __percpu_seg_override
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
+
+#endif /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset		this_cpu_read(this_cpu_off)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+/*
+ * Efficient implementation for cases in which the compiler supports
+ * named address spaces.  Allows the compiler to perform additional
+ * optimizations that can save more instructions.
+ */
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	tcp_ptr__ = __raw_cpu_read(, this_cpu_off);		\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
+})
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
  */
-#define arch_raw_cpu_ptr(ptr)				\
-({							\
-	unsigned long tcp_ptr__;			\
-	asm ("add " __percpu_arg(1) ", %0"		\
-	     : "=r" (tcp_ptr__)				\
-	     : "m" (this_cpu_off), "0" (ptr));		\
-	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	asm ("mov " __percpu_arg(1) ", %0"			\
+	     : "=r" (tcp_ptr__)					\
+	     : "m" (__my_cpu_var(this_cpu_off)));		\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
 })
-#else
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
+#define PER_CPU_VAR(var)	%__percpu_seg:(var)__percpu_rel
+
+#else /* CONFIG_SMP */
+#define __percpu_seg_override
 #define __percpu_prefix		""
-#endif
+#define __force_percpu_prefix	""
+
+#define PER_CPU_VAR(var)	(var)__percpu_rel
 
+#endif /* CONFIG_SMP */
+
+#define __my_cpu_type(var)	typeof(var) __percpu_seg_override
+#define __my_cpu_ptr(ptr)	(__my_cpu_type(*ptr) *)(uintptr_t)(ptr)
+#define __my_cpu_var(var)	(*__my_cpu_ptr(&var))
 #define __percpu_arg(x)		__percpu_prefix "%" #x
+#define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
 /*
  * Initialized pointers to per-cpu variables needed for the boot
@@ -107,14 +165,14 @@ do {									\
 		(void)pto_tmp__;					\
 	}								\
 	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
-	    : [var] "+m" (_var)						\
+	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
 	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
-	    : [var] "+m" (_var));					\
+	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
 /*
@@ -144,16 +202,16 @@ do {									\
 	__pcpu_type_##size pfo_val__;					\
 	asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]")	\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "m" (_var));					\
+	    : [var] "m" (__my_cpu_var(_var)));				\
 	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
 #define percpu_stable_op(size, op, _var)				\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
-	asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]")	\
+	asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]")	\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "p" (&(_var)));					\
+	    : [var] "i" (&(_var)));					\
 	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
@@ -166,7 +224,7 @@ do {									\
 	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
 				     __percpu_arg([var]))		\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
 	(typeof(_var))(unsigned long) (paro_tmp__ + _val);		\
 })
@@ -187,7 +245,7 @@ do {									\
 				    __percpu_arg([var]))		\
 		  "\n\tjnz 1b"						\
 		  : [oval] "=&a" (pxo_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pxo_new__)		\
 		  : "memory");						\
 	(typeof(_var))(unsigned long) pxo_old__;			\
@@ -204,7 +262,7 @@ do {									\
 	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
 				    __percpu_arg([var]))		\
 		  : [oval] "+a" (pco_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
 		  : "memory");						\
 	(typeof(_var))(unsigned long) pco_old__;			\
@@ -221,7 +279,7 @@ do {									\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
 		  : "memory");						\
 	if (unlikely(!success))						\
@@ -244,7 +302,7 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (_var),					\
+		  : [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -276,7 +334,7 @@ do {									\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
-		    [var] "+m" (_var),					\
+		    [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -313,7 +371,7 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (_var),					\
+		  : [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -345,7 +403,7 @@ do {									\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
-		    [var] "+m" (_var),					\
+		    [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -366,9 +424,9 @@ do {									\
  * accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across cpus.  The current users include
- * get_current() and get_thread_info() both of which are actually
- * per-thread variables implemented as per-cpu variables and thus
- * stable for the duration of the respective task.
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
  */
 #define this_cpu_read_stable_1(pcp)	percpu_stable_op(1, "mov", pcp)
 #define this_cpu_read_stable_2(pcp)	percpu_stable_op(2, "mov", pcp)
@@ -376,13 +434,72 @@ do {									\
 #define this_cpu_read_stable_8(pcp)	percpu_stable_op(8, "mov", pcp)
 #define this_cpu_read_stable(pcp)	__pcpu_size_call_return(this_cpu_read_stable_, pcp)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(qual, pcp)					\
+({									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp));		\
+})
+
+#define __raw_cpu_write(qual, pcp, val)					\
+do {									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val);	\
+} while (0)
+
+#define raw_cpu_read_1(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_2(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_4(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_1(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_2(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_4(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_1(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_2(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_4(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_1(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_2(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_4(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_8(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_8(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_8(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#endif
+
+#define this_cpu_read_const(pcp)	__raw_cpu_read(, pcp)
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_read_1(pcp)		percpu_from_op(1, , "mov", pcp)
 #define raw_cpu_read_2(pcp)		percpu_from_op(2, , "mov", pcp)
 #define raw_cpu_read_4(pcp)		percpu_from_op(4, , "mov", pcp)
-
 #define raw_cpu_write_1(pcp, val)	percpu_to_op(1, , "mov", (pcp), val)
 #define raw_cpu_write_2(pcp, val)	percpu_to_op(2, , "mov", (pcp), val)
 #define raw_cpu_write_4(pcp, val)	percpu_to_op(4, , "mov", (pcp), val)
+
+#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
+#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
+#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		percpu_from_op(8, , "mov", pcp)
+#define raw_cpu_write_8(pcp, val)	percpu_to_op(8, , "mov", (pcp), val)
+
+#define this_cpu_read_8(pcp)		percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val)	percpu_to_op(8, volatile, "mov", (pcp), val)
+#endif
+
+/*
+ * The generic per-cpu infrastrucutre is not suitable for
+ * reading const-qualified variables.
+ */
+#define this_cpu_read_const(pcp)	({ BUILD_BUG(); (typeof(pcp))0; })
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_add_1(pcp, val)		percpu_add_op(1, , (pcp), val)
 #define raw_cpu_add_2(pcp, val)		percpu_add_op(2, , (pcp), val)
 #define raw_cpu_add_4(pcp, val)		percpu_add_op(4, , (pcp), val)
@@ -408,12 +525,6 @@ do {									\
 #define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
-#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
 #define this_cpu_add_1(pcp, val)	percpu_add_op(1, volatile, (pcp), val)
 #define this_cpu_add_2(pcp, val)	percpu_add_op(2, volatile, (pcp), val)
 #define this_cpu_add_4(pcp, val)	percpu_add_op(4, volatile, (pcp), val)
@@ -452,8 +563,6 @@ do {									\
  * 32 bit must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)			percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val)		percpu_to_op(8, , "mov", (pcp), val)
 #define raw_cpu_add_8(pcp, val)			percpu_add_op(8, , (pcp), val)
 #define raw_cpu_and_8(pcp, val)			percpu_to_op(8, , "and", (pcp), val)
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
@@ -462,8 +571,6 @@ do {									\
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
 #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
-#define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
 #define this_cpu_add_8(pcp, val)		percpu_add_op(8, volatile, (pcp), val)
 #define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
 #define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)
@@ -494,7 +601,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 	asm volatile("btl "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
-			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
+			: "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
 
 	return oldbit;
 }
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 94de1a05aeba..d65e338b6a5f 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -181,7 +181,7 @@ static inline u64 p4_clear_ht_bit(u64 config)
 static inline int p4_ht_active(void)
 {
 #ifdef CONFIG_SMP
-	return smp_num_siblings > 1;
+	return __max_threads_per_core > 1;
 #endif
 	return 0;
 }
@@ -189,7 +189,7 @@ static inline int p4_ht_active(void)
 static inline int p4_ht_thread(int cpu)
 {
 #ifdef CONFIG_SMP
-	if (smp_num_siblings == 2)
+	if (__max_threads_per_core == 2)
 		return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index c7ec5bb88334..dcd836b59beb 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
  */
 extern gfp_t __userpte_alloc_gfp;
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
  * both 8k in size and 8k-aligned.  That lets us just flip bit 12
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 9e7c0b719c3c..dabafba957ea 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -52,7 +52,7 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
 #endif
 	pxx_xchg64(pud, pudp, native_pud_val(pud));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 9d077bca6a10..df0f7d4a96f3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -909,7 +909,7 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 pmd_t *populate_extra_pmd(unsigned long vaddr);
 pte_t *populate_extra_pte(unsigned long vaddr);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
 
 /*
@@ -923,12 +923,12 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 		return pgd;
 	return __pti_set_user_pgtbl(pgdp, pgd);
 }
-#else   /* CONFIG_PAGE_TABLE_ISOLATION */
+#else   /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	return pgd;
 }
-#endif  /* CONFIG_PAGE_TABLE_ISOLATION */
+#endif  /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
 #endif	/* __ASSEMBLY__ */
 
@@ -1131,7 +1131,7 @@ static inline int p4d_bad(p4d_t p4d)
 {
 	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
 
-	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+	if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
 		ignore_flags |= _PAGE_NX;
 
 	return (p4d_flags(p4d) & ~ignore_flags) != 0;
@@ -1177,7 +1177,7 @@ static inline int pgd_bad(pgd_t pgd)
 	if (!pgtable_l5_enabled())
 		return 0;
 
-	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+	if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
 		ignore_flags |= _PAGE_NX;
 
 	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
@@ -1422,9 +1422,9 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 #define pgd_leaf	pgd_large
 static inline int pgd_large(pgd_t pgd) { return 0; }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages
  * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
  * the user one is in the last 4k.  To switch between them, you
  * just need to flip the 12th bit in their addresses.
@@ -1469,7 +1469,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
 {
 	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
 }
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
@@ -1484,7 +1484,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
 	memcpy(dst, src, count * sizeof(pgd_t));
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
 	/* Clone the user space pgd as well */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 24af25b1551a..7e9db77231ac 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -143,7 +143,8 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
 
-	if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+	if (pgtable_l5_enabled() ||
+	    !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) {
 		WRITE_ONCE(*p4dp, p4d);
 		return;
 	}
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 38b54b992f32..9053dfe9fa03 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -21,9 +21,9 @@ typedef unsigned long	pgprotval_t;
 typedef struct { pteval_t pte; } pte_t;
 typedef struct { pmdval_t pmd; } pmd_t;
 
-#ifdef CONFIG_X86_5LEVEL
 extern unsigned int __pgtable_l5_enabled;
 
+#ifdef CONFIG_X86_5LEVEL
 #ifdef USE_EARLY_PGTABLE_L5
 /*
  * cpu_feature_enabled() is not available in early boot code.
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index af77235fded6..919909d8cb77 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -91,7 +91,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+	return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
 			       __percpu_arg([var]));
 }
 
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index d8cccadc83a6..e5f204b9b33d 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -51,7 +51,7 @@
 #define CR3_NOFLUSH	0
 #endif
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 # define X86_CR3_PTI_PCID_USER_BIT	11
 #endif
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 26620d7642a9..811548f131f4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -20,7 +20,6 @@ struct vm86;
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
-#include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
 #include <asm/special_insns.h>
@@ -100,6 +99,9 @@ struct cpuinfo_topology {
 	u32			logical_pkg_id;
 	u32			logical_die_id;
 
+	// AMD Node ID and Nodes per Package info
+	u32			amd_node_id;
+
 	// Cache level topology IDs
 	u32			llc_id;
 	u32			l2c_id;
@@ -119,8 +121,6 @@ struct cpuinfo_x86 {
 #endif
 	__u8			x86_virt_bits;
 	__u8			x86_phys_bits;
-	/* CPUID returned core id bits: */
-	__u8			x86_coreid_bits;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
@@ -148,8 +148,6 @@ struct cpuinfo_x86 {
 	unsigned long		loops_per_jiffy;
 	/* protected processor identification number */
 	u64			ppin;
-	/* cpuid returned max cores value: */
-	u16			x86_max_cores;
 	u16			x86_clflush_size;
 	/* number of cores as seen by the OS: */
 	u16			booted_cores;
@@ -186,13 +184,8 @@ extern struct cpuinfo_x86	new_cpu_data;
 extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
 extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
 
-#ifdef CONFIG_SMP
 DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)		per_cpu(cpu_info, cpu)
-#else
-#define cpu_info		boot_cpu_data
-#define cpu_data(cpu)		boot_cpu_data
-#endif
 
 extern const struct seq_operations cpuinfo_op;
 
@@ -533,6 +526,9 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  and around vm86 mode and sp0 on x86_64 is special because of the
 	 *  entry trampoline.
 	 */
+	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+		return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+
 	return this_cpu_read_stable(pcpu_hot.top_of_stack);
 }
 
@@ -555,7 +551,7 @@ static inline void load_sp0(unsigned long sp0)
 
 unsigned long __get_wchan(struct task_struct *p);
 
-extern void select_idle_routine(const struct cpuinfo_x86 *c);
+extern void select_idle_routine(void);
 extern void amd_e400_c1e_apic_setup(void);
 
 extern unsigned long		boot_option_idle_override;
@@ -576,28 +572,6 @@ extern void cpu_init(void);
 extern void cpu_init_exception_handling(void);
 extern void cr4_init(void);
 
-static inline unsigned long get_debugctlmsr(void)
-{
-	unsigned long debugctlmsr = 0;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return 0;
-#endif
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
-
-	return debugctlmsr;
-}
-
-static inline void update_debugctlmsr(unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
-}
-
 extern void set_task_blockstep(struct task_struct *task, bool on);
 
 /* Boot loader type from the setup header: */
@@ -664,8 +638,10 @@ static __always_inline void prefetchw(const void *x)
 #else
 extern unsigned long __end_init_task[];
 
-#define INIT_THREAD {							    \
-	.sp	= (unsigned long)&__end_init_task - sizeof(struct pt_regs), \
+#define INIT_THREAD {							\
+	.sp	= (unsigned long)&__end_init_task -			\
+		  TOP_OF_KERNEL_STACK_PADDING -				\
+		  sizeof(struct pt_regs),				\
 }
 
 extern unsigned long KSTK_ESP(struct task_struct *task);
@@ -704,12 +680,10 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
 }
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern u32 amd_get_nodes_per_socket(void);
 extern u32 amd_get_highest_perf(void);
 extern void amd_clear_divider(void);
 extern void amd_check_microcode(void);
 #else
-static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
 static inline u32 amd_get_highest_perf(void)		{ return 0; }
 static inline void amd_clear_divider(void)		{ }
 static inline void amd_check_microcode(void)		{ }
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 65dee2420624..043758a2e627 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -23,11 +23,11 @@ extern int of_ioapic;
 extern u64 initial_dtb;
 extern void add_dtb(u64 data);
 void x86_of_pci_init(void);
-void x86_dtb_init(void);
+void x86_dtb_parse_smp_config(void);
 #else
 static inline void add_dtb(u64 data) { }
 static inline void x86_of_pci_init(void) { }
-static inline void x86_dtb_init(void) { }
+static inline void x86_dtb_parse_smp_config(void) { }
 #define of_ioapic 0
 #endif
 
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 07375b476c4f..ab167c96b9ab 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -3,7 +3,7 @@
 #define _ASM_X86_PTI_H
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
 extern void pti_check_boottime_disable(void);
 extern void pti_finalize(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index f4db78b09c8f..5a83fbd9bc0b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -56,18 +56,64 @@ struct pt_regs {
 
 #else /* __i386__ */
 
+struct fred_cs {
+		/* CS selector */
+	u64	cs	: 16,
+		/* Stack level at event time */
+		sl	:  2,
+		/* IBT in WAIT_FOR_ENDBRANCH state */
+		wfe	:  1,
+			: 45;
+};
+
+struct fred_ss {
+		/* SS selector */
+	u64	ss	: 16,
+		/* STI state */
+		sti	:  1,
+		/* Set if syscall, sysenter or INT n */
+		swevent	:  1,
+		/* Event is NMI type */
+		nmi	:  1,
+			: 13,
+		/* Event vector */
+		vector	:  8,
+			:  8,
+		/* Event type */
+		type	:  4,
+			:  4,
+		/* Event was incident to enclave execution */
+		enclave	:  1,
+		/* CPU was in long mode */
+		lm	:  1,
+		/*
+		 * Nested exception during FRED delivery, not set
+		 * for #DF.
+		 */
+		nested	:  1,
+			:  1,
+		/*
+		 * The length of the instruction causing the event.
+		 * Only set for INTO, INT1, INT3, INT n, SYSCALL
+		 * and SYSENTER.  0 otherwise.
+		 */
+		insnlen	:  4;
+};
+
 struct pt_regs {
-/*
- * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
- * unless syscall needs a complete, fully filled "struct pt_regs".
- */
+	/*
+	 * C ABI says these regs are callee-preserved. They aren't saved on
+	 * kernel entry unless syscall needs a complete, fully filled
+	 * "struct pt_regs".
+	 */
 	unsigned long r15;
 	unsigned long r14;
 	unsigned long r13;
 	unsigned long r12;
 	unsigned long bp;
 	unsigned long bx;
-/* These regs are callee-clobbered. Always saved on kernel entry. */
+
+	/* These regs are callee-clobbered. Always saved on kernel entry. */
 	unsigned long r11;
 	unsigned long r10;
 	unsigned long r9;
@@ -77,18 +123,50 @@ struct pt_regs {
 	unsigned long dx;
 	unsigned long si;
 	unsigned long di;
-/*
- * On syscall entry, this is syscall#. On CPU exception, this is error code.
- * On hw interrupt, it's IRQ number:
- */
+
+	/*
+	 * orig_ax is used on entry for:
+	 * - the syscall number (syscall, sysenter, int80)
+	 * - error_code stored by the CPU on traps and exceptions
+	 * - the interrupt number for device interrupts
+	 *
+	 * A FRED stack frame starts here:
+	 *   1) It _always_ includes an error code;
+	 *
+	 *   2) The return frame for ERET[US] starts here, but
+	 *      the content of orig_ax is ignored.
+	 */
 	unsigned long orig_ax;
-/* Return frame for iretq */
+
+	/* The IRETQ return frame starts here */
 	unsigned long ip;
-	unsigned long cs;
+
+	union {
+		/* CS selector */
+		u16		cs;
+		/* The extended 64-bit data slot containing CS */
+		u64		csx;
+		/* The FRED CS extension */
+		struct fred_cs	fred_cs;
+	};
+
 	unsigned long flags;
 	unsigned long sp;
-	unsigned long ss;
-/* top of stack page */
+
+	union {
+		/* SS selector */
+		u16		ss;
+		/* The extended 64-bit data slot containing SS */
+		u64		ssx;
+		/* The FRED SS extension */
+		struct fred_ss	fred_ss;
+	};
+
+	/*
+	 * Top of stack on IDT systems, while FRED systems have extra fields
+	 * defined above for storing exception related information, e.g. CR2 or
+	 * DR6.
+	 */
 };
 
 #endif /* !__i386__ */
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 255a78d9d906..12dbd2588ca7 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -7,6 +7,13 @@
 #include <linux/sched.h>
 #include <linux/jump_label.h>
 
+/*
+ * This value can never be a valid CLOSID, and is used when mapping a
+ * (closid, rmid) pair to an index and back. On x86 only the RMID is
+ * needed. The index is a software defined value.
+ */
+#define X86_RESCTRL_EMPTY_CLOSID         ((u32)~0)
+
 /**
  * struct resctrl_pqr_state - State cache for the PQR MSR
  * @cur_rmid:		The cached Resource Monitoring ID
@@ -31,10 +38,47 @@ struct resctrl_pqr_state {
 
 DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
+extern bool rdt_alloc_capable;
+extern bool rdt_mon_capable;
+
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
+static inline bool resctrl_arch_alloc_capable(void)
+{
+	return rdt_alloc_capable;
+}
+
+static inline void resctrl_arch_enable_alloc(void)
+{
+	static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_alloc(void)
+{
+	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
+static inline bool resctrl_arch_mon_capable(void)
+{
+	return rdt_mon_capable;
+}
+
+static inline void resctrl_arch_enable_mon(void)
+{
+	static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_mon(void)
+{
+	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
+	static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
@@ -88,12 +132,58 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
+						u32 closid, u32 rmid)
+{
+	WRITE_ONCE(tsk->closid, closid);
+	WRITE_ONCE(tsk->rmid, rmid);
+}
+
+static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid)
+{
+	return READ_ONCE(tsk->closid) == closid;
+}
+
+static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
+					   u32 rmid)
+{
+	return READ_ONCE(tsk->rmid) == rmid;
+}
+
 static inline void resctrl_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
 }
 
+static inline u32 resctrl_arch_system_num_rmid_idx(void)
+{
+	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+	return boot_cpu_data.x86_cache_max_rmid + 1;
+}
+
+static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
+{
+	*rmid = idx;
+	*closid = X86_RESCTRL_EMPTY_CLOSID;
+}
+
+static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
+{
+	return rmid;
+}
+
+/* x86 can always read an rmid, nothing needs allocating */
+struct rdt_resource;
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+{
+	might_sleep();
+	return NULL;
+};
+
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
+					     void *ctx) { };
+
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306..363266cbcada 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c = false;							\
-	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
+	asm goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : [var] "m" (_var), ## __VA_ARGS__		\
 			: clobbers : cc_label);				\
 	if (0) {							\
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index a5e89641bd2d..9aee31862b4a 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages);
 int set_memory_wc(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
+int set_memory_p(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 5c83729c8e71..e61e68d71cba 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -48,7 +48,7 @@ extern unsigned long saved_video_mode;
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
 extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
-extern void startup_64_setup_env(unsigned long physbase);
+extern void startup_64_setup_gdt_idt(void);
 extern void early_setup_idt(void);
 extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
 
diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h
new file mode 100644
index 000000000000..77c51111a893
--- /dev/null
+++ b/arch/x86/include/asm/setup_data.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SETUP_DATA_H
+#define _ASM_X86_SETUP_DATA_H
+
+#include <uapi/asm/setup_data.h>
+
+#ifndef __ASSEMBLY__
+
+struct pci_setup_rom {
+	struct setup_data data;
+	uint16_t vendor;
+	uint16_t devid;
+	uint64_t pcilen;
+	unsigned long segment;
+	unsigned long bus;
+	unsigned long device;
+	unsigned long function;
+	uint8_t romdata[];
+};
+
+/* kexec external ABI */
+struct efi_setup_data {
+	u64 fw_vendor;
+	u64 __unused;
+	u64 tables;
+	u64 smbios;
+	u64 reserved[8];
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 5b4a1ce3d368..9477b4053bce 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -13,7 +13,6 @@
 
 #include <asm/insn.h>
 #include <asm/sev-common.h>
-#include <asm/bootparam.h>
 #include <asm/coco.h>
 
 #define GHCB_PROTOCOL_MIN	1ULL
@@ -22,6 +21,8 @@
 
 #define	VMGEXIT()			{ asm volatile("rep; vmmcall\n\r"); }
 
+struct boot_params;
+
 enum es_result {
 	ES_OK,			/* All good */
 	ES_UNSUPPORTED,		/* Requested operation not supported */
@@ -87,9 +88,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 /* Software defined (when rFlags.CF = 1) */
 #define PVALIDATE_FAIL_NOUPDATE		255
 
+/* RMUPDATE detected 4K page and 2MB page overlap. */
+#define RMPUPDATE_FAIL_OVERLAP		4
+
 /* RMP page size */
 #define RMP_PG_SIZE_4K			0
 #define RMP_PG_SIZE_2M			1
+#define RMP_TO_PG_LEVEL(level)		(((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M)
+#define PG_LEVEL_TO_RMP(level)		(((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M)
+
+struct rmp_state {
+	u64 gpa;
+	u8 assigned;
+	u8 pagesize;
+	u8 immutable;
+	u8 rsvd;
+	u32 asid;
+} __packed;
 
 #define RMPADJUST_VMSA_PAGE_BIT		BIT(16)
 
@@ -199,20 +214,22 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
 struct snp_guest_request_ioctl;
 
 void setup_ghcb(void);
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
-					 unsigned long npages);
-void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
-					unsigned long npages);
+void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+				  unsigned long npages);
+void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+				 unsigned long npages);
 void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
 void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
 void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
 void snp_set_wakeup_secondary_cpu(void);
 bool snp_init(struct boot_params *bp);
-void __init __noreturn snp_abort(void);
+void __noreturn snp_abort(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
 u64 snp_get_unsupported_features(u64 status);
 u64 sev_get_status(void);
+void kdump_sev_callback(void);
+void sev_show_status(void);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }
@@ -241,6 +258,30 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
 static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
 static inline u64 sev_get_status(void) { return 0; }
+static inline void kdump_sev_callback(void) { }
+static inline void sev_show_status(void) { }
+#endif
+
+#ifdef CONFIG_KVM_AMD_SEV
+bool snp_probe_rmptable_info(void);
+int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
+void snp_dump_hva_rmpentry(unsigned long address);
+int psmash(u64 pfn);
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable);
+int rmp_make_shared(u64 pfn, enum pg_level level);
+void snp_leak_pages(u64 pfn, unsigned int npages);
+#else
+static inline bool snp_probe_rmptable_info(void) { return false; }
+static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
+static inline void snp_dump_hva_rmpentry(unsigned long address) {}
+static inline int psmash(u64 pfn) { return -ENODEV; }
+static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid,
+				   bool immutable)
+{
+	return -ENODEV;
+}
+static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
+static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4fab2ed454f3..a35936b512fe 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -8,9 +8,6 @@
 #include <asm/current.h>
 #include <asm/thread_info.h>
 
-extern int smp_num_siblings;
-extern unsigned int num_processors;
-
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
@@ -59,11 +56,6 @@ static inline void stop_other_cpus(void)
 	smp_ops.stop_other_cpus(1);
 }
 
-static inline void smp_prepare_boot_cpu(void)
-{
-	smp_ops.smp_prepare_boot_cpu();
-}
-
 static inline void smp_prepare_cpus(unsigned int max_cpus)
 {
 	smp_ops.smp_prepare_cpus(max_cpus);
@@ -110,7 +102,6 @@ void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void smp_prepare_cpus_common(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
-void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_kick_ap(unsigned int cpu, struct task_struct *tidle);
@@ -174,8 +165,6 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 }
 #endif /* CONFIG_SMP */
 
-extern unsigned disabled_cpus;
-
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
 extern void nmi_selftest(void);
 #else
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index c648502e4535..658b690b2ccb 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -96,4 +96,6 @@ static inline void speculative_store_bypass_ht_init(void) { }
 extern void speculation_ctrl_update(unsigned long tif);
 extern void speculation_ctrl_update_current(void);
 
+extern bool itlb_multihit_kvm_mitigation;
+
 #endif
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c7..2e9fc5c400cd 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -2,11 +2,11 @@
 #ifndef _ASM_X86_SPECIAL_INSNS_H
 #define _ASM_X86_SPECIAL_INSNS_H
 
-
 #ifdef __KERNEL__
-
 #include <asm/nops.h>
 #include <asm/processor-flags.h>
+
+#include <linux/errno.h>
 #include <linux/irqflags.h>
 #include <linux/jump_label.h>
 
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 static inline int write_user_shstk_64(u64 __user *addr, u64 val)
 {
-	asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+	asm goto("1: wrussq %[val], (%[addr])\n"
 			  _ASM_EXTABLE(1b, %l[fail])
 			  :: [addr] "r" (addr), [val] "r" (val)
 			  :: fail);
@@ -224,10 +224,10 @@ static inline void serialize(void)
 }
 
 /* The dst parameter must be 64-bytes aligned */
-static inline void movdir64b(void __iomem *dst, const void *src)
+static inline void movdir64b(void *dst, const void *src)
 {
 	const struct { char _[64]; } *__src = src;
-	struct { char _[64]; } __iomem *__dst = dst;
+	struct { char _[64]; } *__dst = dst;
 
 	/*
 	 * MOVDIR64B %(rdx), rax.
@@ -245,6 +245,11 @@ static inline void movdir64b(void __iomem *dst, const void *src)
 		     :  "m" (*__src), "a" (__dst), "d" (__src));
 }
 
+static inline void movdir64b_io(void __iomem *dst, const void *src)
+{
+	movdir64b((void __force *)dst, src);
+}
+
 /**
  * enqcmds - Enqueue a command in supervisor (CPL0) mode
  * @dst: destination, in MMIO space (must be 512-bit aligned)
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 343b722ccaf2..125c407e2abe 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -46,7 +46,7 @@
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk")
 #else
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index f42dbf17f52b..c3bd0c0758c9 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -70,9 +70,13 @@ static inline void update_task_stack(struct task_struct *task)
 #ifdef CONFIG_X86_32
 	this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
-	/* Xen PV enters the kernel on the thread stack. */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
+		/* WRMSRNS is a baseline feature for FRED. */
+		wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE);
+	} else if (cpu_feature_enabled(X86_FEATURE_XENPV)) {
+		/* Xen PV enters the kernel on the thread stack. */
 		load_sp0(task_top_of_stack(task));
+	}
 #endif
 }
 
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 0b70653a98c1..345aafbc1964 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -15,6 +15,8 @@
 
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
+extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
  * Allows the kernel to edit read-only pages.
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index d63b02940747..12da7dfd5ef1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -31,7 +31,9 @@
  * In vm86 mode, the hardware frame is much longer still, so add 16
  * bytes to make room for the real-mode segments.
  *
- * x86_64 has a fixed-length stack frame.
+ * x86-64 has a fixed-length stack frame, but it depends on whether
+ * or not FRED is enabled. Future versions of FRED might make this
+ * dynamic, but for now it is always 2 words longer.
  */
 #ifdef CONFIG_X86_32
 # ifdef CONFIG_VM86
@@ -39,8 +41,12 @@
 # else
 #  define TOP_OF_KERNEL_STACK_PADDING 8
 # endif
-#else
-# define TOP_OF_KERNEL_STACK_PADDING 0
+#else /* x86-64 */
+# ifdef CONFIG_X86_FRED
+#  define TOP_OF_KERNEL_STACK_PADDING (2 * 8)
+# else
+#  define TOP_OF_KERNEL_STACK_PADDING 0
+# endif
 #endif
 
 /*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 5f87f6b9b09e..abe3a8f22cbd 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -102,6 +102,35 @@ static inline void setup_node_to_cpumask_map(void) { }
 
 #include <asm-generic/topology.h>
 
+/* Topology information */
+enum x86_topology_domains {
+	TOPO_SMT_DOMAIN,
+	TOPO_CORE_DOMAIN,
+	TOPO_MODULE_DOMAIN,
+	TOPO_TILE_DOMAIN,
+	TOPO_DIE_DOMAIN,
+	TOPO_DIEGRP_DOMAIN,
+	TOPO_PKG_DOMAIN,
+	TOPO_MAX_DOMAIN,
+};
+
+struct x86_topology_system {
+	unsigned int	dom_shifts[TOPO_MAX_DOMAIN];
+	unsigned int	dom_size[TOPO_MAX_DOMAIN];
+};
+
+extern struct x86_topology_system x86_topo_system;
+
+static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom)
+{
+	return x86_topo_system.dom_size[dom];
+}
+
+static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom)
+{
+	return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1];
+}
+
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 extern const struct cpumask *cpu_clustergroup_mask(int cpu);
 
@@ -112,7 +141,42 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu);
 #define topology_core_id(cpu)			(cpu_data(cpu).topo.core_id)
 #define topology_ppin(cpu)			(cpu_data(cpu).ppin)
 
-extern unsigned int __max_die_per_package;
+#define topology_amd_node_id(cpu)		(cpu_data(cpu).topo.amd_node_id)
+
+extern unsigned int __max_dies_per_package;
+extern unsigned int __max_logical_packages;
+extern unsigned int __max_threads_per_core;
+extern unsigned int __num_threads_per_package;
+extern unsigned int __num_cores_per_package;
+
+static inline unsigned int topology_max_packages(void)
+{
+	return __max_logical_packages;
+}
+
+static inline unsigned int topology_max_dies_per_package(void)
+{
+	return __max_dies_per_package;
+}
+
+static inline unsigned int topology_num_cores_per_package(void)
+{
+	return __num_cores_per_package;
+}
+
+static inline unsigned int topology_num_threads_per_package(void)
+{
+	return __num_threads_per_package;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level);
+#else
+static inline int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_SMP
 #define topology_cluster_id(cpu)		(cpu_data(cpu).topo.l2c_id)
@@ -121,12 +185,11 @@ extern unsigned int __max_die_per_package;
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
-extern unsigned int __max_logical_packages;
-#define topology_max_packages()			(__max_logical_packages)
 
-static inline int topology_max_die_per_package(void)
+static inline int topology_phys_to_logical_pkg(unsigned int pkg)
 {
-	return __max_die_per_package;
+	return topology_get_logical_id(pkg << x86_topo_system.dom_shifts[TOPO_PKG_DOMAIN],
+				       TOPO_PKG_DOMAIN);
 }
 
 extern int __max_smt_threads;
@@ -138,9 +201,12 @@ static inline int topology_max_smt_threads(void)
 
 #include <linux/cpu_smt.h>
 
-int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-int topology_update_die_map(unsigned int dieid, unsigned int cpu);
-int topology_phys_to_logical_pkg(unsigned int pkg);
+extern unsigned int __amd_nodes_per_pkg;
+
+static inline unsigned int topology_amd_nodes_per_pkg(void)
+{
+	return __amd_nodes_per_pkg;
+}
 
 extern struct cpumask __cpu_primary_thread_mask;
 #define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask)
@@ -153,16 +219,12 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_primary_thread_mask);
 }
+
 #else /* CONFIG_SMP */
-#define topology_max_packages()			(1)
-static inline int
-topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
-static inline int
-topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
-static inline int topology_max_die_per_package(void) { return 1; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; }
 #endif /* !CONFIG_SMP */
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h
index afa524325e55..a23a7b707b64 100644
--- a/arch/x86/include/asm/trap_pf.h
+++ b/arch/x86/include/asm/trap_pf.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_TRAP_PF_H
 #define _ASM_X86_TRAP_PF_H
 
+#include <linux/bits.h>
+
 /*
  * Page fault error code bits:
  *
@@ -13,16 +15,18 @@
  *   bit 5 ==				1: protection keys block access
  *   bit 6 ==				1: shadow stack access fault
  *   bit 15 ==				1: SGX MMU page-fault
+ *   bit 31 ==				1: fault was due to RMP violation
  */
 enum x86_pf_error_code {
-	X86_PF_PROT	=		1 << 0,
-	X86_PF_WRITE	=		1 << 1,
-	X86_PF_USER	=		1 << 2,
-	X86_PF_RSVD	=		1 << 3,
-	X86_PF_INSTR	=		1 << 4,
-	X86_PF_PK	=		1 << 5,
-	X86_PF_SHSTK	=		1 << 6,
-	X86_PF_SGX	=		1 << 15,
+	X86_PF_PROT	=		BIT(0),
+	X86_PF_WRITE	=		BIT(1),
+	X86_PF_USER	=		BIT(2),
+	X86_PF_RSVD	=		BIT(3),
+	X86_PF_INSTR	=		BIT(4),
+	X86_PF_PK	=		BIT(5),
+	X86_PF_SHSTK	=		BIT(6),
+	X86_PF_SGX	=		BIT(15),
+	X86_PF_RMP	=		BIT(31),
 };
 
 #endif /* _ASM_X86_TRAP_PF_H */
diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h
index f5d2325aa0b7..8d1154cdf787 100644
--- a/arch/x86/include/asm/trapnr.h
+++ b/arch/x86/include/asm/trapnr.h
@@ -2,6 +2,18 @@
 #ifndef _ASM_X86_TRAPNR_H
 #define _ASM_X86_TRAPNR_H
 
+/*
+ * Event type codes used by FRED, Intel VT-x and AMD SVM
+ */
+#define EVENT_TYPE_EXTINT	0	// External interrupt
+#define EVENT_TYPE_RESERVED	1
+#define EVENT_TYPE_NMI		2	// NMI
+#define EVENT_TYPE_HWEXC	3	// Hardware originated traps, exceptions
+#define EVENT_TYPE_SWINT	4	// INT n
+#define EVENT_TYPE_PRIV_SWEXC	5	// INT1
+#define EVENT_TYPE_SWEXC	6	// INTO, INT3
+#define EVENT_TYPE_OTHER	7	// FRED SYSCALL/SYSENTER, VT-x MTF
+
 /* Interrupts/Exceptions */
 
 #define X86_TRAP_DE		 0	/* Divide-by-zero */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 594fce0ca744..405efb3e4996 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,8 +5,9 @@
 #ifndef _ASM_X86_TSC_H
 #define _ASM_X86_TSC_H
 
-#include <asm/processor.h>
 #include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 /*
  * Standard way to access the cycle counter.
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5c367c1290c3..237dc8cdd12b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
 
 #ifdef CONFIG_X86_32
 #define __put_user_goto_u64(x, addr, label)			\
-	asm_volatile_goto("\n"					\
+	asm goto("\n"					\
 		     "1:	movl %%eax,0(%1)\n"		\
 		     "2:	movl %%edx,4(%1)\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)			\
@@ -295,7 +295,7 @@ do {									\
 } while (0)
 
 #define __get_user_asm(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)				\
 		     : [output] ltype(x)				\
@@ -375,7 +375,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -394,7 +394,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
  * aliasing issues.
  */
 #define __put_user_goto(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm goto("\n"							\
 		"1:	mov"itype" %0,%1\n"				\
 		_ASM_EXTABLE_UA(1b, %l2)				\
 		: : ltype(x), "m" (__m(addr))				\
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f2c02e4469cc..04789f45ab2b 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -11,6 +11,7 @@
 #include <asm/alternative.h>
 #include <asm/cpufeatures.h>
 #include <asm/page.h>
+#include <asm/percpu.h>
 
 #ifdef CONFIG_ADDRESS_MASKING
 /*
@@ -18,14 +19,10 @@
  */
 static inline unsigned long __untagged_addr(unsigned long addr)
 {
-	/*
-	 * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation
-	 * in alternative instructions. The relocation gets wrong when gets
-	 * copied to the target place.
-	 */
 	asm (ALTERNATIVE("",
-			 "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM)
-	     : [addr] "+r" (addr) : "m" (tlbstate_untag_mask));
+			 "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM)
+	     : [addr] "+r" (addr)
+	     : [mask] "m" (__my_cpu_var(tlbstate_untag_mask)));
 
 	return addr;
 }
@@ -54,7 +51,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
  * half and a user half.  When cast to a signed type, user pointers
  * are positive and kernel pointers are negative.
  */
-#define valid_user_address(x) ((long)(x) >= 0)
+#define valid_user_address(x) ((__force long)(x) >= 0)
 
 /*
  * User pointers can have tag bits on x86-64.  This scheme tolerates
@@ -87,8 +84,9 @@ static inline bool __access_ok(const void __user *ptr, unsigned long size)
 	if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) {
 		return valid_user_address(ptr);
 	} else {
-		unsigned long sum = size + (unsigned long)ptr;
-		return valid_user_address(sum) && sum >= (unsigned long)ptr;
+		unsigned long sum = size + (__force unsigned long)ptr;
+
+		return valid_user_address(sum) && sum >= (__force unsigned long)ptr;
 	}
 }
 #define __access_ok __access_ok
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0e73616b82f3..4dba17363008 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -17,6 +17,7 @@
 #include <linux/types.h>
 
 #include <uapi/asm/vmx.h>
+#include <asm/trapnr.h>
 #include <asm/vmxfeatures.h>
 
 #define VMCS_CONTROL_BIT(x)	BIT(VMX_FEATURE_##x & 0x1f)
@@ -374,14 +375,14 @@ enum vmcs_field {
 #define VECTORING_INFO_DELIVER_CODE_MASK    	INTR_INFO_DELIVER_CODE_MASK
 #define VECTORING_INFO_VALID_MASK       	INTR_INFO_VALID_MASK
 
-#define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
-#define INTR_TYPE_RESERVED              (1 << 8) /* reserved */
-#define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
-#define INTR_TYPE_HARD_EXCEPTION	(3 << 8) /* processor exception */
-#define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
-#define INTR_TYPE_PRIV_SW_EXCEPTION	(5 << 8) /* ICE breakpoint - undocumented */
-#define INTR_TYPE_SOFT_EXCEPTION	(6 << 8) /* software exception */
-#define INTR_TYPE_OTHER_EVENT           (7 << 8) /* other event */
+#define INTR_TYPE_EXT_INTR		(EVENT_TYPE_EXTINT << 8)	/* external interrupt */
+#define INTR_TYPE_RESERVED		(EVENT_TYPE_RESERVED << 8)	/* reserved */
+#define INTR_TYPE_NMI_INTR		(EVENT_TYPE_NMI << 8)		/* NMI */
+#define INTR_TYPE_HARD_EXCEPTION	(EVENT_TYPE_HWEXC << 8)		/* processor exception */
+#define INTR_TYPE_SOFT_INTR		(EVENT_TYPE_SWINT << 8)		/* software interrupt */
+#define INTR_TYPE_PRIV_SW_EXCEPTION	(EVENT_TYPE_PRIV_SWEXC << 8)	/* ICE breakpoint */
+#define INTR_TYPE_SOFT_EXCEPTION	(EVENT_TYPE_SWEXC << 8)		/* software exception */
+#define INTR_TYPE_OTHER_EVENT		(EVENT_TYPE_OTHER << 8)		/* other event */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */
 #define GUEST_INTR_STATE_STI		0x00000001
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index ab60a71a8dcb..472f0263dbc6 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
 
 #include <linux/seqlock.h>
 #include <uapi/asm/vsyscall.h>
+#include <asm/page_types.h>
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
@@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code,
 }
 #endif
 
+/*
+ * The (legacy) vsyscall page is the long page in the kernel portion
+ * of the address space that has user-accessible permissions.
+ */
+static inline bool is_vsyscall_vaddr(unsigned long vaddr)
+{
+	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
+}
+
 #endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index c878616a18b8..b89b40f250e6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_X86_PLATFORM_H
 #define _ASM_X86_PLATFORM_H
 
-#include <asm/bootparam.h>
-
 struct ghcb;
 struct mpc_bus;
 struct mpc_cpu;
@@ -15,13 +13,15 @@ struct irq_domain;
 /**
  * struct x86_init_mpparse - platform specific mpparse ops
  * @setup_ioapic_ids:		platform specific ioapic id override
- * @find_smp_config:		find the smp configuration
- * @get_smp_config:		get the smp configuration
+ * @find_mptable:		Find MPTABLE early to reserve the memory region
+ * @early_parse_smp_cfg:	Parse the SMP configuration data early before initmem_init()
+ * @parse_smp_cfg:		Parse the SMP configuration data
  */
 struct x86_init_mpparse {
 	void (*setup_ioapic_ids)(void);
-	void (*find_smp_config)(void);
-	void (*get_smp_config)(unsigned int early);
+	void (*find_mptable)(void);
+	void (*early_parse_smp_cfg)(void);
+	void (*parse_smp_cfg)(void);
 };
 
 /**
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 01d19fc22346..9b82eebd7add 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -2,21 +2,7 @@
 #ifndef _ASM_X86_BOOTPARAM_H
 #define _ASM_X86_BOOTPARAM_H
 
-/* setup_data/setup_indirect types */
-#define SETUP_NONE			0
-#define SETUP_E820_EXT			1
-#define SETUP_DTB			2
-#define SETUP_PCI			3
-#define SETUP_EFI			4
-#define SETUP_APPLE_PROPERTIES		5
-#define SETUP_JAILHOUSE			6
-#define SETUP_CC_BLOB			7
-#define SETUP_IMA			8
-#define SETUP_RNG_SEED			9
-#define SETUP_ENUM_MAX			SETUP_RNG_SEED
-
-#define SETUP_INDIRECT			(1<<31)
-#define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
+#include <asm/setup_data.h>
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -38,6 +24,7 @@
 #define XLF_EFI_KEXEC			(1<<4)
 #define XLF_5LEVEL			(1<<5)
 #define XLF_5LEVEL_ENABLED		(1<<6)
+#define XLF_MEM_ENCRYPTION		(1<<7)
 
 #ifndef __ASSEMBLY__
 
@@ -48,22 +35,6 @@
 #include <asm/ist.h>
 #include <video/edid.h>
 
-/* extensible setup data list node */
-struct setup_data {
-	__u64 next;
-	__u32 type;
-	__u32 len;
-	__u8 data[];
-};
-
-/* extensible setup indirect data node */
-struct setup_indirect {
-	__u32 type;
-	__u32 reserved;  /* Reserved, must be set to zero. */
-	__u64 len;
-	__u64 addr;
-};
-
 struct setup_header {
 	__u8	setup_sects;
 	__u16	root_flags;
@@ -137,50 +108,10 @@ struct efi_info {
 #define E820_MAX_ENTRIES_ZEROPAGE 128
 
 /*
- * The E820 memory region entry of the boot protocol ABI:
- */
-struct boot_e820_entry {
-	__u64 addr;
-	__u64 size;
-	__u32 type;
-} __attribute__((packed));
-
-/*
  * Smallest compatible version of jailhouse_setup_data required by this kernel.
  */
 #define JAILHOUSE_SETUP_REQUIRED_VERSION	1
 
-/*
- * The boot loader is passing platform information via this Jailhouse-specific
- * setup data structure.
- */
-struct jailhouse_setup_data {
-	struct {
-		__u16	version;
-		__u16	compatible_version;
-	} __attribute__((packed)) hdr;
-	struct {
-		__u16	pm_timer_address;
-		__u16	num_cpus;
-		__u64	pci_mmconfig_base;
-		__u32	tsc_khz;
-		__u32	apic_khz;
-		__u8	standard_ioapic;
-		__u8	cpu_ids[255];
-	} __attribute__((packed)) v1;
-	struct {
-		__u32	flags;
-	} __attribute__((packed)) v2;
-} __attribute__((packed));
-
-/*
- * IMA buffer setup data information from the previous kernel during kexec
- */
-struct ima_setup_data {
-	__u64 addr;
-	__u64 size;
-} __attribute__((packed));
-
 /* The so-called "zeropage" */
 struct boot_params {
 	struct screen_info screen_info;			/* 0x000 */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index d898432947ff..f1a4adc78272 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -139,6 +139,13 @@
 #define X86_CR4_LAM_SUP_BIT	28 /* LAM for supervisor pointers */
 #define X86_CR4_LAM_SUP		_BITUL(X86_CR4_LAM_SUP_BIT)
 
+#ifdef __x86_64__
+#define X86_CR4_FRED_BIT	32 /* enable FRED kernel entry */
+#define X86_CR4_FRED		_BITUL(X86_CR4_FRED_BIT)
+#else
+#define X86_CR4_FRED		(0)
+#endif
+
 /*
  * x86-64 Task Priority Register, CR8
  */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
new file mode 100644
index 000000000000..b111b0c18544
--- /dev/null
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_X86_SETUP_DATA_H
+#define _UAPI_ASM_X86_SETUP_DATA_H
+
+/* setup_data/setup_indirect types */
+#define SETUP_NONE			0
+#define SETUP_E820_EXT			1
+#define SETUP_DTB			2
+#define SETUP_PCI			3
+#define SETUP_EFI			4
+#define SETUP_APPLE_PROPERTIES		5
+#define SETUP_JAILHOUSE			6
+#define SETUP_CC_BLOB			7
+#define SETUP_IMA			8
+#define SETUP_RNG_SEED			9
+#define SETUP_ENUM_MAX			SETUP_RNG_SEED
+
+#define SETUP_INDIRECT			(1<<31)
+#define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/* extensible setup data list node */
+struct setup_data {
+	__u64 next;
+	__u32 type;
+	__u32 len;
+	__u8 data[];
+};
+
+/* extensible setup indirect data node */
+struct setup_indirect {
+	__u32 type;
+	__u32 reserved;  /* Reserved, must be set to zero. */
+	__u64 len;
+	__u64 addr;
+};
+
+/*
+ * The E820 memory region entry of the boot protocol ABI:
+ */
+struct boot_e820_entry {
+	__u64 addr;
+	__u64 size;
+	__u32 type;
+} __attribute__((packed));
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+	struct {
+		__u16	version;
+		__u16	compatible_version;
+	} __attribute__((packed)) hdr;
+	struct {
+		__u16	pm_timer_address;
+		__u16	num_cpus;
+		__u64	pci_mmconfig_base;
+		__u32	tsc_khz;
+		__u32	apic_khz;
+		__u8	standard_ioapic;
+		__u8	cpu_ids[255];
+	} __attribute__((packed)) v1;
+	struct {
+		__u32	flags;
+	} __attribute__((packed)) v2;
+} __attribute__((packed));
+
+/*
+ * IMA buffer setup data information from the previous kernel during kexec
+ */
+struct ima_setup_data {
+	__u64 addr;
+	__u64 size;
+} __attribute__((packed));
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0000325ab98f..d0c744cb2a0e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -33,6 +33,7 @@ KASAN_SANITIZE_sev.o					:= n
 KCSAN_SANITIZE := n
 KMSAN_SANITIZE_head$(BITS).o				:= n
 KMSAN_SANITIZE_nmi.o					:= n
+KMSAN_SANITIZE_sev.o					:= n
 
 # If instrumentation of the following files is enabled, boot hangs during
 # first second.
@@ -48,6 +49,7 @@ obj-y			+= platform-quirks.o
 obj-y			+= process_$(BITS).o signal.o signal_$(BITS).o
 obj-y			+= traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o dumpstack.o nmi.o
+obj-$(CONFIG_X86_FRED)	+= fred.o
 obj-$(CONFIG_MODIFY_LDT_SYSCALL)	+= ldt.o
 obj-$(CONFIG_X86_KERNEL_IBT)		+= ibt_selftest.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 85a3ce2a3666..4bf82dbd2a6b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -164,35 +164,6 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
 	return 0;
 }
 
-/**
- * acpi_register_lapic - register a local apic and generates a logic cpu number
- * @id: local apic id to register
- * @acpiid: ACPI id to register
- * @enabled: this cpu is enabled or not
- *
- * Returns the logic cpu number which maps to the local apic
- */
-static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
-{
-	int cpu;
-
-	if (id >= MAX_LOCAL_APIC) {
-		pr_info("skipped apicid that is too big\n");
-		return -EINVAL;
-	}
-
-	if (!enabled) {
-		++disabled_cpus;
-		return -EINVAL;
-	}
-
-	cpu = generic_processor_info(id);
-	if (cpu >= 0)
-		early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
-
-	return cpu;
-}
-
 static bool __init acpi_is_processor_usable(u32 lapic_flags)
 {
 	if (lapic_flags & ACPI_MADT_ENABLED)
@@ -254,7 +225,7 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 		return 0;
 	}
 
-	acpi_register_lapic(apic_id, processor->uid, enabled);
+	topology_register_apic(apic_id, processor->uid, enabled);
 #else
 	pr_warn("x2apic entry ignored\n");
 #endif
@@ -289,9 +260,9 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	acpi_register_lapic(processor->id,	/* APIC ID */
-			    processor->processor_id, /* ACPI ID */
-			    processor->lapic_flags & ACPI_MADT_ENABLED);
+	topology_register_apic(processor->id,	/* APIC ID */
+			       processor->processor_id, /* ACPI ID */
+			       processor->lapic_flags & ACPI_MADT_ENABLED);
 
 	has_lapic_cpus = true;
 	return 0;
@@ -309,9 +280,9 @@ acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end)
 
 	acpi_table_print_madt_entry(&header->common);
 
-	acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
-			    processor->processor_id, /* ACPI ID */
-			    processor->lapic_flags & ACPI_MADT_ENABLED);
+	topology_register_apic((processor->id << 8) | processor->eid,/* APIC ID */
+			       processor->processor_id, /* ACPI ID */
+			       processor->lapic_flags & ACPI_MADT_ENABLED);
 
 	return 0;
 }
@@ -844,12 +815,10 @@ static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	return 0;
 }
 
-int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
-		 int *pcpu)
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu)
 {
-	int cpu;
+	int cpu = topology_hotplug_apic(physid, acpi_id);
 
-	cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED);
 	if (cpu < 0) {
 		pr_info("Unable to map lapic to logical cpu number\n");
 		return cpu;
@@ -868,15 +837,11 @@ int acpi_unmap_cpu(int cpu)
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
 #endif
-
-	per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
-	set_cpu_present(cpu, false);
-	num_processors--;
-
-	return (0);
+	topology_hotunplug_apic(cpu);
+	return 0;
 }
 EXPORT_SYMBOL(acpi_unmap_cpu);
-#endif				/* CONFIG_ACPI_HOTPLUG_CPU */
+#endif	/* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 {
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index d5d8a352eafa..94ff83f3d3fe 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -17,7 +17,7 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 SYM_FUNC_START(wakeup_long64)
-	movq	saved_magic, %rax
+	movq	saved_magic(%rip), %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
 	je	2f
@@ -33,14 +33,14 @@ SYM_FUNC_START(wakeup_long64)
 	movw	%ax, %es
 	movw	%ax, %fs
 	movw	%ax, %gs
-	movq	saved_rsp, %rsp
+	movq	saved_rsp(%rip), %rsp
 
-	movq	saved_rbx, %rbx
-	movq	saved_rdi, %rdi
-	movq	saved_rsi, %rsi
-	movq	saved_rbp, %rbp
+	movq	saved_rbx(%rip), %rbx
+	movq	saved_rdi(%rip), %rdi
+	movq	saved_rsi(%rip), %rsi
+	movq	saved_rbp(%rip), %rbp
 
-	movq	saved_rip, %rax
+	movq	saved_rip(%rip), %rax
 	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 SYM_FUNC_END(wakeup_long64)
@@ -72,11 +72,11 @@ SYM_FUNC_START(do_suspend_lowlevel)
 
 	movq	$.Lresume_point, saved_rip(%rip)
 
-	movq	%rsp, saved_rsp
-	movq	%rbp, saved_rbp
-	movq	%rbx, saved_rbx
-	movq	%rdi, saved_rdi
-	movq	%rsi, saved_rsi
+	movq	%rsp, saved_rsp(%rip)
+	movq	%rbp, saved_rbp(%rip)
+	movq	%rbx, saved_rbx(%rip)
+	movq	%rdi, saved_rdi(%rip)
+	movq	%rsi, saved_rsi(%rip)
 
 	addq	$8, %rsp
 	movl	$3, %edi
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 1d85cb7071cb..ff6e32ec8259 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(alternatives_patched);
 #define DA_ENDBR	0x08
 #define DA_SMP		0x10
 
-static unsigned int __initdata_or_module debug_alternative;
+static unsigned int debug_alternative;
 
 static int __init debug_alt(char *str)
 {
@@ -133,7 +133,7 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
  * each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and
  * *jump* over instead of executing long and daft NOPs.
  */
-static void __init_or_module add_nop(u8 *instr, unsigned int len)
+static void add_nop(u8 *instr, unsigned int len)
 {
 	u8 *target = instr + len;
 
@@ -206,7 +206,7 @@ static int skip_nops(u8 *instr, int offset, int len)
  * Optimize a sequence of NOPs, possibly preceded by an unconditional jump
  * to the end of the NOP sequence into a single NOP.
  */
-static bool __init_or_module
+static bool
 __optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target)
 {
 	int i = *next - insn->length;
@@ -335,8 +335,7 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len)
 	return (target < src || target > src + src_len);
 }
 
-static void __init_or_module noinline
-apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
+void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
 {
 	int prev, target = 0;
 
@@ -545,7 +544,7 @@ static inline bool is_jcc32(struct insn *insn)
 	return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80;
 }
 
-#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL)
+#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*
  * CALL/JMP *%\reg
@@ -709,8 +708,8 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 	/*
 	 * The compiler is supposed to EMIT an INT3 after every unconditional
 	 * JMP instruction due to AMD BTC. However, if the compiler is too old
-	 * or SLS isn't enabled, we still need an INT3 after indirect JMPs
-	 * even on Intel.
+	 * or MITIGATION_SLS isn't enabled, we still need an INT3 after
+	 * indirect JMPs even on Intel.
 	 */
 	if (op == JMP32_INSN_OPCODE && i < insn->length)
 		bytes[i++] = INT3_INSN_OPCODE;
@@ -770,7 +769,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 	}
 }
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 
 /*
  * Rewrite the compiler generated return thunk tail-calls.
@@ -843,14 +842,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 }
 #else
 void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_MITIGATION_RETHUNK */
 
-#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */
+#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
 void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
 void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */
+#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 053f6dcc6b2c..5bf5f9fc5753 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -386,7 +386,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 
 int amd_get_subcaches(int cpu)
 {
-	struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link;
+	struct pci_dev *link = node_to_amd_nb(topology_amd_node_id(cpu))->link;
 	unsigned int mask;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
@@ -400,7 +400,7 @@ int amd_get_subcaches(int cpu)
 int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
-	struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu));
+	struct amd_northbridge *nb = node_to_amd_nb(topology_amd_node_id(cpu));
 	unsigned int reg;
 	int cuid;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4667bc4b00ab..a42d8a6f7149 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -19,6 +19,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/acpi_pmtmr.h>
+#include <linux/bitmap.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/memblock.h>
@@ -67,10 +68,6 @@
 
 #include "local.h"
 
-unsigned int num_processors;
-
-unsigned disabled_cpus;
-
 /* Processor that is doing the boot up */
 u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID;
 EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
@@ -78,18 +75,6 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 u8 boot_cpu_apic_version __ro_after_init;
 
 /*
- * Bitmask of physically existing CPUs:
- */
-physid_mask_t phys_cpu_present_map;
-
-/*
- * Processor to be disabled specified by kernel parameter
- * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
- * avoid undefined behaviour caused by sending INIT from AP to BSP.
- */
-static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID;
-
-/*
  * This variable controls which CPUs receive external NMIs.  By default,
  * external NMIs are delivered only to the BSP.
  */
@@ -108,14 +93,6 @@ static inline bool apic_accessible(void)
 	return x2apic_mode || apic_mmio_base;
 }
 
-/*
- * Map cpu index to physical APIC ID
- */
-DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
-
 #ifdef CONFIG_X86_32
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase __ro_after_init;
@@ -261,16 +238,6 @@ u64 native_apic_icr_read(void)
 	return icr1 | ((u64)icr2 << 32);
 }
 
-#ifdef CONFIG_X86_32
-/**
- * get_physical_broadcast - Get number of physical broadcast IDs
- */
-int get_physical_broadcast(void)
-{
-	return modern_apic() ? 0xff : 0xf;
-}
-#endif
-
 /**
  * lapic_get_maxlvt - get the maximum number of local vector table entries
  */
@@ -1549,9 +1516,6 @@ static void setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
-	/* Validate that the APIC is registered if required */
-	BUG_ON(apic->apic_id_registered && !apic->apic_id_registered());
-
 	/*
 	 * Intel recommends to set DFR, LDR and TPR before enabling
 	 * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
@@ -1690,8 +1654,6 @@ void apic_ap_setup(void)
 	end_local_APIC_setup();
 }
 
-static __init void cpu_set_boot_apic(void);
-
 static __init void apic_read_boot_cpu_id(bool x2apic)
 {
 	/*
@@ -1706,7 +1668,8 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_physical_apicid = read_apic_id();
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
-	cpu_set_boot_apic();
+	topology_register_boot_apic(boot_cpu_physical_apicid);
+	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
@@ -2091,7 +2054,6 @@ void __init init_apic_mappings(void)
 			pr_info("APIC: disable apic facility\n");
 			apic_disable();
 		}
-		num_processors = 1;
 	}
 }
 
@@ -2305,155 +2267,6 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	apic_write(APIC_LVT1, value);
 }
 
-/*
- * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
- * contiguously, it equals to current allocated max logical CPU ID plus 1.
- * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range,
- * so the maximum of nr_logical_cpuids is nr_cpu_ids.
- *
- * NOTE: Reserve 0 for BSP.
- */
-static int nr_logical_cpuids = 1;
-
-/*
- * Used to store mapping between logical CPU IDs and APIC IDs.
- */
-u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, };
-
-bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
-{
-	return phys_id == (u64)cpuid_to_apicid[cpu];
-}
-
-#ifdef CONFIG_SMP
-static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid)
-{
-	/* Isolate the SMT bit(s) in the APICID and check for 0 */
-	u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
-
-	if (smp_num_siblings == 1 || !(apicid & mask))
-		cpumask_set_cpu(cpu, &__cpu_primary_thread_mask);
-}
-
-/*
- * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid
- * during early boot. Initialize the primary thread mask before SMP
- * bringup.
- */
-static int __init smp_init_primary_thread_mask(void)
-{
-	unsigned int cpu;
-
-	/*
-	 * XEN/PV provides either none or useless topology information.
-	 * Pretend that all vCPUs are primary threads.
-	 */
-	if (xen_pv_domain()) {
-		cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask);
-		return 0;
-	}
-
-	for (cpu = 0; cpu < nr_logical_cpuids; cpu++)
-		cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]);
-	return 0;
-}
-early_initcall(smp_init_primary_thread_mask);
-#else
-static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { }
-#endif
-
-/*
- * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
- * and cpuid_to_apicid[] synchronized.
- */
-static int allocate_logical_cpuid(int apicid)
-{
-	int i;
-
-	/*
-	 * cpuid <-> apicid mapping is persistent, so when a cpu is up,
-	 * check if the kernel has allocated a cpuid for it.
-	 */
-	for (i = 0; i < nr_logical_cpuids; i++) {
-		if (cpuid_to_apicid[i] == apicid)
-			return i;
-	}
-
-	/* Allocate a new cpuid. */
-	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. "
-			     "Processor %d/0x%x and the rest are ignored.\n",
-			     nr_cpu_ids, nr_logical_cpuids, apicid);
-		return -EINVAL;
-	}
-
-	cpuid_to_apicid[nr_logical_cpuids] = apicid;
-	return nr_logical_cpuids++;
-}
-
-static void cpu_update_apic(int cpu, u32 apicid)
-{
-#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
-	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
-#endif
-	set_cpu_possible(cpu, true);
-	physid_set(apicid, phys_cpu_present_map);
-	set_cpu_present(cpu, true);
-	num_processors++;
-
-	if (system_state != SYSTEM_BOOTING)
-		cpu_mark_primary_thread(cpu, apicid);
-}
-
-static __init void cpu_set_boot_apic(void)
-{
-	cpuid_to_apicid[0] = boot_cpu_physical_apicid;
-	cpu_update_apic(0, boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
-}
-
-int generic_processor_info(int apicid)
-{
-	int cpu, max = nr_cpu_ids;
-
-	/* The boot CPU must be set before MADT/MPTABLE parsing happens */
-	if (cpuid_to_apicid[0] == BAD_APICID)
-		panic("Boot CPU APIC not registered yet\n");
-
-	if (apicid == boot_cpu_physical_apicid)
-		return 0;
-
-	if (disabled_cpu_apicid == apicid) {
-		int thiscpu = num_processors + disabled_cpus;
-
-		pr_warn("APIC: Disabling requested cpu. Processor %d/0x%x ignored.\n",
-			thiscpu, apicid);
-
-		disabled_cpus++;
-		return -ENODEV;
-	}
-
-	if (num_processors >= nr_cpu_ids) {
-		int thiscpu = max + disabled_cpus;
-
-		pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. "
-			"Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
-
-		disabled_cpus++;
-		return -EINVAL;
-	}
-
-	cpu = allocate_logical_cpuid(apicid);
-	if (cpu < 0) {
-		disabled_cpus++;
-		return -EINVAL;
-	}
-
-	cpu_update_apic(cpu, apicid);
-	return cpu;
-}
-
-
 void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg,
 			   bool dmar)
 {
@@ -2496,10 +2309,7 @@ EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid);
 
 static void __init apic_bsp_up_setup(void)
 {
-#ifdef CONFIG_X86_64
-	apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid));
-#endif
-	physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
+	reset_phys_cpu_present_map(boot_cpu_physical_apicid);
 }
 
 /**
@@ -2845,15 +2655,6 @@ static int __init lapic_insert_resource(void)
  */
 late_initcall(lapic_insert_resource);
 
-static int __init apic_set_disabled_cpu_apicid(char *arg)
-{
-	if (!arg || !get_option(&arg, &disabled_cpu_apicid))
-		return -EINVAL;
-
-	return 0;
-}
-early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
-
 static int __init apic_set_extnmi(char *arg)
 {
 	if (!arg)
diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c
index 8a00141073ea..9ef3be866832 100644
--- a/arch/x86/kernel/apic/apic_common.c
+++ b/arch/x86/kernel/apic/apic_common.c
@@ -18,16 +18,6 @@ u32 apic_flat_calc_apicid(unsigned int cpu)
 	return 1U << cpu;
 }
 
-bool default_check_apicid_used(physid_mask_t *map, u32 apicid)
-{
-	return physid_isset(apicid, *map);
-}
-
-void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
-{
-	*retmap = *phys_map;
-}
-
 u32 default_cpu_present_to_apicid(int mps_cpu)
 {
 	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
@@ -37,11 +27,6 @@ u32 default_cpu_present_to_apicid(int mps_cpu)
 }
 EXPORT_SYMBOL_GPL(default_cpu_present_to_apicid);
 
-bool default_apic_id_registered(void)
-{
-	return physid_isset(read_apic_id(), phys_cpu_present_map);
-}
-
 /*
  * Set up the logical destination ID when the APIC operates in logical
  * destination mode.
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index b295a056a4fc..f37ad3392fec 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -61,16 +61,6 @@ static u32 flat_get_apic_id(u32 x)
 	return (x >> 24) & 0xFF;
 }
 
-static u32 set_apic_id(u32 id)
-{
-	return (id & 0xFF) << 24;
-}
-
-static u32 flat_phys_pkg_id(u32 initial_apic_id, int index_msb)
-{
-	return initial_apic_id >> index_msb;
-}
-
 static int flat_probe(void)
 {
 	return 1;
@@ -80,7 +70,6 @@ static struct apic apic_flat __ro_after_init = {
 	.name				= "flat",
 	.probe				= flat_probe,
 	.acpi_madt_oem_check		= flat_acpi_madt_oem_check,
-	.apic_id_registered		= default_apic_id_registered,
 
 	.dest_mode_logical		= true,
 
@@ -88,11 +77,9 @@ static struct apic apic_flat __ro_after_init = {
 
 	.init_apic_ldr			= default_init_apic_ldr,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= flat_phys_pkg_id,
 
 	.max_apic_id			= 0xFE,
 	.get_apic_id			= flat_get_apic_id,
-	.set_apic_id			= set_apic_id,
 
 	.calc_dest_apicid		= apic_flat_calc_apicid,
 
@@ -151,18 +138,15 @@ static struct apic apic_physflat __ro_after_init = {
 	.name				= "physical flat",
 	.probe				= physflat_probe,
 	.acpi_madt_oem_check		= physflat_acpi_madt_oem_check,
-	.apic_id_registered		= default_apic_id_registered,
 
 	.dest_mode_logical		= false,
 
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= flat_phys_pkg_id,
 
 	.max_apic_id			= 0xFE,
 	.get_apic_id			= flat_get_apic_id,
-	.set_apic_id			= set_apic_id,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 9f1d553eb48f..b5bb7a2e8340 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -29,7 +29,6 @@ static void noop_send_IPI_self(int vector) { }
 static void noop_apic_icr_write(u32 low, u32 id) { }
 static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; }
 static u64 noop_apic_icr_read(void) { return 0; }
-static u32 noop_phys_pkg_id(u32 cpuid_apic, int index_msb) { return 0; }
 static u32 noop_get_apic_id(u32 apicid) { return 0; }
 static void noop_apic_eoi(void) { }
 
@@ -51,12 +50,8 @@ struct apic apic_noop __ro_after_init = {
 
 	.disable_esr			= 0,
 
-	.check_apicid_used		= default_check_apicid_used,
-	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
 
-	.phys_pkg_id			= noop_phys_pkg_id,
-
 	.max_apic_id			= 0xFE,
 	.get_apic_id			= noop_get_apic_id,
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 7d0c51b9d3bc..16410f087b7a 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -38,11 +38,6 @@ static u32 numachip1_get_apic_id(u32 x)
 	return id;
 }
 
-static u32 numachip1_set_apic_id(u32 id)
-{
-	return (id & 0xff) << 24;
-}
-
 static u32 numachip2_get_apic_id(u32 x)
 {
 	u64 mcfg;
@@ -51,16 +46,6 @@ static u32 numachip2_get_apic_id(u32 x)
 	return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24);
 }
 
-static u32 numachip2_set_apic_id(u32 id)
-{
-	return id << 24;
-}
-
-static u32 numachip_phys_pkg_id(u32 initial_apic_id, int index_msb)
-{
-	return initial_apic_id >> index_msb;
-}
-
 static void numachip1_apic_icr_write(int apicid, unsigned int val)
 {
 	write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val);
@@ -227,11 +212,9 @@ static const struct apic apic_numachip1 __refconst = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= numachip_phys_pkg_id,
 
 	.max_apic_id			= UINT_MAX,
 	.get_apic_id			= numachip1_get_apic_id,
-	.set_apic_id			= numachip1_set_apic_id,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
@@ -263,11 +246,9 @@ static const struct apic apic_numachip2 __refconst = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= numachip_phys_pkg_id,
 
 	.max_apic_id			= UINT_MAX,
 	.get_apic_id			= numachip2_get_apic_id,
-	.set_apic_id			= numachip2_set_apic_id,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 5a0d60b38e6b..9285d500d5b4 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -18,22 +18,6 @@ static u32 bigsmp_get_apic_id(u32 x)
 	return (x >> 24) & 0xFF;
 }
 
-static bool bigsmp_check_apicid_used(physid_mask_t *map, u32 apicid)
-{
-	return false;
-}
-
-static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	physids_promote(0xFFL, retmap);
-}
-
-static u32 bigsmp_phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
 static void bigsmp_send_IPI_allbutself(int vector)
 {
 	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -84,14 +68,10 @@ static struct apic apic_bigsmp __ro_after_init = {
 
 	.disable_esr			= 1,
 
-	.check_apicid_used		= bigsmp_check_apicid_used,
-	.ioapic_phys_id_map		= bigsmp_ioapic_phys_id_map,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= bigsmp_phys_pkg_id,
 
 	.max_apic_id			= 0xFE,
 	.get_apic_id			= bigsmp_get_apic_id,
-	.set_apic_id			= NULL,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 40c7cf180c20..477b740b2f26 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1458,20 +1458,20 @@ void restore_boot_irq_mode(void)
  *
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
-void __init setup_ioapic_ids_from_mpc_nocheck(void)
+static void __init setup_ioapic_ids_from_mpc_nocheck(void)
 {
+	DECLARE_BITMAP(phys_id_present_map, MAX_LOCAL_APIC);
+	const u32 broadcast_id = 0xF;
 	union IO_APIC_reg_00 reg_00;
-	physid_mask_t phys_id_present_map;
-	int ioapic_idx;
-	int i;
 	unsigned char old_id;
 	unsigned long flags;
+	int ioapic_idx, i;
 
 	/*
 	 * This is broken; anything with a real cpu count has to
 	 * circumvent this idiocy regardless.
 	 */
-	apic->ioapic_phys_id_map(&phys_cpu_present_map, &phys_id_present_map);
+	copy_phys_cpu_present_map(phys_id_present_map);
 
 	/*
 	 * Set the IOAPIC ID to the value stored in the MPC table.
@@ -1484,11 +1484,10 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void)
 
 		old_id = mpc_ioapic_id(ioapic_idx);
 
-		if (mpc_ioapic_id(ioapic_idx) >= get_physical_broadcast()) {
-			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
-				ioapic_idx, mpc_ioapic_id(ioapic_idx));
-			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
-				reg_00.bits.ID);
+		if (mpc_ioapic_id(ioapic_idx) >= broadcast_id) {
+			pr_err(FW_BUG "IO-APIC#%d ID is %d in the MPC table!...\n",
+			       ioapic_idx, mpc_ioapic_id(ioapic_idx));
+			pr_err("... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID);
 			ioapics[ioapic_idx].mp_config.apicid = reg_00.bits.ID;
 		}
 
@@ -1497,23 +1496,21 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void)
 		 * system must have a unique ID or we get lots of nice
 		 * 'stuck on smp_invalidate_needed IPI wait' messages.
 		 */
-		if (apic->check_apicid_used(&phys_id_present_map,
-					    mpc_ioapic_id(ioapic_idx))) {
-			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
-				ioapic_idx, mpc_ioapic_id(ioapic_idx));
-			for (i = 0; i < get_physical_broadcast(); i++)
-				if (!physid_isset(i, phys_id_present_map))
+		if (test_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map)) {
+			pr_err(FW_BUG "IO-APIC#%d ID %d is already used!...\n",
+			       ioapic_idx, mpc_ioapic_id(ioapic_idx));
+			for (i = 0; i < broadcast_id; i++)
+				if (!test_bit(i, phys_id_present_map))
 					break;
-			if (i >= get_physical_broadcast())
+			if (i >= broadcast_id)
 				panic("Max APIC ID exceeded!\n");
-			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
-				i);
-			physid_set(i, phys_id_present_map);
+			pr_err("... fixing up to %d. (tell your hw vendor)\n", i);
+			set_bit(i, phys_id_present_map);
 			ioapics[ioapic_idx].mp_config.apicid = i;
 		} else {
 			apic_printk(APIC_VERBOSE, "Setting %d in the phys_id_present_map\n",
 				    mpc_ioapic_id(ioapic_idx));
-			physid_set(mpc_ioapic_id(ioapic_idx), phys_id_present_map);
+			set_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map);
 		}
 
 		/*
@@ -2209,7 +2206,7 @@ static inline void __init check_timer(void)
 	 * 8259A.
 	 */
 	if (pin1 == -1) {
-		panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC");
+		panic_if_irq_remap(FW_BUG "Timer not connected to IO-APIC");
 		pin1 = pin2;
 		apic1 = apic2;
 		no_pin1 = 1;
@@ -2354,7 +2351,7 @@ static int mp_irqdomain_create(int ioapic)
 	fwspec.param_count = 1;
 	fwspec.param[0] = mpc_ioapic_id(ioapic);
 
-	parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY);
+	parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI);
 	if (!parent) {
 		if (!cfg->dev)
 			irq_domain_free_fwnode(fn);
@@ -2494,56 +2491,41 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
 #ifdef CONFIG_X86_32
 static int io_apic_get_unique_id(int ioapic, int apic_id)
 {
+	static DECLARE_BITMAP(apic_id_map, MAX_LOCAL_APIC);
+	const u32 broadcast_id = 0xF;
 	union IO_APIC_reg_00 reg_00;
-	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
-	physid_mask_t tmp;
 	unsigned long flags;
 	int i = 0;
 
-	/*
-	 * The P4 platform supports up to 256 APIC IDs on two separate APIC
-	 * buses (one for LAPICs, one for IOAPICs), where predecessors only
-	 * supports up to 16 on one shared APIC bus.
-	 *
-	 * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
-	 *      advantage of new APIC bus architecture.
-	 */
-
-	if (physids_empty(apic_id_map))
-		apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map);
+	/* Initialize the ID map */
+	if (bitmap_empty(apic_id_map, MAX_LOCAL_APIC))
+		copy_phys_cpu_present_map(apic_id_map);
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(ioapic, 0);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
-	if (apic_id >= get_physical_broadcast()) {
-		printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
-			"%d\n", ioapic, apic_id, reg_00.bits.ID);
+	if (apic_id >= broadcast_id) {
+		pr_warn("IOAPIC[%d]: Invalid apic_id %d, trying %d\n",
+			ioapic, apic_id, reg_00.bits.ID);
 		apic_id = reg_00.bits.ID;
 	}
 
-	/*
-	 * Every APIC in a system must have a unique ID or we get lots of nice
-	 * 'stuck on smp_invalidate_needed IPI wait' messages.
-	 */
-	if (apic->check_apicid_used(&apic_id_map, apic_id)) {
-
-		for (i = 0; i < get_physical_broadcast(); i++) {
-			if (!apic->check_apicid_used(&apic_id_map, i))
+	/* Every APIC in a system must have a unique ID */
+	if (test_bit(apic_id, apic_id_map)) {
+		for (i = 0; i < broadcast_id; i++) {
+			if (!test_bit(i, apic_id_map))
 				break;
 		}
 
-		if (i == get_physical_broadcast())
+		if (i == broadcast_id)
 			panic("Max apic_id exceeded!\n");
 
-		printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, "
-			"trying %d\n", ioapic, apic_id, i);
-
+		pr_warn("IOAPIC[%d]: apic_id %d already used, trying %d\n", ioapic, apic_id, i);
 		apic_id = i;
 	}
 
-	physid_set_mask_of_physid(apic_id, &tmp);
-	physids_or(apic_id_map, apic_id_map, tmp);
+	set_bit(apic_id, apic_id_map);
 
 	if (reg_00.bits.ID != apic_id) {
 		reg_00.bits.ID = apic_id;
@@ -2569,11 +2551,9 @@ static int io_apic_get_unique_id(int ioapic, int apic_id)
 
 static u8 io_apic_unique_id(int idx, u8 id)
 {
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
-	    !APIC_XAPIC(boot_cpu_apic_version))
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && !APIC_XAPIC(boot_cpu_apic_version))
 		return io_apic_get_unique_id(idx, id);
-	else
-		return id;
+	return id;
 }
 #else
 static u8 io_apic_unique_id(int idx, u8 id)
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 9ea6186ea88c..842fe28496be 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -16,8 +16,6 @@
 /* X2APIC */
 void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
 u32 x2apic_get_apic_id(u32 id);
-u32 x2apic_set_apic_id(u32 id);
-u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb);
 
 void x2apic_send_IPI_all(int vector);
 void x2apic_send_IPI_allbutself(int vector);
@@ -63,9 +61,6 @@ void default_send_IPI_allbutself(int vector);
 void default_send_IPI_all(int vector);
 void default_send_IPI_self(int vector);
 
-bool default_apic_id_registered(void);
-bool default_check_apicid_used(physid_mask_t *map, u32 apicid);
-
 #ifdef CONFIG_X86_32
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index c0f78059f06a..f75ee345c02d 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -18,11 +18,6 @@
 
 #include "local.h"
 
-static u32 default_phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
 static u32 default_get_apic_id(u32 x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
@@ -43,17 +38,13 @@ static struct apic apic_default __ro_after_init = {
 
 	.name				= "default",
 	.probe				= probe_default,
-	.apic_id_registered		= default_apic_id_registered,
 
 	.dest_mode_logical		= true,
 
 	.disable_esr			= 0,
 
-	.check_apicid_used		= default_check_apicid_used,
 	.init_apic_ldr			= default_init_apic_ldr,
-	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= default_phys_pkg_id,
 
 	.max_apic_id			= 0xFE,
 	.get_apic_id			= default_get_apic_id,
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 28a7d3f2312d..567dbd2fe4b6 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -231,16 +231,12 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
 
 	.disable_esr			= 0,
 
-	.check_apicid_used		= NULL,
 	.init_apic_ldr			= init_x2apic_ldr,
-	.ioapic_phys_id_map		= NULL,
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= x2apic_phys_pkg_id,
 
 	.max_apic_id			= UINT_MAX,
 	.x2apic_set_max_apicid		= true,
 	.get_apic_id			= x2apic_get_apic_id,
-	.set_apic_id			= x2apic_set_apic_id,
 
 	.calc_dest_apicid		= x2apic_calc_apicid,
 
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 409815a40668..12d4c35547a6 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -129,16 +129,6 @@ u32 x2apic_get_apic_id(u32 id)
 	return id;
 }
 
-u32 x2apic_set_apic_id(u32 id)
-{
-	return id;
-}
-
-u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb)
-{
-	return initial_apicid >> index_msb;
-}
-
 static struct apic apic_x2apic_phys __ro_after_init = {
 
 	.name				= "physical x2apic",
@@ -150,12 +140,10 @@ static struct apic apic_x2apic_phys __ro_after_init = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= x2apic_phys_pkg_id,
 
 	.max_apic_id			= UINT_MAX,
 	.x2apic_set_max_apicid		= true,
 	.get_apic_id			= x2apic_get_apic_id,
-	.set_apic_id			= x2apic_set_apic_id,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f1766b18dcd0..7fef504ca508 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -241,54 +241,20 @@ static void __init uv_tsc_check_sync(void)
 	is_uv(UV3) ? sname.s3.field :		\
 	undef)
 
-/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
-
-#define SMT_LEVEL			0	/* Leaf 0xb SMT level */
-#define INVALID_TYPE			0	/* Leaf 0xb sub-leaf types */
-#define SMT_TYPE			1
-#define CORE_TYPE			2
-#define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
-#define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
-
-static void set_x2apic_bits(void)
-{
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int sid_shift;
-
-	cpuid(0, &eax, &ebx, &ecx, &edx);
-	if (eax < 0xb) {
-		pr_info("UV: CPU does not have CPUID.11\n");
-		return;
-	}
-
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
-	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
-		pr_info("UV: CPUID.11 not implemented\n");
-		return;
-	}
-
-	sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
-	sub_index = 1;
-	do {
-		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
-		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
-			sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
-		}
-		sub_index++;
-	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
-
-	uv_cpuid.apicid_shift	= 0;
-	uv_cpuid.apicid_mask	= (~(-1 << sid_shift));
-	uv_cpuid.socketid_shift = sid_shift;
-}
-
 static void __init early_get_apic_socketid_shift(void)
 {
+	unsigned int sid_shift = topology_get_domain_shift(TOPO_PKG_DOMAIN);
+
 	if (is_uv2_hub() || is_uv3_hub())
 		uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
 
-	set_x2apic_bits();
+	if (sid_shift) {
+		uv_cpuid.apicid_shift	= 0;
+		uv_cpuid.apicid_mask	= (~(-1 << sid_shift));
+		uv_cpuid.socketid_shift = sid_shift;
+	} else {
+		pr_info("UV: CPU does not have valid CPUID.11\n");
+	}
 
 	pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
 	pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
@@ -779,21 +745,6 @@ static void uv_send_IPI_all(int vector)
 	uv_send_IPI_mask(cpu_online_mask, vector);
 }
 
-static u32 set_apic_id(u32 id)
-{
-	return id;
-}
-
-static unsigned int uv_read_apic_id(void)
-{
-	return x2apic_get_apic_id(apic_read(APIC_ID));
-}
-
-static u32 uv_phys_pkg_id(u32 initial_apicid, int index_msb)
-{
-	return uv_read_apic_id() >> index_msb;
-}
-
 static int uv_probe(void)
 {
 	return apic == &apic_x2apic_uv_x;
@@ -810,11 +761,9 @@ static struct apic apic_x2apic_uv_x __ro_after_init = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-	.phys_pkg_id			= uv_phys_pkg_id,
 
 	.max_apic_id			= UINT_MAX,
 	.get_apic_id			= x2apic_get_apic_id,
-	.set_apic_id			= set_apic_id,
 
 	.calc_dest_apicid		= apic_default_calc_apicid,
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 76a5ced278c2..b37ab1095707 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1055,35 +1055,6 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
 	return APM_SUCCESS;
 }
 
-#if 0
-static int apm_get_battery_status(u_short which, u_short *status,
-				  u_short *bat, u_short *life, u_short *nbat)
-{
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 esi;
-
-	if (apm_info.connection_version < 0x0102) {
-		/* pretend we only have one battery. */
-		if (which != 1)
-			return APM_BAD_DEVICE;
-		*nbat = 1;
-		return apm_get_power_status(status, bat, life);
-	}
-
-	if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax,
-			  &ebx, &ecx, &edx, &esi))
-		return (eax >> 8) & 0xff;
-	*status = ebx;
-	*bat = ecx;
-	*life = edx;
-	*nbat = esi;
-	return APM_SUCCESS;
-}
-#endif
-
 /**
  *	apm_engage_power_management	-	enable PM on a device
  *	@device: identity of device
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 6913b372ccf7..a98020bf31bb 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -109,7 +109,7 @@ static void __used common(void)
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
 	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
 	OFFSET(X86_current_task, pcpu_hot, current_task);
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 	OFFSET(X86_call_depth, pcpu_hot, call_depth);
 #endif
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 64ad2ddea121..30335182b6b0 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -24,6 +24,8 @@
 
 static int __initdata_or_module debug_callthunks;
 
+#define MAX_PATCH_LEN (255-1)
+
 #define prdbg(fmt, args...)					\
 do {								\
 	if (debug_callthunks)					\
@@ -42,8 +44,8 @@ DEFINE_PER_CPU(u64, __x86_call_count);
 DEFINE_PER_CPU(u64, __x86_ret_count);
 DEFINE_PER_CPU(u64, __x86_stuffs_count);
 DEFINE_PER_CPU(u64, __x86_ctxsw_count);
-EXPORT_SYMBOL_GPL(__x86_ctxsw_count);
-EXPORT_SYMBOL_GPL(__x86_call_count);
+EXPORT_PER_CPU_SYMBOL_GPL(__x86_ctxsw_count);
+EXPORT_PER_CPU_SYMBOL_GPL(__x86_call_count);
 #endif
 
 extern s32 __call_sites[], __call_sites_end[];
@@ -179,10 +181,15 @@ static const u8 nops[] = {
 static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
+	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *pad = dest - tsize;
 
+	memcpy(insn_buff, skl_call_thunk_template, tsize);
+	apply_relocation(insn_buff, tsize, pad,
+			 skl_call_thunk_template, tsize);
+
 	/* Already patched? */
-	if (!bcmp(pad, skl_call_thunk_template, tsize))
+	if (!bcmp(pad, insn_buff, tsize))
 		return pad;
 
 	/* Ensure there are nops */
@@ -192,9 +199,9 @@ static void *patch_dest(void *dest, bool direct)
 	}
 
 	if (direct)
-		memcpy(pad, skl_call_thunk_template, tsize);
+		memcpy(pad, insn_buff, tsize);
 	else
-		text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+		text_poke_copy_locked(pad, insn_buff, tsize, true);
 	return pad;
 }
 
@@ -290,20 +297,27 @@ void *callthunks_translate_call_dest(void *dest)
 static bool is_callthunk(void *addr)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 	unsigned long dest;
+	u8 *pad;
 
 	dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
 	if (!thunks_initialized || skip_addr((void *)dest))
 		return false;
 
-	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+	pad = (void *)(dest - tmpl_size);
+
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, pad,
+			 skl_call_thunk_template, tmpl_size);
+
+	return !bcmp(pad, insn_buff, tmpl_size);
 }
 
 int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 
 	if (!thunks_initialized)
 		return 0;
@@ -312,7 +326,11 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 	if (func && is_callthunk(func))
 		return 0;
 
-	memcpy(*pprog, tmpl, tmpl_size);
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, *pprog,
+			 skl_call_thunk_template, tmpl_size);
+
+	memcpy(*pprog, insn_buff, tmpl_size);
 	*pprog += tmpl_size;
 	return tmpl_size;
 }
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 93eabf544031..eb4dbcdf41f1 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -17,7 +17,8 @@ KMSAN_SANITIZE_common.o := n
 # As above, instrumenting secondary CPU boot code causes boot hangs.
 KCSAN_SANITIZE_common.o := n
 
-obj-y			:= cacheinfo.o scattered.o topology.o
+obj-y			:= cacheinfo.o scattered.o
+obj-y			+= topology_common.o topology_ext.o topology_amd.o
 obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
@@ -25,14 +26,16 @@ obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
 obj-y			+= umwait.o
+obj-y 			+= capflags.o powerflags.o
 
-obj-$(CONFIG_PROC_FS)	+= proc.o
-obj-y += capflags.o powerflags.o
+obj-$(CONFIG_X86_LOCAL_APIC)		+= topology.o
 
-obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o
+obj-$(CONFIG_PROC_FS)			+= proc.o
+
+obj-$(CONFIG_IA32_FEAT_CTL)		+= feat_ctl.o
 ifdef CONFIG_CPU_SUP_INTEL
-obj-y			+= intel.o intel_pconfig.o tsx.o
-obj-$(CONFIG_PM)	+= intel_epb.o
+obj-y					+= intel.o intel_pconfig.o tsx.o
+obj-$(CONFIG_PM)			+= intel_epb.o
 endif
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
 obj-$(CONFIG_CPU_SUP_HYGON)		+= hygon.o
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index bfeb18fad63f..2c5b51aad91a 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -26,8 +26,8 @@ static u32 __init acrn_detect(void)
 
 static void __init acrn_init_platform(void)
 {
-	/* Setup the IDT for ACRN hypervisor callback */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback);
+	/* Install system interrupt handler for ACRN hypervisor callback */
+	sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback);
 
 	x86_platform.calibrate_tsc = acrn_get_tsc_khz;
 	x86_platform.calibrate_cpu = acrn_get_tsc_khz;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f3abca334199..3282a747b645 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -20,6 +20,7 @@
 #include <asm/delay.h>
 #include <asm/debugreg.h>
 #include <asm/resctrl.h>
+#include <asm/sev.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -27,13 +28,6 @@
 
 #include "cpu.h"
 
-/*
- * nodes_per_socket: Stores the number of nodes per socket.
- * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
- * Node Identifiers[10:8]
- */
-static u32 nodes_per_socket = 1;
-
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -300,97 +294,6 @@ static int nearby_node(int apicid)
 }
 #endif
 
-/*
- * Fix up topo::core_id for pre-F17h systems to be in the
- * [0 .. cores_per_node - 1] range. Not really needed but
- * kept so as not to break existing setups.
- */
-static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
-{
-	u32 cus_per_node;
-
-	if (c->x86 >= 0x17)
-		return;
-
-	cus_per_node = c->x86_max_cores / nodes_per_socket;
-	c->topo.core_id %= cus_per_node;
-}
-
-/*
- * Fixup core topology information for
- * (1) AMD multi-node processors
- *     Assumption: Number of cores in each internal node is the same.
- * (2) AMD processors supporting compute units
- */
-static void amd_get_topology(struct cpuinfo_x86 *c)
-{
-	/* get information required for multi-node processors */
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		int err;
-		u32 eax, ebx, ecx, edx;
-
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-
-		c->topo.die_id  = ecx & 0xff;
-
-		if (c->x86 == 0x15)
-			c->topo.cu_id = ebx & 0xff;
-
-		if (c->x86 >= 0x17) {
-			c->topo.core_id = ebx & 0xff;
-
-			if (smp_num_siblings > 1)
-				c->x86_max_cores /= smp_num_siblings;
-		}
-
-		/*
-		 * In case leaf B is available, use it to derive
-		 * topology information.
-		 */
-		err = detect_extended_topology(c);
-		if (!err)
-			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
-
-		cacheinfo_amd_init_llc_id(c);
-
-	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
-		u64 value;
-
-		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		c->topo.die_id = value & 7;
-		c->topo.llc_id = c->topo.die_id;
-	} else
-		return;
-
-	if (nodes_per_socket > 1) {
-		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		legacy_fixup_core_id(c);
-	}
-}
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
- * Assumes number of cores is a power of two.
- */
-static void amd_detect_cmp(struct cpuinfo_x86 *c)
-{
-	unsigned bits;
-
-	bits = c->x86_coreid_bits;
-	/* Low order bits define the core id (index of core in socket) */
-	c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
-	/* Convert the initial APIC ID into the socket ID */
-	c->topo.pkg_id = c->topo.initial_apicid >> bits;
-	/* use socket ID also for last level cache */
-	c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
-}
-
-u32 amd_get_nodes_per_socket(void)
-{
-	return nodes_per_socket;
-}
-EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
-
 static void srat_detect_node(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_NUMA
@@ -442,32 +345,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned bits, ecx;
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level < 0x80000008)
-		return;
-
-	ecx = cpuid_ecx(0x80000008);
-
-	c->x86_max_cores = (ecx & 0xff) + 1;
-
-	/* CPU telling us the core id bits shift? */
-	bits = (ecx >> 12) & 0xF;
-
-	/* Otherwise recompute */
-	if (bits == 0) {
-		while ((1 << bits) < c->x86_max_cores)
-			bits++;
-	}
-
-	c->x86_coreid_bits = bits;
-#endif
-}
-
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -500,18 +377,6 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_MWAITX))
 		use_mwaitx_delay();
 
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		u32 ecx;
-
-		ecx = cpuid_ecx(0x8000001e);
-		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
-	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
-		u64 value;
-
-		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
-	}
-
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
 	    !boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
 	    c->x86 >= 0x15 && c->x86 <= 0x17) {
@@ -587,6 +452,21 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		break;
 	}
 
+	if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
+		/*
+		 * RMP table entry format is not architectural and it can vary by processor
+		 * and is defined by the per-processor PPR. Restrict SNP support on the
+		 * known CPU model and family for which the RMP table entry format is
+		 * currently defined for.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_ZEN3) &&
+		    !boot_cpu_has(X86_FEATURE_ZEN4) &&
+		    !boot_cpu_has(X86_FEATURE_ZEN5))
+			setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+		else if (!snp_probe_rmptable_info())
+			setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+	}
+
 	return;
 
 warn:
@@ -605,8 +485,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 *	      SME feature (set in scattered.c).
 	 *	      If the kernel has not enabled SME via any means then
 	 *	      don't advertise the SME feature.
-	 *   For SEV: If BIOS has not enabled SEV then don't advertise the
-	 *            SEV and SEV_ES feature (set in scattered.c).
+	 *   For SEV: If BIOS has not enabled SEV then don't advertise SEV and
+	 *	      any additional functionality based on it.
 	 *
 	 *   In all cases, since support for SME and SEV requires long mode,
 	 *   don't advertise the feature under CONFIG_X86_32.
@@ -641,6 +521,7 @@ clear_all:
 clear_sev:
 		setup_clear_cpu_cap(X86_FEATURE_SEV);
 		setup_clear_cpu_cap(X86_FEATURE_SEV_ES);
+		setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
 	}
 }
 
@@ -649,8 +530,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	u64 value;
 	u32 dummy;
 
-	early_init_amd_mc(c);
-
 	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
@@ -730,9 +609,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
-	if (cpu_has(c, X86_FEATURE_TOPOEXT))
-		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
-
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
 		if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
 			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
@@ -941,7 +817,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c)
 
 void init_spectral_chicken(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 	u64 value;
 
 	/*
@@ -969,7 +845,6 @@ static void init_amd_zen_common(void)
 
 static void init_amd_zen1(struct cpuinfo_x86 *c)
 {
-	init_amd_zen_common();
 	fix_erratum_1386(c);
 
 	/* Fix up CPUID bits, but only if not virtualised. */
@@ -1023,7 +898,6 @@ static void zen2_zenbleed_check(struct cpuinfo_x86 *c)
 
 static void init_amd_zen2(struct cpuinfo_x86 *c)
 {
-	init_amd_zen_common();
 	init_spectral_chicken(c);
 	fix_erratum_1386(c);
 	zen2_zenbleed_check(c);
@@ -1031,8 +905,6 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
 
 static void init_amd_zen3(struct cpuinfo_x86 *c)
 {
-	init_amd_zen_common();
-
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		/*
 		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
@@ -1046,15 +918,12 @@ static void init_amd_zen3(struct cpuinfo_x86 *c)
 
 static void init_amd_zen4(struct cpuinfo_x86 *c)
 {
-	init_amd_zen_common();
-
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR))
 		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
 }
 
 static void init_amd_zen5(struct cpuinfo_x86 *c)
 {
-	init_amd_zen_common();
 }
 
 static void init_amd(struct cpuinfo_x86 *c)
@@ -1076,9 +945,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_FSRM))
 		set_cpu_cap(c, X86_FEATURE_FSRS);
 
-	/* get apicid instead of initial apic id from cpuid */
-	c->topo.apicid = read_apic_id();
-
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
 		clear_cpu_cap(c, X86_FEATURE_MCE);
@@ -1094,6 +960,13 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x16: init_amd_jg(c); break;
 	}
 
+	/*
+	 * Save up on some future enablement work and do common Zen
+	 * settings.
+	 */
+	if (c->x86 >= 0x17)
+		init_amd_zen_common();
+
 	if (boot_cpu_has(X86_FEATURE_ZEN1))
 		init_amd_zen1(c);
 	else if (boot_cpu_has(X86_FEATURE_ZEN2))
@@ -1114,8 +987,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	cpu_detect_cache_sizes(c);
 
-	amd_detect_cmp(c);
-	amd_get_topology(c);
 	srat_detect_node(c);
 
 	init_amd_cacheinfo(c);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bb0ab8466b91..e7ba936d798b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
 
 /* The current value of the SPEC_CTRL MSR with task-specific bits set */
 DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
-EXPORT_SYMBOL_GPL(x86_spec_ctrl_current);
+EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
 EXPORT_SYMBOL_GPL(x86_pred_cmd);
@@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-/* Control MDS CPU buffer clear before returning to user space */
-DEFINE_STATIC_KEY_FALSE(mds_user_clear);
-EXPORT_SYMBOL_GPL(mds_user_clear);
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void)
 		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
 
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
 		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
@@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void)
 	 * For guests that can't determine whether the correct microcode is
 	 * present on host, enable the mitigation for UCODE_NEEDED as well.
 	 */
-	static_branch_enable(&mds_user_clear);
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
 
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
@@ -424,7 +421,14 @@ static void __init mmio_select_mitigation(void)
 	 */
 	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
 					      boot_cpu_has(X86_FEATURE_RTM)))
-		static_branch_enable(&mds_user_clear);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+
+	/*
+	 * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based
+	 * mitigations, disable KVM-only mitigation in that case.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
+		static_branch_disable(&mmio_stale_data_clear);
 	else
 		static_branch_enable(&mmio_stale_data_clear);
 
@@ -477,6 +481,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str)
 early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"Register File Data Sampling: " fmt
+
+enum rfds_mitigations {
+	RFDS_MITIGATION_OFF,
+	RFDS_MITIGATION_VERW,
+	RFDS_MITIGATION_UCODE_NEEDED,
+};
+
+/* Default mitigation for Register File Data Sampling */
+static enum rfds_mitigations rfds_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF;
+
+static const char * const rfds_strings[] = {
+	[RFDS_MITIGATION_OFF]			= "Vulnerable",
+	[RFDS_MITIGATION_VERW]			= "Mitigation: Clear Register File",
+	[RFDS_MITIGATION_UCODE_NEEDED]		= "Vulnerable: No microcode",
+};
+
+static void __init rfds_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) {
+		rfds_mitigation = RFDS_MITIGATION_OFF;
+		return;
+	}
+	if (rfds_mitigation == RFDS_MITIGATION_OFF)
+		return;
+
+	if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR)
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+	else
+		rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
+}
+
+static __init int rfds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_RFDS))
+		return 0;
+
+	if (!strcmp(str, "off"))
+		rfds_mitigation = RFDS_MITIGATION_OFF;
+	else if (!strcmp(str, "on"))
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+
+	return 0;
+}
+early_param("reg_file_data_sampling", rfds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "" fmt
 
 static void __init md_clear_update_mitigation(void)
@@ -484,12 +539,12 @@ static void __init md_clear_update_mitigation(void)
 	if (cpu_mitigations_off())
 		return;
 
-	if (!static_key_enabled(&mds_user_clear))
+	if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
 		goto out;
 
 	/*
-	 * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
-	 * mitigation, if necessary.
+	 * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
+	 * Stale Data mitigation, if necessary.
 	 */
 	if (mds_mitigation == MDS_MITIGATION_OFF &&
 	    boot_cpu_has_bug(X86_BUG_MDS)) {
@@ -501,11 +556,19 @@ static void __init md_clear_update_mitigation(void)
 		taa_mitigation = TAA_MITIGATION_VERW;
 		taa_select_mitigation();
 	}
-	if (mmio_mitigation == MMIO_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
+	/*
+	 * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear
+	 * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
 		mmio_mitigation = MMIO_MITIGATION_VERW;
 		mmio_select_mitigation();
 	}
+	if (rfds_mitigation == RFDS_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_RFDS)) {
+		rfds_mitigation = RFDS_MITIGATION_VERW;
+		rfds_select_mitigation();
+	}
 out:
 	if (boot_cpu_has_bug(X86_BUG_MDS))
 		pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
@@ -515,6 +578,8 @@ out:
 		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
 	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
 		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
+	if (boot_cpu_has_bug(X86_BUG_RFDS))
+		pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]);
 }
 
 static void __init md_clear_select_mitigation(void)
@@ -522,11 +587,12 @@ static void __init md_clear_select_mitigation(void)
 	mds_select_mitigation();
 	taa_select_mitigation();
 	mmio_select_mitigation();
+	rfds_select_mitigation();
 
 	/*
-	 * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update
-	 * and print their mitigation after MDS, TAA and MMIO Stale Data
-	 * mitigation selection is done.
+	 * As these mitigations are inter-related and rely on VERW instruction
+	 * to clear the microarchitural buffers, update and print their status
+	 * after mitigation selection is done for each of these vulnerabilities.
 	 */
 	md_clear_update_mitigation();
 }
@@ -671,7 +737,7 @@ enum gds_mitigations {
 	GDS_MITIGATION_HYPERVISOR,
 };
 
-#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION)
+#if IS_ENABLED(CONFIG_MITIGATION_GDS_FORCE)
 static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE;
 #else
 static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL;
@@ -982,10 +1048,10 @@ static void __init retbleed_select_mitigation(void)
 		return;
 
 	case RETBLEED_CMD_UNRET:
-		if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) {
+		if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) {
 			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
 		} else {
-			pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n");
+			pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n");
 			goto do_cmd_auto;
 		}
 		break;
@@ -994,24 +1060,24 @@ static void __init retbleed_select_mitigation(void)
 		if (!boot_cpu_has(X86_FEATURE_IBPB)) {
 			pr_err("WARNING: CPU does not support IBPB.\n");
 			goto do_cmd_auto;
-		} else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) {
+		} else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
 		} else {
-			pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
+			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
 			goto do_cmd_auto;
 		}
 		break;
 
 	case RETBLEED_CMD_STUFF:
-		if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) &&
+		if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) &&
 		    spectre_v2_enabled == SPECTRE_V2_RETPOLINE) {
 			retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
 
 		} else {
-			if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING))
+			if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))
 				pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
 			else
-				pr_err("WARNING: kernel not compiled with CALL_DEPTH_TRACKING.\n");
+				pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n");
 
 			goto do_cmd_auto;
 		}
@@ -1021,9 +1087,10 @@ do_cmd_auto:
 	case RETBLEED_CMD_AUTO:
 		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
 		    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
-			if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY))
+			if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY))
 				retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
-			else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB))
+			else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) &&
+				 boot_cpu_has(X86_FEATURE_IBPB))
 				retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
 		}
 
@@ -1102,7 +1169,7 @@ static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
 static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 static bool spectre_v2_bad_module;
 
 bool retpoline_module_ok(bool has_retpoline)
@@ -1415,7 +1482,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC ||
 	     cmd == SPECTRE_V2_CMD_EIBRS_LFENCE ||
 	     cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) &&
-	    !IS_ENABLED(CONFIG_RETPOLINE)) {
+	    !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) {
 		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
 		       mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
@@ -1438,7 +1505,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
-	if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) {
+	if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY)) {
 		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
 		       mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
@@ -1469,7 +1536,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 
 static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void)
 {
-	if (!IS_ENABLED(CONFIG_RETPOLINE)) {
+	if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) {
 		pr_err("Kernel not compiled with retpoline; no mitigation available!");
 		return SPECTRE_V2_NONE;
 	}
@@ -1564,7 +1631,7 @@ static void __init spectre_v2_select_mitigation(void)
 			break;
 		}
 
-		if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) &&
+		if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) &&
 		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
 		    retbleed_cmd != RETBLEED_CMD_OFF &&
 		    retbleed_cmd != RETBLEED_CMD_STUFF &&
@@ -2457,7 +2524,7 @@ static void __init srso_select_mitigation(void)
 		break;
 
 	case SRSO_CMD_SAFE_RET:
-		if (IS_ENABLED(CONFIG_CPU_SRSO)) {
+		if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
 			/*
 			 * Enable the return thunk for generated code
 			 * like ftrace, static_call, etc.
@@ -2477,29 +2544,29 @@ static void __init srso_select_mitigation(void)
 			else
 				srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
 		} else {
-			pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
+			pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
 		}
 		break;
 
 	case SRSO_CMD_IBPB:
-		if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) {
+		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
 				srso_mitigation = SRSO_MITIGATION_IBPB;
 			}
 		} else {
-			pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
+			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
 		}
 		break;
 
 	case SRSO_CMD_IBPB_ON_VMEXIT:
-		if (IS_ENABLED(CONFIG_CPU_SRSO)) {
+		if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
 			if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
 				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 			}
 		} else {
-			pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
+			pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
                 }
 		break;
 	}
@@ -2615,6 +2682,11 @@ static ssize_t mmio_stale_data_show_state(char *buf)
 			  sched_smt_active() ? "vulnerable" : "disabled");
 }
 
+static ssize_t rfds_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
@@ -2774,6 +2846,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_GDS:
 		return gds_show_state(buf);
 
+	case X86_BUG_RFDS:
+		return rfds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -2848,4 +2923,14 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_GDS);
 }
+
+ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
+}
 #endif
+
+void __warn_thunk(void)
+{
+	WARN_ONCE(1, "Unpatched return thunk in use. This should not happen!\n");
+}
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index c131c412db89..392d09c936d6 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -301,7 +301,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
 	eax->split.num_threads_sharing = 0;
-	eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1;
+	eax->split.num_cores_on_die = topology_num_cores_per_package();
 
 
 	if (assoc == 0xffff)
@@ -595,7 +595,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 	if (index < 3)
 		return;
 
-	node = topology_die_id(smp_processor_id());
+	node = topology_amd_node_id(smp_processor_id());
 	this_leaf->nb = node_to_amd_nb(node);
 	if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
 		amd_calc_l3_indices(this_leaf->nb);
@@ -661,7 +661,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 	return i;
 }
 
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c)
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
 {
 	/*
 	 * We may have multiple LLCs if L3 caches exist, so check if we
@@ -672,7 +672,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c)
 
 	if (c->x86 < 0x17) {
 		/* LLC is at the node level. */
-		c->topo.llc_id = c->topo.die_id;
+		c->topo.llc_id = die_id;
 	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
 		 * LLC is at the core complex level.
@@ -1118,15 +1118,16 @@ static void cache_cpu_init(void)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	cache_disable();
 
-	if (memory_caching_control & CACHE_MTRR)
+	if (memory_caching_control & CACHE_MTRR) {
+		cache_disable();
 		mtrr_generic_set_state();
+		cache_enable();
+	}
 
 	if (memory_caching_control & CACHE_PAT)
 		pat_cpu_init();
 
-	cache_enable();
 	local_irq_restore(flags);
 }
 
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 345f7d905db6..a3b55db35c96 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -128,10 +128,6 @@ static void init_centaur(struct cpuinfo_x86 *c)
 #endif
 	early_init_centaur(c);
 	init_intel_cacheinfo(c);
-	detect_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
 
 	if (c->cpuid_level > 9) {
 		unsigned int eax = cpuid_eax(10);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b97bcde70c6..ba8cf5e9ce56 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -61,6 +61,7 @@
 #include <asm/microcode.h>
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
+#include <asm/fred.h>
 #include <asm/uv/uv.h>
 #include <asm/ia32.h>
 #include <asm/set_memory.h>
@@ -70,11 +71,26 @@
 
 #include "cpu.h"
 
+DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
+EXPORT_PER_CPU_SYMBOL(cpu_info);
+
 u32 elf_hwcap2 __read_mostly;
 
 /* Number of siblings per CPU package */
-int smp_num_siblings = 1;
-EXPORT_SYMBOL(smp_num_siblings);
+unsigned int __max_threads_per_core __ro_after_init = 1;
+EXPORT_SYMBOL(__max_threads_per_core);
+
+unsigned int __max_dies_per_package __ro_after_init = 1;
+EXPORT_SYMBOL(__max_dies_per_package);
+
+unsigned int __max_logical_packages __ro_after_init = 1;
+EXPORT_SYMBOL(__max_logical_packages);
+
+unsigned int __num_cores_per_package __ro_after_init = 1;
+EXPORT_SYMBOL(__num_cores_per_package);
+
+unsigned int __num_threads_per_package __ro_after_init = 1;
+EXPORT_SYMBOL(__num_threads_per_package);
 
 static struct ppin_info {
 	int	feature;
@@ -382,9 +398,8 @@ out:
 }
 
 /* These bits should not change their value after CPU init is finished. */
-static const unsigned long cr4_pinned_mask =
-	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
-	X86_CR4_FSGSBASE | X86_CR4_CET;
+static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
+					     X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -790,19 +805,6 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	*(s + 1) = '\0';
 }
 
-void detect_num_cpu_cores(struct cpuinfo_x86 *c)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	c->x86_max_cores = 1;
-	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
-		return;
-
-	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
-	if (eax & 0x1f)
-		c->x86_max_cores = (eax >> 26) + 1;
-}
-
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, ebx, ecx, edx, l2size;
@@ -864,51 +866,6 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-int detect_ht_early(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	u32 eax, ebx, ecx, edx;
-
-	if (!cpu_has(c, X86_FEATURE_HT))
-		return -1;
-
-	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		return -1;
-
-	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return -1;
-
-	cpuid(1, &eax, &ebx, &ecx, &edx);
-
-	smp_num_siblings = (ebx & 0xff0000) >> 16;
-	if (smp_num_siblings == 1)
-		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-#endif
-	return 0;
-}
-
-void detect_ht(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	int index_msb, core_bits;
-
-	if (detect_ht_early(c) < 0)
-		return;
-
-	index_msb = get_count_order(smp_num_siblings);
-	c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb);
-
-	smp_num_siblings = smp_num_siblings / c->x86_max_cores;
-
-	index_msb = get_count_order(smp_num_siblings);
-
-	core_bits = get_count_order(c->x86_max_cores);
-
-	c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) &
-		((1 << core_bits) - 1);
-#endif
-}
-
 static void get_cpu_vendor(struct cpuinfo_x86 *c)
 {
 	char *v = c->x86_vendor_id;
@@ -1267,6 +1224,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define SRSO		BIT(5)
 /* CPU is affected by GDS */
 #define GDS		BIT(6)
+/* CPU is affected by Register File Data Sampling */
+#define RFDS		BIT(7)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
@@ -1294,9 +1253,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(TIGERLAKE,	X86_STEPPING_ANY,		GDS),
 	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
 	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ALDERLAKE,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(ALDERLAKE_L,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(RAPTORLAKE,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO | RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D,	X86_STEPPING_ANY,		RFDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY,		RFDS),
 
 	VULNBL_AMD(0x15, RETBLEED),
 	VULNBL_AMD(0x16, RETBLEED),
@@ -1330,6 +1298,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap)
 		ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
 }
 
+static bool __init vulnerable_to_rfds(u64 ia32_cap)
+{
+	/* The "immunity" bit trumps everything else: */
+	if (ia32_cap & ARCH_CAP_RFDS_NO)
+		return false;
+
+	/*
+	 * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to
+	 * indicate that mitigation is needed because guest is running on a
+	 * vulnerable hardware or may migrate to such hardware:
+	 */
+	if (ia32_cap & ARCH_CAP_RFDS_CLEAR)
+		return true;
+
+	/* Only consult the blacklist when there is no enumeration: */
+	return cpu_matches(cpu_vuln_blacklist, RFDS);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = x86_read_arch_cap_msr();
@@ -1355,8 +1341,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	/*
 	 * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature
 	 * flag and protect from vendor-specific bugs via the whitelist.
+	 *
+	 * Don't use AutoIBRS when SNP is enabled because it degrades host
+	 * userspace indirect branch performance.
 	 */
-	if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
+	if ((ia32_cap & ARCH_CAP_IBRS_ALL) ||
+	    (cpu_has(c, X86_FEATURE_AUTOIBRS) &&
+	     !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) {
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 		if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
 		    !(ia32_cap & ARCH_CAP_PBRSB_NO))
@@ -1441,6 +1432,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	    boot_cpu_has(X86_FEATURE_AVX))
 		setup_force_cpu_bug(X86_BUG_GDS);
 
+	if (vulnerable_to_rfds(ia32_cap))
+		setup_force_cpu_bug(X86_BUG_RFDS);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
@@ -1589,8 +1583,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 		cpu_parse_early_param();
 
+		cpu_init_topology(c);
+
 		if (this_cpu->c_early_init)
 			this_cpu->c_early_init(c);
 
@@ -1601,10 +1598,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 			this_cpu->c_bsp_init(c);
 	} else {
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
+		cpu_init_topology(c);
 	}
 
-	get_cpu_address_sizes(c);
-
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
 	cpu_set_bug_bits(c);
@@ -1748,18 +1745,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_cpu_address_sizes(c);
 
-	if (c->cpuid_level >= 0x00000001) {
-		c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
-#ifdef CONFIG_X86_32
-# ifdef CONFIG_SMP
-		c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
-# else
-		c->topo.apicid = c->topo.initial_apicid;
-# endif
-#endif
-		c->topo.pkg_id = c->topo.initial_apicid;
-	}
-
 	get_model_name(c); /* Default name */
 
 	/*
@@ -1781,29 +1766,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 }
 
 /*
- * Validate that ACPI/mptables have the same information about the
- * effective APIC id and update the package map.
- */
-static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned int cpu = smp_processor_id();
-	u32 apicid;
-
-	apicid = apic->cpu_present_to_apicid(cpu);
-
-	if (apicid != c->topo.apicid) {
-		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
-		       cpu, apicid, c->topo.initial_apicid);
-	}
-	BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu));
-	BUG_ON(topology_update_die_map(c->topo.die_id, cpu));
-#else
-	c->topo.logical_pkg_id = 0;
-#endif
-}
-
-/*
  * This does the hard work of actually picking apart the CPU stuff...
  */
 static void identify_cpu(struct cpuinfo_x86 *c)
@@ -1816,11 +1778,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model = c->x86_stepping = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
-	c->x86_max_cores = 1;
-	c->x86_coreid_bits = 0;
-	c->topo.cu_id = 0xff;
-	c->topo.llc_id = BAD_APICID;
-	c->topo.l2c_id = BAD_APICID;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;
@@ -1839,17 +1796,14 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 
 	generic_identify(c);
 
+	cpu_parse_topology(c);
+
 	if (this_cpu->c_identify)
 		this_cpu->c_identify(c);
 
 	/* Clear/Set all flags overridden by options, after probe */
 	apply_forced_caps(c);
 
-#ifdef CONFIG_X86_64
-	c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
-#endif
-
-
 	/*
 	 * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
 	 * Hygon will clear it in ->c_init() below.
@@ -1903,10 +1857,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 				c->x86, c->x86_model);
 	}
 
-#ifdef CONFIG_X86_64
-	detect_ht(c);
-#endif
-
 	x86_init_rdrand(c);
 	setup_pku(c);
 	setup_cet(c);
@@ -1938,8 +1888,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	/* Init Machine Check Exception if available. */
 	mcheck_cpu_init(c);
 
-	select_idle_routine(c);
-
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
@@ -1998,7 +1946,6 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_32
 	enable_sep_cpu();
 #endif
-	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
 	update_srbds_msr();
 	if (boot_cpu_has_bug(X86_BUG_GDS))
@@ -2050,6 +1997,7 @@ DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.top_of_stack	= TOP_OF_INIT_STACK,
 };
 EXPORT_PER_CPU_SYMBOL(pcpu_hot);
+EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
@@ -2067,10 +2015,8 @@ static void wrmsrl_cstar(unsigned long val)
 		wrmsrl(MSR_CSTAR, val);
 }
 
-/* May not be marked __init: used by software suspend */
-void syscall_init(void)
+static inline void idt_syscall_init(void)
 {
-	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
 	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 	if (ia32_enabled()) {
@@ -2104,6 +2050,23 @@ void syscall_init(void)
 	       X86_EFLAGS_AC|X86_EFLAGS_ID);
 }
 
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
+{
+	/* The default user and kernel segments */
+	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
+
+	/*
+	 * Except the IA32_STAR MSR, there is NO need to setup SYSCALL and
+	 * SYSENTER MSRs for FRED, because FRED uses the ring 3 FRED
+	 * entrypoint for SYSCALL and SYSENTER, and ERETU is the only legit
+	 * instruction to return to ring 3 (both sysexit and sysret cause
+	 * #UD when FRED is enabled).
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
+		idt_syscall_init();
+}
+
 #else	/* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
@@ -2207,8 +2170,9 @@ void cpu_init_exception_handling(void)
 	/* paranoid_entry() gets the CPU number from the GDT */
 	setup_getcpu(cpu);
 
-	/* IST vectors need TSS to be set up. */
-	tss_setup_ist(tss);
+	/* For IDT mode, IST vectors need to be set in TSS. */
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
+		tss_setup_ist(tss);
 	tss_setup_io_bitmap(tss);
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 
@@ -2217,8 +2181,10 @@ void cpu_init_exception_handling(void)
 	/* GHCB needs to be setup to handle #VC. */
 	setup_ghcb();
 
-	/* Finally load the IDT */
-	load_current_idt();
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		cpu_init_fred_exceptions();
+	else
+		load_current_idt();
 }
 
 /*
@@ -2343,11 +2309,13 @@ void __init arch_cpu_finalize_init(void)
 {
 	identify_boot_cpu();
 
+	select_idle_routine();
+
 	/*
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings);
+	cpu_smt_set_num_threads(__max_threads_per_core, __max_threads_per_core);
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 885281ae79a5..ea9e07d57c8d 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -2,6 +2,11 @@
 #ifndef ARCH_X86_CPU_H
 #define ARCH_X86_CPU_H
 
+#include <asm/cpu.h>
+#include <asm/topology.h>
+
+#include "topology.h"
+
 /* attempt to consolidate cpu attributes */
 struct cpu_dev {
 	const char	*c_vendor;
@@ -71,14 +76,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
 
-extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
-extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
-extern int detect_extended_topology(struct cpuinfo_x86 *c);
-extern int detect_ht_early(struct cpuinfo_x86 *c);
-extern void detect_ht(struct cpuinfo_x86 *c);
 extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
 
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c);
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id);
 void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
@@ -96,4 +96,5 @@ static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode)
 	       mode == SPECTRE_V2_EIBRS_RETPOLINE ||
 	       mode == SPECTRE_V2_EIBRS_LFENCE;
 }
+
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index e462c1d3800a..b7174209d855 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -82,6 +82,8 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
 	{ X86_FEATURE_SHSTK,			X86_FEATURE_XSAVES    },
+	{ X86_FEATURE_FRED,			X86_FEATURE_LKGS      },
+	{ X86_FEATURE_FRED,			X86_FEATURE_WRMSRNS   },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index 0c179d684b3b..3baf3e435834 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -5,6 +5,8 @@
 #include <asm/apic.h>
 #include <asm/processor.h>
 
+#include "cpu.h"
+
 static int cpu_debug_show(struct seq_file *m, void *p)
 {
 	unsigned long cpu = (unsigned long)m->private;
@@ -24,9 +26,12 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	seq_printf(m, "logical_die_id:      %u\n", c->topo.logical_die_id);
 	seq_printf(m, "llc_id:              %u\n", c->topo.llc_id);
 	seq_printf(m, "l2c_id:              %u\n", c->topo.l2c_id);
-	seq_printf(m, "max_cores:           %u\n", c->x86_max_cores);
-	seq_printf(m, "max_die_per_pkg:     %u\n", __max_die_per_package);
-	seq_printf(m, "smp_num_siblings:    %u\n", smp_num_siblings);
+	seq_printf(m, "amd_node_id:         %u\n", c->topo.amd_node_id);
+	seq_printf(m, "amd_nodes_per_pkg:   %u\n", topology_amd_nodes_per_pkg());
+	seq_printf(m, "num_threads:         %u\n", __num_threads_per_package);
+	seq_printf(m, "num_cores:           %u\n", __num_cores_per_package);
+	seq_printf(m, "max_dies_per_pkg:    %u\n", __max_dies_per_package);
+	seq_printf(m, "max_threads_per_core:%u\n", __max_threads_per_core);
 	return 0;
 }
 
@@ -42,12 +47,48 @@ static const struct file_operations dfs_cpu_ops = {
 	.release	= single_release,
 };
 
+static int dom_debug_show(struct seq_file *m, void *p)
+{
+	static const char *domain_names[TOPO_MAX_DOMAIN] = {
+		[TOPO_SMT_DOMAIN]	= "Thread",
+		[TOPO_CORE_DOMAIN]	= "Core",
+		[TOPO_MODULE_DOMAIN]	= "Module",
+		[TOPO_TILE_DOMAIN]	= "Tile",
+		[TOPO_DIE_DOMAIN]	= "Die",
+		[TOPO_DIEGRP_DOMAIN]	= "DieGrp",
+		[TOPO_PKG_DOMAIN]	= "Package",
+	};
+	unsigned int dom, nthreads = 1;
+
+	for (dom = 0; dom < TOPO_MAX_DOMAIN; dom++) {
+		nthreads *= x86_topo_system.dom_size[dom];
+		seq_printf(m, "domain: %-10s shift: %u dom_size: %5u max_threads: %5u\n",
+			   domain_names[dom], x86_topo_system.dom_shifts[dom],
+			   x86_topo_system.dom_size[dom], nthreads);
+	}
+	return 0;
+}
+
+static int dom_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dom_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_dom_ops = {
+	.open		= dom_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static __init int cpu_init_debugfs(void)
 {
 	struct dentry *dir, *base = debugfs_create_dir("topo", arch_debugfs_dir);
 	unsigned long id;
 	char name[24];
 
+	debugfs_create_file("domains", 0444, base, NULL, &dfs_dom_ops);
+
 	dir = debugfs_create_dir("cpus", base);
 	for_each_possible_cpu(id) {
 		sprintf(name, "%lu", id);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index f0cd95502faa..c5191b06f9f2 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -18,14 +18,6 @@
 
 #include "cpu.h"
 
-#define APICID_SOCKET_ID_BIT 6
-
-/*
- * nodes_per_socket: Stores the number of nodes per socket.
- * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
- */
-static u32 nodes_per_socket = 1;
-
 #ifdef CONFIG_NUMA
 /*
  * To workaround broken NUMA config.  Read the comment in
@@ -49,80 +41,6 @@ static int nearby_node(int apicid)
 }
 #endif
 
-static void hygon_get_topology_early(struct cpuinfo_x86 *c)
-{
-	if (cpu_has(c, X86_FEATURE_TOPOEXT))
-		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
-}
-
-/*
- * Fixup core topology information for
- * (1) Hygon multi-node processors
- *     Assumption: Number of cores in each internal node is the same.
- * (2) Hygon processors supporting compute units
- */
-static void hygon_get_topology(struct cpuinfo_x86 *c)
-{
-	/* get information required for multi-node processors */
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		int err;
-		u32 eax, ebx, ecx, edx;
-
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-
-		c->topo.die_id  = ecx & 0xff;
-
-		c->topo.core_id = ebx & 0xff;
-
-		if (smp_num_siblings > 1)
-			c->x86_max_cores /= smp_num_siblings;
-
-		/*
-		 * In case leaf B is available, use it to derive
-		 * topology information.
-		 */
-		err = detect_extended_topology(c);
-		if (!err)
-			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
-
-		/*
-		 * Socket ID is ApicId[6] for the processors with model <= 0x3
-		 * when running on host.
-		 */
-		if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3)
-			c->topo.pkg_id = c->topo.apicid >> APICID_SOCKET_ID_BIT;
-
-		cacheinfo_hygon_init_llc_id(c);
-	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
-		u64 value;
-
-		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		c->topo.die_id = value & 7;
-		c->topo.llc_id = c->topo.die_id;
-	} else
-		return;
-
-	if (nodes_per_socket > 1)
-		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-}
-
-/*
- * On Hygon setup the lower bits of the APIC id distinguish the cores.
- * Assumes number of cores is a power of two.
- */
-static void hygon_detect_cmp(struct cpuinfo_x86 *c)
-{
-	unsigned int bits;
-
-	bits = c->x86_coreid_bits;
-	/* Low order bits define the core id (index of core in socket) */
-	c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
-	/* Convert the initial APIC ID into the socket ID */
-	c->topo.pkg_id = c->topo.initial_apicid >> bits;
-	/* Use package ID also for last level cache */
-	c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
-}
-
 static void srat_detect_node(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_NUMA
@@ -173,32 +91,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void early_init_hygon_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
-	unsigned int bits, ecx;
-
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level < 0x80000008)
-		return;
-
-	ecx = cpuid_ecx(0x80000008);
-
-	c->x86_max_cores = (ecx & 0xff) + 1;
-
-	/* CPU telling us the core id bits shift? */
-	bits = (ecx >> 12) & 0xF;
-
-	/* Otherwise recompute */
-	if (bits == 0) {
-		while ((1 << bits) < c->x86_max_cores)
-			bits++;
-	}
-
-	c->x86_coreid_bits = bits;
-#endif
-}
-
 static void bsp_init_hygon(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -212,18 +104,6 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_MWAITX))
 		use_mwaitx_delay();
 
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		u32 ecx;
-
-		ecx = cpuid_ecx(0x8000001e);
-		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
-	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
-		u64 value;
-
-		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
-	}
-
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
 	    !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) {
 		/*
@@ -242,8 +122,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c)
 {
 	u32 dummy;
 
-	early_init_hygon_mc(c);
-
 	set_cpu_cap(c, X86_FEATURE_K8);
 
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
@@ -284,8 +162,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c)
 	 * we can set it unconditionally.
 	 */
 	set_cpu_cap(c, X86_FEATURE_VMMCALL);
-
-	hygon_get_topology_early(c);
 }
 
 static void init_hygon(struct cpuinfo_x86 *c)
@@ -302,9 +178,6 @@ static void init_hygon(struct cpuinfo_x86 *c)
 
 	set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
-	/* get apicid instead of initial apic id from cpuid */
-	c->topo.apicid = read_apic_id();
-
 	/*
 	 * XXX someone from Hygon needs to confirm this DTRT
 	 *
@@ -316,8 +189,6 @@ static void init_hygon(struct cpuinfo_x86 *c)
 
 	cpu_detect_cache_sizes(c);
 
-	hygon_detect_cmp(c);
-	hygon_get_topology(c);
 	srat_detect_node(c);
 
 	init_hygon_cacheinfo(c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a927a8fc9624..be30d7fa2e66 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	return false;
 }
 
+#define MSR_IA32_TME_ACTIVATE		0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
+#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128	0
+
+#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED			0
+#define MKTME_DISABLED			1
+#define MKTME_UNINITIALIZED		2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+	u64 tme_activate, tme_policy, tme_crypto_algs;
+	int keyid_bits = 0, nr_keyids = 0;
+	static u64 tme_activate_cpu0 = 0;
+
+	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+	if (mktme_status != MKTME_UNINITIALIZED) {
+		if (tme_activate != tme_activate_cpu0) {
+			/* Broken BIOS? */
+			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+			pr_err_once("x86/tme: MKTME is not usable\n");
+			mktme_status = MKTME_DISABLED;
+
+			/* Proceed. We may need to exclude bits from x86_phys_bits. */
+		}
+	} else {
+		tme_activate_cpu0 = tme_activate;
+	}
+
+	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+		pr_info_once("x86/tme: not enabled by BIOS\n");
+		mktme_status = MKTME_DISABLED;
+		return;
+	}
+
+	if (mktme_status != MKTME_UNINITIALIZED)
+		goto detect_keyid_bits;
+
+	pr_info("x86/tme: enabled by BIOS\n");
+
+	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+				tme_crypto_algs);
+		mktme_status = MKTME_DISABLED;
+	}
+detect_keyid_bits:
+	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+	nr_keyids = (1UL << keyid_bits) - 1;
+	if (nr_keyids) {
+		pr_info_once("x86/mktme: enabled by BIOS\n");
+		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+	} else {
+		pr_info_once("x86/mktme: disabled by BIOS\n");
+	}
+
+	if (mktme_status == MKTME_UNINITIALIZED) {
+		/* MKTME is usable */
+		mktme_status = MKTME_ENABLED;
+	}
+
+	/*
+	 * KeyID bits effectively lower the number of physical address
+	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
+	 */
+	c->x86_phys_bits -= keyid_bits;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -317,11 +401,11 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	check_memory_type_self_snoop_errata(c);
 
 	/*
-	 * Get the number of SMT siblings early from the extended topology
-	 * leaf, if available. Otherwise try the legacy SMT detection.
+	 * Adjust the number of physical bits early because it affects the
+	 * valid bits of the MTRR mask registers.
 	 */
-	if (detect_extended_topology_early(c) < 0)
-		detect_ht_early(c);
+	if (cpu_has(c, X86_FEATURE_TME))
+		detect_tme_early(c);
 }
 
 static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -482,90 +566,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define MSR_IA32_TME_ACTIVATE		0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
-#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128	0
-
-#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED			0
-#define MKTME_DISABLED			1
-#define MKTME_UNINITIALIZED		2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
-	u64 tme_activate, tme_policy, tme_crypto_algs;
-	int keyid_bits = 0, nr_keyids = 0;
-	static u64 tme_activate_cpu0 = 0;
-
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
-	if (mktme_status != MKTME_UNINITIALIZED) {
-		if (tme_activate != tme_activate_cpu0) {
-			/* Broken BIOS? */
-			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
-			pr_err_once("x86/tme: MKTME is not usable\n");
-			mktme_status = MKTME_DISABLED;
-
-			/* Proceed. We may need to exclude bits from x86_phys_bits. */
-		}
-	} else {
-		tme_activate_cpu0 = tme_activate;
-	}
-
-	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
-		pr_info_once("x86/tme: not enabled by BIOS\n");
-		mktme_status = MKTME_DISABLED;
-		return;
-	}
-
-	if (mktme_status != MKTME_UNINITIALIZED)
-		goto detect_keyid_bits;
-
-	pr_info("x86/tme: enabled by BIOS\n");
-
-	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
-	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
-		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
-	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
-	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
-		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
-				tme_crypto_algs);
-		mktme_status = MKTME_DISABLED;
-	}
-detect_keyid_bits:
-	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
-	nr_keyids = (1UL << keyid_bits) - 1;
-	if (nr_keyids) {
-		pr_info_once("x86/mktme: enabled by BIOS\n");
-		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
-	} else {
-		pr_info_once("x86/mktme: disabled by BIOS\n");
-	}
-
-	if (mktme_status == MKTME_UNINITIALIZED) {
-		/* MKTME is usable */
-		mktme_status = MKTME_ENABLED;
-	}
-
-	/*
-	 * KeyID bits effectively lower the number of physical address
-	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
-	 */
-	c->x86_phys_bits -= keyid_bits;
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -603,24 +603,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	intel_workarounds(c);
 
-	/*
-	 * Detect the extended topology information if available. This
-	 * will reinitialise the initial_apicid which will be used
-	 * in init_intel_cacheinfo()
-	 */
-	detect_extended_topology(c);
-
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		detect_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
-
 	init_intel_cacheinfo(c);
 
 	if (c->cpuid_level > 9) {
@@ -702,9 +684,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_ia32_feat_ctl(c);
 
-	if (cpu_has(c, X86_FEATURE_TME))
-		detect_tme(c);
-
 	init_intel_misc_features(c);
 
 	split_lock_init();
diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c
index 0771a905b286..5be2b1790282 100644
--- a/arch/x86/kernel/cpu/intel_pconfig.c
+++ b/arch/x86/kernel/cpu/intel_pconfig.c
@@ -7,6 +7,8 @@
  * Author:
  *	Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
  */
+#include <linux/bug.h>
+#include <linux/limits.h>
 
 #include <asm/cpufeature.h>
 #include <asm/intel_pconfig.h>
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 2b46eb0fdf3a..9a0133ef7e20 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1231,7 +1231,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
 		return -ENODEV;
 
 	if (is_shared_bank(bank)) {
-		nb = node_to_amd_nb(topology_die_id(cpu));
+		nb = node_to_amd_nb(topology_amd_node_id(cpu));
 
 		/* threshold descriptor already initialized on this node? */
 		if (nb && nb->bank4) {
@@ -1335,7 +1335,7 @@ static void threshold_remove_bank(struct threshold_bank *bank)
 		 * The last CPU on this node using the shared bank is going
 		 * away, remove that bank now.
 		 */
-		nb = node_to_amd_nb(topology_die_id(smp_processor_id()));
+		nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id()));
 		nb->bank4 = NULL;
 	}
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index bc39252bc54f..b5cc557cfc37 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -46,6 +46,7 @@
 #include <linux/hardirq.h>
 #include <linux/kexec.h>
 
+#include <asm/fred.h>
 #include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -2166,6 +2167,31 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check)
 	exc_machine_check_user(regs);
 	local_db_restore(dr7);
 }
+
+#ifdef CONFIG_X86_FRED
+/*
+ * When occurred on different ring level, i.e., from user or kernel
+ * context, #MCE needs to be handled on different stack: User #MCE
+ * on current task stack, while kernel #MCE on a dedicated stack.
+ *
+ * This is exactly how FRED event delivery invokes an exception
+ * handler: ring 3 event on level 0 stack, i.e., current task stack;
+ * ring 0 event on the #MCE dedicated stack specified in the
+ * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED machine check entry
+ * stub doesn't do stack switch.
+ */
+DEFINE_FREDENTRY_MCE(exc_machine_check)
+{
+	unsigned long dr7;
+
+	dr7 = local_db_save();
+	if (user_mode(regs))
+		exc_machine_check_user(regs);
+	else
+		exc_machine_check_kernel(regs);
+	local_db_restore(dr7);
+}
+#endif
 #else
 /* 32bit unified entry point */
 DEFINE_IDTENTRY_RAW(exc_machine_check)
@@ -2431,7 +2457,7 @@ static void mce_enable_ce(void *all)
 		__mcheck_cpu_init_timer();
 }
 
-static struct bus_type mce_subsys = {
+static const struct bus_type mce_subsys = {
 	.name		= "machinecheck",
 	.dev_name	= "machinecheck",
 };
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 72f0695c3dc1..94953d749475 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -430,11 +430,9 @@ static void trigger_thr_int(void *info)
 
 static u32 get_nbc_for_node(int node_id)
 {
-	struct cpuinfo_x86 *c = &boot_cpu_data;
 	u32 cores_per_node;
 
-	cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket();
-
+	cores_per_node = topology_num_threads_per_package() / topology_amd_nodes_per_pkg();
 	return cores_per_node * node_id;
 }
 
@@ -543,8 +541,8 @@ static void do_inject(void)
 	if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
 	    b == 4 &&
 	    boot_cpu_data.x86 < 0x17) {
-		toggle_nb_mca_mst_cpu(topology_die_id(cpu));
-		cpu = get_nbc_for_node(topology_die_id(cpu));
+		toggle_nb_mca_mst_cpu(topology_amd_node_id(cpu));
+		cpu = get_nbc_for_node(topology_amd_node_id(cpu));
 	}
 
 	cpus_read_lock();
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 857e608af641..5f0414452b67 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -641,7 +641,7 @@ static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c)
 {
 	u64 llc_size = c->x86_cache_size * 1024ULL;
 
-	do_div(llc_size, c->x86_max_cores);
+	do_div(llc_size, topology_num_cores_per_package());
 	llc_size_per_core = (unsigned int)llc_size;
 }
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 01fa06dd06b6..45e0e70e238c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -539,19 +539,18 @@ static void __init ms_hyperv_init_platform(void)
 	 */
 	x86_platform.apic_post_init = hyperv_init;
 	hyperv_setup_mmu_ops();
-	/* Setup the IDT for hypervisor callback */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback);
 
-	/* Setup the IDT for reenlightenment notifications */
+	/* Install system interrupt handler for hypervisor callback */
+	sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
+
+	/* Install system interrupt handler for reenlightenment notifications */
 	if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) {
-		alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
-				asm_sysvec_hyperv_reenlightenment);
+		sysvec_install(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
 	}
 
-	/* Setup the IDT for stimer0 */
+	/* Install system interrupt handler for stimer0 */
 	if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) {
-		alloc_intr_gate(HYPERV_STIMER0_VECTOR,
-				asm_sysvec_hyperv_stimer0);
+		sysvec_install(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0);
 	}
 
 # ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d3524778a545..422a4ddc2ab7 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -108,6 +108,9 @@ static inline void k8_check_syscfg_dram_mod_en(void)
 	      (boot_cpu_data.x86 >= 0x0f)))
 		return;
 
+	if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return;
+
 	rdmsr(MSR_AMD64_SYSCFG, lo, hi);
 	if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) {
 		pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]"
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 26a427fa84ea..eeac00d20926 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -6,6 +6,7 @@
  * Authors: Fenghua Yu <fenghua.yu@intel.com>,
  *          H. Peter Anvin <hpa@linux.intel.com>
  */
+#include <linux/printk.h>
 
 #include <asm/processor.h>
 #include <asm/archrandom.h>
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 19e0681f0435..83e40341583e 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -16,6 +16,7 @@
 
 #define pr_fmt(fmt)	"resctrl: " fmt
 
+#include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/cacheinfo.h>
@@ -25,8 +26,15 @@
 #include <asm/resctrl.h>
 #include "internal.h"
 
-/* Mutex to protect rdtgroup access. */
-DEFINE_MUTEX(rdtgroup_mutex);
+/*
+ * rdt_domain structures are kfree()d when their last CPU goes offline,
+ * and allocated when the first CPU in a new domain comes online.
+ * The rdt_resource's domain list is updated when this happens. Readers of
+ * the domain list must either take cpus_read_lock(), or rely on an RCU
+ * read-side critical section, to avoid observing concurrent modification.
+ * All writers take this mutex:
+ */
+static DEFINE_MUTEX(domain_list_lock);
 
 /*
  * The cached resctrl_pqr_state is strictly per CPU and can never be
@@ -136,15 +144,15 @@ static inline void cache_alloc_hsw_probe(void)
 {
 	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3];
 	struct rdt_resource *r  = &hw_res->r_resctrl;
-	u32 l, h, max_cbm = BIT_MASK(20) - 1;
+	u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0;
 
-	if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0))
+	if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
 		return;
 
-	rdmsr(MSR_IA32_L3_CBM_BASE, l, h);
+	rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
 
 	/* If all the bits were set in MSR, return success */
-	if (l != max_cbm)
+	if (l3_cbm_0 != max_cbm)
 		return;
 
 	hw_res->num_closid = 4;
@@ -231,9 +239,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	union cpuid_0x10_3_eax eax;
-	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx, subleaf;
+	u32 eax, ebx, ecx, edx, subleaf;
 
 	/*
 	 * Query CPUID_Fn80000020_EDX_x01 for MBA and
@@ -241,9 +247,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	 */
 	subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 :  1;
 
-	cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full);
-	hw_res->num_closid = edx.split.cos_max + 1;
-	r->default_ctrl = MAX_MBA_BW_AMD;
+	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
+	hw_res->num_closid = edx + 1;
+	r->default_ctrl = 1 << eax;
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
@@ -512,6 +518,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	struct rdt_domain *d;
 	int err;
 
+	lockdep_assert_held(&domain_list_lock);
+
 	d = rdt_find_domain(r, id, &add_pos);
 	if (IS_ERR(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
@@ -545,11 +553,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	list_add_tail(&d->list, add_pos);
+	list_add_tail_rcu(&d->list, add_pos);
 
 	err = resctrl_online_domain(r, d);
 	if (err) {
-		list_del(&d->list);
+		list_del_rcu(&d->list);
+		synchronize_rcu();
 		domain_free(hw_dom);
 	}
 }
@@ -560,6 +569,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	struct rdt_hw_domain *hw_dom;
 	struct rdt_domain *d;
 
+	lockdep_assert_held(&domain_list_lock);
+
 	d = rdt_find_domain(r, id, NULL);
 	if (IS_ERR_OR_NULL(d)) {
 		pr_warn("Couldn't find cache id for CPU %d\n", cpu);
@@ -570,7 +581,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
 		resctrl_offline_domain(r, d);
-		list_del(&d->list);
+		list_del_rcu(&d->list);
+		synchronize_rcu();
 
 		/*
 		 * rdt_domain "d" is going to be freed below, so clear
@@ -582,73 +594,47 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 		return;
 	}
-
-	if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
-		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
-			cancel_delayed_work(&d->mbm_over);
-			mbm_setup_overflow_handler(d, 0);
-		}
-		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
-		    has_busy_rmid(r, d)) {
-			cancel_delayed_work(&d->cqm_limbo);
-			cqm_setup_limbo_handler(d, 0);
-		}
-	}
 }
 
 static void clear_closid_rmid(int cpu)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
 
-	state->default_closid = 0;
-	state->default_rmid = 0;
-	state->cur_closid = 0;
-	state->cur_rmid = 0;
-	wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
+	state->default_closid = RESCTRL_RESERVED_CLOSID;
+	state->default_rmid = RESCTRL_RESERVED_RMID;
+	state->cur_closid = RESCTRL_RESERVED_CLOSID;
+	state->cur_rmid = RESCTRL_RESERVED_RMID;
+	wrmsr(MSR_IA32_PQR_ASSOC, RESCTRL_RESERVED_RMID,
+	      RESCTRL_RESERVED_CLOSID);
 }
 
-static int resctrl_online_cpu(unsigned int cpu)
+static int resctrl_arch_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
-	mutex_lock(&rdtgroup_mutex);
+	mutex_lock(&domain_list_lock);
 	for_each_capable_rdt_resource(r)
 		domain_add_cpu(cpu, r);
-	/* The cpu is set in default rdtgroup after online. */
-	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	mutex_unlock(&domain_list_lock);
+
 	clear_closid_rmid(cpu);
-	mutex_unlock(&rdtgroup_mutex);
+	resctrl_online_cpu(cpu);
 
 	return 0;
 }
 
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
-{
-	struct rdtgroup *cr;
-
-	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) {
-			break;
-		}
-	}
-}
-
-static int resctrl_offline_cpu(unsigned int cpu)
+static int resctrl_arch_offline_cpu(unsigned int cpu)
 {
-	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 
-	mutex_lock(&rdtgroup_mutex);
+	resctrl_offline_cpu(cpu);
+
+	mutex_lock(&domain_list_lock);
 	for_each_capable_rdt_resource(r)
 		domain_remove_cpu(cpu, r);
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
-			clear_childcpus(rdtgrp, cpu);
-			break;
-		}
-	}
+	mutex_unlock(&domain_list_lock);
+
 	clear_closid_rmid(cpu);
-	mutex_unlock(&rdtgroup_mutex);
 
 	return 0;
 }
@@ -968,7 +954,8 @@ static int __init resctrl_late_init(void)
 
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
-				  resctrl_online_cpu, resctrl_offline_cpu);
+				  resctrl_arch_online_cpu,
+				  resctrl_arch_offline_cpu);
 	if (state < 0)
 		return state;
 
@@ -992,8 +979,14 @@ late_initcall(resctrl_late_init);
 
 static void __exit resctrl_exit(void)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
 	cpuhp_remove_state(rdt_online);
+
 	rdtgroup_exit();
+
+	if (r->mon_capable)
+		rdt_put_mon_l3_config();
 }
 
 __exitcall(resctrl_exit);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index beccb0e87ba7..7997b47743a2 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -19,6 +19,8 @@
 #include <linux/kernfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/tick.h>
+
 #include "internal.h"
 
 /*
@@ -210,6 +212,9 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	struct rdt_domain *d;
 	unsigned long dom_id;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
 		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
@@ -314,6 +319,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	struct rdt_domain *d;
 	u32 idx;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -379,11 +387,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 		return -EINVAL;
 	buf[nbytes - 1] = '\0';
 
-	cpus_read_lock();
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
 		rdtgroup_kn_unlock(of->kn);
-		cpus_read_unlock();
 		return -ENOENT;
 	}
 	rdt_last_cmd_clear();
@@ -445,7 +451,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 out:
 	rdt_staged_configs_clear();
 	rdtgroup_kn_unlock(of->kn);
-	cpus_read_unlock();
 	return ret ?: nbytes;
 }
 
@@ -465,6 +470,9 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 	bool sep = false;
 	u32 ctrl_val;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	seq_printf(s, "%*s:", max_name_width, schema->name);
 	list_for_each_entry(dom, &r->domains, list) {
 		if (sep)
@@ -522,12 +530,24 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
+static int smp_mon_event_count(void *arg)
+{
+	mon_event_count(arg);
+
+	return 0;
+}
+
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first)
 {
+	int cpu;
+
+	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	/*
-	 * setup the parameters to send to the IPI to read the data.
+	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
@@ -535,8 +555,26 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->d = d;
 	rr->val = 0;
 	rr->first = first;
+	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+	if (IS_ERR(rr->arch_mon_ctx)) {
+		rr->err = -EINVAL;
+		return;
+	}
+
+	cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);
+
+	/*
+	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
+	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
+	 * MPAM's resctrl_arch_rmid_read() is unable to read the
+	 * counters on some platforms if its called in IRQ context.
+	 */
+	if (tick_nohz_full_cpu(cpu))
+		smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	else
+		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
-	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a4f1aa15f0a2..c99f26ebe7a6 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -7,6 +7,9 @@
 #include <linux/kernfs.h>
 #include <linux/fs_context.h>
 #include <linux/jump_label.h>
+#include <linux/tick.h>
+
+#include <asm/resctrl.h>
 
 #define L3_QOS_CDP_ENABLE		0x01ULL
 
@@ -18,7 +21,6 @@
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
-#define MAX_MBA_BW_AMD			0x800
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
@@ -54,6 +56,46 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
+/**
+ * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
+ *			        aren't marked nohz_full
+ * @mask:	The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
+ *
+ * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
+ * CPUs that don't use nohz_full, these are preferred. Pass
+ * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
+ *
+ * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
+ */
+static inline unsigned int
+cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
+{
+	unsigned int cpu, hk_cpu;
+
+	if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
+		cpu = cpumask_any(mask);
+	else
+		cpu = cpumask_any_but(mask, exclude_cpu);
+
+	if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+		return cpu;
+
+	/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
+	if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
+		return cpu;
+
+	/* Try to find a CPU that isn't nohz_full to use in preference */
+	hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+	if (hk_cpu == exclude_cpu)
+		hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
+
+	if (hk_cpu < nr_cpu_ids)
+		cpu = hk_cpu;
+
+	return cpu;
+}
+
 struct rdt_fs_context {
 	struct kernfs_fs_context	kfc;
 	bool				enable_cdpl2;
@@ -69,9 +111,6 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
 	return container_of(kfc, struct rdt_fs_context, kfc);
 }
 
-DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
-DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
-
 /**
  * struct mon_evt - Entry in the event list of a resource
  * @evtid:		event id
@@ -112,12 +151,12 @@ struct rmid_read {
 	bool			first;
 	int			err;
 	u64			val;
+	void			*arch_mon_ctx;
 };
 
-extern bool rdt_alloc_capable;
-extern bool rdt_mon_capable;
 extern unsigned int rdt_mon_features;
 extern struct list_head resctrl_schema_all;
+extern bool resctrl_mounted;
 
 enum rdt_group_type {
 	RDTCTRL_GROUP = 0,
@@ -296,14 +335,10 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
- * @delta_bw:	Difference between the current and previous bandwidth
- * @delta_comp:	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
 	u64	prev_bw_bytes;
 	u32	prev_bw;
-	u32	delta_bw;
-	bool	delta_comp;
 };
 
 /**
@@ -395,6 +430,8 @@ struct rdt_parse_data {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
+ * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
+ *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -409,6 +446,7 @@ struct rdt_hw_resource {
 				 struct rdt_resource *r);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
+	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
@@ -426,8 +464,6 @@ extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
-DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-
 extern struct dentry *debugfs_resctrl;
 
 enum resctrl_res_level {
@@ -543,9 +579,10 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
 void closid_free(int closid);
-int alloc_rmid(void);
-void free_rmid(u32 rmid);
+int alloc_rmid(u32 closid);
+void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
+void __exit rdt_put_mon_l3_config(void);
 bool __init rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
@@ -553,17 +590,21 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
 		    int evtid, int first);
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
-				unsigned long delay_ms);
+				unsigned long delay_ms,
+				int exclude_cpu);
 void mbm_handle_overflow(struct work_struct *work);
 void __init intel_rdt_mbm_apply_quirk(void);
 bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+			     int exclude_cpu);
 void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
+bool has_busy_rmid(struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 void __init thread_throttle_mode_init(void);
 void __init mbm_config_rftype_init(const char *config);
 void rdt_staged_configs_clear(void);
+bool closid_allocated(unsigned int closid);
+int resctrl_find_cleanest_closid(void);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f136ac046851..c34a35ec0f03 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -15,6 +15,7 @@
  * Software Developer Manual June 2016, volume 3, section 17.17.
  */
 
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -24,7 +25,20 @@
 
 #include "internal.h"
 
+/**
+ * struct rmid_entry - dirty tracking for all RMID.
+ * @closid:	The CLOSID for this entry.
+ * @rmid:	The RMID for this entry.
+ * @busy:	The number of domains with cached data using this RMID.
+ * @list:	Member of the rmid_free_lru list when busy == 0.
+ *
+ * Depending on the architecture the correct monitor is accessed using
+ * both @closid and @rmid, or @rmid only.
+ *
+ * Take the rdtgroup_mutex when accessing.
+ */
 struct rmid_entry {
+	u32				closid;
 	u32				rmid;
 	int				busy;
 	struct list_head		list;
@@ -38,6 +52,13 @@ struct rmid_entry {
 static LIST_HEAD(rmid_free_lru);
 
 /*
+ * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
+ *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
+ *     Indexed by CLOSID. Protected by rdtgroup_mutex.
+ */
+static u32 *closid_num_dirty_rmid;
+
+/*
  * @rmid_limbo_count - count of currently unused but (potentially)
  *     dirty RMIDs.
  *     This counts RMIDs that no one is currently using but that
@@ -136,12 +157,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
 	return val;
 }
 
-static inline struct rmid_entry *__rmid_entry(u32 rmid)
+/*
+ * x86 and arm64 differ in their handling of monitoring.
+ * x86's RMID are independent numbers, there is only one source of traffic
+ * with an RMID value of '1'.
+ * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
+ * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
+ * value is no longer unique.
+ * To account for this, resctrl uses an index. On x86 this is just the RMID,
+ * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
+ *
+ * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
+ * must accept an attempt to read every index.
+ */
+static inline struct rmid_entry *__rmid_entry(u32 idx)
 {
 	struct rmid_entry *entry;
+	u32 closid, rmid;
+
+	entry = &rmid_ptrs[idx];
+	resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
 
-	entry = &rmid_ptrs[rmid];
-	WARN_ON(entry->rmid != rmid);
+	WARN_ON_ONCE(entry->closid != closid);
+	WARN_ON_ONCE(entry->rmid != rmid);
 
 	return entry;
 }
@@ -190,7 +228,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
-			     u32 rmid, enum resctrl_event_id eventid)
+			     u32 unused, u32 rmid,
+			     enum resctrl_event_id eventid)
 {
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
@@ -230,7 +269,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 }
 
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
+			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val, void *ignored)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
@@ -238,6 +278,8 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	u64 msr_val, chunks;
 	int ret;
 
+	resctrl_arch_rmid_read_context_check();
+
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;
 
@@ -260,6 +302,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	return 0;
 }
 
+static void limbo_release_entry(struct rmid_entry *entry)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rmid_limbo_count--;
+	list_add_tail(&entry->list, &rmid_free_lru);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]--;
+}
+
 /*
  * Check the RMIDs that are marked as busy for this domain. If the
  * reported LLC occupancy is below the threshold clear the busy bit and
@@ -269,11 +322,20 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 void __check_limbo(struct rdt_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	struct rmid_entry *entry;
-	u32 crmid = 1, nrmid;
+	u32 idx, cur_idx = 1;
+	void *arch_mon_ctx;
 	bool rmid_dirty;
 	u64 val = 0;
 
+	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
+	if (IS_ERR(arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(arch_mon_ctx));
+		return;
+	}
+
 	/*
 	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
 	 * are marked as busy for occupancy < threshold. If the occupancy
@@ -281,53 +343,125 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 	 * RMID and move it to the free list when the counter reaches 0.
 	 */
 	for (;;) {
-		nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid);
-		if (nrmid >= r->num_rmid)
+		idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
+		if (idx >= idx_limit)
 			break;
 
-		entry = __rmid_entry(nrmid);
-
-		if (resctrl_arch_rmid_read(r, d, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val)) {
+		entry = __rmid_entry(idx);
+		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
+					   QOS_L3_OCCUP_EVENT_ID, &val,
+					   arch_mon_ctx)) {
 			rmid_dirty = true;
 		} else {
 			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
 		}
 
 		if (force_free || !rmid_dirty) {
-			clear_bit(entry->rmid, d->rmid_busy_llc);
-			if (!--entry->busy) {
-				rmid_limbo_count--;
-				list_add_tail(&entry->list, &rmid_free_lru);
-			}
+			clear_bit(idx, d->rmid_busy_llc);
+			if (!--entry->busy)
+				limbo_release_entry(entry);
 		}
-		crmid = nrmid + 1;
+		cur_idx = idx + 1;
 	}
+
+	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
 }
 
-bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d)
+bool has_busy_rmid(struct rdt_domain *d)
 {
-	return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid;
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+
+	return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
+}
+
+static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
+{
+	struct rmid_entry *itr;
+	u32 itr_idx, cmp_idx;
+
+	if (list_empty(&rmid_free_lru))
+		return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
+
+	list_for_each_entry(itr, &rmid_free_lru, list) {
+		/*
+		 * Get the index of this free RMID, and the index it would need
+		 * to be if it were used with this CLOSID.
+		 * If the CLOSID is irrelevant on this architecture, the two
+		 * index values are always the same on every entry and thus the
+		 * very first entry will be returned.
+		 */
+		itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
+		cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
+
+		if (itr_idx == cmp_idx)
+			return itr;
+	}
+
+	return ERR_PTR(-ENOSPC);
+}
+
+/**
+ * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
+ *                                  RMID are clean, or the CLOSID that has
+ *                                  the most clean RMID.
+ *
+ * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
+ * may not be able to allocate clean RMID. To avoid this the allocator will
+ * choose the CLOSID with the most clean RMID.
+ *
+ * When the CLOSID and RMID are independent numbers, the first free CLOSID will
+ * be returned.
+ */
+int resctrl_find_cleanest_closid(void)
+{
+	u32 cleanest_closid = ~0;
+	int i = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		return -EIO;
+
+	for (i = 0; i < closids_supported(); i++) {
+		int num_dirty;
+
+		if (closid_allocated(i))
+			continue;
+
+		num_dirty = closid_num_dirty_rmid[i];
+		if (num_dirty == 0)
+			return i;
+
+		if (cleanest_closid == ~0)
+			cleanest_closid = i;
+
+		if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
+			cleanest_closid = i;
+	}
+
+	if (cleanest_closid == ~0)
+		return -ENOSPC;
+
+	return cleanest_closid;
 }
 
 /*
- * As of now the RMIDs allocation is global.
- * However we keep track of which packages the RMIDs
- * are used to optimize the limbo list management.
+ * For MPAM the RMID value is not unique, and has to be considered with
+ * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
+ * allows all domains to be managed by a single free list.
+ * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
  */
-int alloc_rmid(void)
+int alloc_rmid(u32 closid)
 {
 	struct rmid_entry *entry;
 
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	if (list_empty(&rmid_free_lru))
-		return rmid_limbo_count ? -EBUSY : -ENOSPC;
+	entry = resctrl_find_free_rmid(closid);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
 
-	entry = list_first_entry(&rmid_free_lru,
-				 struct rmid_entry, list);
 	list_del(&entry->list);
-
 	return entry->rmid;
 }
 
@@ -335,47 +469,50 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rdt_domain *d;
-	int cpu, err;
-	u64 val = 0;
+	u32 idx;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
 
 	entry->busy = 0;
-	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
-		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			err = resctrl_arch_rmid_read(r, d, entry->rmid,
-						     QOS_L3_OCCUP_EVENT_ID,
-						     &val);
-			if (err || val <= resctrl_rmid_realloc_threshold)
-				continue;
-		}
-
 		/*
 		 * For the first limbo RMID in the domain,
 		 * setup up the limbo worker.
 		 */
-		if (!has_busy_rmid(r, d))
-			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
-		set_bit(entry->rmid, d->rmid_busy_llc);
+		if (!has_busy_rmid(d))
+			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
+						RESCTRL_PICK_ANY_CPU);
+		set_bit(idx, d->rmid_busy_llc);
 		entry->busy++;
 	}
-	put_cpu();
 
-	if (entry->busy)
-		rmid_limbo_count++;
-	else
-		list_add_tail(&entry->list, &rmid_free_lru);
+	rmid_limbo_count++;
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]++;
 }
 
-void free_rmid(u32 rmid)
+void free_rmid(u32 closid, u32 rmid)
 {
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
 	struct rmid_entry *entry;
 
-	if (!rmid)
-		return;
-
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	entry = __rmid_entry(rmid);
+	/*
+	 * Do not allow the default rmid to be free'd. Comparing by index
+	 * allows architectures that ignore the closid parameter to avoid an
+	 * unnecessary check.
+	 */
+	if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+						RESCTRL_RESERVED_RMID))
+		return;
+
+	entry = __rmid_entry(idx);
 
 	if (is_llc_occupancy_enabled())
 		add_rmid_to_limbo(entry);
@@ -383,33 +520,36 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
-				       enum resctrl_event_id evtid)
+static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
+				       u32 rmid, enum resctrl_event_id evtid)
 {
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+
 	switch (evtid) {
 	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[rmid];
+		return &d->mbm_total[idx];
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[rmid];
+		return &d->mbm_local[idx];
 	default:
 		return NULL;
 	}
 }
 
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	struct mbm_state *m;
 	u64 tval = 0;
 
 	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, rmid, rr->evtid);
+		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
 		return 0;
 	}
 
-	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
+	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
+					 &tval, rr->arch_mon_ctx);
 	if (rr->err)
 		return rr->err;
 
@@ -421,6 +561,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 /*
  * mbm_bw_count() - Update bw count from values previously read by
  *		    __mon_event_count().
+ * @closid:	The closid used to identify the cached mbm_state.
  * @rmid:	The rmid used to identify the cached mbm_state.
  * @rr:		The struct rmid_read populated by __mon_event_count().
  *
@@ -429,9 +570,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
  * __mon_event_count() is compared with the chunks value from the previous
  * invocation. This must be called once per second to maintain values in MBps.
  */
-static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	struct mbm_state *m = &rr->d->mbm_local[rmid];
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
 
 	cur_bytes = rr->val;
@@ -440,14 +582,11 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 
 	cur_bw = bytes / SZ_1M;
 
-	if (m->delta_comp)
-		m->delta_bw = abs(cur_bw - m->prev_bw);
-	m->delta_comp = false;
 	m->prev_bw = cur_bw;
 }
 
 /*
- * This is called via IPI to read the CQM/MBM counters
+ * This is scheduled by mon_event_read() to read the CQM/MBM counters
  * on a domain.
  */
 void mon_event_count(void *info)
@@ -459,7 +598,7 @@ void mon_event_count(void *info)
 
 	rdtgrp = rr->rgrp;
 
-	ret = __mon_event_count(rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -470,7 +609,8 @@ void mon_event_count(void *info)
 
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->mon.rmid, rr) == 0)
+			if (__mon_event_count(entry->closid, entry->mon.rmid,
+					      rr) == 0)
 				ret = 0;
 		}
 	}
@@ -520,9 +660,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 {
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
-	u32 cur_bw, delta_bw, user_bw;
 	struct rdt_resource *r_mba;
 	struct rdt_domain *dom_mba;
+	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
 
@@ -533,7 +673,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	pmbm_data = &dom_mbm->mbm_local[rmid];
+	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	pmbm_data = &dom_mbm->mbm_local[idx];
 
 	dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
@@ -543,7 +684,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 
 	cur_bw = pmbm_data->prev_bw;
 	user_bw = dom_mba->mbps_val[closid];
-	delta_bw = pmbm_data->delta_bw;
 
 	/* MBA resource doesn't support CDP */
 	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
@@ -555,52 +695,35 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
 		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
 		cur_bw += cmbm_data->prev_bw;
-		delta_bw += cmbm_data->delta_bw;
 	}
 
 	/*
 	 * Scale up/down the bandwidth linearly for the ctrl group.  The
 	 * bandwidth step is the bandwidth granularity specified by the
 	 * hardware.
-	 *
-	 * The delta_bw is used when increasing the bandwidth so that we
-	 * dont alternately increase and decrease the control values
-	 * continuously.
-	 *
-	 * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if
-	 * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep
-	 * switching between 90 and 110 continuously if we only check
-	 * cur_bw < user_bw.
+	 * Always increase throttling if current bandwidth is above the
+	 * target set by user.
+	 * But avoid thrashing up and down on every poll by checking
+	 * whether a decrease in throttling is likely to push the group
+	 * back over target. E.g. if currently throttling to 30% of bandwidth
+	 * on a system with 10% granularity steps, check whether moving to
+	 * 40% would go past the limit by multiplying current bandwidth by
+	 * "(30 + 10) / 30".
 	 */
 	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
 		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
 	} else if (cur_msr_val < MAX_MBA_BW &&
-		   (user_bw > (cur_bw + delta_bw))) {
+		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
 		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
 	} else {
 		return;
 	}
 
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-
-	/*
-	 * Delta values are updated dynamically package wise for each
-	 * rdtgrp every time the throttle MSR changes value.
-	 *
-	 * This is because (1)the increase in bandwidth is not perfectly
-	 * linear and only "approximately" linear even when the hardware
-	 * says it is linear.(2)Also since MBA is a core specific
-	 * mechanism, the delta values vary based on number of cores used
-	 * by the rdtgrp.
-	 */
-	pmbm_data->delta_comp = true;
-	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
-		cmbm_data->delta_comp = true;
-	}
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
+		       u32 closid, u32 rmid)
 {
 	struct rmid_read rr;
 
@@ -615,12 +738,28 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	if (is_mbm_total_enabled()) {
 		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+		if (IS_ERR(rr.arch_mon_ctx)) {
+			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+					    PTR_ERR(rr.arch_mon_ctx));
+			return;
+		}
+
+		__mon_event_count(closid, rmid, &rr);
+
+		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+		if (IS_ERR(rr.arch_mon_ctx)) {
+			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+					    PTR_ERR(rr.arch_mon_ctx));
+			return;
+		}
+
+		__mon_event_count(closid, rmid, &rr);
 
 		/*
 		 * Call the MBA software controller only for the
@@ -628,7 +767,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 		 * the software controller explicitly.
 		 */
 		if (is_mba_sc(NULL))
-			mbm_bw_count(rmid, &rr);
+			mbm_bw_count(closid, rmid, &rr);
+
+		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 	}
 }
 
@@ -639,106 +780,193 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	int cpu = smp_processor_id();
-	struct rdt_resource *r;
 	struct rdt_domain *d;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
-	if (has_busy_rmid(r, d))
-		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
+	if (has_busy_rmid(d)) {
+		d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+							   RESCTRL_PICK_ANY_CPU);
+		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
+					 delay);
+	}
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 }
 
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ *                             domain.
+ * @dom:           The domain the limbo handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @exclude_cpu:   Which CPU the handler should not run on,
+ *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+			     int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
 	dom->cqm_work_cpu = cpu;
 
-	schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
 }
 
 void mbm_handle_overflow(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
-	int cpu = smp_processor_id();
 	struct list_head *head;
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	if (!static_branch_likely(&rdt_mon_enable_key))
+	/*
+	 * If the filesystem has been unmounted this work no longer needs to
+	 * run.
+	 */
+	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
 	}
 
-	schedule_delayed_work_on(cpu, &d->mbm_over, delay);
+	/*
+	 * Re-check for housekeeping CPUs. This allows the overflow handler to
+	 * move off a nohz_full CPU quickly.
+	 */
+	d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+						   RESCTRL_PICK_ANY_CPU);
+	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
 
 out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 }
 
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ *                                domain.
+ * @dom:           The domain the overflow handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @exclude_cpu:   Which CPU the handler should not run on,
+ *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
+				int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
 	int cpu;
 
-	if (!static_branch_likely(&rdt_mon_enable_key))
+	/*
+	 * When a domain comes online there is no guarantee the filesystem is
+	 * mounted. If not, there is no need to catch counter overflow.
+	 */
+	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		return;
-	cpu = cpumask_any(&dom->cpu_mask);
+	cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
 	dom->mbm_work_cpu = cpu;
-	schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
 
 static int dom_data_init(struct rdt_resource *r)
 {
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rmid_entry *entry = NULL;
-	int i, nr_rmids;
+	int err = 0, i;
+	u32 idx;
+
+	mutex_lock(&rdtgroup_mutex);
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		u32 *tmp;
+
+		/*
+		 * If the architecture hasn't provided a sanitised value here,
+		 * this may result in larger arrays than necessary. Resctrl will
+		 * use a smaller system wide value based on the resources in
+		 * use.
+		 */
+		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
 
-	nr_rmids = r->num_rmid;
-	rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs)
-		return -ENOMEM;
+		closid_num_dirty_rmid = tmp;
+	}
+
+	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
+	if (!rmid_ptrs) {
+		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+			kfree(closid_num_dirty_rmid);
+			closid_num_dirty_rmid = NULL;
+		}
+		err = -ENOMEM;
+		goto out_unlock;
+	}
 
-	for (i = 0; i < nr_rmids; i++) {
+	for (i = 0; i < idx_limit; i++) {
 		entry = &rmid_ptrs[i];
 		INIT_LIST_HEAD(&entry->list);
 
-		entry->rmid = i;
+		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
 		list_add_tail(&entry->list, &rmid_free_lru);
 	}
 
 	/*
-	 * RMID 0 is special and is always allocated. It's used for all
-	 * tasks that are not monitored.
+	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
+	 * are always allocated. These are used for the rdtgroup_default
+	 * control group, which will be setup later in rdtgroup_init().
 	 */
-	entry = __rmid_entry(0);
+	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+					   RESCTRL_RESERVED_RMID);
+	entry = __rmid_entry(idx);
 	list_del(&entry->list);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+static void __exit dom_data_exit(void)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		kfree(closid_num_dirty_rmid);
+		closid_num_dirty_rmid = NULL;
+	}
+
+	kfree(rmid_ptrs);
+	rmid_ptrs = NULL;
+
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 static struct mon_evt llc_occupancy_event = {
@@ -813,6 +1041,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		return ret;
 
 	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* Detect list of bandwidth sources that can be tracked */
+		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
+		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 			mbm_total_event.configurable = true;
 			mbm_config_rftype_init("mbm_total_bytes_config");
@@ -830,6 +1064,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	return 0;
 }
 
+void __exit rdt_put_mon_l3_config(void)
+{
+	dom_data_exit();
+}
+
 void __init intel_rdt_mbm_apply_quirk(void)
 {
 	int cf_index;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 8f559eeae08e..884b88e25141 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -581,7 +581,7 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
 	if (ret)
 		goto err_cpus;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
 		if (ret)
 			goto err_cpus_list;
@@ -628,7 +628,7 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
 	if (ret)
 		goto err_cpus;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
 		if (ret)
 			goto err_cpus_list;
@@ -752,7 +752,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * anymore when this group would be used for pseudo-locking. This
 	 * is safe to call on platforms not capable of monitoring.
 	 */
-	free_rmid(rdtgrp->mon.rmid);
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 	ret = 0;
 	goto out;
@@ -776,8 +776,8 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 {
 	int ret;
 
-	if (rdt_mon_capable) {
-		ret = alloc_rmid();
+	if (resctrl_arch_mon_capable()) {
+		ret = alloc_rmid(rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Out of RMIDs\n");
 			return ret;
@@ -787,7 +787,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 
 	ret = rdtgroup_locksetup_user_restore(rdtgrp);
 	if (ret) {
-		free_rmid(rdtgrp->mon.rmid);
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 		return ret;
 	}
 
@@ -844,6 +844,9 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	struct rdt_domain *d_i;
 	bool ret = false;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
 		return true;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 69a1de92384a..011e17efb1a6 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -35,6 +35,10 @@
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
 static struct kernfs_root *rdt_root;
 struct rdtgroup rdtgroup_default;
 LIST_HEAD(rdt_all_groups);
@@ -42,6 +46,9 @@ LIST_HEAD(rdt_all_groups);
 /* list of entries for the schemata file */
 LIST_HEAD(resctrl_schema_all);
 
+/* The filesystem can only be mounted once. */
+bool resctrl_mounted;
+
 /* Kernel fs node for "info" directory under root */
 static struct kernfs_node *kn_info;
 
@@ -102,7 +109,7 @@ void rdt_staged_configs_clear(void)
  *
  * Using a global CLOSID across all resources has some advantages and
  * some drawbacks:
- * + We can simply set "current->closid" to assign a task to a resource
+ * + We can simply set current's closid to assign a task to a resource
  *   group.
  * + Context switch code can avoid extra memory references deciding which
  *   CLOSID to load into the PQR_ASSOC MSR
@@ -111,7 +118,7 @@ void rdt_staged_configs_clear(void)
  * - Our choices on how to configure each resource become progressively more
  *   limited as the number of resources grows.
  */
-static int closid_free_map;
+static unsigned long closid_free_map;
 static int closid_free_map_len;
 
 int closids_supported(void)
@@ -130,26 +137,39 @@ static void closid_init(void)
 
 	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
 
-	/* CLOSID 0 is always reserved for the default group */
-	closid_free_map &= ~1;
+	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
+	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
 	closid_free_map_len = rdt_min_closid;
 }
 
 static int closid_alloc(void)
 {
-	u32 closid = ffs(closid_free_map);
+	int cleanest_closid;
+	u32 closid;
 
-	if (closid == 0)
-		return -ENOSPC;
-	closid--;
-	closid_free_map &= ~(1 << closid);
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		cleanest_closid = resctrl_find_cleanest_closid();
+		if (cleanest_closid < 0)
+			return cleanest_closid;
+		closid = cleanest_closid;
+	} else {
+		closid = ffs(closid_free_map);
+		if (closid == 0)
+			return -ENOSPC;
+		closid--;
+	}
+	__clear_bit(closid, &closid_free_map);
 
 	return closid;
 }
 
 void closid_free(int closid)
 {
-	closid_free_map |= 1 << closid;
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	__set_bit(closid, &closid_free_map);
 }
 
 /**
@@ -159,9 +179,11 @@ void closid_free(int closid)
  * Return: true if @closid is currently associated with a resource group,
  * false if @closid is free
  */
-static bool closid_allocated(unsigned int closid)
+bool closid_allocated(unsigned int closid)
 {
-	return (closid_free_map & (1 << closid)) == 0;
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	return !test_bit(closid, &closid_free_map);
 }
 
 /**
@@ -559,14 +581,26 @@ static void update_task_closid_rmid(struct task_struct *t)
 		_update_task_closid_rmid(t);
 }
 
+static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
+{
+	u32 closid, rmid = rdtgrp->mon.rmid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP)
+		closid = rdtgrp->closid;
+	else if (rdtgrp->type == RDTMON_GROUP)
+		closid = rdtgrp->mon.parent->closid;
+	else
+		return false;
+
+	return resctrl_arch_match_closid(tsk, closid) &&
+	       resctrl_arch_match_rmid(tsk, closid, rmid);
+}
+
 static int __rdtgroup_move_task(struct task_struct *tsk,
 				struct rdtgroup *rdtgrp)
 {
 	/* If the task is already in rdtgrp, no need to move the task. */
-	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
-	     tsk->rmid == rdtgrp->mon.rmid) ||
-	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
-	     tsk->closid == rdtgrp->mon.parent->closid))
+	if (task_in_rdtgroup(tsk, rdtgrp))
 		return 0;
 
 	/*
@@ -577,19 +611,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * For monitor groups, can move the tasks only from
 	 * their parent CTRL group.
 	 */
-
-	if (rdtgrp->type == RDTCTRL_GROUP) {
-		WRITE_ONCE(tsk->closid, rdtgrp->closid);
-		WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
-	} else if (rdtgrp->type == RDTMON_GROUP) {
-		if (rdtgrp->mon.parent->closid == tsk->closid) {
-			WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
-		} else {
-			rdt_last_cmd_puts("Can't move task to different control group\n");
-			return -EINVAL;
-		}
+	if (rdtgrp->type == RDTMON_GROUP &&
+	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
+		rdt_last_cmd_puts("Can't move task to different control group\n");
+		return -EINVAL;
 	}
 
+	if (rdtgrp->type == RDTMON_GROUP)
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
+					     rdtgrp->mon.rmid);
+	else
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
+					     rdtgrp->mon.rmid);
+
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
@@ -611,14 +645,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 
 static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
 {
-	return (rdt_alloc_capable &&
-	       (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
+	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
+		resctrl_arch_match_closid(t, r->closid));
 }
 
 static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
 {
-	return (rdt_mon_capable &&
-	       (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
+	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
+		resctrl_arch_match_rmid(t, r->mon.parent->closid,
+					r->mon.rmid));
 }
 
 /**
@@ -853,7 +888,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 	mutex_lock(&rdtgroup_mutex);
 
 	/* Return empty if resctrl has not been mounted. */
-	if (!static_branch_unlikely(&rdt_enable_key)) {
+	if (!resctrl_mounted) {
 		seq_puts(s, "res:\nmon:\n");
 		goto unlock;
 	}
@@ -869,7 +904,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 		    rdtg->mode != RDT_MODE_EXCLUSIVE)
 			continue;
 
-		if (rdtg->closid != tsk->closid)
+		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
 			continue;
 
 		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
@@ -877,7 +912,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 		seq_puts(s, "mon:");
 		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
 				    mon.crdtgrp_list) {
-			if (tsk->rmid != crg->mon.rmid)
+			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
+						     crg->mon.rmid))
 				continue;
 			seq_printf(s, "%s", crg->kn->name);
 			break;
@@ -982,6 +1018,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 	bool sep = false;
 	u32 ctrl_val;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 	hw_shareable = r->cache.shareable_bits;
 	list_for_each_entry(dom, &r->domains, list) {
@@ -1042,6 +1079,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 	}
 	seq_putc(seq, '\n');
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 	return 0;
 }
 
@@ -1297,6 +1335,9 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
 	struct rdt_domain *d;
 	u32 ctrl;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
 		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
@@ -1561,6 +1602,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 	struct rdt_domain *dom;
 	bool sep = false;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	list_for_each_entry(dom, &r->domains, list) {
@@ -1577,6 +1619,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 	seq_puts(s, "\n");
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return 0;
 }
@@ -1614,17 +1657,10 @@ static void mon_event_config_write(void *info)
 	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
 }
 
-static int mbm_config_write_domain(struct rdt_resource *r,
-				   struct rdt_domain *d, u32 evtid, u32 val)
+static void mbm_config_write_domain(struct rdt_resource *r,
+				    struct rdt_domain *d, u32 evtid, u32 val)
 {
 	struct mon_config_info mon_info = {0};
-	int ret = 0;
-
-	/* mon_config cannot be more than the supported set of events */
-	if (val > MAX_EVT_CONFIG_BITS) {
-		rdt_last_cmd_puts("Invalid event configuration\n");
-		return -EINVAL;
-	}
 
 	/*
 	 * Read the current config value first. If both are the same then
@@ -1633,7 +1669,7 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	mon_info.evtid = evtid;
 	mondata_config_read(d, &mon_info);
 	if (mon_info.mon_config == val)
-		goto out;
+		return;
 
 	mon_info.mon_config = val;
 
@@ -1656,17 +1692,17 @@ static int mbm_config_write_domain(struct rdt_resource *r,
 	 * mbm_local and mbm_total counts for all the RMIDs.
 	 */
 	resctrl_arch_reset_rmid_all(r, d);
-
-out:
-	return ret;
 }
 
 static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	char *dom_str = NULL, *id_str;
 	unsigned long dom_id, val;
 	struct rdt_domain *d;
-	int ret = 0;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
 
 next:
 	if (!tok || tok[0] == '\0')
@@ -1686,11 +1722,16 @@ next:
 		return -EINVAL;
 	}
 
+	/* Value from user cannot be more than the supported set of events */
+	if ((val & hw_res->mbm_cfg_mask) != val) {
+		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
+				    hw_res->mbm_cfg_mask);
+		return -EINVAL;
+	}
+
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
-			ret = mbm_config_write_domain(r, d, evtid, val);
-			if (ret)
-				return -EINVAL;
+			mbm_config_write_domain(r, d, evtid, val);
 			goto next;
 		}
 	}
@@ -1709,6 +1750,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
 		return -EINVAL;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	rdt_last_cmd_clear();
@@ -1718,6 +1760,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return ret ?: nbytes;
 }
@@ -1733,6 +1776,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
 		return -EINVAL;
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	rdt_last_cmd_clear();
@@ -1742,6 +1786,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
 
 	return ret ?: nbytes;
 }
@@ -2218,6 +2263,9 @@ static int set_cache_qos_cfg(int level, bool enable)
 	struct rdt_domain *d;
 	int cpu;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (level == RDT_RESOURCE_L3)
 		update = l3_qos_cfg_update;
 	else if (level == RDT_RESOURCE_L2)
@@ -2417,6 +2465,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
 
 	rdtgroup_kn_get(rdtgrp, kn);
 
+	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
 	/* Was this group deleted while we waited? */
@@ -2434,6 +2483,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 		return;
 
 	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
 	rdtgroup_kn_put(rdtgrp, kn);
 }
 
@@ -2584,7 +2635,7 @@ static int rdt_get_tree(struct fs_context *fc)
 	/*
 	 * resctrl file system can only be mounted once.
 	 */
-	if (static_branch_unlikely(&rdt_enable_key)) {
+	if (resctrl_mounted) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -2605,7 +2656,7 @@ static int rdt_get_tree(struct fs_context *fc)
 
 	closid_init();
 
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		flags |= RFTYPE_MON;
 
 	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
@@ -2618,7 +2669,7 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (ret < 0)
 		goto out_schemata_free;
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
 					  &rdtgroup_default, "mon_groups",
 					  &kn_mongrp);
@@ -2640,18 +2691,19 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (ret < 0)
 		goto out_psl;
 
-	if (rdt_alloc_capable)
-		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
-	if (rdt_mon_capable)
-		static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_enable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_enable_mon();
 
-	if (rdt_alloc_capable || rdt_mon_capable)
-		static_branch_enable_cpuslocked(&rdt_enable_key);
+	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
+		resctrl_mounted = true;
 
 	if (is_mbm_enabled()) {
 		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 		list_for_each_entry(dom, &r->domains, list)
-			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+						   RESCTRL_PICK_ANY_CPU);
 	}
 
 	goto out;
@@ -2659,10 +2711,10 @@ static int rdt_get_tree(struct fs_context *fc)
 out_psl:
 	rdt_pseudo_lock_release();
 out_mondata:
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		kernfs_remove(kn_mondata);
 out_mongrp:
-	if (rdt_mon_capable)
+	if (resctrl_arch_mon_capable())
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
@@ -2765,6 +2817,9 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	struct rdt_domain *d;
 	int i;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
 
@@ -2810,8 +2865,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 	for_each_process_thread(p, t) {
 		if (!from || is_closid_match(t, from) ||
 		    is_rmid_match(t, from)) {
-			WRITE_ONCE(t->closid, to->closid);
-			WRITE_ONCE(t->rmid, to->mon.rmid);
+			resctrl_arch_set_closid_rmid(t, to->closid,
+						     to->mon.rmid);
 
 			/*
 			 * Order the closid/rmid stores above before the loads
@@ -2842,7 +2897,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 
 	head = &rdtgrp->mon.crdtgrp_list;
 	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
-		free_rmid(sentry->mon.rmid);
+		free_rmid(sentry->closid, sentry->mon.rmid);
 		list_del(&sentry->mon.crdtgrp_list);
 
 		if (atomic_read(&sentry->waitcount) != 0)
@@ -2882,7 +2937,7 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
-		free_rmid(rdtgrp->mon.rmid);
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);
@@ -2917,9 +2972,11 @@ static void rdt_kill_sb(struct super_block *sb)
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	schemata_list_destroy();
 	rdtgroup_destroy_root();
-	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
-	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
-	static_branch_disable_cpuslocked(&rdt_enable_key);
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_disable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_disable_mon();
+	resctrl_mounted = false;
 	kernfs_kill_sb(sb);
 	mutex_unlock(&rdtgroup_mutex);
 	cpus_read_unlock();
@@ -3047,6 +3104,9 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
 	struct rdt_domain *dom;
 	int ret;
 
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
 	list_for_each_entry(dom, &r->domains, list) {
 		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
 		if (ret)
@@ -3293,6 +3353,36 @@ out:
 	return ret;
 }
 
+static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (!resctrl_arch_mon_capable())
+		return 0;
+
+	ret = alloc_rmid(rdtgrp->closid);
+	if (ret < 0) {
+		rdt_last_cmd_puts("Out of RMIDs\n");
+		return ret;
+	}
+	rdtgrp->mon.rmid = ret;
+
+	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
+	if (ret) {
+		rdt_last_cmd_puts("kernfs subdir error\n");
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
+{
+	if (resctrl_arch_mon_capable())
+		free_rmid(rgrp->closid, rgrp->mon.rmid);
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     const char *name, umode_t mode,
 			     enum rdt_group_type rtype, struct rdtgroup **r)
@@ -3353,7 +3443,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 
 	if (rtype == RDTCTRL_GROUP) {
 		files = RFTYPE_BASE | RFTYPE_CTRL;
-		if (rdt_mon_capable)
+		if (resctrl_arch_mon_capable())
 			files |= RFTYPE_MON;
 	} else {
 		files = RFTYPE_BASE | RFTYPE_MON;
@@ -3365,29 +3455,11 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_destroy;
 	}
 
-	if (rdt_mon_capable) {
-		ret = alloc_rmid();
-		if (ret < 0) {
-			rdt_last_cmd_puts("Out of RMIDs\n");
-			goto out_destroy;
-		}
-		rdtgrp->mon.rmid = ret;
-
-		ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
-		if (ret) {
-			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_idfree;
-		}
-	}
-	kernfs_activate(kn);
-
 	/*
 	 * The caller unlocks the parent_kn upon success.
 	 */
 	return 0;
 
-out_idfree:
-	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
 	kernfs_put(rdtgrp->kn);
 	kernfs_remove(rdtgrp->kn);
@@ -3401,7 +3473,6 @@ out_unlock:
 static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
 {
 	kernfs_remove(rgrp->kn);
-	free_rmid(rgrp->mon.rmid);
 	rdtgroup_remove(rgrp);
 }
 
@@ -3423,12 +3494,21 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
 	prgrp = rdtgrp->mon.parent;
 	rdtgrp->closid = prgrp->closid;
 
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret) {
+		mkdir_rdt_prepare_clean(rdtgrp);
+		goto out_unlock;
+	}
+
+	kernfs_activate(rdtgrp->kn);
+
 	/*
 	 * Add the rdtgrp to the list of rdtgrps the parent
 	 * ctrl_mon group has to track.
 	 */
 	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
 
+out_unlock:
 	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
@@ -3459,13 +3539,20 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	ret = 0;
 
 	rdtgrp->closid = closid;
+
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret)
+		goto out_closid_free;
+
+	kernfs_activate(rdtgrp->kn);
+
 	ret = rdtgroup_init_alloc(rdtgrp);
 	if (ret < 0)
-		goto out_id_free;
+		goto out_rmid_free;
 
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
 
-	if (rdt_mon_capable) {
+	if (resctrl_arch_mon_capable()) {
 		/*
 		 * Create an empty mon_groups directory to hold the subset
 		 * of tasks and cpus to monitor.
@@ -3481,7 +3568,9 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 
 out_del_list:
 	list_del(&rdtgrp->rdtgroup_list);
-out_id_free:
+out_rmid_free:
+	mkdir_rdt_prepare_rmid_free(rdtgrp);
+out_closid_free:
 	closid_free(closid);
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
@@ -3518,14 +3607,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	 * allocation is supported, add a control and monitoring
 	 * subdirectory
 	 */
-	if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn)
+	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
 		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
 
 	/*
 	 * If RDT monitoring is supported and the parent directory is a valid
 	 * "mon_groups" directory, add a monitoring subdirectory.
 	 */
-	if (rdt_mon_capable && is_mon_groups(parent_kn, name))
+	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
 		return rdtgroup_mkdir_mon(parent_kn, name, mode);
 
 	return -EPERM;
@@ -3550,7 +3639,7 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	update_closid_rmid(tmpmask, NULL);
 
 	rdtgrp->flags = RDT_DELETED;
-	free_rmid(rdtgrp->mon.rmid);
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 	/*
 	 * Remove the rdtgrp from the parent ctrl_mon group's list
@@ -3596,8 +3685,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 	closid_free(rdtgrp->closid);
-	free_rmid(rdtgrp->mon.rmid);
 
 	rdtgroup_ctrl_remove(rdtgrp);
 
@@ -3829,8 +3918,8 @@ static void __init rdtgroup_setup_default(void)
 {
 	mutex_lock(&rdtgroup_mutex);
 
-	rdtgroup_default.closid = 0;
-	rdtgroup_default.mon.rmid = 0;
+	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
+	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
 	rdtgroup_default.type = RDTCTRL_GROUP;
 	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
 
@@ -3848,24 +3937,24 @@ static void domain_destroy_mon_state(struct rdt_domain *d)
 
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
-	lockdep_assert_held(&rdtgroup_mutex);
+	mutex_lock(&rdtgroup_mutex);
 
 	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
 		mba_sc_domain_destroy(r, d);
 
 	if (!r->mon_capable)
-		return;
+		goto out_unlock;
 
 	/*
 	 * If resctrl is mounted, remove all the
 	 * per domain monitor data directories.
 	 */
-	if (static_branch_unlikely(&rdt_mon_enable_key))
+	if (resctrl_mounted && resctrl_arch_mon_capable())
 		rmdir_mondata_subdir_allrdtgrp(r, d->id);
 
 	if (is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
+	if (is_llc_occupancy_enabled() && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -3879,20 +3968,24 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
 	}
 
 	domain_destroy_mon_state(d);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 {
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize;
 
 	if (is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
+		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
 	if (is_mbm_total_enabled()) {
 		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
 			bitmap_free(d->rmid_busy_llc);
 			return -ENOMEM;
@@ -3900,7 +3993,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 	}
 	if (is_mbm_local_enabled()) {
 		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
 			bitmap_free(d->rmid_busy_llc);
 			kfree(d->mbm_total);
@@ -3913,34 +4006,97 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
 
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
 {
-	int err;
+	int err = 0;
 
-	lockdep_assert_held(&rdtgroup_mutex);
+	mutex_lock(&rdtgroup_mutex);
 
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
 		/* RDT_RESOURCE_MBA is never mon_capable */
-		return mba_sc_domain_allocate(r, d);
+		err = mba_sc_domain_allocate(r, d);
+		goto out_unlock;
+	}
 
 	if (!r->mon_capable)
-		return 0;
+		goto out_unlock;
 
 	err = domain_setup_mon_state(r, d);
 	if (err)
-		return err;
+		goto out_unlock;
 
 	if (is_mbm_enabled()) {
 		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
-		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+					   RESCTRL_PICK_ANY_CPU);
 	}
 
 	if (is_llc_occupancy_enabled())
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
-	/* If resctrl is mounted, add per domain monitor data directories. */
-	if (static_branch_unlikely(&rdt_mon_enable_key))
+	/*
+	 * If the filesystem is not mounted then only the default resource group
+	 * exists. Creation of its directories is deferred until mount time
+	 * by rdt_get_tree() calling mkdir_mondata_all().
+	 * If resctrl is mounted, add per domain monitor data directories.
+	 */
+	if (resctrl_mounted && resctrl_arch_mon_capable())
 		mkdir_mondata_subdir_allrdtgrp(r, d);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+void resctrl_online_cpu(unsigned int cpu)
+{
+	mutex_lock(&rdtgroup_mutex);
+	/* The CPU is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
+{
+	struct rdtgroup *cr;
+
+	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
+			break;
+	}
+}
+
+void resctrl_offline_cpu(unsigned int cpu)
+{
+	struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdtgroup *rdtgrp;
+	struct rdt_domain *d;
+
+	mutex_lock(&rdtgroup_mutex);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
+			clear_childcpus(rdtgrp, cpu);
+			break;
+		}
+	}
+
+	if (!l3->mon_capable)
+		goto out_unlock;
+
+	d = get_domain_from_cpu(cpu, l3);
+	if (d) {
+		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
+			cancel_delayed_work(&d->mbm_over);
+			mbm_setup_overflow_handler(d, 0, cpu);
+		}
+		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
+		    has_busy_rmid(d)) {
+			cancel_delayed_work(&d->cqm_limbo);
+			cqm_setup_limbo_handler(d, 0, cpu);
+		}
+	}
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index dc136703566f..3259b1d4fefe 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -1,167 +1,510 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
+ * CPU/APIC topology
+ *
+ * The APIC IDs describe the system topology in multiple domain levels.
+ * The CPUID topology parser provides the information which part of the
+ * APIC ID is associated to the individual levels:
+ *
+ * [PACKAGE][DIEGRP][DIE][TILE][MODULE][CORE][THREAD]
+ *
+ * The root space contains the package (socket) IDs.
+ *
+ * Not enumerated levels consume 0 bits space, but conceptually they are
+ * always represented. If e.g. only CORE and THREAD levels are enumerated
+ * then the DIE, MODULE and TILE have the same physical ID as the PACKAGE.
+ *
+ * If SMT is not supported, then the THREAD domain is still used. It then
+ * has the same physical ID as the CORE domain and is the only child of
+ * the core domain.
+ *
+ * This allows a unified view on the system independent of the enumerated
+ * domain levels without requiring any conditionals in the code.
  */
-
+#define pr_fmt(fmt) "CPU topo: " fmt
 #include <linux/cpu.h>
+
+#include <xen/xen.h>
+
 #include <asm/apic.h>
-#include <asm/memtype.h>
-#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <asm/io_apic.h>
+#include <asm/mpspec.h>
+#include <asm/smp.h>
 
 #include "cpu.h"
 
-/* leaf 0xb SMT level */
-#define SMT_LEVEL	0
+/*
+ * Map cpu index to physical APIC ID
+ */
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, CPU_ACPIID_INVALID);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
 
-/* extended topology sub-leaf types */
-#define INVALID_TYPE	0
-#define SMT_TYPE	1
-#define CORE_TYPE	2
-#define DIE_TYPE	5
+/* Bitmap of physically present CPUs. */
+DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC) __read_mostly;
 
-#define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
-#define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
-#define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
+/* Used for CPU number allocation and parallel CPU bringup */
+u32 cpuid_to_apicid[] __ro_after_init = { [0 ... NR_CPUS - 1] = BAD_APICID, };
+
+/* Bitmaps to mark registered APICs at each topology domain */
+static struct { DECLARE_BITMAP(map, MAX_LOCAL_APIC); } apic_maps[TOPO_MAX_DOMAIN] __ro_after_init;
+
+/*
+ * Keep track of assigned, disabled and rejected CPUs. Present assigned
+ * with 1 as CPU #0 is reserved for the boot CPU.
+ */
+static struct {
+	unsigned int		nr_assigned_cpus;
+	unsigned int		nr_disabled_cpus;
+	unsigned int		nr_rejected_cpus;
+	u32			boot_cpu_apic_id;
+	u32			real_bsp_apic_id;
+} topo_info __ro_after_init = {
+	.nr_assigned_cpus	= 1,
+	.boot_cpu_apic_id	= BAD_APICID,
+	.real_bsp_apic_id	= BAD_APICID,
+};
 
-unsigned int __max_die_per_package __read_mostly = 1;
-EXPORT_SYMBOL(__max_die_per_package);
+#define domain_weight(_dom)	bitmap_weight(apic_maps[_dom].map, MAX_LOCAL_APIC)
+
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == (u64)cpuid_to_apicid[cpu];
+}
 
 #ifdef CONFIG_SMP
+static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid)
+{
+	if (!(apicid & (__max_threads_per_core - 1)))
+		cpumask_set_cpu(cpu, &__cpu_primary_thread_mask);
+}
+#else
+static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { }
+#endif
+
 /*
- * Check if given CPUID extended topology "leaf" is implemented
+ * Convert the APIC ID to a domain level ID by masking out the low bits
+ * below the domain level @dom.
  */
-static int check_extended_topology_leaf(int leaf)
+static inline u32 topo_apicid(u32 apicid, enum x86_topology_domains dom)
+{
+	if (dom == TOPO_SMT_DOMAIN)
+		return apicid;
+	return apicid & (UINT_MAX << x86_topo_system.dom_shifts[dom - 1]);
+}
+
+static int topo_lookup_cpuid(u32 apic_id)
 {
-	unsigned int eax, ebx, ecx, edx;
+	int i;
 
-	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	/* CPU# to APICID mapping is persistent once it is established */
+	for (i = 0; i < topo_info.nr_assigned_cpus; i++) {
+		if (cpuid_to_apicid[i] == apic_id)
+			return i;
+	}
+	return -ENODEV;
+}
 
-	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
-		return -1;
+static __init int topo_get_cpunr(u32 apic_id)
+{
+	int cpu = topo_lookup_cpuid(apic_id);
 
-	return 0;
+	if (cpu >= 0)
+		return cpu;
+
+	return topo_info.nr_assigned_cpus++;
 }
-/*
- * Return best CPUID Extended Topology Leaf supported
+
+static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id)
+{
+#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
+	early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id;
+	early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id;
+#endif
+	set_cpu_possible(cpu, true);
+	set_cpu_present(cpu, true);
+}
+
+static __init bool check_for_real_bsp(u32 apic_id)
+{
+	/*
+	 * There is no real good way to detect whether this a kdump()
+	 * kernel, but except on the Voyager SMP monstrosity which is not
+	 * longer supported, the real BSP APIC ID is the first one which is
+	 * enumerated by firmware. That allows to detect whether the boot
+	 * CPU is the real BSP. If it is not, then do not register the APIC
+	 * because sending INIT to the real BSP would reset the whole
+	 * system.
+	 *
+	 * The first APIC ID which is enumerated by firmware is detectable
+	 * because the boot CPU APIC ID is registered before that without
+	 * invoking this code.
+	 */
+	if (topo_info.real_bsp_apic_id != BAD_APICID)
+		return false;
+
+	if (apic_id == topo_info.boot_cpu_apic_id) {
+		topo_info.real_bsp_apic_id = apic_id;
+		return false;
+	}
+
+	pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n",
+		topo_info.boot_cpu_apic_id, apic_id);
+	pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n");
+
+	topo_info.real_bsp_apic_id = apic_id;
+	return true;
+}
+
+static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level,
+				    unsigned long *map)
+{
+	unsigned int id, end, cnt = 0;
+
+	/* Calculate the exclusive end */
+	end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]);
+
+	/* Unfortunately there is no bitmap_weight_range() */
+	for (id = find_next_bit(map, end, lvlid); id < end; id = find_next_bit(map, end, ++id))
+		cnt++;
+	return cnt;
+}
+
+static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present)
+{
+	int cpu, dom;
+
+	if (present) {
+		set_bit(apic_id, phys_cpu_present_map);
+
+		/*
+		 * Double registration is valid in case of the boot CPU
+		 * APIC because that is registered before the enumeration
+		 * of the APICs via firmware parsers or VM guest
+		 * mechanisms.
+		 */
+		if (apic_id == topo_info.boot_cpu_apic_id)
+			cpu = 0;
+		else
+			cpu = topo_get_cpunr(apic_id);
+
+		cpuid_to_apicid[cpu] = apic_id;
+		topo_set_cpuids(cpu, apic_id, acpi_id);
+	} else {
+		u32 pkgid = topo_apicid(apic_id, TOPO_PKG_DOMAIN);
+
+		/*
+		 * Check for present APICs in the same package when running
+		 * on bare metal. Allow the bogosity in a guest.
+		 */
+		if (hypervisor_is_type(X86_HYPER_NATIVE) &&
+		    topo_unit_count(pkgid, TOPO_PKG_DOMAIN, phys_cpu_present_map)) {
+			pr_info_once("Ignoring hot-pluggable APIC ID %x in present package.\n",
+				     apic_id);
+			topo_info.nr_rejected_cpus++;
+			return;
+		}
+
+		topo_info.nr_disabled_cpus++;
+	}
+
+	/* Register present and possible CPUs in the domain maps */
+	for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++)
+		set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map);
+}
+
+/**
+ * topology_register_apic - Register an APIC in early topology maps
+ * @apic_id:	The APIC ID to set up
+ * @acpi_id:	The ACPI ID associated to the APIC
+ * @present:	True if the corresponding CPU is present
  */
-static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
+void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present)
 {
-	if (c->cpuid_level >= 0x1f) {
-		if (check_extended_topology_leaf(0x1f) == 0)
-			return 0x1f;
+	if (apic_id >= MAX_LOCAL_APIC) {
+		pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1);
+		topo_info.nr_rejected_cpus++;
+		return;
+	}
+
+	if (check_for_real_bsp(apic_id)) {
+		topo_info.nr_rejected_cpus++;
+		return;
 	}
 
-	if (c->cpuid_level >= 0xb) {
-		if (check_extended_topology_leaf(0xb) == 0)
-			return 0xb;
+	/* CPU numbers exhausted? */
+	if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) {
+		pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids);
+		topo_info.nr_rejected_cpus++;
+		return;
 	}
 
-	return -1;
+	topo_register_apic(apic_id, acpi_id, present);
+}
+
+/**
+ * topology_register_boot_apic - Register the boot CPU APIC
+ * @apic_id:	The APIC ID to set up
+ *
+ * Separate so CPU #0 can be assigned
+ */
+void __init topology_register_boot_apic(u32 apic_id)
+{
+	WARN_ON_ONCE(topo_info.boot_cpu_apic_id != BAD_APICID);
+
+	topo_info.boot_cpu_apic_id = apic_id;
+	topo_register_apic(apic_id, CPU_ACPIID_INVALID, true);
+}
+
+/**
+ * topology_get_logical_id - Retrieve the logical ID at a given topology domain level
+ * @apicid:		The APIC ID for which to lookup the logical ID
+ * @at_level:		The topology domain level to use
+ *
+ * @apicid must be a full APIC ID, not the normalized variant. It's valid to have
+ * all bits below the domain level specified by @at_level to be clear. So both
+ * real APIC IDs and backshifted normalized APIC IDs work correctly.
+ *
+ * Returns:
+ *  - >= 0:	The requested logical ID
+ *  - -ERANGE:	@apicid is out of range
+ *  - -ENODEV:	@apicid is not registered
+ */
+int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level)
+{
+	/* Remove the bits below @at_level to get the proper level ID of @apicid */
+	unsigned int lvlid = topo_apicid(apicid, at_level);
+
+	if (lvlid >= MAX_LOCAL_APIC)
+		return -ERANGE;
+	if (!test_bit(lvlid, apic_maps[at_level].map))
+		return -ENODEV;
+	/* Get the number of set bits before @lvlid. */
+	return bitmap_weight(apic_maps[at_level].map, lvlid);
+}
+EXPORT_SYMBOL_GPL(topology_get_logical_id);
+
+/**
+ * topology_unit_count - Retrieve the count of specified units at a given topology domain level
+ * @apicid:		The APIC ID which specifies the search range
+ * @which_units:	The domain level specifying the units to count
+ * @at_level:		The domain level at which @which_units have to be counted
+ *
+ * This returns the number of possible units according to the enumerated
+ * information.
+ *
+ * E.g. topology_count_units(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN)
+ * counts the number of possible cores in the package to which @apicid
+ * belongs.
+ *
+ * @at_level must obviously be greater than @which_level to produce useful
+ * results.  If @at_level is equal to @which_units the result is
+ * unsurprisingly 1. If @at_level is less than @which_units the results
+ * is by definition undefined and the function returns 0.
+ */
+unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+				 enum x86_topology_domains at_level)
+{
+	/* Remove the bits below @at_level to get the proper level ID of @apicid */
+	unsigned int lvlid = topo_apicid(apicid, at_level);
+
+	if (lvlid >= MAX_LOCAL_APIC)
+		return 0;
+	if (!test_bit(lvlid, apic_maps[at_level].map))
+		return 0;
+	if (which_units > at_level)
+		return 0;
+	if (which_units == at_level)
+		return 1;
+	return topo_unit_count(lvlid, at_level, apic_maps[which_units].map);
+}
+
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+/**
+ * topology_hotplug_apic - Handle a physical hotplugged APIC after boot
+ * @apic_id:	The APIC ID to set up
+ * @acpi_id:	The ACPI ID associated to the APIC
+ */
+int topology_hotplug_apic(u32 apic_id, u32 acpi_id)
+{
+	int cpu;
+
+	if (apic_id >= MAX_LOCAL_APIC)
+		return -EINVAL;
+
+	/* Reject if the APIC ID was not registered during enumeration. */
+	if (!test_bit(apic_id, apic_maps[TOPO_SMT_DOMAIN].map))
+		return -ENODEV;
+
+	cpu = topo_lookup_cpuid(apic_id);
+	if (cpu < 0)
+		return -ENOSPC;
+
+	set_bit(apic_id, phys_cpu_present_map);
+	topo_set_cpuids(cpu, apic_id, acpi_id);
+	cpu_mark_primary_thread(cpu, apic_id);
+	return cpu;
+}
+
+/**
+ * topology_hotunplug_apic - Remove a physical hotplugged APIC after boot
+ * @cpu:	The CPU number for which the APIC ID is removed
+ */
+void topology_hotunplug_apic(unsigned int cpu)
+{
+	u32 apic_id = cpuid_to_apicid[cpu];
+
+	if (apic_id == BAD_APICID)
+		return;
+
+	per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
+	clear_bit(apic_id, phys_cpu_present_map);
+	set_cpu_present(cpu, false);
 }
 #endif
 
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
+#ifdef CONFIG_X86_LOCAL_APIC
+static unsigned int max_possible_cpus __initdata = NR_CPUS;
+
+/**
+ * topology_apply_cmdline_limits_early - Apply topology command line limits early
+ *
+ * Ensure that command line limits are in effect before firmware parsing
+ * takes place.
+ */
+void __init topology_apply_cmdline_limits_early(void)
 {
-#ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx;
-	int leaf;
+	unsigned int possible = nr_cpu_ids;
 
-	leaf = detect_extended_topology_leaf(c);
-	if (leaf < 0)
-		return -1;
+	/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */
+	if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled)
+		possible = 1;
 
-	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
+	/* 'possible_cpus=N' */
+	possible = min_t(unsigned int, max_possible_cpus, possible);
+
+	if (possible < nr_cpu_ids) {
+		pr_info("Limiting to %u possible CPUs\n", possible);
+		set_nr_cpu_ids(possible);
+	}
+}
 
-	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+static __init bool restrict_to_up(void)
+{
+	if (!smp_found_config || ioapic_is_disabled)
+		return true;
 	/*
-	 * initial apic id, which also represents 32-bit extended x2apic id.
+	 * XEN PV is special as it does not advertise the local APIC
+	 * properly, but provides a fake topology for it so that the
+	 * infrastructure works. So don't apply the restrictions vs. APIC
+	 * here.
 	 */
-	c->topo.initial_apicid = edx;
-	smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
-#endif
-	return 0;
+	if (xen_pv_domain())
+		return false;
+
+	return apic_is_disabled;
 }
 
-/*
- * Check for extended topology enumeration cpuid leaf, and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
- */
-int detect_extended_topology(struct cpuinfo_x86 *c)
+void __init topology_init_possible_cpus(void)
 {
-#ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
-	unsigned int core_select_mask, core_level_siblings;
-	unsigned int die_select_mask, die_level_siblings;
-	unsigned int pkg_mask_width;
-	bool die_level_present = false;
-	int leaf;
-
-	leaf = detect_extended_topology_leaf(c);
-	if (leaf < 0)
-		return -1;
+	unsigned int assigned = topo_info.nr_assigned_cpus;
+	unsigned int disabled = topo_info.nr_disabled_cpus;
+	unsigned int cnta, cntb, cpu, allowed = 1;
+	unsigned int total = assigned + disabled;
+	u32 apicid, firstid;
+
+	if (!restrict_to_up()) {
+		if (WARN_ON_ONCE(assigned > nr_cpu_ids)) {
+			disabled += assigned - nr_cpu_ids;
+			assigned = nr_cpu_ids;
+		}
+		allowed = min_t(unsigned int, total, nr_cpu_ids);
+	}
+
+	if (total > allowed)
+		pr_warn("%u possible CPUs exceed the limit of %u\n", total, allowed);
+
+	assigned = min_t(unsigned int, allowed, assigned);
+	disabled = allowed - assigned;
 
+	topo_info.nr_assigned_cpus = assigned;
+	topo_info.nr_disabled_cpus = disabled;
+
+	total_cpus = allowed;
+	set_nr_cpu_ids(allowed);
+
+	cnta = domain_weight(TOPO_PKG_DOMAIN);
+	cntb = domain_weight(TOPO_DIE_DOMAIN);
+	__max_logical_packages = cnta;
+	__max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta));
+
+	pr_info("Max. logical packages: %3u\n", cnta);
+	pr_info("Max. logical dies:     %3u\n", cntb);
+	pr_info("Max. dies per package: %3u\n", __max_dies_per_package);
+
+	cnta = domain_weight(TOPO_CORE_DOMAIN);
+	cntb = domain_weight(TOPO_SMT_DOMAIN);
 	/*
-	 * Populate HT related information from sub-leaf level 0.
+	 * Can't use order delta here as order(cnta) can be equal
+	 * order(cntb) even if cnta != cntb.
 	 */
-	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
-	c->topo.initial_apicid = edx;
-	core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-	smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
-	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-	pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-
-	sub_index = 1;
-	while (true) {
-		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
+	__max_threads_per_core = DIV_ROUND_UP(cntb, cnta);
+	pr_info("Max. threads per core: %3u\n", __max_threads_per_core);
 
-		/*
-		 * Check for the Core type in the implemented sub leaves.
-		 */
-		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
-			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			die_level_siblings = core_level_siblings;
-			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-		}
-		if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
-			die_level_present = true;
-			die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-		}
+	firstid = find_first_bit(apic_maps[TOPO_SMT_DOMAIN].map, MAX_LOCAL_APIC);
+	__num_cores_per_package = topology_unit_count(firstid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN);
+	pr_info("Num. cores per package:   %3u\n", __num_cores_per_package);
+	__num_threads_per_package = topology_unit_count(firstid, TOPO_SMT_DOMAIN, TOPO_PKG_DOMAIN);
+	pr_info("Num. threads per package: %3u\n", __num_threads_per_package);
 
-		if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE)
-			pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-		else
-			break;
+	pr_info("Allowing %u present CPUs plus %u hotplug CPUs\n", assigned, disabled);
+	if (topo_info.nr_rejected_cpus)
+		pr_info("Rejected CPUs %u\n", topo_info.nr_rejected_cpus);
 
-		sub_index++;
+	init_cpu_present(cpumask_of(0));
+	init_cpu_possible(cpumask_of(0));
+
+	/* Assign CPU numbers to non-present CPUs */
+	for (apicid = 0; disabled; disabled--, apicid++) {
+		apicid = find_next_andnot_bit(apic_maps[TOPO_SMT_DOMAIN].map, phys_cpu_present_map,
+					      MAX_LOCAL_APIC, apicid);
+		if (apicid >= MAX_LOCAL_APIC)
+			break;
+		cpuid_to_apicid[topo_info.nr_assigned_cpus++] = apicid;
 	}
 
-	core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width;
-	die_select_mask = (~(-1 << die_plus_mask_width)) >>
-				core_plus_mask_width;
+	for (cpu = 0; cpu < allowed; cpu++) {
+		apicid = cpuid_to_apicid[cpu];
 
-	c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid,
-				ht_mask_width) & core_select_mask;
+		set_cpu_possible(cpu, true);
 
-	if (die_level_present) {
-		c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid,
-					core_plus_mask_width) & die_select_mask;
+		if (apicid == BAD_APICID)
+			continue;
+
+		cpu_mark_primary_thread(cpu, apicid);
+		set_cpu_present(cpu, test_bit(apicid, phys_cpu_present_map));
 	}
+}
 
-	c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, pkg_mask_width);
-	/*
-	 * Reinit the apicid, now that we have extended initial_apicid.
-	 */
-	c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
+/*
+ * Late SMP disable after sizing CPU masks when APIC/IOAPIC setup failed.
+ */
+void __init topology_reset_possible_cpus_up(void)
+{
+	init_cpu_present(cpumask_of(0));
+	init_cpu_possible(cpumask_of(0));
 
-	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
-	__max_die_per_package = (die_level_siblings / core_level_siblings);
-#endif
+	bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC);
+	if (topo_info.boot_cpu_apic_id != BAD_APICID)
+		set_bit(topo_info.boot_cpu_apic_id, phys_cpu_present_map);
+}
+
+static int __init setup_possible_cpus(char *str)
+{
+	get_option(&str, &max_possible_cpus);
 	return 0;
 }
+early_param("possible_cpus", setup_possible_cpus);
+#endif
diff --git a/arch/x86/kernel/cpu/topology.h b/arch/x86/kernel/cpu/topology.h
new file mode 100644
index 000000000000..37326297f80c
--- /dev/null
+++ b/arch/x86/kernel/cpu/topology.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_X86_TOPOLOGY_H
+#define ARCH_X86_TOPOLOGY_H
+
+struct topo_scan {
+	struct cpuinfo_x86	*c;
+	unsigned int		dom_shifts[TOPO_MAX_DOMAIN];
+	unsigned int		dom_ncpus[TOPO_MAX_DOMAIN];
+
+	/* Legacy CPUID[1]:EBX[23:16] number of logical processors */
+	unsigned int		ebx1_nproc_shift;
+
+	/* AMD specific node ID which cannot be mapped into APIC space. */
+	u16			amd_nodes_per_pkg;
+	u16			amd_node_id;
+};
+
+void cpu_init_topology(struct cpuinfo_x86 *c);
+void cpu_parse_topology(struct cpuinfo_x86 *c);
+void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom,
+		      unsigned int shift, unsigned int ncpus);
+bool cpu_parse_topology_ext(struct topo_scan *tscan);
+void cpu_parse_topology_amd(struct topo_scan *tscan);
+void cpu_topology_fixup_amd(struct topo_scan *tscan);
+
+static inline u32 topo_shift_apicid(u32 apicid, enum x86_topology_domains dom)
+{
+	if (dom == TOPO_SMT_DOMAIN)
+		return apicid;
+	return apicid >> x86_topo_system.dom_shifts[dom - 1];
+}
+
+static inline u32 topo_relative_domain_id(u32 apicid, enum x86_topology_domains dom)
+{
+	if (dom != TOPO_SMT_DOMAIN)
+		apicid >>= x86_topo_system.dom_shifts[dom - 1];
+	return apicid & (x86_topo_system.dom_size[dom] - 1);
+}
+
+static inline u32 topo_domain_mask(enum x86_topology_domains dom)
+{
+	return (1U << x86_topo_system.dom_shifts[dom]) - 1;
+}
+
+/*
+ * Update a domain level after the fact without propagating. Used to fixup
+ * broken CPUID enumerations.
+ */
+static inline void topology_update_dom(struct topo_scan *tscan, enum x86_topology_domains dom,
+				       unsigned int shift, unsigned int ncpus)
+{
+	tscan->dom_shifts[dom] = shift;
+	tscan->dom_ncpus[dom] = ncpus;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+				 enum x86_topology_domains at_level);
+#else
+static inline unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+					       enum x86_topology_domains at_level)
+{
+	return 1;
+}
+#endif
+
+#endif /* ARCH_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
new file mode 100644
index 000000000000..1a8b3ad493af
--- /dev/null
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpu.h>
+
+#include <asm/apic.h>
+#include <asm/memtype.h>
+#include <asm/processor.h>
+
+#include "cpu.h"
+
+static bool parse_8000_0008(struct topo_scan *tscan)
+{
+	struct {
+		// ecx
+		u32	cpu_nthreads		:  8, // Number of physical threads - 1
+						:  4, // Reserved
+			apicid_coreid_len	:  4, // Number of thread core ID bits (shift) in APIC ID
+			perf_tsc_len		:  2, // Performance time-stamp counter size
+						: 14; // Reserved
+	} ecx;
+	unsigned int sft;
+
+	if (tscan->c->extended_cpuid_level < 0x80000008)
+		return false;
+
+	cpuid_leaf_reg(0x80000008, CPUID_ECX, &ecx);
+
+	/* If the thread bits are 0, then get the shift value from ecx.cpu_nthreads */
+	sft = ecx.apicid_coreid_len;
+	if (!sft)
+		sft = get_count_order(ecx.cpu_nthreads + 1);
+
+	topology_set_dom(tscan, TOPO_SMT_DOMAIN, sft, ecx.cpu_nthreads + 1);
+	return true;
+}
+
+static void store_node(struct topo_scan *tscan, unsigned int nr_nodes, u16 node_id)
+{
+	/*
+	 * Starting with Fam 17h the DIE domain could probably be used to
+	 * retrieve the node info on AMD/HYGON. Analysis of CPUID dumps
+	 * suggests it's the topmost bit(s) of the CPU cores area, but
+	 * that's guess work and neither enumerated nor documented.
+	 *
+	 * Up to Fam 16h this does not work at all and the legacy node ID
+	 * has to be used.
+	 */
+	tscan->amd_nodes_per_pkg = nr_nodes;
+	tscan->amd_node_id = node_id;
+}
+
+static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
+{
+	struct {
+		// eax
+		u32	ext_apic_id		: 32; // Extended APIC ID
+		// ebx
+		u32	core_id			:  8, // Unique per-socket logical core unit ID
+			core_nthreads		:  8, // #Threads per core (zero-based)
+						: 16; // Reserved
+		// ecx
+		u32	node_id			:  8, // Node (die) ID of invoking logical CPU
+			nnodes_per_socket	:  3, // #nodes in invoking logical CPU's package/socket
+						: 21; // Reserved
+		// edx
+		u32				: 32; // Reserved
+	} leaf;
+
+	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
+		return false;
+
+	cpuid_leaf(0x8000001e, &leaf);
+
+	tscan->c->topo.initial_apicid = leaf.ext_apic_id;
+
+	/*
+	 * If leaf 0xb is available, then SMT shift is set already. If not
+	 * take it from ecx.threads_per_core and use topo_update_dom() -
+	 * topology_set_dom() would propagate and overwrite the already
+	 * propagated CORE level.
+	 */
+	if (!has_0xb) {
+		unsigned int nthreads = leaf.core_nthreads + 1;
+
+		topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads);
+	}
+
+	store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id);
+
+	if (tscan->c->x86_vendor == X86_VENDOR_AMD) {
+		if (tscan->c->x86 == 0x15)
+			tscan->c->topo.cu_id = leaf.core_id;
+
+		cacheinfo_amd_init_llc_id(tscan->c, leaf.node_id);
+	} else {
+		/*
+		 * Package ID is ApicId[6..] on certain Hygon CPUs. See
+		 * commit e0ceeae708ce for explanation. The topology info
+		 * is screwed up: The package shift is always 6 and the
+		 * node ID is bit [4:5].
+		 */
+		if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && tscan->c->x86_model <= 0x3) {
+			topology_set_dom(tscan, TOPO_CORE_DOMAIN, 6,
+					 tscan->dom_ncpus[TOPO_CORE_DOMAIN]);
+		}
+		cacheinfo_hygon_init_llc_id(tscan->c);
+	}
+	return true;
+}
+
+static bool parse_fam10h_node_id(struct topo_scan *tscan)
+{
+	struct {
+		union {
+			u64	node_id		:  3,
+				nodes_per_pkg	:  3,
+				unused		: 58;
+			u64	msr;
+		};
+	} nid;
+
+	if (!boot_cpu_has(X86_FEATURE_NODEID_MSR))
+		return false;
+
+	rdmsrl(MSR_FAM10H_NODE_ID, nid.msr);
+	store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id);
+	tscan->c->topo.llc_id = nid.node_id;
+	return true;
+}
+
+static void legacy_set_llc(struct topo_scan *tscan)
+{
+	unsigned int apicid = tscan->c->topo.initial_apicid;
+
+	/* parse_8000_0008() set everything up except llc_id */
+	tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN];
+}
+
+static void parse_topology_amd(struct topo_scan *tscan)
+{
+	bool has_0xb = false;
+
+	/*
+	 * If the extended topology leaf 0x8000_001e is available
+	 * try to get SMT and CORE shift from leaf 0xb first, then
+	 * try to get the CORE shift from leaf 0x8000_0008.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
+		has_0xb = cpu_parse_topology_ext(tscan);
+
+	if (!has_0xb && !parse_8000_0008(tscan))
+		return;
+
+	/* Prefer leaf 0x8000001e if available */
+	if (parse_8000_001e(tscan, has_0xb))
+		return;
+
+	/* Try the NODEID MSR */
+	if (parse_fam10h_node_id(tscan))
+		return;
+
+	legacy_set_llc(tscan);
+}
+
+void cpu_parse_topology_amd(struct topo_scan *tscan)
+{
+	tscan->amd_nodes_per_pkg = 1;
+	parse_topology_amd(tscan);
+
+	if (tscan->amd_nodes_per_pkg > 1)
+		set_cpu_cap(tscan->c, X86_FEATURE_AMD_DCM);
+}
+
+void cpu_topology_fixup_amd(struct topo_scan *tscan)
+{
+	struct cpuinfo_x86 *c = tscan->c;
+
+	/*
+	 * Adjust the core_id relative to the node when there is more than
+	 * one node.
+	 */
+	if (tscan->c->x86 < 0x17 && tscan->amd_nodes_per_pkg > 1)
+		c->topo.core_id %= tscan->dom_ncpus[TOPO_CORE_DOMAIN] / tscan->amd_nodes_per_pkg;
+}
diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c
new file mode 100644
index 000000000000..a50ae8d63d1c
--- /dev/null
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpu.h>
+
+#include <xen/xen.h>
+
+#include <asm/apic.h>
+#include <asm/processor.h>
+#include <asm/smp.h>
+
+#include "cpu.h"
+
+struct x86_topology_system x86_topo_system __ro_after_init;
+EXPORT_SYMBOL_GPL(x86_topo_system);
+
+unsigned int __amd_nodes_per_pkg __ro_after_init;
+EXPORT_SYMBOL_GPL(__amd_nodes_per_pkg);
+
+void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom,
+		      unsigned int shift, unsigned int ncpus)
+{
+	topology_update_dom(tscan, dom, shift, ncpus);
+
+	/* Propagate to the upper levels */
+	for (dom++; dom < TOPO_MAX_DOMAIN; dom++) {
+		tscan->dom_shifts[dom] = tscan->dom_shifts[dom - 1];
+		tscan->dom_ncpus[dom] = tscan->dom_ncpus[dom - 1];
+	}
+}
+
+static unsigned int __maybe_unused parse_num_cores_legacy(struct cpuinfo_x86 *c)
+{
+	struct {
+		u32	cache_type	:  5,
+			unused		: 21,
+			ncores		:  6;
+	} eax;
+
+	if (c->cpuid_level < 4)
+		return 1;
+
+	cpuid_subleaf_reg(4, 0, CPUID_EAX, &eax);
+	if (!eax.cache_type)
+		return 1;
+
+	return eax.ncores + 1;
+}
+
+static void parse_legacy(struct topo_scan *tscan)
+{
+	unsigned int cores, core_shift, smt_shift = 0;
+	struct cpuinfo_x86 *c = tscan->c;
+
+	cores = parse_num_cores_legacy(c);
+	core_shift = get_count_order(cores);
+
+	if (cpu_has(c, X86_FEATURE_HT)) {
+		if (!WARN_ON_ONCE(tscan->ebx1_nproc_shift < core_shift))
+			smt_shift = tscan->ebx1_nproc_shift - core_shift;
+		/*
+		 * The parser expects leaf 0xb/0x1f format, which means
+		 * the number of logical processors at core level is
+		 * counting threads.
+		 */
+		core_shift += smt_shift;
+		cores <<= smt_shift;
+	}
+
+	topology_set_dom(tscan, TOPO_SMT_DOMAIN, smt_shift, 1U << smt_shift);
+	topology_set_dom(tscan, TOPO_CORE_DOMAIN, core_shift, cores);
+}
+
+static bool fake_topology(struct topo_scan *tscan)
+{
+	/*
+	 * Preset the CORE level shift for CPUID less systems and XEN_PV,
+	 * which has useless CPUID information.
+	 */
+	topology_set_dom(tscan, TOPO_SMT_DOMAIN, 0, 1);
+	topology_set_dom(tscan, TOPO_CORE_DOMAIN, 0, 1);
+
+	return tscan->c->cpuid_level < 1;
+}
+
+static void parse_topology(struct topo_scan *tscan, bool early)
+{
+	const struct cpuinfo_topology topo_defaults = {
+		.cu_id			= 0xff,
+		.llc_id			= BAD_APICID,
+		.l2c_id			= BAD_APICID,
+	};
+	struct cpuinfo_x86 *c = tscan->c;
+	struct {
+		u32	unused0		: 16,
+			nproc		:  8,
+			apicid		:  8;
+	} ebx;
+
+	c->topo = topo_defaults;
+
+	if (fake_topology(tscan))
+		return;
+
+	/* Preset Initial APIC ID from CPUID leaf 1 */
+	cpuid_leaf_reg(1, CPUID_EBX, &ebx);
+	c->topo.initial_apicid = ebx.apicid;
+
+	/*
+	 * The initial invocation from early_identify_cpu() happens before
+	 * the APIC is mapped or X2APIC enabled. For establishing the
+	 * topology, that's not required. Use the initial APIC ID.
+	 */
+	if (early)
+		c->topo.apicid = c->topo.initial_apicid;
+	else
+		c->topo.apicid = read_apic_id();
+
+	/* The above is sufficient for UP */
+	if (!IS_ENABLED(CONFIG_SMP))
+		return;
+
+	tscan->ebx1_nproc_shift = get_count_order(ebx.nproc);
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_AMD:
+		if (IS_ENABLED(CONFIG_CPU_SUP_AMD))
+			cpu_parse_topology_amd(tscan);
+		break;
+	case X86_VENDOR_CENTAUR:
+	case X86_VENDOR_ZHAOXIN:
+		parse_legacy(tscan);
+		break;
+	case X86_VENDOR_INTEL:
+		if (!IS_ENABLED(CONFIG_CPU_SUP_INTEL) || !cpu_parse_topology_ext(tscan))
+			parse_legacy(tscan);
+		break;
+	case X86_VENDOR_HYGON:
+		if (IS_ENABLED(CONFIG_CPU_SUP_HYGON))
+			cpu_parse_topology_amd(tscan);
+		break;
+	}
+}
+
+static void topo_set_ids(struct topo_scan *tscan)
+{
+	struct cpuinfo_x86 *c = tscan->c;
+	u32 apicid = c->topo.apicid;
+
+	c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN);
+	c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN);
+
+	c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN);
+	c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN);
+
+	/* Package relative core ID */
+	c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >>
+		x86_topo_system.dom_shifts[TOPO_SMT_DOMAIN];
+
+	c->topo.amd_node_id = tscan->amd_node_id;
+
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		cpu_topology_fixup_amd(tscan);
+}
+
+void cpu_parse_topology(struct cpuinfo_x86 *c)
+{
+	unsigned int dom, cpu = smp_processor_id();
+	struct topo_scan tscan = { .c = c, };
+
+	parse_topology(&tscan, false);
+
+	if (IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
+		if (c->topo.initial_apicid != c->topo.apicid) {
+			pr_err(FW_BUG "CPU%4u: APIC ID mismatch. CPUID: 0x%04x APIC: 0x%04x\n",
+			       cpu, c->topo.initial_apicid, c->topo.apicid);
+		}
+
+		if (c->topo.apicid != cpuid_to_apicid[cpu]) {
+			pr_err(FW_BUG "CPU%4u: APIC ID mismatch. Firmware: 0x%04x APIC: 0x%04x\n",
+			       cpu, cpuid_to_apicid[cpu], c->topo.apicid);
+		}
+	}
+
+	for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) {
+		if (tscan.dom_shifts[dom] == x86_topo_system.dom_shifts[dom])
+			continue;
+		pr_err(FW_BUG "CPU%d: Topology domain %u shift %u != %u\n", cpu, dom,
+		       tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]);
+	}
+
+	topo_set_ids(&tscan);
+}
+
+void __init cpu_init_topology(struct cpuinfo_x86 *c)
+{
+	struct topo_scan tscan = { .c = c, };
+	unsigned int dom, sft;
+
+	parse_topology(&tscan, true);
+
+	/* Copy the shift values and calculate the unit sizes. */
+	memcpy(x86_topo_system.dom_shifts, tscan.dom_shifts, sizeof(x86_topo_system.dom_shifts));
+
+	dom = TOPO_SMT_DOMAIN;
+	x86_topo_system.dom_size[dom] = 1U << x86_topo_system.dom_shifts[dom];
+
+	for (dom++; dom < TOPO_MAX_DOMAIN; dom++) {
+		sft = x86_topo_system.dom_shifts[dom] - x86_topo_system.dom_shifts[dom - 1];
+		x86_topo_system.dom_size[dom] = 1U << sft;
+	}
+
+	topo_set_ids(&tscan);
+
+	/*
+	 * AMD systems have Nodes per package which cannot be mapped to
+	 * APIC ID.
+	 */
+	__amd_nodes_per_pkg = tscan.amd_nodes_per_pkg;
+}
diff --git a/arch/x86/kernel/cpu/topology_ext.c b/arch/x86/kernel/cpu/topology_ext.c
new file mode 100644
index 000000000000..e477228cd5b2
--- /dev/null
+++ b/arch/x86/kernel/cpu/topology_ext.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpu.h>
+
+#include <asm/apic.h>
+#include <asm/memtype.h>
+#include <asm/processor.h>
+
+#include "cpu.h"
+
+enum topo_types {
+	INVALID_TYPE		= 0,
+	SMT_TYPE		= 1,
+	CORE_TYPE		= 2,
+	MAX_TYPE_0B		= 3,
+	MODULE_TYPE		= 3,
+	TILE_TYPE		= 4,
+	DIE_TYPE		= 5,
+	DIEGRP_TYPE		= 6,
+	MAX_TYPE_1F		= 7,
+};
+
+/*
+ * Use a lookup table for the case that there are future types > 6 which
+ * describe an intermediate domain level which does not exist today.
+ */
+static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = {
+	[SMT_TYPE]	= TOPO_SMT_DOMAIN,
+	[CORE_TYPE]	= TOPO_CORE_DOMAIN,
+	[MODULE_TYPE]	= TOPO_MODULE_DOMAIN,
+	[TILE_TYPE]	= TOPO_TILE_DOMAIN,
+	[DIE_TYPE]	= TOPO_DIE_DOMAIN,
+	[DIEGRP_TYPE]	= TOPO_DIEGRP_DOMAIN,
+};
+
+static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
+				unsigned int *last_dom)
+{
+	unsigned int dom, maxtype;
+	const unsigned int *map;
+	struct {
+		// eax
+		u32	x2apic_shift	:  5, // Number of bits to shift APIC ID right
+					      // for the topology ID at the next level
+					: 27; // Reserved
+		// ebx
+		u32	num_processors	: 16, // Number of processors at current level
+					: 16; // Reserved
+		// ecx
+		u32	level		:  8, // Current topology level. Same as sub leaf number
+			type		:  8, // Level type. If 0, invalid
+					: 16; // Reserved
+		// edx
+		u32	x2apic_id	: 32; // X2APIC ID of the current logical processor
+	} sl;
+
+	switch (leaf) {
+	case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break;
+	case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break;
+	default: return false;
+	}
+
+	cpuid_subleaf(leaf, subleaf, &sl);
+
+	if (!sl.num_processors || sl.type == INVALID_TYPE)
+		return false;
+
+	if (sl.type >= maxtype) {
+		pr_err_once("Topology: leaf 0x%x:%d Unknown domain type %u\n",
+			    leaf, subleaf, sl.type);
+		/*
+		 * It really would have been too obvious to make the domain
+		 * type space sparse and leave a few reserved types between
+		 * the points which might change instead of following the
+		 * usual "this can be fixed in software" principle.
+		 */
+		dom = *last_dom + 1;
+	} else {
+		dom = map[sl.type];
+		*last_dom = dom;
+	}
+
+	if (!dom) {
+		tscan->c->topo.initial_apicid = sl.x2apic_id;
+	} else if (tscan->c->topo.initial_apicid != sl.x2apic_id) {
+		pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf %d APIC ID mismatch %x != %x\n",
+			     leaf, subleaf, tscan->c->topo.initial_apicid, sl.x2apic_id);
+	}
+
+	topology_set_dom(tscan, dom, sl.x2apic_shift, sl.num_processors);
+	return true;
+}
+
+static bool parse_topology_leaf(struct topo_scan *tscan, u32 leaf)
+{
+	unsigned int last_dom;
+	u32 subleaf;
+
+	/* Read all available subleafs and populate the levels */
+	for (subleaf = 0, last_dom = 0; topo_subleaf(tscan, leaf, subleaf, &last_dom); subleaf++);
+
+	/* If subleaf 0 failed to parse, give up */
+	if (!subleaf)
+		return false;
+
+	/*
+	 * There are machines in the wild which have shift 0 in the subleaf
+	 * 0, but advertise 2 logical processors at that level. They are
+	 * truly SMT.
+	 */
+	if (!tscan->dom_shifts[TOPO_SMT_DOMAIN] && tscan->dom_ncpus[TOPO_SMT_DOMAIN] > 1) {
+		unsigned int sft = get_count_order(tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
+
+		pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf 0 has shift level 0 but %u CPUs. Fixing it up.\n",
+			     leaf, tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
+		topology_update_dom(tscan, TOPO_SMT_DOMAIN, sft, tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
+	}
+
+	set_cpu_cap(tscan->c, X86_FEATURE_XTOPOLOGY);
+	return true;
+}
+
+bool cpu_parse_topology_ext(struct topo_scan *tscan)
+{
+	/* Intel: Try leaf 0x1F first. */
+	if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f))
+		return true;
+
+	/* Intel/AMD: Fall back to leaf 0xB if available */
+	return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b);
+}
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 415564a6523b..90eba7eb5335 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -71,10 +71,6 @@ static void init_zhaoxin(struct cpuinfo_x86 *c)
 {
 	early_init_zhaoxin(c);
 	init_intel_cacheinfo(c);
-	detect_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
 
 	if (c->cpuid_level > 9) {
 		unsigned int eax = cpuid_eax(10);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index b6b044356f1b..e74d0c4286c1 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -26,6 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/memblock.h>
 
+#include <asm/bootparam.h>
 #include <asm/processor.h>
 #include <asm/hardirq.h>
 #include <asm/nmi.h>
@@ -40,6 +41,7 @@
 #include <asm/intel_pt.h>
 #include <asm/crash.h>
 #include <asm/cmdline.h>
+#include <asm/sev.h>
 
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
@@ -59,6 +61,8 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 	 */
 	cpu_emergency_stop_pt();
 
+	kdump_sev_callback();
+
 	disable_local_APIC();
 }
 
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index afd09924094e..4aeafe63521b 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -136,7 +136,7 @@ static void __init dtb_cpu_setup(void)
 			pr_warn("%pOF: missing local APIC ID\n", dn);
 			continue;
 		}
-		generic_processor_info(apic_id);
+		topology_register_apic(apic_id, CPU_ACPIID_INVALID, true);
 	}
 }
 
@@ -302,7 +302,7 @@ void __init x86_flattree_get_config(void)
 }
 #endif
 
-void __init x86_dtb_init(void)
+void __init x86_dtb_parse_smp_config(void)
 {
 	if (!of_have_populated_dt())
 		return;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index f18ca44c904b..44a91ef5a23b 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -410,7 +410,7 @@ static void __die_header(const char *str, struct pt_regs *regs, long err)
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
 	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",
-	       IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+	       IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) ?
 	       (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
 }
 NOKPROBE_SYMBOL(__die_header);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index fb8cf953380d..b66f540de054 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void)
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
 		/*
-		 * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need
-		 * to be reserved.
+		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
+		 * kexec and do not need to be reserved.
 		 */
-		if (data->type != SETUP_EFI && data->type != SETUP_IMA)
+		if (data->type != SETUP_EFI &&
+		    data->type != SETUP_IMA &&
+		    data->type != SETUP_RNG_SEED)
 			e820__range_update_kexec(pa_data,
 						 sizeof(*data) + data->len,
 						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 16f9814c9be0..6726e0473d0b 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -106,6 +106,10 @@ void __init init_espfix_bsp(void)
 	pgd_t *pgd;
 	p4d_t *p4d;
 
+	/* FRED systems always restore the full value of %rsp */
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		return;
+
 	/* Install the espfix pud into the kernel page directory */
 	pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)];
 	p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR);
@@ -129,6 +133,10 @@ void init_espfix_ap(int cpu)
 	void *stack_page;
 	pteval_t ptemask;
 
+	/* FRED systems always restore the full value of %rsp */
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		return;
+
 	/* We only have to do this once... */
 	if (likely(per_cpu(espfix_stack, cpu)))
 		return;		/* Already initialized */
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
index a06b876bbf2d..edbafc5940e3 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -2,6 +2,8 @@
 /*
  * x86 FPU bug checks:
  */
+#include <linux/printk.h>
+
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 558076dbde5b..247f2225aa9f 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
  * Attempt to restore the FPU registers directly from user memory.
  * Pagefaults are handled and any errors returned are fatal.
  */
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
-				     bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	int ret;
 
+	/* Restore enabled features only. */
+	xrestore &= fpu->fpstate->user_xfeatures;
 retry:
 	fpregs_lock();
 	/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
 		if (ret != X86_TRAP_PF)
 			return false;
 
-		if (!fault_in_readable(buf, size))
+		if (!fault_in_readable(buf, fpu->fpstate->user_size))
 			goto retry;
 		return false;
 	}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
-	unsigned int state_size;
 	u64 user_xfeatures = 0;
 
 	if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 			return false;
 
 		fx_only = !fx_sw_user.magic1;
-		state_size = fx_sw_user.xstate_size;
 		user_xfeatures = fx_sw_user.xfeatures;
 	} else {
 		user_xfeatures = XFEATURE_MASK_FPSSE;
-		state_size = fpu->fpstate->user_size;
 	}
 
 	if (likely(!ia32_fxstate)) {
 		/* Restore the FPU registers directly from user memory. */
-		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
-						state_size);
+		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
 	}
 
 	/*
diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c
new file mode 100644
index 000000000000..4bcd8791ad96
--- /dev/null
+++ b/arch/x86/kernel/fred.c
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/kernel.h>
+
+#include <asm/desc.h>
+#include <asm/fred.h>
+#include <asm/tlbflush.h>
+#include <asm/traps.h>
+
+/* #DB in the kernel would imply the use of a kernel debugger. */
+#define FRED_DB_STACK_LEVEL		1UL
+#define FRED_NMI_STACK_LEVEL		2UL
+#define FRED_MC_STACK_LEVEL		2UL
+/*
+ * #DF is the highest level because a #DF means "something went wrong
+ * *while delivering an exception*." The number of cases for which that
+ * can happen with FRED is drastically reduced and basically amounts to
+ * "the stack you pointed me to is broken." Thus, always change stacks
+ * on #DF, which means it should be at the highest level.
+ */
+#define FRED_DF_STACK_LEVEL		3UL
+
+#define FRED_STKLVL(vector, lvl)	((lvl) << (2 * (vector)))
+
+void cpu_init_fred_exceptions(void)
+{
+	/* When FRED is enabled by default, remove this log message */
+	pr_info("Initialize FRED on CPU%d\n", smp_processor_id());
+
+	wrmsrl(MSR_IA32_FRED_CONFIG,
+	       /* Reserve for CALL emulation */
+	       FRED_CONFIG_REDZONE |
+	       FRED_CONFIG_INT_STKLVL(0) |
+	       FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user));
+
+	/*
+	 * The purpose of separate stacks for NMI, #DB and #MC *in the kernel*
+	 * (remember that user space faults are always taken on stack level 0)
+	 * is to avoid overflowing the kernel stack.
+	 */
+	wrmsrl(MSR_IA32_FRED_STKLVLS,
+	       FRED_STKLVL(X86_TRAP_DB,  FRED_DB_STACK_LEVEL) |
+	       FRED_STKLVL(X86_TRAP_NMI, FRED_NMI_STACK_LEVEL) |
+	       FRED_STKLVL(X86_TRAP_MC,  FRED_MC_STACK_LEVEL) |
+	       FRED_STKLVL(X86_TRAP_DF,  FRED_DF_STACK_LEVEL));
+
+	/* The FRED equivalents to IST stacks... */
+	wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
+	wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
+	wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
+
+	/* Enable FRED */
+	cr4_set_bits(X86_CR4_FRED);
+	/* Any further IDT use is a bug */
+	idt_invalidate();
+
+	/* Use int $0x80 for 32-bit system calls in FRED mode */
+	setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
+	setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 12df54ff0e81..70139d9d2e01 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -307,7 +307,8 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-#define RET_SIZE		(IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS))
+#define RET_SIZE \
+	(IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_MITIGATION_SLS))
 
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index dc0956067944..212e8e06aeba 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -22,6 +22,8 @@
 #include <linux/cc_platform.h>
 #include <linux/pgtable.h>
 
+#include <asm/asm.h>
+#include <asm/page_64.h>
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/smp.h>
@@ -67,42 +69,11 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
 EXPORT_SYMBOL(vmemmap_base);
 #endif
 
-/*
- * GDT used on the boot CPU before switching to virtual addresses.
- */
-static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = {
-	[GDT_ENTRY_KERNEL32_CS]         = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_CS]           = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff),
-	[GDT_ENTRY_KERNEL_DS]           = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff),
-};
-
-/*
- * Address needs to be set at runtime because it references the startup_gdt
- * while the kernel still uses a direct mapping.
- */
-static struct desc_ptr startup_gdt_descr __initdata = {
-	.size = sizeof(startup_gdt)-1,
-	.address = 0,
-};
-
-static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
-{
-	return ptr - (void *)_text + (void *)physaddr;
-}
-
-static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr)
-{
-	return fixup_pointer(ptr, physaddr);
-}
-
-#ifdef CONFIG_X86_5LEVEL
-static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
+static inline bool check_la57_support(void)
 {
-	return fixup_pointer(ptr, physaddr);
-}
+	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+		return false;
 
-static bool __head check_la57_support(unsigned long physaddr)
-{
 	/*
 	 * 5-level paging is detected and enabled at kernel decompression
 	 * stage. Only check if it has been enabled there.
@@ -110,21 +81,8 @@ static bool __head check_la57_support(unsigned long physaddr)
 	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
-	*fixup_int(&__pgtable_l5_enabled, physaddr) = 1;
-	*fixup_int(&pgdir_shift, physaddr) = 48;
-	*fixup_int(&ptrs_per_p4d, physaddr) = 512;
-	*fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5;
-	*fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5;
-	*fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5;
-
 	return true;
 }
-#else
-static bool __head check_la57_support(unsigned long physaddr)
-{
-	return false;
-}
-#endif
 
 static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
 {
@@ -173,23 +131,22 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
  * doesn't have to generate PC-relative relocations when accessing globals from
  * that function. Clang actually does not generate them, which leads to
  * boot-time crashes. To work around this problem, every global pointer must
- * be adjusted using fixup_pointer().
+ * be accessed using RIP_REL_REF().
  */
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
-	unsigned long load_delta, *p;
+	pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
 	unsigned long pgtable_flags;
+	unsigned long load_delta;
 	pgdval_t *pgd;
 	p4dval_t *p4d;
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
-	pteval_t *mask_ptr;
 	bool la57;
 	int i;
-	unsigned int *next_pgt_ptr;
 
-	la57 = check_la57_support(physaddr);
+	la57 = check_la57_support();
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -200,6 +157,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * and the address I am actually running at.
 	 */
 	load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map);
+	RIP_REL_REF(phys_base) = load_delta;
 
 	/* Is the address not 2M aligned? */
 	if (load_delta & ~PMD_MASK)
@@ -210,26 +168,21 @@ unsigned long __head __startup_64(unsigned long physaddr,
 
 	/* Fixup the physical addresses in the page table */
 
-	pgd = fixup_pointer(early_top_pgt, physaddr);
-	p = pgd + pgd_index(__START_KERNEL_map);
-	if (la57)
-		*p = (unsigned long)level4_kernel_pgt;
-	else
-		*p = (unsigned long)level3_kernel_pgt;
-	*p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta;
+	pgd = &RIP_REL_REF(early_top_pgt)->pgd;
+	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
 
 	if (la57) {
-		p4d = fixup_pointer(level4_kernel_pgt, physaddr);
-		p4d[511] += load_delta;
+		p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
+		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
+
+		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE_NOENC;
 	}
 
-	pud = fixup_pointer(level3_kernel_pgt, physaddr);
-	pud[510] += load_delta;
-	pud[511] += load_delta;
+	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
+	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta;
 
-	pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
 	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
-		pmd[i] += load_delta;
+		RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta;
 
 	/*
 	 * Set up the identity mapping for the switchover.  These
@@ -238,15 +191,14 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * it avoids problems around wraparound.
 	 */
 
-	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
-	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
-	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
+	pud = &early_pgts[0]->pmd;
+	pmd = &early_pgts[1]->pmd;
+	RIP_REL_REF(next_early_pgt) = 2;
 
 	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
 
 	if (la57) {
-		p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++],
-				    physaddr);
+		p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd;
 
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
 		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
@@ -267,8 +219,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
 	/* Filter out unsupported __PAGE_KERNEL_* bits: */
-	mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
-	pmd_entry &= *mask_ptr;
+	pmd_entry &= RIP_REL_REF(__supported_pte_mask);
 	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 
@@ -294,7 +245,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * error, causing the BIOS to halt the system.
 	 */
 
-	pmd = fixup_pointer(level2_kernel_pgt, physaddr);
+	pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd;
 
 	/* invalidate pages before the kernel image */
 	for (i = 0; i < pmd_index((unsigned long)_text); i++)
@@ -309,12 +260,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	for (; i < PTRS_PER_PMD; i++)
 		pmd[i] &= ~_PAGE_PRESENT;
 
-	/*
-	 * Fixup phys_base - remove the memory encryption mask to obtain
-	 * the true physical address.
-	 */
-	*fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
-
 	return sme_postprocess_startup(bp, pmd);
 }
 
@@ -486,6 +431,15 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
 				(__START_KERNEL & PGDIR_MASK)));
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
+	if (check_la57_support()) {
+		__pgtable_l5_enabled	= 1;
+		pgdir_shift		= 48;
+		ptrs_per_p4d		= 512;
+		page_offset_base	= __PAGE_OFFSET_BASE_L5;
+		vmalloc_base		= __VMALLOC_BASE_L5;
+		vmemmap_base		= __VMEMMAP_BASE_L5;
+	}
+
 	cr4_init_shadow();
 
 	/* Kill off the identity-map trampoline */
@@ -569,62 +523,52 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data)
  */
 static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
 
-static struct desc_ptr bringup_idt_descr = {
-	.size		= (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1,
-	.address	= 0, /* Set at runtime */
-};
-
-static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler)
+/* This may run while still in the direct mapping */
+static void __head startup_64_load_idt(void *vc_handler)
 {
-#ifdef CONFIG_AMD_MEM_ENCRYPT
+	struct desc_ptr desc = {
+		.address = (unsigned long)&RIP_REL_REF(bringup_idt_table),
+		.size    = sizeof(bringup_idt_table) - 1,
+	};
 	struct idt_data data;
-	gate_desc desc;
-
-	init_idt_data(&data, n, handler);
-	idt_init_desc(&desc, &data);
-	native_write_idt_entry(idt, n, &desc);
-#endif
-}
+	gate_desc idt_desc;
 
-/* This runs while still in the direct mapping */
-static void __head startup_64_load_idt(unsigned long physbase)
-{
-	struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase);
-	gate_desc *idt = fixup_pointer(bringup_idt_table, physbase);
-
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
-		void *handler;
-
-		/* VMM Communication Exception */
-		handler = fixup_pointer(vc_no_ghcb, physbase);
-		set_bringup_idt_handler(idt, X86_TRAP_VC, handler);
+	/* @vc_handler is set only for a VMM Communication Exception */
+	if (vc_handler) {
+		init_idt_data(&data, X86_TRAP_VC, vc_handler);
+		idt_init_desc(&idt_desc, &data);
+		native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
 	}
 
-	desc->address = (unsigned long)idt;
-	native_load_idt(desc);
+	native_load_idt(&desc);
 }
 
 /* This is used when running on kernel addresses */
 void early_setup_idt(void)
 {
-	/* VMM Communication Exception */
+	void *handler = NULL;
+
 	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
 		setup_ghcb();
-		set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb);
+		handler = vc_boot_ghcb;
 	}
 
-	bringup_idt_descr.address = (unsigned long)bringup_idt_table;
-	native_load_idt(&bringup_idt_descr);
+	startup_64_load_idt(handler);
 }
 
 /*
  * Setup boot CPU state needed before kernel switches to virtual addresses.
  */
-void __head startup_64_setup_env(unsigned long physbase)
+void __head startup_64_setup_gdt_idt(void)
 {
+	void *handler = NULL;
+
+	struct desc_ptr startup_gdt_descr = {
+		.address = (unsigned long)&RIP_REL_REF(init_per_cpu_var(gdt_page.gdt)),
+		.size    = GDT_SIZE - 1,
+	};
+
 	/* Load GDT */
-	startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase);
 	native_load_gdt(&startup_gdt_descr);
 
 	/* New GDT is live - reload data segment registers */
@@ -632,5 +576,8 @@ void __head startup_64_setup_env(unsigned long physbase)
 		     "movl %%eax, %%ss\n"
 		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
 
-	startup_64_load_idt(physbase);
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+		handler = &RIP_REL_REF(vc_no_ghcb);
+
+	startup_64_load_idt(handler);
 }
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 487ac57e2c81..b50f3641c4d6 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -414,7 +414,7 @@ __REFDATA
 	.align 4
 SYM_DATA(initial_code,		.long i386_start_kernel)
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 #define	PGD_ALIGN	(2 * PAGE_SIZE)
 #define PTI_USER_PGD_FILL	1024
 #else
@@ -474,7 +474,7 @@ SYM_DATA_START(initial_page_table)
 # endif
 	.align PAGE_SIZE		/* needs to be page-sized too */
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	/*
 	 * PTI needs another page so sync_initial_pagetable() works correctly
 	 * and does not scribble over the data which is placed behind the
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d4918d03efb4..d8198fbd70e5 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -26,6 +26,7 @@
 #include <asm/apicdef.h>
 #include <asm/fixmap.h>
 #include <asm/smp.h>
+#include <asm/thread_info.h>
 
 /*
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
@@ -39,7 +40,6 @@ L4_START_KERNEL = l4_index(__START_KERNEL_map)
 
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
-	.text
 	__HEAD
 	.code64
 SYM_CODE_START_NOALIGN(startup_64)
@@ -66,9 +66,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	mov	%rsi, %r15
 
 	/* Set up the stack for verify_cpu() */
-	leaq	(__end_init_task - PTREGS_SIZE)(%rip), %rsp
-
-	leaq	_text(%rip), %rdi
+	leaq	(__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
 
 	/* Setup GSBASE to allow stack canary access for C code */
 	movl	$MSR_GS_BASE, %ecx
@@ -77,7 +75,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	shrq	$32,  %rdx
 	wrmsr
 
-	call	startup_64_setup_env
+	call	startup_64_setup_gdt_idt
 
 	/* Now switch to __KERNEL_CS so IRET works reliably */
 	pushq	$__KERNEL_CS
@@ -113,13 +111,11 @@ SYM_CODE_START_NOALIGN(startup_64)
 	call	__startup_64
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
-	addq	$(early_top_pgt - __START_KERNEL_map), %rax
+	leaq	early_top_pgt(%rip), %rcx
+	addq	%rcx, %rax
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	mov	%rax, %rdi
-	mov	%rax, %r14
-
-	addq	phys_base(%rip), %rdi
 
 	/*
 	 * For SEV guests: Verify that the C-bit is correct. A malicious
@@ -128,17 +124,23 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 * the next RET instruction.
 	 */
 	call	sev_verify_cbit
+#endif
 
 	/*
-	 * Restore CR3 value without the phys_base which will be added
-	 * below, before writing %cr3.
+	 * Switch to early_top_pgt which still has the identity mappings
+	 * present.
 	 */
-	 mov	%r14, %rax
-#endif
+	movq	%rax, %cr3
 
-	jmp 1f
+	/* Branch to the common startup code at its kernel virtual address */
+	ANNOTATE_RETPOLINE_SAFE
+	jmp	*0f(%rip)
 SYM_CODE_END(startup_64)
 
+	__INITRODATA
+0:	.quad	common_startup_64
+
+	.text
 SYM_CODE_START(secondary_startup_64)
 	UNWIND_HINT_END_OF_STACK
 	ANNOTATE_NOENDBR
@@ -171,22 +173,39 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 
 	/* Clear %R15 which holds the boot_params pointer on the boot CPU */
-	xorq	%r15, %r15
+	xorl	%r15d, %r15d
+
+	/* Derive the runtime physical address of init_top_pgt[] */
+	movq	phys_base(%rip), %rax
+	addq	$(init_top_pgt - __START_KERNEL_map), %rax
 
 	/*
 	 * Retrieve the modifier (SME encryption mask if SME is active) to be
 	 * added to the initial pgdir entry that will be programmed into CR3.
 	 */
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-	movq	sme_me_mask, %rax
-#else
-	xorq	%rax, %rax
+	addq	sme_me_mask(%rip), %rax
 #endif
+	/*
+	 * Switch to the init_top_pgt here, away from the trampoline_pgd and
+	 * unmap the identity mapped ranges.
+	 */
+	movq	%rax, %cr3
 
-	/* Form the CR3 value being sure to include the CR3 modifier */
-	addq	$(init_top_pgt - __START_KERNEL_map), %rax
-1:
+SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
+	UNWIND_HINT_END_OF_STACK
+	ANNOTATE_NOENDBR
 
+	/*
+	 * Create a mask of CR4 bits to preserve. Omit PGE in order to flush
+	 * global 1:1 translations from the TLBs.
+	 *
+	 * From the SDM:
+	 * "If CR4.PGE is changing from 0 to 1, there were no global TLB
+	 *  entries before the execution; if CR4.PGE is changing from 1 to 0,
+	 *  there will be no global TLB entries after the execution."
+	 */
+	movl	$(X86_CR4_PAE | X86_CR4_LA57), %edx
 #ifdef CONFIG_X86_MCE
 	/*
 	 * Preserve CR4.MCE if the kernel will enable #MC support.
@@ -195,52 +214,20 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * configured will crash the system regardless of the CR4.MCE value set
 	 * here.
 	 */
-	movq	%cr4, %rcx
-	andl	$X86_CR4_MCE, %ecx
-#else
-	movl	$0, %ecx
+	orl	$X86_CR4_MCE, %edx
 #endif
+	movq	%cr4, %rcx
+	andl	%edx, %ecx
 
-	/* Enable PAE mode, PSE, PGE and LA57 */
-	orl	$(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
-#ifdef CONFIG_X86_5LEVEL
-	testb	$1, __pgtable_l5_enabled(%rip)
-	jz	1f
-	orl	$X86_CR4_LA57, %ecx
-1:
-#endif
+	/* Even if ignored in long mode, set PSE uniformly on all logical CPUs. */
+	btsl	$X86_CR4_PSE_BIT, %ecx
 	movq	%rcx, %cr4
 
-	/* Setup early boot stage 4-/5-level pagetables. */
-	addq	phys_base(%rip), %rax
-
 	/*
-	 * Switch to new page-table
-	 *
-	 * For the boot CPU this switches to early_top_pgt which still has the
-	 * identity mappings present. The secondary CPUs will switch to the
-	 * init_top_pgt here, away from the trampoline_pgd and unmap the
-	 * identity mapped ranges.
+	 * Set CR4.PGE to re-enable global translations.
 	 */
-	movq	%rax, %cr3
-
-	/*
-	 * Do a global TLB flush after the CR3 switch to make sure the TLB
-	 * entries from the identity mapping are flushed.
-	 */
-	movq	%cr4, %rcx
-	movq	%rcx, %rax
-	xorq	$X86_CR4_PGE, %rcx
+	btsl	$X86_CR4_PGE_BIT, %ecx
 	movq	%rcx, %cr4
-	movq	%rax, %cr4
-
-	/* Ensure I am executing from virtual addresses */
-	movq	$1f, %rax
-	ANNOTATE_RETPOLINE_SAFE
-	jmp	*%rax
-1:
-	UNWIND_HINT_END_OF_STACK
-	ANNOTATE_NOENDBR // above
 
 #ifdef CONFIG_SMP
 	/*
@@ -297,7 +284,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 
 .Llookup_AP:
 	/* EAX contains the APIC ID of the current CPU */
-	xorq	%rcx, %rcx
+	xorl	%ecx, %ecx
 	leaq	cpuid_to_apicid(%rip), %rbx
 
 .Lfind_cpunr:
@@ -428,39 +415,10 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	movq	%r15, %rdi
 
 .Ljump_to_C_code:
-	/*
-	 * Jump to run C code and to be on a real kernel address.
-	 * Since we are running on identity-mapped space we have to jump
-	 * to the full 64bit address, this is only possible as indirect
-	 * jump.  In addition we need to ensure %cs is set so we make this
-	 * a far return.
-	 *
-	 * Note: do not change to far jump indirect with 64bit offset.
-	 *
-	 * AMD does not support far jump indirect with 64bit offset.
-	 * AMD64 Architecture Programmer's Manual, Volume 3: states only
-	 *	JMP FAR mem16:16 FF /5 Far jump indirect,
-	 *		with the target specified by a far pointer in memory.
-	 *	JMP FAR mem16:32 FF /5 Far jump indirect,
-	 *		with the target specified by a far pointer in memory.
-	 *
-	 * Intel64 does support 64bit offset.
-	 * Software Developer Manual Vol 2: states:
-	 *	FF /5 JMP m16:16 Jump far, absolute indirect,
-	 *		address given in m16:16
-	 *	FF /5 JMP m16:32 Jump far, absolute indirect,
-	 *		address given in m16:32.
-	 *	REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
-	 *		address given in m16:64.
-	 */
-	pushq	$.Lafter_lret	# put return address on stack for unwinder
 	xorl	%ebp, %ebp	# clear frame pointer
-	movq	initial_code(%rip), %rax
-	pushq	$__KERNEL_CS	# set correct cs
-	pushq	%rax		# target address in negative space
-	lretq
-.Lafter_lret:
-	ANNOTATE_NOENDBR
+	ANNOTATE_RETPOLINE_SAFE
+	callq	*initial_code(%rip)
+	ud2
 SYM_CODE_END(secondary_startup_64)
 
 #include "verify_cpu.S"
@@ -477,7 +435,7 @@ SYM_CODE_START(soft_restart_cpu)
 	UNWIND_HINT_END_OF_STACK
 
 	/* Find the idle task stack */
-	movq	PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx
+	movq	PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
@@ -622,7 +580,7 @@ SYM_CODE_END(vc_no_ghcb)
 #define SYM_DATA_START_PAGE_ALIGNED(name)			\
 	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Each PGD needs to be 8k long and 8k aligned.  We do not
  * ever go out to userspace with these, so we do not
@@ -655,7 +613,8 @@ SYM_CODE_END(vc_no_ghcb)
 	.balign 4
 
 SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
-	.fill	512,8,0
+	.fill	511,8,0
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	.fill	PTI_USER_PGD_FILL,8,0
 SYM_DATA_END(early_top_pgt)
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a38d0c93a66e..c96ae8fee95e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -568,7 +568,7 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id)
 	fwspec.param_count = 1;
 	fwspec.param[0] = hpet_id;
 
-	parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY);
+	parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI);
 	if (!parent) {
 		irq_domain_free_fwnode(fn);
 		kfree(domain_info);
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 660b601f1d6c..0cd53fa8c65d 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -337,7 +337,7 @@ void idt_invalidate(void)
 	load_idt(&idt);
 }
 
-void __init alloc_intr_gate(unsigned int n, const void *addr)
+void __init idt_install_sysvec(unsigned int n, const void *function)
 {
 	if (WARN_ON(n < FIRST_SYSTEM_VECTOR))
 		return;
@@ -346,5 +346,5 @@ void __init alloc_intr_gate(unsigned int n, const void *addr)
 		return;
 
 	if (!WARN_ON(test_and_set_bit(n, system_vectors)))
-		set_intr_gate(n, addr);
+		set_intr_gate(n, function);
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index c683666876f1..f79c5edc0b89 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -28,6 +28,7 @@
 #include <asm/setup.h>
 #include <asm/i8259.h>
 #include <asm/traps.h>
+#include <asm/fred.h>
 #include <asm/prom.h>
 
 /*
@@ -96,7 +97,11 @@ void __init native_init_IRQ(void)
 	/* Execute any quirks before the call gates are initialised: */
 	x86_init.irqs.pre_vector_init();
 
-	idt_setup_apic_and_irq_gates();
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		fred_complete_exception_setup();
+	else
+		idt_setup_apic_and_irq_gates();
+
 	lapic_assign_system_vectors();
 
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) {
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 578d16fc040f..df337860612d 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -89,7 +89,7 @@ static void __init jailhouse_x2apic_init(void)
 #endif
 }
 
-static void __init jailhouse_get_smp_config(unsigned int early)
+static void __init jailhouse_parse_smp_config(void)
 {
 	struct ioapic_domain_cfg ioapic_cfg = {
 		.type = IOAPIC_DOMAIN_STRICT,
@@ -102,7 +102,7 @@ static void __init jailhouse_get_smp_config(unsigned int early)
 	register_lapic_address(0xfee00000);
 
 	for (cpu = 0; cpu < setup_data.v1.num_cpus; cpu++)
-		generic_processor_info(setup_data.v1.cpu_ids[cpu]);
+		topology_register_apic(setup_data.v1.cpu_ids[cpu], CPU_ACPIID_INVALID, true);
 
 	smp_found_config = 1;
 
@@ -201,21 +201,23 @@ static void __init jailhouse_init_platform(void)
 	struct setup_data header;
 	void *mapping;
 
-	x86_init.irqs.pre_vector_init	= x86_init_noop;
-	x86_init.timers.timer_init	= jailhouse_timer_init;
-	x86_init.mpparse.get_smp_config	= jailhouse_get_smp_config;
-	x86_init.pci.arch_init		= jailhouse_pci_arch_init;
+	x86_init.irqs.pre_vector_init		= x86_init_noop;
+	x86_init.timers.timer_init		= jailhouse_timer_init;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+	x86_init.mpparse.parse_smp_cfg		= jailhouse_parse_smp_config;
+	x86_init.pci.arch_init			= jailhouse_pci_arch_init;
 
-	x86_platform.calibrate_cpu	= jailhouse_get_tsc;
-	x86_platform.calibrate_tsc	= jailhouse_get_tsc;
-	x86_platform.get_wallclock	= jailhouse_get_wallclock;
-	x86_platform.legacy.rtc		= 0;
-	x86_platform.legacy.warm_reset	= 0;
-	x86_platform.legacy.i8042	= X86_LEGACY_I8042_PLATFORM_ABSENT;
+	x86_platform.calibrate_cpu		= jailhouse_get_tsc;
+	x86_platform.calibrate_tsc		= jailhouse_get_tsc;
+	x86_platform.get_wallclock		= jailhouse_get_wallclock;
+	x86_platform.legacy.rtc			= 0;
+	x86_platform.legacy.warm_reset		= 0;
+	x86_platform.legacy.i8042		= X86_LEGACY_I8042_PLATFORM_ABSENT;
 
-	legacy_pic			= &null_legacy_pic;
+	legacy_pic				= &null_legacy_pic;
 
-	machine_ops.emergency_restart	= jailhouse_no_restart;
+	machine_ops.emergency_restart		= jailhouse_no_restart;
 
 	while (pa_data) {
 		mapping = early_memremap(pa_data, sizeof(header));
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 2a422e00ed4b..cde167b0ea92 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -503,7 +503,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.bufsz =  kernel_len - kern16_size;
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
-	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	if (header->pref_address < MIN_KERNEL_LOAD_ADDR)
+		kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	else
+		kbuf.buf_min = header->pref_address;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 517821b48391..36d6809c6c9e 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -324,7 +324,7 @@ static int can_optimize(unsigned long paddr)
 		 * However, the kernel built with retpolines or IBT has jump
 		 * tables disabled so the check can be skipped altogether.
 		 */
-		if (!IS_ENABLED(CONFIG_RETPOLINE) &&
+		if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) &&
 		    !IS_ENABLED(CONFIG_X86_KERNEL_IBT) &&
 		    insn_is_indirect_jump(&insn))
 			return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index dfe9945b9bec..101a7c1bf200 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void)
 {
 	int cpu;
 
-	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+	if (cc_vendor != CC_VENDOR_AMD ||
+	    !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 
 	for_each_possible_cpu(cpu) {
@@ -829,7 +830,7 @@ static void __init kvm_guest_init(void)
 
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
 		static_branch_enable(&kvm_async_pf_enabled);
-		alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_kvm_asyncpf_interrupt);
+		sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_kvm_asyncpf_interrupt);
 	}
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 5bb395551c44..5b2c15214a6b 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -154,15 +154,15 @@ static int kvm_cs_enable(struct clocksource *cs)
 	return 0;
 }
 
-struct clocksource kvm_clock = {
+static struct clocksource kvm_clock = {
 	.name	= "kvm-clock",
 	.read	= kvm_clock_get_cycles,
 	.rating	= 400,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+	.id     = CSID_X86_KVM_CLK,
 	.enable	= kvm_cs_enable,
 };
-EXPORT_SYMBOL_GPL(kvm_clock);
 
 static void kvm_register_clock(char *txt)
 {
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 7a814b41402d..0f19ef355f5f 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -184,7 +184,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	return new_ldt;
 }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 
 static void do_sanity_check(struct mm_struct *mm,
 			    bool had_kernel_mapping,
@@ -377,7 +377,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 	flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);
 }
 
-#else /* !CONFIG_PAGE_TABLE_ISOLATION */
+#else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
@@ -388,11 +388,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 {
 }
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
 static void free_ldt_pgtables(struct mm_struct *mm)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	struct mmu_gather tlb;
 	unsigned long start = LDT_BASE_ADDR;
 	unsigned long end = LDT_END_ADDR;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index b223922248e9..1ccd30c8246f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -36,6 +36,8 @@
  * Checksum an MP configuration block.
  */
 
+static unsigned int num_procs __initdata;
+
 static int __init mpf_checksum(unsigned char *mp, int len)
 {
 	int sum = 0;
@@ -50,16 +52,15 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 {
 	char *bootup_cpu = "";
 
-	if (!(m->cpuflag & CPU_ENABLED)) {
-		disabled_cpus++;
+	topology_register_apic(m->apicid, CPU_ACPIID_INVALID, m->cpuflag & CPU_ENABLED);
+	if (!(m->cpuflag & CPU_ENABLED))
 		return;
-	}
 
 	if (m->cpuflag & CPU_BOOTPROCESSOR)
 		bootup_cpu = " (Bootup-CPU)";
 
 	pr_info("Processor #%d%s\n", m->apicid, bootup_cpu);
-	generic_processor_info(m->apicid);
+	num_procs++;
 }
 
 #ifdef CONFIG_X86_IO_APIC
@@ -236,9 +237,9 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 		}
 	}
 
-	if (!num_processors)
+	if (!num_procs && !acpi_lapic)
 		pr_err("MPTABLE: no processors registered!\n");
-	return num_processors;
+	return num_procs || acpi_lapic;
 }
 
 #ifdef CONFIG_X86_IO_APIC
@@ -473,7 +474,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 /*
  * Scan the memory blocks for an SMP configuration block.
  */
-void __init default_get_smp_config(unsigned int early)
+static __init void mpparse_get_smp_config(unsigned int early)
 {
 	struct mpf_intel *mpf;
 
@@ -529,8 +530,8 @@ void __init default_get_smp_config(unsigned int early)
 	} else
 		BUG();
 
-	if (!early)
-		pr_info("Processors: %d\n", num_processors);
+	if (!early && !acpi_lapic)
+		pr_info("Processors: %d\n", num_procs);
 	/*
 	 * Only use the first configuration found.
 	 */
@@ -538,6 +539,16 @@ out:
 	early_memunmap(mpf, sizeof(*mpf));
 }
 
+void __init mpparse_parse_early_smp_config(void)
+{
+	mpparse_get_smp_config(true);
+}
+
+void __init mpparse_parse_smp_config(void)
+{
+	mpparse_get_smp_config(false);
+}
+
 static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr));
@@ -587,7 +598,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 	return ret;
 }
 
-void __init default_find_smp_config(void)
+void __init mpparse_find_mptable(void)
 {
 	unsigned int address;
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 17e955ab69fe..9a5b372c706f 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -35,6 +35,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/microcode.h>
 #include <asm/sev.h>
+#include <asm/fred.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -303,13 +304,13 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 
 	__this_cpu_add(nmi_stats.unknown, 1);
 
-	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
+	pr_emerg_ratelimited("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+			     reason, smp_processor_id());
 
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
 		nmi_panic(regs, "NMI: Not continuing");
 
-	pr_emerg("Dazed and confused, but trying to continue\n");
+	pr_emerg_ratelimited("Dazed and confused, but trying to continue\n");
 }
 NOKPROBE_SYMBOL(unknown_nmi_error);
 
@@ -502,7 +503,7 @@ DEFINE_IDTENTRY_RAW(exc_nmi)
 	if (IS_ENABLED(CONFIG_NMI_CHECK_CPU))
 		raw_atomic_long_inc(&nsp->idt_calls);
 
-	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) {
+	if (arch_cpu_is_offline(smp_processor_id())) {
 		if (microcode_nmi_handler_enabled())
 			microcode_offline_nmi_handler();
 		return;
@@ -563,9 +564,6 @@ nmi_restart:
 	}
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
-
-	if (user_mode(regs))
-		mds_user_clear_cpu_buffers();
 }
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
@@ -639,7 +637,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp)
 			msgp = nmi_check_stall_msg[idx];
 			if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1))
 				modp = ", but OK because ignore_nmis was set";
-			if (nmi_seq & ~0x1)
+			if (nmi_seq & 0x1)
 				msghp = " (CPU currently in NMI handler function)";
 			else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
 				msghp = " (CPU exited one NMI handler function)";
@@ -651,6 +649,47 @@ void nmi_backtrace_stall_check(const struct cpumask *btp)
 
 #endif
 
+#ifdef CONFIG_X86_FRED
+/*
+ * With FRED, CR2/DR6 is pushed to #PF/#DB stack frame during FRED
+ * event delivery, i.e., there is no problem of transient states.
+ * And NMI unblocking only happens when the stack frame indicates
+ * that so should happen.
+ *
+ * Thus, the NMI entry stub for FRED is really straightforward and
+ * as simple as most exception handlers. As such, #DB is allowed
+ * during NMI handling.
+ */
+DEFINE_FREDENTRY_NMI(exc_nmi)
+{
+	irqentry_state_t irq_state;
+
+	if (arch_cpu_is_offline(smp_processor_id())) {
+		if (microcode_nmi_handler_enabled())
+			microcode_offline_nmi_handler();
+		return;
+	}
+
+	/*
+	 * Save CR2 for eventual restore to cover the case where the NMI
+	 * hits the VMENTER/VMEXIT region where guest CR2 is life. This
+	 * prevents guest state corruption in case that the NMI handler
+	 * takes a page fault.
+	 */
+	this_cpu_write(nmi_cr2, read_cr2());
+
+	irq_state = irqentry_nmi_enter(regs);
+
+	inc_irq_stat(__nmi_count);
+	default_do_nmi(regs);
+
+	irqentry_nmi_exit(regs, irq_state);
+
+	if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+		write_cr2(this_cpu_read(nmi_cr2));
+}
+#endif
+
 void stop_nmi(void)
 {
 	ignore_nmis++;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ab49ade31b0d..b8441147eb5e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -846,31 +846,6 @@ void __noreturn stop_this_cpu(void *dummy)
 }
 
 /*
- * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
- * states (local apic timer and TSC stop).
- *
- * XXX this function is completely buggered vs RCU and tracing.
- */
-static void amd_e400_idle(void)
-{
-	/*
-	 * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
-	 * gets set after static_cpu_has() places have been converted via
-	 * alternatives.
-	 */
-	if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
-		default_idle();
-		return;
-	}
-
-	tick_broadcast_enter();
-
-	default_idle();
-
-	tick_broadcast_exit();
-}
-
-/*
  * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf
  * exists and whenever MONITOR/MWAIT extensions are present there is at
  * least one C1 substate.
@@ -878,21 +853,22 @@ static void amd_e400_idle(void)
  * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait
  * is passed to kernel commandline parameter.
  */
-static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
+static __init bool prefer_mwait_c1_over_halt(void)
 {
+	const struct cpuinfo_x86 *c = &boot_cpu_data;
 	u32 eax, ebx, ecx, edx;
 
-	/* User has disallowed the use of MWAIT. Fallback to HALT */
-	if (boot_option_idle_override == IDLE_NOMWAIT)
-		return 0;
+	/* If override is enforced on the command line, fall back to HALT. */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return false;
 
 	/* MWAIT is not supported on this platform. Fallback to HALT */
 	if (!cpu_has(c, X86_FEATURE_MWAIT))
-		return 0;
+		return false;
 
-	/* Monitor has a bug. Fallback to HALT */
-	if (boot_cpu_has_bug(X86_BUG_MONITOR))
-		return 0;
+	/* Monitor has a bug or APIC stops in C1E. Fallback to HALT */
+	if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E))
+		return false;
 
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
 
@@ -901,13 +877,13 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	 * with EAX=0, ECX=0.
 	 */
 	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED))
-		return 1;
+		return true;
 
 	/*
 	 * If MWAIT extensions are available, there should be at least one
 	 * MWAIT C1 substate present.
 	 */
-	return (edx & MWAIT_C1_SUBSTATE_MASK);
+	return !!(edx & MWAIT_C1_SUBSTATE_MASK);
 }
 
 /*
@@ -933,26 +909,27 @@ static __cpuidle void mwait_idle(void)
 	__current_clr_polling();
 }
 
-void select_idle_routine(const struct cpuinfo_x86 *c)
+void __init select_idle_routine(void)
 {
-#ifdef CONFIG_SMP
-	if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1)
-		pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
-#endif
-	if (x86_idle_set() || boot_option_idle_override == IDLE_POLL)
+	if (boot_option_idle_override == IDLE_POLL) {
+		if (IS_ENABLED(CONFIG_SMP) && __max_threads_per_core > 1)
+			pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
+		return;
+	}
+
+	/* Required to guard against xen_set_default_idle() */
+	if (x86_idle_set())
 		return;
 
-	if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
-		pr_info("using AMD E400 aware idle routine\n");
-		static_call_update(x86_idle, amd_e400_idle);
-	} else if (prefer_mwait_c1_over_halt(c)) {
+	if (prefer_mwait_c1_over_halt()) {
 		pr_info("using mwait in idle threads\n");
 		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
 		static_call_update(x86_idle, tdx_safe_halt);
-	} else
+	} else {
 		static_call_update(x86_idle, default_idle);
+	}
 }
 
 void amd_e400_c1e_apic_setup(void)
@@ -985,7 +962,10 @@ void __init arch_post_acpi_subsys_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		mark_tsc_unstable("TSC halt in AMD C1E");
-	pr_info("System has AMD C1E enabled\n");
+
+	if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE))
+		static_branch_enable(&arch_needs_tick_broadcast);
+	pr_info("System has AMD C1E erratum E400. Workaround enabled.\n");
 }
 
 static int __init idle_setup(char *str)
@@ -998,24 +978,14 @@ static int __init idle_setup(char *str)
 		boot_option_idle_override = IDLE_POLL;
 		cpu_idle_poll_ctrl(true);
 	} else if (!strcmp(str, "halt")) {
-		/*
-		 * When the boot option of idle=halt is added, halt is
-		 * forced to be used for CPU idle. In such case CPU C2/C3
-		 * won't be used again.
-		 * To continue to load the CPU idle driver, don't touch
-		 * the boot_option_idle_override.
-		 */
-		static_call_update(x86_idle, default_idle);
+		/* 'idle=halt' HALT for idle. C-states are disabled. */
 		boot_option_idle_override = IDLE_HALT;
 	} else if (!strcmp(str, "nomwait")) {
-		/*
-		 * If the boot option of "idle=nomwait" is added,
-		 * it means that mwait will be disabled for CPU C1/C2/C3
-		 * states.
-		 */
+		/* 'idle=nomwait' disables MWAIT for idle */
 		boot_option_idle_override = IDLE_NOMWAIT;
-	} else
-		return -1;
+	} else {
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1030,7 +1000,10 @@ unsigned long arch_align_stack(unsigned long sp)
 
 unsigned long arch_randomize_brk(struct mm_struct *mm)
 {
-	return randomize_page(mm->brk, 0x02000000);
+	if (mmap_is_ia32())
+		return randomize_page(mm->brk, SZ_32M);
+
+	return randomize_page(mm->brk, SZ_1G);
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 708c87b88cc1..0917c7f25720 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -156,13 +156,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
 			     *next = &next_p->thread;
-	struct fpu *prev_fpu = &prev->fpu;
 	int cpu = smp_processor_id();
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_p, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -209,7 +208,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	raw_cpu_write(pcpu_hot.current_task, next_p);
 
-	switch_fpu_finish();
+	switch_fpu_finish(next_p);
 
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in(next_p);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 33b268747bb7..7062b84dd467 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -56,6 +56,7 @@
 #include <asm/resctrl.h>
 #include <asm/unistd.h>
 #include <asm/fsgsbase.h>
+#include <asm/fred.h>
 #ifdef CONFIG_IA32_EMULATION
 /* Not included via unistd.h */
 #include <asm/unistd_32_ia32.h>
@@ -117,7 +118,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	printk("%sFS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
 	       log_lvl, fs, fsindex, gs, gsindex, shadowgs);
-	printk("%sCS:  %04lx DS: %04x ES: %04x CR0: %016lx\n",
+	printk("%sCS:  %04x DS: %04x ES: %04x CR0: %016lx\n",
 		log_lvl, regs->cs, ds, es, cr0);
 	printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n",
 		log_lvl, cr2, cr3, cr4);
@@ -166,7 +167,29 @@ static noinstr unsigned long __rdgsbase_inactive(void)
 
 	lockdep_assert_irqs_disabled();
 
-	if (!cpu_feature_enabled(X86_FEATURE_XENPV)) {
+	/*
+	 * SWAPGS is no longer needed thus NOT allowed with FRED because
+	 * FRED transitions ensure that an operating system can _always_
+	 * operate with its own GS base address:
+	 * - For events that occur in ring 3, FRED event delivery swaps
+	 *   the GS base address with the IA32_KERNEL_GS_BASE MSR.
+	 * - ERETU (the FRED transition that returns to ring 3) also swaps
+	 *   the GS base address with the IA32_KERNEL_GS_BASE MSR.
+	 *
+	 * And the operating system can still setup the GS segment for a
+	 * user thread without the need of loading a user thread GS with:
+	 * - Using LKGS, available with FRED, to modify other attributes
+	 *   of the GS segment without compromising its ability always to
+	 *   operate with its own GS base address.
+	 * - Accessing the GS segment base address for a user thread as
+	 *   before using RDMSR or WRMSR on the IA32_KERNEL_GS_BASE MSR.
+	 *
+	 * Note, LKGS loads the GS base address into the IA32_KERNEL_GS_BASE
+	 * MSR instead of the GS segment’s descriptor cache. As such, the
+	 * operating system never changes its runtime GS base address.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) &&
+	    !cpu_feature_enabled(X86_FEATURE_XENPV)) {
 		native_swapgs();
 		gsbase = rdgsbase();
 		native_swapgs();
@@ -191,7 +214,8 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase)
 {
 	lockdep_assert_irqs_disabled();
 
-	if (!cpu_feature_enabled(X86_FEATURE_XENPV)) {
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) &&
+	    !cpu_feature_enabled(X86_FEATURE_XENPV)) {
 		native_swapgs();
 		wrgsbase(gsbase);
 		native_swapgs();
@@ -505,7 +529,7 @@ void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
 static void
 start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 		    unsigned long new_sp,
-		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
+		    u16 _cs, u16 _ss, u16 _ds)
 {
 	WARN_ON_ONCE(regs != current_pt_regs());
 
@@ -522,11 +546,36 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	loadsegment(ds, _ds);
 	load_gs_index(0);
 
-	regs->ip		= new_ip;
-	regs->sp		= new_sp;
-	regs->cs		= _cs;
-	regs->ss		= _ss;
-	regs->flags		= X86_EFLAGS_IF;
+	regs->ip	= new_ip;
+	regs->sp	= new_sp;
+	regs->csx	= _cs;
+	regs->ssx	= _ss;
+	/*
+	 * Allow single-step trap and NMI when starting a new task, thus
+	 * once the new task enters user space, single-step trap and NMI
+	 * are both enabled immediately.
+	 *
+	 * Entering a new task is logically speaking a return from a
+	 * system call (exec, fork, clone, etc.). As such, if ptrace
+	 * enables single stepping a single step exception should be
+	 * allowed to trigger immediately upon entering user space.
+	 * This is not optional.
+	 *
+	 * NMI should *never* be disabled in user space. As such, this
+	 * is an optional, opportunistic way to catch errors.
+	 *
+	 * Paranoia: High-order 48 bits above the lowest 16 bit SS are
+	 * discarded by the legacy IRET instruction on all Intel, AMD,
+	 * and Cyrix/Centaur/VIA CPUs, thus can be set unconditionally,
+	 * even when FRED is not enabled. But we choose the safer side
+	 * to use these bits only when FRED is enabled.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
+		regs->fred_ss.swevent	= true;
+		regs->fred_ss.nmi	= true;
+	}
+
+	regs->flags	= X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 }
 
 void
@@ -562,14 +611,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
 	struct thread_struct *next = &next_p->thread;
-	struct fpu *prev_fpu = &prev->fpu;
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
 
-	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_p, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -623,7 +671,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	raw_cpu_write(pcpu_hot.current_task, next_p);
 	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
 
-	switch_fpu_finish();
+	switch_fpu_finish(next_p);
 
 	/* Reload sp0. */
 	update_task_stack(next_p);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 84201071dfac..46d5a8c520ad 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -970,10 +970,8 @@ void __init setup_arch(char **cmdline_p)
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
-	/*
-	 * Find and reserve possible boot-time SMP configuration:
-	 */
-	find_smp_config();
+	/* Find and reserve MPTABLE area */
+	x86_init.mpparse.find_mptable();
 
 	early_alloc_pgt_buf();
 
@@ -1090,7 +1088,9 @@ void __init setup_arch(char **cmdline_p)
 
 	early_platform_quirks();
 
+	/* Some platforms need the APIC registered for NUMA configuration */
 	early_acpi_boot_init();
+	x86_init.mpparse.early_parse_smp_cfg();
 
 	x86_flattree_get_config();
 
@@ -1131,24 +1131,19 @@ void __init setup_arch(char **cmdline_p)
 
 	early_quirks();
 
-	/*
-	 * Read APIC and some other early information from ACPI tables.
-	 */
-	acpi_boot_init();
-	x86_dtb_init();
+	topology_apply_cmdline_limits_early();
 
 	/*
-	 * get boot-time SMP configuration:
+	 * Parse SMP configuration. Try ACPI first and then the platform
+	 * specific parser.
 	 */
-	get_smp_config();
+	acpi_boot_init();
+	x86_init.mpparse.parse_smp_cfg();
 
-	/*
-	 * Systems w/o ACPI and mptables might not have it mapped the local
-	 * APIC yet, but prefill_possible_map() might need to access it.
-	 */
+	/* Last opportunity to detect and map the local APIC */
 	init_apic_mappings();
 
-	prefill_possible_map();
+	topology_init_possible_cpus();
 
 	init_cpu_to_node();
 	init_gi_nodes();
@@ -1211,6 +1206,16 @@ void __init i386_reserve_resources(void)
 
 #endif /* CONFIG_X86_32 */
 
+#ifndef CONFIG_SMP
+void __init smp_prepare_boot_cpu(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	*c = boot_cpu_data;
+	c->initialized = true;
+}
+#endif
+
 static struct notifier_block kernel_offset_notifier = {
 	.notifier_call = dump_kernel_offset
 };
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 1d24ec679915..8b04958da5e7 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -9,12 +9,18 @@
  * and is included directly into both code-bases.
  */
 
+#include <asm/setup_data.h>
+
 #ifndef __BOOT_COMPRESSED
-#define error(v)	pr_err(v)
-#define has_cpuflag(f)	boot_cpu_has(f)
+#define error(v)			pr_err(v)
+#define has_cpuflag(f)			boot_cpu_has(f)
+#define sev_printk(fmt, ...)		printk(fmt, ##__VA_ARGS__)
+#define sev_printk_rtl(fmt, ...)	printk_ratelimited(fmt, ##__VA_ARGS__)
 #else
 #undef WARN
 #define WARN(condition, format...) (!!(condition))
+#define sev_printk(fmt, ...)
+#define sev_printk_rtl(fmt, ...)
 #endif
 
 /* I/O parameters for CPUID-related helpers */
@@ -89,7 +95,8 @@ static bool __init sev_es_check_cpu_features(void)
 	return true;
 }
 
-static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
+static void __head __noreturn
+sev_es_terminate(unsigned int set, unsigned int reason)
 {
 	u64 val = GHCB_MSR_TERM_REQ;
 
@@ -326,13 +333,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
  */
 static const struct snp_cpuid_table *snp_cpuid_get_table(void)
 {
-	void *ptr;
-
-	asm ("lea cpuid_table_copy(%%rip), %0"
-	     : "=r" (ptr)
-	     : "p" (&cpuid_table_copy));
-
-	return ptr;
+	return &RIP_REL_REF(cpuid_table_copy);
 }
 
 /*
@@ -391,7 +392,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted)
 	return xsave_size;
 }
 
-static bool
+static bool __head
 snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -528,7 +529,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
  * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
  * should be treated as fatal by caller.
  */
-static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+static int __head
+snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
 
@@ -556,9 +558,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le
 		leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
 
 		/* Skip post-processing for out-of-range zero leafs. */
-		if (!(leaf->fn <= cpuid_std_range_max ||
-		      (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
-		      (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
+		if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) ||
+		      (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) ||
+		      (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max))))
 			return 0;
 	}
 
@@ -570,10 +572,11 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le
  * page yet, so it only supports the MSR based communication with the
  * hypervisor and only the CPUID exit-code.
  */
-void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
+void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 {
 	unsigned int subfn = lower_bits(regs->cx, 32);
 	unsigned int fn = lower_bits(regs->ax, 32);
+	u16 opcode = *(unsigned short *)regs->ip;
 	struct cpuid_leaf leaf;
 	int ret;
 
@@ -581,6 +584,10 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 	if (exit_code != SVM_EXIT_CPUID)
 		goto fail;
 
+	/* Is it really a CPUID insn? */
+	if (opcode != 0xa20f)
+		goto fail;
+
 	leaf.fn = fn;
 	leaf.subfn = subfn;
 
@@ -1016,7 +1023,8 @@ struct cc_setup_data {
  * Search for a Confidential Computing blob passed in as a setup_data entry
  * via the Linux Boot Protocol.
  */
-static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
+static __head
+struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
 {
 	struct cc_setup_data *sd = NULL;
 	struct setup_data *hdr;
@@ -1043,7 +1051,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
  * mapping needs to be updated in sync with all the changes to virtual memory
  * layout and related mapping facilities throughout the boot process.
  */
-static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
+static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 {
 	const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table;
 	int i;
@@ -1063,11 +1071,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 		const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
 
 		if (fn->eax_in == 0x0)
-			cpuid_std_range_max = fn->eax;
+			RIP_REL_REF(cpuid_std_range_max) = fn->eax;
 		else if (fn->eax_in == 0x40000000)
-			cpuid_hyp_range_max = fn->eax;
+			RIP_REL_REF(cpuid_hyp_range_max) = fn->eax;
 		else if (fn->eax_in == 0x80000000)
-			cpuid_ext_range_max = fn->eax;
+			RIP_REL_REF(cpuid_ext_range_max) = fn->eax;
 	}
 }
 
@@ -1170,3 +1178,92 @@ static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
 out:
 	return ret;
 }
+
+static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
+					    unsigned long exit_code)
+{
+	unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
+	u8 modrm = ctxt->insn.modrm.value;
+
+	switch (exit_code) {
+
+	case SVM_EXIT_IOIO:
+	case SVM_EXIT_NPF:
+		/* handled separately */
+		return ES_OK;
+
+	case SVM_EXIT_CPUID:
+		if (opcode == 0xa20f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_INVD:
+		if (opcode == 0x080f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MONITOR:
+		if (opcode == 0x010f && modrm == 0xc8)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MWAIT:
+		if (opcode == 0x010f && modrm == 0xc9)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MSR:
+		/* RDMSR */
+		if (opcode == 0x320f ||
+		/* WRMSR */
+		    opcode == 0x300f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDPMC:
+		if (opcode == 0x330f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSC:
+		if (opcode == 0x310f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSCP:
+		if (opcode == 0x010f && modrm == 0xf9)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_READ_DR7:
+		if (opcode == 0x210f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_VMMCALL:
+		if (opcode == 0x010f && modrm == 0xd9)
+			return ES_OK;
+
+		break;
+
+	case SVM_EXIT_WRITE_DR7:
+		if (opcode == 0x230f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_WBINVD:
+		if (opcode == 0x90f)
+			return ES_OK;
+		break;
+
+	default:
+		break;
+	}
+
+	sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
+		   opcode, exit_code, ctxt->regs->ip);
+
+	return ES_UNSUPPORTED;
+}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index c67285824e82..b59b09c2f284 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -25,6 +25,7 @@
 #include <linux/psp-sev.h>
 #include <uapi/linux/sev-guest.h>
 
+#include <asm/init.h>
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/sev.h>
@@ -59,6 +60,25 @@
 #define AP_INIT_CR0_DEFAULT		0x60000010
 #define AP_INIT_MXCSR_DEFAULT		0x1f80
 
+static const char * const sev_status_feat_names[] = {
+	[MSR_AMD64_SEV_ENABLED_BIT]		= "SEV",
+	[MSR_AMD64_SEV_ES_ENABLED_BIT]		= "SEV-ES",
+	[MSR_AMD64_SEV_SNP_ENABLED_BIT]		= "SEV-SNP",
+	[MSR_AMD64_SNP_VTOM_BIT]		= "vTom",
+	[MSR_AMD64_SNP_REFLECT_VC_BIT]		= "ReflectVC",
+	[MSR_AMD64_SNP_RESTRICTED_INJ_BIT]	= "RI",
+	[MSR_AMD64_SNP_ALT_INJ_BIT]		= "AI",
+	[MSR_AMD64_SNP_DEBUG_SWAP_BIT]		= "DebugSwap",
+	[MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT]	= "NoHostIBS",
+	[MSR_AMD64_SNP_BTB_ISOLATION_BIT]	= "BTBIsol",
+	[MSR_AMD64_SNP_VMPL_SSS_BIT]		= "VmplSSS",
+	[MSR_AMD64_SNP_SECURE_TSC_BIT]		= "SecureTSC",
+	[MSR_AMD64_SNP_VMGEXIT_PARAM_BIT]	= "VMGExitParam",
+	[MSR_AMD64_SNP_IBS_VIRT_BIT]		= "IBSVirt",
+	[MSR_AMD64_SNP_VMSA_REG_PROT_BIT]	= "VMSARegProt",
+	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
+};
+
 /* For early boot hypervisor communication in SEV-ES enabled guests */
 static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
 
@@ -682,8 +702,9 @@ static u64 __init get_jump_table_addr(void)
 	return ret;
 }
 
-static void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
-				  unsigned long npages, enum psc_op op)
+static void __head
+early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+		      unsigned long npages, enum psc_op op)
 {
 	unsigned long paddr_end;
 	u64 val;
@@ -739,7 +760,7 @@ e_term:
 	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
 }
 
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
 					 unsigned long npages)
 {
 	/*
@@ -748,7 +769,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd
 	 * This eliminates worries about jump tables or checking boot_cpu_data
 	 * in the cc_platform_has() function.
 	 */
-	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
 		return;
 
 	 /*
@@ -767,7 +788,7 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr
 	 * This eliminates worries about jump tables or checking boot_cpu_data
 	 * in the cc_platform_has() function.
 	 */
-	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
 		return;
 
 	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
@@ -1752,7 +1773,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
 					 struct ghcb *ghcb,
 					 unsigned long exit_code)
 {
-	enum es_result result;
+	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
+
+	if (result != ES_OK)
+		return result;
 
 	switch (exit_code) {
 	case SVM_EXIT_READ_DR7:
@@ -2059,7 +2083,7 @@ fail:
  *
  * Scan for the blob in that order.
  */
-static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
 {
 	struct cc_blob_sev_info *cc_info;
 
@@ -2085,7 +2109,7 @@ found_cc_info:
 	return cc_info;
 }
 
-bool __init snp_init(struct boot_params *bp)
+bool __head snp_init(struct boot_params *bp)
 {
 	struct cc_blob_sev_info *cc_info;
 
@@ -2107,7 +2131,7 @@ bool __init snp_init(struct boot_params *bp)
 	return true;
 }
 
-void __init __noreturn snp_abort(void)
+void __head __noreturn snp_abort(void)
 {
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
 }
@@ -2262,3 +2286,29 @@ static int __init snp_init_platform_device(void)
 	return 0;
 }
 device_initcall(snp_init_platform_device);
+
+void kdump_sev_callback(void)
+{
+	/*
+	 * Do wbinvd() on remote CPUs when SNP is enabled in order to
+	 * safely do SNP_SHUTDOWN on the local CPU.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		wbinvd();
+}
+
+void sev_show_status(void)
+{
+	int i;
+
+	pr_info("Status: ");
+	for (i = 0; i < MSR_AMD64_SNP_RESV_BIT; i++) {
+		if (sev_status & BIT_ULL(i)) {
+			if (!sev_status_feat_names[i])
+				continue;
+
+			pr_cont("%s ", sev_status_feat_names[i]);
+		}
+	}
+	pr_cont("\n");
+}
diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S
index 3355e27c69eb..1ab65f6c6ae7 100644
--- a/arch/x86/kernel/sev_verify_cbit.S
+++ b/arch/x86/kernel/sev_verify_cbit.S
@@ -77,7 +77,7 @@ SYM_FUNC_START(sev_verify_cbit)
 	 * The check failed, prevent any forward progress to prevent ROP
 	 * attacks, invalidate the stack and go into a hlt loop.
 	 */
-	xorq	%rsp, %rsp
+	xorl	%esp, %esp
 	subq	$0x1000, %rsp
 2:	hlt
 	jmp 2b
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 96a771f9f930..2908e063d7d8 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -148,14 +148,16 @@ static int register_stop_handler(void)
 
 static void native_stop_other_cpus(int wait)
 {
-	unsigned int cpu = smp_processor_id();
+	unsigned int old_cpu, this_cpu;
 	unsigned long flags, timeout;
 
 	if (reboot_force)
 		return;
 
 	/* Only proceed if this is the first CPU to reach this code */
-	if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1)
+	old_cpu = -1;
+	this_cpu = smp_processor_id();
+	if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu))
 		return;
 
 	/* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */
@@ -186,7 +188,7 @@ static void native_stop_other_cpus(int wait)
 	 * NMIs.
 	 */
 	cpumask_copy(&cpus_stop_mask, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &cpus_stop_mask);
+	cpumask_clear_cpu(this_cpu, &cpus_stop_mask);
 
 	if (!cpumask_empty(&cpus_stop_mask)) {
 		apic_send_IPI_allbutself(REBOOT_VECTOR);
@@ -210,6 +212,8 @@ static void native_stop_other_cpus(int wait)
 		 * CPUs to stop.
 		 */
 		if (!smp_no_nmi_ipi && !register_stop_handler()) {
+			unsigned int cpu;
+
 			pr_emerg("Shutting down cpus with NMI\n");
 
 			for_each_cpu(cpu, &cpus_stop_mask)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3f57ce68a3f1..fe355c89f6c1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,10 +101,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
 EXPORT_PER_CPU_SYMBOL(cpu_die_map);
 
-/* Per CPU bogomips and other parameters */
-DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
-EXPORT_PER_CPU_SYMBOL(cpu_info);
-
 /* CPUs which are the primary SMT threads */
 struct cpumask __cpu_primary_thread_mask __read_mostly;
 
@@ -125,25 +121,6 @@ struct mwait_cpu_dead {
  */
 static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead);
 
-/* Logical package management. */
-struct logical_maps {
-	u32	phys_pkg_id;
-	u32	phys_die_id;
-	u32	logical_pkg_id;
-	u32	logical_die_id;
-};
-
-/* Temporary workaround until the full topology mechanics is in place */
-static DEFINE_PER_CPU_READ_MOSTLY(struct logical_maps, logical_maps) = {
-	.phys_pkg_id	= U32_MAX,
-	.phys_die_id	= U32_MAX,
-};
-
-unsigned int __max_logical_packages __read_mostly;
-EXPORT_SYMBOL(__max_logical_packages);
-static unsigned int logical_packages __read_mostly;
-static unsigned int logical_die __read_mostly;
-
 /* Maximum number of SMT threads on any online core */
 int __read_mostly __max_smt_threads = 1;
 
@@ -336,103 +313,11 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- * @phys_pkg:	The physical package id to map
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg)
-			return per_cpu(logical_maps.logical_pkg_id, cpu);
-	}
-	return -1;
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
-/**
- * topology_phys_to_logical_die - Map a physical die id to logical
- * @die_id:	The physical die id to map
- * @cur_cpu:	The CPU for which the mapping is done
- *
- * Returns logical die id or -1 if not found
- */
-static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
-{
-	int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id;
-
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(logical_maps.phys_pkg_id, cpu) == proc_id &&
-		    per_cpu(logical_maps.phys_die_id, cpu) == die_id)
-			return per_cpu(logical_maps.logical_die_id, cpu);
-	}
-	return -1;
-}
-
-/**
- * topology_update_package_map - Update the physical to logical package map
- * @pkg:	The physical package id as retrieved via CPUID
- * @cpu:	The cpu for which this is updated
- */
-int topology_update_package_map(unsigned int pkg, unsigned int cpu)
-{
-	int new;
-
-	/* Already available somewhere? */
-	new = topology_phys_to_logical_pkg(pkg);
-	if (new >= 0)
-		goto found;
-
-	new = logical_packages++;
-	if (new != pkg) {
-		pr_info("CPU %u Converting physical %u to logical package %u\n",
-			cpu, pkg, new);
-	}
-found:
-	per_cpu(logical_maps.phys_pkg_id, cpu) = pkg;
-	per_cpu(logical_maps.logical_pkg_id, cpu) = new;
-	cpu_data(cpu).topo.logical_pkg_id = new;
-	return 0;
-}
-/**
- * topology_update_die_map - Update the physical to logical die map
- * @die:	The die id as retrieved via CPUID
- * @cpu:	The cpu for which this is updated
- */
-int topology_update_die_map(unsigned int die, unsigned int cpu)
-{
-	int new;
-
-	/* Already available somewhere? */
-	new = topology_phys_to_logical_die(die, cpu);
-	if (new >= 0)
-		goto found;
-
-	new = logical_die++;
-	if (new != die) {
-		pr_info("CPU %u Converting physical %u to logical die %u\n",
-			cpu, die, new);
-	}
-found:
-	per_cpu(logical_maps.phys_die_id, cpu) = die;
-	per_cpu(logical_maps.logical_die_id, cpu) = new;
-	cpu_data(cpu).topo.logical_die_id = new;
-	return 0;
-}
-
 static void __init smp_store_boot_cpu_info(void)
 {
-	int id = 0; /* CPU 0 */
-	struct cpuinfo_x86 *c = &cpu_data(id);
+	struct cpuinfo_x86 *c = &cpu_data(0);
 
 	*c = boot_cpu_data;
-	c->cpu_index = id;
-	topology_update_package_map(c->topo.pkg_id, id);
-	topology_update_die_map(c->topo.die_id, id);
 	c->initialized = true;
 }
 
@@ -488,6 +373,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 		if (c->topo.pkg_id == o->topo.pkg_id &&
 		    c->topo.die_id == o->topo.die_id &&
+		    c->topo.amd_node_id == o->topo.amd_node_id &&
 		    per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) {
 			if (c->topo.core_id == o->topo.core_id)
 				return topology_sane(c, o, "smt");
@@ -509,10 +395,13 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (c->topo.pkg_id == o->topo.pkg_id &&
-	    c->topo.die_id == o->topo.die_id)
-		return true;
-	return false;
+	if (c->topo.pkg_id != o->topo.pkg_id || c->topo.die_id != o->topo.die_id)
+		return false;
+
+	if (cpu_feature_enabled(X86_FEATURE_TOPOEXT) && topology_amd_nodes_per_pkg() > 1)
+		return c->topo.amd_node_id == o->topo.amd_node_id;
+
+	return true;
 }
 
 static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -670,8 +559,8 @@ static void __init build_sched_topology(void)
 
 void set_cpu_sibling_map(int cpu)
 {
-	bool has_smt = smp_num_siblings > 1;
-	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
+	bool has_smt = __max_threads_per_core > 1;
+	bool has_mp = has_smt || topology_num_cores_per_package() > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
 	int i, threads;
@@ -1068,9 +957,13 @@ int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
 
 	pr_debug("++++++++++++++++++++=_---CPU UP  %u\n", cpu);
 
-	if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) ||
-	    !apic_id_valid(apicid)) {
-		pr_err("%s: bad cpu %d\n", __func__, cpu);
+	if (apicid == BAD_APICID || !apic_id_valid(apicid)) {
+		pr_err("CPU %u has invalid APIC ID %x. Aborting bringup\n", cpu, apicid);
+		return -EINVAL;
+	}
+
+	if (!test_bit(apicid, phys_cpu_present_map)) {
+		pr_err("CPU %u APIC ID %x is not present. Aborting bringup\n", cpu, apicid);
 		return -EINVAL;
 	}
 
@@ -1139,14 +1032,8 @@ static __init void disable_smp(void)
 	pr_info("SMP disabled\n");
 
 	disable_ioapic_support();
+	topology_reset_possible_cpus_up();
 
-	init_cpu_present(cpumask_of(0));
-	init_cpu_possible(cpumask_of(0));
-
-	if (smp_found_config)
-		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
-	else
-		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
 	cpumask_set_cpu(0, topology_die_cpumask(0));
@@ -1187,6 +1074,11 @@ void __init smp_prepare_cpus_common(void)
 	set_cpu_sibling_map(0);
 }
 
+void __init smp_prepare_boot_cpu(void)
+{
+	smp_ops.smp_prepare_boot_cpu();
+}
+
 #ifdef CONFIG_X86_64
 /* Establish whether parallel bringup can be supported. */
 bool __init arch_cpuhp_init_parallel_bringup(void)
@@ -1265,102 +1157,16 @@ void __init native_smp_prepare_boot_cpu(void)
 	native_pv_lock_init();
 }
 
-void __init calculate_max_logical_packages(void)
-{
-	int ncpus;
-
-	/*
-	 * Today neither Intel nor AMD support heterogeneous systems so
-	 * extrapolate the boot cpu's data to all packages.
-	 */
-	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
-	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-	pr_info("Max logical packages: %u\n", __max_logical_packages);
-}
-
 void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done\n");
 
-	calculate_max_logical_packages();
 	build_sched_topology();
 	nmi_selftest();
 	impress_friends();
 	cache_aps_init();
 }
 
-static int __initdata setup_possible_cpus = -1;
-static int __init _setup_possible_cpus(char *str)
-{
-	get_option(&str, &setup_possible_cpus);
-	return 0;
-}
-early_param("possible_cpus", _setup_possible_cpus);
-
-
-/*
- * cpu_possible_mask should be static, it cannot change as cpu's
- * are onlined, or offlined. The reason is per-cpu data-structures
- * are allocated by some modules at init time, and don't expect to
- * do this dynamically on cpu arrival/departure.
- * cpu_present_mask on the other hand can change dynamically.
- * In case when cpu_hotplug is not compiled, then we resort to current
- * behaviour, which is cpu_possible == cpu_present.
- * - Ashok Raj
- *
- * Three ways to find out the number of additional hotplug CPUs:
- * - If the BIOS specified disabled CPUs in ACPI/mptables use that.
- * - The user can overwrite it with possible_cpus=NUM
- * - Otherwise don't reserve additional CPUs.
- * We do this because additional CPUs waste a lot of memory.
- * -AK
- */
-__init void prefill_possible_map(void)
-{
-	int i, possible;
-
-	i = setup_max_cpus ?: 1;
-	if (setup_possible_cpus == -1) {
-		possible = num_processors;
-#ifdef CONFIG_HOTPLUG_CPU
-		if (setup_max_cpus)
-			possible += disabled_cpus;
-#else
-		if (possible > i)
-			possible = i;
-#endif
-	} else
-		possible = setup_possible_cpus;
-
-	total_cpus = max_t(int, possible, num_processors + disabled_cpus);
-
-	/* nr_cpu_ids could be reduced via nr_cpus= */
-	if (possible > nr_cpu_ids) {
-		pr_warn("%d Processors exceeds NR_CPUS limit of %u\n",
-			possible, nr_cpu_ids);
-		possible = nr_cpu_ids;
-	}
-
-#ifdef CONFIG_HOTPLUG_CPU
-	if (!setup_max_cpus)
-#endif
-	if (possible > i) {
-		pr_warn("%d Processors exceeds max_cpus limit of %u\n",
-			possible, setup_max_cpus);
-		possible = i;
-	}
-
-	set_nr_cpu_ids(possible);
-
-	pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
-		possible, max_t(int, possible - num_processors, 0));
-
-	reset_cpu_possible_mask();
-
-	for (i = 0; i < possible; i++)
-		set_cpu_possible(i, true);
-}
-
 /* correctly size the local cpu masks */
 void __init setup_cpu_local_masks(void)
 {
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 77a9316da435..4eefaac64c6c 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -172,7 +172,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 /*
  * This is called by apply_returns() to fix up static call trampolines,
  * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 8e2b2552b5ee..3e2952679b88 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -6,7 +6,9 @@
 #include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/ptrace.h>
+
 #include <asm/desc.h>
+#include <asm/debugreg.h>
 #include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index c783aeb37dce..cb9fa1d5c66f 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -52,13 +52,6 @@ static unsigned long get_align_bits(void)
 	return va_align.bits & get_align_mask();
 }
 
-unsigned long align_vdso_addr(unsigned long addr)
-{
-	unsigned long align_mask = get_align_mask();
-	addr = (addr + align_mask) & ~align_mask;
-	return addr | get_align_bits();
-}
-
 static int __init control_va_addr_alignment(char *str)
 {
 	/* guard against enabling this on other CPU families */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c3b2f863acf0..4fa0b17e5043 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -51,6 +51,7 @@
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
+#include <asm/fred.h>
 #include <asm/fpu/api.h>
 #include <asm/cpu.h>
 #include <asm/cpu_entry_area.h>
@@ -773,7 +774,7 @@ DEFINE_IDTENTRY_RAW(exc_int3)
  */
 asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
-	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1;
+	struct pt_regs *regs = (struct pt_regs *)current_top_of_stack() - 1;
 	if (regs != eregs)
 		*regs = *eregs;
 	return regs;
@@ -791,7 +792,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	 * trust it and switch to the current kernel stack
 	 */
 	if (ip_within_syscall_gap(regs)) {
-		sp = this_cpu_read(pcpu_hot.top_of_stack);
+		sp = current_top_of_stack();
 		goto sync;
 	}
 
@@ -935,8 +936,7 @@ static bool notify_debug(struct pt_regs *regs, unsigned long *dr6)
 	return false;
 }
 
-static __always_inline void exc_debug_kernel(struct pt_regs *regs,
-					     unsigned long dr6)
+static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6)
 {
 	/*
 	 * Disable breakpoints during exception handling; recursive exceptions
@@ -948,6 +948,11 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 *
 	 * Entry text is excluded for HW_BP_X and cpu_entry_area, which
 	 * includes the entry stack is excluded for everything.
+	 *
+	 * For FRED, nested #DB should just work fine. But when a watchpoint or
+	 * breakpoint is set in the code path which is executed by #DB handler,
+	 * it results in an endless recursion and stack overflow. Thus we stay
+	 * with the IDT approach, i.e., save DR7 and disable #DB.
 	 */
 	unsigned long dr7 = local_db_save();
 	irqentry_state_t irq_state = irqentry_nmi_enter(regs);
@@ -977,7 +982,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
 	 * watchpoint at the same time then that will still be handled.
 	 */
-	if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
+	if (!cpu_feature_enabled(X86_FEATURE_FRED) &&
+	    (dr6 & DR_STEP) && is_sysenter_singlestep(regs))
 		dr6 &= ~DR_STEP;
 
 	/*
@@ -1009,8 +1015,7 @@ out:
 	local_db_restore(dr7);
 }
 
-static __always_inline void exc_debug_user(struct pt_regs *regs,
-					   unsigned long dr6)
+static noinstr void exc_debug_user(struct pt_regs *regs, unsigned long dr6)
 {
 	bool icebp;
 
@@ -1094,6 +1099,34 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
 	exc_debug_user(regs, debug_read_clear_dr6());
 }
+
+#ifdef CONFIG_X86_FRED
+/*
+ * When occurred on different ring level, i.e., from user or kernel
+ * context, #DB needs to be handled on different stack: User #DB on
+ * current task stack, while kernel #DB on a dedicated stack.
+ *
+ * This is exactly how FRED event delivery invokes an exception
+ * handler: ring 3 event on level 0 stack, i.e., current task stack;
+ * ring 0 event on the #DB dedicated stack specified in the
+ * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED debug exception
+ * entry stub doesn't do stack switch.
+ */
+DEFINE_FREDENTRY_DEBUG(exc_debug)
+{
+	/*
+	 * FRED #DB stores DR6 on the stack in the format which
+	 * debug_read_clear_dr6() returns for the IDT entry points.
+	 */
+	unsigned long dr6 = fred_event_data(regs);
+
+	if (user_mode(regs))
+		exc_debug_user(regs, dr6);
+	else
+		exc_debug_kernel(regs, dr6);
+}
+#endif /* CONFIG_X86_FRED */
+
 #else
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
@@ -1369,8 +1402,34 @@ DEFINE_IDTENTRY_SW(iret_error)
 }
 #endif
 
+/* Do not enable FRED by default yet. */
+static bool enable_fred __ro_after_init = false;
+
+#ifdef CONFIG_X86_FRED
+static int __init fred_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
+		return 0;
+
+	if (!strcmp(str, "on"))
+		enable_fred = true;
+	else if (!strcmp(str, "off"))
+		enable_fred = false;
+	else
+		pr_warn("invalid FRED option: 'fred=%s'\n", str);
+	return 0;
+}
+early_param("fred", fred_setup);
+#endif
+
 void __init trap_init(void)
 {
+	if (cpu_feature_enabled(X86_FEATURE_FRED) && !enable_fred)
+		setup_clear_cpu_cap(X86_FEATURE_FRED);
+
 	/* Init cpu_entry_area before IST entries are set up */
 	setup_cpu_entry_areas();
 
@@ -1379,7 +1438,10 @@ void __init trap_init(void)
 
 	/* Initialize TSS before setting up traps so ISTs work */
 	cpu_init_exception_handling();
+
 	/* Setup traps as cpu_init() might #GP */
-	idt_setup_traps();
+	if (!cpu_feature_enabled(X86_FEATURE_FRED))
+		idt_setup_traps();
+
 	cpu_init();
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 15f97c0abc9d..5a69a49acc96 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -53,7 +53,7 @@ static int __read_mostly tsc_force_recalibrate;
 static u32 art_to_tsc_numerator;
 static u32 art_to_tsc_denominator;
 static u64 art_to_tsc_offset;
-static struct clocksource *art_related_clocksource;
+static bool have_art;
 
 struct cyc2ns {
 	struct cyc2ns_data data[2];	/*  0 + 2*16 = 32 */
@@ -652,7 +652,7 @@ success:
 }
 
 /**
- * native_calibrate_tsc
+ * native_calibrate_tsc - determine TSC frequency
  * Determine TSC frequency via CPUID, else return 0.
  */
 unsigned long native_calibrate_tsc(void)
@@ -1168,6 +1168,7 @@ static struct clocksource clocksource_tsc_early = {
 	.mask			= CLOCKSOURCE_MASK(64),
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_MUST_VERIFY,
+	.id			= CSID_X86_TSC_EARLY,
 	.vdso_clock_mode	= VDSO_CLOCKMODE_TSC,
 	.enable			= tsc_cs_enable,
 	.resume			= tsc_resume,
@@ -1190,6 +1191,7 @@ static struct clocksource clocksource_tsc = {
 				  CLOCK_SOURCE_VALID_FOR_HRES |
 				  CLOCK_SOURCE_MUST_VERIFY |
 				  CLOCK_SOURCE_VERIFY_PERCPU,
+	.id			= CSID_X86_TSC,
 	.vdso_clock_mode	= VDSO_CLOCKMODE_TSC,
 	.enable			= tsc_cs_enable,
 	.resume			= tsc_resume,
@@ -1309,8 +1311,10 @@ struct system_counterval_t convert_art_to_tsc(u64 art)
 	do_div(tmp, art_to_tsc_denominator);
 	res += tmp + art_to_tsc_offset;
 
-	return (struct system_counterval_t) {.cs = art_related_clocksource,
-			.cycles = res};
+	return (struct system_counterval_t) {
+		.cs_id	= have_art ? CSID_X86_TSC : CSID_GENERIC,
+		.cycles	= res,
+	};
 }
 EXPORT_SYMBOL(convert_art_to_tsc);
 
@@ -1327,12 +1331,10 @@ EXPORT_SYMBOL(convert_art_to_tsc);
  * that this flag is set before conversion to TSC is attempted.
  *
  * Return:
- * struct system_counterval_t - system counter value with the pointer to the
- *	corresponding clocksource
- *	@cycles:	System counter value
- *	@cs:		Clocksource corresponding to system counter value. Used
- *			by timekeeping code to verify comparability of two cycle
- *			values.
+ * struct system_counterval_t - system counter value with the ID of the
+ *	corresponding clocksource:
+ *	cycles:		System counter value
+ *	cs_id:		The clocksource ID for validating comparability
  */
 
 struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns)
@@ -1347,8 +1349,10 @@ struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns)
 	do_div(tmp, USEC_PER_SEC);
 	res += tmp;
 
-	return (struct system_counterval_t) { .cs = art_related_clocksource,
-					      .cycles = res};
+	return (struct system_counterval_t) {
+		.cs_id	= have_art ? CSID_X86_TSC : CSID_GENERIC,
+		.cycles	= res,
+	};
 }
 EXPORT_SYMBOL(convert_art_ns_to_tsc);
 
@@ -1357,7 +1361,7 @@ static void tsc_refine_calibration_work(struct work_struct *work);
 static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
 /**
  * tsc_refine_calibration_work - Further refine tsc freq calibration
- * @work - ignored.
+ * @work: ignored.
  *
  * This functions uses delayed work over a period of a
  * second to further refine the TSC freq value. Since this is
@@ -1455,7 +1459,7 @@ out:
 		goto unreg;
 
 	if (boot_cpu_has(X86_FEATURE_ART))
-		art_related_clocksource = &clocksource_tsc;
+		have_art = true;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 unreg:
 	clocksource_unregister(&clocksource_tsc_early);
@@ -1481,7 +1485,7 @@ static int __init init_tsc_clocksource(void)
 	 */
 	if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
 		if (boot_cpu_has(X86_FEATURE_ART))
-			art_related_clocksource = &clocksource_tsc;
+			have_art = true;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
 		clocksource_unregister(&clocksource_tsc_early);
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a349dbfc6d5a..56451fd2099e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ ENTRY(phys_startup_64)
 #endif
 
 jiffies = jiffies_64;
+const_pcpu_hot = pcpu_hot;
 
 #if defined(CONFIG_X86_64)
 /*
@@ -132,7 +133,7 @@ SECTIONS
 		LOCK_TEXT
 		KPROBES_TEXT
 		SOFTIRQENTRY_TEXT
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 		*(.text..__x86.indirect_thunk)
 		*(.text..__x86.return_thunk)
 #endif
@@ -142,7 +143,7 @@ SECTIONS
 		*(.text..__x86.rethunk_untrain)
 		ENTRY_TEXT
 
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
 		/*
 		 * See the comment above srso_alias_untrain_ret()'s
 		 * definition.
@@ -267,7 +268,7 @@ SECTIONS
 	}
 #endif
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	/*
 	 * List of instructions that call/jmp/jcc to retpoline thunks
 	 * __x86_indirect_thunk_*(). These instructions can be patched along
@@ -504,11 +505,11 @@ INIT_PER_CPU(irq_stack_backing_store);
            "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
 #endif
 
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
 . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
 /*
  * GNU ld cannot do XOR until 2.41.
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index d3fc01770558..73511332bb67 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -127,25 +127,12 @@ static void __init vsmp_cap_cpus(void)
 #endif
 }
 
-static u32 apicid_phys_pkg_id(u32 initial_apic_id, int index_msb)
-{
-	return read_apic_id() >> index_msb;
-}
-
-static void vsmp_apic_post_init(void)
-{
-	/* need to update phys_pkg_id */
-	apic->phys_pkg_id = apicid_phys_pkg_id;
-}
-
 void __init vsmp_init(void)
 {
 	detect_vsmp_box();
 	if (!is_vsmp_box())
 		return;
 
-	x86_platform.apic_post_init = vsmp_apic_post_init;
-
 	vsmp_cap_cpus();
 
 	set_vsmp_ctl();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index a37ebd3b4773..a42830dc151b 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -70,8 +70,9 @@ struct x86_init_ops x86_init __initdata = {
 
 	.mpparse = {
 		.setup_ioapic_ids	= x86_init_noop,
-		.find_smp_config	= default_find_smp_config,
-		.get_smp_config		= default_get_smp_config,
+		.find_mptable		= mpparse_find_mptable,
+		.early_parse_smp_cfg	= mpparse_parse_early_smp_config,
+		.parse_smp_cfg		= mpparse_parse_smp_config,
 	},
 
 	.irqs = {
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 87e3da7b0439..65ed14b6540b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -80,9 +80,10 @@ config KVM_SW_PROTECTED_VM
 	depends on KVM && X86_64
 	select KVM_GENERIC_PRIVATE_MEM
 	help
-	  Enable support for KVM software-protected VMs.  Currently "protected"
-	  means the VM can be backed with memory provided by
-	  KVM_CREATE_GUEST_MEMFD.
+	  Enable support for KVM software-protected VMs.  Currently, software-
+	  protected VMs are purely a development and testing vehicle for
+	  KVM_CREATE_GUEST_MEMFD.  Attempting to run a "real" VM workload as a
+	  software-protected VM will fail miserably.
 
 	  If unsure, say "N".
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4943f6b2bbee..8a47f8541eab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
 	return false;
 }
 
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_hv *hv = to_kvm_hv(kvm);
+
+	/* Check again under the hv_lock.  */
+	if (hv->xsaves_xsavec_checked)
+		return;
+
+	if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+	    KVM_HV_WIN2016_GUEST_ID)
+		return;
+
+	hv->xsaves_xsavec_checked = true;
+
+	/* UP configurations aren't affected */
+	if (atomic_read(&kvm->online_vcpus) < 2)
+		return;
+
+	if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+	    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+		return;
+
+	pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+			      "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+	struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+	if (!vcpu->arch.hyperv_enabled ||
+	    hv->xsaves_xsavec_checked)
+		return;
+
+	mutex_lock(&hv->hv_lock);
+	__kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+	mutex_unlock(&hv->hv_lock);
+}
+
 static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			     bool host)
 {
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 1dc0b6604526..923e64903da9 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -182,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 			   struct pvclock_vcpu_time_info *hv_clock);
 void kvm_hv_request_tsc_page_update(struct kvm *kvm);
 
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu);
+
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
@@ -267,6 +269,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
 static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
 					 struct pvclock_vcpu_time_info *hv_clock) {}
 static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {}
 static inline void kvm_hv_init_vm(struct kvm *kvm) {}
 static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
 static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3242f3da2457..1edf93ee3395 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2815,7 +2815,10 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 
 	vcpu->arch.apic = apic;
 
-	apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+	if (kvm_x86_ops.alloc_apic_backing_page)
+		apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu);
+	else
+		apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!apic->regs) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
 		       vcpu->vcpu_id);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d6cdeab1f8a..9a905f10e10c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -53,12 +53,11 @@
 #include <asm/cmpxchg.h>
 #include <asm/io.h>
 #include <asm/set_memory.h>
+#include <asm/spec-ctrl.h>
 #include <asm/vmx.h>
 
 #include "trace.h"
 
-extern bool itlb_multihit_kvm_mitigation;
-
 static bool nx_hugepage_mitigation_hard_disabled;
 
 int __read_mostly nx_huge_pages = -1;
@@ -263,7 +262,7 @@ static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu)
 static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu,
 						  struct kvm_mmu *mmu)
 {
-	if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3)
+	if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3)
 		return kvm_read_cr3(vcpu);
 
 	return mmu->get_guest_pgd(vcpu);
@@ -4405,6 +4404,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event before getting
+	 * the pfn from the primary MMU, and before acquiring mmu_lock.
+	 *
+	 * For mmu_lock, if there is an in-progress invalidation and the kernel
+	 * allows preemption, the invalidation task may drop mmu_lock and yield
+	 * in response to mmu_lock being contended, which is *very* counter-
+	 * productive as this vCPU can't actually make forward progress until
+	 * the invalidation completes.
+	 *
+	 * Retrying now can also avoid unnessary lock contention in the primary
+	 * MMU, as the primary MMU doesn't necessarily hold a single lock for
+	 * the duration of the invalidation, i.e. faulting in a conflicting pfn
+	 * can cause the invalidation to take longer by holding locks that are
+	 * needed to complete the invalidation.
+	 *
+	 * Do the pre-check even for non-preemtible kernels, i.e. even if KVM
+	 * will never yield mmu_lock in response to contention, as this vCPU is
+	 * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
+	 * to detect retry guarantees the worst case latency for the vCPU.
+	 */
+	if (fault->slot &&
+	    mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+		return RET_PF_RETRY;
+
 	ret = __kvm_faultin_pfn(vcpu, fault);
 	if (ret != RET_PF_CONTINUE)
 		return ret;
@@ -4415,6 +4439,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (unlikely(!fault->slot))
 		return kvm_handle_noslot_fault(vcpu, fault, access);
 
+	/*
+	 * Check again for a relevant mmu_notifier invalidation event purely to
+	 * avoid contending mmu_lock.  Most invalidations will be detected by
+	 * the previous check, but checking is extremely cheap relative to the
+	 * overall cost of failing to detect the invalidation until after
+	 * mmu_lock is acquired.
+	 */
+	if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) {
+		kvm_release_pfn_clean(fault->pfn);
+		return RET_PF_RETRY;
+	}
+
 	return RET_PF_CONTINUE;
 }
 
@@ -4442,6 +4478,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 	if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu))
 		return true;
 
+	/*
+	 * Check for a relevant mmu_notifier invalidation event one last time
+	 * now that mmu_lock is held, as the "unsafe" checks performed without
+	 * holding mmu_lock can get false negatives.
+	 */
 	return fault->slot &&
 	       mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
 }
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 0669a8a668ca..5390a591a571 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -315,7 +315,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	if (!prefetch)
 		vcpu->stat.pf_taken++;
 
-	if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp)
+	if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp)
 		r = kvm_tdp_page_fault(vcpu, &fault);
 	else
 		r = vcpu->arch.mmu->page_fault(vcpu, &fault);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index dee62362a360..55b9a6d96bcf 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm)
 	if (svm->nested.initialized)
 		return 0;
 
-	vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	vmcb02_page = snp_safe_alloc_page(&svm->vcpu);
 	if (!vmcb02_page)
 		return -ENOMEM;
 	svm->nested.vmcb02.ptr = page_address(vmcb02_page);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f760106c31f8..ae0ac12382b9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -57,7 +57,7 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = true;
+static bool sev_es_debug_swap_enabled = false;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
@@ -246,6 +246,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_platform_init_args init_args = {0};
 	int asid, ret;
 
 	if (kvm->created_vcpus)
@@ -262,7 +263,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		goto e_no_asid;
 	sev->asid = asid;
 
-	ret = sev_platform_init(&argp->error);
+	init_args.probe = false;
+	ret = sev_platform_init(&init_args);
 	if (ret)
 		goto e_free;
 
@@ -274,6 +276,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
+	argp->error = init_args.error;
 	sev_asid_free(sev);
 	sev->asid = 0;
 e_no_asid:
@@ -612,8 +615,11 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
-	if (sev_es_debug_swap_enabled)
+	if (sev_es_debug_swap_enabled) {
 		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+		pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
+			     "This will not work starting with Linux 6.10\n");
+	}
 
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
@@ -1975,20 +1981,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		goto e_free;
 	}
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
 	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
+	 * correct C-bit.  Note, this must be done before dropping kvm->lock,
+	 * as region and its array of pages can be freed by a different task
+	 * once kvm->lock is released.
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 
 e_free:
@@ -3160,3 +3168,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 
 	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
 }
+
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
+{
+	unsigned long pfn;
+	struct page *p;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+
+	/*
+	 * Allocate an SNP-safe page to workaround the SNP erratum where
+	 * the CPU will incorrectly signal an RMP violation #PF if a
+	 * hugepage (2MB or 1GB) collides with the RMP entry of a
+	 * 2MB-aligned VMCB, VMSA, or AVIC backing page.
+	 *
+	 * Allocate one extra page, choose a page which is not
+	 * 2MB-aligned, and free the other.
+	 */
+	p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+	if (!p)
+		return NULL;
+
+	split_page(p, 1);
+
+	pfn = page_to_pfn(p);
+	if (IS_ALIGNED(pfn, PTRS_PER_PMD))
+		__free_page(p++);
+	else
+		__free_page(p + 1);
+
+	return p;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index e90b429c84f1..272d5ed37ce7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -703,7 +703,7 @@ static int svm_cpu_init(int cpu)
 	int ret = -ENOMEM;
 
 	memset(sd, 0, sizeof(struct svm_cpu_data));
-	sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	sd->save_area = snp_safe_alloc_page(NULL);
 	if (!sd->save_area)
 		return ret;
 
@@ -1421,7 +1421,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 	svm = to_svm(vcpu);
 
 	err = -ENOMEM;
-	vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	vmcb01_page = snp_safe_alloc_page(vcpu);
 	if (!vmcb01_page)
 		goto out;
 
@@ -1430,7 +1430,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
 		 * SEV-ES guests require a separate VMSA page used to contain
 		 * the encrypted register state of the guest.
 		 */
-		vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		vmsa_page = snp_safe_alloc_page(vcpu);
 		if (!vmsa_page)
 			goto error_free_vmcb_page;
 
@@ -3455,7 +3455,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
 	if (!svm_check_exit_valid(exit_code))
 		return svm_handle_invalid_exit(vcpu, exit_code);
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_code == SVM_EXIT_MSR)
 		return msr_interception(vcpu);
 	else if (exit_code == SVM_EXIT_VINTR)
@@ -4900,6 +4900,16 @@ static int svm_vm_init(struct kvm *kvm)
 	return 0;
 }
 
+static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
+{
+	struct page *page = snp_safe_alloc_page(vcpu);
+
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
 static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -5031,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
+	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 8ef95139cd24..7f1fbd874c45 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -694,6 +694,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm);
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa);
 void sev_es_unmap_ghcb(struct vcpu_svm *svm);
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
 
 /* vmenter.S */
 
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a707..4e725854c63a 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
 
 #define svm_asm(insn, clobber...)				\
 do {								\
-	asm_volatile_goto("1: " __stringify(insn) "\n\t"	\
+	asm goto("1: " __stringify(insn) "\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  ::: clobber : fault);			\
 	return;							\
@@ -18,7 +18,7 @@ fault:								\
 
 #define svm_asm1(insn, op1, clobber...)				\
 do {								\
-	asm_volatile_goto("1: "  __stringify(insn) " %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  :: op1 : clobber : fault);		\
 	return;							\
@@ -28,7 +28,7 @@ fault:								\
 
 #define svm_asm2(insn, op1, op2, clobber...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])			\
 			  :: op1, op2 : clobber : fault);		\
 	return;								\
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 9499f9c6b077..187018c424bf 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -207,7 +207,7 @@ SYM_FUNC_START(__svm_vcpu_run)
 7:	vmload %_ASM_AX
 8:
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 #endif
@@ -344,7 +344,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	/* Pop @svm to RDI, guest registers have been saved already. */
 	pop %_ASM_DI
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 #endif
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a6216c874729..315c7c2ba89b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
 	struct kvm_pmc *pmc;
-	u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+	u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
 	int i;
 
 	pmu->fixed_ctr_ctrl = data;
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
index edc3f16cc189..6a9bfdfbb6e5 100644
--- a/arch/x86/kvm/vmx/run_flags.h
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -2,7 +2,10 @@
 #ifndef __KVM_X86_VMX_RUN_FLAGS_H
 #define __KVM_X86_VMX_RUN_FLAGS_H
 
-#define VMX_RUN_VMRESUME	(1 << 0)
-#define VMX_RUN_SAVE_SPEC_CTRL	(1 << 1)
+#define VMX_RUN_VMRESUME_SHIFT		0
+#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT	1
+
+#define VMX_RUN_VMRESUME		BIT(VMX_RUN_VMRESUME_SHIFT)
+#define VMX_RUN_SAVE_SPEC_CTRL		BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
 
 #endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 906ecd001511..2bfbf758d061 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	mov (%_ASM_SP), %_ASM_AX
 
 	/* Check if vmlaunch or vmresume is needed */
-	test $VMX_RUN_VMRESUME, %ebx
+	bt   $VMX_RUN_VMRESUME_SHIFT, %ebx
 
 	/* Load guest registers.  Don't clobber flags. */
 	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
@@ -161,8 +161,11 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	/* Load guest RAX.  This kills the @regs pointer! */
 	mov VCPU_RAX(%_ASM_AX), %_ASM_AX
 
-	/* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */
-	jz .Lvmlaunch
+	/* Clobbers EFLAGS.ZF */
+	CLEAR_CPU_BUFFERS
+
+	/* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */
+	jnc .Lvmlaunch
 
 	/*
 	 * After a successful VMRESUME/VMLAUNCH, control flow "magically"
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e262bc2ba4e5..305237dcba88 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -38,6 +38,7 @@
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/fred.h>
 #include <asm/idtentry.h>
 #include <asm/io.h>
 #include <asm/irq_remapping.h>
@@ -388,7 +389,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+	/*
+	 * Disable VERW's behavior of clearing CPU buffers for the guest if the
+	 * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled
+	 * the mitigation. Disabling the clearing behavior provides a
+	 * performance boost for guests that aren't aware that manually clearing
+	 * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry
+	 * and VM-Exit.
+	 */
+	vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
+				(host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
 				!boot_cpu_has_bug(X86_BUG_MDS) &&
 				!boot_cpu_has_bug(X86_BUG_TAA);
 
@@ -738,7 +748,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
  */
 static int kvm_cpu_vmxoff(void)
 {
-	asm_volatile_goto("1: vmxoff\n\t"
+	asm goto("1: vmxoff\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  ::: "cc", "memory" : fault);
 
@@ -2784,7 +2794,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
 
 	cr4_set_bits(X86_CR4_VMXE);
 
-	asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+	asm goto("1: vmxon %[vmxon_pointer]\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  : : [vmxon_pointer] "m"(vmxon_pointer)
 			  : : fault);
@@ -6543,7 +6553,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 
 	if (exit_reason.basic >= kvm_vmx_max_exit_handlers)
 		goto unexpected_vmexit;
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_reason.basic == EXIT_REASON_MSR_WRITE)
 		return kvm_emulate_wrmsr(vcpu);
 	else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER)
@@ -6960,14 +6970,16 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 {
 	u32 intr_info = vmx_get_intr_info(vcpu);
 	unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
-	gate_desc *desc = (gate_desc *)host_idt_base + vector;
 
 	if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm,
 	    "unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
 	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
-	vmx_do_interrupt_irqoff(gate_offset(desc));
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector);
+	else
+		vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector));
 	kvm_after_interrupt(vcpu);
 
 	vcpu->arch.at_instruction_boundary = true;
@@ -7224,11 +7236,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	guest_state_enter_irqoff();
 
-	/* L1D Flush includes CPU buffer clear to mitigate MDS */
+	/*
+	 * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW
+	 * mitigation for MDS is done late in VMentry and is still
+	 * executed in spite of L1D Flush. This is because an extra VERW
+	 * should not matter much after the big hammer L1D Flush.
+	 */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
-	else if (static_branch_unlikely(&mds_user_clear))
-		mds_clear_cpu_buffers();
 	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
 		mds_clear_cpu_buffers();
@@ -7260,7 +7275,10 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
 	    is_nmi(vmx_get_intr_info(vcpu))) {
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
-		vmx_do_nmi_irqoff();
+		if (cpu_feature_enabled(X86_FEATURE_FRED))
+			fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR);
+		else
+			vmx_do_nmi_irqoff();
 		kvm_after_interrupt(vcpu);
 	}
 
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index f41ce3c24123..8060e5fc6dbd 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
-	asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+	asm_goto_output("1: vmread %[field], %[output]\n\t"
 			  "jna %l[do_fail]\n\t"
 
 			  _ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)
 
 #define vmx_asm1(insn, op1, error_args...)				\
 do {									\
-	asm_volatile_goto("1: " __stringify(insn) " %0\n\t"		\
+	asm goto("1: " __stringify(insn) " %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
@@ -205,7 +205,7 @@ fault:									\
 
 #define vmx_asm2(insn, op1, op2, error_args...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c080205..ffe580169c93 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1623,7 +1623,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
 	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
-	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO)
+	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
+	 ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1655,6 +1656,8 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_SSB_NO;
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
+	if (!boot_cpu_has_bug(X86_BUG_RFDS))
+		data |= ARCH_CAP_RFDS_NO;
 
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
@@ -1704,22 +1707,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	struct kvm_msr_entry msr;
 	int r;
 
+	/* Unconditionally clear the output for simplicity */
+	msr.data = 0;
 	msr.index = index;
 	r = kvm_get_msr_feature(&msr);
 
-	if (r == KVM_MSR_RET_INVALID) {
-		/* Unconditionally clear the output for simplicity */
-		*data = 0;
-		if (kvm_msr_ignored_check(index, 0, false))
-			r = 0;
-	}
-
-	if (r)
-		return r;
+	if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false))
+		r = 0;
 
 	*data = msr.data;
 
-	return 0;
+	return r;
 }
 
 static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
@@ -1782,6 +1780,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
 		kvm_mmu_reset_context(vcpu);
 
+	if (!static_cpu_has(X86_FEATURE_XSAVES) &&
+	    (efer & EFER_SVME))
+		kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+
 	return 0;
 }
 
@@ -2507,7 +2509,7 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 }
 
 #ifdef CONFIG_X86_64
-static inline int gtod_is_based_on_tsc(int mode)
+static inline bool gtod_is_based_on_tsc(int mode)
 {
 	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
 }
@@ -4581,7 +4583,7 @@ static bool kvm_is_vm_type_supported(unsigned long type)
 {
 	return type == KVM_X86_DEFAULT_VM ||
 	       (type == KVM_X86_SW_PROTECTED_VM &&
-		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -5454,7 +5456,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
 		vcpu->arch.nmi_pending = 0;
 		atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
-		kvm_make_request(KVM_REQ_NMI, vcpu);
+		if (events->nmi.pending)
+			kvm_make_request(KVM_REQ_NMI, vcpu);
 	}
 	static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
 
@@ -7016,6 +7019,9 @@ set_identity_unlock:
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
+		r = -ENOENT;
+		if (!pic_in_kernel(kvm))
+			goto create_pit_unlock;
 		r = -ENOMEM;
 		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
 		if (kvm->arch.vpit)
@@ -8004,6 +8010,16 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
+
+	/*
+	 * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+	 * successful, as the old value is written back on failure.  Note, for
+	 * live migration, this is unnecessarily conservative as CMPXCHG writes
+	 * back the original value and the access is atomic, but KVM's ABI is
+	 * that all writes are dirty logged, regardless of the value written.
+	 */
+	kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index ea3a28e7b613..6da73513f026 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN
 CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE)
 endif
 
-# Early boot use of cmdline; don't instrument it
-ifdef CONFIG_AMD_MEM_ENCRYPT
-KCOV_INSTRUMENT_cmdline.o := n
-KASAN_SANITIZE_cmdline.o  := n
-KCSAN_SANITIZE_cmdline.o  := n
-
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_cmdline.o = -pg
-endif
-
-CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
-endif
-
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
 quiet_cmd_inat_tables = GEN     $@
@@ -49,7 +36,7 @@ lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
-lib-$(CONFIG_RETPOLINE) += retpoline.o
+lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 obj-y += iomem.o
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 6962df315793..4fb44894ad87 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -23,14 +23,14 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	cli
 
 	/* if (*ptr == old) */
-	cmpq	PER_CPU_VAR(0(%rsi)), %rax
+	cmpq	__percpu (%rsi), %rax
 	jne	.Lnot_same
-	cmpq	PER_CPU_VAR(8(%rsi)), %rdx
+	cmpq	__percpu 8(%rsi), %rdx
 	jne	.Lnot_same
 
 	/* *ptr = new */
-	movq	%rbx, PER_CPU_VAR(0(%rsi))
-	movq	%rcx, PER_CPU_VAR(8(%rsi))
+	movq	%rbx, __percpu (%rsi)
+	movq	%rcx, __percpu 8(%rsi)
 
 	/* set ZF in EFLAGS to indicate success */
 	orl	$X86_EFLAGS_ZF, (%rsp)
@@ -42,8 +42,8 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	/* *ptr != old */
 
 	/* old = *ptr */
-	movq	PER_CPU_VAR(0(%rsi)), %rax
-	movq	PER_CPU_VAR(8(%rsi)), %rdx
+	movq	__percpu (%rsi), %rax
+	movq	__percpu 8(%rsi), %rdx
 
 	/* clear ZF in EFLAGS to indicate failure */
 	andl	$(~X86_EFLAGS_ZF), (%rsp)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 873e4ef23e49..1c96be769adc 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -24,12 +24,12 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	pushfl
 	cli
 
-	cmpl	0(%esi), %eax
+	cmpl	(%esi), %eax
 	jne	.Lnot_same
 	cmpl	4(%esi), %edx
 	jne	.Lnot_same
 
-	movl	%ebx, 0(%esi)
+	movl	%ebx, (%esi)
 	movl	%ecx, 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
@@ -38,7 +38,7 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	RET
 
 .Lnot_same:
-	movl	0(%esi), %eax
+	movl	(%esi), %eax
 	movl	4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
@@ -53,18 +53,30 @@ EXPORT_SYMBOL(cmpxchg8b_emu)
 
 #ifndef CONFIG_UML
 
+/*
+ * Emulate 'cmpxchg8b %fs:(%rsi)'
+ *
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
+ */
 SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 
 	pushfl
 	cli
 
-	cmpl	PER_CPU_VAR(0(%esi)), %eax
+	cmpl	__percpu (%esi), %eax
 	jne	.Lnot_same2
-	cmpl	PER_CPU_VAR(4(%esi)), %edx
+	cmpl	__percpu 4(%esi), %edx
 	jne	.Lnot_same2
 
-	movl	%ebx, PER_CPU_VAR(0(%esi))
-	movl	%ecx, PER_CPU_VAR(4(%esi))
+	movl	%ebx, __percpu (%esi)
+	movl	%ecx, __percpu 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
 
@@ -72,8 +84,8 @@ SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 	RET
 
 .Lnot_same2:
-	movl	PER_CPU_VAR(0(%esi)), %eax
-	movl	PER_CPU_VAR(4(%esi)), %edx
+	movl	__percpu (%esi), %eax
+	movl	__percpu 4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 20ef350a60fb..10d5ed8b5990 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
 #endif
 
 /* get_user */
-	_ASM_EXTABLE(1b, __get_user_handle_exception)
-	_ASM_EXTABLE(2b, __get_user_handle_exception)
-	_ASM_EXTABLE(3b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(4b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(4b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(5b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
 #endif
 
 /* __get_user */
-	_ASM_EXTABLE(6b, __get_user_handle_exception)
-	_ASM_EXTABLE(7b, __get_user_handle_exception)
-	_ASM_EXTABLE(8b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(9b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(9b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(10b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
 #endif
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 558a605929db..98631c0e7a11 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1129,15 +1129,15 @@ static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs,
  * get_eff_addr_sib() - Obtain referenced effective address via SIB
  * @insn:	Instruction. Must be valid.
  * @regs:	Register values as seen when entering kernel mode
- * @regoff:	Obtained operand offset, in pt_regs, associated with segment
+ * @base_offset: Obtained operand offset, in pt_regs, associated with segment
  * @eff_addr:	Obtained effective address
  *
  * Obtain the effective address referenced by the SIB byte of @insn. After
  * identifying the registers involved in the indexed, register-indirect memory
  * reference, its value is obtained from the operands in @regs. The computed
  * address is stored @eff_addr. Also, the register operand that indicates the
- * associated segment is stored in @regoff, this parameter can later be used to
- * determine such segment.
+ * associated segment is stored in @base_offset; this parameter can later be
+ * used to determine such segment.
  *
  * Returns:
  *
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 55e371cc69fd..1bb155a0955b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 	insn->kaddr = kaddr;
 	insn->end_kaddr = kaddr + buf_len;
 	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->x86_64 = x86_64;
 	insn->opnd_bytes = 4;
 	if (x86_64)
 		insn->addr_bytes = 8;
@@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn)
 	if (opcode->got)
 		return 0;
 
-	if (!insn->prefixes.got) {
-		ret = insn_get_prefixes(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_prefixes(insn);
+	if (ret)
+		return ret;
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
@@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn)
 	if (modrm->got)
 		return 0;
 
-	if (!insn->opcode.got) {
-		ret = insn_get_opcode(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_opcode(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
@@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn)
 	if (!insn->x86_64)
 		return 0;
 
-	if (!modrm->got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return 0;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return 0;
 	/*
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
@@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn)
 	if (insn->sib.got)
 		return 0;
 
-	if (!insn->modrm.got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		modrm = insn->modrm.bytes[0];
@@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn)
 	if (insn->displacement.got)
 		return 0;
 
-	if (!insn->sib.got) {
-		ret = insn_get_sib(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_sib(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		/*
@@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn)
 	if (insn->immediate.got)
 		return 0;
 
-	if (!insn->displacement.got) {
-		ret = insn_get_displacement(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_displacement(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_moffset(insn->attr)) {
 		if (!__get_moffset(insn))
@@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn)
 	if (insn->length)
 		return 0;
 
-	if (!insn->immediate.got) {
-		ret = insn_get_immediate(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_immediate(insn);
+	if (ret)
+		return ret;
 
 	insn->length = (unsigned char)((unsigned long)insn->next_byte
 				     - (unsigned long)insn->kaddr);
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index 40bbe56bde32..acd463d887e1 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -9,10 +9,9 @@ static void __rdmsr_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
+		reg = this_cpu_ptr(rv->msrs);
 	else
 		reg = &rv->reg;
 
@@ -23,10 +22,9 @@ static void __wrmsr_on_cpu(void *info)
 {
 	struct msr_info *rv = info;
 	struct msr *reg;
-	int this_cpu = raw_smp_processor_id();
 
 	if (rv->msrs)
-		reg = per_cpu_ptr(rv->msrs, this_cpu);
+		reg = this_cpu_ptr(rv->msrs);
 	else
 		reg = &rv->reg;
 
@@ -97,7 +95,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
 EXPORT_SYMBOL(wrmsrl_on_cpu);
 
 static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
-			    struct msr *msrs,
+			    struct msr __percpu *msrs,
 			    void (*msr_func) (void *info))
 {
 	struct msr_info rv;
@@ -124,7 +122,7 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
  * @msrs:       array of MSR values
  *
  */
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs)
 {
 	__rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
 }
@@ -138,7 +136,7 @@ EXPORT_SYMBOL(rdmsr_on_cpus);
  * @msrs:       array of MSR values
  *
  */
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs)
 {
 	__rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
 }
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 47fd9bd6b91d..4bf4fad5b148 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -6,9 +6,9 @@
 #define CREATE_TRACE_POINTS
 #include <asm/msr-trace.h>
 
-struct msr *msrs_alloc(void)
+struct msr __percpu *msrs_alloc(void)
 {
-	struct msr *msrs = NULL;
+	struct msr __percpu *msrs = NULL;
 
 	msrs = alloc_percpu(struct msr);
 	if (!msrs) {
@@ -20,7 +20,7 @@ struct msr *msrs_alloc(void)
 }
 EXPORT_SYMBOL(msrs_alloc);
 
-void msrs_free(struct msr *msrs)
+void msrs_free(struct msr __percpu *msrs)
 {
 	free_percpu(msrs);
 }
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 2877f5934177..975c9c18263d 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
 	RET
 SYM_CODE_END(__put_user_handle_exception)
 
-	_ASM_EXTABLE(1b, __put_user_handle_exception)
-	_ASM_EXTABLE(2b, __put_user_handle_exception)
-	_ASM_EXTABLE(3b, __put_user_handle_exception)
-	_ASM_EXTABLE(4b, __put_user_handle_exception)
-	_ASM_EXTABLE(5b, __put_user_handle_exception)
-	_ASM_EXTABLE(6b, __put_user_handle_exception)
-	_ASM_EXTABLE(7b, __put_user_handle_exception)
-	_ASM_EXTABLE(9b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __put_user_handle_exception)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE(8b, __put_user_handle_exception)
-	_ASM_EXTABLE(10b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(10b, __put_user_handle_exception)
 #endif
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 7b2589877d06..721b528da9ac 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -71,7 +71,7 @@ SYM_CODE_END(__x86_indirect_thunk_array)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 .macro CALL_THUNK reg
 	.align RETPOLINE_THUNK_SIZE
 
@@ -127,7 +127,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
 #undef GEN
 #endif
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 
 /*
  * Be careful here: that label cannot really be removed because in
@@ -138,7 +138,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  */
 	.section .text..__x86.return_thunk
 
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
 
 /*
  * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
@@ -225,12 +225,12 @@ SYM_CODE_END(srso_return_thunk)
 
 #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
 #define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
-#else /* !CONFIG_CPU_SRSO */
+#else /* !CONFIG_MITIGATION_SRSO */
 #define JMP_SRSO_UNTRAIN_RET "ud2"
 #define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
-#endif /* CONFIG_CPU_SRSO */
+#endif /* CONFIG_MITIGATION_SRSO */
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 
 /*
  * Some generic notes on the untraining sequences:
@@ -312,11 +312,11 @@ SYM_CODE_END(retbleed_return_thunk)
 SYM_FUNC_END(retbleed_untrain_ret)
 
 #define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret"
-#else /* !CONFIG_CPU_UNRET_ENTRY */
+#else /* !CONFIG_MITIGATION_UNRET_ENTRY */
 #define JMP_RETBLEED_UNTRAIN_RET "ud2"
-#endif /* CONFIG_CPU_UNRET_ENTRY */
+#endif /* CONFIG_MITIGATION_UNRET_ENTRY */
 
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
 	ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET,				\
@@ -325,9 +325,9 @@ SYM_FUNC_START(entry_untrain_ret)
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
 
-#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
+#endif /* CONFIG_MITIGATION_UNRET_ENTRY || CONFIG_MITIGATION_SRSO */
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 
 	.align 64
 SYM_FUNC_START(call_depth_return_thunk)
@@ -359,7 +359,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	int3
 SYM_FUNC_END(call_depth_return_thunk)
 
-#endif /* CONFIG_CALL_DEPTH_TRACKING */
+#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
@@ -369,21 +369,18 @@ SYM_FUNC_END(call_depth_return_thunk)
  * 'JMP __x86_return_thunk' sites are changed to something else by
  * apply_returns().
  *
- * This should be converted eventually to call a warning function which
- * should scream loudly when the default return thunk is called after
- * alternatives have been applied.
- *
- * That warning function cannot BUG() because the bug splat cannot be
- * displayed in all possible configurations, leading to users not really
- * knowing why the machine froze.
+ * The ALTERNATIVE below adds a really loud warning to catch the case
+ * where the insufficient default return thunk ends up getting used for
+ * whatever reason like miscompilation or failure of
+ * objtool/alternatives/etc to patch all the return sites.
  */
 SYM_CODE_START(__x86_return_thunk)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
-	ANNOTATE_UNRET_SAFE
-	ret
+	ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \
+		   "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS
 	int3
 SYM_CODE_END(__x86_return_thunk)
 EXPORT_SYMBOL(__x86_return_thunk)
 
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5168ee0360b2..12af572201a2 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1051,8 +1051,8 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index c80febc44cd2..428048e73bd2 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -16,6 +16,7 @@ KASAN_SANITIZE_pgprot.o		:= n
 KCSAN_SANITIZE := n
 # Avoid recursion by not calling KMSAN hooks for CEA code.
 KMSAN_SANITIZE_cpu_entry_area.o := n
+KMSAN_SANITIZE_mem_encrypt_identity.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
@@ -60,7 +61,7 @@ obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
 obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
-obj-$(CONFIG_PAGE_TABLE_ISOLATION)		+= pti.o
+obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)	+= pti.o
 
 obj-$(CONFIG_X86_MEM_ENCRYPT)	+= mem_encrypt.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_amd.o
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index b3ca7d23e4b0..9332b36a1091 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -54,13 +54,11 @@ static __init int find_northbridge(void)
 
 int __init amd_numa_init(void)
 {
-	u64 start = PFN_PHYS(0);
+	unsigned int numnodes, cores, apicid;
+	u64 prevbase, start = PFN_PHYS(0);
 	u64 end = PFN_PHYS(max_pfn);
-	unsigned numnodes;
-	u64 prevbase;
-	int i, j, nb;
 	u32 nodeid, reg;
-	unsigned int bits, cores, apicid_base;
+	int i, j, nb;
 
 	if (!early_pci_allowed())
 		return -EINVAL;
@@ -158,26 +156,18 @@ int __init amd_numa_init(void)
 		return -ENOENT;
 
 	/*
-	 * We seem to have valid NUMA configuration.  Map apicids to nodes
-	 * using the coreid bits from early_identify_cpu.
+	 * We seem to have valid NUMA configuration. Map apicids to nodes
+	 * using the size of the core domain in the APIC space.
 	 */
-	bits = boot_cpu_data.x86_coreid_bits;
-	cores = 1 << bits;
-	apicid_base = 0;
+	cores = topology_get_domain_size(TOPO_CORE_DOMAIN);
 
-	/*
-	 * get boot-time SMP configuration:
-	 */
-	early_get_smp_config();
+	apicid = boot_cpu_physical_apicid;
+	if (apicid > 0)
+		pr_info("BSP APIC ID: %02x\n", apicid);
 
-	if (boot_cpu_physical_apicid > 0) {
-		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
-		apicid_base = boot_cpu_physical_apicid;
+	for_each_node_mask(i, numa_nodes_parsed) {
+		for (j = 0; j < cores; j++, apicid++)
+			set_apicid_to_node(apicid, i);
 	}
-
-	for_each_node_mask(i, numa_nodes_parsed)
-		for (j = apicid_base; j < cores + apicid_base; j++)
-			set_apicid_to_node((i << bits) + j, i);
-
 	return 0;
 }
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index b43301cb2a80..ae5c213a1cb0 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -22,7 +22,7 @@ static int ptdump_curknl_show(struct seq_file *m, void *v)
 
 DEFINE_SHOW_ATTRIBUTE(ptdump_curknl);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 static int ptdump_curusr_show(struct seq_file *m, void *v)
 {
 	if (current->mm->pgd)
@@ -54,7 +54,7 @@ static int __init pt_dump_debug_init(void)
 	debugfs_create_file("current_kernel", 0400, dir, NULL,
 			    &ptdump_curknl_fops);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	debugfs_create_file("current_user", 0400, dir, NULL,
 			    &ptdump_curusr_fops);
 #endif
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index e1b599ecbbc2..b7b88c1d91ec 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -408,7 +408,7 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
 				   bool user)
 {
 	pgd_t *pgd = mm->pgd;
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	if (user && boot_cpu_has(X86_FEATURE_PTI))
 		pgd = kernel_to_user_pgdp(pgd);
 #endif
@@ -418,7 +418,7 @@ EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 
 void ptdump_walk_user_pgd_level_checkwx(void)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	pgd_t *pgd = INIT_PGD;
 
 	if (!(__supported_pte_mask & _PAGE_NX) ||
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 271dcb2deabc..b522933bfa56 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -6,6 +6,7 @@
 #include <xen/xen.h>
 
 #include <asm/fpu/api.h>
+#include <asm/fred.h>
 #include <asm/sev.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
@@ -223,6 +224,79 @@ static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup,
 	return ex_handler_uaccess(fixup, regs, trapnr, fault_address);
 }
 
+#ifdef CONFIG_X86_FRED
+static bool ex_handler_eretu(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, unsigned long error_code)
+{
+	struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax));
+	unsigned short ss = uregs->ss;
+	unsigned short cs = uregs->cs;
+
+	/*
+	 * Move the NMI bit from the invalid stack frame, which caused ERETU
+	 * to fault, to the fault handler's stack frame, thus to unblock NMI
+	 * with the fault handler's ERETS instruction ASAP if NMI is blocked.
+	 */
+	regs->fred_ss.nmi = uregs->fred_ss.nmi;
+
+	/*
+	 * Sync event information to uregs, i.e., the ERETU return frame, but
+	 * is it safe to write to the ERETU return frame which is just above
+	 * current event stack frame?
+	 *
+	 * The RSP used by FRED to push a stack frame is not the value in %rsp,
+	 * it is calculated from %rsp with the following 2 steps:
+	 * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0)	// Reserve N*64 bytes
+	 * 2) RSP = RSP & ~0x3f		// Align to a 64-byte cache line
+	 * when an event delivery doesn't trigger a stack level change.
+	 *
+	 * Here is an example with N*64 (N=1) bytes reserved:
+	 *
+	 *  64-byte cache line ==>  ______________
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETU return frame
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *  64-byte cache line ==> |______________| <== RSP after step 1) and 2)
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETS return frame
+	 *
+	 * Thus a new FRED stack frame will always be pushed below a previous
+	 * FRED stack frame ((N*64) bytes may be reserved between), and it is
+	 * safe to write to a previous FRED stack frame as they never overlap.
+	 */
+	fred_info(uregs)->edata = fred_event_data(regs);
+	uregs->ssx = regs->ssx;
+	uregs->fred_ss.ss = ss;
+	/* The NMI bit was moved away above */
+	uregs->fred_ss.nmi = 0;
+	uregs->csx = regs->csx;
+	uregs->fred_cs.sl = 0;
+	uregs->fred_cs.wfe = 0;
+	uregs->cs = cs;
+	uregs->orig_ax = error_code;
+
+	return ex_handler_default(fixup, regs);
+}
+#endif
+
 int ex_get_fixup_type(unsigned long ip)
 {
 	const struct exception_table_entry *e = search_exception_tables(ip);
@@ -300,6 +374,10 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm);
 	case EX_TYPE_ZEROPAD:
 		return ex_handler_zeropad(e, regs, fault_addr);
+#ifdef CONFIG_X86_FRED
+	case EX_TYPE_ERETU:
+		return ex_handler_eretu(e, regs, error_code);
+#endif
 	}
 	BUG();
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 679b09cfe241..402e08f6b7ec 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -34,6 +34,8 @@
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
 #include <asm/irq_stack.h>
+#include <asm/fred.h>
+#include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -547,6 +549,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 		 !(error_code & X86_PF_PROT) ? "not-present page" :
 		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
 		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+		 (error_code & X86_PF_RMP)   ? "RMP violation" :
 					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
@@ -579,6 +582,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 	}
 
 	dump_pagetable(address);
+
+	if (error_code & X86_PF_RMP)
+		snp_dump_hva_rmpentry(address);
 }
 
 static noinline void
@@ -798,15 +804,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
 	show_opcodes(regs, loglvl);
 }
 
-/*
- * The (legacy) vsyscall page is the long page in the kernel portion
- * of the address space that has user-accessible permissions.
- */
-static bool is_vsyscall_vaddr(unsigned long vaddr)
-{
-	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
-}
-
 static void
 __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		       unsigned long address, u32 pkey, int si_code)
@@ -1302,21 +1299,14 @@ void do_user_addr_fault(struct pt_regs *regs,
 		return;
 	}
 
-	/*
-	 * It's safe to allow irq's after cr2 has been saved and the
-	 * vmalloc fault has been handled.
-	 *
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet:
-	 */
-	if (user_mode(regs)) {
-		local_irq_enable();
-		flags |= FAULT_FLAG_USER;
-	} else {
-		if (regs->flags & X86_EFLAGS_IF)
-			local_irq_enable();
+	/* Legacy check - remove this after verifying that it doesn't trigger */
+	if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
+	local_irq_enable();
+
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 	/*
@@ -1332,6 +1322,14 @@ void do_user_addr_fault(struct pt_regs *regs,
 	if (error_code & X86_PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
+	/*
+	 * We set FAULT_FLAG_USER based on the register state, not
+	 * based on X86_PF_USER. User space accesses that cause
+	 * system page faults are still user accesses.
+	 */
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 #ifdef CONFIG_X86_64
 	/*
 	 * Faults in the vsyscall page might need emulation.  The
@@ -1518,8 +1516,10 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
-	unsigned long address = read_cr2();
 	irqentry_state_t state;
+	unsigned long address;
+
+	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
 	prefetchw(&current->mm->mmap_lock);
 
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..f50cc210a981 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		if (info->direct_gbpages) {
-			pud_t pudval;
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_large(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
 
-			if (pud_present(*pud))
-				continue;
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
 
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 6993f026adec..42115ac079cf 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -3,6 +3,8 @@
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 
+#include <asm/vsyscall.h>
+
 #ifdef CONFIG_X86_64
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
@@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 		return false;
 
 	/*
+	 * Reading from the vsyscall page may cause an unhandled fault in
+	 * certain cases.  Though it is at an address above TASK_SIZE_MAX, it is
+	 * usually considered as a user space address.
+	 */
+	if (is_vsyscall_vaddr(vaddr))
+		return false;
+
+	/*
 	 * Allow everything during early boot before 'x86_virt_bits'
 	 * is initialized.  Needed for instruction decoding in early
 	 * exception handlers.
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index c290c55b632b..6f3b3e028718 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -14,6 +14,8 @@
 #include <linux/mem_encrypt.h>
 #include <linux/virtio_anchor.h>
 
+#include <asm/sev.h>
+
 /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 bool force_dma_unencrypted(struct device *dev)
 {
@@ -42,38 +44,45 @@ bool force_dma_unencrypted(struct device *dev)
 
 static void print_mem_encrypt_feature_info(void)
 {
-	pr_info("Memory Encryption Features active:");
-
-	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
-		pr_cont(" Intel TDX\n");
-		return;
-	}
+	pr_info("Memory Encryption Features active: ");
 
-	pr_cont(" AMD");
+	switch (cc_vendor) {
+	case CC_VENDOR_INTEL:
+		pr_cont("Intel TDX\n");
+		break;
+	case CC_VENDOR_AMD:
+		pr_cont("AMD");
 
-	/* Secure Memory Encryption */
-	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		/* Secure Memory Encryption */
+		if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
 		/*
 		 * SME is mutually exclusive with any of the SEV
 		 * features below.
-		 */
-		pr_cont(" SME\n");
-		return;
-	}
+		*/
+			pr_cont(" SME\n");
+			return;
+		}
 
-	/* Secure Encrypted Virtualization */
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		pr_cont(" SEV");
+		/* Secure Encrypted Virtualization */
+		if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+			pr_cont(" SEV");
+
+		/* Encrypted Register State */
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+			pr_cont(" SEV-ES");
 
-	/* Encrypted Register State */
-	if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
-		pr_cont(" SEV-ES");
+		/* Secure Nested Paging */
+		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+			pr_cont(" SEV-SNP");
 
-	/* Secure Nested Paging */
-	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
-		pr_cont(" SEV-SNP");
+		pr_cont("\n");
 
-	pr_cont("\n");
+		sev_show_status();
+
+		break;
+	default:
+		pr_cont("Unknown\n");
+	}
 }
 
 /* Architecture __weak replacement functions */
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index d73aeb16417f..64b5005d49e5 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -41,9 +41,9 @@
 #include <linux/mem_encrypt.h>
 #include <linux/cc_platform.h>
 
+#include <asm/init.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
-#include <asm/cmdline.h>
 #include <asm/coco.h>
 #include <asm/sev.h>
 
@@ -95,11 +95,7 @@ struct sme_populate_pgd_data {
  */
 static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch");
 
-static char sme_cmdline_arg[] __initdata = "mem_encrypt";
-static char sme_cmdline_on[]  __initdata = "on";
-static char sme_cmdline_off[] __initdata = "off";
-
-static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 {
 	unsigned long pgd_start, pgd_end, pgd_size;
 	pgd_t *pgd_p;
@@ -114,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 	memset(pgd_p, 0, pgd_size);
 }
 
-static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
+static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -151,7 +147,7 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
 	return pud;
 }
 
-static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
 {
 	pud_t *pud;
 	pmd_t *pmd;
@@ -167,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
 	set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
 }
 
-static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 {
 	pud_t *pud;
 	pmd_t *pmd;
@@ -193,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 		set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
 }
 
-static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
 {
 	while (ppd->vaddr < ppd->vaddr_end) {
 		sme_populate_pgd_large(ppd);
@@ -203,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
 	}
 }
 
-static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
 {
 	while (ppd->vaddr < ppd->vaddr_end) {
 		sme_populate_pgd(ppd);
@@ -213,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
 	}
 }
 
-static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+static void __head __sme_map_range(struct sme_populate_pgd_data *ppd,
 				   pmdval_t pmd_flags, pteval_t pte_flags)
 {
 	unsigned long vaddr_end;
@@ -237,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
 	__sme_map_range_pte(ppd);
 }
 
-static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
 {
 	__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
 }
 
-static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
 {
 	__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
 }
 
-static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
 {
 	__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
 }
 
-static unsigned long __init sme_pgtable_calc(unsigned long len)
+static unsigned long __head sme_pgtable_calc(unsigned long len)
 {
 	unsigned long entries = 0, tables = 0;
 
@@ -289,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
 	return entries + tables;
 }
 
-void __init sme_encrypt_kernel(struct boot_params *bp)
+void __head sme_encrypt_kernel(struct boot_params *bp)
 {
 	unsigned long workarea_start, workarea_end, workarea_len;
 	unsigned long execute_start, execute_end, execute_len;
@@ -305,7 +301,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
 	 * function.
 	 */
-	if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
+	if (!sme_get_me_mask() ||
+	    RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
 		return;
 
 	/*
@@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	 *     memory from being cached.
 	 */
 
-	/* Physical addresses gives us the identity mapped virtual addresses */
-	kernel_start = __pa_symbol(_text);
-	kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE);
+	kernel_start = (unsigned long)RIP_REL_REF(_text);
+	kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
 	kernel_len = kernel_end - kernel_start;
 
 	initrd_start = 0;
@@ -343,14 +339,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 #endif
 
 	/*
-	 * We're running identity mapped, so we must obtain the address to the
-	 * SME encryption workarea using rip-relative addressing.
-	 */
-	asm ("lea sme_workarea(%%rip), %0"
-	     : "=r" (workarea_start)
-	     : "p" (sme_workarea));
-
-	/*
 	 * Calculate required number of workarea bytes needed:
 	 *   executable encryption area size:
 	 *     stack page (PAGE_SIZE)
@@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	 *   pagetable structures for the encryption of the kernel
 	 *   pagetable structures for workarea (in case not currently mapped)
 	 */
-	execute_start = workarea_start;
+	execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
 	execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
 	execute_len = execute_end - execute_start;
 
@@ -502,14 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	native_write_cr3(__native_read_cr3());
 }
 
-void __init sme_enable(struct boot_params *bp)
+void __head sme_enable(struct boot_params *bp)
 {
-	const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
 	unsigned int eax, ebx, ecx, edx;
 	unsigned long feature_mask;
-	bool active_by_default;
 	unsigned long me_mask;
-	char buffer[16];
 	bool snp;
 	u64 msr;
 
@@ -543,15 +528,18 @@ void __init sme_enable(struct boot_params *bp)
 	me_mask = 1UL << (ebx & 0x3f);
 
 	/* Check the SEV MSR whether SEV or SME is enabled */
-	sev_status   = __rdmsr(MSR_AMD64_SEV);
-	feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
+	RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+	feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
 
 	/* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */
-	if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+	if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED))
 		snp_abort();
 
 	/* Check if memory encryption is enabled */
 	if (feature_mask == AMD_SME_BIT) {
+		if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION))
+			return;
+
 		/*
 		 * No SME if Hypervisor bit is set. This check is here to
 		 * prevent a guest from trying to enable SME. For running as a
@@ -571,48 +559,10 @@ void __init sme_enable(struct boot_params *bp)
 		msr = __rdmsr(MSR_AMD64_SYSCFG);
 		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			return;
-	} else {
-		/* SEV state cannot be controlled by a command line option */
-		sme_me_mask = me_mask;
-		goto out;
 	}
 
-	/*
-	 * Fixups have not been applied to phys_base yet and we're running
-	 * identity mapped, so we must obtain the address to the SME command
-	 * line argument data using rip-relative addressing.
-	 */
-	asm ("lea sme_cmdline_arg(%%rip), %0"
-	     : "=r" (cmdline_arg)
-	     : "p" (sme_cmdline_arg));
-	asm ("lea sme_cmdline_on(%%rip), %0"
-	     : "=r" (cmdline_on)
-	     : "p" (sme_cmdline_on));
-	asm ("lea sme_cmdline_off(%%rip), %0"
-	     : "=r" (cmdline_off)
-	     : "p" (sme_cmdline_off));
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
-		active_by_default = true;
-	else
-		active_by_default = false;
-
-	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
-				     ((u64)bp->ext_cmd_line_ptr << 32));
-
-	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
-		return;
-
-	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
-		sme_me_mask = me_mask;
-	else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
-		sme_me_mask = 0;
-	else
-		sme_me_mask = active_by_default ? me_mask : 0;
-out:
-	if (sme_me_mask) {
-		physical_mask &= ~sme_me_mask;
-		cc_vendor = CC_VENDOR_AMD;
-		cc_set_mask(sme_me_mask);
-	}
+	RIP_REL_REF(sme_me_mask) = me_mask;
+	physical_mask &= ~me_mask;
+	cc_vendor = CC_VENDOR_AMD;
+	cc_set_mask(me_mask);
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index adc497b93f03..65e9a6e391c0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -934,7 +934,7 @@ static int __init cmp_memblk(const void *a, const void *b)
 	const struct numa_memblk *ma = *(const struct numa_memblk **)a;
 	const struct numa_memblk *mb = *(const struct numa_memblk **)b;
 
-	return ma->start - mb->start;
+	return (ma->start > mb->start) - (ma->start < mb->start);
 }
 
 static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
@@ -944,14 +944,12 @@ static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
  * @start: address to begin fill
  * @end: address to end fill
  *
- * Find and extend numa_meminfo memblks to cover the @start-@end
- * physical address range, such that the first memblk includes
- * @start, the last memblk includes @end, and any gaps in between
- * are filled.
+ * Find and extend numa_meminfo memblks to cover the physical
+ * address range @start-@end
  *
  * RETURNS:
  * 0		  : Success
- * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end
  */
 
 int __init numa_fill_memblks(u64 start, u64 end)
@@ -963,17 +961,14 @@ int __init numa_fill_memblks(u64 start, u64 end)
 
 	/*
 	 * Create a list of pointers to numa_meminfo memblks that
-	 * overlap start, end. Exclude (start == bi->end) since
-	 * end addresses in both a CFMWS range and a memblk range
-	 * are exclusive.
-	 *
-	 * This list of pointers is used to make in-place changes
-	 * that fill out the numa_meminfo memblks.
+	 * overlap start, end. The list is used to make in-place
+	 * changes that fill out the numa_meminfo memblks.
 	 */
 	for (int i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *bi = &mi->blk[i];
 
-		if (start < bi->end && end >= bi->start) {
+		if (memblock_addrs_overlap(start, end - start, bi->start,
+					   bi->end - bi->start)) {
 			blk[count] = &mi->blk[i];
 			count++;
 		}
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0904d7e8e126..0d72183b5dd0 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -240,6 +240,8 @@ void pat_cpu_init(void)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+
+	__flush_tlb_all();
 }
 
 /**
@@ -296,13 +298,8 @@ void __init pat_bp_init(void)
 	/*
 	 * Xen PV doesn't allow to set PAT MSR, but all cache modes are
 	 * supported.
-	 * When running as TDX guest setting the PAT MSR won't work either
-	 * due to the requirement to set CR0.CD when doing so. Rely on
-	 * firmware to have set the PAT MSR correctly.
 	 */
-	if (pat_disabled ||
-	    cpu_feature_enabled(X86_FEATURE_XENPV) ||
-	    cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+	if (pat_disabled || cpu_feature_enabled(X86_FEATURE_XENPV)) {
 		init_cache_modes(pat_msr_val);
 		return;
 	}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e9b448d1b1b7..e5b2985a7c51 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * areas on 32-bit NUMA systems.  The percpu areas can
  * end up in this kind of memory, for instance.
  *
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
  */
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
 	return rc;
 }
 
-static int set_memory_p(unsigned long *addr, int numpages)
-{
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
 	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
 
-	return set_memory_p(&addr, 1);
+	return set_memory_p(addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
 					CPA_NO_CHECK_ALIAS, NULL);
 }
 
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
@@ -2153,7 +2157,7 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 
 	/* Notify hypervisor that we are about to set/clr encryption attribute. */
 	if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
-		return -EIO;
+		goto vmm_fail;
 
 	ret = __change_page_attr_set_clr(&cpa, 1);
 
@@ -2166,13 +2170,20 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 	 */
 	cpa_flush(&cpa, 0);
 
+	if (ret)
+		return ret;
+
 	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
-	if (!ret) {
-		if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
-			ret = -EIO;
-	}
+	if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
+		goto vmm_fail;
 
-	return ret;
+	return 0;
+
+vmm_fail:
+	WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
+		  (void *)addr, numpages, enc ? "private" : "shared");
+
+	return -EIO;
 }
 
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0cbc1b8e8e3d..cceb779d882d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -293,7 +293,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 	for (i = 0; i < PREALLOCATED_PMDS; i++)
 		mop_up_one_pmd(mm, &pgdp[i]);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 
 	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
@@ -325,7 +325,7 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 	}
 }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 				     pgd_t *k_pgd, pmd_t *pmds[])
 {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5768d386efab..4af930947380 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -89,10 +89,10 @@
 #define CR3_HW_ASID_BITS		12
 
 /*
- * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for
  * user/kernel switches
  */
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 # define PTI_CONSUMED_PCID_BITS	1
 #else
 # define PTI_CONSUMED_PCID_BITS	0
@@ -114,7 +114,7 @@ static inline u16 kern_pcid(u16 asid)
 {
 	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	/*
 	 * Make sure that the dynamic ASID space does not conflict with the
 	 * bit we are using to switch between user and kernel ASIDs.
@@ -149,7 +149,7 @@ static inline u16 kern_pcid(u16 asid)
 static inline u16 user_pcid(u16 asid)
 {
 	u16 ret = kern_pcid(asid);
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
 #endif
 	return ret;
@@ -262,7 +262,7 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 static inline void invalidate_user_asid(u16 asid)
 {
 	/* There is no user ASID if address space separation is off */
-	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+	if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
 		return;
 
 	/*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 919f647c740f..f3b4716317c1 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -553,7 +553,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 			emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
 	} else {
 		EMIT2(0xFF, 0xE0 + reg);	/* jmp *%\reg */
-		if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS))
+		if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || IS_ENABLED(CONFIG_MITIGATION_SLS))
 			EMIT1(0xCC);		/* int3 */
 	}
 
@@ -568,7 +568,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */
-		if (IS_ENABLED(CONFIG_SLS))
+		if (IS_ENABLED(CONFIG_MITIGATION_SLS))
 			EMIT1(0xCC);	/* int3 */
 	}
 
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index b18ce19981ec..c10083a8e68e 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1273,7 +1273,7 @@ static int emit_jmp_edx(u8 **pprog, u8 *ip)
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5));
 #else
 	EMIT2(0xFF, 0xE2);
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 40745664d92f..f32451bdcfdd 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -135,13 +135,13 @@ static void sdv_pci_init(void)
  */
 void __init x86_ce4100_early_setup(void)
 {
-	x86_init.oem.arch_setup = sdv_arch_setup;
-	x86_init.resources.probe_roms = x86_init_noop;
-	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
-	x86_init.pci.init = ce4100_pci_init;
-	x86_init.pci.init_irq = sdv_pci_init;
+	x86_init.oem.arch_setup			= sdv_arch_setup;
+	x86_init.resources.probe_roms		= x86_init_noop;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+	x86_init.mpparse.parse_smp_cfg		= x86_dtb_parse_smp_config;
+	x86_init.pci.init			= ce4100_pci_init;
+	x86_init.pci.init_irq			= sdv_pci_init;
 
 	/*
 	 * By default, the reboot method is ACPI which is supported by the
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index e9f99c56f3ce..f090ec972d7b 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -950,3 +950,8 @@ umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n)
 	}
 	return attr->mode;
 }
+
+enum efi_secureboot_mode __x86_ima_efi_boot_mode(void)
+{
+	return boot_params.secure_boot;
+}
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index f4592dc7a1c1..7be71c2cdc83 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -118,7 +118,8 @@ void __init x86_intel_mid_early_setup(void)
 	machine_ops.emergency_restart  = intel_mid_reboot;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+	x86_init.mpparse.parse_smp_cfg		= x86_init_noop;
 	set_bit(MP_BUS_ISA, mp_bus_not_pci);
 }
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 00a92cb2c814..944e0290f2c0 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -3,6 +3,7 @@
 
 #include <xen/hvc-console.h>
 
+#include <asm/bootparam.h>
 #include <asm/io_apic.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 08aa0f25f12a..bc31863c5ee6 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -61,7 +61,7 @@ ifdef CONFIG_STACKPROTECTOR_STRONG
 PURGATORY_CFLAGS_REMOVE		+= -fstack-protector-strong
 endif
 
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
 PURGATORY_CFLAGS_REMOVE		+= $(RETPOLINE_CFLAGS)
 endif
 
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index c9f76fae902e..14d9c7daf90f 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -37,13 +37,15 @@
 	.text
 	.code16
 
-.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0
+.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0
 	/*
 	 * Make sure only one CPU fiddles with the realmode stack
 	 */
 .Llock_rm\@:
 	.if \lock_pa
         lock btsl       $0, pa_tr_lock
+	.elseif \lock_rip
+        lock btsl       $0, tr_lock(%rip)
 	.else
         lock btsl       $0, tr_lock
 	.endif
@@ -220,6 +222,35 @@ SYM_CODE_START(trampoline_start64)
 	lidt	tr_idt(%rip)
 	lgdt	tr_gdt64(%rip)
 
+	/* Check if paging mode has to be changed */
+	movq	%cr4, %rax
+	xorl	tr_cr4(%rip), %eax
+	testl	$X86_CR4_LA57, %eax
+	jnz	.L_switch_paging
+
+	/* Paging mode is correct proceed in 64-bit mode */
+
+	LOCK_AND_LOAD_REALMODE_ESP lock_rip=1
+
+	movw	$__KERNEL_DS, %dx
+	movl	%edx, %ss
+	addl	$pa_real_mode_base, %esp
+	movl	%edx, %ds
+	movl	%edx, %es
+	movl	%edx, %fs
+	movl	%edx, %gs
+
+	movl	$pa_trampoline_pgd, %eax
+	movq	%rax, %cr3
+
+	pushq	$__KERNEL_CS
+	pushq	tr_start(%rip)
+	lretq
+.L_switch_paging:
+	/*
+	 * To switch between 4- and 5-level paging modes, it is necessary
+	 * to disable paging. This must be done in the compatibility mode.
+	 */
 	ljmpl	*tr_compat(%rip)
 SYM_CODE_END(trampoline_start64)
 
diff --git a/arch/x86/virt/svm/Makefile b/arch/x86/virt/svm/Makefile
new file mode 100644
index 000000000000..ef2a31bdcc70
--- /dev/null
+++ b/arch/x86/virt/svm/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_KVM_AMD_SEV) += sev.o
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
new file mode 100644
index 000000000000..cffe1157a90a
--- /dev/null
+++ b/arch/x86/virt/svm/sev.c
@@ -0,0 +1,560 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD SVM-SEV Host Support.
+ *
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ *
+ * Author: Ashish Kalra <ashish.kalra@amd.com>
+ *
+ */
+
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/set_memory.h>
+#include <linux/memblock.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/iommu.h>
+#include <linux/amd-iommu.h>
+
+#include <asm/sev.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid.h>
+#include <asm/cmdline.h>
+#include <asm/iommu.h>
+
+/*
+ * The RMP entry format is not architectural. The format is defined in PPR
+ * Family 19h Model 01h, Rev B1 processor.
+ */
+struct rmpentry {
+	union {
+		struct {
+			u64 assigned	: 1,
+			    pagesize	: 1,
+			    immutable	: 1,
+			    rsvd1	: 9,
+			    gpa		: 39,
+			    asid	: 10,
+			    vmsa	: 1,
+			    validated	: 1,
+			    rsvd2	: 1;
+		};
+		u64 lo;
+	};
+	u64 hi;
+} __packed;
+
+/*
+ * The first 16KB from the RMP_BASE is used by the processor for the
+ * bookkeeping, the range needs to be added during the RMP entry lookup.
+ */
+#define RMPTABLE_CPU_BOOKKEEPING_SZ	0x4000
+
+/* Mask to apply to a PFN to get the first PFN of a 2MB page */
+#define PFN_PMD_MASK	GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT)
+
+static u64 probed_rmp_base, probed_rmp_size;
+static struct rmpentry *rmptable __ro_after_init;
+static u64 rmptable_max_pfn __ro_after_init;
+
+static LIST_HEAD(snp_leaked_pages_list);
+static DEFINE_SPINLOCK(snp_leaked_pages_list_lock);
+
+static unsigned long snp_nr_leaked_pages;
+
+#undef pr_fmt
+#define pr_fmt(fmt)	"SEV-SNP: " fmt
+
+static int __mfd_enable(unsigned int cpu)
+{
+	u64 val;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return 0;
+
+	rdmsrl(MSR_AMD64_SYSCFG, val);
+
+	val |= MSR_AMD64_SYSCFG_MFDM;
+
+	wrmsrl(MSR_AMD64_SYSCFG, val);
+
+	return 0;
+}
+
+static __init void mfd_enable(void *arg)
+{
+	__mfd_enable(smp_processor_id());
+}
+
+static int __snp_enable(unsigned int cpu)
+{
+	u64 val;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return 0;
+
+	rdmsrl(MSR_AMD64_SYSCFG, val);
+
+	val |= MSR_AMD64_SYSCFG_SNP_EN;
+	val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN;
+
+	wrmsrl(MSR_AMD64_SYSCFG, val);
+
+	return 0;
+}
+
+static __init void snp_enable(void *arg)
+{
+	__snp_enable(smp_processor_id());
+}
+
+#define RMP_ADDR_MASK GENMASK_ULL(51, 13)
+
+bool snp_probe_rmptable_info(void)
+{
+	u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
+
+	rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
+	rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+
+	if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) {
+		pr_err("Memory for the RMP table has not been reserved by BIOS\n");
+		return false;
+	}
+
+	if (rmp_base > rmp_end) {
+		pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end);
+		return false;
+	}
+
+	rmp_sz = rmp_end - rmp_base + 1;
+
+	/*
+	 * Calculate the amount the memory that must be reserved by the BIOS to
+	 * address the whole RAM, including the bookkeeping area. The RMP itself
+	 * must also be covered.
+	 */
+	max_rmp_pfn = max_pfn;
+	if (PHYS_PFN(rmp_end) > max_pfn)
+		max_rmp_pfn = PHYS_PFN(rmp_end);
+
+	calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
+
+	if (calc_rmp_sz > rmp_sz) {
+		pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
+		       calc_rmp_sz, rmp_sz);
+		return false;
+	}
+
+	probed_rmp_base = rmp_base;
+	probed_rmp_size = rmp_sz;
+
+	pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
+		probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
+
+	return true;
+}
+
+/*
+ * Do the necessary preparations which are verified by the firmware as
+ * described in the SNP_INIT_EX firmware command description in the SNP
+ * firmware ABI spec.
+ */
+static int __init snp_rmptable_init(void)
+{
+	void *rmptable_start;
+	u64 rmptable_size;
+	u64 val;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return 0;
+
+	if (!amd_iommu_snp_en)
+		return 0;
+
+	if (!probed_rmp_size)
+		goto nosnp;
+
+	rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
+	if (!rmptable_start) {
+		pr_err("Failed to map RMP table\n");
+		return 1;
+	}
+
+	/*
+	 * Check if SEV-SNP is already enabled, this can happen in case of
+	 * kexec boot.
+	 */
+	rdmsrl(MSR_AMD64_SYSCFG, val);
+	if (val & MSR_AMD64_SYSCFG_SNP_EN)
+		goto skip_enable;
+
+	memset(rmptable_start, 0, probed_rmp_size);
+
+	/* Flush the caches to ensure that data is written before SNP is enabled. */
+	wbinvd_on_all_cpus();
+
+	/* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */
+	on_each_cpu(mfd_enable, NULL, 1);
+
+	on_each_cpu(snp_enable, NULL, 1);
+
+skip_enable:
+	rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ;
+	rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ;
+
+	rmptable = (struct rmpentry *)rmptable_start;
+	rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1;
+
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL);
+
+	/*
+	 * Setting crash_kexec_post_notifiers to 'true' to ensure that SNP panic
+	 * notifier is invoked to do SNP IOMMU shutdown before kdump.
+	 */
+	crash_kexec_post_notifiers = true;
+
+	return 0;
+
+nosnp:
+	setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+	return -ENOSYS;
+}
+
+/*
+ * This must be called after the IOMMU has been initialized.
+ */
+device_initcall(snp_rmptable_init);
+
+static struct rmpentry *get_rmpentry(u64 pfn)
+{
+	if (WARN_ON_ONCE(pfn > rmptable_max_pfn))
+		return ERR_PTR(-EFAULT);
+
+	return &rmptable[pfn];
+}
+
+static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
+{
+	struct rmpentry *large_entry, *entry;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return ERR_PTR(-ENODEV);
+
+	entry = get_rmpentry(pfn);
+	if (IS_ERR(entry))
+		return entry;
+
+	/*
+	 * Find the authoritative RMP entry for a PFN. This can be either a 4K
+	 * RMP entry or a special large RMP entry that is authoritative for a
+	 * whole 2M area.
+	 */
+	large_entry = get_rmpentry(pfn & PFN_PMD_MASK);
+	if (IS_ERR(large_entry))
+		return large_entry;
+
+	*level = RMP_TO_PG_LEVEL(large_entry->pagesize);
+
+	return entry;
+}
+
+int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level)
+{
+	struct rmpentry *e;
+
+	e = __snp_lookup_rmpentry(pfn, level);
+	if (IS_ERR(e))
+		return PTR_ERR(e);
+
+	*assigned = !!e->assigned;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snp_lookup_rmpentry);
+
+/*
+ * Dump the raw RMP entry for a particular PFN. These bits are documented in the
+ * PPR for a particular CPU model and provide useful information about how a
+ * particular PFN is being utilized by the kernel/firmware at the time certain
+ * unexpected events occur, such as RMP faults.
+ */
+static void dump_rmpentry(u64 pfn)
+{
+	u64 pfn_i, pfn_end;
+	struct rmpentry *e;
+	int level;
+
+	e = __snp_lookup_rmpentry(pfn, &level);
+	if (IS_ERR(e)) {
+		pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n",
+		       pfn, PTR_ERR(e));
+		return;
+	}
+
+	if (e->assigned) {
+		pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n",
+			pfn, e->lo, e->hi);
+		return;
+	}
+
+	/*
+	 * If the RMP entry for a particular PFN is not in an assigned state,
+	 * then it is sometimes useful to get an idea of whether or not any RMP
+	 * entries for other PFNs within the same 2MB region are assigned, since
+	 * those too can affect the ability to access a particular PFN in
+	 * certain situations, such as when the PFN is being accessed via a 2MB
+	 * mapping in the host page table.
+	 */
+	pfn_i = ALIGN_DOWN(pfn, PTRS_PER_PMD);
+	pfn_end = pfn_i + PTRS_PER_PMD;
+
+	pr_info("PFN 0x%llx unassigned, dumping non-zero entries in 2M PFN region: [0x%llx - 0x%llx]\n",
+		pfn, pfn_i, pfn_end);
+
+	while (pfn_i < pfn_end) {
+		e = __snp_lookup_rmpentry(pfn_i, &level);
+		if (IS_ERR(e)) {
+			pr_err("Error %ld reading RMP entry for PFN 0x%llx\n",
+			       PTR_ERR(e), pfn_i);
+			pfn_i++;
+			continue;
+		}
+
+		if (e->lo || e->hi)
+			pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi);
+		pfn_i++;
+	}
+}
+
+void snp_dump_hva_rmpentry(unsigned long hva)
+{
+	unsigned long paddr;
+	unsigned int level;
+	pgd_t *pgd;
+	pte_t *pte;
+
+	pgd = __va(read_cr3_pa());
+	pgd += pgd_index(hva);
+	pte = lookup_address_in_pgd(pgd, hva, &level);
+
+	if (!pte) {
+		pr_err("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva);
+		return;
+	}
+
+	paddr = PFN_PHYS(pte_pfn(*pte)) | (hva & ~page_level_mask(level));
+	dump_rmpentry(PHYS_PFN(paddr));
+}
+
+/*
+ * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the
+ * Validated bit.
+ */
+int psmash(u64 pfn)
+{
+	unsigned long paddr = pfn << PAGE_SHIFT;
+	int ret;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return -ENODEV;
+
+	if (!pfn_valid(pfn))
+		return -EINVAL;
+
+	/* Binutils version 2.36 supports the PSMASH mnemonic. */
+	asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF"
+		      : "=a" (ret)
+		      : "a" (paddr)
+		      : "memory", "cc");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(psmash);
+
+/*
+ * If the kernel uses a 2MB or larger directmap mapping to write to an address,
+ * and that mapping contains any 4KB pages that are set to private in the RMP
+ * table, an RMP #PF will trigger and cause a host crash. Hypervisor code that
+ * owns the PFNs being transitioned will never attempt such a write, but other
+ * kernel tasks writing to other PFNs in the range may trigger these checks
+ * inadvertently due a large directmap mapping that happens to overlap such a
+ * PFN.
+ *
+ * Prevent this by splitting any 2MB+ mappings that might end up containing a
+ * mix of private/shared PFNs as a result of a subsequent RMPUPDATE for the
+ * PFN/rmp_level passed in.
+ *
+ * Note that there is no attempt here to scan all the RMP entries for the 2MB
+ * physical range, since it would only be worthwhile in determining if a
+ * subsequent RMPUPDATE for a 4KB PFN would result in all the entries being of
+ * the same shared/private state, thus avoiding the need to split the mapping.
+ * But that would mean the entries are currently in a mixed state, and so the
+ * mapping would have already been split as a result of prior transitions.
+ * And since the 4K split is only done if the mapping is 2MB+, and there isn't
+ * currently a mechanism in place to restore 2MB+ mappings, such a check would
+ * not provide any usable benefit.
+ *
+ * More specifics on how these checks are carried out can be found in APM
+ * Volume 2, "RMP and VMPL Access Checks".
+ */
+static int adjust_direct_map(u64 pfn, int rmp_level)
+{
+	unsigned long vaddr;
+	unsigned int level;
+	int npages, ret;
+	pte_t *pte;
+
+	/*
+	 * pfn_to_kaddr() will return a vaddr only within the direct
+	 * map range.
+	 */
+	vaddr = (unsigned long)pfn_to_kaddr(pfn);
+
+	/* Only 4KB/2MB RMP entries are supported by current hardware. */
+	if (WARN_ON_ONCE(rmp_level > PG_LEVEL_2M))
+		return -EINVAL;
+
+	if (!pfn_valid(pfn))
+		return -EINVAL;
+
+	if (rmp_level == PG_LEVEL_2M &&
+	    (!IS_ALIGNED(pfn, PTRS_PER_PMD) || !pfn_valid(pfn + PTRS_PER_PMD - 1)))
+		return -EINVAL;
+
+	/*
+	 * If an entire 2MB physical range is being transitioned, then there is
+	 * no risk of RMP #PFs due to write accesses from overlapping mappings,
+	 * since even accesses from 1GB mappings will be treated as 2MB accesses
+	 * as far as RMP table checks are concerned.
+	 */
+	if (rmp_level == PG_LEVEL_2M)
+		return 0;
+
+	pte = lookup_address(vaddr, &level);
+	if (!pte || pte_none(*pte))
+		return 0;
+
+	if (level == PG_LEVEL_4K)
+		return 0;
+
+	npages = page_level_size(rmp_level) / PAGE_SIZE;
+	ret = set_memory_4k(vaddr, npages);
+	if (ret)
+		pr_warn("Failed to split direct map for PFN 0x%llx, ret: %d\n",
+			pfn, ret);
+
+	return ret;
+}
+
+/*
+ * It is expected that those operations are seldom enough so that no mutual
+ * exclusion of updaters is needed and thus the overlap error condition below
+ * should happen very rarely and would get resolved relatively quickly by
+ * the firmware.
+ *
+ * If not, one could consider introducing a mutex or so here to sync concurrent
+ * RMP updates and thus diminish the amount of cases where firmware needs to
+ * lock 2M ranges to protect against concurrent updates.
+ *
+ * The optimal solution would be range locking to avoid locking disjoint
+ * regions unnecessarily but there's no support for that yet.
+ */
+static int rmpupdate(u64 pfn, struct rmp_state *state)
+{
+	unsigned long paddr = pfn << PAGE_SHIFT;
+	int ret, level;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return -ENODEV;
+
+	level = RMP_TO_PG_LEVEL(state->pagesize);
+
+	if (adjust_direct_map(pfn, level))
+		return -EFAULT;
+
+	do {
+		/* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
+		asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
+			     : "=a" (ret)
+			     : "a" (paddr), "c" ((unsigned long)state)
+			     : "memory", "cc");
+	} while (ret == RMPUPDATE_FAIL_OVERLAP);
+
+	if (ret) {
+		pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n",
+		       pfn, level, ret);
+		dump_rmpentry(pfn);
+		dump_stack();
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/* Transition a page to guest-owned/private state in the RMP table. */
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable)
+{
+	struct rmp_state state;
+
+	memset(&state, 0, sizeof(state));
+	state.assigned = 1;
+	state.asid = asid;
+	state.immutable = immutable;
+	state.gpa = gpa;
+	state.pagesize = PG_LEVEL_TO_RMP(level);
+
+	return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_private);
+
+/* Transition a page to hypervisor-owned/shared state in the RMP table. */
+int rmp_make_shared(u64 pfn, enum pg_level level)
+{
+	struct rmp_state state;
+
+	memset(&state, 0, sizeof(state));
+	state.pagesize = PG_LEVEL_TO_RMP(level);
+
+	return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_shared);
+
+void snp_leak_pages(u64 pfn, unsigned int npages)
+{
+	struct page *page = pfn_to_page(pfn);
+
+	pr_warn("Leaking PFN range 0x%llx-0x%llx\n", pfn, pfn + npages);
+
+	spin_lock(&snp_leaked_pages_list_lock);
+	while (npages--) {
+
+		/*
+		 * Reuse the page's buddy list for chaining into the leaked
+		 * pages list. This page should not be on a free list currently
+		 * and is also unsafe to be added to a free list.
+		 */
+		if (likely(!PageCompound(page)) ||
+
+			/*
+			 * Skip inserting tail pages of compound page as
+			 * page->buddy_list of tail pages is not usable.
+			 */
+		    (PageHead(page) && compound_nr(page) <= npages))
+			list_add_tail(&page->buddy_list, &snp_leaked_pages_list);
+
+		dump_rmpentry(pfn);
+		snp_nr_leaked_pages++;
+		pfn++;
+		page++;
+	}
+	spin_unlock(&snp_leaked_pages_list_lock);
+}
+EXPORT_SYMBOL_GPL(snp_leak_pages);
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 9dd5490b3318..8b045dd25196 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -33,12 +33,6 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
 	return 0xfd;
 }
 
-static u32 xen_set_apic_id(u32 x)
-{
-	WARN_ON(1);
-	return x;
-}
-
 static u32 xen_get_apic_id(u32 x)
 {
 	return ((x)>>24) & 0xFFu;
@@ -49,20 +43,20 @@ static u32 xen_apic_read(u32 reg)
 	struct xen_platform_op op = {
 		.cmd = XENPF_get_cpuinfo,
 		.interface_version = XENPF_INTERFACE_VERSION,
-		.u.pcpu_info.xen_cpuid = 0,
 	};
-	int ret;
-
-	/* Shouldn't need this as APIC is turned off for PV, and we only
-	 * get called on the bootup processor. But just in case. */
-	if (!xen_initial_domain() || smp_processor_id())
-		return 0;
+	int ret, cpu;
 
 	if (reg == APIC_LVR)
 		return 0x14;
 	if (reg != APIC_ID)
 		return 0;
 
+	cpu = smp_processor_id();
+	if (!xen_initial_domain())
+		return cpu ? cpuid_to_apicid[cpu] << 24 : 0;
+
+	op.u.pcpu_info.xen_cpuid = cpu;
+
 	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
 		op.u.pcpu_info.apic_id = BAD_APICID;
@@ -110,11 +104,6 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
 	return xen_pv_domain();
 }
 
-static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb)
-{
-	return initial_apic_id >> index_msb;
-}
-
 static u32 xen_cpu_present_to_apicid(int cpu)
 {
 	if (cpu_present(cpu))
@@ -133,11 +122,9 @@ static struct apic xen_pv_apic __ro_after_init = {
 	.disable_esr			= 0,
 
 	.cpu_present_to_apicid		= xen_cpu_present_to_apicid,
-	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */
 
 	.max_apic_id			= UINT_MAX,
 	.get_apic_id			= xen_get_apic_id,
-	.set_apic_id			= xen_set_apic_id,
 
 	.calc_dest_apicid		= apic_flat_calc_apicid,
 
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 3f8c34707c50..99a68fa71dbe 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -168,7 +168,7 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	 */
 	xen_uninit_lock_cpu(cpu);
 
-	if (cpu_acpi_id(cpu) != U32_MAX)
+	if (cpu_acpi_id(cpu) != CPU_ACPIID_INVALID)
 		per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index aeb33e0a3f76..ace2eb054053 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -200,6 +200,9 @@ static void __init xen_pv_init_platform(void)
 		xen_set_mtrr_data();
 	else
 		mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK);
+
+	/* Adjust nr_cpu_ids before "enumeration" happens */
+	xen_smp_count_cpus();
 }
 
 static void __init xen_pv_guest_late_init(void)
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index ada3868c02c2..9e9db601bd52 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -4,6 +4,7 @@
 
 #include <xen/hvc-console.h>
 
+#include <asm/bootparam.h>
 #include <asm/io_apic.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4b0d6fff88de..935771726f9c 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+	if (!resched_name)
+		goto fail_mem;
 	per_cpu(xen_resched_irq, cpu).name = resched_name;
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
@@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu)
 	per_cpu(xen_resched_irq, cpu).irq = rc;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
 	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
@@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	if (!xen_fifo_events) {
 		debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+		if (!debug_name)
+			goto fail_mem;
+
 		per_cpu(xen_debug_irq, cpu).name = debug_name;
 		rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
 					     xen_debug_interrupt,
@@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu)
 	}
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	if (!callfunc_name)
+		goto fail_mem;
+
 	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
@@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu)
 
 	return 0;
 
+ fail_mem:
+	rc = -ENOMEM;
  fail:
 	xen_smp_intr_free(cpu);
 	return rc;
@@ -123,8 +135,6 @@ void __init xen_smp_cpus_done(unsigned int max_cpus)
 {
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
-	else
-		calculate_max_logical_packages();
 }
 
 void xen_smp_send_reschedule(int cpu)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c20cbb14c82b..b8efdbc693f7 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -19,6 +19,7 @@ extern void xen_smp_intr_free(unsigned int cpu);
 int xen_smp_intr_init_pv(unsigned int cpu);
 void xen_smp_intr_free_pv(unsigned int cpu);
 
+void xen_smp_count_cpus(void);
 void xen_smp_cpus_done(unsigned int max_cpus);
 
 void xen_smp_send_reschedule(int cpu);
@@ -44,6 +45,7 @@ static inline int xen_smp_intr_init_pv(unsigned int cpu)
 	return 0;
 }
 static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
+static inline void xen_smp_count_cpus(void) { }
 #endif /* CONFIG_SMP */
 
 #endif
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index a0f07bbfcd6e..27d1a5b7f571 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -29,6 +29,7 @@
 #include <asm/idtentry.h>
 #include <asm/desc.h>
 #include <asm/cpu.h>
+#include <asm/apic.h>
 #include <asm/io_apic.h>
 
 #include <xen/interface/xen.h>
@@ -73,7 +74,6 @@ static void cpu_bringup(void)
 	}
 	cpu = smp_processor_id();
 	smp_store_cpu_info(cpu);
-	cpu_data(cpu).x86_max_cores = 1;
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
@@ -149,39 +149,16 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	return rc;
 }
 
-static void __init _get_smp_config(unsigned int early)
+static void __init xen_pv_smp_config(void)
 {
-	int i, rc;
-	unsigned int subtract = 0;
-
-	if (early)
-		return;
-
-	num_processors = 0;
-	disabled_cpus = 0;
-	for (i = 0; i < nr_cpu_ids; i++) {
-		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
-		if (rc >= 0) {
-			num_processors++;
-			set_cpu_possible(i, true);
-		} else {
-			set_cpu_possible(i, false);
-			set_cpu_present(i, false);
-			subtract++;
-		}
-	}
-#ifdef CONFIG_HOTPLUG_CPU
-	/* This is akin to using 'nr_cpus' on the Linux command line.
-	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
-	 * have up to X, while nr_cpu_ids is greater than X. This
-	 * normally is not a problem, except when CPU hotplugging
-	 * is involved and then there might be more than X CPUs
-	 * in the guest - which will not work as there is no
-	 * hypercall to expand the max number of VCPUs an already
-	 * running guest has. So cap it up to X. */
-	if (subtract)
-		set_nr_cpu_ids(nr_cpu_ids - subtract);
-#endif
+	u32 apicid = 0;
+	int i;
+
+	topology_register_boot_apic(apicid++);
+
+	for (i = 1; i < nr_cpu_ids; i++)
+		topology_register_apic(apicid++, CPU_ACPIID_INVALID, true);
+
 	/* Pretend to be a proper enumerated system */
 	smp_found_config = 1;
 }
@@ -224,8 +201,6 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 
 	smp_prepare_cpus_common();
 
-	cpu_data(0).x86_max_cores = 1;
-
 	speculative_store_bypass_ht_init();
 
 	xen_pmu_init(0);
@@ -434,6 +409,20 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+void __init xen_smp_count_cpus(void)
+{
+	unsigned int cpus;
+
+	for (cpus = 0; cpus < nr_cpu_ids; cpus++) {
+		if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0)
+			break;
+	}
+
+	pr_info("Xen PV: Detected %u vCPUS\n", cpus);
+	if (cpus < nr_cpu_ids)
+		set_nr_cpu_ids(cpus);
+}
+
 static const struct smp_ops xen_smp_ops __initconst = {
 	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
@@ -458,6 +447,12 @@ void __init xen_smp_init(void)
 	smp_ops = xen_smp_ops;
 
 	/* Avoid searching for BIOS MP tables */
-	x86_init.mpparse.find_smp_config = x86_init_noop;
-	x86_init.mpparse.get_smp_config = _get_smp_config;
+	x86_init.mpparse.find_mptable		= x86_init_noop;
+	x86_init.mpparse.early_parse_smp_cfg	= x86_init_noop;
+
+	/* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */
+	if (xen_initial_domain())
+		x86_init.mpparse.parse_smp_cfg	= x86_init_noop;
+	else
+		x86_init.mpparse.parse_smp_cfg	= xen_pv_smp_config;
 }
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index d97adab8420f..f7547807b0bd 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -2,7 +2,6 @@
 #include <linux/screen_info.h>
 #include <linux/init.h>
 
-#include <asm/bootparam.h>
 #include <asm/setup.h>
 
 #include <xen/interface/xen.h>
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1a9cd18dfbd3..83189cf5cdce 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -28,7 +28,7 @@
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
-	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
 
@@ -69,7 +69,7 @@ SYM_FUNC_END(check_events)
 SYM_FUNC_START(xen_irq_enable_direct)
 	FRAME_BEGIN
 	/* Unmask events */
-	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 
 	/*
 	 * Preempt here doesn't matter because that will deal with any
@@ -78,7 +78,7 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	 */
 
 	/* Test for pending */
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
 	jz 1f
 
 	call check_events
@@ -97,7 +97,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
 	RET
@@ -113,7 +113,7 @@ SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_BEGIN
-	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
+	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
 	RET
 SYM_FUNC_END(xen_read_cr2_direct);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index a0ea285878db..04101b984f24 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen)
 	ANNOTATE_NOENDBR
 	cld
 
-	leaq	(__end_init_task - PTREGS_SIZE)(%rip), %rsp
+	leaq	(__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
 
 	/* Set up %gs.
 	 *
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 6f248d87e496..87ec35b3363b 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -44,6 +44,7 @@ config XTENSA
 	select HAVE_GCC_PLUGINS if GCC_VERSION >= 120000
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_PAGE_SIZE_4KB
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_STACKPROTECTOR
diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h
index c812bf85021c..46c8596259d2 100644
--- a/arch/xtensa/include/asm/jump_label.h
+++ b/arch/xtensa/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  "_nop\n\t"
 			  ".pushsection __jump_table,  \"aw\"\n\t"
 			  ".word 1b, %l[l_yes], %c0\n\t"
@@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key,
 	 * make it reachable and wrap both into a no-transform block
 	 * to avoid any assembler interference with this.
 	 */
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  ".begin no-transform\n\t"
 			  "_j %l[l_yes]\n\t"
 			  "2:\n\t"
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index a77d04972eb9..4db56ef052d2 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -22,7 +22,7 @@
  * PAGE_SHIFT determines the page size
  */
 
-#define PAGE_SHIFT	12
+#define PAGE_SHIFT	CONFIG_PAGE_SHIFT
 #define PAGE_SIZE	(__XTENSA_UL_CONST(1) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index 178cf96ca10a..defc67909a9c 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -264,16 +264,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 		struct proc_dir_entry *procdir)
 {
 	char tmp[2] = { '0' + which, 0 };
-	int err = -ENOMEM;
+	int err;
 
 	dev->fd = -1;
 	dev->filename = NULL;
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->gd = blk_alloc_disk(NUMA_NO_NODE);
-	if (!dev->gd)
+	dev->gd = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(dev->gd)) {
+		err = PTR_ERR(dev->gd);
 		goto out;
+	}
 	dev->gd->major = simdisk_major;
 	dev->gd->first_minor = which;
 	dev->gd->minors = SIMDISK_MINORS;
diff --git a/block/bdev.c b/block/bdev.c
index e9f1b12bd75c..e7adaaf1c219 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -49,6 +49,12 @@ struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
+struct block_device *file_bdev(struct file *bdev_file)
+{
+	return I_BDEV(bdev_file->f_mapping->host);
+}
+EXPORT_SYMBOL(file_bdev);
+
 static void bdev_write_inode(struct block_device *bdev)
 {
 	struct inode *inode = bdev->bd_inode;
@@ -368,24 +374,24 @@ static struct file_system_type bd_type = {
 };
 
 struct super_block *blockdev_superblock __ro_after_init;
+struct vfsmount *blockdev_mnt __ro_after_init;
 EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
 {
 	int err;
-	static struct vfsmount *bd_mnt __ro_after_init;
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
-				SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC),
+				SLAB_ACCOUNT|SLAB_PANIC),
 			init_once);
 	err = register_filesystem(&bd_type);
 	if (err)
 		panic("Cannot register bdev pseudo-fs");
-	bd_mnt = kern_mount(&bd_type);
-	if (IS_ERR(bd_mnt))
+	blockdev_mnt = kern_mount(&bd_type);
+	if (IS_ERR(blockdev_mnt))
 		panic("Cannot create bdev pseudo-fs");
-	blockdev_superblock = bd_mnt->mnt_sb;   /* For writeback */
+	blockdev_superblock = blockdev_mnt->mnt_sb;   /* For writeback */
 }
 
 struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
@@ -696,6 +702,31 @@ out_blkdev_put:
 	return ret;
 }
 
+int bdev_permission(dev_t dev, blk_mode_t mode, void *holder)
+{
+	int ret;
+
+	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
+			MAJOR(dev), MINOR(dev),
+			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
+			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
+	if (ret)
+		return ret;
+
+	/* Blocking writes requires exclusive opener */
+	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder)
+		return -EINVAL;
+
+	/*
+	 * We're using error pointers to indicate to ->release() when we
+	 * failed to open that block device. Also this doesn't make sense.
+	 */
+	if (WARN_ON_ONCE(IS_ERR(holder)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static void blkdev_put_part(struct block_device *part)
 {
 	struct block_device *whole = bdev_whole(part);
@@ -775,83 +806,55 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
 		bdev->bd_writers++;
 }
 
-static void bdev_yield_write_access(struct block_device *bdev, blk_mode_t mode)
+static void bdev_yield_write_access(struct file *bdev_file)
 {
+	struct block_device *bdev;
+
 	if (bdev_allow_write_mounted)
 		return;
 
+	bdev = file_bdev(bdev_file);
 	/* Yield exclusive or shared write access. */
-	if (mode & BLK_OPEN_RESTRICT_WRITES)
-		bdev_unblock_writes(bdev);
-	else if (mode & BLK_OPEN_WRITE)
-		bdev->bd_writers--;
+	if (bdev_file->f_mode & FMODE_WRITE) {
+		if (bdev_writes_blocked(bdev))
+			bdev_unblock_writes(bdev);
+		else
+			bdev->bd_writers--;
+	}
 }
 
 /**
- * bdev_open_by_dev - open a block device by device number
- * @dev: device number of block device to open
+ * bdev_open - open a block device
+ * @bdev: block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
  * @hops: holder operations
+ * @bdev_file: file for the block device
  *
- * Open the block device described by device number @dev. If @holder is not
- * %NULL, the block device is opened with exclusive access.  Exclusive opens may
- * nest for the same @holder.
- *
- * Use this interface ONLY if you really do not have anything better - i.e. when
- * you are behind a truly sucky interface and all you are given is a device
- * number.  Everything else should use bdev_open_by_path().
+ * Open the block device. If @holder is not %NULL, the block device is opened
+ * with exclusive access.  Exclusive opens may nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
- * failure.
+ * zero on success, -errno on failure.
  */
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-				     const struct blk_holder_ops *hops)
+int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
+	      const struct blk_holder_ops *hops, struct file *bdev_file)
 {
-	struct bdev_handle *handle = kmalloc(sizeof(struct bdev_handle),
-					     GFP_KERNEL);
-	struct block_device *bdev;
 	bool unblock_events = true;
-	struct gendisk *disk;
+	struct gendisk *disk = bdev->bd_disk;
 	int ret;
 
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-
-	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
-			MAJOR(dev), MINOR(dev),
-			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
-			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
-	if (ret)
-		goto free_handle;
-
-	/* Blocking writes requires exclusive opener */
-	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder) {
-		ret = -EINVAL;
-		goto free_handle;
-	}
-
-	bdev = blkdev_get_no_open(dev);
-	if (!bdev) {
-		ret = -ENXIO;
-		goto free_handle;
-	}
-	disk = bdev->bd_disk;
-
 	if (holder) {
 		mode |= BLK_OPEN_EXCL;
 		ret = bd_prepare_to_claim(bdev, holder, hops);
 		if (ret)
-			goto put_blkdev;
+			return ret;
 	} else {
-		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) {
-			ret = -EIO;
-			goto put_blkdev;
-		}
+		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL))
+			return -EIO;
 	}
 
 	disk_block_events(disk);
@@ -892,10 +895,16 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	handle->bdev = bdev;
-	handle->holder = holder;
-	handle->mode = mode;
-	return handle;
+
+	bdev_file->f_flags |= O_LARGEFILE;
+	bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	if (bdev_nowait(bdev))
+		bdev_file->f_mode |= FMODE_NOWAIT;
+	bdev_file->f_mapping = bdev->bd_inode->i_mapping;
+	bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
+	bdev_file->private_data = holder;
+
+	return 0;
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
@@ -903,36 +912,80 @@ abort_claiming:
 		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
-put_blkdev:
-	blkdev_put_no_open(bdev);
-free_handle:
-	kfree(handle);
-	return ERR_PTR(ret);
+	return ret;
 }
-EXPORT_SYMBOL(bdev_open_by_dev);
 
-/**
- * bdev_open_by_path - open a block device by name
- * @path: path to the block device to open
- * @mode: open mode (BLK_OPEN_*)
- * @holder: exclusive holder identifier
- * @hops: holder operations
- *
- * Open the block device described by the device file at @path.  If @holder is
- * not %NULL, the block device is opened with exclusive access.  Exclusive opens
- * may nest for the same @holder.
- *
- * CONTEXT:
- * Might sleep.
+/*
+ * If BLK_OPEN_WRITE_IOCTL is set then this is a historical quirk
+ * associated with the floppy driver where it has allowed ioctls if the
+ * file was opened for writing, but does not allow reads or writes.
+ * Make sure that this quirk is reflected in @f_flags.
  *
- * RETURNS:
- * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
- * failure.
+ * It can also happen if a block device is opened as O_RDWR | O_WRONLY.
  */
-struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops)
+static unsigned blk_to_file_flags(blk_mode_t mode)
+{
+	unsigned int flags = 0;
+
+	if ((mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) ==
+	    (BLK_OPEN_READ | BLK_OPEN_WRITE))
+		flags |= O_RDWR;
+	else if (mode & BLK_OPEN_WRITE_IOCTL)
+		flags |= O_RDWR | O_WRONLY;
+	else if (mode & BLK_OPEN_WRITE)
+		flags |= O_WRONLY;
+	else if (mode & BLK_OPEN_READ)
+		flags |= O_RDONLY; /* homeopathic, because O_RDONLY is 0 */
+	else
+		WARN_ON_ONCE(true);
+
+	if (mode & BLK_OPEN_NDELAY)
+		flags |= O_NDELAY;
+
+	return flags;
+}
+
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				   const struct blk_holder_ops *hops)
 {
-	struct bdev_handle *handle;
+	struct file *bdev_file;
+	struct block_device *bdev;
+	unsigned int flags;
+	int ret;
+
+	ret = bdev_permission(dev, mode, holder);
+	if (ret)
+		return ERR_PTR(ret);
+
+	bdev = blkdev_get_no_open(dev);
+	if (!bdev)
+		return ERR_PTR(-ENXIO);
+
+	flags = blk_to_file_flags(mode);
+	bdev_file = alloc_file_pseudo_noaccount(bdev->bd_inode,
+			blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops);
+	if (IS_ERR(bdev_file)) {
+		blkdev_put_no_open(bdev);
+		return bdev_file;
+	}
+	ihold(bdev->bd_inode);
+
+	ret = bdev_open(bdev, mode, holder, hops, bdev_file);
+	if (ret) {
+		/* We failed to open the block device. Let ->release() know. */
+		bdev_file->private_data = ERR_PTR(ret);
+		fput(bdev_file);
+		return ERR_PTR(ret);
+	}
+	return bdev_file;
+}
+EXPORT_SYMBOL(bdev_file_open_by_dev);
+
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
+				    void *holder,
+				    const struct blk_holder_ops *hops)
+{
+	struct file *file;
 	dev_t dev;
 	int error;
 
@@ -940,22 +993,28 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 	if (error)
 		return ERR_PTR(error);
 
-	handle = bdev_open_by_dev(dev, mode, holder, hops);
-	if (!IS_ERR(handle) && (mode & BLK_OPEN_WRITE) &&
-	    bdev_read_only(handle->bdev)) {
-		bdev_release(handle);
-		return ERR_PTR(-EACCES);
+	file = bdev_file_open_by_dev(dev, mode, holder, hops);
+	if (!IS_ERR(file) && (mode & BLK_OPEN_WRITE)) {
+		if (bdev_read_only(file_bdev(file))) {
+			fput(file);
+			file = ERR_PTR(-EACCES);
+		}
 	}
 
-	return handle;
+	return file;
 }
-EXPORT_SYMBOL(bdev_open_by_path);
+EXPORT_SYMBOL(bdev_file_open_by_path);
 
-void bdev_release(struct bdev_handle *handle)
+void bdev_release(struct file *bdev_file)
 {
-	struct block_device *bdev = handle->bdev;
+	struct block_device *bdev = file_bdev(bdev_file);
+	void *holder = bdev_file->private_data;
 	struct gendisk *disk = bdev->bd_disk;
 
+	/* We failed to open that block device. */
+	if (IS_ERR(holder))
+		goto put_no_open;
+
 	/*
 	 * Sync early if it looks like we're the last one.  If someone else
 	 * opens the block device between now and the decrement of bd_openers
@@ -967,10 +1026,10 @@ void bdev_release(struct bdev_handle *handle)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	bdev_yield_write_access(bdev, handle->mode);
+	bdev_yield_write_access(bdev_file);
 
-	if (handle->holder)
-		bd_end_claim(bdev, handle->holder);
+	if (holder)
+		bd_end_claim(bdev, holder);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -986,10 +1045,9 @@ void bdev_release(struct bdev_handle *handle)
 	mutex_unlock(&disk->open_mutex);
 
 	module_put(disk->fops->owner);
+put_no_open:
 	blkdev_put_no_open(bdev);
-	kfree(handle);
 }
-EXPORT_SYMBOL(bdev_release);
 
 /**
  * lookup_bdev() - Look up a struct block_device by name.
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 2c90e5de0acd..d442ee358fc2 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -127,7 +127,7 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_waiting(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_group_wait_time)
 		bfq_stat_add(&stats->group_wait_time,
 			      now - stats->start_group_wait_time);
@@ -144,7 +144,7 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 		return;
 	if (bfqg == curr_bfqg)
 		return;
-	stats->start_group_wait_time = ktime_get_ns();
+	stats->start_group_wait_time = blk_time_get_ns();
 	bfqg_stats_mark_waiting(stats);
 }
 
@@ -156,7 +156,7 @@ static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 	if (!bfqg_stats_empty(stats))
 		return;
 
-	now = ktime_get_ns();
+	now = blk_time_get_ns();
 	if (now > stats->start_empty_time)
 		bfq_stat_add(&stats->empty_time,
 			      now - stats->start_empty_time);
@@ -183,7 +183,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
 	if (bfqg_stats_empty(stats))
 		return;
 
-	stats->start_empty_time = ktime_get_ns();
+	stats->start_empty_time = blk_time_get_ns();
 	bfqg_stats_mark_empty(stats);
 }
 
@@ -192,7 +192,7 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
 	struct bfqg_stats *stats = &bfqg->stats;
 
 	if (bfqg_stats_idling(stats)) {
-		u64 now = ktime_get_ns();
+		u64 now = blk_time_get_ns();
 
 		if (now > stats->start_idle_time)
 			bfq_stat_add(&stats->idle_time,
@@ -205,7 +205,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 
-	stats->start_idle_time = ktime_get_ns();
+	stats->start_idle_time = blk_time_get_ns();
 	bfqg_stats_mark_idling(stats);
 }
 
@@ -242,7 +242,7 @@ void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 				  u64 io_start_time_ns, blk_opf_t opf)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
-	u64 now = ktime_get_ns();
+	u64 now = blk_time_get_ns();
 
 	if (now > io_start_time_ns)
 		blkg_rwstat_add(&stats->service_time, opf,
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3cce6de464a7..4b88a54a9b76 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1005,7 +1005,7 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
 
 	rq = rq_entry_fifo(bfqq->fifo.next);
 
-	if (rq == last || ktime_get_ns() < rq->fifo_time)
+	if (rq == last || blk_time_get_ns() < rq->fifo_time)
 		return NULL;
 
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
@@ -1829,7 +1829,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 		 * bfq_bfqq_update_budg_for_activation for
 		 * details on the usage of the next variable.
 		 */
-		arrived_in_time =  ktime_get_ns() <=
+		arrived_in_time =  blk_time_get_ns() <=
 			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
 	unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio);
@@ -2208,7 +2208,7 @@ static void bfq_add_request(struct request *rq)
 	struct request *next_rq, *prev;
 	unsigned int old_wr_coeff = bfqq->wr_coeff;
 	bool interactive = false;
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
 	bfqq->queued[rq_is_sync(rq)]++;
@@ -2262,7 +2262,7 @@ static void bfq_add_request(struct request *rq)
 		      bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) &&
 		    time_is_before_eq_jiffies(bfqq->decrease_time_jif +
 					      msecs_to_jiffies(10))) {
-			bfqd->last_empty_occupied_ns = ktime_get_ns();
+			bfqd->last_empty_occupied_ns = blk_time_get_ns();
 			/*
 			 * Start the state machine for measuring the
 			 * total service time of rq: setting
@@ -3294,7 +3294,7 @@ static void bfq_set_budget_timeout(struct bfq_data *bfqd,
 	else
 		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
 
-	bfqd->last_budget_start = ktime_get();
+	bfqd->last_budget_start = blk_time_get();
 
 	bfqq->budget_timeout = jiffies +
 		bfqd->bfq_timeout * timeout_coeff;
@@ -3394,7 +3394,7 @@ static void bfq_arm_slice_timer(struct bfq_data *bfqd)
 	else if (bfqq->wr_coeff > 1)
 		sl = max_t(u32, sl, 20ULL * NSEC_PER_MSEC);
 
-	bfqd->last_idling_start = ktime_get();
+	bfqd->last_idling_start = blk_time_get();
 	bfqd->last_idling_start_jiffies = jiffies;
 
 	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
@@ -3433,7 +3433,7 @@ static void bfq_reset_rate_computation(struct bfq_data *bfqd,
 				       struct request *rq)
 {
 	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
-		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+		bfqd->last_dispatch = bfqd->first_dispatch = blk_time_get_ns();
 		bfqd->peak_rate_samples = 1;
 		bfqd->sequential_samples = 0;
 		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
@@ -3590,7 +3590,7 @@ reset_computation:
  */
 static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
 		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
@@ -4162,7 +4162,7 @@ static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	if (compensate)
 		delta_ktime = bfqd->last_idling_start;
 	else
-		delta_ktime = ktime_get();
+		delta_ktime = blk_time_get();
 	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
 	delta_usecs = ktime_to_us(delta_ktime);
 
@@ -5591,7 +5591,7 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  struct bfq_io_cq *bic, pid_t pid, int is_sync,
 			  unsigned int act_idx)
 {
-	u64 now_ns = ktime_get_ns();
+	u64 now_ns = blk_time_get_ns();
 
 	bfqq->actuator_idx = act_idx;
 	RB_CLEAR_NODE(&bfqq->entity.rb_node);
@@ -5903,7 +5903,7 @@ static void bfq_update_io_thinktime(struct bfq_data *bfqd,
 	 */
 	if (bfqq->dispatched || bfq_bfqq_busy(bfqq))
 		return;
-	elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+	elapsed = blk_time_get_ns() - bfqq->ttime.last_end_request;
 	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
@@ -6194,7 +6194,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 	bfq_add_request(rq);
 	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
 
-	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = blk_time_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
 	bfq_rq_enqueued(bfqd, bfqq, rq);
@@ -6370,7 +6370,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		bfq_weights_tree_remove(bfqq);
 	}
 
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	bfqq->ttime.last_end_request = now_ns;
 
@@ -6585,7 +6585,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 static void bfq_update_inject_limit(struct bfq_data *bfqd,
 				    struct bfq_queue *bfqq)
 {
-	u64 tot_time_ns = ktime_get_ns() - bfqd->last_empty_occupied_ns;
+	u64 tot_time_ns = blk_time_get_ns() - bfqd->last_empty_occupied_ns;
 	unsigned int old_limit = bfqq->inject_limit;
 
 	if (bfqq->last_serv_time_ns > 0 && bfqd->rqs_injected) {
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index c9a16fba58b9..2e3e8e04961e 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -395,6 +395,7 @@ static blk_status_t bio_integrity_process(struct bio *bio,
 	iter.tuple_size = bi->tuple_size;
 	iter.seed = proc_iter->bi_sector;
 	iter.prot_buf = bvec_virt(bip->bip_vec);
+	iter.pi_offset = bi->pi_offset;
 
 	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
 		void *kaddr = bvec_kmap_local(&bv);
diff --git a/block/bio.c b/block/bio.c
index b9642a41f286..d24420ed1c4c 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -16,7 +16,6 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/highmem.h>
-#include <linux/sched/sysctl.h>
 #include <linux/blk-crypto.h>
 #include <linux/xarray.h>
 
@@ -251,6 +250,7 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	bio->bi_opf = opf;
 	bio->bi_flags = 0;
 	bio->bi_ioprio = 0;
+	bio->bi_write_hint = 0;
 	bio->bi_status = 0;
 	bio->bi_iter.bi_sector = 0;
 	bio->bi_iter.bi_size = 0;
@@ -762,29 +762,31 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 	struct bio_alloc_cache *cache;
 
 	cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
-	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) {
-		put_cpu();
-		bio_free(bio);
-		return;
-	}
+	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX)
+		goto out_free;
 
-	bio_uninit(bio);
-
-	if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) {
+	if (in_task()) {
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list;
+		/* Not necessary but helps not to iopoll already freed bios */
 		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
-	} else {
-		unsigned long flags;
+	} else if (in_hardirq()) {
+		lockdep_assert_irqs_disabled();
 
-		local_irq_save(flags);
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list_irq;
 		cache->free_list_irq = bio;
 		cache->nr_irq++;
-		local_irq_restore(flags);
+	} else {
+		goto out_free;
 	}
 	put_cpu();
+	return;
+out_free:
+	put_cpu();
+	bio_free(bio);
 }
 
 /**
@@ -813,6 +815,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 {
 	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
+	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 
 	if (bio->bi_bdev) {
@@ -1152,7 +1155,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 
 	bio_for_each_folio_all(fi, bio) {
 		struct page *page;
-		size_t done = 0;
+		size_t nr_pages;
 
 		if (mark_dirty) {
 			folio_lock(fi.folio);
@@ -1160,10 +1163,11 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 			folio_unlock(fi.folio);
 		}
 		page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
+		nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE -
+			   fi.offset / PAGE_SIZE + 1;
 		do {
 			bio_release_page(bio, page++);
-			done += PAGE_SIZE;
-		} while (done < fi.length);
+		} while (--nr_pages != 0);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1369,21 +1373,12 @@ int submit_bio_wait(struct bio *bio)
 {
 	DECLARE_COMPLETION_ONSTACK_MAP(done,
 			bio->bi_bdev->bd_disk->lockdep_map);
-	unsigned long hang_check;
 
 	bio->bi_private = &done;
 	bio->bi_end_io = submit_bio_wait_endio;
 	bio->bi_opf |= REQ_SYNC;
 	submit_bio(bio);
-
-	/* Prevent hang_check timer from firing at us during very long I/O */
-	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
-		while (!wait_for_completion_io_timeout(&done,
-					hang_check * (HZ/2)))
-			;
-	else
-		wait_for_completion_io(&done);
+	blk_wait_io(&done);
 
 	return blk_status_to_errno(bio->bi_status);
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ff93c385ba5a..bdbb557feb5a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1846,7 +1846,7 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
 	bool clamp;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index b927a4a0ad03..78b74106bf10 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -19,6 +19,7 @@
 #include <linux/kthread.h>
 #include <linux/blk-mq.h>
 #include <linux/llist.h>
+#include "blk.h"
 
 struct blkcg_gq;
 struct blkg_policy_data;
diff --git a/block/blk-core.c b/block/blk-core.c
index 11342af420d0..a16b5abdbbf5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -49,6 +49,7 @@
 #include "blk-pm.h"
 #include "blk-cgroup.h"
 #include "blk-throttle.h"
+#include "blk-ioprio.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -393,24 +394,34 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 {
 	struct request_queue *q;
+	int error;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO,
 				  node_id);
 	if (!q)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	q->last_merge = NULL;
 
 	q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
-	if (q->id < 0)
+	if (q->id < 0) {
+		error = q->id;
 		goto fail_q;
+	}
 
 	q->stats = blk_alloc_queue_stats();
-	if (!q->stats)
+	if (!q->stats) {
+		error = -ENOMEM;
 		goto fail_id;
+	}
+
+	error = blk_set_default_limits(lim);
+	if (error)
+		goto fail_stats;
+	q->limits = *lim;
 
 	q->node = node_id;
 
@@ -424,6 +435,7 @@ struct request_queue *blk_alloc_queue(int node_id)
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
 	mutex_init(&q->sysfs_dir_lock);
+	mutex_init(&q->limits_lock);
 	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);
 
@@ -434,12 +446,12 @@ struct request_queue *blk_alloc_queue(int node_id)
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
 	 */
-	if (percpu_ref_init(&q->q_usage_counter,
+	error = percpu_ref_init(&q->q_usage_counter,
 				blk_queue_usage_counter_release,
-				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
+				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL);
+	if (error)
 		goto fail_stats;
 
-	blk_set_default_limits(&q->limits);
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
 
 	return q;
@@ -450,7 +462,7 @@ fail_id:
 	ida_free(&blk_queue_ida, q->id);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 /**
@@ -833,6 +845,14 @@ end_io:
 }
 EXPORT_SYMBOL(submit_bio_noacct);
 
+static void bio_set_ioprio(struct bio *bio)
+{
+	/* Nobody set ioprio so far? Initialize it based on task's nice value */
+	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
+		bio->bi_ioprio = get_current_ioprio();
+	blkcg_set_ioprio(bio);
+}
+
 /**
  * submit_bio - submit a bio to the block device layer for I/O
  * @bio: The &struct bio which describes the I/O
@@ -855,6 +875,7 @@ void submit_bio(struct bio *bio)
 		count_vm_events(PGPGOUT, bio_sectors(bio));
 	}
 
+	bio_set_ioprio(bio);
 	submit_bio_noacct(bio);
 }
 EXPORT_SYMBOL(submit_bio);
@@ -1073,6 +1094,7 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
 	if (tsk->plug)
 		return;
 
+	plug->cur_ktime = 0;
 	plug->mq_list = NULL;
 	plug->cached_rq = NULL;
 	plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
@@ -1172,6 +1194,8 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 	 */
 	if (unlikely(!rq_list_empty(plug->cached_rq)))
 		blk_mq_free_plug_rqs(plug);
+
+	current->flags &= ~PF_BLOCK_TS;
 }
 
 /**
@@ -1219,8 +1243,7 @@ int __init blk_dev_init(void)
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
-	blk_requestq_cachep = kmem_cache_create("request_queue",
-			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
+	blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC);
 
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index e6468eab2681..b1e7415f8439 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -172,6 +172,7 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio		= bio_src->bi_ioprio;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3f4d41952ef2..b0f314f4bc14 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -143,7 +143,7 @@ static void blk_account_io_flush(struct request *rq)
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
 	part_stat_add(part, nsecs[STAT_FLUSH],
-		      ktime_get_ns() - rq->start_time_ns);
+		      blk_time_get_ns() - rq->start_time_ns);
 	part_stat_unlock();
 }
 
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d4e9b4556d14..ccbeb6dfa87a 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -370,6 +370,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
+	bi->pi_offset = template->pi_offset;
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c8beec6d7df0..9a85bfbbc45a 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -829,7 +829,7 @@ static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk)
 
 	/* step up/down based on the vrate */
 	vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC);
-	now_ns = ktime_get_ns();
+	now_ns = blk_time_get_ns();
 
 	if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) {
 		if (!ioc->autop_too_fast_at)
@@ -1044,7 +1044,7 @@ static void ioc_now(struct ioc *ioc, struct ioc_now *now)
 	unsigned seq;
 	u64 vrate;
 
-	now->now_ns = ktime_get();
+	now->now_ns = blk_time_get_ns();
 	now->now = ktime_to_us(now->now_ns);
 	vrate = atomic64_read(&ioc->vtime_rate);
 
@@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	lockdep_assert_held(&iocg->waitq.lock);
 
+	/*
+	 * If the delay is set by another CPU, we may be in the past. No need to
+	 * change anything if so. This avoids decay calculation underflow.
+	 */
+	if (time_before64(now->now, iocg->delay_at))
+		return false;
+
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
 	if (iocg->delay)
@@ -2810,7 +2817,7 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq)
 		return;
 	}
 
-	on_q_ns = ktime_get_ns() - rq->alloc_time_ns;
+	on_q_ns = blk_time_get_ns() - rq->alloc_time_ns;
 	rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns;
 	size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC);
 
@@ -2893,7 +2900,7 @@ static int blk_iocost_init(struct gendisk *disk)
 	ioc->vtime_base_rate = VTIME_PER_USEC;
 	atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
 	seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock);
-	ioc->period_at = ktime_to_us(ktime_get());
+	ioc->period_at = ktime_to_us(blk_time_get());
 	atomic64_set(&ioc->cur_period, 0);
 	atomic_set(&ioc->hweight_gen, 0);
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index c1a6aba1d59e..ebb522788d97 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -609,7 +609,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	if (!iolat->blkiolat->enabled)
 		return;
 
-	now = ktime_to_ns(ktime_get());
+	now = blk_time_get_ns();
 	while (blkg && blkg->parent) {
 		iolat = blkg_to_lat(blkg);
 		if (!iolat) {
@@ -661,7 +661,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
 	struct blkcg_gq *blkg;
 	struct cgroup_subsys_state *pos_css;
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(blkg, pos_css,
@@ -985,7 +985,7 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
 	struct rq_qos *rqos = iolat_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = blk_time_get_ns();
 	int cpu;
 
 	if (blk_queue_nonrot(blkg->q))
diff --git a/block/blk-lib.c b/block/blk-lib.c
index e59c3069e835..dc8e35d0a51d 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -35,6 +35,26 @@ static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 	return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT;
 }
 
+static void await_bio_endio(struct bio *bio)
+{
+	complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * await_bio_chain - ends @bio and waits for every chained bio to complete
+ */
+static void await_bio_chain(struct bio *bio)
+{
+	DECLARE_COMPLETION_ONSTACK_MAP(done,
+			bio->bi_bdev->bd_disk->lockdep_map);
+
+	bio->bi_private = &done;
+	bio->bi_end_io = await_bio_endio;
+	bio_endio(bio);
+	blk_wait_io(&done);
+}
+
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
 {
@@ -77,6 +97,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 * is disabled.
 		 */
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -120,32 +144,33 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		struct bio **biop, unsigned flags)
 {
 	struct bio *bio = *biop;
-	unsigned int max_write_zeroes_sectors;
+	unsigned int max_sectors;
 
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
-	max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
+	/* Ensure that max_sectors doesn't overflow bi_size */
+	max_sectors = bdev_write_zeroes_sectors(bdev);
 
-	if (max_write_zeroes_sectors == 0)
+	if (max_sectors == 0)
 		return -EOPNOTSUPP;
 
 	while (nr_sects) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
-		if (nr_sects > max_write_zeroes_sectors) {
-			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
-			nr_sects -= max_write_zeroes_sectors;
-			sector += max_write_zeroes_sectors;
-		} else {
-			bio->bi_iter.bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		nr_sects -= len;
+		sector += len;
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -190,6 +215,10 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 				break;
 		}
 		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			return -EINTR;
+		}
 	}
 
 	*biop = bio;
@@ -280,7 +309,7 @@ retry:
 		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
-	if (ret && try_write_zeroes) {
+	if (ret && ret != -EINTR && try_write_zeroes) {
 		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
 			try_write_zeroes = false;
 			goto retry;
@@ -322,7 +351,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		return -EPERM;
 
 	blk_start_plug(&plug);
-	for (;;) {
+	while (nr_sects) {
 		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
@@ -331,12 +360,17 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 		sector += len;
 		nr_sects -= len;
-		if (!nr_sects) {
-			ret = submit_bio_wait(bio);
-			bio_put(bio);
+		cond_resched();
+		if (fatal_signal_pending(current)) {
+			await_bio_chain(bio);
+			ret = -EINTR;
+			bio = NULL;
 			break;
 		}
-		cond_resched();
+	}
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2d470cf2173e..2a06fd33039d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -810,6 +810,10 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (rq_data_dir(req) != rq_data_dir(next))
 		return NULL;
 
+	/* Don't merge requests with different write hints. */
+	if (req->write_hint != next->write_hint)
+		return NULL;
+
 	if (req->ioprio != next->ioprio)
 		return NULL;
 
@@ -937,6 +941,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!bio_crypt_rq_ctx_compatible(rq, bio))
 		return false;
 
+	/* Don't merge requests with different write hints. */
+	if (rq->write_hint != bio->bi_write_hint)
+		return false;
+
 	if (rq->ioprio != bio_prio(bio))
 		return false;
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index aa87fcfda1ec..555ada922cf0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -21,7 +21,6 @@
 #include <linux/llist.h>
 #include <linux/cpu.h>
 #include <linux/cache.h>
-#include <linux/sched/sysctl.h>
 #include <linux/sched/topology.h>
 #include <linux/sched/signal.h>
 #include <linux/delay.h>
@@ -40,7 +39,6 @@
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
-#include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
@@ -323,7 +321,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->tag = BLK_MQ_NO_TAG;
 	rq->internal_tag = BLK_MQ_NO_TAG;
-	rq->start_time_ns = ktime_get_ns();
+	rq->start_time_ns = blk_time_get_ns();
 	rq->part = NULL;
 	blk_crypto_rq_set_defaults(rq);
 }
@@ -333,7 +331,7 @@ EXPORT_SYMBOL(blk_rq_init);
 static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
 {
 	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
+		rq->start_time_ns = blk_time_get_ns();
 	else
 		rq->start_time_ns = 0;
 
@@ -444,7 +442,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
@@ -629,7 +627,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 
 	/* alloc_time includes depth and tag waits */
 	if (blk_queue_rq_alloc_time(q))
-		alloc_time_ns = ktime_get_ns();
+		alloc_time_ns = blk_time_get_ns();
 
 	/*
 	 * If the tag allocator sleeps we could get an allocation for a
@@ -1042,7 +1040,7 @@ static inline void __blk_mq_end_request_acct(struct request *rq, u64 now)
 inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 {
 	if (blk_mq_need_time_stamp(rq))
-		__blk_mq_end_request_acct(rq, ktime_get_ns());
+		__blk_mq_end_request_acct(rq, blk_time_get_ns());
 
 	blk_mq_finish_request(rq);
 
@@ -1085,7 +1083,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 	u64 now = 0;
 
 	if (iob->need_ts)
-		now = ktime_get_ns();
+		now = blk_time_get_ns();
 
 	while ((rq = rq_list_pop(&iob->req_list)) != NULL) {
 		prefetch(rq->bio);
@@ -1168,10 +1166,11 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	if (force_irqthreads())
 		return false;
 
-	/* same CPU or cache domain?  Complete locally */
+	/* same CPU or cache domain and capacity?  Complete locally */
 	if (cpu == rq->mq_ctx->cpu ||
 	    (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) &&
-	     cpus_share_cache(cpu, rq->mq_ctx->cpu)))
+	     cpus_share_cache(cpu, rq->mq_ctx->cpu) &&
+	     cpus_equal_capacity(cpu, rq->mq_ctx->cpu)))
 		return false;
 
 	/* don't try to IPI to an offline CPU */
@@ -1255,7 +1254,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
 	    !blk_rq_is_passthrough(rq)) {
-		rq->io_start_time_ns = ktime_get_ns();
+		rq->io_start_time_ns = blk_time_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
@@ -1410,22 +1409,10 @@ blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 	blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0);
 	blk_mq_run_hw_queue(hctx, false);
 
-	if (blk_rq_is_poll(rq)) {
+	if (blk_rq_is_poll(rq))
 		blk_rq_poll_completion(rq, &wait.done);
-	} else {
-		/*
-		 * Prevent hang_check timer from firing at us during very long
-		 * I/O
-		 */
-		unsigned long hang_check = sysctl_hung_task_timeout_secs;
-
-		if (hang_check)
-			while (!wait_for_completion_io_timeout(&wait.done,
-					hang_check * (HZ/2)))
-				;
-		else
-			wait_for_completion_io(&wait.done);
-	}
+	else
+		blk_wait_io(&wait.done);
 
 	return wait.ret;
 }
@@ -2585,6 +2572,7 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 		rq->cmd_flags |= REQ_FAILFAST_MASK;
 
 	rq->__sector = bio->bi_iter.bi_sector;
+	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
 
 	/* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */
@@ -2892,9 +2880,6 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (blk_mq_attempt_bio_merge(q, bio, nsegs))
-		return NULL;
-
 	rq_qos_throttle(q, bio);
 
 	if (plug) {
@@ -2913,22 +2898,31 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 }
 
 /*
- * Check if we can use the passed on request for submitting the passed in bio,
- * and remove it from the request list if it can be used.
+ * Check if there is a suitable cached request and return it.
  */
-static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
-		struct bio *bio)
+static struct request *blk_mq_peek_cached_request(struct blk_plug *plug,
+		struct request_queue *q, blk_opf_t opf)
 {
-	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
-	enum hctx_type hctx_type = rq->mq_hctx->type;
+	enum hctx_type type = blk_mq_get_hctx_type(opf);
+	struct request *rq;
 
-	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
+	if (!plug)
+		return NULL;
+	rq = rq_list_peek(&plug->cached_rq);
+	if (!rq || rq->q != q)
+		return NULL;
+	if (type != rq->mq_hctx->type &&
+	    (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT))
+		return NULL;
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(opf))
+		return NULL;
+	return rq;
+}
 
-	if (type != hctx_type &&
-	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
-		return false;
-	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
-		return false;
+static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
+		struct bio *bio)
+{
+	WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq);
 
 	/*
 	 * If any qos ->throttle() end up blocking, we will have flushed the
@@ -2941,15 +2935,6 @@ static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = bio->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
-	return true;
-}
-
-static void bio_set_ioprio(struct bio *bio)
-{
-	/* Nobody set ioprio so far? Initialize it based on task's nice value */
-	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
-		bio->bi_ioprio = get_current_ioprio();
-	blkcg_set_ioprio(bio);
 }
 
 /**
@@ -2971,51 +2956,43 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
-	struct request *rq = NULL;
 	unsigned int nr_segs = 1;
+	struct request *rq;
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	bio_set_ioprio(bio);
 
-	if (plug) {
-		rq = rq_list_peek(&plug->cached_rq);
-		if (rq && rq->q != q)
-			rq = NULL;
-	}
-	if (rq) {
-		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
-			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-			if (!bio)
-				return;
-		}
-		if (!bio_integrity_prep(bio))
-			return;
-		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
-			return;
-		if (blk_mq_use_cached_rq(rq, plug, bio))
-			goto done;
-		percpu_ref_get(&q->q_usage_counter);
-	} else {
+	/*
+	 * If the plug has a cached request for this queue, try use it.
+	 *
+	 * The cached request already holds a q_usage_counter reference and we
+	 * don't have to acquire a new one if we use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+	if (!rq) {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
-		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
-			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-			if (!bio)
-				goto fail;
-		}
-		if (!bio_integrity_prep(bio))
-			goto fail;
 	}
 
-	rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
-	if (unlikely(!rq)) {
-fail:
-		blk_queue_exit(q);
-		return;
+	if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+		if (!bio)
+			goto queue_exit;
+	}
+	if (!bio_integrity_prep(bio))
+		goto queue_exit;
+
+	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
+		goto queue_exit;
+
+	if (!rq) {
+		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
+		if (unlikely(!rq))
+			goto queue_exit;
+	} else {
+		blk_mq_use_cached_rq(rq, plug, bio);
 	}
 
-done:
 	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
@@ -3046,6 +3023,15 @@ done:
 	} else {
 		blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq));
 	}
+	return;
+
+queue_exit:
+	/*
+	 * Don't drop the queue reference if we were trying to use a cached
+	 * request and thus didn't acquire one.
+	 */
+	if (!rq)
+		blk_queue_exit(q);
 }
 
 #ifdef CONFIG_BLK_MQ_STACKING
@@ -3107,7 +3093,7 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	blk_mq_run_dispatch_ops(q,
 			ret = blk_mq_request_issue_directly(rq, true));
 	if (ret)
-		blk_account_io_done(rq, ktime_get_ns());
+		blk_account_io_done(rq, blk_time_get_ns());
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -3185,6 +3171,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	}
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
 	rq->ioprio = rq_src->ioprio;
+	rq->write_hint = rq_src->write_hint;
 
 	if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0)
 		goto free_and_out;
@@ -4086,15 +4073,16 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
-static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
-		void *queuedata)
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node);
-	if (!q)
-		return ERR_PTR(-ENOMEM);
+	q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+	if (IS_ERR(q))
+		return q;
 	q->queuedata = queuedata;
 	ret = blk_mq_init_allocated_queue(set, q);
 	if (ret) {
@@ -4103,20 +4091,15 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	}
 	return q;
 }
-
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
-{
-	return blk_mq_init_queue_data(set, NULL);
-}
-EXPORT_SYMBOL(blk_mq_init_queue);
+EXPORT_SYMBOL(blk_mq_alloc_queue);
 
 /**
  * blk_mq_destroy_queue - shutdown a request queue
  * @q: request queue to shutdown
  *
- * This shuts down a request queue allocated by blk_mq_init_queue(). All future
+ * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future
  * requests will be failed with -ENODEV. The caller is responsible for dropping
- * the reference from blk_mq_init_queue() by calling blk_put_queue().
+ * the reference from blk_mq_alloc_queue() by calling blk_put_queue().
  *
  * Context: can sleep
  */
@@ -4137,13 +4120,14 @@ void blk_mq_destroy_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_destroy_queue);
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass)
 {
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_mq_init_queue_data(set, queuedata);
+	q = blk_mq_alloc_queue(set, lim, queuedata);
 	if (IS_ERR(q))
 		return ERR_CAST(q);
 
@@ -4397,7 +4381,7 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1)
 		set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
 
-	if (set->ops->map_queues && !is_kdump_kernel()) {
+	if (set->ops->map_queues) {
 		int i;
 
 		/*
@@ -4496,14 +4480,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 
 	/*
 	 * If a crashdump is active, then we are potentially in a very
-	 * memory constrained environment. Limit us to 1 queue and
-	 * 64 tags to prevent using too much memory.
+	 * memory constrained environment. Limit us to  64 tags to prevent
+	 * using too much memory.
 	 */
-	if (is_kdump_kernel()) {
-		set->nr_hw_queues = 1;
-		set->nr_maps = 1;
+	if (is_kdump_kernel())
 		set->queue_depth = min(64U, set->queue_depth);
-	}
+
 	/*
 	 * There is no use for more h/w queues than cpus if we just have
 	 * a single map
@@ -4533,7 +4515,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 						  GFP_KERNEL, set->numa_node);
 		if (!set->map[i].mq_map)
 			goto out_free_mq_map;
-		set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues;
+		set->map[i].nr_queues = set->nr_hw_queues;
 	}
 
 	blk_mq_update_queue_map(set);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 06ea91e51b8b..e160d56e8eda 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -26,52 +26,21 @@ void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
 EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
 
 /**
- * blk_set_default_limits - reset limits to default values
- * @lim:  the queue_limits structure to reset
- *
- * Description:
- *   Returns a queue_limit struct to its default state.
- */
-void blk_set_default_limits(struct queue_limits *lim)
-{
-	lim->max_segments = BLK_MAX_SEGMENTS;
-	lim->max_discard_segments = 1;
-	lim->max_integrity_segments = 0;
-	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	lim->virt_boundary_mask = 0;
-	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
-	lim->max_user_sectors = lim->max_dev_sectors = 0;
-	lim->chunk_sectors = 0;
-	lim->max_write_zeroes_sectors = 0;
-	lim->max_zone_append_sectors = 0;
-	lim->max_discard_sectors = 0;
-	lim->max_hw_discard_sectors = 0;
-	lim->max_secure_erase_sectors = 0;
-	lim->discard_granularity = 512;
-	lim->discard_alignment = 0;
-	lim->discard_misaligned = 0;
-	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
-	lim->bounce = BLK_BOUNCE_NONE;
-	lim->alignment_offset = 0;
-	lim->io_opt = 0;
-	lim->misaligned = 0;
-	lim->zoned = false;
-	lim->zone_write_granularity = 0;
-	lim->dma_alignment = 511;
-}
-
-/**
  * blk_set_stacking_limits - set default limits for stacking devices
  * @lim:  the queue_limits structure to reset
  *
- * Description:
- *   Returns a queue_limit struct to its default state. Should be used
- *   by stacking drivers like DM that have no internal limits.
+ * Prepare queue limits for applying limits from underlying devices using
+ * blk_stack_limits().
  */
 void blk_set_stacking_limits(struct queue_limits *lim)
 {
-	blk_set_default_limits(lim);
+	memset(lim, 0, sizeof(*lim));
+	lim->logical_block_size = SECTOR_SIZE;
+	lim->physical_block_size = SECTOR_SIZE;
+	lim->io_min = SECTOR_SIZE;
+	lim->discard_granularity = SECTOR_SIZE;
+	lim->dma_alignment = SECTOR_SIZE - 1;
+	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
@@ -82,9 +51,239 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_user_discard_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
+static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+		struct queue_limits *lim)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
+}
+
+static int blk_validate_zoned_limits(struct queue_limits *lim)
+{
+	if (!lim->zoned) {
+		if (WARN_ON_ONCE(lim->max_open_zones) ||
+		    WARN_ON_ONCE(lim->max_active_zones) ||
+		    WARN_ON_ONCE(lim->zone_write_granularity) ||
+		    WARN_ON_ONCE(lim->max_zone_append_sectors))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
+		return -EINVAL;
+
+	if (lim->zone_write_granularity < lim->logical_block_size)
+		lim->zone_write_granularity = lim->logical_block_size;
+
+	if (lim->max_zone_append_sectors) {
+		/*
+		 * The Zone Append size is limited by the maximum I/O size
+		 * and the zone size given that it can't span zones.
+		 */
+		lim->max_zone_append_sectors =
+			min3(lim->max_hw_sectors,
+			     lim->max_zone_append_sectors,
+			     lim->chunk_sectors);
+	}
+
+	return 0;
+}
+
+/*
+ * Check that the limits in lim are valid, initialize defaults for unset
+ * values, and cap values based on others where needed.
+ */
+static int blk_validate_limits(struct queue_limits *lim)
+{
+	unsigned int max_hw_sectors;
+
+	/*
+	 * Unless otherwise specified, default to 512 byte logical blocks and a
+	 * physical block size equal to the logical block size.
+	 */
+	if (!lim->logical_block_size)
+		lim->logical_block_size = SECTOR_SIZE;
+	if (lim->physical_block_size < lim->logical_block_size)
+		lim->physical_block_size = lim->logical_block_size;
+
+	/*
+	 * The minimum I/O size defaults to the physical block size unless
+	 * explicitly overridden.
+	 */
+	if (lim->io_min < lim->physical_block_size)
+		lim->io_min = lim->physical_block_size;
+
+	/*
+	 * max_hw_sectors has a somewhat weird default for historical reason,
+	 * but driver really should set their own instead of relying on this
+	 * value.
+	 *
+	 * The block layer relies on the fact that every driver can
+	 * handle at lest a page worth of data per I/O, and needs the value
+	 * aligned to the logical block size.
+	 */
+	if (!lim->max_hw_sectors)
+		lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
+		return -EINVAL;
+	lim->max_hw_sectors = round_down(lim->max_hw_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * The actual max_sectors value is a complex beast and also takes the
+	 * max_dev_sectors value (set by SCSI ULPs) and a user configurable
+	 * value into account.  The ->max_sectors value is always calculated
+	 * from these, so directly setting it won't have any effect.
+	 */
+	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
+				lim->max_dev_sectors);
+	if (lim->max_user_sectors) {
+		if (lim->max_user_sectors > max_hw_sectors ||
+		    lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+			return -EINVAL;
+		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else {
+		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
+	}
+	lim->max_sectors = round_down(lim->max_sectors,
+			lim->logical_block_size >> SECTOR_SHIFT);
+
+	/*
+	 * Random default for the maximum number of segments.  Driver should not
+	 * rely on this and set their own.
+	 */
+	if (!lim->max_segments)
+		lim->max_segments = BLK_MAX_SEGMENTS;
+
+	lim->max_discard_sectors =
+		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
+
+	if (!lim->max_discard_segments)
+		lim->max_discard_segments = 1;
+
+	if (lim->discard_granularity < lim->physical_block_size)
+		lim->discard_granularity = lim->physical_block_size;
+
+	/*
+	 * By default there is no limit on the segment boundary alignment,
+	 * but if there is one it can't be smaller than the page size as
+	 * that would break all the normal I/O patterns.
+	 */
+	if (!lim->seg_boundary_mask)
+		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
+		return -EINVAL;
+
+	/*
+	 * Devices that require a virtual boundary do not support scatter/gather
+	 * I/O natively, but instead require a descriptor list entry for each
+	 * page (which might not be identical to the Linux PAGE_SIZE).  Because
+	 * of that they are not limited by our notion of "segment size".
+	 */
+	if (lim->virt_boundary_mask) {
+		if (WARN_ON_ONCE(lim->max_segment_size &&
+				 lim->max_segment_size != UINT_MAX))
+			return -EINVAL;
+		lim->max_segment_size = UINT_MAX;
+	} else {
+		/*
+		 * The maximum segment size has an odd historic 64k default that
+		 * drivers probably should override.  Just like the I/O size we
+		 * require drivers to at least handle a full page per segment.
+		 */
+		if (!lim->max_segment_size)
+			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
+			return -EINVAL;
+	}
+
+	/*
+	 * We require drivers to at least do logical block aligned I/O, but
+	 * historically could not check for that due to the separate calls
+	 * to set the limits.  Once the transition is finished the check
+	 * below should be narrowed down to check the logical block size.
+	 */
+	if (!lim->dma_alignment)
+		lim->dma_alignment = SECTOR_SIZE - 1;
+	if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE))
+		return -EINVAL;
+
+	if (lim->alignment_offset) {
+		lim->alignment_offset &= (lim->physical_block_size - 1);
+		lim->misaligned = 0;
+	}
+
+	return blk_validate_zoned_limits(lim);
+}
+
+/*
+ * Set the default limits for a newly allocated queue.  @lim contains the
+ * initial limits set by the driver, which could be no limit in which case
+ * all fields are cleared to zero.
+ */
+int blk_set_default_limits(struct queue_limits *lim)
+{
+	/*
+	 * Most defaults are set by capping the bounds in blk_validate_limits,
+	 * but max_user_discard_sectors is special and needs an explicit
+	 * initialization to the max value here.
+	 */
+	lim->max_user_discard_sectors = UINT_MAX;
+	return blk_validate_limits(lim);
+}
+
+/**
+ * queue_limits_commit_update - commit an atomic update of queue limits
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were obtained from queue_limits_start_update()
+ * and updated by the caller to @q.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim)
+	__releases(q->limits_lock)
+{
+	int error = blk_validate_limits(lim);
+
+	if (!error) {
+		q->limits = *lim;
+		if (q->disk)
+			blk_apply_bdi_limits(q->disk->bdi, lim);
+	}
+	mutex_unlock(&q->limits_lock);
+	return error;
+}
+EXPORT_SYMBOL_GPL(queue_limits_commit_update);
+
+/**
+ * queue_limits_commit_set - apply queue limits to queue
+ * @q:		queue to update
+ * @lim:	limits to apply
+ *
+ * Apply the limits in @lim that were freshly initialized to @q.
+ * To update existing limits use queue_limits_start_update() and
+ * queue_limits_commit_update() instead.
+ *
+ * Returns 0 if successful, else a negative error code.
+ */
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
+{
+	mutex_lock(&q->limits_lock);
+	return queue_limits_commit_update(q, lim);
+}
+EXPORT_SYMBOL_GPL(queue_limits_set);
+
 /**
  * blk_queue_bounce_limit - set bounce buffer limit for queue
  * @q: the request queue for the device
@@ -177,8 +376,11 @@ EXPORT_SYMBOL(blk_queue_chunk_sectors);
 void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors)
 {
-	q->limits.max_hw_discard_sectors = max_discard_sectors;
-	q->limits.max_discard_sectors = max_discard_sectors;
+	struct queue_limits *lim = &q->limits;
+
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_discard_sectors =
+		min(max_discard_sectors, lim->max_user_discard_sectors);
 }
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
@@ -393,15 +595,7 @@ EXPORT_SYMBOL(blk_queue_alignment_offset);
 
 void disk_update_readahead(struct gendisk *disk)
 {
-	struct request_queue *q = disk->queue;
-
-	/*
-	 * For read-ahead of large files to be effective, we need to read ahead
-	 * at least twice the optimal I/O size.
-	 */
-	disk->bdi->ra_pages =
-		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
-	disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
 }
 EXPORT_SYMBOL_GPL(disk_update_readahead);
 
@@ -689,33 +883,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
 	t->zoned = max(t->zoned, b->zoned);
+	if (!t->zoned) {
+		t->zone_write_granularity = 0;
+		t->max_zone_append_sectors = 0;
+	}
 	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
- * disk_stack_limits - adjust queue limits for stacked drivers
- * @disk:  MD/DM gendisk (top)
+ * queue_limits_stack_bdev - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top device)
  * @bdev:  the underlying block device (bottom)
  * @offset:  offset to beginning of data within component device
+ * @pfx: prefix to use for warnings logged
  *
  * Description:
- *    Merges the limits for a top level gendisk and a bottom level
- *    block_device.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
  */
-void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-		       sector_t offset)
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx)
 {
-	struct request_queue *t = disk->queue;
-
-	if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
-			get_start_sect(bdev) + (offset >> 9)) < 0)
+	if (blk_stack_limits(t, &bdev_get_queue(bdev)->limits,
+			get_start_sect(bdev) + offset))
 		pr_notice("%s: Warning: Device %pg is misaligned\n",
-			disk->disk_name, bdev);
-
-	disk_update_readahead(disk);
+			pfx, bdev);
 }
-EXPORT_SYMBOL(disk_stack_limits);
+EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
 
 /**
  * blk_queue_update_dma_pad - update pad mask
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 7ff76ae6c76a..e42c263e53fb 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -27,7 +27,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat)
 /* src is a per-cpu stat, mean isn't initialized */
 void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
-	if (!src->nr_samples)
+	if (dst->nr_samples + src->nr_samples <= dst->nr_samples)
 		return;
 
 	dst->min = min(dst->min, src->min);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6b2429cad81a..8c8f69d8ba48 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -174,23 +174,29 @@ static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 static ssize_t queue_discard_max_store(struct request_queue *q,
 				       const char *page, size_t count)
 {
-	unsigned long max_discard;
-	ssize_t ret = queue_var_store(&max_discard, page, count);
+	unsigned long max_discard_bytes;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_discard_bytes, page, count);
 	if (ret < 0)
 		return ret;
 
-	if (max_discard & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (q->limits.discard_granularity - 1))
 		return -EINVAL;
 
-	max_discard >>= 9;
-	if (max_discard > UINT_MAX)
+	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	if (max_discard > q->limits.max_hw_discard_sectors)
-		max_discard = q->limits.max_hw_discard_sectors;
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
 
-	q->limits.max_discard_sectors = max_discard;
+	if (err)
+		return err;
 	return ret;
 }
 
@@ -226,35 +232,22 @@ static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
-	unsigned long var;
-	unsigned int max_sectors_kb,
-		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
-			page_kb = 1 << (PAGE_SHIFT - 10);
-	ssize_t ret = queue_var_store(&var, page, count);
+	unsigned long max_sectors_kb;
+	struct queue_limits lim;
+	ssize_t ret;
+	int err;
 
+	ret = queue_var_store(&max_sectors_kb, page, count);
 	if (ret < 0)
 		return ret;
 
-	max_sectors_kb = (unsigned int)var;
-	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb,
-					 q->limits.max_dev_sectors >> 1);
-	if (max_sectors_kb == 0) {
-		q->limits.max_user_sectors = 0;
-		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS_CAP >> 1);
-	} else {
-		if (max_sectors_kb > max_hw_sectors_kb ||
-		    max_sectors_kb < page_kb)
-			return -EINVAL;
-		q->limits.max_user_sectors = max_sectors_kb << 1;
-	}
-
-	spin_lock_irq(&q->queue_lock);
-	q->limits.max_sectors = max_sectors_kb << 1;
-	if (q->disk)
-		q->disk->bdi->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
-	spin_unlock_irq(&q->queue_lock);
-
+	blk_mq_freeze_queue(q);
+	lim = queue_limits_start_update(q);
+	lim.max_user_sectors = max_sectors_kb << 1;
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
+	if (err)
+		return err;
 	return ret;
 }
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 16f5766620a4..f4850a6f860b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1098,7 +1098,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[READ])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, READ);
 		nr_reads++;
 
 		if (nr_reads >= max_nr_reads)
@@ -1108,7 +1108,7 @@ static int throtl_dispatch_tg(struct throtl_grp *tg)
 	while ((bio = throtl_peek_queued(&sq->queued[WRITE])) &&
 	       tg_may_dispatch(tg, bio, NULL)) {
 
-		tg_dispatch_one_bio(tg, bio_data_dir(bio));
+		tg_dispatch_one_bio(tg, WRITE);
 		nr_writes++;
 
 		if (nr_writes >= max_nr_writes)
@@ -1815,7 +1815,7 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
 	time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold);
 	ret = tg->latency_target == DFL_LATENCY_TARGET ||
 	      tg->idletime_threshold == DFL_IDLE_THRESHOLD ||
-	      (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	      (blk_time_get_ns() >> 10) - tg->last_finish_time > time ||
 	      tg->avg_idletime > tg->idletime_threshold ||
 	      (tg->latency_target && tg->bio_cnt &&
 		tg->bad_bio_cnt * 5 < tg->bio_cnt);
@@ -2060,7 +2060,7 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 	if (last_finish_time == 0)
 		return;
 
-	now = ktime_get_ns() >> 10;
+	now = blk_time_get_ns() >> 10;
 	if (now <= last_finish_time ||
 	    last_finish_time == tg->checked_last_finish_time)
 		return;
@@ -2327,7 +2327,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	if (!tg->td->limit_valid[LIMIT_LOW])
 		return;
 
-	finish_time_ns = ktime_get_ns();
+	finish_time_ns = blk_time_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 5ba3cd574eac..64472134dd26 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -29,6 +29,7 @@
 #include "blk-wbt.h"
 #include "blk-rq-qos.h"
 #include "elevator.h"
+#include "blk.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -163,9 +164,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+	struct backing_dev_info *bdi = rwb->rqos.disk->bdi;
 
-	return time_before(jiffies, wb->dirty_sleep + HZ);
+	return time_before(jiffies, bdi->last_bdp_sleep + HZ);
 }
 
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
@@ -274,13 +275,12 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
 {
-	u64 now, issue = READ_ONCE(rwb->sync_issue);
+	u64 issue = READ_ONCE(rwb->sync_issue);
 
 	if (!issue || !rwb->sync_cookie)
 		return 0;
 
-	now = ktime_to_ns(ktime_get());
-	return now - issue;
+	return blk_time_get_ns() - issue;
 }
 
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index d343e5756a9c..da0f4b2a8fa0 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -11,7 +11,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/rbtree.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
 #include <linux/mm.h>
@@ -177,8 +176,7 @@ static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
 	}
 }
 
-static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
-					  gfp_t gfp_mask)
+static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	sector_t capacity = bdev_nr_sectors(bdev);
@@ -205,7 +203,7 @@ static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
 		}
 
 		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
-				   gfp_mask);
+				   GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -223,7 +221,7 @@ out_free_need_reset:
 	return ret;
 }
 
-static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
+static int blkdev_zone_reset_all(struct block_device *bdev)
 {
 	struct bio bio;
 
@@ -238,7 +236,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  * @sector:	Start sector of the first zone to operate on
  * @nr_sectors:	Number of sectors, should be at least the length of one zone and
  *		must be zone size aligned.
- * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
  *    Perform the specified operation on the range of zones specified by
@@ -248,7 +245,7 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
  *    or finish request.
  */
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		     sector_t sector, sector_t nr_sectors, gfp_t gfp_mask)
+		     sector_t sector, sector_t nr_sectors)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
@@ -285,12 +282,12 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 	 */
 	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
 		if (!blk_queue_zone_resetall(q))
-			return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
-		return blkdev_zone_reset_all(bdev, gfp_mask);
+			return blkdev_zone_reset_all_emulated(bdev);
+		return blkdev_zone_reset_all(bdev);
 	}
 
 	while (sector < end_sector) {
-		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, gfp_mask);
+		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -419,8 +416,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		return -ENOTTY;
 	}
 
-	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
-			       GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
 	if (cmd == BLKRESETZONE)
diff --git a/block/blk.h b/block/blk.h
index 1ef920f72e0f..a19b7b42e650 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -4,6 +4,8 @@
 
 #include <linux/blk-crypto.h>
 #include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
+#include <linux/sched/sysctl.h>
+#include <linux/timekeeping.h>
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
 
@@ -70,6 +72,18 @@ static inline int bio_queue_enter(struct bio *bio)
 	return __bio_queue_enter(q, bio);
 }
 
+static inline void blk_wait_io(struct completion *done)
+{
+	/* Prevent hang_check timer from firing at us during very long I/O */
+	unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+
+	if (timeout)
+		while (!wait_for_completion_io_timeout(done, timeout))
+			;
+	else
+		wait_for_completion_io(done);
+}
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
@@ -329,7 +343,7 @@ void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
 enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
-void blk_set_default_limits(struct queue_limits *lim);
+int blk_set_default_limits(struct queue_limits *lim);
 int blk_dev_init(void);
 
 /*
@@ -447,7 +461,7 @@ static inline void bio_release_page(struct bio *bio, struct page *page)
 		unpin_user_page(page);
 }
 
-struct request_queue *blk_alloc_queue(int node_id);
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id);
 
 int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode);
 
@@ -516,4 +530,75 @@ static inline int req_ref_read(struct request *req)
 	return atomic_read(&req->ref);
 }
 
+static inline u64 blk_time_get_ns(void)
+{
+	struct blk_plug *plug = current->plug;
+
+	if (!plug)
+		return ktime_get_ns();
+
+	/*
+	 * 0 could very well be a valid time, but rather than flag "this is
+	 * a valid timestamp" separately, just accept that we'll do an extra
+	 * ktime_get_ns() if we just happen to get 0 as the current time.
+	 */
+	if (!plug->cur_ktime) {
+		plug->cur_ktime = ktime_get_ns();
+		current->flags |= PF_BLOCK_TS;
+	}
+	return plug->cur_ktime;
+}
+
+static inline ktime_t blk_time_get(void)
+{
+	return ns_to_ktime(blk_time_get_ns());
+}
+
+/*
+ * From most significant bit:
+ * 1 bit: reserved for other usage, see below
+ * 12 bits: original size of bio
+ * 51 bits: issue time of bio
+ */
+#define BIO_ISSUE_RES_BITS      1
+#define BIO_ISSUE_SIZE_BITS     12
+#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
+#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
+#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
+#define BIO_ISSUE_SIZE_MASK     \
+	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
+#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
+
+/* Reserved bit for blk-throtl */
+#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
+
+static inline u64 __bio_issue_time(u64 time)
+{
+	return time & BIO_ISSUE_TIME_MASK;
+}
+
+static inline u64 bio_issue_time(struct bio_issue *issue)
+{
+	return __bio_issue_time(issue->value);
+}
+
+static inline sector_t bio_issue_size(struct bio_issue *issue)
+{
+	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
+}
+
+static inline void bio_issue_init(struct bio_issue *issue,
+				       sector_t size)
+{
+	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
+	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
+			(blk_time_get_ns() & BIO_ISSUE_TIME_MASK) |
+			((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
+void bdev_release(struct file *bdev_file);
+int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
+	      const struct blk_holder_ops *hops, struct file *bdev_file);
+int bdev_permission(dev_t dev, blk_mode_t mode, void *holder);
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index 7cfcb242f9a1..d6a5219f29dd 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -169,6 +169,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
 	bio->bi_ioprio		= bio_src->bi_ioprio;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index b3acdbdb6e7e..bcc7dee6abce 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -383,7 +383,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	if (blk_mq_alloc_tag_set(set))
 		goto out_tag_set;
 
-	q = blk_mq_init_queue(set);
+	q = blk_mq_alloc_queue(set, NULL, NULL);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
 		goto out_queue;
diff --git a/block/fops.c b/block/fops.c
index 0cf8cf72cdfa..679d9b752fe8 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -73,6 +73,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 		bio_init(&bio, bdev, vecs, nr_pages, dio_bio_write_op(iocb));
 	}
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio.bi_ioprio = iocb->ki_ioprio;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
@@ -203,6 +204,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	for (;;) {
 		bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+		bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
 		bio->bi_ioprio = iocb->ki_ioprio;
@@ -321,6 +323,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	dio->flags = 0;
 	dio->iocb = iocb;
 	bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+	bio->bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio->bi_end_io = blkdev_bio_end_io_async;
 	bio->bi_ioprio = iocb->ki_ioprio;
 
@@ -482,7 +485,7 @@ static void blkdev_readahead(struct readahead_control *rac)
 }
 
 static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct inode *inode, loff_t offset)
+		struct inode *inode, loff_t offset, unsigned int len)
 {
 	loff_t isize = i_size_read(inode);
 
@@ -569,18 +572,17 @@ static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 blk_mode_t file_to_blk_mode(struct file *file)
 {
 	blk_mode_t mode = 0;
-	struct bdev_handle *handle = file->private_data;
 
 	if (file->f_mode & FMODE_READ)
 		mode |= BLK_OPEN_READ;
 	if (file->f_mode & FMODE_WRITE)
 		mode |= BLK_OPEN_WRITE;
 	/*
-	 * do_dentry_open() clears O_EXCL from f_flags, use handle->mode to
-	 * determine whether the open was exclusive for already open files.
+	 * do_dentry_open() clears O_EXCL from f_flags, use file->private_data
+	 * to determine whether the open was exclusive for already open files.
 	 */
-	if (handle)
-		mode |= handle->mode & BLK_OPEN_EXCL;
+	if (file->private_data)
+		mode |= BLK_OPEN_EXCL;
 	else if (file->f_flags & O_EXCL)
 		mode |= BLK_OPEN_EXCL;
 	if (file->f_flags & O_NDELAY)
@@ -599,36 +601,31 @@ blk_mode_t file_to_blk_mode(struct file *file)
 
 static int blkdev_open(struct inode *inode, struct file *filp)
 {
-	struct bdev_handle *handle;
+	struct block_device *bdev;
 	blk_mode_t mode;
-
-	/*
-	 * Preserve backwards compatibility and allow large file access
-	 * even if userspace doesn't ask for it explicitly. Some mkfs
-	 * binary needs it. We might want to drop this workaround
-	 * during an unstable branch.
-	 */
-	filp->f_flags |= O_LARGEFILE;
-	filp->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
+	int ret;
 
 	mode = file_to_blk_mode(filp);
-	handle = bdev_open_by_dev(inode->i_rdev, mode,
-			mode & BLK_OPEN_EXCL ? filp : NULL, NULL);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	/* Use the file as the holder. */
+	if (mode & BLK_OPEN_EXCL)
+		filp->private_data = filp;
+	ret = bdev_permission(inode->i_rdev, mode, filp->private_data);
+	if (ret)
+		return ret;
 
-	if (bdev_nowait(handle->bdev))
-		filp->f_mode |= FMODE_NOWAIT;
+	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!bdev)
+		return -ENXIO;
 
-	filp->f_mapping = handle->bdev->bd_inode->i_mapping;
-	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
-	filp->private_data = handle;
-	return 0;
+	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
+	if (ret)
+		blkdev_put_no_open(bdev);
+	return ret;
 }
 
 static int blkdev_release(struct inode *inode, struct file *filp)
 {
-	bdev_release(filp->private_data);
+	bdev_release(filp);
 	return 0;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index d74fb5b4ae68..bb29a68e1d67 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -342,7 +342,7 @@ EXPORT_SYMBOL_GPL(disk_uevent);
 
 int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 	int ret = 0;
 
 	if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN))
@@ -366,12 +366,12 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode)
 	}
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	handle = bdev_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL,
-				  NULL);
-	if (IS_ERR(handle))
-		ret = PTR_ERR(handle);
+	file = bdev_file_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL,
+				     NULL, NULL);
+	if (IS_ERR(file))
+		ret = PTR_ERR(file);
 	else
-		bdev_release(handle);
+		fput(file);
 
 	/*
 	 * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set,
@@ -1201,7 +1201,7 @@ static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "DISKSEQ=%llu", disk->diskseq);
 }
 
-struct class block_class = {
+const struct class block_class = {
 	.name		= "block",
 	.dev_uevent	= block_uevent,
 };
@@ -1391,19 +1391,21 @@ out_free_disk:
 	return NULL;
 }
 
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass)
 {
+	struct queue_limits default_lim = { };
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_alloc_queue(node);
-	if (!q)
-		return NULL;
+	q = blk_alloc_queue(lim ? lim : &default_lim, node);
+	if (IS_ERR(q))
+		return ERR_CAST(q);
 
 	disk = __alloc_disk_node(q, node, lkclass);
 	if (!disk) {
 		blk_put_queue(q);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;
diff --git a/block/holder.c b/block/holder.c
index 37d18c13d958..791091a7eac2 100644
--- a/block/holder.c
+++ b/block/holder.c
@@ -8,6 +8,8 @@ struct bd_holder_disk {
 	int			refcnt;
 };
 
+static DEFINE_MUTEX(blk_holder_mutex);
+
 static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
 						  struct gendisk *disk)
 {
@@ -80,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	kobject_get(bdev->bd_holder_dir);
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	WARN_ON_ONCE(!bdev->bd_holder);
 
 	holder = bd_find_holder_disk(bdev, disk);
@@ -108,7 +110,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		goto out_del_symlink;
 	list_add(&holder->list, &disk->slave_bdevs);
 
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	return 0;
 
 out_del_symlink:
@@ -116,7 +118,7 @@ out_del_symlink:
 out_free_holder:
 	kfree(holder);
 out_unlock:
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 	if (ret)
 		kobject_put(bdev->bd_holder_dir);
 	return ret;
@@ -140,7 +142,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 	if (WARN_ON_ONCE(!disk->slave_dir))
 		return;
 
-	mutex_lock(&disk->open_mutex);
+	mutex_lock(&blk_holder_mutex);
 	holder = bd_find_holder_disk(bdev, disk);
 	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
 		del_symlink(disk->slave_dir, bdev_kobj(bdev));
@@ -149,6 +151,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
 		list_del_init(&holder->list);
 		kfree(holder);
 	}
-	mutex_unlock(&disk->open_mutex);
+	mutex_unlock(&blk_holder_mutex);
 }
 EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
diff --git a/block/ioctl.c b/block/ioctl.c
index 438f79c564cf..0c76137adcaa 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -18,7 +18,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	sector_t start, length;
+	sector_t start, length, capacity, end;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -41,6 +41,13 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 
 	start = p.start >> SECTOR_SHIFT;
 	length = p.length >> SECTOR_SHIFT;
+	capacity = get_capacity(disk);
+
+	if (check_add_overflow(start, length, &end))
+		return -EINVAL;
+
+	if (start >= capacity || end > capacity)
+		return -EINVAL;
 
 	switch (op) {
 	case BLKPG_ADD_PARTITION:
@@ -469,7 +476,7 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 		int __user *argp)
 {
 	int ret, n;
-	struct bdev_handle *handle;
+	struct file *file;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -481,12 +488,11 @@ static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode,
 	if (mode & BLK_OPEN_EXCL)
 		return set_blocksize(bdev, n);
 
-	handle = bdev_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
-	if (IS_ERR(handle))
+	file = bdev_file_open_by_dev(bdev->bd_dev, mode, &bdev, NULL);
+	if (IS_ERR(file))
 		return -EBUSY;
 	ret = set_blocksize(bdev, n);
-	bdev_release(handle);
-
+	fput(file);
 	return ret;
 }
 
diff --git a/block/opal_proto.h b/block/opal_proto.h
index dec7ce3a3edb..d247a457bf6e 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -71,6 +71,7 @@ enum opal_response_token {
 #define SHORT_ATOM_BYTE  0xBF
 #define MEDIUM_ATOM_BYTE 0xDF
 #define LONG_ATOM_BYTE   0xE3
+#define EMPTY_ATOM_BYTE  0xFF
 
 #define OPAL_INVAL_PARAM 12
 #define OPAL_MANUFACTURED_INACTIVE 0x08
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 5f5ed5c75f04..b11e88c82c8c 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -419,21 +419,10 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length)
 {
-	sector_t capacity = get_capacity(disk), end;
 	struct block_device *part;
 	int ret;
 
 	mutex_lock(&disk->open_mutex);
-	if (check_add_overflow(start, length, &end)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (start >= capacity || end > capacity) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	if (!disk_live(disk)) {
 		ret = -ENXIO;
 		goto out;
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index 7b521df00a39..c80183156d68 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -20,6 +20,7 @@ extern void note_bootable_part(dev_t dev, int part, int goodness);
  * Code to understand MacOS partition tables.
  */
 
+#ifdef CONFIG_PPC_PMAC
 static inline void mac_fix_string(char *stg, int len)
 {
 	int i;
@@ -27,6 +28,7 @@ static inline void mac_fix_string(char *stg, int len)
 	for (i = len - 1; i >= 0 && stg[i] == ' '; i--)
 		stg[i] = 0;
 }
+#endif
 
 int mac_partition(struct parsed_partitions *state)
 {
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 3d9e9cd250bd..14fe0fef811c 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -1056,16 +1056,20 @@ static int response_parse(const u8 *buf, size_t length,
 			token_length = response_parse_medium(iter, pos);
 		else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */
 			token_length = response_parse_long(iter, pos);
+		else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */
+			token_length = 1;
 		else /* TOKEN */
 			token_length = response_parse_token(iter, pos);
 
 		if (token_length < 0)
 			return token_length;
 
+		if (pos[0] != EMPTY_ATOM_BYTE)
+			num_entries++;
+
 		pos += token_length;
 		total -= token_length;
 		iter++;
-		num_entries++;
 	}
 
 	resp->num = num_entries;
@@ -1208,7 +1212,7 @@ static int cmd_start(struct opal_dev *dev, const u8 *uid, const u8 *method)
 static int start_opal_session_cont(struct opal_dev *dev)
 {
 	u32 hsn, tsn;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -1350,7 +1354,7 @@ static int get_active_key_cont(struct opal_dev *dev)
 {
 	const char *activekey;
 	size_t keylen;
-	int error = 0;
+	int error;
 
 	error = parse_and_check_status(dev);
 	if (error)
@@ -2153,7 +2157,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	u8 lr_buffer[OPAL_UID_LENGTH];
 	struct opal_lock_unlock *lkul = data;
 	u8 read_locked = 1, write_locked = 1;
-	int err = 0;
+	int err;
 
 	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
 				lkul->session.opal_key.lr) < 0)
@@ -2576,7 +2580,7 @@ static int opal_get_discv(struct opal_dev *dev, struct opal_discovery *discv)
 	const struct opal_step discovery0_step = {
 		opal_discovery0, discv
 	};
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&dev->dev_lock);
 	setup_opal_dev(dev);
@@ -3065,7 +3069,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 {
 	struct opal_suspend_data *suspend;
 	bool was_failure = false;
-	int ret = 0;
+	int ret;
 
 	if (!dev)
 		return false;
@@ -3108,10 +3112,9 @@ static int opal_read_table(struct opal_dev *dev,
 		{ read_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, read_table_steps,
 			     ARRAY_SIZE(read_table_steps));
@@ -3125,10 +3128,9 @@ static int opal_write_table(struct opal_dev *dev,
 		{ write_table_data, rw_tbl },
 		{ end_opal_session, }
 	};
-	int ret = 0;
 
 	if (!rw_tbl->size)
-		return ret;
+		return 0;
 
 	return execute_steps(dev, write_table_steps,
 			     ARRAY_SIZE(write_table_steps));
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 914d8cddd43a..d90892fd6f2a 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -12,14 +12,14 @@
 #include <net/checksum.h>
 #include <asm/unaligned.h>
 
-typedef __be16 (csum_fn) (void *, unsigned int);
+typedef __be16 (csum_fn) (__be16, void *, unsigned int);
 
-static __be16 t10_pi_crc_fn(void *data, unsigned int len)
+static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len)
 {
-	return cpu_to_be16(crc_t10dif(data, len));
+	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len));
 }
 
-static __be16 t10_pi_ip_fn(void *data, unsigned int len)
+static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
 {
 	return (__force __be16)ip_compute_csum(data, len);
 }
@@ -32,12 +32,16 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
 static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct t10_pi_tuple *pi = iter->prot_buf;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = fn(iter->data_buf, iter->interval);
+		pi->guard_tag = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = fn(pi->guard_tag, iter->prot_buf,
+					   offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -56,12 +60,13 @@ static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 		csum_fn *fn, enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	BUG_ON(type == T10_PI_TYPE0_PROTECTION);
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct t10_pi_tuple *pi = iter->prot_buf;
+		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 		__be16 csum;
 
 		if (type == T10_PI_TYPE1_PROTECTION ||
@@ -83,7 +88,9 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = fn(iter->data_buf, iter->interval);
+		csum = fn(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = fn(csum, iter->prot_buf, offset);
 
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
@@ -134,8 +141,10 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
  */
 static void t10_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -154,7 +163,7 @@ static void t10_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == virt)
 					pi->ref_tag = cpu_to_be32(ref_tag);
@@ -183,9 +192,11 @@ static void t10_pi_type1_prepare(struct request *rq)
  */
 static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -200,7 +211,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct t10_pi_tuple *pi = p;
+				struct t10_pi_tuple *pi = p + offset;
 
 				if (be32_to_cpu(pi->ref_tag) == ref_tag)
 					pi->ref_tag = cpu_to_be32(virt);
@@ -280,20 +291,24 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
 
-static __be64 ext_pi_crc64(void *data, unsigned int len)
+static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len)
 {
-	return cpu_to_be64(crc64_rocksoft(data, len));
+	return cpu_to_be64(crc64_rocksoft_update(crc, data, len));
 }
 
 static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 					enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = ext_pi_crc64(iter->data_buf, iter->interval);
+		pi->guard_tag = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			pi->guard_tag = ext_pi_crc64(be64_to_cpu(pi->guard_tag),
+					iter->prot_buf, offset);
 		pi->app_tag = 0;
 
 		if (type == T10_PI_TYPE1_PROTECTION)
@@ -319,10 +334,11 @@ static bool ext_pi_ref_escape(u8 *ref_tag)
 static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 				      enum t10_dif_type type)
 {
+	u8 offset = iter->pi_offset;
 	unsigned int i;
 
 	for (i = 0; i < iter->data_size; i += iter->interval) {
-		struct crc64_pi_tuple *pi = iter->prot_buf;
+		struct crc64_pi_tuple *pi = iter->prot_buf + offset;
 		u64 ref, seed;
 		__be64 csum;
 
@@ -343,7 +359,11 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 				goto next;
 		}
 
-		csum = ext_pi_crc64(iter->data_buf, iter->interval);
+		csum = ext_pi_crc64(0, iter->data_buf, iter->interval);
+		if (offset)
+			csum = ext_pi_crc64(be64_to_cpu(csum), iter->prot_buf,
+					    offset);
+
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
 			       "(rcvd %016llx, want %016llx)\n",
@@ -373,8 +393,10 @@ static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
 
 static void ext_pi_type1_prepare(struct request *rq)
 {
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -393,7 +415,7 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p +  offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == virt)
@@ -411,9 +433,11 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
-	const int tuple_sz = rq->q->integrity.tuple_size;
+	struct blk_integrity *bi = &rq->q->integrity;
+	unsigned intervals = nr_bytes >> bi->interval_exp;
+	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
+	u8 offset = bi->pi_offset;
 	struct bio *bio;
 
 	__rq_for_each_bio(bio, rq) {
@@ -428,7 +452,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 
 			p = bvec_kmap_local(&iv);
 			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
-				struct crc64_pi_tuple *pi = p;
+				struct crc64_pi_tuple *pi = p + offset;
 				u64 ref = get_unaligned_be48(pi->ref_tag);
 
 				if (ref == ref_tag)
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 82c44d4899b9..e24c829d7a01 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (!(msg->msg_flags & MSG_MORE)) {
 			err = hash_alloc_result(sk, ctx);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 			ahash_request_set_crypt(&ctx->req, NULL,
 						ctx->result, 0);
 			err = crypto_wait_req(crypto_ahash_final(&ctx->req),
 					      &ctx->wait);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 		}
 		goto done_more;
 	}
@@ -170,6 +170,7 @@ unlock:
 
 unlock_free:
 	af_alg_free_sg(&ctx->sgl);
+unlock_free_result:
 	hash_free_result(sk, ctx);
 	ctx->more = false;
 	goto unlock;
diff --git a/crypto/cbc.c b/crypto/cbc.c
index eedddef9ce40..e81918ca68b7 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -148,6 +148,9 @@ static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (!is_power_of_2(inst->alg.co.base.cra_blocksize))
 		goto out_free_inst;
 
+	if (inst->alg.co.statesize)
+		goto out_free_inst;
+
 	inst->alg.encrypt = crypto_cbc_encrypt;
 	inst->alg.decrypt = crypto_cbc_decrypt;
 
diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c
index 0b6dd8aa21f2..0f1bd7dcde24 100644
--- a/crypto/lskcipher.c
+++ b/crypto/lskcipher.c
@@ -212,13 +212,12 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 
 	ivsize = crypto_lskcipher_ivsize(tfm);
 	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(skcipher) + 1);
+	memcpy(ivs, req->iv, ivsize);
 
 	flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	if (req->base.flags & CRYPTO_SKCIPHER_REQ_CONT)
 		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
-	else
-		memcpy(ivs, req->iv, ivsize);
 
 	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
 		flags |= CRYPTO_LSKCIPHER_FLAG_FINAL;
@@ -234,8 +233,7 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
 	}
 
-	if (flags & CRYPTO_LSKCIPHER_FLAG_FINAL)
-		memcpy(req->iv, ivs, ivsize);
+	memcpy(req->iv, ivs, ivsize);
 
 	return err;
 }
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 9418c73ee8ef..4b0640226986 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -480,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU 37XX does not require 10m D3hot delay */
-	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
-		pdev->d3hot_delay = 0;
+	/* NPU does not require 10m D3hot delay */
+	pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
 	if (ret) {
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6576232f3e67..5fa8bd4603d5 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
 	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
 
 	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
-	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
 	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
 		vdev->wa.disable_d0i3_msg = true;
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index f15a93d83057..89af1006df55 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,22 +510,12 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
 	return ret;
 }
 
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
-	ivpu_boot_dpu_active_drive(vdev, false);
-	ivpu_boot_pwr_island_isolation_drive(vdev, true);
-	ivpu_boot_pwr_island_trickle_drive(vdev, false);
-	ivpu_boot_pwr_island_drive(vdev, false);
-
-	return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
 static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 {
 	u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
-	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+	val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
 	val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
 	return 0;
 }
 
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+	int ret;
+	u32 val;
+
+	if (IVPU_WA(punit_disabled))
+		return 0;
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret) {
+		ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+		return ret;
+	}
+
+	val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+	val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+	REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+	ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+	return ret;
+}
+
 static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
-	if (ivpu_boot_pwr_domain_disable(vdev)) {
-		ivpu_err(vdev, "Failed to disable power domain\n");
+	if (ivpu_hw_37xx_ip_reset(vdev)) {
+		ivpu_err(vdev, "Failed to reset NPU\n");
 		ret = -EIO;
 	}
 
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* PLL requests may fail when powering down, so issue WP 0 here */
+	ret = ivpu_pll_disable(vdev);
+	if (ret)
+		ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 704288084f37..a1523d0b1ef3 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -24,7 +24,7 @@
 #define SKU_HW_ID_SHIFT              16u
 #define SKU_HW_ID_MASK               0xffff0000u
 
-#define PLL_CONFIG_DEFAULT           0x1
+#define PLL_CONFIG_DEFAULT           0x0
 #define PLL_CDYN_DEFAULT             0x80
 #define PLL_EPP_DEFAULT              0x80
 #define PLL_REF_CLK_FREQ	     (50 * 1000000)
@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
 	u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
 
 	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
-	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+	val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
 	val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
 
 	REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 {
 	struct ivpu_hw_info *hw = vdev->hw;
 	u32 tile_disable;
-	u32 tile_enable;
 	u32 fuse;
 
 	fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
 	else
 		ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
 
-	tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
-	hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
-	hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
 	hw->tile_fuse = tile_disable;
 	hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
 
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 0440bee3ecaf..e70cfb859339 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
 		return -ENOENT;
 
 	if (job->file_priv->has_mmu_faults)
-		job_status = VPU_JSM_STATUS_ABORTED;
+		job_status = DRM_IVPU_JOB_STATUS_ABORTED;
 
 	job->bos[CMD_BUF_IDX]->job_status = job_status;
 	dma_fence_signal(job->done_fence);
@@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 	unsigned long id;
 
 	xa_for_each(&vdev->submitted_jobs_xa, id, job)
-		ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
+		ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
 }
 
 static int ivpu_job_submit(struct ivpu_job *job)
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 9a3122ffce03..91bd640655ab 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -72,10 +72,10 @@
 
 #define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
 #define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK            GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK             (IVPU_MMU_Q_COUNT - 1)
 #define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val)             ((val) & IVPU_MMU_Q_COUNT)
 
 #define IVPU_MMU_CMDQ_CMD_SIZE		16
 #define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 	return 0;
 }
 
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+	return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+		(IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
 static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
 {
-	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
-	u64 *queue_buffer = q->base;
-	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+	u64 *queue_buffer = cmdq->base;
+	int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
 
-	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+	if (ivpu_mmu_queue_is_full(cmdq)) {
 		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
 		return -EBUSY;
 	}
 
 	queue_buffer[idx] = data0;
 	queue_buffer[idx + 1] = data1;
-	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+	cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
 
 	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
 
@@ -560,7 +572,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->cmdq.cons = 0;
 
 	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
-	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
@@ -874,14 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
-	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+	if (ivpu_mmu_queue_is_empty(evtq))
 		return NULL;
 
-	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
 	return evt;
 }
 
@@ -902,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
 		}
 
 		ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+		REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
 	}
 }
 
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index f501f27ebafd..5f73854234ba 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -58,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
 {
 	int ret;
 
+	/* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+	pci_save_state(to_pci_dev(vdev->drm.dev));
+
 	ret = ivpu_shutdown(vdev);
-	if (ret) {
+	if (ret)
 		ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-		return ret;
-	}
+
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
 
 	return ret;
 }
@@ -71,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
 {
 	int ret;
 
+	pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+	pci_restore_state(to_pci_dev(vdev->drm.dev));
+
 retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
@@ -120,15 +126,20 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 
 	ivpu_fw_log_dump(vdev);
 
-retry:
-	ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
-	if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
-		cond_resched();
-		goto retry;
-	}
+	atomic_inc(&vdev->pm->reset_counter);
+	atomic_set(&vdev->pm->reset_pending, 1);
+	down_write(&vdev->pm->reset_lock);
+
+	ivpu_suspend(vdev);
+	ivpu_pm_prepare_cold_boot(vdev);
+	ivpu_jobs_abort_all(vdev);
+
+	ret = ivpu_resume(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
 
-	if (ret && ret != -EAGAIN)
-		ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+	up_write(&vdev->pm->reset_lock);
+	atomic_set(&vdev->pm->reset_pending, 0);
 
 	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
@@ -200,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
-	pci_save_state(to_pci_dev(dev));
-	pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
 	ivpu_dbg(vdev, PM, "Suspend done.\n");
 
 	return 0;
@@ -216,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
 
 	ivpu_dbg(vdev, PM, "Resume..\n");
 
-	pci_set_power_state(to_pci_dev(dev), PCI_D0);
-	pci_restore_state(to_pci_dev(dev));
-
 	ret = ivpu_resume(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to resume: %d\n", ret);
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7b7c605166e0..ab2a82cb1b0b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,7 +26,6 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
-#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -674,78 +673,6 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
-/*
- * Only a single callback can be registered for CXL CPER events.
- */
-static DECLARE_RWSEM(cxl_cper_rw_sem);
-static cxl_cper_callback cper_callback;
-
-/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
-
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
-	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
-		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-#define CPER_SEC_CXL_DRAM_GUID						\
-	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
-		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-#define CPER_SEC_CXL_MEM_MODULE_GUID					\
-	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
-		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
-
-static void cxl_cper_post_event(enum cxl_event_type event_type,
-				struct cxl_cper_event_rec *rec)
-{
-	if (rec->hdr.length <= sizeof(rec->hdr) ||
-	    rec->hdr.length > sizeof(*rec)) {
-		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
-		       rec->hdr.length);
-		return;
-	}
-
-	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
-		pr_err(FW_WARN "CXL CPER invalid event\n");
-		return;
-	}
-
-	guard(rwsem_read)(&cxl_cper_rw_sem);
-	if (cper_callback)
-		cper_callback(event_type, rec);
-}
-
-int cxl_cper_register_callback(cxl_cper_callback callback)
-{
-	guard(rwsem_write)(&cxl_cper_rw_sem);
-	if (cper_callback)
-		return -EINVAL;
-	cper_callback = callback;
-	return 0;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
-
-int cxl_cper_unregister_callback(cxl_cper_callback callback)
-{
-	guard(rwsem_write)(&cxl_cper_rw_sem);
-	if (callback != cper_callback)
-		return -EINVAL;
-	cper_callback = NULL;
-	return 0;
-}
-EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
-
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -780,22 +707,6 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
-		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
-			struct cxl_cper_event_rec *rec =
-				acpi_hest_get_payload(gdata);
-
-			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
-		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
-			struct cxl_cper_event_rec *rec =
-				acpi_hest_get_payload(gdata);
-
-			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
-		} else if (guid_equal(sec_type,
-				      &CPER_SEC_CXL_MEM_MODULE_GUID)) {
-			struct cxl_cper_event_rec *rec =
-				acpi_hest_get_payload(gdata);
-
-			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index dbdee2924594..02255795b800 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -525,10 +525,12 @@ static void acpi_ec_clear(struct acpi_ec *ec)
 
 static void acpi_ec_enable_event(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (acpi_ec_started(ec))
 		__acpi_ec_enable_event(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 
 	/* Drain additional events if hardware requires that */
 	if (EC_FLAGS_CLEAR_ON_RESUME)
@@ -544,9 +546,11 @@ static void __acpi_ec_flush_work(void)
 
 static void acpi_ec_disable_event(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	__acpi_ec_disable_event(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 
 	/*
 	 * When ec_freeze_events is true, we need to flush events in
@@ -567,9 +571,10 @@ void acpi_ec_flush_work(void)
 
 static bool acpi_ec_guard_event(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	bool guarded;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	/*
 	 * If firmware SCI_EVT clearing timing is "event", we actually
 	 * don't know when the SCI_EVT will be cleared by firmware after
@@ -585,29 +590,31 @@ static bool acpi_ec_guard_event(struct acpi_ec *ec)
 	guarded = ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT &&
 		ec->event_state != EC_EVENT_READY &&
 		(!ec->curr || ec->curr->command != ACPI_EC_COMMAND_QUERY);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return guarded;
 }
 
 static int ec_transaction_polled(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int ret = 0;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL))
 		ret = 1;
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
 static int ec_transaction_completed(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int ret = 0;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE))
 		ret = 1;
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
@@ -749,6 +756,7 @@ static int ec_guard(struct acpi_ec *ec)
 
 static int ec_poll(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	int repeat = 5; /* number of command restarts */
 
 	while (repeat--) {
@@ -757,14 +765,14 @@ static int ec_poll(struct acpi_ec *ec)
 		do {
 			if (!ec_guard(ec))
 				return 0;
-			spin_lock(&ec->lock);
+			spin_lock_irqsave(&ec->lock, flags);
 			advance_transaction(ec, false);
-			spin_unlock(&ec->lock);
+			spin_unlock_irqrestore(&ec->lock, flags);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
-		spin_lock(&ec->lock);
+		spin_lock_irqsave(&ec->lock, flags);
 		start_transaction(ec);
-		spin_unlock(&ec->lock);
+		spin_unlock_irqrestore(&ec->lock, flags);
 	}
 	return -ETIME;
 }
@@ -772,10 +780,11 @@ static int ec_poll(struct acpi_ec *ec)
 static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 					struct transaction *t)
 {
+	unsigned long tmp;
 	int ret = 0;
 
 	/* start transaction */
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, tmp);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */
 	if (!acpi_ec_submit_flushable_request(ec)) {
 		ret = -EINVAL;
@@ -786,11 +795,11 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	ec->curr = t;
 	ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command));
 	start_transaction(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, tmp);
 
 	ret = ec_poll(ec);
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, tmp);
 	if (t->irq_count == ec_storm_threshold)
 		acpi_ec_unmask_events(ec);
 	ec_dbg_req("Command(%s) stopped", acpi_ec_cmd_string(t->command));
@@ -799,7 +808,7 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	acpi_ec_complete_request(ec);
 	ec_dbg_ref(ec, "Decrease command");
 unlock:
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, tmp);
 	return ret;
 }
 
@@ -927,7 +936,9 @@ EXPORT_SYMBOL(ec_get_handle);
 
 static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (!test_and_set_bit(EC_FLAGS_STARTED, &ec->flags)) {
 		ec_dbg_drv("Starting EC");
 		/* Enable GPE for event processing (SCI_EVT=1) */
@@ -937,28 +948,31 @@ static void acpi_ec_start(struct acpi_ec *ec, bool resuming)
 		}
 		ec_log_drv("EC started");
 	}
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static bool acpi_ec_stopped(struct acpi_ec *ec)
 {
+	unsigned long flags;
 	bool flushed;
 
-	spin_lock(&ec->lock);
+	spin_lock_irqsave(&ec->lock, flags);
 	flushed = acpi_ec_flushed(ec);
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 	return flushed;
 }
 
 static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	if (acpi_ec_started(ec)) {
 		ec_dbg_drv("Stopping EC");
 		set_bit(EC_FLAGS_STOPPED, &ec->flags);
-		spin_unlock(&ec->lock);
+		spin_unlock_irqrestore(&ec->lock, flags);
 		wait_event(ec->wait, acpi_ec_stopped(ec));
-		spin_lock(&ec->lock);
+		spin_lock_irqsave(&ec->lock, flags);
 		/* Disable GPE for event processing (SCI_EVT=1) */
 		if (!suspending) {
 			acpi_ec_complete_request(ec);
@@ -969,25 +983,29 @@ static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 		clear_bit(EC_FLAGS_STOPPED, &ec->flags);
 		ec_log_drv("EC stopped");
 	}
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static void acpi_ec_enter_noirq(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	ec->busy_polling = true;
 	ec->polling_guard = 0;
 	ec_log_drv("interrupt blocked");
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static void acpi_ec_leave_noirq(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 	ec->busy_polling = ec_busy_polling;
 	ec->polling_guard = ec_polling_guard;
 	ec_log_drv("interrupt unblocked");
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 void acpi_ec_block_transactions(void)
@@ -1119,9 +1137,9 @@ static void acpi_ec_event_processor(struct work_struct *work)
 
 	ec_dbg_evt("Query(0x%02x) stopped", handler->query_bit);
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 	ec->queries_in_progress--;
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 
 	acpi_ec_put_query_handler(handler);
 	kfree(q);
@@ -1184,12 +1202,12 @@ static int acpi_ec_submit_query(struct acpi_ec *ec)
 	 */
 	ec_dbg_evt("Query(0x%02x) scheduled", value);
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 
 	ec->queries_in_progress++;
 	queue_work(ec_query_wq, &q->work);
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 
 	return 0;
 
@@ -1205,14 +1223,14 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec_dbg_evt("Event started");
 
-	spin_lock(&ec->lock);
+	spin_lock_irq(&ec->lock);
 
 	while (ec->events_to_process) {
-		spin_unlock(&ec->lock);
+		spin_unlock_irq(&ec->lock);
 
 		acpi_ec_submit_query(ec);
 
-		spin_lock(&ec->lock);
+		spin_lock_irq(&ec->lock);
 
 		ec->events_to_process--;
 	}
@@ -1229,11 +1247,11 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 		ec_dbg_evt("Event stopped");
 
-		spin_unlock(&ec->lock);
+		spin_unlock_irq(&ec->lock);
 
 		guard_timeout = !!ec_guard(ec);
 
-		spin_lock(&ec->lock);
+		spin_lock_irq(&ec->lock);
 
 		/* Take care of SCI_EVT unless someone else is doing that. */
 		if (guard_timeout && !ec->curr)
@@ -1246,7 +1264,7 @@ static void acpi_ec_event_handler(struct work_struct *work)
 
 	ec->events_in_progress--;
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irq(&ec->lock);
 }
 
 static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt)
@@ -1271,11 +1289,13 @@ static void clear_gpe_and_advance_transaction(struct acpi_ec *ec, bool interrupt
 
 static void acpi_ec_handle_interrupt(struct acpi_ec *ec)
 {
-	spin_lock(&ec->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
 
 	clear_gpe_and_advance_transaction(ec, true);
 
-	spin_unlock(&ec->lock);
+	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
@@ -2085,7 +2105,7 @@ bool acpi_ec_dispatch_gpe(void)
 	 * Dispatch the EC GPE in-band, but do not report wakeup in any case
 	 * to allow the caller to process events properly after that.
 	 */
-	spin_lock(&first_ec->lock);
+	spin_lock_irq(&first_ec->lock);
 
 	if (acpi_ec_gpe_status_set(first_ec)) {
 		pm_pr_dbg("ACPI EC GPE status set\n");
@@ -2094,7 +2114,7 @@ bool acpi_ec_dispatch_gpe(void)
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 	}
 
-	spin_unlock(&first_ec->lock);
+	spin_unlock_irq(&first_ec->lock);
 
 	if (!work_in_progress)
 		return false;
@@ -2107,11 +2127,11 @@ bool acpi_ec_dispatch_gpe(void)
 
 		pm_pr_dbg("ACPI EC work flushed\n");
 
-		spin_lock(&first_ec->lock);
+		spin_lock_irq(&first_ec->lock);
 
 		work_in_progress = acpi_ec_work_in_progress(first_ec);
 
-		spin_unlock(&first_ec->lock);
+		spin_unlock_irq(&first_ec->lock);
 	} while (work_in_progress && !pm_wakeup_pending());
 
 	return false;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 8dd23b19e997..eca24f41556d 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
 {
 	WARN_ON(!list_empty(&thread->waiting_thread_node));
 	binder_enqueue_work_ilocked(work, &thread->todo);
+
+	/* (e)poll-based threads require an explicit wakeup signal when
+	 * queuing their own work; they rely on these events to consume
+	 * messages without I/O block. Without it, threads risk waiting
+	 * indefinitely without handling the work.
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+	    thread->pid == current->pid && !thread->process_todo)
+		wake_up_interruptible_sync(&thread->wait);
+
 	thread->process_todo = true;
 }
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index d2460fa985b7..682ff550ccfb 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -606,13 +606,13 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* ASMedia */
-	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci_43bit_dma },	/* ASM1060 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci_43bit_dma },	/* ASM1060 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma },	/* ASM1061 */
 	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma },	/* ASM1061/1062 */
-	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci },   /* ASM1061R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci },   /* ASM1062R */
-	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci },   /* ASM1062+JMB575 */
+	{ PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci_43bit_dma },	/* ASM1061R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci_43bit_dma },	/* ASM1062R */
+	{ PCI_VDEVICE(ASMEDIA, 0x0624), board_ahci_43bit_dma },	/* ASM1062+JMB575 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1062), board_ahci },	/* ASM1062A */
 	{ PCI_VDEVICE(ASMEDIA, 0x1064), board_ahci },	/* ASM1064 */
 	{ PCI_VDEVICE(ASMEDIA, 0x1164), board_ahci },   /* ASM1164 */
@@ -671,9 +671,17 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets");
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 					 struct ahci_host_priv *hpriv)
 {
-	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == 0x1166) {
-		dev_info(&pdev->dev, "ASM1166 has only six ports\n");
-		hpriv->saved_port_map = 0x3f;
+	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA) {
+		switch (pdev->device) {
+		case 0x1166:
+			dev_info(&pdev->dev, "ASM1166 has only six ports\n");
+			hpriv->saved_port_map = 0x3f;
+			break;
+		case 0x1064:
+			dev_info(&pdev->dev, "ASM1064 has only four ports\n");
+			hpriv->saved_port_map = 0xf;
+			break;
+		}
 	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) {
diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index 64f7f7d6ba84..11a2c199a7c2 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -88,7 +88,6 @@ struct ceva_ahci_priv {
 	u32 axicc;
 	bool is_cci_enabled;
 	int flags;
-	struct reset_control *rst;
 };
 
 static unsigned int ceva_ahci_read_id(struct ata_device *dev,
@@ -189,6 +188,60 @@ static const struct scsi_host_template ahci_platform_sht = {
 	AHCI_SHT(DRV_NAME),
 };
 
+static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
+{
+	int rc, i;
+
+	rc = ahci_platform_enable_regulators(hpriv);
+	if (rc)
+		return rc;
+
+	rc = ahci_platform_enable_clks(hpriv);
+	if (rc)
+		goto disable_regulator;
+
+	/* Assert the controller reset */
+	rc = ahci_platform_assert_rsts(hpriv);
+	if (rc)
+		goto disable_clks;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		rc = phy_init(hpriv->phys[i]);
+		if (rc)
+			goto disable_rsts;
+	}
+
+	/* De-assert the controller reset */
+	ahci_platform_deassert_rsts(hpriv);
+
+	for (i = 0; i < hpriv->nports; i++) {
+		rc = phy_power_on(hpriv->phys[i]);
+		if (rc) {
+			phy_exit(hpriv->phys[i]);
+			goto disable_phys;
+		}
+	}
+
+	return 0;
+
+disable_rsts:
+	ahci_platform_deassert_rsts(hpriv);
+
+disable_phys:
+	while (--i >= 0) {
+		phy_power_off(hpriv->phys[i]);
+		phy_exit(hpriv->phys[i]);
+	}
+
+disable_clks:
+	ahci_platform_disable_clks(hpriv);
+
+disable_regulator:
+	ahci_platform_disable_regulators(hpriv);
+
+	return rc;
+}
+
 static int ceva_ahci_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -203,47 +256,19 @@ static int ceva_ahci_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	cevapriv->ahci_pdev = pdev;
-
-	cevapriv->rst = devm_reset_control_get_optional_exclusive(&pdev->dev,
-								  NULL);
-	if (IS_ERR(cevapriv->rst))
-		dev_err_probe(&pdev->dev, PTR_ERR(cevapriv->rst),
-			      "failed to get reset\n");
-
 	hpriv = ahci_platform_get_resources(pdev, 0);
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 
-	if (!cevapriv->rst) {
-		rc = ahci_platform_enable_resources(hpriv);
-		if (rc)
-			return rc;
-	} else {
-		int i;
+	hpriv->rsts = devm_reset_control_get_optional_exclusive(&pdev->dev,
+								NULL);
+	if (IS_ERR(hpriv->rsts))
+		return dev_err_probe(&pdev->dev, PTR_ERR(hpriv->rsts),
+				     "failed to get reset\n");
 
-		rc = ahci_platform_enable_clks(hpriv);
-		if (rc)
-			return rc;
-		/* Assert the controller reset */
-		reset_control_assert(cevapriv->rst);
-
-		for (i = 0; i < hpriv->nports; i++) {
-			rc = phy_init(hpriv->phys[i]);
-			if (rc)
-				return rc;
-		}
-
-		/* De-assert the controller reset */
-		reset_control_deassert(cevapriv->rst);
-
-		for (i = 0; i < hpriv->nports; i++) {
-			rc = phy_power_on(hpriv->phys[i]);
-			if (rc) {
-				phy_exit(hpriv->phys[i]);
-				return rc;
-			}
-		}
-	}
+	rc = ceva_ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
 
 	if (of_property_read_bool(np, "ceva,broken-gen2"))
 		cevapriv->flags = CEVA_FLAG_BROKEN_GEN2;
@@ -252,52 +277,60 @@ static int ceva_ahci_probe(struct platform_device *pdev)
 	if (of_property_read_u8_array(np, "ceva,p0-cominit-params",
 					(u8 *)&cevapriv->pp2c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-cominit-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-cominit-params",
 					(u8 *)&cevapriv->pp2c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-cominit-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read OOB timing value for COMWAKE from device-tree*/
 	if (of_property_read_u8_array(np, "ceva,p0-comwake-params",
 					(u8 *)&cevapriv->pp3c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-comwake-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-comwake-params",
 					(u8 *)&cevapriv->pp3c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-comwake-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read phy BURST timing value from device-tree */
 	if (of_property_read_u8_array(np, "ceva,p0-burst-params",
 					(u8 *)&cevapriv->pp4c[0], 4) < 0) {
 		dev_warn(dev, "ceva,p0-burst-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u8_array(np, "ceva,p1-burst-params",
 					(u8 *)&cevapriv->pp4c[1], 4) < 0) {
 		dev_warn(dev, "ceva,p1-burst-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/* Read phy RETRY interval timing value from device-tree */
 	if (of_property_read_u16_array(np, "ceva,p0-retry-params",
 					(u16 *)&cevapriv->pp5c[0], 2) < 0) {
 		dev_warn(dev, "ceva,p0-retry-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	if (of_property_read_u16_array(np, "ceva,p1-retry-params",
 					(u16 *)&cevapriv->pp5c[1], 2) < 0) {
 		dev_warn(dev, "ceva,p1-retry-params property not defined\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto disable_resources;
 	}
 
 	/*
@@ -335,7 +368,7 @@ static int __maybe_unused ceva_ahci_resume(struct device *dev)
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
 
-	rc = ahci_platform_enable_resources(hpriv);
+	rc = ceva_ahci_platform_enable_resources(hpriv);
 	if (rc)
 		return rc;
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 09ed67772fae..be3412cdb22e 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2001,6 +2001,33 @@ bool ata_dev_power_init_tf(struct ata_device *dev, struct ata_taskfile *tf,
 	return true;
 }
 
+static bool ata_dev_power_is_active(struct ata_device *dev)
+{
+	struct ata_taskfile tf;
+	unsigned int err_mask;
+
+	ata_tf_init(dev, &tf);
+	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+	tf.protocol = ATA_PROT_NODATA;
+	tf.command = ATA_CMD_CHK_POWER;
+
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	if (err_mask) {
+		ata_dev_err(dev, "Check power mode failed (err_mask=0x%x)\n",
+			    err_mask);
+		/*
+		 * Assume we are in standby mode so that we always force a
+		 * spinup in ata_dev_power_set_active().
+		 */
+		return false;
+	}
+
+	ata_dev_dbg(dev, "Power mode: 0x%02x\n", tf.nsect);
+
+	/* Active or idle */
+	return tf.nsect == 0xff;
+}
+
 /**
  *	ata_dev_power_set_standby - Set a device power mode to standby
  *	@dev: target device
@@ -2017,6 +2044,11 @@ void ata_dev_power_set_standby(struct ata_device *dev)
 	struct ata_taskfile tf;
 	unsigned int err_mask;
 
+	/* If the device is already sleeping or in standby, do nothing. */
+	if ((dev->flags & ATA_DFLAG_SLEEPING) ||
+	    !ata_dev_power_is_active(dev))
+		return;
+
 	/*
 	 * Some odd clown BIOSes issue spindown on power off (ACPI S4 or S5)
 	 * causing some drives to spin up and down again. For these, do nothing
@@ -2042,33 +2074,6 @@ void ata_dev_power_set_standby(struct ata_device *dev)
 			    err_mask);
 }
 
-static bool ata_dev_power_is_active(struct ata_device *dev)
-{
-	struct ata_taskfile tf;
-	unsigned int err_mask;
-
-	ata_tf_init(dev, &tf);
-	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
-	tf.protocol = ATA_PROT_NODATA;
-	tf.command = ATA_CMD_CHK_POWER;
-
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
-	if (err_mask) {
-		ata_dev_err(dev, "Check power mode failed (err_mask=0x%x)\n",
-			    err_mask);
-		/*
-		 * Assume we are in standby mode so that we always force a
-		 * spinup in ata_dev_power_set_active().
-		 */
-		return false;
-	}
-
-	ata_dev_dbg(dev, "Power mode: 0x%02x\n", tf.nsect);
-
-	/* Active or idle */
-	return tf.nsect == 0xff;
-}
-
 /**
  *	ata_dev_power_set_active -  Set a device power mode to active
  *	@dev: target device
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index e327a0229dc1..e7f713cd70d3 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card)
 	vc->scq = alloc_scq(card, vc->class);
 	if (!vc->scq) {
 		printk("%s: can't get SCQ.\n", card->name);
+		kfree(card->vcs[0]);
+		card->vcs[0] = NULL;
 		return -ENOMEM;
 	}
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 018ac202de34..024b78a0cfc1 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -431,9 +431,6 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	struct cpufreq_policy *policy = data;
 	int cpu;
 
-	if (!raw_capacity)
-		return 0;
-
 	if (val != CPUFREQ_CREATE_POLICY)
 		return 0;
 
@@ -450,9 +447,11 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	}
 
 	if (cpumask_empty(cpus_to_visit)) {
-		topology_normalize_cpu_scale();
-		schedule_work(&update_topology_flags_work);
-		free_raw_capacity();
+		if (raw_capacity) {
+			topology_normalize_cpu_scale();
+			schedule_work(&update_topology_flags_work);
+			free_raw_capacity();
+		}
 		pr_debug("cpu_capacity: parsing done\n");
 		schedule_work(&parsing_done_work);
 	}
@@ -472,7 +471,7 @@ static int __init register_cpufreq_notifier(void)
 	 * On ACPI-based systems skip registering cpufreq notifier as cpufreq
 	 * information is not needed for cpu capacity initialization.
 	 */
-	if (!acpi_disabled || !raw_capacity)
+	if (!acpi_disabled)
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL))
diff --git a/drivers/base/base.h b/drivers/base/base.h
index eb4c0ace9242..0738ccad08b2 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -207,7 +207,7 @@ static inline int devtmpfs_init(void) { return 0; }
 #endif
 
 #ifdef CONFIG_BLOCK
-extern struct class block_class;
+extern const struct class block_class;
 static inline bool is_blockdev(struct device *dev)
 {
 	return dev->class == &block_class;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 14d46af40f9a..9828da9b933c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -125,7 +125,7 @@ static void __fwnode_link_del(struct fwnode_link *link)
  */
 static void __fwnode_link_cycle(struct fwnode_link *link)
 {
-	pr_debug("%pfwf: Relaxing link with %pfwf\n",
+	pr_debug("%pfwf: cycle: depends on %pfwf\n",
 		 link->consumer, link->supplier);
 	link->flags |= FWLINK_FLAG_CYCLE;
 }
@@ -284,10 +284,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target)
 	return false;
 }
 
+#define DL_MARKER_FLAGS		(DL_FLAG_INFERRED | \
+				 DL_FLAG_CYCLE | \
+				 DL_FLAG_MANAGED)
 static inline bool device_link_flag_is_sync_state_only(u32 flags)
 {
-	return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) ==
-		(DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED);
+	return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY;
 }
 
 /**
@@ -1943,6 +1945,7 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 
 	/* Termination condition. */
 	if (sup_dev == con) {
+		pr_debug("----- cycle: start -----\n");
 		ret = true;
 		goto out;
 	}
@@ -1974,8 +1977,11 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 	else
 		par_dev = fwnode_get_next_parent_dev(sup_handle);
 
-	if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode))
+	if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode)) {
+		pr_debug("%pfwf: cycle: child of %pfwf\n", sup_handle,
+			 par_dev->fwnode);
 		ret = true;
+	}
 
 	if (!sup_dev)
 		goto out;
@@ -1991,6 +1997,8 @@ static bool __fw_devlink_relax_cycles(struct device *con,
 
 		if (__fw_devlink_relax_cycles(con,
 					      dev_link->supplier->fwnode)) {
+			pr_debug("%pfwf: cycle: depends on %pfwf\n", sup_handle,
+				 dev_link->supplier->fwnode);
 			fw_devlink_relax_link(dev_link);
 			dev_link->flags |= DL_FLAG_CYCLE;
 			ret = true;
@@ -2058,13 +2066,19 @@ static int fw_devlink_create_devlink(struct device *con,
 
 	/*
 	 * SYNC_STATE_ONLY device links don't block probing and supports cycles.
-	 * So cycle detection isn't necessary and shouldn't be done.
+	 * So, one might expect that cycle detection isn't necessary for them.
+	 * However, if the device link was marked as SYNC_STATE_ONLY because
+	 * it's part of a cycle, then we still need to do cycle detection. This
+	 * is because the consumer and supplier might be part of multiple cycles
+	 * and we need to detect all those cycles.
 	 */
-	if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) {
+	if (!device_link_flag_is_sync_state_only(flags) ||
+	    flags & DL_FLAG_CYCLE) {
 		device_links_write_lock();
 		if (__fw_devlink_relax_cycles(con, sup_handle)) {
 			__fwnode_link_cycle(link);
 			flags = fw_devlink_get_flags(link->flags);
+			pr_debug("----- cycle: end -----\n");
 			dev_info(con, "Fixed dependency cycle(s) with %pfwf\n",
 				 sup_handle);
 		}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 47de0f140ba6..0b33e81f9c9b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -588,6 +588,7 @@ CPU_SHOW_VULN_FALLBACK(mmio_stale_data);
 CPU_SHOW_VULN_FALLBACK(retbleed);
 CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
 CPU_SHOW_VULN_FALLBACK(gds);
+CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -602,6 +603,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
 static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
 static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL);
 static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
+static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -617,6 +619,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_retbleed.attr,
 	&dev_attr_spec_rstack_overflow.attr,
 	&dev_attr_gather_data_sampling.attr,
+	&dev_attr_reg_file_data_sampling.attr,
 	NULL
 };
 
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index f37ad34c80ec..0d01890160f3 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -13,6 +13,8 @@
 #include <linux/msi.h>
 #include <linux/slab.h>
 
+/* Begin of removal area. Once everything is converted over. Cleanup the includes too! */
+
 #define DEV_ID_SHIFT	21
 #define MAX_DEV_MSIS	(1 << (32 - DEV_ID_SHIFT))
 
@@ -204,8 +206,8 @@ static void platform_msi_free_priv_data(struct device *dev)
  * Returns:
  * Zero for success, or an error code in case of failure
  */
-int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
-				   irq_write_msi_msg_t write_msi_msg)
+static int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
+					  irq_write_msi_msg_t write_msi_msg)
 {
 	int err;
 
@@ -219,18 +221,6 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs);
-
-/**
- * platform_msi_domain_free_irqs - Free MSI interrupts for @dev
- * @dev:	The device for which to free interrupts
- */
-void platform_msi_domain_free_irqs(struct device *dev)
-{
-	msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN);
-	platform_msi_free_priv_data(dev);
-}
-EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs);
 
 /**
  * platform_msi_get_host_data - Query the private data associated with
@@ -350,3 +340,104 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir
 
 	return msi_domain_populate_irqs(domain->parent, dev, virq, nr_irqs, &data->arg);
 }
+
+/* End of removal area */
+
+/* Real per device domain interfaces */
+
+/*
+ * This indirection can go when platform_device_msi_init_and_alloc_irqs()
+ * is switched to a proper irq_chip::irq_write_msi_msg() callback. Keep it
+ * simple for now.
+ */
+static void platform_msi_write_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	irq_write_msi_msg_t cb = d->chip_data;
+
+	cb(irq_data_get_msi_desc(d), msg);
+}
+
+static void platform_msi_set_desc_byindex(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = desc->msi_index;
+}
+
+static const struct msi_domain_template platform_msi_template = {
+	.chip = {
+		.name			= "pMSI",
+		.irq_mask		= irq_chip_mask_parent,
+		.irq_unmask		= irq_chip_unmask_parent,
+		.irq_write_msi_msg	= platform_msi_write_msi_msg,
+		/* The rest is filled in by the platform MSI parent */
+	},
+
+	.ops = {
+		.set_desc		= platform_msi_set_desc_byindex,
+	},
+
+	.info = {
+		.bus_token		= DOMAIN_BUS_DEVICE_MSI,
+	},
+};
+
+/**
+ * platform_device_msi_init_and_alloc_irqs - Initialize platform device MSI
+ *					     and allocate interrupts for @dev
+ * @dev:		The device for which to allocate interrupts
+ * @nvec:		The number of interrupts to allocate
+ * @write_msi_msg:	Callback to write an interrupt message for @dev
+ *
+ * Returns:
+ * Zero for success, or an error code in case of failure
+ *
+ * This creates a MSI domain on @dev which has @dev->msi.domain as
+ * parent. The parent domain sets up the new domain. The domain has
+ * a fixed size of @nvec. The domain is managed by devres and will
+ * be removed when the device is removed.
+ *
+ * Note: For migration purposes this falls back to the original platform_msi code
+ *	 up to the point where all platforms have been converted to the MSI
+ *	 parent model.
+ */
+int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec,
+					    irq_write_msi_msg_t write_msi_msg)
+{
+	struct irq_domain *domain = dev->msi.domain;
+
+	if (!domain || !write_msi_msg)
+		return -EINVAL;
+
+	/* Migration support. Will go away once everything is converted */
+	if (!irq_domain_is_msi_parent(domain))
+		return platform_msi_domain_alloc_irqs(dev, nvec, write_msi_msg);
+
+	/*
+	 * @write_msi_msg is stored in the resulting msi_domain_info::data.
+	 * The underlying domain creation mechanism will assign that
+	 * callback to the resulting irq chip.
+	 */
+	if (!msi_create_device_irq_domain(dev, MSI_DEFAULT_DOMAIN,
+					  &platform_msi_template,
+					  nvec, NULL, write_msi_msg))
+		return -ENODEV;
+
+	return msi_domain_alloc_irqs_range(dev, MSI_DEFAULT_DOMAIN, 0, nvec - 1);
+}
+EXPORT_SYMBOL_GPL(platform_device_msi_init_and_alloc_irqs);
+
+/**
+ * platform_device_msi_free_irqs_all - Free all interrupts for @dev
+ * @dev:	The device for which to free interrupts
+ */
+void platform_device_msi_free_irqs_all(struct device *dev)
+{
+	struct irq_domain *domain = dev->msi.domain;
+
+	msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN);
+
+	/* Migration support. Will go away once everything is converted */
+	if (!irq_domain_is_msi_parent(domain))
+		platform_msi_free_priv_data(dev);
+}
+EXPORT_SYMBOL_GPL(platform_device_msi_free_irqs_all);
diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
index 026bdcb45127..0d957c5f1bcc 100644
--- a/drivers/base/regmap/regmap-kunit.c
+++ b/drivers/base/regmap/regmap-kunit.c
@@ -9,6 +9,23 @@
 
 #define BLOCK_TEST_SIZE 12
 
+static void get_changed_bytes(void *orig, void *new, size_t size)
+{
+	char *o = orig;
+	char *n = new;
+	int i;
+
+	get_random_bytes(new, size);
+
+	/*
+	 * This could be nicer and more efficient but we shouldn't
+	 * super care.
+	 */
+	for (i = 0; i < size; i++)
+		while (n[i] == o[i])
+			get_random_bytes(&n[i], 1);
+}
+
 static const struct regmap_config test_regmap_config = {
 	.max_register = BLOCK_TEST_SIZE,
 	.reg_stride = 1,
@@ -1202,7 +1219,8 @@ static void raw_noinc_write(struct kunit *test)
 	struct regmap *map;
 	struct regmap_config config;
 	struct regmap_ram_data *data;
-	unsigned int val, val_test, val_last;
+	unsigned int val;
+	u16 val_test, val_last;
 	u16 val_array[BLOCK_TEST_SIZE];
 
 	config = raw_regmap_config;
@@ -1251,7 +1269,7 @@ static void raw_sync(struct kunit *test)
 	struct regmap *map;
 	struct regmap_config config;
 	struct regmap_ram_data *data;
-	u16 val[2];
+	u16 val[3];
 	u16 *hw_buf;
 	unsigned int rval;
 	int i;
@@ -1265,17 +1283,13 @@ static void raw_sync(struct kunit *test)
 
 	hw_buf = (u16 *)data->vals;
 
-	get_random_bytes(&val, sizeof(val));
+	get_changed_bytes(&hw_buf[2], &val[0], sizeof(val));
 
 	/* Do a regular write and a raw write in cache only mode */
 	regcache_cache_only(map, true);
-	KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, sizeof(val)));
-	if (config.val_format_endian == REGMAP_ENDIAN_BIG)
-		KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
-						      be16_to_cpu(val[0])));
-	else
-		KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
-						      le16_to_cpu(val[0])));
+	KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val,
+						  sizeof(u16) * 2));
+	KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 4, val[2]));
 
 	/* We should read back the new values, and defaults for the rest */
 	for (i = 0; i < config.max_register + 1; i++) {
@@ -1284,24 +1298,34 @@ static void raw_sync(struct kunit *test)
 		switch (i) {
 		case 2:
 		case 3:
-		case 6:
 			if (config.val_format_endian == REGMAP_ENDIAN_BIG) {
 				KUNIT_EXPECT_EQ(test, rval,
-						be16_to_cpu(val[i % 2]));
+						be16_to_cpu(val[i - 2]));
 			} else {
 				KUNIT_EXPECT_EQ(test, rval,
-						le16_to_cpu(val[i % 2]));
+						le16_to_cpu(val[i - 2]));
 			}
 			break;
+		case 4:
+			KUNIT_EXPECT_EQ(test, rval, val[i - 2]);
+			break;
 		default:
 			KUNIT_EXPECT_EQ(test, config.reg_defaults[i].def, rval);
 			break;
 		}
 	}
+
+	/*
+	 * The value written via _write() was translated by the core,
+	 * translate the original copy for comparison purposes.
+	 */
+	if (config.val_format_endian == REGMAP_ENDIAN_BIG)
+		val[2] = cpu_to_be16(val[2]);
+	else
+		val[2] = cpu_to_le16(val[2]);
 	
 	/* The values should not appear in the "hardware" */
-	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], val, sizeof(val));
-	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[6], val, sizeof(u16));
+	KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], &val[0], sizeof(val));
 
 	for (i = 0; i < config.max_register + 1; i++)
 		data->written[i] = false;
@@ -1312,8 +1336,7 @@ static void raw_sync(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 0, regcache_sync(map));
 
 	/* The values should now appear in the "hardware" */
-	KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], val, sizeof(val));
-	KUNIT_EXPECT_MEMEQ(test, &hw_buf[6], val, sizeof(u16));
+	KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], &val[0], sizeof(val));
 
 	regmap_exit(map);
 }
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 2b98114a9fe0..a25414228e47 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1779,7 +1779,7 @@ static int fd_alloc_disk(int drive, int system)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index b1b47d88f5db..b6dac8cee70f 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -24,8 +24,8 @@ static DEFINE_MUTEX(aoeblk_mutex);
 static struct kmem_cache *buf_pool_cache;
 static struct dentry *aoe_debugfs_dir;
 
-/* GPFS needs a larger value than the default. */
-static int aoe_maxsectors;
+/* random default picked from the historic block max_sectors cap */
+static int aoe_maxsectors = 2560;
 module_param(aoe_maxsectors, int, 0644);
 MODULE_PARM_DESC(aoe_maxsectors,
 	"When nonzero, set the maximum number of sectors per I/O request");
@@ -334,6 +334,10 @@ aoeblk_gdalloc(void *vp)
 	mempool_t *mp;
 	struct blk_mq_tag_set *set;
 	sector_t ssize;
+	struct queue_limits lim = {
+		.max_hw_sectors		= aoe_maxsectors,
+		.io_opt			= SZ_2M,
+	};
 	ulong flags;
 	int late = 0;
 	int err;
@@ -371,7 +375,7 @@ aoeblk_gdalloc(void *vp)
 		goto err_mempool;
 	}
 
-	gd = blk_mq_alloc_disk(set, d);
+	gd = blk_mq_alloc_disk(set, &lim, d);
 	if (IS_ERR(gd)) {
 		pr_err("aoe: cannot allocate block queue for %ld.%d\n",
 			d->aoemajor, d->aoeminor);
@@ -384,14 +388,9 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->flags & DEVFL_TKILL);
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(gd->queue, 2560u);
-	blk_queue_io_opt(gd->queue, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue;
 	d->gd = gd;
-	if (aoe_maxsectors)
-		blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors);
 	gd->major = AOE_MAJOR;
 	gd->first_minor = d->sysminor;
 	gd->minors = AOE_PARTITIONS;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index d7317425be51..cc9077b588d7 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, ifp) {
 		dev_hold(ifp);
-		if (!is_aoe_netif(ifp))
-			goto cont;
+		if (!is_aoe_netif(ifp)) {
+			dev_put(ifp);
+			continue;
+		}
 
 		skb = new_skb(sizeof *h + sizeof *ch);
 		if (skb == NULL) {
 			printk(KERN_INFO "aoe: skb alloc failure\n");
-			goto cont;
+			dev_put(ifp);
+			continue;
 		}
 		skb_put(skb, sizeof *h + sizeof *ch);
 		skb->dev = ifp;
@@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu
 		h->major = cpu_to_be16(aoemajor);
 		h->minor = aoeminor;
 		h->cmd = AOECMD_CFG;
-
-cont:
-		dev_put(ifp);
 	}
 	rcu_read_unlock();
 }
diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
index c51ea95bc2ce..923a134fd766 100644
--- a/drivers/block/aoe/aoenet.c
+++ b/drivers/block/aoe/aoenet.c
@@ -63,6 +63,7 @@ tx(int id) __must_hold(&txlock)
 			pr_warn("aoe: packet could not be sent on %s.  %s\n",
 				ifp ? ifp->name : "netif",
 				"consider increasing tx_queue_len");
+		dev_put(ifp);
 		spin_lock_irq(&txlock);
 	}
 	return 0;
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 50949207798d..cacc4ba942a8 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1994,7 +1994,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
 {
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
+	disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 970bd6ff38c4..e322cef6596b 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -318,6 +318,16 @@ static int brd_alloc(int i)
 	struct gendisk *disk;
 	char buf[DISK_NAME_LEN];
 	int err = -ENOMEM;
+	struct queue_limits lim = {
+		/*
+		 * This is so fdisk will align partitions on 4k, because of
+		 * direct_access API needing 4k alignment, returning a PFN
+		 * (This is only a problem on very small devices <= 4M,
+		 *  otherwise fdisk will align on 1M. Regardless this call
+		 *  is harmless)
+		 */
+		.physical_block_size	= PAGE_SIZE,
+	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
 		if (brd->brd_number == i)
@@ -335,10 +345,11 @@ static int brd_alloc(int i)
 		debugfs_create_u64(buf, 0444, brd_debugfs_dir,
 				&brd->brd_nr_pages);
 
-	disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_free_dev;
-
+	}
 	disk->major		= RAMDISK_MAJOR;
 	disk->first_minor	= i * max_part;
 	disk->minors		= max_part;
@@ -347,15 +358,6 @@ static int brd_alloc(int i)
 	strscpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
 	
-	/*
-	 * This is so fdisk will align partitions on 4k, because of
-	 * direct_access API needing 4k alignment, returning a PFN
-	 * (This is only a problem on very small devices <= 4M,
-	 *  otherwise fdisk will align on 1M. Regardless this call
-	 *  is harmless)
-	 */
-	blk_queue_physical_block_size(disk->queue, PAGE_SIZE);
-
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue);
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c21e3732759e..94dc0a235919 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -524,9 +524,9 @@ struct drbd_md {
 
 struct drbd_backing_dev {
 	struct block_device *backing_bdev;
-	struct bdev_handle *backing_bdev_handle;
+	struct file *backing_bdev_file;
 	struct block_device *md_bdev;
-	struct bdev_handle *md_bdev_handle;
+	struct file *f_md_bdev;
 	struct drbd_md md;
 	struct disk_conf *disk_conf; /* RCU, for updates: resource->conf_update */
 	sector_t known_size; /* last known size of that backing device */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 6bc86106c7b2..113b441d4d36 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2690,6 +2690,14 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	int id;
 	int vnr = adm_ctx->volume;
 	enum drbd_ret_code err = ERR_NOMEM;
+	struct queue_limits lim = {
+		/*
+		 * Setting the max_hw_sectors to an odd value of 8kibyte here.
+		 * This triggers a max_bio_size message upon first attach or
+		 * connect.
+		 */
+		.max_hw_sectors		= DRBD_MAX_BIO_SIZE_SAFE >> 8,
+	};
 
 	device = minor_to_device(minor);
 	if (device)
@@ -2708,9 +2716,11 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	drbd_init_set_defaults(device);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out_no_disk;
+	}
 
 	device->vdisk = disk;
 	device->rq_queue = disk->queue;
@@ -2727,9 +2737,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	blk_queue_write_cache(disk->queue, true, true);
-	/* Setting the max_hw_sectors to an odd value of 8kibyte here
-	   This triggers a max_bio_size message upon first attach or connect */
-	blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8);
 
 	device->md_io.page = alloc_page(GFP_KERNEL);
 	if (!device->md_io.page)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 43747a1aae43..5d65c9754d83 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1189,9 +1189,31 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
 	return 0;
 }
 
-static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity)
+static unsigned int drbd_max_peer_bio_size(struct drbd_device *device)
 {
-	q->limits.discard_granularity = granularity;
+	/*
+	 * We may ignore peer limits if the peer is modern enough.  From 8.3.8
+	 * onwards the peer can use multiple BIOs for a single peer_request.
+	 */
+	if (device->state.conn < C_WF_REPORT_PARAMS)
+		return device->peer_max_bio_size;
+
+	if (first_peer_device(device)->connection->agreed_pro_version < 94)
+		return min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
+
+	/*
+	 * Correct old drbd (up to 8.3.7) if it believes it can do more than
+	 * 32KiB.
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version == 94)
+		return DRBD_MAX_SIZE_H80_PACKET;
+
+	/*
+	 * drbd 8.3.8 onwards, before 8.4.0
+	 */
+	if (first_peer_device(device)->connection->agreed_pro_version < 100)
+		return DRBD_MAX_BIO_SIZE_P95;
+	return DRBD_MAX_BIO_SIZE;
 }
 
 static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
@@ -1204,149 +1226,119 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
 	return AL_EXTENT_SIZE >> 9;
 }
 
-static void decide_on_discard_support(struct drbd_device *device,
+static bool drbd_discard_supported(struct drbd_connection *connection,
 		struct drbd_backing_dev *bdev)
 {
-	struct drbd_connection *connection =
-		first_peer_device(device)->connection;
-	struct request_queue *q = device->rq_queue;
-	unsigned int max_discard_sectors;
-
 	if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
-		goto not_supported;
+		return false;
 
 	if (connection->cstate >= C_CONNECTED &&
 	    !(connection->agreed_features & DRBD_FF_TRIM)) {
 		drbd_info(connection,
 			"peer DRBD too old, does not support TRIM: disabling discards\n");
-		goto not_supported;
+		return false;
 	}
 
-	/*
-	 * We don't care for the granularity, really.
-	 *
-	 * Stacking limits below should fix it for the local device.  Whether or
-	 * not it is a suitable granularity on the remote device is not our
-	 * problem, really. If you care, you need to use devices with similar
-	 * topology on all peers.
-	 */
-	blk_queue_discard_granularity(q, 512);
-	max_discard_sectors = drbd_max_discard_sectors(connection);
-	blk_queue_max_discard_sectors(q, max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	return;
-
-not_supported:
-	blk_queue_discard_granularity(q, 0);
-	blk_queue_max_discard_sectors(q, 0);
+	return true;
 }
 
-static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
+/* This is the workaround for "bio would need to, but cannot, be split" */
+static unsigned int drbd_backing_dev_max_segments(struct drbd_device *device)
 {
-	/* Fixup max_write_zeroes_sectors after blk_stack_limits():
-	 * if we can handle "zeroes" efficiently on the protocol,
-	 * we want to do that, even if our backend does not announce
-	 * max_write_zeroes_sectors itself. */
-	struct drbd_connection *connection = first_peer_device(device)->connection;
-	/* If the peer announces WZEROES support, use it.  Otherwise, rather
-	 * send explicit zeroes than rely on some discard-zeroes-data magic. */
-	if (connection->agreed_features & DRBD_FF_WZEROES)
-		q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
-	else
-		q->limits.max_write_zeroes_sectors = 0;
-}
+	unsigned int max_segments;
 
-static void fixup_discard_support(struct drbd_device *device, struct request_queue *q)
-{
-	unsigned int max_discard = device->rq_queue->limits.max_discard_sectors;
-	unsigned int discard_granularity =
-		device->rq_queue->limits.discard_granularity >> SECTOR_SHIFT;
+	rcu_read_lock();
+	max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
+	rcu_read_unlock();
 
-	if (discard_granularity > max_discard) {
-		blk_queue_discard_granularity(q, 0);
-		blk_queue_max_discard_sectors(q, 0);
-	}
+	if (!max_segments)
+		return BLK_MAX_SEGMENTS;
+	return max_segments;
 }
 
-static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
-				   unsigned int max_bio_size, struct o_qlim *o)
+void drbd_reconsider_queue_parameters(struct drbd_device *device,
+		struct drbd_backing_dev *bdev, struct o_qlim *o)
 {
+	struct drbd_connection *connection =
+		first_peer_device(device)->connection;
 	struct request_queue * const q = device->rq_queue;
-	unsigned int max_hw_sectors = max_bio_size >> 9;
-	unsigned int max_segments = 0;
+	unsigned int now = queue_max_hw_sectors(q) << 9;
+	struct queue_limits lim;
 	struct request_queue *b = NULL;
-	struct disk_conf *dc;
+	unsigned int new;
 
 	if (bdev) {
 		b = bdev->backing_bdev->bd_disk->queue;
 
-		max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
-		rcu_read_lock();
-		dc = rcu_dereference(device->ldev->disk_conf);
-		max_segments = dc->max_bio_bvecs;
-		rcu_read_unlock();
-
-		blk_set_stacking_limits(&q->limits);
+		device->local_max_bio_size =
+			queue_max_hw_sectors(b) << SECTOR_SHIFT;
 	}
 
-	blk_queue_max_hw_sectors(q, max_hw_sectors);
-	/* This is the workaround for "bio would need to, but cannot, be split" */
-	blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
-	blk_queue_segment_boundary(q, PAGE_SIZE-1);
-	decide_on_discard_support(device, bdev);
-
-	if (b) {
-		blk_stack_limits(&q->limits, &b->limits, 0);
-		disk_update_readahead(device->vdisk);
+	/*
+	 * We may later detach and re-attach on a disconnected Primary.  Avoid
+	 * decreasing the value in this case.
+	 *
+	 * We want to store what we know the peer DRBD can handle, not what the
+	 * peer IO backend can handle.
+	 */
+	new = min3(DRBD_MAX_BIO_SIZE, device->local_max_bio_size,
+		max(drbd_max_peer_bio_size(device), device->peer_max_bio_size));
+	if (new != now) {
+		if (device->state.role == R_PRIMARY && new < now)
+			drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n",
+					new, now);
+		drbd_info(device, "max BIO size = %u\n", new);
 	}
-	fixup_write_zeroes(device, q);
-	fixup_discard_support(device, q);
-}
-
-void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
-{
-	unsigned int now, new, local, peer;
-
-	now = queue_max_hw_sectors(device->rq_queue) << 9;
-	local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */
-	peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */
 
+	lim = queue_limits_start_update(q);
 	if (bdev) {
-		local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
-		device->local_max_bio_size = local;
+		blk_set_stacking_limits(&lim);
+		lim.max_segments = drbd_backing_dev_max_segments(device);
+	} else {
+		lim.max_segments = BLK_MAX_SEGMENTS;
 	}
-	local = min(local, DRBD_MAX_BIO_SIZE);
 
-	/* We may ignore peer limits if the peer is modern enough.
-	   Because new from 8.3.8 onwards the peer can use multiple
-	   BIOs for a single peer_request */
-	if (device->state.conn >= C_WF_REPORT_PARAMS) {
-		if (first_peer_device(device)->connection->agreed_pro_version < 94)
-			peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
-			/* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */
-		else if (first_peer_device(device)->connection->agreed_pro_version == 94)
-			peer = DRBD_MAX_SIZE_H80_PACKET;
-		else if (first_peer_device(device)->connection->agreed_pro_version < 100)
-			peer = DRBD_MAX_BIO_SIZE_P95;  /* drbd 8.3.8 onwards, before 8.4.0 */
-		else
-			peer = DRBD_MAX_BIO_SIZE;
+	lim.max_hw_sectors = new >> SECTOR_SHIFT;
+	lim.seg_boundary_mask = PAGE_SIZE - 1;
 
-		/* We may later detach and re-attach on a disconnected Primary.
-		 * Avoid this setting to jump back in that case.
-		 * We want to store what we know the peer DRBD can handle,
-		 * not what the peer IO backend can handle. */
-		if (peer > device->peer_max_bio_size)
-			device->peer_max_bio_size = peer;
+	/*
+	 * We don't care for the granularity, really.
+	 *
+	 * Stacking limits below should fix it for the local device.  Whether or
+	 * not it is a suitable granularity on the remote device is not our
+	 * problem, really. If you care, you need to use devices with similar
+	 * topology on all peers.
+	 */
+	if (drbd_discard_supported(connection, bdev)) {
+		lim.discard_granularity = 512;
+		lim.max_hw_discard_sectors =
+			drbd_max_discard_sectors(connection);
+	} else {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
 	}
-	new = min(local, peer);
 
-	if (device->state.role == R_PRIMARY && new < now)
-		drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now);
+	if (bdev)
+		blk_stack_limits(&lim, &b->limits, 0);
 
-	if (new != now)
-		drbd_info(device, "max BIO size = %u\n", new);
+	/*
+	 * If we can handle "zeroes" efficiently on the protocol, we want to do
+	 * that, even if our backend does not announce max_write_zeroes_sectors
+	 * itself.
+	 */
+	if (connection->agreed_features & DRBD_FF_WZEROES)
+		lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+	else
+		lim.max_write_zeroes_sectors = 0;
+
+	if ((lim.discard_granularity >> SECTOR_SHIFT) >
+	    lim.max_hw_discard_sectors) {
+		lim.discard_granularity = 0;
+		lim.max_hw_discard_sectors = 0;
+	}
 
-	drbd_setup_queue_param(device, bdev, new, o);
+	if (queue_limits_commit_update(q, &lim))
+		drbd_err(device, "setting new queue limits failed\n");
 }
 
 /* Starts the worker thread */
@@ -1635,45 +1627,45 @@ success:
 	return 0;
 }
 
-static struct bdev_handle *open_backing_dev(struct drbd_device *device,
+static struct file *open_backing_dev(struct drbd_device *device,
 		const char *bdev_path, void *claim_ptr, bool do_bd_link)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 	int err = 0;
 
-	handle = bdev_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				   claim_ptr, NULL);
-	if (IS_ERR(handle)) {
+	file = bdev_file_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
+				      claim_ptr, NULL);
+	if (IS_ERR(file)) {
 		drbd_err(device, "open(\"%s\") failed with %ld\n",
-				bdev_path, PTR_ERR(handle));
-		return handle;
+				bdev_path, PTR_ERR(file));
+		return file;
 	}
 
 	if (!do_bd_link)
-		return handle;
+		return file;
 
-	err = bd_link_disk_holder(handle->bdev, device->vdisk);
+	err = bd_link_disk_holder(file_bdev(file), device->vdisk);
 	if (err) {
-		bdev_release(handle);
+		fput(file);
 		drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n",
 				bdev_path, err);
-		handle = ERR_PTR(err);
+		file = ERR_PTR(err);
 	}
-	return handle;
+	return file;
 }
 
 static int open_backing_devices(struct drbd_device *device,
 		struct disk_conf *new_disk_conf,
 		struct drbd_backing_dev *nbc)
 {
-	struct bdev_handle *handle;
+	struct file *file;
 
-	handle = open_backing_dev(device, new_disk_conf->backing_dev, device,
+	file = open_backing_dev(device, new_disk_conf->backing_dev, device,
 				  true);
-	if (IS_ERR(handle))
+	if (IS_ERR(file))
 		return ERR_OPEN_DISK;
-	nbc->backing_bdev = handle->bdev;
-	nbc->backing_bdev_handle = handle;
+	nbc->backing_bdev = file_bdev(file);
+	nbc->backing_bdev_file = file;
 
 	/*
 	 * meta_dev_idx >= 0: external fixed size, possibly multiple
@@ -1683,7 +1675,7 @@ static int open_backing_devices(struct drbd_device *device,
 	 * should check it for you already; but if you don't, or
 	 * someone fooled it, we need to double check here)
 	 */
-	handle = open_backing_dev(device, new_disk_conf->meta_dev,
+	file = open_backing_dev(device, new_disk_conf->meta_dev,
 		/* claim ptr: device, if claimed exclusively; shared drbd_m_holder,
 		 * if potentially shared with other drbd minors */
 			(new_disk_conf->meta_dev_idx < 0) ? (void*)device : (void*)drbd_m_holder,
@@ -1691,21 +1683,21 @@ static int open_backing_devices(struct drbd_device *device,
 		 * as would happen with internal metadata. */
 			(new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_FLEX_INT &&
 			 new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_INTERNAL));
-	if (IS_ERR(handle))
+	if (IS_ERR(file))
 		return ERR_OPEN_MD_DISK;
-	nbc->md_bdev = handle->bdev;
-	nbc->md_bdev_handle = handle;
+	nbc->md_bdev = file_bdev(file);
+	nbc->f_md_bdev = file;
 	return NO_ERROR;
 }
 
 static void close_backing_dev(struct drbd_device *device,
-		struct bdev_handle *handle, bool do_bd_unlink)
+		struct file *bdev_file, bool do_bd_unlink)
 {
-	if (!handle)
+	if (!bdev_file)
 		return;
 	if (do_bd_unlink)
-		bd_unlink_disk_holder(handle->bdev, device->vdisk);
-	bdev_release(handle);
+		bd_unlink_disk_holder(file_bdev(bdev_file), device->vdisk);
+	fput(bdev_file);
 }
 
 void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev)
@@ -1713,9 +1705,9 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *
 	if (ldev == NULL)
 		return;
 
-	close_backing_dev(device, ldev->md_bdev_handle,
+	close_backing_dev(device, ldev->f_md_bdev,
 			  ldev->md_bdev != ldev->backing_bdev);
-	close_backing_dev(device, ldev->backing_bdev_handle, true);
+	close_backing_dev(device, ldev->backing_bdev_file, true);
 
 	kfree(ldev->disk_conf);
 	kfree(ldev);
@@ -2131,9 +2123,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
  fail:
 	conn_reconfig_done(connection);
 	if (nbc) {
-		close_backing_dev(device, nbc->md_bdev_handle,
+		close_backing_dev(device, nbc->f_md_bdev,
 			  nbc->md_bdev != nbc->backing_bdev);
-		close_backing_dev(device, nbc->backing_bdev_handle, true);
+		close_backing_dev(device, nbc->backing_bdev_file, true);
 		kfree(nbc);
 	}
 	kfree(new_disk_conf);
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 287a8d1d3f70..e858e7e0383f 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1542,9 +1542,10 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device,
 
 int notify_resource_state_change(struct sk_buff *skb,
 				  unsigned int seq,
-				  struct drbd_resource_state_change *resource_state_change,
+				  void *state_change,
 				  enum drbd_notification_type type)
 {
+	struct drbd_resource_state_change *resource_state_change = state_change;
 	struct drbd_resource *resource = resource_state_change->resource;
 	struct resource_info resource_info = {
 		.res_role = resource_state_change->role[NEW],
@@ -1558,13 +1559,14 @@ int notify_resource_state_change(struct sk_buff *skb,
 
 int notify_connection_state_change(struct sk_buff *skb,
 				    unsigned int seq,
-				    struct drbd_connection_state_change *connection_state_change,
+				    void *state_change,
 				    enum drbd_notification_type type)
 {
-	struct drbd_connection *connection = connection_state_change->connection;
+	struct drbd_connection_state_change *p = state_change;
+	struct drbd_connection *connection = p->connection;
 	struct connection_info connection_info = {
-		.conn_connection_state = connection_state_change->cstate[NEW],
-		.conn_role = connection_state_change->peer_role[NEW],
+		.conn_connection_state = p->cstate[NEW],
+		.conn_role = p->peer_role[NEW],
 	};
 
 	return notify_connection_state(skb, seq, connection, &connection_info, type);
@@ -1572,9 +1574,10 @@ int notify_connection_state_change(struct sk_buff *skb,
 
 int notify_device_state_change(struct sk_buff *skb,
 				unsigned int seq,
-				struct drbd_device_state_change *device_state_change,
+				void *state_change,
 				enum drbd_notification_type type)
 {
+	struct drbd_device_state_change *device_state_change = state_change;
 	struct drbd_device *device = device_state_change->device;
 	struct device_info device_info = {
 		.dev_disk_state = device_state_change->disk_state[NEW],
@@ -1585,9 +1588,10 @@ int notify_device_state_change(struct sk_buff *skb,
 
 int notify_peer_device_state_change(struct sk_buff *skb,
 				     unsigned int seq,
-				     struct drbd_peer_device_state_change *p,
+				     void *state_change,
 				     enum drbd_notification_type type)
 {
+	struct drbd_peer_device_state_change *p = state_change;
 	struct drbd_peer_device *peer_device = p->peer_device;
 	struct peer_device_info peer_device_info = {
 		.peer_repl_state = p->repl_state[NEW],
@@ -1605,8 +1609,8 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	struct drbd_resource_state_change *resource_state_change = &state_change->resource[0];
 	bool resource_state_has_changed;
 	unsigned int n_device, n_connection, n_peer_device, n_peer_devices;
-	int (*last_func)(struct sk_buff *, unsigned int, void *,
-			  enum drbd_notification_type) = NULL;
+	int (*last_func)(struct sk_buff *, unsigned int,
+		void *, enum drbd_notification_type) = NULL;
 	void *last_arg = NULL;
 
 #define HAS_CHANGED(state) ((state)[OLD] != (state)[NEW])
@@ -1616,7 +1620,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
 	})
 #define REMEMBER_STATE_CHANGE(func, arg, type) \
 	({ FINAL_STATE_CHANGE(type | NOTIFY_CONTINUES); \
-	   last_func = (typeof(last_func))func; \
+	   last_func = func; \
 	   last_arg = arg; \
 	 })
 
diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h
index 9d78d8e3912e..a56a57d67686 100644
--- a/drivers/block/drbd/drbd_state_change.h
+++ b/drivers/block/drbd/drbd_state_change.h
@@ -46,19 +46,19 @@ extern void forget_state_change(struct drbd_state_change *);
 
 extern int notify_resource_state_change(struct sk_buff *,
 					 unsigned int,
-					 struct drbd_resource_state_change *,
+					 void *,
 					 enum drbd_notification_type type);
 extern int notify_connection_state_change(struct sk_buff *,
 					   unsigned int,
-					   struct drbd_connection_state_change *,
+					   void *,
 					   enum drbd_notification_type type);
 extern int notify_device_state_change(struct sk_buff *,
 				       unsigned int,
-				       struct drbd_device_state_change *,
+				       void *,
 				       enum drbd_notification_type type);
 extern int notify_peer_device_state_change(struct sk_buff *,
 					    unsigned int,
-					    struct drbd_peer_device_state_change *,
+					    void *,
 					    enum drbd_notification_type type);
 
 #endif  /* DRBD_STATE_CHANGE_H */
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index d0e41d52d6a9..1b399ec8c07d 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -530,14 +530,13 @@ static struct format_descr format_req;
 static char *floppy_track_buffer;
 static int max_buffer_sectors;
 
-typedef void (*done_f)(int);
 static const struct cont_t {
 	void (*interrupt)(void);
 				/* this is called after the interrupt of the
 				 * main command */
 	void (*redo)(void);	/* this is called to retry the operation */
 	void (*error)(void);	/* this is called to tally an error */
-	done_f done;		/* this is called to say if the operation has
+	void (*done)(int);	/* this is called to say if the operation has
 				 * succeeded/failed */
 } *cont;
 
@@ -985,6 +984,10 @@ static void empty(void)
 {
 }
 
+static void empty_done(int result)
+{
+}
+
 static void (*floppy_work_fn)(void);
 
 static void floppy_work_workfn(struct work_struct *work)
@@ -1998,14 +2001,14 @@ static const struct cont_t wakeup_cont = {
 	.interrupt	= empty,
 	.redo		= do_wakeup,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 static const struct cont_t intr_cont = {
 	.interrupt	= empty,
 	.redo		= process_fd_request,
 	.error		= empty,
-	.done		= (done_f)empty
+	.done		= empty_done,
 };
 
 /* schedules handler, waiting for completion. May be interrupted, will then
@@ -4513,13 +4516,15 @@ static bool floppy_available(int drive)
 
 static int floppy_alloc_disk(unsigned int drive, unsigned int type)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors = 64,
+	};
 	struct gendisk *disk;
 
-	disk = blk_mq_alloc_disk(&tag_sets[drive], NULL);
+	disk = blk_mq_alloc_disk(&tag_sets[drive], &lim, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
-	blk_queue_max_hw_sectors(disk->queue, 64);
 	disk->major = FLOPPY_MAJOR;
 	disk->first_minor = TOMINOR(drive) | (type << 2);
 	disk->minors = 1;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f8145499da38..28a95fd366fe 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -750,12 +750,13 @@ static void loop_sysfs_exit(struct loop_device *lo)
 				   &loop_attribute_group);
 }
 
-static void loop_config_discard(struct loop_device *lo)
+static void loop_config_discard(struct loop_device *lo,
+		struct queue_limits *lim)
 {
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
-	struct request_queue *q = lo->lo_queue;
-	u32 granularity, max_discard_sectors;
+	u32 granularity = 0, max_discard_sectors = 0;
+	struct kstatfs sbuf;
 
 	/*
 	 * If the backing device is a block device, mirror its zeroing
@@ -775,29 +776,17 @@ static void loop_config_discard(struct loop_device *lo)
 	 * We use punch hole to reclaim the free space used by the
 	 * image a.k.a. discard.
 	 */
-	} else if (!file->f_op->fallocate) {
-		max_discard_sectors = 0;
-		granularity = 0;
-
-	} else {
-		struct kstatfs sbuf;
-
+	} else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) {
 		max_discard_sectors = UINT_MAX >> 9;
-		if (!vfs_statfs(&file->f_path, &sbuf))
-			granularity = sbuf.f_bsize;
-		else
-			max_discard_sectors = 0;
+		granularity = sbuf.f_bsize;
 	}
 
-	if (max_discard_sectors) {
-		q->limits.discard_granularity = granularity;
-		blk_queue_max_discard_sectors(q, max_discard_sectors);
-		blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
-	} else {
-		q->limits.discard_granularity = 0;
-		blk_queue_max_discard_sectors(q, 0);
-		blk_queue_max_write_zeroes_sectors(q, 0);
-	}
+	lim->max_hw_discard_sectors = max_discard_sectors;
+	lim->max_write_zeroes_sectors = max_discard_sectors;
+	if (max_discard_sectors)
+		lim->discard_granularity = granularity;
+	else
+		lim->discard_granularity = 0;
 }
 
 struct loop_worker {
@@ -986,6 +975,20 @@ loop_set_status_from_info(struct loop_device *lo,
 	return 0;
 }
 
+static int loop_reconfigure_limits(struct loop_device *lo, unsigned short bsize,
+		bool update_discard_settings)
+{
+	struct queue_limits lim;
+
+	lim = queue_limits_start_update(lo->lo_queue);
+	lim.logical_block_size = bsize;
+	lim.physical_block_size = bsize;
+	lim.io_min = bsize;
+	if (update_discard_settings)
+		loop_config_discard(lo, &lim);
+	return queue_limits_commit_update(lo->lo_queue, &lim);
+}
+
 static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 			  struct block_device *bdev,
 			  const struct loop_config *config)
@@ -1083,11 +1086,10 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	else
 		bsize = 512;
 
-	blk_queue_logical_block_size(lo->lo_queue, bsize);
-	blk_queue_physical_block_size(lo->lo_queue, bsize);
-	blk_queue_io_min(lo->lo_queue, bsize);
+	error = loop_reconfigure_limits(lo, bsize, true);
+	if (WARN_ON_ONCE(error))
+		goto out_unlock;
 
-	loop_config_discard(lo);
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
@@ -1154,9 +1156,7 @@ static void __loop_clr_fd(struct loop_device *lo, bool release)
 	lo->lo_offset = 0;
 	lo->lo_sizelimit = 0;
 	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
-	blk_queue_logical_block_size(lo->lo_queue, 512);
-	blk_queue_physical_block_size(lo->lo_queue, 512);
-	blk_queue_io_min(lo->lo_queue, 512);
+	loop_reconfigure_limits(lo, 512, false);
 	invalidate_disk(lo->lo_disk);
 	loop_sysfs_exit(lo);
 	/* let user-space know about this change */
@@ -1488,9 +1488,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	invalidate_bdev(lo->lo_device);
 
 	blk_mq_freeze_queue(lo->lo_queue);
-	blk_queue_logical_block_size(lo->lo_queue, arg);
-	blk_queue_physical_block_size(lo->lo_queue, arg);
-	blk_queue_io_min(lo->lo_queue, arg);
+	err = loop_reconfigure_limits(lo, arg, false);
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
@@ -1982,6 +1980,12 @@ static const struct blk_mq_ops loop_mq_ops = {
 
 static int loop_add(int i)
 {
+	struct queue_limits lim = {
+		/*
+		 * Random number picked from the historic block max_sectors cap.
+		 */
+		.max_hw_sectors		= 2560u,
+	};
 	struct loop_device *lo;
 	struct gendisk *disk;
 	int err;
@@ -2025,16 +2029,13 @@ static int loop_add(int i)
 	if (err)
 		goto out_free_idr;
 
-	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo);
+	disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, &lim, lo);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_cleanup_tags;
 	}
 	lo->lo_queue = lo->lo_disk->queue;
 
-	/* random number picked from the history block max_sectors cap */
-	blk_queue_max_hw_sectors(lo->lo_queue, 2560u);
-
 	/*
 	 * By default, we do buffer IO, so it doesn't make sense to enable
 	 * merge because the I/O submitted to backing file is handled page by
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index b200950e8fb5..43a187609ef7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3401,6 +3401,12 @@ static const struct blk_mq_ops mtip_mq_ops = {
  */
 static int mtip_block_initialize(struct driver_data *dd)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.max_hw_sectors		= 0xffff,
+		.max_segments		= MTIP_MAX_SG,
+		.max_segment_size	= 0x400000,
+	};
 	int rv = 0, wait_for_rebuild = 0;
 	sector_t capacity;
 	unsigned int index = 0;
@@ -3431,7 +3437,7 @@ static int mtip_block_initialize(struct driver_data *dd)
 		goto block_queue_alloc_tag_error;
 	}
 
-	dd->disk = blk_mq_alloc_disk(&dd->tags, dd);
+	dd->disk = blk_mq_alloc_disk(&dd->tags, &lim, dd);
 	if (IS_ERR(dd->disk)) {
 		dev_err(&dd->pdev->dev,
 			"Unable to allocate request queue\n");
@@ -3481,12 +3487,7 @@ skip_create_disk:
 	/* Set device limits. */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, dd->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, dd->queue);
-	blk_queue_max_segments(dd->queue, MTIP_MAX_SG);
-	blk_queue_physical_block_size(dd->queue, 4096);
-	blk_queue_max_hw_sectors(dd->queue, 0xffff);
-	blk_queue_max_segment_size(dd->queue, 0x400000);
 	dma_set_max_seg_size(&dd->pdev->dev, 0x400000);
-	blk_queue_io_min(dd->queue, 4096);
 
 	/* Set the capacity of the device in 512 byte sectors. */
 	if (!(mtip_hw_get_capacity(dd, &capacity))) {
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index d914156db2d8..27b2187e7a6d 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -114,6 +114,10 @@ static const struct block_device_operations n64cart_fops = {
  */
 static int __init n64cart_probe(struct platform_device *pdev)
 {
+	struct queue_limits lim = {
+		.physical_block_size	= 4096,
+		.logical_block_size	= 4096,
+	};
 	struct gendisk *disk;
 	int err = -ENOMEM;
 
@@ -131,9 +135,11 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	if (IS_ERR(reg_base))
 		return PTR_ERR(reg_base);
 
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		err = PTR_ERR(disk);
 		goto out;
+	}
 
 	disk->first_minor = 0;
 	disk->flags = GENHD_FL_NO_PART;
@@ -145,8 +151,6 @@ static int __init n64cart_probe(struct platform_device *pdev)
 	set_disk_ro(disk, 1);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_physical_block_size(disk->queue, 4096);
-	blk_queue_logical_block_size(disk->queue, 4096);
 
 	err = add_disk(disk);
 	if (err)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 33a8f37bb6a1..9d4ec9273bf9 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -316,9 +316,12 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
 	nsock->sent = 0;
 }
 
-static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 		loff_t blksize)
 {
+	struct queue_limits lim;
+	int error;
+
 	if (!blksize)
 		blksize = 1u << NBD_DEF_BLKSIZE_BITS;
 
@@ -334,10 +337,16 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	if (!nbd->pid)
 		return 0;
 
+	lim = queue_limits_start_update(nbd->disk->queue);
 	if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
-		blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX);
-	blk_queue_logical_block_size(nbd->disk->queue, blksize);
-	blk_queue_physical_block_size(nbd->disk->queue, blksize);
+		lim.max_hw_discard_sectors = UINT_MAX;
+	else
+		lim.max_hw_discard_sectors = 0;
+	lim.logical_block_size = blksize;
+	lim.physical_block_size = blksize;
+	error = queue_limits_commit_update(nbd->disk->queue, &lim);
+	if (error)
+		return error;
 
 	if (max_part)
 		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
@@ -346,6 +355,18 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	return 0;
 }
 
+static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+		loff_t blksize)
+{
+	int error;
+
+	blk_mq_freeze_queue(nbd->disk->queue);
+	error = __nbd_set_size(nbd, bytesize, blksize);
+	blk_mq_unfreeze_queue(nbd->disk->queue);
+
+	return error;
+}
+
 static void nbd_complete_rq(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
@@ -1351,7 +1372,6 @@ static void nbd_config_put(struct nbd_device *nbd)
 		nbd->config = NULL;
 
 		nbd->tag_set.timeout = 0;
-		blk_queue_max_discard_sectors(nbd->disk->queue, 0);
 
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
@@ -1783,6 +1803,12 @@ static const struct blk_mq_ops nbd_mq_ops = {
 
 static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors		= 65536,
+		.max_user_sectors	= 256,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	struct nbd_device *nbd;
 	struct gendisk *disk;
 	int err = -ENOMEM;
@@ -1823,7 +1849,7 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	if (err < 0)
 		goto out_free_tags;
 
-	disk = blk_mq_alloc_disk(&nbd->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_free_idr;
@@ -1843,11 +1869,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	 * Tell the block layer that we are not a rotational device
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_max_discard_sectors(disk->queue, 0);
-	blk_queue_max_segment_size(disk->queue, UINT_MAX);
-	blk_queue_max_segments(disk->queue, USHRT_MAX);
-	blk_queue_max_hw_sectors(disk->queue, 65536);
-	disk->queue->limits.max_sectors = 256;
 
 	mutex_init(&nbd->config_lock);
 	refcount_set(&nbd->config_refs, 0);
@@ -2433,6 +2454,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST);
+	if (!dev_list) {
+		nlmsg_free(reply);
+		ret = -EMSGSIZE;
+		goto out;
+	}
+
 	if (index == -1) {
 		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
 		if (ret) {
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 36755f263e8e..71c39bcd872c 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -115,6 +115,18 @@ module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
 MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
 #endif
 
+/*
+ * Historic queue modes.
+ *
+ * These days nothing but NULL_Q_MQ is actually supported, but we keep it the
+ * enum for error reporting.
+ */
+enum {
+	NULL_Q_BIO	= 0,
+	NULL_Q_RQ	= 1,
+	NULL_Q_MQ	= 2,
+};
+
 static int g_queue_mode = NULL_Q_MQ;
 
 static int null_param_store_val(const char *str, int *val, int min, int max)
@@ -165,8 +177,8 @@ static bool g_blocking;
 module_param_named(blocking, g_blocking, bool, 0444);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
 
-static bool shared_tags;
-module_param(shared_tags, bool, 0444);
+static bool g_shared_tags;
+module_param_named(shared_tags, g_shared_tags, bool, 0444);
 MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
 
 static bool g_shared_tag_bitmap;
@@ -426,6 +438,7 @@ NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
+NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@@ -571,6 +584,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
+	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
 	NULL,
 };
@@ -653,10 +667,11 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"badblocks,blocking,blocksize,cache_size,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
-			"poll_queues,power,queue_mode,shared_tag_bitmap,size,"
-			"submit_queues,use_per_node_hctx,virt_boundary,zoned,"
-			"zone_capacity,zone_max_active,zone_max_open,"
-			"zone_nr_conv,zone_offline,zone_readonly,zone_size\n");
+			"poll_queues,power,queue_mode,shared_tag_bitmap,"
+			"shared_tags,size,submit_queues,use_per_node_hctx,"
+			"virt_boundary,zoned,zone_capacity,zone_max_active,"
+			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
+			"zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -738,6 +753,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_max_active = g_zone_max_active;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
+	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
 	return dev;
 }
@@ -752,98 +768,11 @@ static void null_free_dev(struct nullb_device *dev)
 	kfree(dev);
 }
 
-static void put_tag(struct nullb_queue *nq, unsigned int tag)
-{
-	clear_bit_unlock(tag, nq->tag_map);
-
-	if (waitqueue_active(&nq->wait))
-		wake_up(&nq->wait);
-}
-
-static unsigned int get_tag(struct nullb_queue *nq)
-{
-	unsigned int tag;
-
-	do {
-		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
-		if (tag >= nq->queue_depth)
-			return -1U;
-	} while (test_and_set_bit_lock(tag, nq->tag_map));
-
-	return tag;
-}
-
-static void free_cmd(struct nullb_cmd *cmd)
-{
-	put_tag(cmd->nq, cmd->tag);
-}
-
-static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
-
-static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	unsigned int tag;
-
-	tag = get_tag(nq);
-	if (tag != -1U) {
-		cmd = &nq->cmds[tag];
-		cmd->tag = tag;
-		cmd->error = BLK_STS_OK;
-		cmd->nq = nq;
-		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
-			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL);
-			cmd->timer.function = null_cmd_timer_expired;
-		}
-		return cmd;
-	}
-
-	return NULL;
-}
-
-static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, struct bio *bio)
-{
-	struct nullb_cmd *cmd;
-	DEFINE_WAIT(wait);
-
-	do {
-		/*
-		 * This avoids multiple return statements, multiple calls to
-		 * __alloc_cmd() and a fast path call to prepare_to_wait().
-		 */
-		cmd = __alloc_cmd(nq);
-		if (cmd) {
-			cmd->bio = bio;
-			return cmd;
-		}
-		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
-		io_schedule();
-		finish_wait(&nq->wait, &wait);
-	} while (1);
-}
-
-static void end_cmd(struct nullb_cmd *cmd)
-{
-	int queue_mode = cmd->nq->dev->queue_mode;
-
-	switch (queue_mode)  {
-	case NULL_Q_MQ:
-		blk_mq_end_request(cmd->rq, cmd->error);
-		return;
-	case NULL_Q_BIO:
-		cmd->bio->bi_status = cmd->error;
-		bio_endio(cmd->bio);
-		break;
-	}
-
-	free_cmd(cmd);
-}
-
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-	end_cmd(container_of(timer, struct nullb_cmd, timer));
+	struct nullb_cmd *cmd = container_of(timer, struct nullb_cmd, timer);
 
+	blk_mq_end_request(blk_mq_rq_from_pdu(cmd), cmd->error);
 	return HRTIMER_NORESTART;
 }
 
@@ -856,7 +785,9 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 
 static void null_complete_rq(struct request *rq)
 {
-	end_cmd(blk_mq_rq_to_pdu(rq));
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+	blk_mq_end_request(rq, cmd->error);
 }
 
 static struct nullb_page *null_alloc_page(void)
@@ -1273,7 +1204,7 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 
 static int null_handle_rq(struct nullb_cmd *cmd)
 {
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err;
 	unsigned int len;
@@ -1298,63 +1229,21 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 	return 0;
 }
 
-static int null_handle_bio(struct nullb_cmd *cmd)
-{
-	struct bio *bio = cmd->bio;
-	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
-	unsigned int len;
-	sector_t sector = bio->bi_iter.bi_sector;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-
-	spin_lock_irq(&nullb->lock);
-	bio_for_each_segment(bvec, bio, iter) {
-		len = bvec.bv_len;
-		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(bio_op(bio)), sector,
-				     bio->bi_opf & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
-		sector += len >> SECTOR_SHIFT;
-	}
-	spin_unlock_irq(&nullb->lock);
-	return 0;
-}
-
-static void null_stop_queue(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_stop_hw_queues(q);
-}
-
-static void null_restart_queue_async(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_start_stopped_hw_queues(q, true);
-}
-
 static inline blk_status_t null_handle_throttled(struct nullb_cmd *cmd)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	blk_status_t sts = BLK_STS_OK;
-	struct request *rq = cmd->rq;
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 
 	if (!hrtimer_active(&nullb->bw_timer))
 		hrtimer_restart(&nullb->bw_timer);
 
 	if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) {
-		null_stop_queue(nullb);
+		blk_mq_stop_hw_queues(nullb->q);
 		/* race with timer */
 		if (atomic_long_read(&nullb->cur_bytes) > 0)
-			null_restart_queue_async(nullb);
+			blk_mq_start_stopped_hw_queues(nullb->q, true);
 		/* requeue request */
 		sts = BLK_STS_DEV_RESOURCE;
 	}
@@ -1381,37 +1270,29 @@ static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
 						     sector_t nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
-	int err;
 
 	if (op == REQ_OP_DISCARD)
 		return null_handle_discard(dev, sector, nr_sectors);
+	return errno_to_blk_status(null_handle_rq(cmd));
 
-	if (dev->queue_mode == NULL_Q_BIO)
-		err = null_handle_bio(cmd);
-	else
-		err = null_handle_rq(cmd);
-
-	return errno_to_blk_status(err);
 }
 
 static void nullb_zero_read_cmd_buffer(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb_device *dev = cmd->nq->dev;
 	struct bio *bio;
 
-	if (dev->memory_backed)
-		return;
-
-	if (dev->queue_mode == NULL_Q_BIO && bio_op(cmd->bio) == REQ_OP_READ) {
-		zero_fill_bio(cmd->bio);
-	} else if (req_op(cmd->rq) == REQ_OP_READ) {
-		__rq_for_each_bio(bio, cmd->rq)
+	if (!dev->memory_backed && req_op(rq) == REQ_OP_READ) {
+		__rq_for_each_bio(bio, rq)
 			zero_fill_bio(bio);
 	}
 }
 
 static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 {
+	struct request *rq = blk_mq_rq_from_pdu(cmd);
+
 	/*
 	 * Since root privileges are required to configure the null_blk
 	 * driver, it is fine that this driver does not initialize the
@@ -1425,20 +1306,10 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	/* Complete IO by inline, softirq or timer */
 	switch (cmd->nq->dev->irqmode) {
 	case NULL_IRQ_SOFTIRQ:
-		switch (cmd->nq->dev->queue_mode) {
-		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
-			break;
-		case NULL_Q_BIO:
-			/*
-			 * XXX: no proper submitting cpu information available.
-			 */
-			end_cmd(cmd);
-			break;
-		}
+		blk_mq_complete_request(rq);
 		break;
 	case NULL_IRQ_NONE:
-		end_cmd(cmd);
+		blk_mq_end_request(rq, cmd->error);
 		break;
 	case NULL_IRQ_TIMER:
 		null_cmd_end_timer(cmd);
@@ -1499,7 +1370,7 @@ static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
 		return HRTIMER_NORESTART;
 
 	atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps));
-	null_restart_queue_async(nullb);
+	blk_mq_start_stopped_hw_queues(nullb->q, true);
 
 	hrtimer_forward_now(&nullb->bw_timer, timer_interval);
 
@@ -1516,26 +1387,6 @@ static void nullb_setup_bwtimer(struct nullb *nullb)
 	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
 }
 
-static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
-{
-	int index = 0;
-
-	if (nullb->nr_queues != 1)
-		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);
-
-	return &nullb->queues[index];
-}
-
-static void null_submit_bio(struct bio *bio)
-{
-	sector_t sector = bio->bi_iter.bi_sector;
-	sector_t nr_sectors = bio_sectors(bio);
-	struct nullb *nullb = bio->bi_bdev->bd_disk->private_data;
-	struct nullb_queue *nq = nullb_to_queue(nullb);
-
-	null_handle_cmd(alloc_cmd(nq, bio), sector, nr_sectors, bio_op(bio));
-}
-
 #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
 
 static bool should_timeout_request(struct request *rq)
@@ -1655,7 +1506,7 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 						blk_rq_sectors(req));
 		if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error,
 					blk_mq_end_request_batch))
-			end_cmd(cmd);
+			blk_mq_end_request(req, cmd->error);
 		nr++;
 	}
 
@@ -1711,7 +1562,6 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		cmd->timer.function = null_cmd_timer_expired;
 	}
-	cmd->rq = rq;
 	cmd->error = BLK_STS_OK;
 	cmd->nq = nq;
 	cmd->fake_timeout = should_timeout_request(rq) ||
@@ -1770,34 +1620,8 @@ static void null_queue_rqs(struct request **rqlist)
 	*rqlist = requeue_list;
 }
 
-static void cleanup_queue(struct nullb_queue *nq)
-{
-	bitmap_free(nq->tag_map);
-	kfree(nq->cmds);
-}
-
-static void cleanup_queues(struct nullb *nullb)
-{
-	int i;
-
-	for (i = 0; i < nullb->nr_queues; i++)
-		cleanup_queue(&nullb->queues[i]);
-
-	kfree(nullb->queues);
-}
-
-static void null_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nullb_queue *nq = hctx->driver_data;
-	struct nullb *nullb = nq->dev->nullb;
-
-	nullb->nr_queues--;
-}
-
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
 {
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
 	nq->dev = nullb->dev;
 	INIT_LIST_HEAD(&nq->poll_list);
 	spin_lock_init(&nq->poll_lock);
@@ -1815,7 +1639,6 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 	nq = &nullb->queues[hctx_idx];
 	hctx->driver_data = nq;
 	null_init_queue(nullb, nq);
-	nullb->nr_queues++;
 
 	return 0;
 }
@@ -1828,7 +1651,6 @@ static const struct blk_mq_ops null_mq_ops = {
 	.poll		= null_poll,
 	.map_queues	= null_map_queues,
 	.init_hctx	= null_init_hctx,
-	.exit_hctx	= null_exit_hctx,
 };
 
 static void null_del_dev(struct nullb *nullb)
@@ -1849,21 +1671,20 @@ static void null_del_dev(struct nullb *nullb)
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
 		hrtimer_cancel(&nullb->bw_timer);
 		atomic_long_set(&nullb->cur_bytes, LONG_MAX);
-		null_restart_queue_async(nullb);
+		blk_mq_start_stopped_hw_queues(nullb->q, true);
 	}
 
 	put_disk(nullb->disk);
-	if (dev->queue_mode == NULL_Q_MQ &&
-	    nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 	if (null_cache_active(nullb))
 		null_free_device_storage(nullb->dev, true);
 	kfree(nullb);
 	dev->nullb = NULL;
 }
 
-static void null_config_discard(struct nullb *nullb)
+static void null_config_discard(struct nullb *nullb, struct queue_limits *lim)
 {
 	if (nullb->dev->discard == false)
 		return;
@@ -1880,43 +1701,14 @@ static void null_config_discard(struct nullb *nullb)
 		return;
 	}
 
-	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
+	lim->max_hw_discard_sectors = UINT_MAX >> 9;
 }
 
-static const struct block_device_operations null_bio_ops = {
-	.owner		= THIS_MODULE,
-	.submit_bio	= null_submit_bio,
-	.report_zones	= null_report_zones,
-};
-
-static const struct block_device_operations null_rq_ops = {
+static const struct block_device_operations null_ops = {
 	.owner		= THIS_MODULE,
 	.report_zones	= null_report_zones,
 };
 
-static int setup_commands(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	int i;
-
-	nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL);
-	if (!nq->cmds)
-		return -ENOMEM;
-
-	nq->tag_map = bitmap_zalloc(nq->queue_depth, GFP_KERNEL);
-	if (!nq->tag_map) {
-		kfree(nq->cmds);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nq->queue_depth; i++) {
-		cmd = &nq->cmds[i];
-		cmd->tag = -1U;
-	}
-
-	return 0;
-}
-
 static int setup_queues(struct nullb *nullb)
 {
 	int nqueues = nr_cpu_ids;
@@ -1929,101 +1721,66 @@ static int setup_queues(struct nullb *nullb)
 	if (!nullb->queues)
 		return -ENOMEM;
 
-	nullb->queue_depth = nullb->dev->hw_queue_depth;
 	return 0;
 }
 
-static int init_driver_queues(struct nullb *nullb)
+static int null_init_tag_set(struct blk_mq_tag_set *set, int poll_queues)
 {
-	struct nullb_queue *nq;
-	int i, ret = 0;
-
-	for (i = 0; i < nullb->dev->submit_queues; i++) {
-		nq = &nullb->queues[i];
-
-		null_init_queue(nullb, nq);
-
-		ret = setup_commands(nq);
-		if (ret)
-			return ret;
-		nullb->nr_queues++;
+	set->ops = &null_mq_ops;
+	set->cmd_size = sizeof(struct nullb_cmd);
+	set->timeout = 5 * HZ;
+	set->nr_maps = 1;
+	if (poll_queues) {
+		set->nr_hw_queues += poll_queues;
+		set->nr_maps += 2;
 	}
-	return 0;
+	return blk_mq_alloc_tag_set(set);
 }
 
-static int null_gendisk_register(struct nullb *nullb)
+static int null_init_global_tag_set(void)
 {
-	sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT;
-	struct gendisk *disk = nullb->disk;
+	int error;
 
-	set_capacity(disk, size);
-
-	disk->major		= null_major;
-	disk->first_minor	= nullb->index;
-	disk->minors		= 1;
-	if (queue_is_mq(nullb->q))
-		disk->fops		= &null_rq_ops;
-	else
-		disk->fops		= &null_bio_ops;
-	disk->private_data	= nullb;
-	strscpy_pad(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+	if (tag_set.ops)
+		return 0;
 
-	if (nullb->dev->zoned) {
-		int ret = null_register_zoned_dev(nullb);
+	tag_set.nr_hw_queues = g_submit_queues;
+	tag_set.queue_depth = g_hw_queue_depth;
+	tag_set.numa_node = g_home_node;
+	tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	if (g_no_sched)
+		tag_set.flags |= BLK_MQ_F_NO_SCHED;
+	if (g_shared_tag_bitmap)
+		tag_set.flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (g_blocking)
+		tag_set.flags |= BLK_MQ_F_BLOCKING;
 
-		if (ret)
-			return ret;
-	}
-
-	return add_disk(disk);
+	error = null_init_tag_set(&tag_set, g_poll_queues);
+	if (error)
+		tag_set.ops = NULL;
+	return error;
 }
 
-static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
+static int null_setup_tagset(struct nullb *nullb)
 {
-	unsigned int flags = BLK_MQ_F_SHOULD_MERGE;
-	int hw_queues, numa_node;
-	unsigned int queue_depth;
-	int poll_queues;
-
-	if (nullb) {
-		hw_queues = nullb->dev->submit_queues;
-		poll_queues = nullb->dev->poll_queues;
-		queue_depth = nullb->dev->hw_queue_depth;
-		numa_node = nullb->dev->home_node;
-		if (nullb->dev->no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (nullb->dev->shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (nullb->dev->blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	} else {
-		hw_queues = g_submit_queues;
-		poll_queues = g_poll_queues;
-		queue_depth = g_hw_queue_depth;
-		numa_node = g_home_node;
-		if (g_no_sched)
-			flags |= BLK_MQ_F_NO_SCHED;
-		if (g_shared_tag_bitmap)
-			flags |= BLK_MQ_F_TAG_HCTX_SHARED;
-		if (g_blocking)
-			flags |= BLK_MQ_F_BLOCKING;
-	}
-
-	set->ops = &null_mq_ops;
-	set->cmd_size	= sizeof(struct nullb_cmd);
-	set->flags = flags;
-	set->driver_data = nullb;
-	set->nr_hw_queues = hw_queues;
-	set->queue_depth = queue_depth;
-	set->numa_node = numa_node;
-	if (poll_queues) {
-		set->nr_hw_queues += poll_queues;
-		set->nr_maps = 3;
-	} else {
-		set->nr_maps = 1;
+	if (nullb->dev->shared_tags) {
+		nullb->tag_set = &tag_set;
+		return null_init_global_tag_set();
 	}
 
-	return blk_mq_alloc_tag_set(set);
+	nullb->tag_set = &nullb->__tag_set;
+	nullb->tag_set->driver_data = nullb;
+	nullb->tag_set->nr_hw_queues = nullb->dev->submit_queues;
+	nullb->tag_set->queue_depth = nullb->dev->hw_queue_depth;
+	nullb->tag_set->numa_node = nullb->dev->home_node;
+	nullb->tag_set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (nullb->dev->no_sched)
+		nullb->tag_set->flags |= BLK_MQ_F_NO_SCHED;
+	if (nullb->dev->shared_tag_bitmap)
+		nullb->tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
+	if (nullb->dev->blocking)
+		nullb->tag_set->flags |= BLK_MQ_F_BLOCKING;
+	return null_init_tag_set(nullb->tag_set, nullb->dev->poll_queues);
 }
 
 static int null_validate_conf(struct nullb_device *dev)
@@ -2032,11 +1789,15 @@ static int null_validate_conf(struct nullb_device *dev)
 		pr_err("legacy IO path is no longer available\n");
 		return -EINVAL;
 	}
+	if (dev->queue_mode == NULL_Q_BIO) {
+		pr_err("BIO-based IO path is no longer available, using blk-mq instead.\n");
+		dev->queue_mode = NULL_Q_MQ;
+	}
 
 	dev->blocksize = round_down(dev->blocksize, 512);
 	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
 
-	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
+	if (dev->use_per_node_hctx) {
 		if (dev->submit_queues != nr_online_nodes)
 			dev->submit_queues = nr_online_nodes;
 	} else if (dev->submit_queues > nr_cpu_ids)
@@ -2048,8 +1809,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	if (dev->poll_queues > g_poll_queues)
 		dev->poll_queues = g_poll_queues;
 	dev->prev_poll_queues = dev->poll_queues;
-
-	dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
 	dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
 
 	/* Do memory allocation, so set blocking */
@@ -2060,9 +1819,6 @@ static int null_validate_conf(struct nullb_device *dev)
 	dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024,
 						dev->cache_size);
 	dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps);
-	/* can not stop a queue */
-	if (dev->queue_mode == NULL_Q_BIO)
-		dev->mbps = 0;
 
 	if (dev->zoned &&
 	    (!dev->zone_size || !is_power_of_2(dev->zone_size))) {
@@ -2102,6 +1858,12 @@ static bool null_setup_fault(void)
 
 static int null_add_dev(struct nullb_device *dev)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blocksize,
+		.physical_block_size	= dev->blocksize,
+		.max_hw_sectors		= dev->max_sectors,
+	};
+
 	struct nullb *nullb;
 	int rv;
 
@@ -2123,36 +1885,25 @@ static int null_add_dev(struct nullb_device *dev)
 	if (rv)
 		goto out_free_nullb;
 
-	if (dev->queue_mode == NULL_Q_MQ) {
-		if (shared_tags) {
-			nullb->tag_set = &tag_set;
-			rv = 0;
-		} else {
-			nullb->tag_set = &nullb->__tag_set;
-			rv = null_init_tag_set(nullb, nullb->tag_set);
-		}
+	rv = null_setup_tagset(nullb);
+	if (rv)
+		goto out_cleanup_queues;
 
+	if (dev->virt_boundary)
+		lim.virt_boundary_mask = PAGE_SIZE - 1;
+	null_config_discard(nullb, &lim);
+	if (dev->zoned) {
+		rv = null_init_zoned_dev(dev, &lim);
 		if (rv)
-			goto out_cleanup_queues;
-
-		nullb->tag_set->timeout = 5 * HZ;
-		nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb);
-		if (IS_ERR(nullb->disk)) {
-			rv = PTR_ERR(nullb->disk);
 			goto out_cleanup_tags;
-		}
-		nullb->q = nullb->disk->queue;
-	} else if (dev->queue_mode == NULL_Q_BIO) {
-		rv = -ENOMEM;
-		nullb->disk = blk_alloc_disk(nullb->dev->home_node);
-		if (!nullb->disk)
-			goto out_cleanup_queues;
+	}
 
-		nullb->q = nullb->disk->queue;
-		rv = init_driver_queues(nullb);
-		if (rv)
-			goto out_cleanup_disk;
+	nullb->disk = blk_mq_alloc_disk(nullb->tag_set, &lim, nullb);
+	if (IS_ERR(nullb->disk)) {
+		rv = PTR_ERR(nullb->disk);
+		goto out_cleanup_zone;
 	}
+	nullb->q = nullb->disk->queue;
 
 	if (dev->mbps) {
 		set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags);
@@ -2164,12 +1915,6 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_write_cache(nullb->q, true, true);
 	}
 
-	if (dev->zoned) {
-		rv = null_init_zoned_dev(dev, nullb->q);
-		if (rv)
-			goto out_cleanup_disk;
-	}
-
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
@@ -2177,22 +1922,12 @@ static int null_add_dev(struct nullb_device *dev)
 	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
 	if (rv < 0) {
 		mutex_unlock(&lock);
-		goto out_cleanup_zone;
+		goto out_cleanup_disk;
 	}
 	nullb->index = rv;
 	dev->index = rv;
 	mutex_unlock(&lock);
 
-	blk_queue_logical_block_size(nullb->q, dev->blocksize);
-	blk_queue_physical_block_size(nullb->q, dev->blocksize);
-	if (dev->max_sectors)
-		blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
-
-	if (dev->virt_boundary)
-		blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
-
-	null_config_discard(nullb);
-
 	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
 		snprintf(nullb->disk_name, sizeof(nullb->disk_name),
@@ -2201,7 +1936,22 @@ static int null_add_dev(struct nullb_device *dev)
 		sprintf(nullb->disk_name, "nullb%d", nullb->index);
 	}
 
-	rv = null_gendisk_register(nullb);
+	set_capacity(nullb->disk,
+		((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT);
+	nullb->disk->major = null_major;
+	nullb->disk->first_minor = nullb->index;
+	nullb->disk->minors = 1;
+	nullb->disk->fops = &null_ops;
+	nullb->disk->private_data = nullb;
+	strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
+	if (nullb->dev->zoned) {
+		rv = null_register_zoned_dev(nullb);
+		if (rv)
+			goto out_ida_free;
+	}
+
+	rv = add_disk(nullb->disk);
 	if (rv)
 		goto out_ida_free;
 
@@ -2220,10 +1970,10 @@ out_cleanup_zone:
 out_cleanup_disk:
 	put_disk(nullb->disk);
 out_cleanup_tags:
-	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+	if (nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
 out_cleanup_queues:
-	cleanup_queues(nullb);
+	kfree(nullb->queues);
 out_free_nullb:
 	kfree(nullb);
 	dev->nullb = NULL;
@@ -2299,7 +2049,7 @@ static int __init null_init(void)
 		return -EINVAL;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
+	if (g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("submit_queues param is set to %u.\n",
 				nr_online_nodes);
@@ -2311,18 +2061,12 @@ static int __init null_init(void)
 		g_submit_queues = 1;
 	}
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags) {
-		ret = null_init_tag_set(NULL, &tag_set);
-		if (ret)
-			return ret;
-	}
-
 	config_group_init(&nullb_subsys.su_group);
 	mutex_init(&nullb_subsys.su_mutex);
 
 	ret = configfs_register_subsystem(&nullb_subsys);
 	if (ret)
-		goto err_tagset;
+		return ret;
 
 	mutex_init(&lock);
 
@@ -2349,9 +2093,6 @@ err_dev:
 	unregister_blkdev(null_major, "nullb");
 err_conf:
 	configfs_unregister_subsystem(&nullb_subsys);
-err_tagset:
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
-		blk_mq_free_tag_set(&tag_set);
 	return ret;
 }
 
@@ -2370,7 +2111,7 @@ static void __exit null_exit(void)
 	}
 	mutex_unlock(&lock);
 
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
+	if (tag_set.ops)
 		blk_mq_free_tag_set(&tag_set);
 }
 
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 929f659dd255..477b97746823 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -16,11 +16,6 @@
 #include <linux/mutex.h>
 
 struct nullb_cmd {
-	union {
-		struct request *rq;
-		struct bio *bio;
-	};
-	unsigned int tag;
 	blk_status_t error;
 	bool fake_timeout;
 	struct nullb_queue *nq;
@@ -28,16 +23,11 @@ struct nullb_cmd {
 };
 
 struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
 	struct nullb_device *dev;
 	unsigned int requeue_selection;
 
 	struct list_head poll_list;
 	spinlock_t poll_lock;
-
-	struct nullb_cmd *cmds;
 };
 
 struct nullb_zone {
@@ -60,13 +50,6 @@ struct nullb_zone {
 	unsigned int capacity;
 };
 
-/* Queue modes */
-enum {
-	NULL_Q_BIO	= 0,
-	NULL_Q_RQ	= 1,
-	NULL_Q_MQ	= 2,
-};
-
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_group group;
@@ -119,6 +102,7 @@ struct nullb_device {
 	bool zoned; /* if device is zoned */
 	bool virt_boundary; /* virtual boundary on/off for the device */
 	bool no_sched; /* no IO scheduler for the device */
+	bool shared_tags; /* share tag set between devices for blk-mq */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
 };
 
@@ -130,14 +114,12 @@ struct nullb {
 	struct gendisk *disk;
 	struct blk_mq_tag_set *tag_set;
 	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
 	atomic_long_t cur_bytes;
 	struct hrtimer bw_timer;
 	unsigned long cache_flush_pos;
 	spinlock_t lock;
 
 	struct nullb_queue *queues;
-	unsigned int nr_queues;
 	char disk_name[DISK_NAME_LEN];
 };
 
@@ -147,7 +129,7 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
 			      sector_t sector, unsigned int nr_sectors);
 
 #ifdef CONFIG_BLK_DEV_ZONED
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
+int null_init_zoned_dev(struct nullb_device *dev, struct queue_limits *lim);
 int null_register_zoned_dev(struct nullb *nullb);
 void null_free_zoned_dev(struct nullb_device *dev);
 int null_report_zones(struct gendisk *disk, sector_t sector,
@@ -160,7 +142,7 @@ ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
 			size_t count, enum blk_zone_cond cond);
 #else
 static inline int null_init_zoned_dev(struct nullb_device *dev,
-				      struct request_queue *q)
+		struct queue_limits *lim)
 {
 	pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
 	return -EINVAL;
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index 6b2b370e786f..ef2d05d5f0df 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -41,10 +41,11 @@ TRACE_EVENT(nullb_zone_op,
 		__field(unsigned int, zone_cond)
 	    ),
 	    TP_fast_assign(
-		__entry->op = req_op(cmd->rq);
+		__entry->op = req_op(blk_mq_rq_from_pdu(cmd));
 		__entry->zone_no = zone_no;
 		__entry->zone_cond = zone_cond;
-		__assign_disk_name(__entry->disk, cmd->rq->q->disk);
+		__assign_disk_name(__entry->disk,
+			blk_mq_rq_from_pdu(cmd)->q->disk);
 	    ),
 	    TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
 		      __print_disk_name(__entry->disk),
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 6f5e0994862e..1689e2584104 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -58,7 +58,8 @@ static inline void null_unlock_zone(struct nullb_device *dev,
 		mutex_unlock(&zone->mutex);
 }
 
-int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
+int null_init_zoned_dev(struct nullb_device *dev,
+			struct queue_limits *lim)
 {
 	sector_t dev_capacity_sects, zone_capacity_sects;
 	struct nullb_zone *zone;
@@ -151,27 +152,22 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		sector += dev->zone_size_sects;
 	}
 
+	lim->zoned = true;
+	lim->chunk_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_open_zones = dev->zone_max_open;
+	lim->max_active_zones = dev->zone_max_active;
 	return 0;
 }
 
 int null_register_zoned_dev(struct nullb *nullb)
 {
-	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
-	blk_queue_chunk_sectors(q, dev->zone_size_sects);
 	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	blk_queue_max_zone_append_sectors(q, dev->zone_size_sects);
-	disk_set_max_open_zones(nullb->disk, dev->zone_max_open);
-	disk_set_max_active_zones(nullb->disk, dev->zone_max_active);
-
-	if (queue_is_mq(q))
-		return blk_revalidate_disk_zones(nullb->disk, NULL);
-
-	return 0;
+	return blk_revalidate_disk_zones(nullb->disk, NULL);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)
@@ -394,10 +390,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	 */
 	if (append) {
 		sector = zone->wp;
-		if (dev->queue_mode == NULL_Q_MQ)
-			cmd->rq->__sector = sector;
-		else
-			cmd->bio->bi_iter.bi_sector = sector;
+		blk_mq_rq_from_pdu(cmd)->__sector = sector;
 	} else if (sector != zone->wp) {
 		ret = BLK_STS_IOERR;
 		goto unlock;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index d56d972aadb3..21728e9ea5c3 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -340,8 +340,8 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu
 		n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n",
 			pd->disk->disk_name,
 			MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
-			MAJOR(pd->bdev_handle->bdev->bd_dev),
-			MINOR(pd->bdev_handle->bdev->bd_dev));
+			MAJOR(file_bdev(pd->bdev_file)->bd_dev),
+			MINOR(file_bdev(pd->bdev_file)->bd_dev));
 	}
 	mutex_unlock(&ctl_mutex);
 	return n;
@@ -438,7 +438,7 @@ static int pkt_seq_show(struct seq_file *m, void *p)
 	int states[PACKET_NUM_STATES];
 
 	seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name,
-		   pd->bdev_handle->bdev);
+		   file_bdev(pd->bdev_file));
 
 	seq_printf(m, "\nSettings:\n");
 	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
@@ -715,7 +715,7 @@ static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *nod
  */
 static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
 {
-	struct request_queue *q = bdev_get_queue(pd->bdev_handle->bdev);
+	struct request_queue *q = bdev_get_queue(file_bdev(pd->bdev_file));
 	struct scsi_cmnd *scmd;
 	struct request *rq;
 	int ret = 0;
@@ -828,6 +828,12 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
  */
 static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
 {
+	/*
+	 * Some CDRW drives can not handle writes larger than one packet,
+	 * even if the size is a multiple of the packet size.
+	 */
+	bio->bi_opf |= REQ_NOMERGE;
+
 	spin_lock(&pd->iosched.lock);
 	if (bio_data_dir(bio) == READ)
 		bio_list_add(&pd->iosched.read_queue, bio);
@@ -1048,7 +1054,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 			continue;
 
 		bio = pkt->r_bios[f];
-		bio_init(bio, pd->bdev_handle->bdev, bio->bi_inline_vecs, 1,
+		bio_init(bio, file_bdev(pd->bdev_file), bio->bi_inline_vecs, 1,
 			 REQ_OP_READ);
 		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
 		bio->bi_end_io = pkt_end_io_read;
@@ -1264,7 +1270,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	struct device *ddev = disk_to_dev(pd->disk);
 	int f;
 
-	bio_init(pkt->w_bio, pd->bdev_handle->bdev, pkt->w_bio->bi_inline_vecs,
+	bio_init(pkt->w_bio, file_bdev(pd->bdev_file), pkt->w_bio->bi_inline_vecs,
 		 pkt->frames, REQ_OP_WRITE);
 	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
 	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
@@ -2162,20 +2168,20 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	int ret;
 	long lba;
 	struct request_queue *q;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	/*
 	 * We need to re-open the cdrom device without O_NONBLOCK to be able
 	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
 	 * so open should not fail.
 	 */
-	bdev_handle = bdev_open_by_dev(pd->bdev_handle->bdev->bd_dev,
+	bdev_file = bdev_file_open_by_dev(file_bdev(pd->bdev_file)->bd_dev,
 				       BLK_OPEN_READ, pd, NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		goto out;
 	}
-	pd->open_bdev_handle = bdev_handle;
+	pd->f_open_bdev = bdev_file;
 
 	ret = pkt_get_last_written(pd, &lba);
 	if (ret) {
@@ -2184,18 +2190,13 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	}
 
 	set_capacity(pd->disk, lba << 2);
-	set_capacity_and_notify(pd->bdev_handle->bdev->bd_disk, lba << 2);
+	set_capacity_and_notify(file_bdev(pd->bdev_file)->bd_disk, lba << 2);
 
-	q = bdev_get_queue(pd->bdev_handle->bdev);
+	q = bdev_get_queue(file_bdev(pd->bdev_file));
 	if (write) {
 		ret = pkt_open_write(pd);
 		if (ret)
 			goto out_putdev;
-		/*
-		 * Some CDRW drives can not handle writes larger than one packet,
-		 * even if the size is a multiple of the packet size.
-		 */
-		blk_queue_max_hw_sectors(q, pd->settings.size);
 		set_bit(PACKET_WRITABLE, &pd->flags);
 	} else {
 		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
@@ -2218,7 +2219,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
 	return 0;
 
 out_putdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 out:
 	return ret;
 }
@@ -2237,8 +2238,8 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 	pkt_lock_door(pd, 0);
 
 	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
-	bdev_release(pd->open_bdev_handle);
-	pd->open_bdev_handle = NULL;
+	fput(pd->f_open_bdev);
+	pd->f_open_bdev = NULL;
 
 	pkt_shrink_pktlist(pd);
 }
@@ -2326,7 +2327,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
 
 static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 {
-	struct bio *cloned_bio = bio_alloc_clone(pd->bdev_handle->bdev, bio,
+	struct bio *cloned_bio = bio_alloc_clone(file_bdev(pd->bdev_file), bio,
 		GFP_NOIO, &pkt_bio_set);
 	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
 
@@ -2338,9 +2339,9 @@ static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 	pkt_queue_bio(pd, cloned_bio);
 }
 
-static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+static void pkt_make_request_write(struct bio *bio)
 {
-	struct pktcdvd_device *pd = q->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	sector_t zone;
 	struct packet_data *pkt;
 	int was_empty, blocked_bio;
@@ -2432,7 +2433,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 
 static void pkt_submit_bio(struct bio *bio)
 {
-	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
 	struct device *ddev = disk_to_dev(pd->disk);
 	struct bio *split;
 
@@ -2476,7 +2477,7 @@ static void pkt_submit_bio(struct bio *bio)
 			split = bio;
 		}
 
-		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+		pkt_make_request_write(split);
 	} while (split != bio);
 
 	return;
@@ -2484,20 +2485,11 @@ end_io:
 	bio_io_error(bio);
 }
 
-static void pkt_init_queue(struct pktcdvd_device *pd)
-{
-	struct request_queue *q = pd->disk->queue;
-
-	blk_queue_logical_block_size(q, CD_FRAMESIZE);
-	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
-	q->queuedata = pd;
-}
-
 static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 {
 	struct device *ddev = disk_to_dev(pd->disk);
 	int i;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct scsi_device *sdev;
 
 	if (pd->pkt_dev == dev) {
@@ -2508,9 +2500,9 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		struct pktcdvd_device *pd2 = pkt_devs[i];
 		if (!pd2)
 			continue;
-		if (pd2->bdev_handle->bdev->bd_dev == dev) {
+		if (file_bdev(pd2->bdev_file)->bd_dev == dev) {
 			dev_err(ddev, "%pg already setup\n",
-				pd2->bdev_handle->bdev);
+				file_bdev(pd2->bdev_file));
 			return -EBUSY;
 		}
 		if (pd2->pkt_dev == dev) {
@@ -2519,13 +2511,13 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		}
 	}
 
-	bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY,
+	bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
-	sdev = scsi_device_from_queue(bdev_handle->bdev->bd_disk->queue);
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
+	sdev = scsi_device_from_queue(file_bdev(bdev_file)->bd_disk->queue);
 	if (!sdev) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EINVAL;
 	}
 	put_device(&sdev->sdev_gendev);
@@ -2533,10 +2525,8 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
 
-	pd->bdev_handle = bdev_handle;
-	set_blocksize(bdev_handle->bdev, CD_FRAMESIZE);
-
-	pkt_init_queue(pd);
+	pd->bdev_file = bdev_file;
+	set_blocksize(file_bdev(bdev_file), CD_FRAMESIZE);
 
 	atomic_set(&pd->cdrw.pending_bios, 0);
 	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
@@ -2546,11 +2536,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	}
 
 	proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd);
-	dev_notice(ddev, "writer mapped to %pg\n", bdev_handle->bdev);
+	dev_notice(ddev, "writer mapped to %pg\n", file_bdev(bdev_file));
 	return 0;
 
 out_mem:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return -ENOMEM;
@@ -2605,9 +2595,9 @@ static unsigned int pkt_check_events(struct gendisk *disk,
 
 	if (!pd)
 		return 0;
-	if (!pd->bdev_handle)
+	if (!pd->bdev_file)
 		return 0;
-	attached_disk = pd->bdev_handle->bdev->bd_disk;
+	attached_disk = file_bdev(pd->bdev_file)->bd_disk;
 	if (!attached_disk || !attached_disk->fops->check_events)
 		return 0;
 	return attached_disk->fops->check_events(attached_disk, clearing);
@@ -2634,6 +2624,10 @@ static const struct block_device_operations pktcdvd_ops = {
  */
 static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 {
+	struct queue_limits lim = {
+		.max_hw_sectors		= PACKET_MAX_SECTORS,
+		.logical_block_size	= CD_FRAMESIZE,
+	};
 	int idx;
 	int ret = -ENOMEM;
 	struct pktcdvd_device *pd;
@@ -2673,10 +2667,11 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	pd->write_congestion_on  = write_congestion_on;
 	pd->write_congestion_off = write_congestion_off;
 
-	ret = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		ret = PTR_ERR(disk);
 		goto out_mem;
+	}
 	pd->disk = disk;
 	disk->major = pktdev_major;
 	disk->first_minor = idx;
@@ -2692,7 +2687,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 		goto out_mem2;
 
 	/* inherit events of the host device */
-	disk->events = pd->bdev_handle->bdev->bd_disk->events;
+	disk->events = file_bdev(pd->bdev_file)->bd_disk->events;
 
 	ret = add_disk(disk);
 	if (ret)
@@ -2757,7 +2752,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	pkt_debugfs_dev_remove(pd);
 	pkt_sysfs_dev_remove(pd);
 
-	bdev_release(pd->bdev_handle);
+	fput(pd->bdev_file);
 
 	remove_proc_entry(pd->disk->disk_name, pkt_proc);
 	dev_notice(ddev, "writer unmapped\n");
@@ -2784,7 +2779,7 @@ static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
 
 	pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
 	if (pd) {
-		ctrl_cmd->dev = new_encode_dev(pd->bdev_handle->bdev->bd_dev);
+		ctrl_cmd->dev = new_encode_dev(file_bdev(pd->bdev_file)->bd_dev);
 		ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
 	} else {
 		ctrl_cmd->dev = 0;
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 36d7b36c60c7..b810ac0a5c4b 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -382,6 +382,14 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	struct ps3disk_private *priv;
 	int error;
 	unsigned int devidx;
+	struct queue_limits lim = {
+		.logical_block_size	= dev->blk_size,
+		.max_hw_sectors		= dev->bounce_size >> 9,
+		.max_segments		= -1,
+		.max_segment_size	= dev->bounce_size,
+		.dma_alignment		= dev->blk_size - 1,
+	};
+
 	struct request_queue *queue;
 	struct gendisk *gendisk;
 
@@ -431,7 +439,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	if (error)
 		goto fail_teardown;
 
-	gendisk = blk_mq_alloc_disk(&priv->tag_set, dev);
+	gendisk = blk_mq_alloc_disk(&priv->tag_set, &lim, dev);
 	if (IS_ERR(gendisk)) {
 		dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n",
 			__func__, __LINE__);
@@ -441,15 +449,8 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 
 	queue = gendisk->queue;
 
-	blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9);
-	blk_queue_dma_alignment(queue, dev->blk_size-1);
-	blk_queue_logical_block_size(queue, dev->blk_size);
-
 	blk_queue_write_cache(queue, true, false);
 
-	blk_queue_max_segments(queue, -1);
-	blk_queue_max_segment_size(queue, dev->bounce_size);
-
 	priv->gendisk = gendisk;
 	gendisk->major = ps3disk_major;
 	gendisk->first_minor = devidx * PS3DISK_MINORS;
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index 38d42af01b25..bdcf083b45e2 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -730,10 +730,10 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 
 	ps3vram_proc_init(dev);
 
-	gendisk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!gendisk) {
+	gendisk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(gendisk)) {
 		dev_err(&dev->core, "blk_alloc_disk failed\n");
-		error = -ENOMEM;
+		error = PTR_ERR(gendisk);
 		goto out_cache_cleanup;
 	}
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 12b5d53ec856..26ff5cd2bf0a 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -575,7 +575,7 @@ static const struct attribute_group rbd_bus_group = {
 };
 __ATTRIBUTE_GROUPS(rbd_bus);
 
-static struct bus_type rbd_bus_type = {
+static const struct bus_type rbd_bus_type = {
 	.name		= "rbd",
 	.bus_groups	= rbd_bus_groups,
 };
@@ -4952,6 +4952,14 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	struct request_queue *q;
 	unsigned int objset_bytes =
 	    rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
+	struct queue_limits lim = {
+		.max_hw_sectors		= objset_bytes >> SECTOR_SHIFT,
+		.max_user_sectors	= objset_bytes >> SECTOR_SHIFT,
+		.io_min			= rbd_dev->opts->alloc_size,
+		.io_opt			= rbd_dev->opts->alloc_size,
+		.max_segments		= USHRT_MAX,
+		.max_segment_size	= UINT_MAX,
+	};
 	int err;
 
 	memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set));
@@ -4966,7 +4974,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	if (err)
 		return err;
 
-	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev);
+	if (rbd_dev->opts->trim) {
+		lim.discard_granularity = rbd_dev->opts->alloc_size;
+		lim.max_hw_discard_sectors = objset_bytes >> SECTOR_SHIFT;
+		lim.max_write_zeroes_sectors = objset_bytes >> SECTOR_SHIFT;
+	}
+
+	disk = blk_mq_alloc_disk(&rbd_dev->tag_set, &lim, rbd_dev);
 	if (IS_ERR(disk)) {
 		err = PTR_ERR(disk);
 		goto out_tag_set;
@@ -4987,19 +5001,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
 
-	blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	q->limits.max_sectors = queue_max_hw_sectors(q);
-	blk_queue_max_segments(q, USHRT_MAX);
-	blk_queue_max_segment_size(q, UINT_MAX);
-	blk_queue_io_min(q, rbd_dev->opts->alloc_size);
-	blk_queue_io_opt(q, rbd_dev->opts->alloc_size);
-
-	if (rbd_dev->opts->trim) {
-		q->limits.discard_granularity = rbd_dev->opts->alloc_size;
-		blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
-		blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
-	}
-
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 4044c369d22a..b7ffe03c6160 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1329,43 +1329,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev)
 	}
 }
 
-static void setup_request_queue(struct rnbd_clt_dev *dev,
-				struct rnbd_msg_open_rsp *rsp)
-{
-	blk_queue_logical_block_size(dev->queue,
-				     le16_to_cpu(rsp->logical_block_size));
-	blk_queue_physical_block_size(dev->queue,
-				      le16_to_cpu(rsp->physical_block_size));
-	blk_queue_max_hw_sectors(dev->queue,
-				 dev->sess->max_io_size / SECTOR_SIZE);
-
-	/*
-	 * we don't support discards to "discontiguous" segments
-	 * in on request
-	 */
-	blk_queue_max_discard_segments(dev->queue, 1);
-
-	blk_queue_max_discard_sectors(dev->queue,
-				      le32_to_cpu(rsp->max_discard_sectors));
-	dev->queue->limits.discard_granularity =
-					le32_to_cpu(rsp->discard_granularity);
-	dev->queue->limits.discard_alignment =
-					le32_to_cpu(rsp->discard_alignment);
-	if (le16_to_cpu(rsp->secure_discard))
-		blk_queue_max_secure_erase_sectors(dev->queue,
-					le32_to_cpu(rsp->max_discard_sectors));
-	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
-	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
-	blk_queue_max_segments(dev->queue, dev->sess->max_segments);
-	blk_queue_io_opt(dev->queue, dev->sess->max_io_size);
-	blk_queue_virt_boundary(dev->queue, SZ_4K - 1);
-	blk_queue_write_cache(dev->queue,
-			      !!(rsp->cache_policy & RNBD_WRITEBACK),
-			      !!(rsp->cache_policy & RNBD_FUA));
-	blk_queue_max_write_zeroes_sectors(dev->queue,
-					   le32_to_cpu(rsp->max_write_zeroes_sectors));
-}
-
 static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 				   struct rnbd_msg_open_rsp *rsp, int idx)
 {
@@ -1403,18 +1366,41 @@ static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev,
 static int rnbd_client_setup_device(struct rnbd_clt_dev *dev,
 				    struct rnbd_msg_open_rsp *rsp)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= le16_to_cpu(rsp->logical_block_size),
+		.physical_block_size	= le16_to_cpu(rsp->physical_block_size),
+		.io_opt			= dev->sess->max_io_size,
+		.max_hw_sectors		= dev->sess->max_io_size / SECTOR_SIZE,
+		.max_hw_discard_sectors	= le32_to_cpu(rsp->max_discard_sectors),
+		.discard_granularity	= le32_to_cpu(rsp->discard_granularity),
+		.discard_alignment	= le32_to_cpu(rsp->discard_alignment),
+		.max_segments		= dev->sess->max_segments,
+		.virt_boundary_mask	= SZ_4K - 1,
+		.max_write_zeroes_sectors =
+			le32_to_cpu(rsp->max_write_zeroes_sectors),
+	};
 	int idx = dev->clt_device_id;
 
 	dev->size = le64_to_cpu(rsp->nsectors) *
 			le16_to_cpu(rsp->logical_block_size);
 
-	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev);
+	if (rsp->secure_discard) {
+		lim.max_secure_erase_sectors =
+			le32_to_cpu(rsp->max_discard_sectors);
+	}
+
+	dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, &lim, dev);
 	if (IS_ERR(dev->gd))
 		return PTR_ERR(dev->gd);
 	dev->queue = dev->gd->queue;
 	rnbd_init_mq_hw_queues(dev);
 
-	setup_request_queue(dev, rsp);
+	blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, dev->queue);
+	blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, dev->queue);
+	blk_queue_write_cache(dev->queue,
+			      !!(rsp->cache_policy & RNBD_WRITEBACK),
+			      !!(rsp->cache_policy & RNBD_FUA));
+
 	return rnbd_clt_setup_gen_disk(dev, rsp, idx);
 }
 
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index 3a0d5dcec6f2..f6e3a3c4b76c 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -145,7 +145,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess,
 	priv->sess_dev = sess_dev;
 	priv->id = id;
 
-	bio = bio_alloc(sess_dev->bdev_handle->bdev, 1,
+	bio = bio_alloc(file_bdev(sess_dev->bdev_file), 1,
 			rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL);
 	if (bio_add_page(bio, virt_to_page(data), datalen,
 			offset_in_page(data)) != datalen) {
@@ -219,7 +219,7 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id)
 	rnbd_put_sess_dev(sess_dev);
 	wait_for_completion(&dc); /* wait for inflights to drop to zero */
 
-	bdev_release(sess_dev->bdev_handle);
+	fput(sess_dev->bdev_file);
 	mutex_lock(&sess_dev->dev->lock);
 	list_del(&sess_dev->dev_list);
 	if (!sess_dev->readonly)
@@ -534,7 +534,7 @@ rnbd_srv_get_or_create_srv_dev(struct block_device *bdev,
 static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 					struct rnbd_srv_sess_dev *sess_dev)
 {
-	struct block_device *bdev = sess_dev->bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(sess_dev->bdev_file);
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP);
 	rsp->device_id = cpu_to_le32(sess_dev->device_id);
@@ -560,7 +560,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 static struct rnbd_srv_sess_dev *
 rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 			      const struct rnbd_msg_open *open_msg,
-			      struct bdev_handle *handle, bool readonly,
+			      struct file *bdev_file, bool readonly,
 			      struct rnbd_srv_dev *srv_dev)
 {
 	struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess);
@@ -572,7 +572,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess,
 
 	strscpy(sdev->pathname, open_msg->dev_name, sizeof(sdev->pathname));
 
-	sdev->bdev_handle	= handle;
+	sdev->bdev_file		= bdev_file;
 	sdev->sess		= srv_sess;
 	sdev->dev		= srv_dev;
 	sdev->readonly		= readonly;
@@ -678,7 +678,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	struct rnbd_srv_dev *srv_dev;
 	struct rnbd_srv_sess_dev *srv_sess_dev;
 	const struct rnbd_msg_open *open_msg = msg;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	blk_mode_t open_flags = BLK_OPEN_READ;
 	char *full_path;
 	struct rnbd_msg_open_rsp *rsp = data;
@@ -716,15 +716,15 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto reject;
 	}
 
-	bdev_handle = bdev_open_by_path(full_path, open_flags, NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	bdev_file = bdev_file_open_by_path(full_path, open_flags, NULL, NULL);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %pe\n",
-		       full_path, srv_sess->sessname, bdev_handle);
+		       full_path, srv_sess->sessname, bdev_file);
 		goto free_path;
 	}
 
-	srv_dev = rnbd_srv_get_or_create_srv_dev(bdev_handle->bdev, srv_sess,
+	srv_dev = rnbd_srv_get_or_create_srv_dev(file_bdev(bdev_file), srv_sess,
 						  open_msg->access_mode);
 	if (IS_ERR(srv_dev)) {
 		pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %pe\n",
@@ -734,7 +734,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	}
 
 	srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg,
-				bdev_handle,
+				bdev_file,
 				open_msg->access_mode == RNBD_ACCESS_RO,
 				srv_dev);
 	if (IS_ERR(srv_sess_dev)) {
@@ -750,7 +750,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 	 */
 	mutex_lock(&srv_dev->lock);
 	if (!srv_dev->dev_kobj.state_in_sysfs) {
-		ret = rnbd_srv_create_dev_sysfs(srv_dev, bdev_handle->bdev);
+		ret = rnbd_srv_create_dev_sysfs(srv_dev, file_bdev(bdev_file));
 		if (ret) {
 			mutex_unlock(&srv_dev->lock);
 			rnbd_srv_err(srv_sess_dev,
@@ -793,7 +793,7 @@ srv_dev_put:
 	}
 	rnbd_put_srv_dev(srv_dev);
 blkdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 free_path:
 	kfree(full_path);
 reject:
diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h
index 343cc682b617..18d873808b8d 100644
--- a/drivers/block/rnbd/rnbd-srv.h
+++ b/drivers/block/rnbd/rnbd-srv.h
@@ -46,7 +46,7 @@ struct rnbd_srv_dev {
 struct rnbd_srv_sess_dev {
 	/* Entry inside rnbd_srv_dev struct */
 	struct list_head		dev_list;
-	struct bdev_handle		*bdev_handle;
+	struct file			*bdev_file;
 	struct rnbd_srv_session		*sess;
 	struct rnbd_srv_dev		*dev;
 	struct kobject                  kobj;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 7bf4b48e2282..c99dd6698977 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -784,6 +784,14 @@ static const struct blk_mq_ops vdc_mq_ops = {
 
 static int probe_disk(struct vdc_port *port)
 {
+	struct queue_limits lim = {
+		.physical_block_size		= port->vdisk_phys_blksz,
+		.max_hw_sectors			= port->max_xfer_size,
+		/* Each segment in a request is up to an aligned page in size. */
+		.seg_boundary_mask		= PAGE_SIZE - 1,
+		.max_segment_size		= PAGE_SIZE,
+		.max_segments			= port->ring_cookies,
+	};
 	struct request_queue *q;
 	struct gendisk *g;
 	int err;
@@ -824,7 +832,7 @@ static int probe_disk(struct vdc_port *port)
 	if (err)
 		return err;
 
-	g = blk_mq_alloc_disk(&port->tag_set, port);
+	g = blk_mq_alloc_disk(&port->tag_set, &lim, port);
 	if (IS_ERR(g)) {
 		printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n",
 		       port->vio.name);
@@ -835,12 +843,6 @@ static int probe_disk(struct vdc_port *port)
 	port->disk = g;
 	q = g->queue;
 
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-
-	blk_queue_max_segments(q, port->ring_cookies);
-	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
 	g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT;
 	g->minors = 1 << PARTITION_SHIFT;
@@ -872,8 +874,6 @@ static int probe_disk(struct vdc_port *port)
 		}
 	}
 
-	blk_queue_physical_block_size(q, port->vdisk_phys_blksz);
-
 	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
 	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index f85b6af414b4..6731678f3a41 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -820,7 +820,7 @@ static int swim_floppy_init(struct swim_priv *swd)
 			goto exit_put_disks;
 
 		swd->unit[drive].disk =
-			blk_mq_alloc_disk(&swd->unit[drive].tag_set,
+			blk_mq_alloc_disk(&swd->unit[drive].tag_set, NULL,
 					  &swd->unit[drive]);
 		if (IS_ERR(swd->unit[drive].disk)) {
 			blk_mq_free_tag_set(&swd->unit[drive].tag_set);
@@ -916,7 +916,7 @@ out:
 	return ret;
 }
 
-static int swim_remove(struct platform_device *dev)
+static void swim_remove(struct platform_device *dev)
 {
 	struct swim_priv *swd = platform_get_drvdata(dev);
 	int drive;
@@ -937,13 +937,11 @@ static int swim_remove(struct platform_device *dev)
 		release_mem_region(res->start, resource_size(res));
 
 	kfree(swd);
-
-	return 0;
 }
 
 static struct platform_driver swim_driver = {
 	.probe  = swim_probe,
-	.remove = swim_remove,
+	.remove_new = swim_remove,
 	.driver   = {
 		.name	= CARDNAME,
 	},
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index c2bc85826358..a04756ac778e 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1210,7 +1210,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	if (rc)
 		goto out_unregister;
 
-	disk = blk_mq_alloc_disk(&fs->tag_set, fs);
+	disk = blk_mq_alloc_disk(&fs->tag_set, NULL, fs);
 	if (IS_ERR(disk)) {
 		rc = PTR_ERR(disk);
 		goto out_free_tag_set;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 1dfb2e77898b..bea3d5cf8a83 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -246,21 +246,12 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	const struct ublk_param_zoned *p = &ub->params.zoned;
-
-	disk_set_zoned(ub->ub_disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
-	disk_set_max_active_zones(ub->ub_disk, p->max_active_zones);
-	disk_set_max_open_zones(ub->ub_disk, p->max_open_zones);
-	blk_queue_max_zone_append_sectors(ub->ub_disk->queue, p->max_zone_append_sectors);
-
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
-
-	return 0;
 }
 
 /* Based on virtblk_alloc_report_buffer */
@@ -432,9 +423,8 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 	return -EOPNOTSUPP;
 }
 
-static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
+static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
-	return -EOPNOTSUPP;
 }
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
@@ -498,11 +488,6 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 	struct request_queue *q = ub->ub_disk->queue;
 	const struct ublk_param_basic *p = &ub->params.basic;
 
-	blk_queue_logical_block_size(q, 1 << p->logical_bs_shift);
-	blk_queue_physical_block_size(q, 1 << p->physical_bs_shift);
-	blk_queue_io_min(q, 1 << p->io_min_shift);
-	blk_queue_io_opt(q, 1 << p->io_opt_shift);
-
 	blk_queue_write_cache(q, p->attrs & UBLK_ATTR_VOLATILE_CACHE,
 			p->attrs & UBLK_ATTR_FUA);
 	if (p->attrs & UBLK_ATTR_ROTATIONAL)
@@ -510,29 +495,12 @@ static void ublk_dev_param_basic_apply(struct ublk_device *ub)
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	blk_queue_max_hw_sectors(q, p->max_sectors);
-	blk_queue_chunk_sectors(q, p->chunk_sectors);
-	blk_queue_virt_boundary(q, p->virt_boundary_mask);
-
 	if (p->attrs & UBLK_ATTR_READ_ONLY)
 		set_disk_ro(ub->ub_disk, true);
 
 	set_capacity(ub->ub_disk, p->dev_sectors);
 }
 
-static void ublk_dev_param_discard_apply(struct ublk_device *ub)
-{
-	struct request_queue *q = ub->ub_disk->queue;
-	const struct ublk_param_discard *p = &ub->params.discard;
-
-	q->limits.discard_alignment = p->discard_alignment;
-	q->limits.discard_granularity = p->discard_granularity;
-	blk_queue_max_discard_sectors(q, p->max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q,
-			p->max_write_zeroes_sectors);
-	blk_queue_max_discard_segments(q, p->max_discard_segments);
-}
-
 static int ublk_validate_params(const struct ublk_device *ub)
 {
 	/* basic param is the only one which must be set */
@@ -576,20 +544,12 @@ static int ublk_validate_params(const struct ublk_device *ub)
 	return 0;
 }
 
-static int ublk_apply_params(struct ublk_device *ub)
+static void ublk_apply_params(struct ublk_device *ub)
 {
-	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
-		return -EINVAL;
-
 	ublk_dev_param_basic_apply(ub);
 
-	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD)
-		ublk_dev_param_discard_apply(ub);
-
 	if (ub->params.types & UBLK_PARAM_TYPE_ZONED)
-		return ublk_dev_param_zoned_apply(ub);
-
-	return 0;
+		ublk_dev_param_zoned_apply(ub);
 }
 
 static inline bool ublk_support_user_copy(const struct ublk_queue *ubq)
@@ -645,14 +605,16 @@ static inline bool ublk_need_get_data(const struct ublk_queue *ubq)
 	return ubq->flags & UBLK_F_NEED_GET_DATA;
 }
 
-static struct ublk_device *ublk_get_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline struct ublk_device *ublk_get_device(struct ublk_device *ub)
 {
 	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
 		return ub;
 	return NULL;
 }
 
-static void ublk_put_device(struct ublk_device *ub)
+/* Called in slow path only, keep it noinline for trace purpose */
+static noinline void ublk_put_device(struct ublk_device *ub)
 {
 	put_device(&ub->cdev_dev);
 }
@@ -711,7 +673,7 @@ static void ublk_free_disk(struct gendisk *disk)
 	struct ublk_device *ub = disk->private_data;
 
 	clear_bit(UB_STATE_USED, &ub->state);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 }
 
 static void ublk_store_owner_uid_gid(unsigned int *owner_uid,
@@ -2182,7 +2144,7 @@ static void ublk_remove(struct ublk_device *ub)
 	cancel_work_sync(&ub->stop_work);
 	cancel_work_sync(&ub->quiesce_work);
 	cdev_device_del(&ub->cdev, &ub->cdev_dev);
-	put_device(&ub->cdev_dev);
+	ublk_put_device(ub);
 	ublks_added--;
 }
 
@@ -2205,12 +2167,47 @@ static struct ublk_device *ublk_get_device_from_id(int idx)
 static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 {
 	const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe);
+	const struct ublk_param_basic *p = &ub->params.basic;
 	int ublksrv_pid = (int)header->data[0];
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << p->logical_bs_shift,
+		.physical_block_size	= 1 << p->physical_bs_shift,
+		.io_min			= 1 << p->io_min_shift,
+		.io_opt			= 1 << p->io_opt_shift,
+		.max_hw_sectors		= p->max_sectors,
+		.chunk_sectors		= p->chunk_sectors,
+		.virt_boundary_mask	= p->virt_boundary_mask,
+
+	};
 	struct gendisk *disk;
 	int ret = -EINVAL;
 
 	if (ublksrv_pid <= 0)
 		return -EINVAL;
+	if (!(ub->params.types & UBLK_PARAM_TYPE_BASIC))
+		return -EINVAL;
+
+	if (ub->params.types & UBLK_PARAM_TYPE_DISCARD) {
+		const struct ublk_param_discard *pd = &ub->params.discard;
+
+		lim.discard_alignment = pd->discard_alignment;
+		lim.discard_granularity = pd->discard_granularity;
+		lim.max_hw_discard_sectors = pd->max_discard_sectors;
+		lim.max_write_zeroes_sectors = pd->max_write_zeroes_sectors;
+		lim.max_discard_segments = pd->max_discard_segments;
+	}
+
+	if (ub->params.types & UBLK_PARAM_TYPE_ZONED) {
+		const struct ublk_param_zoned *p = &ub->params.zoned;
+
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+			return -EOPNOTSUPP;
+
+		lim.zoned = true;
+		lim.max_active_zones = p->max_active_zones;
+		lim.max_open_zones =  p->max_open_zones;
+		lim.max_zone_append_sectors = p->max_zone_append_sectors;
+	}
 
 	if (wait_for_completion_interruptible(&ub->completion) != 0)
 		return -EINTR;
@@ -2222,7 +2219,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		goto out_unlock;
 	}
 
-	disk = blk_mq_alloc_disk(&ub->tag_set, NULL);
+	disk = blk_mq_alloc_disk(&ub->tag_set, &lim, NULL);
 	if (IS_ERR(disk)) {
 		ret = PTR_ERR(disk);
 		goto out_unlock;
@@ -2234,15 +2231,13 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 	ub->dev_info.ublksrv_pid = ublksrv_pid;
 	ub->ub_disk = disk;
 
-	ret = ublk_apply_params(ub);
-	if (ret)
-		goto out_put_disk;
+	ublk_apply_params(ub);
 
 	/* don't probe partitions if any one ubq daemon is un-trusted */
 	if (ub->nr_privileged_daemon != ub->nr_queues_ready)
 		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 
-	get_device(&ub->cdev_dev);
+	ublk_get_device(ub);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
 
 	if (ublk_dev_is_zoned(ub)) {
@@ -2262,7 +2257,6 @@ out_put_cdev:
 		ub->dev_info.state = UBLK_S_DEV_DEAD;
 		ublk_put_device(ub);
 	}
-out_put_disk:
 	if (ret)
 		put_disk(disk);
 out_unlock:
@@ -2474,7 +2468,7 @@ static inline bool ublk_idr_freed(int id)
 	return ptr == NULL;
 }
 
-static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
+static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
 {
 	struct ublk_device *ub = *p_ub;
 	int idx = ub->ub_number;
@@ -2508,7 +2502,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub)
 	 * - the device number is freed already, we will not find this
 	 *   device via ublk_get_device_from_id()
 	 */
-	if (wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
+	if (wait && wait_event_interruptible(ublk_idr_wq, ublk_idr_freed(idx)))
 		return -EINTR;
 	return 0;
 }
@@ -2907,7 +2901,10 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_add_dev(cmd);
 		break;
 	case UBLK_CMD_DEL_DEV:
-		ret = ublk_ctrl_del_dev(&ub);
+		ret = ublk_ctrl_del_dev(&ub, true);
+		break;
+	case UBLK_U_CMD_DEL_DEV_ASYNC:
+		ret = ublk_ctrl_del_dev(&ub, false);
 		break;
 	case UBLK_CMD_GET_QUEUE_AFFINITY:
 		ret = ublk_ctrl_get_queue_affinity(ub, cmd);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5bf98fd6a651..42dea7601d87 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -720,25 +720,24 @@ fail_report:
 	return ret;
 }
 
-static int virtblk_probe_zoned_device(struct virtio_device *vdev,
-				       struct virtio_blk *vblk,
-				       struct request_queue *q)
+static int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, wg;
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	lim->zoned = true;
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_open_zones, &v);
-	disk_set_max_open_zones(vblk->disk, v);
+	lim->max_open_zones = v;
 	dev_dbg(&vdev->dev, "max open zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
 		     zoned.max_active_zones, &v);
-	disk_set_max_active_zones(vblk->disk, v);
+	lim->max_active_zones = v;
 	dev_dbg(&vdev->dev, "max active zones = %u\n", v);
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -747,8 +746,8 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 		dev_warn(&vdev->dev, "zero write granularity reported\n");
 		return -ENODEV;
 	}
-	blk_queue_physical_block_size(q, wg);
-	blk_queue_io_min(q, wg);
+	lim->physical_block_size = wg;
+	lim->io_min = wg;
 
 	dev_dbg(&vdev->dev, "write granularity = %u\n", wg);
 
@@ -764,13 +763,13 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			vblk->zone_sectors);
 		return -ENODEV;
 	}
-	blk_queue_chunk_sectors(q, vblk->zone_sectors);
+	lim->chunk_sectors = vblk->zone_sectors;
 	dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors);
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		dev_warn(&vblk->vdev->dev,
 			 "ignoring negotiated F_DISCARD for zoned device\n");
-		blk_queue_max_discard_sectors(q, 0);
+		lim->max_hw_discard_sectors = 0;
 	}
 
 	virtio_cread(vdev, struct virtio_blk_config,
@@ -785,25 +784,21 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 			wg, v);
 		return -ENODEV;
 	}
-	blk_queue_max_zone_append_sectors(q, v);
+	lim->max_zone_append_sectors = v;
 	dev_dbg(&vdev->dev, "max append sectors = %u\n", v);
 
-	return blk_revalidate_disk_zones(vblk->disk, NULL);
+	return 0;
 }
-
 #else
-
 /*
- * Zoned block device support is not configured in this kernel.
- * Host-managed zoned devices can't be supported, but others are
- * good to go as regular block devices.
+ * Zoned block device support is not configured in this kernel, host-managed
+ * zoned devices can't be supported.
  */
 #define virtblk_report_zones       NULL
-
-static inline int virtblk_probe_zoned_device(struct virtio_device *vdev,
-			struct virtio_blk *vblk, struct request_queue *q)
+static inline int virtblk_read_zoned_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	dev_err(&vdev->dev,
+	dev_err(&vblk->vdev->dev,
 		"virtio_blk: zoned devices are not supported");
 	return -EOPNOTSUPP;
 }
@@ -1248,31 +1243,17 @@ static const struct blk_mq_ops virtio_mq_ops = {
 static unsigned int virtblk_queue_depth;
 module_param_named(queue_depth, virtblk_queue_depth, uint, 0444);
 
-static int virtblk_probe(struct virtio_device *vdev)
+static int virtblk_read_limits(struct virtio_blk *vblk,
+		struct queue_limits *lim)
 {
-	struct virtio_blk *vblk;
-	struct request_queue *q;
-	int err, index;
-
+	struct virtio_device *vdev = vblk->vdev;
 	u32 v, blk_size, max_size, sg_elems, opt_io_size;
 	u32 max_discard_segs = 0;
 	u32 discard_granularity = 0;
 	u16 min_io_size;
 	u8 physical_block_exp, alignment_offset;
-	unsigned int queue_depth;
 	size_t max_dma_size;
-
-	if (!vdev->config->get) {
-		dev_err(&vdev->dev, "%s failure: config access disabled\n",
-			__func__);
-		return -EINVAL;
-	}
-
-	err = ida_alloc_range(&vd_index_ida, 0,
-			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
-	if (err < 0)
-		goto out;
-	index = err;
+	int err;
 
 	/* We need to know how many segments before we allocate. */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_SEG_MAX,
@@ -1286,78 +1267,11 @@ static int virtblk_probe(struct virtio_device *vdev)
 	/* Prevent integer overflows and honor max vq size */
 	sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2);
 
-	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
-	if (!vblk) {
-		err = -ENOMEM;
-		goto out_free_index;
-	}
-
-	mutex_init(&vblk->vdev_mutex);
-
-	vblk->vdev = vdev;
-
-	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
-
-	err = init_vq(vblk);
-	if (err)
-		goto out_free_vblk;
-
-	/* Default queue sizing is to fill the ring. */
-	if (!virtblk_queue_depth) {
-		queue_depth = vblk->vqs[0].vq->num_free;
-		/* ... but without indirect descs, we use 2 descs per req */
-		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
-			queue_depth /= 2;
-	} else {
-		queue_depth = virtblk_queue_depth;
-	}
-
-	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
-	vblk->tag_set.ops = &virtio_mq_ops;
-	vblk->tag_set.queue_depth = queue_depth;
-	vblk->tag_set.numa_node = NUMA_NO_NODE;
-	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
-	vblk->tag_set.cmd_size =
-		sizeof(struct virtblk_req) +
-		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
-	vblk->tag_set.driver_data = vblk;
-	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
-	vblk->tag_set.nr_maps = 1;
-	if (vblk->io_queues[HCTX_TYPE_POLL])
-		vblk->tag_set.nr_maps = 3;
-
-	err = blk_mq_alloc_tag_set(&vblk->tag_set);
-	if (err)
-		goto out_free_vq;
-
-	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk);
-	if (IS_ERR(vblk->disk)) {
-		err = PTR_ERR(vblk->disk);
-		goto out_free_tags;
-	}
-	q = vblk->disk->queue;
-
-	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
-
-	vblk->disk->major = major;
-	vblk->disk->first_minor = index_to_minor(index);
-	vblk->disk->minors = 1 << PART_BITS;
-	vblk->disk->private_data = vblk;
-	vblk->disk->fops = &virtblk_fops;
-	vblk->index = index;
-
-	/* configure queue flush support */
-	virtblk_update_cache_mode(vdev);
-
-	/* If disk is read-only in the host, the guest should obey */
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
-		set_disk_ro(vblk->disk, 1);
-
 	/* We can handle whatever the host told us to handle. */
-	blk_queue_max_segments(q, sg_elems);
+	lim->max_segments = sg_elems;
 
 	/* No real sector limit. */
-	blk_queue_max_hw_sectors(q, UINT_MAX);
+	lim->max_hw_sectors = UINT_MAX;
 
 	max_dma_size = virtio_max_dma_size(vdev);
 	max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size;
@@ -1369,7 +1283,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (!err)
 		max_size = min(max_size, v);
 
-	blk_queue_max_segment_size(q, max_size);
+	lim->max_segment_size = max_size;
 
 	/* Host can optionally specify the block size of the device */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
@@ -1381,38 +1295,37 @@ static int virtblk_probe(struct virtio_device *vdev)
 			dev_err(&vdev->dev,
 				"virtio_blk: invalid block size: 0x%x\n",
 				blk_size);
-			goto out_cleanup_disk;
+			return err;
 		}
 
-		blk_queue_logical_block_size(q, blk_size);
+		lim->logical_block_size = blk_size;
 	} else
-		blk_size = queue_logical_block_size(q);
+		blk_size = lim->logical_block_size;
 
 	/* Use topology information if available */
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, physical_block_exp,
 				   &physical_block_exp);
 	if (!err && physical_block_exp)
-		blk_queue_physical_block_size(q,
-				blk_size * (1 << physical_block_exp));
+		lim->physical_block_size = blk_size * (1 << physical_block_exp);
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, alignment_offset,
 				   &alignment_offset);
 	if (!err && alignment_offset)
-		blk_queue_alignment_offset(q, blk_size * alignment_offset);
+		lim->alignment_offset = blk_size * alignment_offset;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, min_io_size,
 				   &min_io_size);
 	if (!err && min_io_size)
-		blk_queue_io_min(q, blk_size * min_io_size);
+		lim->io_min = blk_size * min_io_size;
 
 	err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY,
 				   struct virtio_blk_config, opt_io_size,
 				   &opt_io_size);
 	if (!err && opt_io_size)
-		blk_queue_io_opt(q, blk_size * opt_io_size);
+		lim->io_opt = blk_size * opt_io_size;
 
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) {
 		virtio_cread(vdev, struct virtio_blk_config,
@@ -1420,7 +1333,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_discard_sectors, &v);
-		blk_queue_max_discard_sectors(q, v ? v : UINT_MAX);
+		lim->max_hw_discard_sectors = v ? v : UINT_MAX;
 
 		virtio_cread(vdev, struct virtio_blk_config, max_discard_seg,
 			     &max_discard_segs);
@@ -1429,7 +1342,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) {
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_write_zeroes_sectors, &v);
-		blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX);
+		lim->max_write_zeroes_sectors = v ? v : UINT_MAX;
 	}
 
 	/* The discard and secure erase limits are combined since the Linux
@@ -1455,8 +1368,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: secure_erase_sector_alignment can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
 		discard_granularity = min_not_zero(discard_granularity, v);
@@ -1470,11 +1382,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: max_secure_erase_sectors can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
-		blk_queue_max_secure_erase_sectors(q, v);
+		lim->max_secure_erase_sectors = v;
 
 		virtio_cread(vdev, struct virtio_blk_config,
 			     max_secure_erase_seg, &v);
@@ -1485,8 +1396,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!v) {
 			dev_err(&vdev->dev,
 				"virtio_blk: max_secure_erase_seg can't be 0\n");
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			return -EINVAL;
 		}
 
 		max_discard_segs = min_not_zero(max_discard_segs, v);
@@ -1502,45 +1412,142 @@ static int virtblk_probe(struct virtio_device *vdev)
 		if (!max_discard_segs)
 			max_discard_segs = sg_elems;
 
-		blk_queue_max_discard_segments(q,
-					       min(max_discard_segs, MAX_DISCARD_SEGMENTS));
+		lim->max_discard_segments =
+			min(max_discard_segs, MAX_DISCARD_SEGMENTS);
 
 		if (discard_granularity)
-			q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT;
+			lim->discard_granularity =
+				discard_granularity << SECTOR_SHIFT;
 		else
-			q->limits.discard_granularity = blk_size;
+			lim->discard_granularity = blk_size;
 	}
 
-	virtblk_update_capacity(vblk, false);
-	virtio_device_ready(vdev);
-
-	/*
-	 * All steps that follow use the VQs therefore they need to be
-	 * placed after the virtio_device_ready() call above.
-	 */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_ZONED)) {
 		u8 model;
 
-		virtio_cread(vdev, struct virtio_blk_config, zoned.model,
-				&model);
+		virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model);
 		switch (model) {
 		case VIRTIO_BLK_Z_NONE:
 		case VIRTIO_BLK_Z_HA:
-			/* Present the host-aware device as non-zoned */
-			break;
+			/* treat host-aware devices as non-zoned */
+			return 0;
 		case VIRTIO_BLK_Z_HM:
-			err = virtblk_probe_zoned_device(vdev, vblk, q);
+			err = virtblk_read_zoned_limits(vblk, lim);
 			if (err)
-				goto out_cleanup_disk;
+				return err;
 			break;
 		default:
-			dev_err(&vdev->dev, "unsupported zone model %d\n",
-				model);
-			err = -EINVAL;
-			goto out_cleanup_disk;
+			dev_err(&vdev->dev, "unsupported zone model %d\n", model);
+			return -EINVAL;
 		}
 	}
 
+	return 0;
+}
+
+static int virtblk_probe(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk;
+	struct queue_limits lim = { };
+	int err, index;
+	unsigned int queue_depth;
+
+	if (!vdev->config->get) {
+		dev_err(&vdev->dev, "%s failure: config access disabled\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	err = ida_alloc_range(&vd_index_ida, 0,
+			      minor_to_index(1 << MINORBITS) - 1, GFP_KERNEL);
+	if (err < 0)
+		goto out;
+	index = err;
+
+	vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL);
+	if (!vblk) {
+		err = -ENOMEM;
+		goto out_free_index;
+	}
+
+	mutex_init(&vblk->vdev_mutex);
+
+	vblk->vdev = vdev;
+
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
+
+	err = init_vq(vblk);
+	if (err)
+		goto out_free_vblk;
+
+	/* Default queue sizing is to fill the ring. */
+	if (!virtblk_queue_depth) {
+		queue_depth = vblk->vqs[0].vq->num_free;
+		/* ... but without indirect descs, we use 2 descs per req */
+		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+			queue_depth /= 2;
+	} else {
+		queue_depth = virtblk_queue_depth;
+	}
+
+	memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
+	vblk->tag_set.ops = &virtio_mq_ops;
+	vblk->tag_set.queue_depth = queue_depth;
+	vblk->tag_set.numa_node = NUMA_NO_NODE;
+	vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	vblk->tag_set.cmd_size =
+		sizeof(struct virtblk_req) +
+		sizeof(struct scatterlist) * VIRTIO_BLK_INLINE_SG_CNT;
+	vblk->tag_set.driver_data = vblk;
+	vblk->tag_set.nr_hw_queues = vblk->num_vqs;
+	vblk->tag_set.nr_maps = 1;
+	if (vblk->io_queues[HCTX_TYPE_POLL])
+		vblk->tag_set.nr_maps = 3;
+
+	err = blk_mq_alloc_tag_set(&vblk->tag_set);
+	if (err)
+		goto out_free_vq;
+
+	err = virtblk_read_limits(vblk, &lim);
+	if (err)
+		goto out_free_tags;
+
+	vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, &lim, vblk);
+	if (IS_ERR(vblk->disk)) {
+		err = PTR_ERR(vblk->disk);
+		goto out_free_tags;
+	}
+
+	virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN);
+
+	vblk->disk->major = major;
+	vblk->disk->first_minor = index_to_minor(index);
+	vblk->disk->minors = 1 << PART_BITS;
+	vblk->disk->private_data = vblk;
+	vblk->disk->fops = &virtblk_fops;
+	vblk->index = index;
+
+	/* configure queue flush support */
+	virtblk_update_cache_mode(vdev);
+
+	/* If disk is read-only in the host, the guest should obey */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
+		set_disk_ro(vblk->disk, 1);
+
+	virtblk_update_capacity(vblk, false);
+	virtio_device_ready(vdev);
+
+	/*
+	 * All steps that follow use the VQs therefore they need to be
+	 * placed after the virtio_device_ready() call above.
+	 */
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
+		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
+		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		if (err)
+			goto out_cleanup_disk;
+	}
+
 	err = device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups);
 	if (err)
 		goto out_cleanup_disk;
@@ -1593,14 +1600,15 @@ static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	/* Ensure no requests in virtqueues before deleting vqs. */
+	blk_mq_freeze_queue(vblk->disk->queue);
+
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
-	blk_mq_quiesce_queue(vblk->disk->queue);
-
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
 
@@ -1618,7 +1626,7 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	blk_mq_unquiesce_queue(vblk->disk->queue);
+	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4defd7f387c7..944576d582fb 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -465,7 +465,7 @@ static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
 	}
 
 	req->dev  = vbd->pdevice;
-	req->bdev = vbd->bdev_handle->bdev;
+	req->bdev = file_bdev(vbd->bdev_file);
 	rc = 0;
 
  out:
@@ -969,7 +969,7 @@ static int dispatch_discard_io(struct xen_blkif_ring *ring,
 	int err = 0;
 	int status = BLKIF_RSP_OKAY;
 	struct xen_blkif *blkif = ring->blkif;
-	struct block_device *bdev = blkif->vbd.bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(blkif->vbd.bdev_file);
 	struct phys_req preq;
 
 	xen_blkif_get(blkif);
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 1432c83183d0..b427d54bc120 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -221,7 +221,7 @@ struct xen_vbd {
 	unsigned char		type;
 	/* phys device that this vbd maps to. */
 	u32			pdevice;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 	/* Cached size parameter. */
 	sector_t		size;
 	unsigned int		flush_support:1;
@@ -360,7 +360,7 @@ struct pending_req {
 };
 
 
-#define vbd_sz(_v)	bdev_nr_sectors((_v)->bdev_handle->bdev)
+#define vbd_sz(_v)	bdev_nr_sectors(file_bdev((_v)->bdev_file))
 
 #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
 #define xen_blkif_put(_b)				\
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index e34219ea2b05..0621878940ae 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -81,7 +81,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 	int i;
 
 	/* Not ready to connect? */
-	if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_handle)
+	if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev_file)
 		return;
 
 	/* Already connected? */
@@ -99,13 +99,12 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
 		return;
 	}
 
-	err = sync_blockdev(blkif->vbd.bdev_handle->bdev);
+	err = sync_blockdev(file_bdev(blkif->vbd.bdev_file));
 	if (err) {
 		xenbus_dev_error(blkif->be->dev, err, "block flush");
 		return;
 	}
-	invalidate_inode_pages2(
-			blkif->vbd.bdev_handle->bdev->bd_inode->i_mapping);
+	invalidate_inode_pages2(blkif->vbd.bdev_file->f_mapping);
 
 	for (i = 0; i < blkif->nr_rings; i++) {
 		ring = &blkif->rings[i];
@@ -473,9 +472,9 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev)
 
 static void xen_vbd_free(struct xen_vbd *vbd)
 {
-	if (vbd->bdev_handle)
-		bdev_release(vbd->bdev_handle);
-	vbd->bdev_handle = NULL;
+	if (vbd->bdev_file)
+		fput(vbd->bdev_file);
+	vbd->bdev_file = NULL;
 }
 
 static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
@@ -483,7 +482,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 			  int cdrom)
 {
 	struct xen_vbd *vbd;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	vbd = &blkif->vbd;
 	vbd->handle   = handle;
@@ -492,17 +491,17 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 
 	vbd->pdevice  = MKDEV(major, minor);
 
-	bdev_handle = bdev_open_by_dev(vbd->pdevice, vbd->readonly ?
+	bdev_file = bdev_file_open_by_dev(vbd->pdevice, vbd->readonly ?
 				 BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL);
 
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_warn("xen_vbd_create: device %08x could not be opened\n",
 			vbd->pdevice);
 		return -ENOENT;
 	}
 
-	vbd->bdev_handle = bdev_handle;
-	if (vbd->bdev_handle->bdev->bd_disk == NULL) {
+	vbd->bdev_file = bdev_file;
+	if (file_bdev(vbd->bdev_file)->bd_disk == NULL) {
 		pr_warn("xen_vbd_create: device %08x doesn't exist\n",
 			vbd->pdevice);
 		xen_vbd_free(vbd);
@@ -510,14 +509,14 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	}
 	vbd->size = vbd_sz(vbd);
 
-	if (cdrom || disk_to_cdi(vbd->bdev_handle->bdev->bd_disk))
+	if (cdrom || disk_to_cdi(file_bdev(vbd->bdev_file)->bd_disk))
 		vbd->type |= VDISK_CDROM;
-	if (vbd->bdev_handle->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
+	if (file_bdev(vbd->bdev_file)->bd_disk->flags & GENHD_FL_REMOVABLE)
 		vbd->type |= VDISK_REMOVABLE;
 
-	if (bdev_write_cache(bdev_handle->bdev))
+	if (bdev_write_cache(file_bdev(bdev_file)))
 		vbd->flush_support = true;
-	if (bdev_max_secure_erase_sectors(bdev_handle->bdev))
+	if (bdev_max_secure_erase_sectors(file_bdev(bdev_file)))
 		vbd->discard_secure = true;
 
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
@@ -570,7 +569,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	struct xen_blkif *blkif = be->blkif;
 	int err;
 	int state = 0;
-	struct block_device *bdev = be->blkif->vbd.bdev_handle->bdev;
+	struct block_device *bdev = file_bdev(be->blkif->vbd.bdev_file);
 
 	if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1))
 		return;
@@ -932,7 +931,7 @@ again:
 	}
 	err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu",
 			    (unsigned long)bdev_logical_block_size(
-					be->blkif->vbd.bdev_handle->bdev));
+					file_bdev(be->blkif->vbd.bdev_file)));
 	if (err) {
 		xenbus_dev_fatal(dev, err, "writing %s/sector-size",
 				 dev->nodename);
@@ -940,7 +939,7 @@ again:
 	}
 	err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u",
 			    bdev_physical_block_size(
-					be->blkif->vbd.bdev_handle->bdev));
+					file_bdev(be->blkif->vbd.bdev_file)));
 	if (err)
 		xenbus_dev_error(dev, err, "writing %s/physical-sector-size",
 				 dev->nodename);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 434fab306777..fd7c0ff2139c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -941,39 +941,35 @@ static const struct blk_mq_ops blkfront_mq_ops = {
 	.complete = blkif_complete_rq,
 };
 
-static void blkif_set_queue_limits(struct blkfront_info *info)
+static void blkif_set_queue_limits(const struct blkfront_info *info,
+		struct queue_limits *lim)
 {
-	struct request_queue *rq = info->rq;
-	struct gendisk *gd = info->gd;
 	unsigned int segments = info->max_indirect_segments ? :
 				BLKIF_MAX_SEGMENTS_PER_REQUEST;
 
-	blk_queue_flag_set(QUEUE_FLAG_VIRT, rq);
-
 	if (info->feature_discard) {
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity ?:
-						 info->physical_sector_size;
-		rq->limits.discard_alignment = info->discard_alignment;
+		lim->max_hw_discard_sectors = UINT_MAX;
+		if (info->discard_granularity)
+			lim->discard_granularity = info->discard_granularity;
+		lim->discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			blk_queue_max_secure_erase_sectors(rq,
-							   get_capacity(gd));
+			lim->max_secure_erase_sectors = UINT_MAX;
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, info->sector_size);
-	blk_queue_physical_block_size(rq, info->physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+	lim->logical_block_size = info->sector_size;
+	lim->physical_block_size = info->physical_sector_size;
+	lim->max_hw_sectors = (segments * XEN_PAGE_SIZE) / 512;
 
 	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
+	lim->seg_boundary_mask = PAGE_SIZE - 1;
+	lim->max_segment_size = PAGE_SIZE;
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+	lim->max_segments = segments / GRANTS_PER_PSEG;
 
 	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
+	lim->dma_alignment = 511;
 }
 
 static const char *flush_info(struct blkfront_info *info)
@@ -1070,6 +1066,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		struct blkfront_info *info, u16 sector_size,
 		unsigned int physical_sector_size)
 {
+	struct queue_limits lim = {};
 	struct gendisk *gd;
 	int nr_minors = 1;
 	int err;
@@ -1136,11 +1133,13 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (err)
 		goto out_release_minors;
 
-	gd = blk_mq_alloc_disk(&info->tag_set, info);
+	blkif_set_queue_limits(info, &lim);
+	gd = blk_mq_alloc_disk(&info->tag_set, &lim, info);
 	if (IS_ERR(gd)) {
 		err = PTR_ERR(gd);
 		goto out_free_tag_set;
 	}
+	blk_queue_flag_set(QUEUE_FLAG_VIRT, gd->queue);
 
 	strcpy(gd->disk_name, DEV_NAME);
 	ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset);
@@ -1162,7 +1161,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	info->gd = gd;
 	info->sector_size = sector_size;
 	info->physical_sector_size = physical_sector_size;
-	blkif_set_queue_limits(info);
 
 	xlvbd_flush(info);
 
@@ -2006,18 +2004,19 @@ static int blkfront_probe(struct xenbus_device *dev,
 
 static int blkif_recover(struct blkfront_info *info)
 {
+	struct queue_limits lim;
 	unsigned int r_index;
 	struct request *req, *n;
 	int rc;
 	struct bio *bio;
-	unsigned int segs;
 	struct blkfront_ring_info *rinfo;
 
+	lim = queue_limits_start_update(info->rq);
 	blkfront_gather_backend_features(info);
-	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
-	blkif_set_queue_limits(info);
-	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
+	blkif_set_queue_limits(info, &lim);
+	rc = queue_limits_commit_update(info->rq, &lim);
+	if (rc)
+		return rc;
 
 	for_each_rinfo(info, rinfo, r_index) {
 		rc = blkfront_setup_indirect(rinfo);
@@ -2037,7 +2036,9 @@ static int blkif_recover(struct blkfront_info *info)
 	list_for_each_entry_safe(req, n, &info->requests, queuelist) {
 		/* Requeue pending requests (flush or discard) */
 		list_del_init(&req->queuelist);
-		BUG_ON(req->nr_phys_segments > segs);
+		BUG_ON(req->nr_phys_segments >
+		       (info->max_indirect_segments ? :
+			BLKIF_MAX_SEGMENTS_PER_REQUEST));
 		blk_mq_requeue_request(req, false);
 	}
 	blk_mq_start_stopped_hw_queues(info->rq, true);
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 11493167b0a8..7c5f4e4d9b50 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -318,7 +318,7 @@ static int z2ram_register_disk(int minor)
 	struct gendisk *disk;
 	int err;
 
-	disk = blk_mq_alloc_disk(&tag_set, NULL);
+	disk = blk_mq_alloc_disk(&tag_set, NULL, NULL);
 	if (IS_ERR(disk))
 		return PTR_ERR(disk);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 6772e0c654fa..da7a20fa6152 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -426,11 +426,11 @@ static void reset_bdev(struct zram *zram)
 	if (!zram->backing_dev)
 		return;
 
-	bdev_release(zram->bdev_handle);
+	fput(zram->bdev_file);
 	/* hope filp_close flush all of IO */
 	filp_close(zram->backing_dev, NULL);
 	zram->backing_dev = NULL;
-	zram->bdev_handle = NULL;
+	zram->bdev_file = NULL;
 	zram->disk->fops = &zram_devops;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
@@ -476,7 +476,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	struct address_space *mapping;
 	unsigned int bitmap_sz;
 	unsigned long nr_pages, *bitmap = NULL;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int err;
 	struct zram *zram = dev_to_zram(dev);
 
@@ -513,11 +513,11 @@ static ssize_t backing_dev_store(struct device *dev,
 		goto out;
 	}
 
-	bdev_handle = bdev_open_by_dev(inode->i_rdev,
+	bdev_file = bdev_file_open_by_dev(inode->i_rdev,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, zram, NULL);
-	if (IS_ERR(bdev_handle)) {
-		err = PTR_ERR(bdev_handle);
-		bdev_handle = NULL;
+	if (IS_ERR(bdev_file)) {
+		err = PTR_ERR(bdev_file);
+		bdev_file = NULL;
 		goto out;
 	}
 
@@ -531,7 +531,7 @@ static ssize_t backing_dev_store(struct device *dev,
 
 	reset_bdev(zram);
 
-	zram->bdev_handle = bdev_handle;
+	zram->bdev_file = bdev_file;
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
@@ -544,8 +544,8 @@ static ssize_t backing_dev_store(struct device *dev,
 out:
 	kvfree(bitmap);
 
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 
 	if (backing_dev)
 		filp_close(backing_dev, NULL);
@@ -587,7 +587,7 @@ static void read_from_bdev_async(struct zram *zram, struct page *page,
 {
 	struct bio *bio;
 
-	bio = bio_alloc(zram->bdev_handle->bdev, 1, parent->bi_opf, GFP_NOIO);
+	bio = bio_alloc(file_bdev(zram->bdev_file), 1, parent->bi_opf, GFP_NOIO);
 	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
 	__bio_add_page(bio, page, PAGE_SIZE, 0);
 	bio_chain(bio, parent);
@@ -703,7 +703,7 @@ static ssize_t writeback_store(struct device *dev,
 			continue;
 		}
 
-		bio_init(&bio, zram->bdev_handle->bdev, &bio_vec, 1,
+		bio_init(&bio, file_bdev(zram->bdev_file), &bio_vec, 1,
 			 REQ_OP_WRITE | REQ_SYNC);
 		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
 		__bio_add_page(&bio, page, PAGE_SIZE, 0);
@@ -785,7 +785,7 @@ static void zram_sync_read(struct work_struct *work)
 	struct bio_vec bv;
 	struct bio bio;
 
-	bio_init(&bio, zw->zram->bdev_handle->bdev, &bv, 1, REQ_OP_READ);
+	bio_init(&bio, file_bdev(zw->zram->bdev_file), &bv, 1, REQ_OP_READ);
 	bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9);
 	__bio_add_page(&bio, zw->page, PAGE_SIZE, 0);
 	zw->error = submit_bio_wait(&bio);
@@ -2177,6 +2177,28 @@ ATTRIBUTE_GROUPS(zram_disk);
  */
 static int zram_add(void)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= ZRAM_LOGICAL_BLOCK_SIZE,
+		/*
+		 * To ensure that we always get PAGE_SIZE aligned and
+		 * n*PAGE_SIZED sized I/O requests.
+		 */
+		.physical_block_size		= PAGE_SIZE,
+		.io_min				= PAGE_SIZE,
+		.io_opt				= PAGE_SIZE,
+		.max_hw_discard_sectors		= UINT_MAX,
+		/*
+		 * zram_bio_discard() will clear all logical blocks if logical
+		 * block size is identical with physical block size(PAGE_SIZE).
+		 * But if it is different, we will skip discarding some parts of
+		 * logical blocks in the part of the request range which isn't
+		 * aligned to physical block size.  So we can't ensure that all
+		 * discarded logical blocks are zeroed.
+		 */
+#if ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE
+		.max_write_zeroes_sectors	= UINT_MAX,
+#endif
+	};
 	struct zram *zram;
 	int ret, device_id;
 
@@ -2195,11 +2217,11 @@ static int zram_add(void)
 #endif
 
 	/* gendisk structure */
-	zram->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!zram->disk) {
+	zram->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(zram->disk)) {
 		pr_err("Error allocating disk structure for device %d\n",
 			device_id);
-		ret = -ENOMEM;
+		ret = PTR_ERR(zram->disk);
 		goto out_free_idr;
 	}
 
@@ -2216,29 +2238,6 @@ static int zram_add(void)
 	/* zram devices sort of resembles non-rotational disks */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
-
-	/*
-	 * To ensure that we always get PAGE_SIZE aligned
-	 * and n*PAGE_SIZED sized I/O requests.
-	 */
-	blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
-	blk_queue_logical_block_size(zram->disk->queue,
-					ZRAM_LOGICAL_BLOCK_SIZE);
-	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
-	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
-
-	/*
-	 * zram_bio_discard() will clear all logical blocks if logical block
-	 * size is identical with physical block size(PAGE_SIZE). But if it is
-	 * different, we will skip discarding some parts of logical blocks in
-	 * the part of the request range which isn't aligned to physical block
-	 * size.  So we can't ensure that all discarded logical blocks are
-	 * zeroed.
-	 */
-	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
-		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
-
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	ret = device_add_disk(NULL, zram->disk, zram_disk_groups);
 	if (ret)
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 3b94d12f41b4..37bf29f34d26 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -132,7 +132,7 @@ struct zram {
 	spinlock_t wb_limit_lock;
 	bool wb_limit_enable;
 	u64 bd_wb_limit;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 #endif
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index fdb0fae88d1c..b40b32fa7f1c 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -152,7 +152,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev)
 	bt_dev_dbg(hdev, "QCA Patch config");
 
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd),
-				cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
+				cmd, 0, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err);
diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c
index a61757835695..9a7243d5db71 100644
--- a/drivers/bluetooth/hci_bcm4377.c
+++ b/drivers/bluetooth/hci_bcm4377.c
@@ -1417,7 +1417,7 @@ static int bcm4377_check_bdaddr(struct bcm4377_data *bcm4377)
 
 	bda = (struct hci_rp_read_bd_addr *)skb->data;
 	if (!bcm4377_is_valid_bdaddr(bcm4377, &bda->bdaddr))
-		set_bit(HCI_QUIRK_INVALID_BDADDR, &bcm4377->hdev->quirks);
+		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &bcm4377->hdev->quirks);
 
 	kfree_skb(skb);
 	return 0;
@@ -2368,7 +2368,6 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	hdev->set_bdaddr = bcm4377_hci_set_bdaddr;
 	hdev->setup = bcm4377_hci_setup;
 
-	set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
 	if (bcm4377->hw->broken_mws_transport_config)
 		set_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &hdev->quirks);
 	if (bcm4377->hw->broken_ext_scan)
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 94b8c406f0c0..edd2a81b4d5e 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -7,6 +7,7 @@
  *
  *  Copyright (C) 2007 Texas Instruments, Inc.
  *  Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
+ *  Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  *
  *  Acknowledgements:
  *  This file is based on hci_ll.c, which was...
@@ -1806,13 +1807,12 @@ static int qca_power_on(struct hci_dev *hdev)
 
 static void hci_coredump_qca(struct hci_dev *hdev)
 {
+	int err;
 	static const u8 param[] = { 0x26 };
-	struct sk_buff *skb;
 
-	skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT);
-	if (IS_ERR(skb))
-		bt_dev_err(hdev, "%s: trigger crash failed (%ld)", __func__, PTR_ERR(skb));
-	kfree_skb(skb);
+	err = __hci_cmd_send(hdev, 0xfc0c, 1, param);
+	if (err < 0)
+		bt_dev_err(hdev, "%s: trigger crash failed (%d)", __func__, err);
 }
 
 static int qca_get_data_path_id(struct hci_dev *hdev, __u8 *data_path_id)
@@ -1904,7 +1904,17 @@ retry:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
 	case QCA_WCN7850:
-		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
+		/* Set BDA quirk bit for reading BDA value from fwnode property
+		 * only if that property exist in DT.
+		 */
+		if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) {
+			set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+			bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later");
+		} else {
+			bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA");
+		}
+
 		hci_set_aosp_capable(hdev);
 
 		ret = qca_read_soc_version(hdev, &ver, soc_type);
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index e6742998f372..d5e7fa9173a1 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -186,11 +186,12 @@ config SUNXI_RSB
 
 config TEGRA_ACONNECT
 	tristate "Tegra ACONNECT Bus Driver"
-	depends on ARCH_TEGRA_210_SOC
+	depends on ARCH_TEGRA
 	depends on OF && PM
 	help
 	  Driver for the Tegra ACONNECT bus which is used to interface with
-	  the devices inside the Audio Processing Engine (APE) for Tegra210.
+	  the devices inside the Audio Processing Engine (APE) for
+	  Tegra210 and later.
 
 config TEGRA_GMI
 	tristate "Tegra Generic Memory Interface bus driver"
diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c
index 6b5da73c8541..837bf9d51c6e 100644
--- a/drivers/bus/imx-weim.c
+++ b/drivers/bus/imx-weim.c
@@ -120,7 +120,7 @@ static int imx_weim_gpr_setup(struct platform_device *pdev)
 		i++;
 	}
 
-	if (i == 0 || i % 4)
+	if (i == 0)
 		goto err;
 
 	for (i = 0; i < ARRAY_SIZE(gprvals); i++) {
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index fd3e9d82340a..1e29ba76615d 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -128,7 +128,7 @@ struct sunxi_rsb {
 };
 
 /* bus / slave device related functions */
-static struct bus_type sunxi_rsb_bus;
+static const struct bus_type sunxi_rsb_bus;
 
 static int sunxi_rsb_device_match(struct device *dev, struct device_driver *drv)
 {
@@ -177,7 +177,7 @@ static int sunxi_rsb_device_modalias(const struct device *dev, struct kobj_ueven
 	return of_device_uevent_modalias(dev, env);
 }
 
-static struct bus_type sunxi_rsb_bus = {
+static const struct bus_type sunxi_rsb_bus = {
 	.name		= RSB_CTRL_NAME,
 	.match		= sunxi_rsb_device_match,
 	.probe		= sunxi_rsb_device_probe,
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 245e5e827d0d..41d33f39efe5 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -2400,7 +2400,7 @@ static int sysc_child_add_clocks(struct sysc *ddata,
 	return 0;
 }
 
-static struct device_type sysc_device_type = {
+static const struct device_type sysc_device_type = {
 };
 
 static struct sysc *sysc_child_to_parent(struct device *dev)
diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c
index 57186c58dc84..1d7dd3d2c101 100644
--- a/drivers/cache/ax45mp_cache.c
+++ b/drivers/cache/ax45mp_cache.c
@@ -129,8 +129,12 @@ static void ax45mp_dma_cache_wback(phys_addr_t paddr, size_t size)
 	unsigned long line_size;
 	unsigned long flags;
 
+	if (unlikely(start == end))
+		return;
+
 	line_size = ax45mp_priv.ax45mp_cache_line_size;
 	start = start & (~(line_size - 1));
+	end = ((end + line_size - 1) & (~(line_size - 1)));
 	local_irq_save(flags);
 	ax45mp_cpu_dcache_wb_range(start, end);
 	local_irq_restore(flags);
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index d668b174ace9..eefdd422ad8e 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -724,11 +724,6 @@ static void probe_gdrom_setupdisk(void)
 
 static int probe_gdrom_setupqueue(void)
 {
-	blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR);
-	/* using DMA so memory will need to be contiguous */
-	blk_queue_max_segments(gd.gdrom_rq, 1);
-	/* set a large max size to get most from DMA */
-	blk_queue_max_segment_size(gd.gdrom_rq, 0x40000);
 	gd.disk->queue = gd.gdrom_rq;
 	return gdrom_init_dma_mode();
 }
@@ -743,6 +738,13 @@ static const struct blk_mq_ops gdrom_mq_ops = {
  */
 static int probe_gdrom(struct platform_device *devptr)
 {
+	struct queue_limits lim = {
+		.logical_block_size		= GDROM_HARD_SECTOR,
+		/* using DMA so memory will need to be contiguous */
+		.max_segments			= 1,
+		/* set a large max size to get most from DMA */
+		.max_segment_size		= 0x40000,
+	};
 	int err;
 
 	/*
@@ -778,7 +780,7 @@ static int probe_gdrom(struct platform_device *devptr)
 	if (err)
 		goto probe_fail_free_cd_info;
 
-	gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL);
+	gd.disk = blk_mq_alloc_disk(&gd.tag_set, &lim, NULL);
 	if (IS_ERR(gd.disk)) {
 		err = PTR_ERR(gd.disk);
 		goto probe_fail_free_tag_set;
@@ -829,7 +831,7 @@ probe_fail_no_mem:
 	return err;
 }
 
-static int remove_gdrom(struct platform_device *devptr)
+static void remove_gdrom(struct platform_device *devptr)
 {
 	blk_mq_free_tag_set(&gd.tag_set);
 	free_irq(HW_EVENT_GDROM_CMD, &gd);
@@ -840,13 +842,11 @@ static int remove_gdrom(struct platform_device *devptr)
 	unregister_cdrom(gd.cd_info);
 	kfree(gd.cd_info);
 	kfree(gd.toc);
-
-	return 0;
 }
 
 static struct platform_driver gdrom_driver = {
 	.probe = probe_gdrom,
-	.remove = remove_gdrom,
+	.remove_new = remove_gdrom,
 	.driver = {
 			.name = GDROM_DEV_NAME,
 	},
diff --git a/drivers/clk/rockchip/clk-rk3588.c b/drivers/clk/rockchip/clk-rk3588.c
index 6994165e0395..0b60ae78f9d8 100644
--- a/drivers/clk/rockchip/clk-rk3588.c
+++ b/drivers/clk/rockchip/clk-rk3588.c
@@ -2458,15 +2458,18 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = {
 static void __init rk3588_clk_init(struct device_node *np)
 {
 	struct rockchip_clk_provider *ctx;
+	unsigned long clk_nr_clks;
 	void __iomem *reg_base;
 
+	clk_nr_clks = rockchip_clk_find_max_clk_id(rk3588_clk_branches,
+					ARRAY_SIZE(rk3588_clk_branches)) + 1;
 	reg_base = of_iomap(np, 0);
 	if (!reg_base) {
 		pr_err("%s: could not map cru region\n", __func__);
 		return;
 	}
 
-	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+	ctx = rockchip_clk_init(np, reg_base, clk_nr_clks);
 	if (IS_ERR(ctx)) {
 		pr_err("%s: rockchip clk init failed\n", __func__);
 		iounmap(reg_base);
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index 4059d9365ae6..73d2cbdc716b 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -429,6 +429,23 @@ void rockchip_clk_register_plls(struct rockchip_clk_provider *ctx,
 }
 EXPORT_SYMBOL_GPL(rockchip_clk_register_plls);
 
+unsigned long rockchip_clk_find_max_clk_id(struct rockchip_clk_branch *list,
+					   unsigned int nr_clk)
+{
+	unsigned long max = 0;
+	unsigned int idx;
+
+	for (idx = 0; idx < nr_clk; idx++, list++) {
+		if (list->id > max)
+			max = list->id;
+		if (list->child && list->child->id > max)
+			max = list->id;
+	}
+
+	return max;
+}
+EXPORT_SYMBOL_GPL(rockchip_clk_find_max_clk_id);
+
 void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx,
 				    struct rockchip_clk_branch *list,
 				    unsigned int nr_clk)
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index 758ebaf2236b..fd3b476dedda 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -973,6 +973,8 @@ struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np,
 			void __iomem *base, unsigned long nr_clks);
 void rockchip_clk_of_add_provider(struct device_node *np,
 				struct rockchip_clk_provider *ctx);
+unsigned long rockchip_clk_find_max_clk_id(struct rockchip_clk_branch *list,
+					   unsigned int nr_clk);
 void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx,
 				    struct rockchip_clk_branch *list,
 				    unsigned int nr_clk);
diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
index 0964bb11657f..782993951fff 100644
--- a/drivers/clk/samsung/clk-gs101.c
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -2475,7 +2475,7 @@ static const struct samsung_cmu_info misc_cmu_info __initconst = {
 	.nr_clk_ids		= CLKS_NR_MISC,
 	.clk_regs		= misc_clk_regs,
 	.nr_clk_regs		= ARRAY_SIZE(misc_clk_regs),
-	.clk_name		= "dout_cmu_misc_bus",
+	.clk_name		= "bus",
 };
 
 /* ---- platform_driver ----------------------------------------------------- */
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index e054de92de91..8d4a52056684 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -1807,7 +1807,7 @@ TIMER_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init);
 #endif
 
 int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts,
-				 struct clocksource **cs)
+				 enum clocksource_ids *cs_id)
 {
 	struct arm_smccc_res hvc_res;
 	u32 ptp_counter;
@@ -1831,8 +1831,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *ts,
 	*ts = ktime_to_timespec64(ktime);
 	if (cycle)
 		*cycle = (u64)hvc_res.a2 << 32 | hvc_res.a3;
-	if (cs)
-		*cs = &clocksource_counter;
+	if (cs_id)
+		*cs_id = CSID_ARM_ARCH_COUNTER;
 
 	return 0;
 }
diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c
index e4974b508328..a933ef53845a 100644
--- a/drivers/comedi/drivers/comedi_8255.c
+++ b/drivers/comedi/drivers/comedi_8255.c
@@ -159,6 +159,7 @@ static int __subdev_8255_init(struct comedi_device *dev,
 		return -ENOMEM;
 
 	spriv->context = context;
+	spriv->io      = io;
 
 	s->type		= COMEDI_SUBD_DIO;
 	s->subdev_flags	= SDF_READABLE | SDF_WRITABLE;
diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c
index 30ea8b53ebf8..05ae9122823f 100644
--- a/drivers/comedi/drivers/comedi_test.c
+++ b/drivers/comedi/drivers/comedi_test.c
@@ -87,6 +87,8 @@ struct waveform_private {
 	struct comedi_device *dev;	/* parent comedi device */
 	u64 ao_last_scan_time;		/* time of previous AO scan in usec */
 	unsigned int ao_scan_period;	/* AO scan period in usec */
+	bool ai_timer_enable:1;		/* should AI timer be running? */
+	bool ao_timer_enable:1;		/* should AO timer be running? */
 	unsigned short ao_loopbacks[N_CHANS];
 };
 
@@ -236,8 +238,12 @@ static void waveform_ai_timer(struct timer_list *t)
 			time_increment = devpriv->ai_convert_time - now;
 		else
 			time_increment = 1;
-		mod_timer(&devpriv->ai_timer,
-			  jiffies + usecs_to_jiffies(time_increment));
+		spin_lock(&dev->spinlock);
+		if (devpriv->ai_timer_enable) {
+			mod_timer(&devpriv->ai_timer,
+				  jiffies + usecs_to_jiffies(time_increment));
+		}
+		spin_unlock(&dev->spinlock);
 	}
 
 overrun:
@@ -393,9 +399,12 @@ static int waveform_ai_cmd(struct comedi_device *dev,
 	 * Seem to need an extra jiffy here, otherwise timer expires slightly
 	 * early!
 	 */
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ai_timer_enable = true;
 	devpriv->ai_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1;
 	add_timer(&devpriv->ai_timer);
+	spin_unlock_bh(&dev->spinlock);
 	return 0;
 }
 
@@ -404,6 +413,9 @@ static int waveform_ai_cancel(struct comedi_device *dev,
 {
 	struct waveform_private *devpriv = dev->private;
 
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ai_timer_enable = false;
+	spin_unlock_bh(&dev->spinlock);
 	if (in_softirq()) {
 		/* Assume we were called from the timer routine itself. */
 		del_timer(&devpriv->ai_timer);
@@ -495,8 +507,12 @@ static void waveform_ao_timer(struct timer_list *t)
 		unsigned int time_inc = devpriv->ao_last_scan_time +
 					devpriv->ao_scan_period - now;
 
-		mod_timer(&devpriv->ao_timer,
-			  jiffies + usecs_to_jiffies(time_inc));
+		spin_lock(&dev->spinlock);
+		if (devpriv->ao_timer_enable) {
+			mod_timer(&devpriv->ao_timer,
+				  jiffies + usecs_to_jiffies(time_inc));
+		}
+		spin_unlock(&dev->spinlock);
 	}
 
 underrun:
@@ -517,9 +533,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev,
 	async->inttrig = NULL;
 
 	devpriv->ao_last_scan_time = ktime_to_us(ktime_get());
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ao_timer_enable = true;
 	devpriv->ao_timer.expires =
 		jiffies + usecs_to_jiffies(devpriv->ao_scan_period);
 	add_timer(&devpriv->ao_timer);
+	spin_unlock_bh(&dev->spinlock);
 
 	return 1;
 }
@@ -604,6 +623,9 @@ static int waveform_ao_cancel(struct comedi_device *dev,
 	struct waveform_private *devpriv = dev->private;
 
 	s->async->inttrig = NULL;
+	spin_lock_bh(&dev->spinlock);
+	devpriv->ao_timer_enable = false;
+	spin_unlock_bh(&dev->spinlock);
 	if (in_softirq()) {
 		/* Assume we were called from the timer routine itself. */
 		del_timer(&devpriv->ao_timer);
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 3d5e6d705fc6..44b19e696176 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg)
 		filter_data[1] = 0;
 	}
 
-	if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, (void *)filter_data) == -ESRCH)
-		atomic_set(&proc_event_num_listeners, 0);
+	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+			     cn_filter, (void *)filter_data);
 
 	local_unlock(&local_event.lock);
 }
diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c
index 09c77afb33ca..3f24481fc04a 100644
--- a/drivers/counter/counter-core.c
+++ b/drivers/counter/counter-core.c
@@ -31,10 +31,11 @@ struct counter_device_allochelper {
 	struct counter_device counter;
 
 	/*
-	 * This is cache line aligned to ensure private data behaves like if it
-	 * were kmalloced separately.
+	 * This ensures private data behaves like if it were kmalloced
+	 * separately. Also ensures the minimum alignment for safe DMA
+	 * operations (which may or may not mean cache alignment).
 	 */
-	unsigned long privdata[] ____cacheline_aligned;
+	unsigned long privdata[] __aligned(ARCH_DMA_MINALIGN);
 };
 
 static void counter_device_release(struct device *dev)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ca94e60e705a..79619227ea51 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2987,6 +2987,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum,
 	if (min_pstate < cpu->min_perf_ratio)
 		min_pstate = cpu->min_perf_ratio;
 
+	if (min_pstate > cpu->max_perf_ratio)
+		min_pstate = cpu->max_perf_ratio;
+
 	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
 	if (max_pstate < min_pstate)
 		max_pstate = min_pstate;
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
index 1262a7773ef3..de50c00ba218 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c
@@ -299,22 +299,6 @@ theend:
 	return err;
 }
 
-static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq)
-{
-	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq);
-	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
-	struct sun8i_ce_dev *ce = op->ce;
-	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq);
-	int flow, err;
-
-	flow = rctx->flow;
-	err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm));
-	local_bh_disable();
-	crypto_finalize_skcipher_request(engine, breq, err);
-	local_bh_enable();
-}
-
 static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine,
 				      void *async_req)
 {
@@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine,
 	dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE);
 }
 
+static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq)
+{
+	struct skcipher_request *breq = container_of(areq, struct skcipher_request, base);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq);
+	struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm);
+	struct sun8i_ce_dev *ce = op->ce;
+	struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq);
+	int flow, err;
+
+	flow = rctx->flow;
+	err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm));
+	sun8i_ce_cipher_unprepare(engine, areq);
+	local_bh_disable();
+	crypto_finalize_skcipher_request(engine, breq, err);
+	local_bh_enable();
+}
+
 int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq)
 {
 	int err = sun8i_ce_cipher_prepare(engine, areq);
@@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq)
 		return err;
 
 	sun8i_ce_cipher_run(engine, areq);
-	sun8i_ce_cipher_unprepare(engine, areq);
 	return 0;
 }
 
diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index a148ff1f0872..a4f6884416a0 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -4545,6 +4545,7 @@ struct caam_hash_alg {
 	struct list_head entry;
 	struct device *dev;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_alg ahash_alg;
 };
 
@@ -4571,7 +4572,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 
 	ctx->dev = caam_hash->dev;
 
-	if (alg->setkey) {
+	if (caam_hash->is_hmac) {
 		ctx->adata.key_dma = dma_map_single_attrs(ctx->dev, ctx->key,
 							  ARRAY_SIZE(ctx->key),
 							  DMA_TO_DEVICE,
@@ -4611,7 +4612,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -4646,12 +4647,14 @@ static struct caam_hash_alg *caam_hash_alloc(struct device *dev,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		t_alg->ahash_alg.setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 290c8500c247..fdd724228c2f 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1753,6 +1753,7 @@ static struct caam_hash_template driver_hash[] = {
 struct caam_hash_alg {
 	struct list_head entry;
 	int alg_type;
+	bool is_hmac;
 	struct ahash_engine_alg ahash_alg;
 };
 
@@ -1804,7 +1805,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	} else {
 		if (priv->era >= 6) {
 			ctx->dir = DMA_BIDIRECTIONAL;
-			ctx->key_dir = alg->setkey ? DMA_TO_DEVICE : DMA_NONE;
+			ctx->key_dir = caam_hash->is_hmac ? DMA_TO_DEVICE : DMA_NONE;
 		} else {
 			ctx->dir = DMA_TO_DEVICE;
 			ctx->key_dir = DMA_NONE;
@@ -1862,7 +1863,7 @@ static int caam_hash_cra_init(struct crypto_tfm *tfm)
 	 * For keyed hash algorithms shared descriptors
 	 * will be created later in setkey() callback
 	 */
-	return alg->setkey ? 0 : ahash_set_sh_desc(ahash);
+	return caam_hash->is_hmac ? 0 : ahash_set_sh_desc(ahash);
 }
 
 static void caam_hash_cra_exit(struct crypto_tfm *tfm)
@@ -1915,12 +1916,14 @@ caam_hash_alloc(struct caam_hash_template *template,
 			 template->hmac_name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->hmac_driver_name);
+		t_alg->is_hmac = true;
 	} else {
 		snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->name);
 		snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 			 template->driver_name);
 		halg->setkey = NULL;
+		t_alg->is_hmac = false;
 	}
 	alg->cra_module = THIS_MODULE;
 	alg->cra_init = caam_hash_cra_init;
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 32268e239bf1..f394e45e11ab 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -38,7 +38,7 @@ config CRYPTO_DEV_CCP_CRYPTO
 config CRYPTO_DEV_SP_PSP
 	bool "Platform Security Processor (PSP) device"
 	default y
-	depends on CRYPTO_DEV_CCP_DD && X86_64
+	depends on CRYPTO_DEV_CCP_DD && X86_64 && AMD_IOMMU
 	help
 	 Provide support for the AMD Platform Security Processor (PSP).
 	 The PSP is a dedicated processor that provides support for key
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e4d3f45242f6..f44efbb89c34 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -21,14 +21,18 @@
 #include <linux/hw_random.h>
 #include <linux/ccp.h>
 #include <linux/firmware.h>
+#include <linux/panic_notifier.h>
 #include <linux/gfp.h>
 #include <linux/cpufeature.h>
 #include <linux/fs.h>
 #include <linux/fs_struct.h>
 #include <linux/psp.h>
+#include <linux/amd-iommu.h>
 
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
+#include <asm/e820/types.h>
+#include <asm/sev.h>
 
 #include "psp-dev.h"
 #include "sev-dev.h"
@@ -37,6 +41,19 @@
 #define SEV_FW_FILE		"amd/sev.fw"
 #define SEV_FW_NAME_SIZE	64
 
+/* Minimum firmware version required for the SEV-SNP support */
+#define SNP_MIN_API_MAJOR	1
+#define SNP_MIN_API_MINOR	51
+
+/*
+ * Maximum number of firmware-writable buffers that might be specified
+ * in the parameters of a legacy SEV command buffer.
+ */
+#define CMD_BUF_FW_WRITABLE_MAX 2
+
+/* Leave room in the descriptor array for an end-of-list indicator. */
+#define CMD_BUF_DESC_MAX (CMD_BUF_FW_WRITABLE_MAX + 1)
+
 static DEFINE_MUTEX(sev_cmd_mutex);
 static struct sev_misc_dev *misc_dev;
 
@@ -68,9 +85,14 @@ static int psp_timeout;
  *   The TMR is a 1MB area that must be 1MB aligned.  Use the page allocator
  *   to allocate the memory, which will return aligned memory for the specified
  *   allocation order.
+ *
+ * When SEV-SNP is enabled the TMR needs to be 2MB aligned and 2MB sized.
  */
-#define SEV_ES_TMR_SIZE		(1024 * 1024)
+#define SEV_TMR_SIZE		(1024 * 1024)
+#define SNP_TMR_SIZE		(2 * 1024 * 1024)
+
 static void *sev_es_tmr;
+static size_t sev_es_tmr_size = SEV_TMR_SIZE;
 
 /* INIT_EX NV Storage:
  *   The NV Storage is a 32Kb area and must be 4Kb page aligned.  Use the page
@@ -80,6 +102,13 @@ static void *sev_es_tmr;
 #define NV_LENGTH (32 * 1024)
 static void *sev_init_ex_buffer;
 
+/*
+ * SEV_DATA_RANGE_LIST:
+ *   Array containing range of pages that firmware transitions to HV-fixed
+ *   page state.
+ */
+static struct sev_data_range_list *snp_range_list;
+
 static inline bool sev_version_greater_or_equal(u8 maj, u8 min)
 {
 	struct sev_device *sev = psp_master->sev_data;
@@ -115,6 +144,25 @@ static int sev_wait_cmd_ioc(struct sev_device *sev,
 {
 	int ret;
 
+	/*
+	 * If invoked during panic handling, local interrupts are disabled,
+	 * so the PSP command completion interrupt can't be used. Poll for
+	 * PSP command completion instead.
+	 */
+	if (irqs_disabled()) {
+		unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10;
+
+		/* Poll for SEV command completion: */
+		while (timeout_usecs--) {
+			*reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg);
+			if (*reg & PSP_CMDRESP_RESP)
+				return 0;
+
+			udelay(10);
+		}
+		return -ETIMEDOUT;
+	}
+
 	ret = wait_event_timeout(sev->int_queue,
 			sev->int_rcvd, timeout * HZ);
 	if (!ret)
@@ -130,6 +178,8 @@ static int sev_cmd_buffer_len(int cmd)
 	switch (cmd) {
 	case SEV_CMD_INIT:			return sizeof(struct sev_data_init);
 	case SEV_CMD_INIT_EX:                   return sizeof(struct sev_data_init_ex);
+	case SEV_CMD_SNP_SHUTDOWN_EX:		return sizeof(struct sev_data_snp_shutdown_ex);
+	case SEV_CMD_SNP_INIT_EX:		return sizeof(struct sev_data_snp_init_ex);
 	case SEV_CMD_PLATFORM_STATUS:		return sizeof(struct sev_user_data_status);
 	case SEV_CMD_PEK_CSR:			return sizeof(struct sev_data_pek_csr);
 	case SEV_CMD_PEK_CERT_IMPORT:		return sizeof(struct sev_data_pek_cert_import);
@@ -158,23 +208,27 @@ static int sev_cmd_buffer_len(int cmd)
 	case SEV_CMD_GET_ID:			return sizeof(struct sev_data_get_id);
 	case SEV_CMD_ATTESTATION_REPORT:	return sizeof(struct sev_data_attestation_report);
 	case SEV_CMD_SEND_CANCEL:		return sizeof(struct sev_data_send_cancel);
+	case SEV_CMD_SNP_GCTX_CREATE:		return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_LAUNCH_START:		return sizeof(struct sev_data_snp_launch_start);
+	case SEV_CMD_SNP_LAUNCH_UPDATE:		return sizeof(struct sev_data_snp_launch_update);
+	case SEV_CMD_SNP_ACTIVATE:		return sizeof(struct sev_data_snp_activate);
+	case SEV_CMD_SNP_DECOMMISSION:		return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_PAGE_RECLAIM:		return sizeof(struct sev_data_snp_page_reclaim);
+	case SEV_CMD_SNP_GUEST_STATUS:		return sizeof(struct sev_data_snp_guest_status);
+	case SEV_CMD_SNP_LAUNCH_FINISH:		return sizeof(struct sev_data_snp_launch_finish);
+	case SEV_CMD_SNP_DBG_DECRYPT:		return sizeof(struct sev_data_snp_dbg);
+	case SEV_CMD_SNP_DBG_ENCRYPT:		return sizeof(struct sev_data_snp_dbg);
+	case SEV_CMD_SNP_PAGE_UNSMASH:		return sizeof(struct sev_data_snp_page_unsmash);
+	case SEV_CMD_SNP_PLATFORM_STATUS:	return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_GUEST_REQUEST:		return sizeof(struct sev_data_snp_guest_request);
+	case SEV_CMD_SNP_CONFIG:		return sizeof(struct sev_user_data_snp_config);
+	case SEV_CMD_SNP_COMMIT:		return sizeof(struct sev_data_snp_commit);
 	default:				return 0;
 	}
 
 	return 0;
 }
 
-static void *sev_fw_alloc(unsigned long len)
-{
-	struct page *page;
-
-	page = alloc_pages(GFP_KERNEL, get_order(len));
-	if (!page)
-		return NULL;
-
-	return page_address(page);
-}
-
 static struct file *open_file_as_root(const char *filename, int flags, umode_t mode)
 {
 	struct file *fp;
@@ -305,13 +359,485 @@ static int sev_write_init_ex_file_if_required(int cmd_id)
 	return sev_write_init_ex_file();
 }
 
+/*
+ * snp_reclaim_pages() needs __sev_do_cmd_locked(), and __sev_do_cmd_locked()
+ * needs snp_reclaim_pages(), so a forward declaration is needed.
+ */
+static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret);
+
+static int snp_reclaim_pages(unsigned long paddr, unsigned int npages, bool locked)
+{
+	int ret, err, i;
+
+	paddr = __sme_clr(ALIGN_DOWN(paddr, PAGE_SIZE));
+
+	for (i = 0; i < npages; i++, paddr += PAGE_SIZE) {
+		struct sev_data_snp_page_reclaim data = {0};
+
+		data.paddr = paddr;
+
+		if (locked)
+			ret = __sev_do_cmd_locked(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err);
+		else
+			ret = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err);
+
+		if (ret)
+			goto cleanup;
+
+		ret = rmp_make_shared(__phys_to_pfn(paddr), PG_LEVEL_4K);
+		if (ret)
+			goto cleanup;
+	}
+
+	return 0;
+
+cleanup:
+	/*
+	 * If there was a failure reclaiming the page then it is no longer safe
+	 * to release it back to the system; leak it instead.
+	 */
+	snp_leak_pages(__phys_to_pfn(paddr), npages - i);
+	return ret;
+}
+
+static int rmp_mark_pages_firmware(unsigned long paddr, unsigned int npages, bool locked)
+{
+	unsigned long pfn = __sme_clr(paddr) >> PAGE_SHIFT;
+	int rc, i;
+
+	for (i = 0; i < npages; i++, pfn++) {
+		rc = rmp_make_private(pfn, 0, PG_LEVEL_4K, 0, true);
+		if (rc)
+			goto cleanup;
+	}
+
+	return 0;
+
+cleanup:
+	/*
+	 * Try unrolling the firmware state changes by
+	 * reclaiming the pages which were already changed to the
+	 * firmware state.
+	 */
+	snp_reclaim_pages(paddr, i, locked);
+
+	return rc;
+}
+
+static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order)
+{
+	unsigned long npages = 1ul << order, paddr;
+	struct sev_device *sev;
+	struct page *page;
+
+	if (!psp_master || !psp_master->sev_data)
+		return NULL;
+
+	page = alloc_pages(gfp_mask, order);
+	if (!page)
+		return NULL;
+
+	/* If SEV-SNP is initialized then add the page in RMP table. */
+	sev = psp_master->sev_data;
+	if (!sev->snp_initialized)
+		return page;
+
+	paddr = __pa((unsigned long)page_address(page));
+	if (rmp_mark_pages_firmware(paddr, npages, false))
+		return NULL;
+
+	return page;
+}
+
+void *snp_alloc_firmware_page(gfp_t gfp_mask)
+{
+	struct page *page;
+
+	page = __snp_alloc_firmware_pages(gfp_mask, 0);
+
+	return page ? page_address(page) : NULL;
+}
+EXPORT_SYMBOL_GPL(snp_alloc_firmware_page);
+
+static void __snp_free_firmware_pages(struct page *page, int order, bool locked)
+{
+	struct sev_device *sev = psp_master->sev_data;
+	unsigned long paddr, npages = 1ul << order;
+
+	if (!page)
+		return;
+
+	paddr = __pa((unsigned long)page_address(page));
+	if (sev->snp_initialized &&
+	    snp_reclaim_pages(paddr, npages, locked))
+		return;
+
+	__free_pages(page, order);
+}
+
+void snp_free_firmware_page(void *addr)
+{
+	if (!addr)
+		return;
+
+	__snp_free_firmware_pages(virt_to_page(addr), 0, false);
+}
+EXPORT_SYMBOL_GPL(snp_free_firmware_page);
+
+static void *sev_fw_alloc(unsigned long len)
+{
+	struct page *page;
+
+	page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len));
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
+/**
+ * struct cmd_buf_desc - descriptors for managing legacy SEV command address
+ * parameters corresponding to buffers that may be written to by firmware.
+ *
+ * @paddr_ptr:  pointer to the address parameter in the command buffer which may
+ *              need to be saved/restored depending on whether a bounce buffer
+ *              is used. In the case of a bounce buffer, the command buffer
+ *              needs to be updated with the address of the new bounce buffer
+ *              snp_map_cmd_buf_desc() has allocated specifically for it. Must
+ *              be NULL if this descriptor is only an end-of-list indicator.
+ *
+ * @paddr_orig: storage for the original address parameter, which can be used to
+ *              restore the original value in @paddr_ptr in cases where it is
+ *              replaced with the address of a bounce buffer.
+ *
+ * @len: length of buffer located at the address originally stored at @paddr_ptr
+ *
+ * @guest_owned: true if the address corresponds to guest-owned pages, in which
+ *               case bounce buffers are not needed.
+ */
+struct cmd_buf_desc {
+	u64 *paddr_ptr;
+	u64 paddr_orig;
+	u32 len;
+	bool guest_owned;
+};
+
+/*
+ * If a legacy SEV command parameter is a memory address, those pages in
+ * turn need to be transitioned to/from firmware-owned before/after
+ * executing the firmware command.
+ *
+ * Additionally, in cases where those pages are not guest-owned, a bounce
+ * buffer is needed in place of the original memory address parameter.
+ *
+ * A set of descriptors are used to keep track of this handling, and
+ * initialized here based on the specific commands being executed.
+ */
+static void snp_populate_cmd_buf_desc_list(int cmd, void *cmd_buf,
+					   struct cmd_buf_desc *desc_list)
+{
+	switch (cmd) {
+	case SEV_CMD_PDH_CERT_EXPORT: {
+		struct sev_data_pdh_cert_export *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->pdh_cert_address;
+		desc_list[0].len = data->pdh_cert_len;
+		desc_list[1].paddr_ptr = &data->cert_chain_address;
+		desc_list[1].len = data->cert_chain_len;
+		break;
+	}
+	case SEV_CMD_GET_ID: {
+		struct sev_data_get_id *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		break;
+	}
+	case SEV_CMD_PEK_CSR: {
+		struct sev_data_pek_csr *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		break;
+	}
+	case SEV_CMD_LAUNCH_UPDATE_DATA: {
+		struct sev_data_launch_update_data *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_LAUNCH_UPDATE_VMSA: {
+		struct sev_data_launch_update_vmsa *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_LAUNCH_MEASURE: {
+		struct sev_data_launch_measure *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		break;
+	}
+	case SEV_CMD_LAUNCH_UPDATE_SECRET: {
+		struct sev_data_launch_secret *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->guest_address;
+		desc_list[0].len = data->guest_len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_DBG_DECRYPT: {
+		struct sev_data_dbg *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->dst_addr;
+		desc_list[0].len = data->len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_DBG_ENCRYPT: {
+		struct sev_data_dbg *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->dst_addr;
+		desc_list[0].len = data->len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_ATTESTATION_REPORT: {
+		struct sev_data_attestation_report *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->address;
+		desc_list[0].len = data->len;
+		break;
+	}
+	case SEV_CMD_SEND_START: {
+		struct sev_data_send_start *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->session_address;
+		desc_list[0].len = data->session_len;
+		break;
+	}
+	case SEV_CMD_SEND_UPDATE_DATA: {
+		struct sev_data_send_update_data *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->hdr_address;
+		desc_list[0].len = data->hdr_len;
+		desc_list[1].paddr_ptr = &data->trans_address;
+		desc_list[1].len = data->trans_len;
+		break;
+	}
+	case SEV_CMD_SEND_UPDATE_VMSA: {
+		struct sev_data_send_update_vmsa *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->hdr_address;
+		desc_list[0].len = data->hdr_len;
+		desc_list[1].paddr_ptr = &data->trans_address;
+		desc_list[1].len = data->trans_len;
+		break;
+	}
+	case SEV_CMD_RECEIVE_UPDATE_DATA: {
+		struct sev_data_receive_update_data *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->guest_address;
+		desc_list[0].len = data->guest_len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	case SEV_CMD_RECEIVE_UPDATE_VMSA: {
+		struct sev_data_receive_update_vmsa *data = cmd_buf;
+
+		desc_list[0].paddr_ptr = &data->guest_address;
+		desc_list[0].len = data->guest_len;
+		desc_list[0].guest_owned = true;
+		break;
+	}
+	default:
+		break;
+	}
+}
+
+static int snp_map_cmd_buf_desc(struct cmd_buf_desc *desc)
+{
+	unsigned int npages;
+
+	if (!desc->len)
+		return 0;
+
+	/* Allocate a bounce buffer if this isn't a guest owned page. */
+	if (!desc->guest_owned) {
+		struct page *page;
+
+		page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(desc->len));
+		if (!page) {
+			pr_warn("Failed to allocate bounce buffer for SEV legacy command.\n");
+			return -ENOMEM;
+		}
+
+		desc->paddr_orig = *desc->paddr_ptr;
+		*desc->paddr_ptr = __psp_pa(page_to_virt(page));
+	}
+
+	npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT;
+
+	/* Transition the buffer to firmware-owned. */
+	if (rmp_mark_pages_firmware(*desc->paddr_ptr, npages, true)) {
+		pr_warn("Error moving pages to firmware-owned state for SEV legacy command.\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int snp_unmap_cmd_buf_desc(struct cmd_buf_desc *desc)
+{
+	unsigned int npages;
+
+	if (!desc->len)
+		return 0;
+
+	npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT;
+
+	/* Transition the buffers back to hypervisor-owned. */
+	if (snp_reclaim_pages(*desc->paddr_ptr, npages, true)) {
+		pr_warn("Failed to reclaim firmware-owned pages while issuing SEV legacy command.\n");
+		return -EFAULT;
+	}
+
+	/* Copy data from bounce buffer and then free it. */
+	if (!desc->guest_owned) {
+		void *bounce_buf = __va(__sme_clr(*desc->paddr_ptr));
+		void *dst_buf = __va(__sme_clr(desc->paddr_orig));
+
+		memcpy(dst_buf, bounce_buf, desc->len);
+		__free_pages(virt_to_page(bounce_buf), get_order(desc->len));
+
+		/* Restore the original address in the command buffer. */
+		*desc->paddr_ptr = desc->paddr_orig;
+	}
+
+	return 0;
+}
+
+static int snp_map_cmd_buf_desc_list(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list)
+{
+	int i;
+
+	snp_populate_cmd_buf_desc_list(cmd, cmd_buf, desc_list);
+
+	for (i = 0; i < CMD_BUF_DESC_MAX; i++) {
+		struct cmd_buf_desc *desc = &desc_list[i];
+
+		if (!desc->paddr_ptr)
+			break;
+
+		if (snp_map_cmd_buf_desc(desc))
+			goto err_unmap;
+	}
+
+	return 0;
+
+err_unmap:
+	for (i--; i >= 0; i--)
+		snp_unmap_cmd_buf_desc(&desc_list[i]);
+
+	return -EFAULT;
+}
+
+static int snp_unmap_cmd_buf_desc_list(struct cmd_buf_desc *desc_list)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < CMD_BUF_DESC_MAX; i++) {
+		struct cmd_buf_desc *desc = &desc_list[i];
+
+		if (!desc->paddr_ptr)
+			break;
+
+		if (snp_unmap_cmd_buf_desc(&desc_list[i]))
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+static bool sev_cmd_buf_writable(int cmd)
+{
+	switch (cmd) {
+	case SEV_CMD_PLATFORM_STATUS:
+	case SEV_CMD_GUEST_STATUS:
+	case SEV_CMD_LAUNCH_START:
+	case SEV_CMD_RECEIVE_START:
+	case SEV_CMD_LAUNCH_MEASURE:
+	case SEV_CMD_SEND_START:
+	case SEV_CMD_SEND_UPDATE_DATA:
+	case SEV_CMD_SEND_UPDATE_VMSA:
+	case SEV_CMD_PEK_CSR:
+	case SEV_CMD_PDH_CERT_EXPORT:
+	case SEV_CMD_GET_ID:
+	case SEV_CMD_ATTESTATION_REPORT:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/* After SNP is INIT'ed, the behavior of legacy SEV commands is changed. */
+static bool snp_legacy_handling_needed(int cmd)
+{
+	struct sev_device *sev = psp_master->sev_data;
+
+	return cmd < SEV_CMD_SNP_INIT && sev->snp_initialized;
+}
+
+static int snp_prep_cmd_buf(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list)
+{
+	if (!snp_legacy_handling_needed(cmd))
+		return 0;
+
+	if (snp_map_cmd_buf_desc_list(cmd, cmd_buf, desc_list))
+		return -EFAULT;
+
+	/*
+	 * Before command execution, the command buffer needs to be put into
+	 * the firmware-owned state.
+	 */
+	if (sev_cmd_buf_writable(cmd)) {
+		if (rmp_mark_pages_firmware(__pa(cmd_buf), 1, true))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int snp_reclaim_cmd_buf(int cmd, void *cmd_buf)
+{
+	if (!snp_legacy_handling_needed(cmd))
+		return 0;
+
+	/*
+	 * After command completion, the command buffer needs to be put back
+	 * into the hypervisor-owned state.
+	 */
+	if (sev_cmd_buf_writable(cmd))
+		if (snp_reclaim_pages(__pa(cmd_buf), 1, true))
+			return -EFAULT;
+
+	return 0;
+}
+
 static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 {
+	struct cmd_buf_desc desc_list[CMD_BUF_DESC_MAX] = {0};
 	struct psp_device *psp = psp_master;
 	struct sev_device *sev;
 	unsigned int cmdbuff_hi, cmdbuff_lo;
 	unsigned int phys_lsb, phys_msb;
 	unsigned int reg, ret = 0;
+	void *cmd_buf;
 	int buf_len;
 
 	if (!psp || !psp->sev_data)
@@ -331,12 +857,47 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	 * work for some memory, e.g. vmalloc'd addresses, and @data may not be
 	 * physically contiguous.
 	 */
-	if (data)
-		memcpy(sev->cmd_buf, data, buf_len);
+	if (data) {
+		/*
+		 * Commands are generally issued one at a time and require the
+		 * sev_cmd_mutex, but there could be recursive firmware requests
+		 * due to SEV_CMD_SNP_PAGE_RECLAIM needing to be issued while
+		 * preparing buffers for another command. This is the only known
+		 * case of nesting in the current code, so exactly one
+		 * additional command buffer is available for that purpose.
+		 */
+		if (!sev->cmd_buf_active) {
+			cmd_buf = sev->cmd_buf;
+			sev->cmd_buf_active = true;
+		} else if (!sev->cmd_buf_backup_active) {
+			cmd_buf = sev->cmd_buf_backup;
+			sev->cmd_buf_backup_active = true;
+		} else {
+			dev_err(sev->dev,
+				"SEV: too many firmware commands in progress, no command buffers available.\n");
+			return -EBUSY;
+		}
+
+		memcpy(cmd_buf, data, buf_len);
+
+		/*
+		 * The behavior of the SEV-legacy commands is altered when the
+		 * SNP firmware is in the INIT state.
+		 */
+		ret = snp_prep_cmd_buf(cmd, cmd_buf, desc_list);
+		if (ret) {
+			dev_err(sev->dev,
+				"SEV: failed to prepare buffer for legacy command 0x%x. Error: %d\n",
+				cmd, ret);
+			return ret;
+		}
+	} else {
+		cmd_buf = sev->cmd_buf;
+	}
 
 	/* Get the physical address of the command buffer */
-	phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0;
-	phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0;
+	phys_lsb = data ? lower_32_bits(__psp_pa(cmd_buf)) : 0;
+	phys_msb = data ? upper_32_bits(__psp_pa(cmd_buf)) : 0;
 
 	dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n",
 		cmd, phys_msb, phys_lsb, psp_timeout);
@@ -390,20 +951,41 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 		ret = sev_write_init_ex_file_if_required(cmd);
 	}
 
-	print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data,
-			     buf_len, false);
-
 	/*
 	 * Copy potential output from the PSP back to data.  Do this even on
 	 * failure in case the caller wants to glean something from the error.
 	 */
-	if (data)
-		memcpy(data, sev->cmd_buf, buf_len);
+	if (data) {
+		int ret_reclaim;
+		/*
+		 * Restore the page state after the command completes.
+		 */
+		ret_reclaim = snp_reclaim_cmd_buf(cmd, cmd_buf);
+		if (ret_reclaim) {
+			dev_err(sev->dev,
+				"SEV: failed to reclaim buffer for legacy command %#x. Error: %d\n",
+				cmd, ret_reclaim);
+			return ret_reclaim;
+		}
+
+		memcpy(data, cmd_buf, buf_len);
+
+		if (sev->cmd_buf_backup_active)
+			sev->cmd_buf_backup_active = false;
+		else
+			sev->cmd_buf_active = false;
+
+		if (snp_unmap_cmd_buf_desc_list(desc_list))
+			return -EFAULT;
+	}
+
+	print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data,
+			     buf_len, false);
 
 	return ret;
 }
 
-static int sev_do_cmd(int cmd, void *data, int *psp_ret)
+int sev_do_cmd(int cmd, void *data, int *psp_ret)
 {
 	int rc;
 
@@ -413,6 +995,7 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(sev_do_cmd);
 
 static int __sev_init_locked(int *error)
 {
@@ -427,7 +1010,7 @@ static int __sev_init_locked(int *error)
 		data.tmr_address = __pa(sev_es_tmr);
 
 		data.flags |= SEV_INIT_FLAGS_SEV_ES;
-		data.tmr_len = SEV_ES_TMR_SIZE;
+		data.tmr_len = sev_es_tmr_size;
 	}
 
 	return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error);
@@ -450,7 +1033,7 @@ static int __sev_init_ex_locked(int *error)
 		data.tmr_address = __pa(sev_es_tmr);
 
 		data.flags |= SEV_INIT_FLAGS_SEV_ES;
-		data.tmr_len = SEV_ES_TMR_SIZE;
+		data.tmr_len = sev_es_tmr_size;
 	}
 
 	return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error);
@@ -464,25 +1047,217 @@ static inline int __sev_do_init_locked(int *psp_ret)
 		return __sev_init_locked(psp_ret);
 }
 
-static int __sev_platform_init_locked(int *error)
+static void snp_set_hsave_pa(void *arg)
+{
+	wrmsrl(MSR_VM_HSAVE_PA, 0);
+}
+
+static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg)
+{
+	struct sev_data_range_list *range_list = arg;
+	struct sev_data_range *range = &range_list->ranges[range_list->num_elements];
+	size_t size;
+
+	/*
+	 * Ensure the list of HV_FIXED pages that will be passed to firmware
+	 * do not exceed the page-sized argument buffer.
+	 */
+	if ((range_list->num_elements * sizeof(struct sev_data_range) +
+	     sizeof(struct sev_data_range_list)) > PAGE_SIZE)
+		return -E2BIG;
+
+	switch (rs->desc) {
+	case E820_TYPE_RESERVED:
+	case E820_TYPE_PMEM:
+	case E820_TYPE_ACPI:
+		range->base = rs->start & PAGE_MASK;
+		size = PAGE_ALIGN((rs->end + 1) - rs->start);
+		range->page_count = size >> PAGE_SHIFT;
+		range_list->num_elements++;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int __sev_snp_init_locked(int *error)
 {
-	int rc = 0, psp_ret = SEV_RET_NO_FW_CALL;
 	struct psp_device *psp = psp_master;
+	struct sev_data_snp_init_ex data;
 	struct sev_device *sev;
+	void *arg = &data;
+	int cmd, rc = 0;
 
-	if (!psp || !psp->sev_data)
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
 		return -ENODEV;
 
 	sev = psp->sev_data;
 
-	if (sev->state == SEV_STATE_INIT)
+	if (sev->snp_initialized)
 		return 0;
 
-	if (sev_init_ex_buffer) {
-		rc = sev_read_init_ex_file();
-		if (rc)
+	if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) {
+		dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n",
+			SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR);
+		return 0;
+	}
+
+	/* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */
+	on_each_cpu(snp_set_hsave_pa, NULL, 1);
+
+	/*
+	 * Starting in SNP firmware v1.52, the SNP_INIT_EX command takes a list
+	 * of system physical address ranges to convert into HV-fixed page
+	 * states during the RMP initialization.  For instance, the memory that
+	 * UEFI reserves should be included in the that list. This allows system
+	 * components that occasionally write to memory (e.g. logging to UEFI
+	 * reserved regions) to not fail due to RMP initialization and SNP
+	 * enablement.
+	 *
+	 */
+	if (sev_version_greater_or_equal(SNP_MIN_API_MAJOR, 52)) {
+		/*
+		 * Firmware checks that the pages containing the ranges enumerated
+		 * in the RANGES structure are either in the default page state or in the
+		 * firmware page state.
+		 */
+		snp_range_list = kzalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!snp_range_list) {
+			dev_err(sev->dev,
+				"SEV: SNP_INIT_EX range list memory allocation failed\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Retrieve all reserved memory regions from the e820 memory map
+		 * to be setup as HV-fixed pages.
+		 */
+		rc = walk_iomem_res_desc(IORES_DESC_NONE, IORESOURCE_MEM, 0, ~0,
+					 snp_range_list, snp_filter_reserved_mem_regions);
+		if (rc) {
+			dev_err(sev->dev,
+				"SEV: SNP_INIT_EX walk_iomem_res_desc failed rc = %d\n", rc);
 			return rc;
+		}
+
+		memset(&data, 0, sizeof(data));
+		data.init_rmp = 1;
+		data.list_paddr_en = 1;
+		data.list_paddr = __psp_pa(snp_range_list);
+		cmd = SEV_CMD_SNP_INIT_EX;
+	} else {
+		cmd = SEV_CMD_SNP_INIT;
+		arg = NULL;
+	}
+
+	/*
+	 * The following sequence must be issued before launching the first SNP
+	 * guest to ensure all dirty cache lines are flushed, including from
+	 * updates to the RMP table itself via the RMPUPDATE instruction:
+	 *
+	 * - WBINVD on all running CPUs
+	 * - SEV_CMD_SNP_INIT[_EX] firmware command
+	 * - WBINVD on all running CPUs
+	 * - SEV_CMD_SNP_DF_FLUSH firmware command
+	 */
+	wbinvd_on_all_cpus();
+
+	rc = __sev_do_cmd_locked(cmd, arg, error);
+	if (rc)
+		return rc;
+
+	/* Prepare for first SNP guest launch after INIT. */
+	wbinvd_on_all_cpus();
+	rc = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, error);
+	if (rc)
+		return rc;
+
+	sev->snp_initialized = true;
+	dev_dbg(sev->dev, "SEV-SNP firmware initialized\n");
+
+	sev_es_tmr_size = SNP_TMR_SIZE;
+
+	return rc;
+}
+
+static void __sev_platform_init_handle_tmr(struct sev_device *sev)
+{
+	if (sev_es_tmr)
+		return;
+
+	/* Obtain the TMR memory area for SEV-ES use */
+	sev_es_tmr = sev_fw_alloc(sev_es_tmr_size);
+	if (sev_es_tmr) {
+		/* Must flush the cache before giving it to the firmware */
+		if (!sev->snp_initialized)
+			clflush_cache_range(sev_es_tmr, sev_es_tmr_size);
+	} else {
+			dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n");
 	}
+}
+
+/*
+ * If an init_ex_path is provided allocate a buffer for the file and
+ * read in the contents. Additionally, if SNP is initialized, convert
+ * the buffer pages to firmware pages.
+ */
+static int __sev_platform_init_handle_init_ex_path(struct sev_device *sev)
+{
+	struct page *page;
+	int rc;
+
+	if (!init_ex_path)
+		return 0;
+
+	if (sev_init_ex_buffer)
+		return 0;
+
+	page = alloc_pages(GFP_KERNEL, get_order(NV_LENGTH));
+	if (!page) {
+		dev_err(sev->dev, "SEV: INIT_EX NV memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	sev_init_ex_buffer = page_address(page);
+
+	rc = sev_read_init_ex_file();
+	if (rc)
+		return rc;
+
+	/* If SEV-SNP is initialized, transition to firmware page. */
+	if (sev->snp_initialized) {
+		unsigned long npages;
+
+		npages = 1UL << get_order(NV_LENGTH);
+		if (rmp_mark_pages_firmware(__pa(sev_init_ex_buffer), npages, false)) {
+			dev_err(sev->dev, "SEV: INIT_EX NV memory page state change failed.\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static int __sev_platform_init_locked(int *error)
+{
+	int rc, psp_ret = SEV_RET_NO_FW_CALL;
+	struct sev_device *sev;
+
+	if (!psp_master || !psp_master->sev_data)
+		return -ENODEV;
+
+	sev = psp_master->sev_data;
+
+	if (sev->state == SEV_STATE_INIT)
+		return 0;
+
+	__sev_platform_init_handle_tmr(sev);
+
+	rc = __sev_platform_init_handle_init_ex_path(sev);
+	if (rc)
+		return rc;
 
 	rc = __sev_do_init_locked(&psp_ret);
 	if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) {
@@ -520,12 +1295,46 @@ static int __sev_platform_init_locked(int *error)
 	return 0;
 }
 
-int sev_platform_init(int *error)
+static int _sev_platform_init_locked(struct sev_platform_init_args *args)
+{
+	struct sev_device *sev;
+	int rc;
+
+	if (!psp_master || !psp_master->sev_data)
+		return -ENODEV;
+
+	sev = psp_master->sev_data;
+
+	if (sev->state == SEV_STATE_INIT)
+		return 0;
+
+	/*
+	 * Legacy guests cannot be running while SNP_INIT(_EX) is executing,
+	 * so perform SEV-SNP initialization at probe time.
+	 */
+	rc = __sev_snp_init_locked(&args->error);
+	if (rc && rc != -ENODEV) {
+		/*
+		 * Don't abort the probe if SNP INIT failed,
+		 * continue to initialize the legacy SEV firmware.
+		 */
+		dev_err(sev->dev, "SEV-SNP: failed to INIT rc %d, error %#x\n",
+			rc, args->error);
+	}
+
+	/* Defer legacy SEV/SEV-ES support if allowed by caller/module. */
+	if (args->probe && !psp_init_on_probe)
+		return 0;
+
+	return __sev_platform_init_locked(&args->error);
+}
+
+int sev_platform_init(struct sev_platform_init_args *args)
 {
 	int rc;
 
 	mutex_lock(&sev_cmd_mutex);
-	rc = __sev_platform_init_locked(error);
+	rc = _sev_platform_init_locked(args);
 	mutex_unlock(&sev_cmd_mutex);
 
 	return rc;
@@ -534,10 +1343,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init);
 
 static int __sev_platform_shutdown_locked(int *error)
 {
-	struct sev_device *sev = psp_master->sev_data;
+	struct psp_device *psp = psp_master;
+	struct sev_device *sev;
 	int ret;
 
-	if (!sev || sev->state == SEV_STATE_UNINIT)
+	if (!psp || !psp->sev_data)
+		return 0;
+
+	sev = psp->sev_data;
+
+	if (sev->state == SEV_STATE_UNINIT)
 		return 0;
 
 	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
@@ -550,17 +1365,6 @@ static int __sev_platform_shutdown_locked(int *error)
 	return ret;
 }
 
-static int sev_platform_shutdown(int *error)
-{
-	int rc;
-
-	mutex_lock(&sev_cmd_mutex);
-	rc = __sev_platform_shutdown_locked(NULL);
-	mutex_unlock(&sev_cmd_mutex);
-
-	return rc;
-}
-
 static int sev_get_platform_state(int *state, int *error)
 {
 	struct sev_user_data_status data;
@@ -836,6 +1640,72 @@ fw_err:
 	return ret;
 }
 
+static int __sev_snp_shutdown_locked(int *error, bool panic)
+{
+	struct sev_device *sev = psp_master->sev_data;
+	struct sev_data_snp_shutdown_ex data;
+	int ret;
+
+	if (!sev->snp_initialized)
+		return 0;
+
+	memset(&data, 0, sizeof(data));
+	data.len = sizeof(data);
+	data.iommu_snp_shutdown = 1;
+
+	/*
+	 * If invoked during panic handling, local interrupts are disabled
+	 * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called.
+	 * In that case, a wbinvd() is done on remote CPUs via the NMI
+	 * callback, so only a local wbinvd() is needed here.
+	 */
+	if (!panic)
+		wbinvd_on_all_cpus();
+	else
+		wbinvd();
+
+	ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error);
+	/* SHUTDOWN may require DF_FLUSH */
+	if (*error == SEV_RET_DFFLUSH_REQUIRED) {
+		ret = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, NULL);
+		if (ret) {
+			dev_err(sev->dev, "SEV-SNP DF_FLUSH failed\n");
+			return ret;
+		}
+		/* reissue the shutdown command */
+		ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data,
+					  error);
+	}
+	if (ret) {
+		dev_err(sev->dev, "SEV-SNP firmware shutdown failed\n");
+		return ret;
+	}
+
+	/*
+	 * SNP_SHUTDOWN_EX with IOMMU_SNP_SHUTDOWN set to 1 disables SNP
+	 * enforcement by the IOMMU and also transitions all pages
+	 * associated with the IOMMU to the Reclaim state.
+	 * Firmware was transitioning the IOMMU pages to Hypervisor state
+	 * before version 1.53. But, accounting for the number of assigned
+	 * 4kB pages in a 2M page was done incorrectly by not transitioning
+	 * to the Reclaim state. This resulted in RMP #PF when later accessing
+	 * the 2M page containing those pages during kexec boot. Hence, the
+	 * firmware now transitions these pages to Reclaim state and hypervisor
+	 * needs to transition these pages to shared state. SNP Firmware
+	 * version 1.53 and above are needed for kexec boot.
+	 */
+	ret = amd_iommu_snp_disable();
+	if (ret) {
+		dev_err(sev->dev, "SNP IOMMU shutdown failed\n");
+		return ret;
+	}
+
+	sev->snp_initialized = false;
+	dev_dbg(sev->dev, "SEV-SNP firmware shutdown\n");
+
+	return ret;
+}
+
 static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable)
 {
 	struct sev_device *sev = psp_master->sev_data;
@@ -1078,6 +1948,85 @@ e_free_pdh:
 	return ret;
 }
 
+static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp)
+{
+	struct sev_device *sev = psp_master->sev_data;
+	struct sev_data_snp_addr buf;
+	struct page *status_page;
+	void *data;
+	int ret;
+
+	if (!sev->snp_initialized || !argp->data)
+		return -EINVAL;
+
+	status_page = alloc_page(GFP_KERNEL_ACCOUNT);
+	if (!status_page)
+		return -ENOMEM;
+
+	data = page_address(status_page);
+
+	/*
+	 * Firmware expects status page to be in firmware-owned state, otherwise
+	 * it will report firmware error code INVALID_PAGE_STATE (0x1A).
+	 */
+	if (rmp_mark_pages_firmware(__pa(data), 1, true)) {
+		ret = -EFAULT;
+		goto cleanup;
+	}
+
+	buf.address = __psp_pa(data);
+	ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error);
+
+	/*
+	 * Status page will be transitioned to Reclaim state upon success, or
+	 * left in Firmware state in failure. Use snp_reclaim_pages() to
+	 * transition either case back to Hypervisor-owned state.
+	 */
+	if (snp_reclaim_pages(__pa(data), 1, true))
+		return -EFAULT;
+
+	if (ret)
+		goto cleanup;
+
+	if (copy_to_user((void __user *)argp->data, data,
+			 sizeof(struct sev_user_data_snp_status)))
+		ret = -EFAULT;
+
+cleanup:
+	__free_pages(status_page, 0);
+	return ret;
+}
+
+static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp)
+{
+	struct sev_device *sev = psp_master->sev_data;
+	struct sev_data_snp_commit buf;
+
+	if (!sev->snp_initialized)
+		return -EINVAL;
+
+	buf.len = sizeof(buf);
+
+	return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error);
+}
+
+static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable)
+{
+	struct sev_device *sev = psp_master->sev_data;
+	struct sev_user_data_snp_config config;
+
+	if (!sev->snp_initialized || !argp->data)
+		return -EINVAL;
+
+	if (!writable)
+		return -EPERM;
+
+	if (copy_from_user(&config, (void __user *)argp->data, sizeof(config)))
+		return -EFAULT;
+
+	return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error);
+}
+
 static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
@@ -1129,6 +2078,15 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
 	case SEV_GET_ID2:
 		ret = sev_ioctl_do_get_id2(&input);
 		break;
+	case SNP_PLATFORM_STATUS:
+		ret = sev_ioctl_do_snp_platform_status(&input);
+		break;
+	case SNP_COMMIT:
+		ret = sev_ioctl_do_snp_commit(&input);
+		break;
+	case SNP_SET_CONFIG:
+		ret = sev_ioctl_do_snp_set_config(&input, writable);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -1239,10 +2197,12 @@ int sev_dev_init(struct psp_device *psp)
 	if (!sev)
 		goto e_err;
 
-	sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0);
+	sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 1);
 	if (!sev->cmd_buf)
 		goto e_sev;
 
+	sev->cmd_buf_backup = (uint8_t *)sev->cmd_buf + PAGE_SIZE;
+
 	psp->sev_data = sev;
 
 	sev->dev = dev;
@@ -1281,24 +2241,51 @@ e_err:
 	return ret;
 }
 
-static void sev_firmware_shutdown(struct sev_device *sev)
+static void __sev_firmware_shutdown(struct sev_device *sev, bool panic)
 {
-	sev_platform_shutdown(NULL);
+	int error;
+
+	__sev_platform_shutdown_locked(NULL);
 
 	if (sev_es_tmr) {
-		/* The TMR area was encrypted, flush it from the cache */
-		wbinvd_on_all_cpus();
+		/*
+		 * The TMR area was encrypted, flush it from the cache.
+		 *
+		 * If invoked during panic handling, local interrupts are
+		 * disabled and all CPUs are stopped, so wbinvd_on_all_cpus()
+		 * can't be used. In that case, wbinvd() is done on remote CPUs
+		 * via the NMI callback, and done for this CPU later during
+		 * SNP shutdown, so wbinvd_on_all_cpus() can be skipped.
+		 */
+		if (!panic)
+			wbinvd_on_all_cpus();
 
-		free_pages((unsigned long)sev_es_tmr,
-			   get_order(SEV_ES_TMR_SIZE));
+		__snp_free_firmware_pages(virt_to_page(sev_es_tmr),
+					  get_order(sev_es_tmr_size),
+					  true);
 		sev_es_tmr = NULL;
 	}
 
 	if (sev_init_ex_buffer) {
-		free_pages((unsigned long)sev_init_ex_buffer,
-			   get_order(NV_LENGTH));
+		__snp_free_firmware_pages(virt_to_page(sev_init_ex_buffer),
+					  get_order(NV_LENGTH),
+					  true);
 		sev_init_ex_buffer = NULL;
 	}
+
+	if (snp_range_list) {
+		kfree(snp_range_list);
+		snp_range_list = NULL;
+	}
+
+	__sev_snp_shutdown_locked(&error, panic);
+}
+
+static void sev_firmware_shutdown(struct sev_device *sev)
+{
+	mutex_lock(&sev_cmd_mutex);
+	__sev_firmware_shutdown(sev, false);
+	mutex_unlock(&sev_cmd_mutex);
 }
 
 void sev_dev_destroy(struct psp_device *psp)
@@ -1316,6 +2303,29 @@ void sev_dev_destroy(struct psp_device *psp)
 	psp_clear_sev_irq_handler(psp);
 }
 
+static int snp_shutdown_on_panic(struct notifier_block *nb,
+				 unsigned long reason, void *arg)
+{
+	struct sev_device *sev = psp_master->sev_data;
+
+	/*
+	 * If sev_cmd_mutex is already acquired, then it's likely
+	 * another PSP command is in flight and issuing a shutdown
+	 * would fail in unexpected ways. Rather than create even
+	 * more confusion during a panic, just bail out here.
+	 */
+	if (mutex_is_locked(&sev_cmd_mutex))
+		return NOTIFY_DONE;
+
+	__sev_firmware_shutdown(sev, true);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block snp_panic_notifier = {
+	.notifier_call = snp_shutdown_on_panic,
+};
+
 int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd,
 				void *data, int *error)
 {
@@ -1329,7 +2339,8 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user);
 void sev_pci_init(void)
 {
 	struct sev_device *sev = psp_master->sev_data;
-	int error, rc;
+	struct sev_platform_init_args args = {0};
+	int rc;
 
 	if (!sev)
 		return;
@@ -1342,36 +2353,18 @@ void sev_pci_init(void)
 	if (sev_update_firmware(sev->dev) == 0)
 		sev_get_api_version();
 
-	/* If an init_ex_path is provided rely on INIT_EX for PSP initialization
-	 * instead of INIT.
-	 */
-	if (init_ex_path) {
-		sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH);
-		if (!sev_init_ex_buffer) {
-			dev_err(sev->dev,
-				"SEV: INIT_EX NV memory allocation failed\n");
-			goto err;
-		}
-	}
-
-	/* Obtain the TMR memory area for SEV-ES use */
-	sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE);
-	if (sev_es_tmr)
-		/* Must flush the cache before giving it to the firmware */
-		clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE);
-	else
-		dev_warn(sev->dev,
-			 "SEV: TMR allocation failed, SEV-ES support unavailable\n");
-
-	if (!psp_init_on_probe)
-		return;
-
 	/* Initialize the platform */
-	rc = sev_platform_init(&error);
+	args.probe = true;
+	rc = sev_platform_init(&args);
 	if (rc)
 		dev_err(sev->dev, "SEV: failed to INIT error %#x, rc %d\n",
-			error, rc);
+			args.error, rc);
 
+	dev_info(sev->dev, "SEV%s API:%d.%d build:%d\n", sev->snp_initialized ?
+		"-SNP" : "", sev->api_major, sev->api_minor, sev->build);
+
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &snp_panic_notifier);
 	return;
 
 err:
@@ -1386,4 +2379,7 @@ void sev_pci_exit(void)
 		return;
 
 	sev_firmware_shutdown(sev);
+
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+					 &snp_panic_notifier);
 }
diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h
index 778c95155e74..3e4e5574e88a 100644
--- a/drivers/crypto/ccp/sev-dev.h
+++ b/drivers/crypto/ccp/sev-dev.h
@@ -52,6 +52,11 @@ struct sev_device {
 	u8 build;
 
 	void *cmd_buf;
+	void *cmd_buf_backup;
+	bool cmd_buf_active;
+	bool cmd_buf_backup_active;
+
+	bool snp_initialized;
 };
 
 int sev_dev_init(struct psp_device *psp);
diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
index 479062aa5e6b..94a0ebb03d8c 100644
--- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -463,6 +463,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 		hw_data->fw_name = ADF_402XX_FW;
 		hw_data->fw_mmp_name = ADF_402XX_MMP;
 		hw_data->uof_get_name = uof_get_name_402xx;
+		hw_data->get_ena_thd_mask = get_ena_thd_mask;
 		break;
 	case ADF_401XX_PCI_DEVICE_ID:
 		hw_data->fw_name = ADF_4XXX_FW;
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
index 1b13b4aa16ec..a235e6c300f1 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
@@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq)
 theend:
 	pm_runtime_put_autosuspend(rkc->dev);
 
+	rk_hash_unprepare(engine, breq);
+
 	local_bh_disable();
 	crypto_finalize_hash_request(engine, breq, err);
 	local_bh_enable();
 
-	rk_hash_unprepare(engine, breq);
-
 	return 0;
 }
 
diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
index 2621ff8a9376..de53eddf6796 100644
--- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c
@@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request *
 }
 
 static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx,
-		struct virtio_crypto_ctrl_header *header, void *para,
+		struct virtio_crypto_ctrl_header *header,
+		struct virtio_crypto_akcipher_session_para *para,
 		const uint8_t *key, unsigned int keylen)
 {
 	struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3];
@@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher
 
 	ctrl = &vc_ctrl_req->ctrl;
 	memcpy(&ctrl->header, header, sizeof(ctrl->header));
-	memcpy(&ctrl->u, para, sizeof(ctrl->u));
+	memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para));
 	input = &vc_ctrl_req->input;
 	input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR);
 
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index dcf2b39e1048..1a3e6aafbdcc 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -316,31 +316,27 @@ static const struct cxl_root_ops acpi_root_ops = {
 	.qos_class = cxl_acpi_qos_class,
 };
 
-static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
-			   const unsigned long end)
+static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
+			     struct cxl_cfmws_context *ctx)
 {
 	int target_map[CXL_DECODER_MAX_INTERLEAVE];
-	struct cxl_cfmws_context *ctx = arg;
 	struct cxl_port *root_port = ctx->root_port;
 	struct resource *cxl_res = ctx->cxl_res;
 	struct cxl_cxims_context cxims_ctx;
 	struct cxl_root_decoder *cxlrd;
 	struct device *dev = ctx->dev;
-	struct acpi_cedt_cfmws *cfmws;
 	cxl_calc_hb_fn cxl_calc_hb;
 	struct cxl_decoder *cxld;
 	unsigned int ways, i, ig;
 	struct resource *res;
 	int rc;
 
-	cfmws = (struct acpi_cedt_cfmws *) header;
-
 	rc = cxl_acpi_cfmws_verify(dev, cfmws);
 	if (rc) {
 		dev_err(dev, "CFMWS range %#llx-%#llx not registered\n",
 			cfmws->base_hpa,
 			cfmws->base_hpa + cfmws->window_size - 1);
-		return 0;
+		return rc;
 	}
 
 	rc = eiw_to_ways(cfmws->interleave_ways, &ways);
@@ -376,7 +372,7 @@ static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
 
 	cxlrd = cxl_root_decoder_alloc(root_port, ways, cxl_calc_hb);
 	if (IS_ERR(cxlrd))
-		return 0;
+		return PTR_ERR(cxlrd);
 
 	cxld = &cxlrd->cxlsd.cxld;
 	cxld->flags = cfmws_to_decoder_flags(cfmws->restrictions);
@@ -420,16 +416,7 @@ err_xormap:
 		put_device(&cxld->dev);
 	else
 		rc = cxl_decoder_autoremove(dev, cxld);
-	if (rc) {
-		dev_err(dev, "Failed to add decode range: %pr", res);
-		return rc;
-	}
-	dev_dbg(dev, "add: %s node: %d range [%#llx - %#llx]\n",
-		dev_name(&cxld->dev),
-		phys_to_target_node(cxld->hpa_range.start),
-		cxld->hpa_range.start, cxld->hpa_range.end);
-
-	return 0;
+	return rc;
 
 err_insert:
 	kfree(res->name);
@@ -438,6 +425,29 @@ err_name:
 	return -ENOMEM;
 }
 
+static int cxl_parse_cfmws(union acpi_subtable_headers *header, void *arg,
+			   const unsigned long end)
+{
+	struct acpi_cedt_cfmws *cfmws = (struct acpi_cedt_cfmws *)header;
+	struct cxl_cfmws_context *ctx = arg;
+	struct device *dev = ctx->dev;
+	int rc;
+
+	rc = __cxl_parse_cfmws(cfmws, ctx);
+	if (rc)
+		dev_err(dev,
+			"Failed to add decode range: [%#llx - %#llx] (%d)\n",
+			cfmws->base_hpa,
+			cfmws->base_hpa + cfmws->window_size - 1, rc);
+	else
+		dev_dbg(dev, "decode range: node: %d range [%#llx - %#llx]\n",
+			phys_to_target_node(cfmws->base_hpa), cfmws->base_hpa,
+			cfmws->base_hpa + cfmws->window_size - 1);
+
+	/* never fail cxl_acpi load for a single window failure */
+	return 0;
+}
+
 __mock struct acpi_device *to_cxl_host_bridge(struct device *host,
 					      struct device *dev)
 {
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 6fe11546889f..08fd0baea7a0 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -210,19 +210,12 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
 	return 0;
 }
 
-static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
-			   struct list_head *list)
+static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
+			      struct cxl_dpa_perf *dpa_perf)
 {
-	struct cxl_dpa_perf *dpa_perf;
-
-	dpa_perf = kzalloc(sizeof(*dpa_perf), GFP_KERNEL);
-	if (!dpa_perf)
-		return;
-
 	dpa_perf->dpa_range = dent->dpa_range;
 	dpa_perf->coord = dent->coord;
 	dpa_perf->qos_class = dent->qos_class;
-	list_add_tail(&dpa_perf->list, list);
 	dev_dbg(dev,
 		"DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n",
 		dent->dpa_range.start, dpa_perf->qos_class,
@@ -230,20 +223,6 @@ static void add_perf_entry(struct device *dev, struct dsmas_entry *dent,
 		dent->coord.read_latency, dent->coord.write_latency);
 }
 
-static void free_perf_ents(void *data)
-{
-	struct cxl_memdev_state *mds = data;
-	struct cxl_dpa_perf *dpa_perf, *n;
-	LIST_HEAD(discard);
-
-	list_splice_tail_init(&mds->ram_perf_list, &discard);
-	list_splice_tail_init(&mds->pmem_perf_list, &discard);
-	list_for_each_entry_safe(dpa_perf, n, &discard, list) {
-		list_del(&dpa_perf->list);
-		kfree(dpa_perf);
-	}
-}
-
 static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
 				     struct xarray *dsmas_xa)
 {
@@ -263,16 +242,14 @@ static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
 	xa_for_each(dsmas_xa, index, dent) {
 		if (resource_size(&cxlds->ram_res) &&
 		    range_contains(&ram_range, &dent->dpa_range))
-			add_perf_entry(dev, dent, &mds->ram_perf_list);
+			update_perf_entry(dev, dent, &mds->ram_perf);
 		else if (resource_size(&cxlds->pmem_res) &&
 			 range_contains(&pmem_range, &dent->dpa_range))
-			add_perf_entry(dev, dent, &mds->pmem_perf_list);
+			update_perf_entry(dev, dent, &mds->pmem_perf);
 		else
 			dev_dbg(dev, "no partition for dsmas dpa: %#llx\n",
 				dent->dpa_range.start);
 	}
-
-	devm_add_action_or_reset(&cxlds->cxlmd->dev, free_perf_ents, mds);
 }
 
 static int match_cxlrd_qos_class(struct device *dev, void *data)
@@ -293,24 +270,24 @@ static int match_cxlrd_qos_class(struct device *dev, void *data)
 	return 0;
 }
 
-static void cxl_qos_match(struct cxl_port *root_port,
-			  struct list_head *work_list,
-			  struct list_head *discard_list)
+static void reset_dpa_perf(struct cxl_dpa_perf *dpa_perf)
 {
-	struct cxl_dpa_perf *dpa_perf, *n;
+	*dpa_perf = (struct cxl_dpa_perf) {
+		.qos_class = CXL_QOS_CLASS_INVALID,
+	};
+}
 
-	list_for_each_entry_safe(dpa_perf, n, work_list, list) {
-		int rc;
+static bool cxl_qos_match(struct cxl_port *root_port,
+			  struct cxl_dpa_perf *dpa_perf)
+{
+	if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
+		return false;
 
-		if (dpa_perf->qos_class == CXL_QOS_CLASS_INVALID)
-			return;
+	if (!device_for_each_child(&root_port->dev, &dpa_perf->qos_class,
+				   match_cxlrd_qos_class))
+		return false;
 
-		rc = device_for_each_child(&root_port->dev,
-					   (void *)&dpa_perf->qos_class,
-					   match_cxlrd_qos_class);
-		if (!rc)
-			list_move_tail(&dpa_perf->list, discard_list);
-	}
+	return true;
 }
 
 static int match_cxlrd_hb(struct device *dev, void *data)
@@ -334,23 +311,10 @@ static int match_cxlrd_hb(struct device *dev, void *data)
 	return 0;
 }
 
-static void discard_dpa_perf(struct list_head *list)
-{
-	struct cxl_dpa_perf *dpa_perf, *n;
-
-	list_for_each_entry_safe(dpa_perf, n, list, list) {
-		list_del(&dpa_perf->list);
-		kfree(dpa_perf);
-	}
-}
-DEFINE_FREE(dpa_perf, struct list_head *, if (!list_empty(_T)) discard_dpa_perf(_T))
-
 static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
-	LIST_HEAD(__discard);
-	struct list_head *discard __free(dpa_perf) = &__discard;
 	struct cxl_port *root_port;
 	int rc;
 
@@ -363,16 +327,17 @@ static int cxl_qos_class_verify(struct cxl_memdev *cxlmd)
 	root_port = &cxl_root->port;
 
 	/* Check that the QTG IDs are all sane between end device and root decoders */
-	cxl_qos_match(root_port, &mds->ram_perf_list, discard);
-	cxl_qos_match(root_port, &mds->pmem_perf_list, discard);
+	if (!cxl_qos_match(root_port, &mds->ram_perf))
+		reset_dpa_perf(&mds->ram_perf);
+	if (!cxl_qos_match(root_port, &mds->pmem_perf))
+		reset_dpa_perf(&mds->pmem_perf);
 
 	/* Check to make sure that the device's host bridge is under a root decoder */
 	rc = device_for_each_child(&root_port->dev,
-				   (void *)cxlmd->endpoint->host_bridge,
-				   match_cxlrd_hb);
+				   cxlmd->endpoint->host_bridge, match_cxlrd_hb);
 	if (!rc) {
-		list_splice_tail_init(&mds->ram_perf_list, discard);
-		list_splice_tail_init(&mds->pmem_perf_list, discard);
+		reset_dpa_perf(&mds->ram_perf);
+		reset_dpa_perf(&mds->pmem_perf);
 	}
 
 	return rc;
@@ -417,6 +382,7 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
 
 	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
 	cxl_qos_class_verify(cxlmd);
+	cxl_memdev_update_perf(cxlmd);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL);
 
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 27166a411705..9adda4795eb7 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1391,8 +1391,8 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev)
 	mds->cxlds.reg_map.host = dev;
 	mds->cxlds.reg_map.resource = CXL_RESOURCE_NONE;
 	mds->cxlds.type = CXL_DEVTYPE_CLASSMEM;
-	INIT_LIST_HEAD(&mds->ram_perf_list);
-	INIT_LIST_HEAD(&mds->pmem_perf_list);
+	mds->ram_perf.qos_class = CXL_QOS_CLASS_INVALID;
+	mds->pmem_perf.qos_class = CXL_QOS_CLASS_INVALID;
 
 	return mds;
 }
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index dae8802ecdb0..d4e259f3a7e9 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -447,13 +447,41 @@ static struct attribute *cxl_memdev_attributes[] = {
 	NULL,
 };
 
+static ssize_t pmem_qos_class_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->pmem_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_pmem_qos_class =
+	__ATTR(qos_class, 0444, pmem_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_pmem_attributes[] = {
 	&dev_attr_pmem_size.attr,
+	&dev_attr_pmem_qos_class.attr,
 	NULL,
 };
 
+static ssize_t ram_qos_class_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+
+	return sysfs_emit(buf, "%d\n", mds->ram_perf.qos_class);
+}
+
+static struct device_attribute dev_attr_ram_qos_class =
+	__ATTR(qos_class, 0444, ram_qos_class_show, NULL);
+
 static struct attribute *cxl_memdev_ram_attributes[] = {
 	&dev_attr_ram_size.attr,
+	&dev_attr_ram_qos_class.attr,
 	NULL,
 };
 
@@ -477,14 +505,42 @@ static struct attribute_group cxl_memdev_attribute_group = {
 	.is_visible = cxl_memdev_visible,
 };
 
+static umode_t cxl_ram_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_ram_qos_class.attr)
+		if (mds->ram_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_ram_attribute_group = {
 	.name = "ram",
 	.attrs = cxl_memdev_ram_attributes,
+	.is_visible = cxl_ram_visible,
 };
 
+static umode_t cxl_pmem_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (a == &dev_attr_pmem_qos_class.attr)
+		if (mds->pmem_perf.qos_class == CXL_QOS_CLASS_INVALID)
+			return 0;
+
+	return a->mode;
+}
+
 static struct attribute_group cxl_memdev_pmem_attribute_group = {
 	.name = "pmem",
 	.attrs = cxl_memdev_pmem_attributes,
+	.is_visible = cxl_pmem_visible,
 };
 
 static umode_t cxl_memdev_security_visible(struct kobject *kobj,
@@ -519,6 +575,13 @@ static const struct attribute_group *cxl_memdev_attribute_groups[] = {
 	NULL,
 };
 
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd)
+{
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_ram_attribute_group);
+	sysfs_update_group(&cxlmd->dev.kobj, &cxl_memdev_pmem_attribute_group);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_memdev_update_perf, CXL);
+
 static const struct device_type cxl_memdev_type = {
 	.name = "cxl_memdev",
 	.release = cxl_memdev_release,
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 6c9c8d92f8f7..e9e6c81ce034 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -477,9 +477,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
 		allowed++;
 	}
 
-	if (!allowed) {
-		cxl_set_mem_enable(cxlds, 0);
-		info->mem_enabled = 0;
+	if (!allowed && info->mem_enabled) {
+		dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n");
+		return -ENXIO;
 	}
 
 	/*
@@ -932,11 +932,21 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
 void cxl_cor_error_detected(struct pci_dev *pdev)
 {
 	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct device *dev = &cxlds->cxlmd->dev;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return;
+		}
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
 
-	cxl_handle_endpoint_cor_ras(cxlds);
+		cxl_handle_endpoint_cor_ras(cxlds);
+	}
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
 
@@ -948,16 +958,25 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	struct device *dev = &cxlmd->dev;
 	bool ue;
 
-	if (cxlds->rcd)
-		cxl_handle_rdport_errors(cxlds);
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+		/*
+		 * A frozen channel indicates an impending reset which is fatal to
+		 * CXL.mem operation, and will likely crash the system. On the off
+		 * chance the situation is recoverable dump the status of the RAS
+		 * capability registers and bounce the active state of the memdev.
+		 */
+		ue = cxl_handle_endpoint_ras(cxlds);
+	}
 
-	/*
-	 * A frozen channel indicates an impending reset which is fatal to
-	 * CXL.mem operation, and will likely crash the system. On the off
-	 * chance the situation is recoverable dump the status of the RAS
-	 * capability registers and bounce the active state of the memdev.
-	 */
-	ue = cxl_handle_endpoint_ras(cxlds);
 
 	switch (state) {
 	case pci_channel_io_normal:
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index ce0e2d82bb2b..4c7fd2d5cccb 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -730,12 +730,17 @@ static int match_auto_decoder(struct device *dev, void *data)
 	return 0;
 }
 
-static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
-						   struct cxl_region *cxlr)
+static struct cxl_decoder *
+cxl_region_find_decoder(struct cxl_port *port,
+			struct cxl_endpoint_decoder *cxled,
+			struct cxl_region *cxlr)
 {
 	struct device *dev;
 	int id = 0;
 
+	if (port == cxled_to_port(cxled))
+		return &cxled->cxld;
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
 		dev = device_find_child(&port->dev, &cxlr->params,
 					match_auto_decoder);
@@ -753,8 +758,31 @@ static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
 	return to_cxl_decoder(dev);
 }
 
-static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
-					       struct cxl_region *cxlr)
+static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
+			  struct cxl_decoder *cxld)
+{
+	struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter);
+	struct cxl_decoder *cxld_iter = rr->decoder;
+
+	/*
+	 * Allow the out of order assembly of auto-discovered regions.
+	 * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders
+	 * in HPA order. Confirm that the decoder with the lesser HPA
+	 * starting address has the lesser id.
+	 */
+	dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n",
+		dev_name(&cxld->dev), cxld->id,
+		dev_name(&cxld_iter->dev), cxld_iter->id);
+
+	if (cxld_iter->id > cxld->id)
+		return true;
+
+	return false;
+}
+
+static struct cxl_region_ref *
+alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
+		 struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -764,16 +792,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
 	xa_for_each(&port->regions, index, iter) {
 		struct cxl_region_params *ip = &iter->region->params;
 
-		if (!ip->res)
+		if (!ip->res || ip->res->start < p->res->start)
 			continue;
 
-		if (ip->res->start > p->res->start) {
-			dev_dbg(&cxlr->dev,
-				"%s: HPA order violation %s:%pr vs %pr\n",
-				dev_name(&port->dev),
-				dev_name(&iter->region->dev), ip->res, p->res);
-			return ERR_PTR(-EBUSY);
+		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+			struct cxl_decoder *cxld;
+
+			cxld = cxl_region_find_decoder(port, cxled, cxlr);
+			if (auto_order_ok(port, iter->region, cxld))
+				continue;
 		}
+		dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n",
+			dev_name(&port->dev),
+			dev_name(&iter->region->dev), ip->res, p->res);
+
+		return ERR_PTR(-EBUSY);
 	}
 
 	cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL);
@@ -853,10 +886,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 {
 	struct cxl_decoder *cxld;
 
-	if (port == cxled_to_port(cxled))
-		cxld = &cxled->cxld;
-	else
-		cxld = cxl_region_find_decoder(port, cxlr);
+	cxld = cxl_region_find_decoder(port, cxled, cxlr);
 	if (!cxld) {
 		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
 			dev_name(&port->dev));
@@ -953,7 +983,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr);
+		cxl_rr = alloc_region_ref(port, cxlr, cxled);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 89445435303a..bdf117a33744 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -338,7 +338,7 @@ TRACE_EVENT(cxl_general_media,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
 
 		/* General Media */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -425,7 +425,7 @@ TRACE_EVENT(cxl_dram,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
 
 		/* DRAM */
 		__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -573,7 +573,7 @@ TRACE_EVENT(cxl_memory_module,
 
 	TP_fast_assign(
 		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
-		memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
+		__entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID;
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index b6017c0c57b4..003feebab79b 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -880,6 +880,8 @@ void cxl_switch_parse_cdat(struct cxl_port *port);
 int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
 				      struct access_coordinate *coord);
 
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 5303d6942b88..20fb3b35e89e 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -395,13 +395,11 @@ enum cxl_devtype {
 
 /**
  * struct cxl_dpa_perf - DPA performance property entry
- * @list - list entry
  * @dpa_range - range for DPA address
  * @coord - QoS performance data (i.e. latency, bandwidth)
  * @qos_class - QoS Class cookies
  */
 struct cxl_dpa_perf {
-	struct list_head list;
 	struct range dpa_range;
 	struct access_coordinate coord;
 	int qos_class;
@@ -471,8 +469,8 @@ struct cxl_dev_state {
  * @security: security driver state info
  * @fw: firmware upload / activation state
  * @mbox_send: @dev specific transport for transmitting mailbox commands
- * @ram_perf_list: performance data entries matched to RAM
- * @pmem_perf_list: performance data entries matched to PMEM
+ * @ram_perf: performance data entry matched to RAM partition
+ * @pmem_perf: performance data entry matched to PMEM partition
  *
  * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
  * details on capacity parameters.
@@ -494,8 +492,8 @@ struct cxl_memdev_state {
 	u64 next_volatile_bytes;
 	u64 next_persistent_bytes;
 
-	struct list_head ram_perf_list;
-	struct list_head pmem_perf_list;
+	struct cxl_dpa_perf ram_perf;
+	struct cxl_dpa_perf pmem_perf;
 
 	struct cxl_event_state event;
 	struct cxl_poison_state poison;
diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index c5c9d8e0d88d..0c79d9ce877c 100644
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -215,52 +215,6 @@ static ssize_t trigger_poison_list_store(struct device *dev,
 }
 static DEVICE_ATTR_WO(trigger_poison_list);
 
-static ssize_t ram_qos_class_show(struct device *dev,
-				  struct device_attribute *attr, char *buf)
-{
-	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
-	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
-	struct cxl_dpa_perf *dpa_perf;
-
-	if (!dev->driver)
-		return -ENOENT;
-
-	if (list_empty(&mds->ram_perf_list))
-		return -ENOENT;
-
-	dpa_perf = list_first_entry(&mds->ram_perf_list, struct cxl_dpa_perf,
-				    list);
-
-	return sysfs_emit(buf, "%d\n", dpa_perf->qos_class);
-}
-
-static struct device_attribute dev_attr_ram_qos_class =
-	__ATTR(qos_class, 0444, ram_qos_class_show, NULL);
-
-static ssize_t pmem_qos_class_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
-	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
-	struct cxl_dpa_perf *dpa_perf;
-
-	if (!dev->driver)
-		return -ENOENT;
-
-	if (list_empty(&mds->pmem_perf_list))
-		return -ENOENT;
-
-	dpa_perf = list_first_entry(&mds->pmem_perf_list, struct cxl_dpa_perf,
-				    list);
-
-	return sysfs_emit(buf, "%d\n", dpa_perf->qos_class);
-}
-
-static struct device_attribute dev_attr_pmem_qos_class =
-	__ATTR(qos_class, 0444, pmem_qos_class_show, NULL);
-
 static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -272,21 +226,11 @@ static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
 			      mds->poison.enabled_cmds))
 			return 0;
 
-	if (a == &dev_attr_pmem_qos_class.attr)
-		if (list_empty(&mds->pmem_perf_list))
-			return 0;
-
-	if (a == &dev_attr_ram_qos_class.attr)
-		if (list_empty(&mds->ram_perf_list))
-			return 0;
-
 	return a->mode;
 }
 
 static struct attribute *cxl_mem_attrs[] = {
 	&dev_attr_trigger_poison_list.attr,
-	&dev_attr_ram_qos_class.attr,
-	&dev_attr_pmem_qos_class.attr,
 	NULL
 };
 
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 233e7c42c161..2ff361e756d6 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -974,61 +974,6 @@ static struct pci_driver cxl_pci_driver = {
 	},
 };
 
-#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
-static void cxl_cper_event_call(enum cxl_event_type ev_type,
-				struct cxl_cper_event_rec *rec)
-{
-	struct cper_cxl_event_devid *device_id = &rec->hdr.device_id;
-	struct pci_dev *pdev __free(pci_dev_put) = NULL;
-	enum cxl_event_log_type log_type;
-	struct cxl_dev_state *cxlds;
-	unsigned int devfn;
-	u32 hdr_flags;
-
-	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
-	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
-					   device_id->bus_num, devfn);
-	if (!pdev)
-		return;
-
-	guard(pci_dev)(pdev);
-	if (pdev->driver != &cxl_pci_driver)
-		return;
-
-	cxlds = pci_get_drvdata(pdev);
-	if (!cxlds)
-		return;
-
-	/* Fabricate a log type */
-	hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
-	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
-
-	cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
-			       &uuid_null, &rec->event);
-}
-
-static int __init cxl_pci_driver_init(void)
-{
-	int rc;
-
-	rc = cxl_cper_register_callback(cxl_cper_event_call);
-	if (rc)
-		return rc;
-
-	rc = pci_register_driver(&cxl_pci_driver);
-	if (rc)
-		cxl_cper_unregister_callback(cxl_cper_event_call);
-
-	return rc;
-}
-
-static void __exit cxl_pci_driver_exit(void)
-{
-	pci_unregister_driver(&cxl_pci_driver);
-	cxl_cper_unregister_callback(cxl_cper_event_call);
-}
-
-module_init(cxl_pci_driver_init);
-module_exit(cxl_pci_driver_exit);
+module_pci_driver(cxl_pci_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index ee899f8e6721..4a63567e93ba 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -168,10 +168,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf)
 	if (vmf->pgoff > buffer->pagecount)
 		return VM_FAULT_SIGBUS;
 
-	vmf->page = buffer->pages[vmf->pgoff];
-	get_page(vmf->page);
-
-	return 0;
+	return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff]));
 }
 
 static const struct vm_operations_struct dma_heap_vm_ops = {
@@ -185,6 +182,8 @@ static int cma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
 	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
 		return -EINVAL;
 
+	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+
 	vma->vm_ops = &dma_heap_vm_ops;
 	vma->vm_private_data = buffer;
 
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fb89ecbf0cc5..40052d1bd0b5 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -222,8 +222,14 @@ struct atdma_sg {
  * @vd: pointer to the virtual dma descriptor.
  * @atchan: pointer to the atmel dma channel.
  * @total_len: total transaction byte count
- * @sg_len: number of sg entries.
+ * @sglen: number of sg entries.
  * @sg: array of sgs.
+ * @boundary: number of transfers to perform before the automatic address increment operation
+ * @dst_hole: value to add to the destination address when the boundary has been reached
+ * @src_hole: value to add to the source address when the boundary has been reached
+ * @memset_buffer: buffer used for the memset operation
+ * @memset_paddr: physical address of the buffer used for the memset operation
+ * @memset_vaddr: virtual address of the buffer used for the memset operation
  */
 struct at_desc {
 	struct				virt_dma_desc vd;
@@ -245,7 +251,10 @@ struct at_desc {
 /*--  Channels  --------------------------------------------------------*/
 
 /**
- * atc_status - information bits stored in channel status flag
+ * enum atc_status - information bits stored in channel status flag
+ *
+ * @ATC_IS_PAUSED: If channel is pauses
+ * @ATC_IS_CYCLIC: If channel is cyclic
  *
  * Manipulated with atomic operations.
  */
@@ -282,7 +291,6 @@ struct at_dma_chan {
 	u32			save_cfg;
 	u32			save_dscr;
 	struct dma_slave_config	dma_sconfig;
-	bool			cyclic;
 	struct at_desc		*desc;
 };
 
@@ -328,12 +336,12 @@ static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
 /**
  * struct at_dma - internal representation of an Atmel HDMA Controller
  * @dma_device: dmaengine dma_device object members
- * @atdma_devtype: identifier of DMA controller compatibility
- * @ch_regs: memory mapped register base
+ * @regs: memory mapped register base
  * @clk: dma controller clock
  * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
  * @lli_pool: hw lli table
+ * @memset_pool: hw memset pool
  * @chan: channels table to store at_dma_chan structures
  */
 struct at_dma {
@@ -626,6 +634,9 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
 
 /**
  * atc_get_llis_residue - Get residue for a hardware linked list transfer
+ * @atchan: pointer to an atmel hdmac channel.
+ * @desc: pointer to the descriptor for which the residue is calculated.
+ * @residue: residue to be set to dma_tx_state.
  *
  * Calculate the residue by removing the length of the Linked List Item (LLI)
  * already transferred from the total length. To get the current LLI we can use
@@ -661,10 +672,8 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
  * two DSCR values are different, we read again the CTRLA then the DSCR till two
  * consecutive read values from DSCR are equal or till the maximum trials is
  * reach. This algorithm is very unlikely not to find a stable value for DSCR.
- * @atchan: pointer to an atmel hdmac channel.
- * @desc: pointer to the descriptor for which the residue is calculated.
- * @residue: residue to be set to dma_tx_state.
- * Returns 0 on success, -errno otherwise.
+ *
+ * Returns: %0 on success, -errno otherwise.
  */
 static int atc_get_llis_residue(struct at_dma_chan *atchan,
 				struct at_desc *desc, u32 *residue)
@@ -731,7 +740,8 @@ static int atc_get_llis_residue(struct at_dma_chan *atchan,
  * @chan: DMA channel
  * @cookie: transaction identifier to check status of
  * @residue: residue to be updated.
- * Return 0 on success, -errono otherwise.
+ *
+ * Return: %0 on success, -errno otherwise.
  */
 static int atc_get_residue(struct dma_chan *chan, dma_cookie_t cookie,
 			   u32 *residue)
@@ -1710,7 +1720,7 @@ static void atc_issue_pending(struct dma_chan *chan)
  * atc_alloc_chan_resources - allocate resources for DMA channel
  * @chan: allocate descriptor resources for this channel
  *
- * return - the number of allocated descriptors
+ * Return: the number of allocated descriptors
  */
 static int atc_alloc_chan_resources(struct dma_chan *chan)
 {
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index b38786f0ad79..b75fdaffad9a 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote eDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
 	}
+
+	dw_edma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_RW_32(dw, chan->dir, doorbell,
 		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index 00b735a0202a..10e8f0715114 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw)
 
 static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 {
-	u32 num_ch = 0;
-	int id;
-
-	for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) {
-		if (GET_CH_32(dw, id, dir, ch_en) & BIT(0))
-			num_ch++;
-	}
-
-	if (num_ch > HDMA_V0_MAX_NR_CH)
-		num_ch = HDMA_V0_MAX_NR_CH;
-
-	return (u16)num_ch;
+	/*
+	 * The HDMA IP have no way to know the number of hardware channels
+	 * available, we set it to maximum channels and let the platform
+	 * set the right number of channels.
+	 */
+	return HDMA_V0_MAX_NR_CH;
 }
 
 static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan)
@@ -228,6 +222,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote HDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -242,7 +250,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		/* Interrupt enable&unmask - done, abort */
 		tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
 		      HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
-		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN;
+		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
+		if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+			tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN;
 		SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
 		/* Channel control */
 		SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN);
@@ -256,6 +266,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 	/* Set consumer cycle */
 	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
 		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
+
+	dw_hdma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
 }
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
index a974abdf8aaf..eab5fd7177e5 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -15,7 +15,7 @@
 #define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
 #define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
 #define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
-#define HDMA_V0_REMOTEL_STOP_INT_EN		BIT(3)
+#define HDMA_V0_REMOTE_STOP_INT_EN		BIT(3)
 #define HDMA_V0_ABORT_INT_MASK			BIT(2)
 #define HDMA_V0_STOP_INT_MASK			BIT(0)
 #define HDMA_V0_LINKLIST_EN			BIT(0)
diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
index 7958ac33e36c..5a8061a307cd 100644
--- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
+++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c
@@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan)
 	if (!dpaa2_chan->fd_pool)
 		goto err;
 
-	dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev,
-					      sizeof(struct dpaa2_fl_entry),
-					      sizeof(struct dpaa2_fl_entry), 0);
+	dpaa2_chan->fl_pool =
+		dma_pool_create("fl_pool", dev,
+				 sizeof(struct dpaa2_fl_entry) * 3,
+				 sizeof(struct dpaa2_fl_entry), 0);
+
 	if (!dpaa2_chan->fl_pool)
 		goto err_fd;
 
 	dpaa2_chan->sdd_pool =
 		dma_pool_create("sdd_pool", dev,
-				sizeof(struct dpaa2_qdma_sd_d),
+				sizeof(struct dpaa2_qdma_sd_d) * 2,
 				sizeof(struct dpaa2_qdma_sd_d), 0);
 	if (!dpaa2_chan->sdd_pool)
 		goto err_fl;
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b53f46245c37..793f1a7ad5e3 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -503,7 +503,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	if (fsl_chan->is_multi_fifo) {
 		/* set mloff to support multiple fifo */
 		burst = cfg->direction == DMA_DEV_TO_MEM ?
-				cfg->src_addr_width : cfg->dst_addr_width;
+				cfg->src_maxburst : cfg->dst_maxburst;
 		nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4));
 		/* enable DMLOE/SMLOE */
 		if (cfg->direction == DMA_MEM_TO_DEV) {
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index bb5221158a77..f5e216b157c7 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -30,8 +30,9 @@
 #define EDMA_TCD_ATTR_SSIZE(x)		(((x) & GENMASK(2, 0)) << 8)
 #define EDMA_TCD_ATTR_SMOD(x)		(((x) & GENMASK(4, 0)) << 11)
 
-#define EDMA_TCD_CITER_CITER(x)		((x) & GENMASK(14, 0))
-#define EDMA_TCD_BITER_BITER(x)		((x) & GENMASK(14, 0))
+#define EDMA_TCD_ITER_MASK		GENMASK(14, 0)
+#define EDMA_TCD_CITER_CITER(x)		((x) & EDMA_TCD_ITER_MASK)
+#define EDMA_TCD_BITER_BITER(x)		((x) & EDMA_TCD_ITER_MASK)
 
 #define EDMA_TCD_CSR_START		BIT(0)
 #define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 45cc419b1b4a..d36e28b9c767 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -10,6 +10,7 @@
  */
 
 #include <dt-bindings/dma/fsl-edma.h>
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -582,7 +583,8 @@ static int fsl_edma_probe(struct platform_device *pdev)
 					DMAENGINE_ALIGN_32_BYTES;
 
 	/* Per worst case 'nbytes = 1' take CITER as the max_seg_size */
-	dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff);
+	dma_set_max_seg_size(fsl_edma->dma_dev.dev,
+			     FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK));
 
 	fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index a1d0aa63142a..5005e138fc23 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -109,6 +109,7 @@
 #define FSL_QDMA_CMD_WTHROTL_OFFSET	20
 #define FSL_QDMA_CMD_DSEN_OFFSET	19
 #define FSL_QDMA_CMD_LWC_OFFSET		16
+#define FSL_QDMA_CMD_PF			BIT(17)
 
 /* Field definition for Descriptor status */
 #define QDMA_CCDF_STATUS_RTE		BIT(5)
@@ -160,6 +161,10 @@ struct fsl_qdma_format {
 			u8 __reserved1[2];
 			u8 cfg8b_w1;
 		} __packed;
+		struct {
+			__le32 __reserved2;
+			__le32 cmd;
+		} __packed;
 		__le64 data;
 	};
 } __packed;
@@ -354,7 +359,6 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
 static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 				      dma_addr_t dst, dma_addr_t src, u32 len)
 {
-	u32 cmd;
 	struct fsl_qdma_format *sdf, *ddf;
 	struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
 
@@ -383,14 +387,11 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 	/* This entry is the last entry. */
 	qdma_csgf_set_f(csgf_dest, len);
 	/* Descriptor Buffer */
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	sdf->data = QDMA_SDDF_CMD(cmd);
-
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	cmd |= cpu_to_le32(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET);
-	ddf->data = QDMA_SDDF_CMD(cmd);
+	sdf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       FSL_QDMA_CMD_PF);
+
+	ddf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       (FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET));
 }
 
 /*
@@ -514,11 +515,11 @@ static struct fsl_qdma_queue
 			queue_temp = queue_head + i + (j * queue_num);
 
 			queue_temp->cq =
-			dma_alloc_coherent(&pdev->dev,
-					   sizeof(struct fsl_qdma_format) *
-					   queue_size[i],
-					   &queue_temp->bus_addr,
-					   GFP_KERNEL);
+			dmam_alloc_coherent(&pdev->dev,
+					    sizeof(struct fsl_qdma_format) *
+					    queue_size[i],
+					    &queue_temp->bus_addr,
+					    GFP_KERNEL);
 			if (!queue_temp->cq)
 				return NULL;
 			queue_temp->block_base = fsl_qdma->block_base +
@@ -563,15 +564,14 @@ static struct fsl_qdma_queue
 	/*
 	 * Buffer for queue command
 	 */
-	status_head->cq = dma_alloc_coherent(&pdev->dev,
-					     sizeof(struct fsl_qdma_format) *
-					     status_size,
-					     &status_head->bus_addr,
-					     GFP_KERNEL);
-	if (!status_head->cq) {
-		devm_kfree(&pdev->dev, status_head);
+	status_head->cq = dmam_alloc_coherent(&pdev->dev,
+					      sizeof(struct fsl_qdma_format) *
+					      status_size,
+					      &status_head->bus_addr,
+					      GFP_KERNEL);
+	if (!status_head->cq)
 		return NULL;
-	}
+
 	status_head->n_cq = status_size;
 	status_head->virt_head = status_head->cq;
 	status_head->virt_tail = status_head->cq;
@@ -625,7 +625,7 @@ static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
 
 static int
 fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
-				 void *block,
+				 __iomem void *block,
 				 int id)
 {
 	bool duplicate;
@@ -1197,10 +1197,6 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 	if (!fsl_qdma->queue)
 		return -ENOMEM;
 
-	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
-	if (ret)
-		return ret;
-
 	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
 	if (fsl_qdma->irq_base < 0)
 		return fsl_qdma->irq_base;
@@ -1239,16 +1235,19 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, fsl_qdma);
 
-	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	ret = fsl_qdma_reg_init(fsl_qdma);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"Can't register NXP Layerscape qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
 		return ret;
 	}
 
-	ret = fsl_qdma_reg_init(fsl_qdma);
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
 	if (ret) {
-		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n");
 		return ret;
 	}
 
@@ -1268,8 +1267,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev)
 
 static void fsl_qdma_remove(struct platform_device *pdev)
 {
-	int i;
-	struct fsl_qdma_queue *status;
 	struct device_node *np = pdev->dev.of_node;
 	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
 
@@ -1277,12 +1274,6 @@ static void fsl_qdma_remove(struct platform_device *pdev)
 	fsl_qdma_cleanup_vchan(&fsl_qdma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_qdma->dma_dev);
-
-	for (i = 0; i < fsl_qdma->block_number; i++) {
-		status = fsl_qdma->status[i];
-		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) *
-				status->n_cq, status->cq, status->bus_addr);
-	}
 }
 
 static const struct of_device_id fsl_qdma_dt_ids[] = {
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 77f8885cf407..e5a94a93a3cc 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -345,7 +345,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 	spin_lock(&evl->lock);
 	status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = status.tail;
-	h = evl->head;
+	h = status.head;
 	size = evl->size;
 
 	while (h != t) {
diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c
index 9cfbd9b14c4c..f3f25ee676f3 100644
--- a/drivers/dma/idxd/debugfs.c
+++ b/drivers/dma/idxd/debugfs.c
@@ -68,9 +68,9 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 
 	spin_lock(&evl->lock);
 
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	evl_size = evl->size;
 
 	seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n",
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 47de3f93ff1e..d0f5db6cf1ed 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -300,7 +300,6 @@ struct idxd_evl {
 	unsigned int log_size;
 	/* The number of entries in the event log. */
 	u16 size;
-	u16 head;
 	unsigned long *bmap;
 	bool batch_fail[IDXD_MAX_BATCH_IDENT];
 };
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 14df1f1347a8..4954adc6bb60 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -343,7 +343,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd)
 static int idxd_init_evl(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
+	unsigned int evl_cache_size;
 	struct idxd_evl *evl;
+	const char *idxd_name;
 
 	if (idxd->hw.gen_cap.evl_support == 0)
 		return 0;
@@ -355,9 +357,16 @@ static int idxd_init_evl(struct idxd_device *idxd)
 	spin_lock_init(&evl->lock);
 	evl->size = IDXD_EVL_SIZE_MIN;
 
-	idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)),
-					    sizeof(struct idxd_evl_fault) + evl_ent_size(idxd),
-					    0, 0, NULL);
+	idxd_name = dev_name(idxd_confdev(idxd));
+	evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd);
+	/*
+	 * Since completion record in evl_cache will be copied to user
+	 * when handling completion record page fault, need to create
+	 * the cache suitable for user copy.
+	 */
+	idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size,
+						     0, 0, 0, evl_cache_size,
+						     NULL);
 	if (!idxd->evl_cache) {
 		kfree(evl);
 		return -ENOMEM;
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index c8a0aa874b11..348aa21389a9 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -367,9 +367,9 @@ static void process_evl_entries(struct idxd_device *idxd)
 	/* Clear interrupt pending bit */
 	iowrite32(evl_status.bits_upper32,
 		  idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	size = idxd->evl->size;
 
 	while (h != t) {
@@ -378,7 +378,6 @@ static void process_evl_entries(struct idxd_device *idxd)
 		h = (h + 1) % size;
 	}
 
-	evl->head = h;
 	evl_status.head = h;
 	iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	spin_unlock(&evl->lock);
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index 1ebfbe88e733..97ebc791a30b 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -747,8 +747,8 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	if (IS_ERR(xor_dev->clk))
 		return PTR_ERR(xor_dev->clk);
 
-	ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1,
-					     mv_xor_v2_set_msi_msg);
+	ret = platform_device_msi_init_and_alloc_irqs(&pdev->dev, 1,
+						      mv_xor_v2_set_msi_msg);
 	if (ret)
 		return ret;
 
@@ -851,7 +851,7 @@ free_hw_desq:
 			  xor_dev->desc_size * MV_XOR_V2_DESC_NUM,
 			  xor_dev->hw_desq_virt, xor_dev->hw_desq);
 free_msi_irqs:
-	platform_msi_domain_free_irqs(&pdev->dev);
+	platform_device_msi_free_irqs_all(&pdev->dev);
 	return ret;
 }
 
@@ -867,7 +867,7 @@ static void mv_xor_v2_remove(struct platform_device *pdev)
 
 	devm_free_irq(&pdev->dev, xor_dev->irq, xor_dev);
 
-	platform_msi_domain_free_irqs(&pdev->dev);
+	platform_device_msi_free_irqs_all(&pdev->dev);
 
 	tasklet_kill(&xor_dev->irq_tasklet);
 }
diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c
index 1aa65e5de0f3..f79240734807 100644
--- a/drivers/dma/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/ptdma/ptdma-dmaengine.c
@@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 	chan->vc.desc_free = pt_do_cleanup;
 	vchan_init(&chan->vc, dma_dev);
 
-	dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64));
-
 	ret = dma_async_device_register(dma_dev);
 	if (ret)
 		goto err_reg;
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index d63b93dc7047..202ac95227cb 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -696,7 +696,7 @@ static void hidma_free_msis(struct hidma_dev *dmadev)
 			devm_free_irq(dev, virq, &dmadev->lldev);
 	}
 
-	platform_msi_domain_free_irqs(dev);
+	platform_device_msi_free_irqs_all(dev);
 #endif
 }
 
@@ -706,8 +706,8 @@ static int hidma_request_msi(struct hidma_dev *dmadev,
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	int rc, i, virq;
 
-	rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
-					    hidma_write_msi_msg);
+	rc = platform_device_msi_init_and_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
+						     hidma_write_msi_msg);
 	if (rc)
 		return rc;
 
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index f1f920861fa9..5f8d2e93ff3f 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2404,6 +2404,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
@@ -2420,6 +2425,11 @@ static int edma_probe(struct platform_device *pdev)
 	if (irq > 0) {
 		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint",
 					  dev_name(dev));
+		if (!irq_name) {
+			ret = -ENOMEM;
+			goto err_disable_pm;
+		}
+
 		ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name,
 				       ecc);
 		if (ret) {
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 2841a539c264..6400d06588a2 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -3968,6 +3968,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 {
 	struct udma_chan *uc = to_udma_chan(&vc->chan);
 	struct udma_desc *d;
+	u8 status;
 
 	if (!vd)
 		return;
@@ -3977,12 +3978,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 	if (d->metadata_size)
 		udma_fetch_epib(uc, d);
 
-	/* Provide residue information for the client */
 	if (result) {
 		void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx);
 
 		if (cppi5_desc_get_type(desc_vaddr) ==
 		    CPPI5_INFO0_DESC_TYPE_VAL_HOST) {
+			/* Provide residue information for the client */
 			result->residue = d->residue -
 					  cppi5_hdesc_get_pktlen(desc_vaddr);
 			if (result->residue)
@@ -3991,7 +3992,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc,
 				result->result = DMA_TRANS_NOERROR;
 		} else {
 			result->residue = 0;
-			result->result = DMA_TRANS_NOERROR;
+			/* Propagate TR Response errors to the client */
+			status = d->hwdesc[0].tr_resp_base->status;
+			if (status)
+				result->result = DMA_TRANS_ABORTED;
+			else
+				result->result = DMA_TRANS_NOERROR;
 		}
 	}
 }
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 5152bd1b0daf..7f686d179fc9 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -508,6 +508,26 @@ err_pin_prop:
 	return ERR_PTR(ret);
 }
 
+static void dpll_netdev_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin)
+{
+	rtnl_lock();
+	rcu_assign_pointer(dev->dpll_pin, dpll_pin);
+	rtnl_unlock();
+}
+
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)
+{
+	WARN_ON(!dpll_pin);
+	dpll_netdev_pin_assign(dev, dpll_pin);
+}
+EXPORT_SYMBOL(dpll_netdev_pin_set);
+
+void dpll_netdev_pin_clear(struct net_device *dev)
+{
+	dpll_netdev_pin_assign(dev, NULL);
+}
+EXPORT_SYMBOL(dpll_netdev_pin_clear);
+
 /**
  * dpll_pin_get - find existing or create new dpll pin
  * @clock_id: clock_id of creator
@@ -564,7 +584,7 @@ void dpll_pin_put(struct dpll_pin *pin)
 		xa_destroy(&pin->parent_refs);
 		xa_erase(&dpll_pin_xa, pin->id);
 		dpll_pin_prop_free(&pin->prop);
-		kfree(pin);
+		kfree_rcu(pin, rcu);
 	}
 	mutex_unlock(&dpll_lock);
 }
diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h
index 717f715015c7..2b6d8ef1cdf3 100644
--- a/drivers/dpll/dpll_core.h
+++ b/drivers/dpll/dpll_core.h
@@ -47,6 +47,7 @@ struct dpll_device {
  * @prop:		pin properties copied from the registerer
  * @rclk_dev_name:	holds name of device when pin can recover clock from it
  * @refcount:		refcount
+ * @rcu:		rcu_head for kfree_rcu()
  **/
 struct dpll_pin {
 	u32 id;
@@ -57,6 +58,7 @@ struct dpll_pin {
 	struct xarray parent_refs;
 	struct dpll_pin_properties prop;
 	refcount_t refcount;
+	struct rcu_head rcu;
 };
 
 /**
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 314bb3775465..b57355e0c214 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -8,6 +8,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/netdevice.h>
 #include <net/genetlink.h>
 #include "dpll_core.h"
 #include "dpll_netlink.h"
@@ -48,18 +49,6 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id)
 }
 
 /**
- * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin
- * @pin: pin pointer
- *
- * Return: byte size of pin handle attribute for given pin.
- */
-size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
-{
-	return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */
-}
-EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size);
-
-/**
  * dpll_msg_add_pin_handle - attach pin handle attribute to a given message
  * @msg: pointer to sk_buff message to attach a pin handle
  * @pin: pin pointer
@@ -68,7 +57,7 @@ EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size);
  * * 0 - success
  * * -EMSGSIZE - no space in message to attach pin handle
  */
-int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+static int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
 {
 	if (!pin)
 		return 0;
@@ -76,7 +65,28 @@ int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
 		return -EMSGSIZE;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle);
+
+static struct dpll_pin *dpll_netdev_pin(const struct net_device *dev)
+{
+	return rcu_dereference_rtnl(dev->dpll_pin);
+}
+
+/**
+ * dpll_netdev_pin_handle_size - get size of pin handle attribute of a netdev
+ * @dev: netdev from which to get the pin
+ *
+ * Return: byte size of pin handle attribute, or 0 if @dev has no pin.
+ */
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
+{
+	return dpll_netdev_pin(dev) ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */
+}
+
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+			       const struct net_device *dev)
+{
+	return dpll_msg_add_pin_handle(msg, dpll_netdev_pin(dev));
+}
 
 static int
 dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll,
@@ -1199,6 +1209,7 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned long i;
 	int ret = 0;
 
+	mutex_lock(&dpll_lock);
 	xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
 				 ctx->idx) {
 		if (!dpll_pin_available(pin))
@@ -1218,6 +1229,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 		genlmsg_end(skb, hdr);
 	}
+	mutex_unlock(&dpll_lock);
+
 	if (ret == -EMSGSIZE) {
 		ctx->idx = i;
 		return skb->len;
@@ -1373,6 +1386,7 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned long i;
 	int ret = 0;
 
+	mutex_lock(&dpll_lock);
 	xa_for_each_marked_start(&dpll_device_xa, i, dpll, DPLL_REGISTERED,
 				 ctx->idx) {
 		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
@@ -1389,6 +1403,8 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 		genlmsg_end(skb, hdr);
 	}
+	mutex_unlock(&dpll_lock);
+
 	if (ret == -EMSGSIZE) {
 		ctx->idx = i;
 		return skb->len;
@@ -1439,20 +1455,6 @@ dpll_unlock_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 	mutex_unlock(&dpll_lock);
 }
 
-int dpll_lock_dumpit(struct netlink_callback *cb)
-{
-	mutex_lock(&dpll_lock);
-
-	return 0;
-}
-
-int dpll_unlock_dumpit(struct netlink_callback *cb)
-{
-	mutex_unlock(&dpll_lock);
-
-	return 0;
-}
-
 int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		      struct genl_info *info)
 {
diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c
index eaee5be7aa64..1e95f5397cfc 100644
--- a/drivers/dpll/dpll_nl.c
+++ b/drivers/dpll/dpll_nl.c
@@ -95,9 +95,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
 	},
 	{
 		.cmd	= DPLL_CMD_DEVICE_GET,
-		.start	= dpll_lock_dumpit,
 		.dumpit	= dpll_nl_device_get_dumpit,
-		.done	= dpll_unlock_dumpit,
 		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
 	},
 	{
@@ -129,9 +127,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
 	},
 	{
 		.cmd		= DPLL_CMD_PIN_GET,
-		.start		= dpll_lock_dumpit,
 		.dumpit		= dpll_nl_pin_get_dumpit,
-		.done		= dpll_unlock_dumpit,
 		.policy		= dpll_pin_get_dump_nl_policy,
 		.maxattr	= DPLL_A_PIN_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h
index 92d4c9c4f788..f491262bee4f 100644
--- a/drivers/dpll/dpll_nl.h
+++ b/drivers/dpll/dpll_nl.h
@@ -30,8 +30,6 @@ dpll_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 void
 dpll_pin_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		   struct genl_info *info);
-int dpll_lock_dumpit(struct netlink_callback *cb);
-int dpll_unlock_dumpit(struct netlink_callback *cb);
 
 int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info);
 int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 5a7f3fabee22..16c8de5050e5 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -78,6 +78,7 @@ config EDAC_GHES
 config EDAC_AMD64
 	tristate "AMD64 (Opteron, Athlon64)"
 	depends on AMD_NB && EDAC_DECODE_MCE
+	imply AMD_ATL
 	help
 	  Support for error detection and correction of DRAM ECC errors on
 	  the AMD64 families (>= K8) of memory controllers.
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 537b9987a431..1f3520d76861 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ras.h>
 #include "amd64_edac.h"
 #include <asm/amd_nb.h>
 
@@ -1051,281 +1052,6 @@ static int fixup_node_id(int node_id, struct mce *m)
 	return nid - gpu_node_map.base_node_id + 1;
 }
 
-/* Protect the PCI config register pairs used for DF indirect access. */
-static DEFINE_MUTEX(df_indirect_mutex);
-
-/*
- * Data Fabric Indirect Access uses FICAA/FICAD.
- *
- * Fabric Indirect Configuration Access Address (FICAA): Constructed based
- * on the device's Instance Id and the PCI function and register offset of
- * the desired register.
- *
- * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
- * and FICAD HI registers but so far we only need the LO register.
- *
- * Use Instance Id 0xFF to indicate a broadcast read.
- */
-#define DF_BROADCAST	0xFF
-static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
-{
-	struct pci_dev *F4;
-	u32 ficaa;
-	int err = -ENODEV;
-
-	if (node >= amd_nb_num())
-		goto out;
-
-	F4 = node_to_amd_nb(node)->link;
-	if (!F4)
-		goto out;
-
-	ficaa  = (instance_id == DF_BROADCAST) ? 0 : 1;
-	ficaa |= reg & 0x3FC;
-	ficaa |= (func & 0x7) << 11;
-	ficaa |= instance_id << 16;
-
-	mutex_lock(&df_indirect_mutex);
-
-	err = pci_write_config_dword(F4, 0x5C, ficaa);
-	if (err) {
-		pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
-		goto out_unlock;
-	}
-
-	err = pci_read_config_dword(F4, 0x98, lo);
-	if (err)
-		pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
-
-out_unlock:
-	mutex_unlock(&df_indirect_mutex);
-
-out:
-	return err;
-}
-
-static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
-{
-	return __df_indirect_read(node, func, reg, instance_id, lo);
-}
-
-static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo)
-{
-	return __df_indirect_read(node, func, reg, DF_BROADCAST, lo);
-}
-
-struct addr_ctx {
-	u64 ret_addr;
-	u32 tmp;
-	u16 nid;
-	u8 inst_id;
-};
-
-static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
-{
-	u64 dram_base_addr, dram_limit_addr, dram_hole_base;
-
-	u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
-	u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
-	u8 intlv_addr_sel, intlv_addr_bit;
-	u8 num_intlv_bits, hashed_bit;
-	u8 lgcy_mmio_hole_en, base = 0;
-	u8 cs_mask, cs_id = 0;
-	bool hash_enabled = false;
-
-	struct addr_ctx ctx;
-
-	memset(&ctx, 0, sizeof(ctx));
-
-	/* Start from the normalized address */
-	ctx.ret_addr = norm_addr;
-
-	ctx.nid = nid;
-	ctx.inst_id = umc;
-
-	/* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
-	if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp))
-		goto out_err;
-
-	/* Remove HiAddrOffset from normalized address, if enabled: */
-	if (ctx.tmp & BIT(0)) {
-		u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8;
-
-		if (norm_addr >= hi_addr_offset) {
-			ctx.ret_addr -= hi_addr_offset;
-			base = 1;
-		}
-	}
-
-	/* Read D18F0x110 (DramBaseAddress). */
-	if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp))
-		goto out_err;
-
-	/* Check if address range is valid. */
-	if (!(ctx.tmp & BIT(0))) {
-		pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
-			__func__, ctx.tmp);
-		goto out_err;
-	}
-
-	lgcy_mmio_hole_en = ctx.tmp & BIT(1);
-	intlv_num_chan	  = (ctx.tmp >> 4) & 0xF;
-	intlv_addr_sel	  = (ctx.tmp >> 8) & 0x7;
-	dram_base_addr	  = (ctx.tmp & GENMASK_ULL(31, 12)) << 16;
-
-	/* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
-	if (intlv_addr_sel > 3) {
-		pr_err("%s: Invalid interleave address select %d.\n",
-			__func__, intlv_addr_sel);
-		goto out_err;
-	}
-
-	/* Read D18F0x114 (DramLimitAddress). */
-	if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp))
-		goto out_err;
-
-	intlv_num_sockets = (ctx.tmp >> 8) & 0x1;
-	intlv_num_dies	  = (ctx.tmp >> 10) & 0x3;
-	dram_limit_addr	  = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
-
-	intlv_addr_bit = intlv_addr_sel + 8;
-
-	/* Re-use intlv_num_chan by setting it equal to log2(#channels) */
-	switch (intlv_num_chan) {
-	case 0:	intlv_num_chan = 0; break;
-	case 1: intlv_num_chan = 1; break;
-	case 3: intlv_num_chan = 2; break;
-	case 5:	intlv_num_chan = 3; break;
-	case 7:	intlv_num_chan = 4; break;
-
-	case 8: intlv_num_chan = 1;
-		hash_enabled = true;
-		break;
-	default:
-		pr_err("%s: Invalid number of interleaved channels %d.\n",
-			__func__, intlv_num_chan);
-		goto out_err;
-	}
-
-	num_intlv_bits = intlv_num_chan;
-
-	if (intlv_num_dies > 2) {
-		pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
-			__func__, intlv_num_dies);
-		goto out_err;
-	}
-
-	num_intlv_bits += intlv_num_dies;
-
-	/* Add a bit if sockets are interleaved. */
-	num_intlv_bits += intlv_num_sockets;
-
-	/* Assert num_intlv_bits <= 4 */
-	if (num_intlv_bits > 4) {
-		pr_err("%s: Invalid interleave bits %d.\n",
-			__func__, num_intlv_bits);
-		goto out_err;
-	}
-
-	if (num_intlv_bits > 0) {
-		u64 temp_addr_x, temp_addr_i, temp_addr_y;
-		u8 die_id_bit, sock_id_bit, cs_fabric_id;
-
-		/*
-		 * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
-		 * This is the fabric id for this coherent slave. Use
-		 * umc/channel# as instance id of the coherent slave
-		 * for FICAA.
-		 */
-		if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp))
-			goto out_err;
-
-		cs_fabric_id = (ctx.tmp >> 8) & 0xFF;
-		die_id_bit   = 0;
-
-		/* If interleaved over more than 1 channel: */
-		if (intlv_num_chan) {
-			die_id_bit = intlv_num_chan;
-			cs_mask	   = (1 << die_id_bit) - 1;
-			cs_id	   = cs_fabric_id & cs_mask;
-		}
-
-		sock_id_bit = die_id_bit;
-
-		/* Read D18F1x208 (SystemFabricIdMask). */
-		if (intlv_num_dies || intlv_num_sockets)
-			if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp))
-				goto out_err;
-
-		/* If interleaved over more than 1 die. */
-		if (intlv_num_dies) {
-			sock_id_bit  = die_id_bit + intlv_num_dies;
-			die_id_shift = (ctx.tmp >> 24) & 0xF;
-			die_id_mask  = (ctx.tmp >> 8) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
-		}
-
-		/* If interleaved over more than 1 socket. */
-		if (intlv_num_sockets) {
-			socket_id_shift	= (ctx.tmp >> 28) & 0xF;
-			socket_id_mask	= (ctx.tmp >> 16) & 0xFF;
-
-			cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
-		}
-
-		/*
-		 * The pre-interleaved address consists of XXXXXXIIIYYYYY
-		 * where III is the ID for this CS, and XXXXXXYYYYY are the
-		 * address bits from the post-interleaved address.
-		 * "num_intlv_bits" has been calculated to tell us how many "I"
-		 * bits there are. "intlv_addr_bit" tells us how many "Y" bits
-		 * there are (where "I" starts).
-		 */
-		temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0);
-		temp_addr_i = (cs_id << intlv_addr_bit);
-		temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
-		ctx.ret_addr    = temp_addr_x | temp_addr_i | temp_addr_y;
-	}
-
-	/* Add dram base address */
-	ctx.ret_addr += dram_base_addr;
-
-	/* If legacy MMIO hole enabled */
-	if (lgcy_mmio_hole_en) {
-		if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp))
-			goto out_err;
-
-		dram_hole_base = ctx.tmp & GENMASK(31, 24);
-		if (ctx.ret_addr >= dram_hole_base)
-			ctx.ret_addr += (BIT_ULL(32) - dram_hole_base);
-	}
-
-	if (hash_enabled) {
-		/* Save some parentheses and grab ls-bit at the end. */
-		hashed_bit =	(ctx.ret_addr >> 12) ^
-				(ctx.ret_addr >> 18) ^
-				(ctx.ret_addr >> 21) ^
-				(ctx.ret_addr >> 30) ^
-				cs_id;
-
-		hashed_bit &= BIT(0);
-
-		if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0)))
-			ctx.ret_addr ^= BIT(intlv_addr_bit);
-	}
-
-	/* Is calculated system address is above DRAM limit address? */
-	if (ctx.ret_addr > dram_limit_addr)
-		goto out_err;
-
-	*sys_addr = ctx.ret_addr;
-	return 0;
-
-out_err:
-	return -EINVAL;
-}
-
 static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16);
 
 /*
@@ -1915,7 +1641,7 @@ ddr3:
 /* On F10h and later ErrAddr is MC4_ADDR[47:1] */
 static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 {
-	u16 mce_nid = topology_die_id(m->extcpu);
+	u16 mce_nid = topology_amd_node_id(m->extcpu);
 	struct mem_ctl_info *mci;
 	u8 start_bit = 1;
 	u8 end_bit   = 47;
@@ -3073,9 +2799,10 @@ static void decode_umc_error(int node_id, struct mce *m)
 {
 	u8 ecc_type = (m->status >> 45) & 0x3;
 	struct mem_ctl_info *mci;
+	unsigned long sys_addr;
 	struct amd64_pvt *pvt;
+	struct atl_err a_err;
 	struct err_info err;
-	u64 sys_addr;
 
 	node_id = fixup_node_id(node_id, m);
 
@@ -3106,7 +2833,12 @@ static void decode_umc_error(int node_id, struct mce *m)
 
 	pvt->ops->get_err_info(m, &err);
 
-	if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) {
+	a_err.addr = m->addr;
+	a_err.ipid = m->ipid;
+	a_err.cpu  = m->extcpu;
+
+	sys_addr = amd_convert_umc_mca_addr_to_sys_addr(&a_err);
+	if (IS_ERR_VALUE(sys_addr)) {
 		err.err_code = ERR_NORM_ADDR;
 		goto log_error;
 	}
@@ -3446,7 +3178,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid)
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		if (topology_die_id(cpu) == nid)
+		if (topology_amd_node_id(cpu) == nid)
 			cpumask_set_cpu(cpu, mask);
 }
 
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 2b83d6de9352..3fd22a1eb1a9 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -951,6 +951,7 @@ static const struct x86_cpu_id i10nm_cpuids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(EMERALDRAPIDS_X,	X86_STEPPINGS(0x0, 0xf), &spr_cfg),
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(GRANITERAPIDS_X,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
 	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT_X,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT,	X86_STEPPINGS(0x0, 0xf), &gnr_cfg),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids);
diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 2b0ecdeba5cd..cdd8480e7368 100644
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -238,6 +238,7 @@ static struct work_struct ecclog_work;
 #define DID_ADL_N_SKU9	0x4678
 #define DID_ADL_N_SKU10	0x4679
 #define DID_ADL_N_SKU11	0x467c
+#define DID_ADL_N_SKU12	0x4632
 
 /* Compute die IDs for Raptor Lake-P with IBECC */
 #define DID_RPL_P_SKU1	0xa706
@@ -583,6 +584,7 @@ static const struct pci_device_id igen6_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg },
 	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg },
 	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg },
+	{ PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), (kernel_ulong_t)&adl_n_cfg },
 	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg },
 	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg },
 	{ PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg },
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index ec8b6c9fedfd..8130c3dc64da 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -584,7 +584,7 @@ static void decode_mc3_mce(struct mce *m)
 static void decode_mc4_mce(struct mce *m)
 {
 	unsigned int fam = x86_family(m->cpuid);
-	int node_id = topology_die_id(m->extcpu);
+	int node_id = topology_amd_node_id(m->extcpu);
 	u16 ec = EC(m->status);
 	u8 xec = XEC(m->status, 0x1f);
 	u8 offset = 0;
@@ -746,7 +746,7 @@ static void decode_smca_error(struct mce *m)
 
 	if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) &&
 	    xec == 0 && decode_dram_ecc)
-		decode_dram_ecc(topology_die_id(m->extcpu), m);
+		decode_dram_ecc(topology_amd_node_id(m->extcpu), m);
 }
 
 static inline void amd_decode_err_code(u16 ec)
diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index 709babce43ba..5527055b0964 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -1324,11 +1324,9 @@ static int mc_probe(struct platform_device *pdev)
 	struct synps_edac_priv *priv;
 	struct mem_ctl_info *mci;
 	void __iomem *baseaddr;
-	struct resource *res;
 	int rc;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	baseaddr = devm_ioremap_resource(&pdev->dev, res);
+	baseaddr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(baseaddr))
 		return PTR_ERR(baseaddr);
 
diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 62caf454b567..1688a5050f63 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -42,8 +42,11 @@
 
 #define ECCW0_FLIP_CTRL				0x109C
 #define ECCW0_FLIP0_OFFSET			0x10A0
+#define ECCW0_FLIP0_BITS			31
+#define ECCW0_FLIP1_OFFSET			0x10A4
 #define ECCW1_FLIP_CTRL				0x10AC
 #define ECCW1_FLIP0_OFFSET			0x10B0
+#define ECCW1_FLIP1_OFFSET			0x10B4
 #define ECCR0_CERR_STAT_OFFSET			0x10BC
 #define ECCR0_CE_ADDR_LO_OFFSET			0x10C0
 #define ECCR0_CE_ADDR_HI_OFFSET			0x10C4
@@ -116,9 +119,6 @@
 #define XDDR_BUS_WIDTH_32			1
 #define XDDR_BUS_WIDTH_16			2
 
-#define ECC_CEPOISON_MASK			0x1
-#define ECC_UEPOISON_MASK			0x3
-
 #define XDDR_MAX_ROW_CNT			18
 #define XDDR_MAX_COL_CNT			10
 #define XDDR_MAX_RANK_CNT			2
@@ -133,6 +133,7 @@
  * https://docs.xilinx.com/r/en-US/am012-versal-register-reference/PCSR_LOCK-XRAM_SLCR-Register
  */
 #define PCSR_UNLOCK_VAL				0xF9E8D7C6
+#define PCSR_LOCK_VAL				1
 #define XDDR_ERR_TYPE_CE			0
 #define XDDR_ERR_TYPE_UE			1
 
@@ -142,6 +143,7 @@
 #define XILINX_DRAM_SIZE_12G			3
 #define XILINX_DRAM_SIZE_16G			4
 #define XILINX_DRAM_SIZE_32G			5
+#define NUM_UE_BITPOS				2
 
 /**
  * struct ecc_error_info - ECC error log information.
@@ -479,7 +481,7 @@ static void err_callback(const u32 *payload, void *data)
 	writel(regval, priv->ddrmc_baseaddr + XDDR_ISR_OFFSET);
 
 	/* Lock the PCSR registers */
-	writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
 	edac_dbg(3, "Total error count CE %d UE %d\n",
 		 priv->ce_cnt, priv->ue_cnt);
 }
@@ -650,7 +652,7 @@ static void enable_intr(struct edac_priv *priv)
 	writel(XDDR_IRQ_UE_MASK,
 	       priv->ddrmc_baseaddr + XDDR_IRQ1_EN_OFFSET);
 	/* Lock the PCSR registers */
-	writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
 }
 
 static void disable_intr(struct edac_priv *priv)
@@ -663,7 +665,7 @@ static void disable_intr(struct edac_priv *priv)
 	       priv->ddrmc_baseaddr + XDDR_IRQ_DIS_OFFSET);
 
 	/* Lock the PCSR registers */
-	writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
 }
 
 #define to_mci(k) container_of(k, struct mem_ctl_info, dev)
@@ -734,38 +736,63 @@ static void poison_setup(struct edac_priv *priv)
 	writel(regval, priv->ddrmc_noc_baseaddr + XDDR_NOC_REG_ADEC15_OFFSET);
 }
 
-static ssize_t xddr_inject_data_poison_store(struct mem_ctl_info *mci,
-					     const char __user *data)
+static void xddr_inject_data_ce_store(struct mem_ctl_info *mci, u8 ce_bitpos)
 {
+	u32 ecc0_flip0, ecc1_flip0, ecc0_flip1, ecc1_flip1;
 	struct edac_priv *priv = mci->pvt_info;
 
-	writel(0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET);
-	writel(0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET);
-
-	if (strncmp(data, "CE", 2) == 0) {
-		writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr +
-		       ECCW0_FLIP0_OFFSET);
-		writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr +
-		       ECCW1_FLIP0_OFFSET);
+	if (ce_bitpos < ECCW0_FLIP0_BITS) {
+		ecc0_flip0 = BIT(ce_bitpos);
+		ecc1_flip0 = BIT(ce_bitpos);
+		ecc0_flip1 = 0;
+		ecc1_flip1 = 0;
 	} else {
-		writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr +
-		       ECCW0_FLIP0_OFFSET);
-		writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr +
-		       ECCW1_FLIP0_OFFSET);
+		ce_bitpos = ce_bitpos - ECCW0_FLIP0_BITS;
+		ecc0_flip1 = BIT(ce_bitpos);
+		ecc1_flip1 = BIT(ce_bitpos);
+		ecc0_flip0 = 0;
+		ecc1_flip0 = 0;
 	}
 
-	/* Lock the PCSR registers */
-	writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
-
-	return 0;
+	writel(ecc0_flip0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET);
+	writel(ecc1_flip0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET);
+	writel(ecc0_flip1, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET);
+	writel(ecc1_flip1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET);
 }
 
-static ssize_t inject_data_poison_store(struct file *file, const char __user *data,
-					size_t count, loff_t *ppos)
+/*
+ * To inject a correctable error, the following steps are needed:
+ *
+ * - Write the correctable error bit position value:
+ *	echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ce
+ *
+ * poison_setup() derives the row, column, bank, group and rank and
+ * writes to the ADEC registers based on the address given by the user.
+ *
+ * The ADEC12 and ADEC13 are mask registers; write 0 to make sure default
+ * configuration is there and no addresses are masked.
+ *
+ * The row, column, bank, group and rank registers are written to the
+ * match ADEC bit to generate errors at the particular address. ADEC14
+ * and ADEC15 have the match bits.
+ *
+ * xddr_inject_data_ce_store() updates the ECC FLIP registers with the
+ * bits to be corrupted based on the bit position given by the user.
+ *
+ * Upon doing a read to the address the errors are injected.
+ */
+static ssize_t inject_data_ce_store(struct file *file, const char __user *data,
+				    size_t count, loff_t *ppos)
 {
 	struct device *dev = file->private_data;
 	struct mem_ctl_info *mci = to_mci(dev);
 	struct edac_priv *priv = mci->pvt_info;
+	u8 ce_bitpos;
+	int ret;
+
+	ret = kstrtou8_from_user(data, count, 0, &ce_bitpos);
+	if (ret)
+		return ret;
 
 	/* Unlock the PCSR registers */
 	writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
@@ -773,17 +800,110 @@ static ssize_t inject_data_poison_store(struct file *file, const char __user *da
 
 	poison_setup(priv);
 
+	xddr_inject_data_ce_store(mci, ce_bitpos);
+	ret = count;
+
 	/* Lock the PCSR registers */
-	writel(1, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET);
+
+	return ret;
+}
+
+static const struct file_operations xddr_inject_ce_fops = {
+	.open = simple_open,
+	.write = inject_data_ce_store,
+	.llseek = generic_file_llseek,
+};
+
+static void xddr_inject_data_ue_store(struct mem_ctl_info *mci, u32 val0, u32 val1)
+{
+	struct edac_priv *priv = mci->pvt_info;
+
+	writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET);
+	writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET);
+	writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET);
+	writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET);
+}
+
+/*
+ * To inject an uncorrectable error, the following steps are needed:
+ *	echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ue
+ *
+ * poison_setup() derives the row, column, bank, group and rank and
+ * writes to the ADEC registers based on the address given by the user.
+ *
+ * The ADEC12 and ADEC13 are mask registers; write 0 so that none of the
+ * addresses are masked. The row, column, bank, group and rank registers
+ * are written to the match ADEC bit to generate errors at the
+ * particular address. ADEC14 and ADEC15 have the match bits.
+ *
+ * xddr_inject_data_ue_store() updates the ECC FLIP registers with the
+ * bits to be corrupted based on the bit position given by the user. For
+ * uncorrectable errors
+ * 2 bit errors are injected.
+ *
+ * Upon doing a read to the address the errors are injected.
+ */
+static ssize_t inject_data_ue_store(struct file *file, const char __user *data,
+				    size_t count, loff_t *ppos)
+{
+	struct device *dev = file->private_data;
+	struct mem_ctl_info *mci = to_mci(dev);
+	struct edac_priv *priv = mci->pvt_info;
+	char buf[6], *pbuf, *token[2];
+	u32 val0 = 0, val1 = 0;
+	u8 len, ue0, ue1;
+	int i, ret;
+
+	len = min_t(size_t, count, sizeof(buf));
+	if (copy_from_user(buf, data, len))
+		return -EFAULT;
+
+	buf[len] = '\0';
+	pbuf = &buf[0];
+	for (i = 0; i < NUM_UE_BITPOS; i++)
+		token[i] = strsep(&pbuf, ",");
+
+	ret = kstrtou8(token[0], 0, &ue0);
+	if (ret)
+		return ret;
+
+	ret = kstrtou8(token[1], 0, &ue1);
+	if (ret)
+		return ret;
+
+	if (ue0 < ECCW0_FLIP0_BITS) {
+		val0 = BIT(ue0);
+	} else {
+		ue0 = ue0 - ECCW0_FLIP0_BITS;
+		val1 = BIT(ue0);
+	}
+
+	if (ue1 < ECCW0_FLIP0_BITS) {
+		val0 |= BIT(ue1);
+	} else {
+		ue1 = ue1 - ECCW0_FLIP0_BITS;
+		val1 |= BIT(ue1);
+	}
 
-	xddr_inject_data_poison_store(mci, data);
+	/* Unlock the PCSR registers */
+	writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_UNLOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET);
 
+	poison_setup(priv);
+
+	xddr_inject_data_ue_store(mci, val0, val1);
+
+	/* Lock the PCSR registers */
+	writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET);
+	writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET);
 	return count;
 }
 
-static const struct file_operations xddr_inject_enable_fops = {
+static const struct file_operations xddr_inject_ue_fops = {
 	.open = simple_open,
-	.write = inject_data_poison_store,
+	.write = inject_data_ue_store,
 	.llseek = generic_file_llseek,
 };
 
@@ -795,8 +915,17 @@ static void create_debugfs_attributes(struct mem_ctl_info *mci)
 	if (!priv->debugfs)
 		return;
 
-	edac_debugfs_create_file("inject_error", 0200, priv->debugfs,
-				 &mci->dev, &xddr_inject_enable_fops);
+	if (!edac_debugfs_create_file("inject_ce", 0200, priv->debugfs,
+				      &mci->dev, &xddr_inject_ce_fops)) {
+		debugfs_remove_recursive(priv->debugfs);
+		return;
+	}
+
+	if (!edac_debugfs_create_file("inject_ue", 0200, priv->debugfs,
+				      &mci->dev, &xddr_inject_ue_fops)) {
+		debugfs_remove_recursive(priv->debugfs);
+		return;
+	}
 	debugfs_create_x64("address", 0600, priv->debugfs,
 			   &priv->err_inject_addr);
 	mci->debugfs = priv->debugfs;
@@ -1031,7 +1160,7 @@ free_edac_mc:
 	return rc;
 }
 
-static int mc_remove(struct platform_device *pdev)
+static void mc_remove(struct platform_device *pdev)
 {
 	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
 	struct edac_priv *priv = mci->pvt_info;
@@ -1049,8 +1178,6 @@ static int mc_remove(struct platform_device *pdev)
 			      XPM_EVENT_ERROR_MASK_DDRMC_NCR, err_callback, mci);
 	edac_mc_del_mc(&pdev->dev);
 	edac_mc_free(mci);
-
-	return 0;
 }
 
 static struct platform_driver xilinx_ddr_edac_mc_driver = {
@@ -1059,7 +1186,7 @@ static struct platform_driver xilinx_ddr_edac_mc_driver = {
 		.of_match_table = xlnx_edac_match,
 	},
 	.probe = mc_probe,
-	.remove = mc_remove,
+	.remove_new = mc_remove,
 };
 
 module_platform_driver(xilinx_ddr_edac_mc_driver);
diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 6ac5ff20a2fe..401a77e3b5fa 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work)
 	 */
 	card->bm_generation = generation;
 
-	if (root_device == NULL) {
+	if (card->gap_count == 0) {
+		/*
+		 * If self IDs have inconsistent gap counts, do a
+		 * bus reset ASAP. The config rom read might never
+		 * complete, so don't wait for it. However, still
+		 * send a PHY configuration packet prior to the
+		 * bus reset. The PHY configuration packet might
+		 * fail, but 1394-2008 8.4.5.2 explicitly permits
+		 * it in this case, so it should be safe to try.
+		 */
+		new_root_id = local_id;
+		/*
+		 * We must always send a bus reset if the gap count
+		 * is inconsistent, so bypass the 5-reset limit.
+		 */
+		card->bm_retries = 0;
+	} else if (root_device == NULL) {
 		/*
 		 * Either link_on is false, or we failed to read the
 		 * config rom.  In either case, pick another root.
@@ -484,7 +500,19 @@ static void bm_work(struct work_struct *work)
 		fw_notice(card, "phy config: new root=%x, gap_count=%d\n",
 			  new_root_id, gap_count);
 		fw_send_phy_config(card, new_root_id, generation, gap_count);
-		reset_bus(card, true);
+		/*
+		 * Where possible, use a short bus reset to minimize
+		 * disruption to isochronous transfers. But in the event
+		 * of a gap count inconsistency, use a long bus reset.
+		 *
+		 * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus
+		 * may set different gap counts after a bus reset. On a mixed
+		 * 1394/1394a bus, a short bus reset can get doubled. Some
+		 * nodes may treat the double reset as one bus reset and others
+		 * may treat it as two, causing a gap count inconsistency
+		 * again. Using a long bus reset prevents this.
+		 */
+		reset_bus(card, card->gap_count != 0);
 		/* Will allocate broadcast channel after the reset. */
 		goto out;
 	}
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 0547253d16fe..7d3346b3a2bf 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -118,10 +118,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size)
  * @buf:	where to put the string
  * @size:	size of @buf, in bytes
  *
- * The string is taken from a minimal ASCII text descriptor leaf after
- * the immediate entry with @key.  The string is zero-terminated.
- * An overlong string is silently truncated such that it and the
- * zero byte fit into @size.
+ * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the
+ * @key. The string is zero-terminated. An overlong string is silently truncated such that it
+ * and the zero byte fit into @size.
  *
  * Returns strlen(buf) or a negative error code.
  */
@@ -368,8 +367,17 @@ static ssize_t show_text_leaf(struct device *dev,
 	for (i = 0; i < ARRAY_SIZE(directories) && !!directories[i]; ++i) {
 		int result = fw_csr_string(directories[i], attr->key, buf, bufsize);
 		// Detected.
-		if (result >= 0)
+		if (result >= 0) {
 			ret = result;
+		} else if (i == 0 && attr->key == CSR_VENDOR) {
+			// Sony DVMC-DA1 has configuration ROM such that the descriptor leaf entry
+			// in the root directory follows to the directory entry for vendor ID
+			// instead of the immediate value for vendor ID.
+			result = fw_csr_string(directories[i], CSR_DIRECTORY | attr->key, buf,
+					       bufsize);
+			if (result >= 0)
+				ret = result;
+		}
 	}
 
 	if (ret >= 0) {
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 9db9290c3269..7bc71f4be64a 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3773,6 +3773,7 @@ static int pci_probe(struct pci_dev *dev,
 	return 0;
 
  fail_msi:
+	devm_free_irq(&dev->dev, dev->irq, ohci);
 	pci_disable_msi(dev);
 
 	return err;
@@ -3800,6 +3801,7 @@ static void pci_remove(struct pci_dev *dev)
 
 	software_reset(ohci);
 
+	devm_free_irq(&dev->dev, dev->irq, ohci);
 	pci_disable_msi(dev);
 
 	dev_notice(&dev->dev, "removing fw-ohci device\n");
diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c
index 1c7940ba5539..2f557e90f2eb 100644
--- a/drivers/firmware/arm_ffa/bus.c
+++ b/drivers/firmware/arm_ffa/bus.c
@@ -105,7 +105,7 @@ static struct attribute *ffa_device_attributes_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ffa_device_attributes);
 
-struct bus_type ffa_bus_type = {
+const struct bus_type ffa_bus_type = {
 	.name		= "arm_ffa",
 	.match		= ffa_device_match,
 	.probe		= ffa_device_probe,
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index c15928b8c5cc..77c78be6e79c 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -141,6 +141,17 @@ out:
 	return ret;
 }
 
+static int scmi_protocol_table_register(const struct scmi_device_id *id_table)
+{
+	int ret = 0;
+	const struct scmi_device_id *entry;
+
+	for (entry = id_table; entry->name && ret == 0; entry++)
+		ret = scmi_protocol_device_request(entry);
+
+	return ret;
+}
+
 /**
  * scmi_protocol_device_unrequest  - Helper to unrequest a device
  *
@@ -186,6 +197,15 @@ static void scmi_protocol_device_unrequest(const struct scmi_device_id *id_table
 	mutex_unlock(&scmi_requested_devices_mtx);
 }
 
+static void
+scmi_protocol_table_unregister(const struct scmi_device_id *id_table)
+{
+	const struct scmi_device_id *entry;
+
+	for (entry = id_table; entry->name; entry++)
+		scmi_protocol_device_unrequest(entry);
+}
+
 static const struct scmi_device_id *
 scmi_dev_match_id(struct scmi_device *scmi_dev, struct scmi_driver *scmi_drv)
 {
@@ -263,7 +283,7 @@ static void scmi_dev_remove(struct device *dev)
 		scmi_drv->remove(scmi_dev);
 }
 
-struct bus_type scmi_bus_type = {
+const struct bus_type scmi_bus_type = {
 	.name =	"scmi_protocol",
 	.match = scmi_dev_match,
 	.probe = scmi_dev_probe,
@@ -279,7 +299,7 @@ int scmi_driver_register(struct scmi_driver *driver, struct module *owner,
 	if (!driver->probe)
 		return -EINVAL;
 
-	retval = scmi_protocol_device_request(driver->id_table);
+	retval = scmi_protocol_table_register(driver->id_table);
 	if (retval)
 		return retval;
 
@@ -299,7 +319,7 @@ EXPORT_SYMBOL_GPL(scmi_driver_register);
 void scmi_driver_unregister(struct scmi_driver *driver)
 {
 	driver_unregister(&driver->driver);
-	scmi_protocol_device_unrequest(driver->id_table);
+	scmi_protocol_table_unregister(driver->id_table);
 }
 EXPORT_SYMBOL_GPL(scmi_driver_unregister);
 
diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c
index e2050adbf85c..134019297d08 100644
--- a/drivers/firmware/arm_scmi/clock.c
+++ b/drivers/firmware/arm_scmi/clock.c
@@ -13,7 +13,7 @@
 #include "notify.h"
 
 /* Updated only after ALL the mandatory features for that version are merged */
-#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x20000
+#define SCMI_PROTOCOL_SUPPORTED_VERSION		0x30000
 
 enum scmi_clock_protocol_cmd {
 	CLOCK_ATTRIBUTES = 0x3,
@@ -28,8 +28,13 @@ enum scmi_clock_protocol_cmd {
 	CLOCK_POSSIBLE_PARENTS_GET = 0xC,
 	CLOCK_PARENT_SET = 0xD,
 	CLOCK_PARENT_GET = 0xE,
+	CLOCK_GET_PERMISSIONS = 0xF,
 };
 
+#define CLOCK_STATE_CONTROL_ALLOWED	BIT(31)
+#define CLOCK_PARENT_CONTROL_ALLOWED	BIT(30)
+#define CLOCK_RATE_CONTROL_ALLOWED	BIT(29)
+
 enum clk_state {
 	CLK_STATE_DISABLE,
 	CLK_STATE_ENABLE,
@@ -49,6 +54,8 @@ struct scmi_msg_resp_clock_attributes {
 #define SUPPORTS_RATE_CHANGE_REQUESTED_NOTIF(x)	((x) & BIT(30))
 #define SUPPORTS_EXTENDED_NAMES(x)		((x) & BIT(29))
 #define SUPPORTS_PARENT_CLOCK(x)		((x) & BIT(28))
+#define SUPPORTS_EXTENDED_CONFIG(x)		((x) & BIT(27))
+#define SUPPORTS_GET_PERMISSIONS(x)		((x) & BIT(1))
 	u8 name[SCMI_SHORT_NAME_MAX_SIZE];
 	__le32 clock_enable_latency;
 };
@@ -152,14 +159,18 @@ struct clock_info {
 	u32 version;
 	int num_clocks;
 	int max_async_req;
+	bool notify_rate_changed_cmd;
+	bool notify_rate_change_requested_cmd;
 	atomic_t cur_async_req;
 	struct scmi_clock_info *clk;
 	int (*clock_config_set)(const struct scmi_protocol_handle *ph,
 				u32 clk_id, enum clk_state state,
-				u8 oem_type, u32 oem_val, bool atomic);
+				enum scmi_clock_oem_config oem_type,
+				u32 oem_val, bool atomic);
 	int (*clock_config_get)(const struct scmi_protocol_handle *ph,
-				u32 clk_id, u8 oem_type, u32 *attributes,
-				bool *enabled, u32 *oem_val, bool atomic);
+				u32 clk_id, enum scmi_clock_oem_config oem_type,
+				u32 *attributes, bool *enabled, u32 *oem_val,
+				bool atomic);
 };
 
 static enum scmi_clock_protocol_cmd evt_2_cmd[] = {
@@ -167,6 +178,15 @@ static enum scmi_clock_protocol_cmd evt_2_cmd[] = {
 	CLOCK_RATE_CHANGE_REQUESTED_NOTIFY,
 };
 
+static inline struct scmi_clock_info *
+scmi_clock_domain_lookup(struct clock_info *ci, u32 clk_id)
+{
+	if (clk_id >= ci->num_clocks)
+		return ERR_PTR(-EINVAL);
+
+	return ci->clk + clk_id;
+}
+
 static int
 scmi_clock_protocol_attributes_get(const struct scmi_protocol_handle *ph,
 				   struct clock_info *ci)
@@ -189,6 +209,17 @@ scmi_clock_protocol_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret) {
+		if (!ph->hops->protocol_msg_check(ph, CLOCK_RATE_NOTIFY, NULL))
+			ci->notify_rate_changed_cmd = true;
+
+		if (!ph->hops->protocol_msg_check(ph,
+						  CLOCK_RATE_CHANGE_REQUESTED_NOTIFY,
+						  NULL))
+			ci->notify_rate_change_requested_cmd = true;
+	}
+
 	return ret;
 }
 
@@ -284,14 +315,44 @@ static int scmi_clock_possible_parents(const struct scmi_protocol_handle *ph, u3
 	return ret;
 }
 
+static int
+scmi_clock_get_permissions(const struct scmi_protocol_handle *ph, u32 clk_id,
+			   struct scmi_clock_info *clk)
+{
+	struct scmi_xfer *t;
+	u32 perm;
+	int ret;
+
+	ret = ph->xops->xfer_get_init(ph, CLOCK_GET_PERMISSIONS,
+				      sizeof(clk_id), sizeof(perm), &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(clk_id, t->tx.buf);
+
+	ret = ph->xops->do_xfer(ph, t);
+	if (!ret) {
+		perm = get_unaligned_le32(t->rx.buf);
+
+		clk->state_ctrl_forbidden = !(perm & CLOCK_STATE_CONTROL_ALLOWED);
+		clk->rate_ctrl_forbidden = !(perm & CLOCK_RATE_CONTROL_ALLOWED);
+		clk->parent_ctrl_forbidden = !(perm & CLOCK_PARENT_CONTROL_ALLOWED);
+	}
+
+	ph->xops->xfer_put(ph, t);
+
+	return ret;
+}
+
 static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
-				     u32 clk_id, struct scmi_clock_info *clk,
+				     u32 clk_id, struct clock_info *cinfo,
 				     u32 version)
 {
 	int ret;
 	u32 attributes;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_clock_attributes *attr;
+	struct scmi_clock_info *clk = cinfo->clk + clk_id;
 
 	ret = ph->xops->xfer_get_init(ph, CLOCK_ATTRIBUTES,
 				      sizeof(clk_id), sizeof(*attr), &t);
@@ -324,12 +385,20 @@ static int scmi_clock_attributes_get(const struct scmi_protocol_handle *ph,
 						    NULL, clk->name,
 						    SCMI_MAX_STR_SIZE);
 
-		if (SUPPORTS_RATE_CHANGED_NOTIF(attributes))
+		if (cinfo->notify_rate_changed_cmd &&
+		    SUPPORTS_RATE_CHANGED_NOTIF(attributes))
 			clk->rate_changed_notifications = true;
-		if (SUPPORTS_RATE_CHANGE_REQUESTED_NOTIF(attributes))
+		if (cinfo->notify_rate_change_requested_cmd &&
+		    SUPPORTS_RATE_CHANGE_REQUESTED_NOTIF(attributes))
 			clk->rate_change_requested_notifications = true;
-		if (SUPPORTS_PARENT_CLOCK(attributes))
-			scmi_clock_possible_parents(ph, clk_id, clk);
+		if (PROTOCOL_REV_MAJOR(version) >= 0x3) {
+			if (SUPPORTS_PARENT_CLOCK(attributes))
+				scmi_clock_possible_parents(ph, clk_id, clk);
+			if (SUPPORTS_GET_PERMISSIONS(attributes))
+				scmi_clock_get_permissions(ph, clk_id, clk);
+			if (SUPPORTS_EXTENDED_CONFIG(attributes))
+				clk->extended_config = true;
+		}
 	}
 
 	return ret;
@@ -502,6 +571,14 @@ static int scmi_clock_rate_set(const struct scmi_protocol_handle *ph,
 	struct scmi_xfer *t;
 	struct scmi_clock_set_rate *cfg;
 	struct clock_info *ci = ph->get_priv(ph);
+	struct scmi_clock_info *clk;
+
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (clk->rate_ctrl_forbidden)
+		return -EACCES;
 
 	ret = ph->xops->xfer_get_init(ph, CLOCK_RATE_SET, sizeof(*cfg), 0, &t);
 	if (ret)
@@ -543,7 +620,8 @@ static int scmi_clock_rate_set(const struct scmi_protocol_handle *ph,
 
 static int
 scmi_clock_config_set(const struct scmi_protocol_handle *ph, u32 clk_id,
-		      enum clk_state state, u8 __unused0, u32 __unused1,
+		      enum clk_state state,
+		      enum scmi_clock_oem_config __unused0, u32 __unused1,
 		      bool atomic)
 {
 	int ret;
@@ -580,14 +658,16 @@ scmi_clock_set_parent(const struct scmi_protocol_handle *ph, u32 clk_id,
 	struct clock_info *ci = ph->get_priv(ph);
 	struct scmi_clock_info *clk;
 
-	if (clk_id >= ci->num_clocks)
-		return -EINVAL;
-
-	clk = ci->clk + clk_id;
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
 	if (parent_id >= clk->num_parents)
 		return -EINVAL;
 
+	if (clk->parent_ctrl_forbidden)
+		return -EACCES;
+
 	ret = ph->xops->xfer_get_init(ph, CLOCK_PARENT_SET,
 				      sizeof(*cfg), 0, &t);
 	if (ret)
@@ -628,10 +708,11 @@ scmi_clock_get_parent(const struct scmi_protocol_handle *ph, u32 clk_id,
 	return ret;
 }
 
-/* For SCMI clock v2.1 and onwards */
+/* For SCMI clock v3.0 and onwards */
 static int
 scmi_clock_config_set_v2(const struct scmi_protocol_handle *ph, u32 clk_id,
-			 enum clk_state state, u8 oem_type, u32 oem_val,
+			 enum clk_state state,
+			 enum scmi_clock_oem_config oem_type, u32 oem_val,
 			 bool atomic)
 {
 	int ret;
@@ -671,6 +752,14 @@ static int scmi_clock_enable(const struct scmi_protocol_handle *ph, u32 clk_id,
 			     bool atomic)
 {
 	struct clock_info *ci = ph->get_priv(ph);
+	struct scmi_clock_info *clk;
+
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (clk->state_ctrl_forbidden)
+		return -EACCES;
 
 	return ci->clock_config_set(ph, clk_id, CLK_STATE_ENABLE,
 				    NULL_OEM_TYPE, 0, atomic);
@@ -680,16 +769,24 @@ static int scmi_clock_disable(const struct scmi_protocol_handle *ph, u32 clk_id,
 			      bool atomic)
 {
 	struct clock_info *ci = ph->get_priv(ph);
+	struct scmi_clock_info *clk;
+
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (clk->state_ctrl_forbidden)
+		return -EACCES;
 
 	return ci->clock_config_set(ph, clk_id, CLK_STATE_DISABLE,
 				    NULL_OEM_TYPE, 0, atomic);
 }
 
-/* For SCMI clock v2.1 and onwards */
+/* For SCMI clock v3.0 and onwards */
 static int
 scmi_clock_config_get_v2(const struct scmi_protocol_handle *ph, u32 clk_id,
-			 u8 oem_type, u32 *attributes, bool *enabled,
-			 u32 *oem_val, bool atomic)
+			 enum scmi_clock_oem_config oem_type, u32 *attributes,
+			 bool *enabled, u32 *oem_val, bool atomic)
 {
 	int ret;
 	u32 flags;
@@ -730,8 +827,8 @@ scmi_clock_config_get_v2(const struct scmi_protocol_handle *ph, u32 clk_id,
 
 static int
 scmi_clock_config_get(const struct scmi_protocol_handle *ph, u32 clk_id,
-		      u8 oem_type, u32 *attributes, bool *enabled,
-		      u32 *oem_val, bool atomic)
+		      enum scmi_clock_oem_config oem_type, u32 *attributes,
+		      bool *enabled, u32 *oem_val, bool atomic)
 {
 	int ret;
 	struct scmi_xfer *t;
@@ -768,20 +865,38 @@ static int scmi_clock_state_get(const struct scmi_protocol_handle *ph,
 }
 
 static int scmi_clock_config_oem_set(const struct scmi_protocol_handle *ph,
-				     u32 clk_id, u8 oem_type, u32 oem_val,
-				     bool atomic)
+				     u32 clk_id,
+				     enum scmi_clock_oem_config oem_type,
+				     u32 oem_val, bool atomic)
 {
 	struct clock_info *ci = ph->get_priv(ph);
+	struct scmi_clock_info *clk;
+
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (!clk->extended_config)
+		return -EOPNOTSUPP;
 
 	return ci->clock_config_set(ph, clk_id, CLK_STATE_UNCHANGED,
 				    oem_type, oem_val, atomic);
 }
 
 static int scmi_clock_config_oem_get(const struct scmi_protocol_handle *ph,
-				     u32 clk_id, u8 oem_type, u32 *oem_val,
-				     u32 *attributes, bool atomic)
+				     u32 clk_id,
+				     enum scmi_clock_oem_config oem_type,
+				     u32 *oem_val, u32 *attributes, bool atomic)
 {
 	struct clock_info *ci = ph->get_priv(ph);
+	struct scmi_clock_info *clk;
+
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (!clk->extended_config)
+		return -EOPNOTSUPP;
 
 	return ci->clock_config_get(ph, clk_id, oem_type, attributes,
 				    NULL, oem_val, atomic);
@@ -800,10 +915,10 @@ scmi_clock_info_get(const struct scmi_protocol_handle *ph, u32 clk_id)
 	struct scmi_clock_info *clk;
 	struct clock_info *ci = ph->get_priv(ph);
 
-	if (clk_id >= ci->num_clocks)
+	clk = scmi_clock_domain_lookup(ci, clk_id);
+	if (IS_ERR(clk))
 		return NULL;
 
-	clk = ci->clk + clk_id;
 	if (!clk->name[0])
 		return NULL;
 
@@ -824,6 +939,28 @@ static const struct scmi_clk_proto_ops clk_proto_ops = {
 	.parent_get = scmi_clock_get_parent,
 };
 
+static bool scmi_clk_notify_supported(const struct scmi_protocol_handle *ph,
+				      u8 evt_id, u32 src_id)
+{
+	bool supported;
+	struct scmi_clock_info *clk;
+	struct clock_info *ci = ph->get_priv(ph);
+
+	if (evt_id >= ARRAY_SIZE(evt_2_cmd))
+		return false;
+
+	clk = scmi_clock_domain_lookup(ci, src_id);
+	if (IS_ERR(clk))
+		return false;
+
+	if (evt_id == SCMI_EVENT_CLOCK_RATE_CHANGED)
+		supported = clk->rate_changed_notifications;
+	else
+		supported = clk->rate_change_requested_notifications;
+
+	return supported;
+}
+
 static int scmi_clk_rate_notify(const struct scmi_protocol_handle *ph,
 				u32 clk_id, int message_id, bool enable)
 {
@@ -908,6 +1045,7 @@ static const struct scmi_event clk_events[] = {
 };
 
 static const struct scmi_event_ops clk_event_ops = {
+	.is_notify_supported = scmi_clk_notify_supported,
 	.get_num_sources = scmi_clk_get_num_sources,
 	.set_notify_enabled = scmi_clk_set_notify_enabled,
 	.fill_custom_report = scmi_clk_fill_custom_report,
@@ -949,7 +1087,7 @@ static int scmi_clock_protocol_init(const struct scmi_protocol_handle *ph)
 	for (clkid = 0; clkid < cinfo->num_clocks; clkid++) {
 		struct scmi_clock_info *clk = cinfo->clk + clkid;
 
-		ret = scmi_clock_attributes_get(ph, clkid, clk, version);
+		ret = scmi_clock_attributes_get(ph, clkid, cinfo, version);
 		if (!ret)
 			scmi_clock_describe_rates_get(ph, clkid, clk);
 	}
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index 00b165d1f502..6affbfdd1dec 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -141,7 +141,7 @@ scmi_revision_area_get(const struct scmi_protocol_handle *ph);
 void scmi_setup_protocol_implemented(const struct scmi_protocol_handle *ph,
 				     u8 *prot_imp);
 
-extern struct bus_type scmi_bus_type;
+extern const struct bus_type scmi_bus_type;
 
 #define SCMI_BUS_NOTIFY_DEVICE_REQUEST		0
 #define SCMI_BUS_NOTIFY_DEVICE_UNREQUEST	1
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 3ea64b22cf0d..34d77802c990 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -86,6 +86,12 @@ struct scmi_xfers_info {
  * @users: A refcount to track effective users of this protocol.
  * @priv: Reference for optional protocol private data.
  * @version: Protocol version supported by the platform as detected at runtime.
+ * @negotiated_version: When the platform supports a newer protocol version,
+ *			the agent will try to negotiate with the platform the
+ *			usage of the newest version known to it, since
+ *			backward compatibility is NOT automatically assured.
+ *			This field is NON-zero when a successful negotiation
+ *			has completed.
  * @ph: An embedded protocol handle that will be passed down to protocol
  *	initialization code to identify this instance.
  *
@@ -99,6 +105,7 @@ struct scmi_protocol_instance {
 	refcount_t			users;
 	void				*priv;
 	unsigned int			version;
+	unsigned int			negotiated_version;
 	struct scmi_protocol_handle	ph;
 };
 
@@ -1754,10 +1761,44 @@ static void scmi_common_fastchannel_db_ring(struct scmi_fc_db_info *db)
 #endif
 }
 
+/**
+ * scmi_protocol_msg_check  - Check protocol message attributes
+ *
+ * @ph: A reference to the protocol handle.
+ * @message_id: The ID of the message to check.
+ * @attributes: A parameter to optionally return the retrieved message
+ *		attributes, in case of Success.
+ *
+ * An helper to check protocol message attributes for a specific protocol
+ * and message pair.
+ *
+ * Return: 0 on SUCCESS
+ */
+static int scmi_protocol_msg_check(const struct scmi_protocol_handle *ph,
+				   u32 message_id, u32 *attributes)
+{
+	int ret;
+	struct scmi_xfer *t;
+
+	ret = xfer_get_init(ph, PROTOCOL_MESSAGE_ATTRIBUTES,
+			    sizeof(__le32), 0, &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(message_id, t->tx.buf);
+	ret = do_xfer(ph, t);
+	if (!ret && attributes)
+		*attributes = get_unaligned_le32(t->rx.buf);
+	xfer_put(ph, t);
+
+	return ret;
+}
+
 static const struct scmi_proto_helpers_ops helpers_ops = {
 	.extended_name_get = scmi_common_extended_name_get,
 	.iter_response_init = scmi_iterator_init,
 	.iter_response_run = scmi_iterator_run,
+	.protocol_msg_check = scmi_protocol_msg_check,
 	.fastchannel_init = scmi_common_fastchannel_init,
 	.fastchannel_db_ring = scmi_common_fastchannel_db_ring,
 };
@@ -1782,6 +1823,44 @@ scmi_revision_area_get(const struct scmi_protocol_handle *ph)
 }
 
 /**
+ * scmi_protocol_version_negotiate  - Negotiate protocol version
+ *
+ * @ph: A reference to the protocol handle.
+ *
+ * An helper to negotiate a protocol version different from the latest
+ * advertised as supported from the platform: on Success backward
+ * compatibility is assured by the platform.
+ *
+ * Return: 0 on Success
+ */
+static int scmi_protocol_version_negotiate(struct scmi_protocol_handle *ph)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_protocol_instance *pi = ph_to_pi(ph);
+
+	/* At first check if NEGOTIATE_PROTOCOL_VERSION is supported ... */
+	ret = scmi_protocol_msg_check(ph, NEGOTIATE_PROTOCOL_VERSION, NULL);
+	if (ret)
+		return ret;
+
+	/* ... then attempt protocol version negotiation */
+	ret = xfer_get_init(ph, NEGOTIATE_PROTOCOL_VERSION,
+			    sizeof(__le32), 0, &t);
+	if (ret)
+		return ret;
+
+	put_unaligned_le32(pi->proto->supported_version, t->tx.buf);
+	ret = do_xfer(ph, t);
+	if (!ret)
+		pi->negotiated_version = pi->proto->supported_version;
+
+	xfer_put(ph, t);
+
+	return ret;
+}
+
+/**
  * scmi_alloc_init_protocol_instance  - Allocate and initialize a protocol
  * instance descriptor.
  * @info: The reference to the related SCMI instance.
@@ -1853,11 +1932,21 @@ scmi_alloc_init_protocol_instance(struct scmi_info *info,
 	devres_close_group(handle->dev, pi->gid);
 	dev_dbg(handle->dev, "Initialized protocol: 0x%X\n", pi->proto->id);
 
-	if (pi->version > proto->supported_version)
-		dev_warn(handle->dev,
-			 "Detected UNSUPPORTED higher version 0x%X for protocol 0x%X."
-			 "Backward compatibility is NOT assured.\n",
-			 pi->version, pi->proto->id);
+	if (pi->version > proto->supported_version) {
+		ret = scmi_protocol_version_negotiate(&pi->ph);
+		if (!ret) {
+			dev_info(handle->dev,
+				 "Protocol 0x%X successfully negotiated version 0x%X\n",
+				 proto->id, pi->negotiated_version);
+		} else {
+			dev_warn(handle->dev,
+				 "Detected UNSUPPORTED higher version 0x%X for protocol 0x%X.\n",
+				 pi->version, pi->proto->id);
+			dev_warn(handle->dev,
+				 "Trying version 0x%X. Backward compatibility is NOT assured.\n",
+				 pi->proto->supported_version);
+		}
+	}
 
 	return pi;
 
diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
index 0efd20cd9d69..27c52531194d 100644
--- a/drivers/firmware/arm_scmi/notify.c
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -99,6 +99,7 @@
 #define PROTO_ID_MASK		GENMASK(31, 24)
 #define EVT_ID_MASK		GENMASK(23, 16)
 #define SRC_ID_MASK		GENMASK(15, 0)
+#define NOTIF_UNSUPP		-1
 
 /*
  * Builds an unsigned 32bit key from the given input tuple to be used
@@ -788,6 +789,7 @@ int scmi_register_protocol_events(const struct scmi_handle *handle, u8 proto_id,
 
 	pd->ph = ph;
 	for (i = 0; i < ee->num_events; i++, evt++) {
+		int id;
 		struct scmi_registered_event *r_evt;
 
 		r_evt = devm_kzalloc(ni->handle->dev, sizeof(*r_evt),
@@ -809,6 +811,11 @@ int scmi_register_protocol_events(const struct scmi_handle *handle, u8 proto_id,
 		if (!r_evt->report)
 			return -ENOMEM;
 
+		for (id = 0; id < r_evt->num_sources; id++)
+			if (ee->ops->is_notify_supported &&
+			    !ee->ops->is_notify_supported(ph, r_evt->evt->id, id))
+				refcount_set(&r_evt->sources[id], NOTIF_UNSUPP);
+
 		pd->registered_events[i] = r_evt;
 		/* Ensure events are updated */
 		smp_wmb();
@@ -1166,7 +1173,13 @@ static inline int __scmi_enable_evt(struct scmi_registered_event *r_evt,
 			int ret = 0;
 
 			sid = &r_evt->sources[src_id];
-			if (refcount_read(sid) == 0) {
+			if (refcount_read(sid) == NOTIF_UNSUPP) {
+				dev_dbg(r_evt->proto->ph->dev,
+					"Notification NOT supported - proto_id:%d  evt_id:%d  src_id:%d",
+					r_evt->proto->id, r_evt->evt->id,
+					src_id);
+				ret = -EOPNOTSUPP;
+			} else if (refcount_read(sid) == 0) {
 				ret = REVT_NOTIFY_ENABLE(r_evt, r_evt->evt->id,
 							 src_id);
 				if (!ret)
@@ -1179,6 +1192,8 @@ static inline int __scmi_enable_evt(struct scmi_registered_event *r_evt,
 	} else {
 		for (; num_sources; src_id++, num_sources--) {
 			sid = &r_evt->sources[src_id];
+			if (refcount_read(sid) == NOTIF_UNSUPP)
+				continue;
 			if (refcount_dec_and_test(sid))
 				REVT_NOTIFY_DISABLE(r_evt,
 						    r_evt->evt->id, src_id);
diff --git a/drivers/firmware/arm_scmi/notify.h b/drivers/firmware/arm_scmi/notify.h
index 4e9b627edfef..76758a736cf4 100644
--- a/drivers/firmware/arm_scmi/notify.h
+++ b/drivers/firmware/arm_scmi/notify.h
@@ -35,6 +35,8 @@ struct scmi_protocol_handle;
 
 /**
  * struct scmi_event_ops  - Protocol helpers called by the notification core.
+ * @is_notify_supported: Return 0 if the specified notification for the
+ *			 specified resource (src_id) is supported.
  * @get_num_sources: Returns the number of possible events' sources for this
  *		     protocol
  * @set_notify_enabled: Enable/disable the required evt_id/src_id notifications
@@ -50,6 +52,8 @@ struct scmi_protocol_handle;
  *	    process context.
  */
 struct scmi_event_ops {
+	bool (*is_notify_supported)(const struct scmi_protocol_handle *ph,
+				    u8 evt_id, u32 src_id);
 	int (*get_num_sources)(const struct scmi_protocol_handle *ph);
 	int (*set_notify_enabled)(const struct scmi_protocol_handle *ph,
 				  u8 evt_id, u32 src_id, bool enabled);
diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c
index 25bfb465484d..4e7944b91e38 100644
--- a/drivers/firmware/arm_scmi/optee.c
+++ b/drivers/firmware/arm_scmi/optee.c
@@ -109,8 +109,10 @@ enum scmi_optee_pta_cmd {
  * @rx_len: Response size
  * @mu: Mutex protection on channel access
  * @cinfo: SCMI channel information
- * @shmem: Virtual base address of the shared memory
- * @req: Shared memory protocol handle for SCMI request and synchronous response
+ * @req: union for SCMI interface
+ * @req.shmem: Virtual base address of the shared memory
+ * @req.msg: Shared memory protocol handle for SCMI request and
+ *   synchronous response
  * @tee_shm: TEE shared memory handle @req or NULL if using IOMEM shmem
  * @link: Reference in agent's channel list
  */
diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c
index 211e8e0aef2c..981e327e63e3 100644
--- a/drivers/firmware/arm_scmi/perf.c
+++ b/drivers/firmware/arm_scmi/perf.c
@@ -182,6 +182,8 @@ struct scmi_perf_info {
 	enum scmi_power_scale power_scale;
 	u64 stats_addr;
 	u32 stats_size;
+	bool notify_lvl_cmd;
+	bool notify_lim_cmd;
 	struct perf_dom_info *dom_info;
 };
 
@@ -222,6 +224,15 @@ static int scmi_perf_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret) {
+		if (!ph->hops->protocol_msg_check(ph, PERF_NOTIFY_LEVEL, NULL))
+			pi->notify_lvl_cmd = true;
+
+		if (!ph->hops->protocol_msg_check(ph, PERF_NOTIFY_LIMITS, NULL))
+			pi->notify_lim_cmd = true;
+	}
+
 	return ret;
 }
 
@@ -239,6 +250,7 @@ static void scmi_perf_xa_destroy(void *data)
 static int
 scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 				struct perf_dom_info *dom_info,
+				bool notify_lim_cmd, bool notify_lvl_cmd,
 				u32 version)
 {
 	int ret;
@@ -260,8 +272,12 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 
 		dom_info->set_limits = SUPPORTS_SET_LIMITS(flags);
 		dom_info->info.set_perf = SUPPORTS_SET_PERF_LVL(flags);
-		dom_info->perf_limit_notify = SUPPORTS_PERF_LIMIT_NOTIFY(flags);
-		dom_info->perf_level_notify = SUPPORTS_PERF_LEVEL_NOTIFY(flags);
+		if (notify_lim_cmd)
+			dom_info->perf_limit_notify =
+				SUPPORTS_PERF_LIMIT_NOTIFY(flags);
+		if (notify_lvl_cmd)
+			dom_info->perf_level_notify =
+				SUPPORTS_PERF_LEVEL_NOTIFY(flags);
 		dom_info->perf_fastchannels = SUPPORTS_PERF_FASTCHANNELS(flags);
 		if (PROTOCOL_REV_MAJOR(version) >= 0x4)
 			dom_info->level_indexing_mode =
@@ -270,15 +286,30 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 					le32_to_cpu(attr->sustained_freq_khz);
 		dom_info->sustained_perf_level =
 					le32_to_cpu(attr->sustained_perf_level);
+		/*
+		 * sustained_freq_khz = mult_factor * sustained_perf_level
+		 * mult_factor must be non zero positive integer(not fraction)
+		 */
 		if (!dom_info->sustained_freq_khz ||
 		    !dom_info->sustained_perf_level ||
-		    dom_info->level_indexing_mode)
+		    dom_info->level_indexing_mode) {
 			/* CPUFreq converts to kHz, hence default 1000 */
 			dom_info->mult_factor =	1000;
-		else
+		} else {
 			dom_info->mult_factor =
 					(dom_info->sustained_freq_khz * 1000UL)
 					/ dom_info->sustained_perf_level;
+			if ((dom_info->sustained_freq_khz * 1000UL) %
+			    dom_info->sustained_perf_level)
+				dev_warn(ph->dev,
+					 "multiplier for domain %d rounded\n",
+					 dom_info->id);
+		}
+		if (!dom_info->mult_factor)
+			dev_warn(ph->dev,
+			         "Wrong sustained perf/frequency(domain %d)\n",
+				 dom_info->id);
+
 		strscpy(dom_info->info.name, attr->name,
 			SCMI_SHORT_NAME_MAX_SIZE);
 	}
@@ -295,9 +326,9 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph,
 					    dom_info->id, NULL, dom_info->info.name,
 					    SCMI_MAX_STR_SIZE);
 
+	xa_init(&dom_info->opps_by_lvl);
 	if (dom_info->level_indexing_mode) {
 		xa_init(&dom_info->opps_by_idx);
-		xa_init(&dom_info->opps_by_lvl);
 		hash_init(dom_info->opps_by_freq);
 	}
 
@@ -340,13 +371,21 @@ static int iter_perf_levels_update_state(struct scmi_iterator_state *st,
 }
 
 static inline void
-process_response_opp(struct scmi_opp *opp, unsigned int loop_idx,
+process_response_opp(struct device *dev, struct perf_dom_info *dom,
+		     struct scmi_opp *opp, unsigned int loop_idx,
 		     const struct scmi_msg_resp_perf_describe_levels *r)
 {
+	int ret;
+
 	opp->perf = le32_to_cpu(r->opp[loop_idx].perf_val);
 	opp->power = le32_to_cpu(r->opp[loop_idx].power);
 	opp->trans_latency_us =
 		le16_to_cpu(r->opp[loop_idx].transition_latency_us);
+
+	ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+	if (ret)
+		dev_warn(dev, "Failed to add opps_by_lvl at %d - ret:%d\n",
+			 opp->perf, ret);
 }
 
 static inline void
@@ -354,16 +393,21 @@ process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
 			struct scmi_opp *opp, unsigned int loop_idx,
 			const struct scmi_msg_resp_perf_describe_levels_v4 *r)
 {
+	int ret;
+
 	opp->perf = le32_to_cpu(r->opp[loop_idx].perf_val);
 	opp->power = le32_to_cpu(r->opp[loop_idx].power);
 	opp->trans_latency_us =
 		le16_to_cpu(r->opp[loop_idx].transition_latency_us);
 
+	ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
+	if (ret)
+		dev_warn(dev, "Failed to add opps_by_lvl at %d - ret:%d\n",
+			 opp->perf, ret);
+
 	/* Note that PERF v4 reports always five 32-bit words */
 	opp->indicative_freq = le32_to_cpu(r->opp[loop_idx].indicative_freq);
 	if (dom->level_indexing_mode) {
-		int ret;
-
 		opp->level_index = le32_to_cpu(r->opp[loop_idx].level_index);
 
 		ret = xa_insert(&dom->opps_by_idx, opp->level_index, opp,
@@ -373,12 +417,6 @@ process_response_opp_v4(struct device *dev, struct perf_dom_info *dom,
 				 "Failed to add opps_by_idx at %d - ret:%d\n",
 				 opp->level_index, ret);
 
-		ret = xa_insert(&dom->opps_by_lvl, opp->perf, opp, GFP_KERNEL);
-		if (ret)
-			dev_warn(dev,
-				 "Failed to add opps_by_lvl at %d - ret:%d\n",
-				 opp->perf, ret);
-
 		hash_add(dom->opps_by_freq, &opp->hash, opp->indicative_freq);
 	}
 }
@@ -393,7 +431,8 @@ iter_perf_levels_process_response(const struct scmi_protocol_handle *ph,
 
 	opp = &p->perf_dom->opp[st->desc_index + st->loop_idx];
 	if (PROTOCOL_REV_MAJOR(p->version) <= 0x3)
-		process_response_opp(opp, st->loop_idx, response);
+		process_response_opp(ph->dev, p->perf_dom, opp, st->loop_idx,
+				     response);
 	else
 		process_response_opp_v4(ph->dev, p->perf_dom, opp, st->loop_idx,
 					response);
@@ -978,6 +1017,27 @@ static const struct scmi_perf_proto_ops perf_proto_ops = {
 	.power_scale_get = scmi_power_scale_get,
 };
 
+static bool scmi_perf_notify_supported(const struct scmi_protocol_handle *ph,
+				       u8 evt_id, u32 src_id)
+{
+	bool supported;
+	struct perf_dom_info *dom;
+
+	if (evt_id >= ARRAY_SIZE(evt_2_cmd))
+		return false;
+
+	dom = scmi_perf_domain_lookup(ph, src_id);
+	if (IS_ERR(dom))
+		return false;
+
+	if (evt_id == SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED)
+		supported = dom->perf_limit_notify;
+	else
+		supported = dom->perf_level_notify;
+
+	return supported;
+}
+
 static int scmi_perf_set_notify_enabled(const struct scmi_protocol_handle *ph,
 					u8 evt_id, u32 src_id, bool enable)
 {
@@ -995,18 +1055,47 @@ static int scmi_perf_set_notify_enabled(const struct scmi_protocol_handle *ph,
 	return ret;
 }
 
+static int
+scmi_perf_xlate_opp_to_freq(struct perf_dom_info *dom,
+			    unsigned int index, unsigned long *freq)
+{
+	struct scmi_opp *opp;
+
+	if (!dom || !freq)
+		return -EINVAL;
+
+	if (!dom->level_indexing_mode) {
+		opp = xa_load(&dom->opps_by_lvl, index);
+		if (!opp)
+			return -ENODEV;
+
+		*freq = opp->perf * dom->mult_factor;
+	} else {
+		opp = xa_load(&dom->opps_by_idx, index);
+		if (!opp)
+			return -ENODEV;
+
+		*freq = opp->indicative_freq * dom->mult_factor;
+	}
+
+	return 0;
+}
+
 static void *scmi_perf_fill_custom_report(const struct scmi_protocol_handle *ph,
 					  u8 evt_id, ktime_t timestamp,
 					  const void *payld, size_t payld_sz,
 					  void *report, u32 *src_id)
 {
+	int ret;
 	void *rep = NULL;
+	struct perf_dom_info *dom;
 
 	switch (evt_id) {
 	case SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED:
 	{
 		const struct scmi_perf_limits_notify_payld *p = payld;
 		struct scmi_perf_limits_report *r = report;
+		unsigned long freq_min, freq_max;
 
 		if (sizeof(*p) != payld_sz)
 			break;
@@ -1016,14 +1105,36 @@ static void *scmi_perf_fill_custom_report(const struct scmi_protocol_handle *ph,
 		r->domain_id = le32_to_cpu(p->domain_id);
 		r->range_max = le32_to_cpu(p->range_max);
 		r->range_min = le32_to_cpu(p->range_min);
+		/* Check if the reported domain exist at all */
+		dom = scmi_perf_domain_lookup(ph, r->domain_id);
+		if (IS_ERR(dom))
+			break;
+		/*
+		 * Event will be reported from this point on...
+		 * ...even if, later, xlated frequencies were not retrieved.
+		 */
 		*src_id = r->domain_id;
 		rep = r;
+
+		ret = scmi_perf_xlate_opp_to_freq(dom, r->range_max, &freq_max);
+		if (ret)
+			break;
+
+		ret = scmi_perf_xlate_opp_to_freq(dom, r->range_min, &freq_min);
+		if (ret)
+			break;
+
+		/* Report translated freqs ONLY if both available */
+		r->range_max_freq = freq_max;
+		r->range_min_freq = freq_min;
+
 		break;
 	}
 	case SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED:
 	{
 		const struct scmi_perf_level_notify_payld *p = payld;
 		struct scmi_perf_level_report *r = report;
+		unsigned long freq;
 
 		if (sizeof(*p) != payld_sz)
 			break;
@@ -1031,9 +1142,27 @@ static void *scmi_perf_fill_custom_report(const struct scmi_protocol_handle *ph,
 		r->timestamp = timestamp;
 		r->agent_id = le32_to_cpu(p->agent_id);
 		r->domain_id = le32_to_cpu(p->domain_id);
+		/* Report translated freqs ONLY if available */
 		r->performance_level = le32_to_cpu(p->performance_level);
+		/* Check if the reported domain exist at all */
+		dom = scmi_perf_domain_lookup(ph, r->domain_id);
+		if (IS_ERR(dom))
+			break;
+		/*
+		 * Event will be reported from this point on...
+		 * ...even if, later, xlated frequencies were not retrieved.
+		 */
 		*src_id = r->domain_id;
 		rep = r;
+
+		/* Report translated freqs ONLY if available */
+		ret = scmi_perf_xlate_opp_to_freq(dom, r->performance_level,
+						  &freq);
+		if (ret)
+			break;
+
+		r->performance_level_freq = freq;
+
 		break;
 	}
 	default:
@@ -1067,6 +1196,7 @@ static const struct scmi_event perf_events[] = {
 };
 
 static const struct scmi_event_ops perf_event_ops = {
+	.is_notify_supported = scmi_perf_notify_supported,
 	.get_num_sources = scmi_perf_get_num_sources,
 	.set_notify_enabled = scmi_perf_set_notify_enabled,
 	.fill_custom_report = scmi_perf_fill_custom_report,
@@ -1111,7 +1241,8 @@ static int scmi_perf_protocol_init(const struct scmi_protocol_handle *ph)
 		struct perf_dom_info *dom = pinfo->dom_info + domain;
 
 		dom->id = domain;
-		scmi_perf_domain_attributes_get(ph, dom, version);
+		scmi_perf_domain_attributes_get(ph, dom, pinfo->notify_lim_cmd,
+						pinfo->notify_lvl_cmd, version);
 		scmi_perf_describe_levels_get(ph, dom, version);
 
 		if (dom->perf_fastchannels)
diff --git a/drivers/firmware/arm_scmi/power.c b/drivers/firmware/arm_scmi/power.c
index c2e6b9b4d941..49666bd1d8ac 100644
--- a/drivers/firmware/arm_scmi/power.c
+++ b/drivers/firmware/arm_scmi/power.c
@@ -68,6 +68,7 @@ struct power_dom_info {
 
 struct scmi_power_info {
 	u32 version;
+	bool notify_state_change_cmd;
 	int num_domains;
 	u64 stats_addr;
 	u32 stats_size;
@@ -97,13 +98,18 @@ static int scmi_power_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret)
+		if (!ph->hops->protocol_msg_check(ph, POWER_STATE_NOTIFY, NULL))
+			pi->notify_state_change_cmd = true;
+
 	return ret;
 }
 
 static int
 scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph,
 				 u32 domain, struct power_dom_info *dom_info,
-				 u32 version)
+				 u32 version, bool notify_state_change_cmd)
 {
 	int ret;
 	u32 flags;
@@ -122,7 +128,9 @@ scmi_power_domain_attributes_get(const struct scmi_protocol_handle *ph,
 	if (!ret) {
 		flags = le32_to_cpu(attr->flags);
 
-		dom_info->state_set_notify = SUPPORTS_STATE_SET_NOTIFY(flags);
+		if (notify_state_change_cmd)
+			dom_info->state_set_notify =
+				SUPPORTS_STATE_SET_NOTIFY(flags);
 		dom_info->state_set_async = SUPPORTS_STATE_SET_ASYNC(flags);
 		dom_info->state_set_sync = SUPPORTS_STATE_SET_SYNC(flags);
 		strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE);
@@ -231,6 +239,20 @@ static int scmi_power_request_notify(const struct scmi_protocol_handle *ph,
 	return ret;
 }
 
+static bool scmi_power_notify_supported(const struct scmi_protocol_handle *ph,
+					u8 evt_id, u32 src_id)
+{
+	struct power_dom_info *dom;
+	struct scmi_power_info *pinfo = ph->get_priv(ph);
+
+	if (evt_id != SCMI_EVENT_POWER_STATE_CHANGED ||
+	    src_id >= pinfo->num_domains)
+		return false;
+
+	dom = pinfo->dom_info + src_id;
+	return dom->state_set_notify;
+}
+
 static int scmi_power_set_notify_enabled(const struct scmi_protocol_handle *ph,
 					 u8 evt_id, u32 src_id, bool enable)
 {
@@ -285,6 +307,7 @@ static const struct scmi_event power_events[] = {
 };
 
 static const struct scmi_event_ops power_event_ops = {
+	.is_notify_supported = scmi_power_notify_supported,
 	.get_num_sources = scmi_power_get_num_sources,
 	.set_notify_enabled = scmi_power_set_notify_enabled,
 	.fill_custom_report = scmi_power_fill_custom_report,
@@ -326,7 +349,8 @@ static int scmi_power_protocol_init(const struct scmi_protocol_handle *ph)
 	for (domain = 0; domain < pinfo->num_domains; domain++) {
 		struct power_dom_info *dom = pinfo->dom_info + domain;
 
-		scmi_power_domain_attributes_get(ph, domain, dom, version);
+		scmi_power_domain_attributes_get(ph, domain, dom, version,
+						 pinfo->notify_state_change_cmd);
 	}
 
 	pinfo->version = version;
diff --git a/drivers/firmware/arm_scmi/powercap.c b/drivers/firmware/arm_scmi/powercap.c
index a4c6cd4716fe..2fab92367e42 100644
--- a/drivers/firmware/arm_scmi/powercap.c
+++ b/drivers/firmware/arm_scmi/powercap.c
@@ -124,6 +124,8 @@ struct scmi_powercap_state {
 struct powercap_info {
 	u32 version;
 	int num_domains;
+	bool notify_cap_cmd;
+	bool notify_measurements_cmd;
 	struct scmi_powercap_state *states;
 	struct scmi_powercap_info *powercaps;
 };
@@ -157,6 +159,18 @@ scmi_powercap_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret) {
+		if (!ph->hops->protocol_msg_check(ph,
+						  POWERCAP_CAP_NOTIFY, NULL))
+			pi->notify_cap_cmd = true;
+
+		if (!ph->hops->protocol_msg_check(ph,
+						  POWERCAP_MEASUREMENTS_NOTIFY,
+						  NULL))
+			pi->notify_measurements_cmd = true;
+	}
+
 	return ret;
 }
 
@@ -200,10 +214,12 @@ scmi_powercap_domain_attributes_get(const struct scmi_protocol_handle *ph,
 		flags = le32_to_cpu(resp->attributes);
 
 		dom_info->id = domain;
-		dom_info->notify_powercap_cap_change =
-			SUPPORTS_POWERCAP_CAP_CHANGE_NOTIFY(flags);
-		dom_info->notify_powercap_measurement_change =
-			SUPPORTS_POWERCAP_MEASUREMENTS_CHANGE_NOTIFY(flags);
+		if (pinfo->notify_cap_cmd)
+			dom_info->notify_powercap_cap_change =
+				SUPPORTS_POWERCAP_CAP_CHANGE_NOTIFY(flags);
+		if (pinfo->notify_measurements_cmd)
+			dom_info->notify_powercap_measurement_change =
+				SUPPORTS_POWERCAP_MEASUREMENTS_CHANGE_NOTIFY(flags);
 		dom_info->async_powercap_cap_set =
 			SUPPORTS_ASYNC_POWERCAP_CAP_SET(flags);
 		dom_info->powercap_cap_config =
@@ -788,6 +804,26 @@ static int scmi_powercap_notify(const struct scmi_protocol_handle *ph,
 	return ret;
 }
 
+static bool
+scmi_powercap_notify_supported(const struct scmi_protocol_handle *ph,
+			       u8 evt_id, u32 src_id)
+{
+	bool supported = false;
+	const struct scmi_powercap_info *dom_info;
+	struct powercap_info *pi = ph->get_priv(ph);
+
+	if (evt_id >= ARRAY_SIZE(evt_2_cmd) || src_id >= pi->num_domains)
+		return false;
+
+	dom_info = pi->powercaps + src_id;
+	if (evt_id == SCMI_EVENT_POWERCAP_CAP_CHANGED)
+		supported = dom_info->notify_powercap_cap_change;
+	else if (evt_id == SCMI_EVENT_POWERCAP_MEASUREMENTS_CHANGED)
+		supported = dom_info->notify_powercap_measurement_change;
+
+	return supported;
+}
+
 static int
 scmi_powercap_set_notify_enabled(const struct scmi_protocol_handle *ph,
 				 u8 evt_id, u32 src_id, bool enable)
@@ -904,6 +940,7 @@ static const struct scmi_event powercap_events[] = {
 };
 
 static const struct scmi_event_ops powercap_event_ops = {
+	.is_notify_supported = scmi_powercap_notify_supported,
 	.get_num_sources = scmi_powercap_get_num_sources,
 	.set_notify_enabled = scmi_powercap_set_notify_enabled,
 	.fill_custom_report = scmi_powercap_fill_custom_report,
diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h
index e683c26f24eb..693019fff0f6 100644
--- a/drivers/firmware/arm_scmi/protocols.h
+++ b/drivers/firmware/arm_scmi/protocols.h
@@ -33,6 +33,7 @@ enum scmi_common_cmd {
 	PROTOCOL_VERSION = 0x0,
 	PROTOCOL_ATTRIBUTES = 0x1,
 	PROTOCOL_MESSAGE_ATTRIBUTES = 0x2,
+	NEGOTIATE_PROTOCOL_VERSION = 0x10,
 };
 
 /**
@@ -251,6 +252,8 @@ struct scmi_fc_info {
  *			provided in @ops.
  * @iter_response_run: A common helper to trigger the run of a previously
  *		       initialized iterator.
+ * @protocol_msg_check: A common helper to check is a specific protocol message
+ *			is supported.
  * @fastchannel_init: A common helper used to initialize FC descriptors by
  *		      gathering FC descriptions from the SCMI platform server.
  * @fastchannel_db_ring: A common helper to ring a FC doorbell.
@@ -264,6 +267,8 @@ struct scmi_proto_helpers_ops {
 				    unsigned int max_resources, u8 msg_id,
 				    size_t tx_size, void *priv);
 	int (*iter_response_run)(void *iter);
+	int (*protocol_msg_check)(const struct scmi_protocol_handle *ph,
+				  u32 message_id, u32 *attributes);
 	void (*fastchannel_init)(const struct scmi_protocol_handle *ph,
 				 u8 describe_id, u32 message_id,
 				 u32 valid_size, u32 domain,
diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c
index 19970d9f9e36..1b318316535e 100644
--- a/drivers/firmware/arm_scmi/reset.c
+++ b/drivers/firmware/arm_scmi/reset.c
@@ -67,6 +67,7 @@ struct reset_dom_info {
 struct scmi_reset_info {
 	u32 version;
 	int num_domains;
+	bool notify_reset_cmd;
 	struct reset_dom_info *dom_info;
 };
 
@@ -89,18 +90,24 @@ static int scmi_reset_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret)
+		if (!ph->hops->protocol_msg_check(ph, RESET_NOTIFY, NULL))
+			pi->notify_reset_cmd = true;
+
 	return ret;
 }
 
 static int
 scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
-				 u32 domain, struct reset_dom_info *dom_info,
-				 u32 version)
+				 struct scmi_reset_info *pinfo,
+				 u32 domain, u32 version)
 {
 	int ret;
 	u32 attributes;
 	struct scmi_xfer *t;
 	struct scmi_msg_resp_reset_domain_attributes *attr;
+	struct reset_dom_info *dom_info = pinfo->dom_info + domain;
 
 	ret = ph->xops->xfer_get_init(ph, RESET_DOMAIN_ATTRIBUTES,
 				      sizeof(domain), sizeof(*attr), &t);
@@ -115,7 +122,9 @@ scmi_reset_domain_attributes_get(const struct scmi_protocol_handle *ph,
 		attributes = le32_to_cpu(attr->attributes);
 
 		dom_info->async_reset = SUPPORTS_ASYNC_RESET(attributes);
-		dom_info->reset_notify = SUPPORTS_NOTIFY_RESET(attributes);
+		if (pinfo->notify_reset_cmd)
+			dom_info->reset_notify =
+				SUPPORTS_NOTIFY_RESET(attributes);
 		dom_info->latency_us = le32_to_cpu(attr->latency);
 		if (dom_info->latency_us == U32_MAX)
 			dom_info->latency_us = 0;
@@ -226,6 +235,20 @@ static const struct scmi_reset_proto_ops reset_proto_ops = {
 	.deassert = scmi_reset_domain_deassert,
 };
 
+static bool scmi_reset_notify_supported(const struct scmi_protocol_handle *ph,
+					u8 evt_id, u32 src_id)
+{
+	struct reset_dom_info *dom;
+	struct scmi_reset_info *pi = ph->get_priv(ph);
+
+	if (evt_id != SCMI_EVENT_RESET_ISSUED || src_id >= pi->num_domains)
+		return false;
+
+	dom = pi->dom_info + src_id;
+
+	return dom->reset_notify;
+}
+
 static int scmi_reset_notify(const struct scmi_protocol_handle *ph,
 			     u32 domain_id, bool enable)
 {
@@ -301,6 +324,7 @@ static const struct scmi_event reset_events[] = {
 };
 
 static const struct scmi_event_ops reset_event_ops = {
+	.is_notify_supported = scmi_reset_notify_supported,
 	.get_num_sources = scmi_reset_get_num_sources,
 	.set_notify_enabled = scmi_reset_set_notify_enabled,
 	.fill_custom_report = scmi_reset_fill_custom_report,
@@ -339,11 +363,8 @@ static int scmi_reset_protocol_init(const struct scmi_protocol_handle *ph)
 	if (!pinfo->dom_info)
 		return -ENOMEM;
 
-	for (domain = 0; domain < pinfo->num_domains; domain++) {
-		struct reset_dom_info *dom = pinfo->dom_info + domain;
-
-		scmi_reset_domain_attributes_get(ph, domain, dom, version);
-	}
+	for (domain = 0; domain < pinfo->num_domains; domain++)
+		scmi_reset_domain_attributes_get(ph, pinfo, domain, version);
 
 	pinfo->version = version;
 	return ph->set_priv(ph, pinfo, version);
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 311149965370..7fc5535ca34c 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -215,6 +215,8 @@ struct scmi_sensor_update_notify_payld {
 
 struct sensors_info {
 	u32 version;
+	bool notify_trip_point_cmd;
+	bool notify_continuos_update_cmd;
 	int num_sensors;
 	int max_requests;
 	u64 reg_addr;
@@ -246,6 +248,18 @@ static int scmi_sensor_attributes_get(const struct scmi_protocol_handle *ph,
 	}
 
 	ph->xops->xfer_put(ph, t);
+
+	if (!ret) {
+		if (!ph->hops->protocol_msg_check(ph,
+						  SENSOR_TRIP_POINT_NOTIFY, NULL))
+			si->notify_trip_point_cmd = true;
+
+		if (!ph->hops->protocol_msg_check(ph,
+						  SENSOR_CONTINUOUS_UPDATE_NOTIFY,
+						  NULL))
+			si->notify_continuos_update_cmd = true;
+	}
+
 	return ret;
 }
 
@@ -594,7 +608,8 @@ iter_sens_descr_process_response(const struct scmi_protocol_handle *ph,
 	 * Such bitfields are assumed to be zeroed on non
 	 * relevant fw versions...assuming fw not buggy !
 	 */
-	s->update = SUPPORTS_UPDATE_NOTIFY(attrl);
+	if (si->notify_continuos_update_cmd)
+		s->update = SUPPORTS_UPDATE_NOTIFY(attrl);
 	s->timestamped = SUPPORTS_TIMESTAMP(attrl);
 	if (s->timestamped)
 		s->tstamp_scale = S32_EXT(SENSOR_TSTAMP_EXP(attrl));
@@ -988,6 +1003,25 @@ static const struct scmi_sensor_proto_ops sensor_proto_ops = {
 	.config_set = scmi_sensor_config_set,
 };
 
+static bool scmi_sensor_notify_supported(const struct scmi_protocol_handle *ph,
+					 u8 evt_id, u32 src_id)
+{
+	bool supported = false;
+	const struct scmi_sensor_info *s;
+	struct sensors_info *sinfo = ph->get_priv(ph);
+
+	s = scmi_sensor_info_get(ph, src_id);
+	if (!s)
+		return false;
+
+	if (evt_id == SCMI_EVENT_SENSOR_TRIP_POINT_EVENT)
+		supported = sinfo->notify_trip_point_cmd;
+	else if (evt_id == SCMI_EVENT_SENSOR_UPDATE)
+		supported = s->update;
+
+	return supported;
+}
+
 static int scmi_sensor_set_notify_enabled(const struct scmi_protocol_handle *ph,
 					  u8 evt_id, u32 src_id, bool enable)
 {
@@ -1099,6 +1133,7 @@ static const struct scmi_event sensor_events[] = {
 };
 
 static const struct scmi_event_ops sensor_event_ops = {
+	.is_notify_supported = scmi_sensor_notify_supported,
 	.get_num_sources = scmi_sensor_get_num_sources,
 	.set_notify_enabled = scmi_sensor_set_notify_enabled,
 	.fill_custom_report = scmi_sensor_fill_custom_report,
diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c
index 7611e9665038..39936e1dd30e 100644
--- a/drivers/firmware/arm_scmi/smc.c
+++ b/drivers/firmware/arm_scmi/smc.c
@@ -214,6 +214,13 @@ static int smc_chan_free(int id, void *p, void *data)
 	struct scmi_chan_info *cinfo = p;
 	struct scmi_smc *scmi_info = cinfo->transport_info;
 
+	/*
+	 * Different protocols might share the same chan info, so a previous
+	 * smc_chan_free call might have already freed the structure.
+	 */
+	if (!scmi_info)
+		return 0;
+
 	/* Ignore any possible further reception on the IRQ path */
 	if (scmi_info->irq > 0)
 		free_irq(scmi_info->irq, scmi_info);
diff --git a/drivers/firmware/arm_scmi/system.c b/drivers/firmware/arm_scmi/system.c
index 1621da97bcbb..b6358c155f7f 100644
--- a/drivers/firmware/arm_scmi/system.c
+++ b/drivers/firmware/arm_scmi/system.c
@@ -36,8 +36,20 @@ struct scmi_system_power_state_notifier_payld {
 struct scmi_system_info {
 	u32 version;
 	bool graceful_timeout_supported;
+	bool power_state_notify_cmd;
 };
 
+static bool scmi_system_notify_supported(const struct scmi_protocol_handle *ph,
+					 u8 evt_id, u32 src_id)
+{
+	struct scmi_system_info *pinfo = ph->get_priv(ph);
+
+	if (evt_id != SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER)
+		return false;
+
+	return pinfo->power_state_notify_cmd;
+}
+
 static int scmi_system_request_notify(const struct scmi_protocol_handle *ph,
 				      bool enable)
 {
@@ -114,6 +126,7 @@ static const struct scmi_event system_events[] = {
 };
 
 static const struct scmi_event_ops system_event_ops = {
+	.is_notify_supported = scmi_system_notify_supported,
 	.set_notify_enabled = scmi_system_set_notify_enabled,
 	.fill_custom_report = scmi_system_fill_custom_report,
 };
@@ -147,6 +160,9 @@ static int scmi_system_protocol_init(const struct scmi_protocol_handle *ph)
 	if (PROTOCOL_REV_MAJOR(pinfo->version) >= 0x2)
 		pinfo->graceful_timeout_supported = true;
 
+	if (!ph->hops->protocol_msg_check(ph, SYSTEM_POWER_STATE_NOTIFY, NULL))
+		pinfo->power_state_notify_cmd = true;
+
 	return ph->set_priv(ph, pinfo, version);
 }
 
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 83f5bb57fa4c..83092d93f36a 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c
index 3e8d4b51a814..97bafb5f7038 100644
--- a/drivers/firmware/efi/capsule-loader.c
+++ b/drivers/firmware/efi/capsule-loader.c
@@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
-	cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
+	cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL);
 	if (!cap_info->phys) {
 		kfree(cap_info->pages);
 		kfree(cap_info);
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 35c37f667781..9b3884ff81e6 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx,
 	}
 }
 
+struct ignore_section {
+	guid_t guid;
+	const char *name;
+};
+
+static const struct ignore_section ignore_sections[] = {
+	{ .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" },
+	{ .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" },
+	{ .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" },
+};
+
 static void
 cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata,
 			   int sec_no)
@@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
 
 	snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+	for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) {
+		if (guid_equal(sec_type, &ignore_sections[i].guid)) {
+			printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name);
+			return;
+		}
+	}
+
 	if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
 		struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index d4987d013080..a00e07b853f2 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -144,15 +144,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
 		/*
-		 * Special purpose memory is 'soft reserved', which means it
-		 * is set aside initially, but can be hotplugged back in or
-		 * be assigned to the dax driver after boot.
-		 */
-		if (efi_soft_reserve_enabled() &&
-		    (md->attribute & EFI_MEMORY_SP))
-			return false;
-
-		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use
 		 * them as System RAM if they can be mapped writeback cacheable.
@@ -196,6 +187,16 @@ static __init void reserve_regions(void)
 		size = npages << PAGE_SHIFT;
 
 		if (is_memory(md)) {
+			/*
+			 * Special purpose memory is 'soft reserved', which
+			 * means it is set aside initially. Don't add a memblock
+			 * for it now so that it can be hotplugged back in or
+			 * be assigned to the dax driver after boot.
+			 */
+			if (efi_soft_reserve_enabled() &&
+			    (md->attribute & EFI_MEMORY_SP))
+				continue;
+
 			early_init_dt_add_memory_arch(paddr, size);
 
 			if (!is_usable_memory(md))
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index e7b9ec6f8a86..833cbb995dd3 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -14,16 +14,43 @@ static unsigned int record_size = 1024;
 module_param(record_size, uint, 0444);
 MODULE_PARM_DESC(record_size, "size of each pstore UEFI var (in bytes, min/default=1024)");
 
-static bool efivars_pstore_disable =
-	IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE);
-
-module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
-
 #define PSTORE_EFI_ATTRIBUTES \
 	(EFI_VARIABLE_NON_VOLATILE | \
 	 EFI_VARIABLE_BOOTSERVICE_ACCESS | \
 	 EFI_VARIABLE_RUNTIME_ACCESS)
 
+static bool pstore_disable = IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE);
+
+static int efivars_pstore_init(void);
+static void efivars_pstore_exit(void);
+
+static int efi_pstore_disable_set(const char *val, const struct kernel_param *kp)
+{
+	int err;
+	bool old_pstore_disable = pstore_disable;
+
+	err = param_set_bool(val, kp);
+	if (err)
+		return err;
+
+	if (old_pstore_disable != pstore_disable) {
+		if (pstore_disable)
+			efivars_pstore_exit();
+		else
+			efivars_pstore_init();
+	}
+
+	return 0;
+}
+
+static const struct kernel_param_ops pstore_disable_ops = {
+	.set	= efi_pstore_disable_set,
+	.get	= param_get_bool,
+};
+
+module_param_cb(pstore_disable, &pstore_disable_ops, &pstore_disable, 0644);
+__MODULE_PARM_TYPE(pstore_disable, "bool");
+
 static int efi_pstore_open(struct pstore_info *psi)
 {
 	int err;
@@ -218,12 +245,12 @@ static struct pstore_info efi_pstore_info = {
 	.erase		= efi_pstore_erase,
 };
 
-static __init int efivars_pstore_init(void)
+static int efivars_pstore_init(void)
 {
 	if (!efivar_supports_writes())
 		return 0;
 
-	if (efivars_pstore_disable)
+	if (pstore_disable)
 		return 0;
 
 	/*
@@ -250,7 +277,7 @@ static __init int efivars_pstore_init(void)
 	return 0;
 }
 
-static __exit void efivars_pstore_exit(void)
+static void efivars_pstore_exit(void)
 {
 	if (!efi_pstore_info.bufsize)
 		return;
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 06964a3c130f..73f4810f6db3 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM)		+= -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE
+cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax
 cflags-$(CONFIG_LOONGARCH)	+= -fpie
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
@@ -143,7 +143,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
 # exist.
 STUBCOPY_FLAGS-$(CONFIG_RISCV)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
-STUBCOPY_RELOC-$(CONFIG_RISCV)	:= R_RISCV_HI20
+STUBCOPY_RELOC-$(CONFIG_RISCV)	:= -E R_RISCV_HI20\|R_RISCV_$(BITS)\|R_RISCV_RELAX
 
 # For LoongArch, keep all the symbols in .init section and make sure that no
 # absolute symbols references exist.
diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
index 6b83c492c3b8..31928bd87e0f 100644
--- a/drivers/firmware/efi/libstub/alignedmem.c
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -14,6 +14,7 @@
  * @max:	the address that the last allocated memory page shall not
  *		exceed
  * @align:	minimum alignment of the base of the allocation
+ * @memory_type: the type of memory to allocate
  *
  * Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according
  * to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index bfa30625f5d0..3dc2f9aaf08d 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -24,6 +24,8 @@ static bool efi_noinitrd;
 static bool efi_nosoftreserve;
 static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA);
 
+int efi_mem_encrypt;
+
 bool __pure __efi_soft_reserve_enabled(void)
 {
 	return !efi_nosoftreserve;
@@ -75,6 +77,12 @@ efi_status_t efi_parse_options(char const *cmdline)
 			efi_noinitrd = true;
 		} else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) {
 			efi_no5lvl = true;
+		} else if (IS_ENABLED(CONFIG_ARCH_HAS_MEM_ENCRYPT) &&
+			   !strcmp(param, "mem_encrypt") && val) {
+			if (parse_option_str(val, "on"))
+				efi_mem_encrypt = 1;
+			else if (parse_option_str(val, "off"))
+				efi_mem_encrypt = -1;
 		} else if (!strcmp(param, "efi") && val) {
 			efi_nochunk = parse_option_str(val, "nochunk");
 			efi_novamap |= parse_option_str(val, "novamap");
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 212687c30d79..fc18fd649ed7 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -37,8 +37,8 @@ extern bool efi_no5lvl;
 extern bool efi_nochunk;
 extern bool efi_nokaslr;
 extern int efi_loglevel;
+extern int efi_mem_encrypt;
 extern bool efi_novamap;
-
 extern const efi_system_table_t *efi_system_table;
 
 typedef union efi_dxe_services_table efi_dxe_services_table_t;
@@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
 
 efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
 			      unsigned long *addr, unsigned long random_seed,
-			      int memory_type, unsigned long alloc_limit);
+			      int memory_type, unsigned long alloc_min,
+			      unsigned long alloc_max);
 
 efi_status_t efi_random_get_seed(void);
 
diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
index 62d63f7a2645..1a9808012abd 100644
--- a/drivers/firmware/efi/libstub/kaslr.c
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
 		 */
 		status = efi_random_alloc(*reserve_size, min_kimg_align,
 					  reserve_addr, phys_seed,
-					  EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS)
 			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
 	} else {
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 674a064b8f7a..4e96a855fdf4 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -17,7 +17,7 @@
 static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 					 unsigned long size,
 					 unsigned long align_shift,
-					 u64 alloc_limit)
+					 u64 alloc_min, u64 alloc_max)
 {
 	unsigned long align = 1UL << align_shift;
 	u64 first_slot, last_slot, region_end;
@@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 		return 0;
 
 	region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1,
-			 alloc_limit);
+			 alloc_max);
 	if (region_end < size)
 		return 0;
 
-	first_slot = round_up(md->phys_addr, align);
+	first_slot = round_up(max(md->phys_addr, alloc_min), align);
 	last_slot = round_down(region_end - size + 1, align);
 
 	if (first_slot > last_slot)
@@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 			      unsigned long *addr,
 			      unsigned long random_seed,
 			      int memory_type,
-			      unsigned long alloc_limit)
+			      unsigned long alloc_min,
+			      unsigned long alloc_max)
 {
 	unsigned long total_slots = 0, target_slot;
 	unsigned long total_mirrored_slots = 0;
@@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 		efi_memory_desc_t *md = (void *)map->map + map_offset;
 		unsigned long slots;
 
-		slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit);
+		slots = get_entry_num_slots(md, size, ilog2(align), alloc_min,
+					    alloc_max);
 		MD_NUM_SLOTS(md) = slots;
 		total_slots += slots;
 		if (md->attribute & EFI_MEMORY_MORE_RELIABLE)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 0d510c9a06a4..0336ed175e67 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	}
 }
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size)
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size)
 {
 	efi_status_t status;
 	efi_gcd_memory_space_desc_t desc;
@@ -236,13 +236,17 @@ void efi_adjust_memory_range_protection(unsigned long start,
 	rounded_end = roundup(start + size, EFI_PAGE_SIZE);
 
 	if (memattr != NULL) {
-		efi_call_proto(memattr, clear_memory_attributes, rounded_start,
-			       rounded_end - rounded_start, EFI_MEMORY_XP);
-		return;
+		status = efi_call_proto(memattr, clear_memory_attributes,
+					rounded_start,
+					rounded_end - rounded_start,
+					EFI_MEMORY_XP);
+		if (status != EFI_SUCCESS)
+			efi_warn("Failed to clear EFI_MEMORY_XP attribute\n");
+		return status;
 	}
 
 	if (efi_dxe_table == NULL)
-		return;
+		return EFI_SUCCESS;
 
 	/*
 	 * Don't modify memory region attributes, they are
@@ -255,7 +259,7 @@ void efi_adjust_memory_range_protection(unsigned long start,
 		status = efi_dxe_call(get_memory_space_descriptor, start, &desc);
 
 		if (status != EFI_SUCCESS)
-			return;
+			break;
 
 		next = desc.base_address + desc.length;
 
@@ -280,8 +284,10 @@ void efi_adjust_memory_range_protection(unsigned long start,
 				 unprotect_start,
 				 unprotect_start + unprotect_size,
 				 status);
+			break;
 		}
 	}
+	return EFI_SUCCESS;
 }
 
 static void setup_unaccepted_memory(void)
@@ -793,6 +799,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
 				  seed[0], EFI_LOADER_CODE,
+				  LOAD_PHYSICAL_ADDR,
 				  EFI_X86_KERNEL_ALLOC_LIMIT);
 	if (status != EFI_SUCCESS)
 		return status;
@@ -805,9 +812,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
 
 	*kernel_entry = addr + entry;
 
-	efi_adjust_memory_range_protection(addr, kernel_total_size);
-
-	return EFI_SUCCESS;
+	return efi_adjust_memory_range_protection(addr, kernel_total_size);
 }
 
 static void __noreturn enter_kernel(unsigned long kernel_addr,
@@ -879,6 +884,9 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 		}
 	}
 
+	if (efi_mem_encrypt > 0)
+		hdr->xloadflags |= XLF_MEM_ENCRYPTION;
+
 	status = efi_decompress_kernel(&kernel_entry);
 	if (status != EFI_SUCCESS) {
 		efi_err("Failed to decompress kernel\n");
diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h
index 37c5a36b9d8c..1c20e99a6494 100644
--- a/drivers/firmware/efi/libstub/x86-stub.h
+++ b/drivers/firmware/efi/libstub/x86-stub.h
@@ -5,8 +5,8 @@
 extern void trampoline_32bit_src(void *, bool);
 extern const u16 trampoline_ljmp_imm_offset;
 
-void efi_adjust_memory_range_protection(unsigned long start,
-					unsigned long size);
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+						unsigned long size);
 
 #ifdef CONFIG_X86_64
 efi_status_t efi_setup_5level_paging(void);
diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c
index bdb17eac0cb4..1ceace956758 100644
--- a/drivers/firmware/efi/libstub/zboot.c
+++ b/drivers/firmware/efi/libstub/zboot.c
@@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab)
 		}
 
 		status = efi_random_alloc(alloc_size, min_kimg_align, &image_base,
-					  seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+					  seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to allocate memory\n");
 			goto free_cmdline;
diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c
index 09525fb5c240..01f0f90ea418 100644
--- a/drivers/firmware/efi/riscv-runtime.c
+++ b/drivers/firmware/efi/riscv-runtime.c
@@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void)
 		efi_memory_desc_t *md;
 
 		for_each_efi_memory_desc(md) {
-			int md_size = md->num_pages << EFI_PAGE_SHIFT;
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
 			struct resource *res;
 
 			if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
index 81f5f62e34fc..fbeeaee4ac85 100644
--- a/drivers/firmware/microchip/mpfs-auto-update.c
+++ b/drivers/firmware/microchip/mpfs-auto-update.c
@@ -167,7 +167,7 @@ static int mpfs_auto_update_verify_image(struct fw_upload *fw_uploader)
 	u32 *response_msg;
 	int ret;
 
-	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg),
 				    GFP_KERNEL);
 	if (!response_msg)
 		return -ENOMEM;
@@ -384,7 +384,8 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv)
 	u32 *response_msg;
 	int ret;
 
-	response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg),
+	response_msg = devm_kzalloc(priv->dev,
+				    AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg),
 				    GFP_KERNEL);
 	if (!response_msg)
 		return -ENOMEM;
diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c
index bbcdd9fed3fb..4221fed70ad4 100644
--- a/drivers/firmware/tegra/bpmp-debugfs.c
+++ b/drivers/firmware/tegra/bpmp-debugfs.c
@@ -77,7 +77,7 @@ static const char *get_filename(struct tegra_bpmp *bpmp,
 
 	root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL);
 	if (!root_path_buf)
-		goto out;
+		return NULL;
 
 	root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf,
 				root_path_buf_len);
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index e00c33310517..753e7be039e4 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi)
 	if (IS_ERR(chip->gpiod_oe))
 		return PTR_ERR(chip->gpiod_oe);
 
-	gpiod_set_value_cansleep(chip->gpiod_oe, 1);
-
 	spi_set_drvdata(spi, chip);
 
 	chip->gpio_chip.label = spi->modalias;
@@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi)
 		goto exit_destroy;
 	}
 
+	gpiod_set_value_cansleep(chip->gpiod_oe, 1);
+
 	ret = gpiochip_add_data(&chip->gpio_chip, chip);
 	if (!ret)
 		return 0;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 44c8f5743a24..75be4a3ca7f8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -968,11 +968,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 	ret = gpiochip_irqchip_init_valid_mask(gc);
 	if (ret)
-		goto err_remove_acpi_chip;
+		goto err_free_hogs;
 
 	ret = gpiochip_irqchip_init_hw(gc);
 	if (ret)
-		goto err_remove_acpi_chip;
+		goto err_remove_irqchip_mask;
 
 	ret = gpiochip_add_irqchip(gc, lock_key, request_key);
 	if (ret)
@@ -997,23 +997,23 @@ err_remove_irqchip:
 	gpiochip_irqchip_remove(gc);
 err_remove_irqchip_mask:
 	gpiochip_irqchip_free_valid_mask(gc);
-err_remove_acpi_chip:
+err_free_hogs:
+	gpiochip_free_hogs(gc);
 	acpi_gpiochip_remove(gc);
+	gpiochip_remove_pin_ranges(gc);
 err_remove_of_chip:
-	gpiochip_free_hogs(gc);
 	of_gpiochip_remove(gc);
 err_free_gpiochip_mask:
-	gpiochip_remove_pin_ranges(gc);
 	gpiochip_free_valid_mask(gc);
+err_remove_from_list:
+	spin_lock_irqsave(&gpio_lock, flags);
+	list_del(&gdev->list);
+	spin_unlock_irqrestore(&gpio_lock, flags);
 	if (gdev->dev.release) {
 		/* release() has been registered by gpiochip_setup_dev() */
 		gpio_device_put(gdev);
 		goto err_print_message;
 	}
-err_remove_from_list:
-	spin_lock_irqsave(&gpio_lock, flags);
-	list_del(&gdev->list);
-	spin_unlock_irqrestore(&gpio_lock, flags);
 err_free_label:
 	kfree_const(gdev->label);
 err_free_descs:
@@ -2042,6 +2042,11 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_free);
 int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset,
 			    unsigned long config)
 {
+#ifdef CONFIG_PINCTRL
+	if (list_empty(&gc->gpiodev->pin_ranges))
+		return -ENOTSUPP;
+#endif
+
 	return pinctrl_gpio_set_config(gc, offset, config);
 }
 EXPORT_SYMBOL_GPL(gpiochip_generic_config);
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2520db0b776e..c7edba18a6f0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -199,7 +199,7 @@ config DRM_TTM
 config DRM_TTM_KUNIT_TEST
         tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS
         default n
-        depends on DRM && KUNIT && MMU
+        depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST)
         select DRM_TTM
         select DRM_EXPORT_FOR_TESTS if m
         select DRM_KUNIT_TEST_HELPERS
@@ -207,7 +207,8 @@ config DRM_TTM_KUNIT_TEST
         help
           Enables unit tests for TTM, a GPU memory manager subsystem used
           to manage memory buffers. This option is mostly useful for kernel
-          developers.
+          developers. It depends on (UML || COMPILE_TEST) since no other driver
+          which uses TTM can be loaded while running the tests.
 
           If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b01..79827a6dcd7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -200,6 +200,7 @@ extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dc_visual_confirm;
 extern uint amdgpu_dm_abm_level;
 extern int amdgpu_backlight;
+extern int amdgpu_damage_clips;
 extern struct amdgpu_mgpu_info mgpu_info;
 extern int amdgpu_ras_enable;
 extern uint amdgpu_ras_mask;
@@ -1078,6 +1079,8 @@ struct amdgpu_device {
 	bool				in_s3;
 	bool				in_s4;
 	bool				in_s0ix;
+	/* indicate amdgpu suspension status */
+	bool				suspend_complete;
 
 	enum pp_mp1_state               mp1_state;
 	struct amdgpu_doorbell_index doorbell_index;
@@ -1547,9 +1550,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
+static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
 #endif
 
 #if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 2deebece810e..7099ff9cf8c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,22 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 #endif /* CONFIG_AMD_PMC */
 }
 
+/**
+ * amdgpu_choose_low_power_state
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * Choose the target low power state for the GPU
+ */
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
+{
+	if (adev->in_runpm)
+		return;
+
+	if (amdgpu_acpi_is_s0ix_active(adev))
+		adev->in_s0ix = true;
+	else if (amdgpu_acpi_is_s3_active(adev))
+		adev->in_s3 = true;
+}
+
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 77e263660288..41db030ddc4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -141,11 +141,31 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 static const struct drm_client_funcs kfd_client_funcs = {
 	.unregister	= drm_client_release,
 };
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev)
+{
+	int ret;
+
+	if (!adev->kfd.init_complete)
+		return 0;
+
+	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
+			      &kfd_client_funcs);
+	if (ret) {
+		dev_err(adev->dev, "Failed to init DRM client: %d\n",
+			ret);
+		return ret;
+	}
+
+	drm_client_register(&adev->kfd.client);
+
+	return 0;
+}
+
 void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
 	int i;
 	int last_valid_bit;
-	int ret;
 
 	amdgpu_amdkfd_gpuvm_init_mem_limits();
 
@@ -164,12 +184,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 			.enable_mes = adev->enable_mes,
 		};
 
-		ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
-		if (ret) {
-			dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
-			return;
-		}
-
 		/* this is going to have a few of the MSBs set that we need to
 		 * clear
 		 */
@@ -208,10 +222,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
 		adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
 							&gpu_resources);
-		if (adev->kfd.init_complete)
-			drm_client_register(&adev->kfd.client);
-		else
-			drm_client_release(&adev->kfd.client);
 
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index f262b9d89541..27c61c535e29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -182,6 +182,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
 struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
 				struct mm_struct *mm,
 				struct svm_range_bo *svm_bo);
+
+int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev);
 #if defined(CONFIG_DEBUG_FS)
 int kfd_debugfs_kfd_mem_limits(struct seq_file *m, void *data);
 #endif
@@ -301,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev,
 					  struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
 int amdgpu_amdkfd_gpuvm_sync_memory(
 		struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);
 int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index 899e31e3a5e8..3a3f3ce09f00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -290,7 +290,7 @@ static int suspend_resume_compute_scheduler(struct amdgpu_device *adev, bool sus
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 
-		if (!(ring && drm_sched_wqueue_ready(&ring->sched)))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* stop secheduler and drain ring. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f183d7faeeec..231fd927dcfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2085,21 +2085,35 @@ out:
 	return ret;
 }
 
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
 {
 	struct kfd_mem_attachment *entry;
 	struct amdgpu_vm *vm;
+	int ret;
 
 	vm = drm_priv_to_vm(drm_priv);
 
 	mutex_lock(&mem->lock);
 
+	ret = amdgpu_bo_reserve(mem->bo, true);
+	if (ret)
+		goto out;
+
 	list_for_each_entry(entry, &mem->attachments, list) {
-		if (entry->bo_va->base.vm == vm)
-			kfd_mem_dmaunmap_attachment(mem, entry);
+		if (entry->bo_va->base.vm != vm)
+			continue;
+		if (entry->bo_va->base.bo->tbo.ttm &&
+		    !entry->bo_va->base.bo->tbo.ttm->sg)
+			continue;
+
+		kfd_mem_dmaunmap_attachment(mem, entry);
 	}
 
+	amdgpu_bo_unreserve(mem->bo);
+out:
 	mutex_unlock(&mem->lock);
+
+	return ret;
 }
 
 int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index e485dd3357c6..1afbb2e932c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1678,7 +1678,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_stop(&ring->sched);
 	}
@@ -1694,7 +1694,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 		drm_sched_wqueue_start(&ring->sched);
 	}
@@ -1916,8 +1916,8 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 
 	ring = adev->rings[val];
 
-	if (!ring || !ring->funcs->preempt_ib ||
-	    !drm_sched_wqueue_ready(&ring->sched))
+	if (!amdgpu_ring_sched_ready(ring) ||
+	    !ring->funcs->preempt_ib)
 		return -EINVAL;
 
 	/* the last preemption failed */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b158d27d0a71..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4121,23 +4121,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
-			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-			case IP_VERSION(13, 0, 0):
-			case IP_VERSION(13, 0, 7):
-			case IP_VERSION(13, 0, 10):
-				r = psp_gpu_reset(adev);
-				break;
-			default:
-				tmp = amdgpu_reset_method;
-				/* It should do a default reset when loading or reloading the driver,
-				 * regardless of the module parameter reset_method.
-				 */
-				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-				r = amdgpu_asic_reset(adev);
-				amdgpu_reset_method = tmp;
-				break;
-			}
-
+			tmp = amdgpu_reset_method;
+			/* It should do a default reset when loading or reloading the driver,
+			 * regardless of the module parameter reset_method.
+			 */
+			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+			r = amdgpu_asic_reset(adev);
+			amdgpu_reset_method = tmp;
 			if (r) {
 				dev_err(adev->dev, "asic reset on init failed\n");
 				goto failed;
@@ -4524,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	int i, r;
 
+	amdgpu_choose_low_power_state(adev);
+
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
 	/* Evict the majority of BOs before starting suspend sequence */
 	r = amdgpu_device_evict_resources(adev);
 	if (r)
-		return r;
+		goto unprepare;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -4539,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
 			continue;
 		r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
 		if (r)
-			return r;
+			goto unprepare;
 	}
 
 	return 0;
+
+unprepare:
+	adev->in_s0ix = adev->in_s3 = false;
+
+	return r;
 }
 
 /**
@@ -4579,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
-	flush_delayed_work(&adev->gfx.gfx_off_delay_work);
 
 	amdgpu_ras_suspend(adev);
 
@@ -5031,7 +5027,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		spin_lock(&ring->sched.job_list_lock);
@@ -5170,7 +5166,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		/* Clear job fence from fence drv to avoid force_completion
@@ -5637,7 +5633,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
@@ -5706,7 +5702,7 @@ skip_hw_reset:
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_start(&ring->sched, true);
@@ -6061,7 +6057,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 
-			if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+			if (!amdgpu_ring_sched_ready(ring))
 				continue;
 
 			drm_sched_stop(&ring->sched, NULL);
@@ -6189,7 +6185,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 
-		if (!ring || !drm_sched_wqueue_ready(&ring->sched))
+		if (!amdgpu_ring_sched_ready(ring))
 			continue;
 
 		drm_sched_start(&ring->sched, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index cc69005f5b46..586f4d03039d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -211,6 +211,7 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
+int amdgpu_damage_clips = -1; /* auto */
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -860,6 +861,18 @@ MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (defau
 module_param_named(backlight, amdgpu_backlight, bint, 0444);
 
 /**
+ * DOC: damageclips (int)
+ * Enable or disable damage clips support. If damage clips support is disabled,
+ * we will force full frame updates, irrespective of what user space sends to
+ * us.
+ *
+ * Defaults to -1 (where it is enabled unless a PSR-SU display is detected).
+ */
+MODULE_PARM_DESC(damageclips,
+		 "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
+module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
+
+/**
  * DOC: tmz (int)
  * Trusted Memory Zone (TMZ) is a method to protect data being written
  * to or read from memory.
@@ -2255,6 +2268,10 @@ retry_init:
 	if (ret)
 		goto err_pci;
 
+	ret = amdgpu_amdkfd_drm_client_create(adev);
+	if (ret)
+		goto err_pci;
+
 	/*
 	 * 1. don't init fbdev on hw without DCE
 	 * 2. don't init fbdev if there are no connectors
@@ -2472,6 +2489,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = false;
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else if (amdgpu_acpi_is_s3_active(adev))
@@ -2486,6 +2504,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 
+	adev->suspend_complete = true;
 	if (amdgpu_acpi_should_gpu_reset(adev))
 		return amdgpu_asic_reset(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c436..6ddc8e3360e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -723,8 +723,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix) {
+				if (!amdgpu_dpm_set_powergating_by_smu(adev,
+						AMD_IP_BLOCK_TYPE_GFX, true))
+					adev->gfx.gfx_off_state = true;
+			} else {
+				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
 					      delay);
+			}
 		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4..ca5c86e5f7cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 		}
 	}
 
-	if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
 err_free_shared_buf:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 45424ebf9681..5505d646f43a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -635,6 +635,7 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 			      ring->name);
 
 	ring->sched.ready = !r;
+
 	return r;
 }
 
@@ -717,3 +718,14 @@ void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring)
 	if (ring->is_sw_ring)
 		amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE);
 }
+
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring)
+{
+	if (!ring)
+		return false;
+
+	if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))
+		return false;
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index bbb53720a018..fe1a61eb6e4c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -450,5 +450,5 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);
 void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
-
+bool amdgpu_ring_sched_ready(struct amdgpu_ring *ring);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index 6f7c031dd197..f24e34dc33d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(mmIH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(mmIH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(mmIH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index b8c47e0cf37a..c19681492efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ecb622b7f970..dcdecb18b230 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4027,8 +4027,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);
 
 	gfx_v10_0_check_fw_write_wait(adev);
 out:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d9cf9fd03d30..4f3bfdc75b37 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -107,23 +107,6 @@ static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xfcffffff, 0x0000000a)
 };
 
-static const struct soc15_reg_golden golden_settings_gc_11_5_0[] = {
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_DEBUG5, 0xffffffff, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xfffffff3),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL, 0xffffffff, 0xf37fff3f),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL3, 0xfffffffb, 0x00f40188),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL4, 0xf0ffffff, 0x80009007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPA_CL_ENHANCE, 0xf1ffffff, 0x00880007),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regPC_CONFIG_CNTL_1, 0xffffffff, 0x00010000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL_AUX, 0xf7f7ffff, 0x01030000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTA_CNTL2, 0x007f0000, 0x00000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL2, 0xffcfffff, 0x0000200a),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, regUTCL1_CTRL_2, 0xffffffff, 0x0000048f)
-};
-
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
@@ -304,11 +287,6 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_11_0_1,
 						(const u32)ARRAY_SIZE(golden_settings_gc_11_0_1));
 		break;
-	case IP_VERSION(11, 5, 0):
-		soc15_program_register_sequence(adev,
-						golden_settings_gc_11_5_0,
-						(const u32)ARRAY_SIZE(golden_settings_gc_11_5_0));
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c500910746..3bc6943365a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
 
 	gfx_v9_0_cp_gfx_enable(adev, true);
 
+	/* Now only limit the quirk on the APU gfx9 series and already
+	 * confirmed that the APU gfx10/gfx11 needn't such update.
+	 */
+	if (adev->flags & AMD_IS_APU &&
+			adev->in_s3 && !adev->suspend_complete) {
+		DRM_INFO(" Will skip the CSB packet resubmit\n");
+		return 0;
+	}
 	r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
 	if (r) {
 		DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 42e103d7077d..59d9215e5556 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -915,8 +915,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index efc16e580f1e..45a2f8e031a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1099,8 +1099,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ff4ae73d27ec..4422b27a3cc2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1219,8 +1219,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 17b7a25121b0..e67a62db9e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
 
 static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
 {
-	static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
-	u32 vram_info;
-
-	/* Only for dGPU, vendor informaton is reliable */
-	if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
-		vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
-		adev->gmc.vram_vendor = vram_info & 0xF;
-	}
 	adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
 	adev->gmc.vram_width = 128 * 64;
 }
@@ -2341,8 +2333,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index aecad530b10a..2c02ae69883d 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
 
 out:
 	return (wptr & ih->ptr_mask);
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index d9ed7332d805..ad4ad39f128f 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -418,6 +418,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index 8fb05eae340a..b8da0fc29378 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf8..88ea58d5c4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
-	.set = jpeg_v4_0_set_interrupt_state,
 	.process = jpeg_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8..78b74daf4eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
 			jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 	}
-	amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
 
 	return 0;
 }
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
 	return ret;
 }
 
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
-					struct amdgpu_irq_src *source,
-					unsigned type,
-					enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
 static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 }
 
 static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
-	.set = jpeg_v4_0_5_set_interrupt_state,
 	.process = jpeg_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index e64b33115848..de93614726c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f33780803..b4723d68eab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
 	u32 inst_mask;
 	int i;
 
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(
+				NBIO, 0,
+				regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+			<< 2;
 	WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
 		0xff & ~(adev->gfx.xcc_mask));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 9a24f17a5750..cada9f300a7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(IH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(IH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2ba..1c614451dead 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE1;
 }
 
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+	u32 sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	/* Will reset for the following suspend abort cases.
+	 * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+	 * 2) S3 suspend abort and TOS already launched.
+	 */
+	if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+			!adev->suspend_complete &&
+			sol_reg)
+		return true;
+
+	return false;
+}
+
 static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	/* original raven doesn't have full asic reset */
-	if ((adev->apu_flags & AMD_APU_IS_RAVEN) ||
-	    (adev->apu_flags & AMD_APU_IS_RAVEN2))
+	/* On the latest Raven, the GPU reset can be performed
+	 * successfully. So now, temporarily enable it for the
+	 * S3 suspend abort case.
+	 */
+	if (((adev->apu_flags & AMD_APU_IS_RAVEN) ||
+	    (adev->apu_flags & AMD_APU_IS_RAVEN2)) &&
+		!soc15_need_reset_on_resume(adev))
 		return 0;
 
 	switch (soc15_asic_reset_method(adev)) {
@@ -1302,6 +1325,10 @@ static int soc15_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc15_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+		soc15_asic_reset(adev);
+	}
 	return soc15_common_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac9..4d7188912edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 917707bba7f3..450b6e831509 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 169ed400ee7b..8ab01ae919d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -2018,22 +2018,6 @@ static int vcn_v4_0_set_powergating_state(void *handle, enum amd_powergating_sta
 }
 
 /**
- * vcn_v4_0_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-      unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state
  *
  * @adev: amdgpu_device pointer
@@ -2097,7 +2081,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = {
-	.set = vcn_v4_0_set_interrupt_state,
 	.process = vcn_v4_0_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 2eda30e78f61..49e4c3c09aca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -269,8 +269,6 @@ static int vcn_v4_0_5_hw_fini(void *handle)
 				vcn_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 			}
 		}
-
-		amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
 	}
 
 	return 0;
@@ -1669,22 +1667,6 @@ static int vcn_v4_0_5_set_powergating_state(void *handle, enum amd_powergating_s
 }
 
 /**
- * vcn_v4_0_5_set_interrupt_state - set VCN block interrupt state
- *
- * @adev: amdgpu_device pointer
- * @source: interrupt sources
- * @type: interrupt types
- * @state: interrupt states
- *
- * Set VCN block interrupt state
- */
-static int vcn_v4_0_5_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
-		unsigned type, enum amdgpu_interrupt_state state)
-{
-	return 0;
-}
-
-/**
  * vcn_v4_0_5_process_interrupt - process VCN block interrupt
  *
  * @adev: amdgpu_device pointer
@@ -1726,7 +1708,6 @@ static int vcn_v4_0_5_process_interrupt(struct amdgpu_device *adev, struct amdgp
 }
 
 static const struct amdgpu_irq_src_funcs vcn_v4_0_5_irq_funcs = {
-	.set = vcn_v4_0_5_set_interrupt_state,
 	.process = vcn_v4_0_5_process_interrupt,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index d364c6dd152c..bf68e18e3824 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
index ddfc6941f9d5..db66e6cccaf2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index df75863393fc..d1caaf0e6a7c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -674,7 +674,7 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_nv1x_hex[] = {
@@ -1091,7 +1091,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 	0xb9eef807, 0x876dff6d,
 	0x0000ffff, 0x87fe7e7e,
 	0x87ea6a6a, 0xb9faf802,
-	0xbe80226c, 0xbf810000,
+	0xbe80226c, 0xbf9b0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -1574,7 +1574,7 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_aldebaran_hex[] = {
@@ -2065,7 +2065,7 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
 
 static const uint32_t cwsr_trap_gfx10_hex[] = {
@@ -2500,7 +2500,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x876dff6d, 0x0000ffff,
 	0x87fe7e7e, 0x87ea6a6a,
 	0xb9faf802, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0xbf9b0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 };
@@ -2944,7 +2944,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
 	0xb8eef802, 0xbf0d866e,
 	0xbfa20002, 0xb97af802,
 	0xbe80486c, 0xb97af802,
-	0xbe804a6c, 0xbfb00000,
+	0xbe804a6c, 0xbfb10000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0x00000000,
@@ -3436,5 +3436,5 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x86ea6a6a, 0x8f6e837a,
 	0xb96ee0c2, 0xbf800002,
 	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf810000,
+	0xbe801f6c, 0xbf9b0000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index e0140df0b0ec..71b3dc0c7363 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -1104,7 +1104,7 @@ L_RETURN_WITHOUT_PRIV:
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM:
-	s_endpgm
+	s_endpgm_saved
 end
 
 function write_hwreg_to_mem(s, s_rsrc, s_mem_offset)
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index e506411ad28a..bb26338204f4 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -921,7 +921,7 @@ L_RESTORE:
 /*			the END						  */
 /**************************************************************************/
 L_END_PGM:
-    s_endpgm
+    s_endpgm_saved
 
 end
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ce4c52ec34d8..80e90fdef291 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1442,7 +1442,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 			kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
 
 		/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
-		amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+		if (err)
+			goto sync_memory_failed;
 	}
 
 	mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index f856901055d3..bdc01ca9609a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -574,7 +574,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
 		 prange->last);
 
-	addr = prange->start << PAGE_SHIFT;
+	addr = migrate->start;
 
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index d722cbd31783..826bc4f6c8a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -55,8 +55,8 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 	m = get_mqd(mqd);
 
 	if (has_wa_flag) {
-		uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
-						0xffff : 0xffffffff;
+		uint32_t wa_mask =
+			(minfo->update_flag & UPDATE_FLAG_DBG_WA_ENABLE) ? 0xffff : 0xffffffff;
 
 		m->compute_static_thread_mgmt_se0 = wa_mask;
 		m->compute_static_thread_mgmt_se1 = wa_mask;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 42d881809dc7..697b6d530d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -303,6 +303,15 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		update_cu_mask(mm, mqd, minfo, 0);
 	set_priority(m, q);
 
+	if (minfo && KFD_GC_VERSION(mm->dev) >= IP_VERSION(9, 4, 2)) {
+		if (minfo->update_flag & UPDATE_FLAG_IS_GWS)
+			m->compute_resource_limits |=
+				COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+		else
+			m->compute_resource_limits &=
+				~COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+	}
+
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 17fbedbf3651..80320b8603fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -532,6 +532,7 @@ struct queue_properties {
 enum mqd_update_flag {
 	UPDATE_FLAG_DBG_WA_ENABLE = 1,
 	UPDATE_FLAG_DBG_WA_DISABLE = 2,
+	UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */
 };
 
 struct mqd_update_info {
@@ -1488,10 +1489,15 @@ void kfd_dec_compute_active(struct kfd_node *dev);
 
 /* Cgroup Support */
 /* Check with device cgroup if @kfd device is accessible */
-static inline int kfd_devcgroup_check_permission(struct kfd_node *kfd)
+static inline int kfd_devcgroup_check_permission(struct kfd_node *node)
 {
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
-	struct drm_device *ddev = adev_to_drm(kfd->adev);
+	struct drm_device *ddev;
+
+	if (node->xcp)
+		ddev = node->xcp->ddev;
+	else
+		ddev = adev_to_drm(node->adev);
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, DRM_MAJOR,
 					  ddev->render->index,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 43eff221eae5..4858112f9a53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -95,6 +95,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 			void *gws)
 {
+	struct mqd_update_info minfo = {0};
 	struct kfd_node *dev = NULL;
 	struct process_queue_node *pqn;
 	struct kfd_process_device *pdd;
@@ -146,9 +147,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 	}
 
 	pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
+	minfo.update_flag = gws ? UPDATE_FLAG_IS_GWS : 0;
 
 	return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
-							pqn->q, NULL);
+							pqn->q, &minfo);
 }
 
 void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e5f7c92eebcb..6ed2ec381aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1638,12 +1638,10 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
 		else
 			mode = UNKNOWN_MEMORY_PARTITION_MODE;
 
-		if (pcache->cache_level == 2)
-			pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc;
-		else if (mode)
-			pcache->cache_size = pcache_info[cache_type].cache_size / mode;
-		else
-			pcache->cache_size = pcache_info[cache_type].cache_size;
+		pcache->cache_size = pcache_info[cache_type].cache_size;
+		/* Partition mode only affects L3 cache size */
+		if (mode && pcache->cache_level == 3)
+			pcache->cache_size /= mode;
 
 		if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE)
 			pcache->cache_type |= HSA_CACHE_TYPE_DATA;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6cda5b536362..1a9bbb04bd5e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1843,21 +1843,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			DRM_ERROR("amdgpu: fail to register dmub aux callback");
 			goto error;
 		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true)) {
-			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
-			goto error;
-		}
-	}
-
-	/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
-	 * It is expected that DMUB will resend any pending notifications at this point, for
-	 * example HPD from DPIA.
-	 */
-	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		/* Enable outbox notification only after IRQ handlers are registered and DMUB is alive.
+		 * It is expected that DMUB will resend any pending notifications at this point. Note
+		 * that hpd and hpd_irq handler registration are deferred to register_hpd_handlers() to
+		 * align legacy interface initialization sequence. Connection status will be proactivly
+		 * detected once in the amdgpu_dm_initialize_drm_device.
+		 */
 		dc_enable_dmub_outbox(adev->dm.dc);
 
 		/* DPIA trace goes to dmesg logs only if outbox is enabled */
@@ -1956,7 +1947,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 				      &adev->dm.dmub_bo_gpu_addr,
 				      &adev->dm.dmub_bo_cpu_addr);
 
-	if (adev->dm.hpd_rx_offload_wq) {
+	if (adev->dm.hpd_rx_offload_wq && adev->dm.dc) {
 		for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
 			if (adev->dm.hpd_rx_offload_wq[i].wq) {
 				destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
@@ -2287,6 +2278,7 @@ static int dm_sw_fini(void *handle)
 
 	if (adev->dm.dmub_srv) {
 		dmub_srv_destroy(adev->dm.dmub_srv);
+		kfree(adev->dm.dmub_srv);
 		adev->dm.dmub_srv = NULL;
 	}
 
@@ -3536,6 +3528,14 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 	int_params.requested_polarity = INTERRUPT_POLARITY_DEFAULT;
 	int_params.current_polarity = INTERRUPT_POLARITY_DEFAULT;
 
+	if (dc_is_dmub_outbox_supported(adev->dm.dc)) {
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+
+		if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_IRQ, dmub_hpd_callback, true))
+			DRM_ERROR("amdgpu: fail to register dmub hpd callback");
+	}
+
 	list_for_each_entry(connector,
 			&dev->mode_config.connector_list, head)	{
 
@@ -3564,10 +3564,6 @@ static void register_hpd_handlers(struct amdgpu_device *adev)
 					handle_hpd_rx_irq,
 					(void *) aconnector);
 		}
-
-		if (adev->dm.hpd_rx_offload_wq)
-			adev->dm.hpd_rx_offload_wq[connector->index].aconnector =
-				aconnector;
 	}
 }
 
@@ -4561,6 +4557,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 
+		if (dm->hpd_rx_offload_wq)
+			dm->hpd_rx_offload_wq[aconnector->base.index].aconnector =
+				aconnector;
+
 		if (!dc_link_detect_connection_type(link, &new_connection_type))
 			DRM_ERROR("KMS: Failed to detect connector\n");
 
@@ -5219,6 +5219,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 				struct drm_plane_state *new_plane_state,
 				struct drm_crtc_state *crtc_state,
 				struct dc_flip_addrs *flip_addrs,
+				bool is_psr_su,
 				bool *dirty_regions_changed)
 {
 	struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
@@ -5243,6 +5244,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 	num_clips = drm_plane_get_damage_clips_count(new_plane_state);
 	clips = drm_plane_get_damage_clips(new_plane_state);
 
+	if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 &&
+						   is_psr_su)))
+		goto ffu;
+
 	if (!dm_crtc_state->mpo_requested) {
 		if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS)
 			goto ffu;
@@ -6194,7 +6199,9 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
+			saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
 			drm_mode_copy(&mode, freesync_mode);
+			mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 					&mode, preferred_mode, scale);
@@ -6527,10 +6534,15 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector)
 static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6538,7 +6550,7 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -6579,12 +6591,18 @@ static int get_modes(struct drm_connector *connector)
 static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 {
 	struct drm_connector *connector = &aconnector->base;
-	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(&aconnector->base);
+	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
 	struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
 	/*
 	 * Note: drm_get_edid gets edid in the following order:
@@ -6592,7 +6610,7 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 	 * 2) firmware EDID if set via edid_firmware module parameter
 	 * 3) regular DDC read.
 	 */
-	edid = drm_get_edid(connector, &amdgpu_connector->ddc_bus->aux.ddc);
+	edid = drm_get_edid(connector, ddc);
 	if (!edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
 		return;
@@ -8298,6 +8316,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			fill_dc_dirty_rects(plane, old_plane_state,
 					    new_plane_state, new_crtc_state,
 					    &bundle->flip_addrs[planes_count],
+					    acrtc_state->stream->link->psr_settings.psr_version ==
+					    DC_PSR_VERSION_SU_1,
 					    &dirty_rects_changed);
 
 			/*
@@ -9187,6 +9207,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		dummy_updates = kzalloc(sizeof(struct dc_surface_update) * MAX_SURFACES, GFP_ATOMIC);
+		if (!dummy_updates) {
+			DRM_ERROR("Failed to allocate memory for dummy_updates.\n");
+			continue;
+		}
 		for (j = 0; j < status->plane_count; j++)
 			dummy_updates[j].surface = status->plane_states[0];
 
@@ -10727,11 +10751,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}
 
-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}
 
 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
@@ -11143,14 +11169,23 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 				if (range->flags != 1)
 					continue;
 
-				amdgpu_dm_connector->min_vfreq = range->min_vfreq;
-				amdgpu_dm_connector->max_vfreq = range->max_vfreq;
-				amdgpu_dm_connector->pixel_clock_mhz =
-					range->pixel_clock_mhz * 10;
-
 				connector->display_info.monitor_range.min_vfreq = range->min_vfreq;
 				connector->display_info.monitor_range.max_vfreq = range->max_vfreq;
 
+				if (edid->revision >= 4) {
+					if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ)
+						connector->display_info.monitor_range.min_vfreq += 255;
+					if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ)
+						connector->display_info.monitor_range.max_vfreq += 255;
+				}
+
+				amdgpu_dm_connector->min_vfreq =
+					connector->display_info.monitor_range.min_vfreq;
+				amdgpu_dm_connector->max_vfreq =
+					connector->display_info.monitor_range.max_vfreq;
+				amdgpu_dm_connector->pixel_clock_mhz =
+					range->pixel_clock_mhz * 10;
+
 				break;
 			}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 85b7f58a7f35..c27063305a13 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -67,6 +67,8 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
 	/* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */
 	case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB):
 	case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B):
+	case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A):
+	case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1):
 		DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id);
 		edid_caps->panel_patch.remove_sink_ext_caps = true;
 		break;
@@ -120,6 +122,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 
 	edid_caps->edid_hdmi = connector->display_info.is_hdmi;
 
+	apply_edid_quirks(edid_buf, edid_caps);
+
 	sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
 	if (sad_count <= 0)
 		return result;
@@ -146,8 +150,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	else
 		edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION;
 
-	apply_edid_quirks(edid_buf, edid_caps);
-
 	kfree(sads);
 	kfree(sadb);
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index f2dfa96f9ef5..39530b2ea495 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -94,7 +94,7 @@ static void calculate_bandwidth(
 	const uint32_t s_high = 7;
 	const uint32_t dmif_chunk_buff_margin = 1;
 
-	uint32_t max_chunks_fbc_mode;
+	uint32_t max_chunks_fbc_mode = 0;
 	int32_t num_cursor_lines;
 
 	int32_t i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 960c4b4f6ddf..05f392501c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1850,19 +1850,21 @@ static enum bp_result get_firmware_info_v3_2(
 		/* Vega12 */
 		smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
 		if (!smu_info_v3_2)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
 	} else if (revision.minor == 3) {
 		/* Vega20 */
 		smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
 							DATA_TABLES(smu_info));
-		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
 		if (!smu_info_v3_3)
 			return BP_RESULT_BADBIOSTABLE;
 
+		DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
+
 		info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
 	}
 
@@ -2422,10 +2424,11 @@ static enum bp_result get_integrated_info_v11(
 	info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
 	if (info_v11 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v11->gpucapinfo);
 	/*
@@ -2637,11 +2640,12 @@ static enum bp_result get_integrated_info_v2_1(
 
 	info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1,
 					DATA_TABLES(integratedsysteminfo));
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
 
 	if (info_v2_1 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_1->gpucapinfo);
 	/*
@@ -2799,11 +2803,11 @@ static enum bp_result get_integrated_info_v2_2(
 	info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2,
 					DATA_TABLES(integratedsysteminfo));
 
-	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
-
 	if (info_v2_2 == NULL)
 		return BP_RESULT_BADBIOSTABLE;
 
+	DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
+
 	info->gpu_cap_info =
 	le32_to_cpu(info_v2_2->gpucapinfo);
 	/*
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index a5489fe6875f..aa9fd1dc550a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -546,6 +546,8 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta
 	int i;
 
 	for (i = 0; i < VG_NUM_SOC_VOLTAGE_LEVELS; i++) {
+		if (i >= VG_NUM_DCFCLK_DPM_LEVELS)
+			break;
 		if (clock_table->SocVoltage[i] == voltage)
 			return clock_table->DcfClocks[i];
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 9c660d1facc7..e64890259235 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -437,32 +437,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -474,32 +474,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 14.0,
-			.sr_enter_plus_exit_time_us = 16.0,
+			.sr_exit_time_us = 28.0,
+			.sr_enter_plus_exit_time_us = 30.0,
 			.valid = true,
 		},
 	}
@@ -655,10 +655,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
 	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
 	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
+	uint32_t num_memps, num_fclk, num_dcfclk;
 	int i;
 
 	/* Determine min/max p-state values. */
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	num_memps = (clock_table->NumMemPstatesEnabled > NUM_MEM_PSTATE_LEVELS) ? NUM_MEM_PSTATE_LEVELS :
+		clock_table->NumMemPstatesEnabled;
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
@@ -670,7 +673,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	min_dram_speed_mts = max_dram_speed_mts;
 	min_pstate = max_pstate;
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+	for (i = 0; i < num_memps; i++) {
 		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
 
 		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
@@ -699,9 +702,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
 	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+	num_fclk = (clock_table->NumFclkLevelsEnabled > NUM_FCLK_DPM_LEVELS) ? NUM_FCLK_DPM_LEVELS :
+		clock_table->NumFclkLevelsEnabled;
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
 
-	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+	num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+		clock_table->NumDcfClkLevelsEnabled;
+	for (i = 0; i < num_dcfclk; i++) {
 		int j;
 
 		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e..2c424e435962 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * programming has completed (we turn on phantom OTG in order
 		 * to complete the plane disable for phantom pipes).
 		 */
-		dc->hwss.apply_ctx_to_hw(dc, context);
+
+		if (dc->hwss.disable_phantom_streams)
+			dc->hwss.disable_phantom_streams(dc, context);
 	}
 
 	if (update_type != UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 88c6436b28b6..180ac47868c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
 		dc_stream_release(state->phantom_streams[i]);
 		state->phantom_streams[i] = NULL;
 	}
+	state->phantom_stream_count = 0;
 
 	for (i = 0; i < state->phantom_plane_count; i++) {
 		dc_plane_state_release(state->phantom_planes[i]);
 		state->phantom_planes[i] = NULL;
 	}
+	state->phantom_plane_count = 0;
+
 	state->stream_mask = 0;
 	memset(&state->res_ctx, 0, sizeof(state->res_ctx));
 	memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 2b79a0e5638e..363d522603a2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -125,7 +125,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 		unsigned int count,
 		union dmub_rb_cmd *cmd_list)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	struct dmub_srv *dmub;
 	enum dmub_status status;
 	int i;
@@ -133,6 +133,7 @@ bool dc_dmub_srv_cmd_list_queue_execute(struct dc_dmub_srv *dc_dmub_srv,
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
 		return false;
 
+	dc_ctx = dc_dmub_srv->ctx;
 	dmub = dc_dmub_srv->dmub;
 
 	for (i = 0 ; i < count; i++) {
@@ -1161,7 +1162,7 @@ void dc_dmub_srv_subvp_save_surf_addr(const struct dc_dmub_srv *dc_dmub_srv, con
 
 bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 {
-	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	struct dc_context *dc_ctx;
 	enum dmub_status status;
 
 	if (!dc_dmub_srv || !dc_dmub_srv->dmub)
@@ -1170,6 +1171,8 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait)
 	if (dc_dmub_srv->ctx->dc->debug.dmcub_emulation)
 		return true;
 
+	dc_ctx = dc_dmub_srv->ctx;
+
 	if (wait) {
 		if (dc_dmub_srv->ctx->dc->debug.disable_timeout) {
 			do {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
index e8570060d007..5bca67407c5b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c
@@ -290,4 +290,5 @@ void dce_panel_cntl_construct(
 	dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs;
 	dce_panel_cntl->base.ctx = init_data->ctx;
 	dce_panel_cntl->base.inst = init_data->inst;
+	dce_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00..5f97a868ada3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
@@ -56,16 +56,13 @@ static void dpp3_enable_cm_block(
 
 static enum dc_lut_mode dpp30_get_gamcor_current(struct dpp *dpp_base)
 {
-	enum dc_lut_mode mode;
+	enum dc_lut_mode mode = LUT_BYPASS;
 	uint32_t state_mode;
 	uint32_t lut_mode;
 	struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base);
 
 	REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &state_mode);
 
-	if (state_mode == 0)
-		mode = LUT_BYPASS;
-
 	if (state_mode == 2) {//Programmable RAM LUT
 		REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_SELECT_CURRENT, &lut_mode);
 		if (lut_mode == 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
index ad0df1a72a90..9e96a3ace207 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c
@@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct(
 	dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs;
 	dcn301_panel_cntl->base.ctx = init_data->ctx;
 	dcn301_panel_cntl->base.inst = init_data->inst;
+	dcn301_panel_cntl->base.pwrseq_inst = 0;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
index 03248422d6ff..281be20b1a10 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
@@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct(
 	struct dcn31_panel_cntl *dcn31_panel_cntl,
 	const struct panel_cntl_init_data *init_data)
 {
+	uint8_t pwrseq_inst = 0xF;
+
 	dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs;
 	dcn31_panel_cntl->base.ctx = init_data->ctx;
 	dcn31_panel_cntl->base.inst = init_data->inst;
-	dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst;
+
+	switch (init_data->eng_id) {
+	case ENGINE_ID_DIGA:
+		pwrseq_inst = 0;
+		break;
+	case ENGINE_ID_DIGB:
+		pwrseq_inst = 1;
+		break;
+	default:
+		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id);
+		ASSERT(false);
+		break;
+	}
+
+	dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
index 501388014855..d761b0df2878 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
@@ -203,12 +203,12 @@ void dcn32_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
 	enc10->base.features = *enc_features;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.transmitter = init_data->transmitter;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
index da94e5309fba..81e349d5835b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
@@ -184,8 +184,6 @@ void dcn35_link_encoder_construct(
 	enc10->base.hpd_source = init_data->hpd_source;
 	enc10->base.connector = init_data->connector;
 
-	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
-		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
 
@@ -240,6 +238,8 @@ void dcn35_link_encoder_construct(
 	}
 
 	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
+	if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+		enc10->base.features.flags.bits.DP_IS_USB_C = 1;
 
 	if (bp_funcs->get_connector_speed_cap_info)
 		result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f..59ade76ffb18 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 9f37f717a1f8..a0a65e099104 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1112,7 +1112,7 @@ struct pipe_slice_table {
 		struct pipe_ctx *pri_pipe;
 		struct dc_plane_state *plane;
 		int slice_count;
-	} mpc_combines[MAX_SURFACES];
+	} mpc_combines[MAX_PLANES];
 	int mpc_combine_count;
 };
 
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
 	return updated;
 }
 
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
 		struct dc_state *context, struct vba_vars_st *v, int *split,
 		bool *merge)
 {
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
 {
 	int i;
 	unsigned int new_vlevel;
+	unsigned int cur_policy[MAX_PIPES];
 
-	for (i = 0; i < pipe_cnt; i++)
+	for (i = 0; i < pipe_cnt; i++) {
+		cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
 		pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+	}
 
 	new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
 
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
 		memset(merge, 0, MAX_PIPES * sizeof(bool));
 		*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
 		context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+	} else {
+		for (i = 0; i < pipe_cnt; i++)
+			pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
 	}
 }
 
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
 		}
 	}
 
-	if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+	if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
 		try_odm_power_optimization_and_revalidate(
 				dc, context, pipes, split, merge, vlevel, *pipe_cnt);
 
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
 		int i;
 
 		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
-		dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+		if (!dc->config.enable_windowed_mpo_odm)
+			dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
 
 		/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
 		 * we have to re-calculate the DET allocation and run through DML once more to
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 475c4ec43c01..7ea2bd5374d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -164,8 +164,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 14.0,
-	.sr_enter_plus_exit_time_us = 16.0,
+	.sr_exit_time_us = 28.0,
+	.sr_enter_plus_exit_time_us = 30.0,
 	.sr_exit_z8_time_us = 210.0,
 	.sr_enter_plus_exit_z8_time_us = 320.0,
 	.fclk_change_latency_us = 24.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 64d01a9cd68c..1ba6933d2b36 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -341,9 +341,6 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	if (dml2->config.bbox_overrides.clks_table.num_states)
-			p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
-
 	/* Override from passed values, if available */
 	for (i = 0; i < p->in_states->num_states; i++) {
 		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
@@ -400,7 +397,7 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 	/* Copy clocks tables entries, if available */
 	if (dml2->config.bbox_overrides.clks_table.num_states) {
-
+		p->in_states->num_states = dml2->config.bbox_overrides.clks_table.num_states;
 		for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels; i++) {
 			p->in_states->state_array[i].dcfclk_mhz = dml2->config.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz;
 		}
@@ -439,6 +436,14 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 	}
 
 	dml2_policy_build_synthetic_soc_states(s, p);
+	if (dml2->v20.dml_core_ctx.project == dml_project_dcn35 ||
+		dml2->v20.dml_core_ctx.project == dml_project_dcn351) {
+		// Override last out_state with data from last in_state
+		// This will ensure that out_state contains max fclk
+		memcpy(&p->out_states->state_array[p->out_states->num_states - 1],
+				&p->in_states->state_array[p->in_states->num_states - 1],
+				sizeof(struct soc_state_bounding_box_st));
+	}
 }
 
 void dml2_translate_ip_params(const struct dc *in, struct ip_params_st *out)
@@ -793,35 +798,28 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 	}
 }
 
-/*TODO no support for mpc combine, need rework - should calculate scaling params based on plane+stream*/
-static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, const struct dc_state *context)
+static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context)
 {
 	int i;
-	struct scaler_data data = { 0 };
+	struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
+
+	memset(temp_pipe, 0, sizeof(struct pipe_ctx));
 
 	for (i = 0; i < MAX_PIPES; i++)	{
 		const struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (pipe->plane_state == in && !pipe->prev_odm_pipe) {
-			const struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
-
-			data = context->res_ctx.pipe_ctx[i].plane_res.scl_data;
-			while (next_pipe) {
-				data.h_active += next_pipe->plane_res.scl_data.h_active;
-				data.recout.width += next_pipe->plane_res.scl_data.recout.width;
-				if (in->rotation == ROTATION_ANGLE_0 || in->rotation == ROTATION_ANGLE_180) {
-					data.viewport.width += next_pipe->plane_res.scl_data.viewport.width;
-				} else {
-					data.viewport.height += next_pipe->plane_res.scl_data.viewport.height;
-				}
-				next_pipe = next_pipe->next_odm_pipe;
-			}
+			temp_pipe->stream = pipe->stream;
+			temp_pipe->plane_state = pipe->plane_state;
+			temp_pipe->plane_res.scl_data.taps = pipe->plane_res.scl_data.taps;
+
+			resource_build_scaling_params(temp_pipe);
 			break;
 		}
 	}
 
 	ASSERT(i < MAX_PIPES);
-	return data;
+	return temp_pipe->plane_res.scl_data;
 }
 
 static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
@@ -866,7 +864,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
 	out->ScalerEnabled[location] = false;
 }
 
-static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, const struct dc_state *context)
+static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, struct dc_state *context)
 {
 	const struct scaler_data scaler_data = get_scaler_data_for_plane(in, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 26307e599614..2a58a7687bdb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -76,6 +76,11 @@ static void map_hw_resources(struct dml2_context *dml2,
 			in_out_display_cfg->hw.DLGRefClkFreqMHz = 50;
 		}
 		for (j = 0; j < mode_support_info->DPPPerSurface[i]; j++) {
+			if (i >= __DML2_WRAPPER_MAX_STREAMS_PLANES__) {
+				dml_print("DML::%s: Index out of bounds: i=%d, __DML2_WRAPPER_MAX_STREAMS_PLANES__=%d\n",
+					  __func__, i, __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				break;
+			}
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_stream_id[i];
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id_valid[num_pipes] = true;
 			dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[i];
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 5660f15da291..01493c49bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1183,9 +1183,9 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx)
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
 		if (dccg) {
-			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 			dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst);
 			dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst);
+			dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
 		}
 	} else if (dccg && dccg->funcs->disable_symclk_se) {
 		dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst,
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
 	return DC_OK;
 }
 
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
 			continue;
 
-		status = apply_single_controller_ctx_to_hw(
+		status = dce110_apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
 				dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae..ed3cc3648e8e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context);
 
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
 
 void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index e931342fcf4c..931ac8ed7069 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
@@ -2790,18 +2790,17 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 
 	if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
-		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
-
-		phyd32clk = get_phyd32clk_src(link);
-		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
-
 		dto_params.otg_inst = tg->inst;
 		dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10;
 		dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx);
 		dto_params.timing = &pipe_ctx->stream->timing;
 		dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr);
 		dccg->funcs->set_dtbclk_dto(dccg, &dto_params);
+		dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
+		dccg->funcs->set_dpstreamclk(dccg, DTBCLK0, tg->inst, dp_hpo_inst);
+
+		phyd32clk = get_phyd32clk_src(link);
+		dccg->funcs->enable_symclk32_se(dccg, dp_hpo_inst, phyd32clk);
 	} else {
 		if (dccg->funcs->enable_symclk_se)
 			dccg->funcs->enable_symclk_se(dccg, stream_enc->stream_enc_inst,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abf..d950b3e54ec2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
 void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
 void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
 void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5..7252f5f781f0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
 void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
 {
 	struct abm *abm = pipe_ctx->stream_res.abm;
-	uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
 	struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return;
+
+	otg_inst = tg->inst;
 
 	if (dmcu) {
 		dce110_set_pipe(pipe_ctx);
 		return;
 	}
 
-	if (abm && panel_cntl) {
-		if (abm->funcs && abm->funcs->set_pipe_ex) {
-			abm->funcs->set_pipe_ex(abm,
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
 					otg_inst,
 					SET_ABM_PIPE_NORMAL,
 					panel_cntl->inst,
 					panel_cntl->pwrseq_inst);
-		} else {
-				dmub_abm_set_pipe(abm, otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-		}
+	} else {
+		dmub_abm_set_pipe(abm, otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 }
 
@@ -237,34 +241,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
 {
 	struct dc_context *dc = pipe_ctx->stream->ctx;
 	struct abm *abm = pipe_ctx->stream_res.abm;
+	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 	struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+	uint32_t otg_inst;
+
+	if (!abm || !tg || !panel_cntl)
+		return false;
+
+	otg_inst = tg->inst;
 
 	if (dc->dc->res_pool->dmcu) {
 		dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
 		return true;
 	}
 
-	if (abm != NULL) {
-		uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
-		if (abm && panel_cntl) {
-			if (abm->funcs && abm->funcs->set_pipe_ex) {
-				abm->funcs->set_pipe_ex(abm,
-						otg_inst,
-						SET_ABM_PIPE_NORMAL,
-						panel_cntl->inst,
-						panel_cntl->pwrseq_inst);
-			} else {
-					dmub_abm_set_pipe(abm,
-							otg_inst,
-							SET_ABM_PIPE_NORMAL,
-							panel_cntl->inst,
-							panel_cntl->pwrseq_inst);
-			}
-		}
+	if (abm->funcs && abm->funcs->set_pipe_ex) {
+		abm->funcs->set_pipe_ex(abm,
+					otg_inst,
+					SET_ABM_PIPE_NORMAL,
+					panel_cntl->inst,
+					panel_cntl->pwrseq_inst);
+	} else {
+		dmub_abm_set_pipe(abm,
+				  otg_inst,
+				  SET_ABM_PIPE_NORMAL,
+				  panel_cntl->inst,
+				  panel_cntl->pwrseq_inst);
 	}
 
-	if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+	if (abm->funcs && abm->funcs->set_backlight_level_pwm)
 		abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
 			frame_ramp, 0, panel_cntl->inst);
 	else
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683d..aa36d7a56ca8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
 	}
 }
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	int i;
+
+	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+		struct pipe_ctx *pipe_ctx_old =
+			&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx_old->stream)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+			continue;
+
+		if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+				(pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+			struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+			if (hws->funcs.reset_back_end_for_pipe)
+				hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+			if (old_clk)
+				old_clk->funcs->cs_power_down(old_clk);
+		}
+	}
+}
+
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 {
 	unsigned int i;
+	enum dc_status status = DC_OK;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
 		}
 	}
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-
-		if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
-			// If old context or new context has phantom pipes, apply
-			// the phantom timings now. We can't change the phantom
-			// pipe configuration safely without driver acquiring
-			// the DMCUB lock first.
-			dc->hwss.apply_ctx_to_hw(dc, context);
-			break;
+		struct pipe_ctx *pipe_ctx_old =
+					&dc->current_state->res_ctx.pipe_ctx[i];
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+			continue;
+
+		if (pipe_ctx->stream == pipe_ctx_old->stream &&
+			pipe_ctx->stream->link->link_state_valid) {
+			continue;
 		}
+
+		if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+			continue;
+
+		if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+			continue;
+
+		if (hws->funcs.apply_single_controller_ctx_to_hw)
+			status = hws->funcs.apply_single_controller_ctx_to_hw(
+					pipe_ctx,
+					context,
+					dc);
+
+		ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+		if (hws->funcs.resync_fifo_dccg_dio)
+			hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f5671..069e20bc87c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
 
 void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
 
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
 void dcn32_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4..e8ac94a005b8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.get_dcc_en_bits = dcn10_get_dcc_en_bits,
 	.commit_subvp_config = dcn32_commit_subvp_config,
 	.enable_phantom_streams = dcn32_enable_phantom_streams,
+	.disable_phantom_streams = dcn32_disable_phantom_streams,
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
 	.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+	.reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
 };
 
 void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a54399383318..64ca7c66509b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
 			struct dc_cursor_attributes *cursor_attr);
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+	void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
 			bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54..b3c62a82cb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
 	void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
 			struct dc_state *context);
+	enum dc_status (*apply_single_controller_ctx_to_hw)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
 	bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
 #endif
+	void (*reset_back_end_for_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
 };
 
 struct dce_hwseq {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f74ae0d41d3c..3a6bf77a6873 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -469,6 +469,8 @@ struct resource_context {
 	unsigned int hpo_dp_link_enc_to_link_idx[MAX_HPO_DP2_LINK_ENCODERS];
 	int hpo_dp_link_enc_ref_cnts[MAX_HPO_DP2_LINK_ENCODERS];
 	bool is_mpc_3dlut_acquired[MAX_PIPES];
+	/* solely used for build scalar data in dml2 */
+	struct pipe_ctx temp_pipe;
 };
 
 struct dce_bw_output {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
index 5dcbaa2db964..e97d964a1791 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h
@@ -57,7 +57,7 @@ struct panel_cntl_funcs {
 struct panel_cntl_init_data {
 	struct dc_context *ctx;
 	uint32_t inst;
-	uint32_t pwrseq_inst;
+	uint32_t eng_id;
 };
 
 struct panel_cntl {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a..77a60aa9f27b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
 int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
 
 /*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
  */
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
 
 /*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
  */
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
 
 /* Get the ODM slice index counting from 0 from left most slice */
 int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index 37d3027c32dc..cf22b8f28ba6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter(
 	}
 }
 
-static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link)
-{
-	uint8_t pwrseq_inst = 0xF;
-	struct dc_context *dc_ctx = link->dc->ctx;
-
-	DC_LOGGER_INIT(dc_ctx->logger);
-
-	switch (link->eng_id) {
-	case ENGINE_ID_DIGA:
-		pwrseq_inst = 0;
-		break;
-	case ENGINE_ID_DIGB:
-		pwrseq_inst = 1;
-		break;
-	default:
-		DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id);
-		ASSERT(false);
-		break;
-	}
-
-	return pwrseq_inst;
-}
-
-
 static void link_destruct(struct dc_link *link)
 {
 	int i;
@@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link,
 			link->link_id.id == CONNECTOR_ID_LVDS)) {
 		panel_cntl_init_data.ctx = dc_ctx;
 		panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count;
-		panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link);
+		panel_cntl_init_data.eng_id = link->eng_id;
 		link->panel_cntl =
 			link->dc->res_pool->funcs->panel_cntl_create(
 								&panel_cntl_init_data);
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index 8fe66c367850..5b0bc7f6a188 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -361,7 +361,7 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un
 	struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
 	int num_dpias = 0;
 
-	for (uint8_t i = 0; i < num_streams; ++i) {
+	for (unsigned int i = 0; i < num_streams; ++i) {
 		if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
 			/* new dpia sst stream, check whether it exceeds max dpia */
 			if (num_dpias >= MAX_DPIA_NUM)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index dd0d2b206462..5491b707cec8 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -196,7 +196,7 @@ static int get_host_router_total_dp_tunnel_bw(const struct dc *dc, uint8_t hr_in
 	struct dc_link *link_dpia_primary, *link_dpia_secondary;
 	int total_bw = 0;
 
-	for (uint8_t i = 0; i < MAX_PIPES * 2; ++i) {
+	for (uint8_t i = 0; i < (MAX_PIPES * 2) - 1; ++i) {
 
 		if (!dc->links[i] || dc->links[i]->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
 			continue;
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 5a0b04518956..16a62e018712 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status(
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
 	union lane_status lane_status;
+	union lane_align_status_updated dpcd_lane_status_updated;
 	uint8_t dpcd_buf[6] = {0};
 	uint32_t lane;
 
@@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status(
 		 * check lanes status
 		 */
 		lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane);
+		dpcd_lane_status_updated.raw = dpcd_buf[4];
 
 		if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
 			!lane_status.bits.CR_DONE_0 ||
-			!lane_status.bits.SYMBOL_LOCKED_0) {
+			!lane_status.bits.SYMBOL_LOCKED_0 ||
+			!dp_is_interlane_aligned(dpcd_lane_status_updated)) {
 			/* if one of the channel equalization, clock
 			 * recovery or symbol lock is dropped
 			 * consider it as (link has been
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
index e8dda44b23cb..5d36bab0029c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
@@ -619,7 +619,7 @@ static enum link_training_result dpia_training_eq_non_transparent(
 	uint32_t retries_eq = 0;
 	enum dc_status status;
 	enum dc_dp_training_pattern tr_pattern;
-	uint32_t wait_time_microsec;
+	uint32_t wait_time_microsec = 0;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = {0};
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0};
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b985..7538b548c572 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
 	vpg = dcn301_vpg_create(ctx, vpg_inst);
 	afmt = dcn301_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt) {
+	if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
 		kfree(enc1);
 		kfree(vpg);
 		kfree(afmt);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c4d71e7f18af..6f10052caeef 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
 		dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
 		DC_FP_END();
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
-		pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		if (dc->config.enable_windowed_mpo_odm &&
+				dc->debug.enable_single_display_2to1_odm_policy) {
+			switch (resource_get_odm_slice_count(pipe)) {
+			case 2:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+				break;
+			case 4:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+				break;
+			default:
+				pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+			}
+		} else {
+			pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+		}
 		pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 		pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec9891875..5fdcda8f8602 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.ignore_pg = true,
 	.psp_disabled_wa = true,
-	.ips2_eval_delay_us = 200,
-	.ips2_entry_delay_us = 400,
+	.ips2_eval_delay_us = 2000,
+	.ips2_entry_delay_us = 800,
 	.static_screen_wait_frames = 2,
 };
 
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
 	dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
 	dc->dml2_options.use_native_pstate_optimization = true;
 	dc->dml2_options.use_native_soc_bb_construction = true;
+	dc->dml2_options.minimize_dispclk_using_odm = false;
 	if (dc->config.EnableMinDispClkODM)
 		dc->dml2_options.minimize_dispclk_using_odm = true;
 	dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 087d57850304..39c5e1dfa275 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2558,6 +2558,7 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	int err, ret;
+	u32 pwm_mode;
 	int value;
 
 	if (amdgpu_in_reset(adev))
@@ -2569,13 +2570,22 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 	if (err)
 		return err;
 
+	if (value == 0)
+		pwm_mode = AMD_FAN_CTRL_NONE;
+	else if (value == 1)
+		pwm_mode = AMD_FAN_CTRL_MANUAL;
+	else if (value == 2)
+		pwm_mode = AMD_FAN_CTRL_AUTO;
+	else
+		return -EINVAL;
+
 	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (ret < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return ret;
 	}
 
-	ret = amdgpu_dpm_set_fan_control_mode(adev, value);
+	ret = amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
 
 	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index df4f20293c16..eb4da3666e05 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int si_set_temperature_range(struct amdgpu_device *adev)
+{
+	int ret;
+
+	ret = si_thermal_enable_alert(adev, false);
+	if (ret)
+		return ret;
+	ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+	if (ret)
+		return ret;
+	ret = si_thermal_enable_alert(adev, true);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static void si_dpm_disable(struct amdgpu_device *adev)
 {
 	struct rv7xx_power_info *pi = rv770_get_pi(adev);
@@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev,
 
 static int si_dpm_late_init(void *handle)
 {
+	int ret;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!adev->pm.dpm_enabled)
+		return 0;
+
+	ret = si_set_temperature_range(adev);
+	if (ret)
+		return ret;
+#if 0 //TODO ?
+	si_dpm_powergate_uvd(adev, true);
+#endif
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 7ffad3eb0a01..0ad947df777a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -734,7 +734,7 @@ static int smu_early_init(void *handle)
 	smu->adev = adev;
 	smu->pm_enabled = !!amdgpu_dpm;
 	smu->is_apu = false;
-	smu->smu_baco.state = SMU_BACO_STATE_NONE;
+	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 	smu->user_dpm_profile.fan_mode = -1;
 
@@ -1954,31 +1954,10 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_reset_mp1_state(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0;
-
-	if ((!adev->in_runpm) && (!adev->in_suspend) &&
-		(!amdgpu_in_reset(adev)))
-		switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
-		case IP_VERSION(13, 0, 0):
-		case IP_VERSION(13, 0, 7):
-		case IP_VERSION(13, 0, 10):
-			ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
-			break;
-		default:
-			break;
-		}
-
-	return ret;
-}
-
 static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = adev->powerplay.pp_handle;
-	int ret;
 
 	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
@@ -1996,15 +1975,7 @@ static int smu_hw_fini(void *handle)
 
 	adev->pm.dpm_enabled = false;
 
-	ret = smu_smc_hw_cleanup(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_reset_mp1_state(smu);
-	if (ret)
-		return ret;
-
-	return 0;
+	return smu_smc_hw_cleanup(smu);
 }
 
 static void smu_late_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 2aa4fea87314..66e84defd0b6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,7 +424,6 @@ enum smu_reset_mode {
 enum smu_baco_state {
 	SMU_BACO_STATE_ENTER = 0,
 	SMU_BACO_STATE_EXIT,
-	SMU_BACO_STATE_NONE,
 };
 
 struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 4cd43bbec910..bcad42534da4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1303,13 +1303,12 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 							od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 8d1d29ffb0f1..ed189a3878eb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2357,13 +2357,12 @@ static int navi10_get_power_limit(struct smu_context *smu,
 		*default_power_limit = power_limit;
 
 	if (smu->od_enabled &&
-		    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) {
+		    navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT))
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 21fc033528fa..e2ad2b972ab0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -640,13 +640,12 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 2ff6deedef95..da1f43999d09 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -451,7 +451,7 @@ static int vangogh_init_smc_tables(struct smu_context *smu)
 
 #ifdef CONFIG_X86
 	/* AMD x86 APU only */
-	smu->cpu_core_num = boot_cpu_data.x86_max_cores;
+	smu->cpu_core_num = topology_num_cores_per_package();
 #else
 	smu->cpu_core_num = 4;
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 4fdf34fffa9a..9b80f18ea6c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2369,13 +2369,12 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
@@ -2748,13 +2747,7 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
@@ -2950,7 +2943,7 @@ static bool smu_v13_0_0_wbrf_support_check(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 
-	switch (adev->ip_versions[MP1_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
 	case IP_VERSION(13, 0, 0):
 		return smu->smc_fw_version >= 0x004e6300;
 	case IP_VERSION(13, 0, 10):
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 7c3e162e2d81..3dc7b60cb075 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2333,13 +2333,12 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (smu->od_enabled) {
+	if (smu->od_enabled)
 		od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
-		od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
-	} else {
+	else
 		od_percent_upper = 0;
-		od_percent_lower = 100;
-	}
+
+	od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]);
 
 	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
 					od_percent_upper, od_percent_lower, power_limit);
@@ -2505,13 +2504,7 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu,
 
 	switch (mp1_state) {
 	case PP_MP1_STATE_UNLOAD:
-		ret = smu_cmn_send_smc_msg_with_param(smu,
-											  SMU_MSG_PrepareMp1ForUnload,
-											  0x55, NULL);
-
-		if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
-			ret = smu_v13_0_disable_pmfw_state(smu);
-
+		ret = smu_cmn_set_mp1_state(smu, mp1_state);
 		break;
 	default:
 		/* Ignore others */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 4894f7ee737b..6dae5ad74ff0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -229,8 +229,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_2;
 		break;
 	case IP_VERSION(14, 0, 0):
-		if ((smu->smc_fw_version < 0x5d3a00))
-			dev_warn(smu->adev->dev, "The PMFW version(%x) is behind in this BIOS!\n", smu->smc_fw_version);
 		smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 47fdbae4adfc..9310c4758e38 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -261,7 +261,10 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->MpipuclkFrequency;
 		break;
 	case METRICS_AVERAGE_GFXACTIVITY:
-		*value = metrics->GfxActivity / 100;
+		if ((smu->smc_fw_version > 0x5d4600))
+			*value = metrics->GfxActivity;
+		else
+			*value = metrics->GfxActivity / 100;
 		break;
 	case METRICS_AVERAGE_VCNACTIVITY:
 		*value = metrics->VcnActivity / 100;
diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
index bb55f697a181..6886db2d9e00 100644
--- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
@@ -25,20 +25,18 @@ static void drm_aux_hpd_bridge_release(struct device *dev)
 	ida_free(&drm_aux_hpd_bridge_ida, adev->id);
 
 	of_node_put(adev->dev.platform_data);
+	of_node_put(adev->dev.of_node);
 
 	kfree(adev);
 }
 
-static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
+static void drm_aux_hpd_bridge_free_adev(void *_adev)
 {
-	struct auxiliary_device *adev = _adev;
-
-	auxiliary_device_delete(adev);
-	auxiliary_device_uninit(adev);
+	auxiliary_device_uninit(_adev);
 }
 
 /**
- * drm_dp_hpd_bridge_register - Create a simple HPD DisplayPort bridge
+ * devm_drm_dp_hpd_bridge_alloc - allocate a HPD DisplayPort bridge
  * @parent: device instance providing this bridge
  * @np: device node pointer corresponding to this bridge instance
  *
@@ -46,11 +44,9 @@ static void drm_aux_hpd_bridge_unregister_adev(void *_adev)
  * DRM_MODE_CONNECTOR_DisplayPort, which terminates the bridge chain and is
  * able to send the HPD events.
  *
- * Return: device instance that will handle created bridge or an error code
- * encoded into the pointer.
+ * Return: bridge auxiliary device pointer or an error pointer
  */
-struct device *drm_dp_hpd_bridge_register(struct device *parent,
-					  struct device_node *np)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np)
 {
 	struct auxiliary_device *adev;
 	int ret;
@@ -74,18 +70,62 @@ struct device *drm_dp_hpd_bridge_register(struct device *parent,
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
+		of_node_put(adev->dev.platform_data);
+		of_node_put(adev->dev.of_node);
 		ida_free(&drm_aux_hpd_bridge_ida, adev->id);
 		kfree(adev);
 		return ERR_PTR(ret);
 	}
 
-	ret = auxiliary_device_add(adev);
-	if (ret) {
-		auxiliary_device_uninit(adev);
+	ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_free_adev, adev);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
-	ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_unregister_adev, adev);
+	return adev;
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_alloc);
+
+static void drm_aux_hpd_bridge_del_adev(void *_adev)
+{
+	auxiliary_device_delete(_adev);
+}
+
+/**
+ * devm_drm_dp_hpd_bridge_add - register a HDP DisplayPort bridge
+ * @dev: struct device to tie registration lifetime to
+ * @adev: bridge auxiliary device to be registered
+ *
+ * Returns: zero on success or a negative errno
+ */
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev)
+{
+	int ret;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, drm_aux_hpd_bridge_del_adev, adev);
+}
+EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_add);
+
+/**
+ * drm_dp_hpd_bridge_register - allocate and register a HDP DisplayPort bridge
+ * @parent: device instance providing this bridge
+ * @np: device node pointer corresponding to this bridge instance
+ *
+ * Return: device instance that will handle created bridge or an error pointer
+ */
+struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np)
+{
+	struct auxiliary_device *adev;
+	int ret;
+
+	adev = devm_drm_dp_hpd_bridge_alloc(parent, np);
+	if (IS_ERR(adev))
+		return ERR_CAST(adev);
+
+	ret = devm_drm_dp_hpd_bridge_add(parent, adev);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index f57e6d74fb0e..5ebdd6f8f36e 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm,
 		 u64 start, u64 end,
 		 unsigned int order)
 {
+	u64 req_size = mm->chunk_size << order;
 	struct drm_buddy_block *block;
 	struct drm_buddy_block *buddy;
 	LIST_HEAD(dfs);
@@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm,
 		if (drm_buddy_block_is_allocated(block))
 			continue;
 
+		if (block_start < start || block_end > end) {
+			u64 adjusted_start = max(block_start, start);
+			u64 adjusted_end = min(block_end, end);
+
+			if (round_down(adjusted_end + 1, req_size) <=
+			    round_up(adjusted_start, req_size))
+				continue;
+		}
+
 		if (contains(start, end, block_start, block_end) &&
 		    order == drm_buddy_block_order(block)) {
 			/*
@@ -538,7 +548,13 @@ static int __alloc_range(struct drm_buddy *mm,
 		list_add(&block->left->tmp_link, dfs);
 	} while (1);
 
+	if (total_allocated < size) {
+		err = -ENOSPC;
+		goto err_free;
+	}
+
 	list_splice_tail(&allocated, blocks);
+
 	return 0;
 
 err_undo:
@@ -755,8 +771,12 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
 		return -EINVAL;
 
 	/* Actual range allocation */
-	if (start + size == end)
+	if (start + size == end) {
+		if (!IS_ALIGNED(start | end, min_block_size))
+			return -EINVAL;
+
 		return __drm_buddy_alloc_range(mm, start, size, NULL, blocks);
+	}
 
 	original_size = size;
 	original_min_size = min_block_size;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cb90e70d85e8..65f9f66933bb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -904,6 +904,7 @@ out:
 	connector_set = NULL;
 	fb = NULL;
 	mode = NULL;
+	num_connectors = 0;
 
 	DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 834a5e28abbe..7352bde299d5 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
 	if (max_segment == 0)
 		max_segment = UINT_MAX;
 	err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0,
-						nr_pages << PAGE_SHIFT,
+						(unsigned long)nr_pages << PAGE_SHIFT,
 						max_segment, GFP_KERNEL);
 	if (err) {
 		kfree(sg);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 3f479483d7d8..23b4e9a3361d 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -760,9 +760,11 @@ static void output_poll_execute(struct work_struct *work)
 	changed = dev->mode_config.delayed_event;
 	dev->mode_config.delayed_event = false;
 
-	if (!drm_kms_helper_poll && dev->mode_config.poll_running) {
-		drm_kms_helper_disable_hpd(dev);
-		dev->mode_config.poll_running = false;
+	if (!drm_kms_helper_poll) {
+		if (dev->mode_config.poll_running) {
+			drm_kms_helper_disable_hpd(dev);
+			dev->mode_config.poll_running = false;
+		}
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 84101baeecc6..a6c19de46292 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1040,7 +1040,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	uint64_t *points;
 	uint32_t signaled_count, i;
 
-	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)
+	if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+		     DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE))
 		lockdep_assert_none_held_once();
 
 	points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
@@ -1109,7 +1110,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 	 * fallthough and try a 0 timeout wait!
 	 */
 
-	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
+	if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT |
+		     DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) {
 		for (i = 0; i < count; ++i)
 			drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]);
 	}
@@ -1416,10 +1418,21 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj,
 
 	/* This happens inside the syncobj lock */
 	fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1));
+	if (!fence)
+		return;
+
 	ret = dma_fence_chain_find_seqno(&fence, entry->point);
-	if (ret != 0 || !fence) {
+	if (ret != 0) {
+		/* The given seqno has not been submitted yet. */
 		dma_fence_put(fence);
 		return;
+	} else if (!fence) {
+		/* If dma_fence_chain_find_seqno returns 0 but sets the fence
+		 * to NULL, it implies that the given seqno is signaled and a
+		 * later seqno has already been submitted. Assign a stub fence
+		 * so that the eventfd still gets signaled below.
+		 */
+		fence = dma_fence_get_stub();
 	}
 
 	list_del_init(&entry->node);
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071..3089029abba4 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
 
 	  Note that this driver only supports newer device from Broadwell on.
 	  For further information and setup guide, you can visit:
-	  http://01.org/igvt-g.
+	  https://github.com/intel/gvt-linux/wiki.
 
 	  If in doubt, say "N".
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 47cd6bb04366..06900ff307b2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -246,7 +246,14 @@ static enum phy icl_aux_pw_to_phy(struct drm_i915_private *i915,
 	enum aux_ch aux_ch = icl_aux_pw_to_ch(power_well);
 	struct intel_digital_port *dig_port = aux_ch_to_digital_port(i915, aux_ch);
 
-	return intel_port_to_phy(i915, dig_port->base.port);
+	/*
+	 * FIXME should we care about the (VBT defined) dig_port->aux_ch
+	 * relationship or should this be purely defined by the hardware layout?
+	 * Currently if the port doesn't appear in the VBT, or if it's declared
+	 * as HDMI-only and routed to a combo PHY, the encoder either won't be
+	 * present at all or it will not have an aux_ch assigned.
+	 */
+	return dig_port ? intel_port_to_phy(i915, dig_port->base.port) : PHY_NONE;
 }
 
 static void hsw_wait_for_power_well_enable(struct drm_i915_private *dev_priv,
@@ -414,7 +421,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 
 	intel_de_rmw(dev_priv, regs->driver, 0, HSW_PWR_WELL_CTL_REQ(pw_idx));
 
-	if (DISPLAY_VER(dev_priv) < 12)
+	/* FIXME this is a mess */
+	if (phy != PHY_NONE)
 		intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
 			     0, ICL_LANE_ENABLE_AUX);
 
@@ -437,7 +445,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 
 	drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv));
 
-	intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy), ICL_LANE_ENABLE_AUX, 0);
+	/* FIXME this is a mess */
+	if (phy != PHY_NONE)
+		intel_de_rmw(dev_priv, ICL_PORT_CL_DW12(phy),
+			     ICL_LANE_ENABLE_AUX, 0);
 
 	intel_de_rmw(dev_priv, regs->driver, HSW_PWR_WELL_CTL_REQ(pw_idx), 0);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 3fdd8a517983..ac7fe6281afe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -609,6 +609,13 @@ struct intel_connector {
 	 * and active (i.e. dpms ON state). */
 	bool (*get_hw_state)(struct intel_connector *);
 
+	/*
+	 * Optional hook called during init/resume to sync any state
+	 * stored in the connector (eg. DSC state) wrt. the HW state.
+	 */
+	void (*sync_state)(struct intel_connector *connector,
+			   const struct intel_crtc_state *crtc_state);
+
 	/* Panel info for eDP and LVDS */
 	struct intel_panel panel;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f5ef95da5534..94d2a15d8444 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2355,6 +2355,9 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 	limits->min_rate = intel_dp_common_rate(intel_dp, 0);
 	limits->max_rate = intel_dp_max_link_rate(intel_dp);
 
+	/* FIXME 128b/132b SST support missing */
+	limits->max_rate = min(limits->max_rate, 810000);
+
 	limits->min_lane_count = 1;
 	limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
 
@@ -5696,6 +5699,9 @@ intel_dp_detect(struct drm_connector *connector,
 		goto out;
 	}
 
+	if (!intel_dp_is_edp(intel_dp))
+		intel_psr_init_dpcd(intel_dp);
+
 	intel_dp_detect_dsc_caps(intel_dp, intel_connector);
 
 	intel_dp_configure_mst(intel_dp);
@@ -5856,6 +5862,19 @@ intel_dp_connector_unregister(struct drm_connector *connector)
 	intel_connector_unregister(connector);
 }
 
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+				   const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(connector->base.dev);
+
+	if (crtc_state && crtc_state->dsc.compression_enable) {
+		drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
+		connector->dp.dsc_decompression_enabled = true;
+	} else {
+		connector->dp.dsc_decompression_enabled = false;
+	}
+}
+
 void intel_dp_encoder_flush_work(struct drm_encoder *encoder)
 {
 	struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 05db46b111f2..375d0677cd8c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -45,6 +45,8 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 int intel_dp_min_bpp(enum intel_output_format output_format);
 bool intel_dp_init_connector(struct intel_digital_port *dig_port,
 			     struct intel_connector *intel_connector);
+void intel_dp_connector_sync_state(struct intel_connector *connector,
+				   const struct intel_crtc_state *crtc_state);
 void intel_dp_set_link_params(struct intel_dp *intel_dp,
 			      int link_rate, int lane_count);
 int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index 3a595cd433d4..8538d1ce2fcb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -330,23 +330,13 @@ static const struct hdcp2_dp_msg_data hdcp2_dp_msg_data[] = {
 	  0, 0 },
 };
 
-static struct drm_dp_aux *
-intel_dp_hdcp_get_aux(struct intel_connector *connector)
-{
-	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
-
-	if (intel_encoder_is_mst(connector->encoder))
-		return &connector->port->aux;
-	else
-		return &dig_port->dp.aux;
-}
-
 static int
 intel_dp_hdcp2_read_rx_status(struct intel_connector *connector,
 			      u8 *rx_status)
 {
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	ssize_t ret;
 
 	ret = drm_dp_dpcd_read(aux,
@@ -399,7 +389,9 @@ intel_dp_hdcp2_wait_for_msg(struct intel_connector *connector,
 			    const struct hdcp2_dp_msg_data *hdcp2_msg_data)
 {
 	struct drm_i915_private *i915 = to_i915(connector->base.dev);
-	struct intel_hdcp *hdcp = &connector->hdcp;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct intel_dp *dp = &dig_port->dp;
+	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	u8 msg_id = hdcp2_msg_data->msg_id;
 	int ret, timeout;
 	bool msg_ready = false;
@@ -454,8 +446,9 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
 	unsigned int offset;
 	u8 *byte = buf;
 	ssize_t ret, bytes_to_write, len;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	const struct hdcp2_dp_msg_data *hdcp2_msg_data;
-	struct drm_dp_aux *aux;
 
 	hdcp2_msg_data = get_hdcp2_dp_msg_data(*byte);
 	if (!hdcp2_msg_data)
@@ -463,8 +456,6 @@ int intel_dp_hdcp2_write_msg(struct intel_connector *connector,
 
 	offset = hdcp2_msg_data->offset;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	/* No msg_id in DP HDCP2.2 msgs */
 	bytes_to_write = size - 1;
 	byte++;
@@ -490,7 +481,8 @@ static
 ssize_t get_receiver_id_list_rx_info(struct intel_connector *connector,
 				     u32 *dev_cnt, u8 *byte)
 {
-	struct drm_dp_aux *aux = intel_dp_hdcp_get_aux(connector);
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	ssize_t ret;
 	u8 *rx_info = byte;
 
@@ -515,8 +507,9 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 {
 	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	struct intel_hdcp *hdcp = &connector->hdcp;
-	struct drm_dp_aux *aux;
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
+	struct intel_dp *dp = &dig_port->dp;
+	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	unsigned int offset;
 	u8 *byte = buf;
 	ssize_t ret, bytes_to_recv, len;
@@ -530,8 +523,6 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 		return -EINVAL;
 	offset = hdcp2_msg_data->offset;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	ret = intel_dp_hdcp2_wait_for_msg(connector, hdcp2_msg_data);
 	if (ret < 0)
 		return ret;
@@ -561,13 +552,8 @@ int intel_dp_hdcp2_read_msg(struct intel_connector *connector,
 
 		/* Entire msg read timeout since initiate of msg read */
 		if (bytes_to_recv == size - 1 && hdcp2_msg_data->msg_read_timeout > 0) {
-			if (intel_encoder_is_mst(connector->encoder))
-				msg_end = ktime_add_ms(ktime_get_raw(),
-						       hdcp2_msg_data->msg_read_timeout *
-						       connector->port->parent->num_ports);
-			else
-				msg_end = ktime_add_ms(ktime_get_raw(),
-						       hdcp2_msg_data->msg_read_timeout);
+			msg_end = ktime_add_ms(ktime_get_raw(),
+					       hdcp2_msg_data->msg_read_timeout);
 		}
 
 		ret = drm_dp_dpcd_read(aux, offset,
@@ -651,12 +637,11 @@ static
 int intel_dp_hdcp2_capable(struct intel_connector *connector,
 			   bool *capable)
 {
-	struct drm_dp_aux *aux;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct drm_dp_aux *aux = &dig_port->dp.aux;
 	u8 rx_caps[3];
 	int ret;
 
-	aux = intel_dp_hdcp_get_aux(connector);
-
 	*capable = false;
 	ret = drm_dp_dpcd_read(aux,
 			       DP_HDCP_2_2_REG_RX_CAPS_OFFSET,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 8a9432335030..a01a59f57ae5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1534,6 +1534,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 		return NULL;
 
 	intel_connector->get_hw_state = intel_dp_mst_get_hw_state;
+	intel_connector->sync_state = intel_dp_connector_sync_state;
 	intel_connector->mst_port = intel_dp;
 	intel_connector->port = port;
 	drm_dp_mst_get_port_malloc(port);
diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
index 94eece7f63be..caeca3a8442c 100644
--- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c
+++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c
@@ -318,12 +318,6 @@ static void intel_modeset_update_connector_atomic_state(struct drm_i915_private
 			const struct intel_crtc_state *crtc_state =
 				to_intel_crtc_state(crtc->base.state);
 
-			if (crtc_state->dsc.compression_enable) {
-				drm_WARN_ON(&i915->drm, !connector->dp.dsc_decompression_aux);
-				connector->dp.dsc_decompression_enabled = true;
-			} else {
-				connector->dp.dsc_decompression_enabled = false;
-			}
 			conn_state->max_bpc = (crtc_state->pipe_bpp ?: 24) / 3;
 		}
 	}
@@ -775,8 +769,9 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
 
 	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
+		struct intel_crtc_state *crtc_state = NULL;
+
 		if (connector->get_hw_state(connector)) {
-			struct intel_crtc_state *crtc_state;
 			struct intel_crtc *crtc;
 
 			connector->base.dpms = DRM_MODE_DPMS_ON;
@@ -802,6 +797,10 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915)
 			connector->base.dpms = DRM_MODE_DPMS_OFF;
 			connector->base.encoder = NULL;
 		}
+
+		if (connector->sync_state)
+			connector->sync_state(connector, crtc_state);
+
 		drm_dbg_kms(&i915->drm,
 			    "[CONNECTOR:%d:%s] hw state readout: %s\n",
 			    connector->base.base.id, connector->base.name,
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 57bbf3e3af92..4faaf4b3fc53 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2776,9 +2776,6 @@ void intel_psr_init(struct intel_dp *intel_dp)
 	if (!(HAS_PSR(dev_priv) || HAS_DP20(dev_priv)))
 		return;
 
-	if (!intel_dp_is_edp(intel_dp))
-		intel_psr_init_dpcd(intel_dp);
-
 	/*
 	 * HSW spec explicitly says PSR is tied to port A.
 	 * BDW+ platforms have a instance of PSR registers per transcoder but
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index acc6b6804105..2915d7afe5cc 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -1209,7 +1209,7 @@ static bool intel_sdvo_set_tv_format(struct intel_sdvo *intel_sdvo,
 	struct intel_sdvo_tv_format format;
 	u32 format_map;
 
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memset(&format, 0, sizeof(format));
 	memcpy(&format, &format_map, min(sizeof(format), sizeof(format_map)));
 
@@ -2298,7 +2298,7 @@ static int intel_sdvo_get_tv_modes(struct drm_connector *connector)
 	 * Read the list of supported input resolutions for the selected TV
 	 * format.
 	 */
-	format_map = 1 << conn_state->tv.mode;
+	format_map = 1 << conn_state->tv.legacy_mode;
 	memcpy(&tv_res, &format_map,
 	       min(sizeof(format_map), sizeof(struct intel_sdvo_sdtv_resolution_request)));
 
@@ -2363,7 +2363,7 @@ intel_sdvo_connector_atomic_get_property(struct drm_connector *connector,
 		int i;
 
 		for (i = 0; i < intel_sdvo_connector->format_supported_num; i++)
-			if (state->tv.mode == intel_sdvo_connector->tv_format_supported[i]) {
+			if (state->tv.legacy_mode == intel_sdvo_connector->tv_format_supported[i]) {
 				*val = i;
 
 				return 0;
@@ -2419,7 +2419,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
 	struct intel_sdvo_connector_state *sdvo_state = to_intel_sdvo_connector_state(state);
 
 	if (property == intel_sdvo_connector->tv_format) {
-		state->tv.mode = intel_sdvo_connector->tv_format_supported[val];
+		state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[val];
 
 		if (state->crtc) {
 			struct drm_crtc_state *crtc_state =
@@ -3076,7 +3076,7 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo,
 		drm_property_add_enum(intel_sdvo_connector->tv_format, i,
 				      tv_format_names[intel_sdvo_connector->tv_format_supported[i]]);
 
-	intel_sdvo_connector->base.base.state->tv.mode = intel_sdvo_connector->tv_format_supported[0];
+	intel_sdvo_connector->base.base.state->tv.legacy_mode = intel_sdvo_connector->tv_format_supported[0];
 	drm_object_attach_property(&intel_sdvo_connector->base.base.base,
 				   intel_sdvo_connector->tv_format, 0);
 	return true;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index d4386cb3569e..992a725de751 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -949,7 +949,7 @@ intel_disable_tv(struct intel_atomic_state *state,
 
 static const struct tv_mode *intel_tv_mode_find(const struct drm_connector_state *conn_state)
 {
-	int format = conn_state->tv.mode;
+	int format = conn_state->tv.legacy_mode;
 
 	return &tv_modes[format];
 }
@@ -1704,7 +1704,7 @@ static void intel_tv_find_better_format(struct drm_connector *connector)
 			break;
 	}
 
-	connector->state->tv.mode = i;
+	connector->state->tv.legacy_mode = i;
 }
 
 static int
@@ -1859,7 +1859,7 @@ static int intel_tv_atomic_check(struct drm_connector *connector,
 	old_state = drm_atomic_get_old_connector_state(state, connector);
 	new_crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc);
 
-	if (old_state->tv.mode != new_state->tv.mode ||
+	if (old_state->tv.legacy_mode != new_state->tv.legacy_mode ||
 	    old_state->tv.margins.left != new_state->tv.margins.left ||
 	    old_state->tv.margins.right != new_state->tv.margins.right ||
 	    old_state->tv.margins.top != new_state->tv.margins.top ||
@@ -1896,7 +1896,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 	conn_state->tv.margins.right = 46;
 	conn_state->tv.margins.bottom = 37;
 
-	conn_state->tv.mode = 0;
+	conn_state->tv.legacy_mode = 0;
 
 	/* Create TV properties then attach current values */
 	for (i = 0; i < ARRAY_SIZE(tv_modes); i++) {
@@ -1910,7 +1910,7 @@ static void intel_tv_add_properties(struct drm_connector *connector)
 
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.legacy_tv_mode_property,
-				   conn_state->tv.mode);
+				   conn_state->tv.legacy_mode);
 	drm_object_attach_property(&connector->base,
 				   i915->drm.mode_config.tv_left_margin_property,
 				   conn_state->tv.margins.left);
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b..8b21dc8e26d5 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -51,8 +51,8 @@
 #define DSCC_PICTURE_PARAMETER_SET_0		_MMIO(0x6BA00)
 #define _DSCA_PPS_0				0x6B200
 #define _DSCC_PPS_0				0x6BA00
-#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + (pps) * 4)
-#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + (pps) * 4)
+#define DSCA_PPS(pps)				_MMIO(_DSCA_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
+#define DSCC_PPS(pps)				_MMIO(_DSCC_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
 #define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
 #define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 1d3ebdf4069b..c08b67593565 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -379,6 +379,9 @@ i915_gem_userptr_release(struct drm_i915_gem_object *obj)
 {
 	GEM_WARN_ON(obj->userptr.page_ref);
 
+	if (!obj->userptr.notifier.mm)
+		return;
+
 	mmu_interval_notifier_remove(&obj->userptr.notifier);
 	obj->userptr.notifier.mm = NULL;
 }
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d..efcb00472be2 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
 	for (i = start; i < end; i += 4) {
 		p = intel_gvt_find_mmio_info(gvt, i);
 		if (p) {
-			WARN(1, "dup mmio definition offset %x\n",
-				info->offset);
+			WARN(1, "dup mmio definition offset %x\n", i);
 
 			/* We return -EEXIST here to make GVT-g load fail.
 			 * So duplicated MMIO can be found as soon as
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91a..9b6d87c8b583 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
  * To virtualize GPU resources GVT-g driver depends on hypervisor technology
  * e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
  * and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
  */
 
 static LIST_HEAD(intel_gvt_devices);
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 2990dd4d4a0d..e14ac0ab1314 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -3,6 +3,8 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include <linux/jiffies.h>
+
 //#include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
@@ -12,7 +14,7 @@
 
 #define REDUCED_TIMESLICE	5
 #define REDUCED_PREEMPT		10
-#define WAIT_FOR_RESET_TIME	10000
+#define WAIT_FOR_RESET_TIME_MS	10000
 
 struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt)
 {
@@ -91,7 +93,7 @@ int intel_selftest_wait_for_rq(struct i915_request *rq)
 {
 	long ret;
 
-	ret = i915_request_wait(rq, 0, WAIT_FOR_RESET_TIME);
+	ret = i915_request_wait(rq, 0, msecs_to_jiffies(WAIT_FOR_RESET_TIME_MS));
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
index 3f73b211fa8e..3407450435e2 100644
--- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c
@@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_CVBS]) {
 		meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS];
 		drm_bridge_remove(&meson_encoder_cvbs->bridge);
-		drm_bridge_remove(meson_encoder_cvbs->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/meson/meson_encoder_dsi.c b/drivers/gpu/drm/meson/meson_encoder_dsi.c
index 3f93c70488ca..311b91630fbe 100644
--- a/drivers/gpu/drm/meson/meson_encoder_dsi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_dsi.c
@@ -168,6 +168,5 @@ void meson_encoder_dsi_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_DSI]) {
 		meson_encoder_dsi = priv->encoders[MESON_ENC_DSI];
 		drm_bridge_remove(&meson_encoder_dsi->bridge);
-		drm_bridge_remove(meson_encoder_dsi->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 25ea76558690..c4686568c9ca 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -474,6 +474,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_HDMI]) {
 		meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI];
 		drm_bridge_remove(&meson_encoder_hdmi->bridge);
-		drm_bridge_remove(meson_encoder_hdmi->next_bridge);
 	}
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd302..c9c55e2ea584 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1287,7 +1287,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
 	gpu->ubwc_config.highest_bank_bit = 15;
 
 	if (adreno_is_a610(gpu)) {
-		gpu->ubwc_config.highest_bank_bit = 14;
+		gpu->ubwc_config.highest_bank_bit = 13;
 		gpu->ubwc_config.min_acc_len = 1;
 		gpu->ubwc_config.ubwc_mode = 1;
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00..6a4b489d44e5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
  *			to track crtc in the disable() hook which is called
  *			_after_ encoder_mask is cleared.
  * @connector:		If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
- *				all CTL paths
- * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
- * @debugfs_root:		Debug file system root file node
  * @enc_lock:			Lock around physical encoder
  *				create/destroy/enable/disable
  * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
@@ -2072,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	}
 
 	/* reset the merge 3D HW block */
-	if (phys_enc->hw_pp->merge_3d) {
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
 				BLEND_3D_NONE);
 		if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2103,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 	if (phys_enc->hw_wb)
 		intf_cfg.wb = phys_enc->hw_wb->idx;
 
-	if (phys_enc->hw_pp->merge_3d)
+	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	if (ctl->ops.reset_intf_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326..724537ab776d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 /**
  * struct dpu_rm_requirements - Reservation requirements parameter bundle
  * @topology:  selected topology for the display
- * @hw_res:	   Hardware resources required as reported by the encoders
  */
 struct dpu_rm_requirements {
 	struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
  * _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
  * @rm: dpu resource manager handle
  * @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
  */
 static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
 {
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7..fb588fde298a 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
 	tbd = dp_link_get_test_bits_depth(ctrl->link,
 			ctrl->panel->dp_mode.bpp);
 
-	if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
-		pr_debug("BIT_DEPTH not set. Configure default\n");
-		tbd = DP_TEST_BIT_DEPTH_8;
-	}
-
 	config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
 
 	/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index d37d599aec27..4c72124ffb5d 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -329,10 +329,26 @@ static const struct component_ops dp_display_comp_ops = {
 	.unbind = dp_display_unbind,
 };
 
+static void dp_display_send_hpd_event(struct msm_dp *dp_display)
+{
+	struct dp_display_private *dp;
+	struct drm_connector *connector;
+
+	dp = container_of(dp_display, struct dp_display_private, dp_display);
+
+	connector = dp->dp_display.connector;
+	drm_helper_hpd_irq_event(connector->dev);
+}
+
 static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 					    bool hpd)
 {
-	struct drm_bridge *bridge = dp->dp_display.bridge;
+	if ((hpd && dp->dp_display.link_ready) ||
+			(!hpd && !dp->dp_display.link_ready)) {
+		drm_dbg_dp(dp->drm_dev, "HPD already %s\n",
+				(hpd ? "on" : "off"));
+		return 0;
+	}
 
 	/* reset video pattern flag on disconnect */
 	if (!hpd) {
@@ -348,7 +364,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp,
 
 	drm_dbg_dp(dp->drm_dev, "type=%d hpd=%d\n",
 			dp->dp_display.connector_type, hpd);
-	drm_bridge_hpd_notify(bridge, dp->dp_display.link_ready);
+	dp_display_send_hpd_event(&dp->dp_display);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7..49dfac1fd1ef 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_print.h>
 
+#include "dp_reg.h"
 #include "dp_link.h"
 #include "dp_panel.h"
 
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
 
 int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 {
-	u32 cc;
+	u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
 	struct dp_link_private *link;
 
 	if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
 	 * Unless a video pattern CTS test is ongoing, use RGB_VESA
 	 * Only RGB_VESA and RGB_CEA supported for now
 	 */
-	if (dp_link_is_video_pattern_requested(link))
-		cc = link->dp_link.test_video.test_dyn_range;
-	else
-		cc = DP_TEST_DYNAMIC_RANGE_VESA;
+	if (dp_link_is_video_pattern_requested(link)) {
+		if (link->dp_link.test_video.test_dyn_range &
+					DP_TEST_DYNAMIC_RANGE_CEA)
+			cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+	}
 
 	return cc;
 }
@@ -1179,6 +1181,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
 u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 {
 	u32 tbd;
+	struct dp_link_private *link;
+
+	link = container_of(dp_link, struct dp_link_private, dp_link);
 
 	/*
 	 * Few simplistic rules and assumptions made here:
@@ -1196,12 +1201,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
 		tbd = DP_TEST_BIT_DEPTH_10;
 		break;
 	default:
-		tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+		drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+			   bpp);
+		tbd = DP_TEST_BIT_DEPTH_8;
 		break;
 	}
 
-	if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
-		tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+	tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
 
 	return tbd;
 }
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b..78785ed4b40c 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
 #define DP_MISC0_COLORIMETRY_CFG_SHIFT		(0x00000001)
 #define DP_MISC0_TEST_BITS_DEPTH_SHIFT		(0x00000005)
 
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB	(0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB		(0x04)
+
 #define REG_DP_VALID_BOUNDARY			(0x00000030)
 #define REG_DP_VALID_BOUNDARY_2			(0x00000034)
 
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e..0915f3b68752 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
 	void *vaddr;
 
-	vaddr = msm_gem_get_vaddr(obj);
+	vaddr = msm_gem_get_vaddr_locked(obj);
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 	iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
 
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
 {
-	msm_gem_put_vaddr(obj);
+	msm_gem_put_vaddr_locked(obj);
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 095390774f22..655002b21b0d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -751,12 +751,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned long flags;
 
-	pm_runtime_get_sync(&gpu->pdev->dev);
+	WARN_ON(!mutex_is_locked(&gpu->lock));
 
-	mutex_lock(&gpu->lock);
+	pm_runtime_get_sync(&gpu->pdev->dev);
 
 	msm_gpu_hw_init(gpu);
 
+	submit->seqno = submit->hw_fence->seqno;
+
 	update_sw_cntrs(gpu);
 
 	/*
@@ -781,11 +783,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	gpu->funcs->submit(gpu, submit);
 	gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
 
-	hangcheck_timer_reset(gpu);
-
-	mutex_unlock(&gpu->lock);
-
 	pm_runtime_put(&gpu->pdev->dev);
+	hangcheck_timer_reset(gpu);
 }
 
 /*
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc97..d5512037c38b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
 	struct msm_mmu base;
 	struct msm_mmu *parent;
 	struct io_pgtable_ops *pgtbl_ops;
+	const struct iommu_flush_ops *tlb;
+	struct device *iommu_dev;
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	phys_addr_t ttbr;
 	u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
 
 static void msm_iommu_tlb_flush_all(void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
 		size_t granule, void *cookie)
 {
+	struct msm_iommu_pagetable *pagetable = cookie;
+	struct adreno_smmu_priv *adreno_smmu;
+
+	if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+		return;
+
+	adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+	pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+	pm_runtime_put_autosuspend(pagetable->iommu_dev);
 }
 
 static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
 {
 }
 
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
 	.tlb_flush_all = msm_iommu_tlb_flush_all,
 	.tlb_flush_walk = msm_iommu_tlb_flush_walk,
 	.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* The incoming cfg will have the TTBR1 quirk enabled */
 	ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
-	ttbr0_cfg.tlb = &null_tlb_ops;
+	ttbr0_cfg.tlb = &tlb_ops;
 
 	pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
-		&ttbr0_cfg, iommu->domain);
+		&ttbr0_cfg, pagetable);
 
 	if (!pagetable->pgtbl_ops) {
 		kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
+	pagetable->tlb = ttbr1_cfg->tlb;
+	pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
 	pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
 	pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
 
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd..35423d10aafa 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.highest_bank_bit = 1,
+	.reg_bus_bw = 76800,
 };
 
 static const struct msm_mdss_data sdm845_data = {
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005a..9d6655f96f0c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	msm_fence_init(submit->hw_fence, fctx);
 
-	submit->seqno = submit->hw_fence->seqno;
-
 	mutex_lock(&priv->lru.lock);
 
 	for (i = 0; i < submit->nr_bos; i++) {
@@ -35,8 +33,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	mutex_unlock(&priv->lru.lock);
 
+	/* TODO move submit path over to using a per-ring lock.. */
+	mutex_lock(&gpu->lock);
+
 	msm_gpu_submit(gpu, submit);
 
+	mutex_unlock(&gpu->lock);
+
 	return dma_fence_get(submit->hw_fence);
 }
 
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 1e6aaf95ff7c..ceef470c9fbf 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -100,3 +100,11 @@ config DRM_NOUVEAU_SVM
 	help
 	  Say Y here if you want to enable experimental support for
 	  Shared Virtual Memory (SVM).
+
+config DRM_NOUVEAU_GSP_DEFAULT
+	bool "Use GSP firmware for Turing/Ampere (needs firmware installed)"
+	depends on DRM_NOUVEAU
+	default n
+	help
+	  Say Y here if you want to use the GSP codepaths by default on
+	  Turing and Ampere GPUs.
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
index 0d9fc741a719..932c9fd0b2d8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/client.h
@@ -11,6 +11,7 @@ struct nvkm_client {
 	u32 debug;
 
 	struct rb_root objroot;
+	spinlock_t obj_lock;
 
 	void *data;
 	int (*event)(u64 token, void *argv, u32 argc);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f..6f5d376d8fcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
 struct nvkm_gsp_mem {
-	u32 size;
+	size_t size;
 	void *data;
 	dma_addr_t addr;
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390..80f74ee0fc78 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 	struct nouveau_abi16_ntfy *ntfy, *temp;
 
 	/* Cancel all jobs from the entity's queue. */
-	drm_sched_entity_fini(&chan->sched.entity);
+	if (chan->sched)
+		drm_sched_entity_fini(&chan->sched->entity);
 
 	if (chan->chan)
 		nouveau_channel_idle(chan->chan);
 
-	nouveau_sched_fini(&chan->sched);
+	if (chan->sched)
+		nouveau_sched_destroy(&chan->sched);
 
 	/* cleanup notifier state */
 	list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -197,6 +199,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->client.device;
+	struct nvkm_device *nvkm_device = nvxx_device(&drm->client.device);
 	struct nvkm_gr *gr = nvxx_gr(device);
 	struct drm_nouveau_getparam *getparam = data;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
@@ -261,6 +264,14 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 		getparam->value = nouveau_exec_push_max_from_ib_max(ib_max);
 		break;
 	}
+	case NOUVEAU_GETPARAM_VRAM_BAR_SIZE:
+		getparam->value = nvkm_device->func->resource_size(nvkm_device, 1);
+		break;
+	case NOUVEAU_GETPARAM_VRAM_USED: {
+		struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+		getparam->value = (u64)ttm_resource_manager_usage(vram_mgr);
+		break;
+	}
 	default:
 		NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param);
 		return -EINVAL;
@@ -337,10 +348,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	if (ret)
 		goto done;
 
-	ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
-				 chan->chan->dma.ib_max);
-	if (ret)
-		goto done;
+	/* If we're not using the VM_BIND uAPI, we don't need a scheduler.
+	 *
+	 * The client lock is already acquired by nouveau_abi16_get().
+	 */
+	if (nouveau_cli_uvmm(cli)) {
+		ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+					   chan->chan->dma.ib_max);
+		if (ret)
+			goto done;
+	}
 
 	init->channel = chan->chan->chid;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c75..11c8c4a80079 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -26,7 +26,7 @@ struct nouveau_abi16_chan {
 	struct nouveau_bo *ntfy;
 	struct nouveau_vma *ntfy_vma;
 	struct nvkm_mm  heap;
-	struct nouveau_sched sched;
+	struct nouveau_sched *sched;
 };
 
 struct nouveau_abi16 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6f6c31a9937b..a947e1d5f309 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
 	WARN_ON(!list_empty(&cli->worker));
 
 	usif_client_fini(cli);
-	nouveau_sched_fini(&cli->sched);
+	if (cli->sched)
+		nouveau_sched_destroy(&cli->sched);
 	if (uvmm)
 		nouveau_uvmm_fini(uvmm);
 	nouveau_vmm_fini(&cli->svm);
@@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	cli->mem = &mems[ret];
 
 	/* Don't pass in the (shared) sched_wq in order to let
-	 * nouveau_sched_init() create a dedicated one for VM_BIND jobs.
+	 * nouveau_sched_create() create a dedicated one for VM_BIND jobs.
 	 *
 	 * This is required to ensure that for VM_BIND jobs free_job() work and
 	 * run_job() work can always run concurrently and hence, free_job() work
@@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	 * locks which indirectly or directly are held for allocations
 	 * elsewhere.
 	 */
-	ret = nouveau_sched_init(&cli->sched, drm, NULL, 1);
+	ret = nouveau_sched_create(&cli->sched, drm, NULL, 1);
 	if (ret)
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8a6d94c8b163..e239c6bf4afa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -98,7 +98,7 @@ struct nouveau_cli {
 		bool disabled;
 	} uvmm;
 
-	struct nouveau_sched sched;
+	struct nouveau_sched *sched;
 
 	const struct nvif_mclass *mem;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index bc5d71b79ab2..e65c0ef23bc7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
 	if (ret)
 		goto out;
 
-	args.sched = &chan16->sched;
+	args.sched = chan16->sched;
 	args.file_priv = file_priv;
 	args.chan = chan;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index ca762ea55413..93f08f9479d8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -103,6 +103,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
+	cancel_work_sync(&fctx->uevent_work);
 	nouveau_fence_context_kill(fctx, 0);
 	nvif_event_dtor(&fctx->event);
 	fctx->dead = 1;
@@ -145,12 +146,13 @@ nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fc
 	return drop;
 }
 
-static int
-nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+static void
+nouveau_fence_uevent_work(struct work_struct *work)
 {
-	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	struct nouveau_fence_chan *fctx = container_of(work, struct nouveau_fence_chan,
+						       uevent_work);
 	unsigned long flags;
-	int ret = NVIF_EVENT_KEEP;
+	int drop = 0;
 
 	spin_lock_irqsave(&fctx->lock, flags);
 	if (!list_empty(&fctx->pending)) {
@@ -160,11 +162,20 @@ nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
 		if (nouveau_fence_update(chan, fctx))
-			ret = NVIF_EVENT_DROP;
+			drop = 1;
 	}
+	if (drop)
+		nvif_event_block(&fctx->event);
+
 	spin_unlock_irqrestore(&fctx->lock, flags);
+}
 
-	return ret;
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_event *event, void *repv, u32 repc)
+{
+	struct nouveau_fence_chan *fctx = container_of(event, typeof(*fctx), event);
+	schedule_work(&fctx->uevent_work);
+	return NVIF_EVENT_KEEP;
 }
 
 void
@@ -178,6 +189,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha
 	} args;
 	int ret;
 
+	INIT_WORK(&fctx->uevent_work, nouveau_fence_uevent_work);
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 64d33ae7f356..8bc065acfe35 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -44,6 +44,7 @@ struct nouveau_fence_chan {
 	u32 context;
 	char name[32];
 
+	struct work_struct uevent_work;
 	struct nvif_event event;
 	int notify_ref, dead, killed;
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 49c2bcbef129..5a887d67dc0e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -764,7 +764,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 		return -ENOMEM;
 
 	if (unlikely(nouveau_cli_uvmm(cli)))
-		return -ENOSYS;
+		return nouveau_abi16_put(abi16, -ENOSYS);
 
 	list_for_each_entry(temp, &abi16->channels, head) {
 		if (temp->chan->chid == req->channel) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9c..32fa2e273965 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = {
 	.free_job = nouveau_sched_free_job,
 };
 
-int
+static int
 nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
 		   struct workqueue_struct *wq, u32 credit_limit)
 {
@@ -453,7 +453,30 @@ fail_wq:
 	return ret;
 }
 
-void
+int
+nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+		     struct workqueue_struct *wq, u32 credit_limit)
+{
+	struct nouveau_sched *sched;
+	int ret;
+
+	sched = kzalloc(sizeof(*sched), GFP_KERNEL);
+	if (!sched)
+		return -ENOMEM;
+
+	ret = nouveau_sched_init(sched, drm, wq, credit_limit);
+	if (ret) {
+		kfree(sched);
+		return ret;
+	}
+
+	*psched = sched;
+
+	return 0;
+}
+
+
+static void
 nouveau_sched_fini(struct nouveau_sched *sched)
 {
 	struct drm_gpu_scheduler *drm_sched = &sched->base;
@@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched)
 	if (sched->wq)
 		destroy_workqueue(sched->wq);
 }
+
+void
+nouveau_sched_destroy(struct nouveau_sched **psched)
+{
+	struct nouveau_sched *sched = *psched;
+
+	nouveau_sched_fini(sched);
+	kfree(sched);
+
+	*psched = NULL;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index a6528f5981e6..e1f01a23e6f6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -111,8 +111,8 @@ struct nouveau_sched {
 	} job;
 };
 
-int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
-		       struct workqueue_struct *wq, u32 credit_limit);
-void nouveau_sched_fini(struct nouveau_sched *sched);
+int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+			 struct workqueue_struct *wq, u32 credit_limit);
+void nouveau_sched_destroy(struct nouveau_sched **psched);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index cc03e0c22ff3..5e4565c5011a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id)
 	if (ret)
 		return ret;
 
-	buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL);
+	buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL);
 	if (!buffer->fault)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 4f223c972c6a..0a0a11dc9ec0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	args.sched = &cli->sched;
+	args.sched = cli->sched;
 	args.file_priv = file_priv;
 
 	ret = nouveau_uvmm_vm_bind(&args);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/client.c b/drivers/gpu/drm/nouveau/nvkm/core/client.c
index ebdeb8eb9e77..c55662937ab2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/client.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/client.c
@@ -180,6 +180,7 @@ nvkm_client_new(const char *name, u64 device, const char *cfg, const char *dbg,
 	client->device = device;
 	client->debug = nvkm_dbgopt(dbg, "CLIENT");
 	client->objroot = RB_ROOT;
+	spin_lock_init(&client->obj_lock);
 	client->event = event;
 	INIT_LIST_HEAD(&client->umem);
 	spin_lock_init(&client->lock);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/object.c b/drivers/gpu/drm/nouveau/nvkm/core/object.c
index 7c554c14e884..aea3ba72027a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/object.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/object.c
@@ -30,8 +30,10 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
 		   const struct nvkm_object_func *func)
 {
 	struct nvkm_object *object;
+	unsigned long flags;
 
 	if (handle) {
+		spin_lock_irqsave(&client->obj_lock, flags);
 		struct rb_node *node = client->objroot.rb_node;
 		while (node) {
 			object = rb_entry(node, typeof(*object), node);
@@ -40,9 +42,12 @@ nvkm_object_search(struct nvkm_client *client, u64 handle,
 			else
 			if (handle > object->object)
 				node = node->rb_right;
-			else
+			else {
+				spin_unlock_irqrestore(&client->obj_lock, flags);
 				goto done;
+			}
 		}
+		spin_unlock_irqrestore(&client->obj_lock, flags);
 		return ERR_PTR(-ENOENT);
 	} else {
 		object = &client->object;
@@ -57,30 +62,39 @@ done:
 void
 nvkm_object_remove(struct nvkm_object *object)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&object->client->obj_lock, flags);
 	if (!RB_EMPTY_NODE(&object->node))
 		rb_erase(&object->node, &object->client->objroot);
+	spin_unlock_irqrestore(&object->client->obj_lock, flags);
 }
 
 bool
 nvkm_object_insert(struct nvkm_object *object)
 {
-	struct rb_node **ptr = &object->client->objroot.rb_node;
+	struct rb_node **ptr;
 	struct rb_node *parent = NULL;
+	unsigned long flags;
 
+	spin_lock_irqsave(&object->client->obj_lock, flags);
+	ptr = &object->client->objroot.rb_node;
 	while (*ptr) {
 		struct nvkm_object *this = rb_entry(*ptr, typeof(*this), node);
 		parent = *ptr;
-		if (object->object < this->object)
+		if (object->object < this->object) {
 			ptr = &parent->rb_left;
-		else
-		if (object->object > this->object)
+		} else if (object->object > this->object) {
 			ptr = &parent->rb_right;
-		else
+		} else {
+			spin_unlock_irqrestore(&object->client->obj_lock, flags);
 			return false;
+		}
 	}
 
 	rb_link_node(&object->node, parent, ptr);
 	rb_insert_color(&object->node, &object->client->objroot);
+	spin_unlock_irqrestore(&object->client->obj_lock, flags);
 	return true;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
index 4135690326f4..3a30bea30e36 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bar/r535.c
@@ -168,12 +168,11 @@ r535_bar_new_(const struct nvkm_bar_func *hw, struct nvkm_device *device,
 	rm->flush = r535_bar_flush;
 
 	ret = gf100_bar_new_(rm, device, type, inst, &bar);
-	*pbar = bar;
 	if (ret) {
-		if (!bar)
-			kfree(rm);
+		kfree(rm);
 		return ret;
 	}
+	*pbar = bar;
 
 	bar->flushBAR2PhysMode = ioremap(device->func->resource_addr(device, 3), PAGE_SIZE);
 	if (!bar->flushBAR2PhysMode)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 19188683c8fc..8c2bf1c16f2a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name)
 	return (void *)fw;
 }
 
+static void
+shadow_fw_release(void *fw)
+{
+	release_firmware(fw);
+}
+
 static const struct nvbios_source
 shadow_fw = {
 	.name = "firmware",
 	.init = shadow_fw_init,
-	.fini = (void(*)(void *))release_firmware,
+	.fini = shadow_fw_release,
 	.read = shadow_fw_read,
 	.rw = false,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9ee58e2a0eb2..a73a5b589790 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
 	return 0;
 }
 
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+	if (mem->data) {
+		/*
+		 * Poison the buffer to catch any unexpected access from
+		 * GSP-RM if the buffer was prematurely freed.
+		 */
+		memset(mem->data, 0xFF, mem->size);
+
+		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+		memset(mem, 0, sizeof(*mem));
+	}
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+	mem->size = size;
+	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+	if (WARN_ON(!mem->data))
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int
 r535_gsp_postinit(struct nvkm_gsp *gsp)
 {
@@ -1024,6 +1050,11 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
 
 	nvkm_inth_allow(&gsp->subdev.inth);
 	nvkm_wr32(device, 0x110004, 0x00000040);
+
+	/* Release the DMA buffers that were needed only for boot and init */
+	nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+	nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+
 	return ret;
 }
 
@@ -1078,7 +1109,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 	if (IS_ERR(rpc))
 		return PTR_ERR(rpc);
 
-	rpc->size = sizeof(*rpc);
 	rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
 
 	str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
@@ -1094,6 +1124,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
 		strings += name_len;
 		str_offset += name_len;
 	}
+	rpc->size = str_offset;
 
 	return nvkm_gsp_rpc_wr(gsp, rpc, false);
 }
@@ -1532,27 +1563,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
 	return 0;
 }
 
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
-	if (mem->data) {
-		dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
-		mem->data = NULL;
-	}
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
-	mem->size = size;
-	mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
-	if (WARN_ON(!mem->data))
-		return -ENOMEM;
-
-	return 0;
-}
-
-
 static int
 r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
 {
@@ -1938,20 +1948,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
  * See kgspCreateRadix3_IMPL
  */
 static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
 	u64 addr;
 
 	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
 		u64 *ptes;
-		int idx;
+		size_t bufsize;
+		int ret, idx;
 
-		rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
-						      &rx3->mem[i].addr, GFP_KERNEL);
-		if (WARN_ON(!rx3->mem[i].data))
-			return -ENOMEM;
+		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+		if (ret)
+			return ret;
 
 		ptes = rx3->mem[i].data;
 		if (i == 2) {
@@ -1991,7 +2001,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		if (ret)
 			return ret;
 
-		ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+		ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
 		if (ret)
 			return ret;
 
@@ -2150,6 +2160,13 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
 	mutex_destroy(&gsp->cmdq.mutex);
 
 	r535_gsp_dtor_fws(gsp);
+
+	nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+	nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+	nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+	nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+	nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
 }
 
 int
@@ -2194,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
 	memcpy(gsp->sig.data, data, size);
 
 	/* Build radix3 page table for ELF image. */
-	ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+	ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
 	if (ret)
 		return ret;
 
@@ -2295,8 +2312,12 @@ r535_gsp_load(struct nvkm_gsp *gsp, int ver, const struct nvkm_gsp_fwif *fwif)
 {
 	struct nvkm_subdev *subdev = &gsp->subdev;
 	int ret;
+	bool enable_gsp = fwif->enable;
 
-	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", fwif->enable))
+#if IS_ENABLED(CONFIG_DRM_NOUVEAU_GSP_DEFAULT)
+	enable_gsp = true;
+#endif
+	if (!nvkm_boolopt(subdev->device->cfgopt, "NvGspRm", enable_gsp))
 		return -EINVAL;
 
 	if ((ret = r535_gsp_load_fw(gsp, "gsp", fwif->ver, &gsp->fws.rm)) ||
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index c4c0f08e9202..4945a1e787eb 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1768,11 +1768,11 @@ static const struct panel_desc starry_qfh032011_53g_desc = {
 };
 
 static const struct drm_display_mode starry_himax83102_j02_default_mode = {
-	.clock = 162850,
+	.clock = 162680,
 	.hdisplay = 1200,
-	.hsync_start = 1200 + 50,
-	.hsync_end = 1200 + 50 + 20,
-	.htotal = 1200 + 50 + 20 + 50,
+	.hsync_start = 1200 + 60,
+	.hsync_end = 1200 + 60 + 20,
+	.htotal = 1200 + 60 + 20 + 40,
 	.vdisplay = 1920,
 	.vsync_start = 1920 + 116,
 	.vsync_end = 1920 + 116 + 8,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 85b3b4871a1d..fdd768bbd487 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1985,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
 		clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags);
 	}
 
-	if (!clock)
+	if (!clock) {
+		vop2_unlock(vop2);
 		return;
+	}
 
 	if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
 	    !(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 85f082396d42..d442b893275b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w)
 	struct drm_sched_entity *entity;
 	struct dma_fence *fence;
 	struct drm_sched_fence *s_fence;
-	struct drm_sched_job *sched_job = NULL;
+	struct drm_sched_job *sched_job;
 	int r;
 
 	if (READ_ONCE(sched->pause_submit))
 		return;
 
 	/* Find entity with a ready job */
-	while (!sched_job && (entity = drm_sched_select_entity(sched))) {
-		sched_job = drm_sched_entity_pop_job(entity);
-		if (!sched_job)
-			complete_all(&entity->entity_idle);
-	}
+	entity = drm_sched_select_entity(sched);
 	if (!entity)
 		return;	/* No more work */
 
+	sched_job = drm_sched_entity_pop_job(entity);
+	if (!sched_job) {
+		complete_all(&entity->entity_idle);
+		drm_sched_run_job_queue(sched);
+		return;
+	}
+
 	s_fence = sched_job->s_fence;
 
 	atomic_add(sched_job->credits, &sched->credit_count);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index ff36171c8fb7..03d1c76aec2d 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -960,7 +960,8 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 	 * not the shared IOMMU domain, don't try to attach it to a different
 	 * domain. This allows using the IOMMU-backed DMA API.
 	 */
-	if (domain && domain != tegra->domain)
+	if (domain && domain->type != IOMMU_DOMAIN_IDENTITY &&
+	    domain != tegra->domain)
 		return 0;
 
 	if (tegra->domain) {
@@ -1242,9 +1243,26 @@ static int host1x_drm_probe(struct host1x_device *dev)
 
 	drm_mode_config_reset(drm);
 
-	err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
-	if (err < 0)
-		goto hub;
+	/*
+	 * Only take over from a potential firmware framebuffer if any CRTCs
+	 * have been registered. This must not be a fatal error because there
+	 * are other accelerators that are exposed via this driver.
+	 *
+	 * Another case where this happens is on Tegra234 where the display
+	 * hardware is no longer part of the host1x complex, so this driver
+	 * will not expose any modesetting features.
+	 */
+	if (drm->mode_config.num_crtc > 0) {
+		err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
+		if (err < 0)
+			goto hub;
+	} else {
+		/*
+		 * Indicate to userspace that this doesn't expose any display
+		 * capabilities.
+		 */
+		drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC);
+	}
 
 	err = drm_dev_register(drm, 0);
 	if (err < 0)
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index ea2af6bd9abe..e48863a44556 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -8,16 +8,308 @@
 
 #include <linux/prime_numbers.h>
 #include <linux/sched/signal.h>
+#include <linux/sizes.h>
 
 #include <drm/drm_buddy.h>
 
 #include "../lib/drm_random.h"
 
+static unsigned int random_seed;
+
 static inline u64 get_size(int order, u64 chunk_size)
 {
 	return (1 << order) * chunk_size;
 }
 
+static void drm_test_buddy_alloc_range_bias(struct kunit *test)
+{
+	u32 mm_size, ps, bias_size, bias_start, bias_end, bias_rem;
+	DRM_RND_STATE(prng, random_seed);
+	unsigned int i, count, *order;
+	struct drm_buddy mm;
+	LIST_HEAD(allocated);
+
+	bias_size = SZ_1M;
+	ps = roundup_pow_of_two(prandom_u32_state(&prng) % bias_size);
+	ps = max(SZ_4K, ps);
+	mm_size = (SZ_8M-1) & ~(ps-1); /* Multiple roots */
+
+	kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps);
+
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+			       "buddy_init failed\n");
+
+	count = mm_size / bias_size;
+	order = drm_random_order(count, &prng);
+	KUNIT_EXPECT_TRUE(test, order);
+
+	/*
+	 * Idea is to split the address space into uniform bias ranges, and then
+	 * in some random order allocate within each bias, using various
+	 * patterns within. This should detect if allocations leak out from a
+	 * given bias, for example.
+	 */
+
+	for (i = 0; i < count; i++) {
+		LIST_HEAD(tmp);
+		u32 size;
+
+		bias_start = order[i] * bias_size;
+		bias_end = bias_start + bias_size;
+		bias_rem = bias_size;
+
+		/* internal round_up too big */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_size + ps, bias_size,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_size, bias_size);
+
+		/* size too big */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_size + ps, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_size + ps, ps);
+
+		/* bias range too small for size */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start + ps,
+							     bias_end, bias_size, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start + ps, bias_end, bias_size, ps);
+
+		/* bias misaligned */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start + ps,
+							     bias_end - ps,
+							     bias_size >> 1, bias_size >> 1,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1);
+
+		/* single big page */
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, bias_size, bias_size,
+							      &tmp,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, bias_size, bias_size);
+		drm_buddy_free_list(&mm, &tmp);
+
+		/* single page with internal round_up */
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, ps, bias_size,
+							      &tmp,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, ps, bias_size);
+		drm_buddy_free_list(&mm, &tmp);
+
+		/* random size within */
+		size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+		if (size)
+			KUNIT_ASSERT_FALSE_MSG(test,
+					       drm_buddy_alloc_blocks(&mm, bias_start,
+								      bias_end, size, ps,
+								      &tmp,
+								      DRM_BUDDY_RANGE_ALLOCATION),
+					       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+					       bias_start, bias_end, size, ps);
+
+		bias_rem -= size;
+		/* too big for current avail */
+		KUNIT_ASSERT_TRUE_MSG(test,
+				      drm_buddy_alloc_blocks(&mm, bias_start,
+							     bias_end, bias_rem + ps, ps,
+							     &allocated,
+							     DRM_BUDDY_RANGE_ALLOCATION),
+				      "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
+				      bias_start, bias_end, bias_rem + ps, ps);
+
+		if (bias_rem) {
+			/* random fill of the remainder */
+			size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+			size = max(size, ps);
+
+			KUNIT_ASSERT_FALSE_MSG(test,
+					       drm_buddy_alloc_blocks(&mm, bias_start,
+								      bias_end, size, ps,
+								      &allocated,
+								      DRM_BUDDY_RANGE_ALLOCATION),
+					       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+					       bias_start, bias_end, size, ps);
+			/*
+			 * Intentionally allow some space to be left
+			 * unallocated, and ideally not always on the bias
+			 * boundaries.
+			 */
+			drm_buddy_free_list(&mm, &tmp);
+		} else {
+			list_splice_tail(&tmp, &allocated);
+		}
+	}
+
+	kfree(order);
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+
+	/*
+	 * Something more free-form. Idea is to pick a random starting bias
+	 * range within the address space and then start filling it up. Also
+	 * randomly grow the bias range in both directions as we go along. This
+	 * should give us bias start/end which is not always uniform like above,
+	 * and in some cases will require the allocator to jump over already
+	 * allocated nodes in the middle of the address space.
+	 */
+
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+			       "buddy_init failed\n");
+
+	bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps);
+	bias_end = round_up(bias_start + prandom_u32_state(&prng) % (mm_size - bias_start), ps);
+	bias_end = max(bias_end, bias_start + ps);
+	bias_rem = bias_end - bias_start;
+
+	do {
+		u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
+
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, bias_start,
+							      bias_end, size, ps,
+							      &allocated,
+							      DRM_BUDDY_RANGE_ALLOCATION),
+				       "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
+				       bias_start, bias_end, size, ps);
+		bias_rem -= size;
+
+		/*
+		 * Try to randomly grow the bias range in both directions, or
+		 * only one, or perhaps don't grow at all.
+		 */
+		do {
+			u32 old_bias_start = bias_start;
+			u32 old_bias_end = bias_end;
+
+			if (bias_start)
+				bias_start -= round_up(prandom_u32_state(&prng) % bias_start, ps);
+			if (bias_end != mm_size)
+				bias_end += round_up(prandom_u32_state(&prng) % (mm_size - bias_end), ps);
+
+			bias_rem += old_bias_start - bias_start;
+			bias_rem += bias_end - old_bias_end;
+		} while (!bias_rem && (bias_start || bias_end != mm_size));
+	} while (bias_rem);
+
+	KUNIT_ASSERT_EQ(test, bias_start, 0);
+	KUNIT_ASSERT_EQ(test, bias_end, mm_size);
+	KUNIT_ASSERT_TRUE_MSG(test,
+			      drm_buddy_alloc_blocks(&mm, bias_start, bias_end,
+						     ps, ps,
+						     &allocated,
+						     DRM_BUDDY_RANGE_ALLOCATION),
+			      "buddy_alloc passed with bias(%x-%x), size=%u\n",
+			      bias_start, bias_end, ps);
+
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+}
+
+static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+{
+	const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K;
+	unsigned long i, n_pages, total;
+	struct drm_buddy_block *block;
+	struct drm_buddy mm;
+	LIST_HEAD(left);
+	LIST_HEAD(middle);
+	LIST_HEAD(right);
+	LIST_HEAD(allocated);
+
+	KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+
+	/*
+	 * Idea is to fragment the address space by alternating block
+	 * allocations between three different lists; one for left, middle and
+	 * right. We can then free a list to simulate fragmentation. In
+	 * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+	 * including the try_harder path.
+	 */
+
+	i = 0;
+	n_pages = mm_size / ps;
+	do {
+		struct list_head *list;
+		int slot = i % 3;
+
+		if (slot == 0)
+			list = &left;
+		else if (slot == 1)
+			list = &middle;
+		else
+			list = &right;
+		KUNIT_ASSERT_FALSE_MSG(test,
+				       drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							      ps, ps, list, 0),
+				       "buddy_alloc hit an error size=%lu\n",
+				       ps);
+	} while (++i < n_pages);
+
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+
+	drm_buddy_free_list(&mm, &middle);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   2 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 2 * ps);
+
+	drm_buddy_free_list(&mm, &right);
+	KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							   3 * ps, ps, &allocated,
+							   DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc didn't error size=%lu\n", 3 * ps);
+	/*
+	 * At this point we should have enough contiguous space for 2 blocks,
+	 * however they are never buddies (since we freed middle and right) so
+	 * will require the try_harder logic to find them.
+	 */
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							    2 * ps, ps, &allocated,
+							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc hit an error size=%lu\n", 2 * ps);
+
+	drm_buddy_free_list(&mm, &left);
+	KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+							    3 * ps, ps, &allocated,
+							    DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+			       "buddy_alloc hit an error size=%lu\n", 3 * ps);
+
+	total = 0;
+	list_for_each_entry(block, &allocated, link)
+		total += drm_buddy_block_size(&mm, block);
+
+	KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
+
+	drm_buddy_free_list(&mm, &allocated);
+	drm_buddy_fini(&mm);
+}
+
 static void drm_test_buddy_alloc_pathological(struct kunit *test)
 {
 	u64 mm_size, size, start = 0;
@@ -275,16 +567,30 @@ static void drm_test_buddy_alloc_limit(struct kunit *test)
 	drm_buddy_fini(&mm);
 }
 
+static int drm_buddy_suite_init(struct kunit_suite *suite)
+{
+	while (!random_seed)
+		random_seed = get_random_u32();
+
+	kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n",
+		   random_seed);
+
+	return 0;
+}
+
 static struct kunit_case drm_buddy_tests[] = {
 	KUNIT_CASE(drm_test_buddy_alloc_limit),
 	KUNIT_CASE(drm_test_buddy_alloc_optimistic),
 	KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
 	KUNIT_CASE(drm_test_buddy_alloc_pathological),
+	KUNIT_CASE(drm_test_buddy_alloc_contiguous),
+	KUNIT_CASE(drm_test_buddy_alloc_range_bias),
 	{}
 };
 
 static struct kunit_suite drm_buddy_test_suite = {
 	.name = "drm_buddy",
+	.suite_init = drm_buddy_suite_init,
 	.test_cases = drm_buddy_tests,
 };
 
diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c
index 1eb0c304f960..f37c0d765865 100644
--- a/drivers/gpu/drm/tests/drm_mm_test.c
+++ b/drivers/gpu/drm/tests/drm_mm_test.c
@@ -157,7 +157,7 @@ static void drm_test_mm_init(struct kunit *test)
 
 	/* After creation, it should all be one massive hole */
 	if (!assert_one_hole(test, &mm, 0, size)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm not one hole on creation");
 		goto out;
 	}
 
@@ -171,14 +171,14 @@ static void drm_test_mm_init(struct kunit *test)
 
 	/* After filling the range entirely, there should be no holes */
 	if (!assert_no_holes(test, &mm)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm has holes when filled");
 		goto out;
 	}
 
 	/* And then after emptying it again, the massive hole should be back */
 	drm_mm_remove_node(&tmp);
 	if (!assert_one_hole(test, &mm, 0, size)) {
-		KUNIT_FAIL(test, "");
+		KUNIT_FAIL(test, "mm does not have single hole after emptying");
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index b62f420a9f96..112438d965ff 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -387,7 +387,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
 				enum ttm_caching caching,
 				pgoff_t start_page, pgoff_t end_page)
 {
-	struct page **pages = tt->pages;
+	struct page **pages = &tt->pages[start_page];
 	unsigned int order;
 	pgoff_t i, nr;
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index f8e9abe647b9..9539aa28937f 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -94,6 +94,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev)
 			goto err_free;
 	}
 
+	dma_set_max_seg_size(dev->dev, dma_max_mapping_size(dev->dev) ?: UINT_MAX);
 	ret = virtio_gpu_init(vdev, dev);
 	if (ret)
 		goto err_free;
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 3062e0e0d467..79ba98a169f9 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -50,8 +50,8 @@
 
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_LEN		(GUC_HXG_REQUEST_MSG_MIN_LEN + 3u)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffff << 16)
-#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffff << 0)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY		(0xffffu << 16)
+#define HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN		(0xffffu << 0)
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32		GUC_HXG_REQUEST_MSG_n_DATAn
 #define HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64		GUC_HXG_REQUEST_MSG_n_DATAn
 
diff --git a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
index 811add10c30d..c165e26c0976 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_slpc_abi.h
@@ -242,8 +242,8 @@ struct slpc_shared_data {
 		(HOST2GUC_PC_SLPC_REQUEST_REQUEST_MSG_MIN_LEN + \
 			HOST2GUC_PC_SLPC_EVENT_MAX_INPUT_ARGS)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_0_MBZ		GUC_HXG_REQUEST_MSG_0_DATA0
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xff << 8)
-#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xff << 0)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ID		(0xffu << 8)
+#define HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC	(0xffu << 0)
 #define HOST2GUC_PC_SLPC_REQUEST_MSG_N_EVENT_DATA_N	GUC_HXG_REQUEST_MSG_n_DATAn
 
 #endif
diff --git a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
index 3b83f907ece4..0b1146d0c997 100644
--- a/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_communication_ctb_abi.h
@@ -82,11 +82,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64);
 #define GUC_CTB_HDR_LEN				1u
 #define GUC_CTB_MSG_MIN_LEN			GUC_CTB_HDR_LEN
 #define GUC_CTB_MSG_MAX_LEN			256u
-#define GUC_CTB_MSG_0_FENCE			(0xffff << 16)
-#define GUC_CTB_MSG_0_FORMAT			(0xf << 12)
+#define GUC_CTB_MSG_0_FENCE			(0xffffu << 16)
+#define GUC_CTB_MSG_0_FORMAT			(0xfu << 12)
 #define   GUC_CTB_FORMAT_HXG			0u
-#define GUC_CTB_MSG_0_RESERVED			(0xf << 8)
-#define GUC_CTB_MSG_0_NUM_DWORDS		(0xff << 0)
+#define GUC_CTB_MSG_0_RESERVED			(0xfu << 8)
+#define GUC_CTB_MSG_0_NUM_DWORDS		(0xffu << 0)
 
 /**
  * DOC: CTB HXG Message
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 47094b9b044c..0400bc0fccdc 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -31,9 +31,9 @@
  */
 
 #define GUC_KLV_LEN_MIN				1u
-#define GUC_KLV_0_KEY				(0xffff << 16)
-#define GUC_KLV_0_LEN				(0xffff << 0)
-#define GUC_KLV_n_VALUE				(0xffffffff << 0)
+#define GUC_KLV_0_KEY				(0xffffu << 16)
+#define GUC_KLV_0_LEN				(0xffffu << 0)
+#define GUC_KLV_n_VALUE				(0xffffffffu << 0)
 
 /**
  * DOC: GuC Self Config KLVs
diff --git a/drivers/gpu/drm/xe/abi/guc_messages_abi.h b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
index 3d199016cf88..29e414c82d56 100644
--- a/drivers/gpu/drm/xe/abi/guc_messages_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_messages_abi.h
@@ -40,18 +40,18 @@
  */
 
 #define GUC_HXG_MSG_MIN_LEN			1u
-#define GUC_HXG_MSG_0_ORIGIN			(0x1 << 31)
+#define GUC_HXG_MSG_0_ORIGIN			(0x1u << 31)
 #define   GUC_HXG_ORIGIN_HOST			0u
 #define   GUC_HXG_ORIGIN_GUC			1u
-#define GUC_HXG_MSG_0_TYPE			(0x7 << 28)
+#define GUC_HXG_MSG_0_TYPE			(0x7u << 28)
 #define   GUC_HXG_TYPE_REQUEST			0u
 #define   GUC_HXG_TYPE_EVENT			1u
 #define   GUC_HXG_TYPE_NO_RESPONSE_BUSY		3u
 #define   GUC_HXG_TYPE_NO_RESPONSE_RETRY	5u
 #define   GUC_HXG_TYPE_RESPONSE_FAILURE		6u
 #define   GUC_HXG_TYPE_RESPONSE_SUCCESS		7u
-#define GUC_HXG_MSG_0_AUX			(0xfffffff << 0)
-#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffff << 0)
+#define GUC_HXG_MSG_0_AUX			(0xfffffffu << 0)
+#define GUC_HXG_MSG_n_PAYLOAD			(0xffffffffu << 0)
 
 /**
  * DOC: HXG Request
@@ -85,8 +85,8 @@
  */
 
 #define GUC_HXG_REQUEST_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_REQUEST_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_REQUEST_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_REQUEST_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -117,8 +117,8 @@
  */
 
 #define GUC_HXG_EVENT_MSG_MIN_LEN		GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfff << 16)
-#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffff << 0)
+#define GUC_HXG_EVENT_MSG_0_DATA0		(0xfffu << 16)
+#define GUC_HXG_EVENT_MSG_0_ACTION		(0xffffu << 0)
 #define GUC_HXG_EVENT_MSG_n_DATAn		GUC_HXG_MSG_n_PAYLOAD
 
 /**
@@ -188,8 +188,8 @@
  */
 
 #define GUC_HXG_FAILURE_MSG_LEN			GUC_HXG_MSG_MIN_LEN
-#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfff << 16)
-#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffff << 0)
+#define GUC_HXG_FAILURE_MSG_0_HINT		(0xfffu << 16)
+#define GUC_HXG_FAILURE_MSG_0_ERROR		(0xffffu << 0)
 
 /**
  * DOC: HXG Response
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 68d9f6116bdf..777c20ceabab 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -10,7 +10,7 @@
 
 #include "xe_bo.h"
 
-#define i915_gem_object_is_shmem(obj) ((obj)->flags & XE_BO_CREATE_SYSTEM_BIT)
+#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */
 
 static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n)
 {
diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c
index a6523df0f1d3..c347e2c29f81 100644
--- a/drivers/gpu/drm/xe/tests/xe_migrate.c
+++ b/drivers/gpu/drm/xe/tests/xe_migrate.c
@@ -114,21 +114,21 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo,
 						   region |
 						   XE_BO_NEEDS_CPU_ACCESS);
 	if (IS_ERR(remote)) {
-		KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %li\n",
-			   str, PTR_ERR(remote));
+		KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %pe\n",
+			   str, remote);
 		return;
 	}
 
 	err = xe_bo_validate(remote, NULL, false);
 	if (err) {
-		KUNIT_FAIL(test, "Failed to validate system bo for %s: %li\n",
+		KUNIT_FAIL(test, "Failed to validate system bo for %s: %i\n",
 			   str, err);
 		goto out_unlock;
 	}
 
 	err = xe_bo_vmap(remote);
 	if (err) {
-		KUNIT_FAIL(test, "Failed to vmap system bo for %s: %li\n",
+		KUNIT_FAIL(test, "Failed to vmap system bo for %s: %i\n",
 			   str, err);
 		goto out_unlock;
 	}
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs_test.c b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
index ef56bd517b28..421b819fd4ba 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs_test.c
@@ -21,4 +21,5 @@ kunit_test_suite(xe_mocs_test_suite);
 
 MODULE_AUTHOR("Intel Corporation");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("xe_mocs kunit test");
 MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING);
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 0b0e262e2166..4d3b80ec906d 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -28,6 +28,14 @@
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
 
+const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
+	[XE_PL_SYSTEM] = "system",
+	[XE_PL_TT] = "gtt",
+	[XE_PL_VRAM0] = "vram0",
+	[XE_PL_VRAM1] = "vram1",
+	[XE_PL_STOLEN] = "stolen"
+};
+
 static const struct ttm_place sys_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
@@ -713,8 +721,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		migrate = xe->tiles[0].migrate;
 
 	xe_assert(xe, migrate);
-
-	trace_xe_bo_move(bo);
+	trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source);
 	xe_device_mem_access_get(xe);
 
 	if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) {
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 9b1279aca127..8be42ac6cd07 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -243,6 +243,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo);
 int xe_bo_restore_pinned(struct xe_bo *bo);
 
 extern struct ttm_device_funcs xe_ttm_funcs;
+extern const char *const xe_mem_type_to_name[];
 
 int xe_gem_create_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 1f0b4b9ce84f..5176c27e4b6a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -83,9 +83,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 }
 
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef);
-
 static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -102,8 +99,6 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 	mutex_unlock(&xef->exec_queue.lock);
 	xa_destroy(&xef->exec_queue.xa);
 	mutex_destroy(&xef->exec_queue.lock);
-	device_kill_persistent_exec_queues(xe, xef);
-
 	mutex_lock(&xef->vm.lock);
 	xa_for_each(&xef->vm.xa, idx, vm)
 		xe_vm_close_and_put(vm);
@@ -255,9 +250,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 			xa_erase(&xe->usm.asid_to_vm, asid);
 	}
 
-	drmm_mutex_init(&xe->drm, &xe->persistent_engines.lock);
-	INIT_LIST_HEAD(&xe->persistent_engines.list);
-
 	spin_lock_init(&xe->pinned.lock);
 	INIT_LIST_HEAD(&xe->pinned.kernel_bo_present);
 	INIT_LIST_HEAD(&xe->pinned.external_vram);
@@ -570,37 +562,6 @@ void xe_device_shutdown(struct xe_device *xe)
 {
 }
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	list_add_tail(&q->persistent.link, &xe->persistent_engines.list);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q)
-{
-	mutex_lock(&xe->persistent_engines.lock);
-	if (!list_empty(&q->persistent.link))
-		list_del(&q->persistent.link);
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
-static void device_kill_persistent_exec_queues(struct xe_device *xe,
-					       struct xe_file *xef)
-{
-	struct xe_exec_queue *q, *next;
-
-	mutex_lock(&xe->persistent_engines.lock);
-	list_for_each_entry_safe(q, next, &xe->persistent_engines.list,
-				 persistent.link)
-		if (q->persistent.xef == xef) {
-			xe_exec_queue_kill(q);
-			list_del_init(&q->persistent.link);
-		}
-	mutex_unlock(&xe->persistent_engines.lock);
-}
-
 void xe_device_wmb(struct xe_device *xe)
 {
 	struct xe_gt *gt = xe_root_mmio_gt(xe);
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 3da83b233206..08d8b72c7731 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -42,10 +42,6 @@ int xe_device_probe(struct xe_device *xe);
 void xe_device_remove(struct xe_device *xe);
 void xe_device_shutdown(struct xe_device *xe);
 
-void xe_device_add_persistent_exec_queues(struct xe_device *xe, struct xe_exec_queue *q);
-void xe_device_remove_persistent_exec_queues(struct xe_device *xe,
-					     struct xe_exec_queue *q);
-
 void xe_device_wmb(struct xe_device *xe);
 
 static inline struct xe_file *to_xe_file(const struct drm_file *file)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 5dc9127a2029..e8491979a6f2 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -341,14 +341,6 @@ struct xe_device {
 		struct mutex lock;
 	} usm;
 
-	/** @persistent_engines: engines that are closed but still running */
-	struct {
-		/** @lock: protects persistent engines */
-		struct mutex lock;
-		/** @list: list of persistent engines */
-		struct list_head list;
-	} persistent_engines;
-
 	/** @pinned: pinned BO state */
 	struct {
 		/** @lock: protected pinned BO list state */
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae..e4db069f0db3 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
 
 int xe_display_init_nommio(struct xe_device *xe)
 {
-	int err;
-
 	if (!xe->info.enable_display)
 		return 0;
 
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(xe);
 
-	err = intel_power_domains_init(xe);
-	if (err)
-		return err;
-
 	return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 82d1305e831f..6040e4d22b28 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -131,14 +131,6 @@ static void bo_meminfo(struct xe_bo *bo,
 
 static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 {
-	static const char *const mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
-		[XE_PL_SYSTEM] = "system",
-		[XE_PL_TT] = "gtt",
-		[XE_PL_VRAM0] = "vram0",
-		[XE_PL_VRAM1] = "vram1",
-		[4 ... 6] = NULL,
-		[XE_PL_STOLEN] = "stolen"
-	};
 	struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {};
 	struct xe_file *xef = file->driver_priv;
 	struct ttm_device *bdev = &xef->xe->ttm;
@@ -171,7 +163,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 	spin_unlock(&client->bos_lock);
 
 	for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {
-		if (!mem_type_to_name[mem_type])
+		if (!xe_mem_type_to_name[mem_type])
 			continue;
 
 		man = ttm_manager_type(bdev, mem_type);
@@ -182,7 +174,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
 					       DRM_GEM_OBJECT_RESIDENT |
 					       (mem_type != XE_PL_SYSTEM ? 0 :
 					       DRM_GEM_OBJECT_PURGEABLE),
-					       mem_type_to_name[mem_type]);
+					       xe_mem_type_to_name[mem_type]);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index b853feed9ccc..17f26952e665 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -111,7 +111,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
 	struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
 	struct drm_exec *exec = &vm_exec.exec;
-	u32 i, num_syncs = 0;
+	u32 i, num_syncs = 0, num_ufence = 0;
 	struct xe_sched_job *job;
 	struct dma_fence *rebind_fence;
 	struct xe_vm *vm;
@@ -157,6 +157,14 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_LR_MODE : 0));
 		if (err)
 			goto err_syncs;
+
+		if (xe_sync_is_ufence(&syncs[i]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto err_syncs;
 	}
 
 	if (xe_exec_queue_is_parallel(q)) {
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c5..49223026c89f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -60,7 +60,6 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe,
 	q->fence_irq = &gt->fence_irq[hwe->class];
 	q->ring_ops = gt->ring_ops[hwe->class];
 	q->ops = gt->exec_queue_ops;
-	INIT_LIST_HEAD(&q->persistent.link);
 	INIT_LIST_HEAD(&q->compute.link);
 	INIT_LIST_HEAD(&q->multi_gt_link);
 
@@ -310,102 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue *
 	return q->ops->set_timeslice(q, value);
 }
 
-static int exec_queue_set_preemption_timeout(struct xe_device *xe,
-					     struct xe_exec_queue *q, u64 value,
-					     bool create)
-{
-	u32 min = 0, max = 0;
-
-	xe_exec_queue_get_prop_minmax(q->hwe->eclass,
-				      XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max);
-
-	if (xe_exec_queue_enforce_schedule_limit() &&
-	    !xe_hw_engine_timeout_in_range(value, min, max))
-		return -EINVAL;
-
-	return q->ops->set_preempt_timeout(q, value);
-}
-
-static int exec_queue_set_persistence(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, xe_vm_in_preempt_fence_mode(q->vm)))
-		return -EINVAL;
-
-	if (value)
-		q->flags |= EXEC_QUEUE_FLAG_PERSISTENT;
-	else
-		q->flags &= ~EXEC_QUEUE_FLAG_PERSISTENT;
-
-	return 0;
-}
-
-static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	u32 min = 0, max = 0;
-
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	xe_exec_queue_get_prop_minmax(q->hwe->eclass,
-				      XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max);
-
-	if (xe_exec_queue_enforce_schedule_limit() &&
-	    !xe_hw_engine_timeout_in_range(value, min, max))
-		return -EINVAL;
-
-	return q->ops->set_job_timeout(q, value);
-}
-
-static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q,
-				      u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	q->usm.acc_trigger = value;
-
-	return 0;
-}
-
-static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q,
-				     u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	q->usm.acc_notify = value;
-
-	return 0;
-}
-
-static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q,
-					  u64 value, bool create)
-{
-	if (XE_IOCTL_DBG(xe, !create))
-		return -EINVAL;
-
-	if (XE_IOCTL_DBG(xe, !xe->info.has_usm))
-		return -EINVAL;
-
-	if (value > DRM_XE_ACC_GRANULARITY_64M)
-		return -EINVAL;
-
-	q->usm.acc_granularity = value;
-
-	return 0;
-}
-
 typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
 					     struct xe_exec_queue *q,
 					     u64 value, bool create);
@@ -413,12 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe,
 static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = {
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority,
 	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE] = exec_queue_set_persistence,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify,
-	[DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity,
 };
 
 static int exec_queue_user_ext_set_property(struct xe_device *xe,
@@ -437,10 +334,15 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe,
 
 	if (XE_IOCTL_DBG(xe, ext.property >=
 			 ARRAY_SIZE(exec_queue_set_property_funcs)) ||
-	    XE_IOCTL_DBG(xe, ext.pad))
+	    XE_IOCTL_DBG(xe, ext.pad) ||
+	    XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY &&
+			 ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE))
 		return -EINVAL;
 
 	idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs));
+	if (!exec_queue_set_property_funcs[idx])
+		return -EINVAL;
+
 	return exec_queue_set_property_funcs[idx](xe, q, ext.value,  create);
 }
 
@@ -704,9 +606,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		}
 
 		q = xe_exec_queue_create(xe, vm, logical_mask,
-					 args->width, hwe,
-					 xe_vm_in_lr_mode(vm) ? 0 :
-					 EXEC_QUEUE_FLAG_PERSISTENT);
+					 args->width, hwe, 0);
 		up_read(&vm->lock);
 		xe_vm_put(vm);
 		if (IS_ERR(q))
@@ -728,8 +628,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 			goto kill_exec_queue;
 	}
 
-	q->persistent.xef = xef;
-
 	mutex_lock(&xef->exec_queue.lock);
 	err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xef->exec_queue.lock);
@@ -872,10 +770,7 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 	if (XE_IOCTL_DBG(xe, !q))
 		return -ENOENT;
 
-	if (!(q->flags & EXEC_QUEUE_FLAG_PERSISTENT))
-		xe_exec_queue_kill(q);
-	else
-		xe_device_add_persistent_exec_queues(xe, q);
+	xe_exec_queue_kill(q);
 
 	trace_xe_exec_queue_close(q);
 	xe_exec_queue_put(q);
@@ -926,20 +821,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
  * @q: The exec queue
  * @vm: The VM the engine does a bind or exec for
  *
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
  *
  * Returns: last fence if not signaled, dma fence stub if signaled
  */
 struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
 					       struct xe_vm *vm)
 {
+	struct dma_fence *fence;
+
 	xe_exec_queue_last_fence_lockdep_assert(q, vm);
 
 	if (q->last_fence &&
 	    test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
 		xe_exec_queue_last_fence_put(q, vm);
 
-	return q->last_fence ? q->last_fence : dma_fence_get_stub();
+	fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+	dma_fence_get(fence);
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 8d4b7feb8c30..36f4901d8d7e 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -105,16 +105,6 @@ struct xe_exec_queue {
 		struct xe_guc_exec_queue *guc;
 	};
 
-	/**
-	 * @persistent: persistent exec queue state
-	 */
-	struct {
-		/** @xef: file which this exec queue belongs to */
-		struct xe_file *xef;
-		/** @link: link in list of persistent exec queues */
-		struct list_head link;
-	} persistent;
-
 	union {
 		/**
 		 * @parallel: parallel submission state
@@ -160,16 +150,6 @@ struct xe_exec_queue {
 		spinlock_t lock;
 	} compute;
 
-	/** @usm: unified shared memory state */
-	struct {
-		/** @acc_trigger: access counter trigger */
-		u32 acc_trigger;
-		/** @acc_notify: access counter notify */
-		u32 acc_notify;
-		/** @acc_granularity: access counter granularity */
-		u32 acc_granularity;
-	} usm;
-
 	/** @ops: submission backend exec queue operations */
 	const struct xe_exec_queue_ops *ops;
 
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 96b5224eb478..acb4d9f38fd7 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -212,7 +212,7 @@ static void xe_execlist_port_wake_locked(struct xe_execlist_port *port,
 static void xe_execlist_make_active(struct xe_execlist_exec_queue *exl)
 {
 	struct xe_execlist_port *port = exl->port;
-	enum xe_exec_queue_priority priority = exl->active_priority;
+	enum xe_exec_queue_priority priority = exl->q->sched_props.priority;
 
 	XE_WARN_ON(priority == XE_EXEC_QUEUE_PRIORITY_UNSET);
 	XE_WARN_ON(priority < 0);
@@ -378,8 +378,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w)
 		list_del(&exl->active_link);
 	spin_unlock_irqrestore(&exl->port->lock, flags);
 
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(xe, q);
 	drm_sched_entity_fini(&exl->entity);
 	drm_sched_fini(&exl->sched);
 	kfree(exl);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec1295..35474ddbaf97 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 		 * USM has its only SA pool to non-block behind user operations
 		 */
 		if (gt_to_xe(gt)->info.has_usm) {
-			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+			struct xe_device *xe = gt_to_xe(gt);
+
+			gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+								IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
 			if (IS_ERR(gt->usm.bb_pool)) {
 				err = PTR_ERR(gt->usm.bb_pool);
 				goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 9358f7336889..9fcae65b6469 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -145,10 +145,10 @@ void xe_gt_idle_sysfs_init(struct xe_gt_idle *gtidle)
 	}
 
 	if (xe_gt_is_media_type(gt)) {
-		sprintf(gtidle->name, "gt%d-mc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-mc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_mc6_residency;
 	} else {
-		sprintf(gtidle->name, "gt%d-rc\n", gt->info.id);
+		sprintf(gtidle->name, "gt%d-rc", gt->info.id);
 		gtidle->idle_residency = xe_guc_pc_rc6_residency;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 77925b35cf8d..8546cd3cc50d 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -480,7 +480,7 @@ static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
  * to synchronize with external clients (e.g., firmware), so a semaphore
  * register will also need to be taken.
  */
-static void mcr_lock(struct xe_gt *gt)
+static void mcr_lock(struct xe_gt *gt) __acquires(&gt->mcr_lock)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int ret = 0;
@@ -500,7 +500,7 @@ static void mcr_lock(struct xe_gt *gt)
 	drm_WARN_ON_ONCE(&xe->drm, ret == -ETIMEDOUT);
 }
 
-static void mcr_unlock(struct xe_gt *gt)
+static void mcr_unlock(struct xe_gt *gt) __releases(&gt->mcr_lock)
 {
 	/* Release hardware semaphore - this is done by writing 1 to the register */
 	if (GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 59a70d2e0a7a..73f08f1924df 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -165,7 +165,8 @@ retry_userptr:
 		goto unlock_vm;
 	}
 
-	if (!xe_vma_is_userptr(vma) || !xe_vma_userptr_check_repin(vma)) {
+	if (!xe_vma_is_userptr(vma) ||
+	    !xe_vma_userptr_check_repin(to_userptr_vma(vma))) {
 		downgrade_write(&vm->lock);
 		write_locked = false;
 	}
@@ -181,11 +182,13 @@ retry_userptr:
 	/* TODO: Validate fault */
 
 	if (xe_vma_is_userptr(vma) && write_locked) {
+		struct xe_userptr_vma *uvma = to_userptr_vma(vma);
+
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del_init(&vma->userptr.invalidate_link);
+		list_del_init(&uvma->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 
-		ret = xe_vma_userptr_pin_pages(vma);
+		ret = xe_vma_userptr_pin_pages(uvma);
 		if (ret)
 			goto unlock_vm;
 
@@ -220,7 +223,7 @@ retry_userptr:
 	dma_fence_put(fence);
 
 	if (xe_vma_is_userptr(vma))
-		ret = xe_vma_userptr_check_repin(vma);
+		ret = xe_vma_userptr_check_repin(to_userptr_vma(vma));
 	vma->usm.tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
@@ -332,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		return -EPROTO;
 
 	asid = FIELD_GET(PFD_ASID, msg[1]);
-	pf_queue = &gt->usm.pf_queue[asid % NUM_PF_QUEUE];
+	pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
 
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 7eef23a00d77..f4c485289dbe 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -247,6 +247,14 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
 
 	xe_gt_assert(gt, vma);
 
+	/* Execlists not supported */
+	if (gt_to_xe(gt)->info.force_execlist) {
+		if (fence)
+			__invalidation_fence_signal(fence);
+
+		return 0;
+	}
+
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
 	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
 	if (!xe->info.has_range_tlb_invalidation) {
@@ -317,6 +325,10 @@ int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno)
 	struct drm_printer p = drm_err_printer(__func__);
 	int ret;
 
+	/* Execlists not supported */
+	if (gt_to_xe(gt)->info.force_execlist)
+		return 0;
+
 	/*
 	 * XXX: See above, this algorithm only works if seqno are always in
 	 * order
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index f71085228cb3..d91702592520 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -963,7 +963,9 @@ void xe_guc_pc_fini(struct xe_guc_pc *pc)
 	struct xe_device *xe = pc_to_xe(pc);
 
 	if (xe->info.skip_guc_pc) {
+		xe_device_mem_access_get(xe);
 		xe_gt_idle_disable_c6(pc_to_gt(pc));
+		xe_device_mem_access_put(xe);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 54ffcfcdd41f..f22ae717b0b2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1028,8 +1028,6 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
-	if (q->flags & EXEC_QUEUE_FLAG_PERSISTENT)
-		xe_device_remove_persistent_exec_queues(gt_to_xe(q->gt), q);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
index a6094c81f2ad..a5de3e7b0bd6 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@@ -217,13 +217,13 @@ struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
-	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
-		       ctx->dma_fence_ctx, ctx->next_seqno++);
-
 	fence->ctx = ctx;
 	fence->seqno_map = seqno_map;
 	INIT_LIST_HEAD(&fence->irq_link);
 
+	dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
+		       ctx->dma_fence_ctx, ctx->next_seqno++);
+
 	trace_xe_hw_fence_create(fence);
 
 	return fence;
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b7fa3831b684..b38319d2801e 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -21,10 +21,10 @@
 #include "xe_map.h"
 #include "xe_vm.h"
 
-#define CTX_VALID				(1 << 0)
-#define CTX_PRIVILEGE				(1 << 8)
-#define CTX_ADDRESSING_MODE_SHIFT		3
-#define LEGACY_64B_CONTEXT			3
+#define LRC_VALID				(1 << 0)
+#define LRC_PRIVILEGE				(1 << 8)
+#define LRC_ADDRESSING_MODE_SHIFT		3
+#define LRC_LEGACY_64B_CONTEXT			3
 
 #define ENGINE_CLASS_SHIFT			61
 #define ENGINE_INSTANCE_SHIFT			48
@@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
 
 #define PVC_CTX_ASID		(0x2e + 1)
 #define PVC_CTX_ACC_CTR_THOLD	(0x2a + 1)
-#define ACC_GRANULARITY_S       20
-#define ACC_NOTIFY_S            16
 
 int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 		struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size)
@@ -754,23 +752,17 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL,
 			     RING_CTL_SIZE(lrc->ring.size) | RING_VALID);
 	if (xe->info.has_asid && vm)
-		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID,
-				     (q->usm.acc_granularity <<
-				      ACC_GRANULARITY_S) | vm->usm.asid);
-	if (xe->info.has_usm && vm)
-		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD,
-				     (q->usm.acc_notify << ACC_NOTIFY_S) |
-				     q->usm.acc_trigger);
-
-	lrc->desc = CTX_VALID;
-	lrc->desc |= LEGACY_64B_CONTEXT << CTX_ADDRESSING_MODE_SHIFT;
+		xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid);
+
+	lrc->desc = LRC_VALID;
+	lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT;
 	/* TODO: Priority */
 
 	/* While this appears to have something about privileged batches or
 	 * some such, it really just means PPGTT mode.
 	 */
 	if (vm)
-		lrc->desc |= CTX_PRIVILEGE;
+		lrc->desc |= LRC_PRIVILEGE;
 
 	if (GRAPHICS_VERx100(xe) < 1250) {
 		lrc->desc |= (u64)hwe->instance << ENGINE_INSTANCE_SHIFT;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c54624252..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	if (!IS_DGFX(xe)) {
 		/* Write out batch too */
 		m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
-		if (xe->info.has_usm) {
-			batch = tile->primary_gt->usm.bb_pool->bo;
-			m->usm_batch_base_ofs = m->batch_base_ofs;
-		}
-
 		for (i = 0; i < batch->size;
 		     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
 		     XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  entry);
 			level++;
 		}
+		if (xe->info.has_usm) {
+			xe_tile_assert(tile, batch->size == SZ_1M);
+
+			batch = tile->primary_gt->usm.bb_pool->bo;
+			m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+			xe_tile_assert(tile, batch->size == SZ_512K);
+
+			for (i = 0; i < batch->size;
+			     i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+			     XE_PAGE_SIZE) {
+				entry = vm->pt_ops->pte_encode_bo(batch, i,
+								  pat_index, 0);
+
+				xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+					  entry);
+				level++;
+			}
+		}
 	} else {
 		u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
 
@@ -1204,8 +1217,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
 	}
 	if (q) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			dma_fence_put(fence);
 			return false;
+		}
+		dma_fence_put(fence);
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index 5f6b53ea5528..02f7808f28ca 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -105,7 +105,7 @@ static void xe_resize_vram_bar(struct xe_device *xe)
 
 	pci_bus_for_each_resource(root, root_res, i) {
 		if (root_res && root_res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) &&
-		    root_res->start > 0x100000000ull)
+		    (u64)root_res->start > 0x100000000ul)
 			break;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index de1030a47588..6653c045f3c9 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -20,8 +20,8 @@
 
 struct xe_pt_dir {
 	struct xe_pt pt;
-	/** @dir: Directory structure for the xe_pt_walk functionality */
-	struct xe_ptw_dir dir;
+	/** @children: Array of page-table child nodes */
+	struct xe_ptw *children[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -44,7 +44,7 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 
 static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->dir.entries[index], struct xe_pt, base);
+	return container_of(pt_dir->children[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -65,6 +65,14 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
 		XE_PTE_NULL;
 }
 
+static void xe_pt_free(struct xe_pt *pt)
+{
+	if (pt->level)
+		kfree(as_xe_pt_dir(pt));
+	else
+		kfree(pt);
+}
+
 /**
  * xe_pt_create() - Create a page-table.
  * @vm: The vm to create for.
@@ -85,15 +93,19 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 {
 	struct xe_pt *pt;
 	struct xe_bo *bo;
-	size_t size;
 	int err;
 
-	size = !level ?  sizeof(struct xe_pt) : sizeof(struct xe_pt_dir) +
-		XE_PDES * sizeof(struct xe_ptw *);
-	pt = kzalloc(size, GFP_KERNEL);
+	if (level) {
+		struct xe_pt_dir *dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+
+		pt = (dir) ? &dir->pt : NULL;
+	} else {
+		pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+	}
 	if (!pt)
 		return ERR_PTR(-ENOMEM);
 
+	pt->level = level;
 	bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K,
 				  ttm_bo_type_kernel,
 				  XE_BO_CREATE_VRAM_IF_DGFX(tile) |
@@ -106,8 +118,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 		goto err_kfree;
 	}
 	pt->bo = bo;
-	pt->level = level;
-	pt->base.dir = level ? &as_xe_pt_dir(pt)->dir : NULL;
+	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -116,7 +127,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	return pt;
 
 err_kfree:
-	kfree(pt);
+	xe_pt_free(pt);
 	return ERR_PTR(err);
 }
 
@@ -193,7 +204,7 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 					      deferred);
 		}
 	}
-	kfree(pt);
+	xe_pt_free(pt);
 }
 
 /**
@@ -358,7 +369,7 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		struct iosys_map *map = &parent->bo->vmap;
 
 		if (unlikely(xe_child))
-			parent->base.dir->entries[offset] = &xe_child->base;
+			parent->base.children[offset] = &xe_child->base;
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -488,10 +499,12 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		 * this device *requires* 64K PTE size for VRAM, fail.
 		 */
 		if (level == 0 && !xe_parent->is_compact) {
-			if (xe_pt_is_pte_ps64K(addr, next, xe_walk))
+			if (xe_pt_is_pte_ps64K(addr, next, xe_walk)) {
+				xe_walk->vma->gpuva.flags |= XE_VMA_PTE_64K;
 				pte |= XE_PTE_PS64;
-			else if (XE_WARN_ON(xe_walk->needs_64K))
+			} else if (XE_WARN_ON(xe_walk->needs_64K)) {
 				return -EINVAL;
+			}
 		}
 
 		ret = xe_pt_insert_entry(xe_walk, xe_parent, offset, NULL, pte);
@@ -534,13 +547,16 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 		*child = &xe_child->base;
 
 		/*
-		 * Prefer the compact pagetable layout for L0 if possible.
+		 * Prefer the compact pagetable layout for L0 if possible. Only
+		 * possible if VMA covers entire 2MB region as compact 64k and
+		 * 4k pages cannot be mixed within a 2MB region.
 		 * TODO: Suballocate the pt bo to avoid wasting a lot of
 		 * memory.
 		 */
 		if (GRAPHICS_VERx100(tile_to_xe(xe_walk->tile)) >= 1250 && level == 1 &&
 		    covers && xe_pt_scan_64K(addr, next, xe_walk)) {
 			walk->shifts = xe_compact_pt_shifts;
+			xe_walk->vma->gpuva.flags |= XE_VMA_PTE_COMPACT;
 			flags |= XE_PDE_64K;
 			xe_child->is_compact = true;
 		}
@@ -618,8 +634,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 
 	if (!xe_vma_is_null(vma)) {
 		if (xe_vma_is_userptr(vma))
-			xe_res_first_sg(vma->userptr.sg, 0, xe_vma_size(vma),
-					&curs);
+			xe_res_first_sg(to_userptr_vma(vma)->userptr.sg, 0,
+					xe_vma_size(vma), &curs);
 		else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo))
 			xe_res_first(bo->ttm.resource, xe_vma_bo_offset(vma),
 				     xe_vma_size(vma), &curs);
@@ -853,7 +869,7 @@ static void xe_pt_commit_bind(struct xe_vma *vma,
 				xe_pt_destroy(xe_pt_entry(pt_dir, j_),
 					      xe_vma_vm(vma)->flags, deferred);
 
-			pt_dir->dir.entries[j_] = &newpte->base;
+			pt_dir->children[j_] = &newpte->base;
 		}
 		kfree(entries[i].pt_entries);
 	}
@@ -906,17 +922,17 @@ static void xe_vm_dbg_print_entries(struct xe_device *xe,
 
 #ifdef CONFIG_DRM_XE_USERPTR_INVAL_INJECT
 
-static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static int xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
-	u32 divisor = vma->userptr.divisor ? vma->userptr.divisor : 2;
+	u32 divisor = uvma->userptr.divisor ? uvma->userptr.divisor : 2;
 	static u32 count;
 
 	if (count++ % divisor == divisor - 1) {
-		struct xe_vm *vm = xe_vma_vm(vma);
+		struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 
-		vma->userptr.divisor = divisor << 1;
+		uvma->userptr.divisor = divisor << 1;
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&uvma->userptr.invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 		return true;
@@ -927,7 +943,7 @@ static int xe_pt_userptr_inject_eagain(struct xe_vma *vma)
 
 #else
 
-static bool xe_pt_userptr_inject_eagain(struct xe_vma *vma)
+static bool xe_pt_userptr_inject_eagain(struct xe_userptr_vma *uvma)
 {
 	return false;
 }
@@ -1000,9 +1016,9 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 {
 	struct xe_pt_migrate_pt_update *userptr_update =
 		container_of(pt_update, typeof(*userptr_update), base);
-	struct xe_vma *vma = pt_update->vma;
-	unsigned long notifier_seq = vma->userptr.notifier_seq;
-	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_userptr_vma *uvma = to_userptr_vma(pt_update->vma);
+	unsigned long notifier_seq = uvma->userptr.notifier_seq;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
 	int err = xe_pt_vm_dependencies(pt_update->job,
 					&vm->rftree[pt_update->tile_id],
 					pt_update->start,
@@ -1023,7 +1039,7 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 	 */
 	do {
 		down_read(&vm->userptr.notifier_lock);
-		if (!mmu_interval_read_retry(&vma->userptr.notifier,
+		if (!mmu_interval_read_retry(&uvma->userptr.notifier,
 					     notifier_seq))
 			break;
 
@@ -1032,11 +1048,11 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
 		if (userptr_update->bind)
 			return -EAGAIN;
 
-		notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
+		notifier_seq = mmu_interval_read_begin(&uvma->userptr.notifier);
 	} while (true);
 
 	/* Inject errors to test_whether they are handled correctly */
-	if (userptr_update->bind && xe_pt_userptr_inject_eagain(vma)) {
+	if (userptr_update->bind && xe_pt_userptr_inject_eagain(uvma)) {
 		up_read(&vm->userptr.notifier_lock);
 		return -EAGAIN;
 	}
@@ -1297,7 +1313,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
 		vma->tile_present |= BIT(tile->id);
 
 		if (bind_pt_update.locked) {
-			vma->userptr.initial_bind = true;
+			to_userptr_vma(vma)->userptr.initial_bind = true;
 			up_read(&vm->userptr.notifier_lock);
 			xe_bo_put_commit(&deferred);
 		}
@@ -1507,7 +1523,7 @@ xe_pt_commit_unbind(struct xe_vma *vma,
 					xe_pt_destroy(xe_pt_entry(pt_dir, i),
 						      xe_vma_vm(vma)->flags, deferred);
 
-				pt_dir->dir.entries[i] = NULL;
+				pt_dir->children[i] = NULL;
 			}
 		}
 	}
@@ -1642,7 +1658,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
 
 		if (!vma->tile_present) {
 			spin_lock(&vm->userptr.invalidated_lock);
-			list_del_init(&vma->userptr.invalidate_link);
+			list_del_init(&to_userptr_vma(vma)->userptr.invalidate_link);
 			spin_unlock(&vm->userptr.invalidated_lock);
 		}
 		up_read(&vm->userptr.notifier_lock);
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index 8f6c8d063f39..b8b3d2aea492 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,7 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->dir ? parent->dir->entries : NULL;
+	struct xe_ptw **entries = parent->children ? parent->children : NULL;
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index ec3d1e9efa6d..5ecc4d2f0f65 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -8,28 +8,15 @@
 #include <linux/pagewalk.h>
 #include <linux/types.h>
 
-struct xe_ptw_dir;
-
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
- * @dir: Pointer to an array of children if any.
+ * @children: Pointer to an array of children if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
- * embed the xe_ptw_dir::entries array in the same allocation.
+ * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
-	struct xe_ptw_dir *dir;
-};
-
-/**
- * struct xe_ptw_dir - page directory structure
- * @entries: Array holding page directory children.
- *
- * It is the responsibility of the user to ensure @entries is
- * correctly sized.
- */
-struct xe_ptw_dir {
-	struct xe_ptw *entries[0];
+	struct xe_ptw **children;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 9b35673b286c..7e924faeeea0 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -459,21 +459,21 @@ static size_t calc_topo_query_size(struct xe_device *xe)
 		 sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss));
 }
 
-static void __user *copy_mask(void __user *ptr,
-			      struct drm_xe_query_topology_mask *topo,
-			      void *mask, size_t mask_size)
+static int copy_mask(void __user **ptr,
+		     struct drm_xe_query_topology_mask *topo,
+		     void *mask, size_t mask_size)
 {
 	topo->num_bytes = mask_size;
 
-	if (copy_to_user(ptr, topo, sizeof(*topo)))
-		return ERR_PTR(-EFAULT);
-	ptr += sizeof(topo);
+	if (copy_to_user(*ptr, topo, sizeof(*topo)))
+		return -EFAULT;
+	*ptr += sizeof(topo);
 
-	if (copy_to_user(ptr, mask, mask_size))
-		return ERR_PTR(-EFAULT);
-	ptr += mask_size;
+	if (copy_to_user(*ptr, mask, mask_size))
+		return -EFAULT;
+	*ptr += mask_size;
 
-	return ptr;
+	return 0;
 }
 
 static int query_gt_topology(struct xe_device *xe,
@@ -493,28 +493,28 @@ static int query_gt_topology(struct xe_device *xe,
 	}
 
 	for_each_gt(gt, xe, id) {
+		int err;
+
 		topo.gt_id = id;
 
 		topo.type = DRM_XE_TOPO_DSS_GEOMETRY;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.g_dss_mask,
-				      sizeof(gt->fuse_topo.g_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.g_dss_mask,
+				sizeof(gt->fuse_topo.g_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_DSS_COMPUTE;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.c_dss_mask,
-				      sizeof(gt->fuse_topo.c_dss_mask));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.c_dss_mask,
+				sizeof(gt->fuse_topo.c_dss_mask));
+		if (err)
+			return err;
 
 		topo.type = DRM_XE_TOPO_EU_PER_DSS;
-		query_ptr = copy_mask(query_ptr, &topo,
-				      gt->fuse_topo.eu_mask_per_dss,
-				      sizeof(gt->fuse_topo.eu_mask_per_dss));
-		if (IS_ERR(query_ptr))
-			return PTR_ERR(query_ptr);
+		err = copy_mask(&query_ptr, &topo,
+				gt->fuse_topo.eu_mask_per_dss,
+				sizeof(gt->fuse_topo.eu_mask_per_dss));
+		if (err)
+			return err;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index d35d9ec58e86..372378e89e98 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -151,6 +151,11 @@ xe_range_fence_tree_next(struct xe_range_fence *rfence, u64 start, u64 last)
 	return xe_range_fence_tree_iter_next(rfence, start, last);
 }
 
+static void xe_range_fence_free(struct xe_range_fence *rfence)
+{
+	kfree(rfence);
+}
+
 const struct xe_range_fence_ops xe_range_fence_kfree_ops = {
-	.free = (void (*)(struct xe_range_fence *rfence)) kfree,
+	.free = xe_range_fence_free,
 };
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad..4e2ccad0e52f 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
 	struct dma_fence *fence;
 
 	fence = xe_exec_queue_last_fence_get(job->q, vm);
-	dma_fence_get(fence);
 
 	return drm_sched_job_add_dependency(&job->drm, fence);
 }
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115..02c9577fe418 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -19,7 +19,7 @@
 #include "xe_macros.h"
 #include "xe_sched_job_types.h"
 
-struct user_fence {
+struct xe_user_fence {
 	struct xe_device *xe;
 	struct kref refcount;
 	struct dma_fence_cb cb;
@@ -27,31 +27,32 @@ struct user_fence {
 	struct mm_struct *mm;
 	u64 __user *addr;
 	u64 value;
+	int signalled;
 };
 
 static void user_fence_destroy(struct kref *kref)
 {
-	struct user_fence *ufence = container_of(kref, struct user_fence,
+	struct xe_user_fence *ufence = container_of(kref, struct xe_user_fence,
 						 refcount);
 
 	mmdrop(ufence->mm);
 	kfree(ufence);
 }
 
-static void user_fence_get(struct user_fence *ufence)
+static void user_fence_get(struct xe_user_fence *ufence)
 {
 	kref_get(&ufence->refcount);
 }
 
-static void user_fence_put(struct user_fence *ufence)
+static void user_fence_put(struct xe_user_fence *ufence)
 {
 	kref_put(&ufence->refcount, user_fence_destroy);
 }
 
-static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
-					    u64 value)
+static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr,
+					       u64 value)
 {
-	struct user_fence *ufence;
+	struct xe_user_fence *ufence;
 
 	ufence = kmalloc(sizeof(*ufence), GFP_KERNEL);
 	if (!ufence)
@@ -69,7 +70,7 @@ static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr,
 
 static void user_fence_worker(struct work_struct *w)
 {
-	struct user_fence *ufence = container_of(w, struct user_fence, worker);
+	struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
 
 	if (mmget_not_zero(ufence->mm)) {
 		kthread_use_mm(ufence->mm);
@@ -80,10 +81,11 @@ static void user_fence_worker(struct work_struct *w)
 	}
 
 	wake_up_all(&ufence->xe->ufence_wq);
+	WRITE_ONCE(ufence->signalled, 1);
 	user_fence_put(ufence);
 }
 
-static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
+static void kick_ufence(struct xe_user_fence *ufence, struct dma_fence *fence)
 {
 	INIT_WORK(&ufence->worker, user_fence_worker);
 	queue_work(ufence->xe->ordered_wq, &ufence->worker);
@@ -92,7 +94,7 @@ static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence)
 
 static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	struct user_fence *ufence = container_of(cb, struct user_fence, cb);
+	struct xe_user_fence *ufence = container_of(cb, struct xe_user_fence, cb);
 
 	kick_ufence(ufence, fence);
 }
@@ -307,7 +309,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 	/* Easy case... */
 	if (!num_in_fence) {
 		fence = xe_exec_queue_last_fence_get(q, vm);
-		dma_fence_get(fence);
 		return fence;
 	}
 
@@ -322,7 +323,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		}
 	}
 	fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
-	dma_fence_get(fences[current_fence - 1]);
 	cf = dma_fence_array_create(num_in_fence, fences,
 				    vm->composite_fence_ctx,
 				    vm->composite_fence_seqno++,
@@ -342,3 +342,39 @@ err_out:
 
 	return ERR_PTR(-ENOMEM);
 }
+
+/**
+ * xe_sync_ufence_get() - Get user fence from sync
+ * @sync: input sync
+ *
+ * Get a user fence reference from sync.
+ *
+ * Return: xe_user_fence pointer with reference
+ */
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync)
+{
+	user_fence_get(sync->ufence);
+
+	return sync->ufence;
+}
+
+/**
+ * xe_sync_ufence_put() - Put user fence reference
+ * @ufence: user fence reference
+ *
+ */
+void xe_sync_ufence_put(struct xe_user_fence *ufence)
+{
+	user_fence_put(ufence);
+}
+
+/**
+ * xe_sync_ufence_get_status() - Get user fence status
+ * @ufence: user fence
+ *
+ * Return: 1 if signalled, 0 not signalled, <0 on error
+ */
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence)
+{
+	return READ_ONCE(ufence->signalled);
+}
diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h
index d284afbe917c..0fd0d51208e6 100644
--- a/drivers/gpu/drm/xe/xe_sync.h
+++ b/drivers/gpu/drm/xe/xe_sync.h
@@ -33,4 +33,13 @@ struct dma_fence *
 xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
 		     struct xe_exec_queue *q, struct xe_vm *vm);
 
+static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync)
+{
+	return !!sync->ufence;
+}
+
+struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync);
+void xe_sync_ufence_put(struct xe_user_fence *ufence);
+int xe_sync_ufence_get_status(struct xe_user_fence *ufence);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h
index 852db5e7884f..30ac3f51993b 100644
--- a/drivers/gpu/drm/xe/xe_sync_types.h
+++ b/drivers/gpu/drm/xe/xe_sync_types.h
@@ -18,7 +18,7 @@ struct xe_sync_entry {
 	struct drm_syncobj *syncobj;
 	struct dma_fence *fence;
 	struct dma_fence_chain *chain_fence;
-	struct user_fence *ufence;
+	struct xe_user_fence *ufence;
 	u64 addr;
 	u64 timeline_value;
 	u32 type;
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 044c20881de7..0650b2fa75ef 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -167,9 +167,10 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
 		goto err_mem_access;
 
 	tile->mem.kernel_bb_pool = xe_sa_bo_manager_init(tile, SZ_1M, 16);
-	if (IS_ERR(tile->mem.kernel_bb_pool))
+	if (IS_ERR(tile->mem.kernel_bb_pool)) {
 		err = PTR_ERR(tile->mem.kernel_bb_pool);
-
+		goto err_mem_access;
+	}
 	xe_wa_apply_tile_workarounds(tile);
 
 	xe_tile_sysfs_init(tile);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 95163c303f3e..4ddc55527f9a 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -12,6 +12,7 @@
 #include <linux/tracepoint.h>
 #include <linux/types.h>
 
+#include "xe_bo.h"
 #include "xe_bo_types.h"
 #include "xe_exec_queue_types.h"
 #include "xe_gpu_scheduler_types.h"
@@ -26,16 +27,16 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
 		    TP_ARGS(fence),
 
 		    TP_STRUCT__entry(
-			     __field(u64, fence)
+			     __field(struct xe_gt_tlb_invalidation_fence *, fence)
 			     __field(int, seqno)
 			     ),
 
 		    TP_fast_assign(
-			   __entry->fence = (u64)fence;
+			   __entry->fence = fence;
 			   __entry->seqno = fence->seqno;
 			   ),
 
-		    TP_printk("fence=0x%016llx, seqno=%d",
+		    TP_printk("fence=%p, seqno=%d",
 			      __entry->fence, __entry->seqno)
 );
 
@@ -82,16 +83,16 @@ DECLARE_EVENT_CLASS(xe_bo,
 		    TP_STRUCT__entry(
 			     __field(size_t, size)
 			     __field(u32, flags)
-			     __field(u64, vm)
+			     __field(struct xe_vm *, vm)
 			     ),
 
 		    TP_fast_assign(
 			   __entry->size = bo->size;
 			   __entry->flags = bo->flags;
-			   __entry->vm = (unsigned long)bo->vm;
+			   __entry->vm = bo->vm;
 			   ),
 
-		    TP_printk("size=%zu, flags=0x%02x, vm=0x%016llx",
+		    TP_printk("size=%zu, flags=0x%02x, vm=%p",
 			      __entry->size, __entry->flags, __entry->vm)
 );
 
@@ -100,9 +101,31 @@ DEFINE_EVENT(xe_bo, xe_bo_cpu_fault,
 	     TP_ARGS(bo)
 );
 
-DEFINE_EVENT(xe_bo, xe_bo_move,
-	     TP_PROTO(struct xe_bo *bo),
-	     TP_ARGS(bo)
+TRACE_EVENT(xe_bo_move,
+	    TP_PROTO(struct xe_bo *bo, uint32_t new_placement, uint32_t old_placement,
+		     bool move_lacks_source),
+	    TP_ARGS(bo, new_placement, old_placement, move_lacks_source),
+	    TP_STRUCT__entry(
+		     __field(struct xe_bo *, bo)
+		     __field(size_t, size)
+		     __field(u32, new_placement)
+		     __field(u32, old_placement)
+		     __array(char, device_id, 12)
+		     __field(bool, move_lacks_source)
+			),
+
+	    TP_fast_assign(
+		   __entry->bo      = bo;
+		   __entry->size = bo->size;
+		   __entry->new_placement = new_placement;
+		   __entry->old_placement = old_placement;
+		   strscpy(__entry->device_id, dev_name(xe_bo_device(__entry->bo)->drm.dev), 12);
+		   __entry->move_lacks_source = move_lacks_source;
+		   ),
+	    TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s",
+		      __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size,
+		      xe_mem_type_to_name[__entry->old_placement],
+		      xe_mem_type_to_name[__entry->new_placement], __entry->device_id)
 );
 
 DECLARE_EVENT_CLASS(xe_exec_queue,
@@ -327,16 +350,16 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
 		    TP_STRUCT__entry(
 			     __field(u64, ctx)
 			     __field(u32, seqno)
-			     __field(u64, fence)
+			     __field(struct xe_hw_fence *, fence)
 			     ),
 
 		    TP_fast_assign(
 			   __entry->ctx = fence->dma.context;
 			   __entry->seqno = fence->dma.seqno;
-			   __entry->fence = (unsigned long)fence;
+			   __entry->fence = fence;
 			   ),
 
-		    TP_printk("ctx=0x%016llx, fence=0x%016llx, seqno=%u",
+		    TP_printk("ctx=0x%016llx, fence=%p, seqno=%u",
 			      __entry->ctx, __entry->fence, __entry->seqno)
 );
 
@@ -365,7 +388,7 @@ DECLARE_EVENT_CLASS(xe_vma,
 		    TP_ARGS(vma),
 
 		    TP_STRUCT__entry(
-			     __field(u64, vma)
+			     __field(struct xe_vma *, vma)
 			     __field(u32, asid)
 			     __field(u64, start)
 			     __field(u64, end)
@@ -373,14 +396,14 @@ DECLARE_EVENT_CLASS(xe_vma,
 			     ),
 
 		    TP_fast_assign(
-			   __entry->vma = (unsigned long)vma;
+			   __entry->vma = vma;
 			   __entry->asid = xe_vma_vm(vma)->usm.asid;
 			   __entry->start = xe_vma_start(vma);
 			   __entry->end = xe_vma_end(vma) - 1;
 			   __entry->ptr = xe_vma_userptr(vma);
 			   ),
 
-		    TP_printk("vma=0x%016llx, asid=0x%05x, start=0x%012llx, end=0x%012llx, ptr=0x%012llx,",
+		    TP_printk("vma=%p, asid=0x%05x, start=0x%012llx, end=0x%012llx, userptr=0x%012llx,",
 			      __entry->vma, __entry->asid, __entry->start,
 			      __entry->end, __entry->ptr)
 )
@@ -465,16 +488,16 @@ DECLARE_EVENT_CLASS(xe_vm,
 		    TP_ARGS(vm),
 
 		    TP_STRUCT__entry(
-			     __field(u64, vm)
+			     __field(struct xe_vm *, vm)
 			     __field(u32, asid)
 			     ),
 
 		    TP_fast_assign(
-			   __entry->vm = (unsigned long)vm;
+			   __entry->vm = vm;
 			   __entry->asid = vm->usm.asid;
 			   ),
 
-		    TP_printk("vm=0x%016llx, asid=0x%05x",  __entry->vm,
+		    TP_printk("vm=%p, asid=0x%05x",  __entry->vm,
 			      __entry->asid)
 );
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 53833ab81424..3b21afe5b488 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
 #include "generated/xe_wa_oob.h"
 #include "xe_wa.h"
 
-#define TEST_VM_ASYNC_OPS_ERROR
-
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -46,7 +44,7 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 
 /**
  * xe_vma_userptr_check_repin() - Advisory check for repin needed
- * @vma: The userptr vma
+ * @uvma: The userptr vma
  *
  * Check if the userptr vma has been invalidated since last successful
  * repin. The check is advisory only and can the function can be called
@@ -56,15 +54,17 @@ static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
  *
  * Return: 0 if userptr vma is valid, -EAGAIN otherwise; repin recommended.
  */
-int xe_vma_userptr_check_repin(struct xe_vma *vma)
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma)
 {
-	return mmu_interval_check_retry(&vma->userptr.notifier,
-					vma->userptr.notifier_seq) ?
+	return mmu_interval_check_retry(&uvma->userptr.notifier,
+					uvma->userptr.notifier_seq) ?
 		-EAGAIN : 0;
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma)
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma)
 {
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_device *xe = vm->xe;
 	const unsigned long num_pages = xe_vma_size(vma) >> PAGE_SHIFT;
@@ -80,30 +80,30 @@ retry:
 	if (vma->gpuva.flags & XE_VMA_DESTROYED)
 		return 0;
 
-	notifier_seq = mmu_interval_read_begin(&vma->userptr.notifier);
-	if (notifier_seq == vma->userptr.notifier_seq)
+	notifier_seq = mmu_interval_read_begin(&userptr->notifier);
+	if (notifier_seq == userptr->notifier_seq)
 		return 0;
 
 	pages = kvmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
-	if (vma->userptr.sg) {
+	if (userptr->sg) {
 		dma_unmap_sgtable(xe->drm.dev,
-				  vma->userptr.sg,
+				  userptr->sg,
 				  read_only ? DMA_TO_DEVICE :
 				  DMA_BIDIRECTIONAL, 0);
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 	}
 
 	pinned = ret = 0;
 	if (in_kthread) {
-		if (!mmget_not_zero(vma->userptr.notifier.mm)) {
+		if (!mmget_not_zero(userptr->notifier.mm)) {
 			ret = -EFAULT;
 			goto mm_closed;
 		}
-		kthread_use_mm(vma->userptr.notifier.mm);
+		kthread_use_mm(userptr->notifier.mm);
 	}
 
 	while (pinned < num_pages) {
@@ -112,43 +112,40 @@ retry:
 					  num_pages - pinned,
 					  read_only ? 0 : FOLL_WRITE,
 					  &pages[pinned]);
-		if (ret < 0) {
-			if (in_kthread)
-				ret = 0;
+		if (ret < 0)
 			break;
-		}
 
 		pinned += ret;
 		ret = 0;
 	}
 
 	if (in_kthread) {
-		kthread_unuse_mm(vma->userptr.notifier.mm);
-		mmput(vma->userptr.notifier.mm);
+		kthread_unuse_mm(userptr->notifier.mm);
+		mmput(userptr->notifier.mm);
 	}
 mm_closed:
 	if (ret)
 		goto out;
 
-	ret = sg_alloc_table_from_pages_segment(&vma->userptr.sgt, pages,
+	ret = sg_alloc_table_from_pages_segment(&userptr->sgt, pages,
 						pinned, 0,
 						(u64)pinned << PAGE_SHIFT,
 						xe_sg_segment_size(xe->drm.dev),
 						GFP_KERNEL);
 	if (ret) {
-		vma->userptr.sg = NULL;
+		userptr->sg = NULL;
 		goto out;
 	}
-	vma->userptr.sg = &vma->userptr.sgt;
+	userptr->sg = &userptr->sgt;
 
-	ret = dma_map_sgtable(xe->drm.dev, vma->userptr.sg,
+	ret = dma_map_sgtable(xe->drm.dev, userptr->sg,
 			      read_only ? DMA_TO_DEVICE :
 			      DMA_BIDIRECTIONAL,
 			      DMA_ATTR_SKIP_CPU_SYNC |
 			      DMA_ATTR_NO_KERNEL_MAPPING);
 	if (ret) {
-		sg_free_table(vma->userptr.sg);
-		vma->userptr.sg = NULL;
+		sg_free_table(userptr->sg);
+		userptr->sg = NULL;
 		goto out;
 	}
 
@@ -167,8 +164,8 @@ out:
 	kvfree(pages);
 
 	if (!(ret < 0)) {
-		vma->userptr.notifier_seq = notifier_seq;
-		if (xe_vma_userptr_check_repin(vma) == -EAGAIN)
+		userptr->notifier_seq = notifier_seq;
+		if (xe_vma_userptr_check_repin(uvma) == -EAGAIN)
 			goto retry;
 	}
 
@@ -635,7 +632,9 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				   const struct mmu_notifier_range *range,
 				   unsigned long cur_seq)
 {
-	struct xe_vma *vma = container_of(mni, struct xe_vma, userptr.notifier);
+	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
+	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_vma *vma = &uvma->vma;
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
@@ -651,7 +650,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	mmu_interval_set_seq(mni, cur_seq);
 
 	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!vma->userptr.initial_bind) {
+	if (!userptr->initial_bind) {
 		up_write(&vm->userptr.notifier_lock);
 		return true;
 	}
@@ -663,7 +662,7 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 	if (!xe_vm_in_fault_mode(vm) &&
 	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&vma->userptr.invalidate_link,
+		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
@@ -703,7 +702,7 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
-	struct xe_vma *vma, *next;
+	struct xe_userptr_vma *uvma, *next;
 	int err = 0;
 	LIST_HEAD(tmp_evict);
 
@@ -711,22 +710,23 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
-	list_for_each_entry_safe(vma, next, &vm->userptr.invalidated,
+	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
-		list_del_init(&vma->userptr.invalidate_link);
-		list_move_tail(&vma->combined_links.userptr,
+		list_del_init(&uvma->userptr.invalidate_link);
+		list_move_tail(&uvma->userptr.repin_link,
 			       &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
 	/* Pin and move to temporary list */
-	list_for_each_entry_safe(vma, next, &vm->userptr.repin_list,
-				 combined_links.userptr) {
-		err = xe_vma_userptr_pin_pages(vma);
+	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+				 userptr.repin_link) {
+		err = xe_vma_userptr_pin_pages(uvma);
 		if (err < 0)
 			return err;
 
-		list_move_tail(&vma->combined_links.userptr, &vm->rebind_list);
+		list_del_init(&uvma->userptr.repin_link);
+		list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list);
 	}
 
 	return 0;
@@ -782,6 +782,14 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
 	return fence;
 }
 
+static void xe_vma_free(struct xe_vma *vma)
+{
+	if (xe_vma_is_userptr(vma))
+		kfree(to_userptr_vma(vma));
+	else
+		kfree(vma);
+}
+
 #define VMA_CREATE_FLAG_READ_ONLY	BIT(0)
 #define VMA_CREATE_FLAG_IS_NULL		BIT(1)
 
@@ -800,14 +808,26 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	xe_assert(vm->xe, start < end);
 	xe_assert(vm->xe, end < vm->size);
 
-	if (!bo && !is_null)	/* userptr */
+	/*
+	 * Allocate and ensure that the xe_vma_is_userptr() return
+	 * matches what was allocated.
+	 */
+	if (!bo && !is_null) {
+		struct xe_userptr_vma *uvma = kzalloc(sizeof(*uvma), GFP_KERNEL);
+
+		if (!uvma)
+			return ERR_PTR(-ENOMEM);
+
+		vma = &uvma->vma;
+	} else {
 		vma = kzalloc(sizeof(*vma), GFP_KERNEL);
-	else
-		vma = kzalloc(sizeof(*vma) - sizeof(struct xe_userptr),
-			      GFP_KERNEL);
-	if (!vma) {
-		vma = ERR_PTR(-ENOMEM);
-		return vma;
+		if (!vma)
+			return ERR_PTR(-ENOMEM);
+
+		if (is_null)
+			vma->gpuva.flags |= DRM_GPUVA_SPARSE;
+		if (bo)
+			vma->gpuva.gem.obj = &bo->ttm.base;
 	}
 
 	INIT_LIST_HEAD(&vma->combined_links.rebind);
@@ -818,8 +838,6 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	vma->gpuva.va.range = end - start + 1;
 	if (read_only)
 		vma->gpuva.flags |= XE_VMA_READ_ONLY;
-	if (is_null)
-		vma->gpuva.flags |= DRM_GPUVA_SPARSE;
 
 	for_each_tile(tile, vm->xe, id)
 		vma->tile_mask |= 0x1 << id;
@@ -836,35 +854,35 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 
 		vm_bo = drm_gpuvm_bo_obtain(vma->gpuva.vm, &bo->ttm.base);
 		if (IS_ERR(vm_bo)) {
-			kfree(vma);
+			xe_vma_free(vma);
 			return ERR_CAST(vm_bo);
 		}
 
 		drm_gpuvm_bo_extobj_add(vm_bo);
 		drm_gem_object_get(&bo->ttm.base);
-		vma->gpuva.gem.obj = &bo->ttm.base;
 		vma->gpuva.gem.offset = bo_offset_or_userptr;
 		drm_gpuva_link(&vma->gpuva, vm_bo);
 		drm_gpuvm_bo_put(vm_bo);
 	} else /* userptr or null */ {
 		if (!is_null) {
+			struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
 			u64 size = end - start + 1;
 			int err;
 
-			INIT_LIST_HEAD(&vma->userptr.invalidate_link);
+			INIT_LIST_HEAD(&userptr->invalidate_link);
+			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
 
-			err = mmu_interval_notifier_insert(&vma->userptr.notifier,
+			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
 							   xe_vma_userptr(vma), size,
 							   &vma_userptr_notifier_ops);
 			if (err) {
-				kfree(vma);
-				vma = ERR_PTR(err);
-				return vma;
+				xe_vma_free(vma);
+				return ERR_PTR(err);
 			}
 
-			vma->userptr.notifier_seq = LONG_MAX;
+			userptr->notifier_seq = LONG_MAX;
 		}
 
 		xe_vm_get(vm);
@@ -879,14 +897,21 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 	struct xe_device *xe = vm->xe;
 	bool read_only = xe_vma_read_only(vma);
 
+	if (vma->ufence) {
+		xe_sync_ufence_put(vma->ufence);
+		vma->ufence = NULL;
+	}
+
 	if (xe_vma_is_userptr(vma)) {
-		if (vma->userptr.sg) {
+		struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr;
+
+		if (userptr->sg) {
 			dma_unmap_sgtable(xe->drm.dev,
-					  vma->userptr.sg,
+					  userptr->sg,
 					  read_only ? DMA_TO_DEVICE :
 					  DMA_BIDIRECTIONAL, 0);
-			sg_free_table(vma->userptr.sg);
-			vma->userptr.sg = NULL;
+			sg_free_table(userptr->sg);
+			userptr->sg = NULL;
 		}
 
 		/*
@@ -894,7 +919,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * the notifer until we're sure the GPU is not accessing
 		 * them anymore
 		 */
-		mmu_interval_notifier_remove(&vma->userptr.notifier);
+		mmu_interval_notifier_remove(&userptr->notifier);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
@@ -902,7 +927,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		xe_bo_put(xe_vma_bo(vma));
 	}
 
-	kfree(vma);
+	xe_vma_free(vma);
 }
 
 static void vma_destroy_work_func(struct work_struct *w)
@@ -933,7 +958,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
-		list_del(&vma->userptr.invalidate_link);
+		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {
 		xe_bo_assert_held(xe_vma_bo(vma));
@@ -975,9 +1000,16 @@ int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
 	int err;
 
 	XE_WARN_ON(!vm);
-	err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
-	if (!err && bo && !bo->vm)
-		err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+	if (num_shared)
+		err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
+	else
+		err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+	if (!err && bo && !bo->vm) {
+		if (num_shared)
+			err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+		else
+			err = drm_exec_lock_obj(exec, &bo->ttm.base);
+	}
 
 	return err;
 }
@@ -1581,6 +1613,16 @@ xe_vm_unbind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
 
 	trace_xe_vma_unbind(vma);
 
+	if (vma->ufence) {
+		struct xe_user_fence * const f = vma->ufence;
+
+		if (!xe_sync_ufence_get_status(f))
+			return ERR_PTR(-EBUSY);
+
+		vma->ufence = NULL;
+		xe_sync_ufence_put(f);
+	}
+
 	if (number_tiles > 1) {
 		fences = kmalloc_array(number_tiles, sizeof(*fences),
 				       GFP_KERNEL);
@@ -1714,6 +1756,21 @@ err_fences:
 	return ERR_PTR(err);
 }
 
+static struct xe_user_fence *
+find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_syncs; i++) {
+		struct xe_sync_entry *e = &syncs[i];
+
+		if (xe_sync_is_ufence(e))
+			return xe_sync_ufence_get(e);
+	}
+
+	return NULL;
+}
+
 static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
 			struct xe_exec_queue *q, struct xe_sync_entry *syncs,
 			u32 num_syncs, bool immediate, bool first_op,
@@ -1721,9 +1778,16 @@ static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma,
 {
 	struct dma_fence *fence;
 	struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, q);
+	struct xe_user_fence *ufence;
 
 	xe_vm_assert_held(vm);
 
+	ufence = find_ufence_get(syncs, num_syncs);
+	if (vma->ufence && ufence)
+		xe_sync_ufence_put(vma->ufence);
+
+	vma->ufence = ufence ?: vma->ufence;
+
 	if (immediate) {
 		fence = xe_vm_bind_vma(vma, q, syncs, num_syncs, first_op,
 				       last_op);
@@ -1959,6 +2023,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
 					xe_exec_queue_last_fence_get(wait_exec_queue, vm);
 
 				xe_sync_entry_signal(&syncs[i], NULL, fence);
+				dma_fence_put(fence);
 			}
 		}
 
@@ -2039,7 +2104,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
 	struct drm_gpuva_ops *ops;
 	struct drm_gpuva_op *__op;
-	struct xe_vma_op *op;
 	struct drm_gpuvm_bo *vm_bo;
 	int err;
 
@@ -2086,23 +2150,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
 	if (IS_ERR(ops))
 		return ops;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (operation & FORCE_ASYNC_OP_ERROR) {
-		op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
-					      base.entry);
-		if (op)
-			op->inject_error = true;
-	}
-#endif
-
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
 
 		if (__op->op == DRM_GPUVA_OP_MAP) {
-			op->map.immediate =
-				flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE;
-			op->map.read_only =
-				flags & DRM_XE_VM_BIND_FLAG_READONLY;
 			op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL;
 			op->map.pat_index = pat_index;
 		} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
@@ -2150,7 +2201,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
 		drm_exec_fini(&exec);
 
 	if (xe_vma_is_userptr(vma)) {
-		err = xe_vma_userptr_pin_pages(vma);
+		err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
 		if (err) {
 			prep_vma_destroy(vm, vma, false);
 			xe_vma_destroy_unlocked(vma);
@@ -2172,13 +2223,17 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
 {
 	if (vma->gpuva.flags & XE_VMA_PTE_1G)
 		return SZ_1G;
-	else if (vma->gpuva.flags & XE_VMA_PTE_2M)
+	else if (vma->gpuva.flags & (XE_VMA_PTE_2M | XE_VMA_PTE_COMPACT))
 		return SZ_2M;
+	else if (vma->gpuva.flags & XE_VMA_PTE_64K)
+		return SZ_64K;
+	else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+		return SZ_4K;
 
-	return SZ_4K;
+	return SZ_1G;	/* Uninitialized, used max size */
 }
 
-static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
+static void xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 {
 	switch (size) {
 	case SZ_1G:
@@ -2187,9 +2242,13 @@ static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
 	case SZ_2M:
 		vma->gpuva.flags |= XE_VMA_PTE_2M;
 		break;
+	case SZ_64K:
+		vma->gpuva.flags |= XE_VMA_PTE_64K;
+		break;
+	case SZ_4K:
+		vma->gpuva.flags |= XE_VMA_PTE_4K;
+		break;
 	}
-
-	return SZ_4K;
 }
 
 static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
@@ -2287,8 +2346,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q,
 		switch (op->base.op) {
 		case DRM_GPUVA_OP_MAP:
 		{
-			flags |= op->map.read_only ?
-				VMA_CREATE_FLAG_READ_ONLY : 0;
 			flags |= op->map.is_null ?
 				VMA_CREATE_FLAG_IS_NULL : 0;
 
@@ -2419,7 +2476,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm,
 	case DRM_GPUVA_OP_MAP:
 		err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma),
 				 op->syncs, op->num_syncs,
-				 op->map.immediate || !xe_vm_in_fault_mode(vm),
+				 !xe_vm_in_fault_mode(vm),
 				 op->flags & XE_VMA_OP_FIRST,
 				 op->flags & XE_VMA_OP_LAST);
 		break;
@@ -2505,13 +2562,25 @@ retry_userptr:
 	}
 	drm_exec_fini(&exec);
 
-	if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+	if (err == -EAGAIN) {
 		lockdep_assert_held_write(&vm->lock);
-		err = xe_vma_userptr_pin_pages(vma);
-		if (!err)
-			goto retry_userptr;
 
-		trace_xe_vma_fail(vma);
+		if (op->base.op == DRM_GPUVA_OP_REMAP) {
+			if (!op->remap.unmap_done)
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+			else if (op->remap.prev)
+				vma = op->remap.prev;
+			else
+				vma = op->remap.next;
+		}
+
+		if (xe_vma_is_userptr(vma)) {
+			err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+			if (!err)
+				goto retry_userptr;
+
+			trace_xe_vma_fail(vma);
+		}
 	}
 
 	return err;
@@ -2523,13 +2592,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
 
 	lockdep_assert_held_write(&vm->lock);
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	if (op->inject_error) {
-		op->inject_error = false;
-		return -ENOMEM;
-	}
-#endif
-
 	switch (op->base.op) {
 	case DRM_GPUVA_OP_MAP:
 		ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2644,7 +2706,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
 {
 	int i;
 
-	for (i = num_ops_list - 1; i; ++i) {
+	for (i = num_ops_list - 1; i >= 0; --i) {
 		struct drm_gpuva_ops *__ops = ops[i];
 		struct drm_gpuva_op *__op;
 
@@ -2689,21 +2751,11 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
 	return 0;
 }
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS	\
-	(FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
-#define SUPPORTED_FLAGS	\
-	(DRM_XE_VM_BIND_FLAG_READONLY | \
-	 DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
-	 0xffff)
-#endif
+#define SUPPORTED_FLAGS	(DRM_XE_VM_BIND_FLAG_NULL | \
+	 DRM_XE_VM_BIND_FLAG_DUMPABLE)
 #define XE_64K_PAGE_MASK 0xffffull
 #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
 
-#define MAX_BINDS	512	/* FIXME: Picking random upper limit */
-
 static int vm_bind_ioctl_check_args(struct xe_device *xe,
 				    struct drm_xe_vm_bind *args,
 				    struct drm_xe_vm_bind_op **bind_ops)
@@ -2715,16 +2767,16 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
 	    XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
 		return -EINVAL;
 
-	if (XE_IOCTL_DBG(xe, args->extensions) ||
-	    XE_IOCTL_DBG(xe, args->num_binds > MAX_BINDS))
+	if (XE_IOCTL_DBG(xe, args->extensions))
 		return -EINVAL;
 
 	if (args->num_binds > 1) {
 		u64 __user *bind_user =
 			u64_to_user_ptr(args->vector_of_binds);
 
-		*bind_ops = kmalloc(sizeof(struct drm_xe_vm_bind_op) *
-				    args->num_binds, GFP_KERNEL);
+		*bind_ops = kvmalloc_array(args->num_binds,
+					   sizeof(struct drm_xe_vm_bind_op),
+					   GFP_KERNEL | __GFP_ACCOUNT);
 		if (!*bind_ops)
 			return -ENOMEM;
 
@@ -2814,7 +2866,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
 
 free_bind_ops:
 	if (args->num_binds > 1)
-		kfree(*bind_ops);
+		kvfree(*bind_ops);
 	return err;
 }
 
@@ -2851,7 +2903,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_gpuva_ops **ops = NULL;
 	struct xe_vm *vm;
 	struct xe_exec_queue *q = NULL;
-	u32 num_syncs;
+	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
 	struct drm_xe_vm_bind_op *bind_ops;
 	LIST_HEAD(ops_list);
@@ -2902,13 +2954,15 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	}
 
 	if (args->num_binds) {
-		bos = kcalloc(args->num_binds, sizeof(*bos), GFP_KERNEL);
+		bos = kvcalloc(args->num_binds, sizeof(*bos),
+			       GFP_KERNEL | __GFP_ACCOUNT);
 		if (!bos) {
 			err = -ENOMEM;
 			goto release_vm_lock;
 		}
 
-		ops = kcalloc(args->num_binds, sizeof(*ops), GFP_KERNEL);
+		ops = kvcalloc(args->num_binds, sizeof(*ops),
+			       GFP_KERNEL | __GFP_ACCOUNT);
 		if (!ops) {
 			err = -ENOMEM;
 			goto release_vm_lock;
@@ -2988,6 +3042,14 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 					   SYNC_PARSE_FLAG_DISALLOW_USER_FENCE : 0));
 		if (err)
 			goto free_syncs;
+
+		if (xe_sync_is_ufence(&syncs[num_syncs]))
+			num_ufence++;
+	}
+
+	if (XE_IOCTL_DBG(xe, num_ufence > 1)) {
+		err = -EINVAL;
+		goto free_syncs;
 	}
 
 	if (!args->num_binds) {
@@ -3041,10 +3103,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	for (i = 0; bos && i < args->num_binds; ++i)
 		xe_bo_put(bos[i]);
 
-	kfree(bos);
-	kfree(ops);
+	kvfree(bos);
+	kvfree(ops);
 	if (args->num_binds > 1)
-		kfree(bind_ops);
+		kvfree(bind_ops);
 
 	return err;
 
@@ -3068,10 +3130,10 @@ put_exec_queue:
 	if (q)
 		xe_exec_queue_put(q);
 free_objs:
-	kfree(bos);
-	kfree(ops);
+	kvfree(bos);
+	kvfree(ops);
 	if (args->num_binds > 1)
-		kfree(bind_ops);
+		kvfree(bind_ops);
 	return err;
 }
 
@@ -3130,8 +3192,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		if (xe_vma_is_userptr(vma)) {
 			WARN_ON_ONCE(!mmu_interval_check_retry
-				     (&vma->userptr.notifier,
-				      vma->userptr.notifier_seq));
+				     (&to_userptr_vma(vma)->userptr.notifier,
+				      to_userptr_vma(vma)->userptr.notifier_seq));
 			WARN_ON_ONCE(!dma_resv_test_signaled(xe_vm_resv(xe_vma_vm(vma)),
 							     DMA_RESV_USAGE_BOOKKEEP));
 
@@ -3192,11 +3254,11 @@ int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id)
 		if (is_null) {
 			addr = 0;
 		} else if (is_userptr) {
+			struct sg_table *sg = to_userptr_vma(vma)->userptr.sg;
 			struct xe_res_cursor cur;
 
-			if (vma->userptr.sg) {
-				xe_res_first_sg(vma->userptr.sg, 0, XE_PAGE_SIZE,
-						&cur);
+			if (sg) {
+				xe_res_first_sg(sg, 0, XE_PAGE_SIZE, &cur);
 				addr = xe_res_dma(&cur);
 			} else {
 				addr = 0;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index cf2f96e8c1ab..9654a0612fc2 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -160,6 +160,18 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 	return xe_vma_has_no_bo(vma) && !xe_vma_is_null(vma);
 }
 
+/**
+ * to_userptr_vma() - Return a pointer to an embedding userptr vma
+ * @vma: Pointer to the embedded struct xe_vma
+ *
+ * Return: Pointer to the embedding userptr vma
+ */
+static inline struct xe_userptr_vma *to_userptr_vma(struct xe_vma *vma)
+{
+	xe_assert(xe_vma_vm(vma)->xe, xe_vma_is_userptr(vma));
+	return container_of(vma, struct xe_userptr_vma, vma);
+}
+
 u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile);
 
 int xe_vm_create_ioctl(struct drm_device *dev, void *data,
@@ -224,9 +236,9 @@ static inline void xe_vm_reactivate_rebind(struct xe_vm *vm)
 	}
 }
 
-int xe_vma_userptr_pin_pages(struct xe_vma *vma);
+int xe_vma_userptr_pin_pages(struct xe_userptr_vma *uvma);
 
-int xe_vma_userptr_check_repin(struct xe_vma *vma);
+int xe_vma_userptr_check_repin(struct xe_userptr_vma *uvma);
 
 bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 63e8a50b88e9..7300eea5394b 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -19,11 +19,9 @@
 
 struct xe_bo;
 struct xe_sync_entry;
+struct xe_user_fence;
 struct xe_vm;
 
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR	BIT(31)
-
 #define XE_VMA_READ_ONLY	DRM_GPUVA_USERBITS
 #define XE_VMA_DESTROYED	(DRM_GPUVA_USERBITS << 1)
 #define XE_VMA_ATOMIC_PTE_BIT	(DRM_GPUVA_USERBITS << 2)
@@ -32,11 +30,15 @@ struct xe_vm;
 #define XE_VMA_PTE_4K		(DRM_GPUVA_USERBITS << 5)
 #define XE_VMA_PTE_2M		(DRM_GPUVA_USERBITS << 6)
 #define XE_VMA_PTE_1G		(DRM_GPUVA_USERBITS << 7)
+#define XE_VMA_PTE_64K		(DRM_GPUVA_USERBITS << 8)
+#define XE_VMA_PTE_COMPACT	(DRM_GPUVA_USERBITS << 9)
 
 /** struct xe_userptr - User pointer */
 struct xe_userptr {
 	/** @invalidate_link: Link for the vm::userptr.invalidated list */
 	struct list_head invalidate_link;
+	/** @userptr: link into VM repin list if userptr. */
+	struct list_head repin_link;
 	/**
 	 * @notifier: MMU notifier for user pointer (invalidation call back)
 	 */
@@ -68,8 +70,6 @@ struct xe_vma {
 	 * resv.
 	 */
 	union {
-		/** @userptr: link into VM repin list if userptr. */
-		struct list_head userptr;
 		/** @rebind: link into VM if this VMA needs rebinding. */
 		struct list_head rebind;
 		/** @destroy: link to contested list when VM is being closed. */
@@ -107,9 +107,19 @@ struct xe_vma {
 	u16 pat_index;
 
 	/**
-	 * @userptr: user pointer state, only allocated for VMAs that are
-	 * user pointers
+	 * @ufence: The user fence that was provided with MAP.
+	 * Needs to be signalled before UNMAP can be processed.
 	 */
+	struct xe_user_fence *ufence;
+};
+
+/**
+ * struct xe_userptr_vma - A userptr vma subclass
+ * @vma: The vma.
+ * @userptr: Additional userptr information.
+ */
+struct xe_userptr_vma {
+	struct xe_vma vma;
 	struct xe_userptr userptr;
 };
 
@@ -285,10 +295,6 @@ struct xe_vm {
 struct xe_vma_op_map {
 	/** @vma: VMA to map */
 	struct xe_vma *vma;
-	/** @immediate: Immediate bind */
-	bool immediate;
-	/** @read_only: Read only */
-	bool read_only;
 	/** @is_null: is NULL binding */
 	bool is_null;
 	/** @pat_index: The pat index to use for this operation. */
@@ -356,11 +362,6 @@ struct xe_vma_op {
 	/** @flags: operation flags */
 	enum xe_vma_op_flags flags;
 
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-	/** @inject_error: inject error to test async op error handling */
-	bool inject_error;
-#endif
-
 	union {
 		/** @map: VMA map operation specific data */
 		struct xe_vma_op_map map;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 42fd504abbcd..89983d7d73ca 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -169,6 +169,7 @@ static const struct host1x_info host1x06_info = {
 	.num_sid_entries = ARRAY_SIZE(tegra186_sid_table),
 	.sid_table = tegra186_sid_table,
 	.reserve_vblank_syncpts = false,
+	.skip_reset_assert = true,
 };
 
 static const struct host1x_sid_entry tegra194_sid_table[] = {
@@ -680,13 +681,15 @@ static int __maybe_unused host1x_runtime_suspend(struct device *dev)
 	host1x_intr_stop(host);
 	host1x_syncpt_save(host);
 
-	err = reset_control_bulk_assert(host->nresets, host->resets);
-	if (err) {
-		dev_err(dev, "failed to assert reset: %d\n", err);
-		goto resume_host1x;
-	}
+	if (!host->info->skip_reset_assert) {
+		err = reset_control_bulk_assert(host->nresets, host->resets);
+		if (err) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			goto resume_host1x;
+		}
 
-	usleep_range(1000, 2000);
+		usleep_range(1000, 2000);
+	}
 
 	clk_disable_unprepare(host->clk);
 	reset_control_bulk_release(host->nresets, host->resets);
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index c8e302de7625..925a118db23f 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -116,6 +116,12 @@ struct host1x_info {
 	 * the display driver disables VBLANK increments.
 	 */
 	bool reserve_vblank_syncpts;
+	/*
+	 * On Tegra186, secure world applications may require access to
+	 * host1x during suspend/resume. To allow this, we need to leave
+	 * host1x not in reset.
+	 */
+	bool skip_reset_assert;
 };
 
 struct host1x {
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index d9ef45fcaeab..470ae2c29c94 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -143,6 +143,9 @@ u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *s
 }
 EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup);
 
+/* Disables missing prototype warnings */
+__bpf_kfunc_start_defs();
+
 /**
  * hid_bpf_get_data - Get the kernel memory pointer associated with the context @ctx
  *
@@ -152,7 +155,7 @@ EXPORT_SYMBOL_GPL(call_hid_bpf_rdesc_fixup);
  *
  * @returns %NULL on error, an %__u8 memory pointer on success
  */
-noinline __u8 *
+__bpf_kfunc __u8 *
 hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr_buf_size)
 {
 	struct hid_bpf_ctx_kern *ctx_kern;
@@ -167,6 +170,7 @@ hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr
 
 	return ctx_kern->data + offset;
 }
+__bpf_kfunc_end_defs();
 
 /*
  * The following set contains all functions we agree BPF programs
@@ -241,6 +245,42 @@ int hid_bpf_reconnect(struct hid_device *hdev)
 	return 0;
 }
 
+static int do_hid_bpf_attach_prog(struct hid_device *hdev, int prog_fd, struct bpf_prog *prog,
+				  __u32 flags)
+{
+	int fd, err, prog_type;
+
+	prog_type = hid_bpf_get_prog_attach_type(prog);
+	if (prog_type < 0)
+		return prog_type;
+
+	if (prog_type >= HID_BPF_PROG_TYPE_MAX)
+		return -EINVAL;
+
+	if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) {
+		err = hid_bpf_allocate_event_data(hdev);
+		if (err)
+			return err;
+	}
+
+	fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, prog, flags);
+	if (fd < 0)
+		return fd;
+
+	if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) {
+		err = hid_bpf_reconnect(hdev);
+		if (err) {
+			close_fd(fd);
+			return err;
+		}
+	}
+
+	return fd;
+}
+
+/* Disables missing prototype warnings */
+__bpf_kfunc_start_defs();
+
 /**
  * hid_bpf_attach_prog - Attach the given @prog_fd to the given HID device
  *
@@ -253,22 +293,17 @@ int hid_bpf_reconnect(struct hid_device *hdev)
  * is pinned to the BPF file system).
  */
 /* called from syscall */
-noinline int
+__bpf_kfunc int
 hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
 {
 	struct hid_device *hdev;
+	struct bpf_prog *prog;
 	struct device *dev;
-	int fd, err, prog_type = hid_bpf_get_prog_attach_type(prog_fd);
+	int err, fd;
 
 	if (!hid_bpf_ops)
 		return -EINVAL;
 
-	if (prog_type < 0)
-		return prog_type;
-
-	if (prog_type >= HID_BPF_PROG_TYPE_MAX)
-		return -EINVAL;
-
 	if ((flags & ~HID_BPF_FLAG_MASK))
 		return -EINVAL;
 
@@ -278,25 +313,29 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
 
 	hdev = to_hid_device(dev);
 
-	if (prog_type == HID_BPF_PROG_TYPE_DEVICE_EVENT) {
-		err = hid_bpf_allocate_event_data(hdev);
-		if (err)
-			return err;
+	/*
+	 * take a ref on the prog itself, it will be released
+	 * on errors or when it'll be detached
+	 */
+	prog = bpf_prog_get(prog_fd);
+	if (IS_ERR(prog)) {
+		err = PTR_ERR(prog);
+		goto out_dev_put;
 	}
 
-	fd = __hid_bpf_attach_prog(hdev, prog_type, prog_fd, flags);
-	if (fd < 0)
-		return fd;
-
-	if (prog_type == HID_BPF_PROG_TYPE_RDESC_FIXUP) {
-		err = hid_bpf_reconnect(hdev);
-		if (err) {
-			close_fd(fd);
-			return err;
-		}
+	fd = do_hid_bpf_attach_prog(hdev, prog_fd, prog, flags);
+	if (fd < 0) {
+		err = fd;
+		goto out_prog_put;
 	}
 
 	return fd;
+
+ out_prog_put:
+	bpf_prog_put(prog);
+ out_dev_put:
+	put_device(dev);
+	return err;
 }
 
 /**
@@ -306,7 +345,7 @@ hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags)
  *
  * @returns A pointer to &struct hid_bpf_ctx on success, %NULL on error.
  */
-noinline struct hid_bpf_ctx *
+__bpf_kfunc struct hid_bpf_ctx *
 hid_bpf_allocate_context(unsigned int hid_id)
 {
 	struct hid_device *hdev;
@@ -323,8 +362,10 @@ hid_bpf_allocate_context(unsigned int hid_id)
 	hdev = to_hid_device(dev);
 
 	ctx_kern = kzalloc(sizeof(*ctx_kern), GFP_KERNEL);
-	if (!ctx_kern)
+	if (!ctx_kern) {
+		put_device(dev);
 		return NULL;
+	}
 
 	ctx_kern->ctx.hid = hdev;
 
@@ -337,14 +378,19 @@ hid_bpf_allocate_context(unsigned int hid_id)
  * @ctx: the HID-BPF context to release
  *
  */
-noinline void
+__bpf_kfunc void
 hid_bpf_release_context(struct hid_bpf_ctx *ctx)
 {
 	struct hid_bpf_ctx_kern *ctx_kern;
+	struct hid_device *hid;
 
 	ctx_kern = container_of(ctx, struct hid_bpf_ctx_kern, ctx);
+	hid = (struct hid_device *)ctx_kern->ctx.hid; /* ignore const */
 
 	kfree(ctx_kern);
+
+	/* get_device() is called by bus_find_device() */
+	put_device(&hid->dev);
 }
 
 /**
@@ -358,7 +404,7 @@ hid_bpf_release_context(struct hid_bpf_ctx *ctx)
  *
  * @returns %0 on success, a negative error code otherwise.
  */
-noinline int
+__bpf_kfunc int
 hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
 		   enum hid_report_type rtype, enum hid_class_request reqtype)
 {
@@ -426,6 +472,7 @@ hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
 	kfree(dma_data);
 	return ret;
 }
+__bpf_kfunc_end_defs();
 
 /* our HID-BPF entrypoints */
 BTF_SET8_START(hid_bpf_fmodret_ids)
diff --git a/drivers/hid/bpf/hid_bpf_dispatch.h b/drivers/hid/bpf/hid_bpf_dispatch.h
index 63dfc8605cd2..fbe0639d09f2 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.h
+++ b/drivers/hid/bpf/hid_bpf_dispatch.h
@@ -12,9 +12,9 @@ struct hid_bpf_ctx_kern {
 
 int hid_bpf_preload_skel(void);
 void hid_bpf_free_links_and_skel(void);
-int hid_bpf_get_prog_attach_type(int prog_fd);
+int hid_bpf_get_prog_attach_type(struct bpf_prog *prog);
 int __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type, int prog_fd,
-			  __u32 flags);
+			  struct bpf_prog *prog, __u32 flags);
 void __hid_bpf_destroy_device(struct hid_device *hdev);
 int hid_bpf_prog_run(struct hid_device *hdev, enum hid_bpf_prog_type type,
 		     struct hid_bpf_ctx_kern *ctx_kern);
diff --git a/drivers/hid/bpf/hid_bpf_jmp_table.c b/drivers/hid/bpf/hid_bpf_jmp_table.c
index eca34b7372f9..aa8e1c79cdf5 100644
--- a/drivers/hid/bpf/hid_bpf_jmp_table.c
+++ b/drivers/hid/bpf/hid_bpf_jmp_table.c
@@ -196,6 +196,7 @@ static void __hid_bpf_do_release_prog(int map_fd, unsigned int idx)
 static void hid_bpf_release_progs(struct work_struct *work)
 {
 	int i, j, n, map_fd = -1;
+	bool hdev_destroyed;
 
 	if (!jmp_table.map)
 		return;
@@ -220,6 +221,12 @@ static void hid_bpf_release_progs(struct work_struct *work)
 		if (entry->hdev) {
 			hdev = entry->hdev;
 			type = entry->type;
+			/*
+			 * hdev is still valid, even if we are called after hid_destroy_device():
+			 * when hid_bpf_attach() gets called, it takes a ref on the dev through
+			 * bus_find_device()
+			 */
+			hdev_destroyed = hdev->bpf.destroyed;
 
 			hid_bpf_populate_hdev(hdev, type);
 
@@ -232,12 +239,19 @@ static void hid_bpf_release_progs(struct work_struct *work)
 				if (test_bit(next->idx, jmp_table.enabled))
 					continue;
 
-				if (next->hdev == hdev && next->type == type)
+				if (next->hdev == hdev && next->type == type) {
+					/*
+					 * clear the hdev reference and decrement the device ref
+					 * that was taken during bus_find_device() while calling
+					 * hid_bpf_attach()
+					 */
 					next->hdev = NULL;
+					put_device(&hdev->dev);
+				}
 			}
 
-			/* if type was rdesc fixup, reconnect device */
-			if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP)
+			/* if type was rdesc fixup and the device is not gone, reconnect device */
+			if (type == HID_BPF_PROG_TYPE_RDESC_FIXUP && !hdev_destroyed)
 				hid_bpf_reconnect(hdev);
 		}
 	}
@@ -333,15 +347,10 @@ static int hid_bpf_insert_prog(int prog_fd, struct bpf_prog *prog)
 	return err;
 }
 
-int hid_bpf_get_prog_attach_type(int prog_fd)
+int hid_bpf_get_prog_attach_type(struct bpf_prog *prog)
 {
-	struct bpf_prog *prog = NULL;
-	int i;
 	int prog_type = HID_BPF_PROG_TYPE_UNDEF;
-
-	prog = bpf_prog_get(prog_fd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
+	int i;
 
 	for (i = 0; i < HID_BPF_PROG_TYPE_MAX; i++) {
 		if (hid_bpf_btf_ids[i] == prog->aux->attach_btf_id) {
@@ -350,8 +359,6 @@ int hid_bpf_get_prog_attach_type(int prog_fd)
 		}
 	}
 
-	bpf_prog_put(prog);
-
 	return prog_type;
 }
 
@@ -388,19 +395,13 @@ static const struct bpf_link_ops hid_bpf_link_lops = {
 /* called from syscall */
 noinline int
 __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type,
-		      int prog_fd, __u32 flags)
+		      int prog_fd, struct bpf_prog *prog, __u32 flags)
 {
 	struct bpf_link_primer link_primer;
 	struct hid_bpf_link *link;
-	struct bpf_prog *prog = NULL;
 	struct hid_bpf_prog_entry *prog_entry;
 	int cnt, err = -EINVAL, prog_table_idx = -1;
 
-	/* take a ref on the prog itself */
-	prog = bpf_prog_get(prog_fd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
 	mutex_lock(&hid_bpf_attach_lock);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
@@ -467,7 +468,6 @@ __hid_bpf_attach_prog(struct hid_device *hdev, enum hid_bpf_prog_type prog_type,
  err_unlock:
 	mutex_unlock(&hid_bpf_attach_lock);
 
-	bpf_prog_put(prog);
 	kfree(link);
 
 	return err;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index fb30e228d35f..828a5c022c64 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -298,6 +298,9 @@
 
 #define USB_VENDOR_ID_CIDC		0x1677
 
+#define I2C_VENDOR_ID_CIRQUE           0x0488
+#define I2C_PRODUCT_ID_CIRQUE_1063     0x1063
+
 #define USB_VENDOR_ID_CJTOUCH		0x24b8
 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0020	0x0020
 #define USB_DEVICE_ID_CJTOUCH_MULTI_TOUCH_0040	0x0040
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index fd6d8f1d9b8f..d2f3f234f29d 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -203,6 +203,8 @@ struct hidpp_device {
 	struct hidpp_scroll_counter vertical_wheel_counter;
 
 	u8 wireless_feature_index;
+
+	bool connected_once;
 };
 
 /* HID++ 1.0 error codes */
@@ -988,8 +990,13 @@ static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp)
 	hidpp->protocol_minor = response.rap.params[1];
 
 print_version:
-	hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
-		 hidpp->protocol_major, hidpp->protocol_minor);
+	if (!hidpp->connected_once) {
+		hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+			 hidpp->protocol_major, hidpp->protocol_minor);
+		hidpp->connected_once = true;
+	} else
+		hid_dbg(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+			 hidpp->protocol_major, hidpp->protocol_minor);
 	return 0;
 }
 
@@ -4184,7 +4191,7 @@ static void hidpp_connect_event(struct work_struct *work)
 	/* Get device version to check if it is connected */
 	ret = hidpp_root_get_protocol_version(hidpp);
 	if (ret) {
-		hid_info(hidpp->hid_dev, "Disconnected\n");
+		hid_dbg(hidpp->hid_dev, "Disconnected\n");
 		if (hidpp->battery.ps) {
 			hidpp->battery.online = false;
 			hidpp->battery.status = POWER_SUPPLY_STATUS_UNKNOWN;
@@ -4610,6 +4617,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC088) },
 	{ /* Logitech G Pro X Superlight Gaming Mouse over USB */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC094) },
+	{ /* Logitech G Pro X Superlight 2 Gaming Mouse over USB */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC09b) },
 
 	{ /* G935 Gaming Headset */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0x0a87),
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index fd5b0637dad6..3e91e4d6ba6f 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2153,6 +2153,10 @@ static const struct hid_device_id mt_devices[] = {
 
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_SYNAPTICS, 0xcddc) },
+
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
 			USB_VENDOR_ID_SYNAPTICS, 0xce08) },
 
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
diff --git a/drivers/hid/hid-nvidia-shield.c b/drivers/hid/hid-nvidia-shield.c
index 82d0a77359c4..58b15750dbb0 100644
--- a/drivers/hid/hid-nvidia-shield.c
+++ b/drivers/hid/hid-nvidia-shield.c
@@ -800,6 +800,8 @@ static inline int thunderstrike_led_create(struct thunderstrike *ts)
 
 	led->name = devm_kasprintf(&ts->base.hdev->dev, GFP_KERNEL,
 				   "thunderstrike%d:blue:led", ts->id);
+	if (!led->name)
+		return -ENOMEM;
 	led->max_brightness = 1;
 	led->flags = LED_CORE_SUSPENDRESUME | LED_RETAIN_AT_SHUTDOWN;
 	led->brightness_get = &thunderstrike_led_get_brightness;
@@ -831,6 +833,8 @@ static inline int thunderstrike_psy_create(struct shield_device *shield_dev)
 	shield_dev->battery_dev.desc.name =
 		devm_kasprintf(&ts->base.hdev->dev, GFP_KERNEL,
 			       "thunderstrike_%d", ts->id);
+	if (!shield_dev->battery_dev.desc.name)
+		return -ENOMEM;
 
 	shield_dev->battery_dev.psy = power_supply_register(
 		&hdev->dev, &shield_dev->battery_dev.desc, &psy_cfg);
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index b3c4e50e248a..b08a5ab58528 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1109,10 +1109,9 @@ static int steam_probe(struct hid_device *hdev,
 		return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 
 	steam = devm_kzalloc(&hdev->dev, sizeof(*steam), GFP_KERNEL);
-	if (!steam) {
-		ret = -ENOMEM;
-		goto steam_alloc_fail;
-	}
+	if (!steam)
+		return -ENOMEM;
+
 	steam->hdev = hdev;
 	hid_set_drvdata(hdev, steam);
 	spin_lock_init(&steam->lock);
@@ -1129,14 +1128,14 @@ static int steam_probe(struct hid_device *hdev,
 	 */
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_HIDRAW);
 	if (ret)
-		goto hid_hw_start_fail;
+		goto err_cancel_work;
 
 	ret = hid_hw_open(hdev);
 	if (ret) {
 		hid_err(hdev,
 			"%s:hid_hw_open\n",
 			__func__);
-		goto hid_hw_open_fail;
+		goto err_hw_stop;
 	}
 
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {
@@ -1152,36 +1151,37 @@ static int steam_probe(struct hid_device *hdev,
 			hid_err(hdev,
 				"%s:steam_register failed with error %d\n",
 				__func__, ret);
-			goto input_register_fail;
+			goto err_hw_close;
 		}
 	}
 
 	steam->client_hdev = steam_create_client_hid(hdev);
 	if (IS_ERR(steam->client_hdev)) {
 		ret = PTR_ERR(steam->client_hdev);
-		goto client_hdev_fail;
+		goto err_stream_unregister;
 	}
 	steam->client_hdev->driver_data = steam;
 
 	ret = hid_add_device(steam->client_hdev);
 	if (ret)
-		goto client_hdev_add_fail;
+		goto err_destroy;
 
 	return 0;
 
-client_hdev_add_fail:
-	hid_hw_stop(hdev);
-client_hdev_fail:
+err_destroy:
 	hid_destroy_device(steam->client_hdev);
-input_register_fail:
-hid_hw_open_fail:
-hid_hw_start_fail:
+err_stream_unregister:
+	if (steam->connected)
+		steam_unregister(steam);
+err_hw_close:
+	hid_hw_close(hdev);
+err_hw_stop:
+	hid_hw_stop(hdev);
+err_cancel_work:
 	cancel_work_sync(&steam->work_connect);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->rumble_work);
-steam_alloc_fail:
-	hid_err(hdev, "%s: failed with error %d\n",
-			__func__, ret);
+
 	return ret;
 }
 
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 13c8dd8cd350..2bc762d31ac7 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -357,8 +357,11 @@ static int hidraw_release(struct inode * inode, struct file * file)
 	down_write(&minors_rwsem);
 
 	spin_lock_irqsave(&hidraw_table[minor]->list_lock, flags);
-	for (int i = list->tail; i < list->head; i++)
-		kfree(list->buffer[i].value);
+	while (list->tail != list->head) {
+		kfree(list->buffer[list->tail].value);
+		list->buffer[list->tail].value = NULL;
+		list->tail = (list->tail + 1) & (HIDRAW_BUFFER_SIZE - 1);
+	}
 	list_del(&list->node);
 	spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags);
 	kfree(list);
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 90f316ae9819..2df1ab3c31cc 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -49,6 +49,7 @@
 #define I2C_HID_QUIRK_RESET_ON_RESUME		BIT(2)
 #define I2C_HID_QUIRK_BAD_INPUT_SIZE		BIT(3)
 #define I2C_HID_QUIRK_NO_WAKEUP_AFTER_RESET	BIT(4)
+#define I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND	BIT(5)
 
 /* Command opcodes */
 #define I2C_HID_OPCODE_RESET			0x01
@@ -131,6 +132,8 @@ static const struct i2c_hid_quirks {
 		 I2C_HID_QUIRK_RESET_ON_RESUME },
 	{ USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
 		I2C_HID_QUIRK_BAD_INPUT_SIZE },
+	{ I2C_VENDOR_ID_CIRQUE, I2C_PRODUCT_ID_CIRQUE_1063,
+		I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND },
 	/*
 	 * Sending the wakeup after reset actually break ELAN touchscreen controller
 	 */
@@ -956,7 +959,8 @@ static int i2c_hid_core_suspend(struct i2c_hid *ihid, bool force_poweroff)
 		return ret;
 
 	/* Save some power */
-	i2c_hid_set_power(ihid, I2C_HID_PWR_SLEEP);
+	if (!(ihid->quirks & I2C_HID_QUIRK_NO_SLEEP_ON_SUSPEND))
+		i2c_hid_set_power(ihid, I2C_HID_PWR_SLEEP);
 
 	disable_irq(client->irq);
 
diff --git a/drivers/hid/i2c-hid/i2c-hid-of.c b/drivers/hid/i2c-hid/i2c-hid-of.c
index c4e1fa0273c8..8be4d576da77 100644
--- a/drivers/hid/i2c-hid/i2c-hid-of.c
+++ b/drivers/hid/i2c-hid/i2c-hid-of.c
@@ -87,6 +87,7 @@ static int i2c_hid_of_probe(struct i2c_client *client)
 	if (!ihid_of)
 		return -ENOMEM;
 
+	ihid_of->client = client;
 	ihid_of->ops.power_up = i2c_hid_of_power_up;
 	ihid_of->ops.power_down = i2c_hid_of_power_down;
 
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index aa6cb033bb06..03d5601ce807 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -722,6 +722,8 @@ void ishtp_bus_remove_all_clients(struct ishtp_device *ishtp_dev,
 	spin_lock_irqsave(&ishtp_dev->cl_list_lock, flags);
 	list_for_each_entry(cl, &ishtp_dev->cl_list, link) {
 		cl->state = ISHTP_CL_DISCONNECTED;
+		if (warm_reset && cl->device->reference_count)
+			continue;
 
 		/*
 		 * Wake any pending process. The waiter would check dev->state
diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 82c907f01bd3..8a7f2f6a4f86 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -49,7 +49,9 @@ static void ishtp_read_list_flush(struct ishtp_cl *cl)
 	list_for_each_entry_safe(rb, next, &cl->dev->read_list.list, list)
 		if (rb->cl && ishtp_cl_cmp_id(cl, rb->cl)) {
 			list_del(&rb->list);
-			ishtp_io_rb_free(rb);
+			spin_lock(&cl->free_list_spinlock);
+			list_add_tail(&rb->list, &cl->free_rb_list.list);
+			spin_unlock(&cl->free_list_spinlock);
 		}
 	spin_unlock_irqrestore(&cl->dev->read_list_spinlock, flags);
 }
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b613f11ed949..2bc45b24075c 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2087,7 +2087,7 @@ static int wacom_allocate_inputs(struct wacom *wacom)
 	return 0;
 }
 
-static int wacom_register_inputs(struct wacom *wacom)
+static int wacom_setup_inputs(struct wacom *wacom)
 {
 	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
@@ -2106,10 +2106,6 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(pen_input_dev);
 		wacom_wac->pen_input = NULL;
 		pen_input_dev = NULL;
-	} else {
-		error = input_register_device(pen_input_dev);
-		if (error)
-			goto fail;
 	}
 
 	error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac);
@@ -2118,10 +2114,6 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(touch_input_dev);
 		wacom_wac->touch_input = NULL;
 		touch_input_dev = NULL;
-	} else {
-		error = input_register_device(touch_input_dev);
-		if (error)
-			goto fail;
 	}
 
 	error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
@@ -2130,7 +2122,34 @@ static int wacom_register_inputs(struct wacom *wacom)
 		input_free_device(pad_input_dev);
 		wacom_wac->pad_input = NULL;
 		pad_input_dev = NULL;
-	} else {
+	}
+
+	return 0;
+}
+
+static int wacom_register_inputs(struct wacom *wacom)
+{
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
+	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
+	int error = 0;
+
+	pen_input_dev = wacom_wac->pen_input;
+	touch_input_dev = wacom_wac->touch_input;
+	pad_input_dev = wacom_wac->pad_input;
+
+	if (pen_input_dev) {
+		error = input_register_device(pen_input_dev);
+		if (error)
+			goto fail;
+	}
+
+	if (touch_input_dev) {
+		error = input_register_device(touch_input_dev);
+		if (error)
+			goto fail;
+	}
+
+	if (pad_input_dev) {
 		error = input_register_device(pad_input_dev);
 		if (error)
 			goto fail;
@@ -2383,6 +2402,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 	if (error)
 		goto fail;
 
+	error = wacom_setup_inputs(wacom);
+	if (error)
+		goto fail;
+
+	if (features->type == HID_GENERIC)
+		connect_mask |= HID_CONNECT_DRIVER;
+
+	/* Regular HID work starts now */
+	error = hid_hw_start(hdev, connect_mask);
+	if (error) {
+		hid_err(hdev, "hw start failed\n");
+		goto fail;
+	}
+
 	error = wacom_register_inputs(wacom);
 	if (error)
 		goto fail;
@@ -2397,16 +2430,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 			goto fail;
 	}
 
-	if (features->type == HID_GENERIC)
-		connect_mask |= HID_CONNECT_DRIVER;
-
-	/* Regular HID work starts now */
-	error = hid_hw_start(hdev, connect_mask);
-	if (error) {
-		hid_err(hdev, "hw start failed\n");
-		goto fail;
-	}
-
 	if (!wireless) {
 		/* Note that if query fails it is not a hard failure */
 		wacom_query_tablet_data(wacom);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index da8a01fedd39..fbe10fbc5769 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2575,7 +2575,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev,
 				wacom_wac->hid_data.tipswitch);
 		input_report_key(input, wacom_wac->tool[0], sense);
 		if (wacom_wac->serial[0]) {
-			input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]);
+			/*
+			 * xf86-input-wacom does not accept a serial number
+			 * of '0'. Report the low 32 bits if possible, but
+			 * if they are zero, report the upper ones instead.
+			 */
+			__u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu;
+			__u32 serial_hi = wacom_wac->serial[0] >> 32;
+			input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi));
 			input_report_abs(input, ABS_MISC, sense ? id : 0);
 		}
 
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 56f7e06c673e..adbf674355b2 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
 
 	pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT;
 
-	/* do we need a gpadl body msg */
 	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
 		  sizeof(struct vmbus_channel_gpadl_header) -
 		  sizeof(struct gpa_range);
+	pfncount = umin(pagecount, pfnsize / sizeof(u64));
+
+	msgsize = sizeof(struct vmbus_channel_msginfo) +
+		  sizeof(struct vmbus_channel_gpadl_header) +
+		  sizeof(struct gpa_range) + pfncount * sizeof(u64);
+	msgheader =  kzalloc(msgsize, GFP_KERNEL);
+	if (!msgheader)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&msgheader->submsglist);
+	msgheader->msgsize = msgsize;
+
+	gpadl_header = (struct vmbus_channel_gpadl_header *)
+		msgheader->msg;
+	gpadl_header->rangecount = 1;
+	gpadl_header->range_buflen = sizeof(struct gpa_range) +
+				 pagecount * sizeof(u64);
+	gpadl_header->range[0].byte_offset = 0;
+	gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
+	for (i = 0; i < pfncount; i++)
+		gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+			type, kbuffer, size, send_offset, i);
+	*msginfo = msgheader;
+
+	pfnsum = pfncount;
+	pfnleft = pagecount - pfncount;
+
+	/* how many pfns can we fit in a body message */
+	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
+		  sizeof(struct vmbus_channel_gpadl_body);
 	pfncount = pfnsize / sizeof(u64);
 
-	if (pagecount > pfncount) {
-		/* we need a gpadl body */
-		/* fill in the header */
+	/*
+	 * If pfnleft is zero, everything fits in the header and no body
+	 * messages are needed
+	 */
+	while (pfnleft) {
+		pfncurr = umin(pfncount, pfnleft);
 		msgsize = sizeof(struct vmbus_channel_msginfo) +
-			  sizeof(struct vmbus_channel_gpadl_header) +
-			  sizeof(struct gpa_range) + pfncount * sizeof(u64);
-		msgheader =  kzalloc(msgsize, GFP_KERNEL);
-		if (!msgheader)
-			goto nomem;
-
-		INIT_LIST_HEAD(&msgheader->submsglist);
-		msgheader->msgsize = msgsize;
-
-		gpadl_header = (struct vmbus_channel_gpadl_header *)
-			msgheader->msg;
-		gpadl_header->rangecount = 1;
-		gpadl_header->range_buflen = sizeof(struct gpa_range) +
-					 pagecount * sizeof(u64);
-		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
-		for (i = 0; i < pfncount; i++)
-			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
-				type, kbuffer, size, send_offset, i);
-		*msginfo = msgheader;
-
-		pfnsum = pfncount;
-		pfnleft = pagecount - pfncount;
-
-		/* how many pfns can we fit */
-		pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
-			  sizeof(struct vmbus_channel_gpadl_body);
-		pfncount = pfnsize / sizeof(u64);
-
-		/* fill in the body */
-		while (pfnleft) {
-			if (pfnleft > pfncount)
-				pfncurr = pfncount;
-			else
-				pfncurr = pfnleft;
-
-			msgsize = sizeof(struct vmbus_channel_msginfo) +
-				  sizeof(struct vmbus_channel_gpadl_body) +
-				  pfncurr * sizeof(u64);
-			msgbody = kzalloc(msgsize, GFP_KERNEL);
-
-			if (!msgbody) {
-				struct vmbus_channel_msginfo *pos = NULL;
-				struct vmbus_channel_msginfo *tmp = NULL;
-				/*
-				 * Free up all the allocated messages.
-				 */
-				list_for_each_entry_safe(pos, tmp,
-					&msgheader->submsglist,
-					msglistentry) {
-
-					list_del(&pos->msglistentry);
-					kfree(pos);
-				}
-
-				goto nomem;
-			}
-
-			msgbody->msgsize = msgsize;
-			gpadl_body =
-				(struct vmbus_channel_gpadl_body *)msgbody->msg;
+			  sizeof(struct vmbus_channel_gpadl_body) +
+			  pfncurr * sizeof(u64);
+		msgbody = kzalloc(msgsize, GFP_KERNEL);
 
+		if (!msgbody) {
+			struct vmbus_channel_msginfo *pos = NULL;
+			struct vmbus_channel_msginfo *tmp = NULL;
 			/*
-			 * Gpadl is u32 and we are using a pointer which could
-			 * be 64-bit
-			 * This is governed by the guest/host protocol and
-			 * so the hypervisor guarantees that this is ok.
+			 * Free up all the allocated messages.
 			 */
-			for (i = 0; i < pfncurr; i++)
-				gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
-					kbuffer, size, send_offset, pfnsum + i);
-
-			/* add to msg header */
-			list_add_tail(&msgbody->msglistentry,
-				      &msgheader->submsglist);
-			pfnsum += pfncurr;
-			pfnleft -= pfncurr;
+			list_for_each_entry_safe(pos, tmp,
+				&msgheader->submsglist,
+				msglistentry) {
+
+				list_del(&pos->msglistentry);
+				kfree(pos);
+			}
+			kfree(msgheader);
+			return -ENOMEM;
 		}
-	} else {
-		/* everything fits in a header */
-		msgsize = sizeof(struct vmbus_channel_msginfo) +
-			  sizeof(struct vmbus_channel_gpadl_header) +
-			  sizeof(struct gpa_range) + pagecount * sizeof(u64);
-		msgheader = kzalloc(msgsize, GFP_KERNEL);
-		if (msgheader == NULL)
-			goto nomem;
-
-		INIT_LIST_HEAD(&msgheader->submsglist);
-		msgheader->msgsize = msgsize;
-
-		gpadl_header = (struct vmbus_channel_gpadl_header *)
-			msgheader->msg;
-		gpadl_header->rangecount = 1;
-		gpadl_header->range_buflen = sizeof(struct gpa_range) +
-					 pagecount * sizeof(u64);
-		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
-		for (i = 0; i < pagecount; i++)
-			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
-				type, kbuffer, size, send_offset, i);
-
-		*msginfo = msgheader;
+
+		msgbody->msgsize = msgsize;
+		gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg;
+
+		/*
+		 * Gpadl is u32 and we are using a pointer which could
+		 * be 64-bit
+		 * This is governed by the guest/host protocol and
+		 * so the hypervisor guarantees that this is ok.
+		 */
+		for (i = 0; i < pfncurr; i++)
+			gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
+				kbuffer, size, send_offset, pfnsum + i);
+
+		/* add to msg header */
+		list_add_tail(&msgbody->msglistentry, &msgheader->submsglist);
+		pfnsum += pfncurr;
+		pfnleft -= pfncurr;
 	}
 
 	return 0;
-nomem:
-	kfree(msgheader);
-	kfree(msgbody);
-	return -ENOMEM;
 }
 
 /*
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 42aec2c5606a..9c97c4065fe7 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -296,6 +296,11 @@ static struct {
 	spinlock_t			lock;
 } host_ts;
 
+static bool timesync_implicit;
+
+module_param(timesync_implicit, bool, 0644);
+MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind");
+
 static inline u64 reftime_to_ns(u64 reftime)
 {
 	return (reftime - WLTIMEDELTA) * 100;
@@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work)
 }
 
 /*
+ * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume.
+ * Force a sync if the guest is behind.
+ */
+static inline bool hv_implicit_sync(u64 host_time)
+{
+	struct timespec64 new_ts;
+	struct timespec64 threshold_ts;
+
+	new_ts = ns_to_timespec64(reftime_to_ns(host_time));
+	ktime_get_real_ts64(&threshold_ts);
+
+	threshold_ts.tv_sec += 5;
+
+	/*
+	 * If guest behind the host by 5 or more seconds.
+	 */
+	if (timespec64_compare(&new_ts, &threshold_ts) >= 0)
+		return true;
+
+	return false;
+}
+
+/*
  * Synchronize time with host after reboot, restore, etc.
  *
  * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM.
@@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
 	spin_unlock_irqrestore(&host_ts.lock, flags);
 
 	/* Schedule work to do do_settimeofday64() */
-	if (adj_flags & ICTIMESYNCFLAG_SYNC)
+	if ((adj_flags & ICTIMESYNCFLAG_SYNC) ||
+	    (timesync_implicit && hv_implicit_sync(host_ts.host_time)))
 		schedule_work(&adj_time_work);
 }
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index b33d5abd9beb..7f7965f3d187 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = {
 };
 
 /* The one and only one */
-static struct bus_type  hv_bus = {
+static const struct bus_type  hv_bus = {
 	.name =		"vmbus",
 	.match =		vmbus_match,
 	.shutdown =		vmbus_shutdown,
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index f6e1e55e8292..4acc1858d8ac 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -195,6 +195,8 @@ struct aspeed_pwm_tacho_data {
 	u8 fan_tach_ch_source[MAX_ASPEED_FAN_TACH_CHANNELS];
 	struct aspeed_cooling_device *cdev[8];
 	const struct attribute_group *groups[3];
+	/* protects access to shared ASPEED_PTCR_RESULT */
+	struct mutex tach_lock;
 };
 
 enum type { TYPEM, TYPEN, TYPEO };
@@ -529,6 +531,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 	u8 fan_tach_ch_source, type, mode, both;
 	int ret;
 
+	mutex_lock(&priv->tach_lock);
+
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
 	regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
 
@@ -546,6 +550,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
 		ASPEED_RPM_STATUS_SLEEP_USEC,
 		usec);
 
+	mutex_unlock(&priv->tach_lock);
+
 	/* return -ETIMEDOUT if we didn't get an answer. */
 	if (ret)
 		return ret;
@@ -915,6 +921,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	mutex_init(&priv->tach_lock);
 	priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
 			&aspeed_pwm_tacho_regmap_config);
 	if (IS_ERR(priv->regmap))
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ba82d1e79c13..b0991dde2e59 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -41,7 +41,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define PKG_SYSFS_ATTR_NO	1	/* Sysfs attribute for package temp */
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
-#define NUM_REAL_CORES		128	/* Number of Real cores per cpu */
+#define NUM_REAL_CORES		512	/* Number of Real cores per cpu */
 #define CORETEMP_NAME_LENGTH	28	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
@@ -419,7 +419,7 @@ static ssize_t show_temp(struct device *dev,
 }
 
 static int create_core_attrs(struct temp_data *tdata, struct device *dev,
-			     int attr_no)
+			     int index)
 {
 	int i;
 	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
@@ -431,13 +431,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 	};
 
 	for (i = 0; i < tdata->attr_size; i++) {
+		/*
+		 * We map the attr number to core id of the CPU
+		 * The attr number is always core id + 2
+		 * The Pkgtemp will always show up as temp1_*, if available
+		 */
+		int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2;
+
 		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH,
 			 "temp%d_%s", attr_no, suffixes[i]);
 		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
 		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
 		tdata->sd_attrs[i].dev_attr.attr.mode = 0444;
 		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
-		tdata->sd_attrs[i].index = attr_no;
+		tdata->sd_attrs[i].index = index;
 		tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
 	}
 	tdata->attr_group.attrs = tdata->attrs;
@@ -495,30 +502,25 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, index, attr_no;
+	int err, index;
 
 	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	/*
-	 * Find attr number for sysfs:
-	 * We map the attr number to core id of the CPU
-	 * The attr number is always core id + 2
-	 * The Pkgtemp will always show up as temp1_*, if available
+	 * Get the index of tdata in pdata->core_data[]
+	 * tdata for package: pdata->core_data[1]
+	 * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1]
 	 */
 	if (pkg_flag) {
-		attr_no = PKG_SYSFS_ATTR_NO;
+		index = PKG_SYSFS_ATTR_NO;
 	} else {
-		index = ida_alloc(&pdata->ida, GFP_KERNEL);
+		index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
 		if (index < 0)
 			return index;
-		pdata->cpu_map[index] = topology_core_id(cpu);
-		attr_no = index + BASE_SYSFS_ATTR_NO;
-	}
 
-	if (attr_no > MAX_CORE_DATA - 1) {
-		err = -ERANGE;
-		goto ida_free;
+		pdata->cpu_map[index] = topology_core_id(cpu);
+		index += BASE_SYSFS_ATTR_NO;
 	}
 
 	tdata = init_temp_data(cpu, pkg_flag);
@@ -544,20 +546,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 		if (get_ttarget(tdata, &pdev->dev) >= 0)
 			tdata->attr_size++;
 
-	pdata->core_data[attr_no] = tdata;
+	pdata->core_data[index] = tdata;
 
 	/* Create sysfs interfaces */
-	err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
+	err = create_core_attrs(tdata, pdata->hwmon_dev, index);
 	if (err)
 		goto exit_free;
 
 	return 0;
 exit_free:
-	pdata->core_data[attr_no] = NULL;
+	pdata->core_data[index] = NULL;
 	kfree(tdata);
 ida_free:
 	if (!pkg_flag)
-		ida_free(&pdata->ida, index);
+		ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO);
 	return err;
 }
 
@@ -780,7 +782,7 @@ static int __init coretemp_init(void)
 	if (!x86_match_cpu(coretemp_ids))
 		return -ENODEV;
 
-	max_zones = topology_max_packages() * topology_max_die_per_package();
+	max_zones = topology_max_packages() * topology_max_dies_per_package();
 	zone_devices = kcalloc(max_zones, sizeof(struct platform_device *),
 			      GFP_KERNEL);
 	if (!zone_devices)
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index 6307112c2c0c..9ed2c4b6734e 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -209,7 +209,7 @@ static ssize_t power1_average_show(struct device *dev,
 	 * With the new x86 topology modelling, x86_max_cores is the
 	 * compute unit number.
 	 */
-	cu_num = boot_cpu_data.x86_max_cores;
+	cu_num = topology_num_cores_per_package();
 
 	ret = read_registers(data);
 	if (ret)
diff --git a/drivers/hwmon/gigabyte_waterforce.c b/drivers/hwmon/gigabyte_waterforce.c
index 85e523775714..8129d7b3ceaf 100644
--- a/drivers/hwmon/gigabyte_waterforce.c
+++ b/drivers/hwmon/gigabyte_waterforce.c
@@ -146,7 +146,7 @@ static int waterforce_get_status(struct waterforce_data *priv)
 	/* Send command for getting status */
 	ret = waterforce_write_expanded(priv, get_status_cmd, GET_STATUS_CMD_LENGTH);
 	if (ret < 0)
-		return ret;
+		goto unlock_and_return;
 
 	ret = wait_for_completion_interruptible_timeout(&priv->status_report_received,
 							msecs_to_jiffies(STATUS_VALIDITY));
diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
index 8d2ef3145bca..9fbab8f02334 100644
--- a/drivers/hwmon/nct6775-core.c
+++ b/drivers/hwmon/nct6775-core.c
@@ -3512,6 +3512,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 	const u16 *reg_temp_mon, *reg_temp_alternate, *reg_temp_crit;
 	const u16 *reg_temp_crit_l = NULL, *reg_temp_crit_h = NULL;
 	int num_reg_temp, num_reg_temp_mon, num_reg_tsi_temp;
+	int num_reg_temp_config;
 	struct device *hwmon_dev;
 	struct sensor_template_group tsi_temp_tg;
 
@@ -3594,6 +3595,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6106_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6106_REG_TEMP_HYST;
 		reg_temp_config = NCT6106_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6106_REG_TEMP_CRIT;
 		reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L;
@@ -3669,6 +3671,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6106_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6106_REG_TEMP_HYST;
 		reg_temp_config = NCT6106_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6106_REG_TEMP_CRIT;
 		reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L;
@@ -3746,6 +3749,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6775_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6775_REG_TEMP_HYST;
 		reg_temp_config = NCT6775_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6775_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6775_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6775_REG_TEMP_CRIT;
 
@@ -3821,6 +3825,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6775_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6775_REG_TEMP_HYST;
 		reg_temp_config = NCT6776_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6776_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6776_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6776_REG_TEMP_CRIT;
 
@@ -3900,6 +3905,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6779_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6779_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6779_REG_TEMP_CRIT;
 
@@ -4034,6 +4040,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6779_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6779_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6779_REG_TEMP_CRIT;
 
@@ -4123,6 +4130,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		reg_temp_over = NCT6798_REG_TEMP_OVER;
 		reg_temp_hyst = NCT6798_REG_TEMP_HYST;
 		reg_temp_config = NCT6779_REG_TEMP_CONFIG;
+		num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG);
 		reg_temp_alternate = NCT6798_REG_TEMP_ALTERNATE;
 		reg_temp_crit = NCT6798_REG_TEMP_CRIT;
 
@@ -4204,7 +4212,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 				  = reg_temp_crit[src - 1];
 			if (reg_temp_crit_l && reg_temp_crit_l[i])
 				data->reg_temp[4][src - 1] = reg_temp_crit_l[i];
-			data->reg_temp_config[src - 1] = reg_temp_config[i];
+			if (i < num_reg_temp_config)
+				data->reg_temp_config[src - 1] = reg_temp_config[i];
 			data->temp_src[src - 1] = src;
 			continue;
 		}
@@ -4217,7 +4226,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data,
 		data->reg_temp[0][s] = reg_temp[i];
 		data->reg_temp[1][s] = reg_temp_over[i];
 		data->reg_temp[2][s] = reg_temp_hyst[i];
-		data->reg_temp_config[s] = reg_temp_config[i];
+		if (i < num_reg_temp_config)
+			data->reg_temp_config[s] = reg_temp_config[i];
 		if (reg_temp_crit_h && reg_temp_crit_h[i])
 			data->reg_temp[3][s] = reg_temp_crit_h[i];
 		else if (reg_temp_crit[src - 1])
diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c
index b9bb469e2d8f..e5fa10b3b8bc 100644
--- a/drivers/hwmon/pmbus/mp2975.c
+++ b/drivers/hwmon/pmbus/mp2975.c
@@ -126,6 +126,21 @@ static const struct regulator_desc __maybe_unused mp2975_reg_desc[] = {
 
 #define to_mp2975_data(x)  container_of(x, struct mp2975_data, info)
 
+static int mp2975_read_byte_data(struct i2c_client *client, int page, int reg)
+{
+	switch (reg) {
+	case PMBUS_VOUT_MODE:
+		/*
+		 * Report direct format as configured by MFR_DC_LOOP_CTRL.
+		 * Unlike on MP2971/MP2973 the reported VOUT_MODE isn't automatically
+		 * internally updated, but always reads as PB_VOUT_MODE_VID.
+		 */
+		return PB_VOUT_MODE_DIRECT;
+	default:
+		return -ENODATA;
+	}
+}
+
 static int
 mp2975_read_word_helper(struct i2c_client *client, int page, int phase, u8 reg,
 			u16 mask)
@@ -869,6 +884,7 @@ static struct pmbus_driver_info mp2975_info = {
 		PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
 		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_HAVE_POUT |
 		PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT | PMBUS_PHASE_VIRTUAL,
+	.read_byte_data = mp2975_read_byte_data,
 	.read_word_data = mp2975_read_word_data,
 #if IS_ENABLED(CONFIG_SENSORS_MP2975_REGULATOR)
 	.num_regulators = 1,
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 3757b9391e60..aa0ee8ecd6f2 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -90,10 +90,8 @@ obj-$(CONFIG_I2C_NPCM)		+= i2c-npcm7xx.o
 obj-$(CONFIG_I2C_OCORES)	+= i2c-ocores.o
 obj-$(CONFIG_I2C_OMAP)		+= i2c-omap.o
 obj-$(CONFIG_I2C_OWL)		+= i2c-owl.o
-i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o
-obj-$(CONFIG_I2C_PASEMI)	+= i2c-pasemi.o
-i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o
-obj-$(CONFIG_I2C_APPLE)	+= i2c-apple.o
+obj-$(CONFIG_I2C_PASEMI)	+= i2c-pasemi-core.o i2c-pasemi-pci.o
+obj-$(CONFIG_I2C_APPLE)		+= i2c-pasemi-core.o i2c-pasemi-platform.o
 obj-$(CONFIG_I2C_PCA_PLATFORM)	+= i2c-pca-platform.o
 obj-$(CONFIG_I2C_PNX)		+= i2c-pnx.o
 obj-$(CONFIG_I2C_PXA)		+= i2c-pxa.o
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 5511fd46a65e..ce8c4846b7fa 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -445,6 +445,7 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 			irq_status);
 		irq_handled |= (irq_status & ASPEED_I2CD_INTR_MASTER_ERRORS);
 		if (bus->master_state != ASPEED_I2C_MASTER_INACTIVE) {
+			irq_handled = irq_status;
 			bus->cmd_err = ret;
 			bus->master_state = ASPEED_I2C_MASTER_INACTIVE;
 			goto out_complete;
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 3932e8d96a17..274e987e4cfa 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -498,11 +498,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
 	/* Set block buffer mode */
 	outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv));
 
-	inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
-
 	if (read_write == I2C_SMBUS_WRITE) {
 		len = data->block[0];
 		outb_p(len, SMBHSTDAT0(priv));
+		inb_p(SMBHSTCNT(priv));	/* reset the data buffer index */
 		for (i = 0; i < len; i++)
 			outb_p(data->block[i+1], SMBBLKDAT(priv));
 	}
@@ -520,6 +519,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
 		}
 
 		data->block[0] = len;
+		inb_p(SMBHSTCNT(priv));	/* reset the data buffer index */
 		for (i = 0; i < len; i++)
 			data->block[i + 1] = inb_p(SMBBLKDAT(priv));
 	}
@@ -1416,7 +1416,6 @@ static void i801_add_mux(struct i801_priv *priv)
 		lookup->table[i] = GPIO_LOOKUP(mux_config->gpio_chip,
 					       mux_config->gpios[i], "mux", 0);
 	gpiod_add_lookup_table(lookup);
-	priv->lookup = lookup;
 
 	/*
 	 * Register the mux device, we use PLATFORM_DEVID_NONE here
@@ -1430,7 +1429,10 @@ static void i801_add_mux(struct i801_priv *priv)
 				sizeof(struct i2c_mux_gpio_platform_data));
 	if (IS_ERR(priv->mux_pdev)) {
 		gpiod_remove_lookup_table(lookup);
+		devm_kfree(dev, lookup);
 		dev_err(dev, "Failed to register i2c-mux-gpio device\n");
+	} else {
+		priv->lookup = lookup;
 	}
 }
 
@@ -1742,9 +1744,9 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	i801_enable_host_notify(&priv->adapter);
 
-	i801_probe_optional_slaves(priv);
 	/* We ignore errors - multiplexing is optional */
 	i801_add_mux(priv);
+	i801_probe_optional_slaves(priv);
 
 	pci_set_drvdata(dev, priv);
 
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 88a053987403..60e813137f84 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -803,6 +803,11 @@ static irqreturn_t i2c_imx_slave_handle(struct imx_i2c_struct *i2c_imx,
 		ctl &= ~I2CR_MTX;
 		imx_i2c_write_reg(ctl, i2c_imx, IMX_I2C_I2CR);
 		imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR);
+
+		/* flag the last byte as processed */
+		i2c_imx_slave_event(i2c_imx,
+				    I2C_SLAVE_READ_PROCESSED, &value);
+
 		i2c_imx_slave_finish_op(i2c_imx);
 		return IRQ_HANDLED;
 	}
diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c
index 7d54a9f34c74..bd8becbdeeb2 100644
--- a/drivers/i2c/busses/i2c-pasemi-core.c
+++ b/drivers/i2c/busses/i2c-pasemi-core.c
@@ -369,6 +369,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe);
 
 irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
 {
@@ -378,3 +379,8 @@ irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
 	complete(&smbus->irq_completion);
 	return IRQ_HANDLED;
 }
+EXPORT_SYMBOL_GPL(pasemi_irq_handler);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Olof Johansson <olof@lixom.net>");
+MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver");
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 0d2e7171e3a6..da94df466e83 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -613,20 +613,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i
 
 		peripheral.addr = msgs[i].addr;
 
+		ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
+				    &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c);
+		if (ret)
+			goto err;
+
 		if (msgs[i].flags & I2C_M_RD) {
 			ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
 					    &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c);
 			if (ret)
 				goto err;
-		}
-
-		ret =  geni_i2c_gpi(gi2c, &msgs[i], &config,
-				    &tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c);
-		if (ret)
-			goto err;
 
-		if (msgs[i].flags & I2C_M_RD)
 			dma_async_issue_pending(gi2c->rx_c);
+		}
+
 		dma_async_issue_pending(gi2c->tx_c);
 
 		timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT);
diff --git a/drivers/i2c/busses/i2c-wmt.c b/drivers/i2c/busses/i2c-wmt.c
index ec2a8da134e5..198afee5233c 100644
--- a/drivers/i2c/busses/i2c-wmt.c
+++ b/drivers/i2c/busses/i2c-wmt.c
@@ -378,11 +378,15 @@ static int wmt_i2c_probe(struct platform_device *pdev)
 
 	err = i2c_add_adapter(adap);
 	if (err)
-		return err;
+		goto err_disable_clk;
 
 	platform_set_drvdata(pdev, i2c_dev);
 
 	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(i2c_dev->clk);
+	return err;
 }
 
 static void wmt_i2c_remove(struct platform_device *pdev)
diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig
index 91adcac875a4..c9d7afe489e8 100644
--- a/drivers/iio/accel/Kconfig
+++ b/drivers/iio/accel/Kconfig
@@ -219,10 +219,12 @@ config BMA400
 
 config BMA400_I2C
 	tristate
+	select REGMAP_I2C
 	depends on BMA400
 
 config BMA400_SPI
 	tristate
+	select REGMAP_SPI
 	depends on BMA400
 
 config BMC150_ACCEL
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index 90b7ae6d42b7..484fe2e9fb17 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -1429,9 +1429,11 @@ static int adxl367_verify_devid(struct adxl367_state *st)
 	unsigned int val;
 	int ret;
 
-	ret = regmap_read_poll_timeout(st->regmap, ADXL367_REG_DEVID, val,
-				       val == ADXL367_DEVID_AD, 1000, 10000);
+	ret = regmap_read(st->regmap, ADXL367_REG_DEVID, &val);
 	if (ret)
+		return dev_err_probe(st->dev, ret, "Failed to read dev id\n");
+
+	if (val != ADXL367_DEVID_AD)
 		return dev_err_probe(st->dev, -ENODEV,
 				     "Invalid dev id 0x%02X, expected 0x%02X\n",
 				     val, ADXL367_DEVID_AD);
@@ -1510,6 +1512,8 @@ int adxl367_probe(struct device *dev, const struct adxl367_ops *ops,
 	if (ret)
 		return ret;
 
+	fsleep(15000);
+
 	ret = adxl367_verify_devid(st);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/accel/adxl367_i2c.c b/drivers/iio/accel/adxl367_i2c.c
index b595fe94f3a3..62c74bdc0d77 100644
--- a/drivers/iio/accel/adxl367_i2c.c
+++ b/drivers/iio/accel/adxl367_i2c.c
@@ -11,7 +11,7 @@
 
 #include "adxl367.h"
 
-#define ADXL367_I2C_FIFO_DATA	0x42
+#define ADXL367_I2C_FIFO_DATA	0x18
 
 struct adxl367_i2c_state {
 	struct regmap *regmap;
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index feb86fe6c422..62490424b6ae 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -1821,7 +1821,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st)
 {
 	struct device *dev = &st->spi->dev;
 	struct device_node *of_node = dev_of_node(dev);
-	struct clk_init_data init;
+	struct clk_init_data init = {};
 	const char *clk_name;
 	int ret;
 
@@ -1891,10 +1891,14 @@ static int ad4130_setup(struct iio_dev *indio_dev)
 		return ret;
 
 	/*
-	 * Configure all GPIOs for output. If configured, the interrupt function
-	 * of P2 takes priority over the GPIO out function.
+	 * Configure unused GPIOs for output. If configured, the interrupt
+	 * function of P2 takes priority over the GPIO out function.
 	 */
-	val =  AD4130_IO_CONTROL_GPIO_CTRL_MASK;
+	val = 0;
+	for (i = 0; i < AD4130_MAX_GPIOS; i++)
+		if (st->pins_fn[i + AD4130_AIN2_P1] == AD4130_PIN_FN_NONE)
+			val |= FIELD_PREP(AD4130_IO_CONTROL_GPIO_CTRL_MASK, BIT(i));
+
 	val |= FIELD_PREP(AD4130_IO_CONTROL_INT_PIN_SEL_MASK, st->int_pin_sel);
 
 	ret = regmap_write(st->regmap, AD4130_IO_CONTROL_REG, val);
diff --git a/drivers/iio/adc/ad7091r8.c b/drivers/iio/adc/ad7091r8.c
index 57700f124803..700564305057 100644
--- a/drivers/iio/adc/ad7091r8.c
+++ b/drivers/iio/adc/ad7091r8.c
@@ -195,7 +195,7 @@ static int ad7091r8_gpio_setup(struct ad7091r_state *st)
 	st->reset_gpio = devm_gpiod_get_optional(st->dev, "reset",
 						 GPIOD_OUT_HIGH);
 	if (IS_ERR(st->reset_gpio))
-		return dev_err_probe(st->dev, PTR_ERR(st->convst_gpio),
+		return dev_err_probe(st->dev, PTR_ERR(st->reset_gpio),
 				     "Error on requesting reset GPIO\n");
 
 	if (st->reset_gpio) {
diff --git a/drivers/iio/humidity/Kconfig b/drivers/iio/humidity/Kconfig
index 2de5494e7c22..b15b7a3b66d5 100644
--- a/drivers/iio/humidity/Kconfig
+++ b/drivers/iio/humidity/Kconfig
@@ -48,6 +48,18 @@ config HDC2010
 	  To compile this driver as a module, choose M here: the module
 	  will be called hdc2010.
 
+config HDC3020
+	tristate "TI HDC3020 relative humidity and temperature sensor"
+	depends on I2C
+	select CRC8
+	help
+	  Say yes here to build support for the Texas Instruments
+	  HDC3020, HDC3021 and HDC3022 relative humidity and temperature
+	  sensors.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called hdc3020.
+
 config HID_SENSOR_HUMIDITY
 	tristate "HID Environmental humidity sensor"
 	depends on HID_SENSOR_HUB
diff --git a/drivers/iio/humidity/Makefile b/drivers/iio/humidity/Makefile
index f19ff3de97c5..5fbeef299f61 100644
--- a/drivers/iio/humidity/Makefile
+++ b/drivers/iio/humidity/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_AM2315) += am2315.o
 obj-$(CONFIG_DHT11) += dht11.o
 obj-$(CONFIG_HDC100X) += hdc100x.o
 obj-$(CONFIG_HDC2010) += hdc2010.o
+obj-$(CONFIG_HDC3020) += hdc3020.o
 obj-$(CONFIG_HID_SENSOR_HUMIDITY) += hid-sensor-humidity.o
 
 hts221-y := hts221_core.o \
diff --git a/drivers/iio/humidity/hdc3020.c b/drivers/iio/humidity/hdc3020.c
index 4e3311170725..ed70415512f6 100644
--- a/drivers/iio/humidity/hdc3020.c
+++ b/drivers/iio/humidity/hdc3020.c
@@ -322,7 +322,7 @@ static int hdc3020_read_raw(struct iio_dev *indio_dev,
 		if (chan->type != IIO_TEMP)
 			return -EINVAL;
 
-		*val = 16852;
+		*val = -16852;
 		return IIO_VAL_INT;
 
 	default:
diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig
index 83e53acfbe88..c7f5866a177d 100644
--- a/drivers/iio/imu/bno055/Kconfig
+++ b/drivers/iio/imu/bno055/Kconfig
@@ -8,6 +8,7 @@ config BOSCH_BNO055
 config BOSCH_BNO055_SERIAL
 	tristate "Bosch BNO055 attached via UART"
 	depends on SERIAL_DEV_BUS
+	select REGMAP
 	select BOSCH_BNO055
 	help
 	  Enable this to support Bosch BNO055 IMUs attached via UART.
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 66d4ba088e70..d4f9b5d8d28d 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -109,6 +109,8 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	/* compute and process only all complete datum */
 	nb = fifo_count / bytes_per_datum;
 	fifo_count = nb * bytes_per_datum;
+	if (nb == 0)
+		goto end_session;
 	/* Each FIFO data contains all sensors, so same number for FIFO and sensor data */
 	fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider);
 	inv_sensors_timestamp_interrupt(&st->timestamp, fifo_period, nb, nb, pf->timestamp);
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 676704f9151f..e6e6e94452a3 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -111,6 +111,7 @@ int inv_mpu6050_prepare_fifo(struct inv_mpu6050_state *st, bool enable)
 	if (enable) {
 		/* reset timestamping */
 		inv_sensors_timestamp_reset(&st->timestamp);
+		inv_sensors_timestamp_apply_odr(&st->timestamp, 0, 0, 0);
 		/* reset FIFO */
 		d = st->chip_config.user_ctrl | INV_MPU6050_BIT_FIFO_RST;
 		ret = regmap_write(st->map, st->reg->user_ctrl, d);
@@ -184,6 +185,10 @@ static int inv_mpu6050_set_enable(struct iio_dev *indio_dev, bool enable)
 		if (result)
 			goto error_power_off;
 	} else {
+		st->chip_config.gyro_fifo_enable = 0;
+		st->chip_config.accl_fifo_enable = 0;
+		st->chip_config.temp_fifo_enable = 0;
+		st->chip_config.magn_fifo_enable = 0;
 		result = inv_mpu6050_prepare_fifo(st, false);
 		if (result)
 			goto error_power_off;
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 9a85752124dd..173dc00762a1 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1584,10 +1584,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev)
 	ret = iio_device_register_sysfs_group(indio_dev,
 					      &iio_dev_opaque->chan_attr_group);
 	if (ret)
-		goto error_clear_attrs;
+		goto error_free_chan_attrs;
 
 	return 0;
 
+error_free_chan_attrs:
+	kfree(iio_dev_opaque->chan_attr_group.attrs);
+	iio_dev_opaque->chan_attr_group.attrs = NULL;
 error_clear_attrs:
 	iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list);
 
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index 5cd27f04b45e..b6c4bef2a7bb 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -226,6 +226,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
+		ret = 0;
 		break;
 	default:
 		break;
diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c
index 69938204456f..42b70cd42b39 100644
--- a/drivers/iio/magnetometer/rm3100-core.c
+++ b/drivers/iio/magnetometer/rm3100-core.c
@@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
 	struct rm3100_data *data;
 	unsigned int tmp;
 	int ret;
+	int samp_rate_index;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
 	if (!indio_dev)
@@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
 	ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp);
 	if (ret < 0)
 		return ret;
+
+	samp_rate_index = tmp - RM3100_TMRC_OFFSET;
+	if (samp_rate_index < 0 || samp_rate_index >=  RM3100_SAMP_NUM) {
+		dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n");
+		return -EINVAL;
+	}
 	/* Initializing max wait time, which is double conversion time. */
-	data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2]
-				* 2;
+	data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2;
 
 	/* Cycle count values may not be what we want. */
 	if ((tmp - RM3100_TMRC_OFFSET) == 0)
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 433d6fac83c4..a444d4b2978b 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -4,6 +4,7 @@
  *
  * Inspired by the older BMP085 driver drivers/misc/bmp085-spi.c
  */
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/spi/spi.h>
 #include <linux/err.h>
@@ -35,6 +36,34 @@ static int bmp280_regmap_spi_read(void *context, const void *reg,
 	return spi_write_then_read(spi, reg, reg_size, val, val_size);
 }
 
+static int bmp380_regmap_spi_read(void *context, const void *reg,
+				  size_t reg_size, void *val, size_t val_size)
+{
+	struct spi_device *spi = to_spi_device(context);
+	u8 rx_buf[4];
+	ssize_t status;
+
+	/*
+	 * Maximum number of consecutive bytes read for a temperature or
+	 * pressure measurement is 3.
+	 */
+	if (val_size > 3)
+		return -EINVAL;
+
+	/*
+	 * According to the BMP3xx datasheets, for a basic SPI read opertion,
+	 * the first byte needs to be dropped and the rest are the requested
+	 * data.
+	 */
+	status = spi_write_then_read(spi, reg, 1, rx_buf, val_size + 1);
+	if (status)
+		return status;
+
+	memcpy(val, rx_buf + 1, val_size);
+
+	return 0;
+}
+
 static struct regmap_bus bmp280_regmap_bus = {
 	.write = bmp280_regmap_spi_write,
 	.read = bmp280_regmap_spi_read,
@@ -42,10 +71,19 @@ static struct regmap_bus bmp280_regmap_bus = {
 	.val_format_endian_default = REGMAP_ENDIAN_BIG,
 };
 
+static struct regmap_bus bmp380_regmap_bus = {
+	.write = bmp280_regmap_spi_write,
+	.read = bmp380_regmap_spi_read,
+	.read_flag_mask = BIT(7),
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
+};
+
 static int bmp280_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	const struct bmp280_chip_info *chip_info;
+	struct regmap_bus *bmp_regmap_bus;
 	struct regmap *regmap;
 	int ret;
 
@@ -58,8 +96,18 @@ static int bmp280_spi_probe(struct spi_device *spi)
 
 	chip_info = spi_get_device_match_data(spi);
 
+	switch (chip_info->chip_id[0]) {
+	case BMP380_CHIP_ID:
+	case BMP390_CHIP_ID:
+		bmp_regmap_bus = &bmp380_regmap_bus;
+		break;
+	default:
+		bmp_regmap_bus = &bmp280_regmap_bus;
+		break;
+	}
+
 	regmap = devm_regmap_init(&spi->dev,
-				  &bmp280_regmap_bus,
+				  bmp_regmap_bus,
 				  &spi->dev,
 				  chip_info->regmap_config);
 	if (IS_ERR(regmap)) {
@@ -87,6 +135,7 @@ static const struct of_device_id bmp280_of_spi_match[] = {
 MODULE_DEVICE_TABLE(of, bmp280_of_spi_match);
 
 static const struct spi_device_id bmp280_spi_id[] = {
+	{ "bmp085", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp180", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp181", (kernel_ulong_t)&bmp180_chip_info },
 	{ "bmp280", (kernel_ulong_t)&bmp280_chip_info },
diff --git a/drivers/iio/pressure/dlhl60d.c b/drivers/iio/pressure/dlhl60d.c
index 28c8269ba65d..0bba4c5a8d40 100644
--- a/drivers/iio/pressure/dlhl60d.c
+++ b/drivers/iio/pressure/dlhl60d.c
@@ -250,18 +250,17 @@ static irqreturn_t dlh_trigger_handler(int irq, void *private)
 	struct dlh_state *st = iio_priv(indio_dev);
 	int ret;
 	unsigned int chn, i = 0;
-	__be32 tmp_buf[2];
+	__be32 tmp_buf[2] = { };
 
 	ret = dlh_start_capture_and_read(st);
 	if (ret)
 		goto out;
 
 	for_each_set_bit(chn, indio_dev->active_scan_mask,
-		indio_dev->masklength) {
-		memcpy(tmp_buf + i,
+			 indio_dev->masklength) {
+		memcpy(&tmp_buf[i++],
 			&st->rx_buf[1] + chn * DLH_NUM_DATA_BYTES,
 			DLH_NUM_DATA_BYTES);
-		i++;
 	}
 
 	iio_push_to_buffers(indio_dev, tmp_buf);
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 824349659d69..ce9c5bae83bf 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -401,6 +401,10 @@ static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd)
 	struct bnxt_re_fence_data *fence = &pd->fence;
 	struct ib_mr *ib_mr = &fence->mr->ib_mr;
 	struct bnxt_qplib_swqe *wqe = &fence->bind_wqe;
+	struct bnxt_re_dev *rdev = pd->rdev;
+
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return;
 
 	memset(wqe, 0, sizeof(*wqe));
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW;
@@ -455,6 +459,9 @@ static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd)
 	struct device *dev = &rdev->en_dev->pdev->dev;
 	struct bnxt_re_mr *mr = fence->mr;
 
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return;
+
 	if (fence->mw) {
 		bnxt_re_dealloc_mw(fence->mw);
 		fence->mw = NULL;
@@ -486,6 +493,9 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd)
 	struct ib_mw *mw;
 	int rc;
 
+	if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx))
+		return 0;
+
 	dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES,
 				  DMA_BIDIRECTIONAL);
 	rc = dma_mapping_error(dev, dma_addr);
@@ -1817,7 +1827,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 	switch (srq_attr_mask) {
 	case IB_SRQ_MAX_WR:
 		/* SRQ resize is not supported */
-		break;
+		return -EINVAL;
 	case IB_SRQ_LIMIT:
 		/* Change the SRQ threshold */
 		if (srq_attr->srq_limit > srq->qplib_srq.max_wqe)
@@ -1832,13 +1842,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 		/* On success, update the shadow */
 		srq->srq_limit = srq_attr->srq_limit;
 		/* No need to Build and send response back to udata */
-		break;
+		return 0;
 	default:
 		ibdev_err(&rdev->ibdev,
 			  "Unsupported srq_attr_mask 0x%x", srq_attr_mask);
 		return -EINVAL;
 	}
-	return 0;
 }
 
 int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr)
@@ -2556,11 +2565,6 @@ static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr,
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV;
 	wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey;
 
-	/* Need unconditional fence for local invalidate
-	 * opcode to work as expected.
-	 */
-	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
-
 	if (wr->send_flags & IB_SEND_SIGNALED)
 		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
 	if (wr->send_flags & IB_SEND_SOLICITED)
@@ -2583,12 +2587,6 @@ static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr,
 	wqe->frmr.levels = qplib_frpl->hwq.level;
 	wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR;
 
-	/* Need unconditional fence for reg_mr
-	 * opcode to function as expected.
-	 */
-
-	wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
-
 	if (wr->wr.send_flags & IB_SEND_SIGNALED)
 		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP;
 
@@ -2719,6 +2717,18 @@ bad:
 	return rc;
 }
 
+static void bnxt_re_legacy_set_uc_fence(struct bnxt_qplib_swqe *wqe)
+{
+	/* Need unconditional fence for non-wire memory opcode
+	 * to work as expected.
+	 */
+	if (wqe->type == BNXT_QPLIB_SWQE_TYPE_LOCAL_INV ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_REG_MR ||
+	    wqe->type == BNXT_QPLIB_SWQE_TYPE_BIND_MW)
+		wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE;
+}
+
 int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 		      const struct ib_send_wr **bad_wr)
 {
@@ -2798,8 +2808,11 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr,
 			rc = -EINVAL;
 			goto bad;
 		}
-		if (!rc)
+		if (!rc) {
+			if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx))
+				bnxt_re_legacy_set_uc_fence(&wqe);
 			rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe);
+		}
 bad:
 		if (rc) {
 			ibdev_err(&qp->rdev->ibdev,
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index f022c922fae5..54b4d2f3a5d8 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -280,9 +280,6 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
 
 static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev)
 {
-
-	if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
-		return;
 	rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev);
 	if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) {
 		bnxt_re_set_resource_limits(rdev);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index c98e04fe2ddd..439d0c7c5d0c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -744,7 +744,8 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
 	bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, &sbuf, sizeof(req),
 				sizeof(resp), 0);
 	rc = bnxt_qplib_rcfw_send_message(rcfw, &msg);
-	srq->threshold = le16_to_cpu(sb->srq_limit);
+	if (!rc)
+		srq->threshold = le16_to_cpu(sb->srq_limit);
 	dma_free_coherent(&rcfw->pdev->dev, sbuf.size,
 			  sbuf.sb, sbuf.dma_addr);
 
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 68c621ff59d0..5a91cbda4aee 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -2086,7 +2086,7 @@ int init_credit_return(struct hfi1_devdata *dd)
 				   "Unable to allocate credit return DMA range for NUMA %d\n",
 				   i);
 			ret = -ENOMEM;
-			goto done;
+			goto free_cr_base;
 		}
 	}
 	set_dev_node(&dd->pcidev->dev, dd->node);
@@ -2094,6 +2094,10 @@ int init_credit_return(struct hfi1_devdata *dd)
 	ret = 0;
 done:
 	return ret;
+
+free_cr_base:
+	free_credit_return(dd);
+	goto done;
 }
 
 void free_credit_return(struct hfi1_devdata *dd)
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 6e5ac2023328..b67d23b1f286 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx)
 {
 	int rval = 0;
 
-	if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) {
+	if ((unlikely(tx->num_desc == tx->desc_limit))) {
 		rval = _extend_sdma_tx_descs(dd, tx);
 		if (rval) {
 			__sdma_txclean(dd, tx);
diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h
index 8fb752f2eda2..2cb4b96db721 100644
--- a/drivers/infiniband/hw/irdma/defs.h
+++ b/drivers/infiniband/hw/irdma/defs.h
@@ -346,6 +346,7 @@ enum irdma_cqp_op_type {
 #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES				0x050b
 #define IRDMA_AE_LLP_DOUBT_REACHABILITY					0x050c
 #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED				0x050e
+#define IRDMA_AE_LLP_TOO_MANY_RNRS					0x050f
 #define IRDMA_AE_RESOURCE_EXHAUSTION					0x0520
 #define IRDMA_AE_RESET_SENT						0x0601
 #define IRDMA_AE_TERMINATE_SENT						0x0602
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index bd4b2b896444..ad50b77282f8 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -387,6 +387,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf)
 		case IRDMA_AE_LLP_TOO_MANY_RETRIES:
 		case IRDMA_AE_LCE_QP_CATASTROPHIC:
 		case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC:
+		case IRDMA_AE_LLP_TOO_MANY_RNRS:
 		case IRDMA_AE_LCE_CQ_CATASTROPHIC:
 		case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG:
 		default:
@@ -570,6 +571,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf,
 	dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx);
 	irq_update_affinity_hint(msix_vec->irq, NULL);
 	free_irq(msix_vec->irq, dev_id);
+	if (rf == dev_id) {
+		tasklet_kill(&rf->dpc_tasklet);
+	} else {
+		struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id;
+
+		tasklet_kill(&iwceq->dpc_tasklet);
+	}
 }
 
 /**
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index b5eb8d421988..0b046c061742 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -839,7 +839,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr,
 
 	if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline ||
 	    init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags ||
-	    init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags)
+	    init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags ||
+	    init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta ||
+	    init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta)
 		return -EINVAL;
 
 	if (rdma_protocol_roce(&iwdev->ibdev, 1)) {
@@ -2184,9 +2186,8 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 		info.cq_base_pa = iwcq->kmem.pa;
 	}
 
-	if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
-		info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2,
-						 (u32)IRDMA_MAX_CQ_READ_THRESH);
+	info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2,
+					 (u32)IRDMA_MAX_CQ_READ_THRESH);
 
 	if (irdma_sc_cq_init(cq, &info)) {
 		ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n");
diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
index f87531318feb..a78a067e3ce7 100644
--- a/drivers/infiniband/hw/mlx5/cong.c
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -458,6 +458,12 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num)
 	dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev));
 
 	for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) {
+		if ((i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID ||
+		     i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP))
+			if (!MLX5_CAP_GEN(mdev, roce) ||
+			    !MLX5_CAP_ROCE(mdev, roce_cc_general))
+				continue;
+
 		dbg_cc_params->params[i].offset = i;
 		dbg_cc_params->params[i].dev = dev;
 		dbg_cc_params->params[i].port_num = port_num;
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 869369cb5b5f..253fea374a72 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2949,7 +2949,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 	MLX5_IB_METHOD_DEVX_OBJ_MODIFY,
 	UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE,
 			UVERBS_IDR_ANY_OBJECT,
-			UVERBS_ACCESS_WRITE,
+			UVERBS_ACCESS_READ,
 			UA_MANDATORY),
 	UVERBS_ATTR_PTR_IN(
 		MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN,
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index df1d1b0a3ef7..9947feb7fb8a 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -78,7 +78,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 		 */
 		copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start,
 			       left);
-		memcpy(eseg->inline_hdr.start, pdata, copysz);
+		memcpy(eseg->inline_hdr.data, pdata, copysz);
 		stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) -
 			       sizeof(eseg->inline_hdr.start) + copysz, 16);
 		*size += stride / 16;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 7887a6786ed4..f118ce0a9a61 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 		/* RQ - read access only (0) */
 		rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr,
 					  ureq.rq_len, true, 0, alloc_and_init);
-		if (rc)
+		if (rc) {
+			ib_umem_release(qp->usq.umem);
+			qp->usq.umem = NULL;
+			if (rdma_protocol_roce(&dev->ibdev, 1)) {
+				qedr_free_pbl(dev, &qp->usq.pbl_info,
+					      qp->usq.pbl_tbl);
+			} else {
+				kfree(qp->usq.pbl_tbl);
+			}
 			return rc;
+		}
 	}
 
 	memset(&in_params, 0, sizeof(in_params));
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 58f70cfec45a..040234c01be4 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444);
 MODULE_PARM_DESC(srpt_srq_size,
 		 "Shared receive queue (SRQ) size.");
 
+static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp)
+{
+	return kstrtou64(buffer, 16, (u64 *)kp->arg);
+}
 static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp)
 {
 	return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg);
 }
-module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid,
-		  0444);
+module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x,
+		  &srpt_service_guid, 0444);
 MODULE_PARM_DESC(srpt_service_guid,
 		 "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA.");
 
@@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s)
 /**
  * srpt_qp_event - QP event callback function
  * @event: Description of the event that occurred.
- * @ch: SRPT RDMA channel.
+ * @ptr: SRPT RDMA channel.
  */
-static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch)
+static void srpt_qp_event(struct ib_event *event, void *ptr)
 {
+	struct srpt_rdma_ch *ch = ptr;
+
 	pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n",
 		 event->event, ch, ch->sess_name, ch->qp->qp_num,
 		 get_ch_state_name(ch->state));
@@ -1807,8 +1813,7 @@ retry:
 	ch->cq_size = ch->rq_size + sq_size;
 
 	qp_init->qp_context = (void *)ch;
-	qp_init->event_handler
-		= (void(*)(struct ib_event *, void*))srpt_qp_event;
+	qp_init->event_handler = srpt_qp_event;
 	qp_init->send_cq = ch->cq;
 	qp_init->recv_cq = ch->cq;
 	qp_init->sq_sig_type = IB_SIGNAL_REQ_WR;
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index b1244d7df6cc..14c828adebf7 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -130,7 +130,12 @@ static const struct xpad_device {
 	{ 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 },
 	{ 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 },
 	{ 0x03eb, 0xff02, "Wooting Two (Legacy)", 0, XTYPE_XBOX360 },
+	{ 0x03f0, 0x038D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wired */
+	{ 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 },			/* wireless */
 	{ 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },
+	{ 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE },
+	{ 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE },		/* v2 */
+	{ 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
@@ -294,6 +299,7 @@ static const struct xpad_device {
 	{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfd01, "Razer Onza Classic Edition", 0, XTYPE_XBOX360 },
 	{ 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -462,6 +468,7 @@ static const struct usb_device_id xpad_table[] = {
 	{ USB_INTERFACE_INFO('X', 'B', 0) },	/* Xbox USB-IF not-approved class */
 	XPAD_XBOX360_VENDOR(0x0079),		/* GPD Win 2 controller */
 	XPAD_XBOX360_VENDOR(0x03eb),		/* Wooting Keyboards (Legacy) */
+	XPAD_XBOX360_VENDOR(0x03f0),		/* HP HyperX Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x03f0),		/* HP HyperX Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x044f),		/* Thrustmaster Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft Xbox 360 controllers */
@@ -491,6 +498,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x15e4),		/* Numark Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x162e),		/* Joytech Xbox 360 controllers */
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
+	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 13ef6284223d..7f67f9f2946b 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -811,7 +811,6 @@ static int atkbd_probe(struct atkbd *atkbd)
 {
 	struct ps2dev *ps2dev = &atkbd->ps2dev;
 	unsigned char param[2];
-	bool skip_getid;
 
 /*
  * Some systems, where the bit-twiddling when testing the io-lines of the
@@ -825,6 +824,11 @@ static int atkbd_probe(struct atkbd *atkbd)
 				 "keyboard reset failed on %s\n",
 				 ps2dev->serio->phys);
 
+	if (atkbd_skip_getid(atkbd)) {
+		atkbd->id = 0xab83;
+		goto deactivate_kbd;
+	}
+
 /*
  * Then we check the keyboard ID. We should get 0xab83 under normal conditions.
  * Some keyboards report different values, but the first byte is always 0xab or
@@ -833,18 +837,17 @@ static int atkbd_probe(struct atkbd *atkbd)
  */
 
 	param[0] = param[1] = 0xa5;	/* initialize with invalid values */
-	skip_getid = atkbd_skip_getid(atkbd);
-	if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
+	if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) {
 
 /*
- * If the get ID command was skipped or failed, we check if we can at least set
+ * If the get ID command failed, we check if we can at least set
  * the LEDs on the keyboard. This should work on every keyboard out there.
  * It also turns the LEDs off, which we want anyway.
  */
 		param[0] = 0;
 		if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS))
 			return -1;
-		atkbd->id = skip_getid ? 0xab83 : 0xabba;
+		atkbd->id = 0xabba;
 		return 0;
 	}
 
@@ -860,6 +863,7 @@ static int atkbd_probe(struct atkbd *atkbd)
 		return -1;
 	}
 
+deactivate_kbd:
 /*
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index ba00ecfbd343..b41fd1240f43 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -315,12 +315,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 
 			error = devm_gpio_request_one(dev, button->gpio,
 					flags, button->desc ? : DRV_NAME);
-			if (error) {
-				dev_err(dev,
-					"unable to claim gpio %u, err=%d\n",
-					button->gpio, error);
-				return error;
-			}
+			if (error)
+				return dev_err_probe(dev, error,
+						     "unable to claim gpio %u\n",
+						     button->gpio);
 
 			bdata->gpiod = gpio_to_desc(button->gpio);
 			if (!bdata->gpiod) {
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 258d5fe3d395..42eaebb3bf5c 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -978,12 +978,12 @@ static int rmi_driver_remove(struct device *dev)
 
 	rmi_disable_irq(rmi_dev, false);
 
-	irq_domain_remove(data->irqdomain);
-	data->irqdomain = NULL;
-
 	rmi_f34_remove_sysfs(rmi_dev);
 	rmi_free_function_list(rmi_dev);
 
+	irq_domain_remove(data->irqdomain);
+	data->irqdomain = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index b585b1dab870..dfc6c581873b 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -635,6 +635,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
 	},
 	{
+		/* Fujitsu Lifebook U728 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
+	{
 		/* Gigabyte M912 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
@@ -1210,6 +1218,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	},
 	{
 		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX)
+	},
+	{
+		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
 		},
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index af32fbe57b63..b068ff8afbc9 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -884,7 +884,8 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
 		}
 	}
 
-	if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) {
+	/* Some devices with gpio_int_idx 0 list a third unused GPIO */
+	if ((ts->gpio_count == 2 || ts->gpio_count == 3) && ts->gpio_int_idx == 0) {
 		ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO;
 		gpio_mapping = acpi_goodix_int_first_gpios;
 	} else if (ts->gpio_count == 2 && ts->gpio_int_idx == 1) {
diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c
index 20331e119beb..03d626776ba1 100644
--- a/drivers/interconnect/qcom/sc8180x.c
+++ b/drivers/interconnect/qcom/sc8180x.c
@@ -1372,6 +1372,7 @@ static struct qcom_icc_bcm bcm_mm0 = {
 
 static struct qcom_icc_bcm bcm_co0 = {
 	.name = "CO0",
+	.keepalive = true,
 	.num_nodes = 1,
 	.nodes = { &slv_qns_cdsp_mem_noc }
 };
diff --git a/drivers/interconnect/qcom/sm8550.c b/drivers/interconnect/qcom/sm8550.c
index 629faa4c9aae..fc22cecf650f 100644
--- a/drivers/interconnect/qcom/sm8550.c
+++ b/drivers/interconnect/qcom/sm8550.c
@@ -2223,6 +2223,7 @@ static struct platform_driver qnoc_driver = {
 	.driver = {
 		.name = "qnoc-sm8550",
 		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
 	},
 };
 
diff --git a/drivers/interconnect/qcom/sm8650.c b/drivers/interconnect/qcom/sm8650.c
index b83de54577b6..b962e6c233ef 100644
--- a/drivers/interconnect/qcom/sm8650.c
+++ b/drivers/interconnect/qcom/sm8650.c
@@ -1160,7 +1160,7 @@ static struct qcom_icc_node qns_gemnoc_sf = {
 
 static struct qcom_icc_bcm bcm_acv = {
 	.name = "ACV",
-	.enable_mask = BIT(3),
+	.enable_mask = BIT(0),
 	.num_nodes = 1,
 	.nodes = { &ebi },
 };
diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c
index d19501d913b3..cbaf4f9c41be 100644
--- a/drivers/interconnect/qcom/x1e80100.c
+++ b/drivers/interconnect/qcom/x1e80100.c
@@ -1586,6 +1586,7 @@ static struct qcom_icc_node qns_pcie_south_gem_noc_pcie = {
 
 static struct qcom_icc_bcm bcm_acv = {
 	.name = "ACV",
+	.enable_mask = BIT(3),
 	.num_nodes = 1,
 	.nodes = { &ebi },
 };
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 9a29d742617e..0d6095290b6a 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -179,7 +179,7 @@ config FSL_PAMU
 config MSM_IOMMU
 	bool "MSM IOMMU Support"
 	depends on ARM
-	depends on ARCH_MSM8X60 || ARCH_MSM8960 || COMPILE_TEST
+	depends on ARCH_QCOM || COMPILE_TEST
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_ARMV7S
 	help
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 8b3601f285fd..c970eae2313d 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -164,5 +164,4 @@ void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
 				  u64 *root, int mode);
 struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
 
-extern bool amd_iommu_snp_en;
 #endif
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index c83bd0c2a1c9..480e7681f4f3 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -30,6 +30,7 @@
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/set_memory.h>
+#include <asm/sev.h>
 
 #include <linux/crash_dump.h>
 
@@ -3221,6 +3222,36 @@ out:
 	return true;
 }
 
+static void iommu_snp_enable(void)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return;
+	/*
+	 * The SNP support requires that IOMMU must be enabled, and is
+	 * not configured in the passthrough mode.
+	 */
+	if (no_iommu || iommu_default_passthrough()) {
+		pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n");
+		return;
+	}
+
+	amd_iommu_snp_en = check_feature(FEATURE_SNP);
+	if (!amd_iommu_snp_en) {
+		pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n");
+		return;
+	}
+
+	pr_info("IOMMU SNP support enabled.\n");
+
+	/* Enforce IOMMU v1 pagetable when SNP is enabled. */
+	if (amd_iommu_pgtable != AMD_IOMMU_V1) {
+		pr_warn("Forcing use of AMD IOMMU v1 page table due to SNP.\n");
+		amd_iommu_pgtable = AMD_IOMMU_V1;
+	}
+#endif
+}
+
 /****************************************************************************
  *
  * AMD IOMMU Initialization State Machine
@@ -3256,6 +3287,7 @@ static int __init state_next(void)
 		break;
 	case IOMMU_ENABLED:
 		register_syscore_ops(&amd_iommu_syscore_ops);
+		iommu_snp_enable();
 		ret = amd_iommu_init_pci();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
 		break;
@@ -3767,40 +3799,85 @@ int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64
 	return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
 }
 
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-int amd_iommu_snp_enable(void)
+#ifdef CONFIG_KVM_AMD_SEV
+static int iommu_page_make_shared(void *page)
 {
-	/*
-	 * The SNP support requires that IOMMU must be enabled, and is
-	 * not configured in the passthrough mode.
-	 */
-	if (no_iommu || iommu_default_passthrough()) {
-		pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported");
-		return -EINVAL;
+	unsigned long paddr, pfn;
+
+	paddr = iommu_virt_to_phys(page);
+	/* Cbit maybe set in the paddr */
+	pfn = __sme_clr(paddr) >> PAGE_SHIFT;
+
+	if (!(pfn % PTRS_PER_PMD)) {
+		int ret, level;
+		bool assigned;
+
+		ret = snp_lookup_rmpentry(pfn, &assigned, &level);
+		if (ret) {
+			pr_warn("IOMMU PFN %lx RMP lookup failed, ret %d\n", pfn, ret);
+			return ret;
+		}
+
+		if (!assigned) {
+			pr_warn("IOMMU PFN %lx not assigned in RMP table\n", pfn);
+			return -EINVAL;
+		}
+
+		if (level > PG_LEVEL_4K) {
+			ret = psmash(pfn);
+			if (!ret)
+				goto done;
+
+			pr_warn("PSMASH failed for IOMMU PFN %lx huge RMP entry, ret: %d, level: %d\n",
+				pfn, ret, level);
+			return ret;
+		}
 	}
 
-	/*
-	 * Prevent enabling SNP after IOMMU_ENABLED state because this process
-	 * affect how IOMMU driver sets up data structures and configures
-	 * IOMMU hardware.
-	 */
-	if (init_state > IOMMU_ENABLED) {
-		pr_err("SNP: Too late to enable SNP for IOMMU.\n");
-		return -EINVAL;
+done:
+	return rmp_make_shared(pfn, PG_LEVEL_4K);
+}
+
+static int iommu_make_shared(void *va, size_t size)
+{
+	void *page;
+	int ret;
+
+	if (!va)
+		return 0;
+
+	for (page = va; page < (va + size); page += PAGE_SIZE) {
+		ret = iommu_page_make_shared(page);
+		if (ret)
+			return ret;
 	}
 
-	amd_iommu_snp_en = check_feature(FEATURE_SNP);
+	return 0;
+}
+
+int amd_iommu_snp_disable(void)
+{
+	struct amd_iommu *iommu;
+	int ret;
+
 	if (!amd_iommu_snp_en)
-		return -EINVAL;
+		return 0;
+
+	for_each_iommu(iommu) {
+		ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE);
+		if (ret)
+			return ret;
 
-	pr_info("SNP enabled\n");
+		ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE);
+		if (ret)
+			return ret;
 
-	/* Enforce IOMMU v1 pagetable when SNP is enabled. */
-	if (amd_iommu_pgtable != AMD_IOMMU_V1) {
-		pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n");
-		amd_iommu_pgtable = AMD_IOMMU_V1;
+		ret = iommu_make_shared((void *)iommu->cmd_sem, PAGE_SIZE);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(amd_iommu_snp_disable);
 #endif
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 05722121f00e..4a27fbdb2d84 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -292,10 +292,8 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 			  struct mm_struct *mm)
 {
 	int ret;
-	unsigned long flags;
 	struct arm_smmu_ctx_desc *cd;
 	struct arm_smmu_mmu_notifier *smmu_mn;
-	struct arm_smmu_master *master;
 
 	list_for_each_entry(smmu_mn, &smmu_domain->mmu_notifiers, list) {
 		if (smmu_mn->mn.mm == mm) {
@@ -325,28 +323,9 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 		goto err_free_cd;
 	}
 
-	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
-	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm),
-					      cd);
-		if (ret) {
-			list_for_each_entry_from_reverse(
-				master, &smmu_domain->devices, domain_head)
-				arm_smmu_write_ctx_desc(
-					master, mm_get_enqcmd_pasid(mm), NULL);
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
-	if (ret)
-		goto err_put_notifier;
-
 	list_add(&smmu_mn->list, &smmu_domain->mmu_notifiers);
 	return smmu_mn;
 
-err_put_notifier:
-	/* Frees smmu_mn */
-	mmu_notifier_put(&smmu_mn->mn);
 err_free_cd:
 	arm_smmu_free_shared_cd(cd);
 	return ERR_PTR(ret);
@@ -363,9 +342,6 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 
 	list_del(&smmu_mn->list);
 
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
-					 NULL);
-
 	/*
 	 * If we went through clear(), we've already invalidated, and no
 	 * new TLB entry can have been formed.
@@ -381,7 +357,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 	arm_smmu_free_shared_cd(cd);
 }
 
-static int __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
+static int __arm_smmu_sva_bind(struct device *dev, ioasid_t pasid,
+			       struct mm_struct *mm)
 {
 	int ret;
 	struct arm_smmu_bond *bond;
@@ -404,9 +381,15 @@ static int __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
 		goto err_free_bond;
 	}
 
+	ret = arm_smmu_write_ctx_desc(master, pasid, bond->smmu_mn->cd);
+	if (ret)
+		goto err_put_notifier;
+
 	list_add(&bond->list, &master->bonds);
 	return 0;
 
+err_put_notifier:
+	arm_smmu_mmu_notifier_put(bond->smmu_mn);
 err_free_bond:
 	kfree(bond);
 	return ret;
@@ -568,6 +551,9 @@ void arm_smmu_sva_remove_dev_pasid(struct iommu_domain *domain,
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 
 	mutex_lock(&sva_lock);
+
+	arm_smmu_write_ctx_desc(master, id, NULL);
+
 	list_for_each_entry(t, &master->bonds, list) {
 		if (t->mm == mm) {
 			bond = t;
@@ -590,7 +576,7 @@ static int arm_smmu_sva_set_dev_pasid(struct iommu_domain *domain,
 	struct mm_struct *mm = domain->mm;
 
 	mutex_lock(&sva_lock);
-	ret = __arm_smmu_sva_bind(dev, mm);
+	ret = __arm_smmu_sva_bind(dev, id, mm);
 	mutex_unlock(&sva_lock);
 
 	return ret;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 0ffb1cf17e0b..a74a509bcd63 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3125,7 +3125,8 @@ static int arm_smmu_update_gbpa(struct arm_smmu_device *smmu, u32 set, u32 clr)
 static void arm_smmu_free_msis(void *data)
 {
 	struct device *dev = data;
-	platform_msi_domain_free_irqs(dev);
+
+	platform_device_msi_free_irqs_all(dev);
 }
 
 static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
@@ -3166,7 +3167,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
 	}
 
 	/* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */
-	ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg);
+	ret = platform_device_msi_init_and_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg);
 	if (ret) {
 		dev_warn(dev, "failed to allocate MSIs - falling back to wired irqs\n");
 		return;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 68b6bc5e7c71..6317aaf7b3ab 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -859,10 +859,14 @@ static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 	arm_smmu_rpm_put(smmu);
 }
 
-static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev)
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
+	if (type != IOMMU_DOMAIN_UNMANAGED) {
+		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
+			return NULL;
+	}
 	/*
 	 * Allocate the domain and initialise some of its data structures.
 	 * We can't really do anything meaningful until we've added a
@@ -875,15 +879,6 @@ static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev)
 	mutex_init(&smmu_domain->init_mutex);
 	spin_lock_init(&smmu_domain->cb_lock);
 
-	if (dev) {
-		struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
-
-		if (arm_smmu_init_domain_context(smmu_domain, cfg->smmu, dev)) {
-			kfree(smmu_domain);
-			return NULL;
-		}
-	}
-
 	return &smmu_domain->domain;
 }
 
@@ -1600,7 +1595,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.identity_domain	= &arm_smmu_identity_domain,
 	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
-	.domain_alloc_paging	= arm_smmu_domain_alloc_paging,
+	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.probe_finalize		= arm_smmu_probe_finalize,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 6fb5f6fceea1..11652e0bcab3 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -396,8 +396,6 @@ static int domain_update_device_node(struct dmar_domain *domain)
 	return nid;
 }
 
-static void domain_update_iotlb(struct dmar_domain *domain);
-
 /* Return the super pagesize bitmap if supported. */
 static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 {
@@ -1218,7 +1216,7 @@ domain_lookup_dev_info(struct dmar_domain *domain,
 	return NULL;
 }
 
-static void domain_update_iotlb(struct dmar_domain *domain)
+void domain_update_iotlb(struct dmar_domain *domain)
 {
 	struct dev_pasid_info *dev_pasid;
 	struct device_domain_info *info;
@@ -1368,6 +1366,46 @@ static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
+static void __iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+				    unsigned long pfn, unsigned int pages,
+				    int ih)
+{
+	unsigned int aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned int mask = ilog2(aligned_pages);
+	u64 addr = (u64)pfn << VTD_PAGE_SHIFT;
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	/*
+	 * Fallback to domain selective flush if no PSI support or
+	 * the size is too big.
+	 */
+	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+		iommu->flush.flush_iotlb(iommu, did, 0, 0,
+					 DMA_TLB_DSI_FLUSH);
+	else
+		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+					 DMA_TLB_PSI_FLUSH);
+}
+
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1384,42 +1422,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 	if (ih)
 		ih = 1 << 6;
 
-	if (domain->use_first_level) {
+	if (domain->use_first_level)
 		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
-	} else {
-		unsigned long bitmask = aligned_pages - 1;
-
-		/*
-		 * PSI masks the low order bits of the base address. If the
-		 * address isn't aligned to the mask, then compute a mask value
-		 * needed to ensure the target range is flushed.
-		 */
-		if (unlikely(bitmask & pfn)) {
-			unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
-			/*
-			 * Since end_pfn <= pfn + bitmask, the only way bits
-			 * higher than bitmask can differ in pfn and end_pfn is
-			 * by carrying. This means after masking out bitmask,
-			 * high bits starting with the first set bit in
-			 * shared_bits are all equal in both pfn and end_pfn.
-			 */
-			shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
-			mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
-		}
-
-		/*
-		 * Fallback to domain selective flush if no PSI support or
-		 * the size is too big.
-		 */
-		if (!cap_pgsel_inv(iommu->cap) ||
-		    mask > cap_max_amask_val(iommu->cap))
-			iommu->flush.flush_iotlb(iommu, did, 0, 0,
-							DMA_TLB_DSI_FLUSH);
-		else
-			iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
-							DMA_TLB_PSI_FLUSH);
-	}
+	else
+		__iommu_flush_iotlb_psi(iommu, did, pfn, pages, ih);
 
 	/*
 	 * In caching mode, changes of pages from non-present to present require
@@ -1443,6 +1449,46 @@ static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *
 		iommu_flush_write_buffer(iommu);
 }
 
+/*
+ * Flush the relevant caches in nested translation if the domain
+ * also serves as a parent
+ */
+static void parent_domain_flush(struct dmar_domain *domain,
+				unsigned long pfn,
+				unsigned long pages, int ih)
+{
+	struct dmar_domain *s1_domain;
+
+	spin_lock(&domain->s1_lock);
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		struct device_domain_info *device_info;
+		struct iommu_domain_info *info;
+		unsigned long flags;
+		unsigned long i;
+
+		xa_for_each(&s1_domain->iommu_array, i, info)
+			__iommu_flush_iotlb_psi(info->iommu, info->did,
+						pfn, pages, ih);
+
+		if (!s1_domain->has_iotlb_device)
+			continue;
+
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		list_for_each_entry(device_info, &s1_domain->devices, link)
+			/*
+			 * Address translation cache in device side caches the
+			 * result of nested translation. There is no easy way
+			 * to identify the exact set of nested translations
+			 * affected by a change in S2. So just flush the entire
+			 * device cache.
+			 */
+			__iommu_flush_dev_iotlb(device_info, 0,
+						MAX_AGAW_PFN_WIDTH);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+	}
+	spin_unlock(&domain->s1_lock);
+}
+
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
@@ -1462,6 +1508,9 @@ static void intel_flush_iotlb_all(struct iommu_domain *domain)
 		if (!cap_caching_mode(iommu->cap))
 			iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
 	}
+
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, 0, -1, 0);
 }
 
 static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
@@ -1985,6 +2034,9 @@ static void switch_to_super_page(struct dmar_domain *domain,
 				iommu_flush_iotlb_psi(info->iommu, domain,
 						      start_pfn, lvl_pages,
 						      0, 0);
+			if (domain->nested_parent)
+				parent_domain_flush(domain, start_pfn,
+						    lvl_pages, 0);
 		}
 
 		pte++;
@@ -3883,6 +3935,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 	bool nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
 	struct intel_iommu *iommu = info->iommu;
+	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 
 	/* Must be NESTING domain */
@@ -3908,11 +3961,16 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 	if (!domain)
 		return ERR_PTR(-ENOMEM);
 
-	if (nested_parent)
-		to_dmar_domain(domain)->nested_parent = true;
+	dmar_domain = to_dmar_domain(domain);
+
+	if (nested_parent) {
+		dmar_domain->nested_parent = true;
+		INIT_LIST_HEAD(&dmar_domain->s1_domains);
+		spin_lock_init(&dmar_domain->s1_lock);
+	}
 
 	if (dirty_tracking) {
-		if (to_dmar_domain(domain)->use_first_level) {
+		if (dmar_domain->use_first_level) {
 			iommu_domain_free(domain);
 			return ERR_PTR(-EOPNOTSUPP);
 		}
@@ -3924,8 +3982,12 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
 
 static void intel_iommu_domain_free(struct iommu_domain *domain)
 {
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	WARN_ON(dmar_domain->nested_parent &&
+		!list_empty(&dmar_domain->s1_domains));
 	if (domain != &si_domain->domain)
-		domain_exit(to_dmar_domain(domain));
+		domain_exit(dmar_domain);
 }
 
 int prepare_domain_attach_device(struct iommu_domain *domain,
@@ -4107,6 +4169,9 @@ static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 				      start_pfn, nrpages,
 				      list_empty(&gather->freelist), 0);
 
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, start_pfn, nrpages,
+				    list_empty(&gather->freelist));
 	put_pages_list(&gather->freelist);
 }
 
@@ -4664,21 +4729,70 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
 	return vtd;
 }
 
+/*
+ * Set dirty tracking for the device list of a domain. The caller must
+ * hold the domain->lock when calling it.
+ */
+static int device_set_dirty_tracking(struct list_head *devices, bool enable)
+{
+	struct device_domain_info *info;
+	int ret = 0;
+
+	list_for_each_entry(info, devices, link) {
+		ret = intel_pasid_setup_dirty_tracking(info->iommu, info->dev,
+						       IOMMU_NO_PASID, enable);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int parent_domain_set_dirty_tracking(struct dmar_domain *domain,
+					    bool enable)
+{
+	struct dmar_domain *s1_domain;
+	unsigned long flags;
+	int ret;
+
+	spin_lock(&domain->s1_lock);
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		ret = device_set_dirty_tracking(&s1_domain->devices, enable);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+		if (ret)
+			goto err_unwind;
+	}
+	spin_unlock(&domain->s1_lock);
+	return 0;
+
+err_unwind:
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		device_set_dirty_tracking(&s1_domain->devices,
+					  domain->dirty_tracking);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+	}
+	spin_unlock(&domain->s1_lock);
+	return ret;
+}
+
 static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain,
 					  bool enable)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct device_domain_info *info;
 	int ret;
 
 	spin_lock(&dmar_domain->lock);
 	if (dmar_domain->dirty_tracking == enable)
 		goto out_unlock;
 
-	list_for_each_entry(info, &dmar_domain->devices, link) {
-		ret = intel_pasid_setup_dirty_tracking(info->iommu,
-						       info->domain, info->dev,
-						       IOMMU_NO_PASID, enable);
+	ret = device_set_dirty_tracking(&dmar_domain->devices, enable);
+	if (ret)
+		goto err_unwind;
+
+	if (dmar_domain->nested_parent) {
+		ret = parent_domain_set_dirty_tracking(dmar_domain, enable);
 		if (ret)
 			goto err_unwind;
 	}
@@ -4690,10 +4804,8 @@ out_unlock:
 	return 0;
 
 err_unwind:
-	list_for_each_entry(info, &dmar_domain->devices, link)
-		intel_pasid_setup_dirty_tracking(info->iommu, dmar_domain,
-						 info->dev, IOMMU_NO_PASID,
-						 dmar_domain->dirty_tracking);
+	device_set_dirty_tracking(&dmar_domain->devices,
+				  dmar_domain->dirty_tracking);
 	spin_unlock(&dmar_domain->lock);
 	return ret;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index d02f916d8e59..4145c04cb1c6 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -627,6 +627,10 @@ struct dmar_domain {
 			int		agaw;
 			/* maximum mapped address */
 			u64		max_addr;
+			/* Protect the s1_domains list */
+			spinlock_t	s1_lock;
+			/* Track s1_domains nested on this domain */
+			struct list_head s1_domains;
 		};
 
 		/* Nested user domain */
@@ -637,6 +641,8 @@ struct dmar_domain {
 			unsigned long s1_pgtbl;
 			/* page table attributes */
 			struct iommu_hwpt_vtd_s1 s1_cfg;
+			/* link to parent domain siblings */
+			struct list_head s2_link;
 		};
 	};
 
@@ -1060,6 +1066,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
  */
 #define QI_OPT_WAIT_DRAIN		BIT(0)
 
+void domain_update_iotlb(struct dmar_domain *domain);
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void device_block_translation(struct device *dev);
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index f26c7f1c46cc..a7d68f3d518a 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -65,12 +65,20 @@ static int intel_nested_attach_dev(struct iommu_domain *domain,
 	list_add(&info->link, &dmar_domain->devices);
 	spin_unlock_irqrestore(&dmar_domain->lock, flags);
 
+	domain_update_iotlb(dmar_domain);
+
 	return 0;
 }
 
 static void intel_nested_domain_free(struct iommu_domain *domain)
 {
-	kfree(to_dmar_domain(domain));
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct dmar_domain *s2_domain = dmar_domain->s2_domain;
+
+	spin_lock(&s2_domain->s1_lock);
+	list_del(&dmar_domain->s2_link);
+	spin_unlock(&s2_domain->s1_lock);
+	kfree(dmar_domain);
 }
 
 static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
@@ -95,7 +103,7 @@ static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
 }
 
 static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
-				     unsigned long npages, bool ih)
+				     u64 npages, bool ih)
 {
 	struct iommu_domain_info *info;
 	unsigned int mask;
@@ -201,5 +209,9 @@ struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 	spin_lock_init(&domain->lock);
 	xa_init(&domain->iommu_array);
 
+	spin_lock(&s2_domain->s1_lock);
+	list_add(&domain->s2_link, &s2_domain->s1_domains);
+	spin_unlock(&s2_domain->s1_lock);
+
 	return &domain->domain;
 }
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 3239cefa4c33..108158e2b907 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -428,7 +428,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
  * Set up dirty tracking on a second only or nested translation type.
  */
 int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
 				     struct device *dev, u32 pasid,
 				     bool enabled)
 {
@@ -445,7 +444,7 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
-	did = domain_id_iommu(domain, iommu);
+	did = pasid_get_domain_id(pte);
 	pgtt = pasid_pte_get_pgtt(pte);
 	if (pgtt != PASID_ENTRY_PGTT_SL_ONLY &&
 	    pgtt != PASID_ENTRY_PGTT_NESTED) {
@@ -658,6 +657,8 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, s2_domain->agaw);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	if (s2_domain->dirty_tracking)
+		pasid_set_ssade(pte);
 	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
 	pasid_set_present(pte);
 	spin_unlock(&iommu->lock);
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 8d40d4c66e31..487ede039bdd 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -307,7 +307,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
-				     struct dmar_domain *domain,
 				     struct device *dev, u32 pasid,
 				     bool enabled);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index c3fc9201d0be..65814cbc8402 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -41,6 +41,7 @@ static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct de
 	}
 	iommu_mm->pasid = pasid;
 	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	INIT_LIST_HEAD(&iommu_mm->sva_handles);
 	/*
 	 * Make sure the write to mm->iommu_mm is not reordered in front of
 	 * initialization to iommu_mm fields. If it does, readers may see a
@@ -82,6 +83,14 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 		goto out_unlock;
 	}
 
+	list_for_each_entry(handle, &mm->iommu_mm->sva_handles, handle_item) {
+		if (handle->dev == dev) {
+			refcount_inc(&handle->users);
+			mutex_unlock(&iommu_sva_lock);
+			return handle;
+		}
+	}
+
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
 	if (!handle) {
 		ret = -ENOMEM;
@@ -111,6 +120,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 	list_add(&domain->next, &mm->iommu_mm->sva_domains);
 
 out:
+	refcount_set(&handle->users, 1);
+	list_add(&handle->handle_item, &mm->iommu_mm->sva_handles);
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
@@ -141,6 +152,12 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	if (!refcount_dec_and_test(&handle->users)) {
+		mutex_unlock(&iommu_sva_lock);
+		return;
+	}
+	list_del(&handle->handle_item);
+
 	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
 		list_del(&domain->next);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 68e648b55767..d14413916f93 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1799,7 +1799,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 * domain. Do not use in new drivers.
 	 */
 	if (ops->default_domain) {
-		if (req_type)
+		if (req_type != ops->default_domain->type)
 			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
@@ -1871,10 +1871,18 @@ static int iommu_get_def_domain_type(struct iommu_group *group,
 	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
-	if (!ops->def_domain_type)
-		return cur_type;
-
-	type = ops->def_domain_type(dev);
+	if (ops->default_domain) {
+		/*
+		 * Drivers that declare a global static default_domain will
+		 * always choose that.
+		 */
+		type = ops->default_domain->type;
+	} else {
+		if (ops->def_domain_type)
+			type = ops->def_domain_type(dev);
+		else
+			return cur_type;
+	}
 	if (!type || cur_type == type)
 		return cur_type;
 	if (!cur_type)
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 3f3f1fa1a0a9..33d142f8057d 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -263,7 +263,8 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 
 	if (cmd->__reserved)
 		return -EOPNOTSUPP;
-	if (cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len)
+	if ((cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) ||
+	    (cmd->data_type != IOMMU_HWPT_DATA_NONE && !cmd->data_len))
 		return -EINVAL;
 
 	idev = iommufd_get_device(ucmd, cmd->dev_id);
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 504ac1b01b2d..05fd9d3abf1b 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -1330,20 +1330,23 @@ out_unlock:
 
 int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access)
 {
+	u32 new_id;
 	int rc;
 
 	down_write(&iopt->domains_rwsem);
 	down_write(&iopt->iova_rwsem);
-	rc = xa_alloc(&iopt->access_list, &access->iopt_access_list_id, access,
-		      xa_limit_16b, GFP_KERNEL_ACCOUNT);
+	rc = xa_alloc(&iopt->access_list, &new_id, access, xa_limit_16b,
+		      GFP_KERNEL_ACCOUNT);
+
 	if (rc)
 		goto out_unlock;
 
 	rc = iopt_calculate_iova_alignment(iopt);
 	if (rc) {
-		xa_erase(&iopt->access_list, access->iopt_access_list_id);
+		xa_erase(&iopt->access_list, new_id);
 		goto out_unlock;
 	}
+	access->iopt_access_list_id = new_id;
 
 out_unlock:
 	up_write(&iopt->iova_rwsem);
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 482d4059f5db..e854d3f67205 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -45,6 +45,7 @@ enum {
 
 enum {
 	MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0,
+	MOCK_FLAGS_DEVICE_HUGE_IOVA = 1 << 1,
 };
 
 enum {
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index 0a92c9eeaf7f..db8c46bee155 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -100,7 +100,7 @@ struct iova_bitmap {
 	struct iova_bitmap_map mapped;
 
 	/* userspace address of the bitmap */
-	u64 __user *bitmap;
+	u8 __user *bitmap;
 
 	/* u64 index that @mapped points to */
 	unsigned long mapped_base_index;
@@ -113,6 +113,9 @@ struct iova_bitmap {
 
 	/* length of the IOVA range for the whole bitmap */
 	size_t length;
+
+	/* length of the IOVA range set ahead the pinned pages */
+	unsigned long set_ahead_length;
 };
 
 /*
@@ -162,7 +165,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap)
 {
 	struct iova_bitmap_map *mapped = &bitmap->mapped;
 	unsigned long npages;
-	u64 __user *addr;
+	u8 __user *addr;
 	long ret;
 
 	/*
@@ -176,17 +179,18 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap)
 			       sizeof(*bitmap->bitmap), PAGE_SIZE);
 
 	/*
-	 * We always cap at max number of 'struct page' a base page can fit.
-	 * This is, for example, on x86 means 2M of bitmap data max.
-	 */
-	npages = min(npages,  PAGE_SIZE / sizeof(struct page *));
-
-	/*
 	 * Bitmap address to be pinned is calculated via pointer arithmetic
 	 * with bitmap u64 word index.
 	 */
 	addr = bitmap->bitmap + bitmap->mapped_base_index;
 
+	/*
+	 * We always cap at max number of 'struct page' a base page can fit.
+	 * This is, for example, on x86 means 2M of bitmap data max.
+	 */
+	npages = min(npages + !!offset_in_page(addr),
+		     PAGE_SIZE / sizeof(struct page *));
+
 	ret = pin_user_pages_fast((unsigned long)addr, npages,
 				  FOLL_WRITE, mapped->pages);
 	if (ret <= 0)
@@ -247,7 +251,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
 
 	mapped = &bitmap->mapped;
 	mapped->pgshift = __ffs(page_size);
-	bitmap->bitmap = data;
+	bitmap->bitmap = (u8 __user *)data;
 	bitmap->mapped_total_index =
 		iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
 	bitmap->iova = iova;
@@ -304,7 +308,7 @@ static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap)
 
 	remaining = bitmap->mapped_total_index - bitmap->mapped_base_index;
 	remaining = min_t(unsigned long, remaining,
-			  bytes / sizeof(*bitmap->bitmap));
+			  DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap)));
 
 	return remaining;
 }
@@ -341,6 +345,32 @@ static bool iova_bitmap_done(struct iova_bitmap *bitmap)
 	return bitmap->mapped_base_index >= bitmap->mapped_total_index;
 }
 
+static int iova_bitmap_set_ahead(struct iova_bitmap *bitmap,
+				 size_t set_ahead_length)
+{
+	int ret = 0;
+
+	while (set_ahead_length > 0 && !iova_bitmap_done(bitmap)) {
+		unsigned long length = iova_bitmap_mapped_length(bitmap);
+		unsigned long iova = iova_bitmap_mapped_iova(bitmap);
+
+		ret = iova_bitmap_get(bitmap);
+		if (ret)
+			break;
+
+		length = min(length, set_ahead_length);
+		iova_bitmap_set(bitmap, iova, length);
+
+		set_ahead_length -= length;
+		bitmap->mapped_base_index +=
+			iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
+		iova_bitmap_put(bitmap);
+	}
+
+	bitmap->set_ahead_length = 0;
+	return ret;
+}
+
 /*
  * Advances to the next range, releases the current pinned
  * pages and pins the next set of bitmap pages.
@@ -357,6 +387,15 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap)
 	if (iova_bitmap_done(bitmap))
 		return 0;
 
+	/* Iterate, set and skip any bits requested for next iteration */
+	if (bitmap->set_ahead_length) {
+		int ret;
+
+		ret = iova_bitmap_set_ahead(bitmap, bitmap->set_ahead_length);
+		if (ret)
+			return ret;
+	}
+
 	/* When advancing the index we pin the next set of bitmap pages */
 	return iova_bitmap_get(bitmap);
 }
@@ -409,6 +448,7 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
 	unsigned long last_bit = (((iova + length - 1) - mapped->iova) >>
 			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+	unsigned long last_page_idx = mapped->npages - 1;
 
 	do {
 		unsigned int page_idx = cur_bit / BITS_PER_PAGE;
@@ -417,10 +457,18 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 					 last_bit - cur_bit + 1);
 		void *kaddr;
 
+		if (unlikely(page_idx > last_page_idx))
+			break;
+
 		kaddr = kmap_local_page(mapped->pages[page_idx]);
 		bitmap_set(kaddr, offset, nbits);
 		kunmap_local(kaddr);
 		cur_bit += nbits;
 	} while (cur_bit <= last_bit);
+
+	if (unlikely(cur_bit <= last_bit)) {
+		bitmap->set_ahead_length =
+			((last_bit - cur_bit + 1) << bitmap->mapped.pgshift);
+	}
 }
 EXPORT_SYMBOL_NS_GPL(iova_bitmap_set, IOMMUFD);
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index d9e9920c7eba..7a2199470f31 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -36,11 +36,12 @@ static struct mock_bus_type iommufd_mock_bus_type = {
 	},
 };
 
-static atomic_t mock_dev_num;
+static DEFINE_IDA(mock_dev_ida);
 
 enum {
 	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
+	MOCK_HUGE_PAGE_SIZE = 512 * MOCK_IO_PAGE_SIZE,
 
 	/*
 	 * Like a real page table alignment requires the low bits of the address
@@ -53,6 +54,7 @@ enum {
 	MOCK_PFN_START_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_LAST_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1,
+	MOCK_PFN_HUGE_IOVA = _MOCK_PFN_START << 2,
 };
 
 /*
@@ -61,8 +63,8 @@ enum {
  * In syzkaller mode the 64 bit IOVA is converted into an nth area and offset
  * value. This has a much smaller randomization space and syzkaller can hit it.
  */
-static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
-						u64 *iova)
+static unsigned long __iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
+						  u64 *iova)
 {
 	struct syz_layout {
 		__u32 nth_area;
@@ -86,6 +88,21 @@ static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt,
 	return 0;
 }
 
+static unsigned long iommufd_test_syz_conv_iova(struct iommufd_access *access,
+						u64 *iova)
+{
+	unsigned long ret;
+
+	mutex_lock(&access->ioas_lock);
+	if (!access->ioas) {
+		mutex_unlock(&access->ioas_lock);
+		return 0;
+	}
+	ret = __iommufd_test_syz_conv_iova(&access->ioas->iopt, iova);
+	mutex_unlock(&access->ioas_lock);
+	return ret;
+}
+
 void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 				   unsigned int ioas_id, u64 *iova, u32 *flags)
 {
@@ -98,7 +115,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 	ioas = iommufd_get_ioas(ucmd->ictx, ioas_id);
 	if (IS_ERR(ioas))
 		return;
-	*iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova);
+	*iova = __iommufd_test_syz_conv_iova(&ioas->iopt, iova);
 	iommufd_put_object(ucmd->ictx, &ioas->obj);
 }
 
@@ -121,6 +138,7 @@ enum selftest_obj_type {
 struct mock_dev {
 	struct device dev;
 	unsigned long flags;
+	int id;
 };
 
 struct selftest_obj {
@@ -191,6 +209,34 @@ static int mock_domain_set_dirty_tracking(struct iommu_domain *domain,
 	return 0;
 }
 
+static bool mock_test_and_clear_dirty(struct mock_iommu_domain *mock,
+				      unsigned long iova, size_t page_size,
+				      unsigned long flags)
+{
+	unsigned long cur, end = iova + page_size - 1;
+	bool dirty = false;
+	void *ent, *old;
+
+	for (cur = iova; cur < end; cur += MOCK_IO_PAGE_SIZE) {
+		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
+		if (!ent || !(xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA))
+			continue;
+
+		dirty = true;
+		/* Clear dirty */
+		if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
+			unsigned long val;
+
+			val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+		}
+	}
+
+	return dirty;
+}
+
 static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 					    unsigned long iova, size_t size,
 					    unsigned long flags,
@@ -198,31 +244,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 {
 	struct mock_iommu_domain *mock =
 		container_of(domain, struct mock_iommu_domain, domain);
-	unsigned long i, max = size / MOCK_IO_PAGE_SIZE;
-	void *ent, *old;
+	unsigned long end = iova + size;
+	void *ent;
 
 	if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap)
 		return -EINVAL;
 
-	for (i = 0; i < max; i++) {
-		unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE;
+	do {
+		unsigned long pgsize = MOCK_IO_PAGE_SIZE;
+		unsigned long head;
 
-		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
-		if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) {
-			/* Clear dirty */
-			if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
-				unsigned long val;
-
-				val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
-				old = xa_store(&mock->pfns,
-					       cur / MOCK_IO_PAGE_SIZE,
-					       xa_mk_value(val), GFP_KERNEL);
-				WARN_ON_ONCE(ent != old);
-			}
-			iommu_dirty_bitmap_record(dirty, cur,
-						  MOCK_IO_PAGE_SIZE);
+		ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE);
+		if (!ent) {
+			iova += pgsize;
+			continue;
 		}
-	}
+
+		if (xa_to_value(ent) & MOCK_PFN_HUGE_IOVA)
+			pgsize = MOCK_HUGE_PAGE_SIZE;
+		head = iova & ~(pgsize - 1);
+
+		/* Clear dirty */
+		if (mock_test_and_clear_dirty(mock, head, pgsize, flags))
+			iommu_dirty_bitmap_record(dirty, head, pgsize);
+		iova = head + pgsize;
+	} while (iova < end);
 
 	return 0;
 }
@@ -234,6 +280,7 @@ const struct iommu_dirty_ops dirty_ops = {
 
 static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 {
+	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 	struct mock_iommu_domain *mock;
 
 	mock = kzalloc(sizeof(*mock), GFP_KERNEL);
@@ -242,6 +289,8 @@ static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 	mock->domain.geometry.aperture_start = MOCK_APERTURE_START;
 	mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST;
 	mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE;
+	if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA)
+		mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE;
 	mock->domain.ops = mock_ops.default_domain_ops;
 	mock->domain.type = IOMMU_DOMAIN_UNMANAGED;
 	xa_init(&mock->pfns);
@@ -287,7 +336,7 @@ mock_domain_alloc_user(struct device *dev, u32 flags,
 			return ERR_PTR(-EOPNOTSUPP);
 		if (user_data || (has_dirty_flag && no_dirty_ops))
 			return ERR_PTR(-EOPNOTSUPP);
-		domain = mock_domain_alloc_paging(NULL);
+		domain = mock_domain_alloc_paging(dev);
 		if (!domain)
 			return ERR_PTR(-ENOMEM);
 		if (has_dirty_flag)
@@ -350,6 +399,9 @@ static int mock_domain_map_pages(struct iommu_domain *domain,
 
 			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
 				flags = MOCK_PFN_LAST_IOVA;
+			if (pgsize != MOCK_IO_PAGE_SIZE) {
+				flags |= MOCK_PFN_HUGE_IOVA;
+			}
 			old = xa_store(&mock->pfns, iova / MOCK_IO_PAGE_SIZE,
 				       xa_mk_value((paddr / MOCK_IO_PAGE_SIZE) |
 						   flags),
@@ -394,20 +446,27 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 
 			/*
 			 * iommufd generates unmaps that must be a strict
-			 * superset of the map's performend So every starting
-			 * IOVA should have been an iova passed to map, and the
+			 * superset of the map's performend So every
+			 * starting/ending IOVA should have been an iova passed
+			 * to map.
 			 *
-			 * First IOVA must be present and have been a first IOVA
-			 * passed to map_pages
+			 * This simple logic doesn't work when the HUGE_PAGE is
+			 * turned on since the core code will automatically
+			 * switch between the two page sizes creating a break in
+			 * the unmap calls. The break can land in the middle of
+			 * contiguous IOVA.
 			 */
-			if (first) {
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_START_IOVA));
-				first = false;
+			if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) {
+				if (first) {
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_START_IOVA));
+					first = false;
+				}
+				if (pgcount == 1 &&
+				    cur + MOCK_IO_PAGE_SIZE == pgsize)
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_LAST_IOVA));
 			}
-			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_LAST_IOVA));
 
 			iova += MOCK_IO_PAGE_SIZE;
 			ret += MOCK_IO_PAGE_SIZE;
@@ -595,7 +654,7 @@ static void mock_dev_release(struct device *dev)
 {
 	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 
-	atomic_dec(&mock_dev_num);
+	ida_free(&mock_dev_ida, mdev->id);
 	kfree(mdev);
 }
 
@@ -604,7 +663,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	struct mock_dev *mdev;
 	int rc;
 
-	if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY))
+	if (dev_flags &
+	    ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA))
 		return ERR_PTR(-EINVAL);
 
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
@@ -616,8 +676,12 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	mdev->dev.release = mock_dev_release;
 	mdev->dev.bus = &iommufd_mock_bus_type.bus;
 
-	rc = dev_set_name(&mdev->dev, "iommufd_mock%u",
-			  atomic_inc_return(&mock_dev_num));
+	rc = ida_alloc(&mock_dev_ida, GFP_KERNEL);
+	if (rc < 0)
+		goto err_put;
+	mdev->id = rc;
+
+	rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id);
 	if (rc)
 		goto err_put;
 
@@ -1119,7 +1183,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd,
 	}
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
-		iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt,
+		iova = iommufd_test_syz_conv_iova(staccess->access,
 					&cmd->access_pages.iova);
 
 	npages = (ALIGN(iova + length, PAGE_SIZE) -
@@ -1221,8 +1285,8 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd,
 	}
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
-		iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt,
-					&cmd->access_rw.iova);
+		iova = iommufd_test_syz_conv_iova(staccess->access,
+				&cmd->access_rw.iova);
 
 	rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags);
 	if (rc)
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index f7149d0f3d45..72c07a12f5e1 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -546,6 +546,17 @@ config SIFIVE_PLIC
 	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP
 
+config STARFIVE_JH8100_INTC
+	bool "StarFive JH8100 External Interrupt Controller"
+	depends on ARCH_STARFIVE || COMPILE_TEST
+	default ARCH_STARFIVE
+	select IRQ_DOMAIN_HIERARCHY
+	help
+	  This enables support for the INTC chip found in StarFive JH8100
+	  SoC.
+
+	  If you don't know what to do here, say Y.
+
 config EXYNOS_IRQ_COMBINER
 	bool "Samsung Exynos IRQ combiner support" if COMPILE_TEST
 	depends on (ARCH_EXYNOS && ARM) || COMPILE_TEST
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index ffd945fe71aa..ec4a18380998 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -96,6 +96,7 @@ obj-$(CONFIG_CSKY_MPINTC)		+= irq-csky-mpintc.o
 obj-$(CONFIG_CSKY_APB_INTC)		+= irq-csky-apb-intc.o
 obj-$(CONFIG_RISCV_INTC)		+= irq-riscv-intc.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
+obj-$(CONFIG_STARFIVE_JH8100_INTC)	+= irq-starfive-jh8100-intc.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
 obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o
 obj-$(CONFIG_IMX_MU_MSI)		+= irq-imx-mu-msi.o
diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c
index 9745a119d0e6..eb02d203c963 100644
--- a/drivers/irqchip/irq-bcm6345-l1.c
+++ b/drivers/irqchip/irq-bcm6345-l1.c
@@ -242,7 +242,7 @@ static int __init bcm6345_l1_init_one(struct device_node *dn,
 	else if (intc->n_words != n_words)
 		return -EINVAL;
 
-	cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32),
+	cpu = intc->cpus[idx] = kzalloc(struct_size(cpu, enable_cache, n_words),
 					GFP_KERNEL);
 	if (!cpu)
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index 24ca1d656adc..36e71af054e9 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -249,7 +249,7 @@ static int __init bcm7038_l1_init_one(struct device_node *dn,
 		return -EINVAL;
 	}
 
-	cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32),
+	cpu = intc->cpus[idx] = kzalloc(struct_size(cpu, mask_cache, n_words),
 					GFP_KERNEL);
 	if (!cpu)
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 5559c943f03f..2b0b3175cea0 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -2,7 +2,7 @@
 /*
  * Generic Broadcom Set Top Box Level 2 Interrupt controller driver
  *
- * Copyright (C) 2014-2017 Broadcom
+ * Copyright (C) 2014-2024 Broadcom
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME	": " fmt
@@ -112,6 +112,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 		generic_handle_domain_irq(b->domain, irq);
 	} while (status);
 out:
+	/* Don't ack parent before all device writes are done */
+	wmb();
+
 	chained_irq_exit(chip, desc);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d097001c1e3e..fca888b36680 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -207,6 +207,11 @@ static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
 	return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
 }
 
+static bool rdists_support_shareable(void)
+{
+	return !(gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE);
+}
+
 static u16 get_its_list(struct its_vm *vm)
 {
 	struct its_node *its;
@@ -2710,10 +2715,12 @@ static u64 inherit_vpe_l1_table_from_its(void)
 			break;
 		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
-		val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
-				  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
-		val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
-				  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		if (rdists_support_shareable()) {
+			val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+					  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+			val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+					  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
 
 		return val;
@@ -2936,8 +2943,10 @@ static int allocate_vpe_l1_table(void)
 	WARN_ON(!IS_ALIGNED(pa, psz));
 
 	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
-	val |= GICR_VPROPBASER_RaWb;
-	val |= GICR_VPROPBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPROPBASER_RaWb;
+		val |= GICR_VPROPBASER_InnerShareable;
+	}
 	val |= GICR_VPROPBASER_4_1_Z;
 	val |= GICR_VPROPBASER_4_1_VALID;
 
@@ -3126,7 +3135,7 @@ static void its_cpu_init_lpis(void)
 	gicr_write_propbaser(val, rbase + GICR_PROPBASER);
 	tmp = gicr_read_propbaser(rbase + GICR_PROPBASER);
 
-	if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+	if (!rdists_support_shareable())
 		tmp &= ~GICR_PROPBASER_SHAREABILITY_MASK;
 
 	if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) {
@@ -3153,7 +3162,7 @@ static void its_cpu_init_lpis(void)
 	gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
 	tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
 
-	if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+	if (!rdists_support_shareable())
 		tmp &= ~GICR_PENDBASER_SHAREABILITY_MASK;
 
 	if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) {
@@ -3172,6 +3181,7 @@ static void its_cpu_init_lpis(void)
 	val |= GICR_CTLR_ENABLE_LPIS;
 	writel_relaxed(val, rbase + GICR_CTLR);
 
+out:
 	if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
 		void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 
@@ -3207,7 +3217,6 @@ static void its_cpu_init_lpis(void)
 
 	/* Make sure the GIC has seen the above */
 	dsb(sy);
-out:
 	gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED;
 	pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n",
 		smp_processor_id(),
@@ -3817,8 +3826,9 @@ static int its_vpe_set_affinity(struct irq_data *d,
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	int from, cpu = cpumask_first(mask_val);
+	struct cpumask common, *table_mask;
 	unsigned long flags;
+	int from, cpu;
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
@@ -3834,19 +3844,22 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * taken on any vLPI handling path that evaluates vpe->col_idx.
 	 */
 	from = vpe_to_cpuid_lock(vpe, &flags);
-	if (from == cpu)
-		goto out;
-
-	vpe->col_idx = cpu;
+	table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
 
 	/*
-	 * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
-	 * is sharing its VPE table with the current one.
+	 * If we are offered another CPU in the same GICv4.1 ITS
+	 * affinity, pick this one. Otherwise, any CPU will do.
 	 */
-	if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
-	    cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+	if (table_mask && cpumask_and(&common, mask_val, table_mask))
+		cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (from == cpu)
 		goto out;
 
+	vpe->col_idx = cpu;
+
 	its_send_vmovp(vpe);
 	its_vpe_db_proxy_move(vpe, from, cpu);
 
@@ -3880,14 +3893,18 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val  = virt_to_phys(page_address(vpe->its_vm->vprop_page)) &
 		GENMASK_ULL(51, 12);
 	val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
-	val |= GICR_VPROPBASER_RaWb;
-	val |= GICR_VPROPBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPROPBASER_RaWb;
+		val |= GICR_VPROPBASER_InnerShareable;
+	}
 	gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
 
 	val  = virt_to_phys(page_address(vpe->vpt_page)) &
 		GENMASK_ULL(51, 16);
-	val |= GICR_VPENDBASER_RaWaWb;
-	val |= GICR_VPENDBASER_InnerShareable;
+	if (rdists_support_shareable()) {
+		val |= GICR_VPENDBASER_RaWaWb;
+		val |= GICR_VPENDBASER_InnerShareable;
+	}
 	/*
 	 * There is no good way of finding out if the pending table is
 	 * empty as we can race against the doorbell interrupt very
@@ -4419,12 +4436,12 @@ static const struct irq_domain_ops its_sgi_domain_ops = {
 
 static int its_vpe_id_alloc(void)
 {
-	return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL);
+	return ida_alloc_max(&its_vpeid_ida, ITS_MAX_VPEID - 1, GFP_KERNEL);
 }
 
 static void its_vpe_id_free(u16 id)
 {
-	ida_simple_remove(&its_vpeid_ida, id);
+	ida_free(&its_vpeid_ida, id);
 }
 
 static int its_vpe_init(struct its_vpe *vpe)
@@ -5078,6 +5095,8 @@ static int __init its_probe_one(struct its_node *its)
 	u32 ctlr;
 	int err;
 
+	its_enable_quirks(its);
+
 	if (is_v4(its)) {
 		if (!(its->typer & GITS_TYPER_VMOVP)) {
 			err = its_compute_its_list_map(its);
@@ -5429,7 +5448,6 @@ static int __init its_of_probe(struct device_node *node)
 		if (!its)
 			return -ENOMEM;
 
-		its_enable_quirks(its);
 		err = its_probe_one(its);
 		if (err)  {
 			its_node_destroy(its);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 98b0329b7154..6fb276504bcc 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -19,6 +19,7 @@
 #include <linux/percpu.h>
 #include <linux/refcount.h>
 #include <linux/slab.h>
+#include <linux/iopoll.h>
 
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic-common.h>
@@ -180,11 +181,6 @@ static enum gic_intid_range get_intid_range(struct irq_data *d)
 	return __get_intid_range(d->hwirq);
 }
 
-static inline unsigned int gic_irq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-
 static inline bool gic_irq_in_rdist(struct irq_data *d)
 {
 	switch (get_intid_range(d)) {
@@ -251,17 +247,13 @@ static inline void __iomem *gic_dist_base(struct irq_data *d)
 
 static void gic_do_wait_for_rwp(void __iomem *base, u32 bit)
 {
-	u32 count = 1000000;	/* 1s! */
+	u32 val;
+	int ret;
 
-	while (readl_relaxed(base + GICD_CTLR) & bit) {
-		count--;
-		if (!count) {
-			pr_err_ratelimited("RWP timeout, gone fishing\n");
-			return;
-		}
-		cpu_relax();
-		udelay(1);
-	}
+	ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit),
+						1, USEC_PER_SEC);
+	if (ret == -ETIMEDOUT)
+		pr_err_ratelimited("RWP timeout, gone fishing\n");
 }
 
 /* Wait for completion of a distributor change */
@@ -279,8 +271,8 @@ static void gic_redist_wait_for_rwp(void)
 static void gic_enable_redist(bool enable)
 {
 	void __iomem *rbase;
-	u32 count = 1000000;	/* 1s! */
 	u32 val;
+	int ret;
 
 	if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996)
 		return;
@@ -301,16 +293,13 @@ static void gic_enable_redist(bool enable)
 			return;	/* No PM support in this redistributor */
 	}
 
-	while (--count) {
-		val = readl_relaxed(rbase + GICR_WAKER);
-		if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
-			break;
-		cpu_relax();
-		udelay(1);
-	}
-	if (!count)
+	ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val,
+						enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep),
+						1, USEC_PER_SEC);
+	if (ret == -ETIMEDOUT) {
 		pr_err_ratelimited("redistributor failed to %s...\n",
 				   enable ? "wakeup" : "sleep");
+	}
 }
 
 /*
@@ -548,7 +537,7 @@ static int gic_irq_nmi_setup(struct irq_data *d)
 	 * A secondary irq_chip should be in charge of LPI request,
 	 * it should not be possible to get there
 	 */
-	if (WARN_ON(gic_irq(d) >= 8192))
+	if (WARN_ON(irqd_to_hwirq(d) >= 8192))
 		return -EINVAL;
 
 	/* desc lock should already be held */
@@ -588,7 +577,7 @@ static void gic_irq_nmi_teardown(struct irq_data *d)
 	 * A secondary irq_chip should be in charge of LPI request,
 	 * it should not be possible to get there
 	 */
-	if (WARN_ON(gic_irq(d) >= 8192))
+	if (WARN_ON(irqd_to_hwirq(d) >= 8192))
 		return;
 
 	/* desc lock should already be held */
@@ -626,7 +615,7 @@ static bool gic_arm64_erratum_2941627_needed(struct irq_data *d)
 
 static void gic_eoi_irq(struct irq_data *d)
 {
-	write_gicreg(gic_irq(d), ICC_EOIR1_EL1);
+	write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1);
 	isb();
 
 	if (gic_arm64_erratum_2941627_needed(d)) {
@@ -646,19 +635,19 @@ static void gic_eoimode1_eoi_irq(struct irq_data *d)
 	 * No need to deactivate an LPI, or an interrupt that
 	 * is is getting forwarded to a vcpu.
 	 */
-	if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
+	if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
 		return;
 
 	if (!gic_arm64_erratum_2941627_needed(d))
-		gic_write_dir(gic_irq(d));
+		gic_write_dir(irqd_to_hwirq(d));
 	else
 		gic_poke_irq(d, GICD_ICACTIVER);
 }
 
 static int gic_set_type(struct irq_data *d, unsigned int type)
 {
+	irq_hw_number_t irq = irqd_to_hwirq(d);
 	enum gic_intid_range range;
-	unsigned int irq = gic_irq(d);
 	void __iomem *base;
 	u32 offset, index;
 	int ret;
@@ -684,7 +673,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	ret = gic_configure_irq(index, type, base + offset, NULL);
 	if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) {
 		/* Misconfigured PPIs are usually not fatal */
-		pr_warn("GIC: PPI INTID%d is secure or misconfigured\n", irq);
+		pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq);
 		ret = 0;
 	}
 
@@ -1702,9 +1691,13 @@ static int gic_irq_domain_select(struct irq_domain *d,
 	irq_hw_number_t hwirq;
 
 	/* Not for us */
-        if (fwspec->fwnode != d->fwnode)
+	if (fwspec->fwnode != d->fwnode)
 		return 0;
 
+	/* Handle pure domain searches */
+	if (!fwspec->param_count)
+		return d->bus_token == bus_token;
+
 	/* If this is not DT, then we have a single domain */
 	if (!is_of_node(fwspec->fwnode))
 		return 1;
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 412196a7dad5..98aa383e39db 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -162,11 +162,6 @@ static inline void __iomem *gic_cpu_base(struct irq_data *d)
 	return gic_data_cpu_base(gic_data);
 }
 
-static inline unsigned int gic_irq(struct irq_data *d)
-{
-	return d->hwirq;
-}
-
 static inline bool cascading_gic_irq(struct irq_data *d)
 {
 	void *data = irq_data_get_irq_handler_data(d);
@@ -183,14 +178,16 @@ static inline bool cascading_gic_irq(struct irq_data *d)
  */
 static void gic_poke_irq(struct irq_data *d, u32 offset)
 {
-	u32 mask = 1 << (gic_irq(d) % 32);
-	writel_relaxed(mask, gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4);
+	u32 mask = 1 << (irqd_to_hwirq(d) % 32);
+
+	writel_relaxed(mask, gic_dist_base(d) + offset + (irqd_to_hwirq(d) / 32) * 4);
 }
 
 static int gic_peek_irq(struct irq_data *d, u32 offset)
 {
-	u32 mask = 1 << (gic_irq(d) % 32);
-	return !!(readl_relaxed(gic_dist_base(d) + offset + (gic_irq(d) / 32) * 4) & mask);
+	u32 mask = 1 << (irqd_to_hwirq(d) % 32);
+
+	return !!(readl_relaxed(gic_dist_base(d) + offset + (irqd_to_hwirq(d) / 32) * 4) & mask);
 }
 
 static void gic_mask_irq(struct irq_data *d)
@@ -220,7 +217,7 @@ static void gic_unmask_irq(struct irq_data *d)
 
 static void gic_eoi_irq(struct irq_data *d)
 {
-	u32 hwirq = gic_irq(d);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
 	if (hwirq < 16)
 		hwirq = this_cpu_read(sgi_intid);
@@ -230,7 +227,7 @@ static void gic_eoi_irq(struct irq_data *d)
 
 static void gic_eoimode1_eoi_irq(struct irq_data *d)
 {
-	u32 hwirq = gic_irq(d);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
 	/* Do not deactivate an IRQ forwarded to a vcpu. */
 	if (irqd_is_forwarded_to_vcpu(d))
@@ -293,8 +290,8 @@ static int gic_irq_get_irqchip_state(struct irq_data *d,
 
 static int gic_set_type(struct irq_data *d, unsigned int type)
 {
+	irq_hw_number_t gicirq = irqd_to_hwirq(d);
 	void __iomem *base = gic_dist_base(d);
-	unsigned int gicirq = gic_irq(d);
 	int ret;
 
 	/* Interrupt configuration for SGIs can't be changed */
@@ -309,7 +306,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	ret = gic_configure_irq(gicirq, type, base + GIC_DIST_CONFIG, NULL);
 	if (ret && gicirq < 32) {
 		/* Misconfigured PPIs are usually not fatal */
-		pr_warn("GIC: PPI%d is secure or misconfigured\n", gicirq - 16);
+		pr_warn("GIC: PPI%ld is secure or misconfigured\n", gicirq - 16);
 		ret = 0;
 	}
 
@@ -319,7 +316,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
 	/* Only interrupts on the primary GIC can be forwarded to a vcpu. */
-	if (cascading_gic_irq(d) || gic_irq(d) < 16)
+	if (cascading_gic_irq(d) || irqd_to_hwirq(d) < 16)
 		return -EINVAL;
 
 	if (vcpu)
@@ -796,7 +793,7 @@ static void rmw_writeb(u8 bval, void __iomem *addr)
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + irqd_to_hwirq(d);
 	struct gic_chip_data *gic = irq_data_get_irq_chip_data(d);
 	unsigned int cpu;
 
diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c
index 5831be454673..b42ed68acfa6 100644
--- a/drivers/irqchip/irq-imgpdc.c
+++ b/drivers/irqchip/irq-imgpdc.c
@@ -461,12 +461,11 @@ err_generic:
 	return ret;
 }
 
-static int pdc_intc_remove(struct platform_device *pdev)
+static void pdc_intc_remove(struct platform_device *pdev)
 {
 	struct pdc_intc_priv *priv = platform_get_drvdata(pdev);
 
 	irq_domain_remove(priv->domain);
-	return 0;
 }
 
 static const struct of_device_id pdc_intc_match[] = {
@@ -479,8 +478,8 @@ static struct platform_driver pdc_intc_driver = {
 		.name		= "pdc-intc",
 		.of_match_table	= pdc_intc_match,
 	},
-	.probe = pdc_intc_probe,
-	.remove = pdc_intc_remove,
+	.probe		= pdc_intc_probe,
+	.remove_new	= pdc_intc_remove,
 };
 
 static int __init pdc_intc_init(void)
diff --git a/drivers/irqchip/irq-imx-intmux.c b/drivers/irqchip/irq-imx-intmux.c
index aa041e4dfee0..511adfaeec82 100644
--- a/drivers/irqchip/irq-imx-intmux.c
+++ b/drivers/irqchip/irq-imx-intmux.c
@@ -166,6 +166,10 @@ static int imx_intmux_irq_select(struct irq_domain *d, struct irq_fwspec *fwspec
 	if (fwspec->fwnode != d->fwnode)
 		return false;
 
+	/* Handle pure domain searches */
+	if (!fwspec->param_count)
+		return d->bus_token == bus_token;
+
 	return irqchip_data->chanidx == fwspec->param[1];
 }
 
@@ -282,7 +286,7 @@ out:
 	return ret;
 }
 
-static int imx_intmux_remove(struct platform_device *pdev)
+static void imx_intmux_remove(struct platform_device *pdev)
 {
 	struct intmux_data *data = platform_get_drvdata(pdev);
 	int i;
@@ -298,8 +302,6 @@ static int imx_intmux_remove(struct platform_device *pdev)
 	}
 
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -354,11 +356,11 @@ static const struct of_device_id imx_intmux_id[] = {
 
 static struct platform_driver imx_intmux_driver = {
 	.driver = {
-		.name = "imx-intmux",
-		.of_match_table = imx_intmux_id,
-		.pm = &imx_intmux_pm_ops,
+		.name		= "imx-intmux",
+		.of_match_table	= imx_intmux_id,
+		.pm		= &imx_intmux_pm_ops,
 	},
-	.probe = imx_intmux_probe,
-	.remove = imx_intmux_remove,
+	.probe		= imx_intmux_probe,
+	.remove_new	= imx_intmux_remove,
 };
 builtin_platform_driver(imx_intmux_driver);
diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c
index bd9543314539..20cf7a9e9ece 100644
--- a/drivers/irqchip/irq-imx-irqsteer.c
+++ b/drivers/irqchip/irq-imx-irqsteer.c
@@ -231,7 +231,7 @@ out:
 	return ret;
 }
 
-static int imx_irqsteer_remove(struct platform_device *pdev)
+static void imx_irqsteer_remove(struct platform_device *pdev)
 {
 	struct irqsteer_data *irqsteer_data = platform_get_drvdata(pdev);
 	int i;
@@ -243,8 +243,6 @@ static int imx_irqsteer_remove(struct platform_device *pdev)
 	irq_domain_remove(irqsteer_data->domain);
 
 	clk_disable_unprepare(irqsteer_data->ipg_clk);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -307,11 +305,11 @@ static const struct of_device_id imx_irqsteer_dt_ids[] = {
 
 static struct platform_driver imx_irqsteer_driver = {
 	.driver = {
-		.name = "imx-irqsteer",
-		.of_match_table = imx_irqsteer_dt_ids,
-		.pm = &imx_irqsteer_pm_ops,
+		.name		= "imx-irqsteer",
+		.of_match_table	= imx_irqsteer_dt_ids,
+		.pm		= &imx_irqsteer_pm_ops,
 	},
-	.probe = imx_irqsteer_probe,
-	.remove = imx_irqsteer_remove,
+	.probe		= imx_irqsteer_probe,
+	.remove_new	= imx_irqsteer_remove,
 };
 builtin_platform_driver(imx_irqsteer_driver);
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index a36396db4b08..30f1979fa124 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -190,7 +190,7 @@ static int keystone_irq_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int keystone_irq_remove(struct platform_device *pdev)
+static void keystone_irq_remove(struct platform_device *pdev)
 {
 	struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
 	int hwirq;
@@ -201,7 +201,6 @@ static int keystone_irq_remove(struct platform_device *pdev)
 		irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
 
 	irq_domain_remove(kirq->irqd);
-	return 0;
 }
 
 static const struct of_device_id keystone_irq_dt_ids[] = {
@@ -212,7 +211,7 @@ MODULE_DEVICE_TABLE(of, keystone_irq_dt_ids);
 
 static struct platform_driver keystone_irq_device_driver = {
 	.probe		= keystone_irq_probe,
-	.remove		= keystone_irq_remove,
+	.remove_new	= keystone_irq_remove,
 	.driver		= {
 		.name	= "keystone_irq",
 		.of_match_table	= of_match_ptr(keystone_irq_dt_ids),
diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c
index 1623cd779175..b64cbe3052e8 100644
--- a/drivers/irqchip/irq-loongson-eiointc.c
+++ b/drivers/irqchip/irq-loongson-eiointc.c
@@ -198,6 +198,12 @@ static void eiointc_irq_dispatch(struct irq_desc *desc)
 
 	for (i = 0; i < eiointc_priv[0]->vec_count / VEC_COUNT_PER_REG; i++) {
 		pending = iocsr_read64(EIOINTC_REG_ISR + (i << 3));
+
+		/* Skip handling if pending bitmap is zero */
+		if (!pending)
+			continue;
+
+		/* Clear the IRQs */
 		iocsr_write64(pending, EIOINTC_REG_ISR + (i << 3));
 		while (pending) {
 			int bit = __ffs(pending);
@@ -241,7 +247,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int ret;
 	unsigned int i, type;
 	unsigned long hwirq = 0;
-	struct eiointc *priv = domain->host_data;
+	struct eiointc_priv *priv = domain->host_data;
 
 	ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type);
 	if (ret)
@@ -304,23 +310,7 @@ static int eiointc_suspend(void)
 
 static void eiointc_resume(void)
 {
-	int i, j;
-	struct irq_desc *desc;
-	struct irq_data *irq_data;
-
 	eiointc_router_init(0);
-
-	for (i = 0; i < nr_pics; i++) {
-		for (j = 0; j < eiointc_priv[0]->vec_count; j++) {
-			desc = irq_resolve_mapping(eiointc_priv[i]->eiointc_domain, j);
-			if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) {
-				raw_spin_lock(&desc->lock);
-				irq_data = irq_domain_get_irq_data(eiointc_priv[i]->eiointc_domain, irq_desc_get_irq(desc));
-				eiointc_set_irq_affinity(irq_data, irq_data->common->affinity, 0);
-				raw_spin_unlock(&desc->lock);
-			}
-		}
-	}
 }
 
 static struct syscore_ops eiointc_syscore_ops = {
diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c
index 15cf80b46322..1aef5c4d27c6 100644
--- a/drivers/irqchip/irq-ls-scfg-msi.c
+++ b/drivers/irqchip/irq-ls-scfg-msi.c
@@ -398,7 +398,7 @@ static int ls_scfg_msi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ls_scfg_msi_remove(struct platform_device *pdev)
+static void ls_scfg_msi_remove(struct platform_device *pdev)
 {
 	struct ls_scfg_msi *msi_data = platform_get_drvdata(pdev);
 	int i;
@@ -410,17 +410,15 @@ static int ls_scfg_msi_remove(struct platform_device *pdev)
 	irq_domain_remove(msi_data->parent);
 
 	platform_set_drvdata(pdev, NULL);
-
-	return 0;
 }
 
 static struct platform_driver ls_scfg_msi_driver = {
 	.driver = {
-		.name = "ls-scfg-msi",
-		.of_match_table = ls_scfg_msi_id,
+		.name		= "ls-scfg-msi",
+		.of_match_table	= ls_scfg_msi_id,
 	},
-	.probe = ls_scfg_msi_probe,
-	.remove = ls_scfg_msi_remove,
+	.probe		= ls_scfg_msi_probe,
+	.remove_new	= ls_scfg_msi_remove,
 };
 
 module_platform_driver(ls_scfg_msi_driver);
diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c
index 3eb1f8cdf674..acceb6e7fa95 100644
--- a/drivers/irqchip/irq-madera.c
+++ b/drivers/irqchip/irq-madera.c
@@ -222,7 +222,7 @@ static int madera_irq_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int madera_irq_remove(struct platform_device *pdev)
+static void madera_irq_remove(struct platform_device *pdev)
 {
 	struct madera *madera = dev_get_drvdata(pdev->dev.parent);
 
@@ -232,13 +232,11 @@ static int madera_irq_remove(struct platform_device *pdev)
 	 */
 	madera->irq_dev = NULL;
 	regmap_del_irq_chip(madera->irq, madera->irq_data);
-
-	return 0;
 }
 
 static struct platform_driver madera_irq_driver = {
-	.probe	= &madera_irq_probe,
-	.remove = &madera_irq_remove,
+	.probe		= madera_irq_probe,
+	.remove_new	= madera_irq_remove,
 	.driver = {
 		.name	= "madera-irq",
 		.pm	= &madera_irq_pm_ops,
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 5101a3fb11df..58881d313979 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -235,22 +235,17 @@ static const struct irq_domain_ops mbigen_domain_ops = {
 static int mbigen_of_create_domain(struct platform_device *pdev,
 				   struct mbigen_device *mgn_chip)
 {
-	struct device *parent;
 	struct platform_device *child;
 	struct irq_domain *domain;
 	struct device_node *np;
 	u32 num_pins;
 	int ret = 0;
 
-	parent = bus_get_dev_root(&platform_bus_type);
-	if (!parent)
-		return -ENODEV;
-
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_property_read_bool(np, "interrupt-controller"))
 			continue;
 
-		child = of_platform_device_create(np, NULL, parent);
+		child = of_platform_device_create(np, NULL, NULL);
 		if (!child) {
 			ret = -ENOMEM;
 			break;
@@ -273,7 +268,6 @@ static int mbigen_of_create_domain(struct platform_device *pdev,
 		}
 	}
 
-	put_device(parent);
 	if (ret)
 		of_node_put(np);
 
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index f88df39f4129..9a1791908598 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -154,6 +154,10 @@ static const struct meson_gpio_irq_params c3_params = {
 	INIT_MESON_S4_COMMON_DATA(55)
 };
 
+static const struct meson_gpio_irq_params t7_params = {
+	INIT_MESON_S4_COMMON_DATA(157)
+};
+
 static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = {
 	{ .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params },
 	{ .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params },
@@ -165,6 +169,7 @@ static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = {
 	{ .compatible = "amlogic,meson-a1-gpio-intc", .data = &a1_params },
 	{ .compatible = "amlogic,meson-s4-gpio-intc", .data = &s4_params },
 	{ .compatible = "amlogic,c3-gpio-intc", .data = &c3_params },
+	{ .compatible = "amlogic,t7-gpio-intc", .data = &t7_params },
 	{ }
 };
 
diff --git a/drivers/irqchip/irq-mvebu-pic.c b/drivers/irqchip/irq-mvebu-pic.c
index ef3d3646ccc2..d17d9c0e2880 100644
--- a/drivers/irqchip/irq-mvebu-pic.c
+++ b/drivers/irqchip/irq-mvebu-pic.c
@@ -167,14 +167,12 @@ static int mvebu_pic_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mvebu_pic_remove(struct platform_device *pdev)
+static void mvebu_pic_remove(struct platform_device *pdev)
 {
 	struct mvebu_pic *pic = platform_get_drvdata(pdev);
 
 	on_each_cpu(mvebu_pic_disable_percpu_irq, pic, 1);
 	irq_domain_remove(pic->domain);
-
-	return 0;
 }
 
 static const struct of_device_id mvebu_pic_of_match[] = {
@@ -184,11 +182,11 @@ static const struct of_device_id mvebu_pic_of_match[] = {
 MODULE_DEVICE_TABLE(of, mvebu_pic_of_match);
 
 static struct platform_driver mvebu_pic_driver = {
-	.probe  = mvebu_pic_probe,
-	.remove = mvebu_pic_remove,
+	.probe		= mvebu_pic_probe,
+	.remove_new	= mvebu_pic_remove,
 	.driver = {
-		.name = "mvebu-pic",
-		.of_match_table = mvebu_pic_of_match,
+		.name		= "mvebu-pic",
+		.of_match_table	= mvebu_pic_of_match,
 	},
 };
 module_platform_driver(mvebu_pic_driver);
diff --git a/drivers/irqchip/irq-pruss-intc.c b/drivers/irqchip/irq-pruss-intc.c
index 0f64ecb9b1f4..060eb000e9d3 100644
--- a/drivers/irqchip/irq-pruss-intc.c
+++ b/drivers/irqchip/irq-pruss-intc.c
@@ -599,7 +599,7 @@ fail_irq:
 	return ret;
 }
 
-static int pruss_intc_remove(struct platform_device *pdev)
+static void pruss_intc_remove(struct platform_device *pdev)
 {
 	struct pruss_intc *intc = platform_get_drvdata(pdev);
 	u8 max_system_events = intc->soc_config->num_system_events;
@@ -616,8 +616,6 @@ static int pruss_intc_remove(struct platform_device *pdev)
 		irq_dispose_mapping(irq_find_mapping(intc->domain, hwirq));
 
 	irq_domain_remove(intc->domain);
-
-	return 0;
 }
 
 static const struct pruss_intc_match_data pruss_intc_data = {
@@ -645,12 +643,12 @@ MODULE_DEVICE_TABLE(of, pruss_intc_of_match);
 
 static struct platform_driver pruss_intc_driver = {
 	.driver = {
-		.name = "pruss-intc",
-		.of_match_table = pruss_intc_of_match,
-		.suppress_bind_attrs = true,
+		.name			= "pruss-intc",
+		.of_match_table		= pruss_intc_of_match,
+		.suppress_bind_attrs	= true,
 	},
-	.probe  = pruss_intc_probe,
-	.remove = pruss_intc_remove,
+	.probe		= pruss_intc_probe,
+	.remove_new	= pruss_intc_remove,
 };
 module_platform_driver(pruss_intc_driver);
 
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index cda5838d2232..7942d8eb3d00 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -389,8 +389,8 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent)
 		/* Don't use devm_ioremap_resource, as we're accessing a shared region. */
 		priv->base = devm_ioremap(dev, res.start, resource_size(&res));
 		of_node_put(msgram_np);
-		if (IS_ERR(priv->base))
-			return PTR_ERR(priv->base);
+		if (!priv->base)
+			return -ENOMEM;
 	} else {
 		/* Otherwise, fall back to simple MMIO. */
 		priv->base = devm_platform_ioremap_resource(pdev, 0);
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index fa19585f3dee..9ad37237ba95 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -561,14 +561,13 @@ err0:
 	return ret;
 }
 
-static int intc_irqpin_remove(struct platform_device *pdev)
+static void intc_irqpin_remove(struct platform_device *pdev)
 {
 	struct intc_irqpin_priv *p = platform_get_drvdata(pdev);
 
 	irq_domain_remove(p->irq_domain);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int __maybe_unused intc_irqpin_suspend(struct device *dev)
@@ -585,11 +584,11 @@ static SIMPLE_DEV_PM_OPS(intc_irqpin_pm_ops, intc_irqpin_suspend, NULL);
 
 static struct platform_driver intc_irqpin_device_driver = {
 	.probe		= intc_irqpin_probe,
-	.remove		= intc_irqpin_remove,
+	.remove_new	= intc_irqpin_remove,
 	.driver		= {
-		.name	= "renesas_intc_irqpin",
-		.of_match_table = intc_irqpin_dt_ids,
-		.pm	= &intc_irqpin_pm_ops,
+		.name		= "renesas_intc_irqpin",
+		.of_match_table	= intc_irqpin_dt_ids,
+		.pm		= &intc_irqpin_pm_ops,
 	}
 };
 
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index 49b446b396f9..76026e0b8e20 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -218,14 +218,13 @@ err_runtime_pm_disable:
 	return ret;
 }
 
-static int irqc_remove(struct platform_device *pdev)
+static void irqc_remove(struct platform_device *pdev)
 {
 	struct irqc_priv *p = platform_get_drvdata(pdev);
 
 	irq_domain_remove(p->irq_domain);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return 0;
 }
 
 static int __maybe_unused irqc_suspend(struct device *dev)
@@ -248,11 +247,11 @@ MODULE_DEVICE_TABLE(of, irqc_dt_ids);
 
 static struct platform_driver irqc_device_driver = {
 	.probe		= irqc_probe,
-	.remove		= irqc_remove,
+	.remove_new	= irqc_remove,
 	.driver		= {
-		.name	= "renesas_irqc",
+		.name		= "renesas_irqc",
 		.of_match_table	= irqc_dt_ids,
-		.pm	= &irqc_pm_ops,
+		.pm		= &irqc_pm_ops,
 	}
 };
 
diff --git a/drivers/irqchip/irq-renesas-rza1.c b/drivers/irqchip/irq-renesas-rza1.c
index e4c99c2e0373..f05afe82db4d 100644
--- a/drivers/irqchip/irq-renesas-rza1.c
+++ b/drivers/irqchip/irq-renesas-rza1.c
@@ -244,12 +244,11 @@ out_put_node:
 	return ret;
 }
 
-static int rza1_irqc_remove(struct platform_device *pdev)
+static void rza1_irqc_remove(struct platform_device *pdev)
 {
 	struct rza1_irqc_priv *priv = platform_get_drvdata(pdev);
 
 	irq_domain_remove(priv->irq_domain);
-	return 0;
 }
 
 static const struct of_device_id rza1_irqc_dt_ids[] = {
@@ -260,9 +259,9 @@ MODULE_DEVICE_TABLE(of, rza1_irqc_dt_ids);
 
 static struct platform_driver rza1_irqc_device_driver = {
 	.probe		= rza1_irqc_probe,
-	.remove		= rza1_irqc_remove,
+	.remove_new	= rza1_irqc_remove,
 	.driver		= {
-		.name	= "renesas_rza1_irqc",
+		.name		= "renesas_rza1_irqc",
 		.of_match_table	= rza1_irqc_dt_ids,
 	}
 };
diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c
index e8d01b14ccdd..f87aeab460eb 100644
--- a/drivers/irqchip/irq-riscv-intc.c
+++ b/drivers/irqchip/irq-riscv-intc.c
@@ -17,17 +17,29 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/smp.h>
+#include <linux/soc/andes/irq.h>
+
+#include <asm/hwcap.h>
 
 static struct irq_domain *intc_domain;
+static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG;
+static unsigned int riscv_intc_custom_base __ro_after_init = BITS_PER_LONG;
+static unsigned int riscv_intc_custom_nr_irqs __ro_after_init;
 
 static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
 {
 	unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG;
 
-	if (unlikely(cause >= BITS_PER_LONG))
-		panic("unexpected interrupt cause");
+	if (generic_handle_domain_irq(intc_domain, cause))
+		pr_warn_ratelimited("Failed to handle interrupt (cause: %ld)\n", cause);
+}
+
+static asmlinkage void riscv_intc_aia_irq(struct pt_regs *regs)
+{
+	unsigned long topi;
 
-	generic_handle_domain_irq(intc_domain, cause);
+	while ((topi = csr_read(CSR_TOPI)))
+		generic_handle_domain_irq(intc_domain, topi >> TOPI_IID_SHIFT);
 }
 
 /*
@@ -39,12 +51,43 @@ static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
 
 static void riscv_intc_irq_mask(struct irq_data *d)
 {
-	csr_clear(CSR_IE, BIT(d->hwirq));
+	if (IS_ENABLED(CONFIG_32BIT) && d->hwirq >= BITS_PER_LONG)
+		csr_clear(CSR_IEH, BIT(d->hwirq - BITS_PER_LONG));
+	else
+		csr_clear(CSR_IE, BIT(d->hwirq));
 }
 
 static void riscv_intc_irq_unmask(struct irq_data *d)
 {
-	csr_set(CSR_IE, BIT(d->hwirq));
+	if (IS_ENABLED(CONFIG_32BIT) && d->hwirq >= BITS_PER_LONG)
+		csr_set(CSR_IEH, BIT(d->hwirq - BITS_PER_LONG));
+	else
+		csr_set(CSR_IE, BIT(d->hwirq));
+}
+
+static void andes_intc_irq_mask(struct irq_data *d)
+{
+	/*
+	 * Andes specific S-mode local interrupt causes (hwirq)
+	 * are defined as (256 + n) and controlled by n-th bit
+	 * of SLIE.
+	 */
+	unsigned int mask = BIT(d->hwirq % BITS_PER_LONG);
+
+	if (d->hwirq < ANDES_SLI_CAUSE_BASE)
+		csr_clear(CSR_IE, mask);
+	else
+		csr_clear(ANDES_CSR_SLIE, mask);
+}
+
+static void andes_intc_irq_unmask(struct irq_data *d)
+{
+	unsigned int mask = BIT(d->hwirq % BITS_PER_LONG);
+
+	if (d->hwirq < ANDES_SLI_CAUSE_BASE)
+		csr_set(CSR_IE, mask);
+	else
+		csr_set(ANDES_CSR_SLIE, mask);
 }
 
 static void riscv_intc_irq_eoi(struct irq_data *d)
@@ -70,12 +113,21 @@ static struct irq_chip riscv_intc_chip = {
 	.irq_eoi = riscv_intc_irq_eoi,
 };
 
+static struct irq_chip andes_intc_chip = {
+	.name		= "RISC-V INTC",
+	.irq_mask	= andes_intc_irq_mask,
+	.irq_unmask	= andes_intc_irq_unmask,
+	.irq_eoi	= riscv_intc_irq_eoi,
+};
+
 static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq,
 				 irq_hw_number_t hwirq)
 {
+	struct irq_chip *chip = d->host_data;
+
 	irq_set_percpu_devid(irq);
-	irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data,
-			    handle_percpu_devid_irq, NULL, NULL);
+	irq_domain_set_info(d, irq, hwirq, chip, NULL, handle_percpu_devid_irq,
+			    NULL, NULL);
 
 	return 0;
 }
@@ -93,6 +145,14 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain,
 	if (ret)
 		return ret;
 
+	/*
+	 * Only allow hwirq for which we have corresponding standard or
+	 * custom interrupt enable register.
+	 */
+	if ((hwirq >= riscv_intc_nr_irqs && hwirq < riscv_intc_custom_base) ||
+	    (hwirq >= riscv_intc_custom_base + riscv_intc_custom_nr_irqs))
+		return -EINVAL;
+
 	for (i = 0; i < nr_irqs; i++) {
 		ret = riscv_intc_domain_map(domain, virq + i, hwirq + i);
 		if (ret)
@@ -113,18 +173,20 @@ static struct fwnode_handle *riscv_intc_hwnode(void)
 	return intc_domain->fwnode;
 }
 
-static int __init riscv_intc_init_common(struct fwnode_handle *fn)
+static int __init riscv_intc_init_common(struct fwnode_handle *fn, struct irq_chip *chip)
 {
 	int rc;
 
-	intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG,
-					       &riscv_intc_domain_ops, NULL);
+	intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, chip);
 	if (!intc_domain) {
 		pr_err("unable to add IRQ domain\n");
 		return -ENXIO;
 	}
 
-	rc = set_handle_irq(&riscv_intc_irq);
+	if (riscv_isa_extension_available(NULL, SxAIA))
+		rc = set_handle_irq(&riscv_intc_aia_irq);
+	else
+		rc = set_handle_irq(&riscv_intc_irq);
 	if (rc) {
 		pr_err("failed to set irq handler\n");
 		return rc;
@@ -132,7 +194,11 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn)
 
 	riscv_set_intc_hwnode_fn(riscv_intc_hwnode);
 
-	pr_info("%d local interrupts mapped\n", BITS_PER_LONG);
+	pr_info("%d local interrupts mapped%s\n",
+		riscv_isa_extension_available(NULL, SxAIA) ? 64 : riscv_intc_nr_irqs,
+		riscv_isa_extension_available(NULL, SxAIA) ? " using AIA" : "");
+	if (riscv_intc_custom_nr_irqs)
+		pr_info("%d custom local interrupts mapped\n", riscv_intc_custom_nr_irqs);
 
 	return 0;
 }
@@ -140,8 +206,9 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn)
 static int __init riscv_intc_init(struct device_node *node,
 				  struct device_node *parent)
 {
-	int rc;
+	struct irq_chip *chip = &riscv_intc_chip;
 	unsigned long hartid;
+	int rc;
 
 	rc = riscv_of_parent_hartid(node, &hartid);
 	if (rc < 0) {
@@ -166,10 +233,17 @@ static int __init riscv_intc_init(struct device_node *node,
 		return 0;
 	}
 
-	return riscv_intc_init_common(of_node_to_fwnode(node));
+	if (of_device_is_compatible(node, "andestech,cpu-intc")) {
+		riscv_intc_custom_base = ANDES_SLI_CAUSE_BASE;
+		riscv_intc_custom_nr_irqs = ANDES_RV_IRQ_LAST;
+		chip = &andes_intc_chip;
+	}
+
+	return riscv_intc_init_common(of_node_to_fwnode(node), chip);
 }
 
 IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init);
+IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init);
 
 #ifdef CONFIG_ACPI
 
@@ -196,7 +270,7 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header,
 		return -ENOMEM;
 	}
 
-	return riscv_intc_init_common(fn);
+	return riscv_intc_init_common(fn, &riscv_intc_chip);
 }
 
 IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL,
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 5b7bc4fd9517..f3d4cb9e34f7 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2017 SiFive
  * Copyright (C) 2018 Christoph Hellwig
  */
-#define pr_fmt(fmt) "plic: " fmt
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -64,6 +63,7 @@
 #define PLIC_QUIRK_EDGE_INTERRUPT	0
 
 struct plic_priv {
+	struct device *dev;
 	struct cpumask lmask;
 	struct irq_domain *irqdomain;
 	void __iomem *regs;
@@ -103,9 +103,11 @@ static void __plic_toggle(void __iomem *enable_base, int hwirq, int enable)
 
 static void plic_toggle(struct plic_handler *handler, int hwirq, int enable)
 {
-	raw_spin_lock(&handler->enable_lock);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&handler->enable_lock, flags);
 	__plic_toggle(handler->enable_base, hwirq, enable);
-	raw_spin_unlock(&handler->enable_lock);
+	raw_spin_unlock_irqrestore(&handler->enable_lock, flags);
 }
 
 static inline void plic_irq_toggle(const struct cpumask *mask,
@@ -148,7 +150,13 @@ static void plic_irq_eoi(struct irq_data *d)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
 
-	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	if (unlikely(irqd_irq_disabled(d))) {
+		plic_toggle(handler, d->hwirq, 1);
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+		plic_toggle(handler, d->hwirq, 0);
+	} else {
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	}
 }
 
 #ifdef CONFIG_SMP
@@ -236,6 +244,7 @@ static int plic_irq_set_type(struct irq_data *d, unsigned int type)
 static int plic_irq_suspend(void)
 {
 	unsigned int i, cpu;
+	unsigned long flags;
 	u32 __iomem *reg;
 	struct plic_priv *priv;
 
@@ -253,12 +262,12 @@ static int plic_irq_suspend(void)
 		if (!handler->present)
 			continue;
 
-		raw_spin_lock(&handler->enable_lock);
+		raw_spin_lock_irqsave(&handler->enable_lock, flags);
 		for (i = 0; i < DIV_ROUND_UP(priv->nr_irqs, 32); i++) {
 			reg = handler->enable_base + i * sizeof(u32);
 			handler->enable_save[i] = readl(reg);
 		}
-		raw_spin_unlock(&handler->enable_lock);
+		raw_spin_unlock_irqrestore(&handler->enable_lock, flags);
 	}
 
 	return 0;
@@ -267,6 +276,7 @@ static int plic_irq_suspend(void)
 static void plic_irq_resume(void)
 {
 	unsigned int i, index, cpu;
+	unsigned long flags;
 	u32 __iomem *reg;
 	struct plic_priv *priv;
 
@@ -284,12 +294,12 @@ static void plic_irq_resume(void)
 		if (!handler->present)
 			continue;
 
-		raw_spin_lock(&handler->enable_lock);
+		raw_spin_lock_irqsave(&handler->enable_lock, flags);
 		for (i = 0; i < DIV_ROUND_UP(priv->nr_irqs, 32); i++) {
 			reg = handler->enable_base + i * sizeof(u32);
 			writel(handler->enable_save[i], reg);
 		}
-		raw_spin_unlock(&handler->enable_lock);
+		raw_spin_unlock_irqrestore(&handler->enable_lock, flags);
 	}
 }
 
@@ -370,9 +380,10 @@ static void plic_handle_irq(struct irq_desc *desc)
 	while ((hwirq = readl(claim))) {
 		int err = generic_handle_domain_irq(handler->priv->irqdomain,
 						    hwirq);
-		if (unlikely(err))
-			pr_warn_ratelimited("can't find mapping for hwirq %lu\n",
-					hwirq);
+		if (unlikely(err)) {
+			dev_warn_ratelimited(handler->priv->dev,
+					     "can't find mapping for hwirq %lu\n", hwirq);
+		}
 	}
 
 	chained_irq_exit(chip, desc);
@@ -400,63 +411,122 @@ static int plic_starting_cpu(unsigned int cpu)
 		enable_percpu_irq(plic_parent_irq,
 				  irq_get_trigger_type(plic_parent_irq));
 	else
-		pr_warn("cpu%d: parent irq not available\n", cpu);
+		dev_warn(handler->priv->dev, "cpu%d: parent irq not available\n", cpu);
 	plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
 
 	return 0;
 }
 
-static int __init __plic_init(struct device_node *node,
-			      struct device_node *parent,
-			      unsigned long plic_quirks)
+static const struct of_device_id plic_match[] = {
+	{ .compatible = "sifive,plic-1.0.0" },
+	{ .compatible = "riscv,plic0" },
+	{ .compatible = "andestech,nceplic100",
+	  .data = (const void *)BIT(PLIC_QUIRK_EDGE_INTERRUPT) },
+	{ .compatible = "thead,c900-plic",
+	  .data = (const void *)BIT(PLIC_QUIRK_EDGE_INTERRUPT) },
+	{}
+};
+
+static int plic_parse_nr_irqs_and_contexts(struct platform_device *pdev,
+					   u32 *nr_irqs, u32 *nr_contexts)
 {
-	int error = 0, nr_contexts, nr_handlers = 0, i;
-	u32 nr_irqs;
-	struct plic_priv *priv;
-	struct plic_handler *handler;
-	unsigned int cpu;
+	struct device *dev = &pdev->dev;
+	int rc;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
+	/*
+	 * Currently, only OF fwnode is supported so extend this
+	 * function for ACPI support.
+	 */
+	if (!is_of_node(dev->fwnode))
+		return -EINVAL;
 
-	priv->plic_quirks = plic_quirks;
+	rc = of_property_read_u32(to_of_node(dev->fwnode), "riscv,ndev", nr_irqs);
+	if (rc) {
+		dev_err(dev, "riscv,ndev property not available\n");
+		return rc;
+	}
 
-	priv->regs = of_iomap(node, 0);
-	if (WARN_ON(!priv->regs)) {
-		error = -EIO;
-		goto out_free_priv;
+	*nr_contexts = of_irq_count(to_of_node(dev->fwnode));
+	if (WARN_ON(!(*nr_contexts))) {
+		dev_err(dev, "no PLIC context available\n");
+		return -EINVAL;
 	}
 
-	error = -EINVAL;
-	of_property_read_u32(node, "riscv,ndev", &nr_irqs);
-	if (WARN_ON(!nr_irqs))
-		goto out_iounmap;
+	return 0;
+}
 
-	priv->nr_irqs = nr_irqs;
+static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
+				     u32 *parent_hwirq, int *parent_cpu)
+{
+	struct device *dev = &pdev->dev;
+	struct of_phandle_args parent;
+	unsigned long hartid;
+	int rc;
 
-	priv->prio_save = bitmap_alloc(nr_irqs, GFP_KERNEL);
-	if (!priv->prio_save)
-		goto out_free_priority_reg;
+	/*
+	 * Currently, only OF fwnode is supported so extend this
+	 * function for ACPI support.
+	 */
+	if (!is_of_node(dev->fwnode))
+		return -EINVAL;
 
-	nr_contexts = of_irq_count(node);
-	if (WARN_ON(!nr_contexts))
-		goto out_free_priority_reg;
+	rc = of_irq_parse_one(to_of_node(dev->fwnode), context, &parent);
+	if (rc)
+		return rc;
 
-	error = -ENOMEM;
-	priv->irqdomain = irq_domain_add_linear(node, nr_irqs + 1,
-			&plic_irqdomain_ops, priv);
-	if (WARN_ON(!priv->irqdomain))
-		goto out_free_priority_reg;
+	rc = riscv_of_parent_hartid(parent.np, &hartid);
+	if (rc)
+		return rc;
 
-	for (i = 0; i < nr_contexts; i++) {
-		struct of_phandle_args parent;
-		irq_hw_number_t hwirq;
-		int cpu;
-		unsigned long hartid;
+	*parent_hwirq = parent.args[0];
+	*parent_cpu = riscv_hartid_to_cpuid(hartid);
+	return 0;
+}
+
+static int plic_probe(struct platform_device *pdev)
+{
+	int error = 0, nr_contexts, nr_handlers = 0, cpu, i;
+	struct device *dev = &pdev->dev;
+	unsigned long plic_quirks = 0;
+	struct plic_handler *handler;
+	u32 nr_irqs, parent_hwirq;
+	struct irq_domain *domain;
+	struct plic_priv *priv;
+	irq_hw_number_t hwirq;
+	bool cpuhp_setup;
 
-		if (of_irq_parse_one(node, i, &parent)) {
-			pr_err("failed to parse parent for context %d.\n", i);
+	if (is_of_node(dev->fwnode)) {
+		const struct of_device_id *id;
+
+		id = of_match_node(plic_match, to_of_node(dev->fwnode));
+		if (id)
+			plic_quirks = (unsigned long)id->data;
+	}
+
+	error = plic_parse_nr_irqs_and_contexts(pdev, &nr_irqs, &nr_contexts);
+	if (error)
+		return error;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+	priv->plic_quirks = plic_quirks;
+	priv->nr_irqs = nr_irqs;
+
+	priv->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (WARN_ON(!priv->regs))
+		return -EIO;
+
+	priv->prio_save = devm_bitmap_zalloc(dev, nr_irqs, GFP_KERNEL);
+	if (!priv->prio_save)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_contexts; i++) {
+		error = plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu);
+		if (error) {
+			dev_warn(dev, "hwirq for context%d not found\n", i);
 			continue;
 		}
 
@@ -464,7 +534,7 @@ static int __init __plic_init(struct device_node *node,
 		 * Skip contexts other than external interrupts for our
 		 * privilege level.
 		 */
-		if (parent.args[0] != RV_IRQ_EXT) {
+		if (parent_hwirq != RV_IRQ_EXT) {
 			/* Disable S-mode enable bits if running in M-mode. */
 			if (IS_ENABLED(CONFIG_RISCV_M_MODE)) {
 				void __iomem *enable_base = priv->regs +
@@ -477,24 +547,17 @@ static int __init __plic_init(struct device_node *node,
 			continue;
 		}
 
-		error = riscv_of_parent_hartid(parent.np, &hartid);
-		if (error < 0) {
-			pr_warn("failed to parse hart ID for context %d.\n", i);
-			continue;
-		}
-
-		cpu = riscv_hartid_to_cpuid(hartid);
 		if (cpu < 0) {
-			pr_warn("Invalid cpuid for context %d\n", i);
+			dev_warn(dev, "Invalid cpuid for context %d\n", i);
 			continue;
 		}
 
 		/* Find parent domain and register chained handler */
-		if (!plic_parent_irq && irq_find_host(parent.np)) {
-			plic_parent_irq = irq_of_parse_and_map(node, i);
+		domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY);
+		if (!plic_parent_irq && domain) {
+			plic_parent_irq = irq_create_mapping(domain, RV_IRQ_EXT);
 			if (plic_parent_irq)
-				irq_set_chained_handler(plic_parent_irq,
-							plic_handle_irq);
+				irq_set_chained_handler(plic_parent_irq, plic_handle_irq);
 		}
 
 		/*
@@ -504,7 +567,7 @@ static int __init __plic_init(struct device_node *node,
 		 */
 		handler = per_cpu_ptr(&plic_handlers, cpu);
 		if (handler->present) {
-			pr_warn("handler already present for context %d.\n", i);
+			dev_warn(dev, "handler already present for context %d.\n", i);
 			plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
 			goto done;
 		}
@@ -518,10 +581,10 @@ static int __init __plic_init(struct device_node *node,
 			i * CONTEXT_ENABLE_SIZE;
 		handler->priv = priv;
 
-		handler->enable_save =  kcalloc(DIV_ROUND_UP(nr_irqs, 32),
-						sizeof(*handler->enable_save), GFP_KERNEL);
+		handler->enable_save = devm_kcalloc(dev, DIV_ROUND_UP(nr_irqs, 32),
+						    sizeof(*handler->enable_save), GFP_KERNEL);
 		if (!handler->enable_save)
-			goto out_free_enable_reg;
+			goto fail_cleanup_contexts;
 done:
 		for (hwirq = 1; hwirq <= nr_irqs; hwirq++) {
 			plic_toggle(handler, hwirq, 0);
@@ -531,52 +594,60 @@ done:
 		nr_handlers++;
 	}
 
+	priv->irqdomain = irq_domain_add_linear(to_of_node(dev->fwnode), nr_irqs + 1,
+						&plic_irqdomain_ops, priv);
+	if (WARN_ON(!priv->irqdomain))
+		goto fail_cleanup_contexts;
+
 	/*
 	 * We can have multiple PLIC instances so setup cpuhp state
-	 * and register syscore operations only when context handler
-	 * for current/boot CPU is present.
+	 * and register syscore operations only once after context
+	 * handlers of all online CPUs are initialized.
 	 */
-	handler = this_cpu_ptr(&plic_handlers);
-	if (handler->present && !plic_cpuhp_setup_done) {
-		cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
-				  "irqchip/sifive/plic:starting",
-				  plic_starting_cpu, plic_dying_cpu);
-		register_syscore_ops(&plic_irq_syscore_ops);
-		plic_cpuhp_setup_done = true;
+	if (!plic_cpuhp_setup_done) {
+		cpuhp_setup = true;
+		for_each_online_cpu(cpu) {
+			handler = per_cpu_ptr(&plic_handlers, cpu);
+			if (!handler->present) {
+				cpuhp_setup = false;
+				break;
+			}
+		}
+		if (cpuhp_setup) {
+			cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+					  "irqchip/sifive/plic:starting",
+					  plic_starting_cpu, plic_dying_cpu);
+			register_syscore_ops(&plic_irq_syscore_ops);
+			plic_cpuhp_setup_done = true;
+		}
 	}
 
-	pr_info("%pOFP: mapped %d interrupts with %d handlers for"
-		" %d contexts.\n", node, nr_irqs, nr_handlers, nr_contexts);
+	dev_info(dev, "mapped %d interrupts with %d handlers for %d contexts.\n",
+		 nr_irqs, nr_handlers, nr_contexts);
 	return 0;
 
-out_free_enable_reg:
-	for_each_cpu(cpu, cpu_present_mask) {
+fail_cleanup_contexts:
+	for (i = 0; i < nr_contexts; i++) {
+		if (plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu))
+			continue;
+		if (parent_hwirq != RV_IRQ_EXT || cpu < 0)
+			continue;
+
 		handler = per_cpu_ptr(&plic_handlers, cpu);
-		kfree(handler->enable_save);
+		handler->present = false;
+		handler->hart_base = NULL;
+		handler->enable_base = NULL;
+		handler->enable_save = NULL;
+		handler->priv = NULL;
 	}
-out_free_priority_reg:
-	kfree(priv->prio_save);
-out_iounmap:
-	iounmap(priv->regs);
-out_free_priv:
-	kfree(priv);
-	return error;
+	return -ENOMEM;
 }
 
-static int __init plic_init(struct device_node *node,
-			    struct device_node *parent)
-{
-	return __plic_init(node, parent, 0);
-}
-
-IRQCHIP_DECLARE(sifive_plic, "sifive,plic-1.0.0", plic_init);
-IRQCHIP_DECLARE(riscv_plic0, "riscv,plic0", plic_init); /* for legacy systems */
-
-static int __init plic_edge_init(struct device_node *node,
-				 struct device_node *parent)
-{
-	return __plic_init(node, parent, BIT(PLIC_QUIRK_EDGE_INTERRUPT));
-}
-
-IRQCHIP_DECLARE(andestech_nceplic100, "andestech,nceplic100", plic_edge_init);
-IRQCHIP_DECLARE(thead_c900_plic, "thead,c900-plic", plic_edge_init);
+static struct platform_driver plic_driver = {
+	.driver = {
+		.name		= "riscv-plic",
+		.of_match_table	= plic_match,
+	},
+	.probe = plic_probe,
+};
+builtin_platform_driver(plic_driver);
diff --git a/drivers/irqchip/irq-starfive-jh8100-intc.c b/drivers/irqchip/irq-starfive-jh8100-intc.c
new file mode 100644
index 000000000000..0f5837176e53
--- /dev/null
+++ b/drivers/irqchip/irq-starfive-jh8100-intc.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * StarFive JH8100 External Interrupt Controller driver
+ *
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Changhuang Liang <changhuang.liang@starfivetech.com>
+ */
+
+#define pr_fmt(fmt) "irq-starfive-jh8100: " fmt
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define STARFIVE_INTC_SRC0_CLEAR	0x10
+#define STARFIVE_INTC_SRC0_MASK		0x14
+#define STARFIVE_INTC_SRC0_INT		0x1c
+
+#define STARFIVE_INTC_SRC_IRQ_NUM	32
+
+struct starfive_irq_chip {
+	void __iomem		*base;
+	struct irq_domain	*domain;
+	raw_spinlock_t		lock;
+};
+
+static void starfive_intc_bit_set(struct starfive_irq_chip *irqc,
+				  u32 reg, u32 bit_mask)
+{
+	u32 value;
+
+	value = ioread32(irqc->base + reg);
+	value |= bit_mask;
+	iowrite32(value, irqc->base + reg);
+}
+
+static void starfive_intc_bit_clear(struct starfive_irq_chip *irqc,
+				    u32 reg, u32 bit_mask)
+{
+	u32 value;
+
+	value = ioread32(irqc->base + reg);
+	value &= ~bit_mask;
+	iowrite32(value, irqc->base + reg);
+}
+
+static void starfive_intc_unmask(struct irq_data *d)
+{
+	struct starfive_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+
+	raw_spin_lock(&irqc->lock);
+	starfive_intc_bit_clear(irqc, STARFIVE_INTC_SRC0_MASK, BIT(d->hwirq));
+	raw_spin_unlock(&irqc->lock);
+}
+
+static void starfive_intc_mask(struct irq_data *d)
+{
+	struct starfive_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+
+	raw_spin_lock(&irqc->lock);
+	starfive_intc_bit_set(irqc, STARFIVE_INTC_SRC0_MASK, BIT(d->hwirq));
+	raw_spin_unlock(&irqc->lock);
+}
+
+static struct irq_chip intc_dev = {
+	.name		= "StarFive JH8100 INTC",
+	.irq_unmask	= starfive_intc_unmask,
+	.irq_mask	= starfive_intc_mask,
+};
+
+static int starfive_intc_map(struct irq_domain *d, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_domain_set_info(d, irq, hwirq, &intc_dev, d->host_data,
+			    handle_level_irq, NULL, NULL);
+
+	return 0;
+}
+
+static const struct irq_domain_ops starfive_intc_domain_ops = {
+	.xlate	= irq_domain_xlate_onecell,
+	.map	= starfive_intc_map,
+};
+
+static void starfive_intc_irq_handler(struct irq_desc *desc)
+{
+	struct starfive_irq_chip *irqc = irq_data_get_irq_handler_data(&desc->irq_data);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned long value;
+	int hwirq;
+
+	chained_irq_enter(chip, desc);
+
+	value = ioread32(irqc->base + STARFIVE_INTC_SRC0_INT);
+	while (value) {
+		hwirq = ffs(value) - 1;
+
+		generic_handle_domain_irq(irqc->domain, hwirq);
+
+		starfive_intc_bit_set(irqc, STARFIVE_INTC_SRC0_CLEAR, BIT(hwirq));
+		starfive_intc_bit_clear(irqc, STARFIVE_INTC_SRC0_CLEAR, BIT(hwirq));
+
+		__clear_bit(hwirq, &value);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static int __init starfive_intc_init(struct device_node *intc,
+				     struct device_node *parent)
+{
+	struct starfive_irq_chip *irqc;
+	struct reset_control *rst;
+	struct clk *clk;
+	int parent_irq;
+	int ret;
+
+	irqc = kzalloc(sizeof(*irqc), GFP_KERNEL);
+	if (!irqc)
+		return -ENOMEM;
+
+	irqc->base = of_iomap(intc, 0);
+	if (!irqc->base) {
+		pr_err("Unable to map registers\n");
+		ret = -ENXIO;
+		goto err_free;
+	}
+
+	rst = of_reset_control_get_exclusive(intc, NULL);
+	if (IS_ERR(rst)) {
+		pr_err("Unable to get reset control %pe\n", rst);
+		ret = PTR_ERR(rst);
+		goto err_unmap;
+	}
+
+	clk = of_clk_get(intc, 0);
+	if (IS_ERR(clk)) {
+		pr_err("Unable to get clock %pe\n", clk);
+		ret = PTR_ERR(clk);
+		goto err_reset_put;
+	}
+
+	ret = reset_control_deassert(rst);
+	if (ret)
+		goto err_clk_put;
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		goto err_reset_assert;
+
+	raw_spin_lock_init(&irqc->lock);
+
+	irqc->domain = irq_domain_add_linear(intc, STARFIVE_INTC_SRC_IRQ_NUM,
+					     &starfive_intc_domain_ops, irqc);
+	if (!irqc->domain) {
+		pr_err("Unable to create IRQ domain\n");
+		ret = -EINVAL;
+		goto err_clk_disable;
+	}
+
+	parent_irq = of_irq_get(intc, 0);
+	if (parent_irq < 0) {
+		pr_err("Failed to get main IRQ: %d\n", parent_irq);
+		ret = parent_irq;
+		goto err_remove_domain;
+	}
+
+	irq_set_chained_handler_and_data(parent_irq, starfive_intc_irq_handler,
+					 irqc);
+
+	pr_info("Interrupt controller register, nr_irqs %d\n",
+		STARFIVE_INTC_SRC_IRQ_NUM);
+
+	return 0;
+
+err_remove_domain:
+	irq_domain_remove(irqc->domain);
+err_clk_disable:
+	clk_disable_unprepare(clk);
+err_reset_assert:
+	reset_control_assert(rst);
+err_clk_put:
+	clk_put(clk);
+err_reset_put:
+	reset_control_put(rst);
+err_unmap:
+	iounmap(irqc->base);
+err_free:
+	kfree(irqc);
+	return ret;
+}
+
+IRQCHIP_PLATFORM_DRIVER_BEGIN(starfive_intc)
+IRQCHIP_MATCH("starfive,jh8100-intc", starfive_intc_init)
+IRQCHIP_PLATFORM_DRIVER_END(starfive_intc)
+
+MODULE_DESCRIPTION("StarFive JH8100 External Interrupt Controller");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Changhuang Liang <changhuang.liang@starfivetech.com>");
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 971240e2e31b..26a5193d0ae4 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -898,10 +898,9 @@ static void stm32_exti_remove_irq(void *data)
 	irq_domain_remove(domain);
 }
 
-static int stm32_exti_remove(struct platform_device *pdev)
+static void stm32_exti_remove(struct platform_device *pdev)
 {
 	stm32_exti_h_syscore_deinit();
-	return 0;
 }
 
 static int stm32_exti_probe(struct platform_device *pdev)
@@ -991,10 +990,10 @@ MODULE_DEVICE_TABLE(of, stm32_exti_ids);
 
 static struct platform_driver stm32_exti_driver = {
 	.probe		= stm32_exti_probe,
-	.remove		= stm32_exti_remove,
+	.remove_new	= stm32_exti_remove,
 	.driver		= {
-		.name	= "stm32_exti",
-		.of_match_table = stm32_exti_ids,
+		.name		= "stm32_exti",
+		.of_match_table	= stm32_exti_ids,
 	},
 };
 
diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c
index b2d61d4f6fe6..57f610dab6b8 100644
--- a/drivers/irqchip/irq-ts4800.c
+++ b/drivers/irqchip/irq-ts4800.c
@@ -139,13 +139,11 @@ static int ts4800_ic_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int ts4800_ic_remove(struct platform_device *pdev)
+static void ts4800_ic_remove(struct platform_device *pdev)
 {
 	struct ts4800_irq_data *data = platform_get_drvdata(pdev);
 
 	irq_domain_remove(data->domain);
-
-	return 0;
 }
 
 static const struct of_device_id ts4800_ic_of_match[] = {
@@ -155,11 +153,11 @@ static const struct of_device_id ts4800_ic_of_match[] = {
 MODULE_DEVICE_TABLE(of, ts4800_ic_of_match);
 
 static struct platform_driver ts4800_ic_driver = {
-	.probe  = ts4800_ic_probe,
-	.remove = ts4800_ic_remove,
+	.probe		= ts4800_ic_probe,
+	.remove_new	= ts4800_ic_remove,
 	.driver = {
-		.name = "ts4800-irqc",
-		.of_match_table = ts4800_ic_of_match,
+		.name		= "ts4800-irqc",
+		.of_match_table	= ts4800_ic_of_match,
 	},
 };
 module_platform_driver(ts4800_ic_driver);
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 9e3d5561e04e..ea93e7236c4a 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -47,9 +47,8 @@
 
 /**
  * struct vic_device - VIC PM device
- * @parent_irq: The parent IRQ number of the VIC if cascaded, or 0.
- * @irq: The IRQ number for the base of the VIC.
  * @base: The register base for the VIC.
+ * @irq: The IRQ number for the base of the VIC.
  * @valid_sources: A bitmask of valid interrupts
  * @resume_sources: A bitmask of interrupts for resume.
  * @resume_irqs: The IRQs enabled for resume.
diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
index e3e28a4f7d01..b1abc2a0c971 100644
--- a/drivers/mailbox/bcm-flexrm-mailbox.c
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -1587,8 +1587,8 @@ static int flexrm_mbox_probe(struct platform_device *pdev)
 	}
 
 	/* Allocate platform MSIs for each ring */
-	ret = platform_msi_domain_alloc_irqs(dev, mbox->num_rings,
-						flexrm_mbox_msi_write);
+	ret = platform_device_msi_init_and_alloc_irqs(dev, mbox->num_rings,
+						      flexrm_mbox_msi_write);
 	if (ret)
 		goto fail_destroy_cmpl_pool;
 
@@ -1641,7 +1641,7 @@ skip_debugfs:
 
 fail_free_debugfs_root:
 	debugfs_remove_recursive(mbox->root);
-	platform_msi_domain_free_irqs(dev);
+	platform_device_msi_free_irqs_all(dev);
 fail_destroy_cmpl_pool:
 	dma_pool_destroy(mbox->cmpl_pool);
 fail_destroy_bd_pool:
@@ -1657,7 +1657,7 @@ static void flexrm_mbox_remove(struct platform_device *pdev)
 
 	debugfs_remove_recursive(mbox->root);
 
-	platform_msi_domain_free_irqs(dev);
+	platform_device_msi_free_irqs_all(dev);
 
 	dma_pool_destroy(mbox->cmpl_pool);
 	dma_pool_destroy(mbox->bd_pool);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 6ae2329052c9..4e6afa89921f 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -300,7 +300,7 @@ struct cached_dev {
 	struct list_head	list;
 	struct bcache_device	disk;
 	struct block_device	*bdev;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 
 	struct cache_sb		sb;
 	struct cache_sb_disk	*sb_disk;
@@ -423,7 +423,7 @@ struct cache {
 
 	struct kobject		kobj;
 	struct block_device	*bdev;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 
 	struct task_struct	*alloc_thread;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index dc3f50f69714..330bcd9ea4a9 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -900,9 +900,23 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
 					 SIZE_MAX / sizeof(atomic_t));
+	struct queue_limits lim = {
+		.max_hw_sectors		= UINT_MAX,
+		.max_sectors		= UINT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.max_segments		= BIO_MAX_VECS,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.io_min			= block_size,
+		.logical_block_size	= block_size,
+		.physical_block_size	= block_size,
+	};
 	uint64_t n;
 	int idx;
 
+	if (cached_bdev) {
+		d->stripe_size = bdev_io_opt(cached_bdev) >> SECTOR_SHIFT;
+		lim.io_opt = umax(block_size, bdev_io_opt(cached_bdev));
+	}
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
 	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
@@ -935,8 +949,21 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto out_ida_remove;
 
-	d->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!d->disk)
+	if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
+		/*
+		 * This should only happen with BCACHE_SB_VERSION_BDEV.
+		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
+		 */
+		pr_info("bcache%i: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
+			idx, lim.logical_block_size,
+			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
+
+		/* This also adjusts physical block size/min io size if needed */
+		lim.logical_block_size = bdev_logical_block_size(cached_bdev);
+	}
+
+	d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(d->disk))
 		goto out_bioset_exit;
 
 	set_capacity(d->disk, sectors);
@@ -949,27 +976,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	d->disk->private_data	= d;
 
 	q = d->disk->queue;
-	q->limits.max_hw_sectors	= UINT_MAX;
-	q->limits.max_sectors		= UINT_MAX;
-	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_VECS;
-	blk_queue_max_discard_sectors(q, UINT_MAX);
-	q->limits.io_min		= block_size;
-	q->limits.logical_block_size	= block_size;
-	q->limits.physical_block_size	= block_size;
-
-	if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) {
-		/*
-		 * This should only happen with BCACHE_SB_VERSION_BDEV.
-		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
-		 */
-		pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
-			d->disk->disk_name, q->limits.logical_block_size,
-			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
-
-		/* This also adjusts physical block size/min io size if needed */
-		blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev));
-	}
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
 
@@ -1369,8 +1375,8 @@ static CLOSURE_CALLBACK(cached_dev_free)
 	if (dc->sb_disk)
 		put_page(virt_to_page(dc->sb_disk));
 
-	if (dc->bdev_handle)
-		bdev_release(dc->bdev_handle);
+	if (dc->bdev_file)
+		fput(dc->bdev_file);
 
 	wake_up(&unregister_wait);
 
@@ -1416,9 +1422,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 		hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
 	}
 
-	dc->disk.stripe_size = q->limits.io_opt >> 9;
-
-	if (dc->disk.stripe_size)
+	if (bdev_io_opt(dc->bdev))
 		dc->partial_stripes_expensive =
 			q->limits.raid_partial_stripes_expensive;
 
@@ -1428,9 +1432,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	blk_queue_io_opt(dc->disk.disk->queue,
-		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
-
 	atomic_set(&dc->io_errors, 0);
 	dc->io_disable = false;
 	dc->error_limit = DEFAULT_CACHED_DEV_ERROR_LIMIT;
@@ -1445,7 +1446,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 /* Cached device - bcache superblock */
 
 static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				 struct bdev_handle *bdev_handle,
+				 struct file *bdev_file,
 				 struct cached_dev *dc)
 {
 	const char *err = "cannot allocate memory";
@@ -1453,8 +1454,8 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	int ret = -ENOMEM;
 
 	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
-	dc->bdev_handle = bdev_handle;
-	dc->bdev = bdev_handle->bdev;
+	dc->bdev_file = bdev_file;
+	dc->bdev = file_bdev(bdev_file);
 	dc->sb_disk = sb_disk;
 
 	if (cached_dev_init(dc, sb->block_size << 9))
@@ -2218,8 +2219,8 @@ void bch_cache_release(struct kobject *kobj)
 	if (ca->sb_disk)
 		put_page(virt_to_page(ca->sb_disk));
 
-	if (ca->bdev_handle)
-		bdev_release(ca->bdev_handle);
+	if (ca->bdev_file)
+		fput(ca->bdev_file);
 
 	kfree(ca);
 	module_put(THIS_MODULE);
@@ -2339,18 +2340,18 @@ err_free:
 }
 
 static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				struct bdev_handle *bdev_handle,
+				struct file *bdev_file,
 				struct cache *ca)
 {
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
-	ca->bdev_handle = bdev_handle;
-	ca->bdev = bdev_handle->bdev;
+	ca->bdev_file = bdev_file;
+	ca->bdev = file_bdev(bdev_file);
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors((bdev_handle->bdev)))
+	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
@@ -2361,20 +2362,20 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 			err = "cache_alloc(): cache device is too small";
 		else
 			err = "cache_alloc(): unknown error";
-		pr_notice("error %pg: %s\n", bdev_handle->bdev, err);
+		pr_notice("error %pg: %s\n", file_bdev(bdev_file), err);
 		/*
 		 * If we failed here, it means ca->kobj is not initialized yet,
 		 * kobject_put() won't be called and there is no chance to
-		 * call bdev_release() to bdev in bch_cache_release(). So
-		 * we explicitly call bdev_release() here.
+		 * call fput() to bdev in bch_cache_release(). So
+		 * we explicitly call fput() on the block device here.
 		 */
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return ret;
 	}
 
-	if (kobject_add(&ca->kobj, bdev_kobj(bdev_handle->bdev), "bcache")) {
+	if (kobject_add(&ca->kobj, bdev_kobj(file_bdev(bdev_file)), "bcache")) {
 		pr_notice("error %pg: error calling kobject_add\n",
-			  bdev_handle->bdev);
+			  file_bdev(bdev_file));
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -2388,7 +2389,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto out;
 	}
 
-	pr_info("registered cache device %pg\n", ca->bdev_handle->bdev);
+	pr_info("registered cache device %pg\n", file_bdev(ca->bdev_file));
 
 out:
 	kobject_put(&ca->kobj);
@@ -2446,7 +2447,7 @@ struct async_reg_args {
 	char *path;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	void *holder;
 };
 
@@ -2457,7 +2458,7 @@ static void register_bdev_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	mutex_lock(&bch_register_lock);
-	if (register_bdev(args->sb, args->sb_disk, args->bdev_handle,
+	if (register_bdev(args->sb, args->sb_disk, args->bdev_file,
 			  args->holder) < 0)
 		fail = true;
 	mutex_unlock(&bch_register_lock);
@@ -2478,7 +2479,7 @@ static void register_cache_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	/* blkdev_put() will be called in bch_cache_release() */
-	if (register_cache(args->sb, args->sb_disk, args->bdev_handle,
+	if (register_cache(args->sb, args->sb_disk, args->bdev_file,
 			   args->holder))
 		fail = true;
 
@@ -2516,7 +2517,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	char *path = NULL;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct bdev_handle *bdev_handle, *bdev_handle2;
+	struct file *bdev_file, *bdev_file2;
 	void *holder = NULL;
 	ssize_t ret;
 	bool async_registration = false;
@@ -2549,15 +2550,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	ret = -EINVAL;
 	err = "failed to open device";
-	bdev_handle = bdev_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(bdev_handle))
+	bdev_file = bdev_file_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
+	if (IS_ERR(bdev_file))
 		goto out_free_sb;
 
 	err = "failed to set blocksize";
-	if (set_blocksize(bdev_handle->bdev, 4096))
+	if (set_blocksize(file_bdev(bdev_file), 4096))
 		goto out_blkdev_put;
 
-	err = read_super(sb, bdev_handle->bdev, &sb_disk);
+	err = read_super(sb, file_bdev(bdev_file), &sb_disk);
 	if (err)
 		goto out_blkdev_put;
 
@@ -2569,13 +2570,13 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
-	bdev_handle2 = bdev_open_by_dev(bdev_handle->bdev->bd_dev,
+	bdev_file2 = bdev_file_open_by_dev(file_bdev(bdev_file)->bd_dev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE, holder, NULL);
-	bdev_release(bdev_handle);
-	bdev_handle = bdev_handle2;
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
-		bdev_handle = NULL;
+	fput(bdev_file);
+	bdev_file = bdev_file2;
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
+		bdev_file = NULL;
 		if (ret == -EBUSY) {
 			dev_t dev;
 
@@ -2610,7 +2611,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->path	= path;
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
-		args->bdev_handle	= bdev_handle;
+		args->bdev_file	= bdev_file;
 		args->holder	= holder;
 		register_device_async(args);
 		/* No wait and returns to user space */
@@ -2619,14 +2620,14 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	if (SB_IS_BDEV(sb)) {
 		mutex_lock(&bch_register_lock);
-		ret = register_bdev(sb, sb_disk, bdev_handle, holder);
+		ret = register_bdev(sb, sb_disk, bdev_file, holder);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
 		if (ret < 0)
 			goto out_free_sb;
 	} else {
 		/* blkdev_put() will be called in bch_cache_release() */
-		ret = register_cache(sb, sb_disk, bdev_handle, holder);
+		ret = register_cache(sb, sb_disk, bdev_file, holder);
 		if (ret)
 			goto out_free_sb;
 	}
@@ -2642,8 +2643,8 @@ out_free_holder:
 out_put_sb_page:
 	put_page(virt_to_page(sb_disk));
 out_blkdev_put:
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out_free_sb:
 	kfree(sb);
 out_free_path:
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 095b9b49aa82..e6757a30dcca 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -22,6 +22,8 @@
 #include "dm-ima.h"
 
 #define DM_RESERVED_MAX_IOS		1024
+#define DM_MAX_TARGETS			1048576
+#define DM_MAX_TARGET_PARAMS		1024
 
 struct dm_io;
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 855b482cbff1..59445763e55a 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -53,15 +53,17 @@
 struct convert_context {
 	struct completion restart;
 	struct bio *bio_in;
-	struct bio *bio_out;
 	struct bvec_iter iter_in;
+	struct bio *bio_out;
 	struct bvec_iter iter_out;
-	u64 cc_sector;
 	atomic_t cc_pending;
+	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
 		struct aead_request *req_aead;
 	} r;
+	bool aead_recheck;
+	bool aead_failed;
 
 };
 
@@ -73,10 +75,8 @@ struct dm_crypt_io {
 	struct bio *base_bio;
 	u8 *integrity_metadata;
 	bool integrity_metadata_from_pool:1;
-	bool in_tasklet:1;
 
 	struct work_struct work;
-	struct tasklet_struct tasklet;
 
 	struct convert_context ctx;
 
@@ -84,6 +84,8 @@ struct dm_crypt_io {
 	blk_status_t error;
 	sector_t sector;
 
+	struct bvec_iter saved_bi_iter;
+
 	struct rb_node rb_node;
 } CRYPTO_MINALIGN_ATTR;
 
@@ -1372,10 +1374,13 @@ static int crypt_convert_block_aead(struct crypt_config *cc,
 	if (r == -EBADMSG) {
 		sector_t s = le64_to_cpu(*sector);
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 	}
 
 	if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
@@ -1759,10 +1764,11 @@ static void crypt_io_init(struct dm_crypt_io *io, struct crypt_config *cc,
 	io->base_bio = bio;
 	io->sector = sector;
 	io->error = 0;
+	io->ctx.aead_recheck = false;
+	io->ctx.aead_failed = false;
 	io->ctx.r.req = NULL;
 	io->integrity_metadata = NULL;
 	io->integrity_metadata_from_pool = false;
-	io->in_tasklet = false;
 	atomic_set(&io->io_pending, 0);
 }
 
@@ -1771,12 +1777,7 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
-static void kcryptd_io_bio_endio(struct work_struct *work)
-{
-	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
-
-	bio_endio(io->base_bio);
-}
+static void kcryptd_queue_read(struct dm_crypt_io *io);
 
 /*
  * One of the bios was finished. Check for completion of
@@ -1791,6 +1792,15 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) &&
+	    cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) {
+		io->ctx.aead_recheck = true;
+		io->ctx.aead_failed = false;
+		io->error = 0;
+		kcryptd_queue_read(io);
+		return;
+	}
+
 	if (io->ctx.r.req)
 		crypt_free_req(cc, io->ctx.r.req, base_bio);
 
@@ -1801,20 +1811,6 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 
 	base_bio->bi_status = error;
 
-	/*
-	 * If we are running this function from our tasklet,
-	 * we can't call bio_endio() here, because it will call
-	 * clone_endio() from dm.c, which in turn will
-	 * free the current struct dm_crypt_io structure with
-	 * our tasklet. In this case we need to delay bio_endio()
-	 * execution to after the tasklet is done and dequeued.
-	 */
-	if (io->in_tasklet) {
-		INIT_WORK(&io->work, kcryptd_io_bio_endio);
-		queue_work(cc->io_queue, &io->work);
-		return;
-	}
-
 	bio_endio(base_bio);
 }
 
@@ -1840,15 +1836,19 @@ static void crypt_endio(struct bio *clone)
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned int rw = bio_data_dir(clone);
-	blk_status_t error;
+	blk_status_t error = clone->bi_status;
+
+	if (io->ctx.aead_recheck && !error) {
+		kcryptd_queue_crypt(io);
+		return;
+	}
 
 	/*
 	 * free the processed pages
 	 */
-	if (rw == WRITE)
+	if (rw == WRITE || io->ctx.aead_recheck)
 		crypt_free_buffer_pages(cc, clone);
 
-	error = clone->bi_status;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -1869,6 +1869,22 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	struct crypt_config *cc = io->cc;
 	struct bio *clone;
 
+	if (io->ctx.aead_recheck) {
+		if (!(gfp & __GFP_DIRECT_RECLAIM))
+			return 1;
+		crypt_inc_pending(io);
+		clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
+		if (unlikely(!clone)) {
+			crypt_dec_pending(io);
+			return 1;
+		}
+		clone->bi_iter.bi_sector = cc->start + io->sector;
+		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
+		io->saved_bi_iter = clone->bi_iter;
+		dm_submit_bio_remap(io->base_bio, clone);
+		return 0;
+	}
+
 	/*
 	 * We need the original biovec array in order to decrypt the whole bio
 	 * data *afterwards* -- thanks to immutable biovecs we don't need to
@@ -2095,6 +2111,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	io->ctx.bio_out = clone;
 	io->ctx.iter_out = clone->bi_iter;
 
+	if (crypt_integrity_aead(cc)) {
+		bio_copy_data(clone, io->base_bio);
+		io->ctx.bio_in = clone;
+		io->ctx.iter_in = clone->bi_iter;
+	}
+
 	sector += bio_sectors(clone);
 
 	crypt_inc_pending(io);
@@ -2131,6 +2153,14 @@ dec:
 
 static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 {
+	if (io->ctx.aead_recheck) {
+		if (!io->error) {
+			io->ctx.bio_in->bi_iter = io->saved_bi_iter;
+			bio_copy_data(io->base_bio, io->ctx.bio_in);
+		}
+		crypt_free_buffer_pages(io->cc, io->ctx.bio_in);
+		bio_put(io->ctx.bio_in);
+	}
 	crypt_dec_pending(io);
 }
 
@@ -2160,11 +2190,17 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 
-	crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
-			   io->sector);
+	if (io->ctx.aead_recheck) {
+		io->ctx.cc_sector = io->sector + cc->iv_offset;
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	} else {
+		crypt_convert_init(cc, &io->ctx, io->base_bio, io->base_bio,
+				   io->sector);
 
-	r = crypt_convert(cc, &io->ctx,
-			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+		r = crypt_convert(cc, &io->ctx,
+				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	}
 	/*
 	 * Crypto API backlogged the request, because its queue was full
 	 * and we're in softirq context, so continue from a workqueue
@@ -2206,10 +2242,13 @@ static void kcryptd_async_done(void *data, int error)
 	if (error == -EBADMSG) {
 		sector_t s = le64_to_cpu(*org_sector_of_dmreq(cc, dmreq));
 
-		DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
-			    ctx->bio_in->bi_bdev, s);
-		dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
-				 ctx->bio_in, s, 0);
+		ctx->aead_failed = true;
+		if (ctx->aead_recheck) {
+			DMERR_LIMIT("%pg: INTEGRITY AEAD ERROR, sector %llu",
+				    ctx->bio_in->bi_bdev, s);
+			dm_audit_log_bio(DM_MSG_PREFIX, "integrity-aead",
+					 ctx->bio_in, s, 0);
+		}
 		io->error = BLK_STS_PROTECTION;
 	} else if (error < 0)
 		io->error = BLK_STS_IOERR;
@@ -2246,11 +2285,6 @@ static void kcryptd_crypt(struct work_struct *work)
 		kcryptd_crypt_write_convert(io);
 }
 
-static void kcryptd_crypt_tasklet(unsigned long work)
-{
-	kcryptd_crypt((struct work_struct *)work);
-}
-
 static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2262,15 +2296,10 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
 		 * it is being executed with irqs disabled.
 		 */
-		if (in_hardirq() || irqs_disabled()) {
-			io->in_tasklet = true;
-			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
-			tasklet_schedule(&io->tasklet);
+		if (!(in_hardirq() || irqs_disabled())) {
+			kcryptd_crypt(&io->work);
 			return;
 		}
-
-		kcryptd_crypt(&io->work);
-		return;
 	}
 
 	INIT_WORK(&io->work, kcryptd_crypt);
@@ -3144,7 +3173,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 			sval = strchr(opt_string + strlen("integrity:"), ':') + 1;
 			if (!strcasecmp(sval, "aead")) {
 				set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags);
-			} else  if (strcasecmp(sval, "none")) {
+			} else if (strcasecmp(sval, "none")) {
 				ti->error = "Unknown integrity profile";
 				return -EINVAL;
 			}
@@ -3673,7 +3702,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 24, 0},
+	.version = {1, 25, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index c5f03aab4552..1fc901df84eb 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -278,6 +278,8 @@ struct dm_integrity_c {
 
 	atomic64_t number_of_mismatches;
 
+	mempool_t recheck_pool;
+
 	struct notifier_block reboot_notifier;
 };
 
@@ -1689,6 +1691,77 @@ failed:
 	get_random_bytes(result, ic->tag_size);
 }
 
+static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checksum)
+{
+	struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
+	struct dm_integrity_c *ic = dio->ic;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	sector_t sector, logical_sector, area, offset;
+	struct page *page;
+	void *buffer;
+
+	get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
+	dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset,
+							     &dio->metadata_offset);
+	sector = get_data_sector(ic, area, offset);
+	logical_sector = dio->range.logical_sector;
+
+	page = mempool_alloc(&ic->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
+		unsigned pos = 0;
+
+		do {
+			char *mem;
+			int r;
+			struct dm_io_request io_req;
+			struct dm_io_region io_loc;
+			io_req.bi_opf = REQ_OP_READ;
+			io_req.mem.type = DM_IO_KMEM;
+			io_req.mem.ptr.addr = buffer;
+			io_req.notify.fn = NULL;
+			io_req.client = ic->io;
+			io_loc.bdev = ic->dev->bdev;
+			io_loc.sector = sector;
+			io_loc.count = ic->sectors_per_block;
+
+			r = dm_io(&io_req, 1, &io_loc, NULL);
+			if (unlikely(r)) {
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			integrity_sector_checksum(ic, logical_sector, buffer, checksum);
+			r = dm_integrity_rw_tag(ic, checksum, &dio->metadata_block,
+						&dio->metadata_offset, ic->tag_size, TAG_CMP);
+			if (r) {
+				if (r > 0) {
+					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
+						    bio->bi_bdev, logical_sector);
+					atomic64_inc(&ic->number_of_mismatches);
+					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
+							 bio, logical_sector, 0);
+					r = -EILSEQ;
+				}
+				dio->bi_status = errno_to_blk_status(r);
+				goto free_ret;
+			}
+
+			mem = bvec_kmap_local(&bv);
+			memcpy(mem + pos, buffer, ic->sectors_per_block << SECTOR_SHIFT);
+			kunmap_local(mem);
+
+			pos += ic->sectors_per_block << SECTOR_SHIFT;
+			sector += ic->sectors_per_block;
+			logical_sector += ic->sectors_per_block;
+		} while (pos < bv.bv_len);
+	}
+free_ret:
+	mempool_free(page, &ic->recheck_pool);
+}
+
 static void integrity_metadata(struct work_struct *w)
 {
 	struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work);
@@ -1776,15 +1849,8 @@ again:
 						checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE);
 			if (unlikely(r)) {
 				if (r > 0) {
-					sector_t s;
-
-					s = sector - ((r + ic->tag_size - 1) / ic->tag_size);
-					DMERR_LIMIT("%pg: Checksum failed at sector 0x%llx",
-						    bio->bi_bdev, s);
-					r = -EILSEQ;
-					atomic64_inc(&ic->number_of_mismatches);
-					dm_audit_log_bio(DM_MSG_PREFIX, "integrity-checksum",
-							 bio, s, 0);
+					integrity_recheck(dio, checksums);
+					goto skip_io;
 				}
 				if (likely(checksums != checksums_onstack))
 					kfree(checksums);
@@ -4261,6 +4327,12 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 		goto bad;
 	}
 
+	r = mempool_init_page_pool(&ic->recheck_pool, 1, 0);
+	if (r) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
 	ic->metadata_wq = alloc_workqueue("dm-integrity-metadata",
 					  WQ_MEM_RECLAIM, METADATA_WORKQUEUE_MAX_ACTIVE);
 	if (!ic->metadata_wq) {
@@ -4609,6 +4681,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 	kvfree(ic->bbs);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);
+	mempool_exit(&ic->recheck_pool);
 	mempool_exit(&ic->journal_io_mempool);
 	if (ic->io)
 		dm_io_client_destroy(ic->io);
@@ -4661,7 +4734,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 10, 0},
+	.version		= {1, 11, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index e65058e0ed06..3b1ad7127cb8 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1941,7 +1941,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern
 			   minimum_data_size - sizeof(param_kernel->version)))
 		return -EFAULT;
 
-	if (param_kernel->data_size < minimum_data_size) {
+	if (unlikely(param_kernel->data_size < minimum_data_size) ||
+	    unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) {
 		DMERR("Invalid data size in the ioctl structure: %u",
 		      param_kernel->data_size);
 		return -EINVAL;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index eb009d6bb03a..17e9af60bbf7 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -213,6 +213,7 @@ struct raid_dev {
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
 #define RT_FLAG_RS_GROW			8
+#define RT_FLAG_RS_FROZEN		9
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -3240,11 +3241,12 @@ size_check:
 	rs->md.ro = 1;
 	rs->md.in_sync = 1;
 
-	/* Keep array frozen until resume. */
-	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
-
 	/* Has to be held on running the array */
 	mddev_suspend_and_lock_nointr(&rs->md);
+
+	/* Keep array frozen until resume. */
+	md_frozen_sync_thread(&rs->md);
+
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3339,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	md_handle_request(mddev, bio);
+	if (unlikely(!md_handle_request(mddev, bio)))
+		return DM_MAPIO_REQUEUE;
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
+	int ret = 0;
 
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (!strcasecmp(argv[0], "frozen"))
-		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) ||
+	    test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags))
+		return -EBUSY;
 
-	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
-		}
-	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
+	if (!strcasecmp(argv[0], "frozen")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_frozen_sync_thread(mddev);
+		mddev_unlock(mddev);
+	} else if (!strcasecmp(argv[0], "idle")) {
+		ret = mddev_lock(mddev);
+		if (ret)
+			return ret;
+
+		md_idle_sync_thread(mddev);
+		mddev_unlock(mddev);
+	}
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;
 	else if (!strcasecmp(argv[0], "resync"))
 		; /* MD_RECOVERY_NEEDED set below */
@@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 }
 
+static void raid_presuspend(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
+
+	/*
+	 * From now on, disallow raid_message() to change sync_thread until
+	 * resume, raid_postsuspend() is too late.
+	 */
+	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+
+	if (!reshape_interrupted(mddev))
+		return;
+
+	/*
+	 * For raid456, if reshape is interrupted, IO across reshape position
+	 * will never make progress, while caller will wait for IO to be done.
+	 * Inform raid456 to handle those IO to prevent deadlock.
+	 */
+	if (mddev->pers && mddev->pers->prepare_suspend)
+		mddev->pers->prepare_suspend(mddev);
+}
+
+static void raid_presuspend_undo(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+}
+
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
 	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
-		/* Writes have to be stopped before suspending to avoid deadlocks. */
-		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
-			md_stop_writes(&rs->md);
-
+		/*
+		 * sync_thread must be stopped during suspend, and writes have
+		 * to be stopped before suspending to avoid deadlocks.
+		 */
+		md_stop_writes(&rs->md);
 		mddev_suspend(&rs->md, false);
 	}
 }
@@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti)
 	}
 
 	/* Check for any resize/reshape on @rs and adjust/initiate */
-	/* Be prepared for mddev_resume() in raid_resume() */
-	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		mddev->resync_min = mddev->recovery_cp;
@@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti)
 		 * Take this opportunity to check whether any failed
 		 * devices are reachable again.
 		 */
+		mddev_lock_nointr(mddev);
 		attempt_restore_of_faulty_devices(rs);
+		mddev_unlock(mddev);
 	}
 
 	if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
@@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti)
 		if (mddev->delta_disks < 0)
 			rs_set_capacity(rs);
 
+		WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+		WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+		clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 		mddev_lock_nointr(mddev);
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
+		md_unfrozen_sync_thread(mddev);
 		mddev_unlock_and_resume(mddev);
 	}
 }
@@ -4074,6 +4123,8 @@ static struct target_type raid_target = {
 	.message = raid_message,
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
+	.presuspend = raid_presuspend,
+	.presuspend_undo = raid_presuspend_undo,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index bdc14ec99814..1e5d988f44da 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -66,6 +66,9 @@ struct dm_stats_last_position {
 	unsigned int last_rw;
 };
 
+#define DM_STAT_MAX_ENTRIES		8388608
+#define DM_STAT_MAX_HISTOGRAM_ENTRIES	134217728
+
 /*
  * A typo on the command line could possibly make the kernel run out of memory
  * and crash. To prevent the crash we account all used memory. We fail if we
@@ -285,6 +288,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (n_entries != (size_t)n_entries || !(size_t)(n_entries + 1))
 		return -EOVERFLOW;
 
+	if (n_entries > DM_STAT_MAX_ENTRIES)
+		return -EOVERFLOW;
+
 	shared_alloc_size = struct_size(s, stat_shared, n_entries);
 	if ((shared_alloc_size - sizeof(struct dm_stat)) / sizeof(struct dm_stat_shared) != n_entries)
 		return -EOVERFLOW;
@@ -297,6 +303,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	if (histogram_alloc_size / (n_histogram_entries + 1) != (size_t)n_entries * sizeof(unsigned long long))
 		return -EOVERFLOW;
 
+	if ((n_histogram_entries + 1) * (size_t)n_entries > DM_STAT_MAX_HISTOGRAM_ENTRIES)
+		return -EOVERFLOW;
+
 	if (!check_shared_memory(shared_alloc_size + histogram_alloc_size +
 				 num_possible_cpus() * (percpu_alloc_size + histogram_alloc_size)))
 		return -ENOMEM;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 260b5b8f2b0d..41f1d731ae5a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -129,7 +129,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md)
 {
-	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
+	struct dm_table *t;
+
+	if (num_targets > DM_MAX_TARGETS)
+		return -EOVERFLOW;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
 
 	if (!t)
 		return -ENOMEM;
@@ -144,7 +149,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode,
 
 	if (!num_targets) {
 		kfree(t);
-		return -ENOMEM;
+		return -EOVERFLOW;
 	}
 
 	if (alloc_targets(t, num_targets)) {
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 14e58ae70521..1b591bfa90d5 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -482,6 +482,63 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
+static int verity_recheck_copy(struct dm_verity *v, struct dm_verity_io *io,
+			       u8 *data, size_t len)
+{
+	memcpy(data, io->recheck_buffer, len);
+	io->recheck_buffer += len;
+
+	return 0;
+}
+
+static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io,
+				   struct bvec_iter start, sector_t cur_block)
+{
+	struct page *page;
+	void *buffer;
+	int r;
+	struct dm_io_request io_req;
+	struct dm_io_region io_loc;
+
+	page = mempool_alloc(&v->recheck_pool, GFP_NOIO);
+	buffer = page_to_virt(page);
+
+	io_req.bi_opf = REQ_OP_READ;
+	io_req.mem.type = DM_IO_KMEM;
+	io_req.mem.ptr.addr = buffer;
+	io_req.notify.fn = NULL;
+	io_req.client = v->io;
+	io_loc.bdev = v->data_dev->bdev;
+	io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT);
+	io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT);
+	r = dm_io(&io_req, 1, &io_loc, NULL);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = verity_hash(v, verity_io_hash_req(v, io), buffer,
+			1 << v->data_dev_block_bits,
+			verity_io_real_digest(v, io), true);
+	if (unlikely(r))
+		goto free_ret;
+
+	if (memcmp(verity_io_real_digest(v, io),
+		   verity_io_want_digest(v, io), v->digest_size)) {
+		r = -EIO;
+		goto free_ret;
+	}
+
+	io->recheck_buffer = buffer;
+	r = verity_for_bv_block(v, io, &start, verity_recheck_copy);
+	if (unlikely(r))
+		goto free_ret;
+
+	r = 0;
+free_ret:
+	mempool_free(page, &v->recheck_pool);
+
+	return r;
+}
+
 static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 			  u8 *data, size_t len)
 {
@@ -508,9 +565,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 {
 	bool is_zero;
 	struct dm_verity *v = io->v;
-#if defined(CONFIG_DM_VERITY_FEC)
 	struct bvec_iter start;
-#endif
 	struct bvec_iter iter_copy;
 	struct bvec_iter *iter;
 	struct crypto_wait wait;
@@ -561,10 +616,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 		if (unlikely(r < 0))
 			return r;
 
-#if defined(CONFIG_DM_VERITY_FEC)
-		if (verity_fec_is_enabled(v))
-			start = *iter;
-#endif
+		start = *iter;
 		r = verity_for_io_block(v, io, iter, &wait);
 		if (unlikely(r < 0))
 			return r;
@@ -586,6 +638,10 @@ static int verity_verify_io(struct dm_verity_io *io)
 			 * tasklet since it may sleep, so fallback to work-queue.
 			 */
 			return -EAGAIN;
+		} else if (verity_recheck(v, io, start, cur_block) == 0) {
+			if (v->validated_blocks)
+				set_bit(cur_block, v->validated_blocks);
+			continue;
 #if defined(CONFIG_DM_VERITY_FEC)
 		} else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
 					     cur_block, NULL, &start) == 0) {
@@ -645,23 +701,6 @@ static void verity_work(struct work_struct *w)
 	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
 }
 
-static void verity_tasklet(unsigned long data)
-{
-	struct dm_verity_io *io = (struct dm_verity_io *)data;
-	int err;
-
-	io->in_tasklet = true;
-	err = verity_verify_io(io);
-	if (err == -EAGAIN || err == -ENOMEM) {
-		/* fallback to retrying with work-queue */
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-		return;
-	}
-
-	verity_finish_io(io, errno_to_blk_status(err));
-}
-
 static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
@@ -674,13 +713,8 @@ static void verity_end_io(struct bio *bio)
 		return;
 	}
 
-	if (static_branch_unlikely(&use_tasklet_enabled) && io->v->use_tasklet) {
-		tasklet_init(&io->tasklet, verity_tasklet, (unsigned long)io);
-		tasklet_schedule(&io->tasklet);
-	} else {
-		INIT_WORK(&io->work, verity_work);
-		queue_work(io->v->verify_wq, &io->work);
-	}
+	INIT_WORK(&io->work, verity_work);
+	queue_work(io->v->verify_wq, &io->work);
 }
 
 /*
@@ -963,6 +997,10 @@ static void verity_dtr(struct dm_target *ti)
 	if (v->verify_wq)
 		destroy_workqueue(v->verify_wq);
 
+	mempool_exit(&v->recheck_pool);
+	if (v->io)
+		dm_io_client_destroy(v->io);
+
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
@@ -1401,6 +1439,20 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 	v->hash_blocks = hash_position;
 
+	r = mempool_init_page_pool(&v->recheck_pool, 1, 0);
+	if (unlikely(r)) {
+		ti->error = "Cannot allocate mempool";
+		goto bad;
+	}
+
+	v->io = dm_io_client_create();
+	if (IS_ERR(v->io)) {
+		r = PTR_ERR(v->io);
+		v->io = NULL;
+		ti->error = "Cannot allocate dm io";
+		goto bad;
+	}
+
 	v->bufio = dm_bufio_client_create(v->hash_dev->bdev,
 		1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux),
 		dm_bufio_alloc_callback, NULL,
@@ -1508,7 +1560,7 @@ int dm_verity_get_root_digest(struct dm_target *ti, u8 **root_digest, unsigned i
 static struct target_type verity_target = {
 	.name		= "verity",
 	.features	= DM_TARGET_IMMUTABLE,
-	.version	= {1, 9, 0},
+	.version	= {1, 10, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index f9d522c870e6..db93a91169d5 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -11,6 +11,7 @@
 #ifndef DM_VERITY_H
 #define DM_VERITY_H
 
+#include <linux/dm-io.h>
 #include <linux/dm-bufio.h>
 #include <linux/device-mapper.h>
 #include <linux/interrupt.h>
@@ -68,6 +69,9 @@ struct dm_verity {
 	unsigned long *validated_blocks; /* bitset blocks validated */
 
 	char *signature_key_desc; /* signature keyring reference */
+
+	struct dm_io_client *io;
+	mempool_t recheck_pool;
 };
 
 struct dm_verity_io {
@@ -76,14 +80,15 @@ struct dm_verity_io {
 	/* original value of bio->bi_end_io */
 	bio_end_io_t *orig_bi_end_io;
 
+	struct bvec_iter iter;
+
 	sector_t block;
 	unsigned int n_blocks;
 	bool in_tasklet;
 
-	struct bvec_iter iter;
-
 	struct work_struct work;
-	struct tasklet_struct tasklet;
+
+	char *recheck_buffer;
 
 	/*
 	 * Three variably-size fields follow this struct:
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 074cb785eafc..b463c28c39ad 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -299,7 +299,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		long i;
 
 		wc->memory_map = NULL;
-		pages = kvmalloc_array(p, sizeof(struct page *), GFP_KERNEL);
+		pages = vmalloc_array(p, sizeof(struct page *));
 		if (!pages) {
 			r = -ENOMEM;
 			goto err2;
@@ -330,7 +330,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 			r = -ENOMEM;
 			goto err3;
 		}
-		kvfree(pages);
+		vfree(pages);
 		wc->memory_vmapped = true;
 	}
 
@@ -341,7 +341,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	return 0;
 err3:
-	kvfree(pages);
+	vfree(pages);
 err2:
 	dax_read_unlock(id);
 err1:
@@ -962,7 +962,7 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 
 	if (wc->entries)
 		return 0;
-	wc->entries = vmalloc(array_size(sizeof(struct wc_entry), wc->n_blocks));
+	wc->entries = vmalloc_array(wc->n_blocks, sizeof(struct wc_entry));
 	if (!wc->entries)
 		return -ENOMEM;
 	for (b = 0; b < wc->n_blocks; b++) {
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index fdfe30f7b697..8156881a31de 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1655,10 +1655,13 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zone->dev;
+		unsigned int noio_flag;
 
+		noio_flag = memalloc_noio_save();
 		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
 				       dmz_start_sect(zmd, zone),
-				       zmd->zone_nr_sectors, GFP_NOIO);
+				       zmd->zone_nr_sectors);
+		memalloc_noio_restore(noio_flag);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    zone->id, ret);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8dcabf84d866..447e132d09b5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -726,7 +726,8 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		dev_t dev, blk_mode_t mode)
 {
 	struct table_device *td;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
+	struct block_device *bdev;
 	u64 part_off;
 	int r;
 
@@ -735,34 +736,36 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&td->count, 1);
 
-	bdev_handle = bdev_open_by_dev(dev, mode, _dm_claim_ptr, NULL);
-	if (IS_ERR(bdev_handle)) {
-		r = PTR_ERR(bdev_handle);
+	bdev_file = bdev_file_open_by_dev(dev, mode, _dm_claim_ptr, NULL);
+	if (IS_ERR(bdev_file)) {
+		r = PTR_ERR(bdev_file);
 		goto out_free_td;
 	}
 
+	bdev = file_bdev(bdev_file);
+
 	/*
 	 * We can be called before the dm disk is added.  In that case we can't
 	 * register the holder relation here.  It will be done once add_disk was
 	 * called.
 	 */
 	if (md->disk->slave_dir) {
-		r = bd_link_disk_holder(bdev_handle->bdev, md->disk);
+		r = bd_link_disk_holder(bdev, md->disk);
 		if (r)
 			goto out_blkdev_put;
 	}
 
 	td->dm_dev.mode = mode;
-	td->dm_dev.bdev = bdev_handle->bdev;
-	td->dm_dev.bdev_handle = bdev_handle;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, &part_off,
+	td->dm_dev.bdev = bdev;
+	td->dm_dev.bdev_file = bdev_file;
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off,
 						NULL, NULL);
 	format_dev_t(td->dm_dev.name, dev);
 	list_add(&td->list, &md->table_devices);
 	return td;
 
 out_blkdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 out_free_td:
 	kfree(td);
 	return ERR_PTR(r);
@@ -775,7 +778,7 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
 {
 	if (md->disk->slave_dir)
 		bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
-	bdev_release(td->dm_dev.bdev_handle);
+	fput(td->dm_dev.bdev_file);
 	put_dax(td->dm_dev.dax_dev);
 	list_del(&td->list);
 	kfree(td);
@@ -2098,8 +2101,8 @@ static struct mapped_device *alloc_dev(int minor)
 	 * established. If request-based table is loaded: blk-mq will
 	 * override accordingly.
 	 */
-	md->disk = blk_alloc_disk(md->numa_node_id);
-	if (!md->disk)
+	md->disk = blk_alloc_disk(NULL, md->numa_node_id);
+	if (IS_ERR(md->disk))
 		goto bad;
 	md->queue = md->disk->queue;
 
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 9672f75c3050..059afc24c08b 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -234,7 +234,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	sector_t doff;
 
 	bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev;
-	if (pg_index == store->file_pages - 1) {
+	/* we compare length (page numbers), not page offset. */
+	if ((pg_index - store->sb_index) == store->file_pages - 1) {
 		unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1);
 
 		if (last_page_size == 0)
@@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index,
 	struct page *page = store->filemap[pg_index];
 
 	if (mddev_is_clustered(bitmap->mddev)) {
-		pg_index += bitmap->cluster_slot *
-			DIV_ROUND_UP(store->bytes, PAGE_SIZE);
+		/* go to node bitmap area starting point */
+		pg_index += store->sb_index;
 	}
 
 	if (store->file)
@@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block)
 	unsigned long index = file_page_index(store, chunk);
 	unsigned long node_offset = 0;
 
+	index += store->sb_index;
 	if (mddev_is_clustered(bitmap->mddev))
 		node_offset = bitmap->cluster_slot * store->file_pages;
 
@@ -1043,9 +1046,8 @@ void md_bitmap_unplug(struct bitmap *bitmap)
 		if (dirty || need_write) {
 			if (!writing) {
 				md_bitmap_wait_writes(bitmap);
-				if (bitmap->mddev->queue)
-					blk_add_trace_msg(bitmap->mddev->queue,
-							  "md bitmap_unplug");
+				mddev_add_trace_msg(bitmap->mddev,
+					"md bitmap_unplug");
 			}
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			filemap_write_page(bitmap, i, false);
@@ -1316,9 +1318,7 @@ void md_bitmap_daemon_work(struct mddev *mddev)
 	}
 	bitmap->allclean = 1;
 
-	if (bitmap->mddev->queue)
-		blk_add_trace_msg(bitmap->mddev->queue,
-				  "md bitmap_daemon_work");
+	mddev_add_trace_msg(bitmap->mddev, "md bitmap_daemon_work");
 
 	/* Any file-page which is PENDING now needs to be written.
 	 * So set NEEDWRITE now, then after we make any last-minute changes
diff --git a/drivers/md/md-linear.h b/drivers/md/md-linear.h
deleted file mode 100644
index 5587eeedb882..000000000000
--- a/drivers/md/md-linear.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINEAR_H
-#define _LINEAR_H
-
-struct dev_info {
-	struct md_rdev	*rdev;
-	sector_t	end_sector;
-};
-
-struct linear_conf
-{
-	struct rcu_head		rcu;
-	sector_t		array_sectors;
-	int			raid_disks; /* a copy of mddev->raid_disks */
-	struct dev_info		disks[] __counted_by(raid_disks);
-};
-#endif
diff --git a/drivers/md/md-multipath.h b/drivers/md/md-multipath.h
deleted file mode 100644
index b3099e5fc4d7..000000000000
--- a/drivers/md/md-multipath.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MULTIPATH_H
-#define _MULTIPATH_H
-
-struct multipath_info {
-	struct md_rdev	*rdev;
-};
-
-struct mpconf {
-	struct mddev			*mddev;
-	struct multipath_info	*multipaths;
-	int			raid_disks;
-	spinlock_t		device_lock;
-	struct list_head	retry_list;
-
-	mempool_t		pool;
-};
-
-/*
- * this is our 'private' 'collective' MULTIPATH buffer head.
- * it contains information about what kind of IO operations were started
- * for this MULTIPATH operation, and about their status:
- */
-
-struct multipath_bh {
-	struct mddev			*mddev;
-	struct bio		*master_bio;
-	struct bio		bio;
-	int			path;
-	struct list_head	retry_list;
-};
-#endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2266358d8074..e575e74aabf5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -65,7 +65,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/part_stat.h>
 
-#include <trace/events/block.h>
 #include "md.h"
 #include "md-bitmap.h"
 #include "md-cluster.h"
@@ -99,18 +98,6 @@ static void mddev_detach(struct mddev *mddev);
 static void export_rdev(struct md_rdev *rdev, struct mddev *mddev);
 static void md_wakeup_thread_directly(struct md_thread __rcu *thread);
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -378,7 +365,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 	return true;
 }
 
-void md_handle_request(struct mddev *mddev, struct bio *bio)
+bool md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
 	if (is_suspended(mddev, bio)) {
@@ -386,7 +373,7 @@ check_suspended:
 		/* Bail out if REQ_NOWAIT is set for the bio */
 		if (bio->bi_opf & REQ_NOWAIT) {
 			bio_wouldblock_error(bio);
-			return;
+			return true;
 		}
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
@@ -402,10 +389,13 @@ check_suspended:
 
 	if (!mddev->pers->make_request(mddev, bio)) {
 		percpu_ref_put(&mddev->active_io);
+		if (!mddev->gendisk && mddev->pers->prepare_suspend)
+			return false;
 		goto check_suspended;
 	}
 
 	percpu_ref_put(&mddev->active_io);
+	return true;
 }
 EXPORT_SYMBOL(md_handle_request);
 
@@ -529,6 +519,24 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
+/* sync bdev before setting device to readonly or stopping raid*/
+static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_num)
+{
+	mutex_lock(&mddev->open_mutex);
+	if (mddev->pers && atomic_read(&mddev->openers) > opener_num) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -EBUSY;
+	}
+	mutex_unlock(&mddev->open_mutex);
+
+	sync_blockdev(mddev->gendisk->part0);
+	return 0;
+}
+
 /*
  * Generic flush handling for md
  */
@@ -579,8 +587,12 @@ static void submit_flushes(struct work_struct *ws)
 			rcu_read_lock();
 		}
 	rcu_read_unlock();
-	if (atomic_dec_and_test(&mddev->flush_pending))
+	if (atomic_dec_and_test(&mddev->flush_pending)) {
+		/* The pair is percpu_ref_get() from md_flush_request() */
+		percpu_ref_put(&mddev->active_io);
+
 		queue_work(md_wq, &mddev->flush_work);
+	}
 }
 
 static void md_submit_flush_data(struct work_struct *ws)
@@ -2402,7 +2414,7 @@ int md_integrity_register(struct mddev *mddev)
 
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (!mddev->gendisk || blk_get_integrity(mddev->gendisk))
+	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
 		return 0; /* shouldn't register, or already is */
 	rdev_for_each(rdev, mddev) {
 		/* skip spares and non-functional disks */
@@ -2455,7 +2467,7 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	struct blk_integrity *bi_mddev;
 
-	if (!mddev->gendisk)
+	if (mddev_is_dm(mddev))
 		return 0;
 
 	bi_mddev = blk_get_integrity(mddev->gendisk);
@@ -2562,6 +2574,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
  fail:
 	pr_warn("md: failed to register dev-%s for %s\n",
 		b, mdname(mddev));
+	mddev_destroy_serial_pool(mddev, rdev);
 	return err;
 }
 
@@ -2578,7 +2591,7 @@ static void export_rdev(struct md_rdev *rdev, struct mddev *mddev)
 	if (test_bit(AutoDetected, &rdev->flags))
 		md_autodetect_dev(rdev->bdev->bd_dev);
 #endif
-	bdev_release(rdev->bdev_handle);
+	fput(rdev->bdev_file);
 	rdev->bdev = NULL;
 	kobject_put(&rdev->kobj);
 }
@@ -2591,7 +2604,7 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev)
 	list_del_rcu(&rdev->same_set);
 	pr_debug("md: unbind<%pg>\n", rdev->bdev);
 	mddev_destroy_serial_pool(rdev->mddev, rdev);
-	rdev->mddev = NULL;
+	WRITE_ONCE(rdev->mddev, NULL);
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
 	sysfs_put(rdev->sysfs_unack_badblocks);
@@ -2847,8 +2860,7 @@ repeat:
 	pr_debug("md: updating %s RAID superblock on device (in sync %d)\n",
 		 mdname(mddev), mddev->in_sync);
 
-	if (mddev->queue)
-		blk_add_trace_msg(mddev->queue, "md md_update_sb");
+	mddev_add_trace_msg(mddev, "md md_update_sb");
 rewrite:
 	md_bitmap_update_sb(mddev->bitmap);
 	rdev_for_each(rdev, mddev) {
@@ -2929,7 +2941,6 @@ static int add_bound_rdev(struct md_rdev *rdev)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_new_event();
-	md_wakeup_thread(mddev->thread);
 	return 0;
 }
 
@@ -3044,10 +3055,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 			if (err == 0) {
 				md_kick_rdev_from_array(rdev);
-				if (mddev->pers) {
+				if (mddev->pers)
 					set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-					md_wakeup_thread(mddev->thread);
-				}
 				md_new_event();
 			}
 		}
@@ -3077,7 +3086,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 
 		err = 0;
 	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
@@ -3115,7 +3123,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		    !test_bit(Replacement, &rdev->flags))
 			set_bit(WantReplacement, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 		err = 0;
 	} else if (cmd_match(buf, "-want_replacement")) {
 		/* Clearing 'want_replacement' is always allowed.
@@ -3245,7 +3252,6 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		if (rdev->raid_disk >= 0)
 			return -EBUSY;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
-		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
 		/* Activating a spare .. or possibly reactivating
 		 * if we ever get bitmaps working here.
@@ -3339,8 +3345,7 @@ static ssize_t new_offset_store(struct md_rdev *rdev,
 	if (kstrtoull(buf, 10, &new_offset) < 0)
 		return -EINVAL;
 
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING,&mddev->recovery))
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (new_offset == rdev->data_offset)
 		/* reset is always permitted */
@@ -3671,7 +3676,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct kernfs_node *kn = NULL;
 	bool suspend = false;
 	ssize_t rv;
-	struct mddev *mddev = rdev->mddev;
+	struct mddev *mddev = READ_ONCE(rdev->mddev);
 
 	if (!entry->store)
 		return -EIO;
@@ -3773,16 +3778,16 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	if (err)
 		goto out_clear_rdev;
 
-	rdev->bdev_handle = bdev_open_by_dev(newdev,
+	rdev->bdev_file = bdev_file_open_by_dev(newdev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE,
 			super_format == -2 ? &claim_rdev : rdev, NULL);
-	if (IS_ERR(rdev->bdev_handle)) {
+	if (IS_ERR(rdev->bdev_file)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));
-		err = PTR_ERR(rdev->bdev_handle);
+		err = PTR_ERR(rdev->bdev_file);
 		goto out_clear_rdev;
 	}
-	rdev->bdev = rdev->bdev_handle->bdev;
+	rdev->bdev = file_bdev(rdev->bdev_file);
 
 	kobject_init(&rdev->kobj, &rdev_ktype);
 
@@ -3813,7 +3818,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 	return rdev;
 
 out_blkdev_put:
-	bdev_release(rdev->bdev_handle);
+	fput(rdev->bdev_file);
 out_clear_rdev:
 	md_rdev_clear(rdev);
 out_free_rdev:
@@ -4013,8 +4018,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	 */
 
 	rv = -EBUSY;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector ||
 	    mddev->sysfs_active)
 		goto out_unlock;
@@ -4164,7 +4168,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->in_sync = 1;
 		del_timer_sync(&mddev->safemode_timer);
 	}
-	blk_set_stacking_limits(&mddev->queue->limits);
 	pers->run(mddev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
@@ -4471,8 +4474,8 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
+static int do_md_stop(struct mddev *mddev, int ro);
+static int md_set_readonly(struct mddev *mddev);
 static int restart_array(struct mddev *mddev);
 
 static ssize_t
@@ -4489,6 +4492,17 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case broken:		/* cannot be set */
 	case bad_word:
 		return -EINVAL;
+	case clear:
+	case readonly:
+	case inactive:
+	case read_auto:
+		if (!mddev->pers || !md_is_rdwr(mddev))
+			break;
+		/* write sysfs will not open mddev and opener should be 0 */
+		err = mddev_set_closing_and_sync_blockdev(mddev, 0);
+		if (err)
+			return err;
+		break;
 	default:
 		break;
 	}
@@ -4522,14 +4536,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case inactive:
 		/* stop an active array, return 0 otherwise */
 		if (mddev->pers)
-			err = do_md_stop(mddev, 2, NULL);
+			err = do_md_stop(mddev, 2);
 		break;
 	case clear:
-		err = do_md_stop(mddev, 0, NULL);
+		err = do_md_stop(mddev, 0);
 		break;
 	case readonly:
 		if (mddev->pers)
-			err = md_set_readonly(mddev, NULL);
+			err = md_set_readonly(mddev);
 		else {
 			mddev->ro = MD_RDONLY;
 			set_disk_ro(mddev->gendisk, 1);
@@ -4539,7 +4553,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 	case read_auto:
 		if (mddev->pers) {
 			if (md_is_rdwr(mddev))
-				err = md_set_readonly(mddev, NULL);
+				err = md_set_readonly(mddev);
 			else if (mddev->ro == MD_RDONLY)
 				err = restart_array(mddev);
 			if (err == 0) {
@@ -4588,6 +4602,11 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 	mddev_unlock(mddev);
+
+	if (st == readonly || st == read_auto || st == inactive ||
+	    (err && st == clear))
+		clear_bit(MD_CLOSING, &mddev->flags);
+
 	return err ?: len;
 }
 static struct md_sysfs_entry md_array_state =
@@ -4915,6 +4934,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq)
 		mddev_lock_nointr(mddev);
 }
 
+void md_idle_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, true);
+}
+EXPORT_SYMBOL_GPL(md_idle_sync_thread);
+
+void md_frozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
+}
+EXPORT_SYMBOL_GPL(md_frozen_sync_thread);
+
+void md_unfrozen_sync_thread(struct mddev *mddev)
+{
+	lockdep_assert_held(&mddev->reconfig_mutex);
+
+	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+}
+EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread);
+
 static void idle_sync_thread(struct mddev *mddev)
 {
 	mutex_lock(&mddev->sync_mutex);
@@ -5706,6 +5754,51 @@ static const struct kobj_type md_ktype = {
 
 int mdp_major = 0;
 
+/* stack the limit for all rdevs into lim */
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim)
+{
+	struct md_rdev *rdev;
+
+	rdev_for_each(rdev, mddev) {
+		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
+					mddev->gendisk->disk_name);
+	}
+}
+EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
+
+/* apply the extra stacking limits from a new rdev into mddev */
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return 0;
+
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
+				mddev->gendisk->disk_name);
+	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
+}
+EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
+
+/* update the optimal I/O size after a reshape */
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes)
+{
+	struct queue_limits lim;
+
+	if (mddev_is_dm(mddev))
+		return;
+
+	/* don't bother updating io_opt if we can't suspend the array */
+	if (mddev_suspend(mddev, false) < 0)
+		return;
+	lim = queue_limits_start_update(mddev->gendisk->queue);
+	lim.io_opt = lim.io_min * nr_stripes;
+	queue_limits_commit_update(mddev->gendisk->queue, &lim);
+	mddev_resume(mddev);
+}
+EXPORT_SYMBOL_GPL(mddev_update_io_opt);
+
 static void mddev_delayed_delete(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
@@ -5770,10 +5863,11 @@ struct mddev *md_alloc(dev_t dev, char *name)
 		 */
 		mddev->hold_active = UNTIL_STOP;
 
-	error = -ENOMEM;
-	disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!disk)
+	disk = blk_alloc_disk(NULL, NUMA_NO_NODE);
+	if (IS_ERR(disk)) {
+		error = PTR_ERR(disk);
 		goto out_free_mddev;
+	}
 
 	disk->major = MAJOR(mddev->unit);
 	disk->first_minor = unit << shift;
@@ -5787,9 +5881,7 @@ struct mddev *md_alloc(dev_t dev, char *name)
 	disk->fops = &md_fops;
 	disk->private_data = mddev;
 
-	mddev->queue = disk->queue;
-	blk_set_stacking_limits(&mddev->queue->limits);
-	blk_queue_write_cache(mddev->queue, true, true);
+	blk_queue_write_cache(disk->queue, true, true);
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
@@ -5931,7 +6023,7 @@ int md_run(struct mddev *mddev)
 		invalidate_bdev(rdev->bdev);
 		if (mddev->ro != MD_RDONLY && rdev_read_only(rdev)) {
 			mddev->ro = MD_RDONLY;
-			if (mddev->gendisk)
+			if (!mddev_is_dm(mddev))
 				set_disk_ro(mddev->gendisk, 1);
 		}
 
@@ -6034,7 +6126,10 @@ int md_run(struct mddev *mddev)
 			pr_warn("True protection against single-disk failure might be compromised.\n");
 	}
 
-	mddev->recovery = 0;
+	/* dm-raid expect sync_thread to be frozen until resume */
+	if (mddev->gendisk)
+		mddev->recovery = 0;
+
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
@@ -6090,7 +6185,8 @@ int md_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
+	if (!mddev_is_dm(mddev)) {
+		struct request_queue *q = mddev->gendisk->queue;
 		bool nonrot = true;
 
 		rdev_for_each(rdev, mddev) {
@@ -6102,14 +6198,14 @@ int md_run(struct mddev *mddev)
 		if (mddev->degraded)
 			nonrot = false;
 		if (nonrot)
-			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 		else
-			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
+			blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 
 		/* Set the NOWAIT flags if all underlying devices support it */
 		if (nowait)
-			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue);
+			blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6188,7 +6284,6 @@ int do_md_run(struct mddev *mddev)
 	/* run start up tasks that require md_thread */
 	md_start(mddev);
 
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
@@ -6209,7 +6304,6 @@ int md_start(struct mddev *mddev)
 
 	if (mddev->pers->start) {
 		set_bit(MD_RECOVERY_WAIT, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		ret = mddev->pers->start(mddev);
 		clear_bit(MD_RECOVERY_WAIT, &mddev->recovery);
 		md_wakeup_thread(mddev->sync_thread);
@@ -6254,7 +6348,6 @@ static int restart_array(struct mddev *mddev)
 	pr_debug("md: %s switched to read-write mode.\n", mdname(mddev));
 	/* Kick recovery or resync if necessary */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;
@@ -6274,7 +6367,15 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	mddev->flags = 0;
+	/*
+	 * Don't clear MD_CLOSING, or mddev can be opened again.
+	 * 'hold_active != 0' means mddev is still in the creation
+	 * process and will be used later.
+	 */
+	if (mddev->hold_active)
+		mddev->flags = 0;
+	else
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6311,7 +6412,6 @@ static void md_clean(struct mddev *mddev)
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	stop_sync_thread(mddev, true, false);
 	del_timer_sync(&mddev->safemode_timer);
 
 	if (mddev->pers && mddev->pers->quiesce) {
@@ -6336,6 +6436,8 @@ static void __md_stop_writes(struct mddev *mddev)
 void md_stop_writes(struct mddev *mddev)
 {
 	mddev_lock_nointr(mddev);
+	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	stop_sync_thread(mddev, true, false);
 	__md_stop_writes(mddev);
 	mddev_unlock(mddev);
 }
@@ -6349,8 +6451,10 @@ static void mddev_detach(struct mddev *mddev)
 		mddev->pers->quiesce(mddev, 0);
 	}
 	md_unregister_thread(mddev, &mddev->thread);
-	if (mddev->queue)
-		blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+
+	/* the unplug fn references 'conf' */
+	if (!mddev_is_dm(mddev))
+		blk_sync_queue(mddev->gendisk->queue);
 }
 
 static void __md_stop(struct mddev *mddev)
@@ -6387,7 +6491,8 @@ void md_stop(struct mddev *mddev)
 
 EXPORT_SYMBOL_GPL(md_stop);
 
-static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
+/* ensure 'mddev->pers' exist before calling md_set_readonly() */
+static int md_set_readonly(struct mddev *mddev)
 {
 	int err = 0;
 	int did_freeze = 0;
@@ -6398,7 +6503,6 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, false, false);
@@ -6406,36 +6510,29 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 	mddev_lock_nointr(mddev);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
 		err = -EBUSY;
 		goto out;
 	}
 
-	if (mddev->pers) {
-		__md_stop_writes(mddev);
-
-		if (mddev->ro == MD_RDONLY) {
-			err  = -ENXIO;
-			goto out;
-		}
+	__md_stop_writes(mddev);
 
-		mddev->ro = MD_RDONLY;
-		set_disk_ro(mddev->gendisk, 1);
+	if (mddev->ro == MD_RDONLY) {
+		err  = -ENXIO;
+		goto out;
 	}
 
+	mddev->ro = MD_RDONLY;
+	set_disk_ro(mddev->gendisk, 1);
+
 out:
-	if ((mddev->pers && !err) || did_freeze) {
+	if (!err || did_freeze) {
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	}
 
-	mutex_unlock(&mddev->open_mutex);
 	return err;
 }
 
@@ -6443,8 +6540,7 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev *mddev, int mode,
-		      struct block_device *bdev)
+static int do_md_stop(struct mddev *mddev, int mode)
 {
 	struct gendisk *disk = mddev->gendisk;
 	struct md_rdev *rdev;
@@ -6453,22 +6549,16 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
 		did_freeze = 1;
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
 	}
 
 	stop_sync_thread(mddev, true, false);
 
-	mutex_lock(&mddev->open_mutex);
-	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
-	    mddev->sysfs_active ||
-	    mddev->sync_thread ||
+	if (mddev->sysfs_active ||
 	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		pr_warn("md: %s still in use.\n",mdname(mddev));
-		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			md_wakeup_thread(mddev->thread);
 		}
 		return -EBUSY;
 	}
@@ -6487,13 +6577,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
 				sysfs_unlink_rdev(mddev, rdev);
 
 		set_capacity_and_notify(disk, 0);
-		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
 
 		if (!md_is_rdwr(mddev))
 			mddev->ro = MD_RDWR;
-	} else
-		mutex_unlock(&mddev->open_mutex);
+	}
 	/*
 	 * Free resources if final stop
 	 */
@@ -6539,7 +6627,7 @@ static void autorun_array(struct mddev *mddev)
 	err = do_md_run(mddev);
 	if (err) {
 		pr_warn("md: do_md_run() returned %d\n", err);
-		do_md_stop(mddev, 0, NULL);
+		do_md_stop(mddev, 0);
 	}
 }
 
@@ -7009,9 +7097,7 @@ kick_rdev:
 
 	md_kick_rdev_from_array(rdev);
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	if (mddev->thread)
-		md_wakeup_thread(mddev->thread);
-	else
+	if (!mddev->thread)
 		md_update_sb(mddev, 1);
 	md_new_event();
 
@@ -7086,14 +7172,13 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	if (!bdev_nowait(rdev->bdev)) {
 		pr_info("%s: Disabling nowait because %pg does not support nowait\n",
 			mdname(mddev), rdev->bdev);
-		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue);
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->gendisk->queue);
 	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
 	 */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
 	md_new_event();
 	return 0;
 
@@ -7307,8 +7392,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	 * of each device.  If num_sectors is zero, we find the largest size
 	 * that fits.
 	 */
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    mddev->sync_thread)
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 	if (!md_is_rdwr(mddev))
 		return -EROFS;
@@ -7325,10 +7409,9 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	if (!rv) {
 		if (mddev_is_clustered(mddev))
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
-		else if (mddev->queue) {
+		else if (!mddev_is_dm(mddev))
 			set_capacity_and_notify(mddev->gendisk,
 						mddev->array_sectors);
-		}
 	}
 	return rv;
 }
@@ -7345,8 +7428,7 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 	if (raid_disks <= 0 ||
 	    (mddev->max_disks && raid_disks >= mddev->max_disks))
 		return -EINVAL;
-	if (mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) ||
 	    mddev->reshape_position != MaxSector)
 		return -EBUSY;
@@ -7542,16 +7624,17 @@ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static inline bool md_ioctl_valid(unsigned int cmd)
+static inline int md_ioctl_valid(unsigned int cmd)
 {
 	switch (cmd) {
-	case ADD_NEW_DISK:
 	case GET_ARRAY_INFO:
-	case GET_BITMAP_FILE:
 	case GET_DISK_INFO:
+	case RAID_VERSION:
+		return 0;
+	case ADD_NEW_DISK:
+	case GET_BITMAP_FILE:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
 	case RUN_ARRAY:
 	case SET_ARRAY_INFO:
@@ -7560,9 +7643,11 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case STOP_ARRAY:
 	case STOP_ARRAY_RO:
 	case CLUSTERED_DISK_NACK:
-		return true;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		return 0;
 	default:
-		return false;
+		return -ENOTTY;
 	}
 }
 
@@ -7620,31 +7705,17 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 	int err = 0;
 	void __user *argp = (void __user *)arg;
 	struct mddev *mddev = NULL;
-	bool did_set_md_closing = false;
-
-	if (!md_ioctl_valid(cmd))
-		return -ENOTTY;
 
-	switch (cmd) {
-	case RAID_VERSION:
-	case GET_ARRAY_INFO:
-	case GET_DISK_INFO:
-		break;
-	default:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
-	}
+	err = md_ioctl_valid(cmd);
+	if (err)
+		return err;
 
 	/*
 	 * Commands dealing with the RAID driver but not any
 	 * particular array:
 	 */
-	switch (cmd) {
-	case RAID_VERSION:
-		err = get_version(argp);
-		goto out;
-	default:;
-	}
+	if (cmd == RAID_VERSION)
+		return get_version(argp);
 
 	/*
 	 * Commands creating/starting a new array:
@@ -7652,35 +7723,23 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	mddev = bdev->bd_disk->private_data;
 
-	if (!mddev) {
-		BUG();
-		goto out;
-	}
-
 	/* Some actions do not requires the mutex */
 	switch (cmd) {
 	case GET_ARRAY_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_array_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_array_info(mddev, argp);
 
 	case GET_DISK_INFO:
 		if (!mddev->raid_disks && !mddev->external)
-			err = -ENODEV;
-		else
-			err = get_disk_info(mddev, argp);
-		goto out;
+			return -ENODEV;
+		return get_disk_info(mddev, argp);
 
 	case SET_DISK_FAULTY:
-		err = set_disk_faulty(mddev, new_decode_dev(arg));
-		goto out;
+		return set_disk_faulty(mddev, new_decode_dev(arg));
 
 	case GET_BITMAP_FILE:
-		err = get_bitmap_file(mddev, argp);
-		goto out;
-
+		return get_bitmap_file(mddev, argp);
 	}
 
 	if (cmd == HOT_REMOVE_DISK)
@@ -7693,20 +7752,9 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		/* Need to flush page cache, and ensure no-one else opens
 		 * and writes
 		 */
-		mutex_lock(&mddev->open_mutex);
-		if (mddev->pers && atomic_read(&mddev->openers) > 1) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		if (test_and_set_bit(MD_CLOSING, &mddev->flags)) {
-			mutex_unlock(&mddev->open_mutex);
-			err = -EBUSY;
-			goto out;
-		}
-		did_set_md_closing = true;
-		mutex_unlock(&mddev->open_mutex);
-		sync_blockdev(bdev);
+		err = mddev_set_closing_and_sync_blockdev(mddev, 1);
+		if (err)
+			return err;
 	}
 
 	if (!md_is_rdwr(mddev))
@@ -7747,11 +7795,12 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
 		goto unlock;
 
 	case STOP_ARRAY:
-		err = do_md_stop(mddev, 0, bdev);
+		err = do_md_stop(mddev, 0);
 		goto unlock;
 
 	case STOP_ARRAY_RO:
-		err = md_set_readonly(mddev, bdev);
+		if (mddev->pers)
+			err = md_set_readonly(mddev);
 		goto unlock;
 
 	case HOT_REMOVE_DISK:
@@ -7846,7 +7895,7 @@ unlock:
 				     mddev_unlock(mddev);
 
 out:
-	if(did_set_md_closing)
+	if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY))
 		clear_bit(MD_CLOSING, &mddev->flags);
 	return err;
 }
@@ -8683,10 +8732,7 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 
 	bio_chain(discard_bio, bio);
 	bio_clone_blkg_association(discard_bio, bio);
-	if (mddev->gendisk)
-		trace_block_bio_remap(discard_bio,
-				disk_devt(mddev->gendisk),
-				bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, discard_bio, bio->bi_iter.bi_sector);
 	submit_bio_noacct(discard_bio);
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
@@ -8733,6 +8779,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
 }
 EXPORT_SYMBOL_GPL(md_account_bio);
 
+void md_free_cloned_bio(struct bio *bio)
+{
+	struct md_io_clone *md_io_clone = bio->bi_private;
+	struct bio *orig_bio = md_io_clone->orig_bio;
+	struct mddev *mddev = md_io_clone->mddev;
+
+	if (bio->bi_status && !orig_bio->bi_status)
+		orig_bio->bi_status = bio->bi_status;
+
+	if (md_io_clone->start_time)
+		bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
+	bio_put(bio);
+	percpu_ref_put(&mddev->active_io);
+}
+EXPORT_SYMBOL_GPL(md_free_cloned_bio);
+
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
  * may proceed without blocking.  It is important to call this before
@@ -8788,12 +8851,16 @@ void md_do_sync(struct md_thread *thread)
 	int ret;
 
 	/* just incase thread restarts... */
-	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_WAIT, &mddev->recovery))
+	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
-	if (!md_is_rdwr(mddev)) {/* never try to sync a read-only array */
+
+	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+		goto skip;
+
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    !md_is_rdwr(mddev)) {/* never try to sync a read-only array */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		return;
+		goto skip;
 	}
 
 	if (mddev_is_clustered(mddev)) {
@@ -9162,7 +9229,7 @@ void md_do_sync(struct md_thread *thread)
 			mddev->delta_disks > 0 &&
 			mddev->pers->finish_reshape &&
 			mddev->pers->size &&
-			mddev->queue) {
+			!mddev_is_dm(mddev)) {
 		mddev_lock_nointr(mddev);
 		md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
 		mddev_unlock(mddev);
@@ -9262,9 +9329,14 @@ static bool md_spares_need_change(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
 
-	rdev_for_each(rdev, mddev)
-		if (rdev_removeable(rdev) || rdev_addable(rdev))
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev_removeable(rdev) || rdev_addable(rdev)) {
+			rcu_read_unlock();
 			return true;
+		}
+	}
+	rcu_read_unlock();
 	return false;
 }
 
@@ -9368,13 +9440,19 @@ static void md_start_sync(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, sync_work);
 	int spares = 0;
 	bool suspend = false;
+	char *name;
 
-	if (md_spares_need_change(mddev))
+	/*
+	 * If reshape is still in progress, spares won't be added or removed
+	 * from conf until reshape is done.
+	 */
+	if (mddev->reshape_position == MaxSector &&
+	    md_spares_need_change(mddev)) {
 		suspend = true;
+		mddev_suspend(mddev, false);
+	}
 
-	suspend ? mddev_suspend_and_lock_nointr(mddev) :
-		  mddev_lock_nointr(mddev);
-
+	mddev_lock_nointr(mddev);
 	if (!md_is_rdwr(mddev)) {
 		/*
 		 * On a read-only array we can:
@@ -9400,8 +9478,10 @@ static void md_start_sync(struct work_struct *ws)
 	if (spares)
 		md_bitmap_write_all(mddev->bitmap);
 
+	name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ?
+			"reshape" : "resync";
 	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "resync"));
+			   md_register_thread(md_do_sync, mddev, name));
 	if (!mddev->sync_thread) {
 		pr_warn("%s: could not start resync thread...\n",
 			mdname(mddev));
@@ -9445,6 +9525,20 @@ not_running:
 		sysfs_notify_dirent_safe(mddev->sysfs_action);
 }
 
+static void unregister_sync_thread(struct mddev *mddev)
+{
+	if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+		/* resync/recovery still happening */
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!mddev->sync_thread))
+		return;
+
+	md_reap_sync_thread(mddev);
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -9469,9 +9563,6 @@ not_running:
  */
 void md_check_recovery(struct mddev *mddev)
 {
-	if (READ_ONCE(mddev->suspended))
-		return;
-
 	if (mddev->bitmap)
 		md_bitmap_daemon_work(mddev);
 
@@ -9485,7 +9576,8 @@ void md_check_recovery(struct mddev *mddev)
 	}
 
 	if (!md_is_rdwr(mddev) &&
-	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+	    !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
 	if ( ! (
 		(mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) ||
@@ -9507,8 +9599,7 @@ void md_check_recovery(struct mddev *mddev)
 			struct md_rdev *rdev;
 
 			if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-				/* sync_work already queued. */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				unregister_sync_thread(mddev);
 				goto unlock;
 			}
 
@@ -9571,16 +9662,7 @@ void md_check_recovery(struct mddev *mddev)
 		 * still set.
 		 */
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
-			if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
-				/* resync/recovery still happening */
-				clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-				goto unlock;
-			}
-
-			if (WARN_ON_ONCE(!mddev->sync_thread))
-				goto unlock;
-
-			md_reap_sync_thread(mddev);
+			unregister_sync_thread(mddev);
 			goto unlock;
 		}
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 8d881cc59799..097d9dbd69b8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -18,6 +18,7 @@
 #include <linux/timer.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <trace/events/block.h>
 #include "md-cluster.h"
 
 #define MaxSector (~(sector_t)0)
@@ -59,7 +60,7 @@ struct md_rdev {
 	 */
 	struct block_device *meta_bdev;
 	struct block_device *bdev;	/* block device handle */
-	struct bdev_handle *bdev_handle;	/* Handle from open for bdev */
+	struct file *bdev_file;		/* Handle from open for bdev */
 
 	struct page	*sb_page, *bb_page;
 	int		sb_loaded;
@@ -207,6 +208,7 @@ enum flag_bits {
 				 * check if there is collision between raid1
 				 * serial bios.
 				 */
+	Nonrot,			/* non-rotational device (SSD) */
 };
 
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
@@ -222,6 +224,16 @@ static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 	}
 	return 0;
 }
+
+static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s,
+				    int sectors)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors);
+}
+
 extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
@@ -468,7 +480,6 @@ struct mddev {
 	struct timer_list		safemode_timer;
 	struct percpu_ref		writes_pending;
 	int				sync_checkers;	/* # of threads checking writes_pending */
-	struct request_queue		*queue;	/* for plugging ... */
 
 	struct bitmap			*bitmap; /* the bitmap for the device */
 	struct {
@@ -558,6 +569,37 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
+enum md_ro_state {
+	MD_RDWR,
+	MD_RDONLY,
+	MD_AUTO_READ,
+	MD_MAX_STATE
+};
+
+static inline bool md_is_rdwr(struct mddev *mddev)
+{
+	return (mddev->ro == MD_RDWR);
+}
+
+static inline bool reshape_interrupted(struct mddev *mddev)
+{
+	/* reshape never start */
+	if (mddev->reshape_position == MaxSector)
+		return false;
+
+	/* interrupted */
+	if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return true;
+
+	/* running reshape will be interrupted soon. */
+	if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_INTR, &mddev->recovery) ||
+	    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		return true;
+
+	return false;
+}
+
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -617,6 +659,7 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
+	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -750,6 +793,7 @@ extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
+void md_free_cloned_bio(struct bio *bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
@@ -778,9 +822,12 @@ extern void md_stop_writes(struct mddev *mddev);
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
-extern void md_handle_request(struct mddev *mddev, struct bio *bio);
+extern bool md_handle_request(struct mddev *mddev, struct bio *bio);
 extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
+extern void md_idle_sync_thread(struct mddev *mddev);
+extern void md_frozen_sync_thread(struct mddev *mddev);
+extern void md_unfrozen_sync_thread(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
@@ -821,7 +868,7 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 {
 	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
 	    !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors)
-		mddev->queue->limits.max_write_zeroes_sectors = 0;
+		mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0;
 }
 
 static inline int mddev_suspend_and_lock(struct mddev *mddev)
@@ -860,7 +907,31 @@ void md_autostart_arrays(int part);
 int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info);
 int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info);
 int do_md_run(struct mddev *mddev);
+void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim);
+int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
+void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
 extern const struct block_device_operations md_fops;
 
+/*
+ * MD devices can be used undeneath by DM, in which case ->gendisk is NULL.
+ */
+static inline bool mddev_is_dm(struct mddev *mddev)
+{
+	return !mddev->gendisk;
+}
+
+static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
+		sector_t sector)
+{
+	if (!mddev_is_dm(mddev))
+		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
+}
+
+#define mddev_add_trace_msg(mddev, fmt, args...)			\
+do {									\
+	if (!mddev_is_dm(mddev))					\
+		blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \
+} while (0)
+
 #endif /* _MD_MD_H */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c50a7abda744..c5d4aeb68404 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -379,6 +379,19 @@ static void raid0_free(struct mddev *mddev, void *priv)
 	free_conf(mddev, conf);
 }
 
+static int raid0_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * mddev->raid_disks;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -399,20 +412,10 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (mddev->queue) {
-		struct md_rdev *rdev;
-
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-		}
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			goto out_free_conf;
 	}
 
 	/* calculate array device size */
@@ -426,8 +429,10 @@ static int raid0_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret)
-		free_conf(mddev, conf);
-
+		goto out_free_conf;
+	return 0;
+out_free_conf:
+	free_conf(mddev, conf);
 	return ret;
 }
 
@@ -578,10 +583,7 @@ static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio)
 	bio_set_dev(bio, tmp_dev->bdev);
 	bio->bi_iter.bi_sector = sector + zone->dev_start +
 		tmp_dev->data_offset;
-
-	if (mddev->gendisk)
-		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-				      bio_sector);
+	mddev_trace_remap(mddev, bio, bio_sector);
 	mddev_check_write_zeroes(mddev, bio);
 	submit_bio_noacct(bio);
 }
diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 512746551f36..2ea1710a3b70 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -227,3 +227,72 @@ static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
 
 	return false;
 }
+
+/**
+ * raid1_check_read_range() - check a given read range for bad blocks,
+ * available read length is returned;
+ * @rdev: the rdev to read;
+ * @this_sector: read position;
+ * @len: read length;
+ *
+ * helper function for read_balance()
+ *
+ * 1) If there are no bad blocks in the range, @len is returned;
+ * 2) If the range are all bad blocks, 0 is returned;
+ * 3) If there are partial bad blocks:
+ *  - If the bad block range starts after @this_sector, the length of first
+ *  good region is returned;
+ *  - If the bad block range starts before @this_sector, 0 is returned and
+ *  the @len is updated to the offset into the region before we get to the
+ *  good blocks;
+ */
+static inline int raid1_check_read_range(struct md_rdev *rdev,
+					 sector_t this_sector, int *len)
+{
+	sector_t first_bad;
+	int bad_sectors;
+
+	/* no bad block overlap */
+	if (!is_badblock(rdev, this_sector, *len, &first_bad, &bad_sectors))
+		return *len;
+
+	/*
+	 * bad block range starts offset into our range so we can return the
+	 * number of sectors before the bad blocks start.
+	 */
+	if (first_bad > this_sector)
+		return first_bad - this_sector;
+
+	/* read range is fully consumed by bad blocks. */
+	if (this_sector + *len <= first_bad + bad_sectors)
+		return 0;
+
+	/*
+	 * final case, bad block range starts before or at the start of our
+	 * range but does not cover our entire range so we still return 0 but
+	 * update the length with the number of sectors before we get to the
+	 * good ones.
+	 */
+	*len = first_bad + bad_sectors - this_sector;
+	return 0;
+}
+
+/*
+ * Check if read should choose the first rdev.
+ *
+ * Balance on the whole device if no resync is going on (recovery is ok) or
+ * below the resync window. Otherwise, take the first readable disk.
+ */
+static inline bool raid1_should_read_first(struct mddev *mddev,
+					   sector_t this_sector, int len)
+{
+	if ((mddev->recovery_cp < this_sector + len))
+		return true;
+
+	if (mddev_is_clustered(mddev) &&
+	    md_cluster_ops->area_resyncing(mddev, READ, this_sector,
+					   this_sector + len))
+		return true;
+
+	return false;
+}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 286f8b16c7bd..be8ac24f50b6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -46,9 +46,6 @@
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
 static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 
-#define raid1_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
-
 #define RAID_1_10_NAME "raid1"
 #include "raid1-10.c"
 
@@ -498,9 +495,6 @@ static void raid1_end_write_request(struct bio *bio)
 		 * to user-side. So if something waits for IO, then it
 		 * will wait for the 'master' bio.
 		 */
-		sector_t first_bad;
-		int bad_sectors;
-
 		r1_bio->bios[mirror] = NULL;
 		to_put = bio;
 		/*
@@ -516,8 +510,8 @@ static void raid1_end_write_request(struct bio *bio)
 			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		    !discard_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -582,211 +576,312 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector,
 	return len;
 }
 
-/*
- * This routine returns the disk from which the requested read should
- * be done. There is a per-array 'next expected sequential IO' sector
- * number - if this matches on the next IO then we use the last disk.
- * There is also a per-disk 'last know head position' sector that is
- * maintained from IRQ contexts, both the normal and the resync IO
- * completion handlers update this position correctly. If there is no
- * perfect sequential match then we pick the disk whose head is closest.
- *
- * If there are 2 mirrors in the same 2 devices, performance degrades
- * because position is mirror, not device based.
- *
- * The rdev for the device selected will have nr_pending incremented.
- */
-static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
+static void update_read_sectors(struct r1conf *conf, int disk,
+				sector_t this_sector, int len)
 {
-	const sector_t this_sector = r1_bio->sector;
-	int sectors;
-	int best_good_sectors;
-	int best_disk, best_dist_disk, best_pending_disk;
-	int has_nonrot_disk;
+	struct raid1_info *info = &conf->mirrors[disk];
+
+	atomic_inc(&info->rdev->nr_pending);
+	if (info->next_seq_sect != this_sector)
+		info->seq_start = this_sector;
+	info->next_seq_sect = this_sector + len;
+}
+
+static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			     int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int len = r1_bio->sectors;
 	int disk;
-	sector_t best_dist;
-	unsigned int min_pending;
-	struct md_rdev *rdev;
-	int choose_first;
-	int choose_next_idle;
 
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on, or below the resync window.
-	 * We take the first readable disk when above the resync window.
-	 */
- retry:
-	sectors = r1_bio->sectors;
-	best_disk = -1;
-	best_dist_disk = -1;
-	best_dist = MaxSector;
-	best_pending_disk = -1;
-	min_pending = UINT_MAX;
-	best_good_sectors = 0;
-	has_nonrot_disk = 0;
-	choose_next_idle = 0;
-	clear_bit(R1BIO_FailFast, &r1_bio->state);
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int read_len;
 
-	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-		    this_sector + sectors)))
-		choose_first = 1;
-	else
-		choose_first = 0;
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags))
+			continue;
+
+		/* choose the first disk even if it has some bad blocks. */
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > 0) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			*max_sectors = read_len;
+			return disk;
+		}
+	}
+
+	return -1;
+}
+
+static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			  int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int best_disk = -1;
+	int best_len = 0;
+	int disk;
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
-		sector_t dist;
-		sector_t first_bad;
-		int bad_sectors;
-		unsigned int pending;
-		bool nonrot;
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
 
 		rdev = conf->mirrors[disk].rdev;
-		if (r1_bio->bios[disk] == IO_BLOCKED
-		    || rdev == NULL
-		    || test_bit(Faulty, &rdev->flags))
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    test_bit(WriteMostly, &rdev->flags))
 			continue;
-		if (!test_bit(In_sync, &rdev->flags) &&
-		    rdev->recovery_offset < this_sector + sectors)
+
+		/* keep track of the disk with the most readable sectors. */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > best_len) {
+			best_disk = disk;
+			best_len = read_len;
+		}
+	}
+
+	if (best_disk != -1) {
+		*max_sectors = best_len;
+		update_read_sectors(conf, best_disk, this_sector, best_len);
+	}
+
+	return best_disk;
+}
+
+static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			    int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int bb_disk = -1;
+	int bb_read_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
 			continue;
-		if (test_bit(WriteMostly, &rdev->flags)) {
-			/* Don't balance among write-mostly, just
-			 * use the first as a last resort */
-			if (best_dist_disk < 0) {
-				if (is_badblock(rdev, this_sector, sectors,
-						&first_bad, &bad_sectors)) {
-					if (first_bad <= this_sector)
-						/* Cannot use this */
-						continue;
-					best_good_sectors = first_bad - this_sector;
-				} else
-					best_good_sectors = sectors;
-				best_dist_disk = disk;
-				best_pending_disk = disk;
-			}
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(WriteMostly, &rdev->flags))
 			continue;
+
+		/* there are no bad blocks, we can use this disk */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len == r1_bio->sectors) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			return disk;
 		}
-		/* This is a reasonable device to use.  It might
-		 * even be best.
+
+		/*
+		 * there are partial bad blocks, choose the rdev with largest
+		 * read length.
 		 */
-		if (is_badblock(rdev, this_sector, sectors,
-				&first_bad, &bad_sectors)) {
-			if (best_dist < MaxSector)
-				/* already have a better device */
-				continue;
-			if (first_bad <= this_sector) {
-				/* cannot read here. If this is the 'primary'
-				 * device, then we must not read beyond
-				 * bad_sectors from another device..
-				 */
-				bad_sectors -= (this_sector - first_bad);
-				if (choose_first && sectors > bad_sectors)
-					sectors = bad_sectors;
-				if (best_good_sectors > sectors)
-					best_good_sectors = sectors;
-
-			} else {
-				sector_t good_sectors = first_bad - this_sector;
-				if (good_sectors > best_good_sectors) {
-					best_good_sectors = good_sectors;
-					best_disk = disk;
-				}
-				if (choose_first)
-					break;
-			}
-			continue;
-		} else {
-			if ((sectors > best_good_sectors) && (best_disk >= 0))
-				best_disk = -1;
-			best_good_sectors = sectors;
+		if (read_len > bb_read_len) {
+			bb_disk = disk;
+			bb_read_len = read_len;
 		}
+	}
+
+	if (bb_disk != -1) {
+		*max_sectors = bb_read_len;
+		update_read_sectors(conf, bb_disk, this_sector, bb_read_len);
+	}
+
+	return bb_disk;
+}
+
+static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
+{
+	/* TODO: address issues with this check and concurrency. */
+	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	       conf->mirrors[disk].head_position == r1_bio->sector;
+}
+
+/*
+ * If buffered sequential IO size exceeds optimal iosize, check if there is idle
+ * disk. If yes, choose the idle disk.
+ */
+static bool should_choose_next(struct r1conf *conf, int disk)
+{
+	struct raid1_info *mirror = &conf->mirrors[disk];
+	int opt_iosize;
+
+	if (!test_bit(Nonrot, &mirror->rdev->flags))
+		return false;
+
+	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
+	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
+	       mirror->next_seq_sect > opt_iosize &&
+	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+}
+
+static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
+{
+	if (!rdev || test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* still in recovery */
+	if (!test_bit(In_sync, &rdev->flags) &&
+	    rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
+		return false;
+
+	/* don't read from slow disk unless have to */
+	if (test_bit(WriteMostly, &rdev->flags))
+		return false;
+
+	/* don't split IO for bad blocks unless have to */
+	if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors))
+		return false;
+
+	return true;
+}
+
+struct read_balance_ctl {
+	sector_t closest_dist;
+	int closest_dist_disk;
+	int min_pending;
+	int min_pending_disk;
+	int sequential_disk;
+	int readable_disks;
+};
+
+static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio)
+{
+	int disk;
+	struct read_balance_ctl ctl = {
+		.closest_dist_disk      = -1,
+		.closest_dist           = MaxSector,
+		.min_pending_disk       = -1,
+		.min_pending            = UINT_MAX,
+		.sequential_disk	= -1,
+	};
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		sector_t dist;
+		unsigned int pending;
 
-		if (best_disk >= 0)
-			/* At least two disks to choose from so failfast is OK */
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev_readable(rdev, r1_bio))
+			continue;
+
+		/* At least two disks to choose from so failfast is OK */
+		if (ctl.readable_disks++ == 1)
 			set_bit(R1BIO_FailFast, &r1_bio->state);
 
-		nonrot = bdev_nonrot(rdev->bdev);
-		has_nonrot_disk |= nonrot;
 		pending = atomic_read(&rdev->nr_pending);
-		dist = abs(this_sector - conf->mirrors[disk].head_position);
-		if (choose_first) {
-			best_disk = disk;
-			break;
-		}
+		dist = abs(r1_bio->sector - conf->mirrors[disk].head_position);
+
 		/* Don't change to another disk for sequential reads */
-		if (conf->mirrors[disk].next_seq_sect == this_sector
-		    || dist == 0) {
-			int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
-			struct raid1_info *mirror = &conf->mirrors[disk];
+		if (is_sequential(conf, disk, r1_bio)) {
+			if (!should_choose_next(conf, disk))
+				return disk;
 
-			best_disk = disk;
 			/*
-			 * If buffered sequential IO size exceeds optimal
-			 * iosize, check if there is idle disk. If yes, choose
-			 * the idle disk. read_balance could already choose an
-			 * idle disk before noticing it's a sequential IO in
-			 * this disk. This doesn't matter because this disk
-			 * will idle, next time it will be utilized after the
-			 * first disk has IO size exceeds optimal iosize. In
-			 * this way, iosize of the first disk will be optimal
-			 * iosize at least. iosize of the second disk might be
-			 * small, but not a big deal since when the second disk
-			 * starts IO, the first disk is likely still busy.
+			 * Add 'pending' to avoid choosing this disk if
+			 * there is other idle disk.
 			 */
-			if (nonrot && opt_iosize > 0 &&
-			    mirror->seq_start != MaxSector &&
-			    mirror->next_seq_sect > opt_iosize &&
-			    mirror->next_seq_sect - opt_iosize >=
-			    mirror->seq_start) {
-				choose_next_idle = 1;
-				continue;
-			}
-			break;
+			pending++;
+			/*
+			 * If there is no other idle disk, this disk
+			 * will be chosen.
+			 */
+			ctl.sequential_disk = disk;
 		}
 
-		if (choose_next_idle)
-			continue;
-
-		if (min_pending > pending) {
-			min_pending = pending;
-			best_pending_disk = disk;
+		if (ctl.min_pending > pending) {
+			ctl.min_pending = pending;
+			ctl.min_pending_disk = disk;
 		}
 
-		if (dist < best_dist) {
-			best_dist = dist;
-			best_dist_disk = disk;
+		if (ctl.closest_dist > dist) {
+			ctl.closest_dist = dist;
+			ctl.closest_dist_disk = disk;
 		}
 	}
 
 	/*
+	 * sequential IO size exceeds optimal iosize, however, there is no other
+	 * idle disk, so choose the sequential disk.
+	 */
+	if (ctl.sequential_disk != -1 && ctl.min_pending != 0)
+		return ctl.sequential_disk;
+
+	/*
 	 * If all disks are rotational, choose the closest disk. If any disk is
 	 * non-rotational, choose the disk with less pending request even the
 	 * disk is rotational, which might/might not be optimal for raids with
 	 * mixed ratation/non-rotational disks depending on workload.
 	 */
-	if (best_disk == -1) {
-		if (has_nonrot_disk || min_pending == 0)
-			best_disk = best_pending_disk;
-		else
-			best_disk = best_dist_disk;
-	}
+	if (ctl.min_pending_disk != -1 &&
+	    (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0))
+		return ctl.min_pending_disk;
+	else
+		return ctl.closest_dist_disk;
+}
 
-	if (best_disk >= 0) {
-		rdev = conf->mirrors[best_disk].rdev;
-		if (!rdev)
-			goto retry;
-		atomic_inc(&rdev->nr_pending);
-		sectors = best_good_sectors;
+/*
+ * This routine returns the disk from which the requested read should be done.
+ *
+ * 1) If resync is in progress, find the first usable disk and use it even if it
+ * has some bad blocks.
+ *
+ * 2) Now that there is no resync, loop through all disks and skipping slow
+ * disks and disks with bad blocks for now. Only pay attention to key disk
+ * choice.
+ *
+ * 3) If we've made it this far, now look for disks with bad blocks and choose
+ * the one with most number of sectors.
+ *
+ * 4) If we are all the way at the end, we have no choice but to use a disk even
+ * if it is write mostly.
+ *
+ * The rdev for the device selected will have nr_pending incremented.
+ */
+static int read_balance(struct r1conf *conf, struct r1bio *r1_bio,
+			int *max_sectors)
+{
+	int disk;
 
-		if (conf->mirrors[best_disk].next_seq_sect != this_sector)
-			conf->mirrors[best_disk].seq_start = this_sector;
+	clear_bit(R1BIO_FailFast, &r1_bio->state);
+
+	if (raid1_should_read_first(conf->mddev, r1_bio->sector,
+				    r1_bio->sectors))
+		return choose_first_rdev(conf, r1_bio, max_sectors);
 
-		conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
+	disk = choose_best_rdev(conf, r1_bio);
+	if (disk >= 0) {
+		*max_sectors = r1_bio->sectors;
+		update_read_sectors(conf, disk, r1_bio->sector,
+				    r1_bio->sectors);
+		return disk;
 	}
-	*max_sectors = sectors;
 
-	return best_disk;
+	/*
+	 * If we are here it means we didn't find a perfectly good disk so
+	 * now spend a bit more time trying to find one with the most good
+	 * sectors.
+	 */
+	disk = choose_bb_rdev(conf, r1_bio, max_sectors);
+	if (disk >= 0)
+		return disk;
+
+	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
 static void wake_up_barrier(struct r1conf *conf)
@@ -1098,7 +1193,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 	 */
 	spin_lock_irq(&conf->resync_lock);
 	conf->array_frozen = 1;
-	raid1_log(conf->mddev, "wait freeze");
+	mddev_add_trace_msg(conf->mddev, "raid1 wait freeze");
 	wait_event_lock_irq_cmd(
 		conf->wait_barrier,
 		get_unqueued_pending(conf) == extra,
@@ -1287,7 +1382,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 		 * Reading from a write-mostly device must take care not to
 		 * over-take any writes that are 'behind'
 		 */
-		raid1_log(mddev, "wait behind writes");
+		mddev_add_trace_msg(mddev, "raid1 wait behind writes");
 		wait_event(bitmap->behind_wait,
 			   atomic_read(&bitmap->behind_writes) == 0);
 	}
@@ -1320,11 +1415,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R1BIO_FailFast, &r1_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r1_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-				      r1_bio->sector);
-
+	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
 }
 
@@ -1474,7 +1565,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
+		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
+				blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, bio->bi_iter.bi_sector, false);
 		goto retry_write;
@@ -1557,10 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
-
-		if (mddev->gendisk)
-			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
-					      r1_bio->sector);
+		mddev_trace_remap(mddev, mbio, r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
 		mbio->bi_bdev = (void *)rdev;
 		if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) {
@@ -1760,6 +1849,52 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
+static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk,
+			   bool replacement)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+
+	if (replacement)
+		info += conf->raid_disks;
+
+	if (info->rdev)
+		return false;
+
+	if (bdev_nonrot(rdev->bdev)) {
+		set_bit(Nonrot, &rdev->flags);
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1);
+	}
+
+	rdev->raid_disk = disk;
+	info->head_position = 0;
+	info->seq_start = MaxSector;
+	WRITE_ONCE(info->rdev, rdev);
+
+	return true;
+}
+
+static bool raid1_remove_conf(struct r1conf *conf, int disk)
+{
+	struct raid1_info *info = conf->mirrors + disk;
+	struct md_rdev *rdev = info->rdev;
+
+	if (!rdev || test_bit(In_sync, &rdev->flags) ||
+	    atomic_read(&rdev->nr_pending))
+		return false;
+
+	/* Only remove non-faulty devices if recovery is not possible. */
+	if (!test_bit(Faulty, &rdev->flags) &&
+	    rdev->mddev->recovery_disabled != conf->recovery_disabled &&
+	    rdev->mddev->degraded < conf->raid_disks)
+		return false;
+
+	if (test_and_clear_bit(Nonrot, &rdev->flags))
+		WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1);
+
+	WRITE_ONCE(info->rdev, NULL);
+	return true;
+}
+
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1791,19 +1926,16 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors + mirror;
 		if (!p->rdev) {
-			if (mddev->gendisk)
-				disk_stack_limits(mddev->gendisk, rdev->bdev,
-						  rdev->data_offset << 9);
+			err = mddev_stack_new_rdev(mddev, rdev);
+			if (err)
+				return err;
 
-			p->head_position = 0;
-			rdev->raid_disk = mirror;
-			err = 0;
+			raid1_add_conf(conf, rdev, mirror, false);
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
 			if (rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
-			WRITE_ONCE(p->rdev, rdev);
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
@@ -1813,13 +1945,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (err && repl_slot >= 0) {
 		/* Add this device as a replacement */
-		p = conf->mirrors + repl_slot;
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
-		rdev->raid_disk = repl_slot;
+		raid1_add_conf(conf, rdev, repl_slot, true);
 		err = 0;
 		conf->fullsync = 1;
-		WRITE_ONCE(p[conf->raid_disks].rdev, rdev);
 	}
 
 	print_conf(conf);
@@ -1836,27 +1966,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (unlikely(number >= conf->raid_disks))
 		goto abort;
 
-	if (rdev != p->rdev)
-		p = conf->mirrors + conf->raid_disks + number;
+	if (rdev != p->rdev) {
+		number += conf->raid_disks;
+		p = conf->mirrors + number;
+	}
 
 	print_conf(conf);
 	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
+		if (!raid1_remove_conf(conf, number)) {
 			err = -EBUSY;
 			goto abort;
 		}
-		/* Only remove non-faulty devices if recovery
-		 * is not possible.
-		 */
-		if (!test_bit(Faulty, &rdev->flags) &&
-		    mddev->recovery_disabled != conf->recovery_disabled &&
-		    mddev->degraded < conf->raid_disks) {
-			err = -EBUSY;
-			goto abort;
-		}
-		WRITE_ONCE(p->rdev, NULL);
-		if (conf->mirrors[conf->raid_disks + number].rdev) {
+
+		if (number < conf->raid_disks &&
+		    conf->mirrors[conf->raid_disks + number].rdev) {
 			/* We just removed a device that is being replaced.
 			 * Move down the replacement.  We drain all IO before
 			 * doing this to avoid confusion.
@@ -1944,8 +2067,6 @@ static void end_sync_write(struct bio *bio)
 	struct r1bio *r1_bio = get_resync_r1bio(bio);
 	struct mddev *mddev = r1_bio->mddev;
 	struct r1conf *conf = mddev->private;
-	sector_t first_bad;
-	int bad_sectors;
 	struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
 
 	if (!uptodate) {
@@ -1955,14 +2076,11 @@ static void end_sync_write(struct bio *bio)
 			set_bit(MD_RECOVERY_NEEDED, &
 				mddev->recovery);
 		set_bit(R1BIO_WriteError, &r1_bio->state);
-	} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
-			       &first_bad, &bad_sectors) &&
-		   !is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
-				r1_bio->sector,
-				r1_bio->sectors,
-				&first_bad, &bad_sectors)
-		)
+	} else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
+		   !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev,
+				      r1_bio->sector, r1_bio->sectors)) {
 		set_bit(R1BIO_MadeGood, &r1_bio->state);
+	}
 
 	put_sync_write_buf(r1_bio, uptodate);
 }
@@ -2279,16 +2397,12 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    (test_bit(In_sync, &rdev->flags) ||
 			     (!test_bit(Faulty, &rdev->flags) &&
 			      rdev->recovery_offset >= sect + s)) &&
-			    is_badblock(rdev, sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev, sect, s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				if (sync_page_io(rdev, sect, s<<9,
 					 conf->tmppage, REQ_OP_READ, false))
@@ -3006,23 +3120,17 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
+	conf->raid_disks = mddev->raid_disks;
 	rdev_for_each(rdev, mddev) {
 		int disk_idx = rdev->raid_disk;
-		if (disk_idx >= mddev->raid_disks
-		    || disk_idx < 0)
+
+		if (disk_idx >= conf->raid_disks || disk_idx < 0)
 			continue;
-		if (test_bit(Replacement, &rdev->flags))
-			disk = conf->mirrors + mddev->raid_disks + disk_idx;
-		else
-			disk = conf->mirrors + disk_idx;
 
-		if (disk->rdev)
+		if (!raid1_add_conf(conf, rdev, disk_idx,
+				    test_bit(Replacement, &rdev->flags)))
 			goto abort;
-		disk->rdev = rdev;
-		disk->head_position = 0;
-		disk->seq_start = MaxSector;
 	}
-	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
 	INIT_LIST_HEAD(&conf->retry_list);
 	INIT_LIST_HEAD(&conf->bio_end_io_list);
@@ -3086,12 +3194,21 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
+static int raid1_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
+
 static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
 	int i;
-	struct md_rdev *rdev;
 	int ret;
 
 	if (mddev->level != 1) {
@@ -3118,14 +3235,10 @@ static int raid1_run(struct mddev *mddev)
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
-	if (mddev->queue)
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-	rdev_for_each(rdev, mddev) {
-		if (!mddev->gendisk)
-			continue;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid1_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	mddev->degraded = 0;
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 14d4211a123a..5300cbaa58a4 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -71,6 +71,7 @@ struct r1conf {
 						 * allow for replacements.
 						 */
 	int			raid_disks;
+	int			nonrot_disks;
 
 	spinlock_t		device_lock;
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7412066ea22c..a4556d2e46bf 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,9 +76,6 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
 static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
-#define raid10_log(md, fmt, args...)				\
-	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-
 #include "raid1-10.c"
 
 #define NULL_CMD
@@ -518,11 +515,7 @@ static void raid10_end_write_request(struct bio *bio)
 		 * The 'master' represents the composite IO operation to
 		 * user-side. So if something waits for IO, then it will
 		 * wait for the 'master' bio.
-		 */
-		sector_t first_bad;
-		int bad_sectors;
-
-		/*
+		 *
 		 * Do not set R10BIO_Uptodate if the current device is
 		 * rebuilding or Faulty. This is because we cannot use
 		 * such device for properly reading the data back (we could
@@ -535,10 +528,9 @@ static void raid10_end_write_request(struct bio *bio)
 			set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
-		if (is_badblock(rdev,
-				r10_bio->devs[slot].addr,
-				r10_bio->sectors,
-				&first_bad, &bad_sectors) && !discard_error) {
+		if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				      r10_bio->sectors) &&
+		    !discard_error) {
 			bio_put(bio);
 			if (repl)
 				r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
@@ -753,17 +745,8 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	best_good_sectors = 0;
 	do_balance = 1;
 	clear_bit(R10BIO_FailFast, &r10_bio->state);
-	/*
-	 * Check if we can balance. We can balance on the whole
-	 * device if no resync is going on (recovery is ok), or below
-	 * the resync window. We take the first readable disk when
-	 * above the resync window.
-	 */
-	if ((conf->mddev->recovery_cp < MaxSector
-	     && (this_sector + sectors >= conf->next_resync)) ||
-	    (mddev_is_clustered(conf->mddev) &&
-	     md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
-					    this_sector + sectors)))
+
+	if (raid1_should_read_first(conf->mddev, this_sector, sectors))
 		do_balance = 0;
 
 	for (slot = 0; slot < conf->copies ; slot++) {
@@ -1033,7 +1016,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
 			ret = false;
 		} else {
 			conf->nr_waiting++;
-			raid10_log(conf->mddev, "wait barrier");
+			mddev_add_trace_msg(conf->mddev, "raid10 wait barrier");
 			wait_event_barrier(conf, stop_waiting_barrier(conf));
 			conf->nr_waiting--;
 		}
@@ -1152,7 +1135,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 			bio_wouldblock_error(bio);
 			return false;
 		}
-		raid10_log(conf->mddev, "wait reshape");
+		mddev_add_trace_msg(conf->mddev, "raid10 wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
@@ -1249,10 +1232,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	    test_bit(R10BIO_FailFast, &r10_bio->state))
 	        read_bio->bi_opf |= MD_FAILFAST;
 	read_bio->bi_private = r10_bio;
-
-	if (mddev->gendisk)
-	        trace_block_bio_remap(read_bio, disk_devt(mddev->gendisk),
-	                              r10_bio->sector);
+	mddev_trace_remap(mddev, read_bio, r10_bio->sector);
 	submit_bio_noacct(read_bio);
 	return;
 }
@@ -1288,10 +1268,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			 && enough(conf, devnum))
 		mbio->bi_opf |= MD_FAILFAST;
 	mbio->bi_private = r10_bio;
-
-	if (conf->mddev->gendisk)
-		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
-				      r10_bio->sector);
+	mddev_trace_remap(mddev, mbio, r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
 	mbio->bi_bdev = (void *)rdev;
 
@@ -1330,10 +1307,7 @@ retry_wait:
 		}
 
 		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
-			int bad_sectors;
-			int is_bad;
 
 			/*
 			 * Discard request doesn't care the write result
@@ -1342,9 +1316,8 @@ retry_wait:
 			if (!r10_bio->sectors)
 				continue;
 
-			is_bad = is_badblock(rdev, dev_sector, r10_bio->sectors,
-					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
+			if (rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0) {
 				/*
 				 * Mustn't write here until the bad block
 				 * is acknowledged
@@ -1360,8 +1333,9 @@ retry_wait:
 	if (unlikely(blocked_rdev)) {
 		/* Have to wait for this device to get unblocked, then retry */
 		allow_barrier(conf);
-		raid10_log(conf->mddev, "%s wait rdev %d blocked",
-				__func__, blocked_rdev->raid_disk);
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 %s wait rdev %d blocked",
+			__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		wait_barrier(conf, false);
 		goto retry_wait;
@@ -1416,7 +1390,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 			bio_wouldblock_error(bio);
 			return;
 		}
-		raid10_log(conf->mddev, "wait reshape metadata");
+		mddev_add_trace_msg(conf->mddev,
+			"raid10 wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
@@ -2131,10 +2106,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			continue;
 		}
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
 		rdev->raid_disk = mirror;
@@ -2150,10 +2124,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(In_sync, &rdev->flags);
 		set_bit(Replacement, &rdev->flags);
 		rdev->raid_disk = repl_slot;
-		err = 0;
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+		err = mddev_stack_new_rdev(mddev, rdev);
+		if (err)
+			return err;
 		conf->fullsync = 1;
 		WRITE_ONCE(p->replacement, rdev);
 	}
@@ -2290,8 +2263,6 @@ static void end_sync_write(struct bio *bio)
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
 	int d;
-	sector_t first_bad;
-	int bad_sectors;
 	int slot;
 	int repl;
 	struct md_rdev *rdev = NULL;
@@ -2312,11 +2283,10 @@ static void end_sync_write(struct bio *bio)
 					&rdev->mddev->recovery);
 			set_bit(R10BIO_WriteError, &r10_bio->state);
 		}
-	} else if (is_badblock(rdev,
-			     r10_bio->devs[slot].addr,
-			     r10_bio->sectors,
-			     &first_bad, &bad_sectors))
+	} else if (rdev_has_badblock(rdev, r10_bio->devs[slot].addr,
+				     r10_bio->sectors)) {
 		set_bit(R10BIO_MadeGood, &r10_bio->state);
+	}
 
 	rdev_dec_pending(rdev, mddev);
 
@@ -2597,11 +2567,8 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
-	sector_t first_bad;
-	int bad_sectors;
-
-	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
-	    && (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
+	if (rdev_has_badblock(rdev, sector, sectors) &&
+	    (op == REQ_OP_READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
 	if (sync_page_io(rdev, sector, sectors << 9, page, op, false))
 		/* success */
@@ -2658,16 +2625,14 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 			s = PAGE_SIZE >> 9;
 
 		do {
-			sector_t first_bad;
-			int bad_sectors;
-
 			d = r10_bio->devs[sl].devnum;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
-			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
-					&first_bad, &bad_sectors) == 0) {
+			    rdev_has_badblock(rdev,
+					      r10_bio->devs[sl].addr + sect,
+					      s) == 0) {
 				atomic_inc(&rdev->nr_pending);
 				success = sync_page_io(rdev,
 						       r10_bio->devs[sl].addr +
@@ -4002,14 +3967,26 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 	return ERR_PTR(err);
 }
 
-static void raid10_set_io_opt(struct r10conf *conf)
+static unsigned int raid10_nr_stripes(struct r10conf *conf)
 {
-	int raid_disks = conf->geo.raid_disks;
+	unsigned int raid_disks = conf->geo.raid_disks;
+
+	if (conf->geo.raid_disks % conf->geo.near_copies)
+		return raid_disks;
+	return raid_disks / conf->geo.near_copies;
+}
 
-	if (!(conf->geo.raid_disks % conf->geo.near_copies))
-		raid_disks /= conf->geo.near_copies;
-	blk_queue_io_opt(conf->mddev->queue, (conf->mddev->chunk_sectors << 9) *
-			 raid_disks);
+static int raid10_set_queue_limits(struct mddev *mddev)
+{
+	struct r10conf *conf = mddev->private;
+	struct queue_limits lim;
+
+	blk_set_stacking_limits(&lim);
+	lim.max_write_zeroes_sectors = 0;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
+	mddev_stack_rdev_limits(mddev, &lim);
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid10_run(struct mddev *mddev)
@@ -4021,6 +3998,7 @@ static int raid10_run(struct mddev *mddev)
 	sector_t size;
 	sector_t min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
@@ -4047,12 +4025,6 @@ static int raid10_run(struct mddev *mddev)
 		}
 	}
 
-	if (mddev->queue) {
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		raid10_set_io_opt(conf);
-	}
-
 	rdev_for_each(rdev, mddev) {
 		long long diff;
 
@@ -4081,14 +4053,16 @@ static int raid10_run(struct mddev *mddev)
 		if (first || diff < min_offset_diff)
 			min_offset_diff = diff;
 
-		if (mddev->gendisk)
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
 		disk->head_position = 0;
 		first = 0;
 	}
 
+	if (!mddev_is_dm(conf->mddev)) {
+		ret = raid10_set_queue_limits(mddev);
+		if (ret)
+			goto out_free_conf;
+	}
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		pr_err("md/raid10:%s: not enough operational mirrors.\n",
@@ -4175,11 +4149,7 @@ static int raid10_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto out_free_conf;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	return 0;
@@ -4189,7 +4159,7 @@ out_free_conf:
 	raid10_free_conf(conf);
 	mddev->private = NULL;
 out:
-	return -EIO;
+	return ret;
 }
 
 static void raid10_free(struct mddev *mddev, void *priv)
@@ -4573,16 +4543,8 @@ out:
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		ret = -EAGAIN;
-		goto abort;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 
@@ -4966,8 +4928,7 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	if (conf->mddev->queue)
-		raid10_set_io_opt(conf);
+	mddev_update_io_opt(conf->mddev, raid10_nr_stripes(conf));
 	conf->fullsync = 0;
 }
 
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index da4ba736c4f0..a70cbec12ed0 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1393,7 +1393,8 @@ int ppl_init_log(struct r5conf *conf)
 		ppl_conf->signature = ~crc32c_le(~0, mddev->uuid, sizeof(mddev->uuid));
 		ppl_conf->block_size = 512;
 	} else {
-		ppl_conf->block_size = queue_logical_block_size(mddev->queue);
+		ppl_conf->block_size =
+			queue_logical_block_size(mddev->gendisk->queue);
 	}
 
 	for (i = 0; i < ppl_conf->count; i++) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8497880135ee..d874abfc1836 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,6 +36,7 @@
  */
 
 #include <linux/blkdev.h>
+#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
@@ -760,6 +761,7 @@ enum stripe_result {
 	STRIPE_RETRY,
 	STRIPE_SCHEDULE_AND_RETRY,
 	STRIPE_FAIL,
+	STRIPE_WAIT_RESHAPE,
 };
 
 struct stripe_request_ctx {
@@ -1210,10 +1212,8 @@ again:
 		 */
 		while (op_is_write(op) && rdev &&
 		       test_bit(WriteErrorSeen, &rdev->flags)) {
-			sector_t first_bad;
-			int bad_sectors;
-			int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					      &first_bad, &bad_sectors);
+			int bad = rdev_has_badblock(rdev, sh->sector,
+						    RAID5_STRIPE_SECTORS(conf));
 			if (!bad)
 				break;
 
@@ -1295,10 +1295,7 @@ again:
 			if (rrdev)
 				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
 
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(bi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, bi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, bi);
 			else
@@ -1342,10 +1339,7 @@ again:
 			 */
 			if (op == REQ_OP_DISCARD)
 				rbi->bi_vcnt = 0;
-			if (conf->mddev->gendisk)
-				trace_block_bio_remap(rbi,
-						disk_devt(conf->mddev->gendisk),
-						sh->dev[i].sector);
+			mddev_trace_remap(conf->mddev, rbi, sh->dev[i].sector);
 			if (should_defer && op_is_write(op))
 				bio_list_add(&pending_bios, rbi);
 			else
@@ -2412,7 +2406,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	atomic_inc(&conf->active_stripes);
 
 	raid5_release_stripe(sh);
-	conf->max_nr_stripes++;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1);
 	return 1;
 }
 
@@ -2422,12 +2416,12 @@ static int grow_stripes(struct r5conf *conf, int num)
 	size_t namelen = sizeof(conf->cache_name[0]);
 	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
-	if (conf->mddev->gendisk)
+	if (mddev_is_dm(conf->mddev))
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%s", conf->level, mdname(conf->mddev));
+			"raid%d-%p", conf->level, conf->mddev);
 	else
 		snprintf(conf->cache_name[0], namelen,
-			"raid%d-%p", conf->level, conf->mddev);
+			"raid%d-%s", conf->level, mdname(conf->mddev));
 	snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]);
 
 	conf->active_name = 0;
@@ -2707,7 +2701,7 @@ static int drop_one_stripe(struct r5conf *conf)
 	shrink_buffers(sh);
 	free_stripe(conf->slab_cache, sh);
 	atomic_dec(&conf->active_stripes);
-	conf->max_nr_stripes--;
+	WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1);
 	return 1;
 }
 
@@ -2855,8 +2849,6 @@ static void raid5_end_write_request(struct bio *bi)
 	struct r5conf *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	struct md_rdev *rdev;
-	sector_t first_bad;
-	int bad_sectors;
 	int replacement = 0;
 
 	for (i = 0 ; i < disks; i++) {
@@ -2888,9 +2880,8 @@ static void raid5_end_write_request(struct bio *bi)
 	if (replacement) {
 		if (bi->bi_status)
 			md_error(conf->mddev, rdev);
-		else if (is_badblock(rdev, sh->sector,
-				     RAID5_STRIPE_SECTORS(conf),
-				     &first_bad, &bad_sectors))
+		else if (rdev_has_badblock(rdev, sh->sector,
+					   RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (bi->bi_status) {
@@ -2900,9 +2891,8 @@ static void raid5_end_write_request(struct bio *bi)
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
 				set_bit(MD_RECOVERY_NEEDED,
 					&rdev->mddev->recovery);
-		} else if (is_badblock(rdev, sh->sector,
-				       RAID5_STRIPE_SECTORS(conf),
-				       &first_bad, &bad_sectors)) {
+		} else if (rdev_has_badblock(rdev, sh->sector,
+					     RAID5_STRIPE_SECTORS(conf))) {
 			set_bit(R5_MadeGood, &sh->dev[i].flags);
 			if (test_bit(R5_ReadError, &sh->dev[i].flags))
 				/* That was a successful write so make
@@ -4205,10 +4195,9 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 	set_bit(STRIPE_HANDLE, &sh->state);
 	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) {
 		/* prefer read-modify-write, but need to get some data */
-		if (conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue,
-					  "raid5 rmw %llu %d",
-					  (unsigned long long)sh->sector, rmw);
+		mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d",
+				sh->sector, rmw);
+
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (test_bit(R5_InJournal, &dev->flags) &&
@@ -4285,10 +4274,11 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 					set_bit(STRIPE_DELAYED, &sh->state);
 			}
 		}
-		if (rcw && conf->mddev->queue)
-			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
-					  (unsigned long long)sh->sector,
-					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
+		if (rcw && !mddev_is_dm(conf->mddev))
+			blk_add_trace_msg(conf->mddev->gendisk->queue,
+				"raid5 rcw %llu %d %d %d",
+				(unsigned long long)sh->sector, rcw, qread,
+				test_bit(STRIPE_DELAYED, &sh->state));
 	}
 
 	if (rcw > disks && rmw > disks &&
@@ -4674,8 +4664,6 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 	/* Now to look around and see what can be done */
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
-		sector_t first_bad;
-		int bad_sectors;
 		int is_bad = 0;
 
 		dev = &sh->dev[i];
@@ -4719,8 +4707,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		rdev = conf->disks[i].replacement;
 		if (rdev && !test_bit(Faulty, &rdev->flags) &&
 		    rdev->recovery_offset >= sh->sector + RAID5_STRIPE_SECTORS(conf) &&
-		    !is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-				 &first_bad, &bad_sectors))
+		    !rdev_has_badblock(rdev, sh->sector,
+				       RAID5_STRIPE_SECTORS(conf)))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
 			if (rdev && !test_bit(Faulty, &rdev->flags))
@@ -4733,8 +4721,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (rdev && test_bit(Faulty, &rdev->flags))
 			rdev = NULL;
 		if (rdev) {
-			is_bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
-					     &first_bad, &bad_sectors);
+			is_bad = rdev_has_badblock(rdev, sh->sector,
+						   RAID5_STRIPE_SECTORS(conf));
 			if (s->blocked_rdev == NULL
 			    && (test_bit(Blocked, &rdev->flags)
 				|| is_bad < 0)) {
@@ -5463,8 +5451,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct r5conf *conf = mddev->private;
 	struct bio *align_bio;
 	struct md_rdev *rdev;
-	sector_t sector, end_sector, first_bad;
-	int bad_sectors, dd_idx;
+	sector_t sector, end_sector;
+	int dd_idx;
 	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
@@ -5493,8 +5481,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 
 	atomic_inc(&rdev->nr_pending);
 
-	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
-			&bad_sectors)) {
+	if (rdev_has_badblock(rdev, sector, bio_sectors(raid_bio))) {
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
@@ -5530,9 +5517,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 		spin_unlock_irq(&conf->device_lock);
 	}
 
-	if (mddev->gendisk)
-		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
-				      raid_bio->bi_iter.bi_sector);
+	mddev_trace_remap(mddev, align_bio, raid_bio->bi_iter.bi_sector);
 	submit_bio_noacct(align_bio);
 	return 1;
 }
@@ -5701,8 +5686,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 	}
 	release_inactive_stripe_list(conf, cb->temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
-	if (mddev->queue)
-		trace_block_unplug(mddev->queue, cnt, !from_schedule);
+	if (!mddev_is_dm(mddev))
+		trace_block_unplug(mddev->gendisk->queue, cnt, !from_schedule);
 	kfree(cb);
 }
 
@@ -5946,7 +5931,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 			if (ahead_of_reshape(mddev, logical_sector,
 					     conf->reshape_safe)) {
 				spin_unlock_irq(&conf->device_lock);
-				return STRIPE_SCHEDULE_AND_RETRY;
+				ret = STRIPE_SCHEDULE_AND_RETRY;
+				goto out;
 			}
 		}
 		spin_unlock_irq(&conf->device_lock);
@@ -6025,6 +6011,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
 
 out_release:
 	raid5_release_stripe(sh);
+out:
+	if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) {
+		bi->bi_status = BLK_STS_RESOURCE;
+		ret = STRIPE_WAIT_RESHAPE;
+		pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress");
+	}
 	return ret;
 }
 
@@ -6146,7 +6138,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	while (1) {
 		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
 					  bi);
-		if (res == STRIPE_FAIL)
+		if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
 			break;
 
 		if (res == STRIPE_RETRY)
@@ -6184,6 +6176,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 
 	if (rw == WRITE)
 		md_write_end(mddev);
+	if (res == STRIPE_WAIT_RESHAPE) {
+		md_free_cloned_bio(bi);
+		return false;
+	}
+
 	bio_endio(bi);
 	return true;
 }
@@ -6773,7 +6770,18 @@ static void raid5d(struct md_thread *thread)
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
+
+			/*
+			 * Waiting on MD_SB_CHANGE_PENDING below may deadlock
+			 * seeing md_check_recovery() is needed to clear
+			 * the flag when using mdmon.
+			 */
+			continue;
 		}
+
+		wait_event_lock_irq(mddev->sb_wait,
+			!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
+			conf->device_lock);
 	}
 	pr_debug("%d stripes handled\n", handled);
 
@@ -6820,7 +6828,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	if (size <= 16 || size > 32768)
 		return -EINVAL;
 
-	conf->min_nr_stripes = size;
+	WRITE_ONCE(conf->min_nr_stripes, size);
 	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
@@ -6832,7 +6840,7 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL)) {
-			conf->min_nr_stripes = conf->max_nr_stripes;
+			WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes);
 			result = -ENOMEM;
 			break;
 		}
@@ -6967,10 +6975,8 @@ raid5_store_stripe_size(struct mddev  *mddev, const char *page, size_t len)
 	pr_debug("md/raid: change stripe_size from %lu to %lu\n",
 			conf->stripe_size, new);
 
-	if (mddev->sync_thread ||
-		test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-		mddev->reshape_position != MaxSector ||
-		mddev->sysfs_active) {
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	    mddev->reshape_position != MaxSector || mddev->sysfs_active) {
 		err = -EBUSY;
 		goto out_unlock;
 	}
@@ -7084,7 +7090,7 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
-		struct request_queue *q = mddev->queue;
+		struct request_queue *q = mddev->gendisk->queue;
 
 		conf->skip_copy = new;
 		if (new)
@@ -7390,11 +7396,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink,
 				       struct shrink_control *sc)
 {
 	struct r5conf *conf = shrink->private_data;
+	int max_stripes = READ_ONCE(conf->max_nr_stripes);
+	int min_stripes = READ_ONCE(conf->min_nr_stripes);
 
-	if (conf->max_nr_stripes < conf->min_nr_stripes)
+	if (max_stripes < min_stripes)
 		/* unlikely, but not impossible */
 		return 0;
-	return conf->max_nr_stripes - conf->min_nr_stripes;
+	return max_stripes - min_stripes;
 }
 
 static struct r5conf *setup_conf(struct mddev *mddev)
@@ -7684,10 +7692,65 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
-static void raid5_set_io_opt(struct r5conf *conf)
+static int raid5_set_limits(struct mddev *mddev)
 {
-	blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) *
-			 (conf->raid_disks - conf->max_degraded));
+	struct r5conf *conf = mddev->private;
+	struct queue_limits lim;
+	int data_disks, stripe;
+	struct md_rdev *rdev;
+
+	/*
+	 * The read-ahead size must cover two whole stripes, which is
+	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices.
+	 */
+	data_disks = conf->previous_raid_disks - conf->max_degraded;
+
+	/*
+	 * We can only discard a whole stripe. It doesn't make sense to
+	 * discard data disk but write parity disk
+	 */
+	stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
+
+	blk_set_stacking_limits(&lim);
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
+	lim.raid_partial_stripes_expensive = 1;
+	lim.discard_granularity = stripe;
+	lim.max_write_zeroes_sectors = 0;
+	mddev_stack_rdev_limits(mddev, &lim);
+	rdev_for_each(rdev, mddev)
+		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
+				mddev->gendisk->disk_name);
+
+	/*
+	 * Zeroing is required for discard, otherwise data could be lost.
+	 *
+	 * Consider a scenario: discard a stripe (the stripe could be
+	 * inconsistent if discard_zeroes_data is 0); write one disk of the
+	 * stripe (the stripe could be inconsistent again depending on which
+	 * disks are used to calculate parity); the disk is broken; The stripe
+	 * data of this disk is lost.
+	 *
+	 * We only allow DISCARD if the sysadmin has confirmed that only safe
+	 * devices are in use by setting a module parameter.  A better idea
+	 * might be to turn DISCARD into WRITE_ZEROES requests, as that is
+	 * required to be safe.
+	 */
+	if (!devices_handle_discard_safely ||
+	    lim.max_discard_sectors < (stripe >> 9) ||
+	    lim.discard_granularity < stripe)
+		lim.max_hw_discard_sectors = 0;
+
+	/*
+	 * Requests require having a bitmap for each stripe.
+	 * Limit the max sectors based on this.
+	 */
+	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+
+	/* No restrictions on the number of segments in the request */
+	lim.max_segments = USHRT_MAX;
+
+	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
 static int raid5_run(struct mddev *mddev)
@@ -7700,6 +7763,7 @@ static int raid5_run(struct mddev *mddev)
 	int i;
 	long long min_offset_diff = 0;
 	int first = 1;
+	int ret = -EIO;
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7936,11 +8000,7 @@ static int raid5_run(struct mddev *mddev)
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-		rcu_assign_pointer(mddev->sync_thread,
-			md_register_thread(md_do_sync, mddev, "reshape"));
-		if (!mddev->sync_thread)
-			goto abort;
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 
 	/* Ok, everything is just fine now */
@@ -7952,66 +8012,10 @@ static int raid5_run(struct mddev *mddev)
 			mdname(mddev));
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
-	if (mddev->queue) {
-		int chunk_size;
-		/* read-ahead size must cover two whole stripes, which
-		 * is 2 * (datadisks) * chunksize where 'n' is the
-		 * number of raid devices
-		 */
-		int data_disks = conf->previous_raid_disks - conf->max_degraded;
-		int stripe = data_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		chunk_size = mddev->chunk_sectors << 9;
-		blk_queue_io_min(mddev->queue, chunk_size);
-		raid5_set_io_opt(conf);
-		mddev->queue->limits.raid_partial_stripes_expensive = 1;
-		/*
-		 * We can only discard a whole stripe. It doesn't make sense to
-		 * discard data disk but write parity disk
-		 */
-		stripe = stripe * PAGE_SIZE;
-		stripe = roundup_pow_of_two(stripe);
-		mddev->queue->limits.discard_granularity = stripe;
-
-		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->new_data_offset << 9);
-		}
-
-		/*
-		 * zeroing is required, otherwise data
-		 * could be lost. Consider a scenario: discard a stripe
-		 * (the stripe could be inconsistent if
-		 * discard_zeroes_data is 0); write one disk of the
-		 * stripe (the stripe could be inconsistent again
-		 * depending on which disks are used to calculate
-		 * parity); the disk is broken; The stripe data of this
-		 * disk is lost.
-		 *
-		 * We only allow DISCARD if the sysadmin has confirmed that
-		 * only safe devices are in use by setting a module parameter.
-		 * A better idea might be to turn DISCARD into WRITE_ZEROES
-		 * requests, as that is required to be safe.
-		 */
-		if (!devices_handle_discard_safely ||
-		    mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
-		    mddev->queue->limits.discard_granularity < stripe)
-			blk_queue_max_discard_sectors(mddev->queue, 0);
-
-		/*
-		 * Requests require having a bitmap for each stripe.
-		 * Limit the max sectors based on this.
-		 */
-		blk_queue_max_hw_sectors(mddev->queue,
-			RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf));
-
-		/* No restrictions on the number of segments in the request */
-		blk_queue_max_segments(mddev->queue, USHRT_MAX);
+	if (!mddev_is_dm(mddev)) {
+		ret = raid5_set_limits(mddev);
+		if (ret)
+			goto abort;
 	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
@@ -8024,7 +8028,7 @@ abort:
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	return -EIO;
+	return ret;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -8506,29 +8510,8 @@ static int raid5_start_reshape(struct mddev *mddev)
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	rcu_assign_pointer(mddev->sync_thread,
-			   md_register_thread(md_do_sync, mddev, "reshape"));
-	if (!mddev->sync_thread) {
-		mddev->recovery = 0;
-		spin_lock_irq(&conf->device_lock);
-		write_seqcount_begin(&conf->gen_lock);
-		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		mddev->new_chunk_sectors =
-			conf->chunk_sectors = conf->prev_chunk_sectors;
-		mddev->new_layout = conf->algorithm = conf->prev_algo;
-		rdev_for_each(rdev, mddev)
-			rdev->new_data_offset = rdev->data_offset;
-		smp_wmb();
-		conf->generation --;
-		conf->reshape_progress = MaxSector;
-		mddev->reshape_position = MaxSector;
-		write_seqcount_end(&conf->gen_lock);
-		spin_unlock_irq(&conf->device_lock);
-		return -EAGAIN;
-	}
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	conf->reshape_checkpoint = jiffies;
-	md_wakeup_thread(mddev->sync_thread);
 	md_new_event();
 	return 0;
 }
@@ -8556,8 +8539,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		if (conf->mddev->queue)
-			raid5_set_io_opt(conf);
+		mddev_update_io_opt(conf->mddev,
+			conf->raid_disks - conf->max_degraded);
 	}
 }
 
@@ -8934,6 +8917,18 @@ static int raid5_start(struct mddev *mddev)
 	return r5l_start(conf->log);
 }
 
+/*
+ * This is only used for dm-raid456, caller already frozen sync_thread, hence
+ * if rehsape is still in progress, io that is waiting for reshape can never be
+ * done now, hence wake up and handle those IO.
+ */
+static void raid5_prepare_suspend(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+
+	wake_up(&conf->wait_for_overlap);
+}
+
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -8957,6 +8952,7 @@ static struct md_personality raid6_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 static struct md_personality raid5_personality =
 {
@@ -8981,6 +8977,7 @@ static struct md_personality raid5_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static struct md_personality raid4_personality =
@@ -9006,6 +9003,7 @@ static struct md_personality raid4_personality =
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.prepare_suspend = raid5_prepare_suspend,
 };
 
 static int __init raid5_init(void)
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
index aebd3c12020b..c381c22135a2 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
@@ -725,6 +725,9 @@ irqreturn_t rkisp1_capture_isr(int irq, void *ctx)
 	unsigned int i;
 	u32 status;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_MI_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
index 4b6b28c05b89..b757f75edecf 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
@@ -450,6 +450,7 @@ struct rkisp1_debug {
  * @debug:	   debug params to be exposed on debugfs
  * @info:	   version-specific ISP information
  * @irqs:          IRQ line numbers
+ * @irqs_enabled:  the hardware is enabled and can cause interrupts
  */
 struct rkisp1_device {
 	void __iomem *base_addr;
@@ -471,6 +472,7 @@ struct rkisp1_device {
 	struct rkisp1_debug debug;
 	const struct rkisp1_info *info;
 	int irqs[RKISP1_NUM_IRQS];
+	bool irqs_enabled;
 };
 
 /*
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
index b6e47e2f1b94..4202642e0523 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
@@ -196,6 +196,9 @@ irqreturn_t rkisp1_csi_isr(int irq, void *ctx)
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 	u32 val, status;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
index f96f821a7b50..73cf08a74011 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
@@ -305,6 +305,24 @@ static int __maybe_unused rkisp1_runtime_suspend(struct device *dev)
 {
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 
+	rkisp1->irqs_enabled = false;
+	/* Make sure the IRQ handler will see the above */
+	mb();
+
+	/*
+	 * Wait until any running IRQ handler has returned. The IRQ handler
+	 * may get called even after this (as it's a shared interrupt line)
+	 * but the 'irqs_enabled' flag will make the handler return immediately.
+	 */
+	for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) {
+		if (rkisp1->irqs[il] == -1)
+			continue;
+
+		/* Skip if the irq line is the same as previous */
+		if (il == 0 || rkisp1->irqs[il - 1] != rkisp1->irqs[il])
+			synchronize_irq(rkisp1->irqs[il]);
+	}
+
 	clk_bulk_disable_unprepare(rkisp1->clk_size, rkisp1->clks);
 	return pinctrl_pm_select_sleep_state(dev);
 }
@@ -321,6 +339,10 @@ static int __maybe_unused rkisp1_runtime_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	rkisp1->irqs_enabled = true;
+	/* Make sure the IRQ handler will see the above */
+	mb();
+
 	return 0;
 }
 
@@ -559,7 +581,7 @@ static int rkisp1_probe(struct platform_device *pdev)
 				rkisp1->irqs[il] = irq;
 		}
 
-		ret = devm_request_irq(dev, irq, info->isrs[i].isr, 0,
+		ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED,
 				       dev_driver_string(dev), dev);
 		if (ret) {
 			dev_err(dev, "request irq failed: %d\n", ret);
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
index f00873d31c42..78a1f7a1499b 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
@@ -976,6 +976,9 @@ irqreturn_t rkisp1_isp_isr(int irq, void *ctx)
 	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
 	u32 status, isp_err;
 
+	if (!rkisp1->irqs_enabled)
+		return IRQ_NONE;
+
 	status = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS);
 	if (!status)
 		return IRQ_NONE;
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index 2afe67ffa285..74d69ce22a33 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -319,6 +319,7 @@ config IR_PWM_TX
 	tristate "PWM IR transmitter"
 	depends on LIRC
 	depends on PWM
+	depends on HIGH_RES_TIMERS
 	depends on OF
 	help
 	   Say Y if you want to use a PWM based IR transmitter. This is
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fe17c7f98e81..52d82cbe7685 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (attr->attach_flags)
 		return -EINVAL;
 
-	rcdev = rc_dev_get_from_fd(attr->target_fd);
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
 	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
 
@@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	rcdev = rc_dev_get_from_fd(attr->target_fd);
+	rcdev = rc_dev_get_from_fd(attr->target_fd, true);
 	if (IS_ERR(rcdev)) {
 		bpf_prog_put(prog);
 		return PTR_ERR(rcdev);
@@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (attr->query.query_flags)
 		return -EINVAL;
 
-	rcdev = rc_dev_get_from_fd(attr->query.target_fd);
+	rcdev = rc_dev_get_from_fd(attr->query.target_fd, false);
 	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
 
diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c
index 196806709259..69e630d85262 100644
--- a/drivers/media/rc/ir_toy.c
+++ b/drivers/media/rc/ir_toy.c
@@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 			    sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP);
 	if (err) {
 		dev_err(irtoy->dev, "exit sample mode: %d\n", err);
+		kfree(buf);
 		return err;
 	}
 
@@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 			    sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND);
 	if (err) {
 		dev_err(irtoy->dev, "enter sample mode: %d\n", err);
+		kfree(buf);
 		return err;
 	}
 
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index a537734832c5..caad59f76793 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void)
 	unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX);
 }
 
-struct rc_dev *rc_dev_get_from_fd(int fd)
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write)
 {
 	struct fd f = fdget(fd);
 	struct lirc_fh *fh;
@@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (write && !(f.file->f_mode & FMODE_WRITE))
+		return ERR_PTR(-EPERM);
+
 	fh = f.file->private_data;
 	dev = fh->rc;
 
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index ef1e95e1af7f..7df949fc65e2 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev);
 void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc);
 int lirc_register(struct rc_dev *dev);
 void lirc_unregister(struct rc_dev *dev);
-struct rc_dev *rc_dev_get_from_fd(int fd);
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write);
 #else
 static inline int lirc_dev_init(void) { return 0; }
 static inline void lirc_dev_exit(void) {}
diff --git a/drivers/memory/emif.c b/drivers/memory/emif.c
index 434982545be6..8c5ad5c025fa 100644
--- a/drivers/memory/emif.c
+++ b/drivers/memory/emif.c
@@ -72,7 +72,6 @@ static DEFINE_SPINLOCK(emif_lock);
 static unsigned long	irq_state;
 static LIST_HEAD(device_list);
 
-#ifdef CONFIG_DEBUG_FS
 static void do_emif_regdump_show(struct seq_file *s, struct emif_data *emif,
 	struct emif_regs *regs)
 {
@@ -140,31 +139,24 @@ static int emif_mr4_show(struct seq_file *s, void *unused)
 
 DEFINE_SHOW_ATTRIBUTE(emif_mr4);
 
-static int __init_or_module emif_debugfs_init(struct emif_data *emif)
+static void emif_debugfs_init(struct emif_data *emif)
 {
-	emif->debugfs_root = debugfs_create_dir(dev_name(emif->dev), NULL);
-	debugfs_create_file("regcache_dump", S_IRUGO, emif->debugfs_root, emif,
-			    &emif_regdump_fops);
-	debugfs_create_file("mr4", S_IRUGO, emif->debugfs_root, emif,
-			    &emif_mr4_fops);
-	return 0;
-}
-
-static void __exit emif_debugfs_exit(struct emif_data *emif)
-{
-	debugfs_remove_recursive(emif->debugfs_root);
-	emif->debugfs_root = NULL;
-}
-#else
-static inline int __init_or_module emif_debugfs_init(struct emif_data *emif)
-{
-	return 0;
+	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
+		emif->debugfs_root = debugfs_create_dir(dev_name(emif->dev), NULL);
+		debugfs_create_file("regcache_dump", S_IRUGO, emif->debugfs_root, emif,
+				    &emif_regdump_fops);
+		debugfs_create_file("mr4", S_IRUGO, emif->debugfs_root, emif,
+				    &emif_mr4_fops);
+	}
 }
 
-static inline void __exit emif_debugfs_exit(struct emif_data *emif)
+static void emif_debugfs_exit(struct emif_data *emif)
 {
+	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
+		debugfs_remove_recursive(emif->debugfs_root);
+		emif->debugfs_root = NULL;
+	}
 }
-#endif
 
 /*
  * Get bus width used by EMIF. Note that this may be different from the
@@ -679,7 +671,7 @@ static void disable_and_clear_all_interrupts(struct emif_data *emif)
 	clear_all_interrupts(emif);
 }
 
-static int __init_or_module setup_interrupts(struct emif_data *emif, u32 irq)
+static int setup_interrupts(struct emif_data *emif, u32 irq)
 {
 	u32		interrupts, type;
 	void __iomem	*base = emif->base;
@@ -710,7 +702,7 @@ static int __init_or_module setup_interrupts(struct emif_data *emif, u32 irq)
 
 }
 
-static void __init_or_module emif_onetime_settings(struct emif_data *emif)
+static void emif_onetime_settings(struct emif_data *emif)
 {
 	u32				pwr_mgmt_ctrl, zq, temp_alert_cfg;
 	void __iomem			*base = emif->base;
@@ -834,8 +826,7 @@ static int is_custom_config_valid(struct emif_custom_configs *cust_cfgs,
 	return valid;
 }
 
-#if defined(CONFIG_OF)
-static void __init_or_module of_get_custom_configs(struct device_node *np_emif,
+static void of_get_custom_configs(struct device_node *np_emif,
 		struct emif_data *emif)
 {
 	struct emif_custom_configs	*cust_cfgs = NULL;
@@ -884,7 +875,7 @@ static void __init_or_module of_get_custom_configs(struct device_node *np_emif,
 	emif->plat_data->custom_configs = cust_cfgs;
 }
 
-static void __init_or_module of_get_ddr_info(struct device_node *np_emif,
+static void of_get_ddr_info(struct device_node *np_emif,
 		struct device_node *np_ddr,
 		struct ddr_device_info *dev_info)
 {
@@ -918,7 +909,7 @@ static void __init_or_module of_get_ddr_info(struct device_node *np_emif,
 		dev_info->io_width = __fls(io_width) - 1;
 }
 
-static struct emif_data * __init_or_module of_get_memory_device_details(
+static struct emif_data *of_get_memory_device_details(
 		struct device_node *np_emif, struct device *dev)
 {
 	struct emif_data		*emif = NULL;
@@ -991,16 +982,7 @@ out:
 	return emif;
 }
 
-#else
-
-static struct emif_data * __init_or_module of_get_memory_device_details(
-		struct device_node *np_emif, struct device *dev)
-{
-	return NULL;
-}
-#endif
-
-static struct emif_data *__init_or_module get_device_details(
+static struct emif_data *get_device_details(
 		struct platform_device *pdev)
 {
 	u32				size;
@@ -1104,7 +1086,7 @@ error:
 	return NULL;
 }
 
-static int __init_or_module emif_probe(struct platform_device *pdev)
+static int emif_probe(struct platform_device *pdev)
 {
 	struct emif_data	*emif;
 	int			irq, ret;
@@ -1159,7 +1141,7 @@ error:
 	return -ENODEV;
 }
 
-static void __exit emif_remove(struct platform_device *pdev)
+static void emif_remove(struct platform_device *pdev)
 {
 	struct emif_data *emif = platform_get_drvdata(pdev);
 
@@ -1183,7 +1165,8 @@ MODULE_DEVICE_TABLE(of, emif_of_match);
 #endif
 
 static struct platform_driver emif_driver = {
-	.remove_new	= __exit_p(emif_remove),
+	.probe		= emif_probe,
+	.remove_new	= emif_remove,
 	.shutdown	= emif_shutdown,
 	.driver = {
 		.name = "emif",
@@ -1191,7 +1174,7 @@ static struct platform_driver emif_driver = {
 	},
 };
 
-module_platform_driver_probe(emif_driver, emif_probe);
+module_platform_driver(emif_driver);
 
 MODULE_DESCRIPTION("TI EMIF SDRAM Controller Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/memory/stm32-fmc2-ebi.c b/drivers/memory/stm32-fmc2-ebi.c
index 47d0ea5f1616..1c63eeacd071 100644
--- a/drivers/memory/stm32-fmc2-ebi.c
+++ b/drivers/memory/stm32-fmc2-ebi.c
@@ -11,6 +11,7 @@
 #include <linux/of_platform.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
 
@@ -20,8 +21,15 @@
 #define FMC2_BCR(x)			((x) * 0x8 + FMC2_BCR1)
 #define FMC2_BTR(x)			((x) * 0x8 + FMC2_BTR1)
 #define FMC2_PCSCNTR			0x20
+#define FMC2_CFGR			0x20
+#define FMC2_SR				0x84
 #define FMC2_BWTR1			0x104
 #define FMC2_BWTR(x)			((x) * 0x8 + FMC2_BWTR1)
+#define FMC2_SECCFGR			0x300
+#define FMC2_CIDCFGR0			0x30c
+#define FMC2_CIDCFGR(x)			((x) * 0x8 + FMC2_CIDCFGR0)
+#define FMC2_SEMCR0			0x310
+#define FMC2_SEMCR(x)			((x) * 0x8 + FMC2_SEMCR0)
 
 /* Register: FMC2_BCR1 */
 #define FMC2_BCR1_CCLKEN		BIT(20)
@@ -42,6 +50,7 @@
 #define FMC2_BCR_ASYNCWAIT		BIT(15)
 #define FMC2_BCR_CPSIZE			GENMASK(18, 16)
 #define FMC2_BCR_CBURSTRW		BIT(19)
+#define FMC2_BCR_CSCOUNT		GENMASK(21, 20)
 #define FMC2_BCR_NBLSET			GENMASK(23, 22)
 
 /* Register: FMC2_BTRx/FMC2_BWTRx */
@@ -58,8 +67,28 @@
 #define FMC2_PCSCNTR_CSCOUNT		GENMASK(15, 0)
 #define FMC2_PCSCNTR_CNTBEN(x)		BIT((x) + 16)
 
+/* Register: FMC2_CFGR */
+#define FMC2_CFGR_CLKDIV		GENMASK(19, 16)
+#define FMC2_CFGR_CCLKEN		BIT(20)
+#define FMC2_CFGR_FMC2EN		BIT(31)
+
+/* Register: FMC2_SR */
+#define FMC2_SR_ISOST			GENMASK(1, 0)
+
+/* Register: FMC2_CIDCFGR */
+#define FMC2_CIDCFGR_CFEN		BIT(0)
+#define FMC2_CIDCFGR_SEMEN		BIT(1)
+#define FMC2_CIDCFGR_SCID		GENMASK(6, 4)
+#define FMC2_CIDCFGR_SEMWLC1		BIT(17)
+
+/* Register: FMC2_SEMCR */
+#define FMC2_SEMCR_SEM_MUTEX		BIT(0)
+#define FMC2_SEMCR_SEMCID		GENMASK(6, 4)
+
 #define FMC2_MAX_EBI_CE			4
 #define FMC2_MAX_BANKS			5
+#define FMC2_MAX_RESOURCES		6
+#define FMC2_CID1			1
 
 #define FMC2_BCR_CPSIZE_0		0x0
 #define FMC2_BCR_CPSIZE_128		0x1
@@ -74,6 +103,11 @@
 #define FMC2_BCR_MTYP_PSRAM		0x1
 #define FMC2_BCR_MTYP_NOR		0x2
 
+#define FMC2_BCR_CSCOUNT_0		0x0
+#define FMC2_BCR_CSCOUNT_1		0x1
+#define FMC2_BCR_CSCOUNT_64		0x2
+#define FMC2_BCR_CSCOUNT_256		0x3
+
 #define FMC2_BXTR_EXTMOD_A		0x0
 #define FMC2_BXTR_EXTMOD_B		0x1
 #define FMC2_BXTR_EXTMOD_C		0x2
@@ -88,6 +122,7 @@
 #define FMC2_BTR_CLKDIV_MAX		0xf
 #define FMC2_BTR_DATLAT_MAX		0xf
 #define FMC2_PCSCNTR_CSCOUNT_MAX	0xff
+#define FMC2_CFGR_CLKDIV_MAX		0xf
 
 enum stm32_fmc2_ebi_bank {
 	FMC2_EBI1 = 0,
@@ -101,7 +136,8 @@ enum stm32_fmc2_ebi_register_type {
 	FMC2_REG_BCR = 1,
 	FMC2_REG_BTR,
 	FMC2_REG_BWTR,
-	FMC2_REG_PCSCNTR
+	FMC2_REG_PCSCNTR,
+	FMC2_REG_CFGR
 };
 
 enum stm32_fmc2_ebi_transaction_type {
@@ -132,16 +168,42 @@ enum stm32_fmc2_ebi_cpsize {
 	FMC2_CPSIZE_1024 = 1024
 };
 
+enum stm32_fmc2_ebi_cscount {
+	FMC2_CSCOUNT_0 = 0,
+	FMC2_CSCOUNT_1 = 1,
+	FMC2_CSCOUNT_64 = 64,
+	FMC2_CSCOUNT_256 = 256
+};
+
+struct stm32_fmc2_ebi;
+
+struct stm32_fmc2_ebi_data {
+	const struct stm32_fmc2_prop *child_props;
+	unsigned int nb_child_props;
+	u32 fmc2_enable_reg;
+	u32 fmc2_enable_bit;
+	int (*nwait_used_by_ctrls)(struct stm32_fmc2_ebi *ebi);
+	void (*set_setup)(struct stm32_fmc2_ebi *ebi);
+	int (*save_setup)(struct stm32_fmc2_ebi *ebi);
+	int (*check_rif)(struct stm32_fmc2_ebi *ebi, u32 resource);
+	void (*put_sems)(struct stm32_fmc2_ebi *ebi);
+	void (*get_sems)(struct stm32_fmc2_ebi *ebi);
+};
+
 struct stm32_fmc2_ebi {
 	struct device *dev;
 	struct clk *clk;
 	struct regmap *regmap;
+	const struct stm32_fmc2_ebi_data *data;
 	u8 bank_assigned;
+	u8 sem_taken;
+	bool access_granted;
 
 	u32 bcr[FMC2_MAX_EBI_CE];
 	u32 btr[FMC2_MAX_EBI_CE];
 	u32 bwtr[FMC2_MAX_EBI_CE];
 	u32 pcscntr;
+	u32 cfgr;
 };
 
 /*
@@ -181,8 +243,11 @@ static int stm32_fmc2_ebi_check_mux(struct stm32_fmc2_ebi *ebi,
 				    int cs)
 {
 	u32 bcr;
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
 	if (bcr & FMC2_BCR_MTYP)
 		return 0;
@@ -195,8 +260,11 @@ static int stm32_fmc2_ebi_check_waitcfg(struct stm32_fmc2_ebi *ebi,
 					int cs)
 {
 	u32 bcr, val = FIELD_PREP(FMC2_BCR_MTYP, FMC2_BCR_MTYP_NOR);
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
 	if ((bcr & FMC2_BCR_MTYP) == val && bcr & FMC2_BCR_BURSTEN)
 		return 0;
@@ -209,8 +277,11 @@ static int stm32_fmc2_ebi_check_sync_trans(struct stm32_fmc2_ebi *ebi,
 					   int cs)
 {
 	u32 bcr;
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
 	if (bcr & FMC2_BCR_BURSTEN)
 		return 0;
@@ -218,13 +289,43 @@ static int stm32_fmc2_ebi_check_sync_trans(struct stm32_fmc2_ebi *ebi,
 	return -EINVAL;
 }
 
+static int stm32_fmc2_ebi_mp25_check_cclk(struct stm32_fmc2_ebi *ebi,
+					  const struct stm32_fmc2_prop *prop,
+					  int cs)
+{
+	if (!ebi->access_granted)
+		return -EACCES;
+
+	return stm32_fmc2_ebi_check_sync_trans(ebi, prop, cs);
+}
+
+static int stm32_fmc2_ebi_mp25_check_clk_period(struct stm32_fmc2_ebi *ebi,
+						const struct stm32_fmc2_prop *prop,
+						int cs)
+{
+	u32 cfgr;
+	int ret;
+
+	ret = regmap_read(ebi->regmap, FMC2_CFGR, &cfgr);
+	if (ret)
+		return ret;
+
+	if (cfgr & FMC2_CFGR_CCLKEN && !ebi->access_granted)
+		return -EACCES;
+
+	return stm32_fmc2_ebi_check_sync_trans(ebi, prop, cs);
+}
+
 static int stm32_fmc2_ebi_check_async_trans(struct stm32_fmc2_ebi *ebi,
 					    const struct stm32_fmc2_prop *prop,
 					    int cs)
 {
 	u32 bcr;
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
 	if (!(bcr & FMC2_BCR_BURSTEN) || !(bcr & FMC2_BCR_CBURSTRW))
 		return 0;
@@ -237,8 +338,11 @@ static int stm32_fmc2_ebi_check_cpsize(struct stm32_fmc2_ebi *ebi,
 				       int cs)
 {
 	u32 bcr, val = FIELD_PREP(FMC2_BCR_MTYP, FMC2_BCR_MTYP_PSRAM);
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
 	if ((bcr & FMC2_BCR_MTYP) == val && bcr & FMC2_BCR_BURSTEN)
 		return 0;
@@ -251,12 +355,18 @@ static int stm32_fmc2_ebi_check_address_hold(struct stm32_fmc2_ebi *ebi,
 					     int cs)
 {
 	u32 bcr, bxtr, val = FIELD_PREP(FMC2_BXTR_ACCMOD, FMC2_BXTR_EXTMOD_D);
+	int ret;
+
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
 	if (prop->reg_type == FMC2_REG_BWTR)
-		regmap_read(ebi->regmap, FMC2_BWTR(cs), &bxtr);
+		ret = regmap_read(ebi->regmap, FMC2_BWTR(cs), &bxtr);
 	else
-		regmap_read(ebi->regmap, FMC2_BTR(cs), &bxtr);
+		ret = regmap_read(ebi->regmap, FMC2_BTR(cs), &bxtr);
+	if (ret)
+		return ret;
 
 	if ((!(bcr & FMC2_BCR_BURSTEN) || !(bcr & FMC2_BCR_CBURSTRW)) &&
 	    ((bxtr & FMC2_BXTR_ACCMOD) == val || bcr & FMC2_BCR_MUXEN))
@@ -270,12 +380,19 @@ static int stm32_fmc2_ebi_check_clk_period(struct stm32_fmc2_ebi *ebi,
 					   int cs)
 {
 	u32 bcr, bcr1;
+	int ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
-	if (cs)
-		regmap_read(ebi->regmap, FMC2_BCR1, &bcr1);
-	else
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
+
+	if (cs) {
+		ret = regmap_read(ebi->regmap, FMC2_BCR1, &bcr1);
+		if (ret)
+			return ret;
+	} else {
 		bcr1 = bcr;
+	}
 
 	if (bcr & FMC2_BCR_BURSTEN && (!cs || !(bcr1 & FMC2_BCR1_CCLKEN)))
 		return 0;
@@ -307,18 +424,48 @@ static u32 stm32_fmc2_ebi_ns_to_clk_period(struct stm32_fmc2_ebi *ebi,
 {
 	u32 nb_clk_cycles = stm32_fmc2_ebi_ns_to_clock_cycles(ebi, cs, setup);
 	u32 bcr, btr, clk_period;
+	int ret;
+
+	ret = regmap_read(ebi->regmap, FMC2_BCR1, &bcr);
+	if (ret)
+		return ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR1, &bcr);
 	if (bcr & FMC2_BCR1_CCLKEN || !cs)
-		regmap_read(ebi->regmap, FMC2_BTR1, &btr);
+		ret = regmap_read(ebi->regmap, FMC2_BTR1, &btr);
 	else
-		regmap_read(ebi->regmap, FMC2_BTR(cs), &btr);
+		ret = regmap_read(ebi->regmap, FMC2_BTR(cs), &btr);
+	if (ret)
+		return ret;
 
 	clk_period = FIELD_GET(FMC2_BTR_CLKDIV, btr) + 1;
 
 	return DIV_ROUND_UP(nb_clk_cycles, clk_period);
 }
 
+static u32 stm32_fmc2_ebi_mp25_ns_to_clk_period(struct stm32_fmc2_ebi *ebi,
+						int cs, u32 setup)
+{
+	u32 nb_clk_cycles = stm32_fmc2_ebi_ns_to_clock_cycles(ebi, cs, setup);
+	u32 cfgr, btr, clk_period;
+	int ret;
+
+	ret = regmap_read(ebi->regmap, FMC2_CFGR, &cfgr);
+	if (ret)
+		return ret;
+
+	if (cfgr & FMC2_CFGR_CCLKEN) {
+		clk_period = FIELD_GET(FMC2_CFGR_CLKDIV, cfgr) + 1;
+	} else {
+		ret = regmap_read(ebi->regmap, FMC2_BTR(cs), &btr);
+		if (ret)
+			return ret;
+
+		clk_period = FIELD_GET(FMC2_BTR_CLKDIV, btr) + 1;
+	}
+
+	return DIV_ROUND_UP(nb_clk_cycles, clk_period);
+}
+
 static int stm32_fmc2_ebi_get_reg(int reg_type, int cs, u32 *reg)
 {
 	switch (reg_type) {
@@ -334,6 +481,9 @@ static int stm32_fmc2_ebi_get_reg(int reg_type, int cs, u32 *reg)
 	case FMC2_REG_PCSCNTR:
 		*reg = FMC2_PCSCNTR;
 		break;
+	case FMC2_REG_CFGR:
+		*reg = FMC2_CFGR;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -571,11 +721,16 @@ static int stm32_fmc2_ebi_set_address_setup(struct stm32_fmc2_ebi *ebi,
 	if (ret)
 		return ret;
 
-	regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+	if (ret)
+		return ret;
+
 	if (prop->reg_type == FMC2_REG_BWTR)
-		regmap_read(ebi->regmap, FMC2_BWTR(cs), &bxtr);
+		ret = regmap_read(ebi->regmap, FMC2_BWTR(cs), &bxtr);
 	else
-		regmap_read(ebi->regmap, FMC2_BTR(cs), &bxtr);
+		ret = regmap_read(ebi->regmap, FMC2_BTR(cs), &bxtr);
+	if (ret)
+		return ret;
 
 	if ((bxtr & FMC2_BXTR_ACCMOD) == val || bcr & FMC2_BCR_MUXEN)
 		val = clamp_val(setup, 1, FMC2_BXTR_ADDSET_MAX);
@@ -675,6 +830,30 @@ static int stm32_fmc2_ebi_set_clk_period(struct stm32_fmc2_ebi *ebi,
 	return 0;
 }
 
+static int stm32_fmc2_ebi_mp25_set_clk_period(struct stm32_fmc2_ebi *ebi,
+					      const struct stm32_fmc2_prop *prop,
+					      int cs, u32 setup)
+{
+	u32 val, cfgr;
+	int ret;
+
+	ret = regmap_read(ebi->regmap, FMC2_CFGR, &cfgr);
+	if (ret)
+		return ret;
+
+	if (cfgr & FMC2_CFGR_CCLKEN) {
+		val = setup ? clamp_val(setup - 1, 1, FMC2_CFGR_CLKDIV_MAX) : 1;
+		val = FIELD_PREP(FMC2_CFGR_CLKDIV, val);
+		regmap_update_bits(ebi->regmap, FMC2_CFGR, FMC2_CFGR_CLKDIV, val);
+	} else {
+		val = setup ? clamp_val(setup - 1, 1, FMC2_BTR_CLKDIV_MAX) : 1;
+		val = FIELD_PREP(FMC2_BTR_CLKDIV, val);
+		regmap_update_bits(ebi->regmap, FMC2_BTR(cs), FMC2_BTR_CLKDIV, val);
+	}
+
+	return 0;
+}
+
 static int stm32_fmc2_ebi_set_data_latency(struct stm32_fmc2_ebi *ebi,
 					   const struct stm32_fmc2_prop *prop,
 					   int cs, u32 setup)
@@ -693,11 +872,14 @@ static int stm32_fmc2_ebi_set_max_low_pulse(struct stm32_fmc2_ebi *ebi,
 					    int cs, u32 setup)
 {
 	u32 old_val, new_val, pcscntr;
+	int ret;
 
 	if (setup < 1)
 		return 0;
 
-	regmap_read(ebi->regmap, FMC2_PCSCNTR, &pcscntr);
+	ret = regmap_read(ebi->regmap, FMC2_PCSCNTR, &pcscntr);
+	if (ret)
+		return ret;
 
 	/* Enable counter for the bank */
 	regmap_update_bits(ebi->regmap, FMC2_PCSCNTR,
@@ -717,6 +899,27 @@ static int stm32_fmc2_ebi_set_max_low_pulse(struct stm32_fmc2_ebi *ebi,
 	return 0;
 }
 
+static int stm32_fmc2_ebi_mp25_set_max_low_pulse(struct stm32_fmc2_ebi *ebi,
+						 const struct stm32_fmc2_prop *prop,
+						 int cs, u32 setup)
+{
+	u32 val;
+
+	if (setup == FMC2_CSCOUNT_0)
+		val = FIELD_PREP(FMC2_BCR_CSCOUNT, FMC2_BCR_CSCOUNT_0);
+	else if (setup == FMC2_CSCOUNT_1)
+		val = FIELD_PREP(FMC2_BCR_CSCOUNT, FMC2_BCR_CSCOUNT_1);
+	else if (setup <= FMC2_CSCOUNT_64)
+		val = FIELD_PREP(FMC2_BCR_CSCOUNT, FMC2_BCR_CSCOUNT_64);
+	else
+		val = FIELD_PREP(FMC2_BCR_CSCOUNT, FMC2_BCR_CSCOUNT_256);
+
+	regmap_update_bits(ebi->regmap, FMC2_BCR(cs),
+			   FMC2_BCR_CSCOUNT, val);
+
+	return 0;
+}
+
 static const struct stm32_fmc2_prop stm32_fmc2_child_props[] = {
 	/* st,fmc2-ebi-cs-trans-type must be the first property */
 	{
@@ -882,6 +1085,275 @@ static const struct stm32_fmc2_prop stm32_fmc2_child_props[] = {
 	},
 };
 
+static const struct stm32_fmc2_prop stm32_fmc2_mp25_child_props[] = {
+	/* st,fmc2-ebi-cs-trans-type must be the first property */
+	{
+		.name = "st,fmc2-ebi-cs-transaction-type",
+		.mprop = true,
+		.set = stm32_fmc2_ebi_set_trans_type,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-cclk-enable",
+		.bprop = true,
+		.reg_type = FMC2_REG_CFGR,
+		.reg_mask = FMC2_CFGR_CCLKEN,
+		.check = stm32_fmc2_ebi_mp25_check_cclk,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-mux-enable",
+		.bprop = true,
+		.reg_type = FMC2_REG_BCR,
+		.reg_mask = FMC2_BCR_MUXEN,
+		.check = stm32_fmc2_ebi_check_mux,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-buswidth",
+		.reset_val = FMC2_BUSWIDTH_16,
+		.set = stm32_fmc2_ebi_set_buswidth,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-waitpol-high",
+		.bprop = true,
+		.reg_type = FMC2_REG_BCR,
+		.reg_mask = FMC2_BCR_WAITPOL,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-waitcfg-enable",
+		.bprop = true,
+		.reg_type = FMC2_REG_BCR,
+		.reg_mask = FMC2_BCR_WAITCFG,
+		.check = stm32_fmc2_ebi_check_waitcfg,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-wait-enable",
+		.bprop = true,
+		.reg_type = FMC2_REG_BCR,
+		.reg_mask = FMC2_BCR_WAITEN,
+		.check = stm32_fmc2_ebi_check_sync_trans,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-asyncwait-enable",
+		.bprop = true,
+		.reg_type = FMC2_REG_BCR,
+		.reg_mask = FMC2_BCR_ASYNCWAIT,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.set = stm32_fmc2_ebi_set_bit_field,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-cpsize",
+		.check = stm32_fmc2_ebi_check_cpsize,
+		.set = stm32_fmc2_ebi_set_cpsize,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-byte-lane-setup-ns",
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_bl_setup,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-address-setup-ns",
+		.reg_type = FMC2_REG_BTR,
+		.reset_val = FMC2_BXTR_ADDSET_MAX,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_address_setup,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-address-hold-ns",
+		.reg_type = FMC2_REG_BTR,
+		.reset_val = FMC2_BXTR_ADDHLD_MAX,
+		.check = stm32_fmc2_ebi_check_address_hold,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_address_hold,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-data-setup-ns",
+		.reg_type = FMC2_REG_BTR,
+		.reset_val = FMC2_BXTR_DATAST_MAX,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_data_setup,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-bus-turnaround-ns",
+		.reg_type = FMC2_REG_BTR,
+		.reset_val = FMC2_BXTR_BUSTURN_MAX + 1,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_bus_turnaround,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-data-hold-ns",
+		.reg_type = FMC2_REG_BTR,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_data_hold,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-clk-period-ns",
+		.reset_val = FMC2_CFGR_CLKDIV_MAX + 1,
+		.check = stm32_fmc2_ebi_mp25_check_clk_period,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_mp25_set_clk_period,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-data-latency-ns",
+		.check = stm32_fmc2_ebi_check_sync_trans,
+		.calculate = stm32_fmc2_ebi_mp25_ns_to_clk_period,
+		.set = stm32_fmc2_ebi_set_data_latency,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-write-address-setup-ns",
+		.reg_type = FMC2_REG_BWTR,
+		.reset_val = FMC2_BXTR_ADDSET_MAX,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_address_setup,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-write-address-hold-ns",
+		.reg_type = FMC2_REG_BWTR,
+		.reset_val = FMC2_BXTR_ADDHLD_MAX,
+		.check = stm32_fmc2_ebi_check_address_hold,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_address_hold,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-write-data-setup-ns",
+		.reg_type = FMC2_REG_BWTR,
+		.reset_val = FMC2_BXTR_DATAST_MAX,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_data_setup,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-write-bus-turnaround-ns",
+		.reg_type = FMC2_REG_BWTR,
+		.reset_val = FMC2_BXTR_BUSTURN_MAX + 1,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_bus_turnaround,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-write-data-hold-ns",
+		.reg_type = FMC2_REG_BWTR,
+		.check = stm32_fmc2_ebi_check_async_trans,
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_set_data_hold,
+	},
+	{
+		.name = "st,fmc2-ebi-cs-max-low-pulse-ns",
+		.calculate = stm32_fmc2_ebi_ns_to_clock_cycles,
+		.set = stm32_fmc2_ebi_mp25_set_max_low_pulse,
+	},
+};
+
+static int stm32_fmc2_ebi_mp25_check_rif(struct stm32_fmc2_ebi *ebi, u32 resource)
+{
+	u32 seccfgr, cidcfgr, semcr;
+	int cid, ret;
+
+	if (resource >= FMC2_MAX_RESOURCES)
+		return -EINVAL;
+
+	ret = regmap_read(ebi->regmap, FMC2_SECCFGR, &seccfgr);
+	if (ret)
+		return ret;
+
+	if (seccfgr & BIT(resource)) {
+		if (resource)
+			dev_err(ebi->dev, "resource %d is configured as secure\n",
+				resource);
+
+		return -EACCES;
+	}
+
+	ret = regmap_read(ebi->regmap, FMC2_CIDCFGR(resource), &cidcfgr);
+	if (ret)
+		return ret;
+
+	if (!(cidcfgr & FMC2_CIDCFGR_CFEN))
+		/* CID filtering is turned off: access granted */
+		return 0;
+
+	if (!(cidcfgr & FMC2_CIDCFGR_SEMEN)) {
+		/* Static CID mode */
+		cid = FIELD_GET(FMC2_CIDCFGR_SCID, cidcfgr);
+		if (cid != FMC2_CID1) {
+			if (resource)
+				dev_err(ebi->dev, "static CID%d set for resource %d\n",
+					cid, resource);
+
+			return -EACCES;
+		}
+
+		return 0;
+	}
+
+	/* Pass-list with semaphore mode */
+	if (!(cidcfgr & FMC2_CIDCFGR_SEMWLC1)) {
+		if (resource)
+			dev_err(ebi->dev, "CID1 is block-listed for resource %d\n",
+				resource);
+
+		return -EACCES;
+	}
+
+	ret = regmap_read(ebi->regmap, FMC2_SEMCR(resource), &semcr);
+	if (ret)
+		return ret;
+
+	if (!(semcr & FMC2_SEMCR_SEM_MUTEX)) {
+		regmap_update_bits(ebi->regmap, FMC2_SEMCR(resource),
+				   FMC2_SEMCR_SEM_MUTEX, FMC2_SEMCR_SEM_MUTEX);
+
+		ret = regmap_read(ebi->regmap, FMC2_SEMCR(resource), &semcr);
+		if (ret)
+			return ret;
+	}
+
+	cid = FIELD_GET(FMC2_SEMCR_SEMCID, semcr);
+	if (cid != FMC2_CID1) {
+		if (resource)
+			dev_err(ebi->dev, "resource %d is already used by CID%d\n",
+				resource, cid);
+
+		return -EACCES;
+	}
+
+	ebi->sem_taken |= BIT(resource);
+
+	return 0;
+}
+
+static void stm32_fmc2_ebi_mp25_put_sems(struct stm32_fmc2_ebi *ebi)
+{
+	unsigned int resource;
+
+	for (resource = 0; resource < FMC2_MAX_RESOURCES; resource++) {
+		if (!(ebi->sem_taken & BIT(resource)))
+			continue;
+
+		regmap_update_bits(ebi->regmap, FMC2_SEMCR(resource),
+				   FMC2_SEMCR_SEM_MUTEX, 0);
+	}
+}
+
+static void stm32_fmc2_ebi_mp25_get_sems(struct stm32_fmc2_ebi *ebi)
+{
+	unsigned int resource;
+
+	for (resource = 0; resource < FMC2_MAX_RESOURCES; resource++) {
+		if (!(ebi->sem_taken & BIT(resource)))
+			continue;
+
+		regmap_update_bits(ebi->regmap, FMC2_SEMCR(resource),
+				   FMC2_SEMCR_SEM_MUTEX, FMC2_SEMCR_SEM_MUTEX);
+	}
+}
+
 static int stm32_fmc2_ebi_parse_prop(struct stm32_fmc2_ebi *ebi,
 				     struct device_node *dev_node,
 				     const struct stm32_fmc2_prop *prop,
@@ -944,17 +1416,48 @@ static void stm32_fmc2_ebi_disable_bank(struct stm32_fmc2_ebi *ebi, int cs)
 	regmap_update_bits(ebi->regmap, FMC2_BCR(cs), FMC2_BCR_MBKEN, 0);
 }
 
-static void stm32_fmc2_ebi_save_setup(struct stm32_fmc2_ebi *ebi)
+static int stm32_fmc2_ebi_save_setup(struct stm32_fmc2_ebi *ebi)
 {
 	unsigned int cs;
+	int ret;
 
 	for (cs = 0; cs < FMC2_MAX_EBI_CE; cs++) {
-		regmap_read(ebi->regmap, FMC2_BCR(cs), &ebi->bcr[cs]);
-		regmap_read(ebi->regmap, FMC2_BTR(cs), &ebi->btr[cs]);
-		regmap_read(ebi->regmap, FMC2_BWTR(cs), &ebi->bwtr[cs]);
+		if (!(ebi->bank_assigned & BIT(cs)))
+			continue;
+
+		ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &ebi->bcr[cs]);
+		ret |= regmap_read(ebi->regmap, FMC2_BTR(cs), &ebi->btr[cs]);
+		ret |= regmap_read(ebi->regmap, FMC2_BWTR(cs), &ebi->bwtr[cs]);
+		if (ret)
+			return ret;
 	}
 
-	regmap_read(ebi->regmap, FMC2_PCSCNTR, &ebi->pcscntr);
+	return 0;
+}
+
+static int stm32_fmc2_ebi_mp1_save_setup(struct stm32_fmc2_ebi *ebi)
+{
+	int ret;
+
+	ret = stm32_fmc2_ebi_save_setup(ebi);
+	if (ret)
+		return ret;
+
+	return regmap_read(ebi->regmap, FMC2_PCSCNTR, &ebi->pcscntr);
+}
+
+static int stm32_fmc2_ebi_mp25_save_setup(struct stm32_fmc2_ebi *ebi)
+{
+	int ret;
+
+	ret = stm32_fmc2_ebi_save_setup(ebi);
+	if (ret)
+		return ret;
+
+	if (ebi->access_granted)
+		ret = regmap_read(ebi->regmap, FMC2_CFGR, &ebi->cfgr);
+
+	return ret;
 }
 
 static void stm32_fmc2_ebi_set_setup(struct stm32_fmc2_ebi *ebi)
@@ -962,14 +1465,29 @@ static void stm32_fmc2_ebi_set_setup(struct stm32_fmc2_ebi *ebi)
 	unsigned int cs;
 
 	for (cs = 0; cs < FMC2_MAX_EBI_CE; cs++) {
+		if (!(ebi->bank_assigned & BIT(cs)))
+			continue;
+
 		regmap_write(ebi->regmap, FMC2_BCR(cs), ebi->bcr[cs]);
 		regmap_write(ebi->regmap, FMC2_BTR(cs), ebi->btr[cs]);
 		regmap_write(ebi->regmap, FMC2_BWTR(cs), ebi->bwtr[cs]);
 	}
+}
 
+static void stm32_fmc2_ebi_mp1_set_setup(struct stm32_fmc2_ebi *ebi)
+{
+	stm32_fmc2_ebi_set_setup(ebi);
 	regmap_write(ebi->regmap, FMC2_PCSCNTR, ebi->pcscntr);
 }
 
+static void stm32_fmc2_ebi_mp25_set_setup(struct stm32_fmc2_ebi *ebi)
+{
+	stm32_fmc2_ebi_set_setup(ebi);
+
+	if (ebi->access_granted)
+		regmap_write(ebi->regmap, FMC2_CFGR, ebi->cfgr);
+}
+
 static void stm32_fmc2_ebi_disable_banks(struct stm32_fmc2_ebi *ebi)
 {
 	unsigned int cs;
@@ -983,33 +1501,48 @@ static void stm32_fmc2_ebi_disable_banks(struct stm32_fmc2_ebi *ebi)
 }
 
 /* NWAIT signal can not be connected to EBI controller and NAND controller */
-static bool stm32_fmc2_ebi_nwait_used_by_ctrls(struct stm32_fmc2_ebi *ebi)
+static int stm32_fmc2_ebi_nwait_used_by_ctrls(struct stm32_fmc2_ebi *ebi)
 {
+	struct device *dev = ebi->dev;
 	unsigned int cs;
 	u32 bcr;
+	int ret;
 
 	for (cs = 0; cs < FMC2_MAX_EBI_CE; cs++) {
 		if (!(ebi->bank_assigned & BIT(cs)))
 			continue;
 
-		regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+		ret = regmap_read(ebi->regmap, FMC2_BCR(cs), &bcr);
+		if (ret)
+			return ret;
+
 		if ((bcr & FMC2_BCR_WAITEN || bcr & FMC2_BCR_ASYNCWAIT) &&
-		    ebi->bank_assigned & BIT(FMC2_NAND))
-			return true;
+		    ebi->bank_assigned & BIT(FMC2_NAND)) {
+			dev_err(dev, "NWAIT signal connected to EBI and NAND controllers\n");
+			return -EINVAL;
+		}
 	}
 
-	return false;
+	return 0;
 }
 
 static void stm32_fmc2_ebi_enable(struct stm32_fmc2_ebi *ebi)
 {
-	regmap_update_bits(ebi->regmap, FMC2_BCR1,
-			   FMC2_BCR1_FMC2EN, FMC2_BCR1_FMC2EN);
+	if (!ebi->access_granted)
+		return;
+
+	regmap_update_bits(ebi->regmap, ebi->data->fmc2_enable_reg,
+			   ebi->data->fmc2_enable_bit,
+			   ebi->data->fmc2_enable_bit);
 }
 
 static void stm32_fmc2_ebi_disable(struct stm32_fmc2_ebi *ebi)
 {
-	regmap_update_bits(ebi->regmap, FMC2_BCR1, FMC2_BCR1_FMC2EN, 0);
+	if (!ebi->access_granted)
+		return;
+
+	regmap_update_bits(ebi->regmap, ebi->data->fmc2_enable_reg,
+			   ebi->data->fmc2_enable_bit, 0);
 }
 
 static int stm32_fmc2_ebi_setup_cs(struct stm32_fmc2_ebi *ebi,
@@ -1021,8 +1554,8 @@ static int stm32_fmc2_ebi_setup_cs(struct stm32_fmc2_ebi *ebi,
 
 	stm32_fmc2_ebi_disable_bank(ebi, cs);
 
-	for (i = 0; i < ARRAY_SIZE(stm32_fmc2_child_props); i++) {
-		const struct stm32_fmc2_prop *p = &stm32_fmc2_child_props[i];
+	for (i = 0; i < ebi->data->nb_child_props; i++) {
+		const struct stm32_fmc2_prop *p = &ebi->data->child_props[i];
 
 		ret = stm32_fmc2_ebi_parse_prop(ebi, dev_node, p, cs);
 		if (ret) {
@@ -1066,6 +1599,15 @@ static int stm32_fmc2_ebi_parse_dt(struct stm32_fmc2_ebi *ebi)
 			return -EINVAL;
 		}
 
+		if (ebi->data->check_rif) {
+			ret = ebi->data->check_rif(ebi, bank + 1);
+			if (ret) {
+				dev_err(dev, "bank access failed: %d\n", bank);
+				of_node_put(child);
+				return ret;
+			}
+		}
+
 		if (bank < FMC2_MAX_EBI_CE) {
 			ret = stm32_fmc2_ebi_setup_cs(ebi, child, bank);
 			if (ret) {
@@ -1085,9 +1627,10 @@ static int stm32_fmc2_ebi_parse_dt(struct stm32_fmc2_ebi *ebi)
 		return -ENODEV;
 	}
 
-	if (stm32_fmc2_ebi_nwait_used_by_ctrls(ebi)) {
-		dev_err(dev, "NWAIT signal connected to EBI and NAND controllers\n");
-		return -EINVAL;
+	if (ebi->data->nwait_used_by_ctrls) {
+		ret = ebi->data->nwait_used_by_ctrls(ebi);
+		if (ret)
+			return ret;
 	}
 
 	stm32_fmc2_ebi_enable(ebi);
@@ -1107,6 +1650,11 @@ static int stm32_fmc2_ebi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ebi->dev = dev;
+	platform_set_drvdata(pdev, ebi);
+
+	ebi->data = of_device_get_match_data(dev);
+	if (!ebi->data)
+		return -EINVAL;
 
 	ebi->regmap = device_node_to_regmap(dev->of_node);
 	if (IS_ERR(ebi->regmap))
@@ -1120,28 +1668,57 @@ static int stm32_fmc2_ebi_probe(struct platform_device *pdev)
 	if (PTR_ERR(rstc) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	ret = clk_prepare_enable(ebi->clk);
+	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0)
+		return ret;
+
 	if (!IS_ERR(rstc)) {
 		reset_control_assert(rstc);
 		reset_control_deassert(rstc);
 	}
 
+	/* Check if CFGR register can be modified */
+	ebi->access_granted = true;
+	if (ebi->data->check_rif) {
+		ret = ebi->data->check_rif(ebi, 0);
+		if (ret) {
+			u32 sr;
+
+			ebi->access_granted = false;
+
+			ret = regmap_read(ebi->regmap, FMC2_SR, &sr);
+			if (ret)
+				goto err_release;
+
+			/* In case of CFGR is secure, just check that the FMC2 is enabled */
+			if (sr & FMC2_SR_ISOST) {
+				dev_err(dev, "FMC2 is not ready to be used.\n");
+				ret = -EACCES;
+				goto err_release;
+			}
+		}
+	}
+
 	ret = stm32_fmc2_ebi_parse_dt(ebi);
 	if (ret)
 		goto err_release;
 
-	stm32_fmc2_ebi_save_setup(ebi);
-	platform_set_drvdata(pdev, ebi);
+	ret = ebi->data->save_setup(ebi);
+	if (ret)
+		goto err_release;
 
 	return 0;
 
 err_release:
 	stm32_fmc2_ebi_disable_banks(ebi);
 	stm32_fmc2_ebi_disable(ebi);
-	clk_disable_unprepare(ebi->clk);
+	if (ebi->data->put_sems)
+		ebi->data->put_sems(ebi);
+	pm_runtime_put_sync_suspend(dev);
 
 	return ret;
 }
@@ -1153,7 +1730,25 @@ static void stm32_fmc2_ebi_remove(struct platform_device *pdev)
 	of_platform_depopulate(&pdev->dev);
 	stm32_fmc2_ebi_disable_banks(ebi);
 	stm32_fmc2_ebi_disable(ebi);
+	if (ebi->data->put_sems)
+		ebi->data->put_sems(ebi);
+	pm_runtime_put_sync_suspend(&pdev->dev);
+}
+
+static int __maybe_unused stm32_fmc2_ebi_runtime_suspend(struct device *dev)
+{
+	struct stm32_fmc2_ebi *ebi = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(ebi->clk);
+
+	return 0;
+}
+
+static int __maybe_unused stm32_fmc2_ebi_runtime_resume(struct device *dev)
+{
+	struct stm32_fmc2_ebi *ebi = dev_get_drvdata(dev);
+
+	return clk_prepare_enable(ebi->clk);
 }
 
 static int __maybe_unused stm32_fmc2_ebi_suspend(struct device *dev)
@@ -1161,7 +1756,9 @@ static int __maybe_unused stm32_fmc2_ebi_suspend(struct device *dev)
 	struct stm32_fmc2_ebi *ebi = dev_get_drvdata(dev);
 
 	stm32_fmc2_ebi_disable(ebi);
-	clk_disable_unprepare(ebi->clk);
+	if (ebi->data->put_sems)
+		ebi->data->put_sems(ebi);
+	pm_runtime_put_sync_suspend(dev);
 	pinctrl_pm_select_sleep_state(dev);
 
 	return 0;
@@ -1174,21 +1771,55 @@ static int __maybe_unused stm32_fmc2_ebi_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
-	ret = clk_prepare_enable(ebi->clk);
-	if (ret)
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0)
 		return ret;
 
-	stm32_fmc2_ebi_set_setup(ebi);
+	if (ebi->data->get_sems)
+		ebi->data->get_sems(ebi);
+	ebi->data->set_setup(ebi);
 	stm32_fmc2_ebi_enable(ebi);
 
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(stm32_fmc2_ebi_pm_ops, stm32_fmc2_ebi_suspend,
-			 stm32_fmc2_ebi_resume);
+static const struct dev_pm_ops stm32_fmc2_ebi_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_fmc2_ebi_runtime_suspend,
+			   stm32_fmc2_ebi_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(stm32_fmc2_ebi_suspend, stm32_fmc2_ebi_resume)
+};
+
+static const struct stm32_fmc2_ebi_data stm32_fmc2_ebi_mp1_data = {
+	.child_props = stm32_fmc2_child_props,
+	.nb_child_props = ARRAY_SIZE(stm32_fmc2_child_props),
+	.fmc2_enable_reg = FMC2_BCR1,
+	.fmc2_enable_bit = FMC2_BCR1_FMC2EN,
+	.nwait_used_by_ctrls = stm32_fmc2_ebi_nwait_used_by_ctrls,
+	.set_setup = stm32_fmc2_ebi_mp1_set_setup,
+	.save_setup = stm32_fmc2_ebi_mp1_save_setup,
+};
+
+static const struct stm32_fmc2_ebi_data stm32_fmc2_ebi_mp25_data = {
+	.child_props = stm32_fmc2_mp25_child_props,
+	.nb_child_props = ARRAY_SIZE(stm32_fmc2_mp25_child_props),
+	.fmc2_enable_reg = FMC2_CFGR,
+	.fmc2_enable_bit = FMC2_CFGR_FMC2EN,
+	.set_setup = stm32_fmc2_ebi_mp25_set_setup,
+	.save_setup = stm32_fmc2_ebi_mp25_save_setup,
+	.check_rif = stm32_fmc2_ebi_mp25_check_rif,
+	.put_sems = stm32_fmc2_ebi_mp25_put_sems,
+	.get_sems = stm32_fmc2_ebi_mp25_get_sems,
+};
 
 static const struct of_device_id stm32_fmc2_ebi_match[] = {
-	{.compatible = "st,stm32mp1-fmc2-ebi"},
+	{
+		.compatible = "st,stm32mp1-fmc2-ebi",
+		.data = &stm32_fmc2_ebi_mp1_data,
+	},
+	{
+		.compatible = "st,stm32mp25-fmc2-ebi",
+		.data = &stm32_fmc2_ebi_mp25_data,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, stm32_fmc2_ebi_match);
diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c
index abff87f917cb..5f57cea48b62 100644
--- a/drivers/memory/tegra/tegra234.c
+++ b/drivers/memory/tegra/tegra234.c
@@ -92,6 +92,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0RDB,
 		.name = "dla0rdb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -102,6 +104,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0RDB1,
 		.name = "dla0rdb1",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -112,6 +116,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0WRB,
 		.name = "dla0wrb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -121,7 +127,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1RDB,
-		.name = "dla0rdb",
+		.name = "dla1rdb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -407,7 +415,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1RDB1,
-		.name = "dla0rdb1",
+		.name = "dla1rdb1",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -417,7 +427,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1WRB,
-		.name = "dla0wrb",
+		.name = "dla1wrb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -539,7 +551,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		.bpmp_id = TEGRA_ICC_BPMP_NVJPG_0,
 		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVJPG,
-			.regs = {
+		.regs = {
 			.sid = {
 				.override = 0x3f8,
 				.security = 0x3fc,
@@ -660,6 +672,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0RDA,
 		.name = "dla0rda",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -670,6 +684,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0FALRDB,
 		.name = "dla0falrdb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -680,6 +696,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0WRA,
 		.name = "dla0wra",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -690,6 +708,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0FALWRB,
 		.name = "dla0falwrb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -699,7 +719,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1RDA,
-		.name = "dla0rda",
+		.name = "dla1rda",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -709,7 +731,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1FALRDB,
-		.name = "dla0falrdb",
+		.name = "dla1falrdb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -719,7 +743,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1WRA,
-		.name = "dla0wra",
+		.name = "dla1wra",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -729,7 +755,9 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1FALWRB,
-		.name = "dla0falwrb",
+		.name = "dla1falwrb",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_1,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
@@ -908,6 +936,8 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA0RDA1,
 		.name = "dla0rda1",
+		.bpmp_id = TEGRA_ICC_BPMP_DLA_0,
+		.type = TEGRA_ICC_NISO,
 		.sid = TEGRA234_SID_NVDLA0,
 		.regs = {
 			.sid = {
@@ -917,7 +947,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = {
 		},
 	}, {
 		.id = TEGRA234_MEMORY_CLIENT_DLA1RDA1,
-		.name = "dla0rda1",
+		.name = "dla1rda1",
 		.sid = TEGRA234_SID_NVDLA1,
 		.regs = {
 			.sid = {
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 04115cd92433..47a314a4eb6f 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2078,6 +2078,12 @@ static const struct blk_mq_ops msb_mq_ops = {
 static int msb_init_disk(struct memstick_dev *card)
 {
 	struct msb_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MS_BLOCK_MAX_PAGES,
+		.max_segments		= MS_BLOCK_MAX_SEGS,
+		.max_segment_size	= MS_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	int rc;
 	unsigned long capacity;
 
@@ -2093,19 +2099,13 @@ static int msb_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MS_BLOCK_MAX_PAGES * msb->page_size);
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id);
 	msb->disk->fops = &msb_bdops;
 	msb->disk->private_data = msb;
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 5a69ed33999b..49accfdc89d6 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1103,6 +1103,12 @@ static const struct blk_mq_ops mspro_mq_ops = {
 static int mspro_block_init_disk(struct memstick_dev *card)
 {
 	struct mspro_block_data *msb = memstick_get_drvdata(card);
+	struct queue_limits lim = {
+		.logical_block_size	= msb->page_size,
+		.max_hw_sectors		= MSPRO_BLOCK_MAX_PAGES,
+		.max_segments		= MSPRO_BLOCK_MAX_SEGS,
+		.max_segment_size	= MSPRO_BLOCK_MAX_PAGES * msb->page_size,
+	};
 	struct mspro_devinfo *dev_info = NULL;
 	struct mspro_sys_info *sys_info = NULL;
 	struct mspro_sys_attr *s_attr = NULL;
@@ -1138,18 +1144,13 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	if (rc)
 		goto out_release_id;
 
-	msb->disk = blk_mq_alloc_disk(&msb->tag_set, card);
+	msb->disk = blk_mq_alloc_disk(&msb->tag_set, &lim, card);
 	if (IS_ERR(msb->disk)) {
 		rc = PTR_ERR(msb->disk);
 		goto out_free_tag_set;
 	}
 	msb->queue = msb->disk->queue;
 
-	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
-	blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS);
-	blk_queue_max_segment_size(msb->queue,
-				   MSPRO_BLOCK_MAX_PAGES * msb->page_size);
-
 	msb->disk->major = major;
 	msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT;
 	msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT;
@@ -1158,8 +1159,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 
 	sprintf(msb->disk->disk_name, "mspblk%d", disk_id);
 
-	blk_queue_logical_block_size(msb->queue, msb->page_size);
-
 	capacity = be16_to_cpu(sys_info->user_block_count);
 	capacity *= be16_to_cpu(sys_info->block_size);
 	capacity *= msb->page_size >> 9;
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 1c6c62a7f7f5..dbd26c3b245b 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -263,7 +263,6 @@ struct fastrpc_channel_ctx {
 	int domain_id;
 	int sesscount;
 	int vmcount;
-	u64 perms;
 	struct qcom_scm_vmperm vmperms[FASTRPC_MAX_VMIDS];
 	struct rpmsg_device *rpdev;
 	struct fastrpc_session_ctx session[FASTRPC_MAX_SESSIONS];
@@ -1279,9 +1278,11 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
 
 		/* Map if we have any heap VMIDs associated with this ADSP Static Process. */
 		if (fl->cctx->vmcount) {
+			u64 src_perms = BIT(QCOM_SCM_VMID_HLOS);
+
 			err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
 							(u64)fl->cctx->remote_heap->size,
-							&fl->cctx->perms,
+							&src_perms,
 							fl->cctx->vmperms, fl->cctx->vmcount);
 			if (err) {
 				dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
@@ -1915,8 +1916,10 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
 
 	/* Add memory to static PD pool, protection thru hypervisor */
 	if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) {
+		u64 src_perms = BIT(QCOM_SCM_VMID_HLOS);
+
 		err = qcom_scm_assign_mem(buf->phys, (u64)buf->size,
-			&fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount);
+			&src_perms, fl->cctx->vmperms, fl->cctx->vmcount);
 		if (err) {
 			dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
 					buf->phys, buf->size, err);
@@ -2191,7 +2194,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev)
 	int i;
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) {
+	for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) {
 		if (cctx->session[i].sid == sess->sid) {
 			cctx->session[i].valid = false;
 			cctx->sesscount--;
@@ -2290,7 +2293,6 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 
 	if (vmcount) {
 		data->vmcount = vmcount;
-		data->perms = BIT(QCOM_SCM_VMID_HLOS);
 		for (i = 0; i < data->vmcount; i++) {
 			data->vmperms[i].vmid = vmids[i];
 			data->vmperms[i].perm = QCOM_SCM_PERM_RWX;
diff --git a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
index c6eb27d46cb0..15119584473c 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d_i2c.c
@@ -198,8 +198,14 @@ static int lis3lv02d_i2c_suspend(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct lis3lv02d *lis3 = i2c_get_clientdata(client);
 
-	if (!lis3->pdata || !lis3->pdata->wakeup_flags)
+	/* Turn on for wakeup if turned off by runtime suspend */
+	if (lis3->pdata && lis3->pdata->wakeup_flags) {
+		if (pm_runtime_suspended(dev))
+			lis3lv02d_poweron(lis3);
+	/* For non wakeup turn off if not already turned off by runtime suspend */
+	} else if (!pm_runtime_suspended(dev))
 		lis3lv02d_poweroff(lis3);
+
 	return 0;
 }
 
@@ -208,13 +214,12 @@ static int lis3lv02d_i2c_resume(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct lis3lv02d *lis3 = i2c_get_clientdata(client);
 
-	/*
-	 * pm_runtime documentation says that devices should always
-	 * be powered on at resume. Pm_runtime turns them off after system
-	 * wide resume is complete.
-	 */
-	if (!lis3->pdata || !lis3->pdata->wakeup_flags ||
-		pm_runtime_suspended(dev))
+	/* Turn back off if turned on for wakeup and runtime suspended*/
+	if (lis3->pdata && lis3->pdata->wakeup_flags) {
+		if (pm_runtime_suspended(dev))
+			lis3lv02d_poweroff(lis3);
+	/* For non wakeup turn back on if not runtime suspended */
+	} else if (!pm_runtime_suspended(dev))
 		lis3lv02d_poweron(lis3);
 
 	return 0;
diff --git a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
index be52b113aea9..89364bdbb129 100644
--- a/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
+++ b/drivers/misc/mei/gsc_proxy/mei_gsc_proxy.c
@@ -96,7 +96,8 @@ static const struct component_master_ops mei_component_master_ops = {
  *
  *    The function checks if the device is pci device and
  *    Intel VGA adapter, the subcomponent is SW Proxy
- *    and the parent of MEI PCI and the parent of VGA are the same PCH device.
+ *    and the VGA is on the bus 0 reserved for built-in devices
+ *    to reject discrete GFX.
  *
  * @dev: master device
  * @subcomponent: subcomponent to match (I915_COMPONENT_SWPROXY)
@@ -123,7 +124,8 @@ static int mei_gsc_proxy_component_match(struct device *dev, int subcomponent,
 	if (subcomponent != I915_COMPONENT_GSC_PROXY)
 		return 0;
 
-	return component_compare_dev(dev->parent, ((struct device *)data)->parent);
+	/* Only built-in GFX */
+	return (pdev->bus->number == 0);
 }
 
 static int mei_gsc_proxy_probe(struct mei_cl_device *cldev,
@@ -146,7 +148,7 @@ static int mei_gsc_proxy_probe(struct mei_cl_device *cldev,
 	}
 
 	component_match_add_typed(&cldev->dev, &master_match,
-				  mei_gsc_proxy_component_match, cldev->dev.parent);
+				  mei_gsc_proxy_component_match, NULL);
 	if (IS_ERR_OR_NULL(master_match)) {
 		ret = -ENOMEM;
 		goto err_exit;
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 961e5d53a27a..aac36750d2c5 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -112,6 +112,8 @@
 #define MEI_DEV_ID_RPL_S      0x7A68  /* Raptor Lake Point S */
 
 #define MEI_DEV_ID_MTL_M      0x7E70  /* Meteor Lake Point M */
+#define MEI_DEV_ID_ARL_S      0x7F68  /* Arrow Lake Point S */
+#define MEI_DEV_ID_ARL_H      0x7770  /* Arrow Lake Point H */
 
 /*
  * MEI HW Section
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 676d566f38dd..8cf636c54032 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -119,6 +119,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)},
 
 	/* required last entry */
 	{0, }
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 6f4a4be6ccb5..55f7db490d3b 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -535,6 +535,7 @@ static const struct acpi_device_id vsc_tp_acpi_ids[] = {
 	{ "INTC1009" }, /* Raptor Lake */
 	{ "INTC1058" }, /* Tiger Lake */
 	{ "INTC1094" }, /* Alder Lake */
+	{ "INTC10D0" }, /* Meteor Lake */
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, vsc_tp_acpi_ids);
diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
index 8aea2d070a40..d279a4f195e2 100644
--- a/drivers/misc/open-dice.c
+++ b/drivers/misc/open-dice.c
@@ -140,7 +140,6 @@ static int __init open_dice_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	*drvdata = (struct open_dice_drvdata){
-		.lock = __MUTEX_INITIALIZER(drvdata->lock),
 		.rmem = rmem,
 		.misc = (struct miscdevice){
 			.parent	= dev,
@@ -150,6 +149,7 @@ static int __init open_dice_probe(struct platform_device *pdev)
 			.mode	= 0600,
 		},
 	};
+	mutex_init(&drvdata->lock);
 
 	/* Index overflow check not needed, misc_register() will fail. */
 	snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f410bee50132..58ed7193a3ca 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1015,10 +1015,12 @@ static int mmc_select_bus_width(struct mmc_card *card)
 	static unsigned ext_csd_bits[] = {
 		EXT_CSD_BUS_WIDTH_8,
 		EXT_CSD_BUS_WIDTH_4,
+		EXT_CSD_BUS_WIDTH_1,
 	};
 	static unsigned bus_widths[] = {
 		MMC_BUS_WIDTH_8,
 		MMC_BUS_WIDTH_4,
+		MMC_BUS_WIDTH_1,
 	};
 	struct mmc_host *host = card->host;
 	unsigned idx, bus_width = 0;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index a0a2412f62a7..2ae60d208cdf 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -174,8 +174,8 @@ static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
 	return sg;
 }
 
-static void mmc_queue_setup_discard(struct request_queue *q,
-				    struct mmc_card *card)
+static void mmc_queue_setup_discard(struct mmc_card *card,
+		struct queue_limits *lim)
 {
 	unsigned max_discard;
 
@@ -183,15 +183,17 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (!max_discard)
 		return;
 
-	blk_queue_max_discard_sectors(q, max_discard);
-	q->limits.discard_granularity = card->pref_erase << 9;
-	/* granularity must not be greater than max. discard */
-	if (card->pref_erase > max_discard)
-		q->limits.discard_granularity = SECTOR_SIZE;
+	lim->max_hw_discard_sectors = max_discard;
 	if (mmc_can_secure_erase_trim(card))
-		blk_queue_max_secure_erase_sectors(q, max_discard);
+		lim->max_secure_erase_sectors = max_discard;
 	if (mmc_can_trim(card) && card->erased_byte == 0)
-		blk_queue_max_write_zeroes_sectors(q, max_discard);
+		lim->max_write_zeroes_sectors = max_discard;
+
+	/* granularity must not be greater than max. discard */
+	if (card->pref_erase > max_discard)
+		lim->discard_granularity = SECTOR_SIZE;
+	else
+		lim->discard_granularity = card->pref_erase << 9;
 }
 
 static unsigned short mmc_get_max_segments(struct mmc_host *host)
@@ -341,40 +343,53 @@ static const struct blk_mq_ops mmc_mq_ops = {
 	.timeout	= mmc_mq_timed_out,
 };
 
-static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
+static struct gendisk *mmc_alloc_disk(struct mmc_queue *mq,
+		struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	unsigned block_size = 512;
+	struct queue_limits lim = { };
+	struct gendisk *disk;
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
 	if (mmc_can_erase(card))
-		mmc_queue_setup_discard(mq->queue, card);
+		mmc_queue_setup_discard(card, &lim);
 
 	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
-		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
-	blk_queue_max_hw_sectors(mq->queue,
-		min(host->max_blk_count, host->max_req_size / 512));
-	if (host->can_dma_map_merge)
-		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
-							mmc_dev(host)),
-		     "merging was advertised but not possible");
-	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));
-
-	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) {
-		block_size = card->ext_csd.data_sector_size;
-		WARN_ON(block_size != 512 && block_size != 4096);
-	}
+		lim.bounce = BLK_BOUNCE_HIGH;
+
+	lim.max_hw_sectors = min(host->max_blk_count, host->max_req_size / 512);
+
+	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size)
+		lim.logical_block_size = card->ext_csd.data_sector_size;
+	else
+		lim.logical_block_size = 512;
+
+	WARN_ON_ONCE(lim.logical_block_size != 512 &&
+		     lim.logical_block_size != 4096);
 
-	blk_queue_logical_block_size(mq->queue, block_size);
 	/*
-	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
-	 * since it calls blk_queue_virt_boundary(), the mmc should not call
-	 * both blk_queue_max_segment_size().
+	 * Setting a virt_boundary implicity sets a max_segment_size, so try
+	 * to set the hardware one here.
 	 */
-	if (!host->can_dma_map_merge)
-		blk_queue_max_segment_size(mq->queue,
-			round_down(host->max_seg_size, block_size));
+	if (host->can_dma_map_merge) {
+		lim.virt_boundary_mask = dma_get_merge_boundary(mmc_dev(host));
+		lim.max_segments = MMC_DMA_MAP_MERGE_SEGMENTS;
+	} else {
+		lim.max_segment_size =
+			round_down(host->max_seg_size, lim.logical_block_size);
+		lim.max_segments = host->max_segs;
+	}
+
+	disk = blk_mq_alloc_disk(&mq->tag_set, &lim, mq);
+	if (IS_ERR(disk))
+		return disk;
+	mq->queue = disk->queue;
+
+	if (mmc_host_is_spi(host) && host->use_spi_crc)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
+	blk_queue_rq_timeout(mq->queue, 60 * HZ);
+
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
+	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
 
 	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));
 
@@ -386,6 +401,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
 	init_waitqueue_head(&mq->wait);
 
 	mmc_crypto_setup_queue(mq->queue, host);
+	return disk;
 }
 
 static inline bool mmc_merge_capable(struct mmc_host *host)
@@ -447,18 +463,9 @@ struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 		return ERR_PTR(ret);
 		
 
-	disk = blk_mq_alloc_disk(&mq->tag_set, mq);
-	if (IS_ERR(disk)) {
+	disk = mmc_alloc_disk(mq, card);
+	if (IS_ERR(disk))
 		blk_mq_free_tag_set(&mq->tag_set);
-		return disk;
-	}
-	mq->queue = disk->queue;
-
-	if (mmc_host_is_spi(host) && host->use_spi_crc)
-		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
-	blk_queue_rq_timeout(mq->queue, 60 * HZ);
-
-	mmc_setup_queue(mq, card);
 	return disk;
 }
 
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 2a2d949a9344..39f45c2b6de8 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq);
 int mmc_gpio_get_ro(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
+	int cansleep;
 
 	if (!ctx || !ctx->ro_gpio)
 		return -ENOSYS;
 
-	return gpiod_get_value_cansleep(ctx->ro_gpio);
+	cansleep = gpiod_cansleep(ctx->ro_gpio);
+	return cansleep ?
+		gpiod_get_value_cansleep(ctx->ro_gpio) :
+		gpiod_get_value(ctx->ro_gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_get_ro);
 
diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index 35067e1e6cd8..f5da7f9baa52 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -225,6 +225,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	struct scatterlist *sg;
 	int i;
 
+	host->dma_in_progress = true;
+
 	if (!host->variant->dma_lli || data->sg_len == 1 ||
 	    idma->use_bounce_buffer) {
 		u32 dma_addr;
@@ -263,9 +265,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl)
 	return 0;
 }
 
+static void sdmmc_idma_error(struct mmci_host *host)
+{
+	struct mmc_data *data = host->data;
+	struct sdmmc_idma *idma = host->dma_priv;
+
+	if (!dma_inprogress(host))
+		return;
+
+	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
+	data->host_cookie = 0;
+
+	if (!idma->use_bounce_buffer)
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+}
+
 static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data)
 {
+	if (!dma_inprogress(host))
+		return;
+
 	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
 
 	if (!data->host_cookie)
 		sdmmc_idma_unprep_data(host, data, 0);
@@ -676,6 +699,7 @@ static struct mmci_host_ops sdmmc_variant_ops = {
 	.dma_setup = sdmmc_idma_setup,
 	.dma_start = sdmmc_idma_start,
 	.dma_finalize = sdmmc_idma_finalize,
+	.dma_error = sdmmc_idma_error,
 	.set_clkreg = mmci_sdmmc_set_clkreg,
 	.set_pwrreg = mmci_sdmmc_set_pwrreg,
 	.busy_complete = sdmmc_busy_complete,
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 7bfee28116af..d4a02184784a 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io
 	return 0;
 }
 
+static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode,  unsigned short vdd)
+{
+	struct sdhci_pci_chip *chip;
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	u32 scratch_32 = 0;
+	u8 scratch_8 = 0;
+
+	chip = slot->chip;
+
+	if (mode == MMC_POWER_OFF) {
+		/* UnLock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 &= 0x7f;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+
+		/* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */
+		pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32);
+		scratch_32 &= ~(O2_SD_SEL_DLL);
+		pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32);
+
+		/* Lock WP */
+		pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+		scratch_8 |= 0x80;
+		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+	}
+
+	sdhci_set_power(host, mode, vdd);
+}
+
 static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 {
 	struct sdhci_pci_chip *chip;
@@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_power = sdhci_pci_o2_set_power,
 };
 
 const struct sdhci_pci_fixes sdhci_o2 = {
diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c
index 8cf3a375de65..cc9d28b75eb9 100644
--- a/drivers/mmc/host/sdhci-xenon-phy.c
+++ b/drivers/mmc/host/sdhci-xenon-phy.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
+#include <linux/iopoll.h>
 #include <linux/of_address.h>
 
 #include "sdhci-pltfm.h"
@@ -109,6 +110,8 @@
 #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST	(XENON_EMMC_PHY_REG_BASE + 0x18)
 #define XENON_LOGIC_TIMING_VALUE		0x00AA8977
 
+#define XENON_MAX_PHY_TIMEOUT_LOOPS		100
+
 /*
  * List offset of PHY registers and some special register values
  * in eMMC PHY 5.0 or eMMC PHY 5.1
@@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host)
 	return 0;
 }
 
+static int xenon_check_stability_internal_clk(struct sdhci_host *host)
+{
+	u32 reg;
+	int err;
+
+	err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE,
+				1100, 20000, false, host, SDHCI_CLOCK_CONTROL);
+	if (err)
+		dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n");
+
+	return err;
+}
+
 /*
  * eMMC 5.0/5.1 PHY init/re-init.
  * eMMC PHY init should be executed after:
@@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
 
+	int ret = xenon_check_stability_internal_clk(host);
+
+	if (ret)
+		return ret;
+
 	reg = sdhci_readl(host, phy_regs->timing_adj);
 	reg |= XENON_PHY_INITIALIZAION;
 	sdhci_writel(host, reg, phy_regs->timing_adj);
@@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host)
 	/* get the wait time */
 	wait /= clock;
 	wait++;
-	/* wait for host eMMC PHY init completes */
-	udelay(wait);
 
-	reg = sdhci_readl(host, phy_regs->timing_adj);
-	reg &= XENON_PHY_INITIALIZAION;
-	if (reg) {
+	/*
+	 * AC5X spec says bit must be polled until zero.
+	 * We see cases in which timeout can take longer
+	 * than the standard calculation on AC5X, which is
+	 * expected following the spec comment above.
+	 * According to the spec, we must wait as long as
+	 * it takes for that bit to toggle on AC5X.
+	 * Cap that with 100 delay loops so we won't get
+	 * stuck here forever:
+	 */
+
+	ret = read_poll_timeout(sdhci_readl, reg,
+				!(reg & XENON_PHY_INITIALIZAION),
+				wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait,
+				false, host, phy_regs->timing_adj);
+	if (ret)
 		dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n",
-			wait);
-		return -ETIMEDOUT;
-	}
+			wait * XENON_MAX_PHY_TIMEOUT_LOOPS);
 
-	return 0;
+	return ret;
 }
 
 #define ARMADA_3700_SOC_PAD_1_8V	0x1
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index aa44a23ec045..97a00ec9a4d4 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -37,7 +37,7 @@
 /* Info for the block device */
 struct block2mtd_dev {
 	struct list_head list;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct mtd_info mtd;
 	struct mutex write_mutex;
 };
@@ -55,8 +55,7 @@ static struct page *page_read(struct address_space *mapping, pgoff_t index)
 /* erase a specified part of the device */
 static int _block2mtd_erase(struct block2mtd_dev *dev, loff_t to, size_t len)
 {
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	struct page *page;
 	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int pages = len >> PAGE_SHIFT;
@@ -106,8 +105,7 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 		size_t *retlen, u_char *buf)
 {
 	struct block2mtd_dev *dev = mtd->priv;
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	struct page *page;
 	pgoff_t index = from >> PAGE_SHIFT;
 	int offset = from & (PAGE_SIZE-1);
@@ -142,8 +140,7 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf,
 		loff_t to, size_t len, size_t *retlen)
 {
 	struct page *page;
-	struct address_space *mapping =
-				dev->bdev_handle->bdev->bd_inode->i_mapping;
+	struct address_space *mapping = dev->bdev_file->f_mapping;
 	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int offset = to & ~PAGE_MASK;	// page offset
 	int cpylen;
@@ -198,7 +195,7 @@ static int block2mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
 static void block2mtd_sync(struct mtd_info *mtd)
 {
 	struct block2mtd_dev *dev = mtd->priv;
-	sync_blockdev(dev->bdev_handle->bdev);
+	sync_blockdev(file_bdev(dev->bdev_file));
 	return;
 }
 
@@ -210,10 +207,9 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
 
 	kfree(dev->mtd.name);
 
-	if (dev->bdev_handle) {
-		invalidate_mapping_pages(
-			dev->bdev_handle->bdev->bd_inode->i_mapping, 0, -1);
-		bdev_release(dev->bdev_handle);
+	if (dev->bdev_file) {
+		invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1);
+		fput(dev->bdev_file);
 	}
 
 	kfree(dev);
@@ -223,10 +219,10 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
  * This function is marked __ref because it calls the __init marked
  * early_lookup_bdev when called from the early boot code.
  */
-static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
+static struct file __ref *mdtblock_early_get_bdev(const char *devname,
 		blk_mode_t mode, int timeout, struct block2mtd_dev *dev)
 {
-	struct bdev_handle *bdev_handle = ERR_PTR(-ENODEV);
+	struct file *bdev_file = ERR_PTR(-ENODEV);
 #ifndef MODULE
 	int i;
 
@@ -234,7 +230,7 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
 	 * We can't use early_lookup_bdev from a running system.
 	 */
 	if (system_state >= SYSTEM_RUNNING)
-		return bdev_handle;
+		return bdev_file;
 
 	/*
 	 * We might not have the root device mounted at this point.
@@ -253,20 +249,20 @@ static struct bdev_handle __ref *mdtblock_early_get_bdev(const char *devname,
 		wait_for_device_probe();
 
 		if (!early_lookup_bdev(devname, &devt)) {
-			bdev_handle = bdev_open_by_dev(devt, mode, dev, NULL);
-			if (!IS_ERR(bdev_handle))
+			bdev_file = bdev_file_open_by_dev(devt, mode, dev, NULL);
+			if (!IS_ERR(bdev_file))
 				break;
 		}
 	}
 #endif
-	return bdev_handle;
+	return bdev_file;
 }
 
 static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		char *label, int timeout)
 {
 	const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	struct block2mtd_dev *dev;
 	char *name;
@@ -279,16 +275,16 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		return NULL;
 
 	/* Get a handle on the device */
-	bdev_handle = bdev_open_by_path(devname, mode, dev, NULL);
-	if (IS_ERR(bdev_handle))
-		bdev_handle = mdtblock_early_get_bdev(devname, mode, timeout,
+	bdev_file = bdev_file_open_by_path(devname, mode, dev, NULL);
+	if (IS_ERR(bdev_file))
+		bdev_file = mdtblock_early_get_bdev(devname, mode, timeout,
 						      dev);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_err("error: cannot open device %s\n", devname);
 		goto err_free_block2mtd;
 	}
-	dev->bdev_handle = bdev_handle;
-	bdev = bdev_handle->bdev;
+	dev->bdev_file = bdev_file;
+	bdev = file_bdev(bdev_file);
 
 	if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
 		pr_err("attempting to use an MTD device as a block device\n");
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index f0526dcc2162..3caa0717d46c 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -277,6 +277,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 {
 	struct mtd_blktrans_ops *tr = new->tr;
 	struct mtd_blktrans_dev *d;
+	struct queue_limits lim = { };
 	int last_devnum = -1;
 	struct gendisk *gd;
 	int ret;
@@ -331,9 +332,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 			BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING);
 	if (ret)
 		goto out_kfree_tag_set;
+	
+	lim.logical_block_size = tr->blksize;
+	if (tr->discard)
+		lim.max_hw_discard_sectors = UINT_MAX;
 
 	/* Create gendisk */
-	gd = blk_mq_alloc_disk(new->tag_set, new);
+	gd = blk_mq_alloc_disk(new->tag_set, &lim, new);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tag_set;
@@ -371,14 +376,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	if (tr->flush)
 		blk_queue_write_cache(new->rq, true, false);
 
-	blk_queue_logical_block_size(new->rq, tr->blksize);
-
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
-	if (tr->discard)
-		blk_queue_max_discard_sectors(new->rq, UINT_MAX);
-
 	gd->queue = new->rq;
 
 	if (new->readonly)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index e451b28840d5..5887feb347a4 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -621,6 +621,7 @@ static void mtd_check_of_node(struct mtd_info *mtd)
 		if (plen == mtd_name_len &&
 		    !strncmp(mtd->name, pname + offset, plen)) {
 			mtd_set_of_node(mtd, mtd_dn);
+			of_node_put(mtd_dn);
 			break;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index a46698744850..5b0f5a9cef81 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -290,16 +290,13 @@ static const struct marvell_hw_ecc_layout marvell_nfc_layouts[] = {
 	MARVELL_LAYOUT( 2048,   512,  4,  1,  1, 2048, 32, 30,  0,  0,  0),
 	MARVELL_LAYOUT( 2048,   512,  8,  2,  1, 1024,  0, 30,1024,32, 30),
 	MARVELL_LAYOUT( 2048,   512,  8,  2,  1, 1024,  0, 30,1024,64, 30),
-	MARVELL_LAYOUT( 2048,   512,  12, 3,  2, 704,   0, 30,640,  0, 30),
-	MARVELL_LAYOUT( 2048,   512,  16, 5,  4, 512,   0, 30,  0, 32, 30),
+	MARVELL_LAYOUT( 2048,   512,  16, 4,  4, 512,   0, 30,  0, 32, 30),
 	MARVELL_LAYOUT( 4096,   512,  4,  2,  2, 2048, 32, 30,  0,  0,  0),
-	MARVELL_LAYOUT( 4096,   512,  8,  5,  4, 1024,  0, 30,  0, 64, 30),
-	MARVELL_LAYOUT( 4096,   512,  12, 6,  5, 704,   0, 30,576, 32, 30),
-	MARVELL_LAYOUT( 4096,   512,  16, 9,  8, 512,   0, 30,  0, 32, 30),
+	MARVELL_LAYOUT( 4096,   512,  8,  4,  4, 1024,  0, 30,  0, 64, 30),
+	MARVELL_LAYOUT( 4096,   512,  16, 8,  8, 512,   0, 30,  0, 32, 30),
 	MARVELL_LAYOUT( 8192,   512,  4,  4,  4, 2048,  0, 30,  0,  0,  0),
-	MARVELL_LAYOUT( 8192,   512,  8,  9,  8, 1024,  0, 30,  0, 160, 30),
-	MARVELL_LAYOUT( 8192,   512,  12, 12, 11, 704,  0, 30,448,  64, 30),
-	MARVELL_LAYOUT( 8192,   512,  16, 17, 16, 512,  0, 30,  0,  32, 30),
+	MARVELL_LAYOUT( 8192,   512,  8,  8,  8, 1024,  0, 30,  0, 160, 30),
+	MARVELL_LAYOUT( 8192,   512,  16, 16, 16, 512,  0, 30,  0,  32, 30),
 };
 
 /**
diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c
index 987710e09441..6023cba748bb 100644
--- a/drivers/mtd/nand/spi/gigadevice.c
+++ b/drivers/mtd/nand/spi/gigadevice.c
@@ -186,7 +186,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -207,6 +207,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 		 * report the maximum of 4 in this case
 		 */
 		/* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status & STATUS_ECC_MASK) >> 2) |
 			((status2 & STATUS_ECC_MASK) >> 4);
 
@@ -228,7 +229,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -248,6 +249,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 		 * 1 ... 4 bits are flipped (and corrected)
 		 */
 		/* bits sorted this way (1...0): ECCSE1, ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status2 & STATUS_ECC_MASK) >> 4) + 1;
 
 	case STATUS_ECC_UNCOR_ERROR:
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 654bd7372cd8..5c8fdcc088a0 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -348,6 +348,9 @@ static int calc_disk_capacity(struct ubi_volume_info *vi, u64 *disk_capacity)
 
 int ubiblock_create(struct ubi_volume_info *vi)
 {
+	struct queue_limits lim = {
+		.max_segments		= UBI_MAX_SG_COUNT,
+	};
 	struct ubiblock *dev;
 	struct gendisk *gd;
 	u64 disk_capacity;
@@ -393,7 +396,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 
 
 	/* Initialize the gendisk of this ubiblock device */
-	gd = blk_mq_alloc_disk(&dev->tag_set, dev);
+	gd = blk_mq_alloc_disk(&dev->tag_set, &lim, dev);
 	if (IS_ERR(gd)) {
 		ret = PTR_ERR(gd);
 		goto out_free_tags;
@@ -416,7 +419,6 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	dev->gd = gd;
 
 	dev->rq = gd->queue;
-	blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT);
 
 	list_add_tail(&dev->list, &ubiblock_devices);
 
diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c
index 8c651fdee039..57f1729066f2 100644
--- a/drivers/net/arcnet/arc-rawmode.c
+++ b/drivers/net/arcnet/arc-rawmode.c
@@ -186,4 +186,5 @@ static void __exit arcnet_raw_exit(void)
 module_init(arcnet_raw_init);
 module_exit(arcnet_raw_exit);
 
+MODULE_DESCRIPTION("ARCnet raw mode packet interface module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c
index 8c3ccc7c83cd..53d10a04d1bd 100644
--- a/drivers/net/arcnet/arc-rimi.c
+++ b/drivers/net/arcnet/arc-rimi.c
@@ -312,6 +312,7 @@ module_param(node, int, 0);
 module_param(io, int, 0);
 module_param(irq, int, 0);
 module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx RIM I chipset driver");
 MODULE_LICENSE("GPL");
 
 static struct net_device *my_dev;
diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c
index c09b567845e1..7a0a79973769 100644
--- a/drivers/net/arcnet/capmode.c
+++ b/drivers/net/arcnet/capmode.c
@@ -265,4 +265,5 @@ static void __exit capmode_module_exit(void)
 module_init(capmode_module_init);
 module_exit(capmode_module_exit);
 
+MODULE_DESCRIPTION("ARCnet CAP mode packet interface module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index 7b5c8bb02f11..c5e571ec94c9 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -61,6 +61,7 @@ module_param(timeout, int, 0);
 module_param(backplane, int, 0);
 module_param(clockp, int, 0);
 module_param(clockm, int, 0);
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCI driver");
 MODULE_LICENSE("GPL");
 
 static void led_tx_set(struct led_classdev *led_cdev,
diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c
index 06e1651b594b..a0053e3992a3 100644
--- a/drivers/net/arcnet/com20020.c
+++ b/drivers/net/arcnet/com20020.c
@@ -399,6 +399,7 @@ EXPORT_SYMBOL(com20020_found);
 EXPORT_SYMBOL(com20020_netdev_ops);
 #endif
 
+MODULE_DESCRIPTION("ARCnet COM20020 chipset core driver");
 MODULE_LICENSE("GPL");
 
 #ifdef MODULE
diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c
index dc3253b318da..75f08aa7528b 100644
--- a/drivers/net/arcnet/com20020_cs.c
+++ b/drivers/net/arcnet/com20020_cs.c
@@ -97,6 +97,7 @@ module_param(backplane, int, 0);
 module_param(clockp, int, 0);
 module_param(clockm, int, 0);
 
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCMCIA driver");
 MODULE_LICENSE("GPL");
 
 /*====================================================================*/
diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c
index 37b47749fc8b..3b463fbc6402 100644
--- a/drivers/net/arcnet/com90io.c
+++ b/drivers/net/arcnet/com90io.c
@@ -350,6 +350,7 @@ static char device[9];		/* use eg. device=arc1 to change name */
 module_param_hw(io, int, ioport, 0);
 module_param_hw(irq, int, irq, 0);
 module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx IO mapped chipset driver");
 MODULE_LICENSE("GPL");
 
 #ifndef MODULE
diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c
index f49dae194284..b3b287c16561 100644
--- a/drivers/net/arcnet/com90xx.c
+++ b/drivers/net/arcnet/com90xx.c
@@ -645,6 +645,7 @@ static void com90xx_copy_from_card(struct net_device *dev, int bufnum,
 	TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count));
 }
 
+MODULE_DESCRIPTION("ARCnet COM90xx normal chipset driver");
 MODULE_LICENSE("GPL");
 
 static int __init com90xx_init(void)
diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c
index a7752a5b647f..46519ca63a0a 100644
--- a/drivers/net/arcnet/rfc1051.c
+++ b/drivers/net/arcnet/rfc1051.c
@@ -78,6 +78,7 @@ static void __exit arcnet_rfc1051_exit(void)
 module_init(arcnet_rfc1051_init);
 module_exit(arcnet_rfc1051_exit);
 
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1051) module");
 MODULE_LICENSE("GPL");
 
 /* Determine a packet's protocol ID.
diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c
index a4c856282674..0edf35d971c5 100644
--- a/drivers/net/arcnet/rfc1201.c
+++ b/drivers/net/arcnet/rfc1201.c
@@ -35,6 +35,7 @@
 
 #include "arcdevice.h"
 
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1201) module");
 MODULE_LICENSE("GPL");
 
 static __be16 type_trans(struct sk_buff *skb, struct net_device *dev);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4e0600c7b050..cd0683bcca03 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond)) {
+	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
 		xdp_clear_features_flag(bond_dev);
 		return;
 	}
@@ -1819,6 +1819,8 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 	bond_for_each_slave(bond, slave, iter)
 		val &= slave->dev->xdp_features;
 
+	val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
 	xdp_set_features_flag(bond_dev, val);
 }
 
@@ -5909,9 +5911,6 @@ void bond_setup(struct net_device *bond_dev)
 	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		bond_dev->features |= BOND_XFRM_FEATURES;
 #endif /* CONFIG_XFRM_OFFLOAD */
-
-	if (bond_xdp_check(bond))
-		bond_dev->xdp_features = NETDEV_XDP_ACT_MASK;
 }
 
 /* Destroy a bonding device.
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 036d85ef07f5..dfdc039d92a6 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -346,7 +346,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			/* Neither of TDC parameters nor TDC flags are
 			 * provided: do calculation
 			 */
-			can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming,
+			can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt,
 				      &priv->ctrlmode, priv->ctrlmode_supported);
 		} /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly
 		   * turned off. TDC is disabled: do nothing
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
index 237066d30704..14ca42491512 100644
--- a/drivers/net/dsa/dsa_loop_bdinfo.c
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -32,4 +32,5 @@ static int __init dsa_loop_bdinfo_init(void)
 }
 arch_initcall(dsa_loop_bdinfo_init)
 
+MODULE_DESCRIPTION("DSA mock-up switch driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 61b71bcfe396..c3da97abce20 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
 	mutex_lock(&dev->alu_mutex);
 
 	ctrl_addr = IND_ACC_TABLE(table) | addr;
-	ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
 	if (!ret)
-		ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+		ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
 
 	mutex_unlock(&dev->alu_mutex);
 
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 391c4dbdff42..3c1f657593a8 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2838,8 +2838,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port,
 	/* MT753x MAC works in 1G full duplex mode for all up-clocked
 	 * variants.
 	 */
-	if (interface == PHY_INTERFACE_MODE_INTERNAL ||
-	    interface == PHY_INTERFACE_MODE_TRGMII ||
+	if (interface == PHY_INTERFACE_MODE_TRGMII ||
 	    (phy_interface_mode_is_8023z(interface))) {
 		speed = SPEED_1000;
 		duplex = DUPLEX_FULL;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 383b3c4d6f59..614cabb5c1b0 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad,
 	int err;
 
 	if (!chip->info->ops->phy_read_c45)
-		return -EOPNOTSUPP;
+		return 0xffff;
 
 	mv88e6xxx_reg_lock(chip);
 	err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val);
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index c51f40960961..7a864329cb72 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -2051,12 +2051,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	priv->info = of_device_get_match_data(priv->dev);
 
 	priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset",
-						   GPIOD_ASIS);
+						   GPIOD_OUT_HIGH);
 	if (IS_ERR(priv->reset_gpio))
 		return PTR_ERR(priv->reset_gpio);
 
 	if (priv->reset_gpio) {
-		gpiod_set_value_cansleep(priv->reset_gpio, 1);
 		/* The active low duration must be greater than 10 ms
 		 * and checkpatch.pl wants 20 ms.
 		 */
diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig
index da3bdd302502..760a9a60bc15 100644
--- a/drivers/net/ethernet/adi/Kconfig
+++ b/drivers/net/ethernet/adi/Kconfig
@@ -21,6 +21,7 @@ config ADIN1110
 	tristate "Analog Devices ADIN1110 MAC-PHY"
 	depends on SPI && NET_SWITCHDEV
 	select CRC8
+	select PHYLIB
 	help
 	  Say yes here to build support for Analog Devices ADIN1110
 	  Low Power 10BASE-T1L Ethernet MAC-PHY.
diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c
index 5beadabc2136..ea773cfa0af6 100644
--- a/drivers/net/ethernet/amd/pds_core/adminq.c
+++ b/drivers/net/ethernet/amd/pds_core/adminq.c
@@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 	return nq_work;
 }
 
+static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc)
+{
+	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) ||
+	    pdsc->state & BIT_ULL(PDSC_S_FW_DEAD))
+		return false;
+
+	return refcount_inc_not_zero(&pdsc->adminq_refcnt);
+}
+
 void pdsc_process_adminq(struct pdsc_qcq *qcq)
 {
 	union pds_core_adminq_comp *comp;
@@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 	int aq_work = 0;
 	int credits;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return;
 	}
@@ -124,6 +133,7 @@ credits:
 		pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx],
 				      credits,
 				      PDS_CORE_INTR_CRED_REARM);
+	refcount_dec(&pdsc->adminq_refcnt);
 }
 
 void pdsc_work_thread(struct work_struct *work)
@@ -135,18 +145,20 @@ void pdsc_work_thread(struct work_struct *work)
 
 irqreturn_t pdsc_adminq_isr(int irq, void *data)
 {
-	struct pdsc_qcq *qcq = data;
-	struct pdsc *pdsc = qcq->pdsc;
+	struct pdsc *pdsc = data;
+	struct pdsc_qcq *qcq;
 
-	/* Don't process AdminQ when shutting down */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+	/* Don't process AdminQ when it's not up */
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return IRQ_HANDLED;
 	}
 
+	qcq = &pdsc->adminqcq;
 	queue_work(pdsc->wq, &qcq->work);
 	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
+	refcount_dec(&pdsc->adminq_refcnt);
 
 	return IRQ_HANDLED;
 }
@@ -179,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 
 	/* Check that the FW is running */
 	if (!pdsc_is_fw_running(pdsc)) {
-		u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-		dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
-			 __func__, fw_status);
+		if (pdsc->info_regs) {
+			u8 fw_status =
+				ioread8(&pdsc->info_regs->fw_status);
+
+			dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
+				 __func__, fw_status);
+		} else {
+			dev_info(pdsc->dev, "%s: post failed - BARs not setup\n",
+				 __func__);
+		}
 		ret = -ENXIO;
 
 		goto err_out_unlock;
@@ -230,6 +248,12 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	int err = 0;
 	int index;
 
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n",
+			__func__, cmd->opcode);
+		return -ENXIO;
+	}
+
 	wc.qcq = &pdsc->adminqcq;
 	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
 	if (index < 0) {
@@ -248,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 			break;
 
 		if (!pdsc_is_fw_running(pdsc)) {
-			u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
-
-			dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
-				__func__, fw_status);
+			if (pdsc->info_regs) {
+				u8 fw_status =
+					ioread8(&pdsc->info_regs->fw_status);
+
+				dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
+					__func__, fw_status);
+			} else {
+				dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n",
+					__func__);
+			}
 			err = -ENXIO;
 			break;
 		}
@@ -285,6 +315,8 @@ err_out:
 			queue_work(pdsc->wq, &pdsc->health_work);
 	}
 
+	refcount_dec(&pdsc->adminq_refcnt);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(pdsc_adminq_post);
diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c
index 11c23a7f3172..fd1a5149c003 100644
--- a/drivers/net/ethernet/amd/pds_core/auxbus.c
+++ b/drivers/net/ethernet/amd/pds_core/auxbus.c
@@ -160,23 +160,19 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf,
 	if (err < 0) {
 		dev_warn(cf->dev, "auxiliary_device_init of %s failed: %pe\n",
 			 name, ERR_PTR(err));
-		goto err_out;
+		kfree(padev);
+		return ERR_PTR(err);
 	}
 
 	err = auxiliary_device_add(aux_dev);
 	if (err) {
 		dev_warn(cf->dev, "auxiliary_device_add of %s failed: %pe\n",
 			 name, ERR_PTR(err));
-		goto err_out_uninit;
+		auxiliary_device_uninit(aux_dev);
+		return ERR_PTR(err);
 	}
 
 	return padev;
-
-err_out_uninit:
-	auxiliary_device_uninit(aux_dev);
-err_out:
-	kfree(padev);
-	return ERR_PTR(err);
 }
 
 int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf)
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 0d2091e9eb28..7658a7286767 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 
 	snprintf(name, sizeof(name), "%s-%d-%s",
 		 PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name);
-	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq);
+	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc);
 	if (index < 0)
 		return index;
 	qcq->intx = index;
@@ -404,10 +404,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 	int numdescs;
 	int err;
 
-	if (init)
-		err = pdsc_dev_init(pdsc);
-	else
-		err = pdsc_dev_reinit(pdsc);
+	err = pdsc_dev_init(pdsc);
 	if (err)
 		return err;
 
@@ -450,6 +447,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 		pdsc_debugfs_add_viftype(pdsc);
 	}
 
+	refcount_set(&pdsc->adminq_refcnt, 1);
 	clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
 	return 0;
 
@@ -464,6 +462,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 
 	if (!pdsc->pdev->is_virtfn)
 		pdsc_devcmd_reset(pdsc);
+	if (pdsc->adminqcq.work.func)
+		cancel_work_sync(&pdsc->adminqcq.work);
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
@@ -476,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		for (i = 0; i < pdsc->nintrs; i++)
 			pdsc_intr_free(pdsc, i);
 
-		if (removing) {
-			kfree(pdsc->intr_info);
-			pdsc->intr_info = NULL;
-		}
+		kfree(pdsc->intr_info);
+		pdsc->intr_info = NULL;
+		pdsc->nintrs = 0;
 	}
 
 	if (pdsc->kern_dbpage) {
@@ -487,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		pdsc->kern_dbpage = NULL;
 	}
 
+	pci_free_irq_vectors(pdsc->pdev);
 	set_bit(PDSC_S_FW_DEAD, &pdsc->state);
 }
 
@@ -512,6 +512,24 @@ void pdsc_stop(struct pdsc *pdsc)
 					   PDS_CORE_INTR_MASK_SET);
 }
 
+static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc)
+{
+	/* The driver initializes the adminq_refcnt to 1 when the adminq is
+	 * allocated and ready for use. Other users/requesters will increment
+	 * the refcnt while in use. If the refcnt is down to 1 then the adminq
+	 * is not in use and the refcnt can be cleared and adminq freed. Before
+	 * calling this function the driver will set PDSC_S_FW_DEAD, which
+	 * prevent subsequent attempts to use the adminq and increment the
+	 * refcnt to fail. This guarantees that this function will eventually
+	 * exit.
+	 */
+	while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) {
+		dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n",
+				    __func__);
+		cpu_relax();
+	}
+}
+
 void pdsc_fw_down(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
@@ -527,6 +545,8 @@ void pdsc_fw_down(struct pdsc *pdsc)
 	if (pdsc->pdev->is_virtfn)
 		return;
 
+	pdsc_adminq_wait_and_dec_once_unused(pdsc);
+
 	/* Notify clients of fw_down */
 	if (pdsc->fw_reporter)
 		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
@@ -577,7 +597,13 @@ err_out:
 
 static void pdsc_check_pci_health(struct pdsc *pdsc)
 {
-	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+	u8 fw_status;
+
+	/* some sort of teardown already in progress */
+	if (!pdsc->info_regs)
+		return;
+
+	fw_status = ioread8(&pdsc->info_regs->fw_status);
 
 	/* is PCI broken? */
 	if (fw_status != PDS_RC_BAD_PCI)
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index e35d3e7006bf..110c4b826b22 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -184,6 +184,7 @@ struct pdsc {
 	struct mutex devcmd_lock;	/* lock for dev_cmd operations */
 	struct mutex config_lock;	/* lock for configuration operations */
 	spinlock_t adminq_lock;		/* lock for adminq operations */
+	refcount_t adminq_refcnt;
 	struct pds_core_dev_info_regs __iomem *info_regs;
 	struct pds_core_dev_cmd_regs __iomem *cmd_regs;
 	struct pds_core_intr __iomem *intr_ctrl;
@@ -280,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 		       union pds_core_dev_comp *comp, int max_seconds);
 int pdsc_devcmd_init(struct pdsc *pdsc);
 int pdsc_devcmd_reset(struct pdsc *pdsc);
-int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
 void pdsc_reset_prepare(struct pci_dev *pdev);
diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index 8ec392299b7d..4e8579ca1c8c 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity);
 
 void pdsc_debugfs_add_ident(struct pdsc *pdsc)
 {
+	/* This file will already exist in the reset flow */
+	if (debugfs_lookup("identity", pdsc->dentry))
+		return;
+
 	debugfs_create_file("identity", 0400, pdsc->dentry,
 			    pdsc, &identity_fops);
 }
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index 31940b857e0e..e65a1632df50 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -57,6 +57,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code)
 
 bool pdsc_is_fw_running(struct pdsc *pdsc)
 {
+	if (!pdsc->info_regs)
+		return false;
+
 	pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status);
 	pdsc->last_fw_time = jiffies;
 	pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat);
@@ -182,13 +185,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 {
 	int err;
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd));
 	pdsc_devcmd_dbell(pdsc);
 	err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds);
-	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
 		queue_work(pdsc->wq, &pdsc->health_work);
+	else
+		memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	return err;
 }
@@ -309,13 +316,6 @@ static int pdsc_identify(struct pdsc *pdsc)
 	return 0;
 }
 
-int pdsc_dev_reinit(struct pdsc *pdsc)
-{
-	pdsc_init_devinfo(pdsc);
-
-	return pdsc_identify(pdsc);
-}
-
 int pdsc_dev_init(struct pdsc *pdsc)
 {
 	unsigned int nintrs;
diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index e9948ea5bbcd..54864f27c87a 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -111,7 +111,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 	mutex_lock(&pdsc->devcmd_lock);
 	err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2);
-	memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
+	if (!err)
+		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
 	if (err && err != -EIO)
 		return err;
diff --git a/drivers/net/ethernet/amd/pds_core/fw.c b/drivers/net/ethernet/amd/pds_core/fw.c
index 90a811f3878a..fa626719e68d 100644
--- a/drivers/net/ethernet/amd/pds_core/fw.c
+++ b/drivers/net/ethernet/amd/pds_core/fw.c
@@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
 
 	dev_info(pdsc->dev, "Installing firmware\n");
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	dl = priv_to_devlink(pdsc);
 	devlink_flash_update_status_notify(dl, "Preparing to flash",
 					   NULL, 0, 0);
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 3080898d7b95..0050c5894563 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc)
 	struct pdsc_dev_bar *bars = pdsc->bars;
 	unsigned int i;
 
+	pdsc->info_regs = NULL;
+	pdsc->cmd_regs = NULL;
+	pdsc->intr_status = NULL;
+	pdsc->intr_ctrl = NULL;
+
 	for (i = 0; i < PDS_CORE_BARS_MAX; i++) {
 		if (bars[i].vaddr)
 			pci_iounmap(pdsc->pdev, bars[i].vaddr);
@@ -293,7 +298,7 @@ err_out_stop:
 err_out_teardown:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
-	del_timer_sync(&pdsc->wdtimer);
+	timer_shutdown_sync(&pdsc->wdtimer);
 	if (pdsc->wq)
 		destroy_workqueue(pdsc->wq);
 	mutex_destroy(&pdsc->config_lock);
@@ -420,7 +425,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 */
 		pdsc_sriov_configure(pdev, 0);
 
-		del_timer_sync(&pdsc->wdtimer);
+		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
 			destroy_workqueue(pdsc->wq);
 
@@ -433,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		mutex_destroy(&pdsc->config_lock);
 		mutex_destroy(&pdsc->devcmd_lock);
 
-		pci_free_irq_vectors(pdev);
 		pdsc_unmap_bars(pdsc);
 		pci_release_regions(pdev);
 	}
@@ -445,13 +449,32 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+static void pdsc_stop_health_thread(struct pdsc *pdsc)
+{
+	if (pdsc->pdev->is_virtfn)
+		return;
+
+	timer_shutdown_sync(&pdsc->wdtimer);
+	if (pdsc->health_work.func)
+		cancel_work_sync(&pdsc->health_work);
+}
+
+static void pdsc_restart_health_thread(struct pdsc *pdsc)
+{
+	if (pdsc->pdev->is_virtfn)
+		return;
+
+	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
+	mod_timer(&pdsc->wdtimer, jiffies + 1);
+}
+
 void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
+	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
-	pci_free_irq_vectors(pdev);
 	pdsc_unmap_bars(pdsc);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -486,6 +509,7 @@ void pdsc_reset_done(struct pci_dev *pdev)
 	}
 
 	pdsc_fw_up(pdsc);
+	pdsc_restart_health_thread(pdsc);
 }
 
 static const struct pci_error_handlers pdsc_err_handler = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index abd4832e4ed2..5acb3e16b567 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -993,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
 	return 0;
 
 err_exit_hwts_rx:
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 err_exit_ptp_rx:
 	aq_ring_free(&aq_ptp->ptp_rx);
 err_exit_ptp_tx:
@@ -1011,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic)
 
 	aq_ring_free(&aq_ptp->ptp_tx);
 	aq_ring_free(&aq_ptp->ptp_rx);
-	aq_ring_free(&aq_ptp->hwts_rx);
+	aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
 
 	aq_ptp_skb_ring_release(&aq_ptp->skb_ring);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index cda8597b4e14..f7433abd6591 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -919,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self)
 	}
 }
 
+void aq_ring_hwts_rx_free(struct aq_ring_s *self)
+{
+	if (!self)
+		return;
+
+	if (self->dx_ring) {
+		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
+				  self->size * self->dx_size + AQ_CFG_RXDS_DEF,
+				  self->dx_ring, self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
+}
+
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
 {
 	unsigned int count;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 52847310740a..d627ace850ff 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -210,6 +210,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self);
 int aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
 			  struct aq_nic_s *aq_nic, unsigned int idx,
 			  unsigned int size, unsigned int dx_size);
+void aq_ring_hwts_rx_free(struct aq_ring_s *self);
 void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic);
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data);
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 29b04a274d07..80245c65cc90 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -535,9 +535,6 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 	int j = 0, i;
 
 	for (i = 0; i < NUM_NET_FILTERS; i++) {
-		if (j == *rule_cnt)
-			return -EMSGSIZE;
-
 		if (!priv->net_filters[i].claimed ||
 		    priv->net_filters[i].port != intf->port)
 			continue;
@@ -547,6 +544,9 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs,
 		    priv->net_filters[i - 1].wake_filter)
 			continue;
 
+		if (j == *rule_cnt)
+			return -EMSGSIZE;
+
 		rule_locs[j++] = priv->net_filters[i].fs.location;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 53e542881255..6ad1366270f7 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -684,6 +684,8 @@ static int bcmasp_init_rx(struct bcmasp_intf *intf)
 
 	intf->rx_buf_order = get_order(RING_BUFFER_SIZE);
 	buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order);
+	if (!buffer_pg)
+		return -ENOMEM;
 
 	dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE,
 			   DMA_FROM_DEVICE);
@@ -1048,6 +1050,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 			netdev_err(dev, "could not attach to PHY\n");
 			goto err_phy_disable;
 		}
+
+		/* Indicate that the MAC is responsible for PHY PM */
+		phydev->mac_managed_pm = true;
 	} else if (!intf->wolopts) {
 		ret = phy_resume(dev->phydev);
 		if (ret)
@@ -1092,6 +1097,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
 	return 0;
 
 err_reclaim_tx:
+	netif_napi_del(&intf->tx_napi);
 	bcmasp_reclaim_free_all_tx(intf);
 err_phy_disconnect:
 	if (phydev)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index adad188e38b8..cc07660330f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -684,7 +684,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_WARN_ONCE(bp->dev,
+		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 31191b520b58..c32174484a96 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1091,10 +1091,10 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
  * Free all TxQs buffers and then notify TX_E_CLEANUP_DONE to Tx fsm.
  */
 static void
-bnad_tx_cleanup(struct delayed_work *work)
+bnad_tx_cleanup(struct work_struct *work)
 {
 	struct bnad_tx_info *tx_info =
-		container_of(work, struct bnad_tx_info, tx_cleanup_work);
+		container_of(work, struct bnad_tx_info, tx_cleanup_work.work);
 	struct bnad *bnad = NULL;
 	struct bna_tcb *tcb;
 	unsigned long flags;
@@ -1170,7 +1170,7 @@ bnad_cb_rx_stall(struct bnad *bnad, struct bna_rx *rx)
  * Free all RxQs buffers and then notify RX_E_CLEANUP_DONE to Rx fsm.
  */
 static void
-bnad_rx_cleanup(void *work)
+bnad_rx_cleanup(struct work_struct *work)
 {
 	struct bnad_rx_info *rx_info =
 		container_of(work, struct bnad_rx_info, rx_cleanup_work);
@@ -1991,8 +1991,7 @@ bnad_setup_tx(struct bnad *bnad, u32 tx_id)
 	}
 	tx_info->tx = tx;
 
-	INIT_DELAYED_WORK(&tx_info->tx_cleanup_work,
-			(work_func_t)bnad_tx_cleanup);
+	INIT_DELAYED_WORK(&tx_info->tx_cleanup_work, bnad_tx_cleanup);
 
 	/* Register ISR for the Tx object */
 	if (intr_info->intr_type == BNA_INTR_T_MSIX) {
@@ -2248,8 +2247,7 @@ bnad_setup_rx(struct bnad *bnad, u32 rx_id)
 	rx_info->rx = rx;
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
-	INIT_WORK(&rx_info->rx_cleanup_work,
-			(work_func_t)(bnad_rx_cleanup));
+	INIT_WORK(&rx_info->rx_cleanup_work, bnad_rx_cleanup);
 
 	/*
 	 * Init NAPI, so that state is set to NAPI_STATE_SCHED,
diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.c b/drivers/net/ethernet/cisco/enic/vnic_vic.c
index 20fcb20b42ed..66b577835338 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_vic.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_vic.c
@@ -49,7 +49,8 @@ int vic_provinfo_add_tlv(struct vic_provinfo *vp, u16 type, u16 length,
 
 	tlv->type = htons(type);
 	tlv->length = htons(length);
-	memcpy(tlv->value, value, length);
+	unsafe_memcpy(tlv->value, value, length,
+		      /* Flexible array of flexible arrays */);
 
 	vp->num_tlvs = htonl(ntohl(vp->num_tlvs) + 1);
 	vp->length = htonl(ntohl(vp->length) +
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 9aeff2b37a61..64eadd320798 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -719,17 +719,25 @@ static void tsnep_xdp_xmit_flush(struct tsnep_tx *tx)
 
 static bool tsnep_xdp_xmit_back(struct tsnep_adapter *adapter,
 				struct xdp_buff *xdp,
-				struct netdev_queue *tx_nq, struct tsnep_tx *tx)
+				struct netdev_queue *tx_nq, struct tsnep_tx *tx,
+				bool zc)
 {
 	struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
 	bool xmit;
+	u32 type;
 
 	if (unlikely(!xdpf))
 		return false;
 
+	/* no page pool for zero copy */
+	if (zc)
+		type = TSNEP_TX_TYPE_XDP_NDO;
+	else
+		type = TSNEP_TX_TYPE_XDP_TX;
+
 	__netif_tx_lock(tx_nq, smp_processor_id());
 
-	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, TSNEP_TX_TYPE_XDP_TX);
+	xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, type);
 
 	/* Avoid transmit queue timeout since we share it with the slow path */
 	if (xmit)
@@ -1273,7 +1281,7 @@ static bool tsnep_xdp_run_prog(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, false))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
@@ -1323,7 +1331,7 @@ static bool tsnep_xdp_run_prog_zc(struct tsnep_rx *rx, struct bpf_prog *prog,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+		if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, true))
 			goto out_failure;
 		*status |= TSNEP_XDP_TX;
 		return true;
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 9ba15d3183d7..758535adc9ff 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -1073,6 +1073,14 @@ int memac_initialization(struct mac_device *mac_dev,
 	unsigned long		 capabilities;
 	unsigned long		*supported;
 
+	/* The internal connection to the serdes is XGMII, but this isn't
+	 * really correct for the phy mode (which is the external connection).
+	 * However, this is how all older device trees say that they want
+	 * 10GBASE-R (aka XFI), so just convert it for them.
+	 */
+	if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
+		mac_dev->phy_if = PHY_INTERFACE_MODE_10GBASER;
+
 	mac_dev->phylink_ops		= &memac_mac_ops;
 	mac_dev->set_promisc		= memac_set_promiscuous;
 	mac_dev->change_addr		= memac_modify_mac_address;
@@ -1139,7 +1147,7 @@ int memac_initialization(struct mac_device *mac_dev,
 	 * (and therefore that xfi_pcs cannot be set). If we are defaulting to
 	 * XGMII, assume this is for XFI. Otherwise, assume it is for SGMII.
 	 */
-	if (err && mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
+	if (err && mac_dev->phy_if == PHY_INTERFACE_MODE_10GBASER)
 		memac->xfi_pcs = pcs;
 	else
 		memac->sgmii_pcs = pcs;
@@ -1153,14 +1161,6 @@ int memac_initialization(struct mac_device *mac_dev,
 		goto _return_fm_mac_free;
 	}
 
-	/* The internal connection to the serdes is XGMII, but this isn't
-	 * really correct for the phy mode (which is the external connection).
-	 * However, this is how all older device trees say that they want
-	 * 10GBASE-R (aka XFI), so just convert it for them.
-	 */
-	if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII)
-		mac_dev->phy_if = PHY_INTERFACE_MODE_10GBASER;
-
 	/* TODO: The following interface modes are supported by (some) hardware
 	 * but not by this driver:
 	 * - 1000BASE-KX
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 7a8dc5386fff..76615d47e055 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -356,7 +356,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
 
 static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 					struct gve_rx_slot_page_info *page_info,
-					u16 packet_buffer_size, u16 len,
+					unsigned int truesize, u16 len,
 					struct gve_rx_ctx *ctx)
 {
 	u32 offset = page_info->page_offset + page_info->pad;
@@ -389,10 +389,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 	if (skb != ctx->skb_head) {
 		ctx->skb_head->len += len;
 		ctx->skb_head->data_len += len;
-		ctx->skb_head->truesize += packet_buffer_size;
+		ctx->skb_head->truesize += truesize;
 	}
 	skb_add_rx_frag(skb, num_frags, page_info->page,
-			offset, len, packet_buffer_size);
+			offset, len, truesize);
 
 	return ctx->skb_head;
 }
@@ -486,7 +486,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 
 		memcpy(alloc_page_info.page_address, src, page_info->pad + len);
 		skb = gve_rx_add_frags(napi, &alloc_page_info,
-				       rx->packet_buffer_size,
+				       PAGE_SIZE,
 				       len, ctx);
 
 		u64_stats_update_begin(&rx->statss);
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index a187582d2299..ba9c19e6994c 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of
  * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n)
  * bits to count nanoseconds leaving the rest for fractional nonseconds.
+ *
+ * Any given INCVALUE also has an associated maximum adjustment value. This
+ * maximum adjustment value is the largest increase (or decrease) which can be
+ * safely applied without overflowing the INCVALUE. Since INCVALUE has
+ * a maximum range of 24 bits, its largest value is 0xFFFFFF.
+ *
+ * To understand where the maximum value comes from, consider the following
+ * equation:
+ *
+ *   new_incval = base_incval + (base_incval * adjustment) / 1billion
+ *
+ * To avoid overflow that means:
+ *   max_incval = base_incval + (base_incval * max_adj) / billion
+ *
+ * Re-arranging:
+ *   max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion)
  */
 #define INCVALUE_96MHZ		125
 #define INCVALUE_SHIFT_96MHZ	17
 #define INCPERIOD_SHIFT_96MHZ	2
 #define INCPERIOD_96MHZ		(12 >> INCPERIOD_SHIFT_96MHZ)
+#define MAX_PPB_96MHZ		23999900 /* 23,999,900 ppb */
 
 #define INCVALUE_25MHZ		40
 #define INCVALUE_SHIFT_25MHZ	18
 #define INCPERIOD_25MHZ		1
+#define MAX_PPB_25MHZ		599999900 /* 599,999,900 ppb */
 
 #define INCVALUE_24MHZ		125
 #define INCVALUE_SHIFT_24MHZ	14
 #define INCPERIOD_24MHZ		3
+#define MAX_PPB_24MHZ		999999999 /* 999,999,999 ppb */
 
 #define INCVALUE_38400KHZ	26
 #define INCVALUE_SHIFT_38400KHZ	19
 #define INCPERIOD_38400KHZ	1
+#define MAX_PPB_38400KHZ	230769100 /* 230,769,100 ppb */
 
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index a2788fd5f8bb..19e450a5bd31 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -2559,7 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw)
 		hw->phy.ops.write_reg_page(hw, BM_RAR_H(i),
 					   (u16)(mac_reg & 0xFFFF));
 		hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i),
-					   FIELD_GET(E1000_RAH_AV, mac_reg));
+					   (u16)((mac_reg & E1000_RAH_AV) >> 16));
 	}
 
 	e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg);
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 02d871bc112a..bbcfd529399b 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		break;
 	case e1000_pch_lpt:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
+		break;
 	case e1000_pch_spt:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		break;
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
@@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
 	case e1000_pch_nvp:
-		if ((hw->mac.type < e1000_pch_lpt) ||
-		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
-			adapter->ptp_clock_info.max_adj = 24000000 - 1;
-			break;
-		}
-		fallthrough;
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
-		adapter->ptp_clock_info.max_adj = 600000000 - 1;
+		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
 		break;
 	default:
 		break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 9d88ed6105fd..8db1eb0c1768 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1523,7 +1523,7 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
 		reg = rd32(hw, I40E_PRTDCB_RETSTCC(i));
 		reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK     |
 			 I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK |
-			 I40E_PRTDCB_RETSTCC_ETSTC_SHIFT);
+			 I40E_PRTDCB_RETSTCC_ETSTC_MASK);
 		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK,
 				  bw_share[i]);
 		reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 6b60dc9b7736..d76497566e40 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -43,7 +43,7 @@
 #define I40E_LLDP_TLV_SUBTYPE_SHIFT	0
 #define I40E_LLDP_TLV_SUBTYPE_MASK	(0xFF << I40E_LLDP_TLV_SUBTYPE_SHIFT)
 #define I40E_LLDP_TLV_OUI_SHIFT		8
-#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFF << I40E_LLDP_TLV_OUI_SHIFT)
+#define I40E_LLDP_TLV_OUI_MASK		(0xFFFFFFU << I40E_LLDP_TLV_OUI_SHIFT)
 
 /* Defines for IEEE ETS TLV */
 #define I40E_IEEE_ETS_MAXTC_SHIFT	0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6e7fd473abfd..89a3401d20ab 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4926,27 +4926,23 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
 void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	int pf_q, err, q_end;
+	u32 pf_q, tx_q_end, rx_q_end;
 
 	/* When port TX is suspended, don't wait */
 	if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
 		return i40e_vsi_stop_rings_no_wait(vsi);
 
-	q_end = vsi->base_queue + vsi->num_queue_pairs;
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
-		i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
+	tx_q_end = vsi->base_queue +
+		vsi->alloc_queue_pairs * (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
+	for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
+		i40e_pre_tx_queue_cfg(&pf->hw, pf_q, false);
 
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) {
-		err = i40e_control_wait_rx_q(pf, pf_q, false);
-		if (err)
-			dev_info(&pf->pdev->dev,
-				 "VSI seid %d Rx ring %d disable timeout\n",
-				 vsi->seid, pf_q);
-	}
+	rx_q_end = vsi->base_queue + vsi->num_queue_pairs;
+	for (pf_q = vsi->base_queue; pf_q < rx_q_end; pf_q++)
+		i40e_control_rx_q(pf, pf_q, false);
 
 	msleep(I40E_DISABLE_TX_GAP_MSEC);
-	pf_q = vsi->base_queue;
-	for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+	for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
 		wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
 
 	i40e_vsi_wait_queues_disabled(vsi);
@@ -5360,7 +5356,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
 {
 	int v, ret = 0;
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v]) {
 			ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
 			if (ret)
@@ -13564,9 +13560,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair)
 		return err;
 
 	i40e_queue_pair_disable_irq(vsi, queue_pair);
+	i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
 	err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */);
 	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
-	i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
 	i40e_queue_pair_clean_rings(vsi, queue_pair);
 	i40e_queue_pair_reset_stats(vsi, queue_pair);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index af4269330581..ce1f11b8ad65 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -567,8 +567,7 @@ static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min)
  **/
 static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min)
 {
-	return (hw->aq.fw_maj_ver > maj ||
-		(hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min));
+	return (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min);
 }
 
 #endif /* _I40E_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 908cdbd3ec5d..b34c71770887 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2848,6 +2848,24 @@ error_param:
 				      (u8 *)&stats, sizeof(stats));
 }
 
+/**
+ * i40e_can_vf_change_mac
+ * @vf: pointer to the VF info
+ *
+ * Return true if the VF is allowed to change its MAC filters, false otherwise
+ */
+static bool i40e_can_vf_change_mac(struct i40e_vf *vf)
+{
+	/* If the VF MAC address has been set administratively (via the
+	 * ndo_set_vf_mac command), then deny permission to the VF to
+	 * add/delete unicast MAC addresses, unless the VF is trusted
+	 */
+	if (vf->pf_set_mac && !vf->trusted)
+		return false;
+
+	return true;
+}
+
 #define I40E_MAX_MACVLAN_PER_HW 3072
 #define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW /	\
 	(num_ports))
@@ -2907,8 +2925,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
 		 * The VF may request to set the MAC address filter already
 		 * assigned to it so do not return an error in that case.
 		 */
-		if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
-		    !is_multicast_ether_addr(addr) && vf->pf_set_mac &&
+		if (!i40e_can_vf_change_mac(vf) &&
+		    !is_multicast_ether_addr(addr) &&
 		    !ether_addr_equal(addr, vf->default_lan_addr.addr)) {
 			dev_err(&pf->pdev->dev,
 				"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
@@ -3114,19 +3132,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 			ret = -EINVAL;
 			goto error_param;
 		}
-		if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
-			was_unimac_deleted = true;
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 	/* delete addresses from the list */
-	for (i = 0; i < al->num_elements; i++)
+	for (i = 0; i < al->num_elements; i++) {
+		const u8 *addr = al->list[i].addr;
+
+		/* Allow to delete VF primary MAC only if it was not set
+		 * administratively by PF or if VF is trusted.
+		 */
+		if (ether_addr_equal(addr, vf->default_lan_addr.addr) &&
+		    i40e_can_vf_change_mac(vf))
+			was_unimac_deleted = true;
+		else
+			continue;
+
 		if (i40e_del_mac_filter(vsi, al->list[i].addr)) {
 			ret = -EINVAL;
 			spin_unlock_bh(&vsi->mac_filter_hash_lock);
 			goto error_param;
 		}
+	}
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 7ac847718882..c979192e44d1 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -190,15 +190,13 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	q_vector = vsi->q_vectors[v_idx];
 
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
-		if (vsi->netdev)
-			netif_queue_set_napi(vsi->netdev, tx_ring->q_index,
-					     NETDEV_QUEUE_TYPE_TX, NULL);
+		ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
+				   NULL);
 		tx_ring->q_vector = NULL;
 	}
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
-		if (vsi->netdev)
-			netif_queue_set_napi(vsi->netdev, rx_ring->q_index,
-					     NETDEV_QUEUE_TYPE_RX, NULL);
+		ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
+				   NULL);
 		rx_ring->q_vector = NULL;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index b9c5eced6326..bd9b1fed74ab 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -31,6 +31,26 @@ static const char * const pin_type_name[] = {
 };
 
 /**
+ * ice_dpll_is_reset - check if reset is in progress
+ * @pf: private board structure
+ * @extack: error reporting
+ *
+ * If reset is in progress, fill extack with error.
+ *
+ * Return:
+ * * false - no reset in progress
+ * * true - reset in progress
+ */
+static bool ice_dpll_is_reset(struct ice_pf *pf, struct netlink_ext_ack *extack)
+{
+	if (ice_is_reset_in_progress(pf->state)) {
+		NL_SET_ERR_MSG(extack, "PF reset in progress");
+		return true;
+	}
+	return false;
+}
+
+/**
  * ice_dpll_pin_freq_set - set pin's frequency
  * @pf: private board structure
  * @pin: pointer to a pin
@@ -109,6 +129,9 @@ ice_dpll_frequency_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_pin_freq_set(pf, p, pin_type, frequency, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -254,6 +277,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv,
  * ice_dpll_pin_enable - enable a pin on dplls
  * @hw: board private hw structure
  * @pin: pointer to a pin
+ * @dpll_idx: dpll index to connect to output pin
  * @pin_type: type of pin being enabled
  * @extack: error reporting
  *
@@ -266,7 +290,7 @@ ice_dpll_output_frequency_get(const struct dpll_pin *pin, void *pin_priv,
  */
 static int
 ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
-		    enum ice_dpll_pin_type pin_type,
+		    u8 dpll_idx, enum ice_dpll_pin_type pin_type,
 		    struct netlink_ext_ack *extack)
 {
 	u8 flags = 0;
@@ -280,10 +304,12 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 		ret = ice_aq_set_input_pin_cfg(hw, pin->idx, 0, flags, 0, 0);
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
+		flags = ICE_AQC_SET_CGU_OUT_CFG_UPDATE_SRC_SEL;
 		if (pin->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)
 			flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN;
 		flags |= ICE_AQC_SET_CGU_OUT_CFG_OUT_EN;
-		ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, 0, 0, 0);
+		ret = ice_aq_set_output_pin_cfg(hw, pin->idx, flags, dpll_idx,
+						0, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -370,7 +396,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	case ICE_DPLL_PIN_TYPE_INPUT:
 		ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL,
 					       NULL, &pin->flags[0],
-					       &pin->freq, NULL);
+					       &pin->freq, &pin->phase_adjust);
 		if (ret)
 			goto err;
 		if (ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN & pin->flags[0]) {
@@ -398,14 +424,27 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 		break;
 	case ICE_DPLL_PIN_TYPE_OUTPUT:
 		ret = ice_aq_get_output_pin_cfg(&pf->hw, pin->idx,
-						&pin->flags[0], NULL,
+						&pin->flags[0], &parent,
 						&pin->freq, NULL);
 		if (ret)
 			goto err;
-		if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0])
-			pin->state[0] = DPLL_PIN_STATE_CONNECTED;
-		else
-			pin->state[0] = DPLL_PIN_STATE_DISCONNECTED;
+
+		parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL;
+		if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) {
+			pin->state[pf->dplls.eec.dpll_idx] =
+				parent == pf->dplls.eec.dpll_idx ?
+				DPLL_PIN_STATE_CONNECTED :
+				DPLL_PIN_STATE_DISCONNECTED;
+			pin->state[pf->dplls.pps.dpll_idx] =
+				parent == pf->dplls.pps.dpll_idx ?
+				DPLL_PIN_STATE_CONNECTED :
+				DPLL_PIN_STATE_DISCONNECTED;
+		} else {
+			pin->state[pf->dplls.eec.dpll_idx] =
+				DPLL_PIN_STATE_DISCONNECTED;
+			pin->state[pf->dplls.pps.dpll_idx] =
+				DPLL_PIN_STATE_DISCONNECTED;
+		}
 		break;
 	case ICE_DPLL_PIN_TYPE_RCLK_INPUT:
 		for (parent = 0; parent < pf->dplls.rclk.num_parents;
@@ -568,9 +607,13 @@ ice_dpll_pin_state_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	if (enable)
-		ret = ice_dpll_pin_enable(&pf->hw, p, pin_type, extack);
+		ret = ice_dpll_pin_enable(&pf->hw, p, d->dpll_idx, pin_type,
+					  extack);
 	else
 		ret = ice_dpll_pin_disable(&pf->hw, p, pin_type, extack);
 	if (!ret)
@@ -603,6 +646,11 @@ ice_dpll_output_state_set(const struct dpll_pin *pin, void *pin_priv,
 			  struct netlink_ext_ack *extack)
 {
 	bool enable = state == DPLL_PIN_STATE_CONNECTED;
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+
+	if (!enable && p->state[d->dpll_idx] == DPLL_PIN_STATE_DISCONNECTED)
+		return 0;
 
 	return ice_dpll_pin_state_set(pin, pin_priv, dpll, dpll_priv, enable,
 				      extack, ICE_DPLL_PIN_TYPE_OUTPUT);
@@ -665,14 +713,16 @@ ice_dpll_pin_state_get(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_pin_state_update(pf, p, pin_type, extack);
 	if (ret)
 		goto unlock;
-	if (pin_type == ICE_DPLL_PIN_TYPE_INPUT)
+	if (pin_type == ICE_DPLL_PIN_TYPE_INPUT ||
+	    pin_type == ICE_DPLL_PIN_TYPE_OUTPUT)
 		*state = p->state[d->dpll_idx];
-	else if (pin_type == ICE_DPLL_PIN_TYPE_OUTPUT)
-		*state = p->state[0];
 	ret = 0;
 unlock:
 	mutex_unlock(&pf->dplls.lock);
@@ -790,6 +840,9 @@ ice_dpll_input_prio_set(const struct dpll_pin *pin, void *pin_priv,
 	struct ice_pf *pf = d->pf;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_hw_input_prio_set(pf, d, p, prio, extack);
 	mutex_unlock(&pf->dplls.lock);
@@ -910,6 +963,9 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 	u8 flag, flags_en = 0;
 	int ret;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	switch (type) {
 	case ICE_DPLL_PIN_TYPE_INPUT:
@@ -1069,6 +1125,9 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv,
 	int ret = -EINVAL;
 	u32 hw_idx;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	hw_idx = parent->idx - pf->dplls.base_rclk_idx;
 	if (hw_idx >= pf->dplls.num_inputs)
@@ -1123,6 +1182,9 @@ ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv,
 	int ret = -EINVAL;
 	u32 hw_idx;
 
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+
 	mutex_lock(&pf->dplls.lock);
 	hw_idx = parent->idx - pf->dplls.base_rclk_idx;
 	if (hw_idx >= pf->dplls.num_inputs)
@@ -1305,8 +1367,10 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	struct ice_pf *pf = container_of(d, struct ice_pf, dplls);
 	struct ice_dpll *de = &pf->dplls.eec;
 	struct ice_dpll *dp = &pf->dplls.pps;
-	int ret;
+	int ret = 0;
 
+	if (ice_is_reset_in_progress(pf->state))
+		goto resched;
 	mutex_lock(&pf->dplls.lock);
 	ret = ice_dpll_update_state(pf, de, false);
 	if (!ret)
@@ -1326,6 +1390,7 @@ static void ice_dpll_periodic_work(struct kthread_work *work)
 	ice_dpll_notify_changes(de);
 	ice_dpll_notify_changes(dp);
 
+resched:
 	/* Run twice a second or reschedule if update failed */
 	kthread_queue_delayed_work(d->kworker, &d->work,
 				   ret ? msecs_to_jiffies(10) :
@@ -1532,7 +1597,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf)
 	}
 	if (WARN_ON_ONCE(!vsi || !vsi->netdev))
 		return;
-	netdev_dpll_pin_clear(vsi->netdev);
+	dpll_netdev_pin_clear(vsi->netdev);
 	dpll_pin_put(rclk->pin);
 }
 
@@ -1576,7 +1641,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	}
 	if (WARN_ON((!vsi || !vsi->netdev)))
 		return -EINVAL;
-	netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin);
+	dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin);
 
 	return 0;
 
@@ -2055,6 +2120,7 @@ void ice_dpll_init(struct ice_pf *pf)
 	struct ice_dplls *d = &pf->dplls;
 	int err = 0;
 
+	mutex_init(&d->lock);
 	err = ice_dpll_init_info(pf, cgu);
 	if (err)
 		goto err_exit;
@@ -2067,7 +2133,6 @@ void ice_dpll_init(struct ice_pf *pf)
 	err = ice_dpll_init_pins(pf, cgu);
 	if (err)
 		goto deinit_pps;
-	mutex_init(&d->lock);
 	if (cgu) {
 		err = ice_dpll_init_worker(pf);
 		if (err)
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 2a25323105e5..467372d541d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -152,6 +152,27 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport)
 }
 
 /**
+ * ice_pkg_has_lport_extract - check if lport extraction supported
+ * @hw: HW struct
+ */
+static bool ice_pkg_has_lport_extract(struct ice_hw *hw)
+{
+	int i;
+
+	for (i = 0; i < hw->blk[ICE_BLK_SW].es.count; i++) {
+		u16 offset;
+		u8 fv_prot;
+
+		ice_find_prot_off(hw, ICE_BLK_SW, ICE_SW_DEFAULT_PROFILE, i,
+				  &fv_prot, &offset);
+		if (fv_prot == ICE_FV_PROT_MDID &&
+		    offset == ICE_LP_EXT_BUF_OFFSET)
+			return true;
+	}
+	return false;
+}
+
+/**
  * ice_lag_find_primary - returns pointer to primary interfaces lag struct
  * @lag: local interfaces lag struct
  */
@@ -1206,7 +1227,7 @@ static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
 }
 
 /**
- * ice_lag_init_feature_support_flag - Check for NVM support for LAG
+ * ice_lag_init_feature_support_flag - Check for package and NVM support for LAG
  * @pf: PF struct
  */
 static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
@@ -1219,7 +1240,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
 	else
 		ice_clear_feature_support(pf, ICE_F_ROCE_LAG);
 
-	if (caps->sriov_lag)
+	if (caps->sriov_lag && ice_pkg_has_lport_extract(&pf->hw))
 		ice_set_feature_support(pf, ICE_F_SRIOV_LAG);
 	else
 		ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index ede833dfa658..183b38792ef2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -17,6 +17,9 @@ enum ice_lag_role {
 #define ICE_LAG_INVALID_PORT 0xFF
 
 #define ICE_LAG_RESET_RETRIES		5
+#define ICE_SW_DEFAULT_PROFILE		0
+#define ICE_FV_PROT_MDID		255
+#define ICE_LP_EXT_BUF_OFFSET		32
 
 struct ice_pf;
 struct ice_vf;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 9be724291ef8..fc23dbe302b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2426,7 +2426,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)
 		ice_vsi_map_rings_to_vectors(vsi);
 
 		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi, true);
+		ice_vsi_set_napi_queues(vsi);
 
 		vsi->stat_offsets_loaded = false;
 
@@ -2904,19 +2904,19 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 }
 
 /**
- * ice_queue_set_napi - Set the napi instance for the queue
+ * __ice_queue_set_napi - Set the napi instance for the queue
  * @dev: device to which NAPI and queue belong
  * @queue_index: Index of queue
  * @type: queue type as RX or TX
  * @napi: NAPI context
  * @locked: is the rtnl_lock already held
  *
- * Set the napi instance for the queue
+ * Set the napi instance for the queue. Caller indicates the lock status.
  */
 static void
-ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
-		   enum netdev_queue_type type, struct napi_struct *napi,
-		   bool locked)
+__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+		     enum netdev_queue_type type, struct napi_struct *napi,
+		     bool locked)
 {
 	if (!locked)
 		rtnl_lock();
@@ -2926,26 +2926,79 @@ ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 
 /**
- * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+ * ice_queue_set_napi - Set the napi instance for the queue
+ * @vsi: VSI being configured
+ * @queue_index: Index of queue
+ * @type: queue type as RX or TX
+ * @napi: NAPI context
+ *
+ * Set the napi instance for the queue. The rtnl lock state is derived from the
+ * execution path.
+ */
+void
+ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+		   enum netdev_queue_type type, struct napi_struct *napi)
+{
+	struct ice_pf *pf = vsi->back;
+
+	if (!vsi->netdev)
+		return;
+
+	if (current_work() == &pf->serv_task ||
+	    test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
+	    test_bit(ICE_DOWN, pf->state) ||
+	    test_bit(ICE_SUSPENDED, pf->state))
+		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+				     false);
+	else
+		__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+				     true);
+}
+
+/**
+ * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
  * @q_vector: q_vector pointer
  * @locked: is the rtnl_lock already held
  *
+ * Associate the q_vector napi with all the queue[s] on the vector.
+ * Caller indicates the lock status.
+ */
+void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+{
+	struct ice_rx_ring *rx_ring;
+	struct ice_tx_ring *tx_ring;
+
+	ice_for_each_rx_ring(rx_ring, q_vector->rx)
+		__ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
+				     NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
+				     locked);
+
+	ice_for_each_tx_ring(tx_ring, q_vector->tx)
+		__ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
+				     NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
+				     locked);
+	/* Also set the interrupt number for the NAPI */
+	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+}
+
+/**
+ * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+ * @q_vector: q_vector pointer
+ *
  * Associate the q_vector napi with all the queue[s] on the vector
  */
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
 {
 	struct ice_rx_ring *rx_ring;
 	struct ice_tx_ring *tx_ring;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
-				   locked);
+		ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_RX, &q_vector->napi);
 
 	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
-				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
-				   locked);
+		ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
+				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
 	/* Also set the interrupt number for the NAPI */
 	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
 }
@@ -2953,11 +3006,10 @@ void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
 /**
  * ice_vsi_set_napi_queues
  * @vsi: VSI pointer
- * @locked: is the rtnl_lock already held
  *
  * Associate queue[s] with napi for all vectors
  */
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked)
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 {
 	int i;
 
@@ -2965,7 +3017,7 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked)
 		return;
 
 	ice_for_each_q_vector(vsi, i)
-		ice_q_vector_set_napi_queues(vsi->q_vectors[i], locked);
+		ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
 }
 
 /**
@@ -3140,7 +3192,7 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
 		}
 	}
 
-	tx_ring_stats = vsi_stat->rx_ring_stats;
+	tx_ring_stats = vsi_stat->tx_ring_stats;
 	vsi_stat->tx_ring_stats =
 		krealloc_array(vsi_stat->tx_ring_stats, req_txq,
 			       sizeof(*vsi_stat->tx_ring_stats),
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 71bd27244941..bfcfc582a4c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -91,9 +91,15 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+void
+ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+		   enum netdev_queue_type type, struct napi_struct *napi);
+
+void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+
+void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);
 
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi, bool locked);
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
 
 int ice_vsi_release(struct ice_vsi *vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index dd4a9bc0dfdc..df6a68ab747e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3495,7 +3495,7 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, v_idx) {
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll);
-		ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
+		__ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
 	}
 }
 
@@ -5447,6 +5447,7 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
 		if (ret)
 			goto err_reinit;
 		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+		ice_vsi_set_napi_queues(pf->vsi[v]);
 	}
 
 	ret = ice_req_irq_msix_misc(pf);
@@ -8012,6 +8013,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	pf_sw = pf->first_sw;
 	/* find the attribute in the netlink message */
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
 
 	nla_for_each_nested(attr, br_spec, rem) {
 		__u16 mode;
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index 82bc54fec7f3..a2562f04267f 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -24,7 +24,7 @@
 #define rd64(a, reg)		readq((a)->hw_addr + (reg))
 
 #define ice_flush(a)		rd32((a), GLGEN_STAT)
-#define ICE_M(m, s)		((m) << (s))
+#define ICE_M(m, s)		((m ## U) << (s))
 
 struct ice_dma_mem {
 	void *va;
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index a94a1c48c3de..b0f78c2f2790 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -1068,6 +1068,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 	u16 prev_msix, prev_queues, queues;
 	bool needs_rebuild = false;
+	struct ice_vsi *vsi;
 	struct ice_vf *vf;
 	int id;
 
@@ -1102,6 +1103,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (!vf)
 		return -ENOENT;
 
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi)
+		return -ENOENT;
+
 	prev_msix = vf->num_msix;
 	prev_queues = vf->num_vf_qs;
 
@@ -1122,7 +1127,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
-	if (ice_vf_reconfig_vsi(vf)) {
+	if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) {
 		/* Try to rebuild with previous values */
 		needs_rebuild = true;
 		goto unroll;
@@ -1148,8 +1153,10 @@ unroll:
 	if (vf->first_vector_idx < 0)
 		return -EINVAL;
 
-	if (needs_rebuild)
+	if (needs_rebuild) {
 		ice_vf_reconfig_vsi(vf);
+		ice_vf_init_host_cfg(vf, vsi);
+	}
 
 	ice_ena_vf_mappings(vf);
 	ice_put_vf(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 41ab6d7bbd9e..a508e917ce5f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1072,7 +1072,7 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_OROM_VER_BUILD_SHIFT	8
 #define ICE_OROM_VER_BUILD_MASK		(0xffff << ICE_OROM_VER_BUILD_SHIFT)
 #define ICE_OROM_VER_SHIFT		24
-#define ICE_OROM_VER_MASK		(0xff << ICE_OROM_VER_SHIFT)
+#define ICE_OROM_VER_MASK		(0xffU << ICE_OROM_VER_SHIFT)
 #define ICE_SR_PFA_PTR			0x40
 #define ICE_SR_1ST_NVM_BANK_PTR		0x42
 #define ICE_SR_NVM_BANK_SIZE		0x43
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index c925813ec9ca..6f2328a049bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 		vf->driver_caps = *(u32 *)msg;
 	else
 		vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 |
-				  VIRTCHNL_VF_OFFLOAD_RSS_REG |
 				  VIRTCHNL_VF_OFFLOAD_VLAN;
 
 	vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2;
@@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi,
 						    vf->driver_caps);
 
-	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) {
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF;
-	} else {
-		if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ)
-			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ;
-		else
-			vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG;
-	}
 
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index 5e19d48a05b4..d796dbd2a440 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -13,8 +13,6 @@
  * - opcodes needed by VF when caps are activated
  *
  * Caps that don't use new opcodes (no opcodes should be allowed):
- * - VIRTCHNL_VF_OFFLOAD_RSS_AQ
- * - VIRTCHNL_VF_OFFLOAD_RSS_REG
  * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR
  * - VIRTCHNL_VF_OFFLOAD_CRC
  * - VIRTCHNL_VF_OFFLOAD_RX_POLLING
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8b81a1677045..2eecd0f39aa6 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 			return -EBUSY;
 		usleep_range(1000, 2000);
 	}
+
+	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
+	ice_qvec_toggle_napi(vsi, q_vector, false);
+
 	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
 
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
@@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		if (err)
 			return err;
 	}
-	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
-
 	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
 	if (err)
 		return err;
 
-	ice_qvec_toggle_napi(vsi, q_vector, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
@@ -259,11 +260,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 	if (err)
 		return err;
 
-	clear_bit(ICE_CFG_BUSY, vsi->state);
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
 	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+	clear_bit(ICE_CFG_BUSY, vsi->state);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d0cdd63b3d5b..390977a76de2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -2087,8 +2087,10 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport)
 		set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags);
 
 	/* schedule the napi to receive all the marker packets */
+	local_bh_disable();
 	for (i = 0; i < vport->num_q_vectors; i++)
 		napi_schedule(&vport->q_vectors[i].napi);
+	local_bh_enable();
 
 	return idpf_wait_for_marker_event(vport);
 }
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 8dc837889723..4a3c4454d25a 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -978,7 +978,7 @@ struct virtchnl2_ptype {
 	u8 proto_id_count;
 	__le16 pad;
 	__le16 proto_id[];
-};
+} __packed __aligned(2);
 VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
 
 /**
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index a2b759531cb7..3c2dc7bdebb5 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -637,7 +637,7 @@ struct igb_adapter {
 		struct timespec64 period;
 	} perout[IGB_N_PEROUT];
 
-	char fw_version[32];
+	char fw_version[48];
 #ifdef CONFIG_IGB_HWMON
 	struct hwmon_buff *igb_hwmon_buff;
 	bool ets;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4df8d4153aa5..cebb44f51d5f 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3069,7 +3069,6 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	struct e1000_fw_version fw;
-	char *lbuf;
 
 	igb_get_fw_version(hw, &fw);
 
@@ -3077,34 +3076,36 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 	case e1000_i210:
 	case e1000_i211:
 		if (!(igb_get_flash_presence_i210(hw))) {
-			lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d",
-					 fw.invm_major, fw.invm_minor,
-					 fw.invm_img_type);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%2d.%2d-%d",
+				 fw.invm_major, fw.invm_minor,
+				 fw.invm_img_type);
 			break;
 		}
 		fallthrough;
 	default:
 		/* if option rom is valid, display its version too */
 		if (fw.or_valid) {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d",
-					 fw.eep_major, fw.eep_minor,
-					 fw.etrack_id, fw.or_major, fw.or_build,
-					 fw.or_patch);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d, 0x%08x, %d.%d.%d",
+				 fw.eep_major, fw.eep_minor, fw.etrack_id,
+				 fw.or_major, fw.or_build, fw.or_patch);
 		/* no option rom */
 		} else if (fw.etrack_id != 0X0000) {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x",
-					 fw.eep_major, fw.eep_minor,
-					 fw.etrack_id);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d, 0x%08x",
+				 fw.eep_major, fw.eep_minor, fw.etrack_id);
 		} else {
-			lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major,
-					 fw.eep_minor, fw.eep_build);
+			snprintf(adapter->fw_version,
+				 sizeof(adapter->fw_version),
+				 "%d.%d.%d",
+				 fw.eep_major, fw.eep_minor, fw.eep_build);
 		}
 		break;
 	}
-
-	/* the truncate happens here if it doesn't fit */
-	strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version));
-	kfree(lbuf);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 319c544b9f04..f94570556120 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -957,7 +957,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 
 	igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
 	/* adjust timestamp for the TX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_TX_LATENCY_10;
@@ -1003,6 +1003,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			ktime_t *timestamp)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
+	struct e1000_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps ts;
 	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
@@ -1022,7 +1023,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 	igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
 
 	/* adjust timestamp for the RX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_RX_LATENCY_10;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ba8d3fe186ae..81c21a893ede 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6487,7 +6487,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	int cpu = smp_processor_id();
 	struct netdev_queue *nq;
 	struct igc_ring *ring;
-	int i, drops;
+	int i, nxmit;
 
 	if (unlikely(!netif_carrier_ok(dev)))
 		return -ENETDOWN;
@@ -6503,16 +6503,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	/* Avoid transmit queue timeout since we share it with the slow path */
 	txq_trans_cond_update(nq);
 
-	drops = 0;
+	nxmit = 0;
 	for (i = 0; i < num_frames; i++) {
 		int err;
 		struct xdp_frame *xdpf = frames[i];
 
 		err = igc_xdp_init_tx_descriptor(ring, xdpf);
-		if (err) {
-			xdp_return_frame_rx_napi(xdpf);
-			drops++;
-		}
+		if (err)
+			break;
+		nxmit++;
 	}
 
 	if (flags & XDP_XMIT_FLUSH)
@@ -6520,7 +6519,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 
 	__netif_tx_unlock(nq);
 
-	return num_frames - drops;
+	return nxmit;
 }
 
 static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 7cd8716d2ffa..861f37076861 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -130,11 +130,7 @@ void igc_power_down_phy_copper(struct igc_hw *hw)
 	/* The PHY will retain its settings across a power down/up cycle */
 	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
 	mii_reg |= MII_CR_POWER_DOWN;
-
-	/* Temporary workaround - should be removed when PHY will implement
-	 * IEEE registers as properly
-	 */
-	/* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/
+	hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
 	usleep_range(1000, 2000);
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bd541527c8c7..99876b765b08 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2939,8 +2939,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
 static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
 					   u64 qmask)
 {
-	u32 mask;
 	struct ixgbe_hw *hw = &adapter->hw;
+	u32 mask;
 
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
@@ -10525,6 +10525,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring)
 }
 
 /**
+ * ixgbe_irq_disable_single - Disable single IRQ vector
+ * @adapter: adapter structure
+ * @ring: ring index
+ **/
+static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 qmask = BIT_ULL(ring);
+	u32 mask;
+
+	switch (adapter->hw.mac.type) {
+	case ixgbe_mac_82598EB:
+		mask = qmask & IXGBE_EIMC_RTX_QUEUE;
+		IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		mask = (qmask & 0xFFFFFFFF);
+		if (mask)
+			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
+		mask = (qmask >> 32);
+		if (mask)
+			IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
+		break;
+	default:
+		break;
+	}
+	IXGBE_WRITE_FLUSH(&adapter->hw);
+	if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
+		synchronize_irq(adapter->msix_entries[ring].vector);
+	else
+		synchronize_irq(adapter->pdev->irq);
+}
+
+/**
  * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings
  * @adapter: adapter structure
  * @ring: ring index
@@ -10540,6 +10578,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	tx_ring = adapter->tx_ring[ring];
 	xdp_ring = adapter->xdp_ring[ring];
 
+	ixgbe_irq_disable_single(adapter, ring);
+
+	/* Rx/Tx/XDP Tx share the same napi context. */
+	napi_disable(&rx_ring->q_vector->napi);
+
 	ixgbe_disable_txr(adapter, tx_ring);
 	if (xdp_ring)
 		ixgbe_disable_txr(adapter, xdp_ring);
@@ -10548,9 +10591,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	if (xdp_ring)
 		synchronize_rcu();
 
-	/* Rx/Tx/XDP Tx share the same napi context. */
-	napi_disable(&rx_ring->q_vector->napi);
-
 	ixgbe_clean_tx_ring(tx_ring);
 	if (xdp_ring)
 		ixgbe_clean_tx_ring(xdp_ring);
@@ -10578,9 +10618,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	tx_ring = adapter->tx_ring[ring];
 	xdp_ring = adapter->xdp_ring[ring];
 
-	/* Rx/Tx/XDP Tx share the same napi context. */
-	napi_enable(&rx_ring->q_vector->napi);
-
 	ixgbe_configure_tx_ring(adapter, tx_ring);
 	if (xdp_ring)
 		ixgbe_configure_tx_ring(adapter, xdp_ring);
@@ -10589,6 +10626,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
 	if (xdp_ring)
 		clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+
+	/* Rx/Tx/XDP Tx share the same napi context. */
+	napi_enable(&rx_ring->q_vector->napi);
+	ixgbe_irq_enable_queues(adapter, BIT_ULL(ring));
+	IXGBE_WRITE_FLUSH(&adapter->hw);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 6208923e29a2..c1adc94a5a65 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -716,7 +716,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
 		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to read, error %x\n", error);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	if (!ret)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 167145bdcb75..516adb50f9f6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -61,28 +61,6 @@ int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena)
 	return 0;
 }
 
-static int npc_mcam_verify_pf_func(struct rvu *rvu,
-				   struct mcam_entry *entry_data, u8 intf,
-				   u16 pcifunc)
-{
-	u16 pf_func, pf_func_mask;
-
-	if (is_npc_intf_rx(intf))
-		return 0;
-
-	pf_func_mask = (entry_data->kw_mask[0] >> 32) &
-		NPC_KEX_PF_FUNC_MASK;
-	pf_func = (entry_data->kw[0] >> 32) & NPC_KEX_PF_FUNC_MASK;
-
-	pf_func = be16_to_cpu((__force __be16)pf_func);
-	if (pf_func_mask != NPC_KEX_PF_FUNC_MASK ||
-	    ((pf_func & ~RVU_PFVF_FUNC_MASK) !=
-	     (pcifunc & ~RVU_PFVF_FUNC_MASK)))
-		return -EINVAL;
-
-	return 0;
-}
-
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
 	int blkaddr;
@@ -437,6 +415,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam,
 			return;
 	}
 
+	/* AF modifies given action iff PF/VF has requested for it */
+	if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT)
+		return;
+
 	/* copy VF default entry action to the VF mcam entry */
 	rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr,
 						 target_func);
@@ -1850,8 +1832,8 @@ void npc_mcam_rsrcs_deinit(struct rvu *rvu)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 
-	kfree(mcam->bmap);
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap);
+	bitmap_free(mcam->bmap_reverse);
 	kfree(mcam->entry2pfvf_map);
 	kfree(mcam->cntr2pfvf_map);
 	kfree(mcam->entry2cntr_map);
@@ -1904,21 +1886,20 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
 	/* Allocate bitmaps for managing MCAM entries */
-	mcam->bmap = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-				   sizeof(long), GFP_KERNEL);
+	mcam->bmap = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap)
 		return -ENOMEM;
 
-	mcam->bmap_reverse = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
-					   sizeof(long), GFP_KERNEL);
+	mcam->bmap_reverse = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
 	if (!mcam->bmap_reverse)
 		goto free_bmap;
 
 	mcam->bmap_fcnt = mcam->bmap_entries;
 
 	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
-	mcam->entry2pfvf_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2pfvf_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
+
 	if (!mcam->entry2pfvf_map)
 		goto free_bmap_reverse;
 
@@ -1941,21 +1922,21 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (err)
 		goto free_entry_map;
 
-	mcam->cntr2pfvf_map = kmalloc_array(mcam->counters.max,
-					    sizeof(u16), GFP_KERNEL);
+	mcam->cntr2pfvf_map = kcalloc(mcam->counters.max, sizeof(u16),
+				      GFP_KERNEL);
 	if (!mcam->cntr2pfvf_map)
 		goto free_cntr_bmap;
 
 	/* Alloc memory for MCAM entry to counter mapping and for tracking
 	 * counter's reference count.
 	 */
-	mcam->entry2cntr_map = kmalloc_array(mcam->bmap_entries,
-					     sizeof(u16), GFP_KERNEL);
+	mcam->entry2cntr_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+				       GFP_KERNEL);
 	if (!mcam->entry2cntr_map)
 		goto free_cntr_map;
 
-	mcam->cntr_refcnt = kmalloc_array(mcam->counters.max,
-					  sizeof(u16), GFP_KERNEL);
+	mcam->cntr_refcnt = kcalloc(mcam->counters.max, sizeof(u16),
+				    GFP_KERNEL);
 	if (!mcam->cntr_refcnt)
 		goto free_entry_cntr_map;
 
@@ -1988,9 +1969,9 @@ free_cntr_bmap:
 free_entry_map:
 	kfree(mcam->entry2pfvf_map);
 free_bmap_reverse:
-	kfree(mcam->bmap_reverse);
+	bitmap_free(mcam->bmap_reverse);
 free_bmap:
-	kfree(mcam->bmap);
+	bitmap_free(mcam->bmap);
 
 	return -ENOMEM;
 }
@@ -2852,12 +2833,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	else
 		nix_intf = pfvf->nix_rx_intf;
 
-	if (!is_pffunc_af(pcifunc) &&
-	    npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
-		rc = NPC_MCAM_INVALID_REQ;
-		goto exit;
-	}
-
 	/* For AF installed rules, the nix_intf should be set to target NIX */
 	if (is_pffunc_af(req->hdr.pcifunc))
 		nix_intf = req->intf;
@@ -3209,10 +3184,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 	if (!is_npc_interface_valid(rvu, req->intf))
 		return NPC_MCAM_INVALID_REQ;
 
-	if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
-				    req->hdr.pcifunc))
-		return NPC_MCAM_INVALID_REQ;
-
 	/* Try to allocate a MCAM entry */
 	entry_req.hdr.pcifunc = req->hdr.pcifunc;
 	entry_req.contig = true;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7ca6941ea0b9..02d0b707aea5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -951,8 +951,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	if (pfvf->ptp && qidx < pfvf->hw.tx_queues) {
 		err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt,
 				 sizeof(*sq->timestamps));
-		if (err)
+		if (err) {
+			kfree(sq->sg);
+			sq->sg = NULL;
 			return err;
+		}
 	}
 
 	sq->head = 0;
@@ -968,7 +971,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
 
-	return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+	if (err) {
+		kfree(sq->sg);
+		sq->sg = NULL;
+		return err;
+	}
+
+	return 0;
 
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2928898c7f8d..7f786de61014 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev,
 	pfvf->hw.tx_queues = channel->tx_count;
 	if (pfvf->xdp_prog)
 		pfvf->hw.xdp_queues = channel->rx_count;
-	pfvf->hw.non_qos_queues =  pfvf->hw.tx_queues + pfvf->hw.xdp_queues;
 
 	if (if_up)
 		err = dev->netdev_ops->ndo_open(dev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index a57455aebff6..e5fe67e73865 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev)
 	/* RQ and SQs are mapped to different CQs,
 	 * so find out max CQ IRQs (i.e CINTs) needed.
 	 */
+	pf->hw.non_qos_queues =  pf->hw.tx_queues + pf->hw.xdp_queues;
 	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
 			       pf->hw.tc_tx_queues);
 
@@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
 		xdp_features_clear_redirect_target(dev);
 	}
 
-	pf->hw.non_qos_queues += pf->hw.xdp_queues;
-
 	if (if_up)
 		otx2_open(pf->netdev);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 4d519ea833b2..f828d32737af 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_cq_queue *cq,
 				     bool *need_xdp_flush)
 {
-	unsigned char *hard_start, *data;
+	unsigned char *hard_start;
 	int qidx = cq->cq_idx;
 	struct xdp_buff xdp;
 	struct page *page;
@@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq);
 
-	data = (unsigned char *)phys_to_virt(pa);
-	hard_start = page_address(page);
-	xdp_prepare_buff(&xdp, hard_start, data - hard_start,
+	hard_start = (unsigned char *)phys_to_virt(pa);
+	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
 			 cqe->sg.seg_size, false);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index a6e91573f8da..de123350bd46 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4761,7 +4761,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
+		if (!err)
+			err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+
 		if (err) {
 			dev_err(&pdev->dev, "Wrong DMA config\n");
 			return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3e064234f6fe..98d4306929f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 		return -EOPNOTSUPP;
 	}
 
+	if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE &&
+	    !dev->priv.fw_reset) {
+		NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function");
+		return -EOPNOTSUPP;
+	}
+
 	if (mlx5_core_is_pf(dev) && pci_num_vf(pdev))
 		NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable");
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 18fed2b34fb1..d74a5aaf4268 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -261,7 +261,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll,
 {
 	if (mdpll->tracking_netdev)
 		return;
-	netdev_dpll_pin_set(netdev, mdpll->dpll_pin);
+	dpll_netdev_pin_set(netdev, mdpll->dpll_pin);
 	mdpll->tracking_netdev = netdev;
 }
 
@@ -269,7 +269,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll)
 {
 	if (!mdpll->tracking_netdev)
 		return;
-	netdev_dpll_pin_clear(mdpll->tracking_netdev);
+	dpll_netdev_pin_clear(mdpll->tracking_netdev);
 	mdpll->tracking_netdev = NULL;
 }
 
@@ -389,7 +389,7 @@ static void mlx5_dpll_remove(struct auxiliary_device *adev)
 	struct mlx5_dpll *mdpll = auxiliary_get_drvdata(adev);
 	struct mlx5_core_dev *mdev = mdpll->mdev;
 
-	cancel_delayed_work(&mdpll->work);
+	cancel_delayed_work_sync(&mdpll->work);
 	mlx5_dpll_mdev_netdev_untrack(mdpll, mdev);
 	destroy_workqueue(mdpll->wq);
 	dpll_pin_unregister(mdpll->dpll, mdpll->dpll_pin,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 078f56a3cbb2..ca05b3252a1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad
 
 	WARN_ON_ONCE(tracker->inuse);
 	tracker->inuse = true;
-	spin_lock(&list->tracker_list_lock);
+	spin_lock_bh(&list->tracker_list_lock);
 	list_add_tail(&tracker->entry, &list->tracker_list_head);
-	spin_unlock(&list->tracker_list_lock);
+	spin_unlock_bh(&list->tracker_list_lock);
 }
 
 static void
@@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me
 
 	WARN_ON_ONCE(!tracker->inuse);
 	tracker->inuse = false;
-	spin_lock(&list->tracker_list_lock);
+	spin_lock_bh(&list->tracker_list_lock);
 	list_del(&tracker->entry);
-	spin_unlock(&list->tracker_list_lock);
+	spin_unlock_bh(&list->tracker_list_lock);
 }
 
 void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata)
@@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 	struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map;
 	struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n;
 
-	spin_lock(&cqe_list->tracker_list_lock);
+	spin_lock_bh(&cqe_list->tracker_list_lock);
 	list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) {
 		struct sk_buff *skb =
 			mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id);
@@ -170,7 +170,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq,
 		pos->inuse = false;
 		list_del(&pos->entry);
 	}
-	spin_unlock(&cqe_list->tracker_list_lock);
+	spin_unlock_bh(&cqe_list->tracker_list_lock);
 }
 
 #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
index 86bf007fd05b..b500cc2c9689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 
 	if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) {
 		if (priv->mdev->coredev_type == MLX5_COREDEV_PF)
-			mlx5_core_warn(priv->mdev, "firmware level support is missing\n");
+			mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n");
 		err = -EOPNOTSUPP;
 		goto err_check;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index d4ebd8743114..b2cabd6ab86c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o
 	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
-				    struct mlx5e_macsec_sa *sa,
-				    bool is_tx, struct net_device *netdev, u32 fs_id)
+static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec,
+				       struct mlx5e_macsec_sa *sa, bool is_tx,
+				       struct net_device *netdev, u32 fs_id)
 {
 	int action =  (is_tx) ?  MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
 				 MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
@@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
 
 	mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev,
 				fs_id);
-	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
 	sa->macsec_rule = NULL;
 }
 
+static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec,
+				    struct mlx5e_macsec_sa *sa, bool is_tx,
+				    struct net_device *netdev, u32 fs_id)
+{
+	mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id);
+	mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id);
+}
+
+static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx,
+				   struct mlx5e_macsec_sa *sa, bool encrypt,
+				   bool is_tx, u32 *fs_id)
+{
+	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
+	struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs;
+	struct mlx5_macsec_rule_attrs rule_attrs;
+	union mlx5_macsec_rule *macsec_rule;
+
+	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
+	rule_attrs.sci = sa->sci;
+	rule_attrs.assoc_num = sa->assoc_num;
+	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
+				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
+
+	macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id);
+	if (!macsec_rule)
+		return -ENOMEM;
+
+	sa->macsec_rule = macsec_rule;
+
+	return 0;
+}
+
 static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 				struct mlx5e_macsec_sa *sa,
 				bool encrypt, bool is_tx, u32 *fs_id)
 {
 	struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev);
 	struct mlx5e_macsec *macsec = priv->macsec;
-	struct mlx5_macsec_rule_attrs rule_attrs;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_macsec_obj_attrs obj_attrs;
-	union mlx5_macsec_rule *macsec_rule;
 	int err;
 
 	obj_attrs.next_pn = sa->next_pn;
@@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
 	if (err)
 		return err;
 
-	rule_attrs.macsec_obj_id = sa->macsec_obj_id;
-	rule_attrs.sci = sa->sci;
-	rule_attrs.assoc_num = sa->assoc_num;
-	rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT :
-				      MLX5_ACCEL_MACSEC_ACTION_DECRYPT;
-
-	macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id);
-	if (!macsec_rule) {
-		err = -ENOMEM;
-		goto destroy_macsec_object;
+	if (sa->active) {
+		err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id);
+		if (err)
+			goto destroy_macsec_object;
 	}
 
-	sa->macsec_rule = macsec_rule;
-
 	return 0;
 
 destroy_macsec_object:
@@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx)
 		goto destroy_sa;
 
 	macsec_device->tx_sa[assoc_num] = tx_sa;
-	if (!secy->operational ||
-	    assoc_num != tx_sc->encoding_sa ||
-	    !tx_sa->active)
+	if (!secy->operational)
 		goto out;
 
 	err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
@@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 		goto out;
 
 	if (ctx_tx_sa->active) {
-		err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
+		err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 		if (err)
 			goto out;
 	} else {
@@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx)
 			goto out;
 		}
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
+		mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 out:
 	mutex_unlock(&macsec->lock);
@@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx)
 		goto out;
 	}
 
-	mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
-				rx_sc->sc_xarray_element->fs_id);
+	if (rx_sa->active)
+		mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
+					rx_sc->sc_xarray_element->fs_id);
 	mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id);
 	kfree(rx_sa);
 	rx_sc->rx_sa[assoc_num] = NULL;
@@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 			if (!rx_sa || !rx_sa->macsec_rule)
 				continue;
 
-			mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev,
-						rx_sc->sc_xarray_element->fs_id);
+			mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev,
+						   rx_sc->sc_xarray_element->fs_id);
 		}
 	}
 
@@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx,
 				continue;
 
 			if (rx_sa->active) {
-				err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false,
-							   &rx_sc->sc_xarray_element->fs_id);
+				err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false,
+							      &rx_sc->sc_xarray_element->fs_id);
 				if (err)
 					goto out;
 			}
@@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 		if (!tx_sa)
 			continue;
 
-		mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0);
+		mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0);
 	}
 
 	for (i = 0; i < MACSEC_NUM_AN; ++i) {
@@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx)
 			continue;
 
 		if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) {
-			err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL);
+			err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL);
 			if (err)
 				goto out;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 5c166d9d2dca..2fa076b23fbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -401,6 +401,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		mlx5e_skb_cb_hwtstamp_init(skb);
 		mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
 					   metadata_index);
+		/* ensure skb is put on metadata_map before tracking the index */
+		wmb();
 		mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index);
 		if (!netif_tx_queue_stopped(sq->txq) &&
 		    mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 190f10aba170..5a0047bdcb51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 
 	xa_for_each(&esw->offloads.vport_reps, i, rep) {
 		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
+		if (!rpriv || !rpriv->netdev)
 			continue;
 
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b0455134c98e..baaae628b0a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -535,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw)
 }
 
 static bool
-esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest)
+esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest)
 {
-	bool vf_dest = false, pf_dest = false;
+	bool internal_dest = false, external_dest = false;
 	int i;
 
 	for (i = 0; i < max_dest; i++) {
-		if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
+		if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+		    dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK)
 			continue;
 
-		if (dests[i].vport.num == MLX5_VPORT_UPLINK)
-			pf_dest = true;
+		/* Uplink dest is external, but considered as internal
+		 * if there is reformat because firmware uses LB+hairpin to support it.
+		 */
+		if (dests[i].vport.num == MLX5_VPORT_UPLINK &&
+		    !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID))
+			external_dest = true;
 		else
-			vf_dest = true;
+			internal_dest = true;
 
-		if (vf_dest && pf_dest)
+		if (internal_dest && external_dest)
 			return true;
 	}
 
@@ -695,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 		/* Header rewrite with combined wire+loopback in FDB is not allowed */
 		if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) &&
-		    esw_dests_to_vf_pf_vports(dest, i)) {
+		    esw_dests_to_int_external(dest, i)) {
 			esw_warn(esw->dev,
-				 "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n");
+				 "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n");
 			rule = ERR_PTR(-EINVAL);
 			goto err_esw_get;
 		}
@@ -3658,22 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
 	return 0;
 }
 
-static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
-{
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
-	struct net *devl_net, *netdev_net;
-	bool ret = false;
-
-	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
-	if (dev->mlx5e_res.uplink_netdev) {
-		netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
-		devl_net = devlink_net(devlink);
-		ret = net_eq(devl_net, netdev_net);
-	}
-	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
-	return ret;
-}
-
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
@@ -3718,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	if (esw_mode_from_devlink(mode, &mlx5_mode))
 		return -EINVAL;
 
-	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV &&
-	    !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's.");
-		return -EPERM;
-	}
-
 	mlx5_lag_disable_change(esw->dev);
 	err = mlx5_esw_try_lock(esw);
 	if (err < 0) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index f27eab6e4929..2911aa34a5be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -703,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
 	mlx5_eq_notifier_register(dev, &fw_reset->nb);
 }
 
 void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev)
 {
-	mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb);
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	if (!fw_reset)
+		return;
+
+	mlx5_eq_notifier_unregister(dev, &fw_reset->nb);
 }
 
 void mlx5_drain_fw_reset(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags);
 	cancel_work_sync(&fw_reset->fw_live_patch_work);
 	cancel_work_sync(&fw_reset->reset_request_work);
@@ -733,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = {
 
 int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
+	struct mlx5_fw_reset *fw_reset;
 	int err;
 
+	if (!MLX5_CAP_MCAM_REG(dev, mfrl))
+		return 0;
+
+	fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
 	if (!fw_reset)
 		return -ENOMEM;
 	fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events");
@@ -771,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
+	if (!fw_reset)
+		return;
+
 	devl_params_unregister(priv_to_devlink(dev),
 			       mlx5_fw_reset_devlink_params,
 			       ARRAY_SIZE(mlx5_fw_reset_devlink_params));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 8ff6dc9bc803..b5c709bba155 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 	struct health_buffer __iomem *h = health->health;
 	u8 synd = ioread8(&h->synd);
 
+	devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
 	if (!synd)
 		return 0;
 
-	devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
 	devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd));
 
 	return 0;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
index 41fa2523d91d..5f2cd9a8cf8f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
@@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x)
 
 	/* Now, set PGIDs for each active LAG */
 	for (lag = 0; lag < lan966x->num_phys_ports; ++lag) {
-		struct net_device *bond = lan966x->ports[lag]->bond;
+		struct lan966x_port *port = lan966x->ports[lag];
 		int num_active_ports = 0;
+		struct net_device *bond;
 		unsigned long bond_mask;
 		u8 aggr_idx[16];
 
-		if (!bond || (visited & BIT(lag)))
+		if (!port || !port->bond || (visited & BIT(lag)))
 			continue;
 
+		bond = port->bond;
 		bond_mask = lan966x_lag_get_mask(lan966x, bond);
 
 		for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) {
 			struct lan966x_port *port = lan966x->ports[p];
 
+			if (!port)
+				continue;
+
 			lan_wr(ANA_PGID_PGID_SET(bond_mask),
 			       lan966x, ANA_PGID(p));
 			if (port->lag_tx_active)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index 92108d354051..2e83bbb9477e 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port)
 	lan966x_taprio_speed_set(port, config->speed);
 
 	/* Also the GIGA_MODE_ENA(1) needs to be set regardless of the
-	 * port speed for QSGMII ports.
+	 * port speed for QSGMII or SGMII ports.
 	 */
-	if (phy_interface_num_ports(config->portmode) == 4)
+	if (phy_interface_num_ports(config->portmode) == 4 ||
+	    config->portmode == PHY_INTERFACE_MODE_SGMII)
 		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1);
 
 	lan_wr(config->duplex | mode,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
index 4af285918ea2..75868b3f548e 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c
@@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5,
 				 list) {
 		if ((vid == 0 || mact_entry->vid == vid) &&
 		    ether_addr_equal(addr, mact_entry->mac)) {
+			sparx5_mact_forget(sparx5, addr, mact_entry->vid);
+
 			list_del(&mact_entry->list);
 			devm_kfree(sparx5->dev, mact_entry);
-
-			sparx5_mact_forget(sparx5, addr, mact_entry->vid);
 		}
 	}
 	mutex_unlock(&sparx5->mact_lock);
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index d1f7fc8b1b71..3c066b62e689 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -757,6 +757,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, sparx5);
 	sparx5->pdev = pdev;
 	sparx5->dev = &pdev->dev;
+	spin_lock_init(&sparx5->tx_lock);
 
 	/* Do switch core reset if available */
 	reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch");
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 6f565c0c0c3d..316fed5f2735 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -280,6 +280,7 @@ struct sparx5 {
 	int xtr_irq;
 	/* Frame DMA */
 	int fdma_irq;
+	spinlock_t tx_lock; /* lock for frame transmission */
 	struct sparx5_rx rx;
 	struct sparx5_tx tx;
 	/* PTP */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index 6db6ac6a3bbc..ac7e1cffbcec 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
+	spin_lock(&sparx5->tx_lock);
 	if (sparx5->fdma_irq > 0)
 		ret = sparx5_fdma_xmit(sparx5, ifh, skb);
 	else
 		ret = sparx5_inject(sparx5, ifh, skb, dev);
+	spin_unlock(&sparx5->tx_lock);
 
 	if (ret == -EBUSY)
 		goto busy;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
index 2967bab72505..15180538b80a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
@@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_
 		mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
 		return;
 
+	/* Both struct tcphdr and struct udphdr start with
+	 *	__be16 source;
+	 *	__be16 dest;
+	 * so we can use the same code for both.
+	 */
 	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
-		mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val);
-		mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask);
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) {
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val << 16);
+			/* The mask of mangle action is inverse mask,
+			 * so clear the dest tp port with 0xFFFF to
+			 * instead of rotate-left operation.
+			 */
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF);
+		}
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) {
+			mangle_action->mangle.offset = 0;
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val);
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask);
+		}
 		return;
 
 	default:
@@ -1864,10 +1884,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct flow_action_entry *ct_goto;
 	struct nfp_fl_ct_zone_entry *zt;
+	struct flow_action_entry *act;
 	bool wildcarded = false;
 	struct flow_match_ct ct;
-	struct flow_action_entry *ct_goto;
+	int i;
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_REDIRECT_INGRESS:
+		case FLOW_ACTION_MIRRED:
+		case FLOW_ACTION_MIRRED_INGRESS:
+			if (act->dev->rtnl_link_ops &&
+			    !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "unsupported offload: out port is openvswitch internal port");
+				return -EOPNOTSUPP;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	flow_rule_match_ct(rule, &ct);
 	if (!ct.mask->ct_zone) {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index e522845c7c21..0d7d138d6e0d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -1084,7 +1084,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
 	u16 nfp_mac_idx = 0;
 
 	entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
-	if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+	if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) {
 		if (entry->bridge_count ||
 		    !nfp_flower_is_supported_bridge(netdev)) {
 			nfp_tunnel_offloaded_macs_inc_ref_and_link(entry,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 3b3210d823e8..f28e769e6fda 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2776,6 +2776,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	case NFP_NFD_VER_NFD3:
 		netdev->netdev_ops = &nfp_nfd3_netdev_ops;
 		netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+		netdev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
 		break;
 	case NFP_NFD_VER_NFDK:
 		netdev->netdev_ops = &nfp_nfdk_netdev_ops;
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 33b4c2856316..3f10c5365c80 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface)
 	const u32 barcfg_msix_general =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT;
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT);
 	const u32 barcfg_msix_xpb =
 		NFP_PCIE_BAR_PCIE2CPP_MapType(
 			NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) |
-		NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT |
+		NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+			NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) |
 		NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress(
 			NFP_CPP_TARGET_ISLAND_XPB);
 	const u32 barcfg_explicit[4] = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index c49aa358e424..6ba8d4aca0a0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -93,6 +93,7 @@ static void ionic_unmap_bars(struct ionic *ionic)
 			bars[i].len = 0;
 		}
 	}
+	ionic->num_bars = 0;
 }
 
 void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num)
@@ -215,15 +216,17 @@ out:
 
 static void ionic_clear_pci(struct ionic *ionic)
 {
-	ionic->idev.dev_info_regs = NULL;
-	ionic->idev.dev_cmd_regs = NULL;
-	ionic->idev.intr_status = NULL;
-	ionic->idev.intr_ctrl = NULL;
-
-	ionic_unmap_bars(ionic);
-	pci_release_regions(ionic->pdev);
+	if (ionic->num_bars) {
+		ionic->idev.dev_info_regs = NULL;
+		ionic->idev.dev_cmd_regs = NULL;
+		ionic->idev.intr_status = NULL;
+		ionic->idev.intr_ctrl = NULL;
+
+		ionic_unmap_bars(ionic);
+		pci_release_regions(ionic->pdev);
+	}
 
-	if (atomic_read(&ionic->pdev->enable_cnt) > 0)
+	if (pci_is_enabled(ionic->pdev))
 		pci_disable_device(ionic->pdev);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 1e7c71f7f081..746072b4dbd0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -319,22 +319,32 @@ do_check_time:
 
 u8 ionic_dev_cmd_status(struct ionic_dev *idev)
 {
+	if (!idev->dev_cmd_regs)
+		return (u8)PCI_ERROR_RESPONSE;
 	return ioread8(&idev->dev_cmd_regs->comp.comp.status);
 }
 
 bool ionic_dev_cmd_done(struct ionic_dev *idev)
 {
+	if (!idev->dev_cmd_regs)
+		return false;
 	return ioread32(&idev->dev_cmd_regs->done) & IONIC_DEV_CMD_DONE;
 }
 
 void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp)
 {
+	if (!idev->dev_cmd_regs)
+		return;
 	memcpy_fromio(comp, &idev->dev_cmd_regs->comp, sizeof(*comp));
 }
 
 void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd)
 {
 	idev->opcode = cmd->cmd.opcode;
+
+	if (!idev->dev_cmd_regs)
+		return;
+
 	memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd));
 	iowrite32(0, &idev->dev_cmd_regs->done);
 	iowrite32(1, &idev->dev_cmd_regs->doorbell);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index cd3c0b01402e..0ffc9c4904ac 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -90,18 +90,23 @@ static void ionic_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
 			   void *p)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
+	struct ionic_dev *idev;
 	unsigned int offset;
 	unsigned int size;
 
 	regs->version = IONIC_DEV_CMD_REG_VERSION;
 
+	idev = &lif->ionic->idev;
+	if (!idev->dev_info_regs)
+		return;
+
 	offset = 0;
 	size = IONIC_DEV_INFO_REG_COUNT * sizeof(u32);
 	memcpy_fromio(p + offset, lif->ionic->idev.dev_info_regs->words, size);
 
 	offset += size;
 	size = IONIC_DEV_CMD_REG_COUNT * sizeof(u32);
-	memcpy_fromio(p + offset, lif->ionic->idev.dev_cmd_regs->words, size);
+	memcpy_fromio(p + offset, idev->dev_cmd_regs->words, size);
 }
 
 static void ionic_get_link_ext_stats(struct net_device *netdev,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_fw.c b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
index 5f40324cd243..3c209c1a2337 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_fw.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_fw.c
@@ -109,6 +109,11 @@ int ionic_firmware_update(struct ionic_lif *lif, const struct firmware *fw,
 	dl = priv_to_devlink(ionic);
 	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
 
+	if (!idev->dev_cmd_regs) {
+		err = -ENXIO;
+		goto err_out;
+	}
+
 	buf_sz = sizeof(idev->dev_cmd_regs->data);
 
 	netdev_dbg(netdev,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index cf2d5ad7b68c..fcb44ceeb6aa 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3559,7 +3559,10 @@ int ionic_lif_init(struct ionic_lif *lif)
 			goto err_out_notifyq_deinit;
 	}
 
-	err = ionic_init_nic_features(lif);
+	if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+		err = ionic_set_nic_features(lif, lif->netdev->features);
+	else
+		err = ionic_init_nic_features(lif);
 	if (err)
 		goto err_out_notifyq_deinit;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 165ab08ad2dd..2f479de329fe 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -416,6 +416,9 @@ static void ionic_dev_cmd_clean(struct ionic *ionic)
 {
 	struct ionic_dev *idev = &ionic->idev;
 
+	if (!idev->dev_cmd_regs)
+		return;
+
 	iowrite32(0, &idev->dev_cmd_regs->doorbell);
 	memset_io(&idev->dev_cmd_regs->cmd, 0, sizeof(idev->dev_cmd_regs->cmd));
 }
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 54cd96b035d6..6f4776759863 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -579,6 +579,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
 	work_done = ionic_cq_service(cq, budget,
 				     ionic_tx_service, NULL, NULL);
 
+	if (unlikely(!budget))
+		return budget;
+
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR);
 		flags |= IONIC_INTR_CRED_UNMASK;
@@ -607,6 +610,9 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
 	u32 work_done = 0;
 	u32 flags = 0;
 
+	if (unlikely(!budget))
+		return budget;
+
 	lif = cq->bound_q->lif;
 	idev = &lif->ionic->idev;
 
@@ -656,6 +662,9 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT,
 					ionic_tx_service, NULL, NULL);
 
+	if (unlikely(!budget))
+		return budget;
+
 	rx_work_done = ionic_cq_service(rxcq, budget,
 					ionic_rx_service, NULL, NULL);
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 0e3731f50fc2..f7566cfa45ca 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -772,29 +772,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 	struct ravb_rx_desc *desc;
 	struct sk_buff *skb;
 	dma_addr_t dma_addr;
+	int rx_packets = 0;
 	u8  desc_status;
-	int boguscnt;
 	u16 pkt_len;
 	u8  die_dt;
 	int entry;
 	int limit;
+	int i;
 
 	entry = priv->cur_rx[q] % priv->num_rx_ring[q];
-	boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
+	limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
 	stats = &priv->stats[q];
 
-	boguscnt = min(boguscnt, *quota);
-	limit = boguscnt;
 	desc = &priv->gbeth_rx_ring[entry];
-	while (desc->die_dt != DT_FEMPTY) {
+	for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) {
 		/* Descriptor type must be checked before all other reads */
 		dma_rmb();
 		desc_status = desc->msc;
 		pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
 
-		if (--boguscnt < 0)
-			break;
-
 		/* We use 0-byte descriptors to mark the DMA mapping errors */
 		if (!pkt_len)
 			continue;
@@ -820,7 +816,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 				skb_put(skb, pkt_len);
 				skb->protocol = eth_type_trans(skb, ndev);
 				napi_gro_receive(&priv->napi[q], skb);
-				stats->rx_packets++;
+				rx_packets++;
 				stats->rx_bytes += pkt_len;
 				break;
 			case DT_FSTART:
@@ -848,7 +844,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 					eth_type_trans(priv->rx_1st_skb, ndev);
 				napi_gro_receive(&priv->napi[q],
 						 priv->rx_1st_skb);
-				stats->rx_packets++;
+				rx_packets++;
 				stats->rx_bytes += pkt_len;
 				break;
 			}
@@ -887,9 +883,9 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
 		desc->die_dt = DT_FEMPTY;
 	}
 
-	*quota -= limit - (++boguscnt);
-
-	return boguscnt <= 0;
+	stats->rx_packets += rx_packets;
+	*quota -= rx_packets;
+	return *quota == 0;
 }
 
 /* Packet receive function for Ethernet AVB */
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 721c1f8e892f..5ba606a596e7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,28 +59,51 @@
 #undef FRAME_FILTER_DEBUG
 /* #define FRAME_FILTER_DEBUG */
 
+struct stmmac_q_tx_stats {
+	u64_stats_t tx_bytes;
+	u64_stats_t tx_set_ic_bit;
+	u64_stats_t tx_tso_frames;
+	u64_stats_t tx_tso_nfrags;
+};
+
+struct stmmac_napi_tx_stats {
+	u64_stats_t tx_packets;
+	u64_stats_t tx_pkt_n;
+	u64_stats_t poll;
+	u64_stats_t tx_clean;
+	u64_stats_t tx_set_ic_bit;
+};
+
 struct stmmac_txq_stats {
-	u64 tx_bytes;
-	u64 tx_packets;
-	u64 tx_pkt_n;
-	u64 tx_normal_irq_n;
-	u64 napi_poll;
-	u64 tx_clean;
-	u64 tx_set_ic_bit;
-	u64 tx_tso_frames;
-	u64 tx_tso_nfrags;
-	struct u64_stats_sync syncp;
+	/* Updates protected by tx queue lock. */
+	struct u64_stats_sync q_syncp;
+	struct stmmac_q_tx_stats q;
+
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_tx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+struct stmmac_napi_rx_stats {
+	u64_stats_t rx_bytes;
+	u64_stats_t rx_packets;
+	u64_stats_t rx_pkt_n;
+	u64_stats_t poll;
+};
+
 struct stmmac_rxq_stats {
-	u64 rx_bytes;
-	u64 rx_packets;
-	u64 rx_pkt_n;
-	u64 rx_normal_irq_n;
-	u64 napi_poll;
-	struct u64_stats_sync syncp;
+	/* Updates protected by NAPI poll logic. */
+	struct u64_stats_sync napi_syncp;
+	struct stmmac_napi_rx_stats napi;
 } ____cacheline_aligned_in_smp;
 
+/* Updates on each CPU protected by not allowing nested irqs. */
+struct stmmac_pcpu_stats {
+	struct u64_stats_sync syncp;
+	u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
+	u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+};
+
 /* Extra statistic and debug information exposed by ethtool */
 struct stmmac_extra_stats {
 	/* Transmit errors */
@@ -205,6 +228,7 @@ struct stmmac_extra_stats {
 	/* per queue statistics */
 	struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
 	struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+	struct stmmac_pcpu_stats __percpu *pcpu_stats;
 	unsigned long rx_dropped;
 	unsigned long rx_errors;
 	unsigned long tx_dropped;
@@ -216,6 +240,7 @@ struct stmmac_safety_stats {
 	unsigned long mac_errors[32];
 	unsigned long mtl_errors[32];
 	unsigned long dma_errors[32];
+	unsigned long dma_dpp_errors[32];
 };
 
 /* Number of fields in Safety Stats */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 8f730ada71f9..6b65420e11b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -353,6 +353,10 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
 
+	/* Default TX Q0 to use TSO and rest TXQ for TBS */
+	for (int i = 1; i < plat_dat->tx_queues_to_use; i++)
+		plat_dat->tx_queues_cfg[i].tbs_en = 1;
+
 	plat_dat->host_dma_width = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 137741b94122..b21d99faa2d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 				     struct stmmac_extra_stats *x, u32 chan,
 				     u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	u32 v;
 
@@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_TX_INT) {
 		ret |= handle_tx;
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_TX_DMA_STOP_INT)
@@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
 
 	if (v & EMAC_RX_INT) {
 		ret |= handle_rx;
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 	}
 
 	if (v & EMAC_RX_BUF_UA_INT)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 9470d3fd2ded..0d185e54eb7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
 	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 
 	if (dir == DMA_DIR_RX)
@@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_rx;
 	}
 	if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
 		ret |= handle_tx;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 7907d62d3437..85e18f9a22f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status)
 int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			struct stmmac_extra_stats *x, u32 chan, u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	/* read the status register (CSR5) */
 	u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 			u32 value = readl(ioaddr + DMA_INTR_ENA);
 			/* to schedule NAPI on real RIE event. */
 			if (likely(value & DMA_INTR_ENA_RIE)) {
-				u64_stats_update_begin(&rxq_stats->syncp);
-				rxq_stats->rx_normal_irq_n++;
-				u64_stats_update_end(&rxq_stats->syncp);
+				u64_stats_update_begin(&stats->syncp);
+				u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+				u64_stats_update_end(&stats->syncp);
 				ret |= handle_rx;
 			}
 		}
 		if (likely(intr_status & DMA_STATUS_TI)) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 		if (unlikely(intr_status & DMA_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 207ff1799f2c..6a2c7d22df1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -303,6 +303,8 @@
 #define XGMAC_RXCEIE			BIT(4)
 #define XGMAC_TXCEIE			BIT(0)
 #define XGMAC_MTL_ECC_INT_STATUS	0x000010cc
+#define XGMAC_MTL_DPP_CONTROL		0x000010e0
+#define XGMAC_DPP_DISABLE		BIT(0)
 #define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
 #define XGMAC_TQS			GENMASK(25, 16)
 #define XGMAC_TQS_SHIFT			16
@@ -385,6 +387,7 @@
 #define XGMAC_DCEIE			BIT(1)
 #define XGMAC_TCEIE			BIT(0)
 #define XGMAC_DMA_ECC_INT_STATUS	0x0000306c
+#define XGMAC_DMA_DPP_INT_STATUS	0x00003074
 #define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
 #define XGMAC_SPH			BIT(24)
 #define XGMAC_PBLx8			BIT(16)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index eb48211d9b0e..1af2f89a0504 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -830,6 +830,44 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
 	{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
 };
 
+#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error"
+#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error"
+
+static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
+	{ true, "TDPES0", DPP_TX_ERR },
+	{ true, "TDPES1", DPP_TX_ERR },
+	{ true, "TDPES2", DPP_TX_ERR },
+	{ true, "TDPES3", DPP_TX_ERR },
+	{ true, "TDPES4", DPP_TX_ERR },
+	{ true, "TDPES5", DPP_TX_ERR },
+	{ true, "TDPES6", DPP_TX_ERR },
+	{ true, "TDPES7", DPP_TX_ERR },
+	{ true, "TDPES8", DPP_TX_ERR },
+	{ true, "TDPES9", DPP_TX_ERR },
+	{ true, "TDPES10", DPP_TX_ERR },
+	{ true, "TDPES11", DPP_TX_ERR },
+	{ true, "TDPES12", DPP_TX_ERR },
+	{ true, "TDPES13", DPP_TX_ERR },
+	{ true, "TDPES14", DPP_TX_ERR },
+	{ true, "TDPES15", DPP_TX_ERR },
+	{ true, "RDPES0", DPP_RX_ERR },
+	{ true, "RDPES1", DPP_RX_ERR },
+	{ true, "RDPES2", DPP_RX_ERR },
+	{ true, "RDPES3", DPP_RX_ERR },
+	{ true, "RDPES4", DPP_RX_ERR },
+	{ true, "RDPES5", DPP_RX_ERR },
+	{ true, "RDPES6", DPP_RX_ERR },
+	{ true, "RDPES7", DPP_RX_ERR },
+	{ true, "RDPES8", DPP_RX_ERR },
+	{ true, "RDPES9", DPP_RX_ERR },
+	{ true, "RDPES10", DPP_RX_ERR },
+	{ true, "RDPES11", DPP_RX_ERR },
+	{ true, "RDPES12", DPP_RX_ERR },
+	{ true, "RDPES13", DPP_RX_ERR },
+	{ true, "RDPES14", DPP_RX_ERR },
+	{ true, "RDPES15", DPP_RX_ERR },
+};
+
 static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 				    void __iomem *ioaddr, bool correctable,
 				    struct stmmac_safety_stats *stats)
@@ -841,6 +879,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
 
 	dwxgmac3_log_error(ndev, value, correctable, "DMA",
 			   dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
+
+	value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+	writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+
+	dwxgmac3_log_error(ndev, value, false, "DMA_DPP",
+			   dwxgmac3_dma_dpp_errors,
+			   STAT_OFF(dma_dpp_errors), stats);
 }
 
 static int
@@ -881,6 +926,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
 	value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */
 	writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL);
 
+	/* 5. Enable Data Path Parity Protection */
+	value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
+	/* already enabled by default, explicit enable it again */
+	value &= ~XGMAC_DPP_DISABLE;
+	writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
+
 	return 0;
 }
 
@@ -914,7 +965,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev,
 		ret |= !corr;
 	}
 
-	err = dma & (XGMAC_DEUIS | XGMAC_DECIS);
+	/* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in
+	 * DMA_Safety_Interrupt_Status, so we handle DMA Data Path
+	 * Parity Errors here
+	 */
+	err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS);
 	corr = dma & XGMAC_DECIS;
 	if (err) {
 		dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats);
@@ -930,6 +985,7 @@ static const struct dwxgmac3_error {
 	{ dwxgmac3_mac_errors },
 	{ dwxgmac3_mtl_errors },
 	{ dwxgmac3_dma_errors },
+	{ dwxgmac3_dma_dpp_errors },
 };
 
 static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 3cde695fec91..dd2ab6185c40 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 				  struct stmmac_extra_stats *x, u32 chan,
 				  u32 dir)
 {
-	struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
-	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
 	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
@@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	/* TX/RX NORMAL interrupts */
 	if (likely(intr_status & XGMAC_NIS)) {
 		if (likely(intr_status & XGMAC_RI)) {
-			u64_stats_update_begin(&rxq_stats->syncp);
-			rxq_stats->rx_normal_irq_n++;
-			u64_stats_update_end(&rxq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_rx;
 		}
 		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			u64_stats_update_begin(&txq_stats->syncp);
-			txq_stats->tx_normal_irq_n++;
-			u64_stats_update_end(&txq_stats->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
 			ret |= handle_tx;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 1bd34b2a47e8..29367105df54 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -224,7 +224,7 @@ static const struct stmmac_hwif_entry {
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
 			.mmc_off = MMC_GMAC4_OFFSET,
-			.est_off = EST_XGMAC_OFFSET,
+			.est_off = EST_GMAC4_OFFSET,
 		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 42d27b97dd1d..ec44becf0e2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -549,44 +549,79 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	}
 }
 
+static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
+static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+	u64 total;
+	int cpu;
+
+	total = 0;
+	for_each_possible_cpu(cpu) {
+		struct stmmac_pcpu_stats *pcpu;
+		unsigned int start;
+		u64 irq_n;
+
+		pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+		do {
+			start = u64_stats_fetch_begin(&pcpu->syncp);
+			irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]);
+		} while (u64_stats_fetch_retry(&pcpu->syncp, start));
+		total += irq_n;
+	}
+	return total;
+}
+
 static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int start;
-	int q, stat;
-	char *p;
+	int q;
 
 	for (q = 0; q < tx_cnt; q++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
-		struct stmmac_txq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
-		for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_tx_normal_irq_n(priv, q);
 	}
 
 	for (q = 0; q < rx_cnt; q++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
-		struct stmmac_rxq_stats snapshot;
+		u64 pkt_n;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
-		p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
-		for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
-			*data++ = (*(u64 *)p);
-			p += sizeof(u64);
-		}
+		*data++ = pkt_n;
+		*data++ = stmmac_get_rx_normal_irq_n(priv, q);
 	}
 }
 
@@ -645,39 +680,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	pos = j;
 	for (i = 0; i < rx_queues_count; i++) {
 		struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i];
-		struct stmmac_rxq_stats snapshot;
+		struct stmmac_napi_rx_stats snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			snapshot = *rxq_stats;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
-
-		data[j++] += snapshot.rx_pkt_n;
-		data[j++] += snapshot.rx_normal_irq_n;
-		normal_irq_n += snapshot.rx_normal_irq_n;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			snapshot = rxq_stats->napi;
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&snapshot.rx_pkt_n);
+		n_irq = stmmac_get_rx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		napi_poll += u64_stats_read(&snapshot.poll);
 	}
 
 	pos = j;
 	for (i = 0; i < tx_queues_count; i++) {
 		struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i];
-		struct stmmac_txq_stats snapshot;
+		struct stmmac_napi_tx_stats napi_snapshot;
+		struct stmmac_q_tx_stats q_snapshot;
+		u64 n_irq;
 
 		j = pos;
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			snapshot = *txq_stats;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
-
-		data[j++] += snapshot.tx_pkt_n;
-		data[j++] += snapshot.tx_normal_irq_n;
-		normal_irq_n += snapshot.tx_normal_irq_n;
-		data[j++] += snapshot.tx_clean;
-		data[j++] += snapshot.tx_set_ic_bit;
-		data[j++] += snapshot.tx_tso_frames;
-		data[j++] += snapshot.tx_tso_nfrags;
-		napi_poll += snapshot.napi_poll;
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			q_snapshot = txq_stats->q;
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			napi_snapshot = txq_stats->napi;
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
+
+		data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n);
+		n_irq = stmmac_get_tx_normal_irq_n(priv, i);
+		data[j++] += n_irq;
+		normal_irq_n += n_irq;
+		data[j++] += u64_stats_read(&napi_snapshot.tx_clean);
+		data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) +
+			u64_stats_read(&napi_snapshot.tx_set_ic_bit);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames);
+		data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags);
+		napi_poll += u64_stats_read(&napi_snapshot.poll);
 	}
 	normal_irq_n += priv->xstats.rx_early_irq;
 	data[j++] = normal_irq_n;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b334eb16da23..7c6aef033a45 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2482,7 +2482,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct xdp_desc xdp_desc;
 	bool work_done = true;
 	u32 tx_set_ic_bit = 0;
-	unsigned long flags;
 
 	/* Avoids TX time-out as we are sharing with slow path */
 	txq_trans_cond_update(nq);
@@ -2566,9 +2565,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
 		entry = tx_q->cur_tx;
 	}
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_set_ic_bit += tx_set_ic_bit;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	if (tx_desc) {
 		stmmac_flush_tx_descriptors(priv, queue);
@@ -2616,7 +2615,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	unsigned int bytes_compl = 0, pkts_compl = 0;
 	unsigned int entry, xmits = 0, count = 0;
 	u32 tx_packets = 0, tx_errors = 0;
-	unsigned long flags;
 
 	__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
 
@@ -2674,7 +2672,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 			}
 			if (skb) {
 				stmmac_get_tx_hwtstamp(priv, p, skb);
-			} else {
+			} else if (tx_q->xsk_pool &&
+				   xp_tx_metadata_enabled(tx_q->xsk_pool)) {
 				struct stmmac_xsk_tx_complete tx_compl = {
 					.priv = priv,
 					.desc = p,
@@ -2782,11 +2781,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
 	if (tx_q->dirty_tx != tx_q->cur_tx)
 		*pending_packets = true;
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_packets += tx_packets;
-	txq_stats->tx_pkt_n += tx_packets;
-	txq_stats->tx_clean++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_add(&txq_stats->napi.tx_packets, tx_packets);
+	u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets);
+	u64_stats_inc(&txq_stats->napi.tx_clean);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	priv->xstats.tx_errors += tx_errors;
 
@@ -3932,6 +3931,9 @@ static int __stmmac_open(struct net_device *dev,
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	buf_sz = dma_conf->dma_buf_sz;
+	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
+		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
+			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
 	memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf));
 
 	stmmac_reset_queues_param(priv);
@@ -4004,8 +4006,10 @@ static void stmmac_fpe_stop_wq(struct stmmac_priv *priv)
 {
 	set_bit(__FPE_REMOVING, &priv->fpe_task_state);
 
-	if (priv->fpe_wq)
+	if (priv->fpe_wq) {
 		destroy_workqueue(priv->fpe_wq);
+		priv->fpe_wq = NULL;
+	}
 
 	netdev_info(priv->dev, "FPE workqueue stop");
 }
@@ -4210,7 +4214,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	u8 proto_hdr_len, hdr;
-	unsigned long flags;
 	u32 pay_len, mss;
 	dma_addr_t des;
 	int i;
@@ -4375,13 +4378,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
-	txq_stats->tx_tso_frames++;
-	txq_stats->tx_tso_nfrags += nfrags;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
+	u64_stats_inc(&txq_stats->q.tx_tso_frames);
+	u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4480,7 +4483,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_tx_queue *tx_q;
 	bool has_vlan, set_ic;
 	int entry, first_tx;
-	unsigned long flags;
 	dma_addr_t des;
 
 	tx_q = &priv->dma_conf.tx_queue[queue];
@@ -4650,11 +4652,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->tx_bytes += skb->len;
+	u64_stats_update_begin(&txq_stats->q_syncp);
+	u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
 	if (set_ic)
-		txq_stats->tx_set_ic_bit++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+	u64_stats_update_end(&txq_stats->q_syncp);
 
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4918,12 +4920,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 		set_ic = false;
 
 	if (set_ic) {
-		unsigned long flags;
 		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, tx_desc);
-		flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-		txq_stats->tx_set_ic_bit++;
-		u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+		u64_stats_update_begin(&txq_stats->q_syncp);
+		u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+		u64_stats_update_end(&txq_stats->q_syncp);
 	}
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -5073,7 +5074,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	unsigned int len = xdp->data_end - xdp->data;
 	enum pkt_hash_types hash_type;
 	int coe = priv->hw->rx_csum;
-	unsigned long flags;
 	struct sk_buff *skb;
 	u32 hash;
 
@@ -5103,10 +5103,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
 	skb_record_rx_queue(skb, queue);
 	napi_gro_receive(&ch->rxtx_napi, skb);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n++;
-	rxq_stats->rx_bytes += len;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.rx_pkt_n);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, len);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 }
 
 static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5188,7 +5188,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct bpf_prog *prog;
 	bool failure = false;
-	unsigned long flags;
 	int xdp_status = 0;
 	int status = 0;
 
@@ -5343,9 +5342,9 @@ read_again:
 
 	stmmac_finalize_xdp_rx(priv, xdp_status);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5383,7 +5382,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int desc_size;
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
-	unsigned long flags;
 	int xdp_status = 0;
 	int buf_sz;
 
@@ -5643,11 +5641,11 @@ drain_data:
 
 	stmmac_rx_refill(priv, queue);
 
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->rx_packets += rx_packets;
-	rxq_stats->rx_bytes += rx_bytes;
-	rxq_stats->rx_pkt_n += count;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets);
+	u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes);
+	u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	priv->xstats.rx_dropped += rx_dropped;
 	priv->xstats.rx_errors += rx_errors;
@@ -5662,13 +5660,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 	struct stmmac_priv *priv = ch->priv_data;
 	struct stmmac_rxq_stats *rxq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	work_done = stmmac_rx(priv, budget, chan);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5690,13 +5687,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
 	struct stmmac_txq_stats *txq_stats;
 	bool pending_packets = false;
 	u32 chan = ch->index;
-	unsigned long flags;
 	int work_done;
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets);
 	work_done = min(work_done, budget);
@@ -5726,17 +5722,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
 	struct stmmac_rxq_stats *rxq_stats;
 	struct stmmac_txq_stats *txq_stats;
 	u32 chan = ch->index;
-	unsigned long flags;
 
 	rxq_stats = &priv->xstats.rxq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
-	rxq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+	u64_stats_update_begin(&rxq_stats->napi_syncp);
+	u64_stats_inc(&rxq_stats->napi.poll);
+	u64_stats_update_end(&rxq_stats->napi_syncp);
 
 	txq_stats = &priv->xstats.txq_stats[chan];
-	flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
-	txq_stats->napi_poll++;
-	u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+	u64_stats_update_begin(&txq_stats->napi_syncp);
+	u64_stats_inc(&txq_stats->napi.poll);
+	u64_stats_update_end(&txq_stats->napi_syncp);
 
 	tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets);
 	tx_done = min(tx_done, budget);
@@ -6067,11 +6062,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id)
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6087,11 +6077,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id)
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6113,11 +6098,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
 	dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]);
 	priv = container_of(dma_conf, struct stmmac_priv, dma_conf);
 
-	if (unlikely(!data)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -6144,11 +6124,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data)
 	dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]);
 	priv = container_of(dma_conf, struct stmmac_priv, dma_conf);
 
-	if (unlikely(!data)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -7062,10 +7037,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 tx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&txq_stats->syncp);
-			tx_packets = txq_stats->tx_packets;
-			tx_bytes   = txq_stats->tx_bytes;
-		} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+			tx_bytes   = u64_stats_read(&txq_stats->q.tx_bytes);
+		} while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+		do {
+			start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+			tx_packets = u64_stats_read(&txq_stats->napi.tx_packets);
+		} while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
 
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes += tx_bytes;
@@ -7077,10 +7055,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
 		u64 rx_bytes;
 
 		do {
-			start = u64_stats_fetch_begin(&rxq_stats->syncp);
-			rx_packets = rxq_stats->rx_packets;
-			rx_bytes   = rxq_stats->rx_bytes;
-		} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+			start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+			rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets);
+			rx_bytes   = u64_stats_read(&rxq_stats->napi.rx_bytes);
+		} while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes += rx_bytes;
@@ -7474,9 +7452,16 @@ int stmmac_dvr_probe(struct device *device,
 	priv->dev = ndev;
 
 	for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.rxq_stats[i].syncp);
-	for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
-		u64_stats_init(&priv->xstats.txq_stats[i].syncp);
+		u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp);
+	for (i = 0; i < MTL_MAX_TX_QUEUES; i++) {
+		u64_stats_init(&priv->xstats.txq_stats[i].q_syncp);
+		u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp);
+	}
+
+	priv->xstats.pcpu_stats =
+		devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
+	if (!priv->xstats.pcpu_stats)
+		return -ENOMEM;
 
 	stmmac_set_ethtool_ops(ndev);
 	priv->pause = pause;
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index be01450c20dc..1530d13984d4 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -189,6 +189,7 @@ config TI_ICSSG_PRUETH
 	select TI_K3_CPPI_DESC_POOL
 	depends on PRU_REMOTEPROC
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
 	  This subsystem is available starting with the AM65 platform.
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 9d2f4ac783e4..2939a21ca74f 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -294,7 +294,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev,
 		   txqueue,
 		   netif_tx_queue_stopped(netif_txq),
 		   jiffies_to_msecs(jiffies - trans_start),
-		   dql_avail(&netif_txq->dql),
+		   netdev_queue_dql_avail(netif_txq),
 		   k3_cppi_desc_pool_avail(tx_chn->desc_pool));
 
 	if (netif_tx_queue_stopped(netif_txq)) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ea85c6dd5484..c0a5abd8d9a8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 		}
 	}
 
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 498c50c6d1a7..087dcb67505a 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -773,6 +773,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 			slave->slave_num);
 		return;
 	}
+
+	phy->mac_managed_pm = true;
+
 	slave->phy = phy;
 
 	phy_attached_info(slave->phy);
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index bcccf43d368b..dbbea9146040 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -638,6 +638,16 @@ static void cpts_calc_mult_shift(struct cpts *cpts)
 		 freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC));
 }
 
+static void cpts_clk_unregister(void *clk)
+{
+	clk_hw_unregister_mux(clk);
+}
+
+static void cpts_clk_del_provider(void *np)
+{
+	of_clk_del_provider(np);
+}
+
 static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 {
 	struct device_node *refclk_np;
@@ -687,9 +697,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 		goto mux_fail;
 	}
 
-	ret = devm_add_action_or_reset(cpts->dev,
-				       (void(*)(void *))clk_hw_unregister_mux,
-				       clk_hw);
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_unregister, clk_hw);
 	if (ret) {
 		dev_err(cpts->dev, "add clkmux unreg action %d", ret);
 		goto mux_fail;
@@ -699,8 +707,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
 	if (ret)
 		goto mux_fail;
 
-	ret = devm_add_action_or_reset(cpts->dev,
-				       (void(*)(void *))of_clk_del_provider,
+	ret = devm_add_action_or_reset(cpts->dev, cpts_clk_del_provider,
 				       refclk_np);
 	if (ret) {
 		dev_err(cpts->dev, "add clkmux provider unreg action %d", ret);
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index d5b75af163d3..c1b0d35c8d05 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -384,18 +384,18 @@ static int gelic_descr_prepare_rx(struct gelic_card *card,
 	if (gelic_descr_get_status(descr) !=  GELIC_DESCR_DMA_NOT_IN_USE)
 		dev_info(ctodev(card), "%s: ERROR status\n", __func__);
 
-	descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size);
-	if (!descr->skb) {
-		descr->hw_regs.payload.dev_addr = 0; /* tell DMAC don't touch memory */
-		return -ENOMEM;
-	}
 	descr->hw_regs.dmac_cmd_status = 0;
 	descr->hw_regs.result_size = 0;
 	descr->hw_regs.valid_size = 0;
 	descr->hw_regs.data_error = 0;
 	descr->hw_regs.payload.dev_addr = 0;
 	descr->hw_regs.payload.size = 0;
-	descr->skb = NULL;
+
+	descr->skb = netdev_alloc_skb(*card->netdev, rx_skb_size);
+	if (!descr->skb) {
+		descr->hw_regs.payload.dev_addr = 0; /* tell DMAC don't touch memory */
+		return -ENOMEM;
+	}
 
 	offset = ((unsigned long)descr->skb->data) &
 		(GELIC_NET_RXBUF_ALIGN - 1);
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 2b6a607ac0b7..a273362c9e70 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -153,6 +153,7 @@ static const struct pci_device_id skfddi_pci_tbl[] = {
 	{ }			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(pci, skfddi_pci_tbl);
+MODULE_DESCRIPTION("SysKonnect FDDI PCI driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mirko Lindner <mlindner@syskonnect.de>");
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 32c51c244153..c4ed36c71897 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 	struct genevehdr *gnvh = geneve_hdr(skb);
 	struct metadata_dst *tun_dst = NULL;
 	unsigned int len;
-	int err = 0;
+	int nh, err = 0;
 	void *oiph;
 
 	if (ip_tunnel_collect_metadata() || gs->collect_md) {
@@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		skb->pkt_type = PACKET_HOST;
 	}
 
-	oiph = skb_network_header(skb);
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
 
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(geneve->dev, rx_length_errors);
+		DEV_STATS_INC(geneve->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	oiph = skb->head + nh;
+
 	if (geneve_get_sk_family(gs) == AF_INET)
 		err = IP_ECN_decapsulate(oiph, skb);
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index b1919278e931..2b5357d94ff5 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1903,26 +1903,26 @@ static int __init gtp_init(void)
 
 	get_random_bytes(&gtp_h_initval, sizeof(gtp_h_initval));
 
-	err = rtnl_link_register(&gtp_link_ops);
+	err = register_pernet_subsys(&gtp_net_ops);
 	if (err < 0)
 		goto error_out;
 
-	err = genl_register_family(&gtp_genl_family);
+	err = rtnl_link_register(&gtp_link_ops);
 	if (err < 0)
-		goto unreg_rtnl_link;
+		goto unreg_pernet_subsys;
 
-	err = register_pernet_subsys(&gtp_net_ops);
+	err = genl_register_family(&gtp_genl_family);
 	if (err < 0)
-		goto unreg_genl_family;
+		goto unreg_rtnl_link;
 
 	pr_info("GTP module loaded (pdp ctx size %zd bytes)\n",
 		sizeof(struct pdp_ctx));
 	return 0;
 
-unreg_genl_family:
-	genl_unregister_family(&gtp_genl_family);
 unreg_rtnl_link:
 	rtnl_link_unregister(&gtp_link_ops);
+unreg_pernet_subsys:
+	unregister_pernet_subsys(&gtp_net_ops);
 error_out:
 	pr_err("error loading GTP module loaded\n");
 	return err;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 1dafa44155d0..a6fcbda64ecc 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Disable NAPI and disassociate its context from the device. */
 	for (i = 0; i < net_device->num_chn; i++) {
 		/* See also vmbus_reset_channel_cb(). */
-		napi_disable(&net_device->chan_table[i].napi);
+		/* only disable enabled NAPI channel */
+		if (i < ndev->real_num_rx_queues)
+			napi_disable(&net_device->chan_table[i].napi);
+
 		netif_napi_del(&net_device->chan_table[i].napi);
 	}
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 273bd8a20122..11831a1c9762 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,6 +42,10 @@
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
 
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE		1
+#define VF_REG_IN_NOTIFIER	2
+
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
@@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
 }
 
 static int netvsc_vf_join(struct net_device *vf_netdev,
-			  struct net_device *ndev)
+			  struct net_device *ndev, int context)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	int ret;
@@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+	/* If this registration is called from probe context vf_takeover
+	 * is taken care of later in probe itself.
+	 */
+	if (context == VF_REG_IN_NOTIFIER)
+		schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
 
@@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
 	return NOTIFY_DONE;
 }
 
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
@@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
 
-	if (netvsc_vf_join(vf_netdev, ndev) != 0)
+	if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
 		return NOTIFY_DONE;
 
 	dev_hold(vf_netdev);
@@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+	/* Skip NetVSC interfaces */
+	if (event_ndev->netdev_ops == &device_ops)
+		return -ENODEV;
+
+	/* Avoid non-Ethernet type devices */
+	if (event_ndev->type != ARPHRD_ETHER)
+		return -ENODEV;
+
+	/* Avoid Vlan dev with same MAC registering as VF */
+	if (is_vlan_dev(event_ndev))
+		return -ENODEV;
+
+	/* Avoid Bonding master dev with same MAC registering as VF */
+	if (netif_is_bond_master(event_ndev))
+		return -ENODEV;
+
+	return 0;
+}
+
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
-	struct net_device *net = NULL;
+	struct net_device *net = NULL, *vf_netdev;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info *device_info = NULL;
 	struct netvsc_device *nvdev;
@@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 
 	list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+	/* When the hv_netvsc driver is unloaded and reloaded, the
+	 * NET_DEVICE_REGISTER for the vf device is replayed before probe
+	 * is complete. This is because register_netdevice_notifier() gets
+	 * registered before vmbus_driver_register() so that callback func
+	 * is set before probe and we don't miss events like NETDEV_POST_INIT
+	 * So, in this section we try to register the matching vf device that
+	 * is present as a netdevice, knowing that its register call is not
+	 * processed in the netvsc_netdev_notifier(as probing is progress and
+	 * get_netvsc_byslot fails).
+	 */
+	for_each_netdev(dev_net(net), vf_netdev) {
+		ret = check_dev_is_matching_vf(vf_netdev);
+		if (ret != 0)
+			continue;
+
+		if (net != get_netvsc_byslot(vf_netdev))
+			continue;
+
+		netvsc_prepare_bonding(vf_netdev);
+		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		__netvsc_vf_setup(net, vf_netdev);
+		break;
+	}
 	rtnl_unlock();
 
 	netvsc_devinfo_put(device_info);
@@ -2754,28 +2807,17 @@ static int netvsc_netdev_event(struct notifier_block *this,
 			       unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	int ret = 0;
 
-	/* Skip our own events */
-	if (event_dev->netdev_ops == &device_ops)
-		return NOTIFY_DONE;
-
-	/* Avoid non-Ethernet type devices */
-	if (event_dev->type != ARPHRD_ETHER)
-		return NOTIFY_DONE;
-
-	/* Avoid Vlan dev with same MAC registering as VF */
-	if (is_vlan_dev(event_dev))
-		return NOTIFY_DONE;
-
-	/* Avoid Bonding master dev with same MAC registering as VF */
-	if (netif_is_bond_master(event_dev))
+	ret = check_dev_is_matching_vf(event_dev);
+	if (ret != 0)
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_POST_INIT:
 		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
-		return netvsc_register_vf(event_dev);
+		return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
 	case NETDEV_UNREGISTER:
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 35e55f198e05..2930141d7dd2 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -259,4 +259,5 @@ static __exit void fake_remove_module(void)
 
 module_init(fakelb_init_module);
 module_exit(fake_remove_module);
+MODULE_DESCRIPTION("IEEE 802.15.4 loopback driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c
index 4bc05948f772..a78c692f2d3c 100644
--- a/drivers/net/ipa/ipa_interrupt.c
+++ b/drivers/net/ipa/ipa_interrupt.c
@@ -212,7 +212,7 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt)
 	u32 unit_count;
 	u32 unit;
 
-	unit_count = roundup(ipa->endpoint_count, 32);
+	unit_count = DIV_ROUND_UP(ipa->endpoint_count, 32);
 	for (unit = 0; unit < unit_count; unit++) {
 		const struct reg *reg;
 		u32 val;
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 60944a4beada..1afc4c47be73 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -237,4 +237,5 @@ static void __exit ipvtap_exit(void)
 module_exit(ipvtap_exit);
 MODULE_ALIAS_RTNL_LINK("ipvtap");
 MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_DESCRIPTION("IP-VLAN based tap driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b4d3b9cde8bd..92a7a36b93ac 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work)
 				      trap_report_dw.work);
 	nsim_dev = nsim_trap_data->nsim_dev;
 
-	/* For each running port and enabled packet trap, generate a UDP
-	 * packet with a random 5-tuple and report it.
-	 */
 	if (!devl_trylock(priv_to_devlink(nsim_dev))) {
-		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0);
+		schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1);
 		return;
 	}
 
+	/* For each running port and enabled packet trap, generate a UDP
+	 * packet with a random 5-tuple and report it.
+	 */
 	list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) {
 		if (!netif_running(nsim_dev_port->ns->netdev))
 			continue;
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
index 69b829e6ab35..7fd3377dbd79 100644
--- a/drivers/net/phy/mdio_devres.c
+++ b/drivers/net/phy/mdio_devres.c
@@ -131,4 +131,5 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
 EXPORT_SYMBOL(__devm_of_mdiobus_register);
 #endif /* CONFIG_OF_MDIO */
 
+MODULE_DESCRIPTION("Network MDIO bus devres helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index 8a20d9889f10..0f3a1538a8b8 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val,
 	u16 reg, val;
 
 	if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988)
-		bias = -2;
+		bias = -1;
 
 	val = clamp_val(bias + tx_r50_cal_val, 0, 63);
 
@@ -705,6 +705,11 @@ restore:
 static void mt798x_phy_common_finetune(struct phy_device *phydev)
 {
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
+	__phy_write(phydev, 0x11, 0xc71);
+	__phy_write(phydev, 0x12, 0xc);
+	__phy_write(phydev, 0x10, 0x8fae);
+
 	/* EnabRandUpdTrig = 1 */
 	__phy_write(phydev, 0x11, 0x2f00);
 	__phy_write(phydev, 0x12, 0xe);
@@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x83aa);
 
-	/* TrFreeze = 0 */
+	/* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */
+	__phy_write(phydev, 0x11, 0x240);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x9680);
+
+	/* TrFreeze = 0 (mt7988 default) */
 	__phy_write(phydev, 0x11, 0x0);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9686);
 
+	/* SSTrKp100 = 5 */
+	/* SSTrKf100 = 6 */
+	/* SSTrKp1000Mas = 5 */
+	/* SSTrKf1000Mas = 6 */
 	/* SSTrKp1000Slv = 5 */
+	/* SSTrKf1000Slv = 6 */
 	__phy_write(phydev, 0x11, 0xbaef);
 	__phy_write(phydev, 0x12, 0x2e);
 	__phy_write(phydev, 0x10, 0x968c);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+}
+
+static void mt7981_phy_finetune(struct phy_device *phydev)
+{
+	u16 val[8] = { 0x01ce, 0x01c1,
+		       0x020f, 0x0202,
+		       0x03d0, 0x03c0,
+		       0x0013, 0x0005 };
+	int i, k;
+
+	/* 100M eye finetune:
+	 * Keep middle level of TX MLT3 shapper as default.
+	 * Only change TX MLT3 overshoot level here.
+	 */
+	for (k = 0, i = 1; i < 12; i++) {
+		if (i % 3 == 0)
+			continue;
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
+	}
+
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* ResetSyncOffset = 6 */
+	__phy_write(phydev, 0x11, 0x600);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x8fc0);
+
+	/* VgaDecRate = 1 */
+	__phy_write(phydev, 0x11, 0x4c2a);
+	__phy_write(phydev, 0x12, 0x3e);
+	__phy_write(phydev, 0x10, 0x8fa4);
 
 	/* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2,
 	 * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2
@@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x10, 0x8ec0);
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
-	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
 		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
 		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9));
@@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222);
 }
 
-static void mt7981_phy_finetune(struct phy_device *phydev)
-{
-	u16 val[8] = { 0x01ce, 0x01c1,
-		       0x020f, 0x0202,
-		       0x03d0, 0x03c0,
-		       0x0013, 0x0005 };
-	int i, k;
-
-	/* 100M eye finetune:
-	 * Keep middle level of TX MLT3 shapper as default.
-	 * Only change TX MLT3 overshoot level here.
-	 */
-	for (k = 0, i = 1; i < 12; i++) {
-		if (i % 3 == 0)
-			continue;
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
-	}
-
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
-	__phy_write(phydev, 0x11, 0xc71);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
-	/* ResetSyncOffset = 6 */
-	__phy_write(phydev, 0x11, 0x600);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
-
-	/* VgaDecRate = 1 */
-	__phy_write(phydev, 0x11, 0x4c2a);
-	__phy_write(phydev, 0x12, 0x3e);
-	__phy_write(phydev, 0x10, 0x8fa4);
-
-	/* FfeUpdGainForce = 4 */
-	__phy_write(phydev, 0x11, 0x240);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9680);
-
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
-}
-
 static void mt7988_phy_finetune(struct phy_device *phydev)
 {
 	u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182,
@@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 	/* TCT finetune */
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5);
 
-	/* Disable TX power saving */
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
-		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
-
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */
-	__phy_write(phydev, 0x11, 0x671);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
 	/* ResetSyncOffset = 5 */
 	__phy_write(phydev, 0x11, 0x500);
 	__phy_write(phydev, 0x12, 0x0);
@@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 
 	/* VgaDecRate is 1 at default on mt7988 */
 
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+	/* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7,
+	 * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7
+	 */
+	__phy_write(phydev, 0x11, 0xb90a);
+	__phy_write(phydev, 0x12, 0x6f);
+	__phy_write(phydev, 0x10, 0x8f82);
+
+	/* RemAckCntLimitCtrl = 1 */
+	__phy_write(phydev, 0x11, 0xfbba);
+	__phy_write(phydev, 0x12, 0xc3);
+	__phy_write(phydev, 0x10, 0x87f8);
 
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30);
-	/* TxClkOffset = 2 */
-	__phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK,
-		     FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
+		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
+		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa));
+
+	/* rg_tr_lpf_cnt_val = 1023 */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff);
 }
 
 static void mt798x_phy_eee(struct phy_device *phydev)
@@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 		       MTK_PHY_LPI_SLV_SEND_TX_EN,
 		       FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120));
 
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
-		       MTK_PHY_LPI_SEND_LOC_TIMER_MASK |
-		       MTK_PHY_LPI_TXPCS_LOC_RCV,
-		       FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117));
+	/* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
+			   MTK_PHY_LPI_TXPCS_LOC_RCV);
 
+	/* This also fixes some IoT issues, such as CH340 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7,
 		       MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK,
 		       FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) |
@@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9690);
 
-	/* REG_EEE_st2TrKf1000 = 3 */
+	/* REG_EEE_st2TrKf1000 = 2 */
 	__phy_write(phydev, 0x11, 0x114f);
 	__phy_write(phydev, 0x12, 0x2);
 	__phy_write(phydev, 0x10, 0x969a);
@@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96b8);
 
-	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */
+	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
 	__phy_write(phydev, 0x11, 0x1463);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96ca);
@@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev)
 	if (err)
 		return err;
 
+	/* Disable TX power saving at probing to:
+	 * 1. Meet common mode compliance test criteria
+	 * 2. Make sure that TX-VCM calibration works fine
+	 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
+		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
+
 	return mt798x_phy_calibration(phydev);
 }
 
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 894172a3e15f..337899c69738 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -421,9 +421,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 				ERR_PTR(ret));
 			return ret;
 		}
+
+		return genphy_soft_reset(phydev);
 	}
 
-	return genphy_soft_reset(phydev);
+	return 0;
 }
 
 static int rtl821x_suspend(struct phy_device *phydev)
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index 40ce8abe6999..cc7d1113ece0 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -1437,4 +1437,5 @@ static int __init plip_init (void)
 
 module_init(plip_init);
 module_exit(plip_cleanup_module);
+MODULE_DESCRIPTION("PLIP (parallel port) network module");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c
index db0dc36d12e3..55954594e157 100644
--- a/drivers/net/ppp/bsd_comp.c
+++ b/drivers/net/ppp/bsd_comp.c
@@ -1166,5 +1166,6 @@ static void __exit bsdcomp_cleanup(void)
 
 module_init(bsdcomp_init);
 module_exit(bsdcomp_cleanup);
+MODULE_DESCRIPTION("PPP BSD-Compress compression module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS));
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 840da924708b..c33c3db3cc08 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -87,6 +87,7 @@ struct asyncppp {
 static int flag_time = HZ;
 module_param(flag_time, int, 0);
 MODULE_PARM_DESC(flag_time, "ppp_async: interval between flagged packets (in clock ticks)");
+MODULE_DESCRIPTION("PPP async serial channel module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_PPP);
 
@@ -460,6 +461,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
 	case PPPIOCSMRU:
 		if (get_user(val, p))
 			break;
+		if (val > U16_MAX) {
+			err = -EINVAL;
+			break;
+		}
 		if (val < PPP_MRU)
 			val = PPP_MRU;
 		ap->mru = val;
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index e6d48e5c65a3..4d2ff63f2ee2 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -630,6 +630,7 @@ static void __exit deflate_cleanup(void)
 
 module_init(deflate_init);
 module_exit(deflate_cleanup);
+MODULE_DESCRIPTION("PPP Deflate compression module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE));
 MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT));
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0193af2d31c9..3dd52bf28f15 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3604,6 +3604,7 @@ EXPORT_SYMBOL(ppp_input_error);
 EXPORT_SYMBOL(ppp_output_wakeup);
 EXPORT_SYMBOL(ppp_register_compressor);
 EXPORT_SYMBOL(ppp_unregister_compressor);
+MODULE_DESCRIPTION("Generic PPP layer driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0);
 MODULE_ALIAS_RTNL_LINK("ppp");
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 52d05ce4a281..45bf59ac8f57 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -724,5 +724,6 @@ ppp_sync_cleanup(void)
 
 module_init(ppp_sync_init);
 module_exit(ppp_sync_cleanup);
+MODULE_DESCRIPTION("PPP synchronous TTY channel module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_LDISC(N_SYNC_PPP);
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 8e7238e97d0a..2ea4f4890d23 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1007,26 +1007,21 @@ static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
 	struct sk_buff *skb;
 	int error = 0;
 
-	if (sk->sk_state & PPPOX_BOUND) {
-		error = -EIO;
-		goto end;
-	}
+	if (sk->sk_state & PPPOX_BOUND)
+		return -EIO;
 
 	skb = skb_recv_datagram(sk, flags, &error);
-	if (error < 0)
-		goto end;
+	if (!skb)
+		return error;
 
-	if (skb) {
-		total_len = min_t(size_t, total_len, skb->len);
-		error = skb_copy_datagram_msg(skb, 0, m, total_len);
-		if (error == 0) {
-			consume_skb(skb);
-			return total_len;
-		}
+	total_len = min_t(size_t, total_len, skb->len);
+	error = skb_copy_datagram_msg(skb, 0, m, total_len);
+	if (error == 0) {
+		consume_skb(skb);
+		return total_len;
 	}
 
 	kfree_skb(skb);
-end:
 	return error;
 }
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 4a4f8c8e79fa..8f95a562b8d0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -653,6 +653,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		ntfile->xdp_rxq.queue_index = index;
 		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
 				   NULL);
 
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 99ec1d4a972d..8b6d6a1b3c2e 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -232,7 +232,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	err = dm_read_shared_word(dev, 1, loc, &res);
 	if (err < 0) {
 		netdev_err(dev->net, "MDIO read error: %d\n", err);
-		return err;
+		return 0;
 	}
 
 	netdev_dbg(dev->net,
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a6d653ff552a..d2aa2c5b1989 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1501,7 +1501,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 
 		lan78xx_rx_urb_submit_all(dev);
 
+		local_bh_disable();
 		napi_schedule(&dev->napi);
+		local_bh_enable();
 	}
 
 	return 0;
@@ -3033,7 +3035,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
 
-	if (dev->chipid == ID_REV_CHIP_ID_7800_) {
+	if (dev->chipid == ID_REV_CHIP_ID_7800_ ||
+	    dev->chipid == ID_REV_CHIP_ID_7850_) {
 		ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig);
 		if (!ret && sig != EEPROM_INDICATOR) {
 			/* Implies there is no external eeprom. Set mac speed */
@@ -3132,7 +3135,8 @@ static int lan78xx_open(struct net_device *net)
 done:
 	mutex_unlock(&dev->dev_mutex);
 
-	usb_autopm_put_interface(dev->intf);
+	if (ret < 0)
+		usb_autopm_put_interface(dev->intf);
 
 	return ret;
 }
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index a530f20ee257..2fa46baa589e 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -2105,6 +2105,11 @@ static const struct usb_device_id products[] = {
 		.driver_info = (unsigned long) &smsc95xx_info,
 	},
 	{
+		/* SYSTEC USB-SPEmodule1 10BASE-T1L Ethernet Device */
+		USB_DEVICE(0x0878, 0x1400),
+		.driver_info = (unsigned long)&smsc95xx_info,
+	},
+	{
 		/* Microchip's EVB-LAN8670-USB 10BASE-T1S Ethernet Device */
 		USB_DEVICE(0x184F, 0x0051),
 		.driver_info = (unsigned long)&smsc95xx_info,
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 578e36ea1589..cd4a6fe458f9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1208,14 +1208,6 @@ static int veth_enable_xdp(struct net_device *dev)
 				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
 				return err;
 			}
-
-			if (!veth_gro_requested(dev)) {
-				/* user-space did not require GRO, but adding XDP
-				 * is supposed to get GRO working
-				 */
-				dev->features |= NETIF_F_GRO;
-				netdev_features_change(dev);
-			}
 		}
 	}
 
@@ -1235,18 +1227,9 @@ static void veth_disable_xdp(struct net_device *dev)
 	for (i = 0; i < dev->real_num_rx_queues; i++)
 		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
 
-	if (!netif_running(dev) || !veth_gro_requested(dev)) {
+	if (!netif_running(dev) || !veth_gro_requested(dev))
 		veth_napi_del(dev);
 
-		/* if user-space did not require GRO, since adding XDP
-		 * enabled it, clear it now
-		 */
-		if (!veth_gro_requested(dev) && netif_running(dev)) {
-			dev->features &= ~NETIF_F_GRO;
-			netdev_features_change(dev);
-		}
-	}
-
 	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
 }
 
@@ -1478,7 +1461,8 @@ static int veth_alloc_queues(struct net_device *dev)
 	struct veth_priv *priv = netdev_priv(dev);
 	int i;
 
-	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT);
+	priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq),
+			    GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
 	if (!priv->rq)
 		return -ENOMEM;
 
@@ -1494,7 +1478,7 @@ static void veth_free_queues(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 
-	kfree(priv->rq);
+	kvfree(priv->rq);
 }
 
 static int veth_dev_init(struct net_device *dev)
@@ -1654,6 +1638,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 
 		if (!old_prog) {
+			if (!veth_gro_requested(dev)) {
+				/* user-space did not require GRO, but adding
+				 * XDP is supposed to get GRO working
+				 */
+				dev->features |= NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 			peer->max_mtu = max_mtu;
 		}
@@ -1669,6 +1661,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (dev->flags & IFF_UP)
 				veth_disable_xdp(dev);
 
+			/* if user-space did not require GRO, since adding XDP
+			 * enabled it, clear it now
+			 */
+			if (!veth_gro_requested(dev)) {
+				dev->features &= ~NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			if (peer) {
 				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
 				peer->max_mtu = ETH_MAX_MTU;
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 43e0db78d42b..a742cec44e3d 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1803,5 +1803,6 @@ static struct usb_driver ar5523_driver = {
 
 module_usb_driver(ar5523_driver);
 
+MODULE_DESCRIPTION("Atheros AR5523 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_FIRMWARE(AR5523_FIRMWARE_FILE);
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 41119fb177e3..4e6b4df8562f 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1685,6 +1685,7 @@ static struct platform_driver wcn36xx_driver = {
 
 module_platform_driver(wcn36xx_driver);
 
+MODULE_DESCRIPTION("Qualcomm Atheros WCN3660/3680 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Eugene Krasnikov k.eugene.e@gmail.com");
 MODULE_FIRMWARE(WLAN_NV_FILE);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
index d55f3271d619..4f0c1e1a8e60 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_bca_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_BCA, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom AP chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 133c5ea6429c..28d6a30cc010 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3779,8 +3779,10 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
 		if (req->channels[i] == chan)
 			break;
 	}
-	if (i == req->n_channels)
-		req->channels[req->n_channels++] = chan;
+	if (i == req->n_channels) {
+		req->n_channels++;
+		req->channels[i] = chan;
+	}
 
 	for (i = 0; i < req->n_ssids; i++) {
 		if (req->ssids[i].ssid_len == ssid_len &&
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
index f82fbbe3ecef..90d06cda03a2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_cyw_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_CYW, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Cypress/Infineon chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
index 02918d434556..b66135e3cff4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_wcc_exit(void)
 	brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_WCC, THIS_MODULE);
 }
 
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom mobility chipsets");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_IMPORT_NS(BRCMFMAC);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index b96f30d11644..dcc4810cb324 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -618,7 +618,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 2) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -634,7 +634,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 1) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -650,7 +650,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 0) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -707,7 +707,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 2) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -723,7 +723,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 1) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -739,7 +739,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 					 &tbl_rev);
 	if (!IS_ERR(wifi_pkg)) {
 		if (tbl_rev != 0) {
-			ret = PTR_ERR(wifi_pkg);
+			ret = -EINVAL;
 			goto out_free;
 		}
 
@@ -1116,6 +1116,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
 		goto read_table;
 	}
 
+	ret = PTR_ERR(wifi_pkg);
+	goto out_free;
+
 read_table:
 	fwrt->ppag_ver = tbl_rev;
 	flags = &wifi_pkg->package.elements[1];
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 798731ecbefd..b740c65a7dca 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -537,7 +537,7 @@ enum iwl_fw_dbg_config_cmd_type {
 }; /* LDBG_CFG_CMD_TYPE_API_E_VER_1 */
 
 /* this token disables debug asserts in the firmware */
-#define IWL_FW_DBG_CONFIG_TOKEN 0x00011301
+#define IWL_FW_DBG_CONFIG_TOKEN 0x00010001
 
 /**
  * struct iwl_fw_dbg_config_cmd - configure FW debug
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
index 9c69d3674384..e6c0f928a6bb 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2019-2021, 2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2019-2021, 2023-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -66,6 +66,16 @@ enum iwl_gen2_tx_fifo {
 	IWL_GEN2_TRIG_TX_FIFO_VO,
 };
 
+enum iwl_bz_tx_fifo {
+	IWL_BZ_EDCA_TX_FIFO_BK,
+	IWL_BZ_EDCA_TX_FIFO_BE,
+	IWL_BZ_EDCA_TX_FIFO_VI,
+	IWL_BZ_EDCA_TX_FIFO_VO,
+	IWL_BZ_TRIG_TX_FIFO_BK,
+	IWL_BZ_TRIG_TX_FIFO_BE,
+	IWL_BZ_TRIG_TX_FIFO_VI,
+	IWL_BZ_TRIG_TX_FIFO_VO,
+};
 /**
  * enum iwl_tx_queue_cfg_actions - TXQ config options
  * @TX_QUEUE_CFG_ENABLE_QUEUE: enable a queue
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index e27774e7ed74..80fda056e46a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -19,7 +19,6 @@
  * @fwrt_ptr: pointer to the buffer coming from fwrt
  * @trans_ptr: pointer to struct %iwl_trans_dump_data which contains the
  *	transport's data.
- * @trans_len: length of the valid data in trans_ptr
  * @fwrt_len: length of the valid data in fwrt_ptr
  */
 struct iwl_fw_dump_ptrs {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ffe2670720c9..abf8001bdac1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -128,6 +128,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv)
 	kfree(drv->fw.ucode_capa.cmd_versions);
 	kfree(drv->fw.phy_integration_ver);
 	kfree(drv->trans->dbg.pc_data);
+	drv->trans->dbg.pc_data = NULL;
 
 	for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
 		iwl_free_fw_img(drv, drv->fw.img + i);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 402896988686..2f6774ec37b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -668,7 +668,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 |
@@ -793,7 +792,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
-					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2,
@@ -1020,8 +1018,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 	if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
 	    iftype_data->eht_cap.has_eht) {
 		iftype_data->eht_cap.eht_cap_elem.mac_cap_info[0] &=
-			~(IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
-			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
+			~(IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 			  IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2);
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[3] &=
 			~(IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO |
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 4582afb149d7..05b64176859e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1279,7 +1279,9 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 
 		mvm->net_detect = true;
 	} else {
-		struct iwl_wowlan_config_cmd wowlan_config_cmd = {};
+		struct iwl_wowlan_config_cmd wowlan_config_cmd = {
+			.offloading_tid = 0,
+		};
 
 		wowlan_config_cmd.sta_id = mvmvif->deflink.ap_sta_id;
 
@@ -1291,6 +1293,11 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 			goto out_noreset;
 		}
 
+		ret = iwl_mvm_sta_ensure_queue(
+			mvm, ap_sta->txq[wowlan_config_cmd.offloading_tid]);
+		if (ret)
+			goto out_noreset;
+
 		ret = iwl_mvm_get_wowlan_config(mvm, wowlan, &wowlan_config_cmd,
 						vif, mvmvif, ap_sta);
 		if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index c4f96125cf33..25a5a31e63c2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -31,6 +31,17 @@ const u8 iwl_mvm_ac_to_gen2_tx_fifo[] = {
 	IWL_GEN2_TRIG_TX_FIFO_BK,
 };
 
+const u8 iwl_mvm_ac_to_bz_tx_fifo[] = {
+	IWL_BZ_EDCA_TX_FIFO_VO,
+	IWL_BZ_EDCA_TX_FIFO_VI,
+	IWL_BZ_EDCA_TX_FIFO_BE,
+	IWL_BZ_EDCA_TX_FIFO_BK,
+	IWL_BZ_TRIG_TX_FIFO_VO,
+	IWL_BZ_TRIG_TX_FIFO_VI,
+	IWL_BZ_TRIG_TX_FIFO_BE,
+	IWL_BZ_TRIG_TX_FIFO_BK,
+};
+
 struct iwl_mvm_mac_iface_iterator_data {
 	struct iwl_mvm *mvm;
 	struct ieee80211_vif *vif;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 7f13dff04b26..53e26c3c3a9a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1600,7 +1600,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	 */
 	if (vif->type == NL80211_IFTYPE_AP ||
 	    vif->type == NL80211_IFTYPE_ADHOC) {
-		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+		if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+			iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 		ret = 0;
 		goto out;
 	}
@@ -1640,7 +1641,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 			iwl_mvm_chandef_get_primary_80(&vif->bss_conf.chandef);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
@@ -3685,6 +3687,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm,
 					   NL80211_TDLS_SETUP);
 	}
 
+	if (ret)
+		return ret;
+
 	for_each_sta_active_link(vif, sta, link_sta, i)
 		link_sta->agg.max_rc_amsdu_len = 1;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 61170173f917..893b69fc841b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -81,7 +81,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
 		ieee80211_hw_set(mvm->hw, RX_INCLUDES_FCS);
 	}
 
-	iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+		iwl_mvm_vif_dbgfs_add_link(mvm, vif);
 
 	if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
@@ -437,6 +438,9 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 		mvmvif->ap_ibss_active = false;
 	}
 
+	iwl_mvm_link_changed(mvm, vif, link_conf,
+			     LINK_CONTEXT_MODIFY_ACTIVE, false);
+
 	if (iwl_mvm_is_esr_supported(mvm->fwrt.trans) && n_active > 1) {
 		int ret = iwl_mvm_esr_mode_inactive(mvm, vif);
 
@@ -448,9 +452,6 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
 	if (vif->type == NL80211_IFTYPE_MONITOR)
 		iwl_mvm_mld_rm_snif_sta(mvm, vif);
 
-	iwl_mvm_link_changed(mvm, vif, link_conf,
-			     LINK_CONTEXT_MODIFY_ACTIVE, false);
-
 	if (switching_chanctx)
 		return;
 	mvmvif->link[link_id]->phy_ctxt = NULL;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 40627961b834..81dbef6947f5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1581,12 +1581,16 @@ static inline int iwl_mvm_max_active_links(struct iwl_mvm *mvm,
 
 extern const u8 iwl_mvm_ac_to_tx_fifo[];
 extern const u8 iwl_mvm_ac_to_gen2_tx_fifo[];
+extern const u8 iwl_mvm_ac_to_bz_tx_fifo[];
 
 static inline u8 iwl_mvm_mac_ac_to_tx_fifo(struct iwl_mvm *mvm,
 					   enum ieee80211_ac_numbers ac)
 {
-	return iwl_mvm_has_new_tx_api(mvm) ?
-		iwl_mvm_ac_to_gen2_tx_fifo[ac] : iwl_mvm_ac_to_tx_fifo[ac];
+	if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ)
+		return iwl_mvm_ac_to_bz_tx_fifo[ac];
+	if (iwl_mvm_has_new_tx_api(mvm))
+		return iwl_mvm_ac_to_gen2_tx_fifo[ac];
+	return iwl_mvm_ac_to_tx_fifo[ac];
 }
 
 struct iwl_rate_info {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 886d00098528..af15d470c69b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -505,6 +505,10 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue,
 		return false;
 
 	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+
+	if (WARN_ON_ONCE(!mvm_sta->dup_data))
+		return false;
+
 	dup_data = &mvm_sta->dup_data[queue];
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 2a3ca9785974..c2e0cff740e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1502,6 +1502,34 @@ out_err:
 	return ret;
 }
 
+int iwl_mvm_sta_ensure_queue(struct iwl_mvm *mvm,
+			     struct ieee80211_txq *txq)
+{
+	struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(txq);
+	int ret = -EINVAL;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (likely(test_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state)) ||
+	    !txq->sta) {
+		return 0;
+	}
+
+	if (!iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, txq->tid)) {
+		set_bit(IWL_MVM_TXQ_STATE_READY, &mvmtxq->state);
+		ret = 0;
+	}
+
+	local_bh_disable();
+	spin_lock(&mvm->add_stream_lock);
+	if (!list_empty(&mvmtxq->list))
+		list_del_init(&mvmtxq->list);
+	spin_unlock(&mvm->add_stream_lock);
+	local_bh_enable();
+
+	return ret;
+}
+
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk)
 {
 	struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index b33a0ce096d4..3cf8a70274ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2014 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2016 Intel Deutschland GmbH
  */
@@ -571,6 +571,7 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 				       bool disable);
 
 void iwl_mvm_csa_client_absent(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_sta_ensure_queue(struct iwl_mvm *mvm, struct ieee80211_txq *txq);
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk);
 int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 218fdf1ed530..2e653a417d62 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
@@ -972,6 +972,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 	if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) {
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
+		mvmvif->time_event_data.link_id = -1;
 		iwl_mvm_p2p_roc_finished(mvm);
 		ieee80211_remain_on_channel_expired(mvm->hw);
 	} else if (le32_to_cpu(notif->start)) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index db986bfc4dc3..461f26d9214e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -520,13 +520,24 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
 	}
 }
 
+static void iwl_mvm_copy_hdr(void *cmd, const void *hdr, int hdrlen,
+			     const u8 *addr3_override)
+{
+	struct ieee80211_hdr *out_hdr = cmd;
+
+	memcpy(cmd, hdr, hdrlen);
+	if (addr3_override)
+		memcpy(out_hdr->addr3, addr3_override, ETH_ALEN);
+}
+
 /*
  * Allocates and sets the Tx cmd the driver data pointers in the skb
  */
 static struct iwl_device_tx_cmd *
 iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		      struct ieee80211_tx_info *info, int hdrlen,
-		      struct ieee80211_sta *sta, u8 sta_id)
+		      struct ieee80211_sta *sta, u8 sta_id,
+		      const u8 *addr3_override)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_device_tx_cmd *dev_cmd;
@@ -584,7 +595,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			cmd->len = cpu_to_le16((u16)skb->len);
 
 			/* Copy MAC header from skb into command buffer */
-			memcpy(cmd->hdr, hdr, hdrlen);
+			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le16(flags);
 			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -599,7 +610,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 			cmd->len = cpu_to_le16((u16)skb->len);
 
 			/* Copy MAC header from skb into command buffer */
-			memcpy(cmd->hdr, hdr, hdrlen);
+			iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
 
 			cmd->flags = cpu_to_le32(flags);
 			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -617,7 +628,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 	iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control);
 
 	/* Copy MAC header from skb into command buffer */
-	memcpy(tx_cmd->hdr, hdr, hdrlen);
+	iwl_mvm_copy_hdr(tx_cmd->hdr, hdr, hdrlen, addr3_override);
 
 out:
 	return dev_cmd;
@@ -820,7 +831,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 
 	IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, queue);
 
-	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id);
+	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id,
+					NULL);
 	if (!dev_cmd)
 		return -1;
 
@@ -1140,7 +1152,8 @@ static int iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm,
  */
 static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 			   struct ieee80211_tx_info *info,
-			   struct ieee80211_sta *sta)
+			   struct ieee80211_sta *sta,
+			   const u8 *addr3_override)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_mvm_sta *mvmsta;
@@ -1172,7 +1185,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 		iwl_mvm_probe_resp_set_noa(mvm, skb);
 
 	dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen,
-					sta, mvmsta->deflink.sta_id);
+					sta, mvmsta->deflink.sta_id,
+					addr3_override);
 	if (!dev_cmd)
 		goto drop;
 
@@ -1294,9 +1308,11 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct ieee80211_tx_info info;
 	struct sk_buff_head mpdus_skbs;
+	struct ieee80211_vif *vif;
 	unsigned int payload_len;
 	int ret;
 	struct sk_buff *orig_skb = skb;
+	const u8 *addr3;
 
 	if (WARN_ON_ONCE(!mvmsta))
 		return -1;
@@ -1307,26 +1323,59 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 	memcpy(&info, skb->cb, sizeof(info));
 
 	if (!skb_is_gso(skb))
-		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
 
 	payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) -
 		tcp_hdrlen(skb) + skb->data_len;
 
 	if (payload_len <= skb_shinfo(skb)->gso_size)
-		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
 
 	__skb_queue_head_init(&mpdus_skbs);
 
+	vif = info.control.vif;
+	if (!vif)
+		return -1;
+
 	ret = iwl_mvm_tx_tso(mvm, skb, &info, sta, &mpdus_skbs);
 	if (ret)
 		return ret;
 
 	WARN_ON(skb_queue_empty(&mpdus_skbs));
 
+	/*
+	 * As described in IEEE sta 802.11-2020, table 9-30 (Address
+	 * field contents), A-MSDU address 3 should contain the BSSID
+	 * address.
+	 * Pass address 3 down to iwl_mvm_tx_mpdu() and further to set it
+	 * in the command header. We need to preserve the original
+	 * address 3 in the skb header to correctly create all the
+	 * A-MSDU subframe headers from it.
+	 */
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		addr3 = vif->cfg.ap_addr;
+		break;
+	case NL80211_IFTYPE_AP:
+		addr3 = vif->addr;
+		break;
+	default:
+		addr3 = NULL;
+		break;
+	}
+
 	while (!skb_queue_empty(&mpdus_skbs)) {
+		struct ieee80211_hdr *hdr;
+		bool amsdu;
+
 		skb = __skb_dequeue(&mpdus_skbs);
+		hdr = (void *)skb->data;
+		amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+			(*ieee80211_get_qos_ctl(hdr) &
+			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
 
-		ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+		ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta,
+				      amsdu ? addr3 : NULL);
 		if (ret) {
 			/* Free skbs created as part of TSO logic that have not yet been dequeued */
 			__skb_queue_purge(&mpdus_skbs);
diff --git a/drivers/net/wireless/intersil/p54/p54spi.c b/drivers/net/wireless/intersil/p54/p54spi.c
index ce0179b8ab36..0073b5e0f9c9 100644
--- a/drivers/net/wireless/intersil/p54/p54spi.c
+++ b/drivers/net/wireless/intersil/p54/p54spi.c
@@ -700,6 +700,7 @@ static struct spi_driver p54spi_driver = {
 
 module_spi_driver(p54spi_driver);
 
+MODULE_DESCRIPTION("Prism54 SPI wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Lamparter <chunkeey@web.de>");
 MODULE_ALIAS("spi:cx3110x");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 89d738deea62..e2146d30e553 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -728,6 +728,7 @@ const struct ieee80211_ops mt7603_ops = {
 	.set_sar_specs = mt7603_set_sar_specs,
 };
 
+MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static int __init mt7603_init(void)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index dab16b5fc386..0971c164b57e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -1375,4 +1375,5 @@ const struct ieee80211_ops mt7615_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7615_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index ac036a072439..87a956ea3ad7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -270,4 +270,5 @@ static void __exit mt7615_exit(void)
 
 module_init(mt7615_init);
 module_exit(mt7615_exit);
+MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index 67cedd2555f9..9692890ba51b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -253,4 +253,5 @@ module_sdio_driver(mt7663s_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 04963b9f7498..df737e1ff27b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -281,4 +281,5 @@ module_usb_driver(mt7663u_driver);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index 0052d103e276..820b39590027 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -349,4 +349,5 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_register_device);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 96494ba2fdf7..3a20ba0d2492 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -3160,4 +3160,5 @@ exit:
 EXPORT_SYMBOL_GPL(mt76_connac2_mcu_fill_message);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index c3a392a1a659..bcd24c9072ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -342,4 +342,5 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev)
 	return 0;
 }
 
+MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 9277ff38b7a2..293e66fa83d5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -302,6 +302,7 @@ static const struct pci_device_id mt76x0e_device_table[] = {
 MODULE_DEVICE_TABLE(pci, mt76x0e_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7650E_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76x0e_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 0422c332354a..dd042949cf82 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -336,6 +336,7 @@ err:
 MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
 MODULE_FIRMWARE(MT7610E_FIRMWARE);
 MODULE_FIRMWARE(MT7610U_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
 MODULE_LICENSE("GPL");
 
 static struct usb_driver mt76x0_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index 02da543dfc5c..b2cc44914294 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -293,4 +293,5 @@ void mt76x02u_init_mcu(struct mt76_dev *dev)
 EXPORT_SYMBOL_GPL(mt76x02u_init_mcu);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 8a0e8124b894..8020446be37b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -696,4 +696,5 @@ void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x02_config_mac_addr_list);
 
+MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
index 8c01855885ce..1fe5f5a02f93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
@@ -506,4 +506,5 @@ int mt76x2_eeprom_init(struct mt76x02_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
 
+MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index df85ebc6e1df..30959746e924 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -165,6 +165,7 @@ mt76x2e_resume(struct pci_dev *pdev)
 MODULE_DEVICE_TABLE(pci, mt76x2e_device_table);
 MODULE_FIRMWARE(MT7662_FIRMWARE);
 MODULE_FIRMWARE(MT7662_ROM_PATCH);
+MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct pci_driver mt76pci_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 55068f3252ef..ca78e14251c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -147,4 +147,5 @@ static struct usb_driver mt76x2u_driver = {
 module_usb_driver(mt76x2u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index aff4f21e843d..3039f53e2245 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -958,4 +958,5 @@ static void __exit mt7915_exit(void)
 
 module_init(mt7915_init);
 module_exit(mt7915_exit);
+MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 0645417e0582..0d5adc5ddae3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1418,5 +1418,6 @@ const struct ieee80211_ops mt7921_ops = {
 };
 EXPORT_SYMBOL_GPL(mt7921_ops);
 
+MODULE_DESCRIPTION("MediaTek MT7921 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 57903c6e4f11..dde26f327478 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -544,4 +544,5 @@ MODULE_FIRMWARE(MT7922_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7922_ROM_PATCH);
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 7591e54d2897..a9ce1e746b95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -323,5 +323,6 @@ static struct sdio_driver mt7921s_driver = {
 	.drv.pm		= pm_sleep_ptr(&mt7921s_pm_ops),
 };
 module_sdio_driver(mt7921s_driver);
+MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index e5258c74fc07..8b7c03c47598 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -336,5 +336,6 @@ static struct usb_driver mt7921u_driver = {
 };
 module_usb_driver(mt7921u_driver);
 
+MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 8f1075da4903..125a1be3cb64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1450,4 +1450,5 @@ const struct ieee80211_ops mt7925_ops = {
 EXPORT_SYMBOL_GPL(mt7925_ops);
 
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7925 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 734f31ee40d3..1fd99a856541 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -583,4 +583,5 @@ MODULE_FIRMWARE(MT7925_FIRMWARE_WM);
 MODULE_FIRMWARE(MT7925_ROM_PATCH);
 MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
index 9b885c5b3ed5..1e0f094fc905 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
@@ -329,4 +329,5 @@ static struct usb_driver mt7925u_driver = {
 module_usb_driver(mt7925u_driver);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 502be22dbe36..c42101aa9e45 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -862,5 +862,6 @@ int mt792x_load_firmware(struct mt792x_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt792x_load_firmware);
 
+MODULE_DESCRIPTION("MediaTek MT792x core driver");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index 2dd283caed36..589a3efb9f8c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -314,5 +314,6 @@ void mt792xu_disconnect(struct usb_interface *usb_intf)
 }
 EXPORT_SYMBOL_GPL(mt792xu_disconnect);
 
+MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 3c729b563edc..699be57309c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4477,7 +4477,8 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
 
 	skb_put_data(skb, &req, sizeof(req));
 	/* cck and ofdm */
-	skb_put_data(skb, &la.cck, sizeof(la.cck) + sizeof(la.ofdm));
+	skb_put_data(skb, &la.cck, sizeof(la.cck));
+	skb_put_data(skb, &la.ofdm, sizeof(la.ofdm));
 	/* ht20 */
 	skb_put_data(skb, &la.mcs[0], 8);
 	/* ht40 */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index c50d89a445e9..9f2abfa273c9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -650,4 +650,5 @@ static void __exit mt7996_exit(void)
 
 module_init(mt7996_init);
 module_exit(mt7996_exit);
+MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index c52d550f0c32..3e88798df017 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -672,4 +672,5 @@ EXPORT_SYMBOL_GPL(mt76s_init);
 
 MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 1584665fe3cb..5a0bcb5071bd 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -1128,4 +1128,5 @@ int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf)
 EXPORT_SYMBOL_GPL(mt76u_init);
 
 MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index fc76c66ff1a5..d6c01a2dd198 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -138,4 +138,5 @@ int __mt76_worker_fn(void *ptr)
 }
 EXPORT_SYMBOL_GPL(__mt76_worker_fn);
 
+MODULE_DESCRIPTION("MediaTek MT76x helpers");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 91d71e0f7ef2..81e8f25863f5 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -1018,5 +1018,6 @@ unregister_netdev:
 	return ERR_PTR(ret);
 }
 
+MODULE_DESCRIPTION("Atmel WILC1000 core wireless driver");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(WILC1000_FW(WILC1000_API_VER));
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 0d13e3e46e98..d6d394693090 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -984,4 +984,5 @@ static struct sdio_driver wilc_sdio_driver = {
 module_driver(wilc_sdio_driver,
 	      sdio_register_driver,
 	      sdio_unregister_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SDIO wireless driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 77b4cdff73c3..1d8b241ce43c 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -273,6 +273,7 @@ static struct spi_driver wilc_spi_driver = {
 	.remove = wilc_bus_remove,
 };
 module_spi_driver(wilc_spi_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SPI wireless driver");
 MODULE_LICENSE("GPL");
 
 static int wilc_spi_tx(struct wilc *wilc, u8 *b, u32 len)
diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index 301bd0043a43..4e5b351f80f0 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -343,5 +343,6 @@ static void __exit wl1251_sdio_exit(void)
 module_init(wl1251_sdio_init);
 module_exit(wl1251_sdio_exit);
 
+MODULE_DESCRIPTION("TI WL1251 SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 29292f06bd3d..1936bb3af54a 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -342,6 +342,7 @@ static struct spi_driver wl1251_spi_driver = {
 
 module_spi_driver(wl1251_spi_driver);
 
+MODULE_DESCRIPTION("TI WL1251 SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
 MODULE_ALIAS("spi:wl1251");
diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c
index de045fe4ca1e..b26d42b4e3cc 100644
--- a/drivers/net/wireless/ti/wl12xx/main.c
+++ b/drivers/net/wireless/ti/wl12xx/main.c
@@ -1955,6 +1955,7 @@ module_param_named(tcxo, tcxo_param, charp, 0);
 MODULE_PARM_DESC(tcxo,
 		 "TCXO clock: 19.2, 26, 38.4, 52, 16.368, 32.736, 16.8, 33.6");
 
+MODULE_DESCRIPTION("TI WL12xx wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL127X_FW_NAME_SINGLE);
diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c
index 20d9181b3410..2ccac1cdec01 100644
--- a/drivers/net/wireless/ti/wl18xx/main.c
+++ b/drivers/net/wireless/ti/wl18xx/main.c
@@ -2086,6 +2086,7 @@ module_param_named(num_rx_desc, num_rx_desc_param, int, 0400);
 MODULE_PARM_DESC(num_rx_desc_param,
 		 "Number of Rx descriptors: u8 (default is 32)");
 
+MODULE_DESCRIPTION("TI WiLink 8 wireless driver");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_FIRMWARE(WL18XX_FW_NAME);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index fb9ed97774c7..5736acb4d206 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6793,6 +6793,7 @@ MODULE_PARM_DESC(bug_on_recovery, "BUG() on fw recovery");
 module_param(no_recovery, int, 0600);
 MODULE_PARM_DESC(no_recovery, "Prevent HW recovery. FW will remain stuck.");
 
+MODULE_DESCRIPTION("TI WLAN core driver");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index f0686635db46..eb5482ed76ae 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -447,6 +447,7 @@ module_sdio_driver(wl1271_sdio_driver);
 module_param(dump, bool, 0600);
 MODULE_PARM_DESC(dump, "Enable sdio read/write dumps.");
 
+MODULE_DESCRIPTION("TI WLAN SDIO helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 7d9a139db59e..0aa2b2f3c5c9 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -562,6 +562,7 @@ static struct spi_driver wl1271_spi_driver = {
 };
 
 module_spi_driver(wl1271_spi_driver);
+MODULE_DESCRIPTION("TI WLAN SPI helpers");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
 MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index d7503aef599f..ef76850d9bcd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -104,13 +104,12 @@ bool provides_xdp_headroom = true;
 module_param(provides_xdp_headroom, bool, 0644);
 
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status);
+			       s8 status);
 
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st);
-static void push_tx_responses(struct xenvif_queue *queue);
+			     s8 status);
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
 
@@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue,
 			  unsigned int extra_count, RING_IDX end)
 {
 	RING_IDX cons = queue->tx.req_cons;
-	unsigned long flags;
 
 	do {
-		spin_lock_irqsave(&queue->response_lock, flags);
 		make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR);
-		push_tx_responses(queue);
-		spin_unlock_irqrestore(&queue->response_lock, flags);
 		if (cons == end)
 			break;
 		RING_COPY_REQUEST(&queue->tx, cons++, txp);
@@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
 	     nr_slots--) {
 		if (unlikely(!txp->size)) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&queue->response_lock, flags);
 			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
-			spin_unlock_irqrestore(&queue->response_lock, flags);
 			++txp;
 			continue;
 		}
@@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 
 		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
 			if (unlikely(!txp->size)) {
-				unsigned long flags;
-
-				spin_lock_irqsave(&queue->response_lock, flags);
 				make_tx_response(queue, txp, 0,
 						 XEN_NETIF_RSP_OKAY);
-				push_tx_responses(queue);
-				spin_unlock_irqrestore(&queue->response_lock,
-						       flags);
 				continue;
 			}
 
@@ -995,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 					 (ret == 0) ?
 					 XEN_NETIF_RSP_OKAY :
 					 XEN_NETIF_RSP_ERROR);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1007,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			make_tx_response(queue, &txreq, extra_count,
 					 XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1433,8 +1415,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget)
 	return work_done;
 }
 
+static void _make_tx_response(struct xenvif_queue *queue,
+			     const struct xen_netif_tx_request *txp,
+			     unsigned int extra_count,
+			     s8 status)
+{
+	RING_IDX i = queue->tx.rsp_prod_pvt;
+	struct xen_netif_tx_response *resp;
+
+	resp = RING_GET_RESPONSE(&queue->tx, i);
+	resp->id     = txp->id;
+	resp->status = status;
+
+	while (extra_count-- != 0)
+		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+
+	queue->tx.rsp_prod_pvt = ++i;
+}
+
+static void push_tx_responses(struct xenvif_queue *queue)
+{
+	int notify;
+
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+	if (notify)
+		notify_remote_via_irq(queue->tx_irq);
+}
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status)
+			       s8 status)
 {
 	struct pending_tx_info *pending_tx_info;
 	pending_ring_idx_t index;
@@ -1444,8 +1453,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 
 	spin_lock_irqsave(&queue->response_lock, flags);
 
-	make_tx_response(queue, &pending_tx_info->req,
-			 pending_tx_info->extra_count, status);
+	_make_tx_response(queue, &pending_tx_info->req,
+			  pending_tx_info->extra_count, status);
 
 	/* Release the pending index before pusing the Tx response so
 	 * its available before a new Tx request is pushed by the
@@ -1459,32 +1468,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
-
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st)
+			     s8 status)
 {
-	RING_IDX i = queue->tx.rsp_prod_pvt;
-	struct xen_netif_tx_response *resp;
-
-	resp = RING_GET_RESPONSE(&queue->tx, i);
-	resp->id     = txp->id;
-	resp->status = st;
-
-	while (extra_count-- != 0)
-		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+	unsigned long flags;
 
-	queue->tx.rsp_prod_pvt = ++i;
-}
+	spin_lock_irqsave(&queue->response_lock, flags);
 
-static void push_tx_responses(struct xenvif_queue *queue)
-{
-	int notify;
+	_make_tx_response(queue, txp, extra_count, status);
+	push_tx_responses(queue);
 
-	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
-	if (notify)
-		notify_remote_via_irq(queue->tx_irq);
+	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
@@ -1782,5 +1778,6 @@ static void __exit netback_fini(void)
 }
 module_exit(netback_fini);
 
+MODULE_DESCRIPTION("Xen backend network device module");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("xen-backend:vif");
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index bb3726b622ad..4d0c527e8576 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1496,19 +1496,21 @@ static int btt_blk_init(struct btt *btt)
 {
 	struct nd_btt *nd_btt = btt->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
-	int rc = -ENOMEM;
+	struct queue_limits lim = {
+		.logical_block_size	= btt->sector_size,
+		.max_hw_sectors		= UINT_MAX,
+	};
+	int rc;
 
-	btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!btt->btt_disk)
-		return -ENOMEM;
+	btt->btt_disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(btt->btt_disk))
+		return PTR_ERR(btt->btt_disk);
 
 	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
 	btt->btt_disk->first_minor = 0;
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
 
-	blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size);
-	blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, btt->btt_disk->queue);
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4e8fdcb3f1c8..8dcc10b6db5b 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -451,6 +451,11 @@ static int pmem_attach_disk(struct device *dev,
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct queue_limits lim = {
+		.logical_block_size	= pmem_sector_size(ndns),
+		.physical_block_size	= PAGE_SIZE,
+		.max_hw_sectors		= UINT_MAX,
+	};
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
 	struct range bb_range;
@@ -497,9 +502,9 @@ static int pmem_attach_disk(struct device *dev,
 		return -EBUSY;
 	}
 
-	disk = blk_alloc_disk(nid);
-	if (!disk)
-		return -ENOMEM;
+	disk = blk_alloc_disk(&lim, nid);
+	if (IS_ERR(disk))
+		return PTR_ERR(disk);
 	q = disk->queue;
 
 	pmem->disk = disk;
@@ -539,9 +544,6 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->virt_addr = addr;
 
 	blk_queue_write_cache(q, true, fua);
-	blk_queue_physical_block_size(q, PAGE_SIZE);
-	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
-	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, q);
 	if (pmem->pfn_flags & PFN_MAP)
diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c
index a23ab5c968b9..a3455f1d67fa 100644
--- a/drivers/nvme/common/auth.c
+++ b/drivers/nvme/common/auth.c
@@ -471,4 +471,5 @@ int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key)
 }
 EXPORT_SYMBOL_GPL(nvme_auth_generate_key);
 
+MODULE_DESCRIPTION("NVMe Authentication framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/common/keyring.c b/drivers/nvme/common/keyring.c
index a5c0431c101c..6f7e7a8fa5ae 100644
--- a/drivers/nvme/common/keyring.c
+++ b/drivers/nvme/common/keyring.c
@@ -181,5 +181,6 @@ static void __exit nvme_keyring_exit(void)
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
+MODULE_DESCRIPTION("NVMe Keyring implementation");
 module_init(nvme_keyring_init);
 module_exit(nvme_keyring_exit);
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 596bb11eeba5..a480cdeac288 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -797,6 +797,7 @@ static int apple_nvme_init_request(struct blk_mq_tag_set *set,
 
 static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 	bool dead = false, freeze = false;
 	unsigned long flags;
@@ -808,8 +809,8 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
 	if (csts & NVME_CSTS_CFS)
 		dead = true;
 
-	if (anv->ctrl.state == NVME_CTRL_LIVE ||
-	    anv->ctrl.state == NVME_CTRL_RESETTING) {
+	if (state == NVME_CTRL_LIVE ||
+	    state == NVME_CTRL_RESETTING) {
 		freeze = true;
 		nvme_start_freeze(&anv->ctrl);
 	}
@@ -881,7 +882,7 @@ static enum blk_eh_timer_return apple_nvme_timeout(struct request *req)
 	unsigned long flags;
 	u32 csts = readl(anv->mmio_nvme + NVME_REG_CSTS);
 
-	if (anv->ctrl.state != NVME_CTRL_LIVE) {
+	if (nvme_ctrl_state(&anv->ctrl) != NVME_CTRL_LIVE) {
 		/*
 		 * From rdma.c:
 		 * If we are resetting, connecting or deleting we should
@@ -985,10 +986,10 @@ static void apple_nvme_reset_work(struct work_struct *work)
 	u32 boot_status, aqa;
 	struct apple_nvme *anv =
 		container_of(work, struct apple_nvme, ctrl.reset_work);
+	enum nvme_ctrl_state state = nvme_ctrl_state(&anv->ctrl);
 
-	if (anv->ctrl.state != NVME_CTRL_RESETTING) {
-		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n",
-			 anv->ctrl.state);
+	if (state != NVME_CTRL_RESETTING) {
+		dev_warn(anv->dev, "ctrl state %d is not RESETTING\n", state);
 		ret = -ENODEV;
 		goto out;
 	}
@@ -1515,7 +1516,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 		goto put_dev;
 	}
 
-	anv->ctrl.admin_q = blk_mq_init_queue(&anv->admin_tagset);
+	anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
 	if (IS_ERR(anv->ctrl.admin_q)) {
 		ret = -ENOMEM;
 		goto put_dev;
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index 72c0525c75f5..a264b3ae078b 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -48,11 +48,6 @@ struct nvme_dhchap_queue_context {
 
 static struct workqueue_struct *nvme_auth_wq;
 
-#define nvme_auth_flags_from_qid(qid) \
-	(qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED
-#define nvme_auth_queue_from_qid(ctrl, qid) \
-	(qid == 0) ? (ctrl)->fabrics_q : (ctrl)->connect_q
-
 static inline int ctrl_max_dhchaps(struct nvme_ctrl *ctrl)
 {
 	return ctrl->opts->nr_io_queues + ctrl->opts->nr_write_queues +
@@ -63,10 +58,15 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 			    void *data, size_t data_len, bool auth_send)
 {
 	struct nvme_command cmd = {};
-	blk_mq_req_flags_t flags = nvme_auth_flags_from_qid(qid);
-	struct request_queue *q = nvme_auth_queue_from_qid(ctrl, qid);
+	nvme_submit_flags_t flags = NVME_SUBMIT_RETRY;
+	struct request_queue *q = ctrl->fabrics_q;
 	int ret;
 
+	if (qid != 0) {
+		flags |= NVME_SUBMIT_NOWAIT | NVME_SUBMIT_RESERVED;
+		q = ctrl->connect_q;
+	}
+
 	cmd.auth_common.opcode = nvme_fabrics_command;
 	cmd.auth_common.secp = NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER;
 	cmd.auth_common.spsp0 = 0x01;
@@ -80,8 +80,7 @@ static int nvme_auth_submit(struct nvme_ctrl *ctrl, int qid,
 	}
 
 	ret = __nvme_submit_sync_cmd(q, &cmd, NULL, data, data_len,
-				     qid == 0 ? NVME_QID_ANY : qid,
-				     0, flags);
+				     qid == 0 ? NVME_QID_ANY : qid, flags);
 	if (ret > 0)
 		dev_warn(ctrl->device,
 			"qid %d auth_send failed with status %d\n", qid, ret);
@@ -897,7 +896,7 @@ static void nvme_ctrl_auth_work(struct work_struct *work)
 	 * If the ctrl is no connected, bail as reconnect will handle
 	 * authentication.
 	 */
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	/* Authenticate admin queue first */
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 20f46c230885..6f2ebb5fcdb0 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -171,15 +171,15 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_HOST_ABORTED_CMD] = "Host Aborted Command",
 };
 
-const unsigned char *nvme_get_error_status_str(u16 status)
+const char *nvme_get_error_status_str(u16 status)
 {
 	status &= 0x7ff;
 	if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
-		return nvme_statuses[status & 0x7ff];
+		return nvme_statuses[status];
 	return "Unknown";
 }
 
-const unsigned char *nvme_get_opcode_str(u8 opcode)
+const char *nvme_get_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_ops) && nvme_ops[opcode])
 		return nvme_ops[opcode];
@@ -187,7 +187,7 @@ const unsigned char *nvme_get_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_opcode_str);
 
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	if (opcode < ARRAY_SIZE(nvme_admin_ops) && nvme_admin_ops[opcode])
 		return nvme_admin_ops[opcode];
@@ -195,7 +195,7 @@ const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
 }
 EXPORT_SYMBOL_GPL(nvme_get_admin_opcode_str);
 
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode) {
+const char *nvme_get_fabrics_opcode_str(u8 opcode) {
 	if (opcode < ARRAY_SIZE(nvme_fabrics_ops) && nvme_fabrics_ops[opcode])
 		return nvme_fabrics_ops[opcode];
 	return "Unknown";
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 85ab0fcf9e88..00864a634470 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -114,12 +114,21 @@ static DEFINE_MUTEX(nvme_subsystems_lock);
 
 static DEFINE_IDA(nvme_instance_ida);
 static dev_t nvme_ctrl_base_chr_devt;
-static struct class *nvme_class;
-static struct class *nvme_subsys_class;
+static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env);
+static const struct class nvme_class = {
+	.name = "nvme",
+	.dev_uevent = nvme_class_uevent,
+};
+
+static const struct class nvme_subsys_class = {
+	.name = "nvme-subsystem",
+};
 
 static DEFINE_IDA(nvme_ns_chr_minor_ida);
 static dev_t nvme_ns_chr_devt;
-static struct class *nvme_ns_chr_class;
+static const struct class nvme_ns_chr_class = {
+	.name = "nvme-generic",
+};
 
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -338,6 +347,30 @@ static void nvme_log_error(struct request *req)
 			   nr->status & NVME_SC_DNR  ? "DNR "  : "");
 }
 
+static void nvme_log_err_passthru(struct request *req)
+{
+	struct nvme_ns *ns = req->q->queuedata;
+	struct nvme_request *nr = nvme_req(req);
+
+	pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s"
+		"cdw10=0x%x cdw11=0x%x cdw12=0x%x cdw13=0x%x cdw14=0x%x cdw15=0x%x\n",
+		ns ? ns->disk->disk_name : dev_name(nr->ctrl->device),
+		ns ? nvme_get_opcode_str(nr->cmd->common.opcode) :
+		     nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+		nr->cmd->common.opcode,
+		nvme_get_error_status_str(nr->status),
+		nr->status >> 8 & 7,	/* Status Code Type */
+		nr->status & 0xff,	/* Status Code */
+		nr->status & NVME_SC_MORE ? "MORE " : "",
+		nr->status & NVME_SC_DNR  ? "DNR "  : "",
+		nr->cmd->common.cdw10,
+		nr->cmd->common.cdw11,
+		nr->cmd->common.cdw12,
+		nr->cmd->common.cdw13,
+		nr->cmd->common.cdw14,
+		nr->cmd->common.cdw14);
+}
+
 enum nvme_disposition {
 	COMPLETE,
 	RETRY,
@@ -385,8 +418,12 @@ static inline void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET)))
-		nvme_log_error(req);
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -679,10 +716,21 @@ static inline void nvme_clear_nvme_request(struct request *req)
 /* initialize a passthrough request */
 void nvme_init_request(struct request *req, struct nvme_command *cmd)
 {
-	if (req->q->queuedata)
+	struct nvme_request *nr = nvme_req(req);
+	bool logging_enabled;
+
+	if (req->q->queuedata) {
+		struct nvme_ns *ns = req->q->disk->private_data;
+
+		logging_enabled = ns->head->passthru_err_log_enabled;
 		req->timeout = NVME_IO_TIMEOUT;
-	else /* no queuedata implies admin queue */
+	} else { /* no queuedata implies admin queue */
+		logging_enabled = nr->ctrl->passthru_err_log_enabled;
 		req->timeout = NVME_ADMIN_TIMEOUT;
+	}
+
+	if (!logging_enabled)
+		req->rq_flags |= RQF_QUIET;
 
 	/* passthru commands should let the driver set the SGL flags */
 	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
@@ -691,8 +739,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
 	if (req->mq_hctx->type == HCTX_TYPE_POLL)
 		req->cmd_flags |= REQ_POLLED;
 	nvme_clear_nvme_request(req);
-	req->rq_flags |= RQF_QUIET;
-	memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd));
+	memcpy(nr->cmd, cmd, sizeof(*cmd));
 }
 EXPORT_SYMBOL_GPL(nvme_init_request);
 
@@ -721,7 +768,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
 
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live)
+		bool queue_live, enum nvme_ctrl_state state)
 {
 	struct nvme_request *req = nvme_req(rq);
 
@@ -742,7 +789,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (nvme_ctrl_state(ctrl)) {
+		switch (state) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -1051,20 +1098,27 @@ EXPORT_SYMBOL_NS_GPL(nvme_execute_rq, NVME_TARGET_PASSTHRU);
  */
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head, blk_mq_req_flags_t flags)
+		int qid, nvme_submit_flags_t flags)
 {
 	struct request *req;
 	int ret;
+	blk_mq_req_flags_t blk_flags = 0;
 
+	if (flags & NVME_SUBMIT_NOWAIT)
+		blk_flags |= BLK_MQ_REQ_NOWAIT;
+	if (flags & NVME_SUBMIT_RESERVED)
+		blk_flags |= BLK_MQ_REQ_RESERVED;
 	if (qid == NVME_QID_ANY)
-		req = blk_mq_alloc_request(q, nvme_req_op(cmd), flags);
+		req = blk_mq_alloc_request(q, nvme_req_op(cmd), blk_flags);
 	else
-		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), flags,
+		req = blk_mq_alloc_request_hctx(q, nvme_req_op(cmd), blk_flags,
 						qid - 1);
 
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	nvme_init_request(req, cmd);
+	if (flags & NVME_SUBMIT_RETRY)
+		req->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
 	if (buffer && bufflen) {
 		ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL);
@@ -1072,7 +1126,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out;
 	}
 
-	ret = nvme_execute_rq(req, at_head);
+	ret = nvme_execute_rq(req, flags & NVME_SUBMIT_AT_HEAD);
 	if (result && ret >= 0)
 		*result = nvme_req(req)->result;
  out:
@@ -1085,7 +1139,7 @@ int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buffer, unsigned bufflen)
 {
 	return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 }
 EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd);
 
@@ -1108,6 +1162,10 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	} else {
 		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+
+		/* Ignore execution restrictions if any relaxation bits are set */
+		if (effects & NVME_CMD_EFFECTS_CSER_MASK)
+			effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
 	}
 
 	return effects;
@@ -1349,8 +1407,10 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 
 	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
 			sizeof(struct nvme_id_ctrl));
-	if (error)
+	if (error) {
 		kfree(*id);
+		*id = NULL;
+	}
 	return error;
 }
 
@@ -1479,6 +1539,7 @@ int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	if (error) {
 		dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
 		kfree(*id);
+		*id = NULL;
 	}
 	return error;
 }
@@ -1560,7 +1621,7 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 	c.features.dword11 = cpu_to_le32(dword11);
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res,
-			buffer, buflen, NVME_QID_ANY, 0, 0);
+			buffer, buflen, NVME_QID_ANY, 0);
 	if (ret >= 0 && result)
 		*result = le32_to_cpu(res.u32);
 	return ret;
@@ -1678,12 +1739,23 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk,
-		struct nvme_ns_head *head, u32 max_integrity_segments)
+static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
 {
 	struct blk_integrity integrity = { };
 
+	blk_integrity_unregister(disk);
+
+	if (!head->ms)
+		return true;
+
+	/*
+	 * PI can always be supported as we can ask the controller to simply
+	 * insert/strip it, which is not possible for other kinds of metadata.
+	 */
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) ||
+	    !(head->features & NVME_NS_METADATA_SUPPORTED))
+		return nvme_ns_has_pi(head);
+
 	switch (head->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		switch (head->guard_type) {
@@ -1726,53 +1798,32 @@ static void nvme_init_integrity(struct gendisk *disk,
 	}
 
 	integrity.tuple_size = head->ms;
+	integrity.pi_offset = head->pi_offset;
 	blk_integrity_register(disk, &integrity);
-	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
-}
-#else
-static void nvme_init_integrity(struct gendisk *disk,
-		struct nvme_ns_head *head, u32 max_integrity_segments)
-{
+	return true;
 }
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
-		struct nvme_ns_head *head)
+static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim)
 {
-	struct request_queue *queue = disk->queue;
-	u32 max_discard_sectors;
-
-	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
-		max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
-	} else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
-		max_discard_sectors = UINT_MAX;
-	} else {
-		blk_queue_max_discard_sectors(queue, 0);
-		return;
-	}
+	struct nvme_ctrl *ctrl = ns->ctrl;
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	/*
-	 * If discard is already enabled, don't reset queue limits.
-	 *
-	 * This works around the fact that the block layer can't cope well with
-	 * updating the hardware limits when overridden through sysfs.  This is
-	 * harmless because discard limits in NVMe are purely advisory.
-	 */
-	if (queue->limits.max_discard_sectors)
-		return;
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX))
+		lim->max_hw_discard_sectors =
+			nvme_lba_to_sect(ns->head, ctrl->dmrsl);
+	else if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
+		lim->max_hw_discard_sectors = UINT_MAX;
+	else
+		lim->max_hw_discard_sectors = 0;
+
+	lim->discard_granularity = lim->logical_block_size;
 
-	blk_queue_max_discard_sectors(queue, max_discard_sectors);
 	if (ctrl->dmrl)
-		blk_queue_max_discard_segments(queue, ctrl->dmrl);
+		lim->max_discard_segments = ctrl->dmrl;
 	else
-		blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
-	queue->limits.discard_granularity = queue_logical_block_size(queue);
-
-	if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
-		blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
+		lim->max_discard_segments = NVME_DSM_MAX_RANGES;
 }
 
 static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
@@ -1783,42 +1834,38 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 		a->csi == b->csi;
 }
 
-static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
-		struct nvme_id_ns *id)
+static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid,
+		struct nvme_id_ns_nvm **nvmp)
 {
-	bool first = id->dps & NVME_NS_DPS_PI_FIRST;
-	unsigned lbaf = nvme_lbaf_index(id->flbas);
-	struct nvme_command c = { };
+	struct nvme_command c = {
+		.identify.opcode	= nvme_admin_identify,
+		.identify.nsid		= cpu_to_le32(nsid),
+		.identify.cns		= NVME_ID_CNS_CS_NS,
+		.identify.csi		= NVME_CSI_NVM,
+	};
 	struct nvme_id_ns_nvm *nvm;
-	int ret = 0;
-	u32 elbaf;
-
-	head->pi_size = 0;
-	head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
-	if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
-		head->pi_size = sizeof(struct t10_pi_tuple);
-		head->guard_type = NVME_NVM_NS_16B_GUARD;
-		goto set_pi;
-	}
+	int ret;
 
 	nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
 	if (!nvm)
 		return -ENOMEM;
 
-	c.identify.opcode = nvme_admin_identify;
-	c.identify.nsid = cpu_to_le32(head->ns_id);
-	c.identify.cns = NVME_ID_CNS_CS_NS;
-	c.identify.csi = NVME_CSI_NVM;
-
 	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
 	if (ret)
-		goto free_data;
+		kfree(nvm);
+	else
+		*nvmp = nvm;
+	return ret;
+}
 
-	elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
+static void nvme_configure_pi_elbas(struct nvme_ns_head *head,
+		struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm)
+{
+	u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]);
 
 	/* no support for storage tag formats right now */
 	if (nvme_elbaf_sts(elbaf))
-		goto free_data;
+		return;
 
 	head->guard_type = nvme_elbaf_guard_type(elbaf);
 	switch (head->guard_type) {
@@ -1831,30 +1878,31 @@ static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
 	default:
 		break;
 	}
-
-free_data:
-	kfree(nvm);
-set_pi:
-	if (head->pi_size && (first || head->ms == head->pi_size))
-		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
-	else
-		head->pi_type = 0;
-
-	return ret;
 }
 
-static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
-		struct nvme_ns_head *head, struct nvme_id_ns *id)
+static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head, struct nvme_id_ns *id,
+		struct nvme_id_ns_nvm *nvm)
 {
-	int ret;
-
-	ret = nvme_init_ms(ctrl, head, id);
-	if (ret)
-		return ret;
-
 	head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+	head->pi_type = 0;
+	head->pi_size = 0;
+	head->pi_offset = 0;
+	head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms);
 	if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return 0;
+		return;
+
+	if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
+		nvme_configure_pi_elbas(head, id, nvm);
+	} else {
+		head->pi_size = sizeof(struct t10_pi_tuple);
+		head->guard_type = NVME_NVM_NS_16B_GUARD;
+	}
+
+	if (head->pi_size && head->ms >= head->pi_size)
+		head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+	if (!(id->dps & NVME_NS_DPS_PI_FIRST))
+		head->pi_offset = head->ms - head->pi_size;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
@@ -1863,7 +1911,7 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return 0;
+			return;
 
 		head->features |= NVME_NS_EXT_LBAS;
 
@@ -1890,33 +1938,32 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
 		else
 			head->features |= NVME_NS_METADATA_SUPPORTED;
 	}
-	return 0;
 }
 
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
-		struct request_queue *q)
+static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
 {
-	bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
-
-	if (ctrl->max_hw_sectors) {
-		u32 max_segments =
-			(ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+	return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1;
+}
 
-		max_segments = min_not_zero(max_segments, ctrl->max_segments);
-		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
-		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
-	}
-	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, 3);
-	blk_queue_write_cache(q, vwc, vwc);
+static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl,
+		struct queue_limits *lim)
+{
+	lim->max_hw_sectors = ctrl->max_hw_sectors;
+	lim->max_segments = min_t(u32, USHRT_MAX,
+		min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments));
+	lim->max_integrity_segments = ctrl->max_integrity_segments;
+	lim->virt_boundary_mask = NVME_CTRL_PAGE_SIZE - 1;
+	lim->max_segment_size = UINT_MAX;
+	lim->dma_alignment = 3;
 }
 
-static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
-		struct nvme_ns_head *head, struct nvme_id_ns *id)
+static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
+		struct queue_limits *lim)
 {
-	sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+	struct nvme_ns_head *head = ns->head;
 	u32 bs = 1U << head->lba_shift;
 	u32 atomic_bs, phys_bs, io_opt = 0;
+	bool valid = true;
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
@@ -1924,12 +1971,10 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 	 * allow block I/O.
 	 */
 	if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
-		capacity = 0;
 		bs = (1 << 9);
+		valid = false;
 	}
 
-	blk_integrity_unregister(disk);
-
 	atomic_bs = phys_bs = bs;
 	if (id->nabo == 0) {
 		/*
@@ -1940,7 +1985,7 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
 			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
 		else
-			atomic_bs = (1 + ctrl->subsys->awupf) * bs;
+			atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
 	}
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
@@ -1950,36 +1995,20 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
 		io_opt = bs * (1 + le16_to_cpu(id->nows));
 	}
 
-	blk_queue_logical_block_size(disk->queue, bs);
 	/*
 	 * Linux filesystems assume writing a single physical block is
 	 * an atomic operation. Hence limit the physical block size to the
 	 * value of the Atomic Write Unit Power Fail parameter.
 	 */
-	blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
-	blk_queue_io_min(disk->queue, phys_bs);
-	blk_queue_io_opt(disk->queue, io_opt);
-
-	/*
-	 * Register a metadata profile for PI, or the plain non-integrity NVMe
-	 * metadata masquerading as Type 0 if supported, otherwise reject block
-	 * I/O to namespaces with metadata except when the namespace supports
-	 * PI, as it can strip/insert in that case.
-	 */
-	if (head->ms) {
-		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
-		    (head->features & NVME_NS_METADATA_SUPPORTED))
-			nvme_init_integrity(disk, head,
-					    ctrl->max_integrity_segments);
-		else if (!nvme_ns_has_pi(head))
-			capacity = 0;
-	}
-
-	set_capacity_and_notify(disk, capacity);
-
-	nvme_config_discard(ctrl, disk, head);
-	blk_queue_max_write_zeroes_sectors(disk->queue,
-					   ctrl->max_zeroes_sectors);
+	lim->logical_block_size = bs;
+	lim->physical_block_size = min(phys_bs, atomic_bs);
+	lim->io_min = phys_bs;
+	lim->io_opt = io_opt;
+	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+		lim->max_write_zeroes_sectors = UINT_MAX;
+	else
+		lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors;
+	return valid;
 }
 
 static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -1993,7 +2022,8 @@ static inline bool nvme_first_scan(struct gendisk *disk)
 	return !disk_live(disk);
 }
 
-static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id,
+		struct queue_limits *lim)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u32 iob;
@@ -2021,38 +2051,36 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
 		return;
 	}
 
-	blk_queue_chunk_sectors(ns->queue, iob);
+	lim->chunk_sectors = iob;
 }
 
 static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
+	struct queue_limits lim;
+	int ret;
+
 	blk_mq_freeze_queue(ns->disk->queue);
-	nvme_set_queue_limits(ns->ctrl, ns->queue);
+	lim = queue_limits_start_update(ns->disk->queue);
+	nvme_set_ctrl_limits(ns->ctrl, &lim);
+	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
-	if (nvme_ns_head_multipath(ns->head)) {
-		blk_mq_freeze_queue(ns->head->disk->queue);
-		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
-		nvme_mpath_revalidate_paths(ns);
-		blk_stack_limits(&ns->head->disk->queue->limits,
-				 &ns->queue->limits, 0);
-		ns->head->disk->flags |= GENHD_FL_HIDDEN;
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
-	}
-
 	/* Hide the block-interface for these devices */
-	ns->disk->flags |= GENHD_FL_HIDDEN;
-	set_bit(NVME_NS_READY, &ns->flags);
-
-	return 0;
+	if (!ret)
+		ret = -ENODEV;
+	return ret;
 }
 
 static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
+	bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
+	struct queue_limits lim;
+	struct nvme_id_ns_nvm *nvm = NULL;
 	struct nvme_id_ns *id;
+	sector_t capacity;
 	unsigned lbaf;
 	int ret;
 
@@ -2064,30 +2092,52 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		/* namespace not allocated or attached */
 		info->is_removed = true;
 		ret = -ENODEV;
-		goto error;
+		goto out;
+	}
+
+	if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
+		ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
+		if (ret < 0)
+			goto out;
 	}
 
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
-	nvme_set_queue_limits(ns->ctrl, ns->queue);
+	capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
 
-	ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
-	if (ret < 0) {
-		blk_mq_unfreeze_queue(ns->disk->queue);
-		goto out;
-	}
-	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
-
-	if (ns->head->ids.csi == NVME_CSI_ZNS) {
-		ret = nvme_update_zone_info(ns, lbaf);
+	lim = queue_limits_start_update(ns->disk->queue);
+	nvme_set_ctrl_limits(ns->ctrl, &lim);
+	nvme_configure_metadata(ns->ctrl, ns->head, id, nvm);
+	nvme_set_chunk_sectors(ns, id, &lim);
+	if (!nvme_update_disk_info(ns, id, &lim))
+		capacity = 0;
+	nvme_config_discard(ns, &lim);
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+	    ns->head->ids.csi == NVME_CSI_ZNS) {
+		ret = nvme_update_zone_info(ns, lbaf, &lim);
 		if (ret) {
 			blk_mq_unfreeze_queue(ns->disk->queue);
 			goto out;
 		}
 	}
+	ret = queue_limits_commit_update(ns->disk->queue, &lim);
+	if (ret) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
+
+	/*
+	 * Register a metadata profile for PI, or the plain non-integrity NVMe
+	 * metadata masquerading as Type 0 if supported, otherwise reject block
+	 * I/O to namespaces with metadata except when the namespace supports
+	 * PI, as it can strip/insert in that case.
+	 */
+	if (!nvme_init_integrity(ns->disk, ns->head))
+		capacity = 0;
+
+	set_capacity_and_notify(ns->disk, capacity);
 
 	/*
 	 * Only set the DEAC bit if the device guarantees that reads from
@@ -2098,62 +2148,81 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
 		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
+	blk_queue_write_cache(ns->disk->queue, vwc, vwc);
 	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
-		ret = nvme_revalidate_zones(ns);
+		ret = blk_revalidate_disk_zones(ns->disk, NULL);
 		if (ret && !nvme_first_scan(ns->disk))
 			goto out;
 	}
 
-	if (nvme_ns_head_multipath(ns->head)) {
-		blk_mq_freeze_queue(ns->head->disk->queue);
-		nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
-		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
-		nvme_mpath_revalidate_paths(ns);
-		blk_stack_limits(&ns->head->disk->queue->limits,
-				 &ns->queue->limits, 0);
-		disk_update_readahead(ns->head->disk);
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
-	}
-
 	ret = 0;
 out:
-	/*
-	 * If probing fails due an unsupported feature, hide the block device,
-	 * but still allow other access.
-	 */
-	if (ret == -ENODEV) {
-		ns->disk->flags |= GENHD_FL_HIDDEN;
-		set_bit(NVME_NS_READY, &ns->flags);
-		ret = 0;
-	}
-
-error:
+	kfree(nvm);
 	kfree(id);
 	return ret;
 }
 
 static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 {
+	bool unsupported = false;
+	int ret;
+
 	switch (info->ids.csi) {
 	case NVME_CSI_ZNS:
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
 			dev_info(ns->ctrl->device,
 	"block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
 				info->nsid);
-			return nvme_update_ns_info_generic(ns, info);
+			ret = nvme_update_ns_info_generic(ns, info);
+			break;
 		}
-		return nvme_update_ns_info_block(ns, info);
+		ret = nvme_update_ns_info_block(ns, info);
+		break;
 	case NVME_CSI_NVM:
-		return nvme_update_ns_info_block(ns, info);
+		ret = nvme_update_ns_info_block(ns, info);
+		break;
 	default:
 		dev_info(ns->ctrl->device,
 			"block device for nsid %u not supported (csi %u)\n",
 			info->nsid, info->ids.csi);
-		return nvme_update_ns_info_generic(ns, info);
+		ret = nvme_update_ns_info_generic(ns, info);
+		break;
+	}
+
+	/*
+	 * If probing fails due an unsupported feature, hide the block device,
+	 * but still allow other access.
+	 */
+	if (ret == -ENODEV) {
+		ns->disk->flags |= GENHD_FL_HIDDEN;
+		set_bit(NVME_NS_READY, &ns->flags);
+		unsupported = true;
+		ret = 0;
+	}
+
+	if (!ret && nvme_ns_head_multipath(ns->head)) {
+		struct queue_limits lim;
+
+		blk_mq_freeze_queue(ns->head->disk->queue);
+		if (unsupported)
+			ns->head->disk->flags |= GENHD_FL_HIDDEN;
+		else
+			nvme_init_integrity(ns->head->disk, ns->head);
+		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
+		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
+		nvme_mpath_revalidate_paths(ns);
+
+		lim = queue_limits_start_update(ns->head->disk->queue);
+		queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
+					ns->head->disk->disk_name);
+		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
+
+	return ret;
 }
 
 #ifdef CONFIG_BLK_SED_OPAL
@@ -2172,7 +2241,7 @@ static int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t l
 	cmd.common.cdw11 = cpu_to_le32(len);
 
 	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
-			NVME_QID_ANY, 1, 0);
+			NVME_QID_ANY, NVME_SUBMIT_AT_HEAD);
 }
 
 static void nvme_configure_opal(struct nvme_ctrl *ctrl, bool was_suspended)
@@ -2828,7 +2897,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	subsys->awupf = le16_to_cpu(id->awupf);
 	nvme_mpath_default_iopolicy(subsys);
 
-	subsys->dev.class = nvme_subsys_class;
+	subsys->dev.class = &nvme_subsys_class;
 	subsys->dev.release = nvme_release_subsystem;
 	subsys->dev.groups = nvme_subsys_attrs_groups;
 	dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
@@ -3068,11 +3137,17 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct
 		return -EINVAL;
 	}
 
+	if (!ctrl->maxcmd) {
+		dev_err(ctrl->device, "Maximum outstanding commands is 0\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
 static int nvme_init_identify(struct nvme_ctrl *ctrl)
 {
+	struct queue_limits lim;
 	struct nvme_id_ctrl *id;
 	u32 max_hw_sectors;
 	bool prev_apst_enabled;
@@ -3139,7 +3214,12 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->max_hw_sectors =
 		min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
 
-	nvme_set_queue_limits(ctrl, ctrl->admin_q);
+	lim = queue_limits_start_update(ctrl->admin_q);
+	nvme_set_ctrl_limits(ctrl, &lim);
+	ret = queue_limits_commit_update(ctrl->admin_q, &lim);
+	if (ret)
+		goto out_free;
+
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
 	ctrl->max_namespaces = le32_to_cpu(id->mnan);
@@ -3371,7 +3451,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
 	if (minor < 0)
 		return minor;
 	cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
-	cdev_device->class = nvme_ns_chr_class;
+	cdev_device->class = &nvme_ns_chr_class;
 	cdev_device->release = nvme_cdev_rel;
 	device_initialize(cdev_device);
 	cdev_init(cdev, fops);
@@ -3643,7 +3723,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (!ns)
 		return;
 
-	disk = blk_mq_alloc_disk(ctrl->tagset, ns);
+	disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns);
 	if (IS_ERR(disk))
 		goto out_free_ns;
 	disk->fops = &nvme_bdev_ops;
@@ -3714,6 +3794,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
+	/*
+	 * Set ns->disk->device->driver_data to ns so we can access
+	 * ns->head->passthru_err_log_enabled in
+	 * nvme_io_passthru_err_log_enabled_[store | show]().
+	 */
+	dev_set_drvdata(disk_to_dev(ns->disk), ns);
+
 	return;
 
  out_cleanup_ns_from_list:
@@ -4138,6 +4225,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
 static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 {
 	struct nvme_fw_slot_info_log *log;
+	u8 next_fw_slot, cur_fw_slot;
 
 	log = kmalloc(sizeof(*log), GFP_KERNEL);
 	if (!log)
@@ -4149,13 +4237,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 		goto out_free_log;
 	}
 
-	if (log->afi & 0x70 || !(log->afi & 0x7)) {
+	cur_fw_slot = log->afi & 0x7;
+	next_fw_slot = (log->afi & 0x70) >> 4;
+	if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
 		dev_info(ctrl->device,
 			 "Firmware is activated after next Controller Level Reset\n");
 		goto out_free_log;
 	}
 
-	memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+	memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
 		sizeof(ctrl->subsys->firmware_rev));
 
 out_free_log:
@@ -4294,6 +4384,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		const struct blk_mq_ops *ops, unsigned int cmd_size)
 {
+	struct queue_limits lim = {};
 	int ret;
 
 	memset(set, 0, sizeof(*set));
@@ -4313,14 +4404,14 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ret)
 		return ret;
 
-	ctrl->admin_q = blk_mq_init_queue(set);
+	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
 		goto out_free_tagset;
 	}
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
-		ctrl->fabrics_q = blk_mq_init_queue(set);
+		ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL);
 		if (IS_ERR(ctrl->fabrics_q)) {
 			ret = PTR_ERR(ctrl->fabrics_q);
 			goto out_cleanup_admin_q;
@@ -4384,7 +4475,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		return ret;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
-		ctrl->connect_q = blk_mq_init_queue(set);
+		ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL);
         	if (IS_ERR(ctrl->connect_q)) {
 			ret = PTR_ERR(ctrl->connect_q);
 			goto out_free_tag_set;
@@ -4514,6 +4605,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	int ret;
 
 	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
+	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4553,7 +4645,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	ctrl->device = &ctrl->ctrl_device;
 	ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
 			ctrl->instance);
-	ctrl->device->class = nvme_class;
+	ctrl->device->class = &nvme_class;
 	ctrl->device->parent = ctrl->dev;
 	if (ops->dev_attr_groups)
 		ctrl->device->groups = ops->dev_attr_groups;
@@ -4786,42 +4878,36 @@ static int __init nvme_core_init(void)
 	if (result < 0)
 		goto destroy_delete_wq;
 
-	nvme_class = class_create("nvme");
-	if (IS_ERR(nvme_class)) {
-		result = PTR_ERR(nvme_class);
+	result = class_register(&nvme_class);
+	if (result)
 		goto unregister_chrdev;
-	}
-	nvme_class->dev_uevent = nvme_class_uevent;
 
-	nvme_subsys_class = class_create("nvme-subsystem");
-	if (IS_ERR(nvme_subsys_class)) {
-		result = PTR_ERR(nvme_subsys_class);
+	result = class_register(&nvme_subsys_class);
+	if (result)
 		goto destroy_class;
-	}
 
 	result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
 				     "nvme-generic");
 	if (result < 0)
 		goto destroy_subsys_class;
 
-	nvme_ns_chr_class = class_create("nvme-generic");
-	if (IS_ERR(nvme_ns_chr_class)) {
-		result = PTR_ERR(nvme_ns_chr_class);
+	result = class_register(&nvme_ns_chr_class);
+	if (result)
 		goto unregister_generic_ns;
-	}
+
 	result = nvme_init_auth();
 	if (result)
 		goto destroy_ns_chr;
 	return 0;
 
 destroy_ns_chr:
-	class_destroy(nvme_ns_chr_class);
+	class_unregister(&nvme_ns_chr_class);
 unregister_generic_ns:
 	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 destroy_subsys_class:
-	class_destroy(nvme_subsys_class);
+	class_unregister(&nvme_subsys_class);
 destroy_class:
-	class_destroy(nvme_class);
+	class_unregister(&nvme_class);
 unregister_chrdev:
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 destroy_delete_wq:
@@ -4837,9 +4923,9 @@ out:
 static void __exit nvme_core_exit(void)
 {
 	nvme_exit_auth();
-	class_destroy(nvme_ns_chr_class);
-	class_destroy(nvme_subsys_class);
-	class_destroy(nvme_class);
+	class_unregister(&nvme_ns_chr_class);
+	class_unregister(&nvme_subsys_class);
+	class_unregister(&nvme_class);
 	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
@@ -4851,5 +4937,6 @@ static void __exit nvme_core_exit(void)
 
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host core framework");
 module_init(nvme_core_init);
 module_exit(nvme_core_exit);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index b5752a77ad98..1f0ea1f32d22 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
-			NVME_QID_ANY, 0, 0);
+			NVME_QID_ANY, 0);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
@@ -450,8 +450,10 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res,
-			data, sizeof(*data), NVME_QID_ANY, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), NVME_QID_ANY,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_NOWAIT |
+			NVME_SUBMIT_RESERVED);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
@@ -525,11 +527,14 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		return -ENOMEM;
 
 	ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res,
-			data, sizeof(*data), qid, 1,
-			BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+			data, sizeof(*data), qid,
+			NVME_SUBMIT_AT_HEAD |
+			NVME_SUBMIT_RESERVED |
+			NVME_SUBMIT_NOWAIT);
 	if (ret) {
 		nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
 				       &cmd, data);
+		goto out_free_data;
 	}
 	result = le32_to_cpu(res.u32);
 	if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) {
@@ -633,7 +638,7 @@ static struct key *nvmf_parse_key(int key_id)
 	}
 
 	key = key_lookup(key_id);
-	if (!IS_ERR(key))
+	if (IS_ERR(key))
 		pr_err("key id %08x not found\n", key_id);
 	else
 		pr_debug("Using key id %08x\n", key_id);
@@ -1314,7 +1319,10 @@ out_free_opts:
 	return ERR_PTR(ret);
 }
 
-static struct class *nvmf_class;
+static const struct class nvmf_class = {
+	.name = "nvme-fabrics",
+};
+
 static struct device *nvmf_device;
 static DEFINE_MUTEX(nvmf_dev_mutex);
 
@@ -1434,15 +1442,14 @@ static int __init nvmf_init(void)
 	if (!nvmf_default_host)
 		return -ENOMEM;
 
-	nvmf_class = class_create("nvme-fabrics");
-	if (IS_ERR(nvmf_class)) {
+	ret = class_register(&nvmf_class);
+	if (ret) {
 		pr_err("couldn't register class nvme-fabrics\n");
-		ret = PTR_ERR(nvmf_class);
 		goto out_free_host;
 	}
 
 	nvmf_device =
-		device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+		device_create(&nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
 	if (IS_ERR(nvmf_device)) {
 		pr_err("couldn't create nvme-fabrics device!\n");
 		ret = PTR_ERR(nvmf_device);
@@ -1458,9 +1465,9 @@ static int __init nvmf_init(void)
 	return 0;
 
 out_destroy_device:
-	device_destroy(nvmf_class, MKDEV(0, 0));
+	device_destroy(&nvmf_class, MKDEV(0, 0));
 out_destroy_class:
-	class_destroy(nvmf_class);
+	class_unregister(&nvmf_class);
 out_free_host:
 	nvmf_host_put(nvmf_default_host);
 	return ret;
@@ -1469,8 +1476,8 @@ out_free_host:
 static void __exit nvmf_exit(void)
 {
 	misc_deregister(&nvmf_misc);
-	device_destroy(nvmf_class, MKDEV(0, 0));
-	class_destroy(nvmf_class);
+	device_destroy(&nvmf_class, MKDEV(0, 0));
+	class_unregister(&nvmf_class);
 	nvmf_host_put(nvmf_default_host);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64);
@@ -1488,6 +1495,7 @@ static void __exit nvmf_exit(void)
 }
 
 MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("NVMe host fabrics library");
 
 module_init(nvmf_init);
 module_exit(nvmf_exit);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index fbaee5a7be19..06cc54851b1b 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -185,9 +185,11 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (ctrl->state == NVME_CTRL_DELETING ||
-	    ctrl->state == NVME_CTRL_DELETING_NOIO ||
-	    ctrl->state == NVME_CTRL_DEAD ||
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state == NVME_CTRL_DELETING ||
+	    state == NVME_CTRL_DELETING_NOIO ||
+	    state == NVME_CTRL_DEAD ||
 	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    !uuid_equal(&opts->host->id, &ctrl->opts->host->id))
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 16847a316421..68a5d971657b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -221,11 +221,6 @@ static LIST_HEAD(nvme_fc_lport_list);
 static DEFINE_IDA(nvme_fc_local_port_cnt);
 static DEFINE_IDA(nvme_fc_ctrl_cnt);
 
-static struct workqueue_struct *nvme_fc_wq;
-
-static bool nvme_fc_waiting_to_unload;
-static DECLARE_COMPLETION(nvme_fc_unload_proceed);
-
 /*
  * These items are short-term. They will eventually be moved into
  * a generic FC class. See comments in module init.
@@ -255,8 +250,6 @@ nvme_fc_free_lport(struct kref *ref)
 	/* remove from transport list */
 	spin_lock_irqsave(&nvme_fc_lock, flags);
 	list_del(&lport->port_list);
-	if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list))
-		complete(&nvme_fc_unload_proceed);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
 
 	ida_free(&nvme_fc_local_port_cnt, lport->localport.port_num);
@@ -2574,6 +2567,7 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
+	u16 qnum = op->queue->qnum;
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
 
@@ -2582,10 +2576,11 @@ static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 	 * will detect the aborted io and will fail the connection.
 	 */
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d w10/11: "
+		"NVME-FC{%d.%d}: io timeout: opcode %d fctype %d (%s) w10/11: "
 		"x%08x/x%08x\n",
-		ctrl->cnum, op->queue->qnum, sqe->common.opcode,
-		sqe->connect.fctype, sqe->common.cdw10, sqe->common.cdw11);
+		ctrl->cnum, qnum, sqe->common.opcode, sqe->fabrics.fctype,
+		nvme_fabrics_opcode_str(qnum, sqe),
+		sqe->common.cdw10, sqe->common.cdw11);
 	if (__nvme_fc_abort_op(ctrl, op))
 		nvme_fc_error_recovery(ctrl, "io timeout abort failed");
 
@@ -3575,8 +3570,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	flush_delayed_work(&ctrl->connect_work);
 
 	dev_info(ctrl->ctrl.device,
-		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
+		"NVME-FC{%d}: new ctrl: NQN \"%s\", hostnqn: %s\n",
+		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl), opts->host->nqn);
 
 	return &ctrl->ctrl;
 
@@ -3894,10 +3889,6 @@ static int __init nvme_fc_init_module(void)
 {
 	int ret;
 
-	nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0);
-	if (!nvme_fc_wq)
-		return -ENOMEM;
-
 	/*
 	 * NOTE:
 	 * It is expected that in the future the kernel will combine
@@ -3915,7 +3906,7 @@ static int __init nvme_fc_init_module(void)
 	ret = class_register(&fc_class);
 	if (ret) {
 		pr_err("couldn't register class fc\n");
-		goto out_destroy_wq;
+		return ret;
 	}
 
 	/*
@@ -3939,8 +3930,6 @@ out_destroy_device:
 	device_destroy(&fc_class, MKDEV(0, 0));
 out_destroy_class:
 	class_unregister(&fc_class);
-out_destroy_wq:
-	destroy_workqueue(nvme_fc_wq);
 
 	return ret;
 }
@@ -3960,48 +3949,27 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport)
 	spin_unlock(&rport->lock);
 }
 
-static void
-nvme_fc_cleanup_for_unload(void)
+static void __exit nvme_fc_exit_module(void)
 {
 	struct nvme_fc_lport *lport;
 	struct nvme_fc_rport *rport;
-
-	list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
-		list_for_each_entry(rport, &lport->endp_list, endp_list) {
-			nvme_fc_delete_controllers(rport);
-		}
-	}
-}
-
-static void __exit nvme_fc_exit_module(void)
-{
 	unsigned long flags;
-	bool need_cleanup = false;
 
 	spin_lock_irqsave(&nvme_fc_lock, flags);
-	nvme_fc_waiting_to_unload = true;
-	if (!list_empty(&nvme_fc_lport_list)) {
-		need_cleanup = true;
-		nvme_fc_cleanup_for_unload();
-	}
+	list_for_each_entry(lport, &nvme_fc_lport_list, port_list)
+		list_for_each_entry(rport, &lport->endp_list, endp_list)
+			nvme_fc_delete_controllers(rport);
 	spin_unlock_irqrestore(&nvme_fc_lock, flags);
-	if (need_cleanup) {
-		pr_info("%s: waiting for ctlr deletes\n", __func__);
-		wait_for_completion(&nvme_fc_unload_proceed);
-		pr_info("%s: ctrl deletes complete\n", __func__);
-	}
+	flush_workqueue(nvme_delete_wq);
 
 	nvmf_unregister_transport(&nvme_fc_transport);
 
-	ida_destroy(&nvme_fc_local_port_cnt);
-	ida_destroy(&nvme_fc_ctrl_cnt);
-
 	device_destroy(&fc_class, MKDEV(0, 0));
 	class_unregister(&fc_class);
-	destroy_workqueue(nvme_fc_wq);
 }
 
 module_init(nvme_fc_init_module);
 module_exit(nvme_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe host FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 18f5c1be5d67..3dfd5ae99ae0 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 2dd4137a08b2..5397fb428b24 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -156,7 +156,7 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
 	up_read(&ctrl->namespaces_rwsem);
@@ -223,13 +223,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
+
 	/*
 	 * We don't treat NVME_CTRL_DELETING as a disabled path as I/O should
 	 * still be able to complete assuming that the controller is connected.
 	 * Otherwise it will fail immediately and return to the requeue list.
 	 */
-	if (ns->ctrl->state != NVME_CTRL_LIVE &&
-	    ns->ctrl->state != NVME_CTRL_DELETING)
+	if (state != NVME_CTRL_LIVE && state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
 	    !test_bit(NVME_NS_READY, &ns->flags))
@@ -331,7 +332,7 @@ out:
 
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
-	return ns->ctrl->state == NVME_CTRL_LIVE &&
+	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
 		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
@@ -358,7 +359,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
 		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
 			continue;
-		switch (ns->ctrl->state) {
+		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
@@ -515,6 +516,7 @@ static void nvme_requeue_work(struct work_struct *work)
 
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 {
+	struct queue_limits lim;
 	bool vwc = false;
 
 	mutex_init(&head->lock);
@@ -531,9 +533,14 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	    !nvme_is_unique_nsid(ctrl, head) || !multipath)
 		return 0;
 
-	head->disk = blk_alloc_disk(ctrl->numa_node);
-	if (!head->disk)
-		return -ENOMEM;
+	blk_set_stacking_limits(&lim);
+	lim.dma_alignment = 3;
+	if (head->ids.csi != NVME_CSI_ZNS)
+		lim.max_zone_append_sectors = 0;
+
+	head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
+	if (IS_ERR(head->disk))
+		return PTR_ERR(head->disk);
 	head->disk->fops = &nvme_ns_head_ops;
 	head->disk->private_data = head;
 	sprintf(head->disk->disk_name, "nvme%dn%d",
@@ -552,11 +559,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	    ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
 		blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
 
-	/* set to a default value of 512 until the disk is validated */
-	blk_queue_logical_block_size(head->disk->queue, 512);
-	blk_set_stacking_limits(&head->disk->queue->limits);
-	blk_queue_dma_alignment(head->disk->queue, 3);
-
 	/* we need to propagate up the VMC settings */
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
 		vwc = true;
@@ -667,7 +669,7 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	 * controller is ready.
 	 */
 	if (nvme_state_is_live(ns->ana_state) &&
-	    ns->ctrl->state == NVME_CTRL_LIVE)
+	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
 }
 
@@ -748,7 +750,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 		return;
 
 	nvme_read_ana_log(ctrl);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 030c80818240..24193fcb8bd5 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -263,6 +263,7 @@ enum nvme_ctrl_flags {
 struct nvme_ctrl {
 	bool comp_seen;
 	bool identified;
+	bool passthru_err_log_enabled;
 	enum nvme_ctrl_state state;
 	spinlock_t lock;
 	struct mutex scan_lock;
@@ -454,6 +455,7 @@ struct nvme_ns_head {
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			passthru_err_log_enabled;
 	int			instance;
 	struct nvme_effects_log *effects;
 	u64			nuse;
@@ -462,6 +464,7 @@ struct nvme_ns_head {
 	u16			ms;
 	u16			pi_size;
 	u8			pi_type;
+	u8			pi_offset;
 	u8			guard_type;
 	u16			sgs;
 	u32			sws;
@@ -522,7 +525,6 @@ struct nvme_ns {
 	struct device		cdev_device;
 
 	struct nvme_fault_inject fault_inject;
-
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
@@ -805,17 +807,18 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *req);
 bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live);
+		bool queue_live, enum nvme_ctrl_state state);
 
 static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE))
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (likely(state == NVME_CTRL_LIVE))
 		return true;
-	if (ctrl->ops->flags & NVME_F_FABRICS &&
-	    ctrl->state == NVME_CTRL_DELETING)
+	if (ctrl->ops->flags & NVME_F_FABRICS && state == NVME_CTRL_DELETING)
 		return queue_live;
-	return __nvme_check_ready(ctrl, rq, queue_live);
+	return __nvme_check_ready(ctrl, rq, queue_live, state);
 }
 
 /*
@@ -836,12 +839,27 @@ static inline bool nvme_is_unique_nsid(struct nvme_ctrl *ctrl,
 		(ctrl->ctratt & NVME_CTRL_CTRATT_NVM_SETS);
 }
 
+/*
+ * Flags for __nvme_submit_sync_cmd()
+ */
+typedef __u32 __bitwise nvme_submit_flags_t;
+
+enum {
+	/* Insert request at the head of the queue */
+	NVME_SUBMIT_AT_HEAD  = (__force nvme_submit_flags_t)(1 << 0),
+	/* Set BLK_MQ_REQ_NOWAIT when allocating request */
+	NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
+	/* Set BLK_MQ_REQ_RESERVED when allocating request */
+	NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+	/* Retry command when NVME_SC_DNR is not set in the result */
+	NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
+};
+
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		void *buf, unsigned bufflen);
 int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 		union nvme_result *result, void *buffer, unsigned bufflen,
-		int qid, int at_head,
-		blk_mq_req_flags_t flags);
+		int qid, nvme_submit_flags_t flags);
 int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
 		      unsigned int dword11, void *buffer, size_t buflen,
 		      u32 *result);
@@ -1018,11 +1036,11 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
-int nvme_revalidate_zones(struct nvme_ns *ns);
 int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct queue_limits *lim);
 #ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
 blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 				       struct nvme_command *cmnd,
 				       enum nvme_zone_mgmt_action action);
@@ -1033,13 +1051,6 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
 {
 	return BLK_STS_NOTSUPP;
 }
-
-static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
-{
-	dev_warn(ns->ctrl->device,
-		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
-	return -EPROTONOSUPPORT;
-}
 #endif
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
@@ -1124,35 +1135,42 @@ static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
 }
 
 #ifdef CONFIG_NVME_VERBOSE_ERRORS
-const unsigned char *nvme_get_error_status_str(u16 status);
-const unsigned char *nvme_get_opcode_str(u8 opcode);
-const unsigned char *nvme_get_admin_opcode_str(u8 opcode);
-const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode);
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
 #else /* CONFIG_NVME_VERBOSE_ERRORS */
-static inline const unsigned char *nvme_get_error_status_str(u16 status)
+static inline const char *nvme_get_error_status_str(u16 status)
 {
 	return "I/O Error";
 }
-static inline const unsigned char *nvme_get_opcode_str(u8 opcode)
+static inline const char *nvme_get_opcode_str(u8 opcode)
 {
 	return "I/O Cmd";
 }
-static inline const unsigned char *nvme_get_admin_opcode_str(u8 opcode)
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
 {
 	return "Admin Cmd";
 }
 
-static inline const unsigned char *nvme_get_fabrics_opcode_str(u8 opcode)
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
 {
 	return "Fabrics Cmd";
 }
 #endif /* CONFIG_NVME_VERBOSE_ERRORS */
 
-static inline const unsigned char *nvme_opcode_str(int qid, u8 opcode, u8 fctype)
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
 {
-	if (opcode == nvme_fabrics_command)
-		return nvme_get_fabrics_opcode_str(fctype);
 	return qid ? nvme_get_opcode_str(opcode) :
 		nvme_get_admin_opcode_str(opcode);
 }
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c1d6357ec98a..e6267a6aa380 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1349,7 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 		dev_warn(dev->ctrl.device,
 			 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout, reset controller\n",
 			 req->tag, nvme_cid(req), opcode,
-			 nvme_opcode_str(nvmeq->qid, opcode, 0), nvmeq->qid);
+			 nvme_opcode_str(nvmeq->qid, opcode), nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		goto disable;
 	}
@@ -3543,5 +3543,6 @@ static void __exit nvme_exit(void)
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0");
+MODULE_DESCRIPTION("NVMe host PCIe transport driver");
 module_init(nvme_init);
 module_exit(nvme_exit);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 11dde0d83044..366f0bb4ebfc 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1006,6 +1006,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
 	int ret;
 	bool changed;
+	u16 max_queue_size;
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
@@ -1030,11 +1031,16 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
 	}
 
-	if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+	if (ctrl->ctrl.max_integrity_segments)
+		max_queue_size = NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
+	else
+		max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+
+	if (ctrl->ctrl.sqsize + 1 > max_queue_size) {
 		dev_warn(ctrl->ctrl.device,
-			"ctrl sqsize %u > max queue size %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
-		ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+			 "ctrl sqsize %u > max queue size %u, clamping down\n",
+			 ctrl->ctrl.sqsize + 1, max_queue_size);
+		ctrl->ctrl.sqsize = max_queue_size - 1;
 	}
 
 	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
@@ -1410,6 +1416,8 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct bio *bio = rq->bio;
 	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	u32 xfer_len;
 	int nr;
 
 	req->mr = ib_mr_pool_get(queue->qp, &queue->qp->sig_mrs);
@@ -1422,8 +1430,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	if (unlikely(nr))
 		goto mr_put;
 
-	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->head->pi_type);
+	nvme_rdma_set_sig_attrs(bi, c, req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -1441,7 +1448,11 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		     IB_ACCESS_REMOTE_WRITE;
 
 	sg->addr = cpu_to_le64(req->mr->iova);
-	put_unaligned_le24(req->mr->length, sg->length);
+	xfer_len = req->mr->length;
+	/* Check if PI is added by the HW */
+	if (!pi_count)
+		xfer_len += (xfer_len >> bi->interval_exp) * ns->head->pi_size;
+	put_unaligned_le24(xfer_len, sg->length);
 	put_unaligned_le32(req->mr->rkey, sg->key);
 	sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
 
@@ -1946,14 +1957,13 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
 	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
-	u8 opcode = req->req.cmd->common.opcode;
-	u8 fctype = req->req.cmd->fabrics.fctype;
+	struct nvme_command *cmd = req->req.cmd;
 	int qid = nvme_rdma_queue_idx(queue);
 
 	dev_warn(ctrl->ctrl.device,
 		 "I/O tag %d (%04x) opcode %#x (%s) QID %d timeout\n",
-		 rq->tag, nvme_cid(rq), opcode,
-		 nvme_opcode_str(qid, opcode, fctype), qid);
+		 rq->tag, nvme_cid(rq), cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2296,8 +2306,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
@@ -2400,4 +2410,5 @@ static void __exit nvme_rdma_cleanup_module(void)
 module_init(nvme_rdma_init_module);
 module_exit(nvme_rdma_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host RDMA transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 754e91111042..09fcaa519e5b 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -35,6 +35,31 @@ static ssize_t nvme_sysfs_rescan(struct device *dev,
 }
 static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
 
+static ssize_t nvme_adm_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf,
+			  ctrl->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+
+	ctrl->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
 static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
@@ -44,6 +69,37 @@ static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
 	return nvme_get_ns_from_dev(dev)->head;
 }
 
+static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+
+	return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
+}
+
+static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	bool passthru_err_log_enabled;
+	int err;
+
+	err = kstrtobool(buf, &passthru_err_log_enabled);
+	if (err)
+		return -EINVAL;
+	head->passthru_err_log_enabled = passthru_err_log_enabled;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_adm_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_adm_passthru_err_log_enabled_show, nvme_adm_passthru_err_log_enabled_store);
+
+static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
+	__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
+	nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
+
 static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
@@ -165,14 +221,11 @@ static int ns_update_nuse(struct nvme_ns *ns)
 
 	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
 	if (ret)
-		goto out_free_id;
+		return ret;
 
 	ns->head->nuse = le64_to_cpu(id->nuse);
-
-out_free_id:
 	kfree(id);
-
-	return ret;
+	return 0;
 }
 
 static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
@@ -208,6 +261,7 @@ static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
 #endif
+	&dev_attr_io_passthru_err_log_enabled.attr,
 	NULL,
 };
 
@@ -311,6 +365,7 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 				     char *buf)
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned state = (unsigned)nvme_ctrl_state(ctrl);
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
@@ -321,9 +376,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 		[NVME_CTRL_DEAD]	= "dead",
 	};
 
-	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
-	    state_name[ctrl->state])
-		return sysfs_emit(buf, "%s\n", state_name[ctrl->state]);
+	if (state < ARRAY_SIZE(state_name) && state_name[state])
+		return sysfs_emit(buf, "%s\n", state_name[state]);
 
 	return sysfs_emit(buf, "unknown state\n");
 }
@@ -655,6 +709,7 @@ static struct attribute *nvme_dev_attrs[] = {
 #ifdef CONFIG_NVME_TCP_TLS
 	&dev_attr_tls_key.attr,
 #endif
+	&dev_attr_adm_passthru_err_log_enabled.attr,
 	NULL
 };
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d058d990532b..a6d596e05602 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2428,13 +2428,13 @@ static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
-	u8 opc = pdu->cmd.common.opcode, fctype = pdu->cmd.fabrics.fctype;
+	struct nvme_command *cmd = &pdu->cmd;
 	int qid = nvme_tcp_queue_id(req->queue);
 
 	dev_warn(ctrl->device,
 		 "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n",
-		 rq->tag, nvme_cid(rq), pdu->hdr.type, opc,
-		 nvme_opcode_str(qid, opc, fctype), qid);
+		 rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode,
+		 nvme_fabrics_opcode_str(qid, cmd), qid);
 
 	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE) {
 		/*
@@ -2753,8 +2753,8 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	if (ret)
 		goto out_uninit_ctrl;
 
-	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
-		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
+	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp, hostnqn: %s\n",
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr, opts->host->nqn);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
@@ -2826,4 +2826,5 @@ static void __exit nvme_tcp_cleanup_module(void)
 module_init(nvme_tcp_init_module);
 module_exit(nvme_tcp_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe host TCP transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 499bbb0eee8d..722384bcc765 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -7,16 +7,6 @@
 #include <linux/vmalloc.h>
 #include "nvme.h"
 
-int nvme_revalidate_zones(struct nvme_ns *ns)
-{
-	struct request_queue *q = ns->queue;
-
-	blk_queue_chunk_sectors(q, ns->head->zsze);
-	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
-
-	return blk_revalidate_disk_zones(ns->disk, NULL);
-}
-
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 {
 	struct nvme_command c = { };
@@ -45,10 +35,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
 	return 0;
 }
 
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
+int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
+		struct queue_limits *lim)
 {
 	struct nvme_effects_log *log = ns->head->effects;
-	struct request_queue *q = ns->queue;
 	struct nvme_command c = { };
 	struct nvme_id_ns_zns *id;
 	int status;
@@ -109,10 +99,12 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk);
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
-	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
+	lim->zoned = 1;
+	lim->max_open_zones = le32_to_cpu(id->mor) + 1;
+	lim->max_active_zones = le32_to_cpu(id->mar) + 1;
+	lim->chunk_sectors = ns->head->zsze;
+	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
 free_data:
 	kfree(id);
 	return status;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 39cb570f833d..f5b7054a4a05 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -428,7 +428,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->cqes = (0x4 << 4) | 0x4;
 
 	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 2482a0db2504..77a6e817b315 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -273,6 +273,32 @@ static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, param_inline_data_size);
 
+static ssize_t nvmet_param_max_queue_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->max_queue_size);
+}
+
+static ssize_t nvmet_param_max_queue_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (nvmet_is_port_enabled(port, __func__))
+		return -EACCES;
+	ret = kstrtoint(page, 0, &port->max_queue_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for max_queue_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_max_queue_size);
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 static ssize_t nvmet_param_pi_enable_show(struct config_item *item,
 		char *page)
@@ -1859,6 +1885,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_trtype,
 	&nvmet_attr_addr_tsas,
 	&nvmet_attr_param_inline_data_size,
+	&nvmet_attr_param_max_queue_size,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	&nvmet_attr_param_pi_enable,
 #endif
@@ -1917,6 +1944,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
 	port->inline_data_size = -1;	/* < 0 == let the transport choose */
+	port->max_queue_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index d26aa30f8702..6bbe4df0166c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -248,7 +248,7 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_NS_CHANGED,
 				NVME_LOG_CHANGED_NS);
 	}
@@ -265,7 +265,7 @@ void nvmet_send_ana_event(struct nvmet_subsys *subsys,
 			continue;
 		if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_ANA_CHANGE))
 			continue;
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+		nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
 	}
 	mutex_unlock(&subsys->lock);
@@ -358,6 +358,18 @@ int nvmet_enable_port(struct nvmet_port *port)
 	if (port->inline_data_size < 0)
 		port->inline_data_size = 0;
 
+	/*
+	 * If the transport didn't set the max_queue_size properly, then clamp
+	 * it to the target limits. Also set default values in case the
+	 * transport didn't set it at all.
+	 */
+	if (port->max_queue_size < 0)
+		port->max_queue_size = NVMET_MAX_QUEUE_SIZE;
+	else
+		port->max_queue_size = clamp_t(int, port->max_queue_size,
+					       NVMET_MIN_QUEUE_SIZE,
+					       NVMET_MAX_QUEUE_SIZE);
+
 	port->enabled = true;
 	port->tr_ops = ops;
 	return 0;
@@ -1223,9 +1235,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
 	ctrl->cap |= (15ULL << 24);
 	/* maximum queue entries supported: */
 	if (ctrl->ops->get_max_queue_size)
-		ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+		ctrl->cap |= min_t(u16, ctrl->ops->get_max_queue_size(ctrl),
+				   ctrl->port->max_queue_size) - 1;
 	else
-		ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+		ctrl->cap |= ctrl->port->max_queue_size - 1;
 
 	if (nvmet_is_passthru_subsys(ctrl->subsys))
 		nvmet_passthrough_override_cap(ctrl);
@@ -1411,6 +1424,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	kref_init(&ctrl->ref);
 	ctrl->subsys = subsys;
+	ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
 	nvmet_init_cap(ctrl);
 	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
 
@@ -1705,4 +1719,5 @@ static void __exit nvmet_exit(void)
 module_init(nvmet_init);
 module_exit(nvmet_exit);
 
+MODULE_DESCRIPTION("NVMe target core framework");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 668d257fa986..ce54da8c6b36 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -21,7 +21,7 @@ static void __nvmet_disc_changed(struct nvmet_port *port,
 	if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_DISC_CHANGE))
 		return;
 
-	nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+	nvmet_add_async_event(ctrl, NVME_AER_NOTICE,
 			      NVME_AER_NOTICE_DISC_CHANGED, NVME_LOG_DISC);
 }
 
@@ -282,7 +282,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
 	id->lpa = (1 << 2);
 
 	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d8da840a1c0e..b23f4cf840bd 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -157,7 +157,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
 		return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 	}
 
-	if (sqsize > mqes) {
+	/* for fabrics, this value applies to only the I/O Submission Queues */
+	if (qid && sqsize > mqes) {
 		pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n",
 				sqsize, mqes, ctrl->cntlid);
 		req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
@@ -209,7 +210,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	struct nvmf_connect_command *c = &req->cmd->connect;
 	struct nvmf_connect_data *d;
 	struct nvmet_ctrl *ctrl = NULL;
-	u16 status = 0;
+	u16 status;
 	int ret;
 
 	if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
@@ -251,8 +252,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	if (status)
 		goto out;
 
-	ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
-
 	uuid_copy(&ctrl->hostid, &d->hostid);
 
 	ret = nvmet_setup_auth(ctrl);
@@ -290,7 +289,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
 	struct nvmf_connect_data *d;
 	struct nvmet_ctrl *ctrl;
 	u16 qid = le16_to_cpu(c->qid);
-	u16 status = 0;
+	u16 status;
 
 	if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
 		return;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index bda7a3009e85..fd229f310c93 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -111,6 +111,8 @@ struct nvmet_fc_tgtport {
 	struct nvmet_fc_port_entry	*pe;
 	struct kref			ref;
 	u32				max_sg_cnt;
+
+	struct work_struct		put_work;
 };
 
 struct nvmet_fc_port_entry {
@@ -145,7 +147,6 @@ struct nvmet_fc_tgt_queue {
 	struct list_head		avail_defer_list;
 	struct workqueue_struct		*work_q;
 	struct kref			ref;
-	struct rcu_head			rcu;
 	/* array of fcp_iods */
 	struct nvmet_fc_fcp_iod		fod[] __counted_by(sqsize);
 } __aligned(sizeof(unsigned long long));
@@ -166,10 +167,9 @@ struct nvmet_fc_tgt_assoc {
 	struct nvmet_fc_hostport	*hostport;
 	struct nvmet_fc_ls_iod		*rcv_disconn;
 	struct list_head		a_list;
-	struct nvmet_fc_tgt_queue __rcu	*queues[NVMET_NR_QUEUES + 1];
+	struct nvmet_fc_tgt_queue 	*queues[NVMET_NR_QUEUES + 1];
 	struct kref			ref;
 	struct work_struct		del_work;
-	struct rcu_head			rcu;
 };
 
 
@@ -249,6 +249,13 @@ static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
 static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
 static int nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue);
 static void nvmet_fc_tgtport_put(struct nvmet_fc_tgtport *tgtport);
+static void nvmet_fc_put_tgtport_work(struct work_struct *work)
+{
+	struct nvmet_fc_tgtport *tgtport =
+		container_of(work, struct nvmet_fc_tgtport, put_work);
+
+	nvmet_fc_tgtport_put(tgtport);
+}
 static int nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport);
 static void nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 					struct nvmet_fc_fcp_iod *fod);
@@ -360,7 +367,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 
 	if (!lsop->req_queued) {
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-		return;
+		goto out_putwork;
 	}
 
 	list_del(&lsop->lsreq_list);
@@ -373,7 +380,8 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop)
 				  (lsreq->rqstlen + lsreq->rsplen),
 				  DMA_BIDIRECTIONAL);
 
-	nvmet_fc_tgtport_put(tgtport);
+out_putwork:
+	queue_work(nvmet_wq, &tgtport->put_work);
 }
 
 static int
@@ -489,8 +497,7 @@ nvmet_fc_xmt_disconnect_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	 * message is normal. Otherwise, send unless the hostport has
 	 * already been invalidated by the lldd.
 	 */
-	if (!tgtport->ops->ls_req || !assoc->hostport ||
-	    assoc->hostport->invalid)
+	if (!tgtport->ops->ls_req || assoc->hostport->invalid)
 		return;
 
 	lsop = kzalloc((sizeof(*lsop) +
@@ -802,14 +809,11 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 	if (!queue)
 		return NULL;
 
-	if (!nvmet_fc_tgt_a_get(assoc))
-		goto out_free_queue;
-
 	queue->work_q = alloc_workqueue("ntfc%d.%d.%d", 0, 0,
 				assoc->tgtport->fc_target_port.port_num,
 				assoc->a_id, qid);
 	if (!queue->work_q)
-		goto out_a_put;
+		goto out_free_queue;
 
 	queue->qid = qid;
 	queue->sqsize = sqsize;
@@ -831,15 +835,13 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc,
 		goto out_fail_iodlist;
 
 	WARN_ON(assoc->queues[qid]);
-	rcu_assign_pointer(assoc->queues[qid], queue);
+	assoc->queues[qid] = queue;
 
 	return queue;
 
 out_fail_iodlist:
 	nvmet_fc_destroy_fcp_iodlist(assoc->tgtport, queue);
 	destroy_workqueue(queue->work_q);
-out_a_put:
-	nvmet_fc_tgt_a_put(assoc);
 out_free_queue:
 	kfree(queue);
 	return NULL;
@@ -852,15 +854,11 @@ nvmet_fc_tgt_queue_free(struct kref *ref)
 	struct nvmet_fc_tgt_queue *queue =
 		container_of(ref, struct nvmet_fc_tgt_queue, ref);
 
-	rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL);
-
 	nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue);
 
-	nvmet_fc_tgt_a_put(queue->assoc);
-
 	destroy_workqueue(queue->work_q);
 
-	kfree_rcu(queue, rcu);
+	kfree(queue);
 }
 
 static void
@@ -969,7 +967,7 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport,
 	rcu_read_lock();
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (association_id == assoc->association_id) {
-			queue = rcu_dereference(assoc->queues[qid]);
+			queue = assoc->queues[qid];
 			if (queue &&
 			    (!atomic_read(&queue->connected) ||
 			     !nvmet_fc_tgt_q_get(queue)))
@@ -1078,8 +1076,6 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 		/* new allocation not needed */
 		kfree(newhost);
 		newhost = match;
-		/* no new allocation - release reference */
-		nvmet_fc_tgtport_put(tgtport);
 	} else {
 		newhost->tgtport = tgtport;
 		newhost->hosthandle = hosthandle;
@@ -1094,23 +1090,54 @@ nvmet_fc_alloc_hostport(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 }
 
 static void
-nvmet_fc_delete_assoc(struct work_struct *work)
+nvmet_fc_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_delete_target_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+}
+
+static void
+nvmet_fc_delete_assoc_work(struct work_struct *work)
 {
 	struct nvmet_fc_tgt_assoc *assoc =
 		container_of(work, struct nvmet_fc_tgt_assoc, del_work);
+	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 
-	nvmet_fc_delete_target_assoc(assoc);
-	nvmet_fc_tgt_a_put(assoc);
+	nvmet_fc_delete_assoc(assoc);
+	nvmet_fc_tgtport_put(tgtport);
+}
+
+static void
+nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
+{
+	nvmet_fc_tgtport_get(assoc->tgtport);
+	queue_work(nvmet_wq, &assoc->del_work);
+}
+
+static bool
+nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+{
+	struct nvmet_fc_tgt_assoc *a;
+
+	list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
+		if (association_id == a->association_id)
+			return true;
+	}
+
+	return false;
 }
 
 static struct nvmet_fc_tgt_assoc *
 nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 {
-	struct nvmet_fc_tgt_assoc *assoc, *tmpassoc;
+	struct nvmet_fc_tgt_assoc *assoc;
 	unsigned long flags;
+	bool done;
 	u64 ran;
 	int idx;
-	bool needrandom = true;
+
+	if (!tgtport->pe)
+		return NULL;
 
 	assoc = kzalloc(sizeof(*assoc), GFP_KERNEL);
 	if (!assoc)
@@ -1120,43 +1147,35 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
 	if (idx < 0)
 		goto out_free_assoc;
 
-	if (!nvmet_fc_tgtport_get(tgtport))
-		goto out_ida;
-
 	assoc->hostport = nvmet_fc_alloc_hostport(tgtport, hosthandle);
 	if (IS_ERR(assoc->hostport))
-		goto out_put;
+		goto out_ida;
 
 	assoc->tgtport = tgtport;
 	assoc->a_id = idx;
 	INIT_LIST_HEAD(&assoc->a_list);
 	kref_init(&assoc->ref);
-	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc);
+	INIT_WORK(&assoc->del_work, nvmet_fc_delete_assoc_work);
 	atomic_set(&assoc->terminating, 0);
 
-	while (needrandom) {
+	done = false;
+	do {
 		get_random_bytes(&ran, sizeof(ran) - BYTES_FOR_QID);
 		ran = ran << BYTES_FOR_QID_SHIFT;
 
 		spin_lock_irqsave(&tgtport->lock, flags);
-		needrandom = false;
-		list_for_each_entry(tmpassoc, &tgtport->assoc_list, a_list) {
-			if (ran == tmpassoc->association_id) {
-				needrandom = true;
-				break;
-			}
-		}
-		if (!needrandom) {
+		rcu_read_lock();
+		if (!nvmet_fc_assoc_exits(tgtport, ran)) {
 			assoc->association_id = ran;
 			list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
+			done = true;
 		}
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&tgtport->lock, flags);
-	}
+	} while (!done);
 
 	return assoc;
 
-out_put:
-	nvmet_fc_tgtport_put(tgtport);
 out_ida:
 	ida_free(&tgtport->assoc_cnt, idx);
 out_free_assoc:
@@ -1172,13 +1191,18 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
 	struct nvmet_fc_ls_iod	*oldls;
 	unsigned long flags;
+	int i;
+
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			nvmet_fc_delete_target_queue(assoc->queues[i]);
+	}
 
 	/* Send Disconnect now that all i/o has completed */
 	nvmet_fc_xmt_disconnect_assoc(assoc);
 
 	nvmet_fc_free_hostport(assoc->hostport);
 	spin_lock_irqsave(&tgtport->lock, flags);
-	list_del_rcu(&assoc->a_list);
 	oldls = assoc->rcv_disconn;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 	/* if pending Rcv Disconnect Association LS, send rsp now */
@@ -1188,8 +1212,7 @@ nvmet_fc_target_assoc_free(struct kref *ref)
 	dev_info(tgtport->dev,
 		"{%d:%d} Association freed\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-	kfree_rcu(assoc, rcu);
-	nvmet_fc_tgtport_put(tgtport);
+	kfree(assoc);
 }
 
 static void
@@ -1208,7 +1231,7 @@ static void
 nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 {
 	struct nvmet_fc_tgtport *tgtport = assoc->tgtport;
-	struct nvmet_fc_tgt_queue *queue;
+	unsigned long flags;
 	int i, terminating;
 
 	terminating = atomic_xchg(&assoc->terminating, 1);
@@ -1217,29 +1240,21 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc)
 	if (terminating)
 		return;
 
+	spin_lock_irqsave(&tgtport->lock, flags);
+	list_del_rcu(&assoc->a_list);
+	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
-		rcu_read_lock();
-		queue = rcu_dereference(assoc->queues[i]);
-		if (!queue) {
-			rcu_read_unlock();
-			continue;
-		}
+	synchronize_rcu();
 
-		if (!nvmet_fc_tgt_q_get(queue)) {
-			rcu_read_unlock();
-			continue;
-		}
-		rcu_read_unlock();
-		nvmet_fc_delete_target_queue(queue);
-		nvmet_fc_tgt_q_put(queue);
+	/* ensure all in-flight I/Os have been processed */
+	for (i = NVMET_NR_QUEUES; i >= 0; i--) {
+		if (assoc->queues[i])
+			flush_workqueue(assoc->queues[i]->work_q);
 	}
 
 	dev_info(tgtport->dev,
 		"{%d:%d} Association deleted\n",
 		tgtport->fc_target_port.port_num, assoc->a_id);
-
-	nvmet_fc_tgt_a_put(assoc);
 }
 
 static struct nvmet_fc_tgt_assoc *
@@ -1415,6 +1430,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
 	newrec->max_sg_cnt = template->max_sgl_segments;
+	INIT_WORK(&newrec->put_work, nvmet_fc_put_tgtport_work);
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1492,9 +1508,8 @@ __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport)
 	list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		nvmet_fc_schedule_delete_assoc(assoc);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	rcu_read_unlock();
 }
@@ -1540,16 +1555,14 @@ nvmet_fc_invalidate_host(struct nvmet_fc_target_port *target_port,
 	spin_lock_irqsave(&tgtport->lock, flags);
 	list_for_each_entry_safe(assoc, next,
 				&tgtport->assoc_list, a_list) {
-		if (!assoc->hostport ||
-		    assoc->hostport->hosthandle != hosthandle)
+		if (assoc->hostport->hosthandle != hosthandle)
 			continue;
 		if (!nvmet_fc_tgt_a_get(assoc))
 			continue;
 		assoc->hostport->invalid = 1;
 		noassoc = false;
-		if (!queue_work(nvmet_wq, &assoc->del_work))
-			/* already deleting - release local reference */
-			nvmet_fc_tgt_a_put(assoc);
+		nvmet_fc_schedule_delete_assoc(assoc);
+		nvmet_fc_tgt_a_put(assoc);
 	}
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
@@ -1581,7 +1594,7 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) {
-			queue = rcu_dereference(assoc->queues[0]);
+			queue = assoc->queues[0];
 			if (queue && queue->nvme_sq.ctrl == ctrl) {
 				if (nvmet_fc_tgt_a_get(assoc))
 					found_ctrl = true;
@@ -1593,9 +1606,8 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl)
 		nvmet_fc_tgtport_put(tgtport);
 
 		if (found_ctrl) {
-			if (!queue_work(nvmet_wq, &assoc->del_work))
-				/* already deleting - release local reference */
-				nvmet_fc_tgt_a_put(assoc);
+			nvmet_fc_schedule_delete_assoc(assoc);
+			nvmet_fc_tgt_a_put(assoc);
 			return;
 		}
 
@@ -1625,6 +1637,8 @@ nvmet_fc_unregister_targetport(struct nvmet_fc_target_port *target_port)
 	/* terminate any outstanding associations */
 	__nvmet_fc_free_assocs(tgtport);
 
+	flush_workqueue(nvmet_wq);
+
 	/*
 	 * should terminate LS's as well. However, LS's will be generated
 	 * at the tail end of association termination, so they likely don't
@@ -1870,9 +1884,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 				sizeof(struct fcnvme_ls_disconnect_assoc_acc)),
 			FCNVME_LS_DISCONNECT_ASSOC);
 
-	/* release get taken in nvmet_fc_find_target_assoc */
-	nvmet_fc_tgt_a_put(assoc);
-
 	/*
 	 * The rules for LS response says the response cannot
 	 * go back until ABTS's have been sent for all outstanding
@@ -1887,8 +1898,6 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 	assoc->rcv_disconn = iod;
 	spin_unlock_irqrestore(&tgtport->lock, flags);
 
-	nvmet_fc_delete_target_assoc(assoc);
-
 	if (oldls) {
 		dev_info(tgtport->dev,
 			"{%d:%d} Multiple Disconnect Association LS's "
@@ -1904,6 +1913,9 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		nvmet_fc_xmt_ls_rsp(tgtport, oldls);
 	}
 
+	nvmet_fc_schedule_delete_assoc(assoc);
+	nvmet_fc_tgt_a_put(assoc);
+
 	return false;
 }
 
@@ -2540,8 +2552,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
 
 	fod->req.cmd = &fod->cmdiubuf.sqe;
 	fod->req.cqe = &fod->rspiubuf.cqe;
-	if (tgtport->pe)
-		fod->req.port = tgtport->pe->port;
+	if (!tgtport->pe)
+		goto transport_error;
+	fod->req.port = tgtport->pe->port;
 
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));
@@ -2902,6 +2915,9 @@ nvmet_fc_remove_port(struct nvmet_port *port)
 
 	nvmet_fc_portentry_unbind(pe);
 
+	/* terminate any outstanding associations */
+	__nvmet_fc_free_assocs(pe->tgtport);
+
 	kfree(pe);
 }
 
@@ -2933,6 +2949,9 @@ static int __init nvmet_fc_init_module(void)
 
 static void __exit nvmet_fc_exit_module(void)
 {
+	/* ensure any shutdown operation, e.g. delete ctrls have finished */
+	flush_workqueue(nvmet_wq);
+
 	/* sanity check - all lports should be removed */
 	if (!list_empty(&nvmet_fc_target_list))
 		pr_warn("%s: targetport list not empty\n", __func__);
@@ -2945,4 +2964,5 @@ static void __exit nvmet_fc_exit_module(void)
 module_init(nvmet_fc_init_module);
 module_exit(nvmet_fc_exit_module);
 
+MODULE_DESCRIPTION("NVMe target FC transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index ead349af30f1..913cd2ec7a6f 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport,
 	if (!rport->targetport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 		return ret;
@@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport,
 	if (remoteport) {
 		rport = remoteport->private;
 		spin_lock(&rport->lock);
-		list_add_tail(&rport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &rport->ls_list);
 		spin_unlock(&rport->lock);
 		queue_work(nvmet_wq, &rport->ls_work);
 	}
@@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle,
 	if (!tport->remoteport) {
 		tls_req->status = -ECONNREFUSED;
 		spin_lock(&tport->lock);
-		list_add_tail(&tport->ls_list, &tls_req->ls_list);
+		list_add_tail(&tls_req->ls_list, &tport->ls_list);
 		spin_unlock(&tport->lock);
 		queue_work(nvmet_wq, &tport->ls_work);
 		return ret;
@@ -1556,7 +1556,9 @@ static const struct attribute_group *fcloop_dev_attr_groups[] = {
 	NULL,
 };
 
-static struct class *fcloop_class;
+static const struct class fcloop_class = {
+	.name = "fcloop",
+};
 static struct device *fcloop_device;
 
 
@@ -1564,15 +1566,14 @@ static int __init fcloop_init(void)
 {
 	int ret;
 
-	fcloop_class = class_create("fcloop");
-	if (IS_ERR(fcloop_class)) {
+	ret = class_register(&fcloop_class);
+	if (ret) {
 		pr_err("couldn't register class fcloop\n");
-		ret = PTR_ERR(fcloop_class);
 		return ret;
 	}
 
 	fcloop_device = device_create_with_groups(
-				fcloop_class, NULL, MKDEV(0, 0), NULL,
+				&fcloop_class, NULL, MKDEV(0, 0), NULL,
 				fcloop_dev_attr_groups, "ctl");
 	if (IS_ERR(fcloop_device)) {
 		pr_err("couldn't create ctl device!\n");
@@ -1585,7 +1586,7 @@ static int __init fcloop_init(void)
 	return 0;
 
 out_destroy_class:
-	class_destroy(fcloop_class);
+	class_unregister(&fcloop_class);
 	return ret;
 }
 
@@ -1643,11 +1644,12 @@ static void __exit fcloop_exit(void)
 
 	put_device(fcloop_device);
 
-	device_destroy(fcloop_class, MKDEV(0, 0));
-	class_destroy(fcloop_class);
+	device_destroy(&fcloop_class, MKDEV(0, 0));
+	class_unregister(&fcloop_class);
 }
 
 module_init(fcloop_init);
 module_exit(fcloop_exit);
 
+MODULE_DESCRIPTION("NVMe target FC loop transport driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index f11400a908f2..6426aac2634a 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -50,10 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
 {
-	if (ns->bdev_handle) {
-		bdev_release(ns->bdev_handle);
+	if (ns->bdev_file) {
+		fput(ns->bdev_file);
 		ns->bdev = NULL;
-		ns->bdev_handle = NULL;
+		ns->bdev_file = NULL;
 	}
 }
 
@@ -85,18 +85,18 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
 	if (ns->buffered_io)
 		return -ENOTBLK;
 
-	ns->bdev_handle = bdev_open_by_path(ns->device_path,
+	ns->bdev_file = bdev_file_open_by_path(ns->device_path,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
-	if (IS_ERR(ns->bdev_handle)) {
-		ret = PTR_ERR(ns->bdev_handle);
+	if (IS_ERR(ns->bdev_file)) {
+		ret = PTR_ERR(ns->bdev_file);
 		if (ret != -ENOTBLK) {
 			pr_err("failed to open block device %s: (%d)\n",
 					ns->device_path, ret);
 		}
-		ns->bdev_handle = NULL;
+		ns->bdev_file = NULL;
 		return ret;
 	}
-	ns->bdev = ns->bdev_handle->bdev;
+	ns->bdev = file_bdev(ns->bdev_file);
 	ns->size = bdev_nr_bytes(ns->bdev);
 	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
 
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 9cb434c58075..e589915ddef8 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -400,7 +400,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 	}
 
 	nvme_quiesce_admin_queue(&ctrl->ctrl);
-	if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(&ctrl->ctrl) == NVME_CTRL_LIVE)
 		nvme_disable_ctrl(&ctrl->ctrl, true);
 
 	nvme_cancel_admin_tagset(&ctrl->ctrl);
@@ -434,8 +434,10 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 	nvme_loop_shutdown_ctrl(ctrl);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
-		if (ctrl->ctrl.state != NVME_CTRL_DELETING &&
-		    ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO)
+		enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
+		if (state != NVME_CTRL_DELETING &&
+		    state != NVME_CTRL_DELETING_NOIO)
 			/* state change failure for non-deleted ctrl? */
 			WARN_ON_ONCE(1);
 		return;
@@ -688,5 +690,6 @@ static void __exit nvme_loop_cleanup_module(void)
 module_init(nvme_loop_init_module);
 module_exit(nvme_loop_cleanup_module);
 
+MODULE_DESCRIPTION("NVMe target loop transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-254"); /* 254 == NVMF_TRTYPE_LOOP */
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 6c8acebe1a1a..f460728e1df1 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -58,7 +58,7 @@
 
 struct nvmet_ns {
 	struct percpu_ref	ref;
-	struct bdev_handle	*bdev_handle;
+	struct file		*bdev_file;
 	struct block_device	*bdev;
 	struct file		*file;
 	bool			readonly;
@@ -163,6 +163,7 @@ struct nvmet_port {
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
+	int				max_queue_size;
 	const struct nvmet_fabrics_ops	*tr_ops;
 	bool				pi_enable;
 };
@@ -543,9 +544,10 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 		u8 event_info, u8 log_page);
 
-#define NVMET_QUEUE_SIZE	1024
+#define NVMET_MIN_QUEUE_SIZE	16
+#define NVMET_MAX_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
-#define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+#define NVMET_MAX_CMD(ctrl)	(NVME_CAP_MQES(ctrl->cap) + 1)
 
 /*
  * Nice round number that makes a list of nsids fit into a page.
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f2d963e1fe94..bb4a69d538fd 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -132,7 +132,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 
 	id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
 	id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
-	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
 
 	/* don't support fuse commands */
 	id->fuses = 0;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 667f9c04f35d..f2bb9d95ecf4 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1956,6 +1956,14 @@ static int nvmet_rdma_add_port(struct nvmet_port *nport)
 		nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
 	}
 
+	if (nport->max_queue_size < 0) {
+		nport->max_queue_size = NVME_RDMA_DEFAULT_QUEUE_SIZE;
+	} else if (nport->max_queue_size > NVME_RDMA_MAX_QUEUE_SIZE) {
+		pr_warn("max_queue_size %u is too large, reducing to %u\n",
+			nport->max_queue_size, NVME_RDMA_MAX_QUEUE_SIZE);
+		nport->max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
 			nport->disc_addr.trsvcid, &port->addr);
 	if (ret) {
@@ -2015,6 +2023,8 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
 
 static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
 {
+	if (ctrl->pi_support)
+		return NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
 	return NVME_RDMA_MAX_QUEUE_SIZE;
 }
 
@@ -2104,5 +2114,6 @@ static void __exit nvmet_rdma_exit(void)
 module_init(nvmet_rdma_init);
 module_exit(nvmet_rdma_exit);
 
+MODULE_DESCRIPTION("NVMe target RDMA transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-1"); /* 1 == NVMF_TRTYPE_RDMA */
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 6a1e6bb80062..c8655fc5aa5b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -2216,10 +2216,12 @@ static void __exit nvmet_tcp_exit(void)
 	flush_workqueue(nvmet_wq);
 
 	destroy_workqueue(nvmet_tcp_wq);
+	ida_destroy(&nvmet_tcp_queue_ida);
 }
 
 module_init(nvmet_tcp_init);
 module_exit(nvmet_tcp_exit);
 
+MODULE_DESCRIPTION("NVMe target TCP transport driver");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("nvmet-transport-3"); /* 3 == NVMF_TRTYPE_TCP */
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 5b5c1e481722..3148d9f1bde6 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -456,8 +456,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
 	switch (zsa_req_op(req->cmd->zms.zsa)) {
 	case REQ_OP_ZONE_RESET:
 		ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
-				       get_capacity(req->ns->bdev->bd_disk),
-				       GFP_KERNEL);
+				       get_capacity(req->ns->bdev->bd_disk));
 		if (ret < 0)
 			return blkdev_zone_mgmt_errno_to_nvme_status(ret);
 		break;
@@ -508,7 +507,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
 		goto out;
 	}
 
-	ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
+	ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors);
 	if (ret < 0)
 		status = blkdev_zone_mgmt_errno_to_nvme_status(ret);
 
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 980123fb4dde..eb357ac2e54a 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -460,8 +460,9 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
 	list_for_each_entry(entry, &nvmem->cells, node) {
 		sysfs_bin_attr_init(&attrs[i]);
 		attrs[i].attr.name = devm_kasprintf(&nvmem->dev, GFP_KERNEL,
-						    "%s@%x", entry->name,
-						    entry->offset);
+						    "%s@%x,%x", entry->name,
+						    entry->offset,
+						    entry->bit_offset);
 		attrs[i].attr.mode = 0444;
 		attrs[i].size = entry->bytes;
 		attrs[i].read = &nvmem_cell_attr_read;
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 641a40cf5cf3..fa8cd33be131 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -763,7 +763,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node)
 	/* Walk 3 levels up only if there is 'ports' node. */
 	for (depth = 3; depth && node; depth--) {
 		node = of_get_next_parent(node);
-		if (depth == 2 && !of_node_name_eq(node, "ports"))
+		if (depth == 2 && !of_node_name_eq(node, "ports") &&
+		    !of_node_name_eq(node, "in-ports") &&
+		    !of_node_name_eq(node, "out-ports"))
 			break;
 	}
 	return node;
@@ -1063,36 +1065,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 	return of_device_get_match_data(dev);
 }
 
-static struct device_node *of_get_compat_node(struct device_node *np)
-{
-	of_node_get(np);
-
-	while (np) {
-		if (!of_device_is_available(np)) {
-			of_node_put(np);
-			np = NULL;
-		}
-
-		if (of_property_present(np, "compatible"))
-			break;
-
-		np = of_get_next_parent(np);
-	}
-
-	return np;
-}
-
-static struct device_node *of_get_compat_node_parent(struct device_node *np)
-{
-	struct device_node *parent, *node;
-
-	parent = of_get_parent(np);
-	node = of_get_compat_node(parent);
-	of_node_put(parent);
-
-	return node;
-}
-
 static void of_link_to_phandle(struct device_node *con_np,
 			      struct device_node *sup_np)
 {
@@ -1222,10 +1194,10 @@ static struct device_node *parse_##fname(struct device_node *np,	     \
  *  parse_prop.prop_name: Name of property holding a phandle value
  *  parse_prop.index: For properties holding a list of phandles, this is the
  *		      index into the list
+ * @get_con_dev: If the consumer node containing the property is never converted
+ *		 to a struct device, implement this ops so fw_devlink can use it
+ *		 to find the true consumer.
  * @optional: Describes whether a supplier is mandatory or not
- * @node_not_dev: The consumer node containing the property is never converted
- *		  to a struct device. Instead, parse ancestor nodes for the
- *		  compatible property to find a node corresponding to a device.
  *
  * Returns:
  * parse_prop() return values are
@@ -1236,15 +1208,15 @@ static struct device_node *parse_##fname(struct device_node *np,	     \
 struct supplier_bindings {
 	struct device_node *(*parse_prop)(struct device_node *np,
 					  const char *prop_name, int index);
+	struct device_node *(*get_con_dev)(struct device_node *np);
 	bool optional;
-	bool node_not_dev;
 };
 
 DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells")
 DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells")
 DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells")
 DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells")
-DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells")
+DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells")
 DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL)
 DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells")
 DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells")
@@ -1262,7 +1234,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL)
 DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL)
 DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL)
 DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL)
-DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL)
 DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells")
 DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells")
 DEFINE_SIMPLE_PROP(leds, "leds", NULL)
@@ -1328,6 +1299,17 @@ static struct device_node *parse_interrupts(struct device_node *np,
 	return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np;
 }
 
+static struct device_node *parse_remote_endpoint(struct device_node *np,
+						 const char *prop_name,
+						 int index)
+{
+	/* Return NULL for index > 0 to signify end of remote-endpoints. */
+	if (index > 0 || strcmp(prop_name, "remote-endpoint"))
+		return NULL;
+
+	return of_graph_get_remote_port_parent(np);
+}
+
 static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_clocks, },
 	{ .parse_prop = parse_interconnects, },
@@ -1352,7 +1334,10 @@ static const struct supplier_bindings of_supplier_bindings[] = {
 	{ .parse_prop = parse_pinctrl6, },
 	{ .parse_prop = parse_pinctrl7, },
 	{ .parse_prop = parse_pinctrl8, },
-	{ .parse_prop = parse_remote_endpoint, .node_not_dev = true, },
+	{
+		.parse_prop = parse_remote_endpoint,
+		.get_con_dev = of_graph_get_port_parent,
+	},
 	{ .parse_prop = parse_pwms, },
 	{ .parse_prop = parse_resets, },
 	{ .parse_prop = parse_leds, },
@@ -1403,8 +1388,8 @@ static int of_link_property(struct device_node *con_np, const char *prop_name)
 		while ((phandle = s->parse_prop(con_np, prop_name, i))) {
 			struct device_node *con_dev_np;
 
-			con_dev_np = s->node_not_dev
-					? of_get_compat_node_parent(con_np)
+			con_dev_np = s->get_con_dev
+					? s->get_con_dev(con_np)
 					: of_node_get(con_np);
 			matched = true;
 			i++;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index cfd60e35a899..d7593bde2d02 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -50,6 +50,12 @@ static struct unittest_results {
 	failed; \
 })
 
+#ifdef CONFIG_OF_KOBJ
+#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref)
+#else
+#define OF_KREF_READ(NODE) 1
+#endif
+
 /*
  * Expected message may have a message level other than KERN_INFO.
  * Print the expected message only if the current loglevel will allow
@@ -570,7 +576,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 			pr_err("missing testcase data\n");
 			return;
 		}
-		prefs[i] = kref_read(&p[i]->kobj.kref);
+		prefs[i] = OF_KREF_READ(p[i]);
 	}
 
 	rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells");
@@ -693,9 +699,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
 	unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
 
 	for (i = 0; i < ARRAY_SIZE(p); ++i) {
-		unittest(prefs[i] == kref_read(&p[i]->kobj.kref),
+		unittest(prefs[i] == OF_KREF_READ(p[i]),
 			 "provider%d: expected:%d got:%d\n",
-			 i, prefs[i], kref_read(&p[i]->kobj.kref));
+			 i, prefs[i], OF_KREF_READ(p[i]));
 		of_node_put(p[i]);
 	}
 }
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 9c2137dae429..826b5016a101 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_add_devices);
 
-/** pci_walk_bus - walk devices on/under bus, calling callback.
- *  @top      bus whose devices should be walked
- *  @cb       callback to be called for each device found
- *  @userdata arbitrary pointer to be passed to callback.
- *
- *  Walk the given bus, including any bridged devices
- *  on buses under this bus.  Call the provided callback
- *  on each device found.
- *
- *  We check the return of @cb each time. If it returns anything
- *  other than 0, we break out.
- *
- */
-void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
-		  void *userdata)
+static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			   void *userdata, bool locked)
 {
 	struct pci_dev *dev;
 	struct pci_bus *bus;
@@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 	int retval;
 
 	bus = top;
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	next = top->devices.next;
 	for (;;) {
 		if (next == &bus->devices) {
@@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		if (retval)
 			break;
 	}
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
+}
+
+/**
+ *  pci_walk_bus - walk devices on/under bus, calling callback.
+ *  @top: bus whose devices should be walked
+ *  @cb: callback to be called for each device found
+ *  @userdata: arbitrary pointer to be passed to callback
+ *
+ *  Walk the given bus, including any bridged devices
+ *  on buses under this bus.  Call the provided callback
+ *  on each device found.
+ *
+ *  We check the return of @cb each time. If it returns anything
+ *  other than 0, we break out.
+ */
+void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	__pci_walk_bus(top, cb, userdata, false);
 }
 EXPORT_SYMBOL_GPL(pci_walk_bus);
 
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	__pci_walk_bus(top, cb, userdata, true);
+}
+EXPORT_SYMBOL_GPL(pci_walk_bus_locked);
+
 struct pci_bus *pci_bus_get(struct pci_bus *bus)
 {
 	if (bus)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 5befed2dc02b..9a437cfce073 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -6,6 +6,7 @@
  * Author: Kishon Vijay Abraham I <kishon@ti.com>
  */
 
+#include <linux/align.h>
 #include <linux/bitfield.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -482,9 +483,10 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 		reg = ep_func->msi_cap + PCI_MSI_DATA_32;
 		msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	}
-	aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
-	msg_addr = ((u64)msg_addr_upper) << 32 |
-			(msg_addr_lower & ~aligned_offset);
+	msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower;
+
+	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
@@ -551,7 +553,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 	}
 
 	aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
-	msg_addr &= ~aligned_offset;
+	msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
 	ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
 				  epc->mem->window.page_size);
 	if (ret)
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 10f2d0bb86be..2ce2a3bd932b 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -972,7 +972,7 @@ static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
 	 * Downstream devices need to be in D0 state before enabling PCI PM
 	 * substates.
 	 */
-	pci_set_power_state(pdev, PCI_D0);
+	pci_set_power_state_locked(pdev, PCI_D0);
 	pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
 
 	return 0;
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index a89b7de72dcf..7333b305f2a5 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -26,58 +26,79 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
 					     hotplug_slot);
 	int rc;
 
-	if (zdev->state != ZPCI_FN_STATE_STANDBY)
-		return -EIO;
+	mutex_lock(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_STANDBY) {
+		rc = -EIO;
+		goto out;
+	}
 
 	rc = sclp_pci_configure(zdev->fid);
 	zpci_dbg(3, "conf fid:%x, rc:%d\n", zdev->fid, rc);
 	if (rc)
-		return rc;
+		goto out;
 	zdev->state = ZPCI_FN_STATE_CONFIGURED;
 
-	return zpci_scan_configured_device(zdev, zdev->fh);
+	rc = zpci_scan_configured_device(zdev, zdev->fh);
+out:
+	mutex_unlock(&zdev->state_lock);
+	return rc;
 }
 
 static int disable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev,
 					     hotplug_slot);
-	struct pci_dev *pdev;
+	struct pci_dev *pdev = NULL;
+	int rc;
 
-	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
-		return -EIO;
+	mutex_lock(&zdev->state_lock);
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED) {
+		rc = -EIO;
+		goto out;
+	}
 
 	pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
 	if (pdev && pci_num_vf(pdev)) {
 		pci_dev_put(pdev);
-		return -EBUSY;
+		rc = -EBUSY;
+		goto out;
 	}
-	pci_dev_put(pdev);
 
-	return zpci_deconfigure_device(zdev);
+	rc = zpci_deconfigure_device(zdev);
+out:
+	mutex_unlock(&zdev->state_lock);
+	if (pdev)
+		pci_dev_put(pdev);
+	return rc;
 }
 
 static int reset_slot(struct hotplug_slot *hotplug_slot, bool probe)
 {
 	struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev,
 					     hotplug_slot);
+	int rc = -EIO;
 
-	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
-		return -EIO;
 	/*
-	 * We can't take the zdev->lock as reset_slot may be called during
-	 * probing and/or device removal which already happens under the
-	 * zdev->lock. Instead the user should use the higher level
-	 * pci_reset_function() or pci_bus_reset() which hold the PCI device
-	 * lock preventing concurrent removal. If not using these functions
-	 * holding the PCI device lock is required.
+	 * If we can't get the zdev->state_lock the device state is
+	 * currently undergoing a transition and we bail out - just
+	 * the same as if the device's state is not configured at all.
 	 */
+	if (!mutex_trylock(&zdev->state_lock))
+		return rc;
 
-	/* As long as the function is configured we can reset */
-	if (probe)
-		return 0;
+	/* We can reset only if the function is configured */
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		goto out;
+
+	if (probe) {
+		rc = 0;
+		goto out;
+	}
 
-	return zpci_hot_reset_device(zdev);
+	rc = zpci_hot_reset_device(zdev);
+out:
+	mutex_unlock(&zdev->state_lock);
+	return rc;
 }
 
 static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index c8be056c248d..cfd84a899c82 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -61,7 +61,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 
 	return (irq_hw_number_t)desc->msi_index |
 		pci_dev_id(dev) << 11 |
-		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
+		((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27;
 }
 
 static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d8f11a078924..c3585229c12a 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1354,6 +1354,7 @@ end:
 /**
  * pci_set_full_power_state - Put a PCI device into D0 and update its state
  * @dev: PCI device to power up
+ * @locked: whether pci_bus_sem is held
  *
  * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register
  * to confirm the state change, restore its BARs if they might be lost and
@@ -1363,7 +1364,7 @@ end:
  * to D0, it is more efficient to use pci_power_up() directly instead of this
  * function.
  */
-static int pci_set_full_power_state(struct pci_dev *dev)
+static int pci_set_full_power_state(struct pci_dev *dev, bool locked)
 {
 	u16 pmcsr;
 	int ret;
@@ -1399,7 +1400,7 @@ static int pci_set_full_power_state(struct pci_dev *dev)
 	}
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
@@ -1428,10 +1429,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
 		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
 }
 
+static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked)
+{
+	if (!bus)
+		return;
+
+	if (locked)
+		pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state);
+	else
+		pci_walk_bus(bus, __pci_dev_set_current_state, &state);
+}
+
 /**
  * pci_set_low_power_state - Put a PCI device into a low-power state.
  * @dev: PCI device to handle.
  * @state: PCI power state (D1, D2, D3hot) to put the device into.
+ * @locked: whether pci_bus_sem is held
  *
  * Use the device's PCI_PM_CTRL register to put it into a low-power state.
  *
@@ -1442,7 +1455,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
  * 0 if device already is in the requested state.
  * 0 if device's power state has been successfully changed.
  */
-static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
+static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	u16 pmcsr;
 
@@ -1496,29 +1509,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state)
 				     pci_power_name(state));
 
 	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
+		pcie_aspm_pm_state_change(dev->bus->self, locked);
 
 	return 0;
 }
 
-/**
- * pci_set_power_state - Set the power state of a PCI device
- * @dev: PCI device to handle.
- * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
- *
- * Transition a device to a new power state, using the platform firmware and/or
- * the device's PCI PM registers.
- *
- * RETURN VALUE:
- * -EINVAL if the requested state is invalid.
- * -EIO if device does not support PCI PM or its PM capabilities register has a
- * wrong version, or device doesn't support the requested state.
- * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
- * 0 if device already is in the requested state.
- * 0 if the transition is to D3 but D3 is not supported.
- * 0 if device's power state has been successfully changed.
- */
-int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked)
 {
 	int error;
 
@@ -1542,7 +1538,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		return 0;
 
 	if (state == PCI_D0)
-		return pci_set_full_power_state(dev);
+		return pci_set_full_power_state(dev, locked);
 
 	/*
 	 * This device is quirked not to be put into D3, so don't put it in
@@ -1556,16 +1552,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		 * To put the device in D3cold, put it into D3hot in the native
 		 * way, then put it into D3cold using platform ops.
 		 */
-		error = pci_set_low_power_state(dev, PCI_D3hot);
+		error = pci_set_low_power_state(dev, PCI_D3hot, locked);
 
 		if (pci_platform_power_transition(dev, PCI_D3cold))
 			return error;
 
 		/* Powering off a bridge may power off the whole hierarchy */
 		if (dev->current_state == PCI_D3cold)
-			pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
+			__pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked);
 	} else {
-		error = pci_set_low_power_state(dev, state);
+		error = pci_set_low_power_state(dev, state, locked);
 
 		if (pci_platform_power_transition(dev, state))
 			return error;
@@ -1573,8 +1569,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	return 0;
 }
+
+/**
+ * pci_set_power_state - Set the power state of a PCI device
+ * @dev: PCI device to handle.
+ * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
+ *
+ * Transition a device to a new power state, using the platform firmware and/or
+ * the device's PCI PM registers.
+ *
+ * RETURN VALUE:
+ * -EINVAL if the requested state is invalid.
+ * -EIO if device does not support PCI PM or its PM capabilities register has a
+ * wrong version, or device doesn't support the requested state.
+ * 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
+ * 0 if device already is in the requested state.
+ * 0 if the transition is to D3 but D3 is not supported.
+ * 0 if device's power state has been successfully changed.
+ */
+int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
+{
+	return __pci_set_power_state(dev, state, false);
+}
 EXPORT_SYMBOL(pci_set_power_state);
 
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{
+	lockdep_assert_held(&pci_bus_sem);
+
+	return __pci_set_power_state(dev, state, true);
+}
+EXPORT_SYMBOL(pci_set_power_state_locked);
+
 #define PCI_EXP_SAVE_REGS	7
 
 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev,
@@ -2496,29 +2522,36 @@ static void pci_pme_list_scan(struct work_struct *work)
 		if (pdev->pme_poll) {
 			struct pci_dev *bridge = pdev->bus->self;
 			struct device *dev = &pdev->dev;
-			int pm_status;
+			struct device *bdev = bridge ? &bridge->dev : NULL;
+			int bref = 0;
 
 			/*
-			 * If bridge is in low power state, the
-			 * configuration space of subordinate devices
-			 * may be not accessible
+			 * If we have a bridge, it should be in an active/D0
+			 * state or the configuration space of subordinate
+			 * devices may not be accessible or stable over the
+			 * course of the call.
 			 */
-			if (bridge && bridge->current_state != PCI_D0)
-				continue;
+			if (bdev) {
+				bref = pm_runtime_get_if_active(bdev, true);
+				if (!bref)
+					continue;
+
+				if (bridge->current_state != PCI_D0)
+					goto put_bridge;
+			}
 
 			/*
-			 * If the device is in a low power state it
-			 * should not be polled either.
+			 * The device itself should be suspended but config
+			 * space must be accessible, therefore it cannot be in
+			 * D3cold.
 			 */
-			pm_status = pm_runtime_get_if_active(dev, true);
-			if (!pm_status)
-				continue;
-
-			if (pdev->current_state != PCI_D3cold)
+			if (pm_runtime_suspended(dev) &&
+			    pdev->current_state != PCI_D3cold)
 				pci_pme_wakeup(pdev, NULL);
 
-			if (pm_status > 0)
-				pm_runtime_put(dev);
+put_bridge:
+			if (bref > 0)
+				pm_runtime_put(bdev);
 		} else {
 			list_del(&pme_dev->list);
 			kfree(pme_dev);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 2336a8d1edab..e9750b1b19ba 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -571,12 +571,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt);
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);
 void pcie_aspm_exit_link_state(struct pci_dev *pdev);
-void pcie_aspm_pm_state_change(struct pci_dev *pdev);
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked);
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
 static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
-static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
+static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { }
 static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
 #endif
 
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 5a0066ecc3c5..bc0bd86695ec 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1003,8 +1003,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev)
 	up_read(&pci_bus_sem);
 }
 
-/* @pdev: the root port or switch downstream port */
-void pcie_aspm_pm_state_change(struct pci_dev *pdev)
+/*
+ * @pdev: the root port or switch downstream port
+ * @locked: whether pci_bus_sem is held
+ */
+void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked)
 {
 	struct pcie_link_state *link = pdev->link_state;
 
@@ -1014,12 +1017,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev)
 	 * Devices changed PM state, we should recheck if latency
 	 * meets all functions' requirement
 	 */
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	pcie_update_aspm_capable(link->root);
 	pcie_config_aspm_path(link);
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 }
 
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index c584165b13ba..7e3aa7e2345f 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -2305,6 +2305,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 				dev_dbg(cmn->dev, "ignoring external node %llx\n", reg);
 				continue;
 			}
+			/*
+			 * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus
+			 * child count larger than the number of valid child pointers.
+			 * A child offset of 0 can only occur on CMN-600; otherwise it
+			 * would imply the root node being its own grandchild, which
+			 * we can safely dismiss in general.
+			 */
+			if (reg == 0 && cmn->part != PART_CMN600) {
+				dev_dbg(cmn->dev, "bogus child pointer?\n");
+				continue;
+			}
 
 			arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);
 
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 6303b82566f9..9e5d7fa647b6 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -716,7 +716,7 @@ static void smmu_pmu_free_msis(void *data)
 {
 	struct device *dev = data;
 
-	platform_msi_domain_free_irqs(dev);
+	platform_device_msi_free_irqs_all(dev);
 }
 
 static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
@@ -746,7 +746,7 @@ static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
 	if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
 		return;
 
-	ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+	ret = platform_device_msi_init_and_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
 	if (ret) {
 		dev_warn(dev, "failed to allocate MSIs\n");
 		return;
diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 365d964b0f6a..308c9969642e 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -59,7 +59,7 @@
 #define   CXL_PMU_COUNTER_CFG_EVENT_GRP_ID_IDX_MSK	GENMASK_ULL(63, 59)
 
 #define CXL_PMU_FILTER_CFG_REG(n, f)	(0x400 + 4 * ((f) + (n) * 8))
-#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(15, 0)
+#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(31, 0)
 
 #define CXL_PMU_COUNTER_REG(n)		(0xc00 + 8 * (n))
 
@@ -314,9 +314,9 @@ static bool cxl_pmu_config1_get_edge(struct perf_event *event)
 }
 
 /*
- * CPMU specification allows for 8 filters, each with a 16 bit value...
- * So we need to find 8x16bits to store it in.
- * As the value used for disable is 0xffff, a separate enable switch
+ * CPMU specification allows for 8 filters, each with a 32 bit value...
+ * So we need to find 8x32bits to store it in.
+ * As the value used for disable is 0xffff_ffff, a separate enable switch
  * is needed.
  */
 
@@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp,			CXL_PMU_GID_S2M_NDR, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps,			CXL_PMU_GID_S2M_NDR, BIT(1)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe,			CXL_PMU_GID_S2M_NDR, BIT(2)),
-	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(3)),
+	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(4)),
 	/* CXL rev 3.0 Table 3-46 S2M DRS opcodes */
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata,			CXL_PMU_GID_S2M_DRS, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm,		CXL_PMU_GID_S2M_DRS, BIT(1)),
@@ -642,7 +642,7 @@ static void cxl_pmu_event_start(struct perf_event *event, int flags)
 		if (cxl_pmu_config1_hdm_filter_en(event))
 			cfg = cxl_pmu_config2_get_hdm_decoder(event);
 		else
-			cfg = GENMASK(15, 0); /* No filtering if 0xFFFF_FFFF */
+			cfg = GENMASK(31, 0); /* No filtering if 0xFFFF_FFFF */
 		writeq(cfg, base + CXL_PMU_FILTER_CFG_REG(hwc->idx, 0));
 	}
 
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index 0dda70e1ef90..c78a6fd6c57f 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -150,19 +150,11 @@ u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event)
 	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (!rvpmu->ctr_get_width)
-	/**
-	 * If the pmu driver doesn't support counter width, set it to default
-	 * maximum allowed by the specification.
-	 */
-		cwidth = 63;
-	else {
-		if (hwc->idx == -1)
-			/* Handle init case where idx is not initialized yet */
-			cwidth = rvpmu->ctr_get_width(0);
-		else
-			cwidth = rvpmu->ctr_get_width(hwc->idx);
-	}
+	if (hwc->idx == -1)
+		/* Handle init case where idx is not initialized yet */
+		cwidth = rvpmu->ctr_get_width(0);
+	else
+		cwidth = rvpmu->ctr_get_width(hwc->idx);
 
 	return GENMASK_ULL(cwidth, 0);
 }
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index 79fdd667922e..fa0bccf4edf2 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -37,6 +37,12 @@ static int pmu_legacy_event_map(struct perf_event *event, u64 *config)
 	return pmu_legacy_ctr_get_idx(event);
 }
 
+/* cycle & instret are always 64 bit, one bit less according to SBI spec */
+static int pmu_legacy_ctr_get_width(int idx)
+{
+	return 63;
+}
+
 static u64 pmu_legacy_read_ctr(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -111,12 +117,14 @@ static void pmu_legacy_init(struct riscv_pmu *pmu)
 	pmu->ctr_stop = NULL;
 	pmu->event_map = pmu_legacy_event_map;
 	pmu->ctr_get_idx = pmu_legacy_ctr_get_idx;
-	pmu->ctr_get_width = NULL;
+	pmu->ctr_get_width = pmu_legacy_ctr_get_width;
 	pmu->ctr_clear_idx = NULL;
 	pmu->ctr_read = pmu_legacy_read_ctr;
 	pmu->event_mapped = pmu_legacy_event_mapped;
 	pmu->event_unmapped = pmu_legacy_event_unmapped;
 	pmu->csr_index = pmu_legacy_csr_index;
+	pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
 
 	perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW);
 }
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 16acd4dcdb96..452aab49db1e 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -512,7 +512,7 @@ static void pmu_sbi_set_scounteren(void *arg)
 
 	if (event->hw.idx != -1)
 		csr_write(CSR_SCOUNTEREN,
-			  csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event)));
+			  csr_read(CSR_SCOUNTEREN) | BIT(pmu_sbi_csr_index(event)));
 }
 
 static void pmu_sbi_reset_scounteren(void *arg)
@@ -521,7 +521,7 @@ static void pmu_sbi_reset_scounteren(void *arg)
 
 	if (event->hw.idx != -1)
 		csr_write(CSR_SCOUNTEREN,
-			  csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event)));
+			  csr_read(CSR_SCOUNTEREN) & ~BIT(pmu_sbi_csr_index(event)));
 }
 
 static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival)
@@ -731,14 +731,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 		/* compute hardware counter index */
 		hidx = info->csr - CSR_CYCLE;
 		/* check if the corresponding bit is set in sscountovf */
-		if (!(overflow & (1 << hidx)))
+		if (!(overflow & BIT(hidx)))
 			continue;
 
 		/*
 		 * Keep a track of overflowed counters so that they can be started
 		 * with updated initial value.
 		 */
-		overflowed_ctrs |= 1 << lidx;
+		overflowed_ctrs |= BIT(lidx);
 		hw_evt = &event->hw;
 		riscv_pmu_event_update(event);
 		perf_sample_data_init(&data, 0, hw_evt->last_period);
diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
index e625b32889bf..0928a526e2ab 100644
--- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
+++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c
@@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev)
 			return ret;
 		}
 
-		priv->id = of_alias_get_id(np, "mipi_dphy");
+		priv->id = of_alias_get_id(np, "mipi-dphy");
 		if (priv->id < 0) {
 			dev_err(dev, "Failed to get phy node alias id: %d\n",
 				priv->id);
diff --git a/drivers/phy/microchip/lan966x_serdes.c b/drivers/phy/microchip/lan966x_serdes.c
index c1a41b6cd29b..b5ac2b7995e7 100644
--- a/drivers/phy/microchip/lan966x_serdes.c
+++ b/drivers/phy/microchip/lan966x_serdes.c
@@ -96,6 +96,8 @@ static const struct serdes_mux lan966x_serdes_muxes[] = {
 	SERDES_MUX_SGMII(SERDES6G(1), 3, HSIO_HW_CFG_SD6G_1_CFG,
 			 HSIO_HW_CFG_SD6G_1_CFG_SET(1)),
 
+	SERDES_MUX_SGMII(SERDES6G(2), 4, 0, 0),
+
 	SERDES_MUX_RGMII(RGMII(0), 2, HSIO_HW_CFG_RGMII_0_CFG |
 			 HSIO_HW_CFG_RGMII_ENA |
 			 HSIO_HW_CFG_GMII_ENA,
diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index a623f092b11f..a43e20abb10d 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -37,56 +37,28 @@
 #define EUSB2_TUNE_EUSB_EQU		0x5A
 #define EUSB2_TUNE_EUSB_HS_COMP_CUR	0x5B
 
-#define QCOM_EUSB2_REPEATER_INIT_CFG(r, v)	\
-	{					\
-		.reg = r,			\
-		.val = v,			\
-	}
-
-enum reg_fields {
-	F_TUNE_EUSB_HS_COMP_CUR,
-	F_TUNE_EUSB_EQU,
-	F_TUNE_EUSB_SLEW,
-	F_TUNE_USB2_HS_COMP_CUR,
-	F_TUNE_USB2_PREEM,
-	F_TUNE_USB2_EQU,
-	F_TUNE_USB2_SLEW,
-	F_TUNE_SQUELCH_U,
-	F_TUNE_HSDISC,
-	F_TUNE_RES_FSDIF,
-	F_TUNE_IUSB2,
-	F_TUNE_USB2_CROSSOVER,
-	F_NUM_TUNE_FIELDS,
-
-	F_FORCE_VAL_5 = F_NUM_TUNE_FIELDS,
-	F_FORCE_EN_5,
-
-	F_EN_CTL1,
-
-	F_RPTR_STATUS,
-	F_NUM_FIELDS,
-};
-
-static struct reg_field eusb2_repeater_tune_reg_fields[F_NUM_FIELDS] = {
-	[F_TUNE_EUSB_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_EUSB_HS_COMP_CUR, 0, 1),
-	[F_TUNE_EUSB_EQU] = REG_FIELD(EUSB2_TUNE_EUSB_EQU, 0, 1),
-	[F_TUNE_EUSB_SLEW] = REG_FIELD(EUSB2_TUNE_EUSB_SLEW, 0, 1),
-	[F_TUNE_USB2_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_USB2_HS_COMP_CUR, 0, 1),
-	[F_TUNE_USB2_PREEM] = REG_FIELD(EUSB2_TUNE_USB2_PREEM, 0, 2),
-	[F_TUNE_USB2_EQU] = REG_FIELD(EUSB2_TUNE_USB2_EQU, 0, 1),
-	[F_TUNE_USB2_SLEW] = REG_FIELD(EUSB2_TUNE_USB2_SLEW, 0, 1),
-	[F_TUNE_SQUELCH_U] = REG_FIELD(EUSB2_TUNE_SQUELCH_U, 0, 2),
-	[F_TUNE_HSDISC] = REG_FIELD(EUSB2_TUNE_HSDISC, 0, 2),
-	[F_TUNE_RES_FSDIF] = REG_FIELD(EUSB2_TUNE_RES_FSDIF, 0, 2),
-	[F_TUNE_IUSB2] = REG_FIELD(EUSB2_TUNE_IUSB2, 0, 3),
-	[F_TUNE_USB2_CROSSOVER] = REG_FIELD(EUSB2_TUNE_USB2_CROSSOVER, 0, 2),
-
-	[F_FORCE_VAL_5] = REG_FIELD(EUSB2_FORCE_VAL_5, 0, 7),
-	[F_FORCE_EN_5] = REG_FIELD(EUSB2_FORCE_EN_5, 0, 7),
-
-	[F_EN_CTL1] = REG_FIELD(EUSB2_EN_CTL1, 0, 7),
-
-	[F_RPTR_STATUS] = REG_FIELD(EUSB2_RPTR_STATUS, 0, 7),
+enum eusb2_reg_layout {
+	TUNE_EUSB_HS_COMP_CUR,
+	TUNE_EUSB_EQU,
+	TUNE_EUSB_SLEW,
+	TUNE_USB2_HS_COMP_CUR,
+	TUNE_USB2_PREEM,
+	TUNE_USB2_EQU,
+	TUNE_USB2_SLEW,
+	TUNE_SQUELCH_U,
+	TUNE_HSDISC,
+	TUNE_RES_FSDIF,
+	TUNE_IUSB2,
+	TUNE_USB2_CROSSOVER,
+	NUM_TUNE_FIELDS,
+
+	FORCE_VAL_5 = NUM_TUNE_FIELDS,
+	FORCE_EN_5,
+
+	EN_CTL1,
+
+	RPTR_STATUS,
+	LAYOUT_SIZE,
 };
 
 struct eusb2_repeater_cfg {
@@ -98,10 +70,11 @@ struct eusb2_repeater_cfg {
 
 struct eusb2_repeater {
 	struct device *dev;
-	struct regmap_field *regs[F_NUM_FIELDS];
+	struct regmap *regmap;
 	struct phy *phy;
 	struct regulator_bulk_data *vregs;
 	const struct eusb2_repeater_cfg *cfg;
+	u32 base;
 	enum phy_mode mode;
 };
 
@@ -109,10 +82,10 @@ static const char * const pm8550b_vreg_l[] = {
 	"vdd18", "vdd3",
 };
 
-static const u32 pm8550b_init_tbl[F_NUM_TUNE_FIELDS] = {
-	[F_TUNE_IUSB2] = 0x8,
-	[F_TUNE_SQUELCH_U] = 0x3,
-	[F_TUNE_USB2_PREEM] = 0x5,
+static const u32 pm8550b_init_tbl[NUM_TUNE_FIELDS] = {
+	[TUNE_IUSB2] = 0x8,
+	[TUNE_SQUELCH_U] = 0x3,
+	[TUNE_USB2_PREEM] = 0x5,
 };
 
 static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = {
@@ -140,47 +113,42 @@ static int eusb2_repeater_init_vregs(struct eusb2_repeater *rptr)
 
 static int eusb2_repeater_init(struct phy *phy)
 {
-	struct reg_field *regfields = eusb2_repeater_tune_reg_fields;
 	struct eusb2_repeater *rptr = phy_get_drvdata(phy);
 	struct device_node *np = rptr->dev->of_node;
-	u32 init_tbl[F_NUM_TUNE_FIELDS] = { 0 };
-	u8 override;
+	struct regmap *regmap = rptr->regmap;
+	const u32 *init_tbl = rptr->cfg->init_tbl;
+	u8 tune_usb2_preem = init_tbl[TUNE_USB2_PREEM];
+	u8 tune_hsdisc = init_tbl[TUNE_HSDISC];
+	u8 tune_iusb2 = init_tbl[TUNE_IUSB2];
+	u32 base = rptr->base;
 	u32 val;
 	int ret;
-	int i;
+
+	of_property_read_u8(np, "qcom,tune-usb2-amplitude", &tune_iusb2);
+	of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &tune_hsdisc);
+	of_property_read_u8(np, "qcom,tune-usb2-preem", &tune_usb2_preem);
 
 	ret = regulator_bulk_enable(rptr->cfg->num_vregs, rptr->vregs);
 	if (ret)
 		return ret;
 
-	regmap_field_update_bits(rptr->regs[F_EN_CTL1], EUSB2_RPTR_EN, EUSB2_RPTR_EN);
+	regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN);
 
-	for (i = 0; i < F_NUM_TUNE_FIELDS; i++) {
-		if (init_tbl[i]) {
-			regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]);
-		} else {
-			/* Write 0 if there's no value set */
-			u32 mask = GENMASK(regfields[i].msb, regfields[i].lsb);
-
-			regmap_field_update_bits(rptr->regs[i], mask, 0);
-		}
-	}
-	memcpy(init_tbl, rptr->cfg->init_tbl, sizeof(init_tbl));
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_HS_COMP_CUR, init_tbl[TUNE_EUSB_HS_COMP_CUR]);
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_EQU, init_tbl[TUNE_EUSB_EQU]);
+	regmap_write(regmap, base + EUSB2_TUNE_EUSB_SLEW, init_tbl[TUNE_EUSB_SLEW]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_HS_COMP_CUR, init_tbl[TUNE_USB2_HS_COMP_CUR]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_EQU, init_tbl[TUNE_USB2_EQU]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_SLEW, init_tbl[TUNE_USB2_SLEW]);
+	regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, init_tbl[TUNE_SQUELCH_U]);
+	regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, init_tbl[TUNE_RES_FSDIF]);
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_CROSSOVER, init_tbl[TUNE_USB2_CROSSOVER]);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &override))
-		init_tbl[F_TUNE_IUSB2] = override;
+	regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, tune_usb2_preem);
+	regmap_write(regmap, base + EUSB2_TUNE_HSDISC, tune_hsdisc);
+	regmap_write(regmap, base + EUSB2_TUNE_IUSB2, tune_iusb2);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &override))
-		init_tbl[F_TUNE_HSDISC] = override;
-
-	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &override))
-		init_tbl[F_TUNE_USB2_PREEM] = override;
-
-	for (i = 0; i < F_NUM_TUNE_FIELDS; i++)
-		regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]);
-
-	ret = regmap_field_read_poll_timeout(rptr->regs[F_RPTR_STATUS],
-					     val, val & RPTR_OK, 10, 5);
+	ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, val, val & RPTR_OK, 10, 5);
 	if (ret)
 		dev_err(rptr->dev, "initialization timed-out\n");
 
@@ -191,6 +159,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 				   enum phy_mode mode, int submode)
 {
 	struct eusb2_repeater *rptr = phy_get_drvdata(phy);
+	struct regmap *regmap = rptr->regmap;
+	u32 base = rptr->base;
 
 	switch (mode) {
 	case PHY_MODE_USB_HOST:
@@ -199,10 +169,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 		 * per eUSB 1.2 Spec. Below implement software workaround until
 		 * PHY and controller is fixing seen observation.
 		 */
-		regmap_field_update_bits(rptr->regs[F_FORCE_EN_5],
-					 F_CLK_19P2M_EN, F_CLK_19P2M_EN);
-		regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5],
-					 V_CLK_19P2M_EN, V_CLK_19P2M_EN);
+		regmap_write(regmap, base + EUSB2_FORCE_EN_5, F_CLK_19P2M_EN);
+		regmap_write(regmap, base + EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN);
 		break;
 	case PHY_MODE_USB_DEVICE:
 		/*
@@ -211,10 +179,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
 		 * repeater doesn't clear previous value due to shared
 		 * regulators (say host <-> device mode switch).
 		 */
-		regmap_field_update_bits(rptr->regs[F_FORCE_EN_5],
-					 F_CLK_19P2M_EN, 0);
-		regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5],
-					 V_CLK_19P2M_EN, 0);
+		regmap_write(regmap, base + EUSB2_FORCE_EN_5, 0);
+		regmap_write(regmap, base + EUSB2_FORCE_VAL_5, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -243,9 +209,8 @@ static int eusb2_repeater_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct phy_provider *phy_provider;
 	struct device_node *np = dev->of_node;
-	struct regmap *regmap;
-	int i, ret;
 	u32 res;
+	int ret;
 
 	rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL);
 	if (!rptr)
@@ -258,22 +223,15 @@ static int eusb2_repeater_probe(struct platform_device *pdev)
 	if (!rptr->cfg)
 		return -EINVAL;
 
-	regmap = dev_get_regmap(dev->parent, NULL);
-	if (!regmap)
+	rptr->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!rptr->regmap)
 		return -ENODEV;
 
 	ret = of_property_read_u32(np, "reg", &res);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < F_NUM_FIELDS; i++)
-		eusb2_repeater_tune_reg_fields[i].reg += res;
-
-	ret = devm_regmap_field_bulk_alloc(dev, regmap, rptr->regs,
-					   eusb2_repeater_tune_reg_fields,
-					   F_NUM_FIELDS);
-	if (ret)
-		return ret;
+	rptr->base = res;
 
 	ret = eusb2_repeater_init_vregs(rptr);
 	if (ret < 0) {
diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c
index c2590579190a..03fb0d4b75d7 100644
--- a/drivers/phy/qualcomm/phy-qcom-m31.c
+++ b/drivers/phy/qualcomm/phy-qcom-m31.c
@@ -299,7 +299,7 @@ static int m31usb_phy_probe(struct platform_device *pdev)
 
 	qphy->vreg = devm_regulator_get(dev, "vdda-phy");
 	if (IS_ERR(qphy->vreg))
-		return dev_err_probe(dev, PTR_ERR(qphy->phy),
+		return dev_err_probe(dev, PTR_ERR(qphy->vreg),
 				     "failed to get vreg\n");
 
 	phy_set_drvdata(qphy->phy, qphy);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index 1ad10110dd25..17c4ad7553a5 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -3562,14 +3562,6 @@ static int qmp_combo_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = qmp_combo_typec_switch_register(qmp);
-	if (ret)
-		return ret;
-
-	ret = drm_aux_bridge_register(dev);
-	if (ret)
-		return ret;
-
 	/* Check for legacy binding with child nodes. */
 	usb_np = of_get_child_by_name(dev->of_node, "usb3-phy");
 	if (usb_np) {
@@ -3589,6 +3581,14 @@ static int qmp_combo_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_node_put;
 
+	ret = qmp_combo_typec_switch_register(qmp);
+	if (ret)
+		goto err_node_put;
+
+	ret = drm_aux_bridge_register(dev);
+	if (ret)
+		goto err_node_put;
+
 	pm_runtime_set_active(dev);
 	ret = devm_pm_runtime_enable(dev);
 	if (ret)
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index 243cc2b9a0fb..5c003988c35d 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -1556,6 +1556,14 @@ static const char * const qmp_phy_vreg_l[] = {
 	"vdda-phy", "vdda-pll",
 };
 
+static const struct qmp_usb_offsets qmp_usb_offsets_v3 = {
+	.serdes		= 0,
+	.pcs		= 0x800,
+	.pcs_misc	= 0x600,
+	.tx		= 0x200,
+	.rx		= 0x400,
+};
+
 static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = {
 	.serdes		= 0,
 	.pcs		= 0x800,
@@ -1564,7 +1572,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = {
 	.rx		= 0x400,
 };
 
-static const struct qmp_usb_offsets qmp_usb_offsets_v3 = {
+static const struct qmp_usb_offsets qmp_usb_offsets_v3_msm8996 = {
 	.serdes		= 0,
 	.pcs		= 0x600,
 	.tx		= 0x200,
@@ -1613,6 +1621,24 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v7 = {
 	.rx		= 0x1000,
 };
 
+static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_usb_offsets_v3,
+
+	.serdes_tbl		= ipq9574_usb3_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(ipq9574_usb3_serdes_tbl),
+	.tx_tbl			= msm8996_usb3_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(msm8996_usb3_tx_tbl),
+	.rx_tbl			= ipq8074_usb3_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(ipq8074_usb3_rx_tbl),
+	.pcs_tbl		= ipq8074_usb3_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(ipq8074_usb3_pcs_tbl),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= qmp_v3_usb3phy_regs_layout,
+};
+
 static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = {
 	.lanes			= 1,
 
@@ -1652,7 +1678,7 @@ static const struct qmp_phy_cfg ipq9574_usb3phy_cfg = {
 static const struct qmp_phy_cfg msm8996_usb3phy_cfg = {
 	.lanes			= 1,
 
-	.offsets		= &qmp_usb_offsets_v3,
+	.offsets		= &qmp_usb_offsets_v3_msm8996,
 
 	.serdes_tbl		= msm8996_usb3_serdes_tbl,
 	.serdes_tbl_num		= ARRAY_SIZE(msm8996_usb3_serdes_tbl),
@@ -2563,7 +2589,7 @@ err_node_put:
 static const struct of_device_id qmp_usb_of_match_table[] = {
 	{
 		.compatible = "qcom,ipq6018-qmp-usb3-phy",
-		.data = &ipq8074_usb3phy_cfg,
+		.data = &ipq6018_usb3phy_cfg,
 	}, {
 		.compatible = "qcom,ipq8074-qmp-usb3-phy",
 		.data = &ipq8074_usb3phy_cfg,
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index e53eace7c91e..6387c0d34c55 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -673,8 +673,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 	channel->irq = platform_get_irq_optional(pdev, 0);
 	channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node);
 	if (channel->dr_mode != USB_DR_MODE_UNKNOWN) {
-		int ret;
-
 		channel->is_otg_channel = true;
 		channel->uses_otg_pins = !of_property_read_bool(dev->of_node,
 							"renesas,no-otg-pins");
@@ -738,8 +736,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev)
 		ret = PTR_ERR(provider);
 		goto error;
 	} else if (channel->is_otg_channel) {
-		int ret;
-
 		ret = device_create_file(dev, &dev_attr_role);
 		if (ret < 0)
 			goto error;
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index dd2913ac0fa2..78e19b128962 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -117,7 +117,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->set_vbus)
 		return -ENODEV;
 
 	return phy->comparator->set_vbus(phy->comparator, enabled);
@@ -127,7 +127,7 @@ static int omap_usb_start_srp(struct usb_otg *otg)
 {
 	struct omap_usb *phy = phy_to_omapusb(otg->usb_phy);
 
-	if (!phy->comparator)
+	if (!phy->comparator || !phy->comparator->start_srp)
 		return -ENODEV;
 
 	return phy->comparator->start_srp(phy->comparator);
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index ee56856cb80c..bbcdece83bf4 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -1644,7 +1644,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
 	unsigned int i, pin;
 #ifdef CONFIG_GPIOLIB
-	struct gpio_device *gdev __free(gpio_device_put) = NULL;
+	struct gpio_device *gdev = NULL;
 	struct pinctrl_gpio_range *range;
 	int gpio_num;
 #endif
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 03ecb3d1aaf6..49f89b70dcec 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, gpio_dev);
+			       IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev);
 	if (ret)
 		goto out2;
 
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
index 73f091cd827e..23aebd4695e9 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32mp257.c
@@ -2562,7 +2562,7 @@ static const struct of_device_id stm32mp257_pctrl_match[] = {
 };
 
 static const struct dev_pm_ops stm32_pinctrl_dev_pm_ops = {
-	 SET_LATE_SYSTEM_SLEEP_PM_OPS(NULL, stm32_pinctrl_resume)
+	 SET_LATE_SYSTEM_SLEEP_PM_OPS(stm32_pinctrl_suspend, stm32_pinctrl_resume)
 };
 
 static struct platform_driver stm32mp257_pinctrl_driver = {
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index feaa09f5b35a..4f734e049f4a 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -296,7 +296,8 @@ static int amd_pmf_suspend_handler(struct device *dev)
 {
 	struct amd_pmf_dev *pdev = dev_get_drvdata(dev);
 
-	kfree(pdev->buf);
+	if (pdev->smart_pc_enabled)
+		cancel_delayed_work_sync(&pdev->pb_work);
 
 	return 0;
 }
@@ -312,6 +313,9 @@ static int amd_pmf_resume_handler(struct device *dev)
 			return ret;
 	}
 
+	if (pdev->smart_pc_enabled)
+		schedule_delayed_work(&pdev->pb_work, msecs_to_jiffies(2000));
+
 	return 0;
 }
 
@@ -330,9 +334,14 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev)
 		dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n");
 	}
 
-	if (!amd_pmf_init_smart_pc(dev)) {
+	amd_pmf_init_smart_pc(dev);
+	if (dev->smart_pc_enabled) {
 		dev_dbg(dev->dev, "Smart PC Solution Enabled\n");
-	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
+		/* If Smart PC is enabled, no need to check for other features */
+		return;
+	}
+
+	if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_init_auto_mode(dev);
 		dev_dbg(dev->dev, "Auto Mode Init done\n");
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_AC) ||
@@ -351,7 +360,7 @@ static void amd_pmf_deinit_features(struct amd_pmf_dev *dev)
 		amd_pmf_deinit_sps(dev);
 	}
 
-	if (!dev->smart_pc_enabled) {
+	if (dev->smart_pc_enabled) {
 		amd_pmf_deinit_smart_pc(dev);
 	} else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) {
 		amd_pmf_deinit_auto_mode(dev);
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 16999c5b334f..66cae1cca73c 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -441,11 +441,6 @@ struct apmf_dyn_slider_output {
 	struct apmf_cnqf_power_set ps[APMF_CNQF_MAX];
 } __packed;
 
-enum smart_pc_status {
-	PMF_SMART_PC_ENABLED,
-	PMF_SMART_PC_DISABLED,
-};
-
 /* Smart PC - TA internals */
 enum system_state {
 	SYSTEM_STATE_S0i3,
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index f8c0177afb0d..dcbe8f85e122 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -252,15 +252,17 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 	cookie = readl(dev->policy_buf + POLICY_COOKIE_OFFSET);
 	length = readl(dev->policy_buf + POLICY_COOKIE_LEN);
 
-	if (cookie != POLICY_SIGN_COOKIE || !length)
+	if (cookie != POLICY_SIGN_COOKIE || !length) {
+		dev_dbg(dev->dev, "cookie doesn't match\n");
 		return -EINVAL;
+	}
 
 	/* Update the actual length */
 	dev->policy_sz = length + 512;
 	res = amd_pmf_invoke_cmd_init(dev);
 	if (res == TA_PMF_TYPE_SUCCESS) {
 		/* Now its safe to announce that smart pc is enabled */
-		dev->smart_pc_enabled = PMF_SMART_PC_ENABLED;
+		dev->smart_pc_enabled = true;
 		/*
 		 * Start collecting the data from TA FW after a small delay
 		 * or else, we might end up getting stale values.
@@ -268,7 +270,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
 	} else {
 		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
-		dev->smart_pc_enabled = PMF_SMART_PC_DISABLED;
+		dev->smart_pc_enabled = false;
 		return res;
 	}
 
@@ -336,25 +338,6 @@ static void amd_pmf_remove_pb(struct amd_pmf_dev *dev) {}
 static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) {}
 #endif
 
-static int amd_pmf_get_bios_buffer(struct amd_pmf_dev *dev)
-{
-	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
-	if (!dev->policy_buf)
-		return -ENOMEM;
-
-	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
-	if (!dev->policy_base)
-		return -ENOMEM;
-
-	memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz);
-
-	amd_pmf_hex_dump_pb(dev);
-	if (pb_side_load)
-		amd_pmf_open_pb(dev, dev->dbgfs_dir);
-
-	return amd_pmf_start_policy_engine(dev);
-}
-
 static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const void *data)
 {
 	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
@@ -453,22 +436,59 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		return ret;
 
 	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
-	amd_pmf_set_dram_addr(dev, true);
-	amd_pmf_get_bios_buffer(dev);
+
+	ret = amd_pmf_set_dram_addr(dev, true);
+	if (ret)
+		goto error;
+
+	dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz);
+	if (!dev->policy_base) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
+	if (!dev->policy_buf) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz);
+
+	amd_pmf_hex_dump_pb(dev);
+
 	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
-	if (!dev->prev_data)
-		return -ENOMEM;
+	if (!dev->prev_data) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = amd_pmf_start_policy_engine(dev);
+	if (ret)
+		goto error;
+
+	if (pb_side_load)
+		amd_pmf_open_pb(dev, dev->dbgfs_dir);
+
+	return 0;
 
-	return dev->smart_pc_enabled;
+error:
+	amd_pmf_deinit_smart_pc(dev);
+
+	return ret;
 }
 
 void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev)
 {
-	if (pb_side_load)
+	if (pb_side_load && dev->esbin)
 		amd_pmf_remove_pb(dev);
 
+	cancel_delayed_work_sync(&dev->pb_work);
 	kfree(dev->prev_data);
+	dev->prev_data = NULL;
 	kfree(dev->policy_buf);
-	cancel_delayed_work_sync(&dev->pb_work);
+	dev->policy_buf = NULL;
+	kfree(dev->buf);
+	dev->buf = NULL;
 	amd_pmf_tee_deinit(dev);
 }
diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c
index b6708bab7c53..527d8fbc7cc1 100644
--- a/drivers/platform/x86/intel/int0002_vgpio.c
+++ b/drivers/platform/x86/intel/int0002_vgpio.c
@@ -196,7 +196,7 @@ static int int0002_probe(struct platform_device *pdev)
 	 * IRQs into gpiolib.
 	 */
 	ret = devm_request_irq(dev, irq, int0002_irq,
-			       IRQF_SHARED, "INT0002", chip);
+			       IRQF_ONESHOT | IRQF_SHARED, "INT0002", chip);
 	if (ret) {
 		dev_err(dev, "Error requesting IRQ %d: %d\n", irq, ret);
 		return ret;
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
index a5e0f5c22179..b89c0dda9e5d 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c
@@ -242,7 +242,7 @@ static int __init intel_uncore_init(void)
 		return -ENODEV;
 
 	uncore_max_entries = topology_max_packages() *
-					topology_max_die_per_package();
+					topology_max_dies_per_package();
 	uncore_instances = kcalloc(uncore_max_entries,
 				   sizeof(*uncore_instances), GFP_KERNEL);
 	if (!uncore_instances)
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 210b0a81b7ec..084c355c86f5 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -200,9 +200,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
 	autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE);
 
 	sparse_keymap_report_event(input_dev, event, val, autorelease);
-
-	/* Some devices need this to report further events */
-	acpi_evaluate_object(handle, "VBDL", NULL, NULL);
 }
 
 /*
diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index 6bd14d0132db..3d66e1d4eb1f 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -20,9 +20,11 @@
 #define P2SBC_HIDE		BIT(8)
 
 #define P2SB_DEVFN_DEFAULT	PCI_DEVFN(31, 1)
+#define P2SB_DEVFN_GOLDMONT	PCI_DEVFN(13, 0)
+#define SPI_DEVFN_GOLDMONT	PCI_DEVFN(13, 2)
 
 static const struct x86_cpu_id p2sb_cpu_ids[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	PCI_DEVFN(13, 0)),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT),
 	{}
 };
 
@@ -98,21 +100,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn)
 
 static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
 {
-	unsigned int slot, fn;
-
-	if (PCI_FUNC(devfn) == 0) {
-		/*
-		 * When function number of the P2SB device is zero, scan it and
-		 * other function numbers, and if devices are available, cache
-		 * their BAR0s.
-		 */
-		slot = PCI_SLOT(devfn);
-		for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++)
-			p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn));
-	} else {
-		/* Scan the P2SB device and cache its BAR0 */
-		p2sb_scan_and_cache_devfn(bus, devfn);
-	}
+	/* Scan the P2SB device and cache its BAR0 */
+	p2sb_scan_and_cache_devfn(bus, devfn);
+
+	/* On Goldmont p2sb_bar() also gets called for the SPI controller */
+	if (devfn == P2SB_DEVFN_GOLDMONT)
+		p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT);
 
 	if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res))
 		return -ENOENT;
diff --git a/drivers/platform/x86/serdev_helpers.h b/drivers/platform/x86/serdev_helpers.h
new file mode 100644
index 000000000000..bcf3a0c356ea
--- /dev/null
+++ b/drivers/platform/x86/serdev_helpers.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * In some cases UART attached devices which require an in kernel driver,
+ * e.g. UART attached Bluetooth HCIs are described in the ACPI tables
+ * by an ACPI device with a broken or missing UartSerialBusV2() resource.
+ *
+ * This causes the kernel to create a /dev/ttyS# char-device for the UART
+ * instead of creating an in kernel serdev-controller + serdev-device pair
+ * for the in kernel driver.
+ *
+ * The quirk handling in acpi_quirk_skip_serdev_enumeration() makes the kernel
+ * create a serdev-controller device for these UARTs instead of a /dev/ttyS#.
+ *
+ * Instantiating the actual serdev-device to bind to is up to pdx86 code,
+ * this header provides a helper for getting the serdev-controller device.
+ */
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/printk.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+
+static inline struct device *
+get_serdev_controller(const char *serial_ctrl_hid,
+		      const char *serial_ctrl_uid,
+		      int serial_ctrl_port,
+		      const char *serdev_ctrl_name)
+{
+	struct device *ctrl_dev, *child;
+	struct acpi_device *ctrl_adev;
+	char name[32];
+	int i;
+
+	ctrl_adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1);
+	if (!ctrl_adev) {
+		pr_err("error could not get %s/%s serial-ctrl adev\n",
+		       serial_ctrl_hid, serial_ctrl_uid);
+		return ERR_PTR(-ENODEV);
+	}
+
+	/* get_first_physical_node() returns a weak ref */
+	ctrl_dev = get_device(acpi_get_first_physical_node(ctrl_adev));
+	if (!ctrl_dev) {
+		pr_err("error could not get %s/%s serial-ctrl physical node\n",
+		       serial_ctrl_hid, serial_ctrl_uid);
+		ctrl_dev = ERR_PTR(-ENODEV);
+		goto put_ctrl_adev;
+	}
+
+	/* Walk host -> uart-ctrl -> port -> serdev-ctrl */
+	for (i = 0; i < 3; i++) {
+		switch (i) {
+		case 0:
+			snprintf(name, sizeof(name), "%s:0", dev_name(ctrl_dev));
+			break;
+		case 1:
+			snprintf(name, sizeof(name), "%s.%d",
+				 dev_name(ctrl_dev), serial_ctrl_port);
+			break;
+		case 2:
+			strscpy(name, serdev_ctrl_name, sizeof(name));
+			break;
+		}
+
+		child = device_find_child_by_name(ctrl_dev, name);
+		put_device(ctrl_dev);
+		if (!child) {
+			pr_err("error could not find '%s' device\n", name);
+			ctrl_dev = ERR_PTR(-ENODEV);
+			goto put_ctrl_adev;
+		}
+
+		ctrl_dev = child;
+	}
+
+put_ctrl_adev:
+	acpi_dev_put(ctrl_adev);
+	return ctrl_dev;
+}
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 3a396b763c49..ce3e08815a8e 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -1009,7 +1009,16 @@ static ssize_t current_value_store(struct kobject *kobj,
 		 * Note - this sets the variable and then the password as separate
 		 * WMI calls. Function tlmi_save_bios_settings will error if the
 		 * password is incorrect.
+		 * Workstation's require the opcode to be set before changing the
+		 * attribute.
 		 */
+		if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
+			ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin",
+						  tlmi_priv.pwd_admin->password);
+			if (ret)
+				goto out;
+		}
+
 		set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name,
 				    new_setting);
 		if (!set_str) {
@@ -1021,17 +1030,10 @@ static ssize_t current_value_store(struct kobject *kobj,
 		if (ret)
 			goto out;
 
-		if (tlmi_priv.save_mode == TLMI_SAVE_BULK) {
+		if (tlmi_priv.save_mode == TLMI_SAVE_BULK)
 			tlmi_priv.save_required = true;
-		} else {
-			if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
-				ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin",
-							  tlmi_priv.pwd_admin->password);
-				if (ret)
-					goto out;
-			}
+		else
 			ret = tlmi_save_bios_settings("");
-		}
 	} else { /* old non-opcode based authentication method (deprecated) */
 		if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) {
 			auth_str = kasprintf(GFP_KERNEL, "%s,%s,%s;",
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index c4895e9bc714..5ecd9d33250d 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10308,6 +10308,7 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode,
 		return 0;
 	default:
 		/* Unknown function */
+		pr_debug("unknown function 0x%x\n", funcmode);
 		return -EOPNOTSUPP;
 	}
 	return 0;
@@ -10493,8 +10494,8 @@ static void dytc_profile_refresh(void)
 		return;
 
 	perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
-	convert_dytc_to_profile(funcmode, perfmode, &profile);
-	if (profile != dytc_current_profile) {
+	err = convert_dytc_to_profile(funcmode, perfmode, &profile);
+	if (!err && profile != dytc_current_profile) {
 		dytc_current_profile = profile;
 		platform_profile_notify();
 	}
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index 7aee5e9ff2b8..975cf24ae359 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -81,7 +81,7 @@ static const struct property_entry chuwi_hi8_air_props[] = {
 };
 
 static const struct ts_dmi_data chuwi_hi8_air_data = {
-	.acpi_name	= "MSSL1680:00",
+	.acpi_name	= "MSSL1680",
 	.properties	= chuwi_hi8_air_props,
 };
 
@@ -415,18 +415,13 @@ static const struct property_entry gdix1001_upside_down_props[] = {
 	{ }
 };
 
-static const struct ts_dmi_data gdix1001_00_upside_down_data = {
-	.acpi_name	= "GDIX1001:00",
-	.properties	= gdix1001_upside_down_props,
-};
-
-static const struct ts_dmi_data gdix1001_01_upside_down_data = {
-	.acpi_name	= "GDIX1001:01",
+static const struct ts_dmi_data gdix1001_upside_down_data = {
+	.acpi_name	= "GDIX1001",
 	.properties	= gdix1001_upside_down_props,
 };
 
-static const struct ts_dmi_data gdix1002_00_upside_down_data = {
-	.acpi_name	= "GDIX1002:00",
+static const struct ts_dmi_data gdix1002_upside_down_data = {
+	.acpi_name	= "GDIX1002",
 	.properties	= gdix1001_upside_down_props,
 };
 
@@ -1412,7 +1407,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Juno Tablet */
-		.driver_data = (void *)&gdix1002_00_upside_down_data,
+		.driver_data = (void *)&gdix1002_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
 			/* Both product- and board-name being "Default string" is somewhat rare */
@@ -1658,7 +1653,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X89 (Android version / BIOS) */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "WISKY"),
 			DMI_MATCH(DMI_BOARD_NAME, "3G062i"),
@@ -1666,7 +1661,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X89 (Windows version / BIOS) */
-		.driver_data = (void *)&gdix1001_01_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			/* tPAD is too generic, also match on bios date */
 			DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"),
@@ -1684,7 +1679,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* Teclast X98 Pro */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			/*
 			 * Only match BIOS date, because the manufacturers
@@ -1788,7 +1783,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* "WinBook TW100" */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "TW100")
@@ -1796,7 +1791,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 	},
 	{
 		/* WinBook TW700 */
-		.driver_data = (void *)&gdix1001_00_upside_down_data,
+		.driver_data = (void *)&gdix1001_upside_down_data,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "TW700")
@@ -1821,7 +1816,7 @@ static void ts_dmi_add_props(struct i2c_client *client)
 	int error;
 
 	if (has_acpi_companion(dev) &&
-	    !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) {
+	    strstarts(client->name, ts_data->acpi_name)) {
 		error = device_create_managed_software_node(dev, ts_data->properties, NULL);
 		if (error)
 			dev_err(dev, "failed to add properties: %d\n", error);
diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c
index f8221a15575b..a3415f1c0b5f 100644
--- a/drivers/platform/x86/x86-android-tablets/core.c
+++ b/drivers/platform/x86/x86-android-tablets/core.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 
 #include "x86-android-tablets.h"
+#include "../serdev_helpers.h"
 
 static struct platform_device *x86_android_tablet_device;
 
@@ -113,6 +114,9 @@ int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data)
 		if (irq_type != IRQ_TYPE_NONE && irq_type != irq_get_trigger_type(irq))
 			irq_set_irq_type(irq, irq_type);
 
+		if (data->free_gpio)
+			devm_gpiod_put(&x86_android_tablet_device->dev, gpiod);
+
 		return irq;
 	case X86_ACPI_IRQ_TYPE_PMIC:
 		status = acpi_get_handle(NULL, data->chip, &handle);
@@ -229,38 +233,20 @@ static __init int x86_instantiate_spi_dev(const struct x86_dev_info *dev_info, i
 
 static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int idx)
 {
-	struct acpi_device *ctrl_adev, *serdev_adev;
+	struct acpi_device *serdev_adev;
 	struct serdev_device *serdev;
 	struct device *ctrl_dev;
 	int ret = -ENODEV;
 
-	ctrl_adev = acpi_dev_get_first_match_dev(info->ctrl_hid, info->ctrl_uid, -1);
-	if (!ctrl_adev) {
-		pr_err("error could not get %s/%s ctrl adev\n",
-		       info->ctrl_hid, info->ctrl_uid);
-		return -ENODEV;
-	}
+	ctrl_dev = get_serdev_controller(info->ctrl_hid, info->ctrl_uid, 0,
+					 info->ctrl_devname);
+	if (IS_ERR(ctrl_dev))
+		return PTR_ERR(ctrl_dev);
 
 	serdev_adev = acpi_dev_get_first_match_dev(info->serdev_hid, NULL, -1);
 	if (!serdev_adev) {
 		pr_err("error could not get %s serdev adev\n", info->serdev_hid);
-		goto put_ctrl_adev;
-	}
-
-	/* get_first_physical_node() returns a weak ref, no need to put() it */
-	ctrl_dev = acpi_get_first_physical_node(ctrl_adev);
-	if (!ctrl_dev)	{
-		pr_err("error could not get %s/%s ctrl physical dev\n",
-		       info->ctrl_hid, info->ctrl_uid);
-		goto put_serdev_adev;
-	}
-
-	/* ctrl_dev now points to the controller's parent, get the controller */
-	ctrl_dev = device_find_child_by_name(ctrl_dev, info->ctrl_devname);
-	if (!ctrl_dev) {
-		pr_err("error could not get %s/%s %s ctrl dev\n",
-		       info->ctrl_hid, info->ctrl_uid, info->ctrl_devname);
-		goto put_serdev_adev;
+		goto put_ctrl_dev;
 	}
 
 	serdev = serdev_device_alloc(to_serdev_controller(ctrl_dev));
@@ -283,8 +269,8 @@ static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int
 
 put_serdev_adev:
 	acpi_dev_put(serdev_adev);
-put_ctrl_adev:
-	acpi_dev_put(ctrl_adev);
+put_ctrl_dev:
+	put_device(ctrl_dev);
 	return ret;
 }
 
diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c
index f1c66a61bfc5..c297391955ad 100644
--- a/drivers/platform/x86/x86-android-tablets/lenovo.c
+++ b/drivers/platform/x86/x86-android-tablets/lenovo.c
@@ -116,6 +116,7 @@ static const struct x86_i2c_client_info lenovo_yb1_x90_i2c_clients[] __initconst
 			.trigger = ACPI_EDGE_SENSITIVE,
 			.polarity = ACPI_ACTIVE_LOW,
 			.con_id = "goodix_ts_irq",
+			.free_gpio = true,
 		},
 	}, {
 		/* Wacom Digitizer in keyboard half */
diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c
index bc6bbf7ec6ea..278402dcb808 100644
--- a/drivers/platform/x86/x86-android-tablets/other.c
+++ b/drivers/platform/x86/x86-android-tablets/other.c
@@ -68,7 +68,7 @@ static const struct x86_i2c_client_info acer_b1_750_i2c_clients[] __initconst =
 	},
 };
 
-static struct gpiod_lookup_table acer_b1_750_goodix_gpios = {
+static struct gpiod_lookup_table acer_b1_750_nvt_ts_gpios = {
 	.dev_id = "i2c-NVT-ts",
 	.table = {
 		GPIO_LOOKUP("INT33FC:01", 26, "reset", GPIO_ACTIVE_LOW),
@@ -77,7 +77,7 @@ static struct gpiod_lookup_table acer_b1_750_goodix_gpios = {
 };
 
 static struct gpiod_lookup_table * const acer_b1_750_gpios[] = {
-	&acer_b1_750_goodix_gpios,
+	&acer_b1_750_nvt_ts_gpios,
 	&int3496_reference_gpios,
 	NULL
 };
diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
index 49fed9410adb..468993edfeee 100644
--- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
+++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h
@@ -39,6 +39,7 @@ struct x86_acpi_irq_data {
 	int index;
 	int trigger;  /* ACPI_EDGE_SENSITIVE / ACPI_LEVEL_SENSITIVE */
 	int polarity; /* ACPI_ACTIVE_HIGH / ACPI_ACTIVE_LOW / ACPI_ACTIVE_BOTH */
+	bool free_gpio; /* Release GPIO after getting IRQ (for TYPE_GPIOINT) */
 	const char *con_id;
 };
 
diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c
index 709bbc448fad..d7ef46ccd9b8 100644
--- a/drivers/pmdomain/arm/scmi_perf_domain.c
+++ b/drivers/pmdomain/arm/scmi_perf_domain.c
@@ -159,6 +159,9 @@ static void scmi_perf_domain_remove(struct scmi_device *sdev)
 	struct genpd_onecell_data *scmi_pd_data = dev_get_drvdata(dev);
 	int i;
 
+	if (!scmi_pd_data)
+		return;
+
 	of_genpd_del_provider(dev->of_node);
 
 	for (i = 0; i < scmi_pd_data->num_domains; i++)
diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index a1f6cba3ae6c..18e232b5ed53 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -1109,7 +1109,7 @@ static int __init genpd_power_off_unused(void)
 
 	return 0;
 }
-late_initcall(genpd_power_off_unused);
+late_initcall_sync(genpd_power_off_unused);
 
 #ifdef CONFIG_PM_SLEEP
 
diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c
index e26dc17d07ad..e274e3315fe7 100644
--- a/drivers/pmdomain/mediatek/mtk-pm-domains.c
+++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c
@@ -561,6 +561,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			goto err_put_node;
 		}
 
+		/* recursive call to add all subdomains */
+		ret = scpsys_add_subdomain(scpsys, child);
+		if (ret)
+			goto err_put_node;
+
 		ret = pm_genpd_add_subdomain(parent_pd, child_pd);
 		if (ret) {
 			dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n",
@@ -570,11 +575,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
 			dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name,
 				child_pd->name);
 		}
-
-		/* recursive call to add all subdomains */
-		ret = scpsys_add_subdomain(scpsys, child);
-		if (ret)
-			goto err_put_node;
 	}
 
 	return 0;
@@ -588,9 +588,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 {
 	int ret;
 
-	if (scpsys_domain_is_on(pd))
-		scpsys_power_off(&pd->genpd);
-
 	/*
 	 * We're in the error cleanup already, so we only complain,
 	 * but won't emit another error on top of the original one.
@@ -600,6 +597,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
 		dev_err(pd->scpsys->dev,
 			"failed to remove domain '%s' : %d - state may be inconsistent\n",
 			pd->genpd.name, ret);
+	if (scpsys_domain_is_on(pd))
+		scpsys_power_off(&pd->genpd);
 
 	clk_bulk_put(pd->num_clks, pd->clks);
 	clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c
index 3078896b1300..de9121ef4216 100644
--- a/drivers/pmdomain/qcom/rpmhpd.c
+++ b/drivers/pmdomain/qcom/rpmhpd.c
@@ -217,7 +217,6 @@ static struct rpmhpd *sa8540p_rpmhpds[] = {
 	[SC8280XP_CX] = &cx,
 	[SC8280XP_CX_AO] = &cx_ao,
 	[SC8280XP_EBI] = &ebi,
-	[SC8280XP_GFX] = &gfx,
 	[SC8280XP_LCX] = &lcx,
 	[SC8280XP_LMX] = &lmx,
 	[SC8280XP_MMCX] = &mmcx,
@@ -692,6 +691,7 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner)
 	unsigned int active_corner, sleep_corner;
 	unsigned int this_active_corner = 0, this_sleep_corner = 0;
 	unsigned int peer_active_corner = 0, peer_sleep_corner = 0;
+	unsigned int peer_enabled_corner;
 
 	if (pd->state_synced) {
 		to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner);
@@ -701,9 +701,11 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner)
 		this_sleep_corner = pd->level_count - 1;
 	}
 
-	if (peer && peer->enabled)
-		to_active_sleep(peer, peer->corner, &peer_active_corner,
+	if (peer && peer->enabled) {
+		peer_enabled_corner = max(peer->corner, peer->enable_corner);
+		to_active_sleep(peer, peer_enabled_corner, &peer_active_corner,
 				&peer_sleep_corner);
+	}
 
 	active_corner = max(this_active_corner, peer_active_corner);
 
diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c
index 39ca84a67daa..621e411fc999 100644
--- a/drivers/pmdomain/renesas/r8a77980-sysc.c
+++ b/drivers/pmdomain/renesas/r8a77980-sysc.c
@@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = {
 	  PD_CPU_NOCR },
 	{ "ca53-cpu3",	0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU,
 	  PD_CPU_NOCR },
-	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON },
+	{ "cr7",	0x240, 0, R8A77980_PD_CR7,	R8A77980_PD_ALWAYS_ON,
+	  PD_CPU_NOCR },
 	{ "a3ir",	0x180, 0, R8A77980_PD_A3IR,	R8A77980_PD_ALWAYS_ON },
 	{ "a2ir0",	0x400, 0, R8A77980_PD_A2IR0,	R8A77980_PD_A3IR },
 	{ "a2ir1",	0x400, 1, R8A77980_PD_A2IR1,	R8A77980_PD_A3IR },
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index f21cb05815ec..3e31375491d5 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -978,6 +978,7 @@ config CHARGER_QCOM_SMB2
 config FUEL_GAUGE_MM8013
 	tristate "Mitsumi MM8013 fuel gauge driver"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  Say Y here to enable the Mitsumi MM8013 fuel gauge driver.
 	  It enables the monitoring of many battery parameters, including
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 3a1798b0c1a7..9910c600743e 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client)
 {
 	struct bq27xxx_device_info *di = i2c_get_clientdata(client);
 
-	free_irq(client->irq, di);
+	if (client->irq)
+		free_irq(client->irq, di);
+
 	bq27xxx_battery_teardown(di);
 
 	mutex_lock(&battery_mutex);
diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
index a12e2a66d516..ec163d1bcd18 100644
--- a/drivers/power/supply/qcom_battmgr.c
+++ b/drivers/power/supply/qcom_battmgr.c
@@ -282,7 +282,6 @@ struct qcom_battmgr_wireless {
 
 struct qcom_battmgr {
 	struct device *dev;
-	struct auxiliary_device *adev;
 	struct pmic_glink_client *client;
 
 	enum qcom_battmgr_variant variant;
@@ -1294,69 +1293,11 @@ static void qcom_battmgr_enable_worker(struct work_struct *work)
 		dev_err(battmgr->dev, "failed to request power notifications\n");
 }
 
-static char *qcom_battmgr_battery[] = { "battery" };
-
-static void qcom_battmgr_register_psy(struct qcom_battmgr *battmgr)
-{
-	struct power_supply_config psy_cfg_supply = {};
-	struct auxiliary_device *adev = battmgr->adev;
-	struct power_supply_config psy_cfg = {};
-	struct device *dev = &adev->dev;
-
-	psy_cfg.drv_data = battmgr;
-	psy_cfg.of_node = adev->dev.of_node;
-
-	psy_cfg_supply.drv_data = battmgr;
-	psy_cfg_supply.of_node = adev->dev.of_node;
-	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
-	psy_cfg_supply.num_supplicants = 1;
-
-	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			dev_err(dev, "failed to register battery power supply (%ld)\n",
-				PTR_ERR(battmgr->bat_psy));
-
-		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->ac_psy))
-			dev_err(dev, "failed to register AC power supply (%ld)\n",
-				PTR_ERR(battmgr->ac_psy));
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			dev_err(dev, "failed to register USB power supply (%ld)\n",
-				PTR_ERR(battmgr->usb_psy));
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
-				PTR_ERR(battmgr->wls_psy));
-	} else {
-		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
-		if (IS_ERR(battmgr->bat_psy))
-			dev_err(dev, "failed to register battery power supply (%ld)\n",
-				PTR_ERR(battmgr->bat_psy));
-
-		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->usb_psy))
-			dev_err(dev, "failed to register USB power supply (%ld)\n",
-				PTR_ERR(battmgr->usb_psy));
-
-		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
-		if (IS_ERR(battmgr->wls_psy))
-			dev_err(dev, "failed to register wireless charing power supply (%ld)\n",
-				PTR_ERR(battmgr->wls_psy));
-	}
-}
-
 static void qcom_battmgr_pdr_notify(void *priv, int state)
 {
 	struct qcom_battmgr *battmgr = priv;
 
 	if (state == SERVREG_SERVICE_STATE_UP) {
-		if (!battmgr->bat_psy)
-			qcom_battmgr_register_psy(battmgr);
-
 		battmgr->service_up = true;
 		schedule_work(&battmgr->enable_work);
 	} else {
@@ -1371,9 +1312,13 @@ static const struct of_device_id qcom_battmgr_of_variants[] = {
 	{}
 };
 
+static char *qcom_battmgr_battery[] = { "battery" };
+
 static int qcom_battmgr_probe(struct auxiliary_device *adev,
 			      const struct auxiliary_device_id *id)
 {
+	struct power_supply_config psy_cfg_supply = {};
+	struct power_supply_config psy_cfg = {};
 	const struct of_device_id *match;
 	struct qcom_battmgr *battmgr;
 	struct device *dev = &adev->dev;
@@ -1383,7 +1328,14 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 		return -ENOMEM;
 
 	battmgr->dev = dev;
-	battmgr->adev = adev;
+
+	psy_cfg.drv_data = battmgr;
+	psy_cfg.of_node = adev->dev.of_node;
+
+	psy_cfg_supply.drv_data = battmgr;
+	psy_cfg_supply.of_node = adev->dev.of_node;
+	psy_cfg_supply.supplied_to = qcom_battmgr_battery;
+	psy_cfg_supply.num_supplicants = 1;
 
 	INIT_WORK(&battmgr->enable_work, qcom_battmgr_enable_worker);
 	mutex_init(&battmgr->lock);
@@ -1395,6 +1347,43 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
 	else
 		battmgr->variant = QCOM_BATTMGR_SM8350;
 
+	if (battmgr->variant == QCOM_BATTMGR_SC8280XP) {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sc8280xp_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
+					     "failed to register battery power supply\n");
+
+		battmgr->ac_psy = devm_power_supply_register(dev, &sc8280xp_ac_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->ac_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->ac_psy),
+					     "failed to register AC power supply\n");
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sc8280xp_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
+					     "failed to register USB power supply\n");
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sc8280xp_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
+					     "failed to register wireless charing power supply\n");
+	} else {
+		battmgr->bat_psy = devm_power_supply_register(dev, &sm8350_bat_psy_desc, &psy_cfg);
+		if (IS_ERR(battmgr->bat_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->bat_psy),
+					     "failed to register battery power supply\n");
+
+		battmgr->usb_psy = devm_power_supply_register(dev, &sm8350_usb_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->usb_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->usb_psy),
+					     "failed to register USB power supply\n");
+
+		battmgr->wls_psy = devm_power_supply_register(dev, &sm8350_wls_psy_desc, &psy_cfg_supply);
+		if (IS_ERR(battmgr->wls_psy))
+			return dev_err_probe(dev, PTR_ERR(battmgr->wls_psy),
+					     "failed to register wireless charing power supply\n");
+	}
+
 	battmgr->client = devm_pmic_glink_register_client(dev,
 							  PMIC_GLINK_OWNER_BATTMGR,
 							  qcom_battmgr_callback,
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 2feed036c1cd..00c861899a47 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1564,7 +1564,7 @@ struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id
 	if (id_is_cpu) {
 		rp->id = topology_logical_die_id(id);
 		rp->lead_cpu = id;
-		if (topology_max_die_per_package() > 1)
+		if (topology_max_dies_per_package() > 1)
 			snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d-die-%d",
 				 topology_physical_package_id(id), topology_die_id(id));
 		else
diff --git a/drivers/ptp/ptp_kvm_common.c b/drivers/ptp/ptp_kvm_common.c
index 2418977989be..15ccb7dd2ed0 100644
--- a/drivers/ptp/ptp_kvm_common.c
+++ b/drivers/ptp/ptp_kvm_common.c
@@ -28,15 +28,15 @@ static int ptp_kvm_get_time_fn(ktime_t *device_time,
 			       struct system_counterval_t *system_counter,
 			       void *ctx)
 {
-	long ret;
-	u64 cycle;
+	enum clocksource_ids cs_id;
 	struct timespec64 tspec;
-	struct clocksource *cs;
+	u64 cycle;
+	int ret;
 
 	spin_lock(&kvm_ptp_lock);
 
 	preempt_disable_notrace();
-	ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs);
+	ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs_id);
 	if (ret) {
 		spin_unlock(&kvm_ptp_lock);
 		preempt_enable_notrace();
@@ -46,7 +46,7 @@ static int ptp_kvm_get_time_fn(ktime_t *device_time,
 	preempt_enable_notrace();
 
 	system_counter->cycles = cycle;
-	system_counter->cs = cs;
+	system_counter->cs_id = cs_id;
 
 	*device_time = timespec64_to_ktime(tspec);
 
diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c
index 902844cc1a17..617c8d6706d3 100644
--- a/drivers/ptp/ptp_kvm_x86.c
+++ b/drivers/ptp/ptp_kvm_x86.c
@@ -93,7 +93,7 @@ int kvm_arch_ptp_get_clock(struct timespec64 *ts)
 }
 
 int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec,
-			      struct clocksource **cs)
+			      enum clocksource_ids *cs_id)
 {
 	struct pvclock_vcpu_time_info *src;
 	unsigned int version;
@@ -123,7 +123,7 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec,
 		*cycle = __pvclock_read_cycles(src, clock_pair->tsc);
 	} while (pvclock_read_retry(src, version));
 
-	*cs = &kvm_clock;
+	*cs_id = CSID_X86_KVM_CLK;
 
 	return 0;
 }
diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig
index c2a236f2e846..fc4f4bb94a4c 100644
--- a/drivers/ras/Kconfig
+++ b/drivers/ras/Kconfig
@@ -32,5 +32,18 @@ menuconfig RAS
 if RAS
 
 source "arch/x86/ras/Kconfig"
+source "drivers/ras/amd/atl/Kconfig"
+
+config RAS_FMPM
+	tristate "FRU Memory Poison Manager"
+	default m
+	depends on AMD_ATL && ACPI_APEI
+	help
+	  Support saving and restoring memory error information across reboot
+	  using ACPI ERST as persistent storage. Error information is saved with
+	  the UEFI CPER "FRU Memory Poison" section format.
+
+	  Memory will be retired during boot time and run time depending on
+	  platform-specific policies.
 
 endif
diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile
index 6f0404f50107..11f95d59d397 100644
--- a/drivers/ras/Makefile
+++ b/drivers/ras/Makefile
@@ -2,3 +2,6 @@
 obj-$(CONFIG_RAS)	+= ras.o
 obj-$(CONFIG_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_RAS_CEC)	+= cec.o
+
+obj-$(CONFIG_RAS_FMPM)	+= amd/fmpm.o
+obj-y			+= amd/atl/
diff --git a/drivers/ras/amd/atl/Kconfig b/drivers/ras/amd/atl/Kconfig
new file mode 100644
index 000000000000..df49c23e7f62
--- /dev/null
+++ b/drivers/ras/amd/atl/Kconfig
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# AMD Address Translation Library Kconfig
+#
+# Copyright (c) 2023, Advanced Micro Devices, Inc.
+# All Rights Reserved.
+#
+# Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+
+config AMD_ATL
+	tristate "AMD Address Translation Library"
+	depends on AMD_NB && X86_64 && RAS
+	depends on MEMORY_FAILURE
+	default N
+	help
+	  This library includes support for implementation-specific
+	  address translation procedures needed for various error
+	  handling cases.
+
+	  Enable this option if using DRAM ECC on Zen-based systems
+	  and OS-based error handling.
diff --git a/drivers/ras/amd/atl/Makefile b/drivers/ras/amd/atl/Makefile
new file mode 100644
index 000000000000..4acd5f05bd9c
--- /dev/null
+++ b/drivers/ras/amd/atl/Makefile
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# AMD Address Translation Library Makefile
+#
+# Copyright (c) 2023, Advanced Micro Devices, Inc.
+# All Rights Reserved.
+#
+# Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+
+amd_atl-y		:= access.o
+amd_atl-y		+= core.o
+amd_atl-y		+= dehash.o
+amd_atl-y		+= denormalize.o
+amd_atl-y		+= map.o
+amd_atl-y		+= system.o
+amd_atl-y		+= umc.o
+
+obj-$(CONFIG_AMD_ATL)	+= amd_atl.o
diff --git a/drivers/ras/amd/atl/access.c b/drivers/ras/amd/atl/access.c
new file mode 100644
index 000000000000..ee4661ed28ba
--- /dev/null
+++ b/drivers/ras/amd/atl/access.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * access.c : DF Indirect Access functions
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+/* Protect the PCI config register pairs used for DF indirect access. */
+static DEFINE_MUTEX(df_indirect_mutex);
+
+/*
+ * Data Fabric Indirect Access uses FICAA/FICAD.
+ *
+ * Fabric Indirect Configuration Access Address (FICAA): constructed based
+ * on the device's Instance Id and the PCI function and register offset of
+ * the desired register.
+ *
+ * Fabric Indirect Configuration Access Data (FICAD): there are FICAD
+ * low and high registers but so far only the low register is needed.
+ *
+ * Use Instance Id 0xFF to indicate a broadcast read.
+ */
+#define DF_BROADCAST		0xFF
+
+#define DF_FICAA_INST_EN	BIT(0)
+#define DF_FICAA_REG_NUM	GENMASK(10, 1)
+#define DF_FICAA_FUNC_NUM	GENMASK(13, 11)
+#define DF_FICAA_INST_ID	GENMASK(23, 16)
+
+#define DF_FICAA_REG_NUM_LEGACY	GENMASK(10, 2)
+
+static u16 get_accessible_node(u16 node)
+{
+	/*
+	 * On heterogeneous systems, not all AMD Nodes are accessible
+	 * through software-visible registers. The Node ID needs to be
+	 * adjusted for register accesses. But its value should not be
+	 * changed for the translation methods.
+	 */
+	if (df_cfg.flags.heterogeneous) {
+		/* Only Node 0 is accessible on DF3.5 systems. */
+		if (df_cfg.rev == DF3p5)
+			node = 0;
+
+		/*
+		 * Only the first Node in each Socket is accessible on
+		 * DF4.5 systems, and this is visible to software as one
+		 * Fabric per Socket.  The Socket ID can be derived from
+		 * the Node ID and global shift values.
+		 */
+		if (df_cfg.rev == DF4p5)
+			node >>= df_cfg.socket_id_shift - df_cfg.node_id_shift;
+	}
+
+	return node;
+}
+
+static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+	u32 ficaa_addr = 0x8C, ficad_addr = 0xB8;
+	struct pci_dev *F4;
+	int err = -ENODEV;
+	u32 ficaa = 0;
+
+	node = get_accessible_node(node);
+	if (node >= amd_nb_num())
+		goto out;
+
+	F4 = node_to_amd_nb(node)->link;
+	if (!F4)
+		goto out;
+
+	/* Enable instance-specific access. */
+	if (instance_id != DF_BROADCAST) {
+		ficaa |= FIELD_PREP(DF_FICAA_INST_EN, 1);
+		ficaa |= FIELD_PREP(DF_FICAA_INST_ID, instance_id);
+	}
+
+	/*
+	 * The two least-significant bits are masked when inputing the
+	 * register offset to FICAA.
+	 */
+	reg >>= 2;
+
+	if (df_cfg.flags.legacy_ficaa) {
+		ficaa_addr = 0x5C;
+		ficad_addr = 0x98;
+
+		ficaa |= FIELD_PREP(DF_FICAA_REG_NUM_LEGACY, reg);
+	} else {
+		ficaa |= FIELD_PREP(DF_FICAA_REG_NUM, reg);
+	}
+
+	ficaa |= FIELD_PREP(DF_FICAA_FUNC_NUM, func);
+
+	mutex_lock(&df_indirect_mutex);
+
+	err = pci_write_config_dword(F4, ficaa_addr, ficaa);
+	if (err) {
+		pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
+		goto out_unlock;
+	}
+
+	err = pci_read_config_dword(F4, ficad_addr, lo);
+	if (err)
+		pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
+
+	pr_debug("node=%u inst=0x%x func=0x%x reg=0x%x val=0x%x",
+		 node, instance_id, func, reg << 2, *lo);
+
+out_unlock:
+	mutex_unlock(&df_indirect_mutex);
+
+out:
+	return err;
+}
+
+int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+	return __df_indirect_read(node, func, reg, instance_id, lo);
+}
+
+int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo)
+{
+	return __df_indirect_read(node, func, reg, DF_BROADCAST, lo);
+}
diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c
new file mode 100644
index 000000000000..6dc4e06305f7
--- /dev/null
+++ b/drivers/ras/amd/atl/core.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * core.c : Module init and base translation functions
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include <linux/module.h>
+#include <asm/cpu_device_id.h>
+
+#include "internal.h"
+
+struct df_config df_cfg __read_mostly;
+
+static int addr_over_limit(struct addr_ctx *ctx)
+{
+	u64 dram_limit_addr;
+
+	if (df_cfg.rev >= DF4)
+		dram_limit_addr = FIELD_GET(DF4_DRAM_LIMIT_ADDR, ctx->map.limit);
+	else
+		dram_limit_addr = FIELD_GET(DF2_DRAM_LIMIT_ADDR, ctx->map.limit);
+
+	dram_limit_addr <<= DF_DRAM_BASE_LIMIT_LSB;
+	dram_limit_addr |= GENMASK(DF_DRAM_BASE_LIMIT_LSB - 1, 0);
+
+	/* Is calculated system address above DRAM limit address? */
+	if (ctx->ret_addr > dram_limit_addr) {
+		atl_debug(ctx, "Calculated address (0x%016llx) > DRAM limit (0x%016llx)",
+			  ctx->ret_addr, dram_limit_addr);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static bool legacy_hole_en(struct addr_ctx *ctx)
+{
+	u32 reg = ctx->map.base;
+
+	if (df_cfg.rev >= DF4)
+		reg = ctx->map.ctl;
+
+	return FIELD_GET(DF_LEGACY_MMIO_HOLE_EN, reg);
+}
+
+static int add_legacy_hole(struct addr_ctx *ctx)
+{
+	u32 dram_hole_base;
+	u8 func = 0;
+
+	if (!legacy_hole_en(ctx))
+		return 0;
+
+	if (df_cfg.rev >= DF4)
+		func = 7;
+
+	if (df_indirect_read_broadcast(ctx->node_id, func, 0x104, &dram_hole_base))
+		return -EINVAL;
+
+	dram_hole_base &= DF_DRAM_HOLE_BASE_MASK;
+
+	if (ctx->ret_addr >= dram_hole_base)
+		ctx->ret_addr += (BIT_ULL(32) - dram_hole_base);
+
+	return 0;
+}
+
+static u64 get_base_addr(struct addr_ctx *ctx)
+{
+	u64 base_addr;
+
+	if (df_cfg.rev >= DF4)
+		base_addr = FIELD_GET(DF4_BASE_ADDR, ctx->map.base);
+	else
+		base_addr = FIELD_GET(DF2_BASE_ADDR, ctx->map.base);
+
+	return base_addr << DF_DRAM_BASE_LIMIT_LSB;
+}
+
+static int add_base_and_hole(struct addr_ctx *ctx)
+{
+	ctx->ret_addr += get_base_addr(ctx);
+
+	if (add_legacy_hole(ctx))
+		return -EINVAL;
+
+	return 0;
+}
+
+static bool late_hole_remove(struct addr_ctx *ctx)
+{
+	if (df_cfg.rev == DF3p5)
+		return true;
+
+	if (df_cfg.rev == DF4)
+		return true;
+
+	if (ctx->map.intlv_mode == DF3_6CHAN)
+		return true;
+
+	return false;
+}
+
+unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr)
+{
+	struct addr_ctx ctx;
+
+	if (df_cfg.rev == UNKNOWN)
+		return -EINVAL;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	/* Start from the normalized address */
+	ctx.ret_addr = addr;
+	ctx.inst_id = coh_st_inst_id;
+
+	ctx.inputs.norm_addr = addr;
+	ctx.inputs.socket_id = socket_id;
+	ctx.inputs.die_id = die_id;
+	ctx.inputs.coh_st_inst_id = coh_st_inst_id;
+
+	if (determine_node_id(&ctx, socket_id, die_id))
+		return -EINVAL;
+
+	if (get_address_map(&ctx))
+		return -EINVAL;
+
+	if (denormalize_address(&ctx))
+		return -EINVAL;
+
+	if (!late_hole_remove(&ctx) && add_base_and_hole(&ctx))
+		return -EINVAL;
+
+	if (dehash_address(&ctx))
+		return -EINVAL;
+
+	if (late_hole_remove(&ctx) && add_base_and_hole(&ctx))
+		return -EINVAL;
+
+	if (addr_over_limit(&ctx))
+		return -EINVAL;
+
+	return ctx.ret_addr;
+}
+
+static void check_for_legacy_df_access(void)
+{
+	/*
+	 * All Zen-based systems before Family 19h use the legacy
+	 * DF Indirect Access (FICAA/FICAD) offsets.
+	 */
+	if (boot_cpu_data.x86 < 0x19) {
+		df_cfg.flags.legacy_ficaa = true;
+		return;
+	}
+
+	/* All systems after Family 19h use the current offsets. */
+	if (boot_cpu_data.x86 > 0x19)
+		return;
+
+	/* Some Family 19h systems use the legacy offsets. */
+	switch (boot_cpu_data.x86_model) {
+	case 0x00 ... 0x0f:
+	case 0x20 ... 0x5f:
+	       df_cfg.flags.legacy_ficaa = true;
+	}
+}
+
+/*
+ * This library provides functionality for AMD-based systems with a Data Fabric.
+ * The set of systems with a Data Fabric is equivalent to the set of Zen-based systems
+ * and the set of systems with the Scalable MCA feature at this time. However, these
+ * are technically independent things.
+ *
+ * It's possible to match on the PCI IDs of the Data Fabric devices, but this will be
+ * an ever expanding list. Instead, match on the SMCA and Zen features to cover all
+ * relevant systems.
+ */
+static const struct x86_cpu_id amd_atl_cpuids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_SMCA, NULL),
+	X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL),
+	{ }
+};
+MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids);
+
+static int __init amd_atl_init(void)
+{
+	if (!x86_match_cpu(amd_atl_cpuids))
+		return -ENODEV;
+
+	if (!amd_nb_num())
+		return -ENODEV;
+
+	check_for_legacy_df_access();
+
+	if (get_df_system_info())
+		return -ENODEV;
+
+	/* Increment this module's recount so that it can't be easily unloaded. */
+	__module_get(THIS_MODULE);
+	amd_atl_register_decoder(convert_umc_mca_addr_to_sys_addr);
+
+	pr_info("AMD Address Translation Library initialized");
+	return 0;
+}
+
+/*
+ * Exit function is only needed for testing and debug. Module unload must be
+ * forced to override refcount check.
+ */
+static void __exit amd_atl_exit(void)
+{
+	amd_atl_unregister_decoder();
+}
+
+module_init(amd_atl_init);
+module_exit(amd_atl_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/ras/amd/atl/dehash.c b/drivers/ras/amd/atl/dehash.c
new file mode 100644
index 000000000000..4ea46262c4f5
--- /dev/null
+++ b/drivers/ras/amd/atl/dehash.c
@@ -0,0 +1,500 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * dehash.c : Functions to account for hashing bits
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+/*
+ * Verify the interleave bits are correct in the different interleaving
+ * settings.
+ *
+ * If @num_intlv_dies and/or @num_intlv_sockets are 1, it means the
+ * respective interleaving is disabled.
+ */
+static inline bool map_bits_valid(struct addr_ctx *ctx, u8 bit1, u8 bit2,
+				  u8 num_intlv_dies, u8 num_intlv_sockets)
+{
+	if (!(ctx->map.intlv_bit_pos == bit1 || ctx->map.intlv_bit_pos == bit2)) {
+		pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos);
+		return false;
+	}
+
+	if (ctx->map.num_intlv_dies > num_intlv_dies) {
+		pr_debug("Invalid number of interleave dies: %u", ctx->map.num_intlv_dies);
+		return false;
+	}
+
+	if (ctx->map.num_intlv_sockets > num_intlv_sockets) {
+		pr_debug("Invalid number of interleave sockets: %u", ctx->map.num_intlv_sockets);
+		return false;
+	}
+
+	return true;
+}
+
+static int df2_dehash_addr(struct addr_ctx *ctx)
+{
+	u8 hashed_bit, intlv_bit, intlv_bit_pos;
+
+	if (!map_bits_valid(ctx, 8, 9, 1, 1))
+		return -EINVAL;
+
+	intlv_bit_pos = ctx->map.intlv_bit_pos;
+	intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(12), ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr);
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(intlv_bit_pos);
+
+	return 0;
+}
+
+static int df3_dehash_addr(struct addr_ctx *ctx)
+{
+	bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G;
+	u8 hashed_bit, intlv_bit, intlv_bit_pos;
+
+	if (!map_bits_valid(ctx, 8, 9, 1, 1))
+		return -EINVAL;
+
+	hash_ctl_64k = FIELD_GET(DF3_HASH_CTL_64K, ctx->map.ctl);
+	hash_ctl_2M  = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl);
+	hash_ctl_1G  = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl);
+
+	intlv_bit_pos = ctx->map.intlv_bit_pos;
+	intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(intlv_bit_pos);
+
+	/* Calculation complete for 2 channels. Continue for 4 and 8 channels. */
+	if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH)
+		return 0;
+
+	intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(12);
+
+	/* Calculation complete for 4 channels. Continue for 8 channels. */
+	if (ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH)
+		return 0;
+
+	intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(13);
+
+	return 0;
+}
+
+static int df3_6chan_dehash_addr(struct addr_ctx *ctx)
+{
+	u8 intlv_bit_pos = ctx->map.intlv_bit_pos;
+	u8 hashed_bit, intlv_bit, num_intlv_bits;
+	bool hash_ctl_2M, hash_ctl_1G;
+
+	if (ctx->map.intlv_mode != DF3_6CHAN) {
+		atl_debug_on_bad_intlv_mode(ctx);
+		return -EINVAL;
+	}
+
+	num_intlv_bits = ilog2(ctx->map.num_intlv_chan) + 1;
+
+	hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl);
+	hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl);
+
+	intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= !!(BIT_ULL(intlv_bit_pos + num_intlv_bits) & ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(intlv_bit_pos);
+
+	intlv_bit_pos++;
+	intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(intlv_bit_pos);
+
+	intlv_bit_pos++;
+	intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(intlv_bit_pos);
+
+	return 0;
+}
+
+static int df4_dehash_addr(struct addr_ctx *ctx)
+{
+	bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G;
+	u8 hashed_bit, intlv_bit;
+
+	if (!map_bits_valid(ctx, 8, 8, 1, 2))
+		return -EINVAL;
+
+	hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+	hash_ctl_2M  = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+	hash_ctl_1G  = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl);
+
+	intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G;
+
+	if (ctx->map.num_intlv_sockets == 1)
+		hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr);
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(8);
+
+	/*
+	 * Hashing is possible with socket interleaving, so check the total number
+	 * of channels in the system rather than DRAM map interleaving mode.
+	 *
+	 * Calculation complete for 2 channels. Continue for 4, 8, and 16 channels.
+	 */
+	if (ctx->map.total_intlv_chan <= 2)
+		return 0;
+
+	intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(12);
+
+	/* Calculation complete for 4 channels. Continue for 8 and 16 channels. */
+	if (ctx->map.total_intlv_chan <= 4)
+		return 0;
+
+	intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(13);
+
+	/* Calculation complete for 8 channels. Continue for 16 channels. */
+	if (ctx->map.total_intlv_chan <= 8)
+		return 0;
+
+	intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr);
+
+	hashed_bit = intlv_bit;
+	hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G;
+
+	if (hashed_bit != intlv_bit)
+		ctx->ret_addr ^= BIT_ULL(14);
+
+	return 0;
+}
+
+static int df4p5_dehash_addr(struct addr_ctx *ctx)
+{
+	bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T;
+	u8 hashed_bit, intlv_bit;
+	u64 rehash_vector;
+
+	if (!map_bits_valid(ctx, 8, 8, 1, 2))
+		return -EINVAL;
+
+	hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+	hash_ctl_2M  = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+	hash_ctl_1G  = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl);
+	hash_ctl_1T  = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl);
+
+	/*
+	 * Generate a unique address to determine which bits
+	 * need to be dehashed.
+	 *
+	 * Start with a contiguous bitmask for the total
+	 * number of channels starting at bit 8.
+	 *
+	 * Then make a gap in the proper place based on
+	 * interleave mode.
+	 */
+	rehash_vector = ctx->map.total_intlv_chan - 1;
+	rehash_vector <<= 8;
+
+	if (ctx->map.intlv_mode == DF4p5_NPS2_4CHAN_1K_HASH ||
+	    ctx->map.intlv_mode == DF4p5_NPS1_8CHAN_1K_HASH ||
+	    ctx->map.intlv_mode == DF4p5_NPS1_16CHAN_1K_HASH)
+		rehash_vector = expand_bits(10, 2, rehash_vector);
+	else
+		rehash_vector = expand_bits(9, 3, rehash_vector);
+
+	if (rehash_vector & BIT_ULL(8)) {
+		intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr);
+
+		hashed_bit = intlv_bit;
+		hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k;
+		hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M;
+		hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G;
+		hashed_bit ^= FIELD_GET(BIT_ULL(40), ctx->ret_addr) & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(8);
+	}
+
+	if (rehash_vector & BIT_ULL(9)) {
+		intlv_bit = FIELD_GET(BIT_ULL(9), ctx->ret_addr);
+
+		hashed_bit = intlv_bit;
+		hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k;
+		hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M;
+		hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G;
+		hashed_bit ^= FIELD_GET(BIT_ULL(41), ctx->ret_addr) & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(9);
+	}
+
+	if (rehash_vector & BIT_ULL(12)) {
+		intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr);
+
+		hashed_bit = intlv_bit;
+		hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k;
+		hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M;
+		hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G;
+		hashed_bit ^= FIELD_GET(BIT_ULL(42), ctx->ret_addr) & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(12);
+	}
+
+	if (rehash_vector & BIT_ULL(13)) {
+		intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr);
+
+		hashed_bit = intlv_bit;
+		hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k;
+		hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M;
+		hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G;
+		hashed_bit ^= FIELD_GET(BIT_ULL(43), ctx->ret_addr) & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(13);
+	}
+
+	if (rehash_vector & BIT_ULL(14)) {
+		intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr);
+
+		hashed_bit = intlv_bit;
+		hashed_bit ^= FIELD_GET(BIT_ULL(20), ctx->ret_addr) & hash_ctl_64k;
+		hashed_bit ^= FIELD_GET(BIT_ULL(25), ctx->ret_addr) & hash_ctl_2M;
+		hashed_bit ^= FIELD_GET(BIT_ULL(34), ctx->ret_addr) & hash_ctl_1G;
+		hashed_bit ^= FIELD_GET(BIT_ULL(44), ctx->ret_addr) & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(14);
+	}
+
+	return 0;
+}
+
+/*
+ * MI300 hash bits
+ *					  4K 64K  2M  1G  1T  1T
+ * COH_ST_Select[0]	= XOR of addr{8,  12, 15, 22, 29, 36, 43}
+ * COH_ST_Select[1]	= XOR of addr{9,  13, 16, 23, 30, 37, 44}
+ * COH_ST_Select[2]	= XOR of addr{10, 14, 17, 24, 31, 38, 45}
+ * COH_ST_Select[3]	= XOR of addr{11,     18, 25, 32, 39, 46}
+ * COH_ST_Select[4]	= XOR of addr{14,     19, 26, 33, 40, 47} aka Stack
+ * DieID[0]		= XOR of addr{12,     20, 27, 34, 41    }
+ * DieID[1]		= XOR of addr{13,     21, 28, 35, 42    }
+ */
+static int mi300_dehash_addr(struct addr_ctx *ctx)
+{
+	bool hash_ctl_4k, hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T;
+	bool hashed_bit, intlv_bit, test_bit;
+	u8 num_intlv_bits, base_bit, i;
+
+	if (!map_bits_valid(ctx, 8, 8, 4, 1))
+		return -EINVAL;
+
+	hash_ctl_4k  = FIELD_GET(DF4p5_HASH_CTL_4K, ctx->map.ctl);
+	hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K,  ctx->map.ctl);
+	hash_ctl_2M  = FIELD_GET(DF4_HASH_CTL_2M,   ctx->map.ctl);
+	hash_ctl_1G  = FIELD_GET(DF4_HASH_CTL_1G,   ctx->map.ctl);
+	hash_ctl_1T  = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl);
+
+	/* Channel bits */
+	num_intlv_bits = ilog2(ctx->map.num_intlv_chan);
+
+	for (i = 0; i < num_intlv_bits; i++) {
+		base_bit = 8 + i;
+
+		/* COH_ST_Select[4] jumps to a base bit of 14. */
+		if (i == 4)
+			base_bit = 14;
+
+		intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr;
+
+		hashed_bit = intlv_bit;
+
+		/* 4k hash bit only applies to the first 3 bits. */
+		if (i <= 2) {
+			test_bit    = BIT_ULL(12 + i) & ctx->ret_addr;
+			hashed_bit ^= test_bit & hash_ctl_4k;
+		}
+
+		/* Use temporary 'test_bit' value to avoid Sparse warnings. */
+		test_bit    = BIT_ULL(15 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_64k;
+		test_bit    = BIT_ULL(22 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_2M;
+		test_bit    = BIT_ULL(29 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_1G;
+		test_bit    = BIT_ULL(36 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_1T;
+		test_bit    = BIT_ULL(43 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(base_bit);
+	}
+
+	/* Die bits */
+	num_intlv_bits = ilog2(ctx->map.num_intlv_dies);
+
+	for (i = 0; i < num_intlv_bits; i++) {
+		base_bit = 12 + i;
+
+		intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr;
+
+		hashed_bit = intlv_bit;
+
+		test_bit    = BIT_ULL(20 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_64k;
+		test_bit    = BIT_ULL(27 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_2M;
+		test_bit    = BIT_ULL(34 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_1G;
+		test_bit    = BIT_ULL(41 + i) & ctx->ret_addr;
+		hashed_bit ^= test_bit & hash_ctl_1T;
+
+		if (hashed_bit != intlv_bit)
+			ctx->ret_addr ^= BIT_ULL(base_bit);
+	}
+
+	return 0;
+}
+
+int dehash_address(struct addr_ctx *ctx)
+{
+	switch (ctx->map.intlv_mode) {
+	/* No hashing cases. */
+	case NONE:
+	case NOHASH_2CHAN:
+	case NOHASH_4CHAN:
+	case NOHASH_8CHAN:
+	case NOHASH_16CHAN:
+	case NOHASH_32CHAN:
+	/* Hashing bits handled earlier during CS ID calculation. */
+	case DF4_NPS4_3CHAN_HASH:
+	case DF4_NPS2_5CHAN_HASH:
+	case DF4_NPS2_6CHAN_HASH:
+	case DF4_NPS1_10CHAN_HASH:
+	case DF4_NPS1_12CHAN_HASH:
+	case DF4p5_NPS2_6CHAN_1K_HASH:
+	case DF4p5_NPS2_6CHAN_2K_HASH:
+	case DF4p5_NPS1_10CHAN_1K_HASH:
+	case DF4p5_NPS1_10CHAN_2K_HASH:
+	case DF4p5_NPS1_12CHAN_1K_HASH:
+	case DF4p5_NPS1_12CHAN_2K_HASH:
+	case DF4p5_NPS0_24CHAN_1K_HASH:
+	case DF4p5_NPS0_24CHAN_2K_HASH:
+	/* No hash physical address bits, so nothing to do. */
+	case DF4p5_NPS4_3CHAN_1K_HASH:
+	case DF4p5_NPS4_3CHAN_2K_HASH:
+	case DF4p5_NPS2_5CHAN_1K_HASH:
+	case DF4p5_NPS2_5CHAN_2K_HASH:
+		return 0;
+
+	case DF2_2CHAN_HASH:
+		return df2_dehash_addr(ctx);
+
+	case DF3_COD4_2CHAN_HASH:
+	case DF3_COD2_4CHAN_HASH:
+	case DF3_COD1_8CHAN_HASH:
+		return df3_dehash_addr(ctx);
+
+	case DF3_6CHAN:
+		return df3_6chan_dehash_addr(ctx);
+
+	case DF4_NPS4_2CHAN_HASH:
+	case DF4_NPS2_4CHAN_HASH:
+	case DF4_NPS1_8CHAN_HASH:
+		return df4_dehash_addr(ctx);
+
+	case DF4p5_NPS4_2CHAN_1K_HASH:
+	case DF4p5_NPS4_2CHAN_2K_HASH:
+	case DF4p5_NPS2_4CHAN_2K_HASH:
+	case DF4p5_NPS2_4CHAN_1K_HASH:
+	case DF4p5_NPS1_8CHAN_1K_HASH:
+	case DF4p5_NPS1_8CHAN_2K_HASH:
+	case DF4p5_NPS1_16CHAN_1K_HASH:
+	case DF4p5_NPS1_16CHAN_2K_HASH:
+		return df4p5_dehash_addr(ctx);
+
+	case MI3_HASH_8CHAN:
+	case MI3_HASH_16CHAN:
+	case MI3_HASH_32CHAN:
+		return mi300_dehash_addr(ctx);
+
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return -EINVAL;
+	}
+}
diff --git a/drivers/ras/amd/atl/denormalize.c b/drivers/ras/amd/atl/denormalize.c
new file mode 100644
index 000000000000..e279224288d6
--- /dev/null
+++ b/drivers/ras/amd/atl/denormalize.c
@@ -0,0 +1,718 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * denormalize.c : Functions to account for interleaving bits
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+/*
+ * Returns the Destination Fabric ID. This is the first (lowest)
+ * COH_ST Fabric ID used within a DRAM Address map.
+ */
+static u16 get_dst_fabric_id(struct addr_ctx *ctx)
+{
+	switch (df_cfg.rev) {
+	case DF2:	return FIELD_GET(DF2_DST_FABRIC_ID,	ctx->map.limit);
+	case DF3:	return FIELD_GET(DF3_DST_FABRIC_ID,	ctx->map.limit);
+	case DF3p5:	return FIELD_GET(DF3p5_DST_FABRIC_ID,	ctx->map.limit);
+	case DF4:	return FIELD_GET(DF4_DST_FABRIC_ID,	ctx->map.ctl);
+	case DF4p5:	return FIELD_GET(DF4p5_DST_FABRIC_ID,	ctx->map.ctl);
+	default:
+			atl_debug_on_bad_df_rev();
+			return 0;
+	}
+}
+
+/*
+ * Make a contiguous gap in address for N bits starting at bit P.
+ *
+ * Example:
+ * address bits:		[20:0]
+ * # of interleave bits    (n):	3
+ * starting interleave bit (p):	8
+ *
+ * expanded address bits:	[20+n : n+p][n+p-1 : p][p-1 : 0]
+ *				[23   :  11][10    : 8][7   : 0]
+ */
+static u64 make_space_for_coh_st_id_at_intlv_bit(struct addr_ctx *ctx)
+{
+	return expand_bits(ctx->map.intlv_bit_pos,
+			   ctx->map.total_intlv_bits,
+			   ctx->ret_addr);
+}
+
+/*
+ * Make two gaps in address for N bits.
+ * First gap is a single bit at bit P.
+ * Second gap is the remaining N-1 bits at bit 12.
+ *
+ * Example:
+ * address bits:		[20:0]
+ * # of interleave bits    (n):	3
+ * starting interleave bit (p):	8
+ *
+ * First gap
+ * expanded address bits:	[20+1 : p+1][p][p-1 : 0]
+ *				[21   :   9][8][7   : 0]
+ *
+ * Second gap uses result from first.
+ *				r = n - 1; remaining interleave bits
+ * expanded address bits:	[21+r : 12+r][12+r-1: 12][11 : 0]
+ *				[23   :   14][13    : 12][11 : 0]
+ */
+static u64 make_space_for_coh_st_id_split_2_1(struct addr_ctx *ctx)
+{
+	/* Make a single space at the interleave bit. */
+	u64 denorm_addr = expand_bits(ctx->map.intlv_bit_pos, 1, ctx->ret_addr);
+
+	/* Done if there's only a single interleave bit. */
+	if (ctx->map.total_intlv_bits <= 1)
+		return denorm_addr;
+
+	/* Make spaces for the remaining interleave bits starting at bit 12. */
+	return expand_bits(12, ctx->map.total_intlv_bits - 1, denorm_addr);
+}
+
+/*
+ * Make space for CS ID at bits [14:8] as follows:
+ *
+ * 8 channels	-> bits [10:8]
+ * 16 channels	-> bits [11:8]
+ * 32 channels	-> bits [14,11:8]
+ *
+ * 1 die	-> N/A
+ * 2 dies	-> bit  [12]
+ * 4 dies	-> bits [13:12]
+ */
+static u64 make_space_for_coh_st_id_mi300(struct addr_ctx *ctx)
+{
+	u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan);
+	u64 denorm_addr;
+
+	if (ctx->map.intlv_bit_pos != 8) {
+		pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos);
+		return ~0ULL;
+	}
+
+	/* Channel bits. Covers up to 4 bits at [11:8]. */
+	denorm_addr = expand_bits(8, min(num_intlv_bits, 4), ctx->ret_addr);
+
+	/* Die bits. Always starts at [12]. */
+	denorm_addr = expand_bits(12, ilog2(ctx->map.num_intlv_dies), denorm_addr);
+
+	/* Additional channel bit at [14]. */
+	if (num_intlv_bits > 4)
+		denorm_addr = expand_bits(14, 1, denorm_addr);
+
+	return denorm_addr;
+}
+
+/*
+ * Take the current calculated address and shift enough bits in the middle
+ * to make a gap where the interleave bits will be inserted.
+ */
+static u64 make_space_for_coh_st_id(struct addr_ctx *ctx)
+{
+	switch (ctx->map.intlv_mode) {
+	case NOHASH_2CHAN:
+	case NOHASH_4CHAN:
+	case NOHASH_8CHAN:
+	case NOHASH_16CHAN:
+	case NOHASH_32CHAN:
+	case DF2_2CHAN_HASH:
+		return make_space_for_coh_st_id_at_intlv_bit(ctx);
+
+	case DF3_COD4_2CHAN_HASH:
+	case DF3_COD2_4CHAN_HASH:
+	case DF3_COD1_8CHAN_HASH:
+	case DF4_NPS4_2CHAN_HASH:
+	case DF4_NPS2_4CHAN_HASH:
+	case DF4_NPS1_8CHAN_HASH:
+	case DF4p5_NPS4_2CHAN_1K_HASH:
+	case DF4p5_NPS4_2CHAN_2K_HASH:
+	case DF4p5_NPS2_4CHAN_2K_HASH:
+	case DF4p5_NPS1_8CHAN_2K_HASH:
+	case DF4p5_NPS1_16CHAN_2K_HASH:
+		return make_space_for_coh_st_id_split_2_1(ctx);
+
+	case MI3_HASH_8CHAN:
+	case MI3_HASH_16CHAN:
+	case MI3_HASH_32CHAN:
+		return make_space_for_coh_st_id_mi300(ctx);
+
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return ~0ULL;
+	}
+}
+
+static u16 get_coh_st_id_df2(struct addr_ctx *ctx)
+{
+	u8 num_socket_intlv_bits = ilog2(ctx->map.num_intlv_sockets);
+	u8 num_die_intlv_bits = ilog2(ctx->map.num_intlv_dies);
+	u8 num_intlv_bits;
+	u16 coh_st_id, mask;
+
+	coh_st_id = ctx->coh_st_fabric_id - get_dst_fabric_id(ctx);
+
+	/* Channel interleave bits */
+	num_intlv_bits = order_base_2(ctx->map.num_intlv_chan);
+	mask = GENMASK(num_intlv_bits - 1, 0);
+	coh_st_id &= mask;
+
+	/* Die interleave bits */
+	if (num_die_intlv_bits) {
+		u16 die_bits;
+
+		mask = GENMASK(num_die_intlv_bits - 1, 0);
+		die_bits = ctx->coh_st_fabric_id & df_cfg.die_id_mask;
+		die_bits >>= df_cfg.die_id_shift;
+
+		coh_st_id |= (die_bits & mask) << num_intlv_bits;
+		num_intlv_bits += num_die_intlv_bits;
+	}
+
+	/* Socket interleave bits */
+	if (num_socket_intlv_bits) {
+		u16 socket_bits;
+
+		mask = GENMASK(num_socket_intlv_bits - 1, 0);
+		socket_bits = ctx->coh_st_fabric_id & df_cfg.socket_id_mask;
+		socket_bits >>= df_cfg.socket_id_shift;
+
+		coh_st_id |= (socket_bits & mask) << num_intlv_bits;
+	}
+
+	return coh_st_id;
+}
+
+static u16 get_coh_st_id_df4(struct addr_ctx *ctx)
+{
+	/*
+	 * Start with the original component mask and the number of interleave
+	 * bits for the channels in this map.
+	 */
+	u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan);
+	u16 mask = df_cfg.component_id_mask;
+
+	u16 socket_bits;
+
+	/* Set the derived Coherent Station ID to the input Coherent Station Fabric ID. */
+	u16 coh_st_id = ctx->coh_st_fabric_id & mask;
+
+	/*
+	 * Subtract the "base" Destination Fabric ID.
+	 * This accounts for systems with disabled Coherent Stations.
+	 */
+	coh_st_id -= get_dst_fabric_id(ctx) & mask;
+
+	/*
+	 * Generate and use a new mask based on the number of bits
+	 * needed for channel interleaving in this map.
+	 */
+	mask = GENMASK(num_intlv_bits - 1, 0);
+	coh_st_id &= mask;
+
+	/* Done if socket interleaving is not enabled. */
+	if (ctx->map.num_intlv_sockets <= 1)
+		return coh_st_id;
+
+	/*
+	 * Figure out how many bits are needed for the number of
+	 * interleaved sockets. And shift the derived Coherent Station ID to account
+	 * for these.
+	 */
+	num_intlv_bits = ilog2(ctx->map.num_intlv_sockets);
+	coh_st_id <<= num_intlv_bits;
+
+	/* Generate a new mask for the socket interleaving bits. */
+	mask = GENMASK(num_intlv_bits - 1, 0);
+
+	/* Get the socket interleave bits from the original Coherent Station Fabric ID. */
+	socket_bits = (ctx->coh_st_fabric_id & df_cfg.socket_id_mask) >> df_cfg.socket_id_shift;
+
+	/* Apply the appropriate socket bits to the derived Coherent Station ID. */
+	coh_st_id |= socket_bits & mask;
+
+	return coh_st_id;
+}
+
+/*
+ * MI300 hash has:
+ * (C)hannel[3:0]	= coh_st_id[3:0]
+ * (S)tack[0]		= coh_st_id[4]
+ * (D)ie[1:0]		= coh_st_id[6:5]
+ *
+ * Hashed coh_st_id is swizzled so that Stack bit is at the end.
+ * coh_st_id = SDDCCCC
+ */
+static u16 get_coh_st_id_mi300(struct addr_ctx *ctx)
+{
+	u8 channel_bits, die_bits, stack_bit;
+	u16 die_id;
+
+	/* Subtract the "base" Destination Fabric ID. */
+	ctx->coh_st_fabric_id -= get_dst_fabric_id(ctx);
+
+	die_id = (ctx->coh_st_fabric_id & df_cfg.die_id_mask) >> df_cfg.die_id_shift;
+
+	channel_bits	= FIELD_GET(GENMASK(3, 0), ctx->coh_st_fabric_id);
+	stack_bit	= FIELD_GET(BIT(4), ctx->coh_st_fabric_id) << 6;
+	die_bits	= die_id << 4;
+
+	return stack_bit | die_bits | channel_bits;
+}
+
+/*
+ * Derive the correct Coherent Station ID that represents the interleave bits
+ * used within the system physical address. This accounts for the
+ * interleave mode, number of interleaved channels/dies/sockets, and
+ * other system/mode-specific bit swizzling.
+ *
+ * Returns:	Coherent Station ID on success.
+ *		All bits set on error.
+ */
+static u16 calculate_coh_st_id(struct addr_ctx *ctx)
+{
+	switch (ctx->map.intlv_mode) {
+	case NOHASH_2CHAN:
+	case NOHASH_4CHAN:
+	case NOHASH_8CHAN:
+	case NOHASH_16CHAN:
+	case NOHASH_32CHAN:
+	case DF3_COD4_2CHAN_HASH:
+	case DF3_COD2_4CHAN_HASH:
+	case DF3_COD1_8CHAN_HASH:
+	case DF2_2CHAN_HASH:
+		return get_coh_st_id_df2(ctx);
+
+	case DF4_NPS4_2CHAN_HASH:
+	case DF4_NPS2_4CHAN_HASH:
+	case DF4_NPS1_8CHAN_HASH:
+	case DF4p5_NPS4_2CHAN_1K_HASH:
+	case DF4p5_NPS4_2CHAN_2K_HASH:
+	case DF4p5_NPS2_4CHAN_2K_HASH:
+	case DF4p5_NPS1_8CHAN_2K_HASH:
+	case DF4p5_NPS1_16CHAN_2K_HASH:
+		return get_coh_st_id_df4(ctx);
+
+	case MI3_HASH_8CHAN:
+	case MI3_HASH_16CHAN:
+	case MI3_HASH_32CHAN:
+		return get_coh_st_id_mi300(ctx);
+
+	/* COH_ST ID is simply the COH_ST Fabric ID adjusted by the Destination Fabric ID. */
+	case DF4p5_NPS2_4CHAN_1K_HASH:
+	case DF4p5_NPS1_8CHAN_1K_HASH:
+	case DF4p5_NPS1_16CHAN_1K_HASH:
+		return ctx->coh_st_fabric_id - get_dst_fabric_id(ctx);
+
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return ~0;
+	}
+}
+
+static u64 insert_coh_st_id_at_intlv_bit(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id)
+{
+	return denorm_addr | (coh_st_id << ctx->map.intlv_bit_pos);
+}
+
+static u64 insert_coh_st_id_split_2_1(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id)
+{
+	/* Insert coh_st_id[0] at the interleave bit. */
+	denorm_addr |= (coh_st_id & BIT(0)) << ctx->map.intlv_bit_pos;
+
+	/* Insert coh_st_id[2:1] at bit 12. */
+	denorm_addr |= (coh_st_id & GENMASK(2, 1)) << 11;
+
+	return denorm_addr;
+}
+
+static u64 insert_coh_st_id_split_2_2(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id)
+{
+	/* Insert coh_st_id[1:0] at bit 8. */
+	denorm_addr |= (coh_st_id & GENMASK(1, 0)) << 8;
+
+	/*
+	 * Insert coh_st_id[n:2] at bit 12. 'n' could be 2 or 3.
+	 * Grab both because bit 3 will be clear if unused.
+	 */
+	denorm_addr |= (coh_st_id & GENMASK(3, 2)) << 10;
+
+	return denorm_addr;
+}
+
+static u64 insert_coh_st_id(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id)
+{
+	switch (ctx->map.intlv_mode) {
+	case NOHASH_2CHAN:
+	case NOHASH_4CHAN:
+	case NOHASH_8CHAN:
+	case NOHASH_16CHAN:
+	case NOHASH_32CHAN:
+	case MI3_HASH_8CHAN:
+	case MI3_HASH_16CHAN:
+	case MI3_HASH_32CHAN:
+	case DF2_2CHAN_HASH:
+		return insert_coh_st_id_at_intlv_bit(ctx, denorm_addr, coh_st_id);
+
+	case DF3_COD4_2CHAN_HASH:
+	case DF3_COD2_4CHAN_HASH:
+	case DF3_COD1_8CHAN_HASH:
+	case DF4_NPS4_2CHAN_HASH:
+	case DF4_NPS2_4CHAN_HASH:
+	case DF4_NPS1_8CHAN_HASH:
+	case DF4p5_NPS4_2CHAN_1K_HASH:
+	case DF4p5_NPS4_2CHAN_2K_HASH:
+	case DF4p5_NPS2_4CHAN_2K_HASH:
+	case DF4p5_NPS1_8CHAN_2K_HASH:
+	case DF4p5_NPS1_16CHAN_2K_HASH:
+		return insert_coh_st_id_split_2_1(ctx, denorm_addr, coh_st_id);
+
+	case DF4p5_NPS2_4CHAN_1K_HASH:
+	case DF4p5_NPS1_8CHAN_1K_HASH:
+	case DF4p5_NPS1_16CHAN_1K_HASH:
+		return insert_coh_st_id_split_2_2(ctx, denorm_addr, coh_st_id);
+
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return ~0ULL;
+	}
+}
+
+/*
+ * MI300 systems have a fixed, hardware-defined physical-to-logical
+ * Coherent Station mapping. The Remap registers are not used.
+ */
+static const u16 phy_to_log_coh_st_map_mi300[] = {
+	12, 13, 14, 15,
+	 8,  9, 10, 11,
+	 4,  5,  6,  7,
+	 0,  1,  2,  3,
+	28, 29, 30, 31,
+	24, 25, 26, 27,
+	20, 21, 22, 23,
+	16, 17, 18, 19,
+};
+
+static u16 get_logical_coh_st_fabric_id_mi300(struct addr_ctx *ctx)
+{
+	if (ctx->inst_id >= ARRAY_SIZE(phy_to_log_coh_st_map_mi300)) {
+		atl_debug(ctx, "Instance ID out of range");
+		return ~0;
+	}
+
+	return phy_to_log_coh_st_map_mi300[ctx->inst_id] | (ctx->node_id << df_cfg.node_id_shift);
+}
+
+static u16 get_logical_coh_st_fabric_id(struct addr_ctx *ctx)
+{
+	u16 component_id, log_fabric_id;
+
+	/* Start with the physical COH_ST Fabric ID. */
+	u16 phys_fabric_id = ctx->coh_st_fabric_id;
+
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return get_logical_coh_st_fabric_id_mi300(ctx);
+
+	/* Skip logical ID lookup if remapping is disabled. */
+	if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl) &&
+	    ctx->map.intlv_mode != DF3_6CHAN)
+		return phys_fabric_id;
+
+	/* Mask off the Node ID bits to get the "local" Component ID. */
+	component_id = phys_fabric_id & df_cfg.component_id_mask;
+
+	/*
+	 * Search the list of logical Component IDs for the one that
+	 * matches this physical Component ID.
+	 */
+	for (log_fabric_id = 0; log_fabric_id < MAX_COH_ST_CHANNELS; log_fabric_id++) {
+		if (ctx->map.remap_array[log_fabric_id] == component_id)
+			break;
+	}
+
+	if (log_fabric_id == MAX_COH_ST_CHANNELS)
+		atl_debug(ctx, "COH_ST remap entry not found for 0x%x",
+			  log_fabric_id);
+
+	/* Get the Node ID bits from the physical and apply to the logical. */
+	return (phys_fabric_id & df_cfg.node_id_mask) | log_fabric_id;
+}
+
+static int denorm_addr_common(struct addr_ctx *ctx)
+{
+	u64 denorm_addr;
+	u16 coh_st_id;
+
+	/*
+	 * Convert the original physical COH_ST Fabric ID to a logical value.
+	 * This is required for non-power-of-two and other interleaving modes.
+	 */
+	ctx->coh_st_fabric_id = get_logical_coh_st_fabric_id(ctx);
+
+	denorm_addr = make_space_for_coh_st_id(ctx);
+	coh_st_id = calculate_coh_st_id(ctx);
+	ctx->ret_addr = insert_coh_st_id(ctx, denorm_addr, coh_st_id);
+	return 0;
+}
+
+static int denorm_addr_df3_6chan(struct addr_ctx *ctx)
+{
+	u16 coh_st_id = ctx->coh_st_fabric_id & df_cfg.component_id_mask;
+	u8 total_intlv_bits = ctx->map.total_intlv_bits;
+	u8 low_bit, intlv_bit = ctx->map.intlv_bit_pos;
+	u64 msb_intlv_bits, temp_addr_a, temp_addr_b;
+	u8 np2_bits = ctx->map.np2_bits;
+
+	if (ctx->map.intlv_mode != DF3_6CHAN)
+		return -EINVAL;
+
+	/*
+	 * 'np2_bits' holds the number of bits needed to cover the
+	 * amount of memory (rounded up) in this map using 64K chunks.
+	 *
+	 * Example:
+	 * Total memory in map:			6GB
+	 * Rounded up to next power-of-2:	8GB
+	 * Number of 64K chunks:		0x20000
+	 * np2_bits = log2(# of chunks):	17
+	 *
+	 * Get the two most-significant interleave bits from the
+	 * input address based on the following:
+	 *
+	 * [15 + np2_bits - total_intlv_bits : 14 + np2_bits - total_intlv_bits]
+	 */
+	low_bit = 14 + np2_bits - total_intlv_bits;
+	msb_intlv_bits = ctx->ret_addr >> low_bit;
+	msb_intlv_bits &= 0x3;
+
+	/*
+	 * If MSB are 11b, then logical COH_ST ID is 6 or 7.
+	 * Need to adjust based on the mod3 result.
+	 */
+	if (msb_intlv_bits == 3) {
+		u8 addr_mod, phys_addr_msb, msb_coh_st_id;
+
+		/* Get the remaining interleave bits from the input address. */
+		temp_addr_b = GENMASK_ULL(low_bit - 1, intlv_bit) & ctx->ret_addr;
+		temp_addr_b >>= intlv_bit;
+
+		/* Calculate the logical COH_ST offset based on mod3. */
+		addr_mod = temp_addr_b % 3;
+
+		/* Get COH_ST ID bits [2:1]. */
+		msb_coh_st_id = (coh_st_id >> 1) & 0x3;
+
+		/* Get the bit that starts the physical address bits. */
+		phys_addr_msb = (intlv_bit + np2_bits + 1);
+		phys_addr_msb &= BIT(0);
+		phys_addr_msb++;
+		phys_addr_msb *= 3 - addr_mod + msb_coh_st_id;
+		phys_addr_msb %= 3;
+
+		/* Move the physical address MSB to the correct place. */
+		temp_addr_b |= phys_addr_msb << (low_bit - total_intlv_bits - intlv_bit);
+
+		/* Generate a new COH_ST ID as follows: coh_st_id = [1, 1, coh_st_id[0]] */
+		coh_st_id &= BIT(0);
+		coh_st_id |= GENMASK(2, 1);
+	} else {
+		temp_addr_b = GENMASK_ULL(63, intlv_bit) & ctx->ret_addr;
+		temp_addr_b >>= intlv_bit;
+	}
+
+	temp_addr_a = GENMASK_ULL(intlv_bit - 1, 0) & ctx->ret_addr;
+	temp_addr_b <<= intlv_bit + total_intlv_bits;
+
+	ctx->ret_addr = temp_addr_a | temp_addr_b;
+	ctx->ret_addr |= coh_st_id << intlv_bit;
+	return 0;
+}
+
+static int denorm_addr_df4_np2(struct addr_ctx *ctx)
+{
+	bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G;
+	u16 group, group_offset, log_coh_st_offset;
+	unsigned int mod_value, shift_value;
+	u16 mask = df_cfg.component_id_mask;
+	u64 temp_addr_a, temp_addr_b;
+	bool hash_pa8, hashed_bit;
+
+	switch (ctx->map.intlv_mode) {
+	case DF4_NPS4_3CHAN_HASH:
+		mod_value	= 3;
+		shift_value	= 13;
+		break;
+	case DF4_NPS2_6CHAN_HASH:
+		mod_value	= 3;
+		shift_value	= 12;
+		break;
+	case DF4_NPS1_12CHAN_HASH:
+		mod_value	= 3;
+		shift_value	= 11;
+		break;
+	case DF4_NPS2_5CHAN_HASH:
+		mod_value	= 5;
+		shift_value	= 13;
+		break;
+	case DF4_NPS1_10CHAN_HASH:
+		mod_value	= 5;
+		shift_value	= 12;
+		break;
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return -EINVAL;
+	};
+
+	if (ctx->map.num_intlv_sockets == 1) {
+		hash_pa8	= BIT_ULL(shift_value) & ctx->ret_addr;
+		temp_addr_a	= remove_bits(shift_value, shift_value, ctx->ret_addr);
+	} else {
+		hash_pa8	= ctx->coh_st_fabric_id & df_cfg.socket_id_mask;
+		temp_addr_a	= ctx->ret_addr;
+	}
+
+	/* Make a gap for the real bit [8]. */
+	temp_addr_a = expand_bits(8, 1, temp_addr_a);
+
+	/* Make an additional gap for bits [13:12], as appropriate.*/
+	if (ctx->map.intlv_mode == DF4_NPS2_6CHAN_HASH ||
+	    ctx->map.intlv_mode == DF4_NPS1_10CHAN_HASH) {
+		temp_addr_a = expand_bits(13, 1, temp_addr_a);
+	} else if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH) {
+		temp_addr_a = expand_bits(12, 2, temp_addr_a);
+	}
+
+	/* Keep bits [13:0]. */
+	temp_addr_a &= GENMASK_ULL(13, 0);
+
+	/* Get the appropriate high bits. */
+	shift_value += 1 - ilog2(ctx->map.num_intlv_sockets);
+	temp_addr_b = GENMASK_ULL(63, shift_value) & ctx->ret_addr;
+	temp_addr_b >>= shift_value;
+	temp_addr_b *= mod_value;
+
+	/*
+	 * Coherent Stations are divided into groups.
+	 *
+	 * Multiples of 3 (mod3) are divided into quadrants.
+	 * e.g. NP4_3CHAN ->	[0, 1, 2] [6, 7, 8]
+	 *			[3, 4, 5] [9, 10, 11]
+	 *
+	 * Multiples of 5 (mod5) are divided into sides.
+	 * e.g. NP2_5CHAN ->	[0, 1, 2, 3, 4] [5, 6, 7, 8, 9]
+	 */
+
+	 /*
+	  * Calculate the logical offset for the COH_ST within its DRAM Address map.
+	  * e.g. if map includes [5, 6, 7, 8, 9] and target instance is '8', then
+	  *	 log_coh_st_offset = 8 - 5 = 3
+	  */
+	log_coh_st_offset = (ctx->coh_st_fabric_id & mask) - (get_dst_fabric_id(ctx) & mask);
+
+	/*
+	 * Figure out the group number.
+	 *
+	 * Following above example,
+	 * log_coh_st_offset = 3
+	 * mod_value = 5
+	 * group = 3 / 5 = 0
+	 */
+	group = log_coh_st_offset / mod_value;
+
+	/*
+	 * Figure out the offset within the group.
+	 *
+	 * Following above example,
+	 * log_coh_st_offset = 3
+	 * mod_value = 5
+	 * group_offset = 3 % 5 = 3
+	 */
+	group_offset = log_coh_st_offset % mod_value;
+
+	/* Adjust group_offset if the hashed bit [8] is set. */
+	if (hash_pa8) {
+		if (!group_offset)
+			group_offset = mod_value - 1;
+		else
+			group_offset--;
+	}
+
+	/* Add in the group offset to the high bits. */
+	temp_addr_b += group_offset;
+
+	/* Shift the high bits to the proper starting position. */
+	temp_addr_b <<= 14;
+
+	/* Combine the high and low bits together. */
+	ctx->ret_addr = temp_addr_a | temp_addr_b;
+
+	/* Account for hashing here instead of in dehash_address(). */
+	hash_ctl_64k	= FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+	hash_ctl_2M	= FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+	hash_ctl_1G	= FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl);
+
+	hashed_bit = !!hash_pa8;
+	hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr);
+	hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G;
+
+	ctx->ret_addr |= hashed_bit << 8;
+
+	/* Done for 3 and 5 channel. */
+	if (ctx->map.intlv_mode == DF4_NPS4_3CHAN_HASH ||
+	    ctx->map.intlv_mode == DF4_NPS2_5CHAN_HASH)
+		return 0;
+
+	/* Select the proper 'group' bit to use for Bit 13. */
+	if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH)
+		hashed_bit = !!(group & BIT(1));
+	else
+		hashed_bit = group & BIT(0);
+
+	hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G;
+
+	ctx->ret_addr |= hashed_bit << 13;
+
+	/* Done for 6 and 10 channel. */
+	if (ctx->map.intlv_mode != DF4_NPS1_12CHAN_HASH)
+		return 0;
+
+	hashed_bit = group & BIT(0);
+	hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k;
+	hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M;
+	hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G;
+
+	ctx->ret_addr |= hashed_bit << 12;
+	return 0;
+}
+
+int denormalize_address(struct addr_ctx *ctx)
+{
+	switch (ctx->map.intlv_mode) {
+	case NONE:
+		return 0;
+	case DF4_NPS4_3CHAN_HASH:
+	case DF4_NPS2_6CHAN_HASH:
+	case DF4_NPS1_12CHAN_HASH:
+	case DF4_NPS2_5CHAN_HASH:
+	case DF4_NPS1_10CHAN_HASH:
+		return denorm_addr_df4_np2(ctx);
+	case DF3_6CHAN:
+		return denorm_addr_df3_6chan(ctx);
+	default:
+		return denorm_addr_common(ctx);
+	}
+}
diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h
new file mode 100644
index 000000000000..5de69e0bb0f9
--- /dev/null
+++ b/drivers/ras/amd/atl/internal.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD Address Translation Library
+ *
+ * internal.h : Helper functions and common defines
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#ifndef __AMD_ATL_INTERNAL_H__
+#define __AMD_ATL_INTERNAL_H__
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/ras.h>
+
+#include <asm/amd_nb.h>
+
+#include "reg_fields.h"
+
+/* Maximum possible number of Coherent Stations within a single Data Fabric. */
+#define MAX_COH_ST_CHANNELS		32
+
+/* PCI ID for Zen4 Server DF Function 0. */
+#define DF_FUNC0_ID_ZEN4_SERVER		0x14AD1022
+
+/* PCI IDs for MI300 DF Function 0. */
+#define DF_FUNC0_ID_MI300		0x15281022
+
+/* Shift needed for adjusting register values to true values. */
+#define DF_DRAM_BASE_LIMIT_LSB		28
+#define MI300_DRAM_LIMIT_LSB		20
+
+enum df_revisions {
+	UNKNOWN,
+	DF2,
+	DF3,
+	DF3p5,
+	DF4,
+	DF4p5,
+};
+
+/* These are mapped 1:1 to the hardware values. Special cases are set at > 0x20. */
+enum intlv_modes {
+	NONE				= 0x00,
+	NOHASH_2CHAN			= 0x01,
+	NOHASH_4CHAN			= 0x03,
+	NOHASH_8CHAN			= 0x05,
+	DF3_6CHAN			= 0x06,
+	NOHASH_16CHAN			= 0x07,
+	NOHASH_32CHAN			= 0x08,
+	DF3_COD4_2CHAN_HASH		= 0x0C,
+	DF3_COD2_4CHAN_HASH		= 0x0D,
+	DF3_COD1_8CHAN_HASH		= 0x0E,
+	DF4_NPS4_2CHAN_HASH		= 0x10,
+	DF4_NPS2_4CHAN_HASH		= 0x11,
+	DF4_NPS1_8CHAN_HASH		= 0x12,
+	DF4_NPS4_3CHAN_HASH		= 0x13,
+	DF4_NPS2_6CHAN_HASH		= 0x14,
+	DF4_NPS1_12CHAN_HASH		= 0x15,
+	DF4_NPS2_5CHAN_HASH		= 0x16,
+	DF4_NPS1_10CHAN_HASH		= 0x17,
+	MI3_HASH_8CHAN			= 0x18,
+	MI3_HASH_16CHAN			= 0x19,
+	MI3_HASH_32CHAN			= 0x1A,
+	DF2_2CHAN_HASH			= 0x21,
+	/* DF4.5 modes are all IntLvNumChan + 0x20 */
+	DF4p5_NPS1_16CHAN_1K_HASH	= 0x2C,
+	DF4p5_NPS0_24CHAN_1K_HASH	= 0x2E,
+	DF4p5_NPS4_2CHAN_1K_HASH	= 0x30,
+	DF4p5_NPS2_4CHAN_1K_HASH	= 0x31,
+	DF4p5_NPS1_8CHAN_1K_HASH	= 0x32,
+	DF4p5_NPS4_3CHAN_1K_HASH	= 0x33,
+	DF4p5_NPS2_6CHAN_1K_HASH	= 0x34,
+	DF4p5_NPS1_12CHAN_1K_HASH	= 0x35,
+	DF4p5_NPS2_5CHAN_1K_HASH	= 0x36,
+	DF4p5_NPS1_10CHAN_1K_HASH	= 0x37,
+	DF4p5_NPS4_2CHAN_2K_HASH	= 0x40,
+	DF4p5_NPS2_4CHAN_2K_HASH	= 0x41,
+	DF4p5_NPS1_8CHAN_2K_HASH	= 0x42,
+	DF4p5_NPS1_16CHAN_2K_HASH	= 0x43,
+	DF4p5_NPS4_3CHAN_2K_HASH	= 0x44,
+	DF4p5_NPS2_6CHAN_2K_HASH	= 0x45,
+	DF4p5_NPS1_12CHAN_2K_HASH	= 0x46,
+	DF4p5_NPS0_24CHAN_2K_HASH	= 0x47,
+	DF4p5_NPS2_5CHAN_2K_HASH	= 0x48,
+	DF4p5_NPS1_10CHAN_2K_HASH	= 0x49,
+};
+
+struct df_flags {
+	__u8	legacy_ficaa		: 1,
+		socket_id_shift_quirk	: 1,
+		heterogeneous		: 1,
+		__reserved_0		: 5;
+};
+
+struct df_config {
+	enum df_revisions rev;
+
+	/*
+	 * These masks operate on the 16-bit Coherent Station IDs,
+	 * e.g. Instance, Fabric, Destination, etc.
+	 */
+	u16 component_id_mask;
+	u16 die_id_mask;
+	u16 node_id_mask;
+	u16 socket_id_mask;
+
+	/*
+	 * Least-significant bit of Node ID portion of the
+	 * system-wide Coherent Station Fabric ID.
+	 */
+	u8 node_id_shift;
+
+	/*
+	 * Least-significant bit of Die portion of the Node ID.
+	 * Adjusted to include the Node ID shift in order to apply
+	 * to the Coherent Station Fabric ID.
+	 */
+	u8 die_id_shift;
+
+	/*
+	 * Least-significant bit of Socket portion of the Node ID.
+	 * Adjusted to include the Node ID shift in order to apply
+	 * to the Coherent Station Fabric ID.
+	 */
+	u8 socket_id_shift;
+
+	/* Number of DRAM Address maps visible in a Coherent Station. */
+	u8 num_coh_st_maps;
+
+	/* Global flags to handle special cases. */
+	struct df_flags flags;
+};
+
+extern struct df_config df_cfg;
+
+struct dram_addr_map {
+	/*
+	 * Each DRAM Address Map can operate independently
+	 * in different interleaving modes.
+	 */
+	enum intlv_modes intlv_mode;
+
+	/* System-wide number for this address map. */
+	u8 num;
+
+	/* Raw register values */
+	u32 base;
+	u32 limit;
+	u32 ctl;
+	u32 intlv;
+
+	/*
+	 * Logical to Physical Coherent Station Remapping array
+	 *
+	 * Index: Logical Coherent Station Instance ID
+	 * Value: Physical Coherent Station Instance ID
+	 *
+	 * phys_coh_st_inst_id = remap_array[log_coh_st_inst_id]
+	 */
+	u8 remap_array[MAX_COH_ST_CHANNELS];
+
+	/*
+	 * Number of bits covering DRAM Address map 0
+	 * when interleaving is non-power-of-2.
+	 *
+	 * Used only for DF3_6CHAN.
+	 */
+	u8 np2_bits;
+
+	/* Position of the 'interleave bit'. */
+	u8 intlv_bit_pos;
+	/* Number of channels interleaved in this map. */
+	u8 num_intlv_chan;
+	/* Number of dies interleaved in this map. */
+	u8 num_intlv_dies;
+	/* Number of sockets interleaved in this map. */
+	u8 num_intlv_sockets;
+	/*
+	 * Total number of channels interleaved accounting
+	 * for die and socket interleaving.
+	 */
+	u8 total_intlv_chan;
+	/* Total bits needed to cover 'total_intlv_chan'. */
+	u8 total_intlv_bits;
+};
+
+/* Original input values cached for debug printing. */
+struct addr_ctx_inputs {
+	u64 norm_addr;
+	u8 socket_id;
+	u8 die_id;
+	u8 coh_st_inst_id;
+};
+
+struct addr_ctx {
+	u64 ret_addr;
+
+	struct addr_ctx_inputs inputs;
+	struct dram_addr_map map;
+
+	/* AMD Node ID calculated from Socket and Die IDs. */
+	u8 node_id;
+
+	/*
+	 * Coherent Station Instance ID
+	 * Local ID used within a 'node'.
+	 */
+	u16 inst_id;
+
+	/*
+	 * Coherent Station Fabric ID
+	 * System-wide ID that includes 'node' bits.
+	 */
+	u16 coh_st_fabric_id;
+};
+
+int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo);
+int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo);
+
+int get_df_system_info(void);
+int determine_node_id(struct addr_ctx *ctx, u8 socket_num, u8 die_num);
+int get_addr_hash_mi300(void);
+
+int get_address_map(struct addr_ctx *ctx);
+
+int denormalize_address(struct addr_ctx *ctx);
+int dehash_address(struct addr_ctx *ctx);
+
+unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr);
+unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err);
+
+/*
+ * Make a gap in @data that is @num_bits long starting at @bit_num.
+ * e.g. data		= 11111111'b
+ *	bit_num		= 3
+ *	num_bits	= 2
+ *	result		= 1111100111'b
+ */
+static inline u64 expand_bits(u8 bit_num, u8 num_bits, u64 data)
+{
+	u64 temp1, temp2;
+
+	if (!num_bits)
+		return data;
+
+	if (!bit_num) {
+		WARN_ON_ONCE(num_bits >= BITS_PER_LONG);
+		return data << num_bits;
+	}
+
+	WARN_ON_ONCE(bit_num >= BITS_PER_LONG);
+
+	temp1 = data & GENMASK_ULL(bit_num - 1, 0);
+
+	temp2 = data & GENMASK_ULL(63, bit_num);
+	temp2 <<= num_bits;
+
+	return temp1 | temp2;
+}
+
+/*
+ * Remove bits in @data between @low_bit and @high_bit inclusive.
+ * e.g. data		= XXXYYZZZ'b
+ *	low_bit		= 3
+ *	high_bit	= 4
+ *	result		= XXXZZZ'b
+ */
+static inline u64 remove_bits(u8 low_bit, u8 high_bit, u64 data)
+{
+	u64 temp1, temp2;
+
+	WARN_ON_ONCE(high_bit >= BITS_PER_LONG);
+	WARN_ON_ONCE(low_bit  >= BITS_PER_LONG);
+	WARN_ON_ONCE(low_bit  >  high_bit);
+
+	if (!low_bit)
+		return data >> (high_bit++);
+
+	temp1 = GENMASK_ULL(low_bit - 1, 0) & data;
+	temp2 = GENMASK_ULL(63, high_bit + 1) & data;
+	temp2 >>= high_bit - low_bit + 1;
+
+	return temp1 | temp2;
+}
+
+#define atl_debug(ctx, fmt, arg...) \
+	pr_debug("socket_id=%u die_id=%u coh_st_inst_id=%u norm_addr=0x%016llx: " fmt,\
+		 (ctx)->inputs.socket_id, (ctx)->inputs.die_id,\
+		 (ctx)->inputs.coh_st_inst_id, (ctx)->inputs.norm_addr, ##arg)
+
+static inline void atl_debug_on_bad_df_rev(void)
+{
+	pr_debug("Unrecognized DF rev: %u", df_cfg.rev);
+}
+
+static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx)
+{
+	atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode);
+}
+
+#endif /* __AMD_ATL_INTERNAL_H__ */
diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c
new file mode 100644
index 000000000000..8b908e8d7495
--- /dev/null
+++ b/drivers/ras/amd/atl/map.c
@@ -0,0 +1,682 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * map.c : Functions to read and decode DRAM address maps
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+static int df2_get_intlv_mode(struct addr_ctx *ctx)
+{
+	ctx->map.intlv_mode = FIELD_GET(DF2_INTLV_NUM_CHAN, ctx->map.base);
+
+	if (ctx->map.intlv_mode == 8)
+		ctx->map.intlv_mode = DF2_2CHAN_HASH;
+
+	if (ctx->map.intlv_mode != NONE &&
+	    ctx->map.intlv_mode != NOHASH_2CHAN &&
+	    ctx->map.intlv_mode != DF2_2CHAN_HASH)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int df3_get_intlv_mode(struct addr_ctx *ctx)
+{
+	ctx->map.intlv_mode = FIELD_GET(DF3_INTLV_NUM_CHAN, ctx->map.base);
+	return 0;
+}
+
+static int df3p5_get_intlv_mode(struct addr_ctx *ctx)
+{
+	ctx->map.intlv_mode = FIELD_GET(DF3p5_INTLV_NUM_CHAN, ctx->map.base);
+
+	if (ctx->map.intlv_mode == DF3_6CHAN)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int df4_get_intlv_mode(struct addr_ctx *ctx)
+{
+	ctx->map.intlv_mode = FIELD_GET(DF4_INTLV_NUM_CHAN, ctx->map.intlv);
+
+	if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH ||
+	    ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH ||
+	    ctx->map.intlv_mode == DF3_COD1_8CHAN_HASH ||
+	    ctx->map.intlv_mode == DF3_6CHAN)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int df4p5_get_intlv_mode(struct addr_ctx *ctx)
+{
+	ctx->map.intlv_mode = FIELD_GET(DF4p5_INTLV_NUM_CHAN, ctx->map.intlv);
+
+	if (ctx->map.intlv_mode <= NOHASH_32CHAN)
+		return 0;
+
+	if (ctx->map.intlv_mode >= MI3_HASH_8CHAN &&
+	    ctx->map.intlv_mode <= MI3_HASH_32CHAN)
+		return 0;
+
+	/*
+	 * Modes matching the ranges above are returned as-is.
+	 *
+	 * All other modes are "fixed up" by adding 20h to make a unique value.
+	 */
+	ctx->map.intlv_mode += 0x20;
+
+	return 0;
+}
+
+static int get_intlv_mode(struct addr_ctx *ctx)
+{
+	int ret;
+
+	switch (df_cfg.rev) {
+	case DF2:
+		ret = df2_get_intlv_mode(ctx);
+		break;
+	case DF3:
+		ret = df3_get_intlv_mode(ctx);
+		break;
+	case DF3p5:
+		ret = df3p5_get_intlv_mode(ctx);
+		break;
+	case DF4:
+		ret = df4_get_intlv_mode(ctx);
+		break;
+	case DF4p5:
+		ret = df4p5_get_intlv_mode(ctx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		atl_debug_on_bad_df_rev();
+
+	return ret;
+}
+
+static u64 get_hi_addr_offset(u32 reg_dram_offset)
+{
+	u8 shift = DF_DRAM_BASE_LIMIT_LSB;
+	u64 hi_addr_offset;
+
+	switch (df_cfg.rev) {
+	case DF2:
+		hi_addr_offset = FIELD_GET(DF2_HI_ADDR_OFFSET, reg_dram_offset);
+		break;
+	case DF3:
+	case DF3p5:
+		hi_addr_offset = FIELD_GET(DF3_HI_ADDR_OFFSET, reg_dram_offset);
+		break;
+	case DF4:
+	case DF4p5:
+		hi_addr_offset = FIELD_GET(DF4_HI_ADDR_OFFSET, reg_dram_offset);
+		break;
+	default:
+		hi_addr_offset = 0;
+		atl_debug_on_bad_df_rev();
+	}
+
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		shift = MI300_DRAM_LIMIT_LSB;
+
+	return hi_addr_offset << shift;
+}
+
+/*
+ * Returns:	0 if offset is disabled.
+ *		1 if offset is enabled.
+ *		-EINVAL on error.
+ */
+static int get_dram_offset(struct addr_ctx *ctx, u64 *norm_offset)
+{
+	u32 reg_dram_offset;
+	u8 map_num;
+
+	/* Should not be called for map 0. */
+	if (!ctx->map.num) {
+		atl_debug(ctx, "Trying to find DRAM offset for map 0");
+		return -EINVAL;
+	}
+
+	/*
+	 * DramOffset registers don't exist for map 0, so the base register
+	 * actually refers to map 1.
+	 * Adjust the map_num for the register offsets.
+	 */
+	map_num = ctx->map.num - 1;
+
+	if (df_cfg.rev >= DF4) {
+		/* Read D18F7x140 (DramOffset) */
+		if (df_indirect_read_instance(ctx->node_id, 7, 0x140 + (4 * map_num),
+					      ctx->inst_id, &reg_dram_offset))
+			return -EINVAL;
+
+	} else {
+		/* Read D18F0x1B4 (DramOffset) */
+		if (df_indirect_read_instance(ctx->node_id, 0, 0x1B4 + (4 * map_num),
+					      ctx->inst_id, &reg_dram_offset))
+			return -EINVAL;
+	}
+
+	if (!FIELD_GET(DF_HI_ADDR_OFFSET_EN, reg_dram_offset))
+		return 0;
+
+	*norm_offset = get_hi_addr_offset(reg_dram_offset);
+
+	return 1;
+}
+
+static int df3_6ch_get_dram_addr_map(struct addr_ctx *ctx)
+{
+	u16 dst_fabric_id = FIELD_GET(DF3_DST_FABRIC_ID, ctx->map.limit);
+	u8 i, j, shift = 4, mask = 0xF;
+	u32 reg, offset = 0x60;
+	u16 dst_node_id;
+
+	/* Get Socket 1 register. */
+	if (dst_fabric_id & df_cfg.socket_id_mask)
+		offset = 0x68;
+
+	/* Read D18F0x06{0,8} (DF::Skt0CsTargetRemap0)/(DF::Skt0CsTargetRemap1) */
+	if (df_indirect_read_broadcast(ctx->node_id, 0, offset, &reg))
+		return -EINVAL;
+
+	/* Save 8 remap entries. */
+	for (i = 0, j = 0; i < 8; i++, j++)
+		ctx->map.remap_array[i] = (reg >> (j * shift)) & mask;
+
+	dst_node_id = dst_fabric_id & df_cfg.node_id_mask;
+	dst_node_id >>= df_cfg.node_id_shift;
+
+	/* Read D18F2x090 (DF::Np2ChannelConfig) */
+	if (df_indirect_read_broadcast(dst_node_id, 2, 0x90, &reg))
+		return -EINVAL;
+
+	ctx->map.np2_bits = FIELD_GET(DF_LOG2_ADDR_64K_SPACE0, reg);
+	return 0;
+}
+
+static int df2_get_dram_addr_map(struct addr_ctx *ctx)
+{
+	/* Read D18F0x110 (DramBaseAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 0, 0x110 + (8 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.base))
+		return -EINVAL;
+
+	/* Read D18F0x114 (DramLimitAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 0, 0x114 + (8 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.limit))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int df3_get_dram_addr_map(struct addr_ctx *ctx)
+{
+	if (df2_get_dram_addr_map(ctx))
+		return -EINVAL;
+
+	/* Read D18F0x3F8 (DfGlobalCtl). */
+	if (df_indirect_read_instance(ctx->node_id, 0, 0x3F8,
+				      ctx->inst_id, &ctx->map.ctl))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int df4_get_dram_addr_map(struct addr_ctx *ctx)
+{
+	u8 remap_sel, i, j, shift = 4, mask = 0xF;
+	u32 remap_reg;
+
+	/* Read D18F7xE00 (DramBaseAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0xE00 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.base))
+		return -EINVAL;
+
+	/* Read D18F7xE04 (DramLimitAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0xE04 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.limit))
+		return -EINVAL;
+
+	/* Read D18F7xE08 (DramAddressCtl). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0xE08 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.ctl))
+		return -EINVAL;
+
+	/* Read D18F7xE0C (DramAddressIntlv). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0xE0C + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.intlv))
+		return -EINVAL;
+
+	/* Check if Remap Enable bit is valid. */
+	if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl))
+		return 0;
+
+	/* Fill with bogus values, because '0' is a valid value. */
+	memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array));
+
+	/* Get Remap registers. */
+	remap_sel = FIELD_GET(DF4_REMAP_SEL, ctx->map.ctl);
+
+	/* Read D18F7x180 (CsTargetRemap0A). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (8 * remap_sel),
+				      ctx->inst_id, &remap_reg))
+		return -EINVAL;
+
+	/* Save first 8 remap entries. */
+	for (i = 0, j = 0; i < 8; i++, j++)
+		ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask;
+
+	/* Read D18F7x184 (CsTargetRemap0B). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (8 * remap_sel),
+				      ctx->inst_id, &remap_reg))
+		return -EINVAL;
+
+	/* Save next 8 remap entries. */
+	for (i = 8, j = 0; i < 16; i++, j++)
+		ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask;
+
+	return 0;
+}
+
+static int df4p5_get_dram_addr_map(struct addr_ctx *ctx)
+{
+	u8 remap_sel, i, j, shift = 5, mask = 0x1F;
+	u32 remap_reg;
+
+	/* Read D18F7x200 (DramBaseAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x200 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.base))
+		return -EINVAL;
+
+	/* Read D18F7x204 (DramLimitAddress). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x204 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.limit))
+		return -EINVAL;
+
+	/* Read D18F7x208 (DramAddressCtl). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x208 + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.ctl))
+		return -EINVAL;
+
+	/* Read D18F7x20C (DramAddressIntlv). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x20C + (16 * ctx->map.num),
+				      ctx->inst_id, &ctx->map.intlv))
+		return -EINVAL;
+
+	/* Check if Remap Enable bit is valid. */
+	if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl))
+		return 0;
+
+	/* Fill with bogus values, because '0' is a valid value. */
+	memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array));
+
+	/* Get Remap registers. */
+	remap_sel = FIELD_GET(DF4p5_REMAP_SEL, ctx->map.ctl);
+
+	/* Read D18F7x180 (CsTargetRemap0A). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (24 * remap_sel),
+				      ctx->inst_id, &remap_reg))
+		return -EINVAL;
+
+	/* Save first 6 remap entries. */
+	for (i = 0, j = 0; i < 6; i++, j++)
+		ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask;
+
+	/* Read D18F7x184 (CsTargetRemap0B). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (24 * remap_sel),
+				      ctx->inst_id, &remap_reg))
+		return -EINVAL;
+
+	/* Save next 6 remap entries. */
+	for (i = 6, j = 0; i < 12; i++, j++)
+		ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask;
+
+	/* Read D18F7x188 (CsTargetRemap0C). */
+	if (df_indirect_read_instance(ctx->node_id, 7, 0x188 + (24 * remap_sel),
+				      ctx->inst_id, &remap_reg))
+		return -EINVAL;
+
+	/* Save next 6 remap entries. */
+	for (i = 12, j = 0; i < 18; i++, j++)
+		ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask;
+
+	return 0;
+}
+
+static int get_dram_addr_map(struct addr_ctx *ctx)
+{
+	switch (df_cfg.rev) {
+	case DF2:	return df2_get_dram_addr_map(ctx);
+	case DF3:
+	case DF3p5:	return df3_get_dram_addr_map(ctx);
+	case DF4:	return df4_get_dram_addr_map(ctx);
+	case DF4p5:	return df4p5_get_dram_addr_map(ctx);
+	default:
+			atl_debug_on_bad_df_rev();
+			return -EINVAL;
+	}
+}
+
+static int get_coh_st_fabric_id(struct addr_ctx *ctx)
+{
+	u32 reg;
+
+	/*
+	 * On MI300 systems, the Coherent Station Fabric ID is derived
+	 * later. And it does not depend on the register value.
+	 */
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return 0;
+
+	/* Read D18F0x50 (FabricBlockInstanceInformation3). */
+	if (df_indirect_read_instance(ctx->node_id, 0, 0x50, ctx->inst_id, &reg))
+		return -EINVAL;
+
+	if (df_cfg.rev < DF4p5)
+		ctx->coh_st_fabric_id = FIELD_GET(DF2_COH_ST_FABRIC_ID, reg);
+	else
+		ctx->coh_st_fabric_id = FIELD_GET(DF4p5_COH_ST_FABRIC_ID, reg);
+
+	return 0;
+}
+
+static int find_normalized_offset(struct addr_ctx *ctx, u64 *norm_offset)
+{
+	u64 last_offset = 0;
+	int ret;
+
+	for (ctx->map.num = 1; ctx->map.num < df_cfg.num_coh_st_maps; ctx->map.num++) {
+		ret = get_dram_offset(ctx, norm_offset);
+		if (ret < 0)
+			return ret;
+
+		/* Continue search if this map's offset is not enabled. */
+		if (!ret)
+			continue;
+
+		/* Enabled offsets should never be 0. */
+		if (*norm_offset == 0) {
+			atl_debug(ctx, "Enabled map %u offset is 0", ctx->map.num);
+			return -EINVAL;
+		}
+
+		/* Offsets should always increase from one map to the next. */
+		if (*norm_offset <= last_offset) {
+			atl_debug(ctx, "Map %u offset (0x%016llx) <= previous (0x%016llx)",
+				  ctx->map.num, *norm_offset, last_offset);
+			return -EINVAL;
+		}
+
+		/* Match if this map's offset is less than the current calculated address. */
+		if (ctx->ret_addr >= *norm_offset)
+			break;
+
+		last_offset = *norm_offset;
+	}
+
+	/*
+	 * Finished search without finding a match.
+	 * Reset to map 0 and no offset.
+	 */
+	if (ctx->map.num >= df_cfg.num_coh_st_maps) {
+		ctx->map.num = 0;
+		*norm_offset = 0;
+	}
+
+	return 0;
+}
+
+static bool valid_map(struct addr_ctx *ctx)
+{
+	if (df_cfg.rev >= DF4)
+		return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.ctl);
+	else
+		return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.base);
+}
+
+static int get_address_map_common(struct addr_ctx *ctx)
+{
+	u64 norm_offset = 0;
+
+	if (get_coh_st_fabric_id(ctx))
+		return -EINVAL;
+
+	if (find_normalized_offset(ctx, &norm_offset))
+		return -EINVAL;
+
+	if (get_dram_addr_map(ctx))
+		return -EINVAL;
+
+	if (!valid_map(ctx))
+		return -EINVAL;
+
+	ctx->ret_addr -= norm_offset;
+
+	return 0;
+}
+
+static u8 get_num_intlv_chan(struct addr_ctx *ctx)
+{
+	switch (ctx->map.intlv_mode) {
+	case NONE:
+		return 1;
+	case NOHASH_2CHAN:
+	case DF2_2CHAN_HASH:
+	case DF3_COD4_2CHAN_HASH:
+	case DF4_NPS4_2CHAN_HASH:
+	case DF4p5_NPS4_2CHAN_1K_HASH:
+	case DF4p5_NPS4_2CHAN_2K_HASH:
+		return 2;
+	case DF4_NPS4_3CHAN_HASH:
+	case DF4p5_NPS4_3CHAN_1K_HASH:
+	case DF4p5_NPS4_3CHAN_2K_HASH:
+		return 3;
+	case NOHASH_4CHAN:
+	case DF3_COD2_4CHAN_HASH:
+	case DF4_NPS2_4CHAN_HASH:
+	case DF4p5_NPS2_4CHAN_1K_HASH:
+	case DF4p5_NPS2_4CHAN_2K_HASH:
+		return 4;
+	case DF4_NPS2_5CHAN_HASH:
+	case DF4p5_NPS2_5CHAN_1K_HASH:
+	case DF4p5_NPS2_5CHAN_2K_HASH:
+		return 5;
+	case DF3_6CHAN:
+	case DF4_NPS2_6CHAN_HASH:
+	case DF4p5_NPS2_6CHAN_1K_HASH:
+	case DF4p5_NPS2_6CHAN_2K_HASH:
+		return 6;
+	case NOHASH_8CHAN:
+	case DF3_COD1_8CHAN_HASH:
+	case DF4_NPS1_8CHAN_HASH:
+	case MI3_HASH_8CHAN:
+	case DF4p5_NPS1_8CHAN_1K_HASH:
+	case DF4p5_NPS1_8CHAN_2K_HASH:
+		return 8;
+	case DF4_NPS1_10CHAN_HASH:
+	case DF4p5_NPS1_10CHAN_1K_HASH:
+	case DF4p5_NPS1_10CHAN_2K_HASH:
+		return 10;
+	case DF4_NPS1_12CHAN_HASH:
+	case DF4p5_NPS1_12CHAN_1K_HASH:
+	case DF4p5_NPS1_12CHAN_2K_HASH:
+		return 12;
+	case NOHASH_16CHAN:
+	case MI3_HASH_16CHAN:
+	case DF4p5_NPS1_16CHAN_1K_HASH:
+	case DF4p5_NPS1_16CHAN_2K_HASH:
+		return 16;
+	case DF4p5_NPS0_24CHAN_1K_HASH:
+	case DF4p5_NPS0_24CHAN_2K_HASH:
+		return 24;
+	case NOHASH_32CHAN:
+	case MI3_HASH_32CHAN:
+		return 32;
+	default:
+		atl_debug_on_bad_intlv_mode(ctx);
+		return 0;
+	}
+}
+
+static void calculate_intlv_bits(struct addr_ctx *ctx)
+{
+	ctx->map.num_intlv_chan = get_num_intlv_chan(ctx);
+
+	ctx->map.total_intlv_chan = ctx->map.num_intlv_chan;
+	ctx->map.total_intlv_chan *= ctx->map.num_intlv_dies;
+	ctx->map.total_intlv_chan *= ctx->map.num_intlv_sockets;
+
+	/*
+	 * Get the number of bits needed to cover this many channels.
+	 * order_base_2() rounds up automatically.
+	 */
+	ctx->map.total_intlv_bits = order_base_2(ctx->map.total_intlv_chan);
+}
+
+static u8 get_intlv_bit_pos(struct addr_ctx *ctx)
+{
+	u8 addr_sel = 0;
+
+	switch (df_cfg.rev) {
+	case DF2:
+		addr_sel = FIELD_GET(DF2_INTLV_ADDR_SEL, ctx->map.base);
+		break;
+	case DF3:
+	case DF3p5:
+		addr_sel = FIELD_GET(DF3_INTLV_ADDR_SEL, ctx->map.base);
+		break;
+	case DF4:
+	case DF4p5:
+		addr_sel = FIELD_GET(DF4_INTLV_ADDR_SEL, ctx->map.intlv);
+		break;
+	default:
+		atl_debug_on_bad_df_rev();
+		break;
+	}
+
+	/* Add '8' to get the 'interleave bit position'. */
+	return addr_sel + 8;
+}
+
+static u8 get_num_intlv_dies(struct addr_ctx *ctx)
+{
+	u8 dies = 0;
+
+	switch (df_cfg.rev) {
+	case DF2:
+		dies = FIELD_GET(DF2_INTLV_NUM_DIES, ctx->map.limit);
+		break;
+	case DF3:
+		dies = FIELD_GET(DF3_INTLV_NUM_DIES, ctx->map.base);
+		break;
+	case DF3p5:
+		dies = FIELD_GET(DF3p5_INTLV_NUM_DIES, ctx->map.base);
+		break;
+	case DF4:
+	case DF4p5:
+		dies = FIELD_GET(DF4_INTLV_NUM_DIES, ctx->map.intlv);
+		break;
+	default:
+		atl_debug_on_bad_df_rev();
+		break;
+	}
+
+	/* Register value is log2, e.g. 0 -> 1 die, 1 -> 2 dies, etc. */
+	return 1 << dies;
+}
+
+static u8 get_num_intlv_sockets(struct addr_ctx *ctx)
+{
+	u8 sockets = 0;
+
+	switch (df_cfg.rev) {
+	case DF2:
+		sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.limit);
+		break;
+	case DF3:
+	case DF3p5:
+		sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.base);
+		break;
+	case DF4:
+	case DF4p5:
+		sockets = FIELD_GET(DF4_INTLV_NUM_SOCKETS, ctx->map.intlv);
+		break;
+	default:
+		atl_debug_on_bad_df_rev();
+		break;
+	}
+
+	/* Register value is log2, e.g. 0 -> 1 sockets, 1 -> 2 sockets, etc. */
+	return 1 << sockets;
+}
+
+static int get_global_map_data(struct addr_ctx *ctx)
+{
+	if (get_intlv_mode(ctx))
+		return -EINVAL;
+
+	if (ctx->map.intlv_mode == DF3_6CHAN &&
+	    df3_6ch_get_dram_addr_map(ctx))
+		return -EINVAL;
+
+	ctx->map.intlv_bit_pos		= get_intlv_bit_pos(ctx);
+	ctx->map.num_intlv_dies		= get_num_intlv_dies(ctx);
+	ctx->map.num_intlv_sockets	= get_num_intlv_sockets(ctx);
+	calculate_intlv_bits(ctx);
+
+	return 0;
+}
+
+static void dump_address_map(struct dram_addr_map *map)
+{
+	u8 i;
+
+	pr_debug("intlv_mode=0x%x",		map->intlv_mode);
+	pr_debug("num=0x%x",			map->num);
+	pr_debug("base=0x%x",			map->base);
+	pr_debug("limit=0x%x",			map->limit);
+	pr_debug("ctl=0x%x",			map->ctl);
+	pr_debug("intlv=0x%x",			map->intlv);
+
+	for (i = 0; i < MAX_COH_ST_CHANNELS; i++)
+		pr_debug("remap_array[%u]=0x%x", i, map->remap_array[i]);
+
+	pr_debug("intlv_bit_pos=%u",		map->intlv_bit_pos);
+	pr_debug("num_intlv_chan=%u",		map->num_intlv_chan);
+	pr_debug("num_intlv_dies=%u",		map->num_intlv_dies);
+	pr_debug("num_intlv_sockets=%u",	map->num_intlv_sockets);
+	pr_debug("total_intlv_chan=%u",		map->total_intlv_chan);
+	pr_debug("total_intlv_bits=%u",		map->total_intlv_bits);
+}
+
+int get_address_map(struct addr_ctx *ctx)
+{
+	int ret;
+
+	ret = get_address_map_common(ctx);
+	if (ret)
+		return ret;
+
+	ret = get_global_map_data(ctx);
+	if (ret)
+		return ret;
+
+	dump_address_map(&ctx->map);
+
+	return ret;
+}
diff --git a/drivers/ras/amd/atl/reg_fields.h b/drivers/ras/amd/atl/reg_fields.h
new file mode 100644
index 000000000000..9dcdf6e4a856
--- /dev/null
+++ b/drivers/ras/amd/atl/reg_fields.h
@@ -0,0 +1,606 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD Address Translation Library
+ *
+ * reg_fields.h : Register field definitions
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+/*
+ * Notes on naming:
+ * 1) Use "DF_" prefix for fields that are the same for all revisions.
+ * 2) Use "DFx_" prefix for fields that differ between revisions.
+ *	a) "x" is the first major revision where the new field appears.
+ *	b) E.g., if DF2 and DF3 have the same field, then call it DF2.
+ *	c) E.g., if DF3p5 and DF4 have the same field, then call it DF4.
+ */
+
+/*
+ * Coherent Station Fabric ID
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x50 [Fabric Block Instance Information 3]
+ *	DF2	BlockFabricId	[19:8]
+ *	DF3	BlockFabricId	[19:8]
+ *	DF3p5	BlockFabricId	[19:8]
+ *	DF4	BlockFabricId	[19:8]
+ *	DF4p5	BlockFabricId	[15:8]
+ */
+#define DF2_COH_ST_FABRIC_ID	GENMASK(19, 8)
+#define DF4p5_COH_ST_FABRIC_ID	GENMASK(15, 8)
+
+/*
+ * Component ID Mask
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *
+ *	D18F1x208 [System Fabric ID Mask 0]
+ *	DF3	ComponentIdMask	[9:0]
+ *
+ *	D18F1x150 [System Fabric ID Mask 0]
+ *	DF3p5	ComponentIdMask	[15:0]
+ *
+ *	D18F4x1B0 [System Fabric ID Mask 0]
+ *	DF4	ComponentIdMask	[15:0]
+ *	DF4p5	ComponentIdMask	[15:0]
+ */
+#define DF3_COMPONENT_ID_MASK	GENMASK(9, 0)
+#define DF4_COMPONENT_ID_MASK	GENMASK(15, 0)
+
+/*
+ * Destination Fabric ID
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x114 [DRAM Limit Address]
+ *	DF2	DstFabricID	[7:0]
+ *	DF3	DstFabricID	[9:0]
+ *	DF3	DstFabricID	[11:0]
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	DstFabricID	[27:16]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	DstFabricID	[23:16]
+ */
+#define DF2_DST_FABRIC_ID	GENMASK(7, 0)
+#define DF3_DST_FABRIC_ID	GENMASK(9, 0)
+#define DF3p5_DST_FABRIC_ID	GENMASK(11, 0)
+#define DF4_DST_FABRIC_ID	GENMASK(27, 16)
+#define DF4p5_DST_FABRIC_ID	GENMASK(23, 16)
+
+/*
+ * Die ID Mask
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F1x208 [System Fabric ID Mask]
+ *	DF2	DieIdMask	[15:8]
+ *
+ *	D18F1x20C [System Fabric ID Mask 1]
+ *	DF3	DieIdMask	[18:16]
+ *
+ *	D18F1x158 [System Fabric ID Mask 2]
+ *	DF3p5	DieIdMask	[15:0]
+ *
+ *	D18F4x1B8 [System Fabric ID Mask 2]
+ *	DF4	DieIdMask	[15:0]
+ *	DF4p5	DieIdMask	[15:0]
+ */
+#define DF2_DIE_ID_MASK		GENMASK(15, 8)
+#define DF3_DIE_ID_MASK		GENMASK(18, 16)
+#define DF4_DIE_ID_MASK		GENMASK(15, 0)
+
+/*
+ * Die ID Shift
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F1x208 [System Fabric ID Mask]
+ *	DF2	DieIdShift	[27:24]
+ *
+ *	DF3	N/A
+ *	DF3p5	N/A
+ *	DF4	N/A
+ *	DF4p5	N/A
+ */
+#define DF2_DIE_ID_SHIFT	GENMASK(27, 24)
+
+/*
+ * DRAM Address Range Valid
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF2	AddrRngVal	[0]
+ *	DF3	AddrRngVal	[0]
+ *	DF3p5	AddrRngVal	[0]
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	AddrRngVal	[0]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	AddrRngVal	[0]
+ */
+#define DF_ADDR_RANGE_VAL	BIT(0)
+
+/*
+ * DRAM Base Address
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF2	DramBaseAddr	[31:12]
+ *	DF3	DramBaseAddr	[31:12]
+ *	DF3p5	DramBaseAddr	[31:12]
+ *
+ *	D18F7xE00 [DRAM Base Address]
+ *	DF4	DramBaseAddr	[27:0]
+ *
+ *	D18F7x200 [DRAM Base Address]
+ *	DF4p5	DramBaseAddr	[27:0]
+ */
+#define DF2_BASE_ADDR		GENMASK(31, 12)
+#define DF4_BASE_ADDR		GENMASK(27, 0)
+
+/*
+ * DRAM Hole Base
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x104 [DRAM Hole Control]
+ *	DF2	DramHoleBase	[31:24]
+ *	DF3	DramHoleBase	[31:24]
+ *	DF3p5	DramHoleBase	[31:24]
+ *
+ *	D18F7x104 [DRAM Hole Control]
+ *	DF4	DramHoleBase	[31:24]
+ *	DF4p5	DramHoleBase	[31:24]
+ */
+#define DF_DRAM_HOLE_BASE_MASK	GENMASK(31, 24)
+
+/*
+ * DRAM Limit Address
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x114 [DRAM Limit Address]
+ *	DF2	DramLimitAddr	[31:12]
+ *	DF3	DramLimitAddr	[31:12]
+ *	DF3p5	DramLimitAddr	[31:12]
+ *
+ *	D18F7xE04 [DRAM Limit Address]
+ *	DF4	DramLimitAddr	[27:0]
+ *
+ *	D18F7x204 [DRAM Limit Address]
+ *	DF4p5	DramLimitAddr	[27:0]
+ */
+#define DF2_DRAM_LIMIT_ADDR	GENMASK(31, 12)
+#define DF4_DRAM_LIMIT_ADDR	GENMASK(27, 0)
+
+/*
+ * Hash Interleave Controls
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *
+ *	D18F0x3F8 [DF Global Control]
+ *	DF3	GlbHashIntlvCtl64K	[20]
+ *		GlbHashIntlvCtl2M	[21]
+ *		GlbHashIntlvCtl1G	[22]
+ *
+ *	DF3p5	GlbHashIntlvCtl64K	[20]
+ *		GlbHashIntlvCtl2M	[21]
+ *		GlbHashIntlvCtl1G	[22]
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	HashIntlvCtl64K		[8]
+ *		HashIntlvCtl2M		[9]
+ *		HashIntlvCtl1G		[10]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	HashIntlvCtl4K		[7]
+ *		HashIntlvCtl64K		[8]
+ *		HashIntlvCtl2M		[9]
+ *		HashIntlvCtl1G		[10]
+ *		HashIntlvCtl1T		[15]
+ */
+#define DF3_HASH_CTL_64K		BIT(20)
+#define DF3_HASH_CTL_2M			BIT(21)
+#define DF3_HASH_CTL_1G			BIT(22)
+#define DF4_HASH_CTL_64K		BIT(8)
+#define DF4_HASH_CTL_2M			BIT(9)
+#define DF4_HASH_CTL_1G			BIT(10)
+#define DF4p5_HASH_CTL_4K		BIT(7)
+#define DF4p5_HASH_CTL_1T		BIT(15)
+
+/*
+ * High Address Offset
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x1B4 [DRAM Offset]
+ *	DF2	HiAddrOffset	[31:20]
+ *	DF3	HiAddrOffset	[31:12]
+ *	DF3p5	HiAddrOffset	[31:12]
+ *
+ *	D18F7x140 [DRAM Offset]
+ *	DF4	HiAddrOffset	[24:1]
+ *	DF4p5	HiAddrOffset	[24:1]
+ *	MI300	HiAddrOffset	[31:1]
+ */
+#define DF2_HI_ADDR_OFFSET	GENMASK(31, 20)
+#define DF3_HI_ADDR_OFFSET	GENMASK(31, 12)
+
+/* Follow reference code by including reserved bits for simplicity. */
+#define DF4_HI_ADDR_OFFSET	GENMASK(31, 1)
+
+/*
+ * High Address Offset Enable
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x1B4 [DRAM Offset]
+ *	DF2	HiAddrOffsetEn	[0]
+ *	DF3	HiAddrOffsetEn	[0]
+ *	DF3p5	HiAddrOffsetEn	[0]
+ *
+ *	D18F7x140 [DRAM Offset]
+ *	DF4	HiAddrOffsetEn	[0]
+ *	DF4p5	HiAddrOffsetEn	[0]
+ */
+#define DF_HI_ADDR_OFFSET_EN	BIT(0)
+
+/*
+ * Interleave Address Select
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF2	IntLvAddrSel	[10:8]
+ *	DF3	IntLvAddrSel	[11:9]
+ *	DF3p5	IntLvAddrSel	[11:9]
+ *
+ *	D18F7xE0C [DRAM Address Interleave]
+ *	DF4	IntLvAddrSel	[2:0]
+ *
+ *	D18F7x20C [DRAM Address Interleave]
+ *	DF4p5	IntLvAddrSel	[2:0]
+ */
+#define DF2_INTLV_ADDR_SEL	GENMASK(10, 8)
+#define DF3_INTLV_ADDR_SEL	GENMASK(11, 9)
+#define DF4_INTLV_ADDR_SEL	GENMASK(2, 0)
+
+/*
+ * Interleave Number of Channels
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF2	IntLvNumChan	[7:4]
+ *	DF3	IntLvNumChan	[5:2]
+ *	DF3p5	IntLvNumChan	[6:2]
+ *
+ *	D18F7xE0C [DRAM Address Interleave]
+ *	DF4	IntLvNumChan	[8:4]
+ *
+ *	D18F7x20C [DRAM Address Interleave]
+ *	DF4p5	IntLvNumChan	[9:4]
+ */
+#define DF2_INTLV_NUM_CHAN	GENMASK(7, 4)
+#define DF3_INTLV_NUM_CHAN	GENMASK(5, 2)
+#define DF3p5_INTLV_NUM_CHAN	GENMASK(6, 2)
+#define DF4_INTLV_NUM_CHAN	GENMASK(8, 4)
+#define DF4p5_INTLV_NUM_CHAN	GENMASK(9, 4)
+
+/*
+ * Interleave Number of Dies
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x114 [DRAM Limit Address]
+ *	DF2	IntLvNumDies	[11:10]
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF3	IntLvNumDies	[7:6]
+ *	DF3p5	IntLvNumDies	[7]
+ *
+ *	D18F7xE0C [DRAM Address Interleave]
+ *	DF4	IntLvNumDies	[13:12]
+ *
+ *	D18F7x20C [DRAM Address Interleave]
+ *	DF4p5	IntLvNumDies	[13:12]
+ */
+#define DF2_INTLV_NUM_DIES	GENMASK(11, 10)
+#define DF3_INTLV_NUM_DIES	GENMASK(7, 6)
+#define DF3p5_INTLV_NUM_DIES	BIT(7)
+#define DF4_INTLV_NUM_DIES	GENMASK(13, 12)
+
+/*
+ * Interleave Number of Sockets
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x114 [DRAM Limit Address]
+ *	DF2	IntLvNumSockets	[8]
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF3	IntLvNumSockets	[8]
+ *	DF3p5	IntLvNumSockets	[8]
+ *
+ *	D18F7xE0C [DRAM Address Interleave]
+ *	DF4	IntLvNumSockets	[18]
+ *
+ *	D18F7x20C [DRAM Address Interleave]
+ *	DF4p5	IntLvNumSockets	[18]
+ */
+#define DF2_INTLV_NUM_SOCKETS	BIT(8)
+#define DF4_INTLV_NUM_SOCKETS	BIT(18)
+
+/*
+ * Legacy MMIO Hole Enable
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	D18F0x110 [DRAM Base Address]
+ *	DF2	LgcyMmioHoleEn	[1]
+ *	DF3	LgcyMmioHoleEn	[1]
+ *	DF3p5	LgcyMmioHoleEn	[1]
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	LgcyMmioHoleEn	[1]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	LgcyMmioHoleEn	[1]
+ */
+#define DF_LEGACY_MMIO_HOLE_EN	BIT(1)
+
+/*
+ * Log2 Address 64K Space 0
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname		Bits
+ *
+ *	DF2	N/A
+ *
+ *	D18F2x90 [Non-power-of-2 channel Configuration Register for COH_ST DRAM Address Maps]
+ *	DF3	Log2Addr64KSpace0	[5:0]
+ *
+ *	DF3p5	N/A
+ *	DF4	N/A
+ *	DF4p5	N/A
+ */
+#define DF_LOG2_ADDR_64K_SPACE0		GENMASK(5, 0)
+
+/*
+ * Major Revision
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *	DF3	N/A
+ *	DF3p5	N/A
+ *
+ *	D18F0x040 [Fabric Block Instance Count]
+ *	DF4	MajorRevision	[27:24]
+ *	DF4p5	MajorRevision	[27:24]
+ */
+#define DF_MAJOR_REVISION	GENMASK(27, 24)
+
+/*
+ * Minor Revision
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *	DF3	N/A
+ *	DF3p5	N/A
+ *
+ *	D18F0x040 [Fabric Block Instance Count]
+ *	DF4	MinorRevision	[23:16]
+ *	DF4p5	MinorRevision	[23:16]
+ */
+#define DF_MINOR_REVISION	GENMASK(23, 16)
+
+/*
+ * Node ID Mask
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *
+ *	D18F1x208 [System Fabric ID Mask 0]
+ *	DF3	NodeIdMask	[25:16]
+ *
+ *	D18F1x150 [System Fabric ID Mask 0]
+ *	DF3p5	NodeIdMask	[31:16]
+ *
+ *	D18F4x1B0 [System Fabric ID Mask 0]
+ *	DF4	NodeIdMask	[31:16]
+ *	DF4p5	NodeIdMask	[31:16]
+ */
+#define DF3_NODE_ID_MASK	GENMASK(25, 16)
+#define DF4_NODE_ID_MASK	GENMASK(31, 16)
+
+/*
+ * Node ID Shift
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *
+ *	D18F1x20C [System Fabric ID Mask 1]
+ *	DF3	NodeIdShift	[3:0]
+ *
+ *	D18F1x154 [System Fabric ID Mask 1]
+ *	DF3p5	NodeIdShift	[3:0]
+ *
+ *	D18F4x1B4 [System Fabric ID Mask 1]
+ *	DF4	NodeIdShift	[3:0]
+ *	DF4p5	NodeIdShift	[3:0]
+ */
+#define DF3_NODE_ID_SHIFT	GENMASK(3, 0)
+
+/*
+ * Remap Enable
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *	DF3	N/A
+ *	DF3p5	N/A
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	RemapEn		[4]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	RemapEn		[4]
+ */
+#define DF4_REMAP_EN		BIT(4)
+
+/*
+ * Remap Select
+ *
+ * Access type: Instance
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ *	DF2	N/A
+ *	DF3	N/A
+ *	DF3p5	N/A
+ *
+ *	D18F7xE08 [DRAM Address Control]
+ *	DF4	RemapSel	[7:5]
+ *
+ *	D18F7x208 [DRAM Address Control]
+ *	DF4p5	RemapSel	[6:5]
+ */
+#define DF4_REMAP_SEL		GENMASK(7, 5)
+#define DF4p5_REMAP_SEL		GENMASK(6, 5)
+
+/*
+ * Socket ID Mask
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *	Rev	Fieldname	Bits
+ *
+ * D18F1x208 [System Fabric ID Mask]
+ *	DF2	SocketIdMask	[23:16]
+ *
+ * D18F1x20C [System Fabric ID Mask 1]
+ *	DF3	SocketIdMask	[26:24]
+ *
+ * D18F1x158 [System Fabric ID Mask 2]
+ *	DF3p5	SocketIdMask	[31:16]
+ *
+ * D18F4x1B8 [System Fabric ID Mask 2]
+ *	DF4	SocketIdMask	[31:16]
+ *	DF4p5	SocketIdMask	[31:16]
+ */
+#define DF2_SOCKET_ID_MASK	GENMASK(23, 16)
+#define DF3_SOCKET_ID_MASK	GENMASK(26, 24)
+#define DF4_SOCKET_ID_MASK	GENMASK(31, 16)
+
+/*
+ * Socket ID Shift
+ *
+ * Access type: Broadcast
+ *
+ * Register
+ *		Rev	Fieldname	Bits
+ *
+ * D18F1x208 [System Fabric ID Mask]
+ *	DF2	SocketIdShift	[31:28]
+ *
+ * D18F1x20C [System Fabric ID Mask 1]
+ *	DF3	SocketIdShift	[9:8]
+ *
+ * D18F1x158 [System Fabric ID Mask 2]
+ *	DF3p5	SocketIdShift	[11:8]
+ *
+ * D18F4x1B4 [System Fabric ID Mask 1]
+ *	DF4	SocketIdShift	[11:8]
+ *	DF4p5	SocketIdShift	[11:8]
+ */
+#define DF2_SOCKET_ID_SHIFT	GENMASK(31, 28)
+#define DF3_SOCKET_ID_SHIFT	GENMASK(9, 8)
+#define DF4_SOCKET_ID_SHIFT	GENMASK(11, 8)
diff --git a/drivers/ras/amd/atl/system.c b/drivers/ras/amd/atl/system.c
new file mode 100644
index 000000000000..701349e84942
--- /dev/null
+++ b/drivers/ras/amd/atl/system.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * system.c : Functions to read and save system-wide data
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+int determine_node_id(struct addr_ctx *ctx, u8 socket_id, u8 die_id)
+{
+	u16 socket_id_bits, die_id_bits;
+
+	if (socket_id > 0 && df_cfg.socket_id_mask == 0) {
+		atl_debug(ctx, "Invalid socket inputs: socket_id=%u socket_id_mask=0x%x",
+			  socket_id, df_cfg.socket_id_mask);
+		return -EINVAL;
+	}
+
+	/* Do each step independently to avoid shift out-of-bounds issues. */
+	socket_id_bits =	socket_id;
+	socket_id_bits <<=	df_cfg.socket_id_shift;
+	socket_id_bits &=	df_cfg.socket_id_mask;
+
+	if (die_id > 0 && df_cfg.die_id_mask == 0) {
+		atl_debug(ctx, "Invalid die inputs: die_id=%u die_id_mask=0x%x",
+			  die_id, df_cfg.die_id_mask);
+		return -EINVAL;
+	}
+
+	/* Do each step independently to avoid shift out-of-bounds issues. */
+	die_id_bits =		die_id;
+	die_id_bits <<=		df_cfg.die_id_shift;
+	die_id_bits &=		df_cfg.die_id_mask;
+
+	ctx->node_id = (socket_id_bits | die_id_bits) >> df_cfg.node_id_shift;
+	return 0;
+}
+
+static void df2_get_masks_shifts(u32 mask0)
+{
+	df_cfg.socket_id_shift		= FIELD_GET(DF2_SOCKET_ID_SHIFT, mask0);
+	df_cfg.socket_id_mask		= FIELD_GET(DF2_SOCKET_ID_MASK, mask0);
+	df_cfg.die_id_shift		= FIELD_GET(DF2_DIE_ID_SHIFT, mask0);
+	df_cfg.die_id_mask		= FIELD_GET(DF2_DIE_ID_MASK, mask0);
+	df_cfg.node_id_shift		= df_cfg.die_id_shift;
+	df_cfg.node_id_mask		= df_cfg.socket_id_mask | df_cfg.die_id_mask;
+	df_cfg.component_id_mask	= ~df_cfg.node_id_mask;
+}
+
+static void df3_get_masks_shifts(u32 mask0, u32 mask1)
+{
+	df_cfg.component_id_mask	= FIELD_GET(DF3_COMPONENT_ID_MASK, mask0);
+	df_cfg.node_id_mask		= FIELD_GET(DF3_NODE_ID_MASK, mask0);
+
+	df_cfg.node_id_shift		= FIELD_GET(DF3_NODE_ID_SHIFT, mask1);
+	df_cfg.socket_id_shift		= FIELD_GET(DF3_SOCKET_ID_SHIFT, mask1);
+	df_cfg.socket_id_mask		= FIELD_GET(DF3_SOCKET_ID_MASK, mask1);
+	df_cfg.die_id_mask		= FIELD_GET(DF3_DIE_ID_MASK, mask1);
+}
+
+static void df3p5_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2)
+{
+	df_cfg.component_id_mask	= FIELD_GET(DF4_COMPONENT_ID_MASK, mask0);
+	df_cfg.node_id_mask		= FIELD_GET(DF4_NODE_ID_MASK, mask0);
+
+	df_cfg.node_id_shift		= FIELD_GET(DF3_NODE_ID_SHIFT, mask1);
+	df_cfg.socket_id_shift		= FIELD_GET(DF4_SOCKET_ID_SHIFT, mask1);
+
+	df_cfg.socket_id_mask		= FIELD_GET(DF4_SOCKET_ID_MASK, mask2);
+	df_cfg.die_id_mask		= FIELD_GET(DF4_DIE_ID_MASK, mask2);
+}
+
+static void df4_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2)
+{
+	df3p5_get_masks_shifts(mask0, mask1, mask2);
+
+	if (!(df_cfg.flags.socket_id_shift_quirk && df_cfg.socket_id_shift == 1))
+		return;
+
+	df_cfg.socket_id_shift	= 0;
+	df_cfg.socket_id_mask	= 1;
+	df_cfg.die_id_shift	= 0;
+	df_cfg.die_id_mask	= 0;
+	df_cfg.node_id_shift	= 8;
+	df_cfg.node_id_mask	= 0x100;
+}
+
+static int df4_get_fabric_id_mask_registers(void)
+{
+	u32 mask0, mask1, mask2;
+
+	/* Read D18F4x1B0 (SystemFabricIdMask0) */
+	if (df_indirect_read_broadcast(0, 4, 0x1B0, &mask0))
+		return -EINVAL;
+
+	/* Read D18F4x1B4 (SystemFabricIdMask1) */
+	if (df_indirect_read_broadcast(0, 4, 0x1B4, &mask1))
+		return -EINVAL;
+
+	/* Read D18F4x1B8 (SystemFabricIdMask2) */
+	if (df_indirect_read_broadcast(0, 4, 0x1B8, &mask2))
+		return -EINVAL;
+
+	df4_get_masks_shifts(mask0, mask1, mask2);
+	return 0;
+}
+
+static int df4_determine_df_rev(u32 reg)
+{
+	df_cfg.rev = FIELD_GET(DF_MINOR_REVISION, reg) < 5 ? DF4 : DF4p5;
+
+	/* Check for special cases or quirks based on Device/Vendor IDs.*/
+
+	/* Read D18F0x000 (DeviceVendorId0) */
+	if (df_indirect_read_broadcast(0, 0, 0, &reg))
+		return -EINVAL;
+
+	if (reg == DF_FUNC0_ID_ZEN4_SERVER)
+		df_cfg.flags.socket_id_shift_quirk = 1;
+
+	if (reg == DF_FUNC0_ID_MI300) {
+		df_cfg.flags.heterogeneous = 1;
+
+		if (get_addr_hash_mi300())
+			return -EINVAL;
+	}
+
+	return df4_get_fabric_id_mask_registers();
+}
+
+static int determine_df_rev_legacy(void)
+{
+	u32 fabric_id_mask0, fabric_id_mask1, fabric_id_mask2;
+
+	/*
+	 * Check for DF3.5.
+	 *
+	 * Component ID Mask must be non-zero. Register D18F1x150 is
+	 * reserved pre-DF3.5, so value will be Read-as-Zero.
+	 */
+
+	/* Read D18F1x150 (SystemFabricIdMask0). */
+	if (df_indirect_read_broadcast(0, 1, 0x150, &fabric_id_mask0))
+		return -EINVAL;
+
+	if (FIELD_GET(DF4_COMPONENT_ID_MASK, fabric_id_mask0)) {
+		df_cfg.rev = DF3p5;
+
+		/* Read D18F1x154 (SystemFabricIdMask1) */
+		if (df_indirect_read_broadcast(0, 1, 0x154, &fabric_id_mask1))
+			return -EINVAL;
+
+		/* Read D18F1x158 (SystemFabricIdMask2) */
+		if (df_indirect_read_broadcast(0, 1, 0x158, &fabric_id_mask2))
+			return -EINVAL;
+
+		df3p5_get_masks_shifts(fabric_id_mask0, fabric_id_mask1, fabric_id_mask2);
+		return 0;
+	}
+
+	/*
+	 * Check for DF3.
+	 *
+	 * Component ID Mask must be non-zero. Field is Read-as-Zero on DF2.
+	 */
+
+	/* Read D18F1x208 (SystemFabricIdMask). */
+	if (df_indirect_read_broadcast(0, 1, 0x208, &fabric_id_mask0))
+		return -EINVAL;
+
+	if (FIELD_GET(DF3_COMPONENT_ID_MASK, fabric_id_mask0)) {
+		df_cfg.rev = DF3;
+
+		/* Read D18F1x20C (SystemFabricIdMask1) */
+		if (df_indirect_read_broadcast(0, 1, 0x20C, &fabric_id_mask1))
+			return -EINVAL;
+
+		df3_get_masks_shifts(fabric_id_mask0, fabric_id_mask1);
+		return 0;
+	}
+
+	/* Default to DF2. */
+	df_cfg.rev = DF2;
+	df2_get_masks_shifts(fabric_id_mask0);
+	return 0;
+}
+
+static int determine_df_rev(void)
+{
+	u32 reg;
+	u8 rev;
+
+	if (df_cfg.rev != UNKNOWN)
+		return 0;
+
+	/* Read D18F0x40 (FabricBlockInstanceCount). */
+	if (df_indirect_read_broadcast(0, 0, 0x40, &reg))
+		return -EINVAL;
+
+	/*
+	 * Revision fields added for DF4 and later.
+	 *
+	 * Major revision of '0' is found pre-DF4. Field is Read-as-Zero.
+	 */
+	rev = FIELD_GET(DF_MAJOR_REVISION, reg);
+	if (!rev)
+		return determine_df_rev_legacy();
+
+	/*
+	 * Fail out for major revisions other than '4'.
+	 *
+	 * Explicit support should be added for newer systems to avoid issues.
+	 */
+	if (rev == 4)
+		return df4_determine_df_rev(reg);
+
+	return -EINVAL;
+}
+
+static void get_num_maps(void)
+{
+	switch (df_cfg.rev) {
+	case DF2:
+	case DF3:
+	case DF3p5:
+		df_cfg.num_coh_st_maps	= 2;
+		break;
+	case DF4:
+	case DF4p5:
+		df_cfg.num_coh_st_maps	= 4;
+		break;
+	default:
+		atl_debug_on_bad_df_rev();
+	}
+}
+
+static void apply_node_id_shift(void)
+{
+	if (df_cfg.rev == DF2)
+		return;
+
+	df_cfg.die_id_shift		= df_cfg.node_id_shift;
+	df_cfg.die_id_mask		<<= df_cfg.node_id_shift;
+	df_cfg.socket_id_mask		<<= df_cfg.node_id_shift;
+	df_cfg.socket_id_shift		+= df_cfg.node_id_shift;
+}
+
+static void dump_df_cfg(void)
+{
+	pr_debug("rev=0x%x",				df_cfg.rev);
+
+	pr_debug("component_id_mask=0x%x",		df_cfg.component_id_mask);
+	pr_debug("die_id_mask=0x%x",			df_cfg.die_id_mask);
+	pr_debug("node_id_mask=0x%x",			df_cfg.node_id_mask);
+	pr_debug("socket_id_mask=0x%x",			df_cfg.socket_id_mask);
+
+	pr_debug("die_id_shift=0x%x",			df_cfg.die_id_shift);
+	pr_debug("node_id_shift=0x%x",			df_cfg.node_id_shift);
+	pr_debug("socket_id_shift=0x%x",		df_cfg.socket_id_shift);
+
+	pr_debug("num_coh_st_maps=%u",			df_cfg.num_coh_st_maps);
+
+	pr_debug("flags.legacy_ficaa=%u",		df_cfg.flags.legacy_ficaa);
+	pr_debug("flags.socket_id_shift_quirk=%u",	df_cfg.flags.socket_id_shift_quirk);
+}
+
+int get_df_system_info(void)
+{
+	if (determine_df_rev()) {
+		pr_warn("amd_atl: Failed to determine DF Revision");
+		df_cfg.rev = UNKNOWN;
+		return -EINVAL;
+	}
+
+	apply_node_id_shift();
+
+	get_num_maps();
+
+	dump_df_cfg();
+
+	return 0;
+}
diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c
new file mode 100644
index 000000000000..59b6169093f7
--- /dev/null
+++ b/drivers/ras/amd/atl/umc.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Address Translation Library
+ *
+ * umc.c : Unified Memory Controller (UMC) topology helpers
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
+ */
+
+#include "internal.h"
+
+/*
+ * MI300 has a fixed, model-specific mapping between a UMC instance and
+ * its related Data Fabric Coherent Station instance.
+ *
+ * The MCA_IPID_UMC[InstanceId] field holds a unique identifier for the
+ * UMC instance within a Node. Use this to find the appropriate Coherent
+ * Station ID.
+ *
+ * Redundant bits were removed from the map below.
+ */
+static const u16 umc_coh_st_map[32] = {
+	0x393, 0x293, 0x193, 0x093,
+	0x392, 0x292, 0x192, 0x092,
+	0x391, 0x291, 0x191, 0x091,
+	0x390, 0x290, 0x190, 0x090,
+	0x793, 0x693, 0x593, 0x493,
+	0x792, 0x692, 0x592, 0x492,
+	0x791, 0x691, 0x591, 0x491,
+	0x790, 0x690, 0x590, 0x490,
+};
+
+#define UMC_ID_MI300 GENMASK(23, 12)
+static u8 get_coh_st_inst_id_mi300(struct atl_err *err)
+{
+	u16 umc_id = FIELD_GET(UMC_ID_MI300, err->ipid);
+	u8 i;
+
+	for (i = 0; i < ARRAY_SIZE(umc_coh_st_map); i++) {
+		if (umc_id == umc_coh_st_map[i])
+			break;
+	}
+
+	WARN_ON_ONCE(i >= ARRAY_SIZE(umc_coh_st_map));
+
+	return i;
+}
+
+/* XOR the bits in @val. */
+static u16 bitwise_xor_bits(u16 val)
+{
+	u16 tmp = 0;
+	u8 i;
+
+	for (i = 0; i < 16; i++)
+		tmp ^= (val >> i) & 0x1;
+
+	return tmp;
+}
+
+struct xor_bits {
+	bool	xor_enable;
+	u16	col_xor;
+	u32	row_xor;
+};
+
+#define NUM_BANK_BITS	4
+
+static struct {
+	/* UMC::CH::AddrHashBank */
+	struct xor_bits	bank[NUM_BANK_BITS];
+
+	/* UMC::CH::AddrHashPC */
+	struct xor_bits	pc;
+
+	/* UMC::CH::AddrHashPC2 */
+	u8		bank_xor;
+} addr_hash;
+
+#define MI300_UMC_CH_BASE	0x90000
+#define MI300_ADDR_HASH_BANK0	(MI300_UMC_CH_BASE + 0xC8)
+#define MI300_ADDR_HASH_PC	(MI300_UMC_CH_BASE + 0xE0)
+#define MI300_ADDR_HASH_PC2	(MI300_UMC_CH_BASE + 0xE4)
+
+#define ADDR_HASH_XOR_EN	BIT(0)
+#define ADDR_HASH_COL_XOR	GENMASK(13, 1)
+#define ADDR_HASH_ROW_XOR	GENMASK(31, 14)
+#define ADDR_HASH_BANK_XOR	GENMASK(5, 0)
+
+/*
+ * Read UMC::CH::AddrHash{Bank,PC,PC2} registers to get XOR bits used
+ * for hashing. Do this during module init, since the values will not
+ * change during run time.
+ *
+ * These registers are instantiated for each UMC across each AMD Node.
+ * However, they should be identically programmed due to the fixed hardware
+ * design of MI300 systems. So read the values from Node 0 UMC 0 and keep a
+ * single global structure for simplicity.
+ */
+int get_addr_hash_mi300(void)
+{
+	u32 temp;
+	int ret;
+	u8 i;
+
+	for (i = 0; i < NUM_BANK_BITS; i++) {
+		ret = amd_smn_read(0, MI300_ADDR_HASH_BANK0 + (i * 4), &temp);
+		if (ret)
+			return ret;
+
+		addr_hash.bank[i].xor_enable = FIELD_GET(ADDR_HASH_XOR_EN,  temp);
+		addr_hash.bank[i].col_xor    = FIELD_GET(ADDR_HASH_COL_XOR, temp);
+		addr_hash.bank[i].row_xor    = FIELD_GET(ADDR_HASH_ROW_XOR, temp);
+	}
+
+	ret = amd_smn_read(0, MI300_ADDR_HASH_PC, &temp);
+	if (ret)
+		return ret;
+
+	addr_hash.pc.xor_enable = FIELD_GET(ADDR_HASH_XOR_EN,  temp);
+	addr_hash.pc.col_xor    = FIELD_GET(ADDR_HASH_COL_XOR, temp);
+	addr_hash.pc.row_xor    = FIELD_GET(ADDR_HASH_ROW_XOR, temp);
+
+	ret = amd_smn_read(0, MI300_ADDR_HASH_PC2, &temp);
+	if (ret)
+		return ret;
+
+	addr_hash.bank_xor = FIELD_GET(ADDR_HASH_BANK_XOR, temp);
+
+	return 0;
+}
+
+/*
+ * MI300 systems report a DRAM address in MCA_ADDR for DRAM ECC errors. This must
+ * be converted to the intermediate normalized address (NA) before translating to a
+ * system physical address.
+ *
+ * The DRAM address includes bank, row, and column. Also included are bits for
+ * pseudochannel (PC) and stack ID (SID).
+ *
+ * Abbreviations: (S)tack ID, (P)seudochannel, (R)ow, (B)ank, (C)olumn, (Z)ero
+ *
+ * The MCA address format is as follows:
+ *	MCA_ADDR[27:0] = {S[1:0], P[0], R[14:0], B[3:0], C[4:0], Z[0]}
+ *
+ * The normalized address format is fixed in hardware and is as follows:
+ *	NA[30:0] = {S[1:0], R[13:0], C4, B[1:0], B[3:2], C[3:2], P, C[1:0], Z[4:0]}
+ *
+ * Additionally, the PC and Bank bits may be hashed. This must be accounted for before
+ * reconstructing the normalized address.
+ */
+#define MI300_UMC_MCA_COL	GENMASK(5, 1)
+#define MI300_UMC_MCA_BANK	GENMASK(9, 6)
+#define MI300_UMC_MCA_ROW	GENMASK(24, 10)
+#define MI300_UMC_MCA_PC	BIT(25)
+#define MI300_UMC_MCA_SID	GENMASK(27, 26)
+
+#define MI300_NA_COL_1_0	GENMASK(6, 5)
+#define MI300_NA_PC		BIT(7)
+#define MI300_NA_COL_3_2	GENMASK(9, 8)
+#define MI300_NA_BANK_3_2	GENMASK(11, 10)
+#define MI300_NA_BANK_1_0	GENMASK(13, 12)
+#define MI300_NA_COL_4		BIT(14)
+#define MI300_NA_ROW		GENMASK(28, 15)
+#define MI300_NA_SID		GENMASK(30, 29)
+
+static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr)
+{
+	u16 i, col, row, bank, pc, sid, temp;
+
+	col  = FIELD_GET(MI300_UMC_MCA_COL,  addr);
+	bank = FIELD_GET(MI300_UMC_MCA_BANK, addr);
+	row  = FIELD_GET(MI300_UMC_MCA_ROW,  addr);
+	pc   = FIELD_GET(MI300_UMC_MCA_PC,   addr);
+	sid  = FIELD_GET(MI300_UMC_MCA_SID,  addr);
+
+	/* Calculate hash for each Bank bit. */
+	for (i = 0; i < NUM_BANK_BITS; i++) {
+		if (!addr_hash.bank[i].xor_enable)
+			continue;
+
+		temp  = bitwise_xor_bits(col & addr_hash.bank[i].col_xor);
+		temp ^= bitwise_xor_bits(row & addr_hash.bank[i].row_xor);
+		bank ^= temp << i;
+	}
+
+	/* Calculate hash for PC bit. */
+	if (addr_hash.pc.xor_enable) {
+		/* Bits SID[1:0] act as Bank[6:5] for PC hash, so apply them here. */
+		bank |= sid << 5;
+
+		temp  = bitwise_xor_bits(col  & addr_hash.pc.col_xor);
+		temp ^= bitwise_xor_bits(row  & addr_hash.pc.row_xor);
+		temp ^= bitwise_xor_bits(bank & addr_hash.bank_xor);
+		pc   ^= temp;
+
+		/* Drop SID bits for the sake of debug printing later. */
+		bank &= 0x1F;
+	}
+
+	/* Reconstruct the normalized address starting with NA[4:0] = 0 */
+	addr  = 0;
+
+	/* NA[6:5] = Column[1:0] */
+	temp  = col & 0x3;
+	addr |= FIELD_PREP(MI300_NA_COL_1_0, temp);
+
+	/* NA[7] = PC */
+	addr |= FIELD_PREP(MI300_NA_PC, pc);
+
+	/* NA[9:8] = Column[3:2] */
+	temp  = (col >> 2) & 0x3;
+	addr |= FIELD_PREP(MI300_NA_COL_3_2, temp);
+
+	/* NA[11:10] = Bank[3:2] */
+	temp  = (bank >> 2) & 0x3;
+	addr |= FIELD_PREP(MI300_NA_BANK_3_2, temp);
+
+	/* NA[13:12] = Bank[1:0] */
+	temp  = bank & 0x3;
+	addr |= FIELD_PREP(MI300_NA_BANK_1_0, temp);
+
+	/* NA[14] = Column[4] */
+	temp  = (col >> 4) & 0x1;
+	addr |= FIELD_PREP(MI300_NA_COL_4, temp);
+
+	/* NA[28:15] = Row[13:0] */
+	addr |= FIELD_PREP(MI300_NA_ROW, row);
+
+	/* NA[30:29] = SID[1:0] */
+	addr |= FIELD_PREP(MI300_NA_SID, sid);
+
+	pr_debug("Addr=0x%016lx", addr);
+	pr_debug("Bank=%u Row=%u Column=%u PC=%u SID=%u", bank, row, col, pc, sid);
+
+	return addr;
+}
+
+/*
+ * When a DRAM ECC error occurs on MI300 systems, it is recommended to retire
+ * all memory within that DRAM row. This applies to the memory with a DRAM
+ * bank.
+ *
+ * To find the memory addresses, loop through permutations of the DRAM column
+ * bits and find the System Physical address of each. The column bits are used
+ * to calculate the intermediate Normalized address, so all permutations should
+ * be checked.
+ *
+ * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats.
+ */
+#define MI300_NUM_COL		BIT(HWEIGHT(MI300_UMC_MCA_COL))
+static void retire_row_mi300(struct atl_err *a_err)
+{
+	unsigned long addr;
+	struct page *p;
+	u8 col;
+
+	for (col = 0; col < MI300_NUM_COL; col++) {
+		a_err->addr &= ~MI300_UMC_MCA_COL;
+		a_err->addr |= FIELD_PREP(MI300_UMC_MCA_COL, col);
+
+		addr = amd_convert_umc_mca_addr_to_sys_addr(a_err);
+		if (IS_ERR_VALUE(addr))
+			continue;
+
+		addr = PHYS_PFN(addr);
+
+		/*
+		 * Skip invalid or already poisoned pages to avoid unnecessary
+		 * error messages from memory_failure().
+		 */
+		p = pfn_to_online_page(addr);
+		if (!p)
+			continue;
+
+		if (PageHWPoison(p))
+			continue;
+
+		memory_failure(addr, 0);
+	}
+}
+
+void amd_retire_dram_row(struct atl_err *a_err)
+{
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return retire_row_mi300(a_err);
+}
+EXPORT_SYMBOL_GPL(amd_retire_dram_row);
+
+static unsigned long get_addr(unsigned long addr)
+{
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return convert_dram_to_norm_addr_mi300(addr);
+
+	return addr;
+}
+
+#define MCA_IPID_INST_ID_HI	GENMASK_ULL(47, 44)
+static u8 get_die_id(struct atl_err *err)
+{
+	/*
+	 * AMD Node ID is provided in MCA_IPID[InstanceIdHi], and this
+	 * needs to be divided by 4 to get the internal Die ID.
+	 */
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) {
+		u8 node_id = FIELD_GET(MCA_IPID_INST_ID_HI, err->ipid);
+
+		return node_id >> 2;
+	}
+
+	/*
+	 * For CPUs, this is the AMD Node ID modulo the number
+	 * of AMD Nodes per socket.
+	 */
+	return topology_amd_node_id(err->cpu) % topology_amd_nodes_per_pkg();
+}
+
+#define UMC_CHANNEL_NUM	GENMASK(31, 20)
+static u8 get_coh_st_inst_id(struct atl_err *err)
+{
+	if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous)
+		return get_coh_st_inst_id_mi300(err);
+
+	return FIELD_GET(UMC_CHANNEL_NUM, err->ipid);
+}
+
+unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err)
+{
+	u8 socket_id = topology_physical_package_id(err->cpu);
+	u8 coh_st_inst_id = get_coh_st_inst_id(err);
+	unsigned long addr = get_addr(err->addr);
+	u8 die_id = get_die_id(err);
+
+	pr_debug("socket_id=0x%x die_id=0x%x coh_st_inst_id=0x%x addr=0x%016lx",
+		 socket_id, die_id, coh_st_inst_id, addr);
+
+	return norm_to_sys_addr(socket_id, die_id, coh_st_inst_id, addr);
+}
diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
new file mode 100644
index 000000000000..2f4ac9591c8f
--- /dev/null
+++ b/drivers/ras/amd/fmpm.c
@@ -0,0 +1,1013 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * FRU (Field-Replaceable Unit) Memory Poison Manager
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Authors:
+ *	Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com>
+ *	Muralidhara M K <muralidhara.mk@amd.com>
+ *	Yazen Ghannam <Yazen.Ghannam@amd.com>
+ *
+ * Implementation notes, assumptions, and limitations:
+ *
+ * - FRU memory poison section and memory poison descriptor definitions are not yet
+ *   included in the UEFI specification. So they are defined here. Afterwards, they
+ *   may be moved to linux/cper.h, if appropriate.
+ *
+ * - Platforms based on AMD MI300 systems will be the first to use these structures.
+ *   There are a number of assumptions made here that will need to be generalized
+ *   to support other platforms.
+ *
+ *   AMD MI300-based platform(s) assumptions:
+ *   - Memory errors are reported through x86 MCA.
+ *   - The entire DRAM row containing a memory error should be retired.
+ *   - There will be (1) FRU memory poison section per CPER.
+ *   - The FRU will be the CPU package (processor socket).
+ *   - The default number of memory poison descriptor entries should be (8).
+ *   - The platform will use ACPI ERST for persistent storage.
+ *   - All FRU records should be saved to persistent storage. Module init will
+ *     fail if any FRU record is not successfully written.
+ *
+ * - Boot time memory retirement may occur later than ideal due to dependencies
+ *   on other libraries and drivers. This leaves a gap where bad memory may be
+ *   accessed during early boot stages.
+ *
+ * - Enough memory should be pre-allocated for each FRU record to be able to hold
+ *   the expected number of descriptor entries. This, mostly empty, record is
+ *   written to storage during init time. Subsequent writes to the same record
+ *   should allow the Platform to update the stored record in-place. Otherwise,
+ *   if the record is extended, then the Platform may need to perform costly memory
+ *   management operations on the storage. For example, the Platform may spend time
+ *   in Firmware copying and invalidating memory on a relatively slow SPI ROM.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cper.h>
+#include <linux/ras.h>
+#include <linux/cpu.h>
+
+#include <acpi/apei.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/mce.h>
+
+#include "../debugfs.h"
+
+#define INVALID_CPU			UINT_MAX
+
+/* Validation Bits */
+#define FMP_VALID_ARCH_TYPE		BIT_ULL(0)
+#define FMP_VALID_ARCH			BIT_ULL(1)
+#define FMP_VALID_ID_TYPE		BIT_ULL(2)
+#define FMP_VALID_ID			BIT_ULL(3)
+#define FMP_VALID_LIST_ENTRIES		BIT_ULL(4)
+#define FMP_VALID_LIST			BIT_ULL(5)
+
+/* FRU Architecture Types */
+#define FMP_ARCH_TYPE_X86_CPUID_1_EAX	0
+
+/* FRU ID Types */
+#define FMP_ID_TYPE_X86_PPIN		0
+
+/* FRU Memory Poison Section */
+struct cper_sec_fru_mem_poison {
+	u32 checksum;
+	u64 validation_bits;
+	u32 fru_arch_type;
+	u64 fru_arch;
+	u32 fru_id_type;
+	u64 fru_id;
+	u32 nr_entries;
+} __packed;
+
+/* FRU Descriptor ID Types */
+#define FPD_HW_ID_TYPE_MCA_IPID		0
+
+/* FRU Descriptor Address Types */
+#define FPD_ADDR_TYPE_MCA_ADDR		0
+
+/* Memory Poison Descriptor */
+struct cper_fru_poison_desc {
+	u64 timestamp;
+	u32 hw_id_type;
+	u64 hw_id;
+	u32 addr_type;
+	u64 addr;
+} __packed;
+
+/* Collection of headers and sections for easy pointer use. */
+struct fru_rec {
+	struct cper_record_header	hdr;
+	struct cper_section_descriptor	sec_desc;
+	struct cper_sec_fru_mem_poison	fmp;
+	struct cper_fru_poison_desc	entries[];
+} __packed;
+
+/*
+ * Pointers to the complete CPER record of each FRU.
+ *
+ * Memory allocation will include padded space for descriptor entries.
+ */
+static struct fru_rec **fru_records;
+
+/* system physical addresses array */
+static u64 *spa_entries;
+
+#define INVALID_SPA	~0ULL
+
+static struct dentry *fmpm_dfs_dir;
+static struct dentry *fmpm_dfs_entries;
+
+#define CPER_CREATOR_FMP						\
+	GUID_INIT(0xcd5c2993, 0xf4b2, 0x41b2, 0xb5, 0xd4, 0xf9, 0xc3,	\
+		  0xa0, 0x33, 0x08, 0x75)
+
+#define CPER_SECTION_TYPE_FMP						\
+	GUID_INIT(0x5e4706c1, 0x5356, 0x48c6, 0x93, 0x0b, 0x52, 0xf2,	\
+		  0x12, 0x0a, 0x44, 0x58)
+
+/**
+ * DOC: max_nr_entries (byte)
+ * Maximum number of descriptor entries possible for each FRU.
+ *
+ * Values between '1' and '255' are valid.
+ * No input or '0' will default to FMPM_DEFAULT_MAX_NR_ENTRIES.
+ */
+static u8 max_nr_entries;
+module_param(max_nr_entries, byte, 0644);
+MODULE_PARM_DESC(max_nr_entries,
+		 "Maximum number of memory poison descriptor entries per FRU");
+
+#define FMPM_DEFAULT_MAX_NR_ENTRIES	8
+
+/* Maximum number of FRUs in the system. */
+#define FMPM_MAX_NR_FRU			256
+static unsigned int max_nr_fru;
+
+/* Total length of record including headers and list of descriptor entries. */
+static size_t max_rec_len;
+
+/* Total number of SPA entries across all FRUs. */
+static unsigned int spa_nr_entries;
+
+/*
+ * Protect the local records cache in fru_records and prevent concurrent
+ * writes to storage. This is only needed after init once notifier block
+ * registration is done.
+ *
+ * The majority of a record is fixed at module init and will not change
+ * during run time. The entries within a record will be updated as new
+ * errors are reported. The mutex should be held whenever the entries are
+ * accessed during run time.
+ */
+static DEFINE_MUTEX(fmpm_update_mutex);
+
+#define for_each_fru(i, rec) \
+	for (i = 0; rec = fru_records[i], i < max_nr_fru; i++)
+
+static inline u32 get_fmp_len(struct fru_rec *rec)
+{
+	return rec->sec_desc.section_length - sizeof(struct cper_section_descriptor);
+}
+
+static struct fru_rec *get_fru_record(u64 fru_id)
+{
+	struct fru_rec *rec;
+	unsigned int i;
+
+	for_each_fru(i, rec) {
+		if (rec->fmp.fru_id == fru_id)
+			return rec;
+	}
+
+	pr_debug("Record not found for FRU 0x%016llx\n", fru_id);
+
+	return NULL;
+}
+
+/*
+ * Sum up all bytes within the FRU Memory Poison Section including the Memory
+ * Poison Descriptor entries.
+ *
+ * Don't include the old checksum here. It's a u32 value, so summing each of its
+ * bytes will give the wrong total.
+ */
+static u32 do_fmp_checksum(struct cper_sec_fru_mem_poison *fmp, u32 len)
+{
+	u32 checksum = 0;
+	u8 *buf, *end;
+
+	/* Skip old checksum. */
+	buf = (u8 *)fmp + sizeof(u32);
+	end = buf + len;
+
+	while (buf < end)
+		checksum += (u8)(*(buf++));
+
+	return checksum;
+}
+
+static int update_record_on_storage(struct fru_rec *rec)
+{
+	u32 len, checksum;
+	int ret;
+
+	/* Calculate a new checksum. */
+	len = get_fmp_len(rec);
+
+	/* Get the current total. */
+	checksum = do_fmp_checksum(&rec->fmp, len);
+
+	/* Use the complement value. */
+	rec->fmp.checksum = -checksum;
+
+	pr_debug("Writing to storage\n");
+
+	ret = erst_write(&rec->hdr);
+	if (ret) {
+		pr_warn("Storage update failed for FRU 0x%016llx\n", rec->fmp.fru_id);
+
+		if (ret == -ENOSPC)
+			pr_warn("Not enough space on storage\n");
+	}
+
+	return ret;
+}
+
+static bool rec_has_valid_entries(struct fru_rec *rec)
+{
+	if (!(rec->fmp.validation_bits & FMP_VALID_LIST_ENTRIES))
+		return false;
+
+	if (!(rec->fmp.validation_bits & FMP_VALID_LIST))
+		return false;
+
+	return true;
+}
+
+static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new)
+{
+	/*
+	 * Ignore timestamp field.
+	 * The same physical error may be reported multiple times due to stuck bits, etc.
+	 *
+	 * Also, order the checks from most->least likely to fail to shortcut the code.
+	 */
+	if (old->addr != new->addr)
+		return false;
+
+	if (old->hw_id != new->hw_id)
+		return false;
+
+	if (old->addr_type != new->addr_type)
+		return false;
+
+	if (old->hw_id_type != new->hw_id_type)
+		return false;
+
+	return true;
+}
+
+static bool rec_has_fpd(struct fru_rec *rec, struct cper_fru_poison_desc *fpd)
+{
+	unsigned int i;
+
+	for (i = 0; i < rec->fmp.nr_entries; i++) {
+		struct cper_fru_poison_desc *fpd_i = &rec->entries[i];
+
+		if (fpds_equal(fpd_i, fpd)) {
+			pr_debug("Found duplicate record\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static void save_spa(struct fru_rec *rec, unsigned int entry,
+		     u64 addr, u64 id, unsigned int cpu)
+{
+	unsigned int i, fru_idx, spa_entry;
+	struct atl_err a_err;
+	unsigned long spa;
+
+	if (entry >= max_nr_entries) {
+		pr_warn_once("FRU descriptor entry %d out-of-bounds (max: %d)\n",
+			     entry, max_nr_entries);
+		return;
+	}
+
+	/* spa_nr_entries is always multiple of max_nr_entries */
+	for (i = 0; i < spa_nr_entries; i += max_nr_entries) {
+		fru_idx = i / max_nr_entries;
+		if (fru_records[fru_idx] == rec)
+			break;
+	}
+
+	if (i >= spa_nr_entries) {
+		pr_warn_once("FRU record %d not found\n", i);
+		return;
+	}
+
+	spa_entry = i + entry;
+	if (spa_entry >= spa_nr_entries) {
+		pr_warn_once("spa_entries[] index out-of-bounds\n");
+		return;
+	}
+
+	memset(&a_err, 0, sizeof(struct atl_err));
+
+	a_err.addr = addr;
+	a_err.ipid = id;
+	a_err.cpu  = cpu;
+
+	spa = amd_convert_umc_mca_addr_to_sys_addr(&a_err);
+	if (IS_ERR_VALUE(spa)) {
+		pr_debug("Failed to get system address\n");
+		return;
+	}
+
+	spa_entries[spa_entry] = spa;
+	pr_debug("fru_idx: %u, entry: %u, spa_entry: %u, spa: 0x%016llx\n",
+		 fru_idx, entry, spa_entry, spa_entries[spa_entry]);
+}
+
+static void update_fru_record(struct fru_rec *rec, struct mce *m)
+{
+	struct cper_sec_fru_mem_poison *fmp = &rec->fmp;
+	struct cper_fru_poison_desc fpd, *fpd_dest;
+	u32 entry = 0;
+
+	mutex_lock(&fmpm_update_mutex);
+
+	memset(&fpd, 0, sizeof(struct cper_fru_poison_desc));
+
+	fpd.timestamp	= m->time;
+	fpd.hw_id_type = FPD_HW_ID_TYPE_MCA_IPID;
+	fpd.hw_id	= m->ipid;
+	fpd.addr_type	= FPD_ADDR_TYPE_MCA_ADDR;
+	fpd.addr	= m->addr;
+
+	/* This is the first entry, so just save it. */
+	if (!rec_has_valid_entries(rec))
+		goto save_fpd;
+
+	/* Ignore already recorded errors. */
+	if (rec_has_fpd(rec, &fpd))
+		goto out_unlock;
+
+	if (rec->fmp.nr_entries >= max_nr_entries) {
+		pr_warn("Exceeded number of entries for FRU 0x%016llx\n", rec->fmp.fru_id);
+		goto out_unlock;
+	}
+
+	entry  = fmp->nr_entries;
+
+save_fpd:
+	save_spa(rec, entry, m->addr, m->ipid, m->extcpu);
+	fpd_dest  = &rec->entries[entry];
+	memcpy(fpd_dest, &fpd, sizeof(struct cper_fru_poison_desc));
+
+	fmp->nr_entries		 = entry + 1;
+	fmp->validation_bits	|= FMP_VALID_LIST_ENTRIES;
+	fmp->validation_bits	|= FMP_VALID_LIST;
+
+	pr_debug("Updated FRU 0x%016llx entry #%u\n", fmp->fru_id, entry);
+
+	update_record_on_storage(rec);
+
+out_unlock:
+	mutex_unlock(&fmpm_update_mutex);
+}
+
+static void retire_dram_row(u64 addr, u64 id, u32 cpu)
+{
+	struct atl_err a_err;
+
+	memset(&a_err, 0, sizeof(struct atl_err));
+
+	a_err.addr = addr;
+	a_err.ipid = id;
+	a_err.cpu  = cpu;
+
+	amd_retire_dram_row(&a_err);
+}
+
+static int fru_handle_mem_poison(struct notifier_block *nb, unsigned long val, void *data)
+{
+	struct mce *m = (struct mce *)data;
+	struct fru_rec *rec;
+
+	if (!mce_is_memory_error(m))
+		return NOTIFY_DONE;
+
+	retire_dram_row(m->addr, m->ipid, m->extcpu);
+
+	/*
+	 * An invalid FRU ID should not happen on real errors. But it
+	 * could happen from software error injection, etc.
+	 */
+	rec = get_fru_record(m->ppin);
+	if (!rec)
+		return NOTIFY_DONE;
+
+	update_fru_record(rec, m);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fru_mem_poison_nb = {
+	.notifier_call  = fru_handle_mem_poison,
+	.priority	= MCE_PRIO_LOWEST,
+};
+
+static void retire_mem_fmp(struct fru_rec *rec)
+{
+	struct cper_sec_fru_mem_poison *fmp = &rec->fmp;
+	unsigned int i, cpu;
+
+	for (i = 0; i < fmp->nr_entries; i++) {
+		struct cper_fru_poison_desc *fpd = &rec->entries[i];
+		unsigned int err_cpu = INVALID_CPU;
+
+		if (fpd->hw_id_type != FPD_HW_ID_TYPE_MCA_IPID)
+			continue;
+
+		if (fpd->addr_type != FPD_ADDR_TYPE_MCA_ADDR)
+			continue;
+
+		cpus_read_lock();
+		for_each_online_cpu(cpu) {
+			if (topology_ppin(cpu) == fmp->fru_id) {
+				err_cpu = cpu;
+				break;
+			}
+		}
+		cpus_read_unlock();
+
+		if (err_cpu == INVALID_CPU)
+			continue;
+
+		retire_dram_row(fpd->addr, fpd->hw_id, err_cpu);
+		save_spa(rec, i, fpd->addr, fpd->hw_id, err_cpu);
+	}
+}
+
+static void retire_mem_records(void)
+{
+	struct fru_rec *rec;
+	unsigned int i;
+
+	for_each_fru(i, rec) {
+		if (!rec_has_valid_entries(rec))
+			continue;
+
+		retire_mem_fmp(rec);
+	}
+}
+
+/* Set the CPER Record Header and CPER Section Descriptor fields. */
+static void set_rec_fields(struct fru_rec *rec)
+{
+	struct cper_section_descriptor	*sec_desc = &rec->sec_desc;
+	struct cper_record_header	*hdr	  = &rec->hdr;
+
+	memcpy(hdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+	hdr->revision			= CPER_RECORD_REV;
+	hdr->signature_end		= CPER_SIG_END;
+
+	/*
+	 * Currently, it is assumed that there is one FRU Memory Poison
+	 * section per CPER. But this may change for other implementations.
+	 */
+	hdr->section_count		= 1;
+
+	/* The logged errors are recoverable. Otherwise, they'd never make it here. */
+	hdr->error_severity		= CPER_SEV_RECOVERABLE;
+
+	hdr->validation_bits		= 0;
+	hdr->record_length		= max_rec_len;
+	hdr->creator_id			= CPER_CREATOR_FMP;
+	hdr->notification_type		= CPER_NOTIFY_MCE;
+	hdr->record_id			= cper_next_record_id();
+	hdr->flags			= CPER_HW_ERROR_FLAGS_PREVERR;
+
+	sec_desc->section_offset	= sizeof(struct cper_record_header);
+	sec_desc->section_length	= max_rec_len - sizeof(struct cper_record_header);
+	sec_desc->revision		= CPER_SEC_REV;
+	sec_desc->validation_bits	= 0;
+	sec_desc->flags			= CPER_SEC_PRIMARY;
+	sec_desc->section_type		= CPER_SECTION_TYPE_FMP;
+	sec_desc->section_severity	= CPER_SEV_RECOVERABLE;
+}
+
+static int save_new_records(void)
+{
+	DECLARE_BITMAP(new_records, FMPM_MAX_NR_FRU);
+	struct fru_rec *rec;
+	unsigned int i;
+	int ret = 0;
+
+	for_each_fru(i, rec) {
+		if (rec->hdr.record_length)
+			continue;
+
+		set_rec_fields(rec);
+
+		ret = update_record_on_storage(rec);
+		if (ret)
+			goto out_clear;
+
+		set_bit(i, new_records);
+	}
+
+	return ret;
+
+out_clear:
+	for_each_fru(i, rec) {
+		if (!test_bit(i, new_records))
+			continue;
+
+		erst_clear(rec->hdr.record_id);
+	}
+
+	return ret;
+}
+
+/* Check that the record matches expected types for the current system.*/
+static bool fmp_is_usable(struct fru_rec *rec)
+{
+	struct cper_sec_fru_mem_poison *fmp = &rec->fmp;
+	u64 cpuid;
+
+	pr_debug("Validation bits: 0x%016llx\n", fmp->validation_bits);
+
+	if (!(fmp->validation_bits & FMP_VALID_ARCH_TYPE)) {
+		pr_debug("Arch type unknown\n");
+		return false;
+	}
+
+	if (fmp->fru_arch_type != FMP_ARCH_TYPE_X86_CPUID_1_EAX) {
+		pr_debug("Arch type not 'x86 Family/Model/Stepping'\n");
+		return false;
+	}
+
+	if (!(fmp->validation_bits & FMP_VALID_ARCH)) {
+		pr_debug("Arch value unknown\n");
+		return false;
+	}
+
+	cpuid = cpuid_eax(1);
+	if (fmp->fru_arch != cpuid) {
+		pr_debug("Arch value mismatch: record = 0x%016llx, system = 0x%016llx\n",
+			 fmp->fru_arch, cpuid);
+		return false;
+	}
+
+	if (!(fmp->validation_bits & FMP_VALID_ID_TYPE)) {
+		pr_debug("FRU ID type unknown\n");
+		return false;
+	}
+
+	if (fmp->fru_id_type != FMP_ID_TYPE_X86_PPIN) {
+		pr_debug("FRU ID type is not 'x86 PPIN'\n");
+		return false;
+	}
+
+	if (!(fmp->validation_bits & FMP_VALID_ID)) {
+		pr_debug("FRU ID value unknown\n");
+		return false;
+	}
+
+	return true;
+}
+
+static bool fmp_is_valid(struct fru_rec *rec)
+{
+	struct cper_sec_fru_mem_poison *fmp = &rec->fmp;
+	u32 checksum, len;
+
+	len = get_fmp_len(rec);
+	if (len < sizeof(struct cper_sec_fru_mem_poison)) {
+		pr_debug("fmp length is too small\n");
+		return false;
+	}
+
+	/* Checksum must sum to zero for the entire section. */
+	checksum = do_fmp_checksum(fmp, len) + fmp->checksum;
+	if (checksum) {
+		pr_debug("fmp checksum failed: sum = 0x%x\n", checksum);
+		print_hex_dump_debug("fmp record: ", DUMP_PREFIX_NONE, 16, 1, fmp, len, false);
+		return false;
+	}
+
+	if (!fmp_is_usable(rec))
+		return false;
+
+	return true;
+}
+
+static struct fru_rec *get_valid_record(struct fru_rec *old)
+{
+	struct fru_rec *new;
+
+	if (!fmp_is_valid(old)) {
+		pr_debug("Ignoring invalid record\n");
+		return NULL;
+	}
+
+	new = get_fru_record(old->fmp.fru_id);
+	if (!new)
+		pr_debug("Ignoring record for absent FRU\n");
+
+	return new;
+}
+
+/*
+ * Fetch saved records from persistent storage.
+ *
+ * For each found record:
+ * - If it was not created by this module, then ignore it.
+ * - If it is valid, then copy its data to the local cache.
+ * - If it is not valid, then erase it.
+ */
+static int get_saved_records(void)
+{
+	struct fru_rec *old, *new;
+	u64 record_id;
+	int ret, pos;
+	ssize_t len;
+
+	/*
+	 * Assume saved records match current max size.
+	 *
+	 * However, this may not be true depending on module parameters.
+	 */
+	old = kmalloc(max_rec_len, GFP_KERNEL);
+	if (!old) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = erst_get_record_id_begin(&pos);
+	if (ret < 0)
+		goto out_end;
+
+	while (!erst_get_record_id_next(&pos, &record_id)) {
+		if (record_id == APEI_ERST_INVALID_RECORD_ID)
+			goto out_end;
+		/*
+		 * Make sure to clear temporary buffer between reads to avoid
+		 * leftover data from records of various sizes.
+		 */
+		memset(old, 0, max_rec_len);
+
+		len = erst_read_record(record_id, &old->hdr, max_rec_len,
+				       sizeof(struct fru_rec), &CPER_CREATOR_FMP);
+		if (len < 0)
+			continue;
+
+		if (len > max_rec_len) {
+			pr_debug("Found record larger than max_rec_len\n");
+			continue;
+		}
+
+		new = get_valid_record(old);
+		if (!new)
+			erst_clear(record_id);
+
+		/* Restore the record */
+		memcpy(new, old, len);
+	}
+
+out_end:
+	erst_get_record_id_end();
+	kfree(old);
+out:
+	return ret;
+}
+
+static void set_fmp_fields(struct fru_rec *rec, unsigned int cpu)
+{
+	struct cper_sec_fru_mem_poison *fmp = &rec->fmp;
+
+	fmp->fru_arch_type    = FMP_ARCH_TYPE_X86_CPUID_1_EAX;
+	fmp->validation_bits |= FMP_VALID_ARCH_TYPE;
+
+	/* Assume all CPUs in the system have the same value for now. */
+	fmp->fru_arch	      = cpuid_eax(1);
+	fmp->validation_bits |= FMP_VALID_ARCH;
+
+	fmp->fru_id_type      = FMP_ID_TYPE_X86_PPIN;
+	fmp->validation_bits |= FMP_VALID_ID_TYPE;
+
+	fmp->fru_id	      = topology_ppin(cpu);
+	fmp->validation_bits |= FMP_VALID_ID;
+}
+
+static int init_fmps(void)
+{
+	struct fru_rec *rec;
+	unsigned int i, cpu;
+	int ret = 0;
+
+	for_each_fru(i, rec) {
+		unsigned int fru_cpu = INVALID_CPU;
+
+		cpus_read_lock();
+		for_each_online_cpu(cpu) {
+			if (topology_physical_package_id(cpu) == i) {
+				fru_cpu = cpu;
+				break;
+			}
+		}
+		cpus_read_unlock();
+
+		if (fru_cpu == INVALID_CPU) {
+			pr_debug("Failed to find matching CPU for FRU #%u\n", i);
+			ret = -ENODEV;
+			break;
+		}
+
+		set_fmp_fields(rec, fru_cpu);
+	}
+
+	return ret;
+}
+
+static int get_system_info(void)
+{
+	/* Only load on MI300A systems for now. */
+	if (!(boot_cpu_data.x86_model >= 0x90 &&
+	      boot_cpu_data.x86_model <= 0x9f))
+		return -ENODEV;
+
+	if (!cpu_feature_enabled(X86_FEATURE_AMD_PPIN)) {
+		pr_debug("PPIN feature not available\n");
+		return -ENODEV;
+	}
+
+	/* Use CPU socket as FRU for MI300 systems. */
+	max_nr_fru = topology_max_packages();
+	if (!max_nr_fru)
+		return -ENODEV;
+
+	if (max_nr_fru > FMPM_MAX_NR_FRU) {
+		pr_warn("Too many FRUs to manage: found: %u, max: %u\n",
+			max_nr_fru, FMPM_MAX_NR_FRU);
+		return -ENODEV;
+	}
+
+	if (!max_nr_entries)
+		max_nr_entries = FMPM_DEFAULT_MAX_NR_ENTRIES;
+
+	spa_nr_entries = max_nr_fru * max_nr_entries;
+
+	max_rec_len  = sizeof(struct fru_rec);
+	max_rec_len += sizeof(struct cper_fru_poison_desc) * max_nr_entries;
+
+	pr_info("max FRUs: %u, max entries: %u, max record length: %lu\n",
+		 max_nr_fru, max_nr_entries, max_rec_len);
+
+	return 0;
+}
+
+static void free_records(void)
+{
+	struct fru_rec *rec;
+	int i;
+
+	for_each_fru(i, rec)
+		kfree(rec);
+
+	kfree(fru_records);
+	kfree(spa_entries);
+}
+
+static int allocate_records(void)
+{
+	int i, ret = 0;
+
+	fru_records = kcalloc(max_nr_fru, sizeof(struct fru_rec *), GFP_KERNEL);
+	if (!fru_records) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < max_nr_fru; i++) {
+		fru_records[i] = kzalloc(max_rec_len, GFP_KERNEL);
+		if (!fru_records[i]) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+	}
+
+	spa_entries = kcalloc(spa_nr_entries, sizeof(u64), GFP_KERNEL);
+	if (!spa_entries) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	for (i = 0; i < spa_nr_entries; i++)
+		spa_entries[i] = INVALID_SPA;
+
+	return ret;
+
+out_free:
+	while (--i >= 0)
+		kfree(fru_records[i]);
+
+	kfree(fru_records);
+out:
+	return ret;
+}
+
+static void *fmpm_start(struct seq_file *f, loff_t *pos)
+{
+	if (*pos >= (spa_nr_entries + 1))
+		return NULL;
+	return pos;
+}
+
+static void *fmpm_next(struct seq_file *f, void *data, loff_t *pos)
+{
+	if (++(*pos) >= (spa_nr_entries + 1))
+		return NULL;
+	return pos;
+}
+
+static void fmpm_stop(struct seq_file *f, void *data)
+{
+}
+
+#define SHORT_WIDTH	8
+#define U64_WIDTH	18
+#define TIMESTAMP_WIDTH	19
+#define LONG_WIDTH	24
+#define U64_PAD		(LONG_WIDTH - U64_WIDTH)
+#define TS_PAD		(LONG_WIDTH - TIMESTAMP_WIDTH)
+static int fmpm_show(struct seq_file *f, void *data)
+{
+	unsigned int fru_idx, entry, spa_entry, line;
+	struct cper_fru_poison_desc *fpd;
+	struct fru_rec *rec;
+
+	line = *(loff_t *)data;
+	if (line == 0) {
+		seq_printf(f, "%-*s", SHORT_WIDTH, "fru_idx");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "fru_id");
+		seq_printf(f, "%-*s", SHORT_WIDTH, "entry");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "timestamp");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "hw_id");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "addr");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "spa");
+		goto out_newline;
+	}
+
+	spa_entry = line - 1;
+	fru_idx	  = spa_entry / max_nr_entries;
+	entry	  = spa_entry % max_nr_entries;
+
+	rec = fru_records[fru_idx];
+	if (!rec)
+		goto out;
+
+	seq_printf(f, "%-*u",		SHORT_WIDTH, fru_idx);
+	seq_printf(f, "0x%016llx%-*s",	rec->fmp.fru_id, U64_PAD, "");
+	seq_printf(f, "%-*u",		SHORT_WIDTH, entry);
+
+	mutex_lock(&fmpm_update_mutex);
+
+	if (entry >= rec->fmp.nr_entries) {
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		goto out_unlock;
+	}
+
+	fpd = &rec->entries[entry];
+
+	seq_printf(f, "%ptT%-*s",	&fpd->timestamp, TS_PAD,  "");
+	seq_printf(f, "0x%016llx%-*s",	fpd->hw_id,	 U64_PAD, "");
+	seq_printf(f, "0x%016llx%-*s",	fpd->addr,	 U64_PAD, "");
+
+	if (spa_entries[spa_entry] == INVALID_SPA)
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+	else
+		seq_printf(f, "0x%016llx%-*s", spa_entries[spa_entry], U64_PAD, "");
+
+out_unlock:
+	mutex_unlock(&fmpm_update_mutex);
+out_newline:
+	seq_putc(f, '\n');
+out:
+	return 0;
+}
+
+static const struct seq_operations fmpm_seq_ops = {
+	.start	= fmpm_start,
+	.next	= fmpm_next,
+	.stop	= fmpm_stop,
+	.show	= fmpm_show,
+};
+
+static int fmpm_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fmpm_seq_ops);
+}
+
+static const struct file_operations fmpm_fops = {
+	.open		= fmpm_open,
+	.release	= seq_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static void setup_debugfs(void)
+{
+	struct dentry *dfs = ras_get_debugfs_root();
+
+	if (!dfs)
+		return;
+
+	fmpm_dfs_dir = debugfs_create_dir("fmpm", dfs);
+	if (!fmpm_dfs_dir)
+		return;
+
+	fmpm_dfs_entries = debugfs_create_file("entries", 0400, fmpm_dfs_dir, NULL, &fmpm_fops);
+	if (!fmpm_dfs_entries)
+		debugfs_remove(fmpm_dfs_dir);
+}
+
+static const struct x86_cpu_id fmpm_cpuids[] = {
+	X86_MATCH_VENDOR_FAM(AMD, 0x19, NULL),
+	{ }
+};
+MODULE_DEVICE_TABLE(x86cpu, fmpm_cpuids);
+
+static int __init fru_mem_poison_init(void)
+{
+	int ret;
+
+	if (!x86_match_cpu(fmpm_cpuids)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (erst_disable) {
+		pr_debug("ERST not available\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	ret = get_system_info();
+	if (ret)
+		goto out;
+
+	ret = allocate_records();
+	if (ret)
+		goto out;
+
+	ret = init_fmps();
+	if (ret)
+		goto out_free;
+
+	ret = get_saved_records();
+	if (ret)
+		goto out_free;
+
+	ret = save_new_records();
+	if (ret)
+		goto out_free;
+
+	setup_debugfs();
+
+	retire_mem_records();
+
+	mce_register_decode_chain(&fru_mem_poison_nb);
+
+	pr_info("FRU Memory Poison Manager initialized\n");
+	return 0;
+
+out_free:
+	free_records();
+out:
+	return ret;
+}
+
+static void __exit fru_mem_poison_exit(void)
+{
+	mce_unregister_decode_chain(&fru_mem_poison_nb);
+	debugfs_remove(fmpm_dfs_dir);
+	free_records();
+}
+
+module_init(fru_mem_poison_init);
+module_exit(fru_mem_poison_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("FRU Memory Poison Manager");
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 321af498ee11..e440b15fbabc 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -480,9 +480,15 @@ DEFINE_SHOW_ATTRIBUTE(array);
 
 static int __init create_debugfs_nodes(void)
 {
-	struct dentry *d, *pfn, *decay, *count, *array;
+	struct dentry *d, *pfn, *decay, *count, *array, *dfs;
 
-	d = debugfs_create_dir("cec", ras_debugfs_dir);
+	dfs = ras_get_debugfs_root();
+	if (!dfs) {
+		pr_warn("Error getting RAS debugfs root!\n");
+		return -1;
+	}
+
+	d = debugfs_create_dir("cec", dfs);
 	if (!d) {
 		pr_warn("Error creating cec debugfs node!\n");
 		return -1;
diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c
index ffb973c328e3..42afd3de68b2 100644
--- a/drivers/ras/debugfs.c
+++ b/drivers/ras/debugfs.c
@@ -3,10 +3,16 @@
 #include <linux/ras.h>
 #include "debugfs.h"
 
-struct dentry *ras_debugfs_dir;
+static struct dentry *ras_debugfs_dir;
 
 static atomic_t trace_count = ATOMIC_INIT(0);
 
+struct dentry *ras_get_debugfs_root(void)
+{
+	return ras_debugfs_dir;
+}
+EXPORT_SYMBOL_GPL(ras_get_debugfs_root);
+
 int ras_userspace_consumers(void)
 {
 	return atomic_read(&trace_count);
diff --git a/drivers/ras/debugfs.h b/drivers/ras/debugfs.h
index c07443b462ad..4749ccdeeba1 100644
--- a/drivers/ras/debugfs.h
+++ b/drivers/ras/debugfs.h
@@ -4,6 +4,6 @@
 
 #include <linux/debugfs.h>
 
-extern struct dentry *ras_debugfs_dir;
+struct dentry *ras_get_debugfs_root(void);
 
 #endif /* __RAS_DEBUGFS_H__ */
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 95540ea8dd9d..a6e4792a1b2e 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -10,6 +10,37 @@
 #include <linux/ras.h>
 #include <linux/uuid.h>
 
+#if IS_ENABLED(CONFIG_AMD_ATL)
+/*
+ * Once set, this function pointer should never be unset.
+ *
+ * The library module will set this pointer if it successfully loads. The module
+ * should not be unloaded except for testing and debug purposes.
+ */
+static unsigned long (*amd_atl_umc_na_to_spa)(struct atl_err *err);
+
+void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *))
+{
+	amd_atl_umc_na_to_spa = f;
+}
+EXPORT_SYMBOL_GPL(amd_atl_register_decoder);
+
+void amd_atl_unregister_decoder(void)
+{
+	amd_atl_umc_na_to_spa = NULL;
+}
+EXPORT_SYMBOL_GPL(amd_atl_unregister_decoder);
+
+unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err)
+{
+	if (!amd_atl_umc_na_to_spa)
+		return -EINVAL;
+
+	return amd_atl_umc_na_to_spa(err);
+}
+EXPORT_SYMBOL_GPL(amd_convert_umc_mca_addr_to_sys_addr);
+#endif /* CONFIG_AMD_ATL */
+
 #define CREATE_TRACE_POINTS
 #define TRACE_INCLUDE_PATH ../../include/ras
 #include <ras/ras_event.h>
diff --git a/drivers/regulator/max5970-regulator.c b/drivers/regulator/max5970-regulator.c
index bc88a40a88d4..8bbcd983a74a 100644
--- a/drivers/regulator/max5970-regulator.c
+++ b/drivers/regulator/max5970-regulator.c
@@ -29,8 +29,8 @@ struct max5970_regulator {
 };
 
 enum max597x_regulator_id {
-	MAX597X_SW0,
-	MAX597X_SW1,
+	MAX597X_sw0,
+	MAX597X_sw1,
 };
 
 static int max5970_read_adc(struct regmap *regmap, int reg, long *val)
@@ -378,8 +378,8 @@ static int max597x_dt_parse(struct device_node *np,
 }
 
 static const struct regulator_desc regulators[] = {
-	MAX597X_SWITCH(SW0, MAX5970_REG_CHXEN, 0, "vss1"),
-	MAX597X_SWITCH(SW1, MAX5970_REG_CHXEN, 1, "vss2"),
+	MAX597X_SWITCH(sw0, MAX5970_REG_CHXEN, 0, "vss1"),
+	MAX597X_SWITCH(sw1, MAX5970_REG_CHXEN, 1, "vss2"),
 };
 
 static int max597x_regmap_read_clear(struct regmap *map, unsigned int reg,
@@ -392,7 +392,7 @@ static int max597x_regmap_read_clear(struct regmap *map, unsigned int reg,
 		return ret;
 
 	if (*val)
-		return regmap_write(map, reg, *val);
+		return regmap_write(map, reg, 0);
 
 	return 0;
 }
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 698c420e0869..60cfcd741c2a 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -157,7 +157,17 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev)
 
 	pwm_get_state(drvdata->pwm, &pstate);
 
+	if (!pstate.enabled) {
+		if (pstate.polarity == PWM_POLARITY_INVERSED)
+			pstate.duty_cycle = pstate.period;
+		else
+			pstate.duty_cycle = 0;
+	}
+
 	voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit);
+	if (voltage < min(max_uV_duty, min_uV_duty) ||
+	    voltage > max(max_uV_duty, min_uV_duty))
+		return -ENOTRECOVERABLE;
 
 	/*
 	 * The dutycycle for min_uV might be greater than the one for max_uV.
@@ -313,6 +323,32 @@ static int pwm_regulator_init_continuous(struct platform_device *pdev,
 	return 0;
 }
 
+static int pwm_regulator_init_boot_on(struct platform_device *pdev,
+				      struct pwm_regulator_data *drvdata,
+				      const struct regulator_init_data *init_data)
+{
+	struct pwm_state pstate;
+
+	if (!init_data->constraints.boot_on || drvdata->enb_gpio)
+		return 0;
+
+	pwm_get_state(drvdata->pwm, &pstate);
+	if (pstate.enabled)
+		return 0;
+
+	/*
+	 * Update the duty cycle so the output does not change
+	 * when the regulator core enables the regulator (and
+	 * thus the PWM channel).
+	 */
+	if (pstate.polarity == PWM_POLARITY_INVERSED)
+		pstate.duty_cycle = pstate.period;
+	else
+		pstate.duty_cycle = 0;
+
+	return pwm_apply_might_sleep(drvdata->pwm, &pstate);
+}
+
 static int pwm_regulator_probe(struct platform_device *pdev)
 {
 	const struct regulator_init_data *init_data;
@@ -372,6 +408,13 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = pwm_regulator_init_boot_on(pdev, drvdata, init_data);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to apply boot_on settings: %d\n",
+			ret);
+		return ret;
+	}
+
 	regulator = devm_regulator_register(&pdev->dev,
 					    &drvdata->desc, &config);
 	if (IS_ERR(regulator)) {
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index e374fa6e5f28..d89ae7f16d7a 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -1017,14 +1017,14 @@ static const struct regulator_desc rk805_reg[] = {
 };
 
 static const struct linear_range rk806_buck_voltage_ranges[] = {
-	REGULATOR_LINEAR_RANGE(500000, 0, 160, 6250), /* 500mV ~ 1500mV */
-	REGULATOR_LINEAR_RANGE(1500000, 161, 237, 25000), /* 1500mV ~ 3400mV */
-	REGULATOR_LINEAR_RANGE(3400000, 238, 255, 0),
+	REGULATOR_LINEAR_RANGE(500000, 0, 159, 6250), /* 500mV ~ 1500mV */
+	REGULATOR_LINEAR_RANGE(1500000, 160, 235, 25000), /* 1500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(3400000, 236, 255, 0),
 };
 
 static const struct linear_range rk806_ldo_voltage_ranges[] = {
-	REGULATOR_LINEAR_RANGE(500000, 0, 232, 12500), /* 500mV ~ 3400mV */
-	REGULATOR_LINEAR_RANGE(3400000, 233, 255, 0), /* 500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(500000, 0, 231, 12500), /* 500mV ~ 3400mV */
+	REGULATOR_LINEAR_RANGE(3400000, 232, 255, 0),
 };
 
 static const struct regulator_desc rk806_reg[] = {
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index f48214e2c3b4..04133510e5af 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -726,9 +726,25 @@ static int ti_abb_probe(struct platform_device *pdev)
 			return PTR_ERR(abb->setup_reg);
 	}
 
-	abb->int_base = devm_platform_ioremap_resource_byname(pdev, "int-address");
-	if (IS_ERR(abb->int_base))
-		return PTR_ERR(abb->int_base);
+	pname = "int-address";
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, pname);
+	if (!res) {
+		dev_err(dev, "Missing '%s' IO resource\n", pname);
+		return -ENODEV;
+	}
+	/*
+	 * The MPU interrupt status register (PRM_IRQSTATUS_MPU) is
+	 * shared between regulator-abb-{ivahd,dspeve,gpu} driver
+	 * instances. Therefore use devm_ioremap() rather than
+	 * devm_platform_ioremap_resource_byname() to avoid busy
+	 * resource region conflicts.
+	 */
+	abb->int_base = devm_ioremap(dev, res->start,
+					     resource_size(res));
+	if (!abb->int_base) {
+		dev_err(dev, "Unable to map '%s'\n", pname);
+		return -ENOMEM;
+	}
 
 	/* Map Optional resources */
 	pname = "efuse-address";
diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c
index d5caf36c56cd..225c859d6da5 100644
--- a/drivers/rtc/lib_test.c
+++ b/drivers/rtc/lib_test.c
@@ -54,7 +54,7 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test)
 
 		days = div_s64(secs, 86400);
 
-		#define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \
+		#define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \
 			year, month, mday, yday, days
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 7327e81352e9..cead018c3f06 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -8,9 +8,6 @@
  * Copyright IBM Corp. 1999, 2009
  */
 
-#define KMSG_COMPONENT "dasd"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -30,9 +27,6 @@
 #include <asm/itcw.h>
 #include <asm/diag.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd:"
-
 #include "dasd_int.h"
 /*
  * SECTION: Constant definitions to be used within this file
@@ -313,39 +307,57 @@ static int dasd_state_basic_to_known(struct dasd_device *device)
  */
 static int dasd_state_basic_to_ready(struct dasd_device *device)
 {
-	int rc;
-	struct dasd_block *block;
-	struct gendisk *disk;
+	struct dasd_block *block = device->block;
+	struct queue_limits lim;
+	int rc = 0;
 
-	rc = 0;
-	block = device->block;
 	/* make disk known with correct capacity */
-	if (block) {
-		if (block->base->discipline->do_analysis != NULL)
-			rc = block->base->discipline->do_analysis(block);
-		if (rc) {
-			if (rc != -EAGAIN) {
-				device->state = DASD_STATE_UNFMT;
-				disk = device->block->gdp;
-				kobject_uevent(&disk_to_dev(disk)->kobj,
-					       KOBJ_CHANGE);
-				goto out;
-			}
-			return rc;
-		}
-		if (device->discipline->setup_blk_queue)
-			device->discipline->setup_blk_queue(block);
-		set_capacity(block->gdp,
-			     block->blocks << block->s2b_shift);
+	if (!block) {
 		device->state = DASD_STATE_READY;
-		rc = dasd_scan_partitions(block);
-		if (rc) {
-			device->state = DASD_STATE_BASIC;
+		goto out;
+	}
+
+	if (block->base->discipline->do_analysis != NULL)
+		rc = block->base->discipline->do_analysis(block);
+	if (rc) {
+		if (rc == -EAGAIN)
 			return rc;
-		}
-	} else {
-		device->state = DASD_STATE_READY;
+		device->state = DASD_STATE_UNFMT;
+		kobject_uevent(&disk_to_dev(device->block->gdp)->kobj,
+			       KOBJ_CHANGE);
+		goto out;
+	}
+
+	lim = queue_limits_start_update(block->gdp->queue);
+	lim.max_dev_sectors = device->discipline->max_sectors(block);
+	lim.max_hw_sectors = lim.max_dev_sectors;
+	lim.logical_block_size = block->bp_block;
+
+	if (device->discipline->has_discard) {
+		unsigned int max_bytes;
+
+		lim.discard_granularity = block->bp_block;
+
+		/* Calculate max_discard_sectors and make it PAGE aligned */
+		max_bytes = USHRT_MAX * block->bp_block;
+		max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE);
+
+		lim.max_hw_discard_sectors = max_bytes / block->bp_block;
+		lim.max_write_zeroes_sectors = lim.max_hw_discard_sectors;
 	}
+	rc = queue_limits_commit_update(block->gdp->queue, &lim);
+	if (rc)
+		return rc;
+
+	set_capacity(block->gdp, block->blocks << block->s2b_shift);
+	device->state = DASD_STATE_READY;
+
+	rc = dasd_scan_partitions(block);
+	if (rc) {
+		device->state = DASD_STATE_BASIC;
+		return rc;
+	}
+
 out:
 	if (device->discipline->basic_to_ready)
 		rc = device->discipline->basic_to_ready(device);
@@ -412,7 +424,7 @@ dasd_state_ready_to_online(struct dasd_device * device)
 					KOBJ_CHANGE);
 			return 0;
 		}
-		disk_uevent(device->block->bdev_handle->bdev->bd_disk,
+		disk_uevent(file_bdev(device->block->bdev_file)->bd_disk,
 			    KOBJ_CHANGE);
 	}
 	return 0;
@@ -433,7 +445,7 @@ static int dasd_state_online_to_ready(struct dasd_device *device)
 
 	device->state = DASD_STATE_READY;
 	if (device->block && !(device->features & DASD_FEATURE_USERAW))
-		disk_uevent(device->block->bdev_handle->bdev->bd_disk,
+		disk_uevent(file_bdev(device->block->bdev_file)->bd_disk,
 			    KOBJ_CHANGE);
 	return 0;
 }
@@ -1301,7 +1313,6 @@ int dasd_term_IO(struct dasd_ccw_req *cqr)
 {
 	struct dasd_device *device;
 	int retries, rc;
-	char errorstring[ERRORLENGTH];
 
 	/* Check the cqr */
 	rc = dasd_check_cqr(cqr);
@@ -1340,10 +1351,8 @@ int dasd_term_IO(struct dasd_ccw_req *cqr)
 			rc = 0;
 			break;
 		default:
-			/* internal error 10 - unknown rc*/
-			snprintf(errorstring, ERRORLENGTH, "10 %d", rc);
-			dev_err(&device->cdev->dev, "An error occurred in the "
-				"DASD device driver, reason=%s\n", errorstring);
+			dev_err(&device->cdev->dev,
+				"Unexpected error during request termination %d\n", rc);
 			BUG();
 			break;
 		}
@@ -1362,7 +1371,6 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 {
 	struct dasd_device *device;
 	int rc;
-	char errorstring[ERRORLENGTH];
 
 	/* Check the cqr */
 	rc = dasd_check_cqr(cqr);
@@ -1382,10 +1390,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 		return -EPERM;
 	}
 	if (cqr->retries < 0) {
-		/* internal error 14 - start_IO run out of retries */
-		sprintf(errorstring, "14 %p", cqr);
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", errorstring);
+		dev_err(&device->cdev->dev,
+			"Start I/O ran out of retries\n");
 		cqr->status = DASD_CQR_ERROR;
 		return -EIO;
 	}
@@ -1463,11 +1469,8 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
 			      "not accessible");
 		break;
 	default:
-		/* internal error 11 - unknown rc */
-		snprintf(errorstring, ERRORLENGTH, "11 %d", rc);
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", errorstring);
+			"Unexpected error during request start %d", rc);
 		BUG();
 		break;
 	}
@@ -1904,8 +1907,6 @@ static void __dasd_device_process_ccw_queue(struct dasd_device *device,
 static void __dasd_process_cqr(struct dasd_device *device,
 			       struct dasd_ccw_req *cqr)
 {
-	char errorstring[ERRORLENGTH];
-
 	switch (cqr->status) {
 	case DASD_CQR_SUCCESS:
 		cqr->status = DASD_CQR_DONE;
@@ -1917,11 +1918,8 @@ static void __dasd_process_cqr(struct dasd_device *device,
 		cqr->status = DASD_CQR_TERMINATED;
 		break;
 	default:
-		/* internal error 12 - wrong cqr status*/
-		snprintf(errorstring, ERRORLENGTH, "12 %p %x02", cqr, cqr->status);
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", errorstring);
+			"Unexpected CQR status %02x", cqr->status);
 		BUG();
 	}
 	if (cqr->callback)
@@ -1986,16 +1984,14 @@ static void __dasd_device_check_expire(struct dasd_device *device)
 		if (device->discipline->term_IO(cqr) != 0) {
 			/* Hmpf, try again in 5 sec */
 			dev_err(&device->cdev->dev,
-				"cqr %p timed out (%lus) but cannot be "
-				"ended, retrying in 5 s\n",
-				cqr, (cqr->expires/HZ));
+				"CQR timed out (%lus) but cannot be ended, retrying in 5s\n",
+				(cqr->expires / HZ));
 			cqr->expires += 5*HZ;
 			dasd_device_set_timer(device, 5*HZ);
 		} else {
 			dev_err(&device->cdev->dev,
-				"cqr %p timed out (%lus), %i retries "
-				"remaining\n", cqr, (cqr->expires/HZ),
-				cqr->retries);
+				"CQR timed out (%lus), %i retries remaining\n",
+				(cqr->expires / HZ), cqr->retries);
 		}
 		__dasd_device_check_autoquiesce_timeout(device, cqr);
 	}
@@ -2116,8 +2112,7 @@ int dasd_flush_device_queue(struct dasd_device *device)
 			if (rc) {
 				/* unable to terminate requeust */
 				dev_err(&device->cdev->dev,
-					"Flushing the DASD request queue "
-					"failed for request %p\n", cqr);
+					"Flushing the DASD request queue failed\n");
 				/* stop flush processing */
 				goto finished;
 			}
@@ -2633,8 +2628,7 @@ static int __dasd_cancel_req(struct dasd_ccw_req *cqr)
 		rc = device->discipline->term_IO(cqr);
 		if (rc) {
 			dev_err(&device->cdev->dev,
-				"Cancelling request %p failed with rc=%d\n",
-				cqr, rc);
+				"Cancelling request failed with rc=%d\n", rc);
 		} else {
 			cqr->stopclk = get_tod_clock();
 		}
@@ -3402,8 +3396,7 @@ static void dasd_generic_auto_online(void *data, async_cookie_t cookie)
 
 	ret = ccw_device_set_online(cdev);
 	if (ret)
-		pr_warn("%s: Setting the DASD online failed with rc=%d\n",
-			dev_name(&cdev->dev), ret);
+		dev_warn(&cdev->dev, "Setting the DASD online failed with rc=%d\n", ret);
 }
 
 /*
@@ -3490,8 +3483,11 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 {
 	struct dasd_discipline *discipline;
 	struct dasd_device *device;
+	struct device *dev;
 	int rc;
 
+	dev = &cdev->dev;
+
 	/* first online clears initial online feature flag */
 	dasd_set_feature(cdev, DASD_FEATURE_INITIAL_ONLINE, 0);
 	device = dasd_create_device(cdev);
@@ -3504,11 +3500,10 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 			/* Try to load the required module. */
 			rc = request_module(DASD_DIAG_MOD);
 			if (rc) {
-				pr_warn("%s Setting the DASD online failed "
-					"because the required module %s "
-					"could not be loaded (rc=%d)\n",
-					dev_name(&cdev->dev), DASD_DIAG_MOD,
-					rc);
+				dev_warn(dev, "Setting the DASD online failed "
+					 "because the required module %s "
+					 "could not be loaded (rc=%d)\n",
+					 DASD_DIAG_MOD, rc);
 				dasd_delete_device(device);
 				return -ENODEV;
 			}
@@ -3516,8 +3511,7 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 		/* Module init could have failed, so check again here after
 		 * request_module(). */
 		if (!dasd_diag_discipline_pointer) {
-			pr_warn("%s Setting the DASD online failed because of missing DIAG discipline\n",
-				dev_name(&cdev->dev));
+			dev_warn(dev, "Setting the DASD online failed because of missing DIAG discipline\n");
 			dasd_delete_device(device);
 			return -ENODEV;
 		}
@@ -3527,37 +3521,33 @@ int dasd_generic_set_online(struct ccw_device *cdev,
 		dasd_delete_device(device);
 		return -EINVAL;
 	}
+	device->base_discipline = base_discipline;
 	if (!try_module_get(discipline->owner)) {
-		module_put(base_discipline->owner);
 		dasd_delete_device(device);
 		return -EINVAL;
 	}
-	device->base_discipline = base_discipline;
 	device->discipline = discipline;
 
 	/* check_device will allocate block device if necessary */
 	rc = discipline->check_device(device);
 	if (rc) {
-		pr_warn("%s Setting the DASD online with discipline %s failed with rc=%i\n",
-			dev_name(&cdev->dev), discipline->name, rc);
-		module_put(discipline->owner);
-		module_put(base_discipline->owner);
+		dev_warn(dev, "Setting the DASD online with discipline %s failed with rc=%i\n",
+			 discipline->name, rc);
 		dasd_delete_device(device);
 		return rc;
 	}
 
 	dasd_set_target_state(device, DASD_STATE_ONLINE);
 	if (device->state <= DASD_STATE_KNOWN) {
-		pr_warn("%s Setting the DASD online failed because of a missing discipline\n",
-			dev_name(&cdev->dev));
+		dev_warn(dev, "Setting the DASD online failed because of a missing discipline\n");
 		rc = -ENODEV;
 		dasd_set_target_state(device, DASD_STATE_NEW);
 		if (device->block)
 			dasd_free_block(device->block);
 		dasd_delete_device(device);
-	} else
-		pr_debug("dasd_generic device %s found\n",
-				dev_name(&cdev->dev));
+	} else {
+		dev_dbg(dev, "dasd_generic device found\n");
+	}
 
 	wait_event(dasd_init_waitq, _wait_for_device(device));
 
@@ -3568,10 +3558,13 @@ EXPORT_SYMBOL_GPL(dasd_generic_set_online);
 
 int dasd_generic_set_offline(struct ccw_device *cdev)
 {
+	int max_count, open_count, rc;
 	struct dasd_device *device;
 	struct dasd_block *block;
-	int max_count, open_count, rc;
 	unsigned long flags;
+	struct device *dev;
+
+	dev = &cdev->dev;
 
 	rc = 0;
 	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
@@ -3588,15 +3581,14 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 	 * in the other openers.
 	 */
 	if (device->block) {
-		max_count = device->block->bdev_handle ? 0 : -1;
+		max_count = device->block->bdev_file ? 0 : -1;
 		open_count = atomic_read(&device->block->open_count);
 		if (open_count > max_count) {
 			if (open_count > 0)
-				pr_warn("%s: The DASD cannot be set offline with open count %i\n",
-					dev_name(&cdev->dev), open_count);
+				dev_warn(dev, "The DASD cannot be set offline with open count %i\n",
+					 open_count);
 			else
-				pr_warn("%s: The DASD cannot be set offline while it is in use\n",
-					dev_name(&cdev->dev));
+				dev_warn(dev, "The DASD cannot be set offline while it is in use\n");
 			rc = -EBUSY;
 			goto out_err;
 		}
@@ -3634,8 +3626,8 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 		 * so sync bdev first and then wait for our queues to become
 		 * empty
 		 */
-		if (device->block && device->block->bdev_handle)
-			bdev_mark_dead(device->block->bdev_handle->bdev, false);
+		if (device->block && device->block->bdev_file)
+			bdev_mark_dead(file_bdev(device->block->bdev_file), false);
 		dasd_schedule_device_bh(device);
 		rc = wait_event_interruptible(shutdown_waitq,
 					      _wait_for_empty_queues(device));
@@ -3956,8 +3948,8 @@ static int dasd_handle_autoquiesce(struct dasd_device *device,
 	if (dasd_eer_enabled(device))
 		dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE);
 
-	pr_info("%s: The DASD has been put in the quiesce state\n",
-		dev_name(&device->cdev->dev));
+	dev_info(&device->cdev->dev,
+		 "The DASD has been put in the quiesce state\n");
 	dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE);
 
 	if (device->features & DASD_FEATURE_REQUEUEQUIESCE)
@@ -3977,10 +3969,8 @@ static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device,
 				   NULL);
 
 	if (IS_ERR(cqr)) {
-		/* internal error 13 - Allocating the RDC request failed*/
-		dev_err(&device->cdev->dev,
-			 "An error occurred in the DASD device driver, "
-			 "reason=%s\n", "13");
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
+				"Could not allocate RDC request");
 		return cqr;
 	}
 
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 89957bb7244d..459b7f8ac883 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -7,13 +7,9 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/timer.h>
 #include <asm/idals.h>
 
-#define PRINTK_HEADER "dasd_erp(3990): "
-
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
@@ -398,7 +394,6 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense)
 	struct dasd_device *device = erp->startdev;
 	char msg_format = (sense[7] & 0xF0);
 	char msg_no = (sense[7] & 0x0F);
-	char errorstring[ERRORLENGTH];
 
 	switch (msg_format) {
 	case 0x00:		/* Format 0 - Program or System Checks */
@@ -1004,12 +999,9 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense)
 		}
 		break;
 
-	default:	/* unknown message format - should not happen
-			   internal error 03 - unknown message format */
-		snprintf(errorstring, ERRORLENGTH, "03 %x02", msg_format);
+	default:
 		dev_err(&device->cdev->dev,
-			 "An error occurred in the DASD device driver, "
-			 "reason=%s\n", errorstring);
+			"Unknown message format %02x", msg_format);
 		break;
 	}			/* end switch message format */
 
@@ -1056,11 +1048,9 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense)
 		set_bit(DASD_CQR_SUPPRESS_CR, &erp->refers->flags);
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	} else {
-		/* fatal error -  set status to FAILED
-		   internal error 09 - Command Reject */
 		if (!test_bit(DASD_CQR_SUPPRESS_CR, &erp->flags))
 			dev_err(&device->cdev->dev,
-				"An error occurred in the DASD device driver, reason=09\n");
+				"An I/O command request was rejected\n");
 
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
@@ -1128,13 +1118,7 @@ dasd_3990_erp_equip_check(struct dasd_ccw_req * erp, char *sense)
 	erp->function = dasd_3990_erp_equip_check;
 
 	if (sense[1] & SNS1_WRITE_INHIBITED) {
-		dev_info(&device->cdev->dev,
-			    "Write inhibited path encountered\n");
-
-		/* vary path offline
-		   internal error 04 - Path should be varied off-line.*/
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "04");
+		dev_err(&device->cdev->dev, "Write inhibited path encountered\n");
 
 		erp = dasd_3990_erp_action_1(erp);
 
@@ -1285,11 +1269,7 @@ dasd_3990_erp_inv_format(struct dasd_ccw_req * erp, char *sense)
 		erp = dasd_3990_erp_action_4(erp, sense);
 
 	} else {
-		/* internal error 06 - The track format is not valid*/
-		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", "06");
-
+		dev_err(&device->cdev->dev, "Track format is not valid\n");
 		erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 	}
 
@@ -1663,9 +1643,8 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense)
 				     sizeof(struct LO_eckd_data), device);
 
 	if (IS_ERR(erp)) {
-		/* internal error 01 - Unable to allocate ERP */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "01");
+		DBF_DEV_EVENT(DBF_ERR, device, "%s",
+			      "Unable to allocate ERP request (1B 32)");
 		return dasd_3990_erp_cleanup(default_erp, DASD_CQR_FAILED);
 	}
 
@@ -1807,10 +1786,8 @@ dasd_3990_update_1B(struct dasd_ccw_req * previous_erp, char *sense)
 	cpa = previous_erp->irb.scsw.cmd.cpa;
 
 	if (cpa == 0) {
-		/* internal error 02 -
-		   Unable to determine address of the CCW to be restarted */
-		dev_err(&device->cdev->dev, "An error occurred in the DASD "
-			"device driver, reason=%s\n", "02");
+		dev_err(&device->cdev->dev,
+			"Unable to determine address of to be restarted CCW\n");
 
 		previous_erp->status = DASD_CQR_FAILED;
 
@@ -2009,15 +1986,9 @@ dasd_3990_erp_compound_config(struct dasd_ccw_req * erp, char *sense)
 {
 
 	if ((sense[25] & DASD_SENSE_BIT_1) && (sense[26] & DASD_SENSE_BIT_2)) {
-
-		/* set to suspended duplex state then restart
-		   internal error 05 - Set device to suspended duplex state
-		   should be done */
 		struct dasd_device *device = erp->startdev;
 		dev_err(&device->cdev->dev,
-			"An error occurred in the DASD device driver, "
-			"reason=%s\n", "05");
-
+			"Compound configuration error occurred\n");
 	}
 
 	erp->function = dasd_3990_erp_compound_config;
@@ -2153,10 +2124,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense)
 			erp = dasd_3990_erp_int_req(erp);
 			break;
 
-		case 0x0F:  /* length mismatch during update write command
-			       internal error 08 - update write command error*/
-			dev_err(&device->cdev->dev, "An error occurred in the "
-				"DASD device driver, reason=%s\n", "08");
+		case 0x0F:
+			dev_err(&device->cdev->dev,
+				"Update write command error occurred\n");
 
 			erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 			break;
@@ -2165,12 +2135,9 @@ dasd_3990_erp_inspect_32(struct dasd_ccw_req * erp, char *sense)
 			erp = dasd_3990_erp_action_10_32(erp, sense);
 			break;
 
-		case 0x15:	/* next track outside defined extend
-				   internal error 07 - The next track is not
-				   within the defined storage extent */
+		case 0x15:
 			dev_err(&device->cdev->dev,
-				"An error occurred in the DASD device driver, "
-				"reason=%s\n", "07");
+				"Track outside defined extent error occurred\n");
 
 			erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
 			break;
@@ -2663,7 +2630,7 @@ dasd_3990_erp_further_erp(struct dasd_ccw_req *erp)
 		 * necessary
 		 */
 		dev_err(&device->cdev->dev,
-			"ERP %p has run out of retries and failed\n", erp);
+			"ERP %px has run out of retries and failed\n", erp);
 
 		erp->status = DASD_CQR_FAILED;
 	}
@@ -2704,8 +2671,7 @@ dasd_3990_erp_handle_match_erp(struct dasd_ccw_req *erp_head,
 	while (erp_done != erp) {
 
 		if (erp_done == NULL)	/* end of chain reached */
-			panic(PRINTK_HEADER "Programming error in ERP! The "
-			      "original request was lost\n");
+			panic("Programming error in ERP! The original request was lost\n");
 
 		/* remove the request from the device queue */
 		list_del(&erp_done->blocklist);
@@ -2786,11 +2752,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr)
 			    "ERP chain at BEGINNING of ERP-ACTION\n");
 		for (temp_erp = cqr;
 		     temp_erp != NULL; temp_erp = temp_erp->refers) {
-
 			dev_err(&device->cdev->dev,
-				    "ERP %p (%02x) refers to %p\n",
-				    temp_erp, temp_erp->status,
-				    temp_erp->refers);
+				"ERP %px (%02x) refers to %px\n",
+				temp_erp, temp_erp->status, temp_erp->refers);
 		}
 	}
 
@@ -2837,11 +2801,9 @@ dasd_3990_erp_action(struct dasd_ccw_req * cqr)
 			    "ERP chain at END of ERP-ACTION\n");
 		for (temp_erp = erp;
 		     temp_erp != NULL; temp_erp = temp_erp->refers) {
-
 			dev_err(&device->cdev->dev,
-				    "ERP %p (%02x) refers to %p\n",
-				    temp_erp, temp_erp->status,
-				    temp_erp->refers);
+				"ERP %px (%02x) refers to %px\n",
+				temp_erp, temp_erp->status, temp_erp->refers);
 		}
 	}
 
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index c9740ae88d1a..e84cd5436556 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -6,20 +6,12 @@
  * Author(s): Stefan Weinhuber <wein@de.ibm.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eckd):"
-
-
 /*
  * General concept of alias management:
  * - PAV and DASD alias management is specific to the eckd discipline.
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index c4e36650c426..0316c20823ee 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -13,8 +13,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -24,8 +22,6 @@
 #include <linux/uaccess.h>
 #include <asm/ipl.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_devmap:"
 #define DASD_MAX_PARAMS 256
 
 #include "dasd_int.h"
@@ -1114,7 +1110,7 @@ dasd_use_diag_show(struct device *dev, struct device_attribute *attr, char *buf)
 		use_diag = (devmap->features & DASD_FEATURE_USEDIAG) != 0;
 	else
 		use_diag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USEDIAG) != 0;
-	return sprintf(buf, use_diag ? "1\n" : "0\n");
+	return sysfs_emit(buf, use_diag ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1163,7 +1159,7 @@ dasd_use_raw_show(struct device *dev, struct device_attribute *attr, char *buf)
 		use_raw = (devmap->features & DASD_FEATURE_USERAW) != 0;
 	else
 		use_raw = (DASD_FEATURE_DEFAULT & DASD_FEATURE_USERAW) != 0;
-	return sprintf(buf, use_raw ? "1\n" : "0\n");
+	return sysfs_emit(buf, use_raw ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1259,7 +1255,7 @@ dasd_access_show(struct device *dev, struct device_attribute *attr,
 	if (count < 0)
 		return count;
 
-	return sprintf(buf, "%d\n", count);
+	return sysfs_emit(buf, "%d\n", count);
 }
 
 static DEVICE_ATTR(host_access_count, 0444, dasd_access_show, NULL);
@@ -1338,19 +1334,19 @@ static ssize_t dasd_alias_show(struct device *dev,
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
-		return sprintf(buf, "0\n");
+		return sysfs_emit(buf, "0\n");
 
 	if (device->discipline && device->discipline->get_uid &&
 	    !device->discipline->get_uid(device, &uid)) {
 		if (uid.type == UA_BASE_PAV_ALIAS ||
 		    uid.type == UA_HYPER_PAV_ALIAS) {
 			dasd_put_device(device);
-			return sprintf(buf, "1\n");
+			return sysfs_emit(buf, "1\n");
 		}
 	}
 	dasd_put_device(device);
 
-	return sprintf(buf, "0\n");
+	return sysfs_emit(buf, "0\n");
 }
 
 static DEVICE_ATTR(alias, 0444, dasd_alias_show, NULL);
@@ -1412,15 +1408,9 @@ dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 			break;
 		}
 
-		if (strlen(uid.vduit) > 0)
-			snprintf(uid_string, sizeof(uid_string),
-				 "%s.%s.%04x.%s.%s",
-				 uid.vendor, uid.serial, uid.ssid, ua_string,
-				 uid.vduit);
-		else
-			snprintf(uid_string, sizeof(uid_string),
-				 "%s.%s.%04x.%s",
-				 uid.vendor, uid.serial, uid.ssid, ua_string);
+		snprintf(uid_string, sizeof(uid_string), "%s.%s.%04x.%s%s%s",
+			 uid.vendor, uid.serial, uid.ssid, ua_string,
+			 uid.vduit[0] ? "." : "", uid.vduit);
 	}
 	dasd_put_device(device);
 
@@ -1862,7 +1852,7 @@ static ssize_t dasd_pm_show(struct device *dev,
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
-		return sprintf(buf, "0\n");
+		return sysfs_emit(buf, "0\n");
 
 	opm = dasd_path_get_opm(device);
 	nppm = dasd_path_get_nppm(device);
@@ -1872,8 +1862,8 @@ static ssize_t dasd_pm_show(struct device *dev,
 	ifccpm = dasd_path_get_ifccpm(device);
 	dasd_put_device(device);
 
-	return sprintf(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm,
-		       cablepm, cuirpm, hpfpm, ifccpm);
+	return sysfs_emit(buf, "%02x %02x %02x %02x %02x %02x\n", opm, nppm,
+			  cablepm, cuirpm, hpfpm, ifccpm);
 }
 
 static DEVICE_ATTR(path_masks, 0444, dasd_pm_show, NULL);
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index 2e4e555b37c3..ea4b1d01bb76 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -8,8 +8,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/kernel_stat.h>
 #include <linux/stddef.h>
 #include <linux/kernel.h>
@@ -31,8 +29,6 @@
 #include "dasd_int.h"
 #include "dasd_diag.h"
 
-#define PRINTK_HEADER "dasd(diag):"
-
 MODULE_LICENSE("GPL");
 
 /* The maximum number of blocks per request (max_blocks) is dependent on the
@@ -621,25 +617,9 @@ dasd_diag_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		    "dump sense not available for DIAG data");
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_diag_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_diag_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	int max;
-
-	max = DIAG_MAX_BLOCKS << block->s2b_shift;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, PAGE_SIZE - 1);
+	return DIAG_MAX_BLOCKS << block->s2b_shift;
 }
 
 static int dasd_diag_pe_handler(struct dasd_device *device,
@@ -652,10 +632,10 @@ static struct dasd_discipline dasd_diag_discipline = {
 	.owner = THIS_MODULE,
 	.name = "DIAG",
 	.ebcname = "DIAG",
+	.max_sectors = dasd_diag_max_sectors,
 	.check_device = dasd_diag_check_device,
 	.pe_handler = dasd_diag_pe_handler,
 	.fill_geometry = dasd_diag_fill_geometry,
-	.setup_blk_queue = dasd_diag_setup_blk_queue,
 	.start_IO = dasd_start_diag,
 	.term_IO = dasd_diag_term_IO,
 	.handle_terminated_request = dasd_diag_handle_terminated_request,
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bd89b032968a..373c1a86c33e 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -10,8 +10,6 @@
  * Author.........: Nigel Hislop <hislop_nigel@emc.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -37,11 +35,6 @@
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eckd):"
-
 /*
  * raw track access always map to 64k in memory
  * so it maps to 16 blocks of 4k per track
@@ -1072,22 +1065,14 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device)
 	}
 }
 
-static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
-				     char *print_uid)
+static void dasd_eckd_get_uid_string(struct dasd_conf *conf, char *print_uid)
 {
 	struct dasd_uid uid;
 
 	create_uid(conf, &uid);
-	if (strlen(uid.vduit) > 0)
-		snprintf(print_uid, DASD_UID_STRLEN,
-			 "%s.%s.%04x.%02x.%s",
-			 uid.vendor, uid.serial, uid.ssid,
-			 uid.real_unit_addr, uid.vduit);
-	else
-		snprintf(print_uid, DASD_UID_STRLEN,
-			 "%s.%s.%04x.%02x",
-			 uid.vendor, uid.serial, uid.ssid,
-			 uid.real_unit_addr);
+	snprintf(print_uid, DASD_UID_STRLEN, "%s.%s.%04x.%02x%s%s",
+		 uid.vendor, uid.serial, uid.ssid, uid.real_unit_addr,
+		 uid.vduit[0] ? "." : "", uid.vduit);
 }
 
 static int dasd_eckd_check_cabling(struct dasd_device *device,
@@ -5529,15 +5514,15 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp)
  * and return number of printed chars.
  */
 static void
-dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page)
+dasd_eckd_dump_ccw_range(struct dasd_device *device, struct ccw1 *from,
+			 struct ccw1 *to, char *page)
 {
 	int len, count;
 	char *datap;
 
 	len = 0;
 	while (from <= to) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       from, ((int *) from)[0], ((int *) from)[1]);
 
 		/* get pointer to data (consider IDALs) */
@@ -5560,7 +5545,7 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page)
 		from++;
 	}
 	if (len > 0)
-		printk(KERN_ERR "%s", page);
+		dev_err(&device->cdev->dev, "%s", page);
 }
 
 static void
@@ -5591,9 +5576,12 @@ dasd_eckd_dump_sense_dbf(struct dasd_device *device, struct irb *irb,
 static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 				 struct dasd_ccw_req *req, struct irb *irb)
 {
-	char *page;
 	struct ccw1 *first, *last, *fail, *from, *to;
+	struct device *dev;
 	int len, sl, sct;
+	char *page;
+
+	dev = &device->cdev->dev;
 
 	page = (char *) get_zeroed_page(GFP_ATOMIC);
 	if (page == NULL) {
@@ -5602,24 +5590,18 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
-		       "CS:%02X RC:%d\n",
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len,
+		       "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X CS:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
 		       scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw),
 		       scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw),
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing CCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len += sprintf(page + len, "Failing CCW: %px\n",
 		       phys_to_virt(irb->scsw.cmd.cpa));
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, PRINTK_HEADER
-				       " Sense(hex) %2d-%2d:",
+			len += sprintf(page + len, "Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
 			for (sct = 0; sct < 8; sct++) {
@@ -5631,23 +5613,20 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 
 		if (irb->ecw[27] & DASD_SENSE_BIT_0) {
 			/* 24 Byte Sense Data */
-			sprintf(page + len, PRINTK_HEADER
-				" 24 Byte: %x MSG %x, "
-				"%s MSGb to SYSOP\n",
+			sprintf(page + len,
+				"24 Byte: %x MSG %x, %s MSGb to SYSOP\n",
 				irb->ecw[7] >> 4, irb->ecw[7] & 0x0f,
 				irb->ecw[1] & 0x10 ? "" : "no");
 		} else {
 			/* 32 Byte Sense Data */
-			sprintf(page + len, PRINTK_HEADER
-				" 32 Byte: Format: %x "
-				"Exception class %x\n",
+			sprintf(page + len,
+				"32 Byte: Format: %x Exception class %x\n",
 				irb->ecw[6] & 0x0f, irb->ecw[22] >> 4);
 		}
 	} else {
-		sprintf(page + len, PRINTK_HEADER
-			" SORRY - NO VALID SENSE AVAILABLE\n");
+		sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(dev, "%s", page);
 
 	if (req) {
 		/* req == NULL for unsolicited interrupts */
@@ -5656,8 +5635,8 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		first = req->cpaddr;
 		for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 		to = min(first + 6, last);
-		printk(KERN_ERR PRINTK_HEADER " Related CP in req: %p\n", req);
-		dasd_eckd_dump_ccw_range(first, to, page);
+		dev_err(dev, "Related CP in req: %px\n", req);
+		dasd_eckd_dump_ccw_range(device, first, to, page);
 
 		/* print failing CCW area (maximum 4) */
 		/* scsw->cda is either valid or zero  */
@@ -5665,19 +5644,19 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device,
 		fail = phys_to_virt(irb->scsw.cmd.cpa); /* failing CCW */
 		if (from <  fail - 2) {
 			from = fail - 2;     /* there is a gap - print header */
-			printk(KERN_ERR PRINTK_HEADER "......\n");
+			dev_err(dev, "......\n");
 		}
 		to = min(fail + 1, last);
-		dasd_eckd_dump_ccw_range(from, to, page + len);
+		dasd_eckd_dump_ccw_range(device, from, to, page + len);
 
 		/* print last CCWs (maximum 2) */
 		len = 0;
 		from = max(from, ++to);
 		if (from < last - 1) {
 			from = last - 1;     /* there is a gap - print header */
-			printk(KERN_ERR PRINTK_HEADER "......\n");
+			dev_err(dev, "......\n");
 		}
-		dasd_eckd_dump_ccw_range(from, last, page + len);
+		dasd_eckd_dump_ccw_range(device, from, last, page + len);
 	}
 	free_page((unsigned long) page);
 }
@@ -5701,11 +5680,9 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		return;
 	}
 	/* dump the sense data */
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len,
+		       "in req: %px CC:%02X FC:%02X AC:%02X SC:%02X DS:%02X "
 		       "CS:%02X fcxs:%02X schxs:%02X RC:%d\n",
 		       req, scsw_cc(&irb->scsw), scsw_fctl(&irb->scsw),
 		       scsw_actl(&irb->scsw), scsw_stctl(&irb->scsw),
@@ -5713,9 +5690,7 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		       irb->scsw.tm.fcxs,
 		       (irb->scsw.tm.ifob << 7) | irb->scsw.tm.sesq,
 		       req ? req->intrc : 0);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing TCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len += sprintf(page + len, "Failing TCW: %px\n",
 		       phys_to_virt(irb->scsw.tm.tcw));
 
 	tsb = NULL;
@@ -5724,47 +5699,37 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 		tsb = tcw_get_tsb(phys_to_virt(irb->scsw.tm.tcw));
 
 	if (tsb) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->length %d\n", tsb->length);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->flags %x\n", tsb->flags);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->dcw_offset %d\n", tsb->dcw_offset);
-		len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->count %d\n", tsb->count);
+		len += sprintf(page + len, "tsb->length %d\n", tsb->length);
+		len += sprintf(page + len, "tsb->flags %x\n", tsb->flags);
+		len += sprintf(page + len, "tsb->dcw_offset %d\n", tsb->dcw_offset);
+		len += sprintf(page + len, "tsb->count %d\n", tsb->count);
 		residual = tsb->count - 28;
-		len += sprintf(page + len, PRINTK_HEADER
-			       " residual %d\n", residual);
+		len += sprintf(page + len, "residual %d\n", residual);
 
 		switch (tsb->flags & 0x07) {
 		case 1:	/* tsa_iostat */
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_time %d\n",
 				       tsb->tsa.iostat.dev_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.def_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.def_time %d\n",
 				       tsb->tsa.iostat.def_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.queue_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.queue_time %d\n",
 				       tsb->tsa.iostat.queue_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_busy_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_busy_time %d\n",
 				       tsb->tsa.iostat.dev_busy_time);
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.iostat.dev_act_time %d\n",
+			len += sprintf(page + len, "tsb->tsa.iostat.dev_act_time %d\n",
 				       tsb->tsa.iostat.dev_act_time);
 			sense = tsb->tsa.iostat.sense;
 			break;
 		case 2: /* ts_ddpc */
-			len += sprintf(page + len, PRINTK_HEADER
-			       " tsb->tsa.ddpc.rc %d\n", tsb->tsa.ddpc.rc);
+			len += sprintf(page + len, "tsb->tsa.ddpc.rc %d\n",
+				       tsb->tsa.ddpc.rc);
 			for (sl = 0; sl < 2; sl++) {
-				len += sprintf(page + len, PRINTK_HEADER
-					       " tsb->tsa.ddpc.rcq %2d-%2d: ",
+				len += sprintf(page + len,
+					       "tsb->tsa.ddpc.rcq %2d-%2d: ",
 					       (8 * sl), ((8 * sl) + 7));
 				rcq = tsb->tsa.ddpc.rcq;
 				for (sct = 0; sct < 8; sct++) {
-					len += sprintf(page + len, " %02x",
+					len += sprintf(page + len, "%02x",
 						       rcq[8 * sl + sct]);
 				}
 				len += sprintf(page + len, "\n");
@@ -5772,15 +5737,15 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 			sense = tsb->tsa.ddpc.sense;
 			break;
 		case 3: /* tsa_intrg */
-			len += sprintf(page + len, PRINTK_HEADER
-				      " tsb->tsa.intrg.: not supported yet\n");
+			len += sprintf(page + len,
+				      "tsb->tsa.intrg.: not supported yet\n");
 			break;
 		}
 
 		if (sense) {
 			for (sl = 0; sl < 4; sl++) {
-				len += sprintf(page + len, PRINTK_HEADER
-					       " Sense(hex) %2d-%2d:",
+				len += sprintf(page + len,
+					       "Sense(hex) %2d-%2d:",
 					       (8 * sl), ((8 * sl) + 7));
 				for (sct = 0; sct < 8; sct++) {
 					len += sprintf(page + len, " %02x",
@@ -5791,27 +5756,23 @@ static void dasd_eckd_dump_sense_tcw(struct dasd_device *device,
 
 			if (sense[27] & DASD_SENSE_BIT_0) {
 				/* 24 Byte Sense Data */
-				sprintf(page + len, PRINTK_HEADER
-					" 24 Byte: %x MSG %x, "
-					"%s MSGb to SYSOP\n",
+				sprintf(page + len,
+					"24 Byte: %x MSG %x, %s MSGb to SYSOP\n",
 					sense[7] >> 4, sense[7] & 0x0f,
 					sense[1] & 0x10 ? "" : "no");
 			} else {
 				/* 32 Byte Sense Data */
-				sprintf(page + len, PRINTK_HEADER
-					" 32 Byte: Format: %x "
-					"Exception class %x\n",
+				sprintf(page + len,
+					"32 Byte: Format: %x Exception class %x\n",
 					sense[6] & 0x0f, sense[22] >> 4);
 			}
 		} else {
-			sprintf(page + len, PRINTK_HEADER
-				" SORRY - NO VALID SENSE AVAILABLE\n");
+			sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 		}
 	} else {
-		sprintf(page + len, PRINTK_HEADER
-			" SORRY - NO TSB DATA AVAILABLE\n");
+		sprintf(page + len, "SORRY - NO TSB DATA AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(&device->cdev->dev, "%s", page);
 	free_page((unsigned long) page);
 }
 
@@ -6865,17 +6826,9 @@ static void dasd_eckd_handle_hpf_error(struct dasd_device *device,
 	dasd_schedule_requeue(device);
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_eckd_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	struct dasd_device *device = block->base;
-	int max;
-
-	if (device->features & DASD_FEATURE_USERAW) {
+	if (block->base->features & DASD_FEATURE_USERAW) {
 		/*
 		 * the max_blocks value for raw_track access is 256
 		 * it is higher than the native ECKD value because we
@@ -6883,19 +6836,10 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
 		 * so the max_hw_sectors are
 		 * 2048 x 512B = 1024kB = 16 tracks
 		 */
-		max = DASD_ECKD_MAX_BLOCKS_RAW << block->s2b_shift;
-	} else {
-		max = DASD_ECKD_MAX_BLOCKS << block->s2b_shift;
+		return DASD_ECKD_MAX_BLOCKS_RAW << block->s2b_shift;
 	}
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, PAGE_SIZE - 1);
+
+	return DASD_ECKD_MAX_BLOCKS << block->s2b_shift;
 }
 
 static struct ccw_driver dasd_eckd_driver = {
@@ -6927,7 +6871,7 @@ static struct dasd_discipline dasd_eckd_discipline = {
 	.basic_to_ready = dasd_eckd_basic_to_ready,
 	.online_to_ready = dasd_eckd_online_to_ready,
 	.basic_to_known = dasd_eckd_basic_to_known,
-	.setup_blk_queue = dasd_eckd_setup_blk_queue,
+	.max_sectors = dasd_eckd_max_sectors,
 	.fill_geometry = dasd_eckd_fill_geometry,
 	.start_IO = dasd_start_IO,
 	.term_IO = dasd_term_IO,
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index c956de711cf7..5064a616e041 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -7,8 +7,6 @@
  *  Author(s): Stefan Weinhuber <wein@de.ibm.com>
  */
 
-#define KMSG_COMPONENT "dasd-eckd"
-
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -28,11 +26,6 @@
 #include "dasd_int.h"
 #include "dasd_eckd.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(eer):"
-
 /*
  * SECTION: the internal buffer
  */
diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c
index c07e6e713518..4c0d3a704513 100644
--- a/drivers/s390/block/dasd_erp.c
+++ b/drivers/s390/block/dasd_erp.c
@@ -9,8 +9,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/init.h>
 
@@ -18,9 +16,6 @@
 #include <asm/ebcdic.h>
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_erp:"
-
 #include "dasd_int.h"
 
 struct dasd_ccw_req *
@@ -170,12 +165,12 @@ dasd_log_sense(struct dasd_ccw_req *cqr, struct irb *irb)
 	device = cqr->startdev;
 	if (cqr->intrc == -ETIMEDOUT) {
 		dev_err(&device->cdev->dev,
-			"A timeout error occurred for cqr %p\n", cqr);
+			"A timeout error occurred for cqr %px\n", cqr);
 		return;
 	}
 	if (cqr->intrc == -ENOLINK) {
 		dev_err(&device->cdev->dev,
-			"A transport error occurred for cqr %p\n", cqr);
+			"A transport error occurred for cqr %px\n", cqr);
 		return;
 	}
 	/* dump sense data */
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index c06fa2b27120..bcbb2f8e91fe 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -25,11 +25,6 @@
 #include "dasd_int.h"
 #include "dasd_fba.h"
 
-#ifdef PRINTK_HEADER
-#undef PRINTK_HEADER
-#endif				/* PRINTK_HEADER */
-#define PRINTK_HEADER "dasd(fba):"
-
 #define FBA_DEFAULT_RETRIES 32
 
 #define DASD_FBA_CCW_WRITE 0x41
@@ -660,30 +655,27 @@ static void
 dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		    struct irb *irb)
 {
-	char *page;
 	struct ccw1 *act, *end, *last;
 	int len, sl, sct, count;
+	struct device *dev;
+	char *page;
+
+	dev = &device->cdev->dev;
 
 	page = (char *) get_zeroed_page(GFP_ATOMIC);
 	if (page == NULL) {
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
-			    "No memory to dump sense data");
+			      "No memory to dump sense data");
 		return;
 	}
-	len = sprintf(page, PRINTK_HEADER
-		      " I/O status report for device %s:\n",
-		      dev_name(&device->cdev->dev));
-	len += sprintf(page + len, PRINTK_HEADER
-		       " in req: %p CS: 0x%02X DS: 0x%02X\n", req,
-		       irb->scsw.cmd.cstat, irb->scsw.cmd.dstat);
-	len += sprintf(page + len, PRINTK_HEADER
-		       " device %s: Failing CCW: %p\n",
-		       dev_name(&device->cdev->dev),
+	len = sprintf(page, "I/O status report:\n");
+	len += sprintf(page + len, "in req: %px CS: 0x%02X DS: 0x%02X\n",
+		       req, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat);
+	len += sprintf(page + len, "Failing CCW: %px\n",
 		       (void *) (addr_t) irb->scsw.cmd.cpa);
 	if (irb->esw.esw0.erw.cons) {
 		for (sl = 0; sl < 4; sl++) {
-			len += sprintf(page + len, PRINTK_HEADER
-				       " Sense(hex) %2d-%2d:",
+			len += sprintf(page + len, "Sense(hex) %2d-%2d:",
 				       (8 * sl), ((8 * sl) + 7));
 
 			for (sct = 0; sct < 8; sct++) {
@@ -693,20 +685,18 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 			len += sprintf(page + len, "\n");
 		}
 	} else {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " SORRY - NO VALID SENSE AVAILABLE\n");
+		len += sprintf(page + len, "SORRY - NO VALID SENSE AVAILABLE\n");
 	}
-	printk(KERN_ERR "%s", page);
+	dev_err(dev, "%s", page);
 
 	/* dump the Channel Program */
 	/* print first CCWs (maximum 8) */
 	act = req->cpaddr;
-        for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
+	for (last = act; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++);
 	end = min(act + 8, last);
-	len = sprintf(page, PRINTK_HEADER " Related CP in req: %p\n", req);
+	len = sprintf(page, "Related CP in req: %px\n", req);
 	while (act <= end) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -716,19 +706,17 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		len += sprintf(page + len, "\n");
 		act++;
 	}
-	printk(KERN_ERR "%s", page);
-
+	dev_err(dev, "%s", page);
 
 	/* print failing CCW area */
 	len = 0;
 	if (act <  ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2) {
 		act = ((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa) - 2;
-		len += sprintf(page + len, PRINTK_HEADER "......\n");
+		len += sprintf(page + len, "......\n");
 	}
 	end = min((struct ccw1 *)(addr_t) irb->scsw.cmd.cpa + 2, last);
 	while (act <= end) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -742,11 +730,10 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 	/* print last CCWs */
 	if (act <  last - 2) {
 		act = last - 2;
-		len += sprintf(page + len, PRINTK_HEADER "......\n");
+		len += sprintf(page + len, "......\n");
 	}
 	while (act <= last) {
-		len += sprintf(page + len, PRINTK_HEADER
-			       " CCW %p: %08X %08X DAT:",
+		len += sprintf(page + len, "CCW %px: %08X %08X DAT:",
 			       act, ((int *) act)[0], ((int *) act)[1]);
 		for (count = 0; count < 32 && count < act->count;
 		     count += sizeof(int))
@@ -757,39 +744,13 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req,
 		act++;
 	}
 	if (len > 0)
-		printk(KERN_ERR "%s", page);
+		dev_err(dev, "%s", page);
 	free_page((unsigned long) page);
 }
 
-/*
- * Initialize block layer request queue.
- */
-static void dasd_fba_setup_blk_queue(struct dasd_block *block)
+static unsigned int dasd_fba_max_sectors(struct dasd_block *block)
 {
-	unsigned int logical_block_size = block->bp_block;
-	struct request_queue *q = block->gdp->queue;
-	unsigned int max_bytes, max_discard_sectors;
-	int max;
-
-	max = DASD_FBA_MAX_BLOCKS << block->s2b_shift;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
-	q->limits.max_dev_sectors = max;
-	blk_queue_logical_block_size(q, logical_block_size);
-	blk_queue_max_hw_sectors(q, max);
-	blk_queue_max_segments(q, USHRT_MAX);
-	/* With page sized segments each segment can be translated into one idaw/tidaw */
-	blk_queue_max_segment_size(q, PAGE_SIZE);
-	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-
-	q->limits.discard_granularity = logical_block_size;
-
-	/* Calculate max_discard_sectors and make it PAGE aligned */
-	max_bytes = USHRT_MAX * logical_block_size;
-	max_bytes = ALIGN_DOWN(max_bytes, PAGE_SIZE);
-	max_discard_sectors = max_bytes / logical_block_size;
-
-	blk_queue_max_discard_sectors(q, max_discard_sectors);
-	blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
+	return DASD_FBA_MAX_BLOCKS << block->s2b_shift;
 }
 
 static int dasd_fba_pe_handler(struct dasd_device *device,
@@ -802,10 +763,11 @@ static struct dasd_discipline dasd_fba_discipline = {
 	.owner = THIS_MODULE,
 	.name = "FBA ",
 	.ebcname = "FBA ",
+	.has_discard = true,
 	.check_device = dasd_fba_check_characteristics,
 	.do_analysis = dasd_fba_do_analysis,
 	.pe_handler = dasd_fba_pe_handler,
-	.setup_blk_queue = dasd_fba_setup_blk_queue,
+	.max_sectors = dasd_fba_max_sectors,
 	.fill_geometry = dasd_fba_fill_geometry,
 	.start_IO = dasd_start_IO,
 	.term_IO = dasd_term_IO,
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 55e3abe94cde..4533dd055ca8 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -11,8 +11,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/interrupt.h>
 #include <linux/major.h>
 #include <linux/fs.h>
@@ -20,9 +18,6 @@
 
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_gendisk:"
-
 #include "dasd_int.h"
 
 static unsigned int queue_depth = 32;
@@ -39,6 +34,16 @@ MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD d
  */
 int dasd_gendisk_alloc(struct dasd_block *block)
 {
+	struct queue_limits lim = {
+		/*
+		 * With page sized segments, each segment can be translated into
+		 * one idaw/tidaw.
+		 */
+		.max_segment_size = PAGE_SIZE,
+		.seg_boundary_mask = PAGE_SIZE - 1,
+		.dma_alignment = PAGE_SIZE - 1,
+		.max_segments = USHRT_MAX,
+	};
 	struct gendisk *gdp;
 	struct dasd_device *base;
 	int len, rc;
@@ -58,11 +63,12 @@ int dasd_gendisk_alloc(struct dasd_block *block)
 	if (rc)
 		return rc;
 
-	gdp = blk_mq_alloc_disk(&block->tag_set, block);
+	gdp = blk_mq_alloc_disk(&block->tag_set, &lim, block);
 	if (IS_ERR(gdp)) {
 		blk_mq_free_tag_set(&block->tag_set);
 		return PTR_ERR(gdp);
 	}
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, gdp->queue);
 
 	/* Initialize gendisk structure. */
 	gdp->major = DASD_MAJOR;
@@ -127,15 +133,15 @@ void dasd_gendisk_free(struct dasd_block *block)
  */
 int dasd_scan_partitions(struct dasd_block *block)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int rc;
 
-	bdev_handle = bdev_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ,
+	bdev_file = bdev_file_open_by_dev(disk_devt(block->gdp), BLK_OPEN_READ,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		DBF_DEV_EVENT(DBF_ERR, block->base,
 			      "scan partitions error, blkdev_get returned %ld",
-			      PTR_ERR(bdev_handle));
+			      PTR_ERR(bdev_file));
 		return -ENODEV;
 	}
 
@@ -147,15 +153,15 @@ int dasd_scan_partitions(struct dasd_block *block)
 				"scan partitions error, rc %d", rc);
 
 	/*
-	 * Since the matching bdev_release() call to the
-	 * bdev_open_by_path() in this function is not called before
+	 * Since the matching fput() call to the
+	 * bdev_file_open_by_path() in this function is not called before
 	 * dasd_destroy_partitions the offline open_count limit needs to be
-	 * increased from 0 to 1. This is done by setting device->bdev_handle
+	 * increased from 0 to 1. This is done by setting device->bdev_file
 	 * (see dasd_generic_set_offline). As long as the partition detection
 	 * is running no offline should be allowed. That is why the assignment
-	 * to block->bdev_handle is done AFTER the BLKRRPART ioctl.
+	 * to block->bdev_file is done AFTER the BLKRRPART ioctl.
 	 */
-	block->bdev_handle = bdev_handle;
+	block->bdev_file = bdev_file;
 	return 0;
 }
 
@@ -165,21 +171,21 @@ int dasd_scan_partitions(struct dasd_block *block)
  */
 void dasd_destroy_partitions(struct dasd_block *block)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 
 	/*
-	 * Get the bdev_handle pointer from the device structure and clear
-	 * device->bdev_handle to lower the offline open_count limit again.
+	 * Get the bdev_file pointer from the device structure and clear
+	 * device->bdev_file to lower the offline open_count limit again.
 	 */
-	bdev_handle = block->bdev_handle;
-	block->bdev_handle = NULL;
+	bdev_file = block->bdev_file;
+	block->bdev_file = NULL;
 
-	mutex_lock(&bdev_handle->bdev->bd_disk->open_mutex);
-	bdev_disk_changed(bdev_handle->bdev->bd_disk, true);
-	mutex_unlock(&bdev_handle->bdev->bd_disk->open_mutex);
+	mutex_lock(&file_bdev(bdev_file)->bd_disk->open_mutex);
+	bdev_disk_changed(file_bdev(bdev_file)->bd_disk, true);
+	mutex_unlock(&file_bdev(bdev_file)->bd_disk->open_mutex);
 
 	/* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 }
 
 int dasd_gendisk_init(void)
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 1b1b8a41c4d4..e5f40536b425 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -113,9 +113,6 @@ do { \
 			    __dev_id.ssid, __dev_id.devno, d_data);	\
 } while (0)
 
-/* limit size for an errorstring */
-#define ERRORLENGTH 30
-
 /* definition of dbf debug levels */
 #define	DBF_EMERG	0	/* system is unusable			*/
 #define	DBF_ALERT	1	/* action must be taken immediately	*/
@@ -126,32 +123,6 @@ do { \
 #define	DBF_INFO	6	/* informational			*/
 #define	DBF_DEBUG	6	/* debug-level messages			*/
 
-/* messages to be written via klogd and dbf */
-#define DEV_MESSAGE(d_loglevel,d_device,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \
-	       dev_name(&d_device->cdev->dev), d_args); \
-	DBF_DEV_EVENT(DBF_ALERT, d_device, d_string, d_args); \
-} while(0)
-
-#define MESSAGE(d_loglevel,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \
-	DBF_EVENT(DBF_ALERT, d_string, d_args); \
-} while(0)
-
-/* messages to be written via klogd only */
-#define DEV_MESSAGE_LOG(d_loglevel,d_device,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " %s: " d_string "\n", \
-	       dev_name(&d_device->cdev->dev), d_args); \
-} while(0)
-
-#define MESSAGE_LOG(d_loglevel,d_string,d_args...)\
-do { \
-	printk(d_loglevel PRINTK_HEADER " " d_string "\n", d_args); \
-} while(0)
-
 /* Macro to calculate number of blocks per page */
 #define BLOCKS_PER_PAGE(blksize) (PAGE_SIZE / blksize)
 
@@ -322,6 +293,7 @@ struct dasd_discipline {
 	struct module *owner;
 	char ebcname[8];	/* a name used for tagging and printks */
 	char name[8];		/* a name used for tagging and printks */
+	bool has_discard;
 
 	struct list_head list;	/* used for list of disciplines */
 
@@ -360,10 +332,7 @@ struct dasd_discipline {
 	int (*online_to_ready) (struct dasd_device *);
 	int (*basic_to_known)(struct dasd_device *);
 
-	/*
-	 * Initialize block layer request queue.
-	 */
-	void (*setup_blk_queue)(struct dasd_block *);
+	unsigned int (*max_sectors)(struct dasd_block *);
 	/* (struct dasd_device *);
 	 * Device operation functions. build_cp creates a ccw chain for
 	 * a block device request, start_io starts the request and
@@ -650,7 +619,7 @@ struct dasd_block {
 	struct gendisk *gdp;
 	spinlock_t request_queue_lock;
 	struct blk_mq_tag_set tag_set;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	atomic_t open_count;
 
 	unsigned long blocks;	   /* size of volume in blocks */
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 61b9675e2a67..7e0ed7032f76 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -10,8 +10,6 @@
  * i/o controls for the dasd driver.
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/interrupt.h>
 #include <linux/compat.h>
 #include <linux/major.h>
@@ -24,12 +22,8 @@
 #include <linux/uaccess.h>
 #include <linux/dasd_mod.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_ioctl:"
-
 #include "dasd_int.h"
 
-
 static int
 dasd_ioctl_api_version(void __user *argp)
 {
@@ -537,7 +531,7 @@ static int __dasd_ioctl_information(struct dasd_block *block,
 	 * This must be hidden from user-space.
 	 */
 	dasd_info->open_count = atomic_read(&block->open_count);
-	if (!block->bdev_handle)
+	if (!block->bdev_file)
 		dasd_info->open_count++;
 
 	/*
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index 62a859ea67f8..0faaa437d9be 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -11,8 +11,6 @@
  *
  */
 
-#define KMSG_COMPONENT "dasd"
-
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -23,9 +21,6 @@
 #include <asm/debug.h>
 #include <linux/uaccess.h>
 
-/* This is ugly... */
-#define PRINTK_HEADER "dasd_proc:"
-
 #include "dasd_int.h"
 
 static struct proc_dir_entry *dasd_proc_root_entry = NULL;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 4b7ecd4fd431..9c8f529b827c 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -546,6 +546,9 @@ static const struct attribute_group *dcssblk_dev_attr_groups[] = {
 static ssize_t
 dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
 {
+	struct queue_limits lim = {
+		.logical_block_size	= 4096,
+	};
 	int rc, i, j, num_of_segments;
 	struct dcssblk_dev_info *dev_info;
 	struct segment_info *seg_info, *temp;
@@ -629,9 +632,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->dev.release = dcssblk_release_segment;
 	dev_info->dev.groups = dcssblk_dev_attr_groups;
 	INIT_LIST_HEAD(&dev_info->lh);
-	dev_info->gd = blk_alloc_disk(NUMA_NO_NODE);
-	if (dev_info->gd == NULL) {
-		rc = -ENOMEM;
+	dev_info->gd = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(dev_info->gd)) {
+		rc = PTR_ERR(dev_info->gd);
 		goto seg_list_del;
 	}
 	dev_info->gd->major = dcssblk_major;
@@ -639,7 +642,6 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->fops = &dcssblk_devops;
 	dev_info->gd->private_data = dev_info;
 	dev_info->gd->flags |= GENHD_FL_NO_PART;
-	blk_queue_logical_block_size(dev_info->gd->queue, 4096);
 	blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index ade95e91b3c8..9f6fdd0daa74 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -435,10 +435,17 @@ static const struct blk_mq_ops scm_mq_ops = {
 
 int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 {
-	unsigned int devindex, nr_max_blk;
+	struct queue_limits lim = {
+		.logical_block_size	= 1 << 12,
+	};
+	unsigned int devindex;
 	struct request_queue *rq;
 	int len, ret;
 
+	lim.max_segments = min(scmdev->nr_max_block,
+		(unsigned int) (PAGE_SIZE / sizeof(struct aidaw)));
+	lim.max_hw_sectors = lim.max_segments << 3; /* 8 * 512 = blk_size */
+
 	devindex = atomic_inc_return(&nr_devices) - 1;
 	/* scma..scmz + scmaa..scmzz */
 	if (devindex > 701) {
@@ -462,18 +469,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	if (ret)
 		goto out;
 
-	bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, scmdev);
+	bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, &lim, scmdev);
 	if (IS_ERR(bdev->gendisk)) {
 		ret = PTR_ERR(bdev->gendisk);
 		goto out_tag;
 	}
 	rq = bdev->rq = bdev->gendisk->queue;
-	nr_max_blk = min(scmdev->nr_max_block,
-			 (unsigned int) (PAGE_SIZE / sizeof(struct aidaw)));
-
-	blk_queue_logical_block_size(rq, 1 << 12);
-	blk_queue_max_hw_sectors(rq, nr_max_blk << 3); /* 8 * 512 = blk_size */
-	blk_queue_max_segments(rq, nr_max_blk);
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, rq);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq);
 
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index 82efdd20ad01..1d17a83569ce 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -195,7 +195,7 @@ static void free_chan_prog(struct ccw1 *cpa)
 	struct ccw1 *ptr = cpa;
 
 	while (ptr->cda) {
-		kfree((void *)(addr_t) ptr->cda);
+		kfree(phys_to_virt(ptr->cda));
 		ptr++;
 	}
 	kfree(cpa);
@@ -237,7 +237,7 @@ static struct ccw1 *alloc_chan_prog(const char __user *ubuf, int rec_count,
 			free_chan_prog(cpa);
 			return ERR_PTR(-ENOMEM);
 		}
-		cpa[i].cda = (u32)(addr_t) kbuf;
+		cpa[i].cda = (u32)virt_to_phys(kbuf);
 		if (copy_from_user(kbuf, ubuf, reclen)) {
 			free_chan_prog(cpa);
 			return ERR_PTR(-EFAULT);
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index bc3be0330f1d..0969fa01df58 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -29,7 +29,6 @@
 #include <asm/irqflags.h>
 #include <asm/checksum.h>
 #include <asm/os_info.h>
-#include <asm/switch_to.h>
 #include <asm/maccess.h>
 #include "sclp.h"
 
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index aa3292e57e38..6eb8bcd948dc 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -31,7 +31,7 @@
  * to devices that use multiple subchannels.
  */
 
-static struct bus_type ccwgroup_bus_type;
+static const struct bus_type ccwgroup_bus_type;
 
 static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev)
 {
@@ -465,7 +465,7 @@ static void ccwgroup_shutdown(struct device *dev)
 		gdrv->shutdown(gdev);
 }
 
-static struct bus_type ccwgroup_bus_type = {
+static const struct bus_type ccwgroup_bus_type = {
 	.name   = "ccwgroup",
 	.dev_groups = ccwgroup_dev_groups,
 	.remove = ccwgroup_remove,
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 64ed55c3aed6..3d88899dff7c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -1091,8 +1091,8 @@ int __init chsc_init(void)
 {
 	int ret;
 
-	sei_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
-	chsc_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	sei_page = (void *)get_zeroed_page(GFP_KERNEL);
+	chsc_page = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sei_page || !chsc_page) {
 		ret = -ENOMEM;
 		goto out_err;
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 902237d0baef..e6c800653f98 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -293,7 +293,7 @@ static int chsc_ioctl_start(void __user *user_area)
 	if (!css_general_characteristics.dynio)
 		/* It makes no sense to try. */
 		return -EOPNOTSUPP;
-	chsc_area = (void *)get_zeroed_page(GFP_DMA | GFP_KERNEL);
+	chsc_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!chsc_area)
 		return -ENOMEM;
 	request = kzalloc(sizeof(*request), GFP_KERNEL);
@@ -341,7 +341,7 @@ static int chsc_ioctl_on_close_set(void __user *user_area)
 		ret = -ENOMEM;
 		goto out_unlock;
 	}
-	on_close_chsc_area = (void *)get_zeroed_page(GFP_DMA | GFP_KERNEL);
+	on_close_chsc_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!on_close_chsc_area) {
 		ret = -ENOMEM;
 		goto out_free_request;
@@ -393,7 +393,7 @@ static int chsc_ioctl_start_sync(void __user *user_area)
 	struct chsc_sync_area *chsc_area;
 	int ret, ccode;
 
-	chsc_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	chsc_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!chsc_area)
 		return -ENOMEM;
 	if (copy_from_user(chsc_area, user_area, PAGE_SIZE)) {
@@ -439,7 +439,7 @@ static int chsc_ioctl_info_channel_path(void __user *user_cd)
 		u8 data[PAGE_SIZE - 20];
 	} __attribute__ ((packed)) *scpcd_area;
 
-	scpcd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	scpcd_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scpcd_area)
 		return -ENOMEM;
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
@@ -501,7 +501,7 @@ static int chsc_ioctl_info_cu(void __user *user_cd)
 		u8 data[PAGE_SIZE - 20];
 	} __attribute__ ((packed)) *scucd_area;
 
-	scucd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	scucd_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scucd_area)
 		return -ENOMEM;
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
@@ -564,7 +564,7 @@ static int chsc_ioctl_info_sch_cu(void __user *user_cud)
 		u8 data[PAGE_SIZE - 20];
 	} __attribute__ ((packed)) *sscud_area;
 
-	sscud_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	sscud_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sscud_area)
 		return -ENOMEM;
 	cud = kzalloc(sizeof(*cud), GFP_KERNEL);
@@ -626,7 +626,7 @@ static int chsc_ioctl_conf_info(void __user *user_ci)
 		u8 data[PAGE_SIZE - 20];
 	} __attribute__ ((packed)) *sci_area;
 
-	sci_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	sci_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sci_area)
 		return -ENOMEM;
 	ci = kzalloc(sizeof(*ci), GFP_KERNEL);
@@ -697,7 +697,7 @@ static int chsc_ioctl_conf_comp_list(void __user *user_ccl)
 		u32 res;
 	} __attribute__ ((packed)) *cssids_parm;
 
-	sccl_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	sccl_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sccl_area)
 		return -ENOMEM;
 	ccl = kzalloc(sizeof(*ccl), GFP_KERNEL);
@@ -757,7 +757,7 @@ static int chsc_ioctl_chpd(void __user *user_chpd)
 	int ret;
 
 	chpd = kzalloc(sizeof(*chpd), GFP_KERNEL);
-	scpd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	scpd_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scpd_area || !chpd) {
 		ret = -ENOMEM;
 		goto out_free;
@@ -797,7 +797,7 @@ static int chsc_ioctl_dcal(void __user *user_dcal)
 		u8 data[PAGE_SIZE - 36];
 	} __attribute__ ((packed)) *sdcal_area;
 
-	sdcal_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	sdcal_area = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sdcal_area)
 		return -ENOMEM;
 	dcal = kzalloc(sizeof(*dcal), GFP_KERNEL);
diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c
index 5584aa46c94e..f80dc18e2a76 100644
--- a/drivers/s390/cio/cmf.c
+++ b/drivers/s390/cio/cmf.c
@@ -169,7 +169,8 @@ static inline void cmf_activate(void *area, unsigned int onoff)
 		"	lgr	2,%[mbo]\n"
 		"	schm\n"
 		:
-		: [r1] "d" ((unsigned long)onoff), [mbo] "d" (area)
+		: [r1] "d" ((unsigned long)onoff),
+		  [mbo] "d" (virt_to_phys(area))
 		: "1", "2");
 }
 
@@ -501,8 +502,7 @@ static int alloc_cmb(struct ccw_device *cdev)
 		WARN_ON(!list_empty(&cmb_area.list));
 
 		spin_unlock(&cmb_area.lock);
-		mem = (void*)__get_free_pages(GFP_KERNEL | GFP_DMA,
-				 get_order(size));
+		mem = (void *)__get_free_pages(GFP_KERNEL, get_order(size));
 		spin_lock(&cmb_area.lock);
 
 		if (cmb_area.mem) {
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 28a88ed2c3aa..094431a62ad5 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -39,7 +39,7 @@ int max_ssid;
 
 #define MAX_CSS_IDX 0
 struct channel_subsystem *channel_subsystems[MAX_CSS_IDX + 1];
-static struct bus_type css_bus_type;
+static const struct bus_type css_bus_type;
 
 int
 for_each_subchannel(int(*fn)(struct subchannel_id, void *), void *data)
@@ -1409,7 +1409,7 @@ static int css_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return ret;
 }
 
-static struct bus_type css_bus_type = {
+static const struct bus_type css_bus_type = {
 	.name     = "css",
 	.match    = css_bus_match,
 	.probe    = css_probe,
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 0cfb179e1bcb..f95d12345d98 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -49,7 +49,7 @@ static const unsigned long recovery_delay[] = { 3, 30, 300 };
 
 static atomic_t ccw_device_init_count = ATOMIC_INIT(0);
 static DECLARE_WAIT_QUEUE_HEAD(ccw_device_init_wq);
-static struct bus_type ccw_bus_type;
+static const struct bus_type ccw_bus_type;
 
 /******************* bus type handling ***********************/
 
@@ -1776,7 +1776,7 @@ static void ccw_device_shutdown(struct device *dev)
 	__disable_cmf(cdev);
 }
 
-static struct bus_type ccw_bus_type = {
+static const struct bus_type ccw_bus_type = {
 	.name   = "ccw",
 	.match  = ccw_bus_match,
 	.uevent = ccw_uevent,
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index c533d1dadc6b..a5dba3829769 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -202,7 +202,8 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa,
 		return -EINVAL;
 	if (cdev->private->state == DEV_STATE_NOT_OPER)
 		return -ENODEV;
-	if (cdev->private->state == DEV_STATE_VERIFY) {
+	if (cdev->private->state == DEV_STATE_VERIFY ||
+	    cdev->private->flags.doverify) {
 		/* Remember to fake irb when finished. */
 		if (!cdev->private->flags.fake_irb) {
 			cdev->private->flags.fake_irb = FAKE_CMD_IRB;
@@ -214,8 +215,7 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa,
 	}
 	if (cdev->private->state != DEV_STATE_ONLINE ||
 	    ((sch->schib.scsw.cmd.stctl & SCSW_STCTL_PRIM_STATUS) &&
-	     !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)) ||
-	    cdev->private->flags.doverify)
+	     !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)))
 		return -EBUSY;
 	ret = cio_set_options (sch, flags);
 	if (ret)
diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c
index 6b21ba68c1fe..c7894d61306d 100644
--- a/drivers/s390/cio/scm.c
+++ b/drivers/s390/cio/scm.c
@@ -42,7 +42,7 @@ static int scmdev_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "MODALIAS=scm:scmdev");
 }
 
-static struct bus_type scm_bus_type = {
+static const struct bus_type scm_bus_type = {
 	.name  = "scm",
 	.probe = scmdev_probe,
 	.remove = scmdev_remove,
@@ -228,7 +228,7 @@ int scm_update_information(void)
 	size_t num;
 	int ret;
 
-	scm_info = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+	scm_info = (void *)__get_free_page(GFP_KERNEL);
 	if (!scm_info)
 		return -ENOMEM;
 
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index f46dd6abacd7..cce0bafd4c92 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -38,6 +38,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
+#include <asm/uv.h>
 
 #include "ap_bus.h"
 #include "ap_debug.h"
@@ -83,14 +84,11 @@ EXPORT_SYMBOL(ap_perms);
 DEFINE_MUTEX(ap_perms_mutex);
 EXPORT_SYMBOL(ap_perms_mutex);
 
-/* # of bus scans since init */
-static atomic64_t ap_scan_bus_count;
-
 /* # of bindings complete since init */
 static atomic64_t ap_bindings_complete_count = ATOMIC64_INIT(0);
 
-/* completion for initial APQN bindings complete */
-static DECLARE_COMPLETION(ap_init_apqn_bindings_complete);
+/* completion for APQN bindings complete */
+static DECLARE_COMPLETION(ap_apqn_bindings_complete);
 
 static struct ap_config_info *ap_qci_info;
 static struct ap_config_info *ap_qci_info_old;
@@ -101,12 +99,16 @@ static struct ap_config_info *ap_qci_info_old;
 debug_info_t *ap_dbf_info;
 
 /*
- * Workqueue timer for bus rescan.
+ * AP bus rescan related things.
  */
-static struct timer_list ap_config_timer;
-static int ap_config_time = AP_CONFIG_TIME;
-static void ap_scan_bus(struct work_struct *);
-static DECLARE_WORK(ap_scan_work, ap_scan_bus);
+static bool ap_scan_bus(void);
+static bool ap_scan_bus_result; /* result of last ap_scan_bus() */
+static DEFINE_MUTEX(ap_scan_bus_mutex); /* mutex ap_scan_bus() invocations */
+static atomic64_t ap_scan_bus_count; /* counter ap_scan_bus() invocations */
+static int ap_scan_bus_time = AP_CONFIG_TIME;
+static struct timer_list ap_scan_bus_timer;
+static void ap_scan_bus_wq_callback(struct work_struct *);
+static DECLARE_WORK(ap_scan_bus_work, ap_scan_bus_wq_callback);
 
 /*
  * Tasklet & timer for AP request polling and interrupts
@@ -135,7 +137,7 @@ static int ap_max_domain_id = 15;
 /* Maximum adapter id, if not given via qci */
 static int ap_max_adapter_id = 63;
 
-static struct bus_type ap_bus_type;
+static const struct bus_type ap_bus_type;
 
 /* Adapter interrupt definitions */
 static void ap_interrupt_handler(struct airq_struct *airq,
@@ -753,7 +755,7 @@ static void ap_calc_bound_apqns(unsigned int *apqns, unsigned int *bound)
 }
 
 /*
- * After initial ap bus scan do check if all existing APQNs are
+ * After ap bus scan do check if all existing APQNs are
  * bound to device drivers.
  */
 static void ap_check_bindings_complete(void)
@@ -763,9 +765,9 @@ static void ap_check_bindings_complete(void)
 	if (atomic64_read(&ap_scan_bus_count) >= 1) {
 		ap_calc_bound_apqns(&apqns, &bound);
 		if (bound == apqns) {
-			if (!completion_done(&ap_init_apqn_bindings_complete)) {
-				complete_all(&ap_init_apqn_bindings_complete);
-				AP_DBF_INFO("%s complete\n", __func__);
+			if (!completion_done(&ap_apqn_bindings_complete)) {
+				complete_all(&ap_apqn_bindings_complete);
+				pr_debug("%s all apqn bindings complete\n", __func__);
 			}
 			ap_send_bindings_complete_uevent();
 		}
@@ -782,27 +784,29 @@ static void ap_check_bindings_complete(void)
  * -ETIME is returned. On failures negative return values are
  * returned to the caller.
  */
-int ap_wait_init_apqn_bindings_complete(unsigned long timeout)
+int ap_wait_apqn_bindings_complete(unsigned long timeout)
 {
+	int rc = 0;
 	long l;
 
-	if (completion_done(&ap_init_apqn_bindings_complete))
+	if (completion_done(&ap_apqn_bindings_complete))
 		return 0;
 
 	if (timeout)
 		l = wait_for_completion_interruptible_timeout(
-			&ap_init_apqn_bindings_complete, timeout);
+			&ap_apqn_bindings_complete, timeout);
 	else
 		l = wait_for_completion_interruptible(
-			&ap_init_apqn_bindings_complete);
+			&ap_apqn_bindings_complete);
 	if (l < 0)
-		return l == -ERESTARTSYS ? -EINTR : l;
+		rc = l == -ERESTARTSYS ? -EINTR : l;
 	else if (l == 0 && timeout)
-		return -ETIME;
+		rc = -ETIME;
 
-	return 0;
+	pr_debug("%s rc=%d\n", __func__, rc);
+	return rc;
 }
-EXPORT_SYMBOL(ap_wait_init_apqn_bindings_complete);
+EXPORT_SYMBOL(ap_wait_apqn_bindings_complete);
 
 static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data)
 {
@@ -826,8 +830,8 @@ static int __ap_revise_reserved(struct device *dev, void *dummy)
 		drvres = to_ap_drv(dev->driver)->flags
 			& AP_DRIVER_FLAG_DEFAULT;
 		if (!!devres != !!drvres) {
-			AP_DBF_DBG("%s reprobing queue=%02x.%04x\n",
-				   __func__, card, queue);
+			pr_debug("%s reprobing queue=%02x.%04x\n",
+				 __func__, card, queue);
 			rc = device_reprobe(dev);
 			if (rc)
 				AP_DBF_WARN("%s reprobing queue=%02x.%04x failed\n",
@@ -939,8 +943,6 @@ static int ap_device_probe(struct device *dev)
 		if (is_queue_dev(dev))
 			hash_del(&to_ap_queue(dev)->hnode);
 		spin_unlock_bh(&ap_queues_lock);
-	} else {
-		ap_check_bindings_complete();
 	}
 
 out:
@@ -1012,16 +1014,47 @@ void ap_driver_unregister(struct ap_driver *ap_drv)
 }
 EXPORT_SYMBOL(ap_driver_unregister);
 
-void ap_bus_force_rescan(void)
+/*
+ * Enforce a synchronous AP bus rescan.
+ * Returns true if the bus scan finds a change in the AP configuration
+ * and AP devices have been added or deleted when this function returns.
+ */
+bool ap_bus_force_rescan(void)
 {
+	unsigned long scan_counter = atomic64_read(&ap_scan_bus_count);
+	bool rc = false;
+
+	pr_debug(">%s scan counter=%lu\n", __func__, scan_counter);
+
 	/* Only trigger AP bus scans after the initial scan is done */
-	if (atomic64_read(&ap_scan_bus_count) <= 0)
-		return;
+	if (scan_counter <= 0)
+		goto out;
+
+	/* Try to acquire the AP scan bus mutex */
+	if (mutex_trylock(&ap_scan_bus_mutex)) {
+		/* mutex acquired, run the AP bus scan */
+		ap_scan_bus_result = ap_scan_bus();
+		rc = ap_scan_bus_result;
+		mutex_unlock(&ap_scan_bus_mutex);
+		goto out;
+	}
+
+	/*
+	 * Mutex acquire failed. So there is currently another task
+	 * already running the AP bus scan. Then let's simple wait
+	 * for the lock which means the other task has finished and
+	 * stored the result in ap_scan_bus_result.
+	 */
+	if (mutex_lock_interruptible(&ap_scan_bus_mutex)) {
+		/* some error occurred, ignore and go out */
+		goto out;
+	}
+	rc = ap_scan_bus_result;
+	mutex_unlock(&ap_scan_bus_mutex);
 
-	/* processing a asynchronous bus rescan */
-	del_timer(&ap_config_timer);
-	queue_work(system_long_wq, &ap_scan_work);
-	flush_work(&ap_scan_work);
+out:
+	pr_debug("%s rc=%d\n", __func__, rc);
+	return rc;
 }
 EXPORT_SYMBOL(ap_bus_force_rescan);
 
@@ -1030,7 +1063,7 @@ EXPORT_SYMBOL(ap_bus_force_rescan);
  */
 void ap_bus_cfg_chg(void)
 {
-	AP_DBF_DBG("%s config change, forcing bus rescan\n", __func__);
+	pr_debug("%s config change, forcing bus rescan\n", __func__);
 
 	ap_bus_force_rescan();
 }
@@ -1250,7 +1283,7 @@ static BUS_ATTR_RO(ap_interrupts);
 
 static ssize_t config_time_show(const struct bus_type *bus, char *buf)
 {
-	return sysfs_emit(buf, "%d\n", ap_config_time);
+	return sysfs_emit(buf, "%d\n", ap_scan_bus_time);
 }
 
 static ssize_t config_time_store(const struct bus_type *bus,
@@ -1260,8 +1293,8 @@ static ssize_t config_time_store(const struct bus_type *bus,
 
 	if (sscanf(buf, "%d\n", &time) != 1 || time < 5 || time > 120)
 		return -EINVAL;
-	ap_config_time = time;
-	mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ);
+	ap_scan_bus_time = time;
+	mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ);
 	return count;
 }
 
@@ -1603,7 +1636,7 @@ static struct attribute *ap_bus_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ap_bus);
 
-static struct bus_type ap_bus_type = {
+static const struct bus_type ap_bus_type = {
 	.name = "ap",
 	.bus_groups = ap_bus_groups,
 	.match = &ap_bus_match,
@@ -1888,8 +1921,8 @@ static inline void ap_scan_domains(struct ap_card *ac)
 				aq->last_err_rc = AP_RESPONSE_CHECKSTOPPED;
 			}
 			spin_unlock_bh(&aq->lock);
-			AP_DBF_DBG("%s(%d,%d) queue dev checkstop on\n",
-				   __func__, ac->id, dom);
+			pr_debug("%s(%d,%d) queue dev checkstop on\n",
+				 __func__, ac->id, dom);
 			/* 'receive' pending messages with -EAGAIN */
 			ap_flush_queue(aq);
 			goto put_dev_and_continue;
@@ -1899,8 +1932,8 @@ static inline void ap_scan_domains(struct ap_card *ac)
 			if (aq->dev_state > AP_DEV_STATE_UNINITIATED)
 				_ap_queue_init_state(aq);
 			spin_unlock_bh(&aq->lock);
-			AP_DBF_DBG("%s(%d,%d) queue dev checkstop off\n",
-				   __func__, ac->id, dom);
+			pr_debug("%s(%d,%d) queue dev checkstop off\n",
+				 __func__, ac->id, dom);
 			goto put_dev_and_continue;
 		}
 		/* config state change */
@@ -1912,8 +1945,8 @@ static inline void ap_scan_domains(struct ap_card *ac)
 				aq->last_err_rc = AP_RESPONSE_DECONFIGURED;
 			}
 			spin_unlock_bh(&aq->lock);
-			AP_DBF_DBG("%s(%d,%d) queue dev config off\n",
-				   __func__, ac->id, dom);
+			pr_debug("%s(%d,%d) queue dev config off\n",
+				 __func__, ac->id, dom);
 			ap_send_config_uevent(&aq->ap_dev, aq->config);
 			/* 'receive' pending messages with -EAGAIN */
 			ap_flush_queue(aq);
@@ -1924,8 +1957,8 @@ static inline void ap_scan_domains(struct ap_card *ac)
 			if (aq->dev_state > AP_DEV_STATE_UNINITIATED)
 				_ap_queue_init_state(aq);
 			spin_unlock_bh(&aq->lock);
-			AP_DBF_DBG("%s(%d,%d) queue dev config on\n",
-				   __func__, ac->id, dom);
+			pr_debug("%s(%d,%d) queue dev config on\n",
+				 __func__, ac->id, dom);
 			ap_send_config_uevent(&aq->ap_dev, aq->config);
 			goto put_dev_and_continue;
 		}
@@ -1997,8 +2030,8 @@ static inline void ap_scan_adapter(int ap)
 			ap_scan_rm_card_dev_and_queue_devs(ac);
 			put_device(dev);
 		} else {
-			AP_DBF_DBG("%s(%d) no type info (no APQN found), ignored\n",
-				   __func__, ap);
+			pr_debug("%s(%d) no type info (no APQN found), ignored\n",
+				 __func__, ap);
 		}
 		return;
 	}
@@ -2010,8 +2043,8 @@ static inline void ap_scan_adapter(int ap)
 			ap_scan_rm_card_dev_and_queue_devs(ac);
 			put_device(dev);
 		} else {
-			AP_DBF_DBG("%s(%d) no valid type (0) info, ignored\n",
-				   __func__, ap);
+			pr_debug("%s(%d) no valid type (0) info, ignored\n",
+				 __func__, ap);
 		}
 		return;
 	}
@@ -2135,23 +2168,80 @@ static bool ap_get_configuration(void)
 		      sizeof(struct ap_config_info)) != 0;
 }
 
+/*
+ * ap_config_has_new_aps - Check current against old qci info if
+ * new adapters have appeared. Returns true if at least one new
+ * adapter in the apm mask is showing up. Existing adapters or
+ * receding adapters are not counted.
+ */
+static bool ap_config_has_new_aps(void)
+{
+
+	unsigned long m[BITS_TO_LONGS(AP_DEVICES)];
+
+	if (!ap_qci_info)
+		return false;
+
+	bitmap_andnot(m, (unsigned long *)ap_qci_info->apm,
+		      (unsigned long *)ap_qci_info_old->apm, AP_DEVICES);
+	if (!bitmap_empty(m, AP_DEVICES))
+		return true;
+
+	return false;
+}
+
+/*
+ * ap_config_has_new_doms - Check current against old qci info if
+ * new (usage) domains have appeared. Returns true if at least one
+ * new domain in the aqm mask is showing up. Existing domains or
+ * receding domains are not counted.
+ */
+static bool ap_config_has_new_doms(void)
+{
+	unsigned long m[BITS_TO_LONGS(AP_DOMAINS)];
+
+	if (!ap_qci_info)
+		return false;
+
+	bitmap_andnot(m, (unsigned long *)ap_qci_info->aqm,
+		      (unsigned long *)ap_qci_info_old->aqm, AP_DOMAINS);
+	if (!bitmap_empty(m, AP_DOMAINS))
+		return true;
+
+	return false;
+}
+
 /**
  * ap_scan_bus(): Scan the AP bus for new devices
- * Runs periodically, workqueue timer (ap_config_time)
- * @unused: Unused pointer.
+ * Always run under mutex ap_scan_bus_mutex protection
+ * which needs to get locked/unlocked by the caller!
+ * Returns true if any config change has been detected
+ * during the scan, otherwise false.
  */
-static void ap_scan_bus(struct work_struct *unused)
+static bool ap_scan_bus(void)
 {
-	int ap, config_changed = 0;
+	bool config_changed;
+	int ap;
+
+	pr_debug(">%s\n", __func__);
 
-	/* config change notify */
+	/* (re-)fetch configuration via QCI */
 	config_changed = ap_get_configuration();
-	if (config_changed)
+	if (config_changed) {
+		if (ap_config_has_new_aps() || ap_config_has_new_doms()) {
+			/*
+			 * Appearance of new adapters and/or domains need to
+			 * build new ap devices which need to get bound to an
+			 * device driver. Thus reset the APQN bindings complete
+			 * completion.
+			 */
+			reinit_completion(&ap_apqn_bindings_complete);
+		}
+		/* post a config change notify */
 		notify_config_changed();
+	}
 	ap_select_domain();
 
-	AP_DBF_DBG("%s running\n", __func__);
-
 	/* loop over all possible adapters */
 	for (ap = 0; ap <= ap_max_adapter_id; ap++)
 		ap_scan_adapter(ap);
@@ -2174,23 +2264,56 @@ static void ap_scan_bus(struct work_struct *unused)
 	}
 
 	if (atomic64_inc_return(&ap_scan_bus_count) == 1) {
-		AP_DBF_DBG("%s init scan complete\n", __func__);
+		pr_debug("%s init scan complete\n", __func__);
 		ap_send_init_scan_done_uevent();
-		ap_check_bindings_complete();
 	}
 
-	mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ);
+	ap_check_bindings_complete();
+
+	mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ);
+
+	pr_debug("<%s config_changed=%d\n", __func__, config_changed);
+
+	return config_changed;
 }
 
-static void ap_config_timeout(struct timer_list *unused)
+/*
+ * Callback for the ap_scan_bus_timer
+ * Runs periodically, workqueue timer (ap_scan_bus_time)
+ */
+static void ap_scan_bus_timer_callback(struct timer_list *unused)
 {
-	queue_work(system_long_wq, &ap_scan_work);
+	/*
+	 * schedule work into the system long wq which when
+	 * the work is finally executed, calls the AP bus scan.
+	 */
+	queue_work(system_long_wq, &ap_scan_bus_work);
+}
+
+/*
+ * Callback for the ap_scan_bus_work
+ */
+static void ap_scan_bus_wq_callback(struct work_struct *unused)
+{
+	/*
+	 * Try to invoke an ap_scan_bus(). If the mutex acquisition
+	 * fails there is currently another task already running the
+	 * AP scan bus and there is no need to wait and re-trigger the
+	 * scan again. Please note at the end of the scan bus function
+	 * the AP scan bus timer is re-armed which triggers then the
+	 * ap_scan_bus_timer_callback which enqueues a work into the
+	 * system_long_wq which invokes this function here again.
+	 */
+	if (mutex_trylock(&ap_scan_bus_mutex)) {
+		ap_scan_bus_result = ap_scan_bus();
+		mutex_unlock(&ap_scan_bus_mutex);
+	}
 }
 
 static int __init ap_debug_init(void)
 {
 	ap_dbf_info = debug_register("ap", 2, 1,
-				     DBF_MAX_SPRINTF_ARGS * sizeof(long));
+				     AP_DBF_MAX_SPRINTF_ARGS * sizeof(long));
 	debug_register_view(ap_dbf_info, &debug_sprintf_view);
 	debug_set_level(ap_dbf_info, DBF_ERR);
 
@@ -2274,7 +2397,7 @@ static int __init ap_module_init(void)
 	ap_root_device->bus = &ap_bus_type;
 
 	/* Setup the AP bus rescan timer. */
-	timer_setup(&ap_config_timer, ap_config_timeout, 0);
+	timer_setup(&ap_scan_bus_timer, ap_scan_bus_timer_callback, 0);
 
 	/*
 	 * Setup the high resolution poll timer.
@@ -2292,7 +2415,7 @@ static int __init ap_module_init(void)
 			goto out_work;
 	}
 
-	queue_work(system_long_wq, &ap_scan_work);
+	queue_work(system_long_wq, &ap_scan_bus_work);
 
 	return 0;
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 98814839ef30..59c7ed49aa02 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -266,7 +266,7 @@ int ap_sb_available(void);
 bool ap_is_se_guest(void);
 void ap_wait(enum ap_sm_wait wait);
 void ap_request_timeout(struct timer_list *t);
-void ap_bus_force_rescan(void);
+bool ap_bus_force_rescan(void);
 
 int ap_test_config_usage_domain(unsigned int domain);
 int ap_test_config_ctrl_domain(unsigned int domain);
@@ -352,8 +352,12 @@ int ap_parse_mask_str(const char *str,
  * the return value is 0. If the timeout (in jiffies) hits instead
  * -ETIME is returned. On failures negative return values are
  * returned to the caller.
+ * It may be that the AP bus scan finds new devices. Then the
+ * condition that all APQNs are bound to their device drivers
+ * is reset to false and this call again blocks until either all
+ * APQNs are bound to a device driver or the timeout hits again.
  */
-int ap_wait_init_apqn_bindings_complete(unsigned long timeout);
+int ap_wait_apqn_bindings_complete(unsigned long timeout);
 
 void ap_send_config_uevent(struct ap_device *ap_dev, bool cfg);
 void ap_send_online_uevent(struct ap_device *ap_dev, int online);
diff --git a/drivers/s390/crypto/ap_debug.h b/drivers/s390/crypto/ap_debug.h
index c083ce88a9a6..2f66271b8564 100644
--- a/drivers/s390/crypto/ap_debug.h
+++ b/drivers/s390/crypto/ap_debug.h
@@ -16,7 +16,7 @@
 #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO)
 #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO)
 
-#define DBF_MAX_SPRINTF_ARGS 6
+#define AP_DBF_MAX_SPRINTF_ARGS 6
 
 #define AP_DBF(...)					\
 	debug_sprintf_event(ap_dbf_info, ##__VA_ARGS__)
@@ -26,8 +26,6 @@
 	debug_sprintf_event(ap_dbf_info, DBF_WARN, ##__VA_ARGS__)
 #define AP_DBF_INFO(...)					\
 	debug_sprintf_event(ap_dbf_info, DBF_INFO, ##__VA_ARGS__)
-#define AP_DBF_DBG(...)					\
-	debug_sprintf_event(ap_dbf_info, DBF_DEBUG, ##__VA_ARGS__)
 
 extern debug_info_t *ap_dbf_info;
 
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index 682595443145..6e4e8d324a6d 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -136,6 +136,8 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq)
 
 	switch (status.response_code) {
 	case AP_RESPONSE_NORMAL:
+		print_hex_dump_debug("aprpl: ", DUMP_PREFIX_ADDRESS, 16, 1,
+				     aq->reply->msg, aq->reply->len, false);
 		aq->queue_count = max_t(int, 0, aq->queue_count - 1);
 		if (!status.queue_empty && !aq->queue_count)
 			aq->queue_count++;
@@ -169,6 +171,9 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq)
 		aq->queue_count = 0;
 		list_splice_init(&aq->pendingq, &aq->requestq);
 		aq->requestq_count += aq->pendingq_count;
+		pr_debug("%s queue 0x%02x.%04x rescheduled %d reqs (new req %d)\n",
+			 __func__, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid),
+			 aq->pendingq_count, aq->requestq_count);
 		aq->pendingq_count = 0;
 		break;
 	default:
@@ -243,6 +248,8 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq)
 
 	/* Start the next request on the queue. */
 	ap_msg = list_entry(aq->requestq.next, struct ap_message, list);
+	print_hex_dump_debug("apreq: ", DUMP_PREFIX_ADDRESS, 16, 1,
+			     ap_msg->msg, ap_msg->len, false);
 	status = __ap_send(qid, ap_msg->psmid,
 			   ap_msg->msg, ap_msg->len,
 			   ap_msg->flags & AP_MSG_FLAG_SPECIAL);
@@ -446,9 +453,9 @@ static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq)
 	case AP_BS_Q_USABLE:
 		/* association is through */
 		aq->sm_state = AP_SM_STATE_IDLE;
-		AP_DBF_DBG("%s queue 0x%02x.%04x associated with %u\n",
-			   __func__, AP_QID_CARD(aq->qid),
-			   AP_QID_QUEUE(aq->qid), aq->assoc_idx);
+		pr_debug("%s queue 0x%02x.%04x associated with %u\n",
+			 __func__, AP_QID_CARD(aq->qid),
+			 AP_QID_QUEUE(aq->qid), aq->assoc_idx);
 		return AP_SM_WAIT_NONE;
 	case AP_BS_Q_USABLE_NO_SECURE_KEY:
 		/* association still pending */
@@ -690,9 +697,9 @@ static ssize_t ap_functions_show(struct device *dev,
 
 	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
-		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
-			   __func__, status.response_code,
-			   AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			 __func__, status.response_code,
+			 AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
 		return -EIO;
 	}
 
@@ -846,9 +853,9 @@ static ssize_t se_bind_show(struct device *dev,
 
 	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
-		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
-			   __func__, status.response_code,
-			   AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			 __func__, status.response_code,
+			 AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
 		return -EIO;
 	}
 
@@ -974,9 +981,9 @@ static ssize_t se_associate_show(struct device *dev,
 
 	status = ap_test_queue(aq->qid, 1, &hwinfo);
 	if (status.response_code > AP_RESPONSE_BUSY) {
-		AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
-			   __func__, status.response_code,
-			   AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
+		pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n",
+			 __func__, status.response_code,
+			 AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid));
 		return -EIO;
 	}
 
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 6cfb6b2340c9..dccf664a3d95 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -42,24 +42,23 @@ MODULE_DESCRIPTION("s390 protected key interface");
  * debug feature data and functions
  */
 
-static debug_info_t *debug_info;
+static debug_info_t *pkey_dbf_info;
 
-#define DEBUG_DBG(...)	debug_sprintf_event(debug_info, 6, ##__VA_ARGS__)
-#define DEBUG_INFO(...) debug_sprintf_event(debug_info, 5, ##__VA_ARGS__)
-#define DEBUG_WARN(...) debug_sprintf_event(debug_info, 4, ##__VA_ARGS__)
-#define DEBUG_ERR(...)	debug_sprintf_event(debug_info, 3, ##__VA_ARGS__)
+#define PKEY_DBF_INFO(...) debug_sprintf_event(pkey_dbf_info, 5, ##__VA_ARGS__)
+#define PKEY_DBF_WARN(...) debug_sprintf_event(pkey_dbf_info, 4, ##__VA_ARGS__)
+#define PKEY_DBF_ERR(...)  debug_sprintf_event(pkey_dbf_info, 3, ##__VA_ARGS__)
 
 static void __init pkey_debug_init(void)
 {
 	/* 5 arguments per dbf entry (including the format string ptr) */
-	debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long));
-	debug_register_view(debug_info, &debug_sprintf_view);
-	debug_set_level(debug_info, 3);
+	pkey_dbf_info = debug_register("pkey", 1, 1, 5 * sizeof(long));
+	debug_register_view(pkey_dbf_info, &debug_sprintf_view);
+	debug_set_level(pkey_dbf_info, 3);
 }
 
 static void __exit pkey_debug_exit(void)
 {
-	debug_unregister(debug_info);
+	debug_unregister(pkey_dbf_info);
 }
 
 /* inside view of a protected key token (only type 0x00 version 0x01) */
@@ -163,14 +162,14 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey,
 		fc = CPACF_PCKMO_ENC_ECC_ED448_KEY;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keytype %u\n",
-			  __func__, keytype);
+		PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n",
+			     __func__, keytype);
 		return -EINVAL;
 	}
 
 	if (*protkeylen < keysize + AES_WK_VP_SIZE) {
-		DEBUG_ERR("%s prot key buffer size too small: %u < %d\n",
-			  __func__, *protkeylen, keysize + AES_WK_VP_SIZE);
+		PKEY_DBF_ERR("%s prot key buffer size too small: %u < %d\n",
+			     __func__, *protkeylen, keysize + AES_WK_VP_SIZE);
 		return -EINVAL;
 	}
 
@@ -182,7 +181,7 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey,
 	}
 	/* check for the pckmo subfunction we need now */
 	if (!cpacf_test_func(&pckmo_functions, fc)) {
-		DEBUG_ERR("%s pckmo functions not available\n", __func__);
+		PKEY_DBF_ERR("%s pckmo functions not available\n", __func__);
 		return -ENODEV;
 	}
 
@@ -244,7 +243,7 @@ static int pkey_skey2pkey(const u8 *key, u8 *protkey,
 	}
 
 	if (rc)
-		DEBUG_DBG("%s failed rc=%d\n", __func__, rc);
+		pr_debug("%s failed rc=%d\n", __func__, rc);
 
 	return rc;
 }
@@ -283,7 +282,7 @@ static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen,
 out:
 	kfree(apqns);
 	if (rc)
-		DEBUG_DBG("%s failed rc=%d\n", __func__, rc);
+		pr_debug("%s failed rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -294,33 +293,36 @@ static int pkey_ep11key2pkey(const u8 *key, size_t keylen,
 			     u8 *protkey, u32 *protkeylen, u32 *protkeytype)
 {
 	u32 nr_apqns, *apqns = NULL;
+	int i, j, rc = -ENODEV;
 	u16 card, dom;
-	int i, rc;
 
 	zcrypt_wait_api_operational();
 
-	/* build a list of apqns suitable for this key */
-	rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
-			    ZCRYPT_CEX7,
-			    ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4,
-			    ep11_kb_wkvp(key, keylen));
-	if (rc)
-		goto out;
+	/* try two times in case of failure */
+	for (i = 0; i < 2 && rc; i++) {
 
-	/* go through the list of apqns and try to derive an pkey */
-	for (rc = -ENODEV, i = 0; i < nr_apqns; i++) {
-		card = apqns[i] >> 16;
-		dom = apqns[i] & 0xFFFF;
-		rc = ep11_kblob2protkey(card, dom, key, keylen,
-					protkey, protkeylen, protkeytype);
-		if (rc == 0)
-			break;
+		/* build a list of apqns suitable for this key */
+		rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
+				    ZCRYPT_CEX7,
+				    ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4,
+				    ep11_kb_wkvp(key, keylen));
+		if (rc)
+			continue; /* retry findcard on failure */
+
+		/* go through the list of apqns and try to derive an pkey */
+		for (rc = -ENODEV, j = 0; j < nr_apqns && rc; j++) {
+			card = apqns[j] >> 16;
+			dom = apqns[j] & 0xFFFF;
+			rc = ep11_kblob2protkey(card, dom, key, keylen,
+						protkey, protkeylen, protkeytype);
+		}
+
+		kfree(apqns);
 	}
 
-out:
-	kfree(apqns);
 	if (rc)
-		DEBUG_DBG("%s failed rc=%d\n", __func__, rc);
+		pr_debug("%s failed rc=%d\n", __func__, rc);
+
 	return rc;
 }
 
@@ -336,7 +338,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey,
 	int rc;
 
 	/* check the secure key for valid AES secure key */
-	rc = cca_check_secaeskeytoken(debug_info, 3, (u8 *)seckey, 0);
+	rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, (u8 *)seckey, 0);
 	if (rc)
 		goto out;
 	if (pattributes)
@@ -351,7 +353,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey,
 
 	if (rc > 0) {
 		/* key mkvp matches to old master key mkvp */
-		DEBUG_DBG("%s secure key has old mkvp\n", __func__);
+		pr_debug("%s secure key has old mkvp\n", __func__);
 		if (pattributes)
 			*pattributes |= PKEY_VERIFY_ATTR_OLD_MKVP;
 		rc = 0;
@@ -363,7 +365,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey,
 		*pdomain = domain;
 
 out:
-	DEBUG_DBG("%s rc=%d\n", __func__, rc);
+	pr_debug("%s rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -379,8 +381,8 @@ static int pkey_genprotkey(u32 keytype, u8 *protkey,
 
 	keysize = pkey_keytype_aes_to_size(keytype);
 	if (!keysize) {
-		DEBUG_ERR("%s unknown/unsupported keytype %d\n", __func__,
-			  keytype);
+		PKEY_DBF_ERR("%s unknown/unsupported keytype %d\n", __func__,
+			     keytype);
 		return -EINVAL;
 	}
 
@@ -428,13 +430,13 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen,
 		fc = CPACF_KMC_PAES_256;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keytype %u\n", __func__,
-			  protkeytype);
+		PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", __func__,
+			     protkeytype);
 		return -EINVAL;
 	}
 	if (protkeylen != pkeylen) {
-		DEBUG_ERR("%s invalid protected key size %u for keytype %u\n",
-			  __func__, protkeylen, protkeytype);
+		PKEY_DBF_ERR("%s invalid protected key size %u for keytype %u\n",
+			     __func__, protkeylen, protkeytype);
 		return -EINVAL;
 	}
 
@@ -446,7 +448,7 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen,
 	k = cpacf_kmc(fc | CPACF_ENCRYPT, &param, null_msg, dest_buf,
 		      sizeof(null_msg));
 	if (k != sizeof(null_msg)) {
-		DEBUG_ERR("%s protected key is not valid\n", __func__);
+		PKEY_DBF_ERR("%s protected key is not valid\n", __func__);
 		return -EKEYREJECTED;
 	}
 
@@ -464,13 +466,13 @@ static int nonccatokaes2pkey(const struct clearkeytoken *t,
 
 	keysize = pkey_keytype_aes_to_size(t->keytype);
 	if (!keysize) {
-		DEBUG_ERR("%s unknown/unsupported keytype %u\n",
-			  __func__, t->keytype);
+		PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n",
+			     __func__, t->keytype);
 		return -EINVAL;
 	}
 	if (t->len != keysize) {
-		DEBUG_ERR("%s non clear key aes token: invalid key len %u\n",
-			  __func__, t->len);
+		PKEY_DBF_ERR("%s non clear key aes token: invalid key len %u\n",
+			     __func__, t->len);
 		return -EINVAL;
 	}
 
@@ -505,7 +507,7 @@ try_via_ep11:
 		goto out;
 
 failure:
-	DEBUG_ERR("%s unable to build protected key from clear", __func__);
+	PKEY_DBF_ERR("%s unable to build protected key from clear", __func__);
 
 out:
 	kfree(tmpbuf);
@@ -536,14 +538,14 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t,
 		keylen = 64;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keytype %u\n",
-			  __func__, t->keytype);
+		PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n",
+			     __func__, t->keytype);
 		return -EINVAL;
 	}
 
 	if (t->len != keylen) {
-		DEBUG_ERR("%s non clear key ecc token: invalid key len %u\n",
-			  __func__, t->len);
+		PKEY_DBF_ERR("%s non clear key ecc token: invalid key len %u\n",
+			     __func__, t->len);
 		return -EINVAL;
 	}
 
@@ -551,8 +553,8 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t,
 	rc = pkey_clr2protkey(t->keytype, t->clearkey,
 			      protkey, protkeylen, protkeytype);
 	if (rc) {
-		DEBUG_ERR("%s unable to build protected key from clear",
-			  __func__);
+		PKEY_DBF_ERR("%s unable to build protected key from clear",
+			     __func__);
 	}
 
 	return rc;
@@ -604,15 +606,15 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen,
 					       protkeylen, protkeytype);
 			break;
 		default:
-			DEBUG_ERR("%s unknown/unsupported non cca clear key type %u\n",
-				  __func__, t->keytype);
+			PKEY_DBF_ERR("%s unknown/unsupported non cca clear key type %u\n",
+				     __func__, t->keytype);
 			return -EINVAL;
 		}
 		break;
 	}
 	case TOKVER_EP11_AES: {
 		/* check ep11 key for exportable as protected key */
-		rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1);
+		rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1);
 		if (rc)
 			goto out;
 		rc = pkey_ep11key2pkey(key, keylen,
@@ -621,15 +623,16 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen,
 	}
 	case TOKVER_EP11_AES_WITH_HEADER:
 		/* check ep11 key with header for exportable as protected key */
-		rc = ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1);
+		rc = ep11_check_aes_key_with_hdr(pkey_dbf_info,
+						 3, key, keylen, 1);
 		if (rc)
 			goto out;
 		rc = pkey_ep11key2pkey(key, keylen,
 				       protkey, protkeylen, protkeytype);
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported non-CCA token version %d\n",
-			  __func__, hdr->version);
+		PKEY_DBF_ERR("%s unknown/unsupported non-CCA token version %d\n",
+			     __func__, hdr->version);
 	}
 
 out:
@@ -654,8 +657,8 @@ static int pkey_ccainttok2pkey(const u8 *key, u32 keylen,
 			return -EINVAL;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported CCA internal token version %d\n",
-			  __func__, hdr->version);
+		PKEY_DBF_ERR("%s unknown/unsupported CCA internal token version %d\n",
+			     __func__, hdr->version);
 		return -EINVAL;
 	}
 
@@ -672,7 +675,7 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen,
 	int rc;
 
 	if (keylen < sizeof(struct keytoken_header)) {
-		DEBUG_ERR("%s invalid keylen %d\n", __func__, keylen);
+		PKEY_DBF_ERR("%s invalid keylen %d\n", __func__, keylen);
 		return -EINVAL;
 	}
 
@@ -686,12 +689,12 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen,
 					 protkey, protkeylen, protkeytype);
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported blob type %d\n",
-			  __func__, hdr->type);
+		PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n",
+			     __func__, hdr->type);
 		return -EINVAL;
 	}
 
-	DEBUG_DBG("%s rc=%d\n", __func__, rc);
+	pr_debug("%s rc=%d\n", __func__, rc);
 	return rc;
 }
 EXPORT_SYMBOL(pkey_keyblob2pkey);
@@ -839,7 +842,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 	    hdr->version == TOKVER_CCA_AES) {
 		struct secaeskeytoken *t = (struct secaeskeytoken *)key;
 
-		rc = cca_check_secaeskeytoken(debug_info, 3, key, 0);
+		rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0);
 		if (rc)
 			goto out;
 		if (ktype)
@@ -869,7 +872,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 		   hdr->version == TOKVER_CCA_VLSC) {
 		struct cipherkeytoken *t = (struct cipherkeytoken *)key;
 
-		rc = cca_check_secaescipherkey(debug_info, 3, key, 0, 1);
+		rc = cca_check_secaescipherkey(pkey_dbf_info, 3, key, 0, 1);
 		if (rc)
 			goto out;
 		if (ktype)
@@ -907,7 +910,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 		struct ep11keyblob *kb = (struct ep11keyblob *)key;
 		int api;
 
-		rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1);
+		rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1);
 		if (rc)
 			goto out;
 		if (ktype)
@@ -933,8 +936,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 		struct ep11kblob_header *kh = (struct ep11kblob_header *)key;
 		int api;
 
-		rc = ep11_check_aes_key_with_hdr(debug_info, 3,
-						 key, keylen, 1);
+		rc = ep11_check_aes_key_with_hdr(pkey_dbf_info,
+						 3, key, keylen, 1);
 		if (rc)
 			goto out;
 		if (ktype)
@@ -981,25 +984,27 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 		if (hdr->version == TOKVER_CCA_AES) {
 			if (keylen != sizeof(struct secaeskeytoken))
 				return -EINVAL;
-			if (cca_check_secaeskeytoken(debug_info, 3, key, 0))
+			if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0))
 				return -EINVAL;
 		} else if (hdr->version == TOKVER_CCA_VLSC) {
 			if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE)
 				return -EINVAL;
-			if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1))
+			if (cca_check_secaescipherkey(pkey_dbf_info,
+						      3, key, 0, 1))
 				return -EINVAL;
 		} else {
-			DEBUG_ERR("%s unknown CCA internal token version %d\n",
-				  __func__, hdr->version);
+			PKEY_DBF_ERR("%s unknown CCA internal token version %d\n",
+				     __func__, hdr->version);
 			return -EINVAL;
 		}
 	} else if (hdr->type == TOKTYPE_NON_CCA) {
 		if (hdr->version == TOKVER_EP11_AES) {
-			if (ep11_check_aes_key(debug_info, 3, key, keylen, 1))
+			if (ep11_check_aes_key(pkey_dbf_info,
+					       3, key, keylen, 1))
 				return -EINVAL;
 		} else if (hdr->version == TOKVER_EP11_AES_WITH_HEADER) {
-			if (ep11_check_aes_key_with_hdr(debug_info, 3,
-							key, keylen, 1))
+			if (ep11_check_aes_key_with_hdr(pkey_dbf_info,
+							3, key, keylen, 1))
 				return -EINVAL;
 		} else {
 			return pkey_nonccatok2pkey(key, keylen,
@@ -1007,8 +1012,8 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 						   protkeytype);
 		}
 	} else {
-		DEBUG_ERR("%s unknown/unsupported blob type %d\n",
-			  __func__, hdr->type);
+		PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n",
+			     __func__, hdr->type);
 		return -EINVAL;
 	}
 
@@ -1234,50 +1239,53 @@ static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns,
 	    hdr->version == TOKVER_EP11_AES_WITH_HEADER &&
 	    is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) {
 		/* EP11 AES key blob with header */
-		if (ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1))
+		if (ep11_check_aes_key_with_hdr(pkey_dbf_info,
+						3, key, keylen, 1))
 			return -EINVAL;
 	} else if (hdr->type == TOKTYPE_NON_CCA &&
 		   hdr->version == TOKVER_EP11_ECC_WITH_HEADER &&
 		   is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) {
 		/* EP11 ECC key blob with header */
-		if (ep11_check_ecc_key_with_hdr(debug_info, 3, key, keylen, 1))
+		if (ep11_check_ecc_key_with_hdr(pkey_dbf_info,
+						3, key, keylen, 1))
 			return -EINVAL;
 	} else if (hdr->type == TOKTYPE_NON_CCA &&
 		   hdr->version == TOKVER_EP11_AES &&
 		   is_ep11_keyblob(key)) {
 		/* EP11 AES key blob with header in session field */
-		if (ep11_check_aes_key(debug_info, 3, key, keylen, 1))
+		if (ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1))
 			return -EINVAL;
 	} else	if (hdr->type == TOKTYPE_CCA_INTERNAL) {
 		if (hdr->version == TOKVER_CCA_AES) {
 			/* CCA AES data key */
 			if (keylen != sizeof(struct secaeskeytoken))
 				return -EINVAL;
-			if (cca_check_secaeskeytoken(debug_info, 3, key, 0))
+			if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0))
 				return -EINVAL;
 		} else if (hdr->version == TOKVER_CCA_VLSC) {
 			/* CCA AES cipher key */
 			if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE)
 				return -EINVAL;
-			if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1))
+			if (cca_check_secaescipherkey(pkey_dbf_info,
+						      3, key, 0, 1))
 				return -EINVAL;
 		} else {
-			DEBUG_ERR("%s unknown CCA internal token version %d\n",
-				  __func__, hdr->version);
+			PKEY_DBF_ERR("%s unknown CCA internal token version %d\n",
+				     __func__, hdr->version);
 			return -EINVAL;
 		}
 	} else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) {
 		/* CCA ECC (private) key */
 		if (keylen < sizeof(struct eccprivkeytoken))
 			return -EINVAL;
-		if (cca_check_sececckeytoken(debug_info, 3, key, keylen, 1))
+		if (cca_check_sececckeytoken(pkey_dbf_info, 3, key, keylen, 1))
 			return -EINVAL;
 	} else if (hdr->type == TOKTYPE_NON_CCA) {
 		return pkey_nonccatok2pkey(key, keylen,
 					   protkey, protkeylen, protkeytype);
 	} else {
-		DEBUG_ERR("%s unknown/unsupported blob type %d\n",
-			  __func__, hdr->type);
+		PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n",
+			     __func__, hdr->type);
 		return -EINVAL;
 	}
 
@@ -1350,7 +1358,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		rc = cca_genseckey(kgs.cardnr, kgs.domain,
 				   kgs.keytype, kgs.seckey.seckey);
-		DEBUG_DBG("%s cca_genseckey()=%d\n", __func__, rc);
+		pr_debug("%s cca_genseckey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(ugs, &kgs, sizeof(kgs)))
@@ -1365,7 +1373,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		rc = cca_clr2seckey(kcs.cardnr, kcs.domain, kcs.keytype,
 				    kcs.clrkey.clrkey, kcs.seckey.seckey);
-		DEBUG_DBG("%s cca_clr2seckey()=%d\n", __func__, rc);
+		pr_debug("%s cca_clr2seckey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(ucs, &kcs, sizeof(kcs)))
@@ -1383,7 +1391,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = cca_sec2protkey(ksp.cardnr, ksp.domain,
 				     ksp.seckey.seckey, ksp.protkey.protkey,
 				     &ksp.protkey.len, &ksp.protkey.type);
-		DEBUG_DBG("%s cca_sec2protkey()=%d\n", __func__, rc);
+		pr_debug("%s cca_sec2protkey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(usp, &ksp, sizeof(ksp)))
@@ -1400,7 +1408,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = pkey_clr2protkey(kcp.keytype, kcp.clrkey.clrkey,
 				      kcp.protkey.protkey,
 				      &kcp.protkey.len, &kcp.protkey.type);
-		DEBUG_DBG("%s pkey_clr2protkey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_clr2protkey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(ucp, &kcp, sizeof(kcp)))
@@ -1416,7 +1424,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		rc = cca_findcard(kfc.seckey.seckey,
 				  &kfc.cardnr, &kfc.domain, 1);
-		DEBUG_DBG("%s cca_findcard()=%d\n", __func__, rc);
+		pr_debug("%s cca_findcard()=%d\n", __func__, rc);
 		if (rc < 0)
 			break;
 		if (copy_to_user(ufc, &kfc, sizeof(kfc)))
@@ -1432,7 +1440,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		ksp.protkey.len = sizeof(ksp.protkey.protkey);
 		rc = pkey_skey2pkey(ksp.seckey.seckey, ksp.protkey.protkey,
 				    &ksp.protkey.len, &ksp.protkey.type);
-		DEBUG_DBG("%s pkey_skey2pkey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_skey2pkey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(usp, &ksp, sizeof(ksp)))
@@ -1447,7 +1455,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		rc = pkey_verifykey(&kvk.seckey, &kvk.cardnr, &kvk.domain,
 				    &kvk.keysize, &kvk.attributes);
-		DEBUG_DBG("%s pkey_verifykey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_verifykey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(uvk, &kvk, sizeof(kvk)))
@@ -1463,7 +1471,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		kgp.protkey.len = sizeof(kgp.protkey.protkey);
 		rc = pkey_genprotkey(kgp.keytype, kgp.protkey.protkey,
 				     &kgp.protkey.len, &kgp.protkey.type);
-		DEBUG_DBG("%s pkey_genprotkey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_genprotkey()=%d\n", __func__, rc);
 		if (rc)
 			break;
 		if (copy_to_user(ugp, &kgp, sizeof(kgp)))
@@ -1478,7 +1486,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		rc = pkey_verifyprotkey(kvp.protkey.protkey,
 					kvp.protkey.len, kvp.protkey.type);
-		DEBUG_DBG("%s pkey_verifyprotkey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_verifyprotkey()=%d\n", __func__, rc);
 		break;
 	}
 	case PKEY_KBLOB2PROTK: {
@@ -1494,7 +1502,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		ktp.protkey.len = sizeof(ktp.protkey.protkey);
 		rc = pkey_keyblob2pkey(kkey, ktp.keylen, ktp.protkey.protkey,
 				       &ktp.protkey.len, &ktp.protkey.type);
-		DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc);
+		pr_debug("%s pkey_keyblob2pkey()=%d\n", __func__, rc);
 		memzero_explicit(kkey, ktp.keylen);
 		kfree(kkey);
 		if (rc)
@@ -1523,7 +1531,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = pkey_genseckey2(apqns, kgs.apqn_entries,
 				     kgs.type, kgs.size, kgs.keygenflags,
 				     kkey, &klen);
-		DEBUG_DBG("%s pkey_genseckey2()=%d\n", __func__, rc);
+		pr_debug("%s pkey_genseckey2()=%d\n", __func__, rc);
 		kfree(apqns);
 		if (rc) {
 			kfree(kkey);
@@ -1565,7 +1573,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = pkey_clr2seckey2(apqns, kcs.apqn_entries,
 				      kcs.type, kcs.size, kcs.keygenflags,
 				      kcs.clrkey.clrkey, kkey, &klen);
-		DEBUG_DBG("%s pkey_clr2seckey2()=%d\n", __func__, rc);
+		pr_debug("%s pkey_clr2seckey2()=%d\n", __func__, rc);
 		kfree(apqns);
 		if (rc) {
 			kfree(kkey);
@@ -1601,7 +1609,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = pkey_verifykey2(kkey, kvk.keylen,
 				     &kvk.cardnr, &kvk.domain,
 				     &kvk.type, &kvk.size, &kvk.flags);
-		DEBUG_DBG("%s pkey_verifykey2()=%d\n", __func__, rc);
+		pr_debug("%s pkey_verifykey2()=%d\n", __func__, rc);
 		kfree(kkey);
 		if (rc)
 			break;
@@ -1630,7 +1638,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 					kkey, ktp.keylen,
 					ktp.protkey.protkey, &ktp.protkey.len,
 					&ktp.protkey.type);
-		DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc);
+		pr_debug("%s pkey_keyblob2pkey2()=%d\n", __func__, rc);
 		kfree(apqns);
 		memzero_explicit(kkey, ktp.keylen);
 		kfree(kkey);
@@ -1664,7 +1672,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		}
 		rc = pkey_apqns4key(kkey, kak.keylen, kak.flags,
 				    apqns, &nr_apqns);
-		DEBUG_DBG("%s pkey_apqns4key()=%d\n", __func__, rc);
+		pr_debug("%s pkey_apqns4key()=%d\n", __func__, rc);
 		kfree(kkey);
 		if (rc && rc != -ENOSPC) {
 			kfree(apqns);
@@ -1707,7 +1715,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		}
 		rc = pkey_apqns4keytype(kat.type, kat.cur_mkvp, kat.alt_mkvp,
 					kat.flags, apqns, &nr_apqns);
-		DEBUG_DBG("%s pkey_apqns4keytype()=%d\n", __func__, rc);
+		pr_debug("%s pkey_apqns4keytype()=%d\n", __func__, rc);
 		if (rc && rc != -ENOSPC) {
 			kfree(apqns);
 			break;
@@ -1757,7 +1765,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		rc = pkey_keyblob2pkey3(apqns, ktp.apqn_entries,
 					kkey, ktp.keylen,
 					protkey, &protkeylen, &ktp.pkeytype);
-		DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc);
+		pr_debug("%s pkey_keyblob2pkey3()=%d\n", __func__, rc);
 		kfree(apqns);
 		memzero_explicit(kkey, ktp.keylen);
 		kfree(kkey);
diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c
index a5ab03e42ff1..4aeb3e1213c7 100644
--- a/drivers/s390/crypto/vfio_ap_drv.c
+++ b/drivers/s390/crypto/vfio_ap_drv.c
@@ -60,7 +60,7 @@ static void vfio_ap_matrix_dev_release(struct device *dev)
 	kfree(matrix_dev);
 }
 
-static struct bus_type matrix_bus = {
+static const struct bus_type matrix_bus = {
 	.name = "matrix",
 };
 
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 983b3b16196c..fc169bc61593 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -659,6 +659,21 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
 			     AP_DOMAINS);
 }
 
+static bool _queue_passable(struct vfio_ap_queue *q)
+{
+	if (!q)
+		return false;
+
+	switch (q->reset_status.response_code) {
+	case AP_RESPONSE_NORMAL:
+	case AP_RESPONSE_DECONFIGURED:
+	case AP_RESPONSE_CHECKSTOPPED:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * vfio_ap_mdev_filter_matrix - filter the APQNs assigned to the matrix mdev
  *				to ensure no queue devices are passed through to
@@ -687,7 +702,6 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
 	DECLARE_BITMAP(prev_shadow_aqm, AP_DOMAINS);
-	struct vfio_ap_queue *q;
 
 	bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES);
 	bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS);
@@ -716,8 +730,7 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
 			 * hardware device.
 			 */
 			apqn = AP_MKQID(apid, apqi);
-			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
-			if (!q || q->reset_status.response_code) {
+			if (!_queue_passable(vfio_ap_mdev_get_queue(matrix_mdev, apqn))) {
 				clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 
 				/*
@@ -1691,6 +1704,7 @@ static int apq_status_check(int apqn, struct ap_queue_status *status)
 	switch (status->response_code) {
 	case AP_RESPONSE_NORMAL:
 	case AP_RESPONSE_DECONFIGURED:
+	case AP_RESPONSE_CHECKSTOPPED:
 		return 0;
 	case AP_RESPONSE_RESET_IN_PROGRESS:
 	case AP_RESPONSE_BUSY:
@@ -1747,14 +1761,6 @@ static void apq_reset_check(struct work_struct *reset_work)
 				memcpy(&q->reset_status, &status, sizeof(status));
 				continue;
 			}
-			/*
-			 * When an AP adapter is deconfigured, the
-			 * associated queues are reset, so let's set the
-			 * status response code to 0 so the queue may be
-			 * passed through (i.e., not filtered)
-			 */
-			if (status.response_code == AP_RESPONSE_DECONFIGURED)
-				q->reset_status.response_code = 0;
 			if (q->saved_isc != VFIO_AP_ISC_INVALID)
 				vfio_ap_free_aqic_resources(q);
 			break;
@@ -1781,12 +1787,7 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q)
 		queue_work(system_long_wq, &q->reset_work);
 		break;
 	case AP_RESPONSE_DECONFIGURED:
-		/*
-		 * When an AP adapter is deconfigured, the associated
-		 * queues are reset, so let's set the status response code to 0
-		 * so the queue may be passed through (i.e., not filtered).
-		 */
-		q->reset_status.response_code = 0;
+	case AP_RESPONSE_CHECKSTOPPED:
 		vfio_ap_free_aqic_resources(q);
 		break;
 	default:
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 74200f54dfff..02c503f16bc2 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -12,6 +12,9 @@
  *  Multiple device nodes: Harald Freudenberger <freude@linux.ibm.com>
  */
 
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -57,10 +60,6 @@ DEFINE_SPINLOCK(zcrypt_list_lock);
 LIST_HEAD(zcrypt_card_list);
 
 static atomic_t zcrypt_open_count = ATOMIC_INIT(0);
-static atomic_t zcrypt_rescan_count = ATOMIC_INIT(0);
-
-atomic_t zcrypt_rescan_req = ATOMIC_INIT(0);
-EXPORT_SYMBOL(zcrypt_rescan_req);
 
 static LIST_HEAD(zcrypt_ops_list);
 
@@ -69,20 +68,15 @@ debug_info_t *zcrypt_dbf_info;
 
 /*
  * Process a rescan of the transport layer.
- *
- * Returns 1, if the rescan has been processed, otherwise 0.
+ * Runs a synchronous AP bus rescan.
+ * Returns true if something has changed (for example the
+ * bus scan has found and build up new devices) and it is
+ * worth to do a retry. Otherwise false is returned meaning
+ * no changes on the AP bus level.
  */
-static inline int zcrypt_process_rescan(void)
-{
-	if (atomic_read(&zcrypt_rescan_req)) {
-		atomic_set(&zcrypt_rescan_req, 0);
-		atomic_inc(&zcrypt_rescan_count);
-		ap_bus_force_rescan();
-		ZCRYPT_DBF_INFO("%s rescan count=%07d\n", __func__,
-				atomic_inc_return(&zcrypt_rescan_count));
-		return 1;
-	}
-	return 0;
+static inline bool zcrypt_process_rescan(void)
+{
+	return ap_bus_force_rescan();
 }
 
 void zcrypt_msgtype_register(struct zcrypt_ops *zops)
@@ -715,8 +709,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
-		ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n",
-			       __func__);
+		pr_debug("%s no matching queue found => ENODEV\n", __func__);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -820,8 +813,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
-		ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n",
-			       __func__);
+		pr_debug("%s no matching queue found => ENODEV\n", __func__);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -865,6 +857,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms,
 	rc = prep_cca_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain);
 	if (rc)
 		goto out;
+	print_hex_dump_debug("ccareq: ", DUMP_PREFIX_ADDRESS, 16, 1,
+			     ap_msg.msg, ap_msg.len, false);
 
 	tdom = *domain;
 	if (perms != &ap_perms && tdom < AP_DOMAINS) {
@@ -940,8 +934,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms,
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
-		ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n",
-			       __func__, xcrb->user_defined, *domain);
+		pr_debug("%s no match for address %02x.%04x => ENODEV\n",
+			 __func__, xcrb->user_defined, *domain);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -952,6 +946,10 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms,
 		*domain = AP_QID_QUEUE(qid);
 
 	rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcrb, &ap_msg);
+	if (!rc) {
+		print_hex_dump_debug("ccarpl: ", DUMP_PREFIX_ADDRESS, 16, 1,
+				     ap_msg.msg, ap_msg.len, false);
+	}
 
 	spin_lock(&zcrypt_list_lock);
 	zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt);
@@ -970,7 +968,26 @@ out:
 
 long zcrypt_send_cprb(struct ica_xcRB *xcrb)
 {
-	return _zcrypt_send_cprb(false, &ap_perms, NULL, xcrb);
+	struct zcrypt_track tr;
+	int rc;
+
+	memset(&tr, 0, sizeof(tr));
+
+	do {
+		rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb);
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
+		do {
+			rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
+		rc = -EIO;
+	if (rc)
+		pr_debug("%s rc=%d\n", __func__, rc);
+
+	return rc;
 }
 EXPORT_SYMBOL(zcrypt_send_cprb);
 
@@ -1045,6 +1062,8 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms,
 	rc = prep_ep11_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain);
 	if (rc)
 		goto out_free;
+	print_hex_dump_debug("ep11req: ", DUMP_PREFIX_ADDRESS, 16, 1,
+			     ap_msg.msg, ap_msg.len, false);
 
 	if (perms != &ap_perms && domain < AUTOSEL_DOM) {
 		if (ap_msg.flags & AP_MSG_FLAG_ADMIN) {
@@ -1113,15 +1132,15 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms,
 
 	if (!pref_zq) {
 		if (targets && target_num == 1) {
-			ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n",
-				       __func__, (int)targets->ap_id,
-				       (int)targets->dom_id);
+			pr_debug("%s no match for address %02x.%04x => ENODEV\n",
+				 __func__, (int)targets->ap_id,
+				 (int)targets->dom_id);
 		} else if (targets) {
-			ZCRYPT_DBF_DBG("%s no match for %d target addrs => ENODEV\n",
-				       __func__, (int)target_num);
+			pr_debug("%s no match for %d target addrs => ENODEV\n",
+				 __func__, (int)target_num);
 		} else {
-			ZCRYPT_DBF_DBG("%s no match for address ff.ffff => ENODEV\n",
-				       __func__);
+			pr_debug("%s no match for address ff.ffff => ENODEV\n",
+				 __func__);
 		}
 		rc = -ENODEV;
 		goto out_free;
@@ -1129,6 +1148,10 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms,
 
 	qid = pref_zq->queue->qid;
 	rc = pref_zq->ops->send_ep11_cprb(userspace, pref_zq, xcrb, &ap_msg);
+	if (!rc) {
+		print_hex_dump_debug("ep11rpl: ", DUMP_PREFIX_ADDRESS, 16, 1,
+				     ap_msg.msg, ap_msg.len, false);
+	}
 
 	spin_lock(&zcrypt_list_lock);
 	zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt);
@@ -1149,7 +1172,26 @@ out:
 
 long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
 {
-	return _zcrypt_send_ep11_cprb(false, &ap_perms, NULL, xcrb);
+	struct zcrypt_track tr;
+	int rc;
+
+	memset(&tr, 0, sizeof(tr));
+
+	do {
+		rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb);
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
+		do {
+			rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
+		rc = -EIO;
+	if (rc)
+		pr_debug("%s rc=%d\n", __func__, rc);
+
+	return rc;
 }
 EXPORT_SYMBOL(zcrypt_send_ep11_cprb);
 
@@ -1199,8 +1241,7 @@ static long zcrypt_rng(char *buffer)
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
-		ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n",
-			       __func__);
+		pr_debug("%s no matching queue found => ENODEV\n", __func__);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -1431,20 +1472,17 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg)
 
 	do {
 		rc = zcrypt_rsa_modexpo(perms, &tr, &mex);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = zcrypt_rsa_modexpo(perms, &tr, &mex);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc) {
-		ZCRYPT_DBF_DBG("ioctl ICARSAMODEXPO rc=%d\n", rc);
+		pr_debug("ioctl ICARSAMODEXPO rc=%d\n", rc);
 		return rc;
 	}
 	return put_user(mex.outputdatalength, &umex->outputdatalength);
@@ -1463,20 +1501,17 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg)
 
 	do {
 		rc = zcrypt_rsa_crt(perms, &tr, &crt);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = zcrypt_rsa_crt(perms, &tr, &crt);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc) {
-		ZCRYPT_DBF_DBG("ioctl ICARSACRT rc=%d\n", rc);
+		pr_debug("ioctl ICARSACRT rc=%d\n", rc);
 		return rc;
 	}
 	return put_user(crt.outputdatalength, &ucrt->outputdatalength);
@@ -1495,21 +1530,18 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg)
 
 	do {
 		rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc)
-		ZCRYPT_DBF_DBG("ioctl ZSENDCPRB rc=%d status=0x%x\n",
-			       rc, xcrb.status);
+		pr_debug("ioctl ZSENDCPRB rc=%d status=0x%x\n",
+			 rc, xcrb.status);
 	if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb)))
 		return -EFAULT;
 	return rc;
@@ -1528,20 +1560,17 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg)
 
 	do {
 		rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc)
-		ZCRYPT_DBF_DBG("ioctl ZSENDEP11CPRB rc=%d\n", rc);
+		pr_debug("ioctl ZSENDEP11CPRB rc=%d\n", rc);
 	if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb)))
 		return -EFAULT;
 	return rc;
@@ -1670,7 +1699,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
 	}
 	/* unknown ioctl number */
 	default:
-		ZCRYPT_DBF_DBG("unknown ioctl 0x%08x\n", cmd);
+		pr_debug("unknown ioctl 0x%08x\n", cmd);
 		return -ENOIOCTLCMD;
 	}
 }
@@ -1708,16 +1737,13 @@ static long trans_modexpo32(struct ap_perms *perms, struct file *filp,
 	mex64.n_modulus = compat_ptr(mex32.n_modulus);
 	do {
 		rc = zcrypt_rsa_modexpo(perms, &tr, &mex64);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = zcrypt_rsa_modexpo(perms, &tr, &mex64);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc)
@@ -1761,16 +1787,13 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp,
 	crt64.u_mult_inv = compat_ptr(crt32.u_mult_inv);
 	do {
 		rc = zcrypt_rsa_crt(perms, &tr, &crt64);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = zcrypt_rsa_crt(perms, &tr, &crt64);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	if (rc)
@@ -1833,16 +1856,13 @@ static long trans_xcrb32(struct ap_perms *perms, struct file *filp,
 	xcrb64.status = xcrb32.status;
 	do {
 		rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64);
-		if (rc == -EAGAIN)
-			tr.again_counter++;
-	} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
-	/* on failure: retry once again after a requested rescan */
-	if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+	} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
+
+	/* on ENODEV failure: retry once again after a requested rescan */
+	if (rc == -ENODEV && zcrypt_process_rescan())
 		do {
 			rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64);
-			if (rc == -EAGAIN)
-				tr.again_counter++;
-		} while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX);
+		} while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX);
 	if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX)
 		rc = -EIO;
 	xcrb32.reply_control_blk_length = xcrb64.reply_control_blk_length;
@@ -1914,8 +1934,8 @@ static int zcrypt_rng_data_read(struct hwrng *rng, u32 *data)
 	 */
 	if (zcrypt_rng_buffer_index == 0) {
 		rc = zcrypt_rng((char *)zcrypt_rng_buffer);
-		/* on failure: retry once again after a requested rescan */
-		if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+		/* on ENODEV failure: retry once again after an AP bus rescan */
+		if (rc == -ENODEV && zcrypt_process_rescan())
 			rc = zcrypt_rng((char *)zcrypt_rng_buffer);
 		if (rc < 0)
 			return -EIO;
@@ -1977,7 +1997,7 @@ void zcrypt_rng_device_remove(void)
  * an asynchronous job. This function waits until these initial jobs
  * are done and so the zcrypt api should be ready to serve crypto
  * requests - if there are resources available. The function uses an
- * internal timeout of 60s. The very first caller will either wait for
+ * internal timeout of 30s. The very first caller will either wait for
  * ap bus bindings complete or the timeout happens. This state will be
  * remembered for further callers which will only be blocked until a
  * decision is made (timeout or bindings complete).
@@ -1996,8 +2016,8 @@ int zcrypt_wait_api_operational(void)
 	switch (zcrypt_wait_api_state) {
 	case 0:
 		/* initial state, invoke wait for the ap bus complete */
-		rc = ap_wait_init_apqn_bindings_complete(
-			msecs_to_jiffies(60 * 1000));
+		rc = ap_wait_apqn_bindings_complete(
+			msecs_to_jiffies(ZCRYPT_WAIT_BINDINGS_COMPLETE_MS));
 		switch (rc) {
 		case 0:
 			/* ap bus bindings are complete */
@@ -2014,8 +2034,8 @@ int zcrypt_wait_api_operational(void)
 			break;
 		default:
 			/* other failure */
-			ZCRYPT_DBF_DBG("%s ap_wait_init_apqn_bindings_complete()=%d\n",
-				       __func__, rc);
+			pr_debug("%s ap_wait_init_apqn_bindings_complete()=%d\n",
+				 __func__, rc);
 			break;
 		}
 		break;
@@ -2038,7 +2058,7 @@ EXPORT_SYMBOL(zcrypt_wait_api_operational);
 int __init zcrypt_debug_init(void)
 {
 	zcrypt_dbf_info = debug_register("zcrypt", 2, 1,
-					 DBF_MAX_SPRINTF_ARGS * sizeof(long));
+					 ZCRYPT_DBF_MAX_SPRINTF_ARGS * sizeof(long));
 	debug_register_view(zcrypt_dbf_info, &debug_sprintf_view);
 	debug_set_level(zcrypt_dbf_info, DBF_ERR);
 
diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h
index de659954c8f7..4ed481df57ca 100644
--- a/drivers/s390/crypto/zcrypt_api.h
+++ b/drivers/s390/crypto/zcrypt_api.h
@@ -38,6 +38,15 @@
  */
 #define ZCRYPT_RNG_BUFFER_SIZE	4096
 
+/**
+ * The zcrypt_wait_api_operational() function waits this
+ * amount in milliseconds for ap_wait_aqpn_bindings_complete().
+ * Also on a cprb send failure with ENODEV the send functions
+ * trigger an ap bus rescan and wait this time in milliseconds
+ * for ap_wait_aqpn_bindings_complete() before resending.
+ */
+#define ZCRYPT_WAIT_BINDINGS_COMPLETE_MS 30000
+
 /*
  * Identifier for Crypto Request Performance Index
  */
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 263fe182648b..0a3a678ffc7e 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -23,11 +23,6 @@
 #include "zcrypt_msgtype6.h"
 #include "zcrypt_ccamisc.h"
 
-#define DEBUG_DBG(...)	ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__)
-#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__)
-#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__)
-#define DEBUG_ERR(...)	ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__)
-
 /* Size of parameter block used for all cca requests/replies */
 #define PARMBSIZE 512
 
@@ -367,8 +362,8 @@ int cca_genseckey(u16 cardnr, u16 domain,
 		memcpy(preqparm->lv1.key_length, "KEYLN32 ", 8);
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keybitsize %d\n",
-			  __func__, keybitsize);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n",
+			       __func__, keybitsize);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -386,15 +381,15 @@ int cca_genseckey(u16 cardnr, u16 domain,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n",
-			  __func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR("%s secure key generate failure, card response %d/%d\n",
-			  __func__,
+		ZCRYPT_DBF_ERR("%s secure key generate failure, card response %d/%d\n",
+			       __func__,
 			  (int)prepcblk->ccp_rtcode,
 			  (int)prepcblk->ccp_rscode);
 		rc = -EIO;
@@ -411,8 +406,8 @@ int cca_genseckey(u16 cardnr, u16 domain,
 		- sizeof(prepparm->lv3.keyblock.toklen)
 		- sizeof(prepparm->lv3.keyblock.tokattr);
 	if (seckeysize != SECKEYBLOBSIZE) {
-		DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n",
-			  __func__, seckeysize, SECKEYBLOBSIZE);
+		ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n",
+			       __func__, seckeysize, SECKEYBLOBSIZE);
 		rc = -EIO;
 		goto out;
 	}
@@ -505,8 +500,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize,
 		keysize = 32;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keybitsize %d\n",
-			  __func__, keybitsize);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n",
+			       __func__, keybitsize);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -524,17 +519,17 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			  __func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR("%s clear key import failure, card response %d/%d\n",
-			  __func__,
-			  (int)prepcblk->ccp_rtcode,
-			  (int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s clear key import failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		rc = -EIO;
 		goto out;
 	}
@@ -549,8 +544,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize,
 		- sizeof(prepparm->lv3.keyblock.toklen)
 		- sizeof(prepparm->lv3.keyblock.tokattr);
 	if (seckeysize != SECKEYBLOBSIZE) {
-		DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n",
-			  __func__, seckeysize, SECKEYBLOBSIZE);
+		ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n",
+			       __func__, seckeysize, SECKEYBLOBSIZE);
 		rc = -EIO;
 		goto out;
 	}
@@ -651,17 +646,17 @@ int cca_sec2protkey(u16 cardnr, u16 domain,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			  __func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n",
-			  __func__,
-			  (int)prepcblk->ccp_rtcode,
-			  (int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
 			rc = -EAGAIN;
 		else
@@ -669,10 +664,10 @@ int cca_sec2protkey(u16 cardnr, u16 domain,
 		goto out;
 	}
 	if (prepcblk->ccp_rscode != 0) {
-		DEBUG_WARN("%s unwrap secure key warning, card response %d/%d\n",
-			   __func__,
-			   (int)prepcblk->ccp_rtcode,
-			   (int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n",
+				__func__,
+				(int)prepcblk->ccp_rtcode,
+				(int)prepcblk->ccp_rscode);
 	}
 
 	/* process response cprb param block */
@@ -683,8 +678,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain,
 	/* check the returned keyblock */
 	if (prepparm->lv3.ckb.version != 0x01 &&
 	    prepparm->lv3.ckb.version != 0x02) {
-		DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n",
-			  __func__, (int)prepparm->lv3.ckb.version);
+		ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n",
+			       __func__, (int)prepparm->lv3.ckb.version);
 		rc = -EIO;
 		goto out;
 	}
@@ -707,8 +702,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain,
 			*protkeytype = PKEY_KEYTYPE_AES_256;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keylen %d\n",
-			  __func__, prepparm->lv3.ckb.len);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n",
+			       __func__, prepparm->lv3.ckb.len);
 		rc = -EIO;
 		goto out;
 	}
@@ -840,9 +835,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags,
 	case 256:
 		break;
 	default:
-		DEBUG_ERR(
-			"%s unknown/unsupported keybitsize %d\n",
-			__func__, keybitsize);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n",
+			       __func__, keybitsize);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -880,19 +874,17 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			__func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR(
-			"%s cipher key generate failure, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s cipher key generate failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		rc = -EIO;
 		goto out;
 	}
@@ -905,8 +897,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags,
 	/* do some plausibility checks on the key block */
 	if (prepparm->kb.len < 120 + 5 * sizeof(uint16_t) ||
 	    prepparm->kb.len > 136 + 5 * sizeof(uint16_t)) {
-		DEBUG_ERR("%s reply with invalid or unknown key block\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n",
+			       __func__);
 		rc = -EIO;
 		goto out;
 	}
@@ -1048,19 +1040,17 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			__func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR(
-			"%s CSNBKPI2 failure, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s CSNBKPI2 failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		rc = -EIO;
 		goto out;
 	}
@@ -1073,8 +1063,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain,
 	/* do some plausibility checks on the key block */
 	if (prepparm->kb.len < 120 + 3 * sizeof(uint16_t) ||
 	    prepparm->kb.len > 136 + 3 * sizeof(uint16_t)) {
-		DEBUG_ERR("%s reply with invalid or unknown key block\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n",
+			       __func__);
 		rc = -EIO;
 		goto out;
 	}
@@ -1132,33 +1122,29 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags,
 	rc = _ip_cprb_helper(card, dom, "AES     ", "FIRST   ", "MIN3PART",
 			     exorbuf, keybitsize, token, &tokensize);
 	if (rc) {
-		DEBUG_ERR(
-			"%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 	rc = _ip_cprb_helper(card, dom, "AES     ", "ADD-PART", NULL,
 			     clrkey, keybitsize, token, &tokensize);
 	if (rc) {
-		DEBUG_ERR(
-			"%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 	rc = _ip_cprb_helper(card, dom, "AES     ", "ADD-PART", NULL,
 			     exorbuf, keybitsize, token, &tokensize);
 	if (rc) {
-		DEBUG_ERR(
-			"%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 	rc = _ip_cprb_helper(card, dom, "AES     ", "COMPLETE", NULL,
 			     NULL, keybitsize, token, &tokensize);
 	if (rc) {
-		DEBUG_ERR(
-			"%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 
@@ -1265,19 +1251,17 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			__func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR(
-			"%s unwrap secure key failure, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
 			rc = -EAGAIN;
 		else
@@ -1285,11 +1269,10 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey,
 		goto out;
 	}
 	if (prepcblk->ccp_rscode != 0) {
-		DEBUG_WARN(
-			"%s unwrap secure key warning, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n",
+				__func__,
+				(int)prepcblk->ccp_rtcode,
+				(int)prepcblk->ccp_rscode);
 	}
 
 	/* process response cprb param block */
@@ -1300,15 +1283,14 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey,
 	/* check the returned keyblock */
 	if (prepparm->vud.ckb.version != 0x01 &&
 	    prepparm->vud.ckb.version != 0x02) {
-		DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n",
-			  __func__, (int)prepparm->vud.ckb.version);
+		ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n",
+			       __func__, (int)prepparm->vud.ckb.version);
 		rc = -EIO;
 		goto out;
 	}
 	if (prepparm->vud.ckb.algo != 0x02) {
-		DEBUG_ERR(
-			"%s reply param keyblock algo mismatch 0x%02x != 0x02\n",
-			__func__, (int)prepparm->vud.ckb.algo);
+		ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x02\n",
+			       __func__, (int)prepparm->vud.ckb.algo);
 		rc = -EIO;
 		goto out;
 	}
@@ -1331,8 +1313,8 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey,
 			*protkeytype = PKEY_KEYTYPE_AES_256;
 		break;
 	default:
-		DEBUG_ERR("%s unknown/unsupported keylen %d\n",
-			  __func__, prepparm->vud.ckb.keylen);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n",
+			       __func__, prepparm->vud.ckb.keylen);
 		rc = -EIO;
 		goto out;
 	}
@@ -1432,19 +1414,17 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			__func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR(
-			"%s unwrap secure key failure, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
 			rc = -EAGAIN;
 		else
@@ -1452,11 +1432,10 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key,
 		goto out;
 	}
 	if (prepcblk->ccp_rscode != 0) {
-		DEBUG_WARN(
-			"%s unwrap secure key warning, card response %d/%d\n",
-			__func__,
-			(int)prepcblk->ccp_rtcode,
-			(int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n",
+				__func__,
+				(int)prepcblk->ccp_rtcode,
+				(int)prepcblk->ccp_rscode);
 	}
 
 	/* process response cprb param block */
@@ -1466,23 +1445,22 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key,
 
 	/* check the returned keyblock */
 	if (prepparm->vud.ckb.version != 0x02) {
-		DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n",
-			  __func__, (int)prepparm->vud.ckb.version);
+		ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n",
+			       __func__, (int)prepparm->vud.ckb.version);
 		rc = -EIO;
 		goto out;
 	}
 	if (prepparm->vud.ckb.algo != 0x81) {
-		DEBUG_ERR(
-			"%s reply param keyblock algo mismatch 0x%02x != 0x81\n",
-			__func__, (int)prepparm->vud.ckb.algo);
+		ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x81\n",
+			       __func__, (int)prepparm->vud.ckb.algo);
 		rc = -EIO;
 		goto out;
 	}
 
 	/* copy the translated protected key */
 	if (prepparm->vud.ckb.keylen > *protkeylen) {
-		DEBUG_ERR("%s prot keylen mismatch %d > buffersize %u\n",
-			  __func__, prepparm->vud.ckb.keylen, *protkeylen);
+		ZCRYPT_DBF_ERR("%s prot keylen mismatch %d > buffersize %u\n",
+			       __func__, prepparm->vud.ckb.keylen, *protkeylen);
 		rc = -EIO;
 		goto out;
 	}
@@ -1550,17 +1528,17 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain,
 	/* forward xcrb with request CPRB and reply CPRB to zcrypt dd */
 	rc = zcrypt_send_cprb(&xcrb);
 	if (rc) {
-		DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
-			  __func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
 	/* check response returncode and reasoncode */
 	if (prepcblk->ccp_rtcode != 0) {
-		DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n",
-			  __func__,
-			  (int)prepcblk->ccp_rtcode,
-			  (int)prepcblk->ccp_rscode);
+		ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n",
+			       __func__,
+			       (int)prepcblk->ccp_rtcode,
+			       (int)prepcblk->ccp_rscode);
 		rc = -EIO;
 		goto out;
 	}
diff --git a/drivers/s390/crypto/zcrypt_debug.h b/drivers/s390/crypto/zcrypt_debug.h
index 5cf88aabd64b..9a208dc4c200 100644
--- a/drivers/s390/crypto/zcrypt_debug.h
+++ b/drivers/s390/crypto/zcrypt_debug.h
@@ -17,7 +17,7 @@
 #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO)
 #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO)
 
-#define DBF_MAX_SPRINTF_ARGS 6
+#define ZCRYPT_DBF_MAX_SPRINTF_ARGS 6
 
 #define ZCRYPT_DBF(...)					\
 	debug_sprintf_event(zcrypt_dbf_info, ##__VA_ARGS__)
@@ -27,8 +27,6 @@
 	debug_sprintf_event(zcrypt_dbf_info, DBF_WARN, ##__VA_ARGS__)
 #define ZCRYPT_DBF_INFO(...)					\
 	debug_sprintf_event(zcrypt_dbf_info, DBF_INFO, ##__VA_ARGS__)
-#define ZCRYPT_DBF_DBG(...)					\
-	debug_sprintf_event(zcrypt_dbf_info, DBF_DEBUG, ##__VA_ARGS__)
 
 extern debug_info_t *zcrypt_dbf_info;
 
diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c
index 0a877f9792c2..eb7f5489ccf9 100644
--- a/drivers/s390/crypto/zcrypt_ep11misc.c
+++ b/drivers/s390/crypto/zcrypt_ep11misc.c
@@ -24,11 +24,6 @@
 #include "zcrypt_ep11misc.h"
 #include "zcrypt_ccamisc.h"
 
-#define DEBUG_DBG(...)	ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__)
-#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__)
-#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__)
-#define DEBUG_ERR(...)	ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__)
-
 #define EP11_PINBLOB_V1_BYTES 56
 
 /* default iv used here */
@@ -510,7 +505,7 @@ static int check_reply_pl(const u8 *pl, const char *func)
 
 	/* start tag */
 	if (*pl++ != 0x30) {
-		DEBUG_ERR("%s reply start tag mismatch\n", func);
+		ZCRYPT_DBF_ERR("%s reply start tag mismatch\n", func);
 		return -EIO;
 	}
 
@@ -527,40 +522,41 @@ static int check_reply_pl(const u8 *pl, const char *func)
 		len = *((u16 *)pl);
 		pl += 2;
 	} else {
-		DEBUG_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n",
-			  func, *pl);
+		ZCRYPT_DBF_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n",
+			       func, *pl);
 		return -EIO;
 	}
 
 	/* len should cover at least 3 fields with 32 bit value each */
 	if (len < 3 * 6) {
-		DEBUG_ERR("%s reply length %d too small\n", func, len);
+		ZCRYPT_DBF_ERR("%s reply length %d too small\n", func, len);
 		return -EIO;
 	}
 
 	/* function tag, length and value */
 	if (pl[0] != 0x04 || pl[1] != 0x04) {
-		DEBUG_ERR("%s function tag or length mismatch\n", func);
+		ZCRYPT_DBF_ERR("%s function tag or length mismatch\n", func);
 		return -EIO;
 	}
 	pl += 6;
 
 	/* dom tag, length and value */
 	if (pl[0] != 0x04 || pl[1] != 0x04) {
-		DEBUG_ERR("%s dom tag or length mismatch\n", func);
+		ZCRYPT_DBF_ERR("%s dom tag or length mismatch\n", func);
 		return -EIO;
 	}
 	pl += 6;
 
 	/* return value tag, length and value */
 	if (pl[0] != 0x04 || pl[1] != 0x04) {
-		DEBUG_ERR("%s return value tag or length mismatch\n", func);
+		ZCRYPT_DBF_ERR("%s return value tag or length mismatch\n",
+			       func);
 		return -EIO;
 	}
 	pl += 2;
 	ret = *((u32 *)pl);
 	if (ret != 0) {
-		DEBUG_ERR("%s return value 0x%04x != 0\n", func, ret);
+		ZCRYPT_DBF_ERR("%s return value 0x%04x != 0\n", func, ret);
 		return -EIO;
 	}
 
@@ -626,9 +622,8 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type,
 
 	rc = zcrypt_send_ep11_cprb(urb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
-			__func__, (int)cardnr, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			       __func__, (int)cardnr, (int)domain, rc);
 		goto out;
 	}
 
@@ -636,13 +631,13 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type,
 	if (rc)
 		goto out;
 	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
-		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__);
 		rc = -EIO;
 		goto out;
 	}
 	if (rep_pl->data_len > buflen) {
-		DEBUG_ERR("%s mismatch between reply data len and buffer len\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s mismatch between reply data len and buffer len\n",
+			       __func__);
 		rc = -ENOSPC;
 		goto out;
 	}
@@ -816,9 +811,8 @@ static int _ep11_genaeskey(u16 card, u16 domain,
 	case 256:
 		break;
 	default:
-		DEBUG_ERR(
-			"%s unknown/unsupported keybitsize %d\n",
-			__func__, keybitsize);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n",
+			       __func__, keybitsize);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -878,9 +872,8 @@ static int _ep11_genaeskey(u16 card, u16 domain,
 
 	rc = zcrypt_send_ep11_cprb(urb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
-			__func__, (int)card, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			       __func__, (int)card, (int)domain, rc);
 		goto out;
 	}
 
@@ -888,13 +881,13 @@ static int _ep11_genaeskey(u16 card, u16 domain,
 	if (rc)
 		goto out;
 	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
-		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__);
 		rc = -EIO;
 		goto out;
 	}
 	if (rep_pl->data_len > *keybufsize) {
-		DEBUG_ERR("%s mismatch reply data len / key buffer len\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n",
+			       __func__);
 		rc = -ENOSPC;
 		goto out;
 	}
@@ -1030,9 +1023,8 @@ static int ep11_cryptsingle(u16 card, u16 domain,
 
 	rc = zcrypt_send_ep11_cprb(urb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
-			__func__, (int)card, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			       __func__, (int)card, (int)domain, rc);
 		goto out;
 	}
 
@@ -1040,7 +1032,7 @@ static int ep11_cryptsingle(u16 card, u16 domain,
 	if (rc)
 		goto out;
 	if (rep_pl->data_tag != 0x04) {
-		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__);
 		rc = -EIO;
 		goto out;
 	}
@@ -1053,14 +1045,14 @@ static int ep11_cryptsingle(u16 card, u16 domain,
 		n = *((u16 *)p);
 		p += 2;
 	} else {
-		DEBUG_ERR("%s unknown reply data length format 0x%02hhx\n",
-			  __func__, rep_pl->data_lenfmt);
+		ZCRYPT_DBF_ERR("%s unknown reply data length format 0x%02hhx\n",
+			       __func__, rep_pl->data_lenfmt);
 		rc = -EIO;
 		goto out;
 	}
 	if (n > *outbufsize) {
-		DEBUG_ERR("%s mismatch reply data len %d / output buffer %zu\n",
-			  __func__, n, *outbufsize);
+		ZCRYPT_DBF_ERR("%s mismatch reply data len %d / output buffer %zu\n",
+			       __func__, n, *outbufsize);
 		rc = -ENOSPC;
 		goto out;
 	}
@@ -1188,9 +1180,8 @@ static int _ep11_unwrapkey(u16 card, u16 domain,
 
 	rc = zcrypt_send_ep11_cprb(urb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
-			__func__, (int)card, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			       __func__, (int)card, (int)domain, rc);
 		goto out;
 	}
 
@@ -1198,13 +1189,13 @@ static int _ep11_unwrapkey(u16 card, u16 domain,
 	if (rc)
 		goto out;
 	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
-		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__);
 		rc = -EIO;
 		goto out;
 	}
 	if (rep_pl->data_len > *keybufsize) {
-		DEBUG_ERR("%s mismatch reply data len / key buffer len\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n",
+			       __func__);
 		rc = -ENOSPC;
 		goto out;
 	}
@@ -1343,9 +1334,8 @@ static int _ep11_wrapkey(u16 card, u16 domain,
 
 	rc = zcrypt_send_ep11_cprb(urb);
 	if (rc) {
-		DEBUG_ERR(
-			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
-			__func__, (int)card, (int)domain, rc);
+		ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			       __func__, (int)card, (int)domain, rc);
 		goto out;
 	}
 
@@ -1353,13 +1343,13 @@ static int _ep11_wrapkey(u16 card, u16 domain,
 	if (rc)
 		goto out;
 	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
-		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__);
 		rc = -EIO;
 		goto out;
 	}
 	if (rep_pl->data_len > *datasize) {
-		DEBUG_ERR("%s mismatch reply data len / data buffer len\n",
-			  __func__);
+		ZCRYPT_DBF_ERR("%s mismatch reply data len / data buffer len\n",
+			       __func__);
 		rc = -ENOSPC;
 		goto out;
 	}
@@ -1386,9 +1376,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
 	if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256) {
 		clrkeylen = keybitsize / 8;
 	} else {
-		DEBUG_ERR(
-			"%s unknown/unsupported keybitsize %d\n",
-			__func__, keybitsize);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n",
+			       __func__, keybitsize);
 		return -EINVAL;
 	}
 
@@ -1405,9 +1394,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
 			     0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */
 			     kek, &keklen);
 	if (rc) {
-		DEBUG_ERR(
-			"%s generate kek key failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s generate kek key failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 
@@ -1415,9 +1403,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
 	rc = ep11_cryptsingle(card, domain, 0, 0, def_iv, kek, keklen,
 			      clrkey, clrkeylen, encbuf, &encbuflen);
 	if (rc) {
-		DEBUG_ERR(
-			"%s encrypting key value with kek key failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s encrypting key value with kek key failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 
@@ -1426,9 +1413,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
 			    encbuf, encbuflen, 0, def_iv,
 			    keybitsize, 0, keybuf, keybufsize, keytype);
 	if (rc) {
-		DEBUG_ERR(
-			"%s importing key value as new key failed,, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s importing key value as new key failed,, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 
@@ -1476,17 +1462,16 @@ int ep11_kblob2protkey(u16 card, u16 dom,
 	rc = _ep11_wrapkey(card, dom, (u8 *)key, keylen,
 			   0, def_iv, wkbuf, &wkbuflen);
 	if (rc) {
-		DEBUG_ERR(
-			"%s rewrapping ep11 key to pkey failed, rc=%d\n",
-			__func__, rc);
+		ZCRYPT_DBF_ERR("%s rewrapping ep11 key to pkey failed, rc=%d\n",
+			       __func__, rc);
 		goto out;
 	}
 	wki = (struct wk_info *)wkbuf;
 
 	/* check struct version and pkey type */
 	if (wki->version != 1 || wki->pkeytype < 1 || wki->pkeytype > 5) {
-		DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n",
-			  __func__, (int)wki->version, (int)wki->pkeytype);
+		ZCRYPT_DBF_ERR("%s wk info version %d or pkeytype %d mismatch.\n",
+			       __func__, (int)wki->version, (int)wki->pkeytype);
 		rc = -EIO;
 		goto out;
 	}
@@ -1511,8 +1496,8 @@ int ep11_kblob2protkey(u16 card, u16 dom,
 				*protkeytype = PKEY_KEYTYPE_AES_256;
 			break;
 		default:
-			DEBUG_ERR("%s unknown/unsupported AES pkeysize %d\n",
-				  __func__, (int)wki->pkeysize);
+			ZCRYPT_DBF_ERR("%s unknown/unsupported AES pkeysize %d\n",
+				       __func__, (int)wki->pkeysize);
 			rc = -EIO;
 			goto out;
 		}
@@ -1525,16 +1510,16 @@ int ep11_kblob2protkey(u16 card, u16 dom,
 		break;
 	case 2: /* TDES */
 	default:
-		DEBUG_ERR("%s unknown/unsupported key type %d\n",
-			  __func__, (int)wki->pkeytype);
+		ZCRYPT_DBF_ERR("%s unknown/unsupported key type %d\n",
+			       __func__, (int)wki->pkeytype);
 		rc = -EIO;
 		goto out;
 	}
 
 	/* copy the translated protected key */
 	if (wki->pkeysize > *protkeylen) {
-		DEBUG_ERR("%s wk info pkeysize %llu > protkeysize %u\n",
-			  __func__, wki->pkeysize, *protkeylen);
+		ZCRYPT_DBF_ERR("%s wk info pkeysize %llu > protkeysize %u\n",
+			       __func__, wki->pkeysize, *protkeylen);
 		rc = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h
index a44fcfcec938..46e27b43a8af 100644
--- a/drivers/s390/crypto/zcrypt_error.h
+++ b/drivers/s390/crypto/zcrypt_error.h
@@ -119,10 +119,9 @@ static inline int convert_error(struct zcrypt_queue *zq,
 	case REP82_ERROR_MESSAGE_TYPE:		 /* 0x20 */
 	case REP82_ERROR_TRANSPORT_FAIL:	 /* 0x90 */
 		/*
-		 * Msg to wrong type or card/infrastructure failure.
-		 * Trigger rescan of the ap bus, trigger retry request.
+		 * Msg to wrong type or card/infrastructure failure. Return
+		 * EAGAIN, the upper layer may do a retry on the request.
 		 */
-		atomic_set(&zcrypt_rescan_req, 1);
 		/* For type 86 response show the apfs value (failure reason) */
 		if (ehdr->reply_code == REP82_ERROR_TRANSPORT_FAIL &&
 		    ehdr->type == TYPE86_RSP_CODE) {
diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c
index 2e155de8abe5..3b39cb8f926d 100644
--- a/drivers/s390/crypto/zcrypt_msgtype50.c
+++ b/drivers/s390/crypto/zcrypt_msgtype50.c
@@ -427,7 +427,7 @@ static void zcrypt_msgtype50_receive(struct ap_queue *aq,
 		len = t80h->len;
 		if (len > reply->bufsize || len > msg->bufsize ||
 		    len != reply->len) {
-			ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__);
+			pr_debug("%s len mismatch => EMSGSIZE\n", __func__);
 			msg->rc = -EMSGSIZE;
 			goto out;
 		}
@@ -487,9 +487,9 @@ static long zcrypt_msgtype50_modexpo(struct zcrypt_queue *zq,
 out:
 	ap_msg->private = NULL;
 	if (rc)
-		ZCRYPT_DBF_DBG("%s send me cprb at dev=%02x.%04x rc=%d\n",
-			       __func__, AP_QID_CARD(zq->queue->qid),
-			       AP_QID_QUEUE(zq->queue->qid), rc);
+		pr_debug("%s send me cprb at dev=%02x.%04x rc=%d\n",
+			 __func__, AP_QID_CARD(zq->queue->qid),
+			 AP_QID_QUEUE(zq->queue->qid), rc);
 	return rc;
 }
 
@@ -537,9 +537,9 @@ static long zcrypt_msgtype50_modexpo_crt(struct zcrypt_queue *zq,
 out:
 	ap_msg->private = NULL;
 	if (rc)
-		ZCRYPT_DBF_DBG("%s send crt cprb at dev=%02x.%04x rc=%d\n",
-			       __func__, AP_QID_CARD(zq->queue->qid),
-			       AP_QID_QUEUE(zq->queue->qid), rc);
+		pr_debug("%s send crt cprb at dev=%02x.%04x rc=%d\n",
+			 __func__, AP_QID_CARD(zq->queue->qid),
+			 AP_QID_QUEUE(zq->queue->qid), rc);
 	return rc;
 }
 
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 3c53abbdc342..215f257d2360 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -437,9 +437,9 @@ static int xcrb_msg_to_type6cprb_msgx(bool userspace, struct ap_message *ap_msg,
 		ap_msg->flags |= AP_MSG_FLAG_ADMIN;
 		break;
 	default:
-		ZCRYPT_DBF_DBG("%s unknown CPRB minor version '%c%c'\n",
-			       __func__, msg->cprbx.func_id[0],
-			       msg->cprbx.func_id[1]);
+		pr_debug("%s unknown CPRB minor version '%c%c'\n",
+			 __func__, msg->cprbx.func_id[0],
+			 msg->cprbx.func_id[1]);
 	}
 
 	/* copy data block */
@@ -629,9 +629,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq,
 
 	/* Copy CPRB to user */
 	if (xcrb->reply_control_blk_length < msg->fmt2.count1) {
-		ZCRYPT_DBF_DBG("%s reply_control_blk_length %u < required %u => EMSGSIZE\n",
-			       __func__, xcrb->reply_control_blk_length,
-			       msg->fmt2.count1);
+		pr_debug("%s reply_control_blk_length %u < required %u => EMSGSIZE\n",
+			 __func__, xcrb->reply_control_blk_length,
+			 msg->fmt2.count1);
 		return -EMSGSIZE;
 	}
 	if (z_copy_to_user(userspace, xcrb->reply_control_blk_addr,
@@ -642,9 +642,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq,
 	/* Copy data buffer to user */
 	if (msg->fmt2.count2) {
 		if (xcrb->reply_data_length < msg->fmt2.count2) {
-			ZCRYPT_DBF_DBG("%s reply_data_length %u < required %u => EMSGSIZE\n",
-				       __func__, xcrb->reply_data_length,
-				       msg->fmt2.count2);
+			pr_debug("%s reply_data_length %u < required %u => EMSGSIZE\n",
+				 __func__, xcrb->reply_data_length,
+				 msg->fmt2.count2);
 			return -EMSGSIZE;
 		}
 		if (z_copy_to_user(userspace, xcrb->reply_data_addr,
@@ -673,9 +673,9 @@ static int convert_type86_ep11_xcrb(bool userspace, struct zcrypt_queue *zq,
 	char *data = reply->msg;
 
 	if (xcrb->resp_len < msg->fmt2.count1) {
-		ZCRYPT_DBF_DBG("%s resp_len %u < required %u => EMSGSIZE\n",
-			       __func__, (unsigned int)xcrb->resp_len,
-			       msg->fmt2.count1);
+		pr_debug("%s resp_len %u < required %u => EMSGSIZE\n",
+			 __func__, (unsigned int)xcrb->resp_len,
+			 msg->fmt2.count1);
 		return -EMSGSIZE;
 	}
 
@@ -875,7 +875,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq,
 			len = sizeof(struct type86x_reply) + t86r->length;
 			if (len > reply->bufsize || len > msg->bufsize ||
 			    len != reply->len) {
-				ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__);
+				pr_debug("%s len mismatch => EMSGSIZE\n",
+					 __func__);
 				msg->rc = -EMSGSIZE;
 				goto out;
 			}
@@ -889,7 +890,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq,
 				len = t86r->fmt2.offset1 + t86r->fmt2.count1;
 			if (len > reply->bufsize || len > msg->bufsize ||
 			    len != reply->len) {
-				ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__);
+				pr_debug("%s len mismatch => EMSGSIZE\n",
+					 __func__);
 				msg->rc = -EMSGSIZE;
 				goto out;
 			}
@@ -939,7 +941,8 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq,
 			len = t86r->fmt2.offset1 + t86r->fmt2.count1;
 			if (len > reply->bufsize || len > msg->bufsize ||
 			    len != reply->len) {
-				ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__);
+				pr_debug("%s len mismatch => EMSGSIZE\n",
+					 __func__);
 				msg->rc = -EMSGSIZE;
 				goto out;
 			}
@@ -1151,9 +1154,9 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq,
 
 out:
 	if (rc)
-		ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n",
-			       __func__, AP_QID_CARD(zq->queue->qid),
-			       AP_QID_QUEUE(zq->queue->qid), rc);
+		pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n",
+			 __func__, AP_QID_CARD(zq->queue->qid),
+			 AP_QID_QUEUE(zq->queue->qid), rc);
 	return rc;
 }
 
@@ -1274,9 +1277,9 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue *
 
 out:
 	if (rc)
-		ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n",
-			       __func__, AP_QID_CARD(zq->queue->qid),
-			       AP_QID_QUEUE(zq->queue->qid), rc);
+		pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n",
+			 __func__, AP_QID_CARD(zq->queue->qid),
+			 AP_QID_QUEUE(zq->queue->qid), rc);
 	return rc;
 }
 
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b92a32b4b114..04c64ce0a1ca 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
 		if (!recover) {
 			hash_del(&addr->hnode);
 			kfree(addr);
-			continue;
+		} else {
+			/* prepare for recovery */
+			addr->disp_flag = QETH_DISP_ADDR_ADD;
 		}
-		addr->disp_flag = QETH_DISP_ADDR_ADD;
 	}
 
 	mutex_unlock(&card->ip_lock);
@@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
 		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
 			rc = qeth_l3_register_addr_entry(card, addr);
 
-			if (!rc) {
+			if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) {
+				/* keep it in the records */
 				addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			} else {
+				/* bad address */
 				hash_del(&addr->hnode);
 				kfree(addr);
 			}
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index addac7fbe37b..9ce27092729c 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1270,7 +1270,7 @@ source "drivers/scsi/arm/Kconfig"
 
 config JAZZ_ESP
 	bool "MIPS JAZZ FAS216 SCSI support"
-	depends on MACH_JAZZ && SCSI
+	depends on MACH_JAZZ && SCSI=y
 	select SCSI_SPI_ATTRS
 	help
 	  This is the driver for the onboard SCSI host adapter of MIPS Magnum
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 19eee108db02..5c8d1ba3f8f3 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *sel;
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 
 	mutex_lock(&fip->ctlr_mutex);
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 
 	kfree_skb(fip->flogi_req);
 	fip->flogi_req = NULL;
 	list_for_each_entry(fcf, &fip->fcfs, list)
 		fcf->flogi_sent = 0;
 
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 	sel = fip->sel_fcf;
 
 	if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr))
@@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 {
 	struct fc_frame *fp;
 	struct fc_frame_header *fh;
-	unsigned long flags;
 	u16 old_xid;
 	u8 op;
 	u8 mac[ETH_ALEN];
@@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 		op = FIP_DT_FLOGI;
 		if (fip->mode == FIP_MODE_VN2VN)
 			break;
-		spin_lock_irqsave(&fip->ctlr_lock, flags);
+		spin_lock_bh(&fip->ctlr_lock);
 		kfree_skb(fip->flogi_req);
 		fip->flogi_req = skb;
 		fip->flogi_req_send = 1;
-		spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+		spin_unlock_bh(&fip->ctlr_lock);
 		schedule_work(&fip->timer_work);
 		return -EINPROGRESS;
 	case ELS_FDISC:
@@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip)
 static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 	int error;
 
 	mutex_lock(&fip->ctlr_mutex);
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 	LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n");
 	fcf = fcoe_ctlr_select(fip);
 	if (!fcf || fcf->flogi_sent) {
@@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 		fcoe_ctlr_solicit(fip, NULL);
 		error = fcoe_ctlr_flogi_send_locked(fip);
 	}
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 	mutex_unlock(&fip->ctlr_mutex);
 	return error;
 }
@@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
 static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
 {
 	struct fcoe_fcf *fcf;
-	unsigned long flags;
 
-	spin_lock_irqsave(&fip->ctlr_lock, flags);
+	spin_lock_bh(&fip->ctlr_lock);
 	fcf = fip->sel_fcf;
 	if (!fcf || !fip->flogi_req_send)
 		goto unlock;
@@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
 	} else /* XXX */
 		LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n");
 unlock:
-	spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+	spin_unlock_bh(&fip->ctlr_lock);
 }
 
 /**
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 2074937c05bc..ce73f08ee889 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -305,6 +305,7 @@ struct fnic {
 	unsigned int copy_wq_base;
 	struct work_struct link_work;
 	struct work_struct frame_work;
+	struct work_struct flush_work;
 	struct sk_buff_head frame_queue;
 	struct sk_buff_head tx_queue;
 
@@ -363,7 +364,7 @@ void fnic_handle_event(struct work_struct *work);
 int fnic_rq_cmpl_handler(struct fnic *fnic, int);
 int fnic_alloc_rq_frame(struct vnic_rq *rq);
 void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
-void fnic_flush_tx(struct fnic *);
+void fnic_flush_tx(struct work_struct *work);
 void fnic_eth_send(struct fcoe_ctlr *, struct sk_buff *skb);
 void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *);
 void fnic_update_mac(struct fc_lport *, u8 *new);
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 5e312a55cc7d..a08293b2ad9f 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -1182,7 +1182,7 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
 
 /**
  * fnic_flush_tx() - send queued frames.
- * @fnic: fnic device
+ * @work: pointer to work element
  *
  * Send frames that were waiting to go out in FC or Ethernet mode.
  * Whenever changing modes we purge queued frames, so these frames should
@@ -1190,8 +1190,9 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
  *
  * Called without fnic_lock held.
  */
-void fnic_flush_tx(struct fnic *fnic)
+void fnic_flush_tx(struct work_struct *work)
 {
+	struct fnic *fnic = container_of(work, struct fnic, flush_work);
 	struct sk_buff *skb;
 	struct fc_frame *fp;
 
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 5ed1d897311a..29eead383eb9 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -830,6 +830,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		spin_lock_init(&fnic->vlans_lock);
 		INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame);
 		INIT_WORK(&fnic->event_work, fnic_handle_event);
+		INIT_WORK(&fnic->flush_work, fnic_flush_tx);
 		skb_queue_head_init(&fnic->fip_frame_queue);
 		INIT_LIST_HEAD(&fnic->evlist);
 		INIT_LIST_HEAD(&fnic->vlans);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 8d7fc5284293..fc4cee91b175 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -680,7 +680,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	fnic_flush_tx(fnic);
+	queue_work(fnic_event_queue, &fnic->flush_work);
 
  reset_cmpl_handler_end:
 	fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET);
@@ -736,7 +736,7 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic,
 		}
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-		fnic_flush_tx(fnic);
+		queue_work(fnic_event_queue, &fnic->flush_work);
 		queue_work(fnic_event_queue, &fnic->frame_work);
 	} else {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 2a50fda3a628..625fd547ee60 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -371,7 +371,6 @@ static u16 initio_se2_rd(unsigned long base, u8 addr)
  */
 static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 {
-	u8 rb;
 	u8 instr;
 	int i;
 
@@ -400,7 +399,7 @@ static void initio_se2_wr(unsigned long base, u8 addr, u16 val)
 		udelay(30);
 		outb(SE2CS, base + TUL_NVRAM);			/* -CLK */
 		udelay(30);
-		if ((rb = inb(base + TUL_NVRAM)) & SE2DI)
+		if (inb(base + TUL_NVRAM) & SE2DI)
 			break;	/* write complete */
 	}
 	outb(0, base + TUL_NVRAM);				/* -CS */
diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c
index 71f711cb0628..355a0bc0828e 100644
--- a/drivers/scsi/isci/request.c
+++ b/drivers/scsi/isci/request.c
@@ -3387,7 +3387,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost,
 		return SCI_FAILURE;
 	}
 
-	return SCI_SUCCESS;
+	return status;
 }
 
 static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag)
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index d26941b131fd..bf879d81846b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1918,7 +1918,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datasegcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -1926,8 +1926,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	struct scatterlist *sgde = NULL; /* s/g data entry */
 	struct sli4_sge_diseed *diseed = NULL;
 	dma_addr_t physaddr;
-	int i = 0, num_sge = 0, status;
-	uint32_t reftag;
+	int i = 0, status;
+	uint32_t reftag, num_sge = 0;
 	uint8_t txop, rxop;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
 	uint32_t rc;
@@ -2099,7 +2099,7 @@ out:
  *
  * Returns the number of SGEs added to the SGL.
  **/
-static int
+static uint32_t
 lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 		struct sli4_sge *sgl, int datacnt, int protcnt,
 		struct lpfc_io_buf *lpfc_cmd)
@@ -2123,8 +2123,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
 	uint32_t rc;
 #endif
 	uint32_t checking = 1;
-	uint32_t dma_offset = 0;
-	int num_sge = 0, j = 2;
+	uint32_t dma_offset = 0, num_sge = 0;
+	int j = 2;
 	struct sli4_hybrid_sgl *sgl_xtra = NULL;
 
 	sgpe = scsi_prot_sglist(sc);
diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c
index c0c8ab586957..d32ad46318cb 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_transport.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c
@@ -1671,7 +1671,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port,
 void
 mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 {
-	struct host_port h_port[64];
+	struct host_port *h_port = NULL;
 	int i, j, found, host_port_count = 0, port_idx;
 	u16 sz, attached_handle, ioc_status;
 	struct mpi3_sas_io_unit_page0 *sas_io_unit_pg0 = NULL;
@@ -1685,6 +1685,10 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 	sas_io_unit_pg0 = kzalloc(sz, GFP_KERNEL);
 	if (!sas_io_unit_pg0)
 		return;
+	h_port = kcalloc(64, sizeof(struct host_port), GFP_KERNEL);
+	if (!h_port)
+		goto out;
+
 	if (mpi3mr_cfg_get_sas_io_unit_pg0(mrioc, sas_io_unit_pg0, sz)) {
 		ioc_err(mrioc, "failure at %s:%d/%s()!\n",
 		    __FILE__, __LINE__, __func__);
@@ -1814,6 +1818,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc)
 		}
 	}
 out:
+	kfree(h_port);
 	kfree(sas_io_unit_pg0);
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 8761bc58d965..b8120ca93c79 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -7378,7 +7378,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
 		return -EFAULT;
 	}
 
- issue_diag_reset:
+	return 0;
+
+issue_diag_reset:
 	rc = _base_diag_reset(ioc);
 	return rc;
 }
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 76d369343c7a..8cad9792a562 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -328,21 +328,39 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer,
 	return result + 4;
 }
 
+enum scsi_vpd_parameters {
+	SCSI_VPD_HEADER_SIZE = 4,
+	SCSI_VPD_LIST_SIZE = 36,
+};
+
 static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page)
 {
-	unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4);
+	unsigned char vpd[SCSI_VPD_LIST_SIZE] __aligned(4);
 	int result;
 
 	if (sdev->no_vpd_size)
 		return SCSI_DEFAULT_VPD_LEN;
 
 	/*
+	 * Fetch the supported pages VPD and validate that the requested page
+	 * number is present.
+	 */
+	if (page != 0) {
+		result = scsi_vpd_inquiry(sdev, vpd, 0, sizeof(vpd));
+		if (result < SCSI_VPD_HEADER_SIZE)
+			return 0;
+
+		result -= SCSI_VPD_HEADER_SIZE;
+		if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result))
+			return 0;
+	}
+	/*
 	 * Fetch the VPD page header to find out how big the page
 	 * is. This is done to prevent problems on legacy devices
 	 * which can not handle allocation lengths as large as
 	 * potentially requested by the caller.
 	 */
-	result = scsi_vpd_inquiry(sdev, vpd_header, page, sizeof(vpd_header));
+	result = scsi_vpd_inquiry(sdev, vpd, page, SCSI_VPD_HEADER_SIZE);
 	if (result < 0)
 		return 0;
 
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 79da4b1c1df0..612489afe8d2 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd);
 static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *,
 						   struct scsi_cmnd *);
 
-void scsi_eh_wakeup(struct Scsi_Host *shost)
+void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (scsi_host_busy(shost) == shost->host_failed) {
+	if (busy == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost)
 	if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 ||
 	    scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) {
 		shost->host_eh_scheduled++;
-		scsi_eh_wakeup(shost);
+		scsi_eh_wakeup(shost, scsi_host_busy(shost));
 	}
 
 	spin_unlock_irqrestore(shost->host_lock, flags);
@@ -282,11 +282,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
 {
 	struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
 	struct Scsi_Host *shost = scmd->device->host;
+	unsigned int busy = scsi_host_busy(shost);
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_failed++;
-	scsi_eh_wakeup(shost);
+	scsi_eh_wakeup(shost, busy);
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index cf3864f72093..df5ac03d5d6c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -278,9 +278,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	rcu_read_lock();
 	__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 	if (unlikely(scsi_host_in_recovery(shost))) {
+		unsigned int busy = scsi_host_busy(shost);
+
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
-			scsi_eh_wakeup(shost);
+			scsi_eh_wakeup(shost, busy);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 	}
 	rcu_read_unlock();
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 3f0dfb97db6b..1fbfe1b52c9f 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work);
 extern enum blk_eh_timer_return scsi_timeout(struct request *req);
 extern int scsi_error_handler(void *host);
 extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd);
-extern void scsi_eh_wakeup(struct Scsi_Host *shost);
+extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy);
 extern void scsi_eh_scmd_add(struct scsi_cmnd *);
 void scsi_eh_ready_devs(struct Scsi_Host *shost,
 			struct list_head *work_q,
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 44680f65ea14..9969f4e2f1c3 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -332,7 +332,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 
 	sdev->sg_reserved_size = INT_MAX;
 
-	q = blk_mq_init_queue(&sdev->host->tag_set);
+	q = blk_mq_alloc_queue(&sdev->host->tag_set, NULL, NULL);
 	if (IS_ERR(q)) {
 		/* release fn is set up in scsi_sysfs_device_initialise, so
 		 * have to free and put manually here */
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 0833b3e6aa6e..bdd0acf7fa3c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3407,6 +3407,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp,
 	return true;
 }
 
+static void sd_read_block_zero(struct scsi_disk *sdkp)
+{
+	unsigned int buf_len = sdkp->device->sector_size;
+	char *buffer, cmd[10] = { };
+
+	buffer = kmalloc(buf_len, GFP_KERNEL);
+	if (!buffer)
+		return;
+
+	cmd[0] = READ_10;
+	put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */
+	put_unaligned_be16(1, &cmd[7]);	/* Transfer 1 logical block */
+
+	scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len,
+			 SD_TIMEOUT, sdkp->max_retries, NULL);
+	kfree(buffer);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -3446,7 +3464,13 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	if (sdkp->media_present) {
 		sd_read_capacity(sdkp, buffer);
-
+		/*
+		 * Some USB/UAS devices return generic values for mode pages
+		 * until the media has been accessed. Trigger a READ operation
+		 * to force the device to populate mode pages.
+		 */
+		if (sdp->read_before_ms)
+			sd_read_block_zero(sdkp);
 		/*
 		 * set the default to rotational.  All non-rotational devices
 		 * support the block characteristics VPD page, which will
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index ceff1ec13f9e..385180c98be4 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -6533,8 +6533,11 @@ static void pqi_map_queues(struct Scsi_Host *shost)
 {
 	struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost);
 
-	blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+	if (!ctrl_info->disable_managed_interrupts)
+		return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
 			      ctrl_info->pci_dev, 0);
+	else
+		return blk_mq_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT]);
 }
 
 static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index a95936b18f69..7ceb982040a5 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -330,6 +330,7 @@ enum storvsc_request_type {
  */
 
 static int storvsc_ringbuffer_size = (128 * 1024);
+static int aligned_ringbuffer_size;
 static u32 max_outstanding_req_per_channel;
 static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);
 
@@ -687,8 +688,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 	new_sc->next_request_id_callback = storvsc_next_request_id;
 
 	ret = vmbus_open(new_sc,
-			 storvsc_ringbuffer_size,
-			 storvsc_ringbuffer_size,
+			 aligned_ringbuffer_size,
+			 aligned_ringbuffer_size,
 			 (void *)&props,
 			 sizeof(struct vmstorage_channel_properties),
 			 storvsc_on_channel_callback, new_sc);
@@ -1973,7 +1974,7 @@ static int storvsc_probe(struct hv_device *device,
 	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
-	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
+	ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc);
 	if (ret)
 		goto err_out1;
 
@@ -2164,7 +2165,7 @@ static int storvsc_resume(struct hv_device *hv_dev)
 {
 	int ret;
 
-	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
+	ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size,
 				     hv_dev_is_fc(hv_dev));
 	return ret;
 }
@@ -2198,8 +2199,9 @@ static int __init storvsc_drv_init(void)
 	 * the ring buffer indices) by the max request size (which is
 	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
 	 */
+	aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size);
 	max_outstanding_req_per_channel =
-		((storvsc_ringbuffer_size - PAGE_SIZE) /
+		((aligned_ringbuffer_size - PAGE_SIZE) /
 		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
 		sizeof(struct vstor_packet) + sizeof(u64),
 		sizeof(u64)));
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 4cf20be668a6..617eb892f4ad 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -188,8 +188,6 @@ static void virtscsi_vq_done(struct virtio_scsi *vscsi,
 		while ((buf = virtqueue_get_buf(vq, &len)) != NULL)
 			fn(vscsi, buf);
 
-		if (unlikely(virtqueue_is_broken(vq)))
-			break;
 	} while (!virtqueue_enable_cb(vq));
 	spin_unlock_irqrestore(&virtscsi_vq->vq_lock, flags);
 }
diff --git a/drivers/soc/apple/mailbox.c b/drivers/soc/apple/mailbox.c
index 780199bf351e..49a0955e82d6 100644
--- a/drivers/soc/apple/mailbox.c
+++ b/drivers/soc/apple/mailbox.c
@@ -296,14 +296,14 @@ struct apple_mbox *apple_mbox_get(struct device *dev, int index)
 	of_node_put(args.np);
 
 	if (!pdev)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	mbox = platform_get_drvdata(pdev);
 	if (!mbox)
-		return ERR_PTR(EPROBE_DEFER);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_CONSUMER))
-		return ERR_PTR(ENODEV);
+		return ERR_PTR(-ENODEV);
 
 	return mbox;
 }
diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig
index 0810b5b0c688..50c664b65f4d 100644
--- a/drivers/soc/mediatek/Kconfig
+++ b/drivers/soc/mediatek/Kconfig
@@ -68,4 +68,13 @@ config MTK_SVS
 	  chip process corner, temperatures and other factors. Then DVFS
 	  driver could apply SVS bank voltage to PMIC/Buck.
 
+config MTK_SOCINFO
+	tristate "MediaTek SoC Information"
+	default y
+	depends on NVMEM_MTK_EFUSE
+	help
+	  The MediaTek SoC Information (mtk-socinfo) driver provides
+	  information about the SoC to the userspace including the
+	  manufacturer name, marketing name and soc name.
+
 endmenu
diff --git a/drivers/soc/mediatek/Makefile b/drivers/soc/mediatek/Makefile
index 9d3ce7878c5c..6830512848fd 100644
--- a/drivers/soc/mediatek/Makefile
+++ b/drivers/soc/mediatek/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_MTK_REGULATOR_COUPLER) += mtk-regulator-coupler.o
 obj-$(CONFIG_MTK_MMSYS) += mtk-mmsys.o
 obj-$(CONFIG_MTK_MMSYS) += mtk-mutex.o
 obj-$(CONFIG_MTK_SVS) += mtk-svs.o
+obj-$(CONFIG_MTK_SOCINFO) += mtk-socinfo.o
diff --git a/drivers/soc/mediatek/mtk-socinfo.c b/drivers/soc/mediatek/mtk-socinfo.c
new file mode 100644
index 000000000000..42572e8c1520
--- /dev/null
+++ b/drivers/soc/mediatek/mtk-socinfo.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/device.h>
+#include <linux/device/bus.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <linux/sys_soc.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+
+#define MTK_SOCINFO_ENTRY(_soc_name, _segment_name, _marketing_name, _cell_data1, _cell_data2) {\
+	.soc_name = _soc_name,									\
+	.segment_name = _segment_name,								\
+	.marketing_name = _marketing_name,							\
+	.cell_data = {_cell_data1, _cell_data2}							\
+}
+#define CELL_NOT_USED (0xFFFFFFFF)
+#define MAX_CELLS (2)
+
+struct mtk_socinfo {
+	struct device *dev;
+	struct name_data *name_data;
+	struct socinfo_data *socinfo_data;
+	struct soc_device *soc_dev;
+};
+
+struct socinfo_data {
+	char *soc_name;
+	char *segment_name;
+	char *marketing_name;
+	u32 cell_data[MAX_CELLS];
+};
+
+static const char *cell_names[MAX_CELLS] = {"socinfo-data1", "socinfo-data2"};
+
+static struct socinfo_data socinfo_data_table[] = {
+	MTK_SOCINFO_ENTRY("MT8173", "MT8173V/AC", "MT8173", 0x6CA20004, 0x10000000),
+	MTK_SOCINFO_ENTRY("MT8183", "MT8183V/AZA", "Kompanio 500", 0x00010043, 0x00000840),
+	MTK_SOCINFO_ENTRY("MT8183", "MT8183V/AZA", "Kompanio 500", 0x00010043, 0x00000940),
+	MTK_SOCINFO_ENTRY("MT8186", "MT8186GV/AZA", "Kompanio 520", 0x81861001, CELL_NOT_USED),
+	MTK_SOCINFO_ENTRY("MT8186T", "MT8186TV/AZA", "Kompanio 528", 0x81862001, CELL_NOT_USED),
+	MTK_SOCINFO_ENTRY("MT8188", "MT8188GV/AZA", "Kompanio 830", 0x81880000, 0x00000010),
+	MTK_SOCINFO_ENTRY("MT8188", "MT8188GV/HZA", "Kompanio 830", 0x81880000, 0x00000011),
+	MTK_SOCINFO_ENTRY("MT8192", "MT8192V/AZA", "Kompanio 820", 0x00001100, 0x00040080),
+	MTK_SOCINFO_ENTRY("MT8192T", "MT8192V/ATZA", "Kompanio 828", 0x00000100, 0x000400C0),
+	MTK_SOCINFO_ENTRY("MT8195", "MT8195GV/EZA", "Kompanio 1200", 0x81950300, CELL_NOT_USED),
+	MTK_SOCINFO_ENTRY("MT8195", "MT8195GV/EHZA", "Kompanio 1200", 0x81950304, CELL_NOT_USED),
+	MTK_SOCINFO_ENTRY("MT8195", "MT8195TV/EZA", "Kompanio 1380", 0x81950400, CELL_NOT_USED),
+	MTK_SOCINFO_ENTRY("MT8195", "MT8195TV/EHZA", "Kompanio 1380", 0x81950404, CELL_NOT_USED),
+};
+
+static int mtk_socinfo_create_socinfo_node(struct mtk_socinfo *mtk_socinfop)
+{
+	struct soc_device_attribute *attrs;
+	static char machine[30] = {0};
+	static const char *soc_manufacturer = "MediaTek";
+
+	attrs = devm_kzalloc(mtk_socinfop->dev, sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		return -ENOMEM;
+
+	snprintf(machine, sizeof(machine), "%s (%s)", mtk_socinfop->socinfo_data->marketing_name,
+		mtk_socinfop->socinfo_data->soc_name);
+	attrs->family = soc_manufacturer;
+	attrs->machine = machine;
+
+	mtk_socinfop->soc_dev = soc_device_register(attrs);
+	if (IS_ERR(mtk_socinfop->soc_dev))
+		return PTR_ERR(mtk_socinfop->soc_dev);
+
+	dev_info(mtk_socinfop->dev, "%s %s SoC detected.\n", soc_manufacturer, attrs->machine);
+	return 0;
+}
+
+static u32 mtk_socinfo_read_cell(struct device *dev, const char *name)
+{
+	struct nvmem_device *nvmemp;
+	struct device_node *np, *nvmem_node = dev->parent->of_node;
+	u32 offset;
+	u32 cell_val = CELL_NOT_USED;
+
+	/* should never fail since the nvmem driver registers this child */
+	nvmemp = nvmem_device_find(nvmem_node, device_match_of_node);
+	if (IS_ERR(nvmemp))
+		goto out;
+
+	np = of_get_child_by_name(nvmem_node, name);
+	if (!np)
+		goto put_device;
+
+	if (of_property_read_u32_index(np, "reg", 0, &offset))
+		goto put_node;
+
+	nvmem_device_read(nvmemp, offset, sizeof(cell_val), &cell_val);
+
+put_node:
+	of_node_put(np);
+put_device:
+	nvmem_device_put(nvmemp);
+out:
+	return cell_val;
+}
+
+static int mtk_socinfo_get_socinfo_data(struct mtk_socinfo *mtk_socinfop)
+{
+	unsigned int i, j;
+	unsigned int num_cell_data = 0;
+	u32 cell_data[MAX_CELLS] = {0};
+	bool match_socinfo;
+	int match_socinfo_index = -1;
+
+	for (i = 0; i < MAX_CELLS; i++) {
+		cell_data[i] = mtk_socinfo_read_cell(mtk_socinfop->dev, cell_names[i]);
+		if (cell_data[i] != CELL_NOT_USED)
+			num_cell_data++;
+		else
+			break;
+	}
+
+	if (!num_cell_data)
+		return -ENOENT;
+
+	for (i = 0; i < ARRAY_SIZE(socinfo_data_table); i++) {
+		match_socinfo = true;
+		for (j = 0; j < num_cell_data; j++) {
+			if (cell_data[j] != socinfo_data_table[i].cell_data[j]) {
+				match_socinfo = false;
+				break;
+			}
+		}
+		if (match_socinfo) {
+			mtk_socinfop->socinfo_data = &(socinfo_data_table[i]);
+			match_socinfo_index = i;
+			break;
+		}
+	}
+
+	return match_socinfo_index >= 0 ? match_socinfo_index : -ENOENT;
+}
+
+static int mtk_socinfo_probe(struct platform_device *pdev)
+{
+	struct mtk_socinfo *mtk_socinfop;
+	int ret;
+
+	mtk_socinfop = devm_kzalloc(&pdev->dev, sizeof(*mtk_socinfop), GFP_KERNEL);
+	if (!mtk_socinfop)
+		return -ENOMEM;
+
+	mtk_socinfop->dev = &pdev->dev;
+
+	ret = mtk_socinfo_get_socinfo_data(mtk_socinfop);
+	if (ret < 0)
+		return dev_err_probe(mtk_socinfop->dev, ret, "Failed to get socinfo data\n");
+
+	ret = mtk_socinfo_create_socinfo_node(mtk_socinfop);
+	if (ret)
+		return dev_err_probe(mtk_socinfop->dev, ret, "Cannot create node\n");
+
+	platform_set_drvdata(pdev, mtk_socinfop);
+	return 0;
+}
+
+static void mtk_socinfo_remove(struct platform_device *pdev)
+{
+	struct mtk_socinfo *mtk_socinfop = platform_get_drvdata(pdev);
+
+	soc_device_unregister(mtk_socinfop->soc_dev);
+}
+
+static struct platform_driver mtk_socinfo = {
+	.probe = mtk_socinfo_probe,
+	.remove_new = mtk_socinfo_remove,
+	.driver = {
+		.name = "mtk-socinfo",
+	},
+};
+module_platform_driver(mtk_socinfo);
+
+MODULE_AUTHOR("William-TW LIN <william-tw.lin@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek socinfo driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/soc/microchip/Kconfig b/drivers/soc/microchip/Kconfig
index 9b0fdd95276e..19f4b576f822 100644
--- a/drivers/soc/microchip/Kconfig
+++ b/drivers/soc/microchip/Kconfig
@@ -1,5 +1,5 @@
 config POLARFIRE_SOC_SYS_CTRL
-	tristate "POLARFIRE_SOC_SYS_CTRL"
+	tristate "Microchip PolarFire SoC (MPFS) system controller support"
 	depends on POLARFIRE_SOC_MAILBOX
 	depends on MTD
 	help
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index c6ca4de42586..5af33b0e3470 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -268,4 +268,13 @@ config QCOM_INLINE_CRYPTO_ENGINE
 	tristate
 	select QCOM_SCM
 
+config QCOM_PBS
+	tristate "PBS trigger support for Qualcomm Technologies, Inc. PMICS"
+	depends on SPMI
+	help
+	  This driver supports configuring software programmable boot sequencer (PBS)
+	  trigger event through PBS RAM on Qualcomm Technologies, Inc. PMICs.
+	  This module provides the APIs to the client drivers that wants to send the
+	  PBS trigger event to the PBS RAM.
+
 endmenu
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 05b3d54e8dc9..ca0bece0dfff 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS_rpmh-rsc.o := -I$(src)
+CFLAGS_qcom_aoss.o := -I$(src)
 obj-$(CONFIG_QCOM_AOSS_QMP) +=	qcom_aoss.o
 obj-$(CONFIG_QCOM_GENI_SE) +=	qcom-geni-se.o
 obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
@@ -34,3 +35,4 @@ obj-$(CONFIG_QCOM_KRYO_L2_ACCESSORS) +=	kryo-l2-accessors.o
 obj-$(CONFIG_QCOM_ICC_BWMON)	+= icc-bwmon.o
 qcom_ice-objs			+= ice.o
 obj-$(CONFIG_QCOM_INLINE_CRYPTO_ENGINE)	+= qcom_ice.o
+obj-$(CONFIG_QCOM_PBS) +=	qcom-pbs.o
diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c
index 1f8b315576a4..50749e870efa 100644
--- a/drivers/soc/qcom/apr.c
+++ b/drivers/soc/qcom/apr.c
@@ -399,7 +399,7 @@ static int apr_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "MODALIAS=apr:%s", adev->name);
 }
 
-struct bus_type aprbus = {
+const struct bus_type aprbus = {
 	.name		= "aprbus",
 	.match		= apr_device_match,
 	.probe		= apr_device_probe,
diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c
index 4ca88eaebf06..cbef0dea1d5d 100644
--- a/drivers/soc/qcom/llcc-qcom.c
+++ b/drivers/soc/qcom/llcc-qcom.c
@@ -859,6 +859,8 @@ static int llcc_update_act_ctrl(u32 sid,
 	ret = regmap_read_poll_timeout(drv_data->bcast_regmap, status_reg,
 				      slice_status, !(slice_status & status),
 				      0, LLCC_STATUS_READ_DELAY);
+	if (ret)
+		return ret;
 
 	if (drv_data->version >= LLCC_VERSION_4_1_0_0)
 		ret = regmap_write(drv_data->bcast_regmap, act_clear_reg,
diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index f4bfd24386f1..f913e9bd57ed 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -265,10 +265,17 @@ static int pmic_glink_probe(struct platform_device *pdev)
 
 	pg->client_mask = *match_data;
 
+	pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg);
+	if (IS_ERR(pg->pdr)) {
+		ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr),
+				    "failed to initialize pdr\n");
+		return ret;
+	}
+
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) {
 		ret = pmic_glink_add_aux_device(pg, &pg->ucsi_aux, "ucsi");
 		if (ret)
-			return ret;
+			goto out_release_pdr_handle;
 	}
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_ALTMODE)) {
 		ret = pmic_glink_add_aux_device(pg, &pg->altmode_aux, "altmode");
@@ -281,17 +288,11 @@ static int pmic_glink_probe(struct platform_device *pdev)
 			goto out_release_altmode_aux;
 	}
 
-	pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg);
-	if (IS_ERR(pg->pdr)) {
-		ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), "failed to initialize pdr\n");
-		goto out_release_aux_devices;
-	}
-
 	service = pdr_add_lookup(pg->pdr, "tms/servreg", "msm/adsp/charger_pd");
 	if (IS_ERR(service)) {
 		ret = dev_err_probe(&pdev->dev, PTR_ERR(service),
 				    "failed adding pdr lookup for charger_pd\n");
-		goto out_release_pdr_handle;
+		goto out_release_aux_devices;
 	}
 
 	mutex_lock(&__pmic_glink_lock);
@@ -300,8 +301,6 @@ static int pmic_glink_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_release_pdr_handle:
-	pdr_handle_release(pg->pdr);
 out_release_aux_devices:
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_BATT))
 		pmic_glink_del_aux_device(pg, &pg->ps_aux);
@@ -311,6 +310,8 @@ out_release_altmode_aux:
 out_release_ucsi_aux:
 	if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI))
 		pmic_glink_del_aux_device(pg, &pg->ucsi_aux);
+out_release_pdr_handle:
+	pdr_handle_release(pg->pdr);
 
 	return ret;
 }
diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index 5fcd0fdd2faa..b3808fc24c69 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -76,7 +76,7 @@ struct pmic_glink_altmode_port {
 
 	struct work_struct work;
 
-	struct device *bridge;
+	struct auxiliary_device *bridge;
 
 	enum typec_orientation orientation;
 	u16 svid;
@@ -230,7 +230,7 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 	else
 		pmic_glink_altmode_enable_usb(altmode, alt_port);
 
-	drm_aux_hpd_bridge_notify(alt_port->bridge,
+	drm_aux_hpd_bridge_notify(&alt_port->bridge->dev,
 				  alt_port->hpd_state ?
 				  connector_status_connected :
 				  connector_status_disconnected);
@@ -454,7 +454,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
 		alt_port->index = port;
 		INIT_WORK(&alt_port->work, pmic_glink_altmode_worker);
 
-		alt_port->bridge = drm_dp_hpd_bridge_register(dev, to_of_node(fwnode));
+		alt_port->bridge = devm_drm_dp_hpd_bridge_alloc(dev, to_of_node(fwnode));
 		if (IS_ERR(alt_port->bridge)) {
 			fwnode_handle_put(fwnode);
 			return PTR_ERR(alt_port->bridge);
@@ -510,6 +510,16 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
 		}
 	}
 
+	for (port = 0; port < ARRAY_SIZE(altmode->ports); port++) {
+		alt_port = &altmode->ports[port];
+		if (!alt_port->bridge)
+			continue;
+
+		ret = devm_drm_dp_hpd_bridge_add(dev, alt_port->bridge);
+		if (ret)
+			return ret;
+	}
+
 	altmode->client = devm_pmic_glink_register_client(dev,
 							  altmode->owner_id,
 							  pmic_glink_altmode_callback,
diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c
index bdcf44b85b2f..2e8f24d5da80 100644
--- a/drivers/soc/qcom/qcom-geni-se.c
+++ b/drivers/soc/qcom/qcom-geni-se.c
@@ -89,7 +89,6 @@
  * @base:		Base address of this instance of QUP wrapper core
  * @clks:		Handle to the primary & optional secondary AHB clocks
  * @num_clks:		Count of clocks
- * @to_core:		Core ICC path
  */
 struct geni_wrapper {
 	struct device *dev;
diff --git a/drivers/soc/qcom/qcom-pbs.c b/drivers/soc/qcom/qcom-pbs.c
new file mode 100644
index 000000000000..6af49b5060e5
--- /dev/null
+++ b/drivers/soc/qcom/qcom-pbs.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/spmi.h>
+#include <linux/soc/qcom/qcom-pbs.h>
+
+#define PBS_CLIENT_TRIG_CTL		0x42
+#define PBS_CLIENT_SW_TRIG_BIT		BIT(7)
+#define PBS_CLIENT_SCRATCH1		0x50
+#define PBS_CLIENT_SCRATCH2		0x51
+#define PBS_CLIENT_SCRATCH2_ERROR	0xFF
+
+#define RETRIES				2000
+#define DELAY				1100
+
+struct pbs_dev {
+	struct device		*dev;
+	struct regmap		*regmap;
+	struct mutex		lock;
+	struct device_link	*link;
+
+	u32			base;
+};
+
+static int qcom_pbs_wait_for_ack(struct pbs_dev *pbs, u8 bit_pos)
+{
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read_poll_timeout(pbs->regmap,  pbs->base + PBS_CLIENT_SCRATCH2,
+				       val, val & BIT(bit_pos), DELAY, DELAY * RETRIES);
+
+	if (ret < 0) {
+		dev_err(pbs->dev, "Timeout for PBS ACK/NACK for bit %u\n", bit_pos);
+		return -ETIMEDOUT;
+	}
+
+	if (val == PBS_CLIENT_SCRATCH2_ERROR) {
+		ret = regmap_write(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH2, 0);
+		dev_err(pbs->dev, "NACK from PBS for bit %u\n", bit_pos);
+		return -EINVAL;
+	}
+
+	dev_dbg(pbs->dev, "PBS sequence for bit %u executed!\n", bit_pos);
+	return 0;
+}
+
+/**
+ * qcom_pbs_trigger_event() - Trigger the PBS RAM sequence
+ * @pbs: Pointer to PBS device
+ * @bitmap: bitmap
+ *
+ * This function is used to trigger the PBS RAM sequence to be
+ * executed by the client driver.
+ *
+ * The PBS trigger sequence involves
+ * 1. setting the PBS sequence bit in PBS_CLIENT_SCRATCH1
+ * 2. Initiating the SW PBS trigger
+ * 3. Checking the equivalent bit in PBS_CLIENT_SCRATCH2 for the
+ *    completion of the sequence.
+ * 4. If PBS_CLIENT_SCRATCH2 == 0xFF, the PBS sequence failed to execute
+ *
+ * Return: 0 on success, < 0 on failure
+ */
+int qcom_pbs_trigger_event(struct pbs_dev *pbs, u8 bitmap)
+{
+	unsigned int val;
+	u16 bit_pos;
+	int ret;
+
+	if (WARN_ON(!bitmap))
+		return -EINVAL;
+
+	if (IS_ERR_OR_NULL(pbs))
+		return -EINVAL;
+
+	mutex_lock(&pbs->lock);
+	ret = regmap_read(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH2, &val);
+	if (ret < 0)
+		goto out;
+
+	if (val == PBS_CLIENT_SCRATCH2_ERROR) {
+		/* PBS error - clear SCRATCH2 register */
+		ret = regmap_write(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH2, 0);
+		if (ret < 0)
+			goto out;
+	}
+
+	for (bit_pos = 0; bit_pos < 8; bit_pos++) {
+		if (!(bitmap & BIT(bit_pos)))
+			continue;
+
+		/* Clear the PBS sequence bit position */
+		ret = regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH2,
+					 BIT(bit_pos), 0);
+		if (ret < 0)
+			goto out_clear_scratch1;
+
+		/* Set the PBS sequence bit position */
+		ret = regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH1,
+					 BIT(bit_pos), BIT(bit_pos));
+		if (ret < 0)
+			goto out_clear_scratch1;
+
+		/* Initiate the SW trigger */
+		ret = regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_TRIG_CTL,
+					 PBS_CLIENT_SW_TRIG_BIT, PBS_CLIENT_SW_TRIG_BIT);
+		if (ret < 0)
+			goto out_clear_scratch1;
+
+		ret = qcom_pbs_wait_for_ack(pbs, bit_pos);
+		if (ret < 0)
+			goto out_clear_scratch1;
+
+		/* Clear the PBS sequence bit position */
+		regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH1, BIT(bit_pos), 0);
+		regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH2, BIT(bit_pos), 0);
+	}
+
+out_clear_scratch1:
+	/* Clear all the requested bitmap */
+	ret = regmap_update_bits(pbs->regmap, pbs->base + PBS_CLIENT_SCRATCH1, bitmap, 0);
+
+out:
+	mutex_unlock(&pbs->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(qcom_pbs_trigger_event);
+
+/**
+ * get_pbs_client_device() - Get the PBS device used by client
+ * @dev: Client device
+ *
+ * This function is used to get the PBS device that is being
+ * used by the client.
+ *
+ * Return: pbs_dev on success, ERR_PTR on failure
+ */
+struct pbs_dev *get_pbs_client_device(struct device *dev)
+{
+	struct device_node *pbs_dev_node;
+	struct platform_device *pdev;
+	struct pbs_dev *pbs;
+
+	pbs_dev_node = of_parse_phandle(dev->of_node, "qcom,pbs", 0);
+	if (!pbs_dev_node) {
+		dev_err(dev, "Missing qcom,pbs property\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	pdev = of_find_device_by_node(pbs_dev_node);
+	if (!pdev) {
+		dev_err(dev, "Unable to find PBS dev_node\n");
+		pbs = ERR_PTR(-EPROBE_DEFER);
+		goto out;
+	}
+
+	pbs = platform_get_drvdata(pdev);
+	if (!pbs) {
+		dev_err(dev, "Cannot get pbs instance from %s\n", dev_name(&pdev->dev));
+		platform_device_put(pdev);
+		pbs = ERR_PTR(-EPROBE_DEFER);
+		goto out;
+	}
+
+	pbs->link = device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER);
+	if (!pbs->link) {
+		dev_err(&pdev->dev, "Failed to create device link to consumer %s\n", dev_name(dev));
+		platform_device_put(pdev);
+		pbs = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
+out:
+	of_node_put(pbs_dev_node);
+	return pbs;
+}
+EXPORT_SYMBOL_GPL(get_pbs_client_device);
+
+static int qcom_pbs_probe(struct platform_device *pdev)
+{
+	struct pbs_dev *pbs;
+	u32 val;
+	int ret;
+
+	pbs = devm_kzalloc(&pdev->dev, sizeof(*pbs), GFP_KERNEL);
+	if (!pbs)
+		return -ENOMEM;
+
+	pbs->dev = &pdev->dev;
+	pbs->regmap = dev_get_regmap(pbs->dev->parent, NULL);
+	if (!pbs->regmap) {
+		dev_err(pbs->dev, "Couldn't get parent's regmap\n");
+		return -EINVAL;
+	}
+
+	ret = device_property_read_u32(pbs->dev, "reg", &val);
+	if (ret < 0) {
+		dev_err(pbs->dev, "Couldn't find reg, ret = %d\n", ret);
+		return ret;
+	}
+	pbs->base = val;
+	mutex_init(&pbs->lock);
+
+	platform_set_drvdata(pdev, pbs);
+
+	return 0;
+}
+
+static const struct of_device_id qcom_pbs_match_table[] = {
+	{ .compatible = "qcom,pbs" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_pbs_match_table);
+
+static struct platform_driver qcom_pbs_driver = {
+	.driver = {
+		.name		= "qcom-pbs",
+		.of_match_table	= qcom_pbs_match_table,
+	},
+	.probe = qcom_pbs_probe,
+};
+module_platform_driver(qcom_pbs_driver)
+
+MODULE_DESCRIPTION("QCOM PBS DRIVER");
+MODULE_LICENSE("GPL");
diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c
index aff0cfb71482..ca2f6b7629ce 100644
--- a/drivers/soc/qcom/qcom_aoss.c
+++ b/drivers/soc/qcom/qcom_aoss.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2019, Linaro Ltd
  */
 #include <linux/clk-provider.h>
+#include <linux/debugfs.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/mailbox_client.h>
@@ -13,6 +14,9 @@
 #include <linux/slab.h>
 #include <linux/soc/qcom/qcom_aoss.h>
 
+#define CREATE_TRACE_POINTS
+#include "trace-aoss.h"
+
 #define QMP_DESC_MAGIC			0x0
 #define QMP_DESC_VERSION		0x4
 #define QMP_DESC_FEATURES		0x8
@@ -44,6 +48,8 @@
 
 #define QMP_NUM_COOLING_RESOURCES	2
 
+#define QMP_DEBUGFS_FILES		4
+
 static bool qmp_cdev_max_state = 1;
 
 struct qmp_cooling_device {
@@ -65,6 +71,8 @@ struct qmp_cooling_device {
  * @tx_lock: provides synchronization between multiple callers of qmp_send()
  * @qdss_clk: QDSS clock hw struct
  * @cooling_devs: thermal cooling devices
+ * @debugfs_root: directory for the developer/tester interface
+ * @debugfs_files: array of individual debugfs entries under debugfs_root
  */
 struct qmp {
 	void __iomem *msgram;
@@ -82,6 +90,8 @@ struct qmp {
 
 	struct clk_hw qdss_clk;
 	struct qmp_cooling_device *cooling_devs;
+	struct dentry *debugfs_root;
+	struct dentry *debugfs_files[QMP_DEBUGFS_FILES];
 };
 
 static void qmp_kick(struct qmp *qmp)
@@ -214,7 +224,7 @@ static bool qmp_message_empty(struct qmp *qmp)
  *
  * Return: 0 on success, negative errno on failure
  */
-int qmp_send(struct qmp *qmp, const char *fmt, ...)
+int __printf(2, 3) qmp_send(struct qmp *qmp, const char *fmt, ...)
 {
 	char buf[QMP_MSG_LEN];
 	long time_left;
@@ -235,6 +245,8 @@ int qmp_send(struct qmp *qmp, const char *fmt, ...)
 
 	mutex_lock(&qmp->tx_lock);
 
+	trace_aoss_send(buf);
+
 	/* The message RAM only implements 32-bit accesses */
 	__iowrite32_copy(qmp->msgram + qmp->offset + sizeof(u32),
 			 buf, sizeof(buf) / sizeof(u32));
@@ -256,6 +268,8 @@ int qmp_send(struct qmp *qmp, const char *fmt, ...)
 		ret = 0;
 	}
 
+	trace_aoss_send_done(buf, ret);
+
 	mutex_unlock(&qmp->tx_lock);
 
 	return ret;
@@ -475,6 +489,91 @@ void qmp_put(struct qmp *qmp)
 }
 EXPORT_SYMBOL_GPL(qmp_put);
 
+struct qmp_debugfs_entry {
+	const char *name;
+	const char *fmt;
+	bool is_bool;
+	const char *true_val;
+	const char *false_val;
+};
+
+static const struct qmp_debugfs_entry qmp_debugfs_entries[QMP_DEBUGFS_FILES] = {
+	{ "ddr_frequency_mhz", "{class: ddr, res: fixed, val: %u}", false },
+	{ "prevent_aoss_sleep", "{class: aoss_slp, res: sleep: %s}", true, "enable", "disable" },
+	{ "prevent_cx_collapse", "{class: cx_mol, res: cx, val: %s}", true, "mol", "off" },
+	{ "prevent_ddr_collapse", "{class: ddr_mol, res: ddr, val: %s}", true, "mol", "off" },
+};
+
+static ssize_t qmp_debugfs_write(struct file *file, const char __user *user_buf,
+				 size_t count, loff_t *pos)
+{
+	const struct qmp_debugfs_entry *entry = NULL;
+	struct qmp *qmp = file->private_data;
+	char buf[QMP_MSG_LEN];
+	unsigned int uint_val;
+	const char *str_val;
+	bool bool_val;
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qmp->debugfs_files); i++) {
+		if (qmp->debugfs_files[i] == file->f_path.dentry) {
+			entry = &qmp_debugfs_entries[i];
+			break;
+		}
+	}
+	if (WARN_ON(!entry))
+		return -EFAULT;
+
+	if (entry->is_bool) {
+		ret = kstrtobool_from_user(user_buf, count, &bool_val);
+		if (ret)
+			return ret;
+
+		str_val = bool_val ? entry->true_val : entry->false_val;
+
+		ret = snprintf(buf, sizeof(buf), entry->fmt, str_val);
+		if (ret >= sizeof(buf))
+			return -EINVAL;
+	} else {
+		ret = kstrtou32_from_user(user_buf, count, 0, &uint_val);
+		if (ret)
+			return ret;
+
+		ret = snprintf(buf, sizeof(buf), entry->fmt, uint_val);
+		if (ret >= sizeof(buf))
+			return -EINVAL;
+	}
+
+	ret = qmp_send(qmp, buf);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static const struct file_operations qmp_debugfs_fops = {
+	.open = simple_open,
+	.write = qmp_debugfs_write,
+};
+
+static void qmp_debugfs_create(struct qmp *qmp)
+{
+	const struct qmp_debugfs_entry *entry;
+	int i;
+
+	qmp->debugfs_root = debugfs_create_dir("qcom_aoss", NULL);
+
+	for (i = 0; i < ARRAY_SIZE(qmp->debugfs_files); i++) {
+		entry = &qmp_debugfs_entries[i];
+
+		qmp->debugfs_files[i] = debugfs_create_file(entry->name, 0200,
+							    qmp->debugfs_root,
+							    qmp,
+							    &qmp_debugfs_fops);
+	}
+}
+
 static int qmp_probe(struct platform_device *pdev)
 {
 	struct qmp *qmp;
@@ -523,6 +622,8 @@ static int qmp_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, qmp);
 
+	qmp_debugfs_create(qmp);
+
 	return 0;
 
 err_close_qmp:
@@ -537,6 +638,8 @@ static void qmp_remove(struct platform_device *pdev)
 {
 	struct qmp *qmp = platform_get_drvdata(pdev);
 
+	debugfs_remove_recursive(qmp->debugfs_root);
+
 	qmp_qdss_clk_remove(qmp);
 	qmp_cooling_devices_remove(qmp);
 
diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c
index 690afc9a12f4..7191fa0c087f 100644
--- a/drivers/soc/qcom/smem.c
+++ b/drivers/soc/qcom/smem.c
@@ -655,8 +655,6 @@ invalid_canary:
 void *qcom_smem_get(unsigned host, unsigned item, size_t *size)
 {
 	struct smem_partition *part;
-	unsigned long flags;
-	int ret;
 	void *ptr = ERR_PTR(-EPROBE_DEFER);
 
 	if (!__smem)
@@ -665,12 +663,6 @@ void *qcom_smem_get(unsigned host, unsigned item, size_t *size)
 	if (WARN_ON(item >= __smem->item_count))
 		return ERR_PTR(-EINVAL);
 
-	ret = hwspin_lock_timeout_irqsave(__smem->hwlock,
-					  HWSPINLOCK_TIMEOUT,
-					  &flags);
-	if (ret)
-		return ERR_PTR(ret);
-
 	if (host < SMEM_HOST_COUNT && __smem->partitions[host].virt_base) {
 		part = &__smem->partitions[host];
 		ptr = qcom_smem_get_private(__smem, part, item, size);
@@ -681,10 +673,7 @@ void *qcom_smem_get(unsigned host, unsigned item, size_t *size)
 		ptr = qcom_smem_get_global(__smem, item, size);
 	}
 
-	hwspin_unlock_irqrestore(__smem->hwlock, &flags);
-
 	return ptr;
-
 }
 EXPORT_SYMBOL_GPL(qcom_smem_get);
 
diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c
index 914b2246148f..a21241cbeec7 100644
--- a/drivers/soc/qcom/smp2p.c
+++ b/drivers/soc/qcom/smp2p.c
@@ -58,8 +58,8 @@
  * @valid_entries:	number of allocated entries
  * @flags:
  * @entries:		individual communication entries
- *     @name:		name of the entry
- *     @value:		content of the entry
+ * @entries.name:	name of the entry
+ * @entries.value:	content of the entry
  */
 struct smp2p_smem_item {
 	u32 magic;
@@ -275,6 +275,8 @@ static void qcom_smp2p_notify_in(struct qcom_smp2p *smp2p)
  *
  * Handle notifications from the remote side to handle newly allocated entries
  * or any changes to the state bits of existing entries.
+ *
+ * Return: %IRQ_HANDLED
  */
 static irqreturn_t qcom_smp2p_intr(int irq, void *data)
 {
diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
index 6349a0debeb5..e8ff9819ac47 100644
--- a/drivers/soc/qcom/socinfo.c
+++ b/drivers/soc/qcom/socinfo.c
@@ -124,7 +124,7 @@ static const char *const pmic_models[] = {
 	[50] = "PM8350B",
 	[51] = "PMR735A",
 	[52] = "PMR735B",
-	[55] = "PM2250",
+	[55] = "PM4125",
 	[58] = "PM8450",
 	[65] = "PM8010",
 	[69] = "PM8550VS",
@@ -424,8 +424,11 @@ static const struct soc_id soc_id[] = {
 	{ qcom_board_id(IPQ9510) },
 	{ qcom_board_id(QRB4210) },
 	{ qcom_board_id(QRB2210) },
+	{ qcom_board_id(SM8475) },
+	{ qcom_board_id(SM8475P) },
 	{ qcom_board_id(SA8775P) },
 	{ qcom_board_id(QRU1000) },
+	{ qcom_board_id(SM8475_2) },
 	{ qcom_board_id(QDU1000) },
 	{ qcom_board_id(SM8650) },
 	{ qcom_board_id(SM4450) },
@@ -437,6 +440,8 @@ static const struct soc_id soc_id[] = {
 	{ qcom_board_id(IPQ5322) },
 	{ qcom_board_id(IPQ5312) },
 	{ qcom_board_id(IPQ5302) },
+	{ qcom_board_id(QCS8550) },
+	{ qcom_board_id(QCM8550) },
 	{ qcom_board_id(IPQ5300) },
 };
 
diff --git a/drivers/soc/qcom/spm.c b/drivers/soc/qcom/spm.c
index 2f0b1bfe7658..06e2c4c2a4a8 100644
--- a/drivers/soc/qcom/spm.c
+++ b/drivers/soc/qcom/spm.c
@@ -6,20 +6,40 @@
  * SAW power controller driver
  */
 
-#include <linux/kernel.h>
+#include <linux/bitfield.h>
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/linear_range.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/err.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+
+#include <linux/regulator/driver.h>
+
 #include <soc/qcom/spm.h>
 
+#define FIELD_SET(current, mask, val)	\
+	(((current) & ~(mask)) | FIELD_PREP((mask), (val)))
+
 #define SPM_CTL_INDEX		0x7f
 #define SPM_CTL_INDEX_SHIFT	4
 #define SPM_CTL_EN		BIT(0)
 
+/* These registers might be specific to SPM 1.1 */
+#define SPM_VCTL_VLVL			GENMASK(7, 0)
+#define SPM_PMIC_DATA_0_VLVL		GENMASK(7, 0)
+#define SPM_PMIC_DATA_1_MIN_VSEL	GENMASK(5, 0)
+#define SPM_PMIC_DATA_1_MAX_VSEL	GENMASK(21, 16)
+
+#define SPM_1_1_AVS_CTL_AVS_ENABLED	BIT(27)
+#define SPM_AVS_CTL_MAX_VLVL		GENMASK(22, 17)
+#define SPM_AVS_CTL_MIN_VLVL		GENMASK(15, 10)
+
 enum spm_reg {
 	SPM_REG_CFG,
 	SPM_REG_SPM_CTL,
@@ -29,13 +49,44 @@ enum spm_reg {
 	SPM_REG_PMIC_DATA_1,
 	SPM_REG_VCTL,
 	SPM_REG_SEQ_ENTRY,
-	SPM_REG_SPM_STS,
+	SPM_REG_STS0,
+	SPM_REG_STS1,
 	SPM_REG_PMIC_STS,
 	SPM_REG_AVS_CTL,
 	SPM_REG_AVS_LIMIT,
+	SPM_REG_RST,
 	SPM_REG_NR,
 };
 
+#define MAX_PMIC_DATA		2
+#define MAX_SEQ_DATA		64
+
+struct spm_reg_data {
+	const u16 *reg_offset;
+	u32 spm_cfg;
+	u32 spm_dly;
+	u32 pmic_dly;
+	u32 pmic_data[MAX_PMIC_DATA];
+	u32 avs_ctl;
+	u32 avs_limit;
+	u8 seq[MAX_SEQ_DATA];
+	u8 start_index[PM_SLEEP_MODE_NR];
+
+	smp_call_func_t set_vdd;
+	/* for now we support only a single range */
+	struct linear_range *range;
+	unsigned int ramp_delay;
+	unsigned int init_uV;
+};
+
+struct spm_driver_data {
+	void __iomem *reg_base;
+	const struct spm_reg_data *reg_data;
+	struct device *dev;
+	unsigned int volt_sel;
+	int reg_cpu;
+};
+
 static const u16 spm_reg_offset_v4_1[SPM_REG_NR] = {
 	[SPM_REG_AVS_CTL]	= 0x904,
 	[SPM_REG_AVS_LIMIT]	= 0x908,
@@ -169,6 +220,10 @@ static const struct spm_reg_data spm_reg_8226_cpu  = {
 
 static const u16 spm_reg_offset_v1_1[SPM_REG_NR] = {
 	[SPM_REG_CFG]		= 0x08,
+	[SPM_REG_STS0]		= 0x0c,
+	[SPM_REG_STS1]		= 0x10,
+	[SPM_REG_VCTL]		= 0x14,
+	[SPM_REG_AVS_CTL]	= 0x18,
 	[SPM_REG_SPM_CTL]	= 0x20,
 	[SPM_REG_PMIC_DLY]	= 0x24,
 	[SPM_REG_PMIC_DATA_0]	= 0x28,
@@ -176,7 +231,12 @@ static const u16 spm_reg_offset_v1_1[SPM_REG_NR] = {
 	[SPM_REG_SEQ_ENTRY]	= 0x80,
 };
 
+static void smp_set_vdd_v1_1(void *data);
+
 /* SPM register data for 8064 */
+static struct linear_range spm_v1_1_regulator_range =
+	REGULATOR_LINEAR_RANGE(700000, 0, 56, 12500);
+
 static const struct spm_reg_data spm_reg_8064_cpu = {
 	.reg_offset = spm_reg_offset_v1_1,
 	.spm_cfg = 0x1F,
@@ -187,6 +247,10 @@ static const struct spm_reg_data spm_reg_8064_cpu = {
 		0x10, 0x54, 0x30, 0x0C, 0x24, 0x30, 0x0F },
 	.start_index[PM_SLEEP_MODE_STBY] = 0,
 	.start_index[PM_SLEEP_MODE_SPC] = 2,
+	.set_vdd = smp_set_vdd_v1_1,
+	.range = &spm_v1_1_regulator_range,
+	.init_uV = 1300000,
+	.ramp_delay = 1250,
 };
 
 static inline void spm_register_write(struct spm_driver_data *drv,
@@ -238,6 +302,178 @@ void spm_set_low_power_mode(struct spm_driver_data *drv,
 	spm_register_write_sync(drv, SPM_REG_SPM_CTL, ctl_val);
 }
 
+static int spm_set_voltage_sel(struct regulator_dev *rdev, unsigned int selector)
+{
+	struct spm_driver_data *drv = rdev_get_drvdata(rdev);
+
+	drv->volt_sel = selector;
+
+	/* Always do the SAW register writes on the corresponding CPU */
+	return smp_call_function_single(drv->reg_cpu, drv->reg_data->set_vdd, drv, true);
+}
+
+static int spm_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct spm_driver_data *drv = rdev_get_drvdata(rdev);
+
+	return drv->volt_sel;
+}
+
+static const struct regulator_ops spm_reg_ops = {
+	.set_voltage_sel	= spm_set_voltage_sel,
+	.get_voltage_sel	= spm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
+};
+
+static void smp_set_vdd_v1_1(void *data)
+{
+	struct spm_driver_data *drv = data;
+	unsigned int vctl, data0, data1, avs_ctl, sts;
+	unsigned int vlevel, volt_sel;
+	bool avs_enabled;
+
+	volt_sel = drv->volt_sel;
+	vlevel = volt_sel | 0x80; /* band */
+
+	avs_ctl = spm_register_read(drv, SPM_REG_AVS_CTL);
+	vctl = spm_register_read(drv, SPM_REG_VCTL);
+	data0 = spm_register_read(drv, SPM_REG_PMIC_DATA_0);
+	data1 = spm_register_read(drv, SPM_REG_PMIC_DATA_1);
+
+	avs_enabled = avs_ctl & SPM_1_1_AVS_CTL_AVS_ENABLED;
+
+	/* If AVS is enabled, switch it off during the voltage change */
+	if (avs_enabled) {
+		avs_ctl &= ~SPM_1_1_AVS_CTL_AVS_ENABLED;
+		spm_register_write(drv, SPM_REG_AVS_CTL, avs_ctl);
+	}
+
+	/* Kick the state machine back to idle */
+	spm_register_write(drv, SPM_REG_RST, 1);
+
+	vctl = FIELD_SET(vctl, SPM_VCTL_VLVL, vlevel);
+	data0 = FIELD_SET(data0, SPM_PMIC_DATA_0_VLVL, vlevel);
+	data1 = FIELD_SET(data1, SPM_PMIC_DATA_1_MIN_VSEL, volt_sel);
+	data1 = FIELD_SET(data1, SPM_PMIC_DATA_1_MAX_VSEL, volt_sel);
+
+	spm_register_write(drv, SPM_REG_VCTL, vctl);
+	spm_register_write(drv, SPM_REG_PMIC_DATA_0, data0);
+	spm_register_write(drv, SPM_REG_PMIC_DATA_1, data1);
+
+	if (read_poll_timeout_atomic(spm_register_read,
+				     sts, sts == vlevel,
+				     1, 200, false,
+				     drv, SPM_REG_STS1)) {
+		dev_err_ratelimited(drv->dev, "timeout setting the voltage (%x %x)!\n", sts, vlevel);
+		goto enable_avs;
+	}
+
+	if (avs_enabled) {
+		unsigned int max_avs = volt_sel;
+		unsigned int min_avs = max(max_avs, 4U) - 4;
+
+		avs_ctl = FIELD_SET(avs_ctl, SPM_AVS_CTL_MIN_VLVL, min_avs);
+		avs_ctl = FIELD_SET(avs_ctl, SPM_AVS_CTL_MAX_VLVL, max_avs);
+		spm_register_write(drv, SPM_REG_AVS_CTL, avs_ctl);
+	}
+
+enable_avs:
+	if (avs_enabled) {
+		avs_ctl |= SPM_1_1_AVS_CTL_AVS_ENABLED;
+		spm_register_write(drv, SPM_REG_AVS_CTL, avs_ctl);
+	}
+}
+
+static int spm_get_cpu(struct device *dev)
+{
+	int cpu;
+	bool found;
+
+	for_each_possible_cpu(cpu) {
+		struct device_node *cpu_node, *saw_node;
+
+		cpu_node = of_cpu_device_node_get(cpu);
+		if (!cpu_node)
+			continue;
+
+		saw_node = of_parse_phandle(cpu_node, "qcom,saw", 0);
+		found = (saw_node == dev->of_node);
+		of_node_put(saw_node);
+		of_node_put(cpu_node);
+
+		if (found)
+			return cpu;
+	}
+
+	/* L2 SPM is not bound to any CPU, voltage setting is not supported */
+
+	return -EOPNOTSUPP;
+}
+
+static int spm_register_regulator(struct device *dev, struct spm_driver_data *drv)
+{
+	struct regulator_config config = {
+		.dev = dev,
+		.driver_data = drv,
+	};
+	struct regulator_desc *rdesc;
+	struct regulator_dev *rdev;
+	int ret;
+	bool found;
+
+	if (!drv->reg_data->set_vdd)
+		return 0;
+
+	rdesc = devm_kzalloc(dev, sizeof(*rdesc), GFP_KERNEL);
+	if (!rdesc)
+		return -ENOMEM;
+
+	rdesc->name = "spm";
+	rdesc->of_match = of_match_ptr("regulator");
+	rdesc->type = REGULATOR_VOLTAGE;
+	rdesc->owner = THIS_MODULE;
+	rdesc->ops = &spm_reg_ops;
+
+	rdesc->linear_ranges = drv->reg_data->range;
+	rdesc->n_linear_ranges = 1;
+	rdesc->n_voltages = rdesc->linear_ranges[rdesc->n_linear_ranges - 1].max_sel + 1;
+	rdesc->ramp_delay = drv->reg_data->ramp_delay;
+
+	ret = spm_get_cpu(dev);
+	if (ret < 0)
+		return ret;
+
+	drv->reg_cpu = ret;
+	dev_dbg(dev, "SAW2 bound to CPU %d\n", drv->reg_cpu);
+
+	/*
+	 * Program initial voltage, otherwise registration will also try
+	 * setting the voltage, which might result in undervolting the CPU.
+	 */
+	drv->volt_sel = DIV_ROUND_UP(drv->reg_data->init_uV - rdesc->min_uV,
+				     rdesc->uV_step);
+	ret = linear_range_get_selector_high(drv->reg_data->range,
+					     drv->reg_data->init_uV,
+					     &drv->volt_sel,
+					     &found);
+	if (ret) {
+		dev_err(dev, "Initial uV value out of bounds\n");
+		return ret;
+	}
+
+	/* Always do the SAW register writes on the corresponding CPU */
+	smp_call_function_single(drv->reg_cpu, drv->reg_data->set_vdd, drv, true);
+
+	rdev = devm_regulator_register(dev, rdesc, &config);
+	if (IS_ERR(rdev)) {
+		dev_err(dev, "failed to register regulator\n");
+		return PTR_ERR(rdev);
+	}
+
+	return 0;
+}
+
 static const struct of_device_id spm_match_table[] = {
 	{ .compatible = "qcom,sdm660-gold-saw2-v4.1-l2",
 	  .data = &spm_reg_660_gold_l2 },
@@ -288,6 +524,7 @@ static int spm_dev_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	drv->reg_data = match_id->data;
+	drv->dev = &pdev->dev;
 	platform_set_drvdata(pdev, drv);
 
 	/* Write the SPM sequences first.. */
@@ -315,6 +552,9 @@ static int spm_dev_probe(struct platform_device *pdev)
 	if (drv->reg_data->reg_offset[SPM_REG_SPM_CTL])
 		spm_set_low_power_mode(drv, PM_SLEEP_MODE_STBY);
 
+	if (IS_ENABLED(CONFIG_REGULATOR))
+		return spm_register_regulator(&pdev->dev, drv);
+
 	return 0;
 }
 
diff --git a/drivers/soc/qcom/trace-aoss.h b/drivers/soc/qcom/trace-aoss.h
new file mode 100644
index 000000000000..554029b33b44
--- /dev/null
+++ b/drivers/soc/qcom/trace-aoss.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM qcom_aoss
+
+#if !defined(_TRACE_QCOM_AOSS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_QCOM_AOSS_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(aoss_send,
+	TP_PROTO(const char *msg),
+	TP_ARGS(msg),
+	TP_STRUCT__entry(
+		__string(msg, msg)
+	),
+	TP_fast_assign(
+		__assign_str(msg, msg);
+	),
+	TP_printk("%s", __get_str(msg))
+);
+
+TRACE_EVENT(aoss_send_done,
+	TP_PROTO(const char *msg, int ret),
+	TP_ARGS(msg, ret),
+	TP_STRUCT__entry(
+		__string(msg, msg)
+		__field(int, ret)
+	),
+	TP_fast_assign(
+		__assign_str(msg, msg);
+		__entry->ret = ret;
+	),
+	TP_printk("%s: %d", __get_str(msg), __entry->ret)
+);
+
+#endif /* _TRACE_QCOM_AOSS_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-aoss
+
+#include <trace/define_trace.h>
diff --git a/drivers/soc/renesas/Kconfig b/drivers/soc/renesas/Kconfig
index 0986672f6375..5deca747fb77 100644
--- a/drivers/soc/renesas/Kconfig
+++ b/drivers/soc/renesas/Kconfig
@@ -34,6 +34,10 @@ config ARCH_RCAR_GEN3
 	select SYS_SUPPORTS_SH_CMT
 	select SYS_SUPPORTS_SH_TMU
 
+config ARCH_RCAR_GEN4
+	bool
+	select ARCH_RCAR_GEN3
+
 config ARCH_RMOBILE
 	bool
 	select PM
@@ -240,7 +244,7 @@ config ARCH_R8A77961
 
 config ARCH_R8A779F0
 	bool "ARM64 Platform support for R-Car S4-8"
-	select ARCH_RCAR_GEN3
+	select ARCH_RCAR_GEN4
 	select SYSC_R8A779F0
 	help
 	  This enables support for the Renesas R-Car S4-8 SoC.
@@ -261,18 +265,25 @@ config ARCH_R8A77970
 
 config ARCH_R8A779A0
 	bool "ARM64 Platform support for R-Car V3U"
-	select ARCH_RCAR_GEN3
+	select ARCH_RCAR_GEN4
 	select SYSC_R8A779A0
 	help
 	  This enables support for the Renesas R-Car V3U SoC.
 
 config ARCH_R8A779G0
 	bool "ARM64 Platform support for R-Car V4H"
-	select ARCH_RCAR_GEN3
+	select ARCH_RCAR_GEN4
 	select SYSC_R8A779G0
 	help
 	  This enables support for the Renesas R-Car V4H SoC.
 
+config ARCH_R8A779H0
+	bool "ARM64 Platform support for R-Car V4M"
+	select ARCH_RCAR_GEN4
+	select SYSC_R8A779H0
+	help
+	  This enables support for the Renesas R-Car V4M SoC.
+
 config ARCH_R8A774C0
 	bool "ARM64 Platform support for RZ/G2E"
 	select ARCH_RCAR_GEN3
diff --git a/drivers/soc/renesas/rcar-rst.c b/drivers/soc/renesas/rcar-rst.c
index 98fd97da6cd4..7ba02f3a4a4f 100644
--- a/drivers/soc/renesas/rcar-rst.c
+++ b/drivers/soc/renesas/rcar-rst.c
@@ -117,6 +117,7 @@ static const struct of_device_id rcar_rst_matches[] __initconst = {
 	{ .compatible = "renesas,r8a779a0-rst", .data = &rcar_rst_v3u },
 	{ .compatible = "renesas,r8a779f0-rst", .data = &rcar_rst_gen4 },
 	{ .compatible = "renesas,r8a779g0-rst", .data = &rcar_rst_gen4 },
+	{ .compatible = "renesas,r8a779h0-rst", .data = &rcar_rst_gen4 },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/soc/renesas/renesas-soc.c b/drivers/soc/renesas/renesas-soc.c
index 27eae1a354ab..8f9b8d3736dc 100644
--- a/drivers/soc/renesas/renesas-soc.c
+++ b/drivers/soc/renesas/renesas-soc.c
@@ -270,6 +270,11 @@ static const struct renesas_soc soc_rcar_v4h __initconst __maybe_unused = {
 	.id	= 0x5c,
 };
 
+static const struct renesas_soc soc_rcar_v4m __initconst __maybe_unused = {
+	.family = &fam_rcar_gen4,
+	.id     = 0x5d,
+};
+
 static const struct renesas_soc soc_shmobile_ag5 __initconst __maybe_unused = {
 	.family	= &fam_shmobile,
 	.id	= 0x37,
@@ -380,6 +385,9 @@ static const struct of_device_id renesas_socs[] __initconst __maybe_unused = {
 #ifdef CONFIG_ARCH_R8A779G0
 	{ .compatible = "renesas,r8a779g0",	.data = &soc_rcar_v4h },
 #endif
+#ifdef CONFIG_ARCH_R8A779H0
+	{ .compatible = "renesas,r8a779h0",	.data = &soc_rcar_v4m },
+#endif
 #ifdef CONFIG_ARCH_R9A07G043
 #ifdef CONFIG_RISCV
 	{ .compatible = "renesas,r9a07g043",	.data = &soc_rz_five },
diff --git a/drivers/soc/samsung/Kconfig b/drivers/soc/samsung/Kconfig
index 27ec99af77e3..1a5dfdc978dc 100644
--- a/drivers/soc/samsung/Kconfig
+++ b/drivers/soc/samsung/Kconfig
@@ -42,6 +42,7 @@ config EXYNOS_PMU
 	depends on ARCH_EXYNOS || ((ARM || ARM64) && COMPILE_TEST)
 	select EXYNOS_PMU_ARM_DRIVERS if ARM && ARCH_EXYNOS
 	select MFD_CORE
+	select REGMAP_MMIO
 
 # There is no need to enable these drivers for ARMv8
 config EXYNOS_PMU_ARM_DRIVERS
diff --git a/drivers/soc/samsung/exynos-pmu.c b/drivers/soc/samsung/exynos-pmu.c
index 250537d7cfd6..fd8b6ac06656 100644
--- a/drivers/soc/samsung/exynos-pmu.c
+++ b/drivers/soc/samsung/exynos-pmu.c
@@ -5,6 +5,7 @@
 //
 // Exynos - CPU PMU(Power Management Unit) support
 
+#include <linux/arm-smccc.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/mfd/core.h>
@@ -12,19 +13,134 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/regmap.h>
 
 #include <linux/soc/samsung/exynos-regs-pmu.h>
 #include <linux/soc/samsung/exynos-pmu.h>
 
 #include "exynos-pmu.h"
 
+#define PMUALIVE_MASK			GENMASK(13, 0)
+#define TENSOR_SET_BITS			(BIT(15) | BIT(14))
+#define TENSOR_CLR_BITS			BIT(15)
+#define TENSOR_SMC_PMU_SEC_REG		0x82000504
+#define TENSOR_PMUREG_READ		0
+#define TENSOR_PMUREG_WRITE		1
+#define TENSOR_PMUREG_RMW		2
+
 struct exynos_pmu_context {
 	struct device *dev;
 	const struct exynos_pmu_data *pmu_data;
+	struct regmap *pmureg;
 };
 
 void __iomem *pmu_base_addr;
 static struct exynos_pmu_context *pmu_context;
+/* forward declaration */
+static struct platform_driver exynos_pmu_driver;
+
+/*
+ * Tensor SoCs are configured so that PMU_ALIVE registers can only be written
+ * from EL3, but are still read accessible. As Linux needs to write some of
+ * these registers, the following functions are provided and exposed via
+ * regmap.
+ *
+ * Note: This SMC interface is known to be implemented on gs101 and derivative
+ * SoCs.
+ */
+
+/* Write to a protected PMU register. */
+static int tensor_sec_reg_write(void *context, unsigned int reg,
+				unsigned int val)
+{
+	struct arm_smccc_res res;
+	unsigned long pmu_base = (unsigned long)context;
+
+	arm_smccc_smc(TENSOR_SMC_PMU_SEC_REG, pmu_base + reg,
+		      TENSOR_PMUREG_WRITE, val, 0, 0, 0, 0, &res);
+
+	/* returns -EINVAL if access isn't allowed or 0 */
+	if (res.a0)
+		pr_warn("%s(): SMC failed: %d\n", __func__, (int)res.a0);
+
+	return (int)res.a0;
+}
+
+/* Read/Modify/Write a protected PMU register. */
+static int tensor_sec_reg_rmw(void *context, unsigned int reg,
+			      unsigned int mask, unsigned int val)
+{
+	struct arm_smccc_res res;
+	unsigned long pmu_base = (unsigned long)context;
+
+	arm_smccc_smc(TENSOR_SMC_PMU_SEC_REG, pmu_base + reg,
+		      TENSOR_PMUREG_RMW, mask, val, 0, 0, 0, &res);
+
+	/* returns -EINVAL if access isn't allowed or 0 */
+	if (res.a0)
+		pr_warn("%s(): SMC failed: %d\n", __func__, (int)res.a0);
+
+	return (int)res.a0;
+}
+
+/*
+ * Read a protected PMU register. All PMU registers can be read by Linux.
+ * Note: The SMC read register is not used, as only registers that can be
+ * written are readable via SMC.
+ */
+static int tensor_sec_reg_read(void *context, unsigned int reg,
+			       unsigned int *val)
+{
+	*val = pmu_raw_readl(reg);
+	return 0;
+}
+
+/*
+ * For SoCs that have set/clear bit hardware this function can be used when
+ * the PMU register will be accessed by multiple masters.
+ *
+ * For example, to set bits 13:8 in PMU reg offset 0x3e80
+ * tensor_set_bits_atomic(ctx, 0x3e80, 0x3f00, 0x3f00);
+ *
+ * Set bit 8, and clear bits 13:9 PMU reg offset 0x3e80
+ * tensor_set_bits_atomic(0x3e80, 0x100, 0x3f00);
+ */
+static int tensor_set_bits_atomic(void *ctx, unsigned int offset, u32 val,
+				  u32 mask)
+{
+	int ret;
+	unsigned int i;
+
+	for (i = 0; i < 32; i++) {
+		if (!(mask & BIT(i)))
+			continue;
+
+		offset &= ~TENSOR_SET_BITS;
+
+		if (val & BIT(i))
+			offset |= TENSOR_SET_BITS;
+		else
+			offset |= TENSOR_CLR_BITS;
+
+		ret = tensor_sec_reg_write(ctx, offset, i);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
+static int tensor_sec_update_bits(void *ctx, unsigned int reg,
+				  unsigned int mask, unsigned int val)
+{
+	/*
+	 * Use atomic operations for PMU_ALIVE registers (offset 0~0x3FFF)
+	 * as the target registers can be accessed by multiple masters.
+	 */
+	if (reg > PMUALIVE_MASK)
+		return tensor_sec_reg_rmw(ctx, reg, mask, val);
+
+	return tensor_set_bits_atomic(ctx, reg, val, mask);
+}
 
 void pmu_raw_writel(u32 val, u32 offset)
 {
@@ -75,11 +191,41 @@ void exynos_sys_powerdown_conf(enum sys_powerdown mode)
 #define exynos_pmu_data_arm_ptr(data)	NULL
 #endif
 
+static const struct regmap_config regmap_smccfg = {
+	.name = "pmu_regs",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+	.use_single_read = true,
+	.use_single_write = true,
+	.reg_read = tensor_sec_reg_read,
+	.reg_write = tensor_sec_reg_write,
+	.reg_update_bits = tensor_sec_update_bits,
+};
+
+static const struct regmap_config regmap_mmiocfg = {
+	.name = "pmu_regs",
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+	.use_single_read = true,
+	.use_single_write = true,
+};
+
+static const struct exynos_pmu_data gs101_pmu_data = {
+	.pmu_secure = true
+};
+
 /*
  * PMU platform driver and devicetree bindings.
  */
 static const struct of_device_id exynos_pmu_of_device_ids[] = {
 	{
+		.compatible = "google,gs101-pmu",
+		.data = &gs101_pmu_data,
+	}, {
 		.compatible = "samsung,exynos3250-pmu",
 		.data = exynos_pmu_data_arm_ptr(exynos3250_pmu_data),
 	}, {
@@ -113,19 +259,75 @@ static const struct mfd_cell exynos_pmu_devs[] = {
 	{ .name = "exynos-clkout", },
 };
 
+/**
+ * exynos_get_pmu_regmap() - Obtain pmureg regmap
+ *
+ * Find the pmureg regmap previously configured in probe() and return regmap
+ * pointer.
+ *
+ * Return: A pointer to regmap if found or ERR_PTR error value.
+ */
 struct regmap *exynos_get_pmu_regmap(void)
 {
 	struct device_node *np = of_find_matching_node(NULL,
 						      exynos_pmu_of_device_ids);
 	if (np)
-		return syscon_node_to_regmap(np);
+		return exynos_get_pmu_regmap_by_phandle(np, NULL);
 	return ERR_PTR(-ENODEV);
 }
 EXPORT_SYMBOL_GPL(exynos_get_pmu_regmap);
 
+/**
+ * exynos_get_pmu_regmap_by_phandle() - Obtain pmureg regmap via phandle
+ * @np: Device node holding PMU phandle property
+ * @propname: Name of property holding phandle value
+ *
+ * Find the pmureg regmap previously configured in probe() and return regmap
+ * pointer.
+ *
+ * Return: A pointer to regmap if found or ERR_PTR error value.
+ */
+struct regmap *exynos_get_pmu_regmap_by_phandle(struct device_node *np,
+						const char *propname)
+{
+	struct exynos_pmu_context *ctx;
+	struct device_node *pmu_np;
+	struct device *dev;
+
+	if (propname)
+		pmu_np = of_parse_phandle(np, propname, 0);
+	else
+		pmu_np = np;
+
+	if (!pmu_np)
+		return ERR_PTR(-ENODEV);
+
+	/*
+	 * Determine if exynos-pmu device has probed and therefore regmap
+	 * has been created and can be returned to the caller. Otherwise we
+	 * return -EPROBE_DEFER.
+	 */
+	dev = driver_find_device_by_of_node(&exynos_pmu_driver.driver,
+					    (void *)pmu_np);
+
+	if (propname)
+		of_node_put(pmu_np);
+
+	if (!dev)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	ctx = dev_get_drvdata(dev);
+
+	return ctx->pmureg;
+}
+EXPORT_SYMBOL_GPL(exynos_get_pmu_regmap_by_phandle);
+
 static int exynos_pmu_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct regmap_config pmu_regmcfg;
+	struct regmap *regmap;
+	struct resource *res;
 	int ret;
 
 	pmu_base_addr = devm_platform_ioremap_resource(pdev, 0);
@@ -137,9 +339,38 @@ static int exynos_pmu_probe(struct platform_device *pdev)
 			GFP_KERNEL);
 	if (!pmu_context)
 		return -ENOMEM;
-	pmu_context->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
 	pmu_context->pmu_data = of_device_get_match_data(dev);
 
+	/* For SoCs that secure PMU register writes use custom regmap */
+	if (pmu_context->pmu_data && pmu_context->pmu_data->pmu_secure) {
+		pmu_regmcfg = regmap_smccfg;
+		pmu_regmcfg.max_register = resource_size(res) -
+					   pmu_regmcfg.reg_stride;
+		/* Need physical address for SMC call */
+		regmap = devm_regmap_init(dev, NULL,
+					  (void *)(uintptr_t)res->start,
+					  &pmu_regmcfg);
+	} else {
+		/* All other SoCs use a MMIO regmap */
+		pmu_regmcfg = regmap_mmiocfg;
+		pmu_regmcfg.max_register = resource_size(res) -
+					   pmu_regmcfg.reg_stride;
+		regmap = devm_regmap_init_mmio(dev, pmu_base_addr,
+					       &pmu_regmcfg);
+	}
+
+	if (IS_ERR(regmap))
+		return dev_err_probe(&pdev->dev, PTR_ERR(regmap),
+				     "regmap init failed\n");
+
+	pmu_context->pmureg = regmap;
+	pmu_context->dev = dev;
+
 	if (pmu_context->pmu_data && pmu_context->pmu_data->pmu_init)
 		pmu_context->pmu_data->pmu_init();
 
diff --git a/drivers/soc/samsung/exynos-pmu.h b/drivers/soc/samsung/exynos-pmu.h
index 1c652ffd79b4..0a49a2c9a08e 100644
--- a/drivers/soc/samsung/exynos-pmu.h
+++ b/drivers/soc/samsung/exynos-pmu.h
@@ -21,6 +21,7 @@ struct exynos_pmu_conf {
 struct exynos_pmu_data {
 	const struct exynos_pmu_conf *pmu_config;
 	const struct exynos_pmu_conf *pmu_config_extra;
+	bool pmu_secure;
 
 	void (*pmu_init)(void);
 	void (*powerdown_conf)(enum sys_powerdown);
diff --git a/drivers/soc/tegra/Kconfig b/drivers/soc/tegra/Kconfig
index f16beeabaa92..33512558af9f 100644
--- a/drivers/soc/tegra/Kconfig
+++ b/drivers/soc/tegra/Kconfig
@@ -133,6 +133,11 @@ config ARCH_TEGRA_234_SOC
 	help
 	  Enable support for the NVIDIA Tegra234 SoC.
 
+config ARCH_TEGRA_241_SOC
+	bool "NVIDIA Tegra241 SoC"
+	help
+	  Enable support for the NVIDIA Tegra241 SoC.
+
 endif
 endif
 
diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c
index a2c28f493a75..b6bfd6729df3 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra.c
@@ -3,11 +3,13 @@
  * Copyright (c) 2013-2023, NVIDIA CORPORATION.  All rights reserved.
  */
 
+#include <linux/acpi.h>
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/kobject.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/mod_devicetable.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/nvmem-provider.h>
 #include <linux/of.h>
@@ -113,6 +115,28 @@ static void tegra_fuse_restore(void *base)
 	fuse->clk = NULL;
 }
 
+static void tegra_fuse_print_sku_info(struct tegra_sku_info *tegra_sku_info)
+{
+	pr_info("Tegra Revision: %s SKU: %d CPU Process: %d SoC Process: %d\n",
+		tegra_revision_name[tegra_sku_info->revision],
+		tegra_sku_info->sku_id, tegra_sku_info->cpu_process_id,
+		tegra_sku_info->soc_process_id);
+	pr_debug("Tegra CPU Speedo ID %d, SoC Speedo ID %d\n",
+		tegra_sku_info->cpu_speedo_id, tegra_sku_info->soc_speedo_id);
+}
+
+static int tegra_fuse_add_lookups(struct tegra_fuse *fuse)
+{
+	fuse->lookups = kmemdup_array(fuse->soc->lookups, sizeof(*fuse->lookups),
+				      fuse->soc->num_lookups, GFP_KERNEL);
+	if (!fuse->lookups)
+		return -ENOMEM;
+
+	nvmem_add_cell_lookups(fuse->lookups, fuse->soc->num_lookups);
+
+	return 0;
+}
+
 static int tegra_fuse_probe(struct platform_device *pdev)
 {
 	void __iomem *base = fuse->base;
@@ -130,15 +154,46 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 		return PTR_ERR(fuse->base);
 	fuse->phys = res->start;
 
-	fuse->clk = devm_clk_get(&pdev->dev, "fuse");
-	if (IS_ERR(fuse->clk)) {
-		if (PTR_ERR(fuse->clk) != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "failed to get FUSE clock: %ld",
-				PTR_ERR(fuse->clk));
+	/* Initialize the soc data and lookups if using ACPI boot. */
+	if (is_acpi_node(dev_fwnode(&pdev->dev)) && !fuse->soc) {
+		u8 chip;
 
-		return PTR_ERR(fuse->clk);
+		tegra_acpi_init_apbmisc();
+
+		chip = tegra_get_chip_id();
+		switch (chip) {
+#if defined(CONFIG_ARCH_TEGRA_194_SOC)
+		case TEGRA194:
+			fuse->soc = &tegra194_fuse_soc;
+			break;
+#endif
+#if defined(CONFIG_ARCH_TEGRA_234_SOC)
+		case TEGRA234:
+			fuse->soc = &tegra234_fuse_soc;
+			break;
+#endif
+#if defined(CONFIG_ARCH_TEGRA_241_SOC)
+		case TEGRA241:
+			fuse->soc = &tegra241_fuse_soc;
+			break;
+#endif
+		default:
+			return dev_err_probe(&pdev->dev, -EINVAL, "Unsupported SoC: %02x\n", chip);
+		}
+
+		fuse->soc->init(fuse);
+		tegra_fuse_print_sku_info(&tegra_sku_info);
+		tegra_soc_device_register();
+
+		err = tegra_fuse_add_lookups(fuse);
+		if (err)
+			return dev_err_probe(&pdev->dev, err, "failed to add FUSE lookups\n");
 	}
 
+	fuse->clk = devm_clk_get_optional(&pdev->dev, "fuse");
+	if (IS_ERR(fuse->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(fuse->clk), "failed to get FUSE clock\n");
+
 	platform_set_drvdata(pdev, fuse);
 	fuse->dev = &pdev->dev;
 
@@ -179,12 +234,8 @@ static int tegra_fuse_probe(struct platform_device *pdev)
 	}
 
 	fuse->rst = devm_reset_control_get_optional(&pdev->dev, "fuse");
-	if (IS_ERR(fuse->rst)) {
-		err = PTR_ERR(fuse->rst);
-		dev_err(&pdev->dev, "failed to get FUSE reset: %pe\n",
-			fuse->rst);
-		return err;
-	}
+	if (IS_ERR(fuse->rst))
+		return dev_err_probe(&pdev->dev, PTR_ERR(fuse->rst), "failed to get FUSE reset\n");
 
 	/*
 	 * FUSE clock is enabled at a boot time, hence this resume/suspend
@@ -262,10 +313,17 @@ static const struct dev_pm_ops tegra_fuse_pm = {
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_fuse_suspend, tegra_fuse_resume)
 };
 
+static const struct acpi_device_id tegra_fuse_acpi_match[] = {
+	{ "NVDA200F" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(acpi, tegra_fuse_acpi_match);
+
 static struct platform_driver tegra_fuse_driver = {
 	.driver = {
 		.name = "tegra-fuse",
 		.of_match_table = tegra_fuse_match,
+		.acpi_match_table = tegra_fuse_acpi_match,
 		.pm = &tegra_fuse_pm,
 		.suppress_bind_attrs = true,
 	},
@@ -287,7 +345,16 @@ u32 __init tegra_fuse_read_early(unsigned int offset)
 
 int tegra_fuse_readl(unsigned long offset, u32 *value)
 {
-	if (!fuse->read || !fuse->clk)
+	if (!fuse->dev)
+		return -EPROBE_DEFER;
+
+	/*
+	 * Wait for fuse->clk to be initialized if device-tree boot is used.
+	 */
+	if (is_of_node(dev_fwnode(fuse->dev)) && !fuse->clk)
+		return -EPROBE_DEFER;
+
+	if (!fuse->read)
 		return -EPROBE_DEFER;
 
 	if (IS_ERR(fuse->clk))
@@ -343,7 +410,8 @@ const struct attribute_group tegra_soc_attr_group = {
 };
 
 #if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) || \
-    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC)
+    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC) || \
+    IS_ENABLED(CONFIG_ARCH_TEGRA_241_SOC)
 static ssize_t platform_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
@@ -370,7 +438,7 @@ const struct attribute_group tegra194_soc_attr_group = {
 };
 #endif
 
-struct device * __init tegra_soc_device_register(void)
+struct device *tegra_soc_device_register(void)
 {
 	struct soc_device_attribute *attr;
 	struct soc_device *dev;
@@ -407,6 +475,7 @@ static int __init tegra_init_fuse(void)
 	const struct of_device_id *match;
 	struct device_node *np;
 	struct resource regs;
+	int err;
 
 	tegra_init_apbmisc();
 
@@ -497,22 +566,13 @@ static int __init tegra_init_fuse(void)
 
 	fuse->soc->init(fuse);
 
-	pr_info("Tegra Revision: %s SKU: %d CPU Process: %d SoC Process: %d\n",
-		tegra_revision_name[tegra_sku_info.revision],
-		tegra_sku_info.sku_id, tegra_sku_info.cpu_process_id,
-		tegra_sku_info.soc_process_id);
-	pr_debug("Tegra CPU Speedo ID %d, SoC Speedo ID %d\n",
-		 tegra_sku_info.cpu_speedo_id, tegra_sku_info.soc_speedo_id);
+	tegra_fuse_print_sku_info(&tegra_sku_info);
 
-	if (fuse->soc->lookups) {
-		size_t size = sizeof(*fuse->lookups) * fuse->soc->num_lookups;
-
-		fuse->lookups = kmemdup(fuse->soc->lookups, size, GFP_KERNEL);
-		if (fuse->lookups)
-			nvmem_add_cell_lookups(fuse->lookups, fuse->soc->num_lookups);
-	}
+	err = tegra_fuse_add_lookups(fuse);
+	if (err)
+		pr_err("failed to add FUSE lookups\n");
 
-	return 0;
+	return err;
 }
 early_initcall(tegra_init_fuse);
 
diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c
index e94d46372a63..eb14e5ff5a0a 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra30.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra30.c
@@ -38,7 +38,8 @@
     defined(CONFIG_ARCH_TEGRA_210_SOC) || \
     defined(CONFIG_ARCH_TEGRA_186_SOC) || \
     defined(CONFIG_ARCH_TEGRA_194_SOC) || \
-    defined(CONFIG_ARCH_TEGRA_234_SOC)
+    defined(CONFIG_ARCH_TEGRA_234_SOC) || \
+    defined(CONFIG_ARCH_TEGRA_241_SOC)
 static u32 tegra30_fuse_read_early(struct tegra_fuse *fuse, unsigned int offset)
 {
 	if (WARN_ON(!fuse->base))
@@ -678,3 +679,23 @@ const struct tegra_fuse_soc tegra234_fuse_soc = {
 	.clk_suspend_on = false,
 };
 #endif
+
+#if defined(CONFIG_ARCH_TEGRA_241_SOC)
+static const struct tegra_fuse_info tegra241_fuse_info = {
+	.read = tegra30_fuse_read,
+	.size = 0x16008,
+	.spare = 0xcf0,
+};
+
+static const struct nvmem_keepout tegra241_fuse_keepouts[] = {
+	{ .start = 0xc, .end = 0x1600c }
+};
+
+const struct tegra_fuse_soc tegra241_fuse_soc = {
+	.init = tegra30_fuse_init,
+	.info = &tegra241_fuse_info,
+	.keepouts = tegra241_fuse_keepouts,
+	.num_keepouts = ARRAY_SIZE(tegra241_fuse_keepouts),
+	.soc_attr_group = &tegra194_soc_attr_group,
+};
+#endif
diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h
index 90f23be73894..9fee6ad6ad9e 100644
--- a/drivers/soc/tegra/fuse/fuse.h
+++ b/drivers/soc/tegra/fuse/fuse.h
@@ -69,6 +69,7 @@ struct tegra_fuse {
 
 void tegra_init_revision(void);
 void tegra_init_apbmisc(void);
+void tegra_acpi_init_apbmisc(void);
 
 u32 __init tegra_fuse_read_spare(unsigned int spare);
 u32 __init tegra_fuse_read_early(unsigned int offset);
@@ -123,7 +124,8 @@ extern const struct tegra_fuse_soc tegra186_fuse_soc;
 #endif
 
 #if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) || \
-    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC)
+    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC) || \
+    IS_ENABLED(CONFIG_ARCH_TEGRA_241_SOC)
 extern const struct attribute_group tegra194_soc_attr_group;
 #endif
 
@@ -135,4 +137,8 @@ extern const struct tegra_fuse_soc tegra194_fuse_soc;
 extern const struct tegra_fuse_soc tegra234_fuse_soc;
 #endif
 
+#ifdef CONFIG_ARCH_TEGRA_241_SOC
+extern const struct tegra_fuse_soc tegra241_fuse_soc;
+#endif
+
 #endif
diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c
index da970f3dbf35..e2ca5d55fd31 100644
--- a/drivers/soc/tegra/fuse/tegra-apbmisc.c
+++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c
@@ -3,9 +3,11 @@
  * Copyright (c) 2014-2023, NVIDIA CORPORATION.  All rights reserved.
  */
 
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
@@ -62,6 +64,7 @@ bool tegra_is_silicon(void)
 	switch (tegra_get_chip_id()) {
 	case TEGRA194:
 	case TEGRA234:
+	case TEGRA241:
 	case TEGRA264:
 		if (tegra_get_platform() == 0)
 			return true;
@@ -160,9 +163,34 @@ void __init tegra_init_revision(void)
 	tegra_sku_info.platform = tegra_get_platform();
 }
 
-void __init tegra_init_apbmisc(void)
+static void tegra_init_apbmisc_resources(struct resource *apbmisc,
+					 struct resource *straps)
 {
 	void __iomem *strapping_base;
+
+	apbmisc_base = ioremap(apbmisc->start, resource_size(apbmisc));
+	if (apbmisc_base)
+		chipid = readl_relaxed(apbmisc_base + 4);
+	else
+		pr_err("failed to map APBMISC registers\n");
+
+	strapping_base = ioremap(straps->start, resource_size(straps));
+	if (strapping_base) {
+		strapping = readl_relaxed(strapping_base);
+		iounmap(strapping_base);
+	} else {
+		pr_err("failed to map strapping options registers\n");
+	}
+}
+
+/**
+ * tegra_init_apbmisc - Initializes Tegra APBMISC and Strapping registers.
+ *
+ * This is called during early init as some of the old 32-bit ARM code needs
+ * information from the APBMISC registers very early during boot.
+ */
+void __init tegra_init_apbmisc(void)
+{
 	struct resource apbmisc, straps;
 	struct device_node *np;
 
@@ -219,23 +247,73 @@ void __init tegra_init_apbmisc(void)
 		}
 	}
 
-	apbmisc_base = ioremap(apbmisc.start, resource_size(&apbmisc));
-	if (!apbmisc_base) {
-		pr_err("failed to map APBMISC registers\n");
-	} else {
-		chipid = readl_relaxed(apbmisc_base + 4);
+	tegra_init_apbmisc_resources(&apbmisc, &straps);
+	long_ram_code = of_property_read_bool(np, "nvidia,long-ram-code");
+
+put:
+	of_node_put(np);
+}
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id apbmisc_acpi_match[] = {
+	{ "NVDA2010" },
+	{ /* sentinel */ }
+};
+
+void tegra_acpi_init_apbmisc(void)
+{
+	struct resource *resources[2] = { NULL };
+	struct resource_entry *rentry;
+	struct acpi_device *adev = NULL;
+	struct list_head resource_list;
+	int rcount = 0;
+	int ret;
+
+	adev = acpi_dev_get_first_match_dev(apbmisc_acpi_match[0].id, NULL, -1);
+	if (!adev)
+		return;
+
+	INIT_LIST_HEAD(&resource_list);
+
+	ret = acpi_dev_get_memory_resources(adev, &resource_list);
+	if (ret < 0) {
+		pr_err("failed to get APBMISC memory resources");
+		goto out_put_acpi_dev;
 	}
 
-	strapping_base = ioremap(straps.start, resource_size(&straps));
-	if (!strapping_base) {
-		pr_err("failed to map strapping options registers\n");
-	} else {
-		strapping = readl_relaxed(strapping_base);
-		iounmap(strapping_base);
+	/*
+	 * Get required memory resources.
+	 *
+	 * resources[0]: apbmisc.
+	 * resources[1]: straps.
+	 */
+	resource_list_for_each_entry(rentry, &resource_list) {
+		if (rcount >= ARRAY_SIZE(resources))
+			break;
+
+		resources[rcount++] = rentry->res;
 	}
 
-	long_ram_code = of_property_read_bool(np, "nvidia,long-ram-code");
+	if (!resources[0]) {
+		pr_err("failed to get APBMISC registers\n");
+		goto out_free_resource_list;
+	}
 
-put:
-	of_node_put(np);
+	if (!resources[1]) {
+		pr_err("failed to get strapping options registers\n");
+		goto out_free_resource_list;
+	}
+
+	tegra_init_apbmisc_resources(resources[0], resources[1]);
+
+out_free_resource_list:
+	acpi_dev_free_resource_list(&resource_list);
+
+out_put_acpi_dev:
+	acpi_dev_put(adev);
+}
+#else
+void tegra_acpi_init_apbmisc(void)
+{
 }
+#endif
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index f432aa022ace..d6bfcea5ee65 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -3,7 +3,7 @@
  * drivers/soc/tegra/pmc.c
  *
  * Copyright (c) 2010 Google, Inc
- * Copyright (c) 2018-2023, NVIDIA CORPORATION. All rights reserved.
+ * Copyright (c) 2018-2024, NVIDIA CORPORATION. All rights reserved.
  *
  * Author:
  *	Colin Cross <ccross@google.com>
@@ -384,6 +384,7 @@ struct tegra_pmc_soc {
 	bool has_blink_output;
 	bool has_usb_sleepwalk;
 	bool supports_core_domain;
+	bool has_single_mmio_aperture;
 };
 
 /**
@@ -1777,30 +1778,6 @@ static int tegra_io_pad_get_voltage(struct tegra_pmc *pmc, enum tegra_io_pad id)
 	return TEGRA_IO_PAD_VOLTAGE_3V3;
 }
 
-/**
- * tegra_io_rail_power_on() - enable power to I/O rail
- * @id: Tegra I/O pad ID for which to enable power
- *
- * See also: tegra_io_pad_power_enable()
- */
-int tegra_io_rail_power_on(unsigned int id)
-{
-	return tegra_io_pad_power_enable(id);
-}
-EXPORT_SYMBOL(tegra_io_rail_power_on);
-
-/**
- * tegra_io_rail_power_off() - disable power to I/O rail
- * @id: Tegra I/O pad ID for which to disable power
- *
- * See also: tegra_io_pad_power_disable()
- */
-int tegra_io_rail_power_off(unsigned int id)
-{
-	return tegra_io_pad_power_disable(id);
-}
-EXPORT_SYMBOL(tegra_io_rail_power_off);
-
 #ifdef CONFIG_PM_SLEEP
 enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void)
 {
@@ -2909,31 +2886,33 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "wake");
-	if (res) {
+	if (pmc->soc->has_single_mmio_aperture) {
+		pmc->wake = base;
+		pmc->aotag = base;
+		pmc->scratch = base;
+	} else {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						"wake");
 		pmc->wake = devm_ioremap_resource(&pdev->dev, res);
 		if (IS_ERR(pmc->wake))
 			return PTR_ERR(pmc->wake);
-	} else {
-		pmc->wake = base;
-	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "aotag");
-	if (res) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						"aotag");
 		pmc->aotag = devm_ioremap_resource(&pdev->dev, res);
 		if (IS_ERR(pmc->aotag))
 			return PTR_ERR(pmc->aotag);
-	} else {
-		pmc->aotag = base;
-	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "scratch");
-	if (res) {
-		pmc->scratch = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(pmc->scratch))
-			return PTR_ERR(pmc->scratch);
-	} else {
-		pmc->scratch = base;
+		/* "scratch" is an optional aperture */
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						"scratch");
+		if (res) {
+			pmc->scratch = devm_ioremap_resource(&pdev->dev, res);
+			if (IS_ERR(pmc->scratch))
+				return PTR_ERR(pmc->scratch);
+		} else {
+			pmc->scratch = NULL;
+		}
 	}
 
 	pmc->clk = devm_clk_get_optional(&pdev->dev, "pclk");
@@ -2945,12 +2924,15 @@ static int tegra_pmc_probe(struct platform_device *pdev)
 	 * PMC should be last resort for restarting since it soft-resets
 	 * CPU without resetting everything else.
 	 */
-	err = devm_register_reboot_notifier(&pdev->dev,
-					    &tegra_pmc_reboot_notifier);
-	if (err) {
-		dev_err(&pdev->dev, "unable to register reboot notifier, %d\n",
-			err);
-		return err;
+	if (pmc->scratch) {
+		err = devm_register_reboot_notifier(&pdev->dev,
+						    &tegra_pmc_reboot_notifier);
+		if (err) {
+			dev_err(&pdev->dev,
+				"unable to register reboot notifier, %d\n",
+				err);
+			return err;
+		}
 	}
 
 	err = devm_register_sys_off_handler(&pdev->dev,
@@ -3324,6 +3306,7 @@ static const struct tegra_pmc_soc tegra20_pmc_soc = {
 	.num_pmc_clks = 0,
 	.has_blink_output = true,
 	.has_usb_sleepwalk = true,
+	.has_single_mmio_aperture = true,
 };
 
 static const char * const tegra30_powergates[] = {
@@ -3385,6 +3368,7 @@ static const struct tegra_pmc_soc tegra30_pmc_soc = {
 	.num_pmc_clks = ARRAY_SIZE(tegra_pmc_clks_data),
 	.has_blink_output = true,
 	.has_usb_sleepwalk = true,
+	.has_single_mmio_aperture = true,
 };
 
 static const char * const tegra114_powergates[] = {
@@ -3442,6 +3426,7 @@ static const struct tegra_pmc_soc tegra114_pmc_soc = {
 	.num_pmc_clks = ARRAY_SIZE(tegra_pmc_clks_data),
 	.has_blink_output = true,
 	.has_usb_sleepwalk = true,
+	.has_single_mmio_aperture = true,
 };
 
 static const char * const tegra124_powergates[] = {
@@ -3586,6 +3571,7 @@ static const struct tegra_pmc_soc tegra124_pmc_soc = {
 	.num_pmc_clks = ARRAY_SIZE(tegra_pmc_clks_data),
 	.has_blink_output = true,
 	.has_usb_sleepwalk = true,
+	.has_single_mmio_aperture = true,
 };
 
 static const char * const tegra210_powergates[] = {
@@ -3749,6 +3735,7 @@ static const struct tegra_pmc_soc tegra210_pmc_soc = {
 	.num_pmc_clks = ARRAY_SIZE(tegra_pmc_clks_data),
 	.has_blink_output = true,
 	.has_usb_sleepwalk = true,
+	.has_single_mmio_aperture = true,
 };
 
 static const struct tegra_io_pad_soc tegra186_io_pads[] = {
@@ -3946,6 +3933,7 @@ static const struct tegra_pmc_soc tegra186_pmc_soc = {
 	.num_pmc_clks = 0,
 	.has_blink_output = false,
 	.has_usb_sleepwalk = false,
+	.has_single_mmio_aperture = false,
 };
 
 static const struct tegra_io_pad_soc tegra194_io_pads[] = {
@@ -4131,6 +4119,7 @@ static const struct tegra_pmc_soc tegra194_pmc_soc = {
 	.num_pmc_clks = 0,
 	.has_blink_output = false,
 	.has_usb_sleepwalk = false,
+	.has_single_mmio_aperture = false,
 };
 
 static const struct tegra_io_pad_soc tegra234_io_pads[] = {
@@ -4220,6 +4209,7 @@ static const char * const tegra234_reset_sources[] = {
 };
 
 static const struct tegra_wake_event tegra234_wake_events[] = {
+	TEGRA_WAKE_GPIO("sd-wake", 8, 0, TEGRA234_MAIN_GPIO(G, 7)),
 	TEGRA_WAKE_IRQ("pmu", 24, 209),
 	TEGRA_WAKE_GPIO("power", 29, 1, TEGRA234_AON_GPIO(EE, 4)),
 	TEGRA_WAKE_GPIO("mgbe", 56, 0, TEGRA234_MAIN_GPIO(Y, 3)),
@@ -4259,6 +4249,7 @@ static const struct tegra_pmc_soc tegra234_pmc_soc = {
 	.pmc_clks_data = NULL,
 	.num_pmc_clks = 0,
 	.has_blink_output = false,
+	.has_single_mmio_aperture = false,
 };
 
 static const struct of_device_id tegra_pmc_match[] = {
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index f94e0d370d46..1a8d03958dff 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1927,24 +1927,18 @@ static void cqspi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 }
 
-static int cqspi_suspend(struct device *dev)
+static int cqspi_runtime_suspend(struct device *dev)
 {
 	struct cqspi_st *cqspi = dev_get_drvdata(dev);
-	struct spi_controller *host = dev_get_drvdata(dev);
-	int ret;
 
-	ret = spi_controller_suspend(host);
 	cqspi_controller_enable(cqspi, 0);
-
 	clk_disable_unprepare(cqspi->clk);
-
-	return ret;
+	return 0;
 }
 
-static int cqspi_resume(struct device *dev)
+static int cqspi_runtime_resume(struct device *dev)
 {
 	struct cqspi_st *cqspi = dev_get_drvdata(dev);
-	struct spi_controller *host = dev_get_drvdata(dev);
 
 	clk_prepare_enable(cqspi->clk);
 	cqspi_wait_idle(cqspi);
@@ -1952,12 +1946,27 @@ static int cqspi_resume(struct device *dev)
 
 	cqspi->current_cs = -1;
 	cqspi->sclk = 0;
+	return 0;
+}
+
+static int cqspi_suspend(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	return spi_controller_suspend(cqspi->host);
+}
 
-	return spi_controller_resume(host);
+static int cqspi_resume(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	return spi_controller_resume(cqspi->host);
 }
 
-static DEFINE_RUNTIME_DEV_PM_OPS(cqspi_dev_pm_ops, cqspi_suspend,
-				 cqspi_resume, NULL);
+static const struct dev_pm_ops cqspi_dev_pm_ops = {
+	RUNTIME_PM_OPS(cqspi_runtime_suspend, cqspi_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(cqspi_suspend, cqspi_resume)
+};
 
 static const struct cqspi_driver_platdata cdns_qspi = {
 	.quirks = CQSPI_DISABLE_DAC_MODE,
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index b24190526ce9..adf19e8c4c8a 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -148,8 +148,7 @@ static void cs42l43_set_cs(struct spi_device *spi, bool is_high)
 {
 	struct cs42l43_spi *priv = spi_controller_get_devdata(spi->controller);
 
-	if (spi_get_chipselect(spi, 0) == 0)
-		regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high);
+	regmap_write(priv->regmap, CS42L43_SPI_CONFIG2, !is_high);
 }
 
 static int cs42l43_prepare_message(struct spi_controller *ctlr, struct spi_message *msg)
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 546cdce525fc..833a1bb7a914 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -2,6 +2,7 @@
 // Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
 // Copyright (C) 2008 Juergen Beisert
 
+#include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -660,15 +661,15 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
 			<< MX51_ECSPI_CTRL_BL_OFFSET;
 	else {
 		if (spi_imx->usedma) {
-			ctrl |= (spi_imx->bits_per_word *
-				spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1)
+			ctrl |= (spi_imx->bits_per_word - 1)
 				<< MX51_ECSPI_CTRL_BL_OFFSET;
 		} else {
 			if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST)
-				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1)
+				ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1)
 						<< MX51_ECSPI_CTRL_BL_OFFSET;
 			else
-				ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+				ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word,
+						BITS_PER_BYTE) * spi_imx->bits_per_word
 						<< MX51_ECSPI_CTRL_BL_OFFSET;
 		}
 	}
diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index 07d20ca1164c..4337ca51d7aa 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -85,6 +85,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa2a4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 1bf080339b5a..88cbe4f00cc3 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -39,6 +39,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/mxs-spi.h>
 #include <trace/events/spi.h>
+#include <linux/dma/mxs-dma.h>
 
 #define DRIVER_NAME		"mxs-spi"
 
@@ -252,7 +253,7 @@ static int mxs_spi_txrx_dma(struct mxs_spi *spi,
 		desc = dmaengine_prep_slave_sg(ssp->dmach,
 				&dma_xfer[sg_count].sg, 1,
 				(flags & TXRX_WRITE) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+				DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END);
 
 		if (!desc) {
 			dev_err(ssp->dev,
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index a0c9fea908f5..ddf1c684bcc7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -53,8 +53,6 @@
 
 /* per-register bitmasks: */
 #define OMAP2_MCSPI_IRQSTATUS_EOW	BIT(17)
-#define OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY    BIT(0)
-#define OMAP2_MCSPI_IRQSTATUS_RX0_FULL    BIT(2)
 
 #define OMAP2_MCSPI_MODULCTRL_SINGLE	BIT(0)
 #define OMAP2_MCSPI_MODULCTRL_MS	BIT(2)
@@ -293,7 +291,7 @@ static void omap2_mcspi_set_mode(struct spi_controller *ctlr)
 }
 
 static void omap2_mcspi_set_fifo(const struct spi_device *spi,
-				struct spi_transfer *t, int enable, int dma_enabled)
+				struct spi_transfer *t, int enable)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct omap2_mcspi_cs *cs = spi->controller_state;
@@ -314,28 +312,20 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi,
 			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH / 2;
 		else
 			max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH;
-		if (dma_enabled)
-			wcnt = t->len / bytes_per_word;
-		else
-			wcnt = 0;
+
+		wcnt = t->len / bytes_per_word;
 		if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT)
 			goto disable_fifo;
 
 		xferlevel = wcnt << 16;
 		if (t->rx_buf != NULL) {
 			chconf |= OMAP2_MCSPI_CHCONF_FFER;
-			if (dma_enabled)
-				xferlevel |= (bytes_per_word - 1) << 8;
-			else
-				xferlevel |= (max_fifo_depth - 1) << 8;
+			xferlevel |= (bytes_per_word - 1) << 8;
 		}
 
 		if (t->tx_buf != NULL) {
 			chconf |= OMAP2_MCSPI_CHCONF_FFET;
-			if (dma_enabled)
-				xferlevel |= bytes_per_word - 1;
-			else
-				xferlevel |= (max_fifo_depth - 1);
+			xferlevel |= bytes_per_word - 1;
 		}
 
 		mcspi_write_reg(ctlr, OMAP2_MCSPI_XFERLEVEL, xferlevel);
@@ -892,113 +882,6 @@ out:
 	return count - c;
 }
 
-static unsigned
-omap2_mcspi_txrx_piofifo(struct spi_device *spi, struct spi_transfer *xfer)
-{
-	struct omap2_mcspi_cs	*cs = spi->controller_state;
-	struct omap2_mcspi    *mcspi;
-	unsigned int		count, c;
-	unsigned int		iter, cwc;
-	int last_request;
-	void __iomem		*base = cs->base;
-	void __iomem		*tx_reg;
-	void __iomem		*rx_reg;
-	void __iomem		*chstat_reg;
-	void __iomem        *irqstat_reg;
-	int			word_len, bytes_per_word;
-	u8		*rx;
-	const u8	*tx;
-
-	mcspi = spi_controller_get_devdata(spi->controller);
-	count = xfer->len;
-	c = count;
-	word_len = cs->word_len;
-	bytes_per_word = mcspi_bytes_per_word(word_len);
-
-	/*
-	 * We store the pre-calculated register addresses on stack to speed
-	 * up the transfer loop.
-	 */
-	tx_reg		= base + OMAP2_MCSPI_TX0;
-	rx_reg		= base + OMAP2_MCSPI_RX0;
-	chstat_reg	= base + OMAP2_MCSPI_CHSTAT0;
-	irqstat_reg    = base + OMAP2_MCSPI_IRQSTATUS;
-
-	if (c < (word_len >> 3))
-		return 0;
-
-	rx = xfer->rx_buf;
-	tx = xfer->tx_buf;
-
-	do {
-		/* calculate number of words in current iteration */
-		cwc = min((unsigned int)mcspi->fifo_depth / bytes_per_word,
-			  c / bytes_per_word);
-		last_request = cwc != (mcspi->fifo_depth / bytes_per_word);
-		if (tx) {
-			if (mcspi_wait_for_reg_bit(irqstat_reg,
-						   OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY) < 0) {
-				dev_err(&spi->dev, "TX Empty timed out\n");
-				goto out;
-			}
-			writel_relaxed(OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY, irqstat_reg);
-
-			for (iter = 0; iter < cwc; iter++, tx += bytes_per_word) {
-				if (bytes_per_word == 1)
-					writel_relaxed(*tx, tx_reg);
-				else if (bytes_per_word == 2)
-					writel_relaxed(*((u16 *)tx), tx_reg);
-				else if (bytes_per_word == 4)
-					writel_relaxed(*((u32 *)tx), tx_reg);
-			}
-		}
-
-		if (rx) {
-			if (!last_request &&
-			    mcspi_wait_for_reg_bit(irqstat_reg,
-						   OMAP2_MCSPI_IRQSTATUS_RX0_FULL) < 0) {
-				dev_err(&spi->dev, "RX_FULL timed out\n");
-				goto out;
-			}
-			writel_relaxed(OMAP2_MCSPI_IRQSTATUS_RX0_FULL, irqstat_reg);
-
-			for (iter = 0; iter < cwc; iter++, rx += bytes_per_word) {
-				if (last_request &&
-				    mcspi_wait_for_reg_bit(chstat_reg,
-							   OMAP2_MCSPI_CHSTAT_RXS) < 0) {
-					dev_err(&spi->dev, "RXS timed out\n");
-					goto out;
-				}
-				if (bytes_per_word == 1)
-					*rx = readl_relaxed(rx_reg);
-				else if (bytes_per_word == 2)
-					*((u16 *)rx) = readl_relaxed(rx_reg);
-				else if (bytes_per_word == 4)
-					*((u32 *)rx) = readl_relaxed(rx_reg);
-			}
-		}
-
-		if (last_request) {
-			if (mcspi_wait_for_reg_bit(chstat_reg,
-						   OMAP2_MCSPI_CHSTAT_EOT) < 0) {
-				dev_err(&spi->dev, "EOT timed out\n");
-				goto out;
-			}
-			if (mcspi_wait_for_reg_bit(chstat_reg,
-						   OMAP2_MCSPI_CHSTAT_TXFFE) < 0) {
-				dev_err(&spi->dev, "TXFFE timed out\n");
-				goto out;
-			}
-			omap2_mcspi_set_enable(spi, 0);
-		}
-		c -= cwc * bytes_per_word;
-	} while (c >= bytes_per_word);
-
-out:
-	omap2_mcspi_set_enable(spi, 1);
-	return count - c;
-}
-
 static u32 omap2_mcspi_calc_divisor(u32 speed_hz, u32 ref_clk_hz)
 {
 	u32 div;
@@ -1323,9 +1206,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
 		    ctlr->cur_msg_mapped &&
 		    ctlr->can_dma(ctlr, spi, t))
-			omap2_mcspi_set_fifo(spi, t, 1, 1);
-		else if (t->len > OMAP2_MCSPI_MAX_FIFODEPTH)
-			omap2_mcspi_set_fifo(spi, t, 1, 0);
+			omap2_mcspi_set_fifo(spi, t, 1);
 
 		omap2_mcspi_set_enable(spi, 1);
 
@@ -1338,8 +1219,6 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 		    ctlr->cur_msg_mapped &&
 		    ctlr->can_dma(ctlr, spi, t))
 			count = omap2_mcspi_txrx_dma(spi, t);
-		else if (mcspi->fifo_depth > 0)
-			count = omap2_mcspi_txrx_piofifo(spi, t);
 		else
 			count = omap2_mcspi_txrx_pio(spi, t);
 
@@ -1352,7 +1231,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 	omap2_mcspi_set_enable(spi, 0);
 
 	if (mcspi->fifo_depth > 0)
-		omap2_mcspi_set_fifo(spi, t, 0, 0);
+		omap2_mcspi_set_fifo(spi, t, 0);
 
 out:
 	/* Restore defaults if they were overriden */
@@ -1375,7 +1254,7 @@ out:
 		omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH));
 
 	if (mcspi->fifo_depth > 0 && t)
-		omap2_mcspi_set_fifo(spi, t, 0, 0);
+		omap2_mcspi_set_fifo(spi, t, 0);
 
 	return status;
 }
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 03aab661be9d..82d6264841fc 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -25,11 +25,13 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
+#include <linux/platform_device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/platform_device.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
@@ -166,10 +168,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
 	int scr;
 	u8 cdm = 0;
 	u32 speed;
-	u8 bits_per_word;
 
 	/* Start with the generic configuration for this device. */
-	bits_per_word = spi->bits_per_word;
 	speed = spi->max_speed_hz;
 
 	/*
@@ -177,9 +177,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
 	 * the transfer to overwrite the generic configuration with zeros.
 	 */
 	if (t) {
-		if (t->bits_per_word)
-			bits_per_word = t->bits_per_word;
-
 		if (t->speed_hz)
 			speed = min(t->speed_hz, spi->max_speed_hz);
 	}
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index cfc3b1ddbd22..6f12e4fb2e2e 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -136,14 +136,14 @@ struct sh_msiof_spi_priv {
 
 /* SIFCTR */
 #define SIFCTR_TFWM_MASK	GENMASK(31, 29)	/* Transmit FIFO Watermark */
-#define SIFCTR_TFWM_64		(0 << 29)	/*  Transfer Request when 64 empty stages */
-#define SIFCTR_TFWM_32		(1 << 29)	/*  Transfer Request when 32 empty stages */
-#define SIFCTR_TFWM_24		(2 << 29)	/*  Transfer Request when 24 empty stages */
-#define SIFCTR_TFWM_16		(3 << 29)	/*  Transfer Request when 16 empty stages */
-#define SIFCTR_TFWM_12		(4 << 29)	/*  Transfer Request when 12 empty stages */
-#define SIFCTR_TFWM_8		(5 << 29)	/*  Transfer Request when 8 empty stages */
-#define SIFCTR_TFWM_4		(6 << 29)	/*  Transfer Request when 4 empty stages */
-#define SIFCTR_TFWM_1		(7 << 29)	/*  Transfer Request when 1 empty stage */
+#define SIFCTR_TFWM_64		(0UL << 29)	/*  Transfer Request when 64 empty stages */
+#define SIFCTR_TFWM_32		(1UL << 29)	/*  Transfer Request when 32 empty stages */
+#define SIFCTR_TFWM_24		(2UL << 29)	/*  Transfer Request when 24 empty stages */
+#define SIFCTR_TFWM_16		(3UL << 29)	/*  Transfer Request when 16 empty stages */
+#define SIFCTR_TFWM_12		(4UL << 29)	/*  Transfer Request when 12 empty stages */
+#define SIFCTR_TFWM_8		(5UL << 29)	/*  Transfer Request when 8 empty stages */
+#define SIFCTR_TFWM_4		(6UL << 29)	/*  Transfer Request when 4 empty stages */
+#define SIFCTR_TFWM_1		(7UL << 29)	/*  Transfer Request when 1 empty stage */
 #define SIFCTR_TFUA_MASK	GENMASK(26, 20) /* Transmit FIFO Usable Area */
 #define SIFCTR_TFUA_SHIFT	20
 #define SIFCTR_TFUA(i)		((i) << SIFCTR_TFUA_SHIFT)
diff --git a/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt b/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
index b1f9474f36d5..f34a95611645 100644
--- a/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
+++ b/drivers/staging/fieldbus/Documentation/devicetree/bindings/fieldbus/arcx,anybus-controller.txt
@@ -48,7 +48,7 @@ Example of usage:
 -----------------
 
 This example places the bridge on top of the i.MX WEIM parallel bus, see:
-Documentation/devicetree/bindings/bus/imx-weim.txt
+Documentation/devicetree/bindings/memory-controllers/fsl/fsl,imx-weim.yaml
 
 &weim {
 	controller@0,0 {
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index e748a5d04e97..9149d41fe65b 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work)
 		struct ad5933_state, work.work);
 	struct iio_dev *indio_dev = i2c_get_clientdata(st->client);
 	__be16 buf[2];
-	int val[2];
+	u16 val[2];
 	unsigned char status;
 	int ret;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index f44e6412f4e3..d0db2efe0045 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -3723,12 +3723,10 @@ apply_min_padding:
 
 static int atomisp_set_crop(struct atomisp_device *isp,
 			    const struct v4l2_mbus_framefmt *format,
+			    struct v4l2_subdev_state *sd_state,
 			    int which)
 {
 	struct atomisp_input_subdev *input = &isp->inputs[isp->asd.input_curr];
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_selection sel = {
 		.which = which,
 		.target = V4L2_SEL_TGT_CROP,
@@ -3754,7 +3752,7 @@ static int atomisp_set_crop(struct atomisp_device *isp,
 	sel.r.left = ((input->native_rect.width - sel.r.width) / 2) & ~1;
 	sel.r.top = ((input->native_rect.height - sel.r.height) / 2) & ~1;
 
-	ret = v4l2_subdev_call(input->camera, pad, set_selection, &pad_state, &sel);
+	ret = v4l2_subdev_call(input->camera, pad, set_selection, sd_state, &sel);
 	if (ret)
 		dev_err(isp->dev, "Error setting crop to %ux%u @%ux%u: %d\n",
 			sel.r.width, sel.r.height, sel.r.left, sel.r.top, ret);
@@ -3770,9 +3768,6 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
 	const struct atomisp_format_bridge *fmt, *snr_fmt;
 	struct atomisp_sub_device *asd = &isp->asd;
 	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -3809,11 +3804,16 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
 	dev_dbg(isp->dev, "try_mbus_fmt: asking for %ux%u\n",
 		format.format.width, format.format.height);
 
-	ret = atomisp_set_crop(isp, &format.format, V4L2_SUBDEV_FORMAT_TRY);
-	if (ret)
-		return ret;
+	v4l2_subdev_lock_state(input->try_sd_state);
+
+	ret = atomisp_set_crop(isp, &format.format, input->try_sd_state,
+			       V4L2_SUBDEV_FORMAT_TRY);
+	if (ret == 0)
+		ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+				       input->try_sd_state, &format);
+
+	v4l2_subdev_unlock_state(input->try_sd_state);
 
-	ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &format);
 	if (ret)
 		return ret;
 
@@ -4238,9 +4238,7 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 	struct atomisp_device *isp = asd->isp;
 	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	const struct atomisp_format_bridge *format;
-	struct v4l2_subdev_state pad_state = {
-		.pads = &input->pad_cfg,
-	};
+	struct v4l2_subdev_state *act_sd_state;
 	struct v4l2_subdev_format vformat = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -4268,12 +4266,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 
 	/* Disable dvs if resolution can't be supported by sensor */
 	if (asd->params.video_dis_en && asd->run_mode->val == ATOMISP_RUN_MODE_VIDEO) {
-		ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_TRY);
-		if (ret)
-			return ret;
+		v4l2_subdev_lock_state(input->try_sd_state);
+
+		ret = atomisp_set_crop(isp, &vformat.format, input->try_sd_state,
+				       V4L2_SUBDEV_FORMAT_TRY);
+		if (ret == 0) {
+			vformat.which = V4L2_SUBDEV_FORMAT_TRY;
+			ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+					       input->try_sd_state, &vformat);
+		}
+
+		v4l2_subdev_unlock_state(input->try_sd_state);
 
-		vformat.which = V4L2_SUBDEV_FORMAT_TRY;
-		ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &vformat);
 		if (ret)
 			return ret;
 
@@ -4291,12 +4295,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
 		}
 	}
 
-	ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_ACTIVE);
-	if (ret)
-		return ret;
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
+	ret = atomisp_set_crop(isp, &vformat.format, act_sd_state,
+			       V4L2_SUBDEV_FORMAT_ACTIVE);
+	if (ret == 0) {
+		vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+		ret = v4l2_subdev_call(input->camera, pad, set_fmt, act_sd_state, &vformat);
+	}
+
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 
-	vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	ret = v4l2_subdev_call(input->camera, pad, set_fmt, NULL, &vformat);
 	if (ret)
 		return ret;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_internal.h b/drivers/staging/media/atomisp/pci/atomisp_internal.h
index f7b4bee9574b..d5b077e602ca 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_internal.h
+++ b/drivers/staging/media/atomisp/pci/atomisp_internal.h
@@ -132,8 +132,8 @@ struct atomisp_input_subdev {
 	/* Sensor rects for sensors which support crop */
 	struct v4l2_rect native_rect;
 	struct v4l2_rect active_rect;
-	/* Sensor pad_cfg for which == V4L2_SUBDEV_FORMAT_TRY calls */
-	struct v4l2_subdev_pad_config pad_cfg;
+	/* Sensor state for which == V4L2_SUBDEV_FORMAT_TRY calls */
+	struct v4l2_subdev_state *try_sd_state;
 
 	struct v4l2_subdev *motor;
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
index 01b7fa9b56a2..5b2d88c02d36 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
@@ -781,12 +781,20 @@ static int atomisp_enum_framesizes(struct file *file, void *priv,
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 		.code = input->code,
 	};
+	struct v4l2_subdev_state *act_sd_state;
 	int ret;
 
+	if (!input->camera)
+		return -EINVAL;
+
 	if (input->crop_support)
 		return atomisp_enum_framesizes_crop(isp, fsize);
 
-	ret = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+			       act_sd_state, &fse);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 	if (ret)
 		return ret;
 
@@ -803,18 +811,25 @@ static int atomisp_enum_frameintervals(struct file *file, void *priv,
 	struct video_device *vdev = video_devdata(file);
 	struct atomisp_device *isp = video_get_drvdata(vdev);
 	struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	struct v4l2_subdev_frame_interval_enum fie = {
-		.code	= atomisp_in_fmt_conv[0].code,
+		.code = atomisp_in_fmt_conv[0].code,
 		.index = fival->index,
 		.width = fival->width,
 		.height = fival->height,
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
+	struct v4l2_subdev_state *act_sd_state;
 	int ret;
 
-	ret = v4l2_subdev_call(isp->inputs[asd->input_curr].camera,
-			       pad, enum_frame_interval, NULL,
-			       &fie);
+	if (!input->camera)
+		return -EINVAL;
+
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_frame_interval,
+			       act_sd_state, &fie);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 	if (ret)
 		return ret;
 
@@ -830,30 +845,25 @@ static int atomisp_enum_fmt_cap(struct file *file, void *fh,
 	struct video_device *vdev = video_devdata(file);
 	struct atomisp_device *isp = video_get_drvdata(vdev);
 	struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+	struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
 	struct v4l2_subdev_mbus_code_enum code = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
 	const struct atomisp_format_bridge *format;
-	struct v4l2_subdev *camera;
+	struct v4l2_subdev_state *act_sd_state;
 	unsigned int i, fi = 0;
-	int rval;
+	int ret;
 
-	camera = isp->inputs[asd->input_curr].camera;
-	if(!camera) {
-		dev_err(isp->dev, "%s(): camera is NULL, device is %s\n",
-			__func__, vdev->name);
+	if (!input->camera)
 		return -EINVAL;
-	}
 
-	rval = v4l2_subdev_call(camera, pad, enum_mbus_code, NULL, &code);
-	if (rval == -ENOIOCTLCMD) {
-		dev_warn(isp->dev,
-			 "enum_mbus_code pad op not supported by %s. Please fix your sensor driver!\n",
-			 camera->name);
-	}
-
-	if (rval)
-		return rval;
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+	ret = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+			       act_sd_state, &code);
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < ARRAY_SIZE(atomisp_output_fmts); i++) {
 		format = &atomisp_output_fmts[i];
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index c1c8501ec61f..547e1444ad97 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -862,6 +862,9 @@ static void atomisp_unregister_entities(struct atomisp_device *isp)
 	v4l2_device_unregister(&isp->v4l2_dev);
 	media_device_unregister(&isp->media_dev);
 	media_device_cleanup(&isp->media_dev);
+
+	for (i = 0; i < isp->input_cnt; i++)
+		__v4l2_subdev_state_free(isp->inputs[i].try_sd_state);
 }
 
 static int atomisp_register_entities(struct atomisp_device *isp)
@@ -933,32 +936,49 @@ v4l2_device_failed:
 
 static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 {
+	static struct lock_class_key try_sd_state_key;
 	struct v4l2_subdev_mbus_code_enum mbus_code_enum = { };
 	struct v4l2_subdev_frame_size_enum fse = { };
-	struct v4l2_subdev_state sd_state = {
-		.pads = &input->pad_cfg,
-	};
 	struct v4l2_subdev_selection sel = { };
+	struct v4l2_subdev_state *try_sd_state, *act_sd_state;
 	int i, err;
 
+	/*
+	 * FIXME: Drivers are not supposed to use __v4l2_subdev_state_alloc()
+	 * but atomisp needs this for try_fmt on its /dev/video# node since
+	 * it emulates a normal v4l2 device there, passing through try_fmt /
+	 * set_fmt to the sensor.
+	 */
+	try_sd_state = __v4l2_subdev_state_alloc(input->camera,
+				"atomisp:try_sd_state->lock", &try_sd_state_key);
+	if (IS_ERR(try_sd_state))
+		return;
+
+	input->try_sd_state = try_sd_state;
+
+	act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
 	mbus_code_enum.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-	err = v4l2_subdev_call(input->camera, pad, enum_mbus_code, NULL, &mbus_code_enum);
+	err = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+			       act_sd_state, &mbus_code_enum);
 	if (!err)
 		input->code = mbus_code_enum.code;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_NATIVE_SIZE;
-	err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, get_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	input->native_rect = sel.r;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_CROP_DEFAULT;
-	err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, get_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	input->active_rect = sel.r;
 
@@ -973,7 +993,8 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 		fse.code = input->code;
 		fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 
-		err = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+		err = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+				       act_sd_state, &fse);
 		if (err)
 			break;
 
@@ -989,22 +1010,26 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 	 * for padding, set the crop rect to cover the entire sensor instead
 	 * of only the default active area.
 	 *
-	 * Do this for both try and active formats since the try_crop rect in
-	 * pad_cfg may influence (clamp) future try_fmt calls with which == try.
+	 * Do this for both try and active formats since the crop rect in
+	 * try_sd_state may influence (clamp size) in calls with which == try.
 	 */
 	sel.which = V4L2_SUBDEV_FORMAT_TRY;
 	sel.target = V4L2_SEL_TGT_CROP;
 	sel.r = input->native_rect;
-	err = v4l2_subdev_call(input->camera, pad, set_selection, &sd_state, &sel);
+	v4l2_subdev_lock_state(input->try_sd_state);
+	err = v4l2_subdev_call(input->camera, pad, set_selection,
+			       input->try_sd_state, &sel);
+	v4l2_subdev_unlock_state(input->try_sd_state);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 	sel.target = V4L2_SEL_TGT_CROP;
 	sel.r = input->native_rect;
-	err = v4l2_subdev_call(input->camera, pad, set_selection, NULL, &sel);
+	err = v4l2_subdev_call(input->camera, pad, set_selection,
+			       act_sd_state, &sel);
 	if (err)
-		return;
+		goto unlock_act_sd_state;
 
 	dev_info(input->camera->dev, "Supports crop native %dx%d active %dx%d binning %d\n",
 		 input->native_rect.width, input->native_rect.height,
@@ -1012,6 +1037,10 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
 		 input->binning_support);
 
 	input->crop_support = true;
+
+unlock_act_sd_state:
+	if (act_sd_state)
+		v4l2_subdev_unlock_state(act_sd_state);
 }
 
 int atomisp_register_device_nodes(struct atomisp_device *isp)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index a5f58988130a..c1fbcdd16182 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -759,6 +759,29 @@ static ssize_t emulate_tas_store(struct config_item *item,
 	return count;
 }
 
+static int target_try_configure_unmap(struct se_device *dev,
+				      const char *config_opt)
+{
+	if (!dev->transport->configure_unmap) {
+		pr_err("Generic Block Discard not supported\n");
+		return -ENOSYS;
+	}
+
+	if (!target_dev_configured(dev)) {
+		pr_err("Generic Block Discard setup for %s requires device to be configured\n",
+		       config_opt);
+		return -ENODEV;
+	}
+
+	if (!dev->transport->configure_unmap(dev)) {
+		pr_err("Generic Block Discard setup for %s failed\n",
+		       config_opt);
+		return -ENOSYS;
+	}
+
+	return 0;
+}
+
 static ssize_t emulate_tpu_store(struct config_item *item,
 		const char *page, size_t count)
 {
@@ -776,11 +799,9 @@ static ssize_t emulate_tpu_store(struct config_item *item,
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("Generic Block Discard not supported\n");
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "emulate_tpu");
+		if (ret)
+			return ret;
 	}
 
 	da->emulate_tpu = flag;
@@ -806,11 +827,9 @@ static ssize_t emulate_tpws_store(struct config_item *item,
 	 * Discard supported is detected iblock_create_virtdevice().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("Generic Block Discard not supported\n");
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "emulate_tpws");
+		if (ret)
+			return ret;
 	}
 
 	da->emulate_tpws = flag;
@@ -1022,12 +1041,9 @@ static ssize_t unmap_zeroes_data_store(struct config_item *item,
 	 * Discard supported is detected iblock_configure_device().
 	 */
 	if (flag && !da->max_unmap_block_desc_count) {
-		if (!dev->transport->configure_unmap ||
-		    !dev->transport->configure_unmap(dev)) {
-			pr_err("dev[%p]: Thin Provisioning LBPRZ will not be set because max_unmap_block_desc_count is zero\n",
-			       da->da_dev);
-			return -ENOSYS;
-		}
+		ret = target_try_configure_unmap(dev, "unmap_zeroes_data");
+		if (ret)
+			return ret;
 	}
 	da->unmap_zeroes_data = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 8eb9eb7ce5df..7f6ca8177845 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -91,7 +91,7 @@ static int iblock_configure_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 	struct request_queue *q;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bd;
 	struct blk_integrity *bi;
 	blk_mode_t mode = BLK_OPEN_READ;
@@ -117,14 +117,14 @@ static int iblock_configure_device(struct se_device *dev)
 	else
 		dev->dev_flags |= DF_READ_ONLY;
 
-	bdev_handle = bdev_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev,
+	bdev_file = bdev_file_open_by_path(ib_dev->ibd_udev_path, mode, ib_dev,
 					NULL);
-	if (IS_ERR(bdev_handle)) {
-		ret = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
 		goto out_free_bioset;
 	}
-	ib_dev->ibd_bdev_handle = bdev_handle;
-	ib_dev->ibd_bd = bd = bdev_handle->bdev;
+	ib_dev->ibd_bdev_file = bdev_file;
+	ib_dev->ibd_bd = bd = file_bdev(bdev_file);
 
 	q = bdev_get_queue(bd);
 
@@ -180,7 +180,7 @@ static int iblock_configure_device(struct se_device *dev)
 	return 0;
 
 out_blkdev_put:
-	bdev_release(ib_dev->ibd_bdev_handle);
+	fput(ib_dev->ibd_bdev_file);
 out_free_bioset:
 	bioset_exit(&ib_dev->ibd_bio_set);
 out:
@@ -205,8 +205,8 @@ static void iblock_destroy_device(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 
-	if (ib_dev->ibd_bdev_handle)
-		bdev_release(ib_dev->ibd_bdev_handle);
+	if (ib_dev->ibd_bdev_file)
+		fput(ib_dev->ibd_bdev_file);
 	bioset_exit(&ib_dev->ibd_bio_set);
 }
 
diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h
index 683f9a55945b..91f6f4280666 100644
--- a/drivers/target/target_core_iblock.h
+++ b/drivers/target/target_core_iblock.h
@@ -32,7 +32,7 @@ struct iblock_dev {
 	u32	ibd_flags;
 	struct bio_set	ibd_bio_set;
 	struct block_device *ibd_bd;
-	struct bdev_handle *ibd_bdev_handle;
+	struct file *ibd_bdev_file;
 	bool ibd_readonly;
 	struct iblock_dev_plug *ibd_plug;
 } ____cacheline_aligned;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 41b7489d37ce..f98ebb18666b 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -352,7 +352,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr;
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct Scsi_Host *sh = sd->host;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int ret;
 
 	if (scsi_device_get(sd)) {
@@ -366,18 +366,18 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	 * Claim exclusive struct block_device access to struct scsi_device
 	 * for TYPE_DISK and TYPE_ZBC using supplied udev_path
 	 */
-	bdev_handle = bdev_open_by_path(dev->udev_path,
+	bdev_file = bdev_file_open_by_path(dev->udev_path,
 				BLK_OPEN_WRITE | BLK_OPEN_READ, pdv, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_err("pSCSI: bdev_open_by_path() failed\n");
 		scsi_device_put(sd);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	pdv->pdv_bdev_handle = bdev_handle;
+	pdv->pdv_bdev_file = bdev_file;
 
 	ret = pscsi_add_device_to_list(dev, sd);
 	if (ret) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		scsi_device_put(sd);
 		return ret;
 	}
@@ -564,9 +564,9 @@ static void pscsi_destroy_device(struct se_device *dev)
 		 * from pscsi_create_type_disk()
 		 */
 		if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) &&
-		    pdv->pdv_bdev_handle) {
-			bdev_release(pdv->pdv_bdev_handle);
-			pdv->pdv_bdev_handle = NULL;
+		    pdv->pdv_bdev_file) {
+			fput(pdv->pdv_bdev_file);
+			pdv->pdv_bdev_file = NULL;
 		}
 		/*
 		 * For HBA mode PHV_LLD_SCSI_HOST_NO, release the reference
@@ -907,12 +907,15 @@ new_bio:
 
 	return 0;
 fail:
-	if (bio)
-		bio_put(bio);
+	if (bio) {
+		bio_uninit(bio);
+		kfree(bio);
+	}
 	while (req->bio) {
 		bio = req->bio;
 		req->bio = bio->bi_next;
-		bio_put(bio);
+		bio_uninit(bio);
+		kfree(bio);
 	}
 	req->biotail = NULL;
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -994,8 +997,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev)
 {
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 
-	if (pdv->pdv_bdev_handle)
-		return bdev_nr_sectors(pdv->pdv_bdev_handle->bdev);
+	if (pdv->pdv_bdev_file)
+		return bdev_nr_sectors(file_bdev(pdv->pdv_bdev_file));
 	return 0;
 }
 
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index b0a3ef136592..9acaa21e4c78 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -37,7 +37,7 @@ struct pscsi_dev_virt {
 	int	pdv_channel_id;
 	int	pdv_target_id;
 	int	pdv_lun_id;
-	struct bdev_handle *pdv_bdev_handle;
+	struct file *pdv_bdev_file;
 	struct scsi_device *pdv_sd;
 	struct Scsi_Host *pdv_lld_host;
 } ____cacheline_aligned;
diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c
index 4b1092127694..1892e49a8e6a 100644
--- a/drivers/tee/optee/device.c
+++ b/drivers/tee/optee/device.c
@@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func)
 	if (rc) {
 		pr_err("device registration failed, err: %d\n", rc);
 		put_device(&optee_device->dev);
+		return rc;
 	}
 
 	if (func == PTA_CMD_GET_DEVICES_SUPP)
 		device_create_file(&optee_device->dev,
 				   &dev_attr_need_supplicant);
 
-	return rc;
+	return 0;
 }
 
 static int __optee_enumerate_devices(u32 func)
diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 792d6fae4354..e59c20d74b36 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -1226,7 +1226,7 @@ static int tee_client_device_uevent(const struct device *dev,
 	return add_uevent_var(env, "MODALIAS=tee:%pUb", dev_id);
 }
 
-struct bus_type tee_bus_type = {
+const struct bus_type tee_bus_type = {
 	.name		= "tee",
 	.match		= tee_client_device_match,
 	.uevent		= tee_client_device_uevent,
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
index 3b04c6ec4fca..40d664a66cdc 100644
--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -607,7 +607,7 @@ void __init intel_hfi_init(void)
 
 	/* There is one HFI instance per die/package. */
 	max_hfi_instances = topology_max_packages() *
-			    topology_max_die_per_package();
+			    topology_max_dies_per_package();
 
 	/*
 	 * This allocation may fail. CPU hotplug callbacks must check
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index bc6eb0dd66a4..4ba649370aa1 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -587,7 +587,7 @@ static int powerclamp_idle_injection_register(void)
 	poll_pkg_cstate_enable = false;
 	if (cpumask_equal(cpu_present_mask, idle_injection_cpu_mask)) {
 		ii_dev = idle_inject_register_full(idle_injection_cpu_mask, idle_inject_update);
-		if (topology_max_packages() == 1 && topology_max_die_per_package() == 1)
+		if (topology_max_packages() == 1 && topology_max_dies_per_package() == 1)
 			poll_pkg_cstate_enable = true;
 	} else {
 		ii_dev = idle_inject_register(idle_injection_cpu_mask);
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
index 11a7f8108bbb..f6c2e5964b8f 100644
--- a/drivers/thermal/intel/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -494,7 +494,7 @@ static int __init pkg_temp_thermal_init(void)
 	if (!x86_match_cpu(pkg_temp_thermal_ids))
 		return -ENODEV;
 
-	max_id = topology_max_packages() * topology_max_die_per_package();
+	max_id = topology_max_packages() * topology_max_dies_per_package();
 	zones = kcalloc(max_id, sizeof(struct zone_device *),
 			   GFP_KERNEL);
 	if (!zones)
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 900114ba4371..fad40c4bc710 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -1249,6 +1249,9 @@ int tb_port_update_credits(struct tb_port *port)
 	ret = tb_port_do_update_credits(port);
 	if (ret)
 		return ret;
+
+	if (!port->dual_link_port)
+		return 0;
 	return tb_port_do_update_credits(port->dual_link_port);
 }
 
diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h
index 87e4795275fe..6f798f6a2b84 100644
--- a/drivers/thunderbolt/tb_regs.h
+++ b/drivers/thunderbolt/tb_regs.h
@@ -203,7 +203,7 @@ struct tb_regs_switch_header {
 #define ROUTER_CS_5_WOP				BIT(1)
 #define ROUTER_CS_5_WOU				BIT(2)
 #define ROUTER_CS_5_WOD				BIT(3)
-#define ROUTER_CS_5_C3S				BIT(23)
+#define ROUTER_CS_5_CNS				BIT(23)
 #define ROUTER_CS_5_PTO				BIT(24)
 #define ROUTER_CS_5_UTO				BIT(25)
 #define ROUTER_CS_5_HCO				BIT(26)
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index f8f0d24ff6e4..1515eff8cc3e 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -290,7 +290,7 @@ int usb4_switch_setup(struct tb_switch *sw)
 	}
 
 	/* TBT3 supported by the CM */
-	val |= ROUTER_CS_5_C3S;
+	val &= ~ROUTER_CS_5_CNS;
 
 	return tb_sw_write(sw, &val, TB_CFG_SWITCH, ROUTER_CS_5, 1);
 }
diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig
index 6e05c5c7bca1..c2a4e88b328f 100644
--- a/drivers/tty/hvc/Kconfig
+++ b/drivers/tty/hvc/Kconfig
@@ -108,13 +108,15 @@ config HVC_DCC_SERIALIZE_SMP
 
 config HVC_RISCV_SBI
 	bool "RISC-V SBI console support"
-	depends on RISCV_SBI
+	depends on RISCV_SBI && NONPORTABLE
 	select HVC_DRIVER
 	help
 	  This enables support for console output via RISC-V SBI calls, which
-	  is normally used only during boot to output printk.
+	  is normally used only during boot to output printk.  This driver
+	  conflicts with real console drivers and should not be enabled on
+	  systems that directly access the console.
 
-	  If you don't know what do to here, say Y.
+	  If you don't know what do to here, say N.
 
 config HVCS
 	tristate "IBM Hypervisor Virtual Console Server support"
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 2d1f350a4bea..c1d43f040c43 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -357,9 +357,9 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 	long rate;
 	int ret;
 
-	clk_disable_unprepare(d->clk);
 	rate = clk_round_rate(d->clk, newrate);
-	if (rate > 0) {
+	if (rate > 0 && p->uartclk != rate) {
+		clk_disable_unprepare(d->clk);
 		/*
 		 * Note that any clock-notifer worker will block in
 		 * serial8250_update_uartclk() until we are done.
@@ -367,8 +367,8 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios,
 		ret = clk_set_rate(d->clk, newrate);
 		if (!ret)
 			p->uartclk = rate;
+		clk_prepare_enable(d->clk);
 	}
-	clk_prepare_enable(d->clk);
 
 	dw8250_do_set_termios(p, termios, old);
 }
diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 558c4c7f3104..2dda737b1660 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -311,7 +311,7 @@ static void pci1xxxx_process_read_data(struct uart_port *port,
 	}
 
 	while (*valid_byte_count) {
-		if (*buff_index > RX_BUF_SIZE)
+		if (*buff_index >= RX_BUF_SIZE)
 			break;
 		rx_buff[*buff_index] = readb(port->membase +
 					     UART_RX_BYTE_FIFO);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index fccec1698a54..cf2c890a560f 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1339,11 +1339,41 @@ static void pl011_start_tx_pio(struct uart_amba_port *uap)
 	}
 }
 
+static void pl011_rs485_tx_start(struct uart_amba_port *uap)
+{
+	struct uart_port *port = &uap->port;
+	u32 cr;
+
+	/* Enable transmitter */
+	cr = pl011_read(uap, REG_CR);
+	cr |= UART011_CR_TXE;
+
+	/* Disable receiver if half-duplex */
+	if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
+		cr &= ~UART011_CR_RXE;
+
+	if (port->rs485.flags & SER_RS485_RTS_ON_SEND)
+		cr &= ~UART011_CR_RTS;
+	else
+		cr |= UART011_CR_RTS;
+
+	pl011_write(cr, uap, REG_CR);
+
+	if (port->rs485.delay_rts_before_send)
+		mdelay(port->rs485.delay_rts_before_send);
+
+	uap->rs485_tx_started = true;
+}
+
 static void pl011_start_tx(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
+	if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
+	    !uap->rs485_tx_started)
+		pl011_rs485_tx_start(uap);
+
 	if (!pl011_dma_tx_start(uap))
 		pl011_start_tx_pio(uap);
 }
@@ -1424,42 +1454,12 @@ static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c,
 	return true;
 }
 
-static void pl011_rs485_tx_start(struct uart_amba_port *uap)
-{
-	struct uart_port *port = &uap->port;
-	u32 cr;
-
-	/* Enable transmitter */
-	cr = pl011_read(uap, REG_CR);
-	cr |= UART011_CR_TXE;
-
-	/* Disable receiver if half-duplex */
-	if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
-		cr &= ~UART011_CR_RXE;
-
-	if (port->rs485.flags & SER_RS485_RTS_ON_SEND)
-		cr &= ~UART011_CR_RTS;
-	else
-		cr |= UART011_CR_RTS;
-
-	pl011_write(cr, uap, REG_CR);
-
-	if (port->rs485.delay_rts_before_send)
-		mdelay(port->rs485.delay_rts_before_send);
-
-	uap->rs485_tx_started = true;
-}
-
 /* Returns true if tx interrupts have to be (kept) enabled  */
 static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq)
 {
 	struct circ_buf *xmit = &uap->port.state->xmit;
 	int count = uap->fifosize >> 1;
 
-	if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
-	    !uap->rs485_tx_started)
-		pl011_rs485_tx_start(uap);
-
 	if (uap->port.x_char) {
 		if (!pl011_tx_char(uap, uap->port.x_char, from_irq))
 			return true;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 5ddf110aedbe..bbcbc91482af 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -2345,9 +2345,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios,
 
 	lpuart32_write(&sport->port, bd, UARTBAUD);
 	lpuart32_serial_setbrg(sport, baud);
-	lpuart32_write(&sport->port, modem, UARTMODIR);
-	lpuart32_write(&sport->port, ctrl, UARTCTRL);
+	/* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */
+	lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR);
 	/* restore control register */
+	lpuart32_write(&sport->port, ctrl, UARTCTRL);
+	/* re-enable the CTS if needed */
+	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	if ((ctrl & (UARTCTRL_PE | UARTCTRL_M)) == UARTCTRL_PE)
 		sport->is_cs7 = true;
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 4aa72d5aeafb..e14813250616 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -462,8 +462,7 @@ static void imx_uart_stop_tx(struct uart_port *port)
 	}
 }
 
-/* called with port.lock taken and irqs off */
-static void imx_uart_stop_rx(struct uart_port *port)
+static void imx_uart_stop_rx_with_loopback_ctrl(struct uart_port *port, bool loopback)
 {
 	struct imx_port *sport = (struct imx_port *)port;
 	u32 ucr1, ucr2, ucr4, uts;
@@ -485,7 +484,7 @@ static void imx_uart_stop_rx(struct uart_port *port)
 	/* See SER_RS485_ENABLED/UTS_LOOP comment in imx_uart_probe() */
 	if (port->rs485.flags & SER_RS485_ENABLED &&
 	    port->rs485.flags & SER_RS485_RTS_ON_SEND &&
-	    sport->have_rtscts && !sport->have_rtsgpio) {
+	    sport->have_rtscts && !sport->have_rtsgpio && loopback) {
 		uts = imx_uart_readl(sport, imx_uart_uts_reg(sport));
 		uts |= UTS_LOOP;
 		imx_uart_writel(sport, uts, imx_uart_uts_reg(sport));
@@ -498,6 +497,16 @@ static void imx_uart_stop_rx(struct uart_port *port)
 }
 
 /* called with port.lock taken and irqs off */
+static void imx_uart_stop_rx(struct uart_port *port)
+{
+	/*
+	 * Stop RX and enable loopback in order to make sure RS485 bus
+	 * is not blocked. Se comment in imx_uart_probe().
+	 */
+	imx_uart_stop_rx_with_loopback_ctrl(port, true);
+}
+
+/* called with port.lock taken and irqs off */
 static void imx_uart_enable_ms(struct uart_port *port)
 {
 	struct imx_port *sport = (struct imx_port *)port;
@@ -682,9 +691,14 @@ static void imx_uart_start_tx(struct uart_port *port)
 				imx_uart_rts_inactive(sport, &ucr2);
 			imx_uart_writel(sport, ucr2, UCR2);
 
+			/*
+			 * Since we are about to transmit we can not stop RX
+			 * with loopback enabled because that will make our
+			 * transmitted data being just looped to RX.
+			 */
 			if (!(port->rs485.flags & SER_RS485_RX_DURING_TX) &&
 			    !port->rs485_rx_during_tx_gpio)
-				imx_uart_stop_rx(port);
+				imx_uart_stop_rx_with_loopback_ctrl(port, false);
 
 			sport->tx_state = WAIT_AFTER_RTS;
 
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index f3a99daebdaa..10bf6d75bf9e 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -237,6 +237,14 @@
 #define MAX310x_REV_MASK		(0xf8)
 #define MAX310X_WRITE_BIT		0x80
 
+/* Port startup definitions */
+#define MAX310X_PORT_STARTUP_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS	10 /* Delay between retries */
+
+/* Crystal-related definitions */
+#define MAX310X_XTAL_WAIT_RETRIES	20 /* Number of retries */
+#define MAX310X_XTAL_WAIT_DELAY_MS	10 /* Delay between retries */
+
 /* MAX3107 specific */
 #define MAX3107_REV_ID			(0xa0)
 
@@ -583,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr)
 	return 1;
 }
 
-static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
+static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 			       unsigned long freq, bool xtal)
 {
 	unsigned int div, clksrc, pllcfg = 0;
@@ -641,12 +649,20 @@ static u32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s,
 
 	/* Wait for crystal */
 	if (xtal) {
-		unsigned int val;
-		msleep(10);
-		regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
-		if (!(val & MAX310X_STS_CLKREADY_BIT)) {
-			dev_warn(dev, "clock is not stable yet\n");
-		}
+		bool stable = false;
+		unsigned int try = 0, val = 0;
+
+		do {
+			msleep(MAX310X_XTAL_WAIT_DELAY_MS);
+			regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val);
+
+			if (val & MAX310X_STS_CLKREADY_BIT)
+				stable = true;
+		} while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES));
+
+		if (!stable)
+			return dev_err_probe(dev, -EAGAIN,
+					     "clock is not stable\n");
 	}
 
 	return bestfreq;
@@ -1271,7 +1287,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 {
 	int i, ret, fmin, fmax, freq;
 	struct max310x_port *s;
-	u32 uartclk = 0;
+	s32 uartclk = 0;
 	bool xtal;
 
 	for (i = 0; i < devtype->nr; i++)
@@ -1334,6 +1350,9 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 		goto out_clk;
 
 	for (i = 0; i < devtype->nr; i++) {
+		bool started = false;
+		unsigned int try = 0, val = 0;
+
 		/* Reset port */
 		regmap_write(regmaps[i], MAX310X_MODE2_REG,
 			     MAX310X_MODE2_RST_BIT);
@@ -1342,13 +1361,27 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 
 		/* Wait for port startup */
 		do {
-			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &ret);
-		} while (ret != 0x01);
+			msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS);
+			regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val);
+
+			if (val == 0x01)
+				started = true;
+		} while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES));
+
+		if (!started) {
+			ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n");
+			goto out_uart;
+		}
 
 		regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1);
 	}
 
 	uartclk = max310x_set_ref_clk(dev, s, freq, xtal);
+	if (uartclk < 0) {
+		ret = uartclk;
+		goto out_uart;
+	}
+
 	dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk);
 
 	for (i = 0; i < devtype->nr; i++) {
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 3ec725555bcc..4749331fe618 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -605,13 +605,16 @@ static void mxs_auart_tx_chars(struct mxs_auart_port *s)
 		return;
 	}
 
-	pending = uart_port_tx(&s->port, ch,
+	pending = uart_port_tx_flags(&s->port, ch, UART_TX_NOSTOP,
 		!(mxs_read(s, REG_STAT) & AUART_STAT_TXFF),
 		mxs_write(ch, s, REG_DATA));
 	if (pending)
 		mxs_set(AUART_INTR_TXIEN, s, REG_INTR);
 	else
 		mxs_clr(AUART_INTR_TXIEN, s, REG_INTR);
+
+	if (uart_tx_stopped(&s->port))
+               mxs_auart_stop_tx(&s->port);
 }
 
 static void mxs_auart_rx_char(struct mxs_auart_port *s)
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index e63a8fbe63bd..99e08737f293 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -851,19 +851,21 @@ static void qcom_geni_serial_stop_tx(struct uart_port *uport)
 }
 
 static void qcom_geni_serial_send_chunk_fifo(struct uart_port *uport,
-					     unsigned int remaining)
+					     unsigned int chunk)
 {
 	struct qcom_geni_serial_port *port = to_dev_port(uport);
 	struct circ_buf *xmit = &uport->state->xmit;
-	unsigned int tx_bytes;
+	unsigned int tx_bytes, c, remaining = chunk;
 	u8 buf[BYTES_PER_FIFO_WORD];
 
 	while (remaining) {
 		memset(buf, 0, sizeof(buf));
 		tx_bytes = min(remaining, BYTES_PER_FIFO_WORD);
 
-		memcpy(buf, &xmit->buf[xmit->tail], tx_bytes);
-		uart_xmit_advance(uport, tx_bytes);
+		for (c = 0; c < tx_bytes ; c++) {
+			buf[c] = xmit->buf[xmit->tail];
+			uart_xmit_advance(uport, 1);
+		}
 
 		iowrite32_rep(uport->membase + SE_GENI_TX_FIFOn, buf, 1);
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index b56ed8c376b2..d6a58a9e072a 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1084,8 +1084,8 @@ static int uart_tiocmget(struct tty_struct *tty)
 		goto out;
 
 	if (!tty_io_error(tty)) {
-		result = uport->mctrl;
 		uart_port_lock_irq(uport);
+		result = uport->mctrl;
 		result |= uport->ops->get_mctrl(uport);
 		uart_port_unlock_irq(uport);
 	}
diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c
index 88975a4df306..72b6f4f326e2 100644
--- a/drivers/tty/serial/serial_port.c
+++ b/drivers/tty/serial/serial_port.c
@@ -46,8 +46,31 @@ out:
 	return 0;
 }
 
+static int serial_port_runtime_suspend(struct device *dev)
+{
+	struct serial_port_device *port_dev = to_serial_base_port_device(dev);
+	struct uart_port *port = port_dev->port;
+	unsigned long flags;
+	bool busy;
+
+	if (port->flags & UPF_DEAD)
+		return 0;
+
+	uart_port_lock_irqsave(port, &flags);
+	busy = __serial_port_busy(port);
+	if (busy)
+		port->ops->start_tx(port);
+	uart_port_unlock_irqrestore(port, flags);
+
+	if (busy)
+		pm_runtime_mark_last_busy(dev);
+
+	return busy ? -EBUSY : 0;
+}
+
 static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm,
-				 NULL, serial_port_runtime_resume, NULL);
+				 serial_port_runtime_suspend,
+				 serial_port_runtime_resume, NULL);
 
 static int serial_port_probe(struct device *dev)
 {
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 794b77512740..693e932d6feb 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -251,7 +251,9 @@ static int stm32_usart_config_rs485(struct uart_port *port, struct ktermios *ter
 		writel_relaxed(cr3, port->membase + ofs->cr3);
 		writel_relaxed(cr1, port->membase + ofs->cr1);
 
-		rs485conf->flags |= SER_RS485_RX_DURING_TX;
+		if (!port->rs485_rx_during_tx_gpio)
+			rs485conf->flags |= SER_RS485_RX_DURING_TX;
+
 	} else {
 		stm32_usart_clr_bits(port, ofs->cr3,
 				     USART_CR3_DEM | USART_CR3_DEP);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 156efda7c80d..38a765eadbe2 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -381,7 +381,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr)
 		u32 *ln = vc->vc_uni_lines[vc->state.y];
 		unsigned int x = vc->state.x, cols = vc->vc_cols;
 
-		memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
+		memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln));
 		memset32(&ln[cols - nr], ' ', nr);
 	}
 }
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 029d017fc1b6..eac7fff6992d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1469,7 +1469,7 @@ static int ufshcd_devfreq_target(struct device *dev,
 	int ret = 0;
 	struct ufs_hba *hba = dev_get_drvdata(dev);
 	ktime_t start;
-	bool scale_up, sched_clk_scaling_suspend_work = false;
+	bool scale_up = false, sched_clk_scaling_suspend_work = false;
 	struct list_head *clk_list = &hba->clk_list_head;
 	struct ufs_clk_info *clki;
 	unsigned long irq_flags;
@@ -3057,7 +3057,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd)
  */
 static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 {
-	u32 mask = 1U << task_tag;
+	u32 mask;
 	unsigned long flags;
 	int err;
 
@@ -3075,6 +3075,8 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
 		return 0;
 	}
 
+	mask = 1U << task_tag;
+
 	/* clear outstanding transaction before retry */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_utrl_clear(hba, mask);
@@ -6352,7 +6354,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 		ufshcd_hold(hba);
 		if (!ufshcd_is_clkgating_allowed(hba))
 			ufshcd_setup_clocks(hba, true);
-		ufshcd_release(hba);
 		pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM;
 		ufshcd_vops_resume(hba, pm_op);
 	} else {
@@ -10592,7 +10593,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
 	if (err < 0)
 		goto out_remove_scsi_host;
-	hba->tmf_queue = blk_mq_init_queue(&hba->tmf_tag_set);
+	hba->tmf_queue = blk_mq_alloc_queue(&hba->tmf_tag_set, NULL, NULL);
 	if (IS_ERR(hba->tmf_queue)) {
 		err = PTR_ERR(hba->tmf_queue);
 		goto free_tmf_tag_set;
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 39eef470f8fa..8fde5204e88b 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -1712,8 +1712,8 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 	 * 2. Poll queues do not need ESI.
 	 */
 	nr_irqs = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL];
-	ret = platform_msi_domain_alloc_irqs(hba->dev, nr_irqs,
-					     ufs_qcom_write_msi_msg);
+	ret = platform_device_msi_init_and_alloc_irqs(hba->dev, nr_irqs,
+						      ufs_qcom_write_msi_msg);
 	if (ret) {
 		dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret);
 		return ret;
@@ -1742,7 +1742,7 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 			devm_free_irq(hba->dev, desc->irq, hba);
 		}
 		msi_unlock_descs(hba->dev);
-		platform_msi_domain_free_irqs(hba->dev);
+		platform_device_msi_free_irqs_all(hba->dev);
 	} else {
 		if (host->hw_ver.major == 6 && host->hw_ver.minor == 0 &&
 		    host->hw_ver.step == 0)
@@ -1818,7 +1818,7 @@ static void ufs_qcom_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&(pdev)->dev);
 	ufshcd_remove(hba);
-	platform_msi_domain_free_irqs(hba->dev);
+	platform_device_msi_free_irqs_all(hba->dev);
 }
 
 static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = {
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index aeca902ab6cc..fd1beb10bba7 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -828,7 +828,11 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep,
 			return;
 	}
 
-	if (request->complete) {
+	/*
+	 * zlp request is appended by driver, needn't call usb_gadget_giveback_request() to notify
+	 * gadget composite driver.
+	 */
+	if (request->complete && request->buf != priv_dev->zlp_buf) {
 		spin_unlock(&priv_dev->lock);
 		usb_gadget_giveback_request(&priv_ep->endpoint,
 					    request);
@@ -2540,11 +2544,11 @@ static int cdns3_gadget_ep_disable(struct usb_ep *ep)
 
 	while (!list_empty(&priv_ep->wa2_descmiss_req_list)) {
 		priv_req = cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list);
+		list_del_init(&priv_req->list);
 
 		kfree(priv_req->request.buf);
 		cdns3_gadget_ep_free_request(&priv_ep->endpoint,
 					     &priv_req->request);
-		list_del_init(&priv_req->list);
 		--priv_ep->wa2_counter;
 	}
 
diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c
index 33548771a0d3..465e9267b49c 100644
--- a/drivers/usb/cdns3/core.c
+++ b/drivers/usb/cdns3/core.c
@@ -395,7 +395,6 @@ pm_put:
 	return ret;
 }
 
-
 /**
  * cdns_wakeup_irq - interrupt handler for wakeup events
  * @irq: irq number for cdns3/cdnsp core device
diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c
index 04b6d12f2b9a..ee917f1b091c 100644
--- a/drivers/usb/cdns3/drd.c
+++ b/drivers/usb/cdns3/drd.c
@@ -156,7 +156,8 @@ bool cdns_is_device(struct cdns *cdns)
  */
 static void cdns_otg_disable_irq(struct cdns *cdns)
 {
-	writel(0, &cdns->otg_irq_regs->ien);
+	if (cdns->version)
+		writel(0, &cdns->otg_irq_regs->ien);
 }
 
 /**
@@ -422,15 +423,20 @@ int cdns_drd_init(struct cdns *cdns)
 
 		cdns->otg_regs = (void __iomem *)&cdns->otg_v1_regs->cmd;
 
-		if (readl(&cdns->otg_cdnsp_regs->did) == OTG_CDNSP_DID) {
+		state = readl(&cdns->otg_cdnsp_regs->did);
+
+		if (OTG_CDNSP_CHECK_DID(state)) {
 			cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *)
 					      &cdns->otg_cdnsp_regs->ien;
 			cdns->version  = CDNSP_CONTROLLER_V2;
-		} else {
+		} else if (OTG_CDNS3_CHECK_DID(state)) {
 			cdns->otg_irq_regs = (struct cdns_otg_irq_regs __iomem *)
 					      &cdns->otg_v1_regs->ien;
 			writel(1, &cdns->otg_v1_regs->simulate);
 			cdns->version  = CDNS3_CONTROLLER_V1;
+		} else {
+			dev_err(cdns->dev, "not supporte DID=0x%08x\n", state);
+			return -EINVAL;
 		}
 
 		dev_dbg(cdns->dev, "DRD version v1 (ID: %08x, rev: %08x)\n",
@@ -483,7 +489,6 @@ int cdns_drd_exit(struct cdns *cdns)
 	return 0;
 }
 
-
 /* Indicate the cdns3 core was power lost before */
 bool cdns_power_is_lost(struct cdns *cdns)
 {
diff --git a/drivers/usb/cdns3/drd.h b/drivers/usb/cdns3/drd.h
index cbdf94f73ed9..d72370c321d3 100644
--- a/drivers/usb/cdns3/drd.h
+++ b/drivers/usb/cdns3/drd.h
@@ -79,7 +79,11 @@ struct cdnsp_otg_regs {
 	__le32 susp_timing_ctrl;
 };
 
-#define OTG_CDNSP_DID	0x0004034E
+/* CDNSP driver supports 0x000403xx Cadence USB controller family. */
+#define OTG_CDNSP_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040300)
+
+/* CDNS3 driver supports 0x000402xx Cadence USB controller family. */
+#define OTG_CDNS3_CHECK_DID(did) (((did) & GENMASK(31, 8)) == 0x00040200)
 
 /*
  * Common registers interface for both CDNS3 and CDNSP version of DRD.
diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c
index 6164fc4c96a4..ceca4d839dfd 100644
--- a/drivers/usb/cdns3/host.c
+++ b/drivers/usb/cdns3/host.c
@@ -18,6 +18,11 @@
 #include "../host/xhci.h"
 #include "../host/xhci-plat.h"
 
+/*
+ * The XECP_PORT_CAP_REG and XECP_AUX_CTRL_REG1 exist only
+ * in Cadence USB3 dual-role controller, so it can't be used
+ * with Cadence CDNSP dual-role controller.
+ */
 #define XECP_PORT_CAP_REG	0x8000
 #define XECP_AUX_CTRL_REG1	0x8120
 
@@ -57,6 +62,8 @@ static const struct xhci_plat_priv xhci_plat_cdns3_xhci = {
 	.resume_quirk = xhci_cdns3_resume_quirk,
 };
 
+static const struct xhci_plat_priv xhci_plat_cdnsp_xhci;
+
 static int __cdns_host_init(struct cdns *cdns)
 {
 	struct platform_device *xhci;
@@ -81,8 +88,13 @@ static int __cdns_host_init(struct cdns *cdns)
 		goto err1;
 	}
 
-	cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci,
-			sizeof(struct xhci_plat_priv), GFP_KERNEL);
+	if (cdns->version < CDNSP_CONTROLLER_V2)
+		cdns->xhci_plat_data = kmemdup(&xhci_plat_cdns3_xhci,
+				sizeof(struct xhci_plat_priv), GFP_KERNEL);
+	else
+		cdns->xhci_plat_data = kmemdup(&xhci_plat_cdnsp_xhci,
+				sizeof(struct xhci_plat_priv), GFP_KERNEL);
+
 	if (!cdns->xhci_plat_data) {
 		ret = -ENOMEM;
 		goto err1;
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index d9bb3d3f026e..2a38e1eb6546 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -176,6 +176,7 @@ struct hw_bank {
  * @enabled_otg_timer_bits: bits of enabled otg timers
  * @next_otg_timer: next nearest enabled timer to be expired
  * @work: work for role changing
+ * @power_lost_work: work for power lost handling
  * @wq: workqueue thread
  * @qh_pool: allocation pool for queue heads
  * @td_pool: allocation pool for transfer descriptors
@@ -226,6 +227,7 @@ struct ci_hdrc {
 	enum otg_fsm_timer		next_otg_timer;
 	struct usb_role_switch		*role_switch;
 	struct work_struct		work;
+	struct work_struct		power_lost_work;
 	struct workqueue_struct		*wq;
 
 	struct dma_pool			*qh_pool;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 41014f93cfdf..835bf2428dc6 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -856,6 +856,27 @@ static int ci_extcon_register(struct ci_hdrc *ci)
 	return 0;
 }
 
+static void ci_power_lost_work(struct work_struct *work)
+{
+	struct ci_hdrc *ci = container_of(work, struct ci_hdrc, power_lost_work);
+	enum ci_role role;
+
+	disable_irq_nosync(ci->irq);
+	pm_runtime_get_sync(ci->dev);
+	if (!ci_otg_is_fsm_mode(ci)) {
+		role = ci_get_role(ci);
+
+		if (ci->role != role) {
+			ci_handle_id_switch(ci);
+		} else if (role == CI_ROLE_GADGET) {
+			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
+				usb_gadget_vbus_connect(&ci->gadget);
+		}
+	}
+	pm_runtime_put_sync(ci->dev);
+	enable_irq(ci->irq);
+}
+
 static DEFINE_IDA(ci_ida);
 
 struct platform_device *ci_hdrc_add_device(struct device *dev,
@@ -1045,6 +1066,8 @@ static int ci_hdrc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&ci->lock);
 	mutex_init(&ci->mutex);
+	INIT_WORK(&ci->power_lost_work, ci_power_lost_work);
+
 	ci->dev = dev;
 	ci->platdata = dev_get_platdata(dev);
 	ci->imx28_write_fix = !!(ci->platdata->flags &
@@ -1396,25 +1419,6 @@ static int ci_suspend(struct device *dev)
 	return 0;
 }
 
-static void ci_handle_power_lost(struct ci_hdrc *ci)
-{
-	enum ci_role role;
-
-	disable_irq_nosync(ci->irq);
-	if (!ci_otg_is_fsm_mode(ci)) {
-		role = ci_get_role(ci);
-
-		if (ci->role != role) {
-			ci_handle_id_switch(ci);
-		} else if (role == CI_ROLE_GADGET) {
-			if (ci->is_otg && hw_read_otgsc(ci, OTGSC_BSV))
-				usb_gadget_vbus_connect(&ci->gadget);
-		}
-	}
-
-	enable_irq(ci->irq);
-}
-
 static int ci_resume(struct device *dev)
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
@@ -1446,7 +1450,7 @@ static int ci_resume(struct device *dev)
 		ci_role(ci)->resume(ci, power_lost);
 
 	if (power_lost)
-		ci_handle_power_lost(ci);
+		queue_work(system_freezable_wq, &ci->power_lost_work);
 
 	if (ci->supports_runtime_pm) {
 		pm_runtime_disable(dev);
diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 84d91b1c1eed..0886b19d2e1c 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -301,7 +301,7 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi)
 		return ret;
 	}
 
-	root = debugfs_create_dir(dev_name(dev), ulpi_root);
+	root = debugfs_create_dir(dev_name(&ulpi->dev), ulpi_root);
 	debugfs_create_file("regs", 0444, root, ulpi, &ulpi_regs_fops);
 
 	dev_dbg(&ulpi->dev, "registered ULPI PHY: vendor %04x, product %04x\n",
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 12b6dfeaf658..edf74458474a 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1664,9 +1664,10 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	usb_put_urb(urb);
 }
 
-static void usb_giveback_urb_bh(struct tasklet_struct *t)
+static void usb_giveback_urb_bh(struct work_struct *work)
 {
-	struct giveback_urb_bh *bh = from_tasklet(bh, t, bh);
+	struct giveback_urb_bh *bh =
+		container_of(work, struct giveback_urb_bh, bh);
 	struct list_head local_list;
 
 	spin_lock_irq(&bh->lock);
@@ -1691,9 +1692,9 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t)
 	spin_lock_irq(&bh->lock);
 	if (!list_empty(&bh->head)) {
 		if (bh->high_prio)
-			tasklet_hi_schedule(&bh->bh);
+			queue_work(system_bh_highpri_wq, &bh->bh);
 		else
-			tasklet_schedule(&bh->bh);
+			queue_work(system_bh_wq, &bh->bh);
 	}
 	bh->running = false;
 	spin_unlock_irq(&bh->lock);
@@ -1706,7 +1707,7 @@ static void usb_giveback_urb_bh(struct tasklet_struct *t)
  * @status: completion status code for the URB.
  *
  * Context: atomic. The completion callback is invoked in caller's context.
- * For HCDs with HCD_BH flag set, the completion callback is invoked in tasklet
+ * For HCDs with HCD_BH flag set, the completion callback is invoked in BH
  * context (except for URBs submitted to the root hub which always complete in
  * caller's context).
  *
@@ -1725,7 +1726,7 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 	struct giveback_urb_bh *bh;
 	bool running;
 
-	/* pass status to tasklet via unlinked */
+	/* pass status to BH via unlinked */
 	if (likely(!urb->unlinked))
 		urb->unlinked = status;
 
@@ -1747,9 +1748,9 @@ void usb_hcd_giveback_urb(struct usb_hcd *hcd, struct urb *urb, int status)
 	if (running)
 		;
 	else if (bh->high_prio)
-		tasklet_hi_schedule(&bh->bh);
+		queue_work(system_bh_highpri_wq, &bh->bh);
 	else
-		tasklet_schedule(&bh->bh);
+		queue_work(system_bh_wq, &bh->bh);
 }
 EXPORT_SYMBOL_GPL(usb_hcd_giveback_urb);
 
@@ -2540,7 +2541,7 @@ static void init_giveback_urb_bh(struct giveback_urb_bh *bh)
 
 	spin_lock_init(&bh->lock);
 	INIT_LIST_HEAD(&bh->head);
-	tasklet_setup(&bh->bh, usb_giveback_urb_bh);
+	INIT_WORK(&bh->bh, usb_giveback_urb_bh);
 }
 
 struct usb_hcd *__usb_create_hcd(const struct hc_driver *driver,
@@ -2926,7 +2927,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 			&& device_can_wakeup(&hcd->self.root_hub->dev))
 		dev_dbg(hcd->self.controller, "supports USB remote wakeup\n");
 
-	/* initialize tasklets */
+	/* initialize BHs */
 	init_giveback_urb_bh(&hcd->high_prio_bh);
 	hcd->high_prio_bh.high_prio = true;
 	init_giveback_urb_bh(&hcd->low_prio_bh);
@@ -3036,7 +3037,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 	mutex_unlock(&usb_bus_idr_lock);
 
 	/*
-	 * tasklet_kill() isn't needed here because:
+	 * flush_work() isn't needed here because:
 	 * - driver's disconnect() called from usb_disconnect() should
 	 *   make sure its URBs are completed during the disconnect()
 	 *   callback
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index ffd7c99e24a3..e38a4124f610 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2053,9 +2053,19 @@ static void update_port_device_state(struct usb_device *udev)
 
 	if (udev->parent) {
 		hub = usb_hub_to_struct_hub(udev->parent);
-		port_dev = hub->ports[udev->portnum - 1];
-		WRITE_ONCE(port_dev->state, udev->state);
-		sysfs_notify_dirent(port_dev->state_kn);
+
+		/*
+		 * The Link Layer Validation System Driver (lvstest)
+		 * has a test step to unbind the hub before running the
+		 * rest of the procedure. This triggers hub_disconnect
+		 * which will set the hub's maxchild to 0, further
+		 * resulting in usb_hub_to_struct_hub returning NULL.
+		 */
+		if (hub) {
+			port_dev = hub->ports[udev->portnum - 1];
+			WRITE_ONCE(port_dev->state, udev->state);
+			sysfs_notify_dirent(port_dev->state_kn);
+		}
 	}
 }
 
@@ -2388,17 +2398,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev)
 			}
 		} else if (desc->bLength == sizeof
 				(struct usb_otg_descriptor)) {
-			/* Set a_alt_hnp_support for legacy otg device */
-			err = usb_control_msg(udev,
-				usb_sndctrlpipe(udev, 0),
-				USB_REQ_SET_FEATURE, 0,
-				USB_DEVICE_A_ALT_HNP_SUPPORT,
-				0, NULL, 0,
-				USB_CTRL_SET_TIMEOUT);
-			if (err < 0)
-				dev_err(&udev->dev,
-					"set a_alt_hnp_support failed: %d\n",
-					err);
+			/*
+			 * We are operating on a legacy OTP device
+			 * These should be told that they are operating
+			 * on the wrong port if we have another port that does
+			 * support HNP
+			 */
+			if (bus->otg_port != 0) {
+				/* Set a_alt_hnp_support for legacy otg device */
+				err = usb_control_msg(udev,
+					usb_sndctrlpipe(udev, 0),
+					USB_REQ_SET_FEATURE, 0,
+					USB_DEVICE_A_ALT_HNP_SUPPORT,
+					0, NULL, 0,
+					USB_CTRL_SET_TIMEOUT);
+				if (err < 0)
+					dev_err(&udev->dev,
+						"set a_alt_hnp_support failed: %d\n",
+						err);
+			}
 		}
 	}
 #endif
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index c628c1abc907..4d63496f98b6 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -573,7 +573,7 @@ static int match_location(struct usb_device *peer_hdev, void *p)
 	struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev);
 	struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent);
 
-	if (!peer_hub)
+	if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED)
 		return 0;
 
 	hcd = bus_to_hcd(hdev->bus);
@@ -584,7 +584,8 @@ static int match_location(struct usb_device *peer_hdev, void *p)
 
 	for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) {
 		peer = peer_hub->ports[port1 - 1];
-		if (peer && peer->location == port_dev->location) {
+		if (peer && peer->connect_type != USB_PORT_NOT_USED &&
+		    peer->location == port_dev->location) {
 			link_peers_report(port_dev, peer);
 			return 1; /* done */
 		}
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index e3eea965e57b..e120611a5174 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -376,7 +376,6 @@
 /* Global HWPARAMS4 Register */
 #define DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(n)	(((n) & (0x0f << 13)) >> 13)
 #define DWC3_MAX_HIBER_SCRATCHBUFS		15
-#define DWC3_EXT_BUFF_CONTROL		BIT(21)
 
 /* Global HWPARAMS6 Register */
 #define DWC3_GHWPARAMS6_BCSUPPORT		BIT(14)
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6604845c397c..39564e17f3b0 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -51,6 +51,8 @@
 #define PCI_DEVICE_ID_INTEL_MTLP		0x7ec1
 #define PCI_DEVICE_ID_INTEL_MTLS		0x7f6f
 #define PCI_DEVICE_ID_INTEL_MTL			0x7e7e
+#define PCI_DEVICE_ID_INTEL_ARLH		0x7ec1
+#define PCI_DEVICE_ID_INTEL_ARLH_PCH		0x777e
 #define PCI_DEVICE_ID_INTEL_TGL			0x9a15
 #define PCI_DEVICE_ID_AMD_MR			0x163a
 
@@ -421,6 +423,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, MTLS, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, ARLH_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) },
 
 	{ PCI_DEVICE_DATA(AMD, NL_USB, &dwc3_pci_amd_swnode) },
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 019368f8e9c4..28f49400f3e8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -673,12 +673,6 @@ static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
 		params.param1 |= DWC3_DEPCFG_BINTERVAL_M1(bInterval_m1);
 	}
 
-	if (dep->endpoint.fifo_mode) {
-		if (!(dwc->hwparams.hwparams4 & DWC3_EXT_BUFF_CONTROL))
-			return -EINVAL;
-		params.param1 |= DWC3_DEPCFG_EBC_HWO_NOWB | DWC3_DEPCFG_USE_EBC;
-	}
-
 	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, &params);
 }
 
@@ -2656,6 +2650,11 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc)
 	int ret;
 
 	spin_lock_irqsave(&dwc->lock, flags);
+	if (!dwc->pullups_connected) {
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return 0;
+	}
+
 	dwc->connected = false;
 
 	/*
@@ -4709,15 +4708,13 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	unsigned long flags;
 	int ret;
 
-	if (!dwc->gadget_driver)
-		return 0;
-
 	ret = dwc3_gadget_soft_disconnect(dwc);
 	if (ret)
 		goto err;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dwc3_disconnect_gadget(dwc);
+	if (dwc->gadget_driver)
+		dwc3_disconnect_gadget(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index fd7a4e94397e..55a56cf67d73 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -26,8 +26,6 @@ struct dwc3;
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	BIT(10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	BIT(11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	BIT(13)
-#define DWC3_DEPCFG_EBC_HWO_NOWB	BIT(14)
-#define DWC3_DEPCFG_USE_EBC		BIT(15)
 #define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	BIT(24)
 #define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 61f57fe5bb78..43230915323c 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -61,7 +61,7 @@ out:
 
 int dwc3_host_init(struct dwc3 *dwc)
 {
-	struct property_entry	props[4];
+	struct property_entry	props[5];
 	struct platform_device	*xhci;
 	int			ret, irq;
 	int			prop_idx = 0;
@@ -89,6 +89,8 @@ int dwc3_host_init(struct dwc3 *dwc)
 
 	memset(props, 0, sizeof(struct property_entry) * ARRAY_SIZE(props));
 
+	props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-sg-trb-cache-size-quirk");
+
 	if (dwc->usb3_lpm_capable)
 		props[prop_idx++] = PROPERTY_ENTRY_BOOL("usb3-lpm-capable");
 
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 722a3ab2b337..c265a1f62fc1 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -545,21 +545,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep,
 
 static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_SENDING;
-	if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq);
+	if (rc) {
 		bh->state = BUF_STATE_EMPTY;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
 static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh)
 {
+	int rc;
+
 	if (!fsg_is_set(common))
 		return false;
 	bh->state = BUF_STATE_RECEIVING;
-	if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq))
+	rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq);
+	if (rc) {
 		bh->state = BUF_STATE_FULL;
+		if (rc == -ESHUTDOWN) {
+			common->running = 0;
+			return false;
+		}
+	}
 	return true;
 }
 
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index a1575a0ca568..28f4e6552e84 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -105,8 +105,8 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 
 /*
  * Although max mtu as dictated by u_ether is 15412 bytes, setting
- * max_segment_sizeto 15426 would not be efficient. If user chooses segment
- * size to be (>= 8192), then we can't aggregate more than one  buffer in each
+ * max_segment_size to 15426 would not be efficient. If user chooses segment
+ * size to be (>= 8192), then we can't aggregate more than one buffer in each
  * NTB (assuming each packet coming from network layer is >= 8192 bytes) as ep
  * maxpacket limit is 16384. So let max_segment_size be limited to 8000 to allow
  * at least 2 packets to be aggregated reducing wastage of NTB buffer space
@@ -1338,7 +1338,15 @@ parse_ntb:
 	     "Parsed NTB with %d frames\n", dgram_counter);
 
 	to_process -= block_len;
-	if (to_process != 0) {
+
+	/*
+	 * Windows NCM driver avoids USB ZLPs by adding a 1-byte
+	 * zero pad as needed.
+	 */
+	if (to_process == 1 &&
+	    (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) {
+		to_process--;
+	} else if ((to_process > 0) && (block_len != 0)) {
 		ntb_ptr = (unsigned char *)(ntb_ptr + block_len);
 		goto parse_ntb;
 	}
@@ -1489,7 +1497,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	ncm_data_intf.bInterfaceNumber = status;
 	ncm_union_desc.bSlaveInterface0 = status;
 
-	ecm_desc.wMaxSegmentSize = ncm_opts->max_segment_size;
+	ecm_desc.wMaxSegmentSize = cpu_to_le16(ncm_opts->max_segment_size);
 
 	status = -ENODEV;
 
@@ -1685,7 +1693,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 		kfree(opts);
 		return ERR_CAST(net);
 	}
-	opts->max_segment_size = cpu_to_le16(ETH_FRAME_LEN);
+	opts->max_segment_size = ETH_FRAME_LEN;
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
 	descs[0] = &opts->ncm_os_desc;
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index 10c5d7f726a1..f90eeecf27de 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -2036,7 +2036,8 @@ static irqreturn_t omap_udc_iso_irq(int irq, void *_dev)
 
 static inline int machine_without_vbus_sense(void)
 {
-	return  machine_is_omap_osk() || machine_is_sx1();
+	return  machine_is_omap_osk() || machine_is_omap_palmte() ||
+		machine_is_sx1();
 }
 
 static int omap_udc_start(struct usb_gadget *g,
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index 4f8617210d85..169f72665739 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -274,7 +274,6 @@ struct pch_udc_cfg_data {
  * @td_data:		for data request
  * @dev:		reference to device struct
  * @offset_addr:	offset address of ep register
- * @desc:		for this ep
  * @queue:		queue for requests
  * @num:		endpoint number
  * @in:			endpoint is IN
diff --git a/drivers/usb/host/uhci-grlib.c b/drivers/usb/host/uhci-grlib.c
index ac3fc5970315..cfebb833668e 100644
--- a/drivers/usb/host/uhci-grlib.c
+++ b/drivers/usb/host/uhci-grlib.c
@@ -22,6 +22,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 static int uhci_grlib_init(struct usb_hcd *hcd)
 {
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 4460fa7e9fab..a7716202a8dd 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1861,14 +1861,14 @@ void xhci_remove_secondary_interrupter(struct usb_hcd *hcd, struct xhci_interrup
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 	unsigned int intr_num;
 
+	spin_lock_irq(&xhci->lock);
+
 	/* interrupter 0 is primary interrupter, don't touch it */
-	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters)
+	if (!ir || !ir->intr_num || ir->intr_num >= xhci->max_interrupters) {
 		xhci_dbg(xhci, "Invalid secondary interrupter, can't remove\n");
-
-	/* fixme, should we check xhci->interrupter[intr_num] == ir */
-	/* fixme locking */
-
-	spin_lock_irq(&xhci->lock);
+		spin_unlock_irq(&xhci->lock);
+		return;
+	}
 
 	intr_num = ir->intr_num;
 
@@ -2322,7 +2322,7 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
 	u64 erst_base;
 	u32 erst_size;
 
-	if (intr_num > xhci->max_interrupters) {
+	if (intr_num >= xhci->max_interrupters) {
 		xhci_warn(xhci, "Can't add interrupter %d, max interrupters %d\n",
 			  intr_num, xhci->max_interrupters);
 		return -EINVAL;
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index f04fde19f551..3d071b875308 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -253,6 +253,9 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 		if (device_property_read_bool(tmpdev, "quirk-broken-port-ped"))
 			xhci->quirks |= XHCI_BROKEN_PORT_PED;
 
+		if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk"))
+			xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK;
+
 		device_property_read_u32(tmpdev, "imod-interval-ns",
 					 &xhci->imod_interval);
 	}
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 33806ae966f9..4f64b814d4aa 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -326,7 +326,13 @@ static unsigned int xhci_ring_expansion_needed(struct xhci_hcd *xhci, struct xhc
 	/* how many trbs will be queued past the enqueue segment? */
 	trbs_past_seg = enq_used + num_trbs - (TRBS_PER_SEGMENT - 1);
 
-	if (trbs_past_seg <= 0)
+	/*
+	 * Consider expanding the ring already if num_trbs fills the current
+	 * segment (i.e. trbs_past_seg == 0), not only when num_trbs goes into
+	 * the next segment. Avoids confusing full ring with special empty ring
+	 * case below
+	 */
+	if (trbs_past_seg < 0)
 		return 0;
 
 	/* Empty ring special case, enqueue stuck on link trb while dequeue advanced */
@@ -2376,6 +2382,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	/* handle completion code */
 	switch (trb_comp_code) {
 	case COMP_SUCCESS:
+		/* Don't overwrite status if TD had an error, see xHCI 4.9.1 */
+		if (td->error_mid_td)
+			break;
 		if (remaining) {
 			frame->status = short_framestatus;
 			if (xhci->quirks & XHCI_TRUST_TX_LENGTH)
@@ -2391,9 +2400,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 	case COMP_BANDWIDTH_OVERRUN_ERROR:
 		frame->status = -ECOMM;
 		break;
-	case COMP_ISOCH_BUFFER_OVERRUN:
 	case COMP_BABBLE_DETECTED_ERROR:
+		sum_trbs_for_length = true;
+		fallthrough;
+	case COMP_ISOCH_BUFFER_OVERRUN:
 		frame->status = -EOVERFLOW;
+		if (ep_trb != td->last_trb)
+			td->error_mid_td = true;
 		break;
 	case COMP_INCOMPATIBLE_DEVICE_ERROR:
 	case COMP_STALL_ERROR:
@@ -2401,8 +2414,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	case COMP_USB_TRANSACTION_ERROR:
 		frame->status = -EPROTO;
+		sum_trbs_for_length = true;
 		if (ep_trb != td->last_trb)
-			return 0;
+			td->error_mid_td = true;
 		break;
 	case COMP_STOPPED:
 		sum_trbs_for_length = true;
@@ -2422,6 +2436,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 		break;
 	}
 
+	if (td->urb_length_set)
+		goto finish_td;
+
 	if (sum_trbs_for_length)
 		frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) +
 			ep_trb_len - remaining;
@@ -2430,6 +2447,14 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep,
 
 	td->urb->actual_length += frame->actual_length;
 
+finish_td:
+	/* Don't give back TD yet if we encountered an error mid TD */
+	if (td->error_mid_td && ep_trb != td->last_trb) {
+		xhci_dbg(xhci, "Error mid isoc TD, wait for final completion event\n");
+		td->urb_length_set = true;
+		return 0;
+	}
+
 	return finish_td(xhci, ep, ep_ring, td, trb_comp_code);
 }
 
@@ -2808,17 +2833,51 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		}
 
 		if (!ep_seg) {
-			if (!ep->skip ||
-			    !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
-				/* Some host controllers give a spurious
-				 * successful event after a short transfer.
-				 * Ignore it.
-				 */
-				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
-						ep_ring->last_td_was_short) {
-					ep_ring->last_td_was_short = false;
-					goto cleanup;
+
+			if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+				skip_isoc_td(xhci, td, ep, status);
+				goto cleanup;
+			}
+
+			/*
+			 * Some hosts give a spurious success event after a short
+			 * transfer. Ignore it.
+			 */
+			if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
+			    ep_ring->last_td_was_short) {
+				ep_ring->last_td_was_short = false;
+				goto cleanup;
+			}
+
+			/*
+			 * xhci 4.10.2 states isoc endpoints should continue
+			 * processing the next TD if there was an error mid TD.
+			 * So host like NEC don't generate an event for the last
+			 * isoc TRB even if the IOC flag is set.
+			 * xhci 4.9.1 states that if there are errors in mult-TRB
+			 * TDs xHC should generate an error for that TRB, and if xHC
+			 * proceeds to the next TD it should genete an event for
+			 * any TRB with IOC flag on the way. Other host follow this.
+			 * So this event might be for the next TD.
+			 */
+			if (td->error_mid_td &&
+			    !list_is_last(&td->td_list, &ep_ring->td_list)) {
+				struct xhci_td *td_next = list_next_entry(td, td_list);
+
+				ep_seg = trb_in_td(xhci, td_next->start_seg, td_next->first_trb,
+						   td_next->last_trb, ep_trb_dma, false);
+				if (ep_seg) {
+					/* give back previous TD, start handling new */
+					xhci_dbg(xhci, "Missing TD completion event after mid TD error\n");
+					ep_ring->dequeue = td->last_trb;
+					ep_ring->deq_seg = td->last_trb_seg;
+					inc_deq(xhci, ep_ring);
+					xhci_td_cleanup(xhci, td, ep_ring, td->status);
+					td = td_next;
 				}
+			}
+
+			if (!ep_seg) {
 				/* HC is busted, give up! */
 				xhci_err(xhci,
 					"ERROR Transfer event TRB DMA ptr not "
@@ -2830,9 +2889,6 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 					  ep_trb_dma, true);
 				return -ESHUTDOWN;
 			}
-
-			skip_isoc_td(xhci, td, ep, status);
-			goto cleanup;
 		}
 		if (trb_comp_code == COMP_SHORT_PACKET)
 			ep_ring->last_td_was_short = true;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index a5c72a634e6a..6f82d404883f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1549,6 +1549,7 @@ struct xhci_td {
 	struct xhci_segment	*bounce_seg;
 	/* actual_length of the URB has already been set */
 	bool			urb_length_set;
+	bool			error_mid_td;
 	unsigned int		num_trbs;
 };
 
diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index ae41578bd014..70165dd86b5d 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -21,7 +21,9 @@ static const struct class role_class = {
 struct usb_role_switch {
 	struct device dev;
 	struct mutex lock; /* device lock*/
+	struct module *module; /* the module this device depends on */
 	enum usb_role role;
+	bool registered;
 
 	/* From descriptor */
 	struct device *usb2_port;
@@ -48,6 +50,9 @@ int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role)
 	if (IS_ERR_OR_NULL(sw))
 		return 0;
 
+	if (!sw->registered)
+		return -EOPNOTSUPP;
+
 	mutex_lock(&sw->lock);
 
 	ret = sw->set(sw, role);
@@ -73,7 +78,7 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw)
 {
 	enum usb_role role;
 
-	if (IS_ERR_OR_NULL(sw))
+	if (IS_ERR_OR_NULL(sw) || !sw->registered)
 		return USB_ROLE_NONE;
 
 	mutex_lock(&sw->lock);
@@ -135,7 +140,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev)
 						  usb_role_switch_match);
 
 	if (!IS_ERR_OR_NULL(sw))
-		WARN_ON(!try_module_get(sw->dev.parent->driver->owner));
+		WARN_ON(!try_module_get(sw->module));
 
 	return sw;
 }
@@ -157,7 +162,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode)
 		sw = fwnode_connection_find_match(fwnode, "usb-role-switch",
 						  NULL, usb_role_switch_match);
 	if (!IS_ERR_OR_NULL(sw))
-		WARN_ON(!try_module_get(sw->dev.parent->driver->owner));
+		WARN_ON(!try_module_get(sw->module));
 
 	return sw;
 }
@@ -172,7 +177,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get);
 void usb_role_switch_put(struct usb_role_switch *sw)
 {
 	if (!IS_ERR_OR_NULL(sw)) {
-		module_put(sw->dev.parent->driver->owner);
+		module_put(sw->module);
 		put_device(&sw->dev);
 	}
 }
@@ -189,15 +194,18 @@ struct usb_role_switch *
 usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode)
 {
 	struct device *dev;
+	struct usb_role_switch *sw = NULL;
 
 	if (!fwnode)
 		return NULL;
 
 	dev = class_find_device_by_fwnode(&role_class, fwnode);
-	if (dev)
-		WARN_ON(!try_module_get(dev->parent->driver->owner));
+	if (dev) {
+		sw = to_role_switch(dev);
+		WARN_ON(!try_module_get(sw->module));
+	}
 
-	return dev ? to_role_switch(dev) : NULL;
+	return sw;
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode);
 
@@ -338,6 +346,7 @@ usb_role_switch_register(struct device *parent,
 	sw->set = desc->set;
 	sw->get = desc->get;
 
+	sw->module = parent->driver->owner;
 	sw->dev.parent = parent;
 	sw->dev.fwnode = desc->fwnode;
 	sw->dev.class = &role_class;
@@ -352,6 +361,8 @@ usb_role_switch_register(struct device *parent,
 		return ERR_PTR(ret);
 	}
 
+	sw->registered = true;
+
 	/* TODO: Symlinks for the host port and the device controller. */
 
 	return sw;
@@ -366,8 +377,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_register);
  */
 void usb_role_switch_unregister(struct usb_role_switch *sw)
 {
-	if (!IS_ERR_OR_NULL(sw))
+	if (!IS_ERR_OR_NULL(sw)) {
+		sw->registered = false;
 		device_unregister(&sw->dev);
+	}
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_unregister);
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 1e61fe043171..923e0ed85444 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -146,6 +146,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+	{ USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */
 	{ USB_DEVICE(0x10C4, 0x8856) },	/* CEL EM357 ZigBee USB Stick - LR */
 	{ USB_DEVICE(0x10C4, 0x8857) },	/* CEL EM357 ZigBee USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 72390dbf0769..2ae124c49d44 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2269,6 +2269,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) },			/* Fibocom FM160 (MBIM mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index b1e844bf31f8..703a9c563557 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
 	{DEVICE_SWI(0x413c, 0x81d2)},   /* Dell Wireless 5818 */
+	{DEVICE_SWI(0x413c, 0x8217)},	/* Dell Wireless DW5826e */
+	{DEVICE_SWI(0x413c, 0x8218)},	/* Dell Wireless DW5826e QDL */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c
index 4e0eef1440b7..300aeef160e7 100644
--- a/drivers/usb/storage/isd200.c
+++ b/drivers/usb/storage/isd200.c
@@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id)
 static int isd200_get_inquiry_data( struct us_data *us )
 {
 	struct isd200_info *info = (struct isd200_info *)us->extra;
-	int retStatus = ISD200_GOOD;
+	int retStatus;
 	u16 *id = info->id;
 
 	usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n");
@@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us )
 				isd200_fix_driveid(id);
 				isd200_dump_driveid(us, id);
 
+				/* Prevent division by 0 in isd200_scsi_to_ata() */
+				if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) {
+					usb_stor_dbg(us, "   Invalid ATA Identify data\n");
+					retStatus = ISD200_ERROR;
+					goto Done;
+				}
+
 				memset(&info->InquiryData, 0, sizeof(info->InquiryData));
 
 				/* Standard IDE interface only supports disks */
@@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us )
 		}
 	}
 
+ Done:
 	usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus);
 
 	return(retStatus);
@@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us)
 
 static int isd200_Initialization(struct us_data *us)
 {
+	int rc = 0;
+
 	usb_stor_dbg(us, "ISD200 Initialization...\n");
 
 	/* Initialize ISD200 info struct */
 
-	if (isd200_init_info(us) == ISD200_ERROR) {
+	if (isd200_init_info(us) < 0) {
 		usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n");
+		rc = -ENOMEM;
 	} else {
 		/* Get device specific data */
 
-		if (isd200_get_inquiry_data(us) != ISD200_GOOD)
+		if (isd200_get_inquiry_data(us) != ISD200_GOOD) {
 			usb_stor_dbg(us, "ISD200 Initialization Failure\n");
-		else
+			rc = -EINVAL;
+		} else {
 			usb_stor_dbg(us, "ISD200 Initialization complete\n");
+		}
 	}
 
-	return 0;
+	return rc;
 }
 
 
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index c54e9805da53..12cf9940e5b6 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -180,6 +180,13 @@ static int slave_configure(struct scsi_device *sdev)
 		sdev->use_192_bytes_for_3f = 1;
 
 		/*
+		 * Some devices report generic values until the media has been
+		 * accessed. Force a READ(10) prior to querying device
+		 * characteristics.
+		 */
+		sdev->read_before_ms = 1;
+
+		/*
 		 * Some devices don't like MODE SENSE with page=0x3f,
 		 * which is the command used for checking if a device
 		 * is write-protected.  Now that we tell the sd driver
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 9707f53cfda9..71ace274761f 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -879,6 +879,13 @@ static int uas_slave_configure(struct scsi_device *sdev)
 		sdev->guess_capacity = 1;
 
 	/*
+	 * Some devices report generic values until the media has been
+	 * accessed. Force a READ(10) prior to querying device
+	 * characteristics.
+	 */
+	sdev->read_before_ms = 1;
+
+	/*
 	 * Some devices don't like MODE SENSE with page=0x3f,
 	 * which is the command used for checking if a device
 	 * is write-protected.  Now that we tell the sd driver
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index f81bec0c7b86..f8ea3054be54 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -559,16 +559,21 @@ static ssize_t hpd_show(struct device *dev, struct device_attribute *attr, char
 }
 static DEVICE_ATTR_RO(hpd);
 
-static struct attribute *dp_altmode_attrs[] = {
+static struct attribute *displayport_attrs[] = {
 	&dev_attr_configuration.attr,
 	&dev_attr_pin_assignment.attr,
 	&dev_attr_hpd.attr,
 	NULL
 };
 
-static const struct attribute_group dp_altmode_group = {
+static const struct attribute_group displayport_group = {
 	.name = "displayport",
-	.attrs = dp_altmode_attrs,
+	.attrs = displayport_attrs,
+};
+
+static const struct attribute_group *displayport_groups[] = {
+	&displayport_group,
+	NULL,
 };
 
 int dp_altmode_probe(struct typec_altmode *alt)
@@ -576,7 +581,6 @@ int dp_altmode_probe(struct typec_altmode *alt)
 	const struct typec_altmode *port = typec_altmode_get_partner(alt);
 	struct fwnode_handle *fwnode;
 	struct dp_altmode *dp;
-	int ret;
 
 	/* FIXME: Port can only be DFP_U. */
 
@@ -587,10 +591,6 @@ int dp_altmode_probe(struct typec_altmode *alt)
 	      DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo)))
 		return -ENODEV;
 
-	ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group);
-	if (ret)
-		return ret;
-
 	dp = devm_kzalloc(&alt->dev, sizeof(*dp), GFP_KERNEL);
 	if (!dp)
 		return -ENOMEM;
@@ -624,7 +624,6 @@ void dp_altmode_remove(struct typec_altmode *alt)
 {
 	struct dp_altmode *dp = typec_altmode_get_drvdata(alt);
 
-	sysfs_remove_group(&alt->dev.kobj, &dp_altmode_group);
 	cancel_work_sync(&dp->work);
 
 	if (dp->connector_fwnode) {
@@ -649,6 +648,7 @@ static struct typec_altmode_driver dp_altmode_driver = {
 	.driver = {
 		.name = "typec_displayport",
 		.owner = THIS_MODULE,
+		.dev_groups = displayport_groups,
 	},
 };
 module_typec_altmode_driver(dp_altmode_driver);
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 5945e3a2b0f7..096597231027 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3743,9 +3743,6 @@ static void tcpm_detach(struct tcpm_port *port)
 	if (tcpm_port_is_disconnected(port))
 		port->hard_reset_count = 0;
 
-	port->try_src_count = 0;
-	port->try_snk_count = 0;
-
 	if (!port->attached)
 		return;
 
@@ -4876,8 +4873,11 @@ static void run_state_machine(struct tcpm_port *port)
 		break;
 	case PORT_RESET:
 		tcpm_reset_port(port);
-		tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
-			    TYPEC_CC_RD : tcpm_rp_cc(port));
+		if (port->self_powered)
+			tcpm_set_cc(port, TYPEC_CC_OPEN);
+		else
+			tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
+				    TYPEC_CC_RD : tcpm_rp_cc(port));
 		tcpm_set_state(port, PORT_RESET_WAIT_OFF,
 			       PD_T_ERROR_RECOVERY);
 		break;
@@ -6848,7 +6848,8 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	if (err)
 		goto out_role_sw_put;
 
-	port->typec_caps.pd = port->pds[0];
+	if (port->pds)
+		port->typec_caps.pd = port->pds[0];
 
 	port->typec_port = typec_register_port(port->dev, &port->typec_caps);
 	if (IS_ERR(port->typec_port)) {
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 5392ec698959..14f5a7bfae2e 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -938,7 +938,9 @@ static void ucsi_handle_connector_change(struct work_struct *work)
 
 	clear_bit(EVENT_PENDING, &con->ucsi->flags);
 
+	mutex_lock(&ucsi->ppm_lock);
 	ret = ucsi_acknowledge_connector_change(ucsi);
+	mutex_unlock(&ucsi->ppm_lock);
 	if (ret)
 		dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret);
 
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 6bbf490ac401..928eacbeb21a 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -25,6 +25,8 @@ struct ucsi_acpi {
 	unsigned long flags;
 	guid_t guid;
 	u64 cmd;
+	bool dell_quirk_probed;
+	bool dell_quirk_active;
 };
 
 static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func)
@@ -73,9 +75,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 				const void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI;
 	int ret;
 
-	set_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		set_bit(ACK_PENDING, &ua->flags);
+	else
+		set_bit(COMMAND_PENDING, &ua->flags);
 
 	ret = ucsi_acpi_async_write(ucsi, offset, val, val_len);
 	if (ret)
@@ -85,7 +91,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset,
 		ret = -ETIMEDOUT;
 
 out_clear_bit:
-	clear_bit(COMMAND_PENDING, &ua->flags);
+	if (ack)
+		clear_bit(ACK_PENDING, &ua->flags);
+	else
+		clear_bit(COMMAND_PENDING, &ua->flags);
 
 	return ret;
 }
@@ -119,12 +128,73 @@ static const struct ucsi_operations ucsi_zenbook_ops = {
 	.async_write = ucsi_acpi_async_write
 };
 
-static const struct dmi_system_id zenbook_dmi_id[] = {
+/*
+ * Some Dell laptops expect that an ACK command with the
+ * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate)
+ * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set.
+ * If this is not done events are not delivered to OSPM and
+ * subsequent commands will timeout.
+ */
+static int
+ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset,
+		     const void *val, size_t val_len)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	u64 cmd = *(u64 *)val, ack = 0;
+	int ret;
+
+	if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI &&
+	    cmd & UCSI_ACK_CONNECTOR_CHANGE)
+		ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE;
+
+	ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len);
+	if (ret != 0)
+		return ret;
+	if (ack == 0)
+		return ret;
+
+	if (!ua->dell_quirk_probed) {
+		ua->dell_quirk_probed = true;
+
+		cmd = UCSI_GET_CAPABILITY;
+		ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd,
+					   sizeof(cmd));
+		if (ret == 0)
+			return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL,
+						    &ack, sizeof(ack));
+		if (ret != -ETIMEDOUT)
+			return ret;
+
+		ua->dell_quirk_active = true;
+		dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n");
+		dev_err(ua->dev, "Firmware bug: Enabling workaround\n");
+	}
+
+	if (!ua->dell_quirk_active)
+		return ret;
+
+	return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack));
+}
+
+static const struct ucsi_operations ucsi_dell_ops = {
+	.read = ucsi_acpi_read,
+	.sync_write = ucsi_dell_sync_write,
+	.async_write = ucsi_acpi_async_write
+};
+
+static const struct dmi_system_id ucsi_acpi_quirks[] = {
 	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
 		},
+		.driver_data = (void *)&ucsi_zenbook_ops,
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		},
+		.driver_data = (void *)&ucsi_dell_ops,
 	},
 	{ }
 };
@@ -142,8 +212,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data)
 	if (UCSI_CCI_CONNECTOR(cci))
 		ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci));
 
-	if (test_bit(COMMAND_PENDING, &ua->flags) &&
-	    cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE))
+	if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags))
+		complete(&ua->complete);
+	if (cci & UCSI_CCI_COMMAND_COMPLETE &&
+	    test_bit(COMMAND_PENDING, &ua->flags))
 		complete(&ua->complete);
 }
 
@@ -151,6 +223,7 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
 	const struct ucsi_operations *ops = &ucsi_acpi_ops;
+	const struct dmi_system_id *id;
 	struct ucsi_acpi *ua;
 	struct resource *res;
 	acpi_status status;
@@ -180,8 +253,9 @@ static int ucsi_acpi_probe(struct platform_device *pdev)
 	init_completion(&ua->complete);
 	ua->dev = &pdev->dev;
 
-	if (dmi_check_system(zenbook_dmi_id))
-		ops = &ucsi_zenbook_ops;
+	id = dmi_first_match(ucsi_acpi_quirks);
+	if (id)
+		ops = id->driver_data;
 
 	ua->ucsi = ucsi_create(&pdev->dev, ops);
 	if (IS_ERR(ua->ucsi))
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index 53a7ede8556d..faccc942b381 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -301,6 +301,7 @@ static const struct of_device_id pmic_glink_ucsi_of_quirks[] = {
 	{ .compatible = "qcom,sc8180x-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{ .compatible = "qcom,sc8280xp-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{ .compatible = "qcom,sm8350-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
+	{ .compatible = "qcom,sm8550-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, },
 	{}
 };
 
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index 1183e7a871f8..46823c2e2ba1 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -2399,11 +2399,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
 	int resize, ret, old_userfont, old_width, old_height, old_charcount;
-	char *old_data = NULL;
+	u8 *old_data = vc->vc_font.data;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
-	if (p->userfont)
-		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
 	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
@@ -2437,13 +2435,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		update_screen(vc);
 	}
 
-	if (old_data && (--REFCOUNT(old_data) == 0))
+	if (old_userfont && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
 
 err_out:
 	p->fontdata = old_data;
-	vc->vc_font.data = (void *)old_data;
+	vc->vc_font.data = old_data;
 
 	if (userfont) {
 		p->userfont = old_userfont;
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index c26ee6fd73c9..8fdccf033b2d 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1010,8 +1010,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 			goto getmem_done;
 		}
 		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
-	} else {
-		goto err1;
 	}
 
 	/*
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 7d22051b15a2..d78fe7137799 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -512,7 +512,6 @@ config S3C2410_WATCHDOG
 	tristate "S3C6410/S5Pv210/Exynos Watchdog"
 	depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST
 	select WATCHDOG_CORE
-	select MFD_SYSCON if ARCH_EXYNOS
 	help
 	  Watchdog timer block in the Samsung S3C64xx, S5Pv210 and Exynos
 	  SoCs. This will reboot the system when the timer expires with
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 349d30462c8c..686cf544d0ae 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -24,9 +24,9 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 #include <linux/delay.h>
+#include <linux/soc/samsung/exynos-pmu.h>
 
 #define S3C2410_WTCON		0x00
 #define S3C2410_WTDAT		0x04
@@ -699,11 +699,11 @@ static int s3c2410wdt_probe(struct platform_device *pdev)
 		return ret;
 
 	if (wdt->drv_data->quirks & QUIRKS_HAVE_PMUREG) {
-		wdt->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node,
-						"samsung,syscon-phandle");
+		wdt->pmureg = exynos_get_pmu_regmap_by_phandle(dev->of_node,
+						 "samsung,syscon-phandle");
 		if (IS_ERR(wdt->pmureg))
 			return dev_err_probe(dev, PTR_ERR(wdt->pmureg),
-					     "syscon regmap lookup failed.\n");
+					     "PMU regmap lookup failed.\n");
 	}
 
 	wdt_irq = platform_get_irq(pdev, 0);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b8cfea7812d6..2faa4bf78c7a 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -923,8 +923,8 @@ static void shutdown_pirq(struct irq_data *data)
 		return;
 
 	do_mask(info, EVT_MASK_REASON_EXPLICIT);
-	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
+	xen_evtchn_close(evtchn);
 }
 
 static void enable_pirq(struct irq_data *data)
@@ -956,6 +956,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 {
 	evtchn_port_t evtchn;
+	bool close_evtchn = false;
 
 	if (!info) {
 		xen_irq_free_desc(irq);
@@ -975,7 +976,7 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 		struct xenbus_device *dev;
 
 		if (!info->is_static)
-			xen_evtchn_close(evtchn);
+			close_evtchn = true;
 
 		switch (info->type) {
 		case IRQT_VIRQ:
@@ -995,6 +996,9 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
 		}
 
 		xen_irq_info_cleanup(info);
+
+		if (close_evtchn)
+			xen_evtchn_close(evtchn);
 	}
 
 	xen_free_irq(info);
@@ -2216,7 +2220,7 @@ static __init void xen_alloc_callback_vector(void)
 		return;
 
 	pr_info("Xen HVM callback vector for event delivery is enabled\n");
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_xen_hvm_callback);
+	sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_xen_hvm_callback);
 }
 #else
 void xen_setup_callback_vector(void) {}
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index 26ffb8755ffb..f93f73ecefee 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		rc = -EFAULT;
 		goto out_free;
 	}
-	if (copy_to_user(arg->gref_ids, gref_ids,
+	if (copy_to_user(arg->gref_ids_flex, gref_ids,
 			sizeof(gref_ids[0]) * op.count)) {
 		rc = -EFAULT;
 		goto out_free;
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index 508655273145..c63f317e3df3 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -65,7 +65,7 @@ struct pcpu {
 	uint32_t flags;
 };
 
-static struct bus_type xen_pcpu_subsys = {
+static const struct bus_type xen_pcpu_subsys = {
 	.name = "xen_cpu",
 	.dev_name = "xen_cpu",
 };
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 35b6e306026a..67dfa4778864 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1223,18 +1223,13 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
 	kioreq->ioreq = (struct ioreq *)(page_to_virt(pages[0]));
 	mmap_write_unlock(mm);
 
-	size = sizeof(*ports) * kioreq->vcpus;
-	ports = kzalloc(size, GFP_KERNEL);
-	if (!ports) {
-		ret = -ENOMEM;
+	ports = memdup_array_user(u64_to_user_ptr(ioeventfd->ports),
+				  kioreq->vcpus, sizeof(*ports));
+	if (IS_ERR(ports)) {
+		ret = PTR_ERR(ports);
 		goto error_kfree;
 	}
 
-	if (copy_from_user(ports, u64_to_user_ptr(ioeventfd->ports), size)) {
-		ret = -EFAULT;
-		goto error_kfree_ports;
-	}
-
 	for (i = 0; i < kioreq->vcpus; i++) {
 		kioreq->ports[i].vcpu = i;
 		kioreq->ports[i].port = ports[i];
@@ -1256,7 +1251,7 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
 error_unbind:
 	while (--i >= 0)
 		unbind_from_irqhandler(irq_from_evtchn(ports[i]), &kioreq->ports[i]);
-error_kfree_ports:
+
 	kfree(ports);
 error_kfree:
 	kfree(kioreq);
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index 8cd583db20b1..b293d7652f15 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -237,7 +237,7 @@ static const struct attribute_group *balloon_groups[] = {
 	NULL
 };
 
-static struct bus_type balloon_subsys = {
+static const struct bus_type balloon_subsys = {
 	.name = BALLOON_CLASS_NAME,
 	.dev_name = BALLOON_CLASS_NAME,
 };
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 32835b4b9bc5..51b3124b0d56 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -116,14 +116,15 @@ EXPORT_SYMBOL_GPL(xenbus_strstate);
  * @dev: xenbus device
  * @path: path to watch
  * @watch: watch to register
+ * @will_handle: events queuing determine callback
  * @callback: callback to register
  *
  * Register a @watch on the given path, using the given xenbus_watch structure
- * for storage, and the given @callback function as the callback.  On success,
- * the given @path will be saved as @watch->node, and remains the
- * caller's to free.  On error, @watch->node will
- * be NULL, the device will switch to %XenbusStateClosing, and the error will
- * be saved in the store.
+ * for storage, @will_handle function as the callback to determine if each
+ * event need to be queued, and the given @callback function as the callback.
+ * On success, the given @path will be saved as @watch->node, and remains the
+ * caller's to free.  On error, @watch->node will be NULL, the device will
+ * switch to %XenbusStateClosing, and the error will be saved in the store.
  *
  * Returns: %0 on success or -errno on error
  */
@@ -158,11 +159,13 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path);
  * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path
  * @dev: xenbus device
  * @watch: watch to register
+ * @will_handle: events queuing determine callback
  * @callback: callback to register
  * @pathfmt: format of path to watch
  *
  * Register a watch on the given @path, using the given xenbus_watch
- * structure for storage, and the given @callback function as the
+ * structure for storage, @will_handle function as the callback to determine if
+ * each event need to be queued, and the given @callback function as the
  * callback.  On success, the watched path (@path/@path2) will be saved
  * as @watch->node, and becomes the caller's to kfree().
  * On error, watch->node will be NULL, so the caller has nothing to
diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c
index 025edfccedcf..f49d19977e82 100644
--- a/drivers/zorro/zorro-driver.c
+++ b/drivers/zorro/zorro-driver.c
@@ -150,7 +150,7 @@ static int zorro_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct bus_type zorro_bus_type = {
+const struct bus_type zorro_bus_type = {
 	.name		= "zorro",
 	.dev_name	= "zorro",
 	.dev_groups	= zorro_device_attribute_groups,
diff --git a/drivers/zorro/zorro.h b/drivers/zorro/zorro.h
index f84df9fb4c20..df44e35203fd 100644
--- a/drivers/zorro/zorro.h
+++ b/drivers/zorro/zorro.h
@@ -4,7 +4,7 @@
      *  Zorro bus
      */
 
-extern struct bus_type zorro_bus_type;
+extern const struct bus_type zorro_bus_type;
 
 
 #ifdef CONFIG_ZORRO_NAMES
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index bae330c2f0cf..abdbbaee5184 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -107,7 +107,7 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
 
 	p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
@@ -121,13 +121,12 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	struct p9_fid *fid;
 	uint8_t status = P9_LOCK_ERROR;
 	int res = 0;
-	unsigned char fl_type;
 	struct v9fs_session_info *v9ses;
 
 	fid = filp->private_data;
 	BUG_ON(fid == NULL);
 
-	BUG_ON((fl->fl_flags & FL_POSIX) != FL_POSIX);
+	BUG_ON((fl->c.flc_flags & FL_POSIX) != FL_POSIX);
 
 	res = locks_lock_file_wait(filp, fl);
 	if (res < 0)
@@ -136,7 +135,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	/* convert posix lock to p9 tlock args */
 	memset(&flock, 0, sizeof(flock));
 	/* map the lock type */
-	switch (fl->fl_type) {
+	switch (fl->c.flc_type) {
 	case F_RDLCK:
 		flock.type = P9_LOCK_TYPE_RDLCK;
 		break;
@@ -152,7 +151,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		flock.length = 0;
 	else
 		flock.length = fl->fl_end - fl->fl_start + 1;
-	flock.proc_id = fl->fl_pid;
+	flock.proc_id = fl->c.flc_pid;
 	flock.client_id = fid->clnt->name;
 	if (IS_SETLKW(cmd))
 		flock.flags = P9_LOCK_FLAGS_BLOCK;
@@ -207,12 +206,13 @@ out_unlock:
 	 * incase server returned error for lock request, revert
 	 * it locally
 	 */
-	if (res < 0 && fl->fl_type != F_UNLCK) {
-		fl_type = fl->fl_type;
-		fl->fl_type = F_UNLCK;
+	if (res < 0 && fl->c.flc_type != F_UNLCK) {
+		unsigned char type = fl->c.flc_type;
+
+		fl->c.flc_type = F_UNLCK;
 		/* Even if this fails we want to return the remote error */
 		locks_lock_file_wait(filp, fl);
-		fl->fl_type = fl_type;
+		fl->c.flc_type = type;
 	}
 	if (flock.client_id != fid->clnt->name)
 		kfree(flock.client_id);
@@ -234,7 +234,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 	 * if we have a conflicting lock locally, no need to validate
 	 * with server
 	 */
-	if (fl->fl_type != F_UNLCK)
+	if (fl->c.flc_type != F_UNLCK)
 		return res;
 
 	/* convert posix lock to p9 tgetlock args */
@@ -245,7 +245,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 		glock.length = 0;
 	else
 		glock.length = fl->fl_end - fl->fl_start + 1;
-	glock.proc_id = fl->fl_pid;
+	glock.proc_id = fl->c.flc_pid;
 	glock.client_id = fid->clnt->name;
 
 	res = p9_client_getlock_dotl(fid, &glock);
@@ -254,13 +254,13 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:
-		fl->fl_type = F_RDLCK;
+		fl->c.flc_type = F_RDLCK;
 		break;
 	case P9_LOCK_TYPE_WRLCK:
-		fl->fl_type = F_WRLCK;
+		fl->c.flc_type = F_WRLCK;
 		break;
 	case P9_LOCK_TYPE_UNLCK:
-		fl->fl_type = F_UNLCK;
+		fl->c.flc_type = F_UNLCK;
 		break;
 	}
 	if (glock.type != P9_LOCK_TYPE_UNLCK) {
@@ -269,7 +269,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 			fl->fl_end = OFFSET_MAX;
 		else
 			fl->fl_end = glock.start + glock.length - 1;
-		fl->fl_pid = -glock.proc_id;
+		fl->c.flc_pid = -glock.proc_id;
 	}
 out:
 	if (glock.client_id != fid->clnt->name)
@@ -293,7 +293,7 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
 	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
 		 filp, cmd, fl, filp);
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
@@ -324,16 +324,16 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd,
 	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
 		 filp, cmd, fl, filp);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		goto out_err;
 
-	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->c.flc_type != F_UNLCK) {
 		filemap_write_and_wait(inode->i_mapping);
 		invalidate_mapping_pages(&inode->i_data, 0, -1);
 	}
 	/* Convert flock to posix lock */
-	fl->fl_flags |= FL_POSIX;
-	fl->fl_flags ^= FL_FLOCK;
+	fl->c.flc_flags |= FL_POSIX;
+	fl->c.flc_flags ^= FL_FLOCK;
 
 	if (IS_SETLK(cmd) | IS_SETLKW(cmd))
 		ret = v9fs_file_do_lock(filp, cmd, fl);
diff --git a/fs/Kconfig b/fs/Kconfig
index 89fdbefd1075..4bc7dd420874 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -162,7 +162,6 @@ menu "DOS/FAT/EXFAT/NT Filesystems"
 
 source "fs/fat/Kconfig"
 source "fs/exfat/Kconfig"
-source "fs/ntfs/Kconfig"
 source "fs/ntfs3/Kconfig"
 
 endmenu
@@ -174,6 +173,13 @@ source "fs/proc/Kconfig"
 source "fs/kernfs/Kconfig"
 source "fs/sysfs/Kconfig"
 
+config FS_PID
+	bool "Pseudo filesystem for process file descriptors"
+	depends on 64BIT
+	default y
+	help
+	  Pidfs implements advanced features for process file descriptors.
+
 config TMPFS
 	bool "Tmpfs virtual memory file system support (former shm fs)"
 	depends on SHMEM
diff --git a/fs/Makefile b/fs/Makefile
index c09016257f05..6ecc9b0a53f2 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -15,7 +15,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
 		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
-		kernel_read_file.o mnt_idmapping.o remap_range.o
+		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o
 
 obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o
@@ -91,7 +91,6 @@ obj-y				+= unicode/
 obj-$(CONFIG_SYSV_FS)		+= sysv/
 obj-$(CONFIG_SMBFS)		+= smb/
 obj-$(CONFIG_HPFS_FS)		+= hpfs/
-obj-$(CONFIG_NTFS_FS)		+= ntfs/
 obj-$(CONFIG_NTFS3_FS)		+= ntfs3/
 obj-$(CONFIG_UFS_FS)		+= ufs/
 obj-$(CONFIG_EFS_FS)		+= efs/
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 60685ec76d98..2e612834329a 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -105,6 +105,7 @@ struct affs_sb_info {
 	int work_queued;		/* non-zero delayed work is queued */
 	struct delayed_work sb_work;	/* superblock flush delayed work */
 	spinlock_t work_lock;		/* protects sb_work and work_queued */
+	struct rcu_head rcu;
 };
 
 #define AFFS_MOUNT_SF_INTL		0x0001 /* International filesystem. */
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 58b391446ae1..3c5821339609 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -130,8 +130,7 @@ static int __init init_inodecache(void)
 {
 	affs_inode_cachep = kmem_cache_create("affs_inode_cache",
 					     sizeof(struct affs_inode_info),
-					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+					     0, (SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT),
 					     init_once);
 	if (affs_inode_cachep == NULL)
 		return -ENOMEM;
@@ -640,7 +639,7 @@ static void affs_kill_sb(struct super_block *sb)
 		affs_brelse(sbi->s_root_bh);
 		kfree(sbi->s_prefix);
 		mutex_destroy(&sbi->s_bmlock);
-		kfree(sbi);
+		kfree_rcu(sbi, rcu);
 	}
 }
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index b5b8de521f99..8a67fc427e74 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -479,8 +479,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 		    dire->u.name[0] == '.' &&
 		    ctx->actor != afs_lookup_filldir &&
 		    ctx->actor != afs_lookup_one_filldir &&
-		    memcmp(dire->u.name, ".__afs", 6) == 0)
+		    memcmp(dire->u.name, ".__afs", 6) == 0) {
+			ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent);
 			continue;
+		}
 
 		/* found the next entry */
 		if (!dir_emit(ctx, dire->u.name, nlen,
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 3d33b221d9ca..ef2cc8f565d2 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -417,13 +417,17 @@ static void afs_add_open_mmap(struct afs_vnode *vnode)
 
 static void afs_drop_open_mmap(struct afs_vnode *vnode)
 {
-	if (!atomic_dec_and_test(&vnode->cb_nr_mmap))
+	if (atomic_add_unless(&vnode->cb_nr_mmap, -1, 1))
 		return;
 
 	down_write(&vnode->volume->open_mmaps_lock);
 
-	if (atomic_read(&vnode->cb_nr_mmap) == 0)
+	read_seqlock_excl(&vnode->cb_lock);
+	// the only place where ->cb_nr_mmap may hit 0
+	// see __afs_break_callback() for the other side...
+	if (atomic_dec_and_test(&vnode->cb_nr_mmap))
 		list_del_init(&vnode->cb_mmap_link);
+	read_sequnlock_excl(&vnode->cb_lock);
 
 	up_write(&vnode->volume->open_mmaps_lock);
 	flush_work(&vnode->cb_work);
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 9c6dea3139f5..f0e96a35093f 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -93,13 +93,13 @@ static void afs_grant_locks(struct afs_vnode *vnode)
 	bool exclusive = (vnode->lock_type == AFS_LOCK_WRITE);
 
 	list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) {
-		if (!exclusive && p->fl_type == F_WRLCK)
+		if (!exclusive && lock_is_write(p))
 			continue;
 
 		list_move_tail(&p->fl_u.afs.link, &vnode->granted_locks);
 		p->fl_u.afs.state = AFS_LOCK_GRANTED;
 		trace_afs_flock_op(vnode, p, afs_flock_op_grant);
-		wake_up(&p->fl_wait);
+		locks_wake_up(p);
 	}
 }
 
@@ -112,25 +112,24 @@ static void afs_next_locker(struct afs_vnode *vnode, int error)
 {
 	struct file_lock *p, *_p, *next = NULL;
 	struct key *key = vnode->lock_key;
-	unsigned int fl_type = F_RDLCK;
+	unsigned int type = F_RDLCK;
 
 	_enter("");
 
 	if (vnode->lock_type == AFS_LOCK_WRITE)
-		fl_type = F_WRLCK;
+		type = F_WRLCK;
 
 	list_for_each_entry_safe(p, _p, &vnode->pending_locks, fl_u.afs.link) {
 		if (error &&
-		    p->fl_type == fl_type &&
-		    afs_file_key(p->fl_file) == key) {
+		    p->c.flc_type == type &&
+		    afs_file_key(p->c.flc_file) == key) {
 			list_del_init(&p->fl_u.afs.link);
 			p->fl_u.afs.state = error;
-			wake_up(&p->fl_wait);
+			locks_wake_up(p);
 		}
 
 		/* Select the next locker to hand off to. */
-		if (next &&
-		    (next->fl_type == F_WRLCK || p->fl_type == F_RDLCK))
+		if (next && (lock_is_write(next) || lock_is_read(p)))
 			continue;
 		next = p;
 	}
@@ -142,7 +141,7 @@ static void afs_next_locker(struct afs_vnode *vnode, int error)
 		afs_set_lock_state(vnode, AFS_VNODE_LOCK_SETTING);
 		next->fl_u.afs.state = AFS_LOCK_YOUR_TRY;
 		trace_afs_flock_op(vnode, next, afs_flock_op_wake);
-		wake_up(&next->fl_wait);
+		locks_wake_up(next);
 	} else {
 		afs_set_lock_state(vnode, AFS_VNODE_LOCK_NONE);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_no_lockers, 0);
@@ -166,7 +165,7 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode)
 			       struct file_lock, fl_u.afs.link);
 		list_del_init(&p->fl_u.afs.link);
 		p->fl_u.afs.state = -ENOENT;
-		wake_up(&p->fl_wait);
+		locks_wake_up(p);
 	}
 
 	key_put(vnode->lock_key);
@@ -464,14 +463,14 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%llu-%llu,%u,%u",
 	       vnode->fid.vid, vnode->fid.vnode,
-	       fl->fl_start, fl->fl_end, fl->fl_type, mode);
+	       fl->fl_start, fl->fl_end, fl->c.flc_type, mode);
 
 	fl->fl_ops = &afs_lock_ops;
 	INIT_LIST_HEAD(&fl->fl_u.afs.link);
 	fl->fl_u.afs.state = AFS_LOCK_PENDING;
 
 	partial = (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX);
-	type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
+	type = lock_is_read(fl) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
 	if (mode == afs_flock_mode_write && partial)
 		type = AFS_LOCK_WRITE;
 
@@ -524,7 +523,7 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl)
 	}
 
 	if (vnode->lock_state == AFS_VNODE_LOCK_NONE &&
-	    !(fl->fl_flags & FL_SLEEP)) {
+	    !(fl->c.flc_flags & FL_SLEEP)) {
 		ret = -EAGAIN;
 		if (type == AFS_LOCK_READ) {
 			if (vnode->status.lock_count == -1)
@@ -621,7 +620,7 @@ skip_server_lock:
 	return 0;
 
 lock_is_contended:
-	if (!(fl->fl_flags & FL_SLEEP)) {
+	if (!(fl->c.flc_flags & FL_SLEEP)) {
 		list_del_init(&fl->fl_u.afs.link);
 		afs_next_locker(vnode, 0);
 		ret = -EAGAIN;
@@ -641,7 +640,7 @@ need_to_wait:
 	spin_unlock(&vnode->lock);
 
 	trace_afs_flock_ev(vnode, fl, afs_flock_waiting, 0);
-	ret = wait_event_interruptible(fl->fl_wait,
+	ret = wait_event_interruptible(fl->c.flc_wait,
 				       fl->fl_u.afs.state != AFS_LOCK_PENDING);
 	trace_afs_flock_ev(vnode, fl, afs_flock_waited, ret);
 
@@ -704,7 +703,8 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl)
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	int ret;
 
-	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type);
+	_enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode,
+	       fl->c.flc_type);
 
 	trace_afs_flock_op(vnode, fl, afs_flock_op_unlock);
 
@@ -730,11 +730,11 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 	if (vnode->lock_state == AFS_VNODE_LOCK_DELETED)
 		return -ENOENT;
 
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 
 	/* check local lock records first */
 	posix_test_lock(file, fl);
-	if (fl->fl_type == F_UNLCK) {
+	if (lock_is_unlock(fl)) {
 		/* no local locks; consult the server */
 		ret = afs_fetch_status(vnode, key, false, NULL);
 		if (ret < 0)
@@ -743,18 +743,18 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl)
 		lock_count = READ_ONCE(vnode->status.lock_count);
 		if (lock_count != 0) {
 			if (lock_count > 0)
-				fl->fl_type = F_RDLCK;
+				fl->c.flc_type = F_RDLCK;
 			else
-				fl->fl_type = F_WRLCK;
+				fl->c.flc_type = F_WRLCK;
 			fl->fl_start = 0;
 			fl->fl_end = OFFSET_MAX;
-			fl->fl_pid = 0;
+			fl->c.flc_pid = 0;
 		}
 	}
 
 	ret = 0;
 error:
-	_leave(" = %d [%hd]", ret, fl->fl_type);
+	_leave(" = %d [%hd]", ret, fl->c.flc_type);
 	return ret;
 }
 
@@ -769,7 +769,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%d,{t=%x,fl=%x,r=%Ld:%Ld}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
-	       fl->fl_type, fl->fl_flags,
+	       fl->c.flc_type, fl->c.flc_flags,
 	       (long long) fl->fl_start, (long long) fl->fl_end);
 
 	if (IS_GETLK(cmd))
@@ -778,7 +778,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl)
 	fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id);
 	trace_afs_flock_op(vnode, fl, afs_flock_op_lock);
 
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		ret = afs_do_unlk(file, fl);
 	else
 		ret = afs_do_setlk(file, fl);
@@ -804,7 +804,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	_enter("{%llx:%llu},%d,{t=%x,fl=%x}",
 	       vnode->fid.vid, vnode->fid.vnode, cmd,
-	       fl->fl_type, fl->fl_flags);
+	       fl->c.flc_type, fl->c.flc_flags);
 
 	/*
 	 * No BSD flocks over NFS allowed.
@@ -813,14 +813,14 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
 	 * Not sure whether that would be unique, though, or whether
 	 * that would break in other places.
 	 */
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	fl->fl_u.afs.debug_id = atomic_inc_return(&afs_file_lock_debug_id);
 	trace_afs_flock_op(vnode, fl, afs_flock_op_flock);
 
 	/* we're simulating flock() locks using posix locks on the server */
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		ret = afs_do_unlk(file, fl);
 	else
 		ret = afs_do_setlk(file, fl);
@@ -843,7 +843,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl)
  */
 static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file));
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->c.flc_file));
 
 	_enter("");
 
@@ -861,7 +861,7 @@ static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl)
  */
 static void afs_fl_release_private(struct file_lock *fl)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->fl_file));
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(fl->c.flc_file));
 
 	_enter("");
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 9c03fcf7ffaa..6ce5a612937c 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -321,8 +321,7 @@ struct afs_net {
 	struct list_head	fs_probe_slow;	/* List of afs_server to probe at 5m intervals */
 	struct hlist_head	fs_proc;	/* procfs servers list */
 
-	struct hlist_head	fs_addresses4;	/* afs_server (by lowest IPv4 addr) */
-	struct hlist_head	fs_addresses6;	/* afs_server (by lowest IPv6 addr) */
+	struct hlist_head	fs_addresses;	/* afs_server (by lowest IPv6 addr) */
 	seqlock_t		fs_addr_lock;	/* For fs_addresses[46] */
 
 	struct work_struct	fs_manager;
@@ -561,8 +560,7 @@ struct afs_server {
 	struct afs_server __rcu	*uuid_next;	/* Next server with same UUID */
 	struct afs_server	*uuid_prev;	/* Previous server with same UUID */
 	struct list_head	probe_link;	/* Link in net->fs_probe_list */
-	struct hlist_node	addr4_link;	/* Link in net->fs_addresses4 */
-	struct hlist_node	addr6_link;	/* Link in net->fs_addresses6 */
+	struct hlist_node	addr_link;	/* Link in net->fs_addresses6 */
 	struct hlist_node	proc_link;	/* Link in net->fs_proc */
 	struct list_head	volumes;	/* RCU list of afs_server_entry objects */
 	struct afs_server	*gc_next;	/* Next server in manager's list */
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 1b3bd21c168a..a14f6013e316 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -90,8 +90,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	INIT_LIST_HEAD(&net->fs_probe_slow);
 	INIT_HLIST_HEAD(&net->fs_proc);
 
-	INIT_HLIST_HEAD(&net->fs_addresses4);
-	INIT_HLIST_HEAD(&net->fs_addresses6);
+	INIT_HLIST_HEAD(&net->fs_addresses);
 	seqlock_init(&net->fs_addr_lock);
 
 	INIT_WORK(&net->fs_manager, afs_manage_servers);
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e169121f603e..038f9d0ae3af 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -38,7 +38,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer
 		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
-		hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
+		hlist_for_each_entry_rcu(server, &net->fs_addresses, addr_link) {
 			estate = rcu_dereference(server->endpoint_state);
 			alist = estate->addresses;
 			for (i = 0; i < alist->nr_addrs; i++)
@@ -177,10 +177,8 @@ added_dup:
 	 * bit, but anything we might want to do gets messy and memory
 	 * intensive.
 	 */
-	if (alist->nr_ipv4 > 0)
-		hlist_add_head_rcu(&server->addr4_link, &net->fs_addresses4);
-	if (alist->nr_addrs > alist->nr_ipv4)
-		hlist_add_head_rcu(&server->addr6_link, &net->fs_addresses6);
+	if (alist->nr_addrs > 0)
+		hlist_add_head_rcu(&server->addr_link, &net->fs_addresses);
 
 	write_sequnlock(&net->fs_addr_lock);
 
@@ -511,10 +509,8 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list)
 
 			list_del(&server->probe_link);
 			hlist_del_rcu(&server->proc_link);
-			if (!hlist_unhashed(&server->addr4_link))
-				hlist_del_rcu(&server->addr4_link);
-			if (!hlist_unhashed(&server->addr6_link))
-				hlist_del_rcu(&server->addr6_link);
+			if (!hlist_unhashed(&server->addr_link))
+				hlist_del_rcu(&server->addr_link);
 		}
 		write_sequnlock(&net->fs_lock);
 
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 020ecd45e476..af3a3f57c1b3 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -353,7 +353,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 {
 	struct afs_server_list *new, *old, *discard;
 	struct afs_vldb_entry *vldb;
-	char idbuf[16];
+	char idbuf[24];
 	int ret, idsz;
 
 	_enter("");
@@ -361,7 +361,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 	/* We look up an ID by passing it as a decimal string in the
 	 * operation's name parameter.
 	 */
-	idsz = sprintf(idbuf, "%llu", volume->vid);
+	idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid);
 
 	vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz);
 	if (IS_ERR(vldb)) {
diff --git a/fs/aio.c b/fs/aio.c
index bb2ff48991f3..9cdaa2faa536 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -589,13 +589,24 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
 
 void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
 {
-	struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
-	struct kioctx *ctx = req->ki_ctx;
+	struct aio_kiocb *req;
+	struct kioctx *ctx;
 	unsigned long flags;
 
+	/*
+	 * kiocb didn't come from aio or is neither a read nor a write, hence
+	 * ignore it.
+	 */
+	if (!(iocb->ki_flags & IOCB_AIO_RW))
+		return;
+
+	req = container_of(iocb, struct aio_kiocb, rw);
+
 	if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
 		return;
 
+	ctx = req->ki_ctx;
+
 	spin_lock_irqsave(&ctx->ctx_lock, flags);
 	list_add_tail(&req->ki_list, &ctx->active_reqs);
 	req->ki_cancel = cancel;
@@ -1509,7 +1520,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
 	req->ki_complete = aio_complete_rw;
 	req->private = NULL;
 	req->ki_pos = iocb->aio_offset;
-	req->ki_flags = req->ki_filp->f_iocb_flags;
+	req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW;
 	if (iocb->aio_flags & IOCB_FLAG_RESFD)
 		req->ki_flags |= IOCB_EVENTFD;
 	if (iocb->aio_flags & IOCB_FLAG_IOPRIO) {
diff --git a/fs/attr.c b/fs/attr.c
index 5a13f0c8495f..49d23b5dbab4 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -352,7 +352,7 @@ int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 EXPORT_SYMBOL(may_setattr);
 
 /**
- * notify_change - modify attributes of a filesytem object
+ * notify_change - modify attributes of a filesystem object
  * @idmap:	idmap of the mount the inode was found from
  * @dentry:	object affected
  * @attr:	new attributes
diff --git a/fs/backing-file.c b/fs/backing-file.c
index a681f38d84d8..740185198db3 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -325,9 +325,7 @@ EXPORT_SYMBOL_GPL(backing_file_mmap);
 
 static int __init backing_aio_init(void)
 {
-	backing_aio_cachep = kmem_cache_create("backing_aio",
-					       sizeof(struct backing_aio),
-					       0, SLAB_HWCACHE_ALIGN, NULL);
+	backing_aio_cachep = KMEM_CACHE(backing_aio, SLAB_HWCACHE_ALIGN);
 	if (!backing_aio_cachep)
 		return -ENOMEM;
 
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index b4dc319bcb2b..569b97904da4 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -68,9 +68,11 @@ void bch2_backpointer_to_text(struct printbuf *out, const struct bch_backpointer
 
 void bch2_backpointer_k_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
 {
-	prt_str(out, "bucket=");
-	bch2_bpos_to_text(out, bp_pos_to_bucket(c, k.k->p));
-	prt_str(out, " ");
+	if (bch2_dev_exists2(c, k.k->p.inode)) {
+		prt_str(out, "bucket=");
+		bch2_bpos_to_text(out, bp_pos_to_bucket(c, k.k->p));
+		prt_str(out, " ");
+	}
 
 	bch2_backpointer_to_text(out, bkey_s_c_to_backpointer(k).v);
 }
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index b80c6c9efd8c..69d0d60d50e3 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -1249,6 +1249,18 @@ static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
 	return stdio;
 }
 
+static inline unsigned metadata_replicas_required(struct bch_fs *c)
+{
+	return min(c->opts.metadata_replicas,
+		   c->opts.metadata_replicas_required);
+}
+
+static inline unsigned data_replicas_required(struct bch_fs *c)
+{
+	return min(c->opts.data_replicas,
+		   c->opts.data_replicas_required);
+}
+
 #define BKEY_PADDED_ONSTACK(key, pad)				\
 	struct { struct bkey_i key; __u64 key ## _pad[pad]; }
 
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 5467a8635be1..3ef338df82f5 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2156,7 +2156,9 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 		 * isn't monotonically increasing before FILTER_SNAPSHOTS, and
 		 * that's what we check against in extents mode:
 		 */
-		if (k.k->p.inode > end.inode)
+		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
+			     ? bkey_gt(k.k->p, end)
+			     : k.k->p.inode > end.inode))
 			goto end;
 
 		if (iter->update_path &&
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 17a5938aa71a..4530b14ff2c3 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -280,7 +280,8 @@ retry:
 				      writepoint_ptr(&c->btree_write_point),
 				      &devs_have,
 				      res->nr_replicas,
-				      c->opts.metadata_replicas_required,
+				      min(res->nr_replicas,
+					  c->opts.metadata_replicas_required),
 				      watermark, 0, cl, &wp);
 	if (unlikely(ret))
 		return ERR_PTR(ret);
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 73c12e565af5..27710cdd5710 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -303,18 +303,6 @@ void bch2_readahead(struct readahead_control *ractl)
 	darray_exit(&readpages_iter.folios);
 }
 
-static void __bchfs_readfolio(struct bch_fs *c, struct bch_read_bio *rbio,
-			     subvol_inum inum, struct folio *folio)
-{
-	bch2_folio_create(folio, __GFP_NOFAIL);
-
-	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
-	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
-	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
-
-	bch2_trans_run(c, (bchfs_read(trans, rbio, inum, NULL), 0));
-}
-
 static void bch2_read_single_folio_end_io(struct bio *bio)
 {
 	complete(bio->bi_private);
@@ -329,6 +317,9 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(done);
 
+	if (!bch2_folio_create(folio, GFP_KERNEL))
+		return -ENOMEM;
+
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
 	rbio = rbio_init(bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_KERNEL, &c->bio_read),
@@ -336,7 +327,11 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	rbio->bio.bi_private = &done;
 	rbio->bio.bi_end_io = bch2_read_single_folio_end_io;
 
-	__bchfs_readfolio(c, rbio, inode_inum(inode), folio);
+	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
+	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
+	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
+
+	bch2_trans_run(c, (bchfs_read(trans, rbio, inode_inum(inode), NULL), 0));
 	wait_for_completion(&done);
 
 	ret = blk_status_to_errno(rbio->bio.bi_status);
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index e3b219e19e10..33cb6da3a5ad 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -88,6 +88,8 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 		return ret;
 
 	shorten = iov_iter_count(iter) - round_up(ret, block_bytes(c));
+	if (shorten >= iter->count)
+		shorten = 0;
 	iter->count -= shorten;
 
 	bio = bio_alloc_bioset(NULL,
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 3a4c24c28e7f..3dc8630ff9fe 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -455,6 +455,7 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 	if (IS_ERR(victim))
 		return PTR_ERR(victim);
 
+	dir = d_inode(path.dentry);
 	if (victim->d_sb->s_fs_info != c) {
 		ret = -EXDEV;
 		goto err;
@@ -463,14 +464,13 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 		ret = -ENOENT;
 		goto err;
 	}
-	dir = d_inode(path.dentry);
 	ret = __bch2_unlink(dir, victim, true);
 	if (!ret) {
 		fsnotify_rmdir(dir, victim);
 		d_delete(victim);
 	}
-	inode_unlock(dir);
 err:
+	inode_unlock(dir);
 	dput(victim);
 	path_put(&path);
 	return ret;
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index ec419b8e2c43..77ae65542db9 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -435,7 +435,7 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir,
 		bch2_subvol_is_ro(c, inode->ei_subvol) ?:
 		__bch2_link(c, inode, dir, dentry);
 	if (unlikely(ret))
-		return ret;
+		return bch2_err_class(ret);
 
 	ihold(&inode->v);
 	d_instantiate(dentry, &inode->v);
@@ -487,8 +487,9 @@ static int bch2_unlink(struct inode *vdir, struct dentry *dentry)
 	struct bch_inode_info *dir= to_bch_ei(vdir);
 	struct bch_fs *c = dir->v.i_sb->s_fs_info;
 
-	return bch2_subvol_is_ro(c, dir->ei_subvol) ?:
+	int ret = bch2_subvol_is_ro(c, dir->ei_subvol) ?:
 		__bch2_unlink(vdir, dentry, false);
+	return bch2_err_class(ret);
 }
 
 static int bch2_symlink(struct mnt_idmap *idmap,
@@ -523,7 +524,7 @@ static int bch2_symlink(struct mnt_idmap *idmap,
 	return 0;
 err:
 	iput(&inode->v);
-	return ret;
+	return bch2_err_class(ret);
 }
 
 static int bch2_mkdir(struct mnt_idmap *idmap,
@@ -641,7 +642,7 @@ err:
 			   src_inode,
 			   dst_inode);
 
-	return ret;
+	return bch2_err_class(ret);
 }
 
 static void bch2_setattr_copy(struct mnt_idmap *idmap,
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index ef3a53f9045a..2c098ac017b3 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -1564,6 +1564,7 @@ CLOSURE_CALLBACK(bch2_write)
 	BUG_ON(!op->write_point.v);
 	BUG_ON(bkey_eq(op->pos, POS_MAX));
 
+	op->nr_replicas_required = min_t(unsigned, op->nr_replicas_required, op->nr_replicas);
 	op->start_time = local_clock();
 	bch2_keylist_init(&op->insert_keys, op->inline_keys);
 	wbio_init(bio)->put_bio = false;
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index bfd6585e746d..47805193f18c 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1478,6 +1478,8 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w)
 		c->opts.foreground_target;
 	unsigned i, replicas = 0, replicas_want =
 		READ_ONCE(c->opts.metadata_replicas);
+	unsigned replicas_need = min_t(unsigned, replicas_want,
+				       READ_ONCE(c->opts.metadata_replicas_required));
 
 	rcu_read_lock();
 retry:
@@ -1526,7 +1528,7 @@ done:
 
 	BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX);
 
-	return replicas >= c->opts.metadata_replicas_required ? 0 : -EROFS;
+	return replicas >= replicas_need ? 0 : -EROFS;
 }
 
 static void journal_buf_realloc(struct journal *j, struct journal_buf *buf)
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 820d25e19e5f..c33dca641575 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -205,7 +205,7 @@ void bch2_journal_space_available(struct journal *j)
 
 	j->can_discard = can_discard;
 
-	if (nr_online < c->opts.metadata_replicas_required) {
+	if (nr_online < metadata_replicas_required(c)) {
 		ret = JOURNAL_ERR_insufficient_devices;
 		goto out;
 	}
@@ -892,9 +892,11 @@ int bch2_journal_flush_device_pins(struct journal *j, int dev_idx)
 					 journal_seq_pin(j, seq)->devs);
 		seq++;
 
-		spin_unlock(&j->lock);
-		ret = bch2_mark_replicas(c, &replicas.e);
-		spin_lock(&j->lock);
+		if (replicas.e.nr_devs) {
+			spin_unlock(&j->lock);
+			ret = bch2_mark_replicas(c, &replicas.e);
+			spin_lock(&j->lock);
+		}
 	}
 	spin_unlock(&j->lock);
 err:
diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h
index b2be565bb8f2..64df11ab422b 100644
--- a/fs/bcachefs/mean_and_variance.h
+++ b/fs/bcachefs/mean_and_variance.h
@@ -17,7 +17,7 @@
  * Rust and rustc has issues with u128.
  */
 
-#if defined(__SIZEOF_INT128__) && defined(__KERNEL__)
+#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC)
 
 typedef struct {
 	unsigned __int128 v;
diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c
index accf246c3233..b27d22925929 100644
--- a/fs/bcachefs/printbuf.c
+++ b/fs/bcachefs/printbuf.c
@@ -56,6 +56,7 @@ void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list args)
 
 		va_copy(args2, args);
 		len = vsnprintf(out->buf + out->pos, printbuf_remaining(out), fmt, args2);
+		va_end(args2);
 	} while (len + 1 >= printbuf_remaining(out) &&
 		 !bch2_printbuf_make_room(out, len + 1));
 
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 9127d0e3ca2f..21e13bb4335b 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -577,8 +577,9 @@ u64 bch2_recovery_passes_from_stable(u64 v)
 
 static bool check_version_upgrade(struct bch_fs *c)
 {
-	unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version);
 	unsigned latest_version	= bcachefs_metadata_version_current;
+	unsigned latest_compatible = min(latest_version,
+					 bch2_latest_compatible_version(c->sb.version));
 	unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version;
 	unsigned new_version = 0;
 
@@ -597,7 +598,7 @@ static bool check_version_upgrade(struct bch_fs *c)
 			new_version = latest_version;
 			break;
 		case BCH_VERSION_UPGRADE_none:
-			new_version = old_version;
+			new_version = min(old_version, latest_version);
 			break;
 		}
 	}
@@ -774,7 +775,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 		goto err;
 	}
 
-	if (!(c->opts.nochanges && c->opts.norecovery)) {
+	if (!c->opts.nochanges) {
 		mutex_lock(&c->sb_lock);
 		bool write_sb = false;
 
@@ -804,7 +805,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 		if (bch2_check_version_downgrade(c)) {
 			struct printbuf buf = PRINTBUF;
 
-			prt_str(&buf, "Version downgrade required:\n");
+			prt_str(&buf, "Version downgrade required:");
 
 			__le64 passes = ext->recovery_passes_required[0];
 			bch2_sb_set_downgrade(c,
@@ -812,7 +813,7 @@ int bch2_fs_recovery(struct bch_fs *c)
 					BCH_VERSION_MINOR(c->sb.version));
 			passes = ext->recovery_passes_required[0] & ~passes;
 			if (passes) {
-				prt_str(&buf, "  running recovery passes: ");
+				prt_str(&buf, "\n  running recovery passes: ");
 				prt_bitflags(&buf, bch2_recovery_passes,
 					     bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
 			}
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index a45354d2acde..eff5ce18c69c 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -421,7 +421,7 @@ void bch2_dev_errors_reset(struct bch_dev *ca)
 	m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
 	for (unsigned i = 0; i < ARRAY_SIZE(m->errors_at_reset); i++)
 		m->errors_at_reset[i] = cpu_to_le64(atomic64_read(&ca->errors[i]));
-	m->errors_reset_time = ktime_get_real_seconds();
+	m->errors_reset_time = cpu_to_le64(ktime_get_real_seconds());
 
 	bch2_write_super(c);
 	mutex_unlock(&c->sb_lock);
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 45f67e8b29eb..ac6ba04d5521 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -728,7 +728,7 @@ static int check_snapshot(struct btree_trans *trans,
 		return 0;
 
 	memset(&s, 0, sizeof(s));
-	memcpy(&s, k.v, bkey_val_bytes(k.k));
+	memcpy(&s, k.v, min(sizeof(s), bkey_val_bytes(k.k)));
 
 	id = le32_to_cpu(s.parent);
 	if (id) {
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index d60c7d27a047..bd64eb68e84a 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -142,8 +142,8 @@ void bch2_sb_field_delete(struct bch_sb_handle *sb,
 void bch2_free_super(struct bch_sb_handle *sb)
 {
 	kfree(sb->bio);
-	if (!IS_ERR_OR_NULL(sb->bdev_handle))
-		bdev_release(sb->bdev_handle);
+	if (!IS_ERR_OR_NULL(sb->s_bdev_file))
+		fput(sb->s_bdev_file);
 	kfree(sb->holder);
 	kfree(sb->sb_name);
 
@@ -704,22 +704,22 @@ retry:
 	if (!opt_get(*opts, nochanges))
 		sb->mode |= BLK_OPEN_WRITE;
 
-	sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-	if (IS_ERR(sb->bdev_handle) &&
-	    PTR_ERR(sb->bdev_handle) == -EACCES &&
+	sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+	if (IS_ERR(sb->s_bdev_file) &&
+	    PTR_ERR(sb->s_bdev_file) == -EACCES &&
 	    opt_get(*opts, read_only)) {
 		sb->mode &= ~BLK_OPEN_WRITE;
 
-		sb->bdev_handle = bdev_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
-		if (!IS_ERR(sb->bdev_handle))
+		sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops);
+		if (!IS_ERR(sb->s_bdev_file))
 			opt_set(*opts, nochanges, true);
 	}
 
-	if (IS_ERR(sb->bdev_handle)) {
-		ret = PTR_ERR(sb->bdev_handle);
-		goto out;
+	if (IS_ERR(sb->s_bdev_file)) {
+		ret = PTR_ERR(sb->s_bdev_file);
+		goto err;
 	}
-	sb->bdev = sb->bdev_handle->bdev;
+	sb->bdev = file_bdev(sb->s_bdev_file);
 
 	ret = bch2_sb_realloc(sb, 0);
 	if (ret) {
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index b9911402b175..6b23e11825e6 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1428,10 +1428,10 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
 
 		required = max(!(flags & BCH_FORCE_IF_METADATA_DEGRADED)
 			       ? c->opts.metadata_replicas
-			       : c->opts.metadata_replicas_required,
+			       : metadata_replicas_required(c),
 			       !(flags & BCH_FORCE_IF_DATA_DEGRADED)
 			       ? c->opts.data_replicas
-			       : c->opts.data_replicas_required);
+			       : data_replicas_required(c));
 
 		return nr_rw >= required;
 	case BCH_MEMBER_STATE_failed:
diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h
index 0e5a14fc8e7f..ec784d975f66 100644
--- a/fs/bcachefs/super_types.h
+++ b/fs/bcachefs/super_types.h
@@ -4,7 +4,7 @@
 
 struct bch_sb_handle {
 	struct bch_sb		*sb;
-	struct bdev_handle	*bdev_handle;
+	struct file		*s_bdev_file;
 	struct block_device	*bdev;
 	char			*sb_name;
 	struct bio		*bio;
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index b1c867aa2b58..9220d7de10db 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -53,9 +53,9 @@ int bch2_run_thread_with_file(struct thread_with_file *thr,
 	if (ret)
 		goto err;
 
-	fd_install(fd, file);
 	get_task_struct(thr->task);
 	wake_up_process(thr->task);
+	fd_install(fd, file);
 	return fd;
 err:
 	if (fd >= 0)
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 56b815fd9fc6..3a32faa86b5c 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -289,7 +289,7 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigne
 	do {
 		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, skipnr + 1);
 	} while (nr_entries == stack->size &&
-		 !(ret = darray_make_room(stack, stack->size * 2)));
+		 !(ret = darray_make_room_gfp(stack, stack->size * 2, gfp)));
 
 	stack->nr = nr_entries;
 	up_read(&task->signal->exec_update_lock);
@@ -418,14 +418,15 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
 		bch2_quantiles_update(&stats->quantiles, duration);
 	}
 
-	if (time_after64(end, stats->last_event)) {
+	if (stats->last_event && time_after64(end, stats->last_event)) {
 		freq = end - stats->last_event;
 		mean_and_variance_update(&stats->freq_stats, freq);
 		mean_and_variance_weighted_update(&stats->freq_stats_weighted, freq);
 		stats->max_freq = max(stats->max_freq, freq);
 		stats->min_freq = min(stats->min_freq, freq);
-		stats->last_event = end;
 	}
+
+	stats->last_event = end;
 }
 
 static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c
index 1925a0919ca6..79026917db19 100644
--- a/fs/btrfs/accessors.c
+++ b/fs/btrfs/accessors.c
@@ -5,7 +5,8 @@
 
 #include <asm/unaligned.h>
 #include "messages.h"
-#include "ctree.h"
+#include "extent_io.h"
+#include "fs.h"
 #include "accessors.h"
 
 static bool check_setget_bounds(const struct extent_buffer *eb,
@@ -63,8 +64,8 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
 	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
 	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
 							 member_offset);\
-	const int unit_size = folio_size(token->eb->folios[0]);		\
-	const int unit_shift = folio_shift(token->eb->folios[0]);	\
+	const int unit_size = token->eb->folio_size;			\
+	const int unit_shift = token->eb->folio_shift;			\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = unit_size - oil;				\
@@ -94,7 +95,7 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
 	const unsigned long oil = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = folio_size(eb->folios[0]);		\
+	const int unit_size = eb->folio_size;				\
 	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = unit_size - oil;				\
@@ -117,8 +118,8 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
 	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
 	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
 							 member_offset);\
-	const int unit_size = folio_size(token->eb->folios[0]);		\
-	const int unit_shift = folio_shift(token->eb->folios[0]);	\
+	const int unit_size = token->eb->folio_size;			\
+	const int unit_shift = token->eb->folio_shift;			\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = unit_size - oil;				\
@@ -151,7 +152,7 @@ void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
 	const unsigned long oil = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = folio_size(eb->folios[0]);		\
+	const int unit_size = eb->folio_size;				\
 	char *kaddr = folio_address(eb->folios[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = unit_size - oil;				\
diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index ed7aa32972ad..6fce3e8d3dac 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -3,8 +3,17 @@
 #ifndef BTRFS_ACCESSORS_H
 #define BTRFS_ACCESSORS_H
 
-#include <linux/stddef.h>
 #include <asm/unaligned.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/align.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct extent_buffer;
 
 struct btrfs_map_token {
 	struct extent_buffer *eb;
@@ -844,45 +853,6 @@ static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
 	write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
 }
 
-static inline void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
-			       const struct btrfs_disk_balance_args *disk)
-{
-	memset(cpu, 0, sizeof(*cpu));
-
-	cpu->profiles = le64_to_cpu(disk->profiles);
-	cpu->usage = le64_to_cpu(disk->usage);
-	cpu->devid = le64_to_cpu(disk->devid);
-	cpu->pstart = le64_to_cpu(disk->pstart);
-	cpu->pend = le64_to_cpu(disk->pend);
-	cpu->vstart = le64_to_cpu(disk->vstart);
-	cpu->vend = le64_to_cpu(disk->vend);
-	cpu->target = le64_to_cpu(disk->target);
-	cpu->flags = le64_to_cpu(disk->flags);
-	cpu->limit = le64_to_cpu(disk->limit);
-	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
-	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
-}
-
-static inline void btrfs_cpu_balance_args_to_disk(
-				struct btrfs_disk_balance_args *disk,
-				const struct btrfs_balance_args *cpu)
-{
-	memset(disk, 0, sizeof(*disk));
-
-	disk->profiles = cpu_to_le64(cpu->profiles);
-	disk->usage = cpu_to_le64(cpu->usage);
-	disk->devid = cpu_to_le64(cpu->devid);
-	disk->pstart = cpu_to_le64(cpu->pstart);
-	disk->pend = cpu_to_le64(cpu->pend);
-	disk->vstart = cpu_to_le64(cpu->vstart);
-	disk->vend = cpu_to_le64(cpu->vend);
-	disk->target = cpu_to_le64(cpu->target);
-	disk->flags = cpu_to_le64(cpu->flags);
-	disk->limit = cpu_to_le64(cpu->limit);
-	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
-	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
-}
-
 /* struct btrfs_super_block */
 BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
 BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 7427449a04a3..e0ba00d64ea0 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -12,7 +12,6 @@
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
 #include "ctree.h"
-#include "btrfs_inode.h"
 #include "xattr.h"
 #include "acl.h"
 
diff --git a/fs/btrfs/acl.h b/fs/btrfs/acl.h
index a270e71ec05f..48b9ddae4a46 100644
--- a/fs/btrfs/acl.h
+++ b/fs/btrfs/acl.h
@@ -3,8 +3,15 @@
 #ifndef BTRFS_ACL_H
 #define BTRFS_ACL_H
 
+struct posix_acl;
+struct inode;
+struct btrfs_trans_handle;
+
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 
+struct mnt_idmap;
+struct dentry;
+
 struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
 int btrfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		  struct posix_acl *acl, int type);
@@ -13,6 +20,10 @@ int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
 
 #else
 
+#include <linux/errno.h>
+
+struct btrfs_trans_handle;
+
 #define btrfs_get_acl NULL
 #define btrfs_set_acl NULL
 static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 9e261aac671e..361a866c1995 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -11,7 +11,6 @@
 #include <linux/freezer.h>
 #include <trace/events/btrfs.h>
 #include "async-thread.h"
-#include "ctree.h"
 
 enum {
 	WORK_DONE_BIT,
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 62b8a0d57898..04c2f3175828 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -7,11 +7,14 @@
 #ifndef BTRFS_ASYNC_THREAD_H
 #define BTRFS_ASYNC_THREAD_H
 
+#include <linux/compiler_types.h>
 #include <linux/workqueue.h>
+#include <linux/list.h>
 
 struct btrfs_fs_info;
 struct btrfs_workqueue;
 struct btrfs_work;
+
 typedef void (*btrfs_func_t)(struct btrfs_work *arg);
 typedef void (*btrfs_ordered_func_t)(struct btrfs_work *arg, bool);
 
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index beed7e459dab..c1e6a5bbeeaf 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -198,10 +198,7 @@ static struct kmem_cache *btrfs_prelim_ref_cache;
 int __init btrfs_prelim_ref_init(void)
 {
 	btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref",
-					sizeof(struct prelim_ref),
-					0,
-					SLAB_MEM_SPREAD,
-					NULL);
+					sizeof(struct prelim_ref), 0, 0, NULL);
 	if (!btrfs_prelim_ref_cache)
 		return -ENOMEM;
 	return 0;
@@ -1036,8 +1033,6 @@ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx,
 	slot = path->slots[0];
 
 	item_size = btrfs_item_size(leaf, slot);
-	BUG_ON(item_size < sizeof(*ei));
-
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 
 	if (ctx->check_extent_item) {
@@ -1435,8 +1430,10 @@ again:
 	if (ret < 0)
 		goto out;
 	if (ret == 0) {
-		/* This shouldn't happen, indicates a bug or fs corruption. */
-		ASSERT(ret != 0);
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
 		ret = -EUCLEAN;
 		goto out;
 	}
@@ -2225,6 +2222,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		return -EUCLEAN;
+	}
 
 	ret = btrfs_previous_extent_item(extent_root, path, 0);
 	if (ret) {
@@ -2247,7 +2251,6 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 
 	eb = path->nodes[0];
 	item_size = btrfs_item_size(eb, path->slots[0]);
-	BUG_ON(item_size < sizeof(*ei));
 
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
@@ -2850,6 +2853,16 @@ struct btrfs_backref_iter *btrfs_backref_iter_alloc(struct btrfs_fs_info *fs_inf
 	return ret;
 }
 
+static void btrfs_backref_iter_release(struct btrfs_backref_iter *iter)
+{
+	iter->bytenr = 0;
+	iter->item_ptr = 0;
+	iter->cur_ptr = 0;
+	iter->end_ptr = 0;
+	btrfs_release_path(iter->path);
+	memset(&iter->cur_key, 0, sizeof(iter->cur_key));
+}
+
 int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr)
 {
 	struct btrfs_fs_info *fs_info = iter->fs_info;
@@ -2868,6 +2881,10 @@ int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr)
 	if (ret < 0)
 		return ret;
 	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
 		ret = -EUCLEAN;
 		goto release;
 	}
@@ -2938,6 +2955,14 @@ release:
 	return ret;
 }
 
+static bool btrfs_backref_iter_is_inline_ref(struct btrfs_backref_iter *iter)
+{
+	if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY ||
+	    iter->cur_key.type == BTRFS_METADATA_ITEM_KEY)
+		return true;
+	return false;
+}
+
 /*
  * Go to the next backref item of current bytenr, can be either inlined or
  * keyed.
@@ -2950,7 +2975,7 @@ release:
  */
 int btrfs_backref_iter_next(struct btrfs_backref_iter *iter)
 {
-	struct extent_buffer *eb = btrfs_backref_get_eb(iter);
+	struct extent_buffer *eb = iter->path->nodes[0];
 	struct btrfs_root *extent_root;
 	struct btrfs_path *path = iter->path;
 	struct btrfs_extent_inline_ref *iref;
@@ -3038,6 +3063,19 @@ struct btrfs_backref_node *btrfs_backref_alloc_node(
 	return node;
 }
 
+void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_node *node)
+{
+	if (node) {
+		ASSERT(list_empty(&node->list));
+		ASSERT(list_empty(&node->lower));
+		ASSERT(node->eb == NULL);
+		cache->nr_nodes--;
+		btrfs_put_root(node->root);
+		kfree(node);
+	}
+}
+
 struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 		struct btrfs_backref_cache *cache)
 {
@@ -3049,6 +3087,52 @@ struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 	return edge;
 }
 
+void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_edge *edge)
+{
+	if (edge) {
+		cache->nr_edges--;
+		kfree(edge);
+	}
+}
+
+void btrfs_backref_unlock_node_buffer(struct btrfs_backref_node *node)
+{
+	if (node->locked) {
+		btrfs_tree_unlock(node->eb);
+		node->locked = 0;
+	}
+}
+
+void btrfs_backref_drop_node_buffer(struct btrfs_backref_node *node)
+{
+	if (node->eb) {
+		btrfs_backref_unlock_node_buffer(node);
+		free_extent_buffer(node->eb);
+		node->eb = NULL;
+	}
+}
+
+/*
+ * Drop the backref node from cache without cleaning up its children
+ * edges.
+ *
+ * This can only be called on node without parent edges.
+ * The children edges are still kept as is.
+ */
+void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
+			     struct btrfs_backref_node *node)
+{
+	ASSERT(list_empty(&node->upper));
+
+	btrfs_backref_drop_node_buffer(node);
+	list_del_init(&node->list);
+	list_del_init(&node->lower);
+	if (!RB_EMPTY_NODE(&node->rb_node))
+		rb_erase(&node->rb_node, &tree->rb_root);
+	btrfs_backref_free_node(tree, node);
+}
+
 /*
  * Drop the backref node from cache, also cleaning up all its
  * upper edges and any uncached nodes in the path.
@@ -3120,6 +3204,19 @@ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache)
 	ASSERT(!cache->nr_edges);
 }
 
+void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
+			     struct btrfs_backref_node *lower,
+			     struct btrfs_backref_node *upper,
+			     int link_which)
+{
+	ASSERT(upper && lower && upper->level == lower->level + 1);
+	edge->node[LOWER] = lower;
+	edge->node[UPPER] = upper;
+	if (link_which & LINK_LOWER)
+		list_add_tail(&edge->list[LOWER], &lower->upper);
+	if (link_which & LINK_UPPER)
+		list_add_tail(&edge->list[UPPER], &upper->lower);
+}
 /*
  * Handle direct tree backref
  *
@@ -3428,7 +3525,7 @@ int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans,
 		int type;
 
 		cond_resched();
-		eb = btrfs_backref_get_eb(iter);
+		eb = iter->path->nodes[0];
 
 		key.objectid = iter->bytenr;
 		if (btrfs_backref_iter_is_inline_ref(iter)) {
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index ab4ca0eda605..e8c22cccb5c1 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -6,11 +6,23 @@
 #ifndef BTRFS_BACKREF_H
 #define BTRFS_BACKREF_H
 
-#include <linux/btrfs.h>
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <uapi/linux/btrfs.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "messages.h"
-#include "ulist.h"
+#include "locking.h"
 #include "disk-io.h"
 #include "extent_io.h"
+#include "ctree.h"
+
+struct extent_inode_elem;
+struct ulist;
+struct btrfs_extent_item;
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
 
 /*
  * Used by implementations of iterate_extent_inodes_t (see definition below) to
@@ -271,22 +283,6 @@ struct btrfs_backref_iter {
 
 struct btrfs_backref_iter *btrfs_backref_iter_alloc(struct btrfs_fs_info *fs_info);
 
-static inline void btrfs_backref_iter_free(struct btrfs_backref_iter *iter)
-{
-	if (!iter)
-		return;
-	btrfs_free_path(iter->path);
-	kfree(iter);
-}
-
-static inline struct extent_buffer *btrfs_backref_get_eb(
-		struct btrfs_backref_iter *iter)
-{
-	if (!iter)
-		return NULL;
-	return iter->path->nodes[0];
-}
-
 /*
  * For metadata with EXTENT_ITEM key (non-skinny) case, the first inline data
  * is btrfs_tree_block_info, without a btrfs_extent_inline_ref header.
@@ -306,25 +302,6 @@ int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr);
 
 int btrfs_backref_iter_next(struct btrfs_backref_iter *iter);
 
-static inline bool btrfs_backref_iter_is_inline_ref(
-		struct btrfs_backref_iter *iter)
-{
-	if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY ||
-	    iter->cur_key.type == BTRFS_METADATA_ITEM_KEY)
-		return true;
-	return false;
-}
-
-static inline void btrfs_backref_iter_release(struct btrfs_backref_iter *iter)
-{
-	iter->bytenr = 0;
-	iter->item_ptr = 0;
-	iter->cur_ptr = 0;
-	iter->end_ptr = 0;
-	btrfs_release_path(iter->path);
-	memset(&iter->cur_key, 0, sizeof(iter->cur_key));
-}
-
 /*
  * Backref cache related structures
  *
@@ -452,83 +429,22 @@ struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 
 #define		LINK_LOWER	(1 << 0)
 #define		LINK_UPPER	(1 << 1)
-static inline void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
-					   struct btrfs_backref_node *lower,
-					   struct btrfs_backref_node *upper,
-					   int link_which)
-{
-	ASSERT(upper && lower && upper->level == lower->level + 1);
-	edge->node[LOWER] = lower;
-	edge->node[UPPER] = upper;
-	if (link_which & LINK_LOWER)
-		list_add_tail(&edge->list[LOWER], &lower->upper);
-	if (link_which & LINK_UPPER)
-		list_add_tail(&edge->list[UPPER], &upper->lower);
-}
-
-static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
-					   struct btrfs_backref_node *node)
-{
-	if (node) {
-		ASSERT(list_empty(&node->list));
-		ASSERT(list_empty(&node->lower));
-		ASSERT(node->eb == NULL);
-		cache->nr_nodes--;
-		btrfs_put_root(node->root);
-		kfree(node);
-	}
-}
-
-static inline void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
-					   struct btrfs_backref_edge *edge)
-{
-	if (edge) {
-		cache->nr_edges--;
-		kfree(edge);
-	}
-}
-
-static inline void btrfs_backref_unlock_node_buffer(
-		struct btrfs_backref_node *node)
-{
-	if (node->locked) {
-		btrfs_tree_unlock(node->eb);
-		node->locked = 0;
-	}
-}
 
-static inline void btrfs_backref_drop_node_buffer(
-		struct btrfs_backref_node *node)
-{
-	if (node->eb) {
-		btrfs_backref_unlock_node_buffer(node);
-		free_extent_buffer(node->eb);
-		node->eb = NULL;
-	}
-}
-
-/*
- * Drop the backref node from cache without cleaning up its children
- * edges.
- *
- * This can only be called on node without parent edges.
- * The children edges are still kept as is.
- */
-static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
-					   struct btrfs_backref_node *node)
-{
-	ASSERT(list_empty(&node->upper));
-
-	btrfs_backref_drop_node_buffer(node);
-	list_del_init(&node->list);
-	list_del_init(&node->lower);
-	if (!RB_EMPTY_NODE(&node->rb_node))
-		rb_erase(&node->rb_node, &tree->rb_root);
-	btrfs_backref_free_node(tree, node);
-}
+void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
+			     struct btrfs_backref_node *lower,
+			     struct btrfs_backref_node *upper,
+			     int link_which);
+void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_node *node);
+void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,
+			     struct btrfs_backref_edge *edge);
+void btrfs_backref_unlock_node_buffer(struct btrfs_backref_node *node);
+void btrfs_backref_drop_node_buffer(struct btrfs_backref_node *node);
 
 void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache,
 				struct btrfs_backref_node *node);
+void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
+			     struct btrfs_backref_node *node);
 
 void btrfs_backref_release_cache(struct btrfs_backref_cache *cache);
 
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 928f512cdb4a..477f350a8bd0 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -11,7 +11,6 @@
 #include "raid56.h"
 #include "async-thread.h"
 #include "dev-replace.h"
-#include "rcu-string.h"
 #include "zoned.h"
 #include "file-item.h"
 #include "raid-stripe-tree.h"
@@ -509,8 +508,6 @@ static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
 	if (!bioc) {
 		/* Single mirror read/write fast path. */
 		btrfs_bio(bio)->mirror_num = mirror_num;
-		if (bio_op(bio) != REQ_OP_READ)
-			btrfs_bio(bio)->orig_physical = smap->physical;
 		bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT;
 		if (bio_op(bio) != REQ_OP_READ)
 			btrfs_bio(bio)->orig_physical = smap->physical;
@@ -611,8 +608,20 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free)
 
 static bool should_async_write(struct btrfs_bio *bbio)
 {
+	bool auto_csum_mode = true;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct btrfs_fs_devices *fs_devices = bbio->fs_info->fs_devices;
+	enum btrfs_offload_csum_mode csum_mode = READ_ONCE(fs_devices->offload_csum_mode);
+
+	if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_OFF)
+		return false;
+
+	auto_csum_mode = (csum_mode == BTRFS_OFFLOAD_CSUM_AUTO);
+#endif
+
 	/* Submit synchronously if the checksum implementation is fast. */
-	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
+	if (auto_csum_mode && test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags))
 		return false;
 
 	/*
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index bbaed317161a..d9dd5276093d 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -7,12 +7,14 @@
 #ifndef BTRFS_BIO_H
 #define BTRFS_BIO_H
 
+#include <linux/types.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include "tree-checker.h"
 
 struct btrfs_bio;
 struct btrfs_fs_info;
+struct btrfs_inode;
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE	64
 
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index a9be9ac99222..5f7587ca1ca7 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -418,7 +418,7 @@ struct btrfs_caching_control *btrfs_get_caching_control(
 	return ctl;
 }
 
-void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
+static void btrfs_put_caching_control(struct btrfs_caching_control *ctl)
 {
 	if (refcount_dec_and_test(&ctl->count))
 		kfree(ctl);
@@ -1063,7 +1063,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	bool remove_rsv = false;
 
 	block_group = btrfs_lookup_block_group(fs_info, map->start);
-	BUG_ON(!block_group);
+	if (!block_group)
+		return -ENOENT;
+
 	BUG_ON(!block_group->ro);
 
 	trace_btrfs_remove_block_group(block_group);
@@ -1429,7 +1431,7 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	 * group in pinned_extents before we were able to clear the whole block
 	 * group range from pinned_extents. This means that task can lookup for
 	 * the block group after we unpinned it from pinned_extents and removed
-	 * it, leading to a BUG_ON() at unpin_extent_range().
+	 * it, leading to an error at unpin_extent_range().
 	 */
 	mutex_lock(&fs_info->unused_bg_unpin_mutex);
 	if (prev_trans) {
@@ -1455,6 +1457,7 @@ out:
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
+	LIST_HEAD(retry_list);
 	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
@@ -1476,6 +1479,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 	spin_lock(&fs_info->unused_bgs_lock);
 	while (!list_empty(&fs_info->unused_bgs)) {
+		u64 used;
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
@@ -1511,22 +1515,68 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			goto next;
 		}
 
+		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved || block_group->pinned ||
-		    block_group->used || block_group->ro ||
+		if (btrfs_is_block_group_used(block_group) || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
 			 * outstanding allocations in this block group.  We do
 			 * the ro check in case balance is currently acting on
 			 * this block group.
+			 *
+			 * Also bail out if this is the only block group for its
+			 * type, because otherwise we would lose profile
+			 * information from fs_info->avail_*_alloc_bits and the
+			 * next block group of this type would be created with a
+			 * "single" profile (even if we're in a raid fs) because
+			 * fs_info->avail_*_alloc_bits would be 0.
+			 */
+			trace_btrfs_skip_unused_block_group(block_group);
+			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+
+		/*
+		 * The block group may be unused but there may be space reserved
+		 * accounting with the existence of that block group, that is,
+		 * space_info->bytes_may_use was incremented by a task but no
+		 * space was yet allocated from the block group by the task.
+		 * That space may or may not be allocated, as we are generally
+		 * pessimistic about space reservation for metadata as well as
+		 * for data when using compression (as we reserve space based on
+		 * the worst case, when data can't be compressed, and before
+		 * actually attempting compression, before starting writeback).
+		 *
+		 * So check if the total space of the space_info minus the size
+		 * of this block group is less than the used space of the
+		 * space_info - if that's the case, then it means we have tasks
+		 * that might be relying on the block group in order to allocate
+		 * extents, and add back the block group to the unused list when
+		 * we finish, so that we retry later in case no tasks ended up
+		 * needing to allocate extents from the block group.
+		 */
+		used = btrfs_space_info_used(space_info, true);
+		if (space_info->total_bytes - block_group->length < used) {
+			/*
+			 * Add a reference for the list, compensate for the ref
+			 * drop under the "next" label for the
+			 * fs_info->unused_bgs list.
 			 */
+			btrfs_get_block_group(block_group);
+			list_add_tail(&block_group->bg_list, &retry_list);
+
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+
 		spin_unlock(&block_group->lock);
+		spin_unlock(&space_info->lock);
 
 		/* We don't want to force the issue, only flip if it's ok. */
 		ret = inc_block_group_ro(block_group, 0);
@@ -1650,12 +1700,16 @@ next:
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	return;
 
 flip_async:
 	btrfs_end_transaction(trans);
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	btrfs_put_block_group(block_group);
 	btrfs_discard_punt_unused_bgs_list(fs_info);
@@ -2684,6 +2738,37 @@ next:
 		btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+
+		/*
+		 * If the block group is still unused, add it to the list of
+		 * unused block groups. The block group may have been created in
+		 * order to satisfy a space reservation, in which case the
+		 * extent allocation only happens later. But often we don't
+		 * actually need to allocate space that we previously reserved,
+		 * so the block group may become unused for a long time. For
+		 * example for metadata we generally reserve space for a worst
+		 * possible scenario, but then don't end up allocating all that
+		 * space or none at all (due to no need to COW, extent buffers
+		 * were already COWed in the current transaction and still
+		 * unwritten, tree heights lower than the maximum possible
+		 * height, etc). For data we generally reserve the axact amount
+		 * of space we are going to allocate later, the exception is
+		 * when using compression, as we must reserve space based on the
+		 * uncompressed data size, because the compression is only done
+		 * when writeback triggered and we don't know how much space we
+		 * are actually going to need, so we reserve the uncompressed
+		 * size because the data may be uncompressible in the worst case.
+		 */
+		if (ret == 0) {
+			bool used;
+
+			spin_lock(&block_group->lock);
+			used = btrfs_is_block_group_used(block_group);
+			spin_unlock(&block_group->lock);
+
+			if (!used)
+				btrfs_mark_bg_unused(block_group);
+		}
 	}
 	btrfs_trans_release_chunk_metadata(trans);
 }
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c4a1f01cc1c2..85e2d4cd12dc 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -3,9 +3,22 @@
 #ifndef BTRFS_BLOCK_GROUP_H
 #define BTRFS_BLOCK_GROUP_H
 
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
+#include <linux/wait.h>
+#include <linux/sizes.h>
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "free-space-cache.h"
 
 struct btrfs_chunk_map;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_trans_handle;
 
 enum btrfs_disk_cache_state {
 	BTRFS_DC_WRITTEN,
@@ -257,6 +270,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
 	return (block_group->start + block_group->length);
 }
 
+static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg)
+{
+	lockdep_assert_held(&bg->lock);
+
+	return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0);
+}
+
 static inline bool btrfs_is_block_group_data_only(
 					struct btrfs_block_group *block_group)
 {
@@ -290,7 +310,6 @@ void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
 int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
-void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
 int btrfs_add_new_free_space(struct btrfs_block_group *block_group,
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index ceb5f586a2d5..95c174f9fd4f 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -6,7 +6,6 @@
 #include "space-info.h"
 #include "transaction.h"
 #include "block-group.h"
-#include "disk-io.h"
 #include "fs.h"
 #include "accessors.h"
 
@@ -494,7 +493,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
 
 	block_rsv = get_block_rsv(trans, root);
 
-	if (unlikely(block_rsv->size == 0))
+	if (unlikely(btrfs_block_rsv_size(block_rsv) == 0))
 		goto try_reserve;
 again:
 	ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize);
diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h
index b0bd12b8652f..1f53b967d069 100644
--- a/fs/btrfs/block-rsv.h
+++ b/fs/btrfs/block-rsv.h
@@ -3,8 +3,15 @@
 #ifndef BTRFS_BLOCK_RSV_H
 #define BTRFS_BLOCK_RSV_H
 
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/spinlock.h>
+
 struct btrfs_trans_handle;
 struct btrfs_root;
+struct btrfs_space_info;
+struct btrfs_block_rsv;
+struct btrfs_fs_info;
 enum btrfs_reserve_flush_enum;
 
 /*
@@ -101,4 +108,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv)
 	return data_race(rsv->full);
 }
 
+/*
+ * Get the reserved mount of a block reserve in a context where getting a stale
+ * value is acceptable, instead of accessing it directly and trigger data race
+ * warning from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->reserved;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
+/*
+ * Get the size of a block reserve in a context where getting a stale value is
+ * acceptable, instead of accessing it directly and trigger data race warning
+ * from KCSAN.
+ */
+static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv)
+{
+	u64 ret;
+
+	spin_lock(&rsv->lock);
+	ret = rsv->size;
+	spin_unlock(&rsv->lock);
+
+	return ret;
+}
+
 #endif /* BTRFS_BLOCK_RSV_H */
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7f7c5a92d2b8..100020ca4658 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -8,13 +8,32 @@
 
 #include <linux/hash.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/compiler.h>
 #include <linux/fscrypt.h>
+#include <linux/lockdep.h>
+#include <uapi/linux/btrfs_tree.h>
 #include <trace/events/btrfs.h>
+#include "block-rsv.h"
+#include "btrfs_inode.h"
 #include "extent_map.h"
 #include "extent_io.h"
+#include "extent-io-tree.h"
 #include "ordered-data.h"
 #include "delayed-inode.h"
 
+struct extent_state;
+struct posix_acl;
+struct iov_iter;
+struct writeback_control;
+struct btrfs_root;
+struct btrfs_fs_info;
+struct btrfs_trans_handle;
+
 /*
  * Since we search a directory based on f_pos (struct dir_context::pos) we have
  * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so
@@ -41,7 +60,6 @@ enum {
 	  */
 	BTRFS_INODE_NEEDS_FULL_SYNC,
 	BTRFS_INODE_COPY_EVERYTHING,
-	BTRFS_INODE_IN_DELALLOC_LIST,
 	BTRFS_INODE_HAS_PROPS,
 	BTRFS_INODE_SNAPSHOT_FLUSH,
 	/*
@@ -428,7 +446,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes, bool nowait, bool strict);
 
-void __btrfs_del_delalloc_inode(struct btrfs_root *root, struct btrfs_inode *inode);
+void btrfs_del_delalloc_inode(struct btrfs_inode *inode);
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
 int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
@@ -490,8 +508,7 @@ struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
 			      struct btrfs_root *root, struct btrfs_path *path);
 struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
-				    struct page *page, size_t pg_offset,
-				    u64 start, u64 len);
+				    struct page *page, u64 start, u64 len);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 68345f73d429..b2b94009959d 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -25,8 +25,6 @@
 #include "misc.h"
 #include "ctree.h"
 #include "fs.h"
-#include "disk-io.h"
-#include "transaction.h"
 #include "btrfs_inode.h"
 #include "bio.h"
 #include "ordered-data.h"
@@ -34,8 +32,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 #include "subpage.h"
-#include "zoned.h"
-#include "file-item.h"
+#include "messages.h"
 #include "super.h"
 
 static struct bio_set btrfs_compressed_bioset;
@@ -284,7 +281,7 @@ static void end_bbio_comprssed_read(struct btrfs_bio *bbio)
 static noinline void end_compressed_writeback(const struct compressed_bio *cb)
 {
 	struct inode *inode = &cb->bbio.inode->vfs_inode;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	unsigned long index = cb->start >> PAGE_SHIFT;
 	unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
 	struct folio_batch fbatch;
@@ -415,7 +412,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 				     struct compressed_bio *cb,
 				     int *memstall, unsigned long *pflags)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	unsigned long end_index;
 	struct bio *orig_bio = &cb->orig_bbio->bio;
 	u64 cur = cb->orig_bbio->file_offset + orig_bio->bi_iter.bi_size;
@@ -441,7 +438,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	 * This makes readahead less effective, so here disable readahead for
 	 * subpage for now, until full compressed write is supported.
 	 */
-	if (btrfs_sb(inode->i_sb)->sectorsize < PAGE_SIZE)
+	if (fs_info->sectorsize < PAGE_SIZE)
 		return 0;
 
 	end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
@@ -1039,7 +1036,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
 int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page,
 		     unsigned long dest_pgoff, size_t srclen, size_t destlen)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page);
 	struct list_head *workspace;
 	const u32 sectorsize = fs_info->sectorsize;
 	int ret;
@@ -1479,11 +1476,6 @@ static void heuristic_collect_sample(struct inode *inode, u64 start, u64 end,
 /*
  * Compression heuristic.
  *
- * For now is's a naive and optimistic 'return true', we'll extend the logic to
- * quickly (compared to direct compression) detect data characteristics
- * (compressible/incompressible) to avoid wasting CPU time on incompressible
- * data.
- *
  * The following types of analysis can be performed:
  * - detect mostly zero data
  * - detect data with low "byte set" size (text, etc)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index afd7e50d073d..4691a84ca838 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -7,10 +7,18 @@
 #define BTRFS_COMPRESSION_H
 
 #include <linux/sizes.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
 #include "bio.h"
 
+struct address_space;
+struct page;
+struct inode;
 struct btrfs_inode;
 struct btrfs_ordered_extent;
+struct btrfs_bio;
 
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
@@ -32,8 +40,6 @@ static_assert((BTRFS_MAX_COMPRESSED % PAGE_SIZE) == 0);
 
 #define	BTRFS_ZLIB_DEFAULT_LEVEL		3
 
-struct page;
-
 struct compressed_bio {
 	/* Number of compressed pages in the array */
 	unsigned int nr_pages;
@@ -169,7 +175,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out);
 int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen);
 void zstd_init_workspace_manager(void);
 void zstd_cleanup_workspace_manager(void);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index e65e012bac55..aaf53fd84358 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -820,7 +820,7 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot,
 	}
 
 	while (low < high) {
-		const int unit_size = folio_size(eb->folios[0]);
+		const int unit_size = eb->folio_size;
 		unsigned long oil;
 		unsigned long offset;
 		struct btrfs_disk_key *tmp;
@@ -4280,6 +4280,10 @@ void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans,
 /*
  * Given a key and some data, insert items into the tree.
  * This does all the path init required, making room in the tree if needed.
+ *
+ * Returns: 0        on success
+ *          -EEXIST  if the first key already exists
+ *          < 0      on other errors
  */
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root,
@@ -5082,9 +5086,7 @@ int btrfs_previous_extent_item(struct btrfs_root *root,
 
 int __init btrfs_ctree_init(void)
 {
-	btrfs_path_cachep = kmem_cache_create("btrfs_path",
-			sizeof(struct btrfs_path), 0,
-			SLAB_MEM_SPREAD, NULL);
+	btrfs_path_cachep = KMEM_CACHE(btrfs_path, 0);
 	if (!btrfs_path_cachep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 70e828d33177..c03c58246033 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -7,25 +7,24 @@
 #define BTRFS_CTREE_H
 
 #include <linux/pagemap.h>
+#include <linux/spinlock.h>
+#include <linux/rbtree.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+#include <linux/xarray.h>
+#include <linux/refcount.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "locking.h"
 #include "fs.h"
 #include "accessors.h"
+#include "extent-io-tree.h"
 
+struct extent_buffer;
+struct btrfs_block_rsv;
 struct btrfs_trans_handle;
-struct btrfs_transaction;
-struct btrfs_pending_snapshot;
-struct btrfs_delayed_ref_root;
-struct btrfs_space_info;
 struct btrfs_block_group;
-struct btrfs_ordered_sum;
-struct btrfs_ref;
-struct btrfs_bio;
-struct btrfs_ioctl_encoded_io_args;
-struct btrfs_device;
-struct btrfs_fs_devices;
-struct btrfs_balance_control;
-struct btrfs_delayed_root;
-struct reloc_control;
 
 /* Read ahead values for struct btrfs_path.reada */
 enum {
@@ -478,8 +477,7 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 	return mapping_gfp_constraint(mapping, ~__GFP_FS);
 }
 
-int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
-				   u64 start, u64 end);
+void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end);
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes);
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index c276b136ab63..f015fa1b6301 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -6,7 +6,6 @@
 #include <linux/sched.h>
 #include "ctree.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "transaction.h"
 #include "locking.h"
 #include "accessors.h"
@@ -521,7 +520,7 @@ static int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 	 * keep_locks set and lowest_level is 1, regardless of the value of
 	 * path->slots[1].
 	 */
-	BUG_ON(path->locks[1] == 0);
+	ASSERT(path->locks[1] != 0);
 	ret = btrfs_realloc_node(trans, root,
 				 path->nodes[1], 0,
 				 &last_ret,
@@ -810,7 +809,7 @@ static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info,
 static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 				     u32 extent_thresh, u64 newer_than, bool locked)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *next;
 	bool ret = false;
 
@@ -861,20 +860,21 @@ out:
  * NOTE: Caller should also wait for page writeback after the cluster is
  * prepared, here we don't do writeback wait for each page.
  */
-static struct page *defrag_prepare_one_page(struct btrfs_inode *inode, pgoff_t index)
+static struct folio *defrag_prepare_one_folio(struct btrfs_inode *inode, pgoff_t index)
 {
 	struct address_space *mapping = inode->vfs_inode.i_mapping;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	u64 page_start = (u64)index << PAGE_SHIFT;
 	u64 page_end = page_start + PAGE_SIZE - 1;
 	struct extent_state *cached_state = NULL;
-	struct page *page;
+	struct folio *folio;
 	int ret;
 
 again:
-	page = find_or_create_page(mapping, index, mask);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+	if (IS_ERR(folio))
+		return folio;
 
 	/*
 	 * Since we can defragment files opened read-only, we can encounter
@@ -884,16 +884,16 @@ again:
 	 * executables that explicitly enable them, so this isn't very
 	 * restrictive.
 	 */
-	if (PageCompound(page)) {
-		unlock_page(page);
-		put_page(page);
+	if (folio_test_large(folio)) {
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(-ETXTBSY);
 	}
 
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(ret);
 	}
 
@@ -908,17 +908,17 @@ again:
 		if (!ordered)
 			break;
 
-		unlock_page(page);
+		folio_unlock(folio);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
-		lock_page(page);
+		folio_lock(folio);
 		/*
-		 * We unlocked the page above, so we need check if it was
+		 * We unlocked the folio above, so we need check if it was
 		 * released or not.
 		 */
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
 	}
@@ -927,21 +927,21 @@ again:
 	 * Now the page range has no ordered extent any more.  Read the page to
 	 * make it uptodate.
 	 */
-	if (!PageUptodate(page)) {
-		btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+	if (!folio_test_uptodate(folio)) {
+		btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
-		if (!PageUptodate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (!folio_test_uptodate(folio)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			return ERR_PTR(-EIO);
 		}
 	}
-	return page;
+	return folio;
 }
 
 struct defrag_target_range {
@@ -1046,7 +1046,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 			goto add;
 
 		/* Skip too large extent */
-		if (range_len >= extent_thresh)
+		if (em->len >= extent_thresh)
 			goto next;
 
 		/*
@@ -1162,7 +1162,7 @@ static_assert(PAGE_ALIGNED(CLUSTER_SIZE));
  */
 static int defrag_one_locked_target(struct btrfs_inode *inode,
 				    struct defrag_target_range *target,
-				    struct page **pages, int nr_pages,
+				    struct folio **folios, int nr_pages,
 				    struct extent_state **cached_state)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -1171,7 +1171,7 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 	const u64 len = target->len;
 	unsigned long last_index = (start + len - 1) >> PAGE_SHIFT;
 	unsigned long start_index = start >> PAGE_SHIFT;
-	unsigned long first_index = page_index(pages[0]);
+	unsigned long first_index = folios[0]->index;
 	int ret = 0;
 	int i;
 
@@ -1188,8 +1188,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 
 	/* Update the page status */
 	for (i = start_index - first_index; i <= last_index - first_index; i++) {
-		ClearPageChecked(pages[i]);
-		btrfs_folio_clamp_set_dirty(fs_info, page_folio(pages[i]), start, len);
+		folio_clear_checked(folios[i]);
+		btrfs_folio_clamp_set_dirty(fs_info, folios[i], start, len);
 	}
 	btrfs_delalloc_release_extents(inode, len);
 	extent_changeset_free(data_reserved);
@@ -1205,7 +1205,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	struct defrag_target_range *entry;
 	struct defrag_target_range *tmp;
 	LIST_HEAD(target_list);
-	struct page **pages;
+	struct folio **folios;
 	const u32 sectorsize = inode->root->fs_info->sectorsize;
 	u64 last_index = (start + len - 1) >> PAGE_SHIFT;
 	u64 start_index = start >> PAGE_SHIFT;
@@ -1216,21 +1216,21 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	ASSERT(nr_pages <= CLUSTER_SIZE / PAGE_SIZE);
 	ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(len, sectorsize));
 
-	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
-	if (!pages)
+	folios = kcalloc(nr_pages, sizeof(struct folio *), GFP_NOFS);
+	if (!folios)
 		return -ENOMEM;
 
 	/* Prepare all pages */
 	for (i = 0; i < nr_pages; i++) {
-		pages[i] = defrag_prepare_one_page(inode, start_index + i);
-		if (IS_ERR(pages[i])) {
-			ret = PTR_ERR(pages[i]);
-			pages[i] = NULL;
-			goto free_pages;
+		folios[i] = defrag_prepare_one_folio(inode, start_index + i);
+		if (IS_ERR(folios[i])) {
+			ret = PTR_ERR(folios[i]);
+			nr_pages = i;
+			goto free_folios;
 		}
 	}
 	for (i = 0; i < nr_pages; i++)
-		wait_on_page_writeback(pages[i]);
+		folio_wait_writeback(folios[i]);
 
 	/* Lock the pages range */
 	lock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
@@ -1250,7 +1250,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 		goto unlock_extent;
 
 	list_for_each_entry(entry, &target_list, list) {
-		ret = defrag_one_locked_target(inode, entry, pages, nr_pages,
+		ret = defrag_one_locked_target(inode, entry, folios, nr_pages,
 					       &cached_state);
 		if (ret < 0)
 			break;
@@ -1264,14 +1264,12 @@ unlock_extent:
 	unlock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
 		      (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
 		      &cached_state);
-free_pages:
+free_folios:
 	for (i = 0; i < nr_pages; i++) {
-		if (pages[i]) {
-			unlock_page(pages[i]);
-			put_page(pages[i]);
-		}
+		folio_unlock(folios[i]);
+		folio_put(folios[i]);
 	}
-	kfree(pages);
+	kfree(folios);
 	return ret;
 }
 
@@ -1366,7 +1364,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_to_defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	unsigned long sectors_defragged = 0;
 	u64 isize = i_size_read(inode);
 	u64 cur;
@@ -1512,9 +1510,7 @@ void __cold btrfs_auto_defrag_exit(void)
 int __init btrfs_auto_defrag_init(void)
 {
 	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
-					sizeof(struct inode_defrag), 0,
-					SLAB_MEM_SPREAD,
-					NULL);
+					sizeof(struct inode_defrag), 0, 0, NULL);
 	if (!btrfs_inode_defrag_cachep)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/defrag.h b/fs/btrfs/defrag.h
index 5a62763528d1..878528e086fb 100644
--- a/fs/btrfs/defrag.h
+++ b/fs/btrfs/defrag.h
@@ -3,6 +3,16 @@
 #ifndef BTRFS_DEFRAG_H
 #define BTRFS_DEFRAG_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
+
+struct inode;
+struct file_ra_state;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_trans_handle;
+struct btrfs_ioctl_defrag_range_args;
+
 int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_to_defrag);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2833e8ef4c09..b3527efd0b4b 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -6,9 +6,7 @@
 #include "block-rsv.h"
 #include "btrfs_inode.h"
 #include "space-info.h"
-#include "transaction.h"
 #include "qgroup.h"
-#include "block-group.h"
 #include "fs.h"
 
 /*
@@ -245,7 +243,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 reserve_size = 0;
 	u64 qgroup_rsv_size = 0;
-	u64 csum_leaves;
 	unsigned outstanding_extents;
 
 	lockdep_assert_held(&inode->lock);
@@ -260,10 +257,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 						outstanding_extents);
 		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
 	}
-	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
-						 inode->csum_bytes);
-	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
-							csum_leaves);
+	if (!(inode->flags & BTRFS_INODE_NODATASUM)) {
+		u64 csum_leaves;
+
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
+		reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves);
+	}
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -278,14 +277,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	spin_unlock(&block_rsv->lock);
 }
 
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+static void calc_inode_reservations(struct btrfs_inode *inode,
 				    u64 num_bytes, u64 disk_num_bytes,
 				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 nr_extents = count_max_extents(fs_info, num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+	u64 csum_leaves;
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		csum_leaves = 0;
+	else
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
 						nr_extents + csum_leaves);
 
@@ -337,7 +342,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+	calc_inode_reservations(inode, num_bytes, disk_num_bytes,
 				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
 						 noflush);
@@ -359,7 +364,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	nr_extents = count_max_extents(fs_info, num_bytes);
 	spin_lock(&inode->lock);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += disk_num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
@@ -393,7 +399,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
-	inode->csum_bytes -= num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes -= num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
diff --git a/fs/btrfs/delalloc-space.h b/fs/btrfs/delalloc-space.h
index c5d573f2366e..ce4f889e4f17 100644
--- a/fs/btrfs/delalloc-space.h
+++ b/fs/btrfs/delalloc-space.h
@@ -3,7 +3,11 @@
 #ifndef BTRFS_DELALLOC_SPACE_H
 #define BTRFS_DELALLOC_SPACE_H
 
+#include <linux/types.h>
+
 struct extent_changeset;
+struct btrfs_inode;
+struct btrfs_fs_info;
 
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
 int btrfs_check_data_free_space(struct btrfs_inode *inode,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 08102883f560..dd6f566a383f 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -28,11 +28,7 @@ static struct kmem_cache *delayed_node_cache;
 
 int __init btrfs_delayed_inode_init(void)
 {
-	delayed_node_cache = kmem_cache_create("btrfs_delayed_node",
-					sizeof(struct btrfs_delayed_node),
-					0,
-					SLAB_MEM_SPREAD,
-					NULL);
+	delayed_node_cache = KMEM_CACHE(btrfs_delayed_node, 0);
 	if (!delayed_node_cache)
 		return -ENOMEM;
 	return 0;
@@ -43,6 +39,17 @@ void __cold btrfs_delayed_inode_exit(void)
 	kmem_cache_destroy(delayed_node_cache);
 }
 
+void btrfs_init_delayed_root(struct btrfs_delayed_root *delayed_root)
+{
+	atomic_set(&delayed_root->items, 0);
+	atomic_set(&delayed_root->items_seq, 0);
+	delayed_root->nodes = 0;
+	spin_lock_init(&delayed_root->lock);
+	init_waitqueue_head(&delayed_root->wait);
+	INIT_LIST_HEAD(&delayed_root->node_list);
+	INIT_LIST_HEAD(&delayed_root->prepare_list);
+}
+
 static inline void btrfs_init_delayed_node(
 				struct btrfs_delayed_node *delayed_node,
 				struct btrfs_root *root, u64 inode_id)
@@ -430,8 +437,6 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 
 	delayed_root = delayed_node->root->fs_info->delayed_root;
 
-	BUG_ON(!delayed_root);
-
 	if (delayed_item->type == BTRFS_DELAYED_INSERTION_ITEM)
 		root = &delayed_node->ins_root;
 	else
@@ -980,7 +985,7 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
 
 	if (delayed_node &&
 	    test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
-		BUG_ON(!delayed_node->root);
+		ASSERT(delayed_node->root);
 		clear_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags);
 		delayed_node->count--;
 
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 5cceb31bbd16..64e115d97499 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -7,15 +7,23 @@
 #ifndef BTRFS_DELAYED_INODE_H
 #define BTRFS_DELAYED_INODE_H
 
+#include <linux/types.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/refcount.h>
 #include "ctree.h"
 
+struct btrfs_disk_key;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_trans_handle;
+
 enum btrfs_delayed_item_type {
 	BTRFS_DELAYED_INSERTION_ITEM,
 	BTRFS_DELAYED_DELETION_ITEM
@@ -98,18 +106,7 @@ struct btrfs_delayed_item {
 	char data[] __counted_by(data_len);
 };
 
-static inline void btrfs_init_delayed_root(
-				struct btrfs_delayed_root *delayed_root)
-{
-	atomic_set(&delayed_root->items, 0);
-	atomic_set(&delayed_root->items_seq, 0);
-	delayed_root->nodes = 0;
-	spin_lock_init(&delayed_root->lock);
-	init_waitqueue_head(&delayed_root->wait);
-	INIT_LIST_HEAD(&delayed_root->node_list);
-	INIT_LIST_HEAD(&delayed_root->prepare_list);
-}
-
+void btrfs_init_delayed_root(struct btrfs_delayed_root *delayed_root);
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 891ea2fa263c..e44e62cf76bc 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1004,6 +1004,52 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&ref->add_list);
 }
 
+void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
+			    u64 len, u64 parent, u64 owning_root)
+{
+	generic_ref->action = action;
+	generic_ref->bytenr = bytenr;
+	generic_ref->len = len;
+	generic_ref->parent = parent;
+	generic_ref->owning_root = owning_root;
+}
+
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
+			 u64 mod_root, bool skip_qgroup)
+{
+#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	/* If @real_root not set, use @root as fallback */
+	generic_ref->real_root = mod_root ?: root;
+#endif
+	generic_ref->tree_ref.level = level;
+	generic_ref->tree_ref.ref_root = root;
+	generic_ref->type = BTRFS_REF_METADATA;
+	if (skip_qgroup || !(is_fstree(root) &&
+			     (!mod_root || is_fstree(mod_root))))
+		generic_ref->skip_qgroup = true;
+	else
+		generic_ref->skip_qgroup = false;
+
+}
+
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
+			 u64 offset, u64 mod_root, bool skip_qgroup)
+{
+#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	/* If @real_root not set, use @root as fallback */
+	generic_ref->real_root = mod_root ?: ref_root;
+#endif
+	generic_ref->data_ref.ref_root = ref_root;
+	generic_ref->data_ref.ino = ino;
+	generic_ref->data_ref.offset = offset;
+	generic_ref->type = BTRFS_REF_DATA;
+	if (skip_qgroup || !(is_fstree(ref_root) &&
+			     (!mod_root || is_fstree(mod_root))))
+		generic_ref->skip_qgroup = true;
+	else
+		generic_ref->skip_qgroup = false;
+}
+
 /*
  * add a delayed tree ref.  This does all of the accounting required
  * to make sure the delayed ref is eventually processed before this
@@ -1220,6 +1266,25 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
+{
+	if (refcount_dec_and_test(&ref->refs)) {
+		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
+		switch (ref->type) {
+		case BTRFS_TREE_BLOCK_REF_KEY:
+		case BTRFS_SHARED_BLOCK_REF_KEY:
+			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			break;
+		case BTRFS_EXTENT_DATA_REF_KEY:
+		case BTRFS_SHARED_DATA_REF_KEY:
+			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+			break;
+		default:
+			BUG();
+		}
+	}
+}
+
 /*
  * This does a simple search for the head node for a given extent.  Returns the
  * head node if found, or NULL if not.
@@ -1242,31 +1307,19 @@ void __cold btrfs_delayed_ref_exit(void)
 
 int __init btrfs_delayed_ref_init(void)
 {
-	btrfs_delayed_ref_head_cachep = kmem_cache_create(
-				"btrfs_delayed_ref_head",
-				sizeof(struct btrfs_delayed_ref_head), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_ref_head_cachep = KMEM_CACHE(btrfs_delayed_ref_head, 0);
 	if (!btrfs_delayed_ref_head_cachep)
 		goto fail;
 
-	btrfs_delayed_tree_ref_cachep = kmem_cache_create(
-				"btrfs_delayed_tree_ref",
-				sizeof(struct btrfs_delayed_tree_ref), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_tree_ref_cachep = KMEM_CACHE(btrfs_delayed_tree_ref, 0);
 	if (!btrfs_delayed_tree_ref_cachep)
 		goto fail;
 
-	btrfs_delayed_data_ref_cachep = kmem_cache_create(
-				"btrfs_delayed_data_ref",
-				sizeof(struct btrfs_delayed_data_ref), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_data_ref_cachep = KMEM_CACHE(btrfs_delayed_data_ref, 0);
 	if (!btrfs_delayed_data_ref_cachep)
 		goto fail;
 
-	btrfs_delayed_extent_op_cachep = kmem_cache_create(
-				"btrfs_delayed_extent_op",
-				sizeof(struct btrfs_delayed_extent_op), 0,
-				SLAB_MEM_SPREAD, NULL);
+	btrfs_delayed_extent_op_cachep = KMEM_CACHE(btrfs_delayed_extent_op, 0);
 	if (!btrfs_delayed_extent_op_cachep)
 		goto fail;
 
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 62d679d40f4f..b291147cb8ab 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -6,7 +6,17 @@
 #ifndef BTRFS_DELAYED_REF_H
 #define BTRFS_DELAYED_REF_H
 
+#include <linux/types.h>
 #include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
 
 /* these are the possible values of struct btrfs_delayed_ref_node->action */
 enum btrfs_delayed_ref_action {
@@ -308,53 +318,12 @@ static inline u64 btrfs_calc_delayed_ref_csum_bytes(const struct btrfs_fs_info *
 	return btrfs_calc_metadata_size(fs_info, num_csum_items);
 }
 
-static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref,
-					  int action, u64 bytenr, u64 len,
-					  u64 parent, u64 owning_root)
-{
-	generic_ref->action = action;
-	generic_ref->bytenr = bytenr;
-	generic_ref->len = len;
-	generic_ref->parent = parent;
-	generic_ref->owning_root = owning_root;
-}
-
-static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level,
-				       u64 root, u64 mod_root, bool skip_qgroup)
-{
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
-	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: root;
-#endif
-	generic_ref->tree_ref.level = level;
-	generic_ref->tree_ref.ref_root = root;
-	generic_ref->type = BTRFS_REF_METADATA;
-	if (skip_qgroup || !(is_fstree(root) &&
-			     (!mod_root || is_fstree(mod_root))))
-		generic_ref->skip_qgroup = true;
-	else
-		generic_ref->skip_qgroup = false;
-
-}
-
-static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref,
-				u64 ref_root, u64 ino, u64 offset, u64 mod_root,
-				bool skip_qgroup)
-{
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
-	/* If @real_root not set, use @root as fallback */
-	generic_ref->real_root = mod_root ?: ref_root;
-#endif
-	generic_ref->data_ref.ref_root = ref_root;
-	generic_ref->data_ref.ino = ino;
-	generic_ref->data_ref.offset = offset;
-	generic_ref->type = BTRFS_REF_DATA;
-	if (skip_qgroup || !(is_fstree(ref_root) &&
-			     (!mod_root || is_fstree(mod_root))))
-		generic_ref->skip_qgroup = true;
-	else
-		generic_ref->skip_qgroup = false;
-}
+void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, int action, u64 bytenr,
+			    u64 len, u64 parent, u64 owning_root);
+void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, int level, u64 root,
+			 u64 mod_root, bool skip_qgroup);
+void btrfs_init_data_ref(struct btrfs_ref *generic_ref, u64 ref_root, u64 ino,
+			 u64 offset, u64 mod_root, bool skip_qgroup);
 
 static inline struct btrfs_delayed_extent_op *
 btrfs_alloc_delayed_extent_op(void)
@@ -369,24 +338,7 @@ btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op)
 		kmem_cache_free(btrfs_delayed_extent_op_cachep, op);
 }
 
-static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
-{
-	if (refcount_dec_and_test(&ref->refs)) {
-		WARN_ON(!RB_EMPTY_NODE(&ref->ref_node));
-		switch (ref->type) {
-		case BTRFS_TREE_BLOCK_REF_KEY:
-		case BTRFS_SHARED_BLOCK_REF_KEY:
-			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-			break;
-		case BTRFS_EXTENT_DATA_REF_KEY:
-		case BTRFS_SHARED_DATA_REF_KEY:
-			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
-			break;
-		default:
-			BUG();
-		}
-	}
-}
+void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref);
 
 static inline u64 btrfs_ref_head_to_space_flags(
 				struct btrfs_delayed_ref_head *head_ref)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1502d664c892..7696beec4c21 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -11,10 +11,8 @@
 #include <linux/math64.h>
 #include "misc.h"
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "async-thread.h"
 #include "dev-replace.h"
@@ -246,7 +244,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	u64 devid = BTRFS_DEV_REPLACE_DEVID;
 	int ret = 0;
@@ -257,13 +255,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return -EINVAL;
 	}
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 
 	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
 		btrfs_err(fs_info,
@@ -314,7 +312,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	device->commit_bytes_used = device->bytes_used;
 	device->fs_info = fs_info;
 	device->bdev = bdev;
-	device->bdev_handle = bdev_handle;
+	device->bdev_file = bdev_file;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->dev_stats_valid = 1;
@@ -335,7 +333,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	return 0;
 
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ret;
 }
 
@@ -725,6 +723,23 @@ leave:
 	return ret;
 }
 
+static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args)
+{
+	if (args->start.srcdevid == 0) {
+		if (memchr(args->start.srcdev_name, 0,
+			   sizeof(args->start.srcdev_name)) == NULL)
+			return -ENAMETOOLONG;
+	} else {
+		args->start.srcdev_name[0] = 0;
+	}
+
+	if (memchr(args->start.tgtdev_name, 0,
+		   sizeof(args->start.tgtdev_name)) == NULL)
+	    return -ENAMETOOLONG;
+
+	return 0;
+}
+
 int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 			    struct btrfs_ioctl_dev_replace_args *args)
 {
@@ -737,10 +752,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 	default:
 		return -EINVAL;
 	}
-
-	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
-	    args->start.tgtdev_name[0] == '\0')
-		return -EINVAL;
+	ret = btrfs_check_replace_dev_names(args);
+	if (ret < 0)
+		return ret;
 
 	ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name,
 					args->start.srcdevid,
@@ -984,8 +998,7 @@ error:
 	btrfs_sysfs_remove_device(src_device);
 	btrfs_sysfs_update_devid(tgt_device);
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state))
-		btrfs_scratch_superblocks(fs_info, src_device->bdev,
-					  src_device->name->str);
+		btrfs_scratch_superblocks(fs_info, src_device);
 
 	/* write back the superblocks */
 	trans = btrfs_start_transaction(root, 0);
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 675082ccec89..23e480efe5e6 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -6,11 +6,15 @@
 #ifndef BTRFS_DEV_REPLACE_H
 #define BTRFS_DEV_REPLACE_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
+
 struct btrfs_ioctl_dev_replace_args;
 struct btrfs_fs_info;
 struct btrfs_trans_handle;
 struct btrfs_dev_replace;
 struct btrfs_block_group;
+struct btrfs_device;
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_replace(struct btrfs_trans_handle *trans);
diff --git a/fs/btrfs/dir-item.h b/fs/btrfs/dir-item.h
index e40a226373d7..00b3d83d7569 100644
--- a/fs/btrfs/dir-item.h
+++ b/fs/btrfs/dir-item.h
@@ -3,9 +3,15 @@
 #ifndef BTRFS_DIR_ITEM_H
 #define BTRFS_DIR_ITEM_H
 
+#include <linux/types.h>
 #include <linux/crc32c.h>
 
 struct fscrypt_str;
+struct btrfs_fs_info;
+struct btrfs_key;
+struct btrfs_path;
+struct btrfs_root;
+struct btrfs_trans_handle;
 
 int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 			  const struct fscrypt_str *name);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c6907d533fe8..3df5477d48a8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -29,7 +29,6 @@
 #include "tree-log.h"
 #include "free-space-cache.h"
 #include "free-space-tree.h"
-#include "rcu-string.h"
 #include "dev-replace.h"
 #include "raid56.h"
 #include "sysfs.h"
@@ -193,7 +192,7 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb,
 		struct folio *folio = eb->folios[i];
 		u64 start = max_t(u64, eb->start, folio_pos(folio));
 		u64 end = min_t(u64, eb->start + eb->len,
-				folio_pos(folio) + folio_size(folio));
+				folio_pos(folio) + eb->folio_size);
 		u32 len = end - start;
 
 		ret = btrfs_repair_io_failure(fs_info, 0, start, len,
@@ -498,15 +497,15 @@ static int btree_migrate_folio(struct address_space *mapping,
 static int btree_writepages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
-	struct btrfs_fs_info *fs_info;
 	int ret;
 
 	if (wbc->sync_mode == WB_SYNC_NONE) {
+		struct btrfs_fs_info *fs_info;
 
 		if (wbc->for_kupdate)
 			return 0;
 
-		fs_info = BTRFS_I(mapping->host)->root->fs_info;
+		fs_info = inode_to_fs_info(mapping->host);
 		/* this is a bit racy, but that's ok */
 		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
 					     BTRFS_DIRTY_METADATA_THRESH,
@@ -529,11 +528,12 @@ static void btree_invalidate_folio(struct folio *folio, size_t offset,
 				 size_t length)
 {
 	struct extent_io_tree *tree;
-	tree = &BTRFS_I(folio->mapping->host)->io_tree;
+
+	tree = &folio_to_inode(folio)->io_tree;
 	extent_invalidate_folio(tree, folio, offset);
 	btree_release_folio(folio, GFP_NOFS);
 	if (folio_get_private(folio)) {
-		btrfs_warn(BTRFS_I(folio->mapping->host)->root->fs_info,
+		btrfs_warn(folio_to_fs_info(folio),
 			   "folio private not zero on folio %llu",
 			   (unsigned long long)folio_pos(folio));
 		folio_detach_private(folio);
@@ -544,7 +544,7 @@ static void btree_invalidate_folio(struct folio *folio, size_t offset,
 static bool btree_dirty_folio(struct address_space *mapping,
 		struct folio *folio)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host);
 	struct btrfs_subpage_info *spi = fs_info->subpage_info;
 	struct btrfs_subpage *subpage;
 	struct extent_buffer *eb;
@@ -1244,6 +1244,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
 		btrfs_err(fs_info, "leaked root %s refcount %d",
 			  btrfs_root_name(&root->root_key, buf),
 			  refcount_read(&root->refs));
+		WARN_ON_ONCE(1);
 		while (refcount_read(&root->refs) > 1)
 			btrfs_put_root(root);
 		btrfs_put_root(root);
@@ -1307,12 +1308,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
  *
  * @objectid:	root id
  * @anon_dev:	preallocated anonymous block device number for new roots,
- * 		pass 0 for new allocation.
+ *		pass NULL for a new allocation.
  * @check_ref:	whether to check root item references, If true, return -ENOENT
  *		for orphan roots
  */
 static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
-					     u64 objectid, dev_t anon_dev,
+					     u64 objectid, dev_t *anon_dev,
 					     bool check_ref)
 {
 	struct btrfs_root *root;
@@ -1336,8 +1337,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
-		/* Shouldn't get preallocated anon_dev for cached roots */
-		ASSERT(!anon_dev);
+		/*
+		 * Some other caller may have read out the newly inserted
+		 * subvolume already (for things like backref walk etc).  Not
+		 * that common but still possible.  In that case, we just need
+		 * to free the anon_dev.
+		 */
+		if (unlikely(anon_dev && *anon_dev)) {
+			free_anon_bdev(*anon_dev);
+			*anon_dev = 0;
+		}
+
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1357,7 +1367,7 @@ again:
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root, anon_dev);
+	ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0);
 	if (ret)
 		goto fail;
 
@@ -1393,7 +1403,7 @@ fail:
 	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
 	 * and once again by our caller.
 	 */
-	if (anon_dev)
+	if (anon_dev && *anon_dev)
 		root->anon_dev = 0;
 	btrfs_put_root(root);
 	return ERR_PTR(ret);
@@ -1409,7 +1419,7 @@ fail:
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref)
 {
-	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+	return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref);
 }
 
 /*
@@ -1417,11 +1427,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
  * the anonymous block device id
  *
  * @objectid:	tree objectid
- * @anon_dev:	if zero, allocate a new anonymous block device or use the
- *		parameter value
+ * @anon_dev:	if NULL, allocate a new anonymous block device or use the
+ *		parameter value if not NULL
  */
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev)
+					 u64 objectid, dev_t *anon_dev)
 {
 	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
 }
@@ -2230,7 +2240,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	struct btrfs_key location;
 	int ret;
 
-	BUG_ON(!fs_info->tree_root);
+	ASSERT(fs_info->tree_root);
 
 	ret = load_global_roots(tree_root);
 	if (ret)
@@ -2830,6 +2840,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 	int ret;
 
 	fs_info->sb = sb;
+	/* Temporary fixed values for block size until we read the superblock. */
 	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
 	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);
 
@@ -3347,6 +3358,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
+	/* Update the values for the current filesystem. */
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
 	memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE);
@@ -4617,7 +4629,7 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 		struct inode *inode = NULL;
 		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
 					       delalloc_inodes);
-		__btrfs_del_delalloc_inode(root, btrfs_inode);
+		btrfs_del_delalloc_inode(btrfs_inode);
 		spin_unlock(&root->delalloc_lock);
 
 		/*
@@ -4916,7 +4928,14 @@ int btrfs_init_root_free_objectid(struct btrfs_root *root)
 	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	if (ret < 0)
 		goto error;
-	BUG_ON(ret == 0); /* Corruption */
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of valid range.
+		 */
+		ret = -EUCLEAN;
+		goto error;
+	}
 	if (path->slots[0] > 0) {
 		slot = path->slots[0] - 1;
 		l = path->nodes[0];
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 9413726b329b..76eb53fe7a11 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -6,6 +6,22 @@
 #ifndef BTRFS_DISK_IO_H
 #define BTRFS_DISK_IO_H
 
+#include <linux/sizes.h>
+#include <linux/compiler_types.h>
+#include "ctree.h"
+#include "fs.h"
+
+struct block_device;
+struct super_block;
+struct extent_buffer;
+struct btrfs_device;
+struct btrfs_fs_devices;
+struct btrfs_fs_info;
+struct btrfs_super_block;
+struct btrfs_trans_handle;
+struct btrfs_tree_parent_check;
+struct btrfs_transaction;
+
 #define BTRFS_SUPER_MIRROR_MAX	 3
 #define BTRFS_SUPER_MIRROR_SHIFT 12
 
@@ -25,10 +41,6 @@ static inline u64 btrfs_sb_offset(int mirror)
 	return BTRFS_SUPER_INFO_OFFSET;
 }
 
-struct btrfs_device;
-struct btrfs_fs_devices;
-struct btrfs_tree_parent_check;
-
 void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
 void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
@@ -61,7 +73,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref);
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev);
+					 u64 objectid, dev_t *anon_dev);
 struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 u64 objectid);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 744a02b7fd67..8398d345ec5b 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -5,7 +5,6 @@
 #include "ctree.h"
 #include "disk-io.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "export.h"
 #include "accessors.h"
 #include "super.h"
@@ -174,8 +173,15 @@ struct dentry *btrfs_get_parent(struct dentry *child)
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto fail;
+	if (ret == 0) {
+		/*
+		 * Key with offset of -1 found, there would have to exist an
+		 * inode with such number or a root with such id.
+		 */
+		ret = -EUCLEAN;
+		goto fail;
+	}
 
-	BUG_ON(ret == 0); /* Key with offset of -1 found */
 	if (path->slots[0] == 0) {
 		ret = -ENOENT;
 		goto fail;
@@ -215,7 +221,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 {
 	struct inode *inode = d_inode(child);
 	struct inode *dir = d_inode(parent);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_path *path;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_inode_ref *iref;
diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h
index eba6bc4f5a61..464582273af9 100644
--- a/fs/btrfs/export.h
+++ b/fs/btrfs/export.h
@@ -4,6 +4,10 @@
 #define BTRFS_EXPORT_H
 
 #include <linux/exportfs.h>
+#include <linux/types.h>
+
+struct dentry;
+struct super_block;
 
 extern const struct export_operations btrfs_export_ops;
 
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index e3ee5449cc4a..c09b428823d7 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -6,7 +6,6 @@
 #include "ctree.h"
 #include "extent-io-tree.h"
 #include "btrfs_inode.h"
-#include "misc.h"
 
 static struct kmem_cache *extent_state_cache;
 
@@ -48,6 +47,7 @@ static inline void btrfs_extent_state_leak_debug_check(void)
 		       extent_state_in_tree(state),
 		       refcount_read(&state->refs));
 		list_del(&state->leak_list);
+		WARN_ON_ONCE(1);
 		kmem_cache_free(extent_state_cache, state);
 	}
 }
@@ -1883,8 +1883,8 @@ void __cold extent_state_free_cachep(void)
 int __init extent_state_init_cachep(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
-			sizeof(struct extent_state), 0,
-			SLAB_MEM_SPREAD, NULL);
+					       sizeof(struct extent_state), 0, 0,
+					       NULL);
 	if (!extent_state_cache)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index ebe6390d65e9..9d3a52d8f59a 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -3,9 +3,16 @@
 #ifndef BTRFS_EXTENT_IO_TREE_H
 #define BTRFS_EXTENT_IO_TREE_H
 
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/wait.h>
 #include "misc.h"
 
 struct extent_changeset;
+struct btrfs_fs_info;
+struct btrfs_inode;
 
 /* Bits for the extent state */
 enum {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 8e8cc1111277..beedd6ed64d3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -18,7 +18,7 @@
 #include <linux/crc32c.h>
 #include "ctree.h"
 #include "extent-tree.h"
-#include "tree-log.h"
+#include "transaction.h"
 #include "disk-io.h"
 #include "print-tree.h"
 #include "volumes.h"
@@ -26,14 +26,11 @@
 #include "locking.h"
 #include "free-space-cache.h"
 #include "free-space-tree.h"
-#include "sysfs.h"
 #include "qgroup.h"
 #include "ref-verify.h"
 #include "space-info.h"
 #include "block-rsv.h"
-#include "delalloc-space.h"
 #include "discard.h"
-#include "rcu-string.h"
 #include "zoned.h"
 #include "dev-replace.h"
 #include "fs.h"
@@ -2399,7 +2396,14 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret == 0); /* Corruption */
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = -ENOENT;
 	if (path->slots[0] == 0)
@@ -2780,6 +2784,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 	u64 total_unpinned = 0;
 	u64 empty_cluster = 0;
 	bool readonly;
+	int ret = 0;
 
 	while (start <= end) {
 		readonly = false;
@@ -2789,7 +2794,11 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 				btrfs_put_block_group(cache);
 			total_unpinned = 0;
 			cache = btrfs_lookup_block_group(fs_info, start);
-			BUG_ON(!cache); /* Logic error */
+			if (cache == NULL) {
+				/* Logic error, something removed the block group. */
+				ret = -EUCLEAN;
+				goto out;
+			}
 
 			cluster = fetch_cluster_info(fs_info,
 						     cache->space_info,
@@ -2858,7 +2867,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 
 	if (cache)
 		btrfs_put_block_group(cache);
-	return 0;
+out:
+	return ret;
 }
 
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
@@ -2888,7 +2898,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, &cached_state);
-		unpin_extent_range(fs_info, start, end, true);
+		ret = unpin_extent_range(fs_info, start, end, true);
+		BUG_ON(ret);
 		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		free_extent_state(cached_state);
 		cond_resched();
@@ -3447,16 +3458,17 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   u64 parent, int last_ref)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_ref generic_ref = { 0 };
 	struct btrfs_block_group *bg;
 	int ret;
 
-	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
-			       buf->start, buf->len, parent, btrfs_header_owner(buf));
-	btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
-			    root_id, 0, false);
-
 	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
+		struct btrfs_ref generic_ref = { 0 };
+
+		btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
+				       buf->start, buf->len, parent,
+				       btrfs_header_owner(buf));
+		btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
+				    root_id, 0, false);
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
 		BUG_ON(ret); /* -ENOMEM */
@@ -4950,7 +4962,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	u64 root_objectid = root->root_key.objectid;
 	u64 owning_root = root_objectid;
 
-	BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID);
+	ASSERT(root_objectid != BTRFS_TREE_LOG_OBJECTID);
 
 	if (btrfs_is_data_reloc_root(root) && is_fstree(root->relocation_src_root))
 		owning_root = root->relocation_src_root;
@@ -6167,10 +6179,13 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
-				   u64 start, u64 end)
+/*
+ * Unpin the extent range in an error context and don't add the space back.
+ * Errors are not propagated further.
+ */
+void btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, u64 start, u64 end)
 {
-	return unpin_extent_range(fs_info, start, end, false);
+	unpin_extent_range(fs_info, start, end, false);
 }
 
 /*
diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
index 2e066035ccee..af9f8800d5ac 100644
--- a/fs/btrfs/extent-tree.h
+++ b/fs/btrfs/extent-tree.h
@@ -3,11 +3,21 @@
 #ifndef BTRFS_EXTENT_TREE_H
 #define BTRFS_EXTENT_TREE_H
 
+#include <linux/types.h>
 #include "misc.h"
 #include "block-group.h"
+#include "locking.h"
 
+struct extent_buffer;
 struct btrfs_free_cluster;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_path;
+struct btrfs_ref;
+struct btrfs_disk_key;
 struct btrfs_delayed_ref_head;
+struct btrfs_delayed_ref_root;
+struct btrfs_extent_inline_ref;
 
 enum btrfs_extent_allocation_policy {
 	BTRFS_EXTENT_ALLOC_CLUSTERED,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cfd2967f04a2..7441245b1ceb 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,7 +14,6 @@
 #include <linux/pagevec.h>
 #include <linux/prefetch.h>
 #include <linux/fsverity.h>
-#include "misc.h"
 #include "extent_io.h"
 #include "extent-io-tree.h"
 #include "extent_map.h"
@@ -22,7 +21,6 @@
 #include "btrfs_inode.h"
 #include "bio.h"
 #include "locking.h"
-#include "rcu-string.h"
 #include "backref.h"
 #include "disk-io.h"
 #include "subpage.h"
@@ -78,10 +76,11 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)
 		eb = list_first_entry(&fs_info->allocated_ebs,
 				      struct extent_buffer, leak_list);
 		pr_err(
-	"BTRFS: buffer leak start %llu len %lu refs %d bflags %lu owner %llu\n",
+	"BTRFS: buffer leak start %llu len %u refs %d bflags %lu owner %llu\n",
 		       eb->start, eb->len, atomic_read(&eb->refs), eb->bflags,
 		       btrfs_header_owner(eb));
 		list_del(&eb->leak_list);
+		WARN_ON_ONCE(1);
 		kmem_cache_free(extent_buffer_cache, eb);
 	}
 	spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags);
@@ -147,8 +146,8 @@ static void submit_write_bio(struct btrfs_bio_ctrl *bio_ctrl, int ret)
 int __init extent_buffer_init_cachep(void)
 {
 	extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
-			sizeof(struct extent_buffer), 0,
-			SLAB_MEM_SPREAD, NULL);
+						sizeof(struct extent_buffer), 0, 0,
+						NULL);
 	if (!extent_buffer_cache)
 		return -ENOMEM;
 
@@ -207,7 +206,7 @@ static void __process_pages_contig(struct address_space *mapping,
 				   struct page *locked_page, u64 start, u64 end,
 				   unsigned long page_ops)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host);
 	pgoff_t start_index = start >> PAGE_SHIFT;
 	pgoff_t end_index = end >> PAGE_SHIFT;
 	pgoff_t index = start_index;
@@ -251,7 +250,7 @@ static noinline int lock_delalloc_pages(struct inode *inode,
 					u64 start,
 					u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct address_space *mapping = inode->i_mapping;
 	pgoff_t start_index = start >> PAGE_SHIFT;
 	pgoff_t end_index = end >> PAGE_SHIFT;
@@ -323,7 +322,7 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
 				    struct page *locked_page, u64 *start,
 				    u64 *end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 	const u64 orig_start = *start;
 	const u64 orig_end = *end;
@@ -433,7 +432,7 @@ static bool btrfs_verify_page(struct page *page, u64 start)
 
 static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(page);
 	struct folio *folio = page_folio(page);
 
 	ASSERT(page_offset(page) <= start &&
@@ -462,16 +461,15 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
  */
 static void end_bbio_data_write(struct btrfs_bio *bbio)
 {
+	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct bio *bio = &bbio->bio;
 	int error = blk_status_to_errno(bio->bi_status);
 	struct folio_iter fi;
+	const u32 sectorsize = fs_info->sectorsize;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_folio_all(fi, bio) {
 		struct folio *folio = fi.folio;
-		struct inode *inode = folio->mapping->host;
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-		const u32 sectorsize = fs_info->sectorsize;
 		u64 start = folio_pos(folio) + fi.offset;
 		u32 len = fi.length;
 
@@ -593,22 +591,17 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
  */
 static void end_bbio_data_read(struct btrfs_bio *bbio)
 {
+	struct btrfs_fs_info *fs_info = bbio->fs_info;
 	struct bio *bio = &bbio->bio;
 	struct processed_extent processed = { 0 };
 	struct folio_iter fi;
-	/*
-	 * The offset to the beginning of a bio, since one bio can never be
-	 * larger than UINT_MAX, u32 here is enough.
-	 */
-	u32 bio_offset = 0;
+	const u32 sectorsize = fs_info->sectorsize;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_folio_all(fi, &bbio->bio) {
 		bool uptodate = !bio->bi_status;
 		struct folio *folio = fi.folio;
 		struct inode *inode = folio->mapping->host;
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-		const u32 sectorsize = fs_info->sectorsize;
 		u64 start;
 		u64 end;
 		u32 len;
@@ -667,10 +660,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
 		end_page_read(folio_page(folio, 0), uptodate, start, len);
 		endio_readpage_release_extent(&processed, BTRFS_I(inode),
 					      start, end, uptodate);
-
-		ASSERT(bio_offset + len > bio_offset);
-		bio_offset += len;
-
 	}
 	/* Release the last extent */
 	endio_readpage_release_extent(&processed, NULL, 0, 0, false);
@@ -738,6 +727,8 @@ static int alloc_eb_folio_array(struct extent_buffer *eb, gfp_t extra_gfp)
 
 	for (int i = 0; i < num_pages; i++)
 		eb->folios[i] = page_folio(page_array[i]);
+	eb->folio_size = PAGE_SIZE;
+	eb->folio_shift = PAGE_SHIFT;
 	return 0;
 }
 
@@ -827,7 +818,7 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl,
 			       u64 disk_bytenr, struct page *page,
 			       size_t size, unsigned long pg_offset)
 {
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+	struct btrfs_inode *inode = page_to_inode(page);
 
 	ASSERT(pg_offset + size <= PAGE_SIZE);
 	ASSERT(bio_ctrl->end_io_func);
@@ -936,17 +927,21 @@ static int attach_extent_buffer_folio(struct extent_buffer *eb,
 
 int set_page_extent_mapped(struct page *page)
 {
-	struct folio *folio = page_folio(page);
+	return set_folio_extent_mapped(page_folio(page));
+}
+
+int set_folio_extent_mapped(struct folio *folio)
+{
 	struct btrfs_fs_info *fs_info;
 
-	ASSERT(page->mapping);
+	ASSERT(folio->mapping);
 
 	if (folio_test_private(folio))
 		return 0;
 
-	fs_info = btrfs_sb(page->mapping->host->i_sb);
+	fs_info = folio_to_fs_info(folio);
 
-	if (btrfs_is_subpage(fs_info, page->mapping))
+	if (btrfs_is_subpage(fs_info, folio->mapping))
 		return btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_DATA);
 
 	folio_attach_private(folio, (void *)EXTENT_FOLIO_PRIVATE);
@@ -963,20 +958,21 @@ void clear_page_extent_mapped(struct page *page)
 	if (!folio_test_private(folio))
 		return;
 
-	fs_info = btrfs_sb(page->mapping->host->i_sb);
+	fs_info = page_to_fs_info(page);
 	if (btrfs_is_subpage(fs_info, page->mapping))
 		return btrfs_detach_subpage(fs_info, folio);
 
 	folio_detach_private(folio);
 }
 
-static struct extent_map *
-__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
+static struct extent_map *__get_extent_map(struct inode *inode, struct page *page,
 		 u64 start, u64 len, struct extent_map **em_cached)
 {
 	struct extent_map *em;
 
-	if (em_cached && *em_cached) {
+	ASSERT(em_cached);
+
+	if (*em_cached) {
 		em = *em_cached;
 		if (extent_map_in_tree(em) && start >= em->start &&
 		    start < extent_map_end(em)) {
@@ -988,8 +984,8 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		*em_cached = NULL;
 	}
 
-	em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, start, len);
-	if (em_cached && !IS_ERR(em)) {
+	em = btrfs_get_extent(BTRFS_I(inode), page, start, len);
+	if (!IS_ERR(em)) {
 		BUG_ON(*em_cached);
 		refcount_inc(&em->refs);
 		*em_cached = em;
@@ -1007,7 +1003,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		      struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	u64 start = page_offset(page);
 	const u64 end = start + PAGE_SIZE - 1;
 	u64 cur = start;
@@ -1018,7 +1014,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 	int ret = 0;
 	size_t pg_offset = 0;
 	size_t iosize;
-	size_t blocksize = inode->i_sb->s_blocksize;
+	size_t blocksize = fs_info->sectorsize;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	ret = set_page_extent_mapped(page);
@@ -1051,8 +1047,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 			end_page_read(page, true, cur, iosize);
 			break;
 		}
-		em = __get_extent_map(inode, page, pg_offset, cur,
-				      end - cur + 1, em_cached);
+		em = __get_extent_map(inode, page, cur, end - cur + 1, em_cached);
 		if (IS_ERR(em)) {
 			unlock_extent(tree, cur, end, NULL);
 			end_page_read(page, false, cur, end + 1 - cur);
@@ -1157,15 +1152,18 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 int btrfs_read_folio(struct file *file, struct folio *folio)
 {
 	struct page *page = &folio->page;
-	struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+	struct btrfs_inode *inode = page_to_inode(page);
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
 	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
+	struct extent_map *em_cached = NULL;
 	int ret;
 
 	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
 
-	ret = btrfs_do_readpage(page, NULL, &bio_ctrl, NULL);
+	ret = btrfs_do_readpage(page, &em_cached, &bio_ctrl, NULL);
+	free_extent_map(em_cached);
+
 	/*
 	 * If btrfs_do_readpage() failed we will want to submit the assembled
 	 * bio to do the cleanup.
@@ -1180,9 +1178,11 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages,
 					struct btrfs_bio_ctrl *bio_ctrl,
 					u64 *prev_em_start)
 {
-	struct btrfs_inode *inode = BTRFS_I(pages[0]->mapping->host);
+	struct btrfs_inode *inode = page_to_inode(pages[0]);
 	int index;
 
+	ASSERT(em_cached);
+
 	btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
 
 	for (index = 0; index < nr_pages; index++) {
@@ -1371,7 +1371,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 			continue;
 		}
 
-		em = btrfs_get_extent(inode, NULL, 0, cur, len);
+		em = btrfs_get_extent(inode, NULL, cur, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR_OR_ZERO(em);
 			goto out_error;
@@ -1739,10 +1739,10 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
 			folio_lock(folio);
 			folio_clear_dirty_for_io(folio);
 			folio_start_writeback(folio);
-			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
 			ASSERT(ret);
 			wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
-						 folio_size(folio));
+						 eb->folio_size);
 			wbc->nr_to_write -= folio_nr_pages(folio);
 			folio_unlock(folio);
 		}
@@ -1766,7 +1766,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
  */
 static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(page);
 	struct folio *folio = page_folio(page);
 	int submitted = 0;
 	u64 page_start = page_offset(page);
@@ -1857,7 +1857,7 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 	if (!folio_test_private(folio))
 		return 0;
 
-	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
+	if (page_to_fs_info(page)->nodesize < PAGE_SIZE)
 		return submit_eb_subpage(page, wbc);
 
 	spin_lock(&mapping->i_private_lock);
@@ -1915,7 +1915,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 				   struct writeback_control *wbc)
 {
 	struct btrfs_eb_write_context ctx = { .wbc = wbc };
-	struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host);
 	int ret = 0;
 	int done = 0;
 	int nr_to_write_done = 0;
@@ -2203,7 +2203,7 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page,
 	bool found_error = false;
 	int ret = 0;
 	struct address_space *mapping = inode->i_mapping;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	const u32 sectorsize = fs_info->sectorsize;
 	loff_t i_size = i_size_read(inode);
 	u64 cur = start;
@@ -2309,7 +2309,7 @@ int extent_invalidate_folio(struct extent_io_tree *tree,
 	struct extent_state *cached_state = NULL;
 	u64 start = folio_pos(folio);
 	u64 end = start + folio_size(folio) - 1;
-	size_t blocksize = folio->mapping->host->i_sb->s_blocksize;
+	size_t blocksize = folio_to_fs_info(folio)->sectorsize;
 
 	/* This function is only called for the btree inode */
 	ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO);
@@ -2378,7 +2378,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
+	struct btrfs_inode *btrfs_inode = page_to_inode(page);
 	struct extent_io_tree *tree = &btrfs_inode->io_tree;
 	struct extent_map_tree *map = &btrfs_inode->extent_tree;
 
@@ -2453,12 +2453,65 @@ next:
 	return try_release_extent_state(tree, page, mask);
 }
 
+struct btrfs_fiemap_entry {
+	u64 offset;
+	u64 phys;
+	u64 len;
+	u32 flags;
+};
+
 /*
- * To cache previous fiemap extent
+ * Indicate the caller of emit_fiemap_extent() that it needs to unlock the file
+ * range from the inode's io tree, unlock the subvolume tree search path, flush
+ * the fiemap cache and relock the file range and research the subvolume tree.
+ * The value here is something negative that can't be confused with a valid
+ * errno value and different from 1 because that's also a return value from
+ * fiemap_fill_next_extent() and also it's often used to mean some btree search
+ * did not find a key, so make it some distinct negative value.
+ */
+#define BTRFS_FIEMAP_FLUSH_CACHE (-(MAX_ERRNO + 1))
+
+/*
+ * Used to:
+ *
+ * - Cache the next entry to be emitted to the fiemap buffer, so that we can
+ *   merge extents that are contiguous and can be grouped as a single one;
  *
- * Will be used for merging fiemap extent
+ * - Store extents ready to be written to the fiemap buffer in an intermediary
+ *   buffer. This intermediary buffer is to ensure that in case the fiemap
+ *   buffer is memory mapped to the fiemap target file, we don't deadlock
+ *   during btrfs_page_mkwrite(). This is because during fiemap we are locking
+ *   an extent range in order to prevent races with delalloc flushing and
+ *   ordered extent completion, which is needed in order to reliably detect
+ *   delalloc in holes and prealloc extents. And this can lead to a deadlock
+ *   if the fiemap buffer is memory mapped to the file we are running fiemap
+ *   against (a silly, useless in practice scenario, but possible) because
+ *   btrfs_page_mkwrite() will try to lock the same extent range.
  */
 struct fiemap_cache {
+	/* An array of ready fiemap entries. */
+	struct btrfs_fiemap_entry *entries;
+	/* Number of entries in the entries array. */
+	int entries_size;
+	/* Index of the next entry in the entries array to write to. */
+	int entries_pos;
+	/*
+	 * Once the entries array is full, this indicates what's the offset for
+	 * the next file extent item we must search for in the inode's subvolume
+	 * tree after unlocking the extent range in the inode's io tree and
+	 * releasing the search path.
+	 */
+	u64 next_search_offset;
+	/*
+	 * This matches struct fiemap_extent_info::fi_mapped_extents, we use it
+	 * to count ourselves emitted extents and stop instead of relying on
+	 * fiemap_fill_next_extent() because we buffer ready fiemap entries at
+	 * the @entries array, and we want to stop as soon as we hit the max
+	 * amount of extents to map, not just to save time but also to make the
+	 * logic at extent_fiemap() simpler.
+	 */
+	unsigned int extents_mapped;
+	/* Fields for the cached extent (unsubmitted, not ready, extent). */
 	u64 offset;
 	u64 phys;
 	u64 len;
@@ -2466,6 +2519,28 @@ struct fiemap_cache {
 	bool cached;
 };
 
+static int flush_fiemap_cache(struct fiemap_extent_info *fieinfo,
+			      struct fiemap_cache *cache)
+{
+	for (int i = 0; i < cache->entries_pos; i++) {
+		struct btrfs_fiemap_entry *entry = &cache->entries[i];
+		int ret;
+
+		ret = fiemap_fill_next_extent(fieinfo, entry->offset,
+					      entry->phys, entry->len,
+					      entry->flags);
+		/*
+		 * Ignore 1 (reached max entries) because we keep track of that
+		 * ourselves in emit_fiemap_extent().
+		 */
+		if (ret < 0)
+			return ret;
+	}
+	cache->entries_pos = 0;
+
+	return 0;
+}
+
 /*
  * Helper to submit fiemap extent.
  *
@@ -2480,7 +2555,8 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 				struct fiemap_cache *cache,
 				u64 offset, u64 phys, u64 len, u32 flags)
 {
-	int ret = 0;
+	struct btrfs_fiemap_entry *entry;
+	u64 cache_end;
 
 	/* Set at the end of extent_fiemap(). */
 	ASSERT((flags & FIEMAP_EXTENT_LAST) == 0);
@@ -2489,15 +2565,104 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 		goto assign;
 
 	/*
-	 * Sanity check, extent_fiemap() should have ensured that new
-	 * fiemap extent won't overlap with cached one.
-	 * Not recoverable.
+	 * When iterating the extents of the inode, at extent_fiemap(), we may
+	 * find an extent that starts at an offset behind the end offset of the
+	 * previous extent we processed. This happens if fiemap is called
+	 * without FIEMAP_FLAG_SYNC and there are ordered extents completing
+	 * after we had to unlock the file range, release the search path, emit
+	 * the fiemap extents stored in the buffer (cache->entries array) and
+	 * the lock the remainder of the range and re-search the btree.
+	 *
+	 * For example we are in leaf X processing its last item, which is the
+	 * file extent item for file range [512K, 1M[, and after
+	 * btrfs_next_leaf() releases the path, there's an ordered extent that
+	 * completes for the file range [768K, 2M[, and that results in trimming
+	 * the file extent item so that it now corresponds to the file range
+	 * [512K, 768K[ and a new file extent item is inserted for the file
+	 * range [768K, 2M[, which may end up as the last item of leaf X or as
+	 * the first item of the next leaf - in either case btrfs_next_leaf()
+	 * will leave us with a path pointing to the new extent item, for the
+	 * file range [768K, 2M[, since that's the first key that follows the
+	 * last one we processed. So in order not to report overlapping extents
+	 * to user space, we trim the length of the previously cached extent and
+	 * emit it.
 	 *
-	 * NOTE: Physical address can overlap, due to compression
+	 * Upon calling btrfs_next_leaf() we may also find an extent with an
+	 * offset smaller than or equals to cache->offset, and this happens
+	 * when we had a hole or prealloc extent with several delalloc ranges in
+	 * it, but after btrfs_next_leaf() released the path, delalloc was
+	 * flushed and the resulting ordered extents were completed, so we can
+	 * now have found a file extent item for an offset that is smaller than
+	 * or equals to what we have in cache->offset. We deal with this as
+	 * described below.
 	 */
-	if (cache->offset + cache->len > offset) {
-		WARN_ON(1);
-		return -EINVAL;
+	cache_end = cache->offset + cache->len;
+	if (cache_end > offset) {
+		if (offset == cache->offset) {
+			/*
+			 * We cached a dealloc range (found in the io tree) for
+			 * a hole or prealloc extent and we have now found a
+			 * file extent item for the same offset. What we have
+			 * now is more recent and up to date, so discard what
+			 * we had in the cache and use what we have just found.
+			 */
+			goto assign;
+		} else if (offset > cache->offset) {
+			/*
+			 * The extent range we previously found ends after the
+			 * offset of the file extent item we found and that
+			 * offset falls somewhere in the middle of that previous
+			 * extent range. So adjust the range we previously found
+			 * to end at the offset of the file extent item we have
+			 * just found, since this extent is more up to date.
+			 * Emit that adjusted range and cache the file extent
+			 * item we have just found. This corresponds to the case
+			 * where a previously found file extent item was split
+			 * due to an ordered extent completing.
+			 */
+			cache->len = offset - cache->offset;
+			goto emit;
+		} else {
+			const u64 range_end = offset + len;
+
+			/*
+			 * The offset of the file extent item we have just found
+			 * is behind the cached offset. This means we were
+			 * processing a hole or prealloc extent for which we
+			 * have found delalloc ranges (in the io tree), so what
+			 * we have in the cache is the last delalloc range we
+			 * found while the file extent item we found can be
+			 * either for a whole delalloc range we previously
+			 * emmitted or only a part of that range.
+			 *
+			 * We have two cases here:
+			 *
+			 * 1) The file extent item's range ends at or behind the
+			 *    cached extent's end. In this case just ignore the
+			 *    current file extent item because we don't want to
+			 *    overlap with previous ranges that may have been
+			 *    emmitted already;
+			 *
+			 * 2) The file extent item starts behind the currently
+			 *    cached extent but its end offset goes beyond the
+			 *    end offset of the cached extent. We don't want to
+			 *    overlap with a previous range that may have been
+			 *    emmitted already, so we emit the currently cached
+			 *    extent and then partially store the current file
+			 *    extent item's range in the cache, for the subrange
+			 *    going the cached extent's end to the end of the
+			 *    file extent item.
+			 */
+			if (range_end <= cache_end)
+				return 0;
+
+			if (!(flags & (FIEMAP_EXTENT_ENCODED | FIEMAP_EXTENT_DELALLOC)))
+				phys += cache_end - offset;
+
+			offset = cache_end;
+			len = range_end - cache_end;
+			goto emit;
+		}
 	}
 
 	/*
@@ -2517,12 +2682,37 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
 		return 0;
 	}
 
+emit:
 	/* Not mergeable, need to submit cached one */
-	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
-				      cache->len, cache->flags);
-	cache->cached = false;
-	if (ret)
-		return ret;
+
+	if (cache->entries_pos == cache->entries_size) {
+		/*
+		 * We will need to research for the end offset of the last
+		 * stored extent and not from the current offset, because after
+		 * unlocking the range and releasing the path, if there's a hole
+		 * between that end offset and this current offset, a new extent
+		 * may have been inserted due to a new write, so we don't want
+		 * to miss it.
+		 */
+		entry = &cache->entries[cache->entries_size - 1];
+		cache->next_search_offset = entry->offset + entry->len;
+		cache->cached = false;
+
+		return BTRFS_FIEMAP_FLUSH_CACHE;
+	}
+
+	entry = &cache->entries[cache->entries_pos];
+	entry->offset = cache->offset;
+	entry->phys = cache->phys;
+	entry->len = cache->len;
+	entry->flags = cache->flags;
+	cache->entries_pos++;
+	cache->extents_mapped++;
+
+	if (cache->extents_mapped == fieinfo->fi_extents_max) {
+		cache->cached = false;
+		return 1;
+	}
 assign:
 	cache->cached = true;
 	cache->offset = offset;
@@ -2562,7 +2752,7 @@ static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
 
 static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *path)
 {
-	struct extent_buffer *clone;
+	struct extent_buffer *clone = path->nodes[0];
 	struct btrfs_key key;
 	int slot;
 	int ret;
@@ -2571,29 +2761,45 @@ static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *p
 	if (path->slots[0] < btrfs_header_nritems(path->nodes[0]))
 		return 0;
 
+	/*
+	 * Add a temporary extra ref to an already cloned extent buffer to
+	 * prevent btrfs_next_leaf() freeing it, we want to reuse it to avoid
+	 * the cost of allocating a new one.
+	 */
+	ASSERT(test_bit(EXTENT_BUFFER_UNMAPPED, &clone->bflags));
+	atomic_inc(&clone->refs);
+
 	ret = btrfs_next_leaf(inode->root, path);
 	if (ret != 0)
-		return ret;
+		goto out;
 
 	/*
 	 * Don't bother with cloning if there are no more file extent items for
 	 * our inode.
 	 */
 	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-	if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY)
-		return 1;
+	if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY) {
+		ret = 1;
+		goto out;
+	}
 
 	/* See the comment at fiemap_search_slot() about why we clone. */
-	clone = btrfs_clone_extent_buffer(path->nodes[0]);
-	if (!clone)
-		return -ENOMEM;
+	copy_extent_buffer_full(clone, path->nodes[0]);
+	/*
+	 * Important to preserve the start field, for the optimizations when
+	 * checking if extents are shared (see extent_fiemap()).
+	 */
+	clone->start = path->nodes[0]->start;
 
 	slot = path->slots[0];
 	btrfs_release_path(path);
 	path->nodes[0] = clone;
 	path->slots[0] = slot;
+out:
+	if (ret)
+		free_extent_buffer(clone);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -2648,8 +2854,8 @@ static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path
 	 * neighbour leaf).
 	 * We also need the private clone because holding a read lock on an
 	 * extent buffer of the subvolume's b+tree will make lockdep unhappy
-	 * when we call fiemap_fill_next_extent(), because that may cause a page
-	 * fault when filling the user space buffer with fiemap data.
+	 * when we check if extents are shared, as backref walking may need to
+	 * lock the same leaf we are processing.
 	 */
 	clone = btrfs_clone_extent_buffer(path->nodes[0]);
 	if (!clone)
@@ -2873,24 +3079,29 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 	struct btrfs_backref_share_check_ctx *backref_ctx;
 	u64 last_extent_end;
 	u64 prev_extent_end;
-	u64 lockstart;
-	u64 lockend;
+	u64 range_start;
+	u64 range_end;
+	const u64 sectorsize = inode->root->fs_info->sectorsize;
 	bool stopped = false;
 	int ret;
 
+	cache.entries_size = PAGE_SIZE / sizeof(struct btrfs_fiemap_entry);
+	cache.entries = kmalloc_array(cache.entries_size,
+				      sizeof(struct btrfs_fiemap_entry),
+				      GFP_KERNEL);
 	backref_ctx = btrfs_alloc_backref_share_check_ctx();
 	path = btrfs_alloc_path();
-	if (!backref_ctx || !path) {
+	if (!cache.entries || !backref_ctx || !path) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	lockstart = round_down(start, inode->root->fs_info->sectorsize);
-	lockend = round_up(start + len, inode->root->fs_info->sectorsize);
-	prev_extent_end = lockstart;
+restart:
+	range_start = round_down(start, sectorsize);
+	range_end = round_up(start + len, sectorsize);
+	prev_extent_end = range_start;
 
-	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
+	lock_extent(&inode->io_tree, range_start, range_end, &cached_state);
 
 	ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
 	if (ret < 0)
@@ -2898,7 +3109,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 	btrfs_release_path(path);
 
 	path->reada = READA_FORWARD;
-	ret = fiemap_search_slot(inode, path, lockstart);
+	ret = fiemap_search_slot(inode, path, range_start);
 	if (ret < 0) {
 		goto out_unlock;
 	} else if (ret > 0) {
@@ -2910,7 +3121,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		goto check_eof_delalloc;
 	}
 
-	while (prev_extent_end < lockend) {
+	while (prev_extent_end < range_end) {
 		struct extent_buffer *leaf = path->nodes[0];
 		struct btrfs_file_extent_item *ei;
 		struct btrfs_key key;
@@ -2933,19 +3144,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		 * The first iteration can leave us at an extent item that ends
 		 * before our range's start. Move to the next item.
 		 */
-		if (extent_end <= lockstart)
+		if (extent_end <= range_start)
 			goto next_item;
 
 		backref_ctx->curr_leaf_bytenr = leaf->start;
 
 		/* We have in implicit hole (NO_HOLES feature enabled). */
 		if (prev_extent_end < key.offset) {
-			const u64 range_end = min(key.offset, lockend) - 1;
+			const u64 hole_end = min(key.offset, range_end) - 1;
 
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
 						  &delalloc_cached_state,
 						  backref_ctx, 0, 0, 0,
-						  prev_extent_end, range_end);
+						  prev_extent_end, hole_end);
 			if (ret < 0) {
 				goto out_unlock;
 			} else if (ret > 0) {
@@ -2955,7 +3166,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 			}
 
 			/* We've reached the end of the fiemap range, stop. */
-			if (key.offset >= lockend) {
+			if (key.offset >= range_end) {
 				stopped = true;
 				break;
 			}
@@ -3016,7 +3227,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		if (ret < 0) {
 			goto out_unlock;
 		} else if (ret > 0) {
-			/* fiemap_fill_next_extent() told us to stop. */
+			/* emit_fiemap_extent() told us to stop. */
 			stopped = true;
 			break;
 		}
@@ -3039,23 +3250,13 @@ next_item:
 	}
 
 check_eof_delalloc:
-	/*
-	 * Release (and free) the path before emitting any final entries to
-	 * fiemap_fill_next_extent() to keep lockdep happy. This is because
-	 * once we find no more file extent items exist, we may have a
-	 * non-cloned leaf, and fiemap_fill_next_extent() can trigger page
-	 * faults when copying data to the user space buffer.
-	 */
-	btrfs_free_path(path);
-	path = NULL;
-
-	if (!stopped && prev_extent_end < lockend) {
+	if (!stopped && prev_extent_end < range_end) {
 		ret = fiemap_process_hole(inode, fieinfo, &cache,
 					  &delalloc_cached_state, backref_ctx,
-					  0, 0, 0, prev_extent_end, lockend - 1);
+					  0, 0, 0, prev_extent_end, range_end - 1);
 		if (ret < 0)
 			goto out_unlock;
-		prev_extent_end = lockend;
+		prev_extent_end = range_end;
 	}
 
 	if (cache.cached && cache.offset + cache.len >= last_extent_end) {
@@ -3079,13 +3280,39 @@ check_eof_delalloc:
 		}
 	}
 
-	ret = emit_last_fiemap_cache(fieinfo, &cache);
-
 out_unlock:
-	unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
-	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
+	unlock_extent(&inode->io_tree, range_start, range_end, &cached_state);
+
+	if (ret == BTRFS_FIEMAP_FLUSH_CACHE) {
+		btrfs_release_path(path);
+		ret = flush_fiemap_cache(fieinfo, &cache);
+		if (ret)
+			goto out;
+		len -= cache.next_search_offset - start;
+		start = cache.next_search_offset;
+		goto restart;
+	} else if (ret < 0) {
+		goto out;
+	}
+
+	/*
+	 * Must free the path before emitting to the fiemap buffer because we
+	 * may have a non-cloned leaf and if the fiemap buffer is memory mapped
+	 * to a file, a write into it (through btrfs_page_mkwrite()) may trigger
+	 * waiting for an ordered extent that in order to complete needs to
+	 * modify that leaf, therefore leading to a deadlock.
+	 */
+	btrfs_free_path(path);
+	path = NULL;
+
+	ret = flush_fiemap_cache(fieinfo, &cache);
+	if (ret)
+		goto out;
+
+	ret = emit_last_fiemap_cache(fieinfo, &cache);
 out:
 	free_extent_state(delalloc_cached_state);
+	kfree(cache.entries);
 	btrfs_free_backref_share_ctx(backref_ctx);
 	btrfs_free_path(path);
 	return ret;
@@ -3534,7 +3761,7 @@ retry:
 	/* For now, we should only have single-page folios for btree inode. */
 	ASSERT(folio_nr_pages(existing_folio) == 1);
 
-	if (folio_size(existing_folio) != folio_size(eb->folios[0])) {
+	if (folio_size(existing_folio) != eb->folio_size) {
 		folio_unlock(existing_folio);
 		folio_put(existing_folio);
 		return -EAGAIN;
@@ -3677,6 +3904,8 @@ reallocate:
 		 * and free the allocated page.
 		 */
 		folio = eb->folios[i];
+		eb->folio_size = folio_size(folio);
+		eb->folio_shift = folio_shift(folio);
 		spin_lock(&mapping->i_private_lock);
 		/* Should not fail, as we have preallocated the memory */
 		ret = attach_extent_buffer_folio(eb, folio, prealloc);
@@ -4126,7 +4355,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 		for (int i = 0; i < num_folios; i++) {
 			struct folio *folio = eb->folios[i];
 
-			ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0);
+			ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
 			ASSERT(ret);
 		}
 	}
@@ -4146,7 +4375,7 @@ static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
 			    unsigned long len)
 {
 	btrfs_warn(eb->fs_info,
-		"access to eb bytenr %llu len %lu out of range start %lu len %lu",
+		"access to eb bytenr %llu len %u out of range start %lu len %lu",
 		eb->start, eb->len, start, len);
 	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
 
@@ -4175,7 +4404,7 @@ static inline int check_eb_range(const struct extent_buffer *eb,
 void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 			unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *dst = (char *)dstv;
@@ -4215,7 +4444,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 				       void __user *dstv,
 				       unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char __user *dst = (char __user *)dstv;
@@ -4255,7 +4484,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
 int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 			 unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *kaddr;
@@ -4326,7 +4555,7 @@ static void __write_extent_buffer(const struct extent_buffer *eb,
 				  const void *srcv, unsigned long start,
 				  unsigned long len, bool use_memmove)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	size_t cur;
 	size_t offset;
 	char *kaddr;
@@ -4375,7 +4604,7 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 static void memset_extent_buffer(const struct extent_buffer *eb, int c,
 				 unsigned long start, unsigned long len)
 {
-	const int unit_size = folio_size(eb->folios[0]);
+	const int unit_size = eb->folio_size;
 	unsigned long cur = start;
 
 	if (eb->addr) {
@@ -4406,7 +4635,7 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
 void copy_extent_buffer_full(const struct extent_buffer *dst,
 			     const struct extent_buffer *src)
 {
-	const int unit_size = folio_size(src->folios[0]);
+	const int unit_size = src->folio_size;
 	unsigned long cur = 0;
 
 	ASSERT(dst->len == src->len);
@@ -4428,7 +4657,7 @@ void copy_extent_buffer(const struct extent_buffer *dst,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len)
 {
-	const int unit_size = folio_size(dst->folios[0]);
+	const int unit_size = dst->folio_size;
 	u64 dst_len = dst->len;
 	size_t cur;
 	size_t offset;
@@ -4484,10 +4713,10 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb,
 	 * the bitmap item in the extent buffer + the offset of the byte in the
 	 * bitmap item.
 	 */
-	offset = start + offset_in_folio(eb->folios[0], eb->start) + byte_offset;
+	offset = start + offset_in_eb_folio(eb, eb->start) + byte_offset;
 
-	*folio_index = offset >> folio_shift(eb->folios[0]);
-	*folio_offset = offset_in_folio(eb->folios[0], offset);
+	*folio_index = offset >> eb->folio_shift;
+	*folio_offset = offset_in_eb_folio(eb, offset);
 }
 
 /*
@@ -4601,7 +4830,7 @@ void memcpy_extent_buffer(const struct extent_buffer *dst,
 			  unsigned long dst_offset, unsigned long src_offset,
 			  unsigned long len)
 {
-	const int unit_size = folio_size(dst->folios[0]);
+	const int unit_size = dst->folio_size;
 	unsigned long cur_off = 0;
 
 	if (check_eb_range(dst, dst_offset, len) ||
@@ -4725,7 +4954,7 @@ out:
 
 static int try_release_subpage_extent_buffer(struct page *page)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(page);
 	u64 cur = page_offset(page);
 	const u64 end = page_offset(page) + PAGE_SIZE;
 	int ret;
@@ -4798,7 +5027,7 @@ int try_release_extent_buffer(struct page *page)
 	struct folio *folio = page_folio(page);
 	struct extent_buffer *eb;
 
-	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
+	if (page_to_fs_info(page)->nodesize < PAGE_SIZE)
 		return try_release_subpage_extent_buffer(page);
 
 	/*
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 46050500529b..e3530d427e1f 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -7,11 +7,32 @@
 #include <linux/refcount.h>
 #include <linux/fiemap.h>
 #include <linux/btrfs_tree.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <linux/rwsem.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include "compression.h"
+#include "messages.h"
 #include "ulist.h"
 #include "misc.h"
 
+struct page;
+struct file;
+struct folio;
+struct inode;
+struct fiemap_extent_info;
+struct readahead_control;
+struct address_space;
+struct writeback_control;
+struct extent_io_tree;
+struct extent_map_tree;
+struct btrfs_block_group;
+struct btrfs_fs_info;
+struct btrfs_inode;
+struct btrfs_root;
 struct btrfs_trans_handle;
+struct btrfs_tree_parent_check;
 
 enum {
 	EXTENT_BUFFER_UPTODATE,
@@ -63,11 +84,6 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
-struct btrfs_root;
-struct btrfs_inode;
-struct btrfs_fs_info;
-struct extent_io_tree;
-struct btrfs_tree_parent_check;
 
 int __init extent_buffer_init_cachep(void);
 void __cold extent_buffer_free_cachep(void);
@@ -75,7 +91,8 @@ void __cold extent_buffer_free_cachep(void);
 #define INLINE_EXTENT_BUFFER_PAGES     (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE)
 struct extent_buffer {
 	u64 start;
-	unsigned long len;
+	u32 len;
+	u32 folio_size;
 	unsigned long bflags;
 	struct btrfs_fs_info *fs_info;
 
@@ -90,6 +107,7 @@ struct extent_buffer {
 	int read_mirror;
 	/* >= 0 if eb belongs to a log tree, -1 otherwise */
 	s8 log_index;
+	u8 folio_shift;
 	struct rcu_head rcu_head;
 
 	struct rw_semaphore lock;
@@ -113,6 +131,13 @@ struct btrfs_eb_write_context {
 	struct btrfs_block_group *zoned_bg;
 };
 
+static inline unsigned long offset_in_eb_folio(const struct extent_buffer *eb,
+					       u64 start)
+{
+	ASSERT(eb->folio_size);
+	return start & (eb->folio_size - 1);
+}
+
 /*
  * Get the correct offset inside the page of extent buffer.
  *
@@ -151,13 +176,13 @@ static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb,
 	 *	   the folio_shift would be large enough to always make us
 	 *	   return 0 as index.
 	 *    1.2) Several page sized folios
-	 *         The folio_shift() would be PAGE_SHIFT, giving us the correct
+	 *         The folio_shift would be PAGE_SHIFT, giving us the correct
 	 *         index.
 	 *
 	 * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case
 	 *    The folio would only be page sized, and always give us 0 as index.
 	 */
-	return offset >> folio_shift(eb->folios[0]);
+	return offset >> eb->folio_shift;
 }
 
 /*
@@ -205,8 +230,6 @@ static inline void extent_changeset_free(struct extent_changeset *changeset)
 	kfree(changeset);
 }
 
-struct extent_map_tree;
-
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
@@ -221,6 +244,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 void extent_readahead(struct readahead_control *rac);
 int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		  u64 start, u64 len);
+int set_folio_extent_mapped(struct folio *folio);
 int set_page_extent_mapped(struct page *page);
 void clear_page_extent_mapped(struct page *page);
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index b61099bf97a8..347ca13d15a9 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -5,7 +5,6 @@
 #include <linux/spinlock.h>
 #include "messages.h"
 #include "ctree.h"
-#include "volumes.h"
 #include "extent_map.h"
 #include "compression.h"
 #include "btrfs_inode.h"
@@ -16,8 +15,7 @@ static struct kmem_cache *extent_map_cache;
 int __init extent_map_init(void)
 {
 	extent_map_cache = kmem_cache_create("btrfs_extent_map",
-			sizeof(struct extent_map), 0,
-			SLAB_MEM_SPREAD, NULL);
+					     sizeof(struct extent_map), 0, 0, NULL);
 	if (!extent_map_cache)
 		return -ENOMEM;
 	return 0;
@@ -291,6 +289,10 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
  * Called after an extent has been written to disk properly.  Set the generation
  * to the generation that actually added the file item to the inode so we know
  * we need to sync this extent when we call fsync().
+ *
+ * Returns: 0	     on success
+ * 	    -ENOENT  when the extent is not found in the tree
+ * 	    -EUCLEAN if the found extent does not match the expected start
  */
 int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 {
@@ -308,14 +310,18 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 "no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu",
 			   btrfs_ino(inode), btrfs_root_id(inode->root),
 			   start, len, gen);
+		ret = -ENOENT;
 		goto out;
 	}
 
-	if (WARN_ON(em->start != start))
+	if (WARN_ON(em->start != start)) {
 		btrfs_warn(fs_info,
 "found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu",
 			   btrfs_ino(inode), btrfs_root_id(inode->root),
 			   em->start, start, len, gen);
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	em->generation = gen;
 	em->flags &= ~EXTENT_FLAG_PINNED;
@@ -531,7 +537,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 	u64 end;
 	u64 start_diff;
 
-	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
+	if (map_start < em->start || map_start >= extent_map_end(em))
+		return -EINVAL;
 
 	if (existing->start > map_start) {
 		next = existing;
@@ -626,9 +633,9 @@ int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info,
 				free_extent_map(em);
 				*em_in = NULL;
 				WARN_ONCE(ret,
-"unexpected error %d: merge existing(start %llu len %llu) with em(start %llu len %llu)\n",
-					  ret, existing->start, existing->len,
-					  orig_start, orig_len);
+"extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu\n",
+					  existing->start, existing->len,
+					  orig_start, orig_len, start);
 			}
 			free_extent_map(existing);
 		}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index e380fc08bbe4..c5a098c99cc6 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -3,10 +3,18 @@
 #ifndef BTRFS_EXTENT_MAP_H
 #define BTRFS_EXTENT_MAP_H
 
+#include <linux/compiler_types.h>
+#include <linux/rwlock_types.h>
 #include <linux/rbtree.h>
+#include <linux/list.h>
 #include <linux/refcount.h>
+#include "misc.h"
+#include "extent_map.h"
 #include "compression.h"
 
+struct btrfs_inode;
+struct btrfs_fs_info;
+
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
 #define EXTENT_MAP_INLINE ((u64)-2)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 81ac1d474bf1..e58fb5347e65 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -10,17 +10,14 @@
 #include <linux/sched/mm.h>
 #include <crypto/hash.h>
 #include "messages.h"
-#include "misc.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "bio.h"
-#include "print-tree.h"
 #include "compression.h"
 #include "fs.h"
 #include "accessors.h"
 #include "file-item.h"
-#include "super.h"
 
 #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
@@ -179,7 +176,6 @@ int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans,
 				      sizeof(*item));
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret); /* Can't happen */
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0],
 			      struct btrfs_file_extent_item);
@@ -1229,8 +1225,6 @@ insert:
 				      ins_size);
 	if (ret < 0)
 		goto out;
-	if (WARN_ON(ret != 0))
-		goto out;
 	leaf = path->nodes[0];
 csum:
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 04bd2d34efb1..15c05cc0fce6 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -3,8 +3,21 @@
 #ifndef BTRFS_FILE_ITEM_H
 #define BTRFS_FILE_ITEM_H
 
+#include <linux/list.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "accessors.h"
 
+struct extent_map;
+struct btrfs_file_extent_item;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_bio;
+struct btrfs_trans_handle;
+struct btrfs_root;
+struct btrfs_ordered_sum;
+struct btrfs_path;
+struct btrfs_inode;
+
 #define BTRFS_FILE_EXTENT_INLINE_DATA_START		\
 		(offsetof(struct btrfs_file_extent_item, disk_bytenr))
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 38dfcac47609..f9d76072398d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -22,10 +22,8 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "tree-log.h"
 #include "locking.h"
-#include "volumes.h"
 #include "qgroup.h"
 #include "compression.h"
 #include "delalloc-space.h"
@@ -1137,7 +1135,7 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	loff_t pos = iocb->ki_pos;
 	int ret;
 	loff_t oldsize;
@@ -1185,7 +1183,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 	struct file *file = iocb->ki_filp;
 	loff_t pos;
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct page **pages = NULL;
 	struct extent_changeset *data_reserved = NULL;
 	u64 release_bytes = 0;
@@ -1461,7 +1459,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	loff_t pos;
 	ssize_t written = 0;
 	ssize_t written_buffered;
@@ -1787,7 +1785,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = d_inode(dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
@@ -1912,6 +1910,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out_release_extents;
 	}
 
+	btrfs_init_log_ctx_scratch_eb(&ctx);
+
 	/*
 	 * We use start here because we will need to wait on the IO to complete
 	 * in btrfs_sync_log, which could require joining a transaction (for
@@ -1931,6 +1931,15 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trans->in_fsync = true;
 
 	ret = btrfs_log_dentry_safe(trans, dentry, &ctx);
+	/*
+	 * Scratch eb no longer needed, release before syncing log or commit
+	 * transaction, to avoid holding unnecessary memory during such long
+	 * operations.
+	 */
+	if (ctx.scratch_eb) {
+		free_extent_buffer(ctx.scratch_eb);
+		ctx.scratch_eb = NULL;
+	}
 	btrfs_release_log_ctx_extents(&ctx);
 	if (ret < 0) {
 		/* Fallthrough and commit/free transaction. */
@@ -2006,6 +2015,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	ret = btrfs_commit_transaction(trans);
 out:
+	free_extent_buffer(ctx.scratch_eb);
 	ASSERT(list_empty(&ctx.list));
 	ASSERT(list_empty(&ctx.conflict_inodes));
 	err = file_check_and_advance_wb_err(file);
@@ -2176,7 +2186,7 @@ static int find_first_non_hole(struct btrfs_inode *inode, u64 *start, u64 *len)
 	struct extent_map *em;
 	int ret = 0;
 
-	em = btrfs_get_extent(inode, NULL, 0,
+	em = btrfs_get_extent(inode, NULL,
 			      round_down(*start, fs_info->sectorsize),
 			      round_up(*len, fs_info->sectorsize));
 	if (IS_ERR(em))
@@ -2593,7 +2603,7 @@ out:
 static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
@@ -2835,7 +2845,7 @@ static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode,
 	int ret;
 
 	offset = round_down(offset, sectorsize);
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(inode, NULL, offset, sectorsize);
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 
@@ -2866,7 +2876,7 @@ static int btrfs_zero_range(struct inode *inode,
 	u64 bytes_to_reserve = 0;
 	bool space_reserved = false;
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, alloc_start,
 			      alloc_end - alloc_start);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
@@ -2909,8 +2919,7 @@ static int btrfs_zero_range(struct inode *inode,
 
 	if (BTRFS_BYTES_TO_BLKS(fs_info, offset) ==
 	    BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) {
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
-				      sectorsize);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, alloc_start, sectorsize);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
@@ -3005,7 +3014,7 @@ reserve_space:
 		}
 		ret = btrfs_prealloc_file_range(inode, mode, alloc_start,
 						alloc_end - alloc_start,
-						i_blocksize(inode),
+						fs_info->sectorsize,
 						offset + len, &alloc_hint);
 		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			      &cached_state);
@@ -3049,7 +3058,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	int ret;
 
 	/* Do not allow fallocate in ZONED mode */
-	if (btrfs_is_zoned(btrfs_sb(inode->i_sb)))
+	if (btrfs_is_zoned(inode_to_fs_info(inode)))
 		return -EOPNOTSUPP;
 
 	alloc_start = round_down(offset, blocksize);
@@ -3126,7 +3135,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 
 	/* First, check if we exceed the qgroup limit */
 	while (cur_offset < alloc_end) {
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, cur_offset,
 				      alloc_end - cur_offset);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
@@ -3177,7 +3186,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret) {
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, i_blocksize(inode),
+					range->len, blocksize,
 					offset + len, &alloc_hint);
 			/*
 			 * btrfs_prealloc_file_range() releases space even
@@ -3754,7 +3763,7 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to)
 	if (fsverity_active(inode))
 		return 0;
 
-	if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos))
+	if (check_direct_read(inode_to_fs_info(inode), to, iocb->ki_pos))
 		return 0;
 
 	btrfs_inode_lock(BTRFS_I(inode), BTRFS_ILOCK_SHARED);
diff --git a/fs/btrfs/file.h b/fs/btrfs/file.h
index 82b34fbb295f..77aaca208c7b 100644
--- a/fs/btrfs/file.h
+++ b/fs/btrfs/file.h
@@ -3,6 +3,21 @@
 #ifndef BTRFS_FILE_H
 #define BTRFS_FILE_H
 
+#include <linux/types.h>
+
+struct file;
+struct extent_state;
+struct kiocb;
+struct iov_iter;
+struct page;
+struct btrfs_ioctl_encoded_io_args;
+struct btrfs_drop_extents_args;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_path;
+struct btrfs_replace_extent_info;
+struct btrfs_trans_handle;
+
 extern const struct file_operations btrfs_file_operations;
 
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d372c7ce0e6b..c8a05d5eb9cb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -19,9 +19,7 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "extent_io.h"
-#include "volumes.h"
 #include "space-info.h"
-#include "delalloc-space.h"
 #include "block-group.h"
 #include "discard.h"
 #include "subpage.h"
@@ -399,7 +397,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 		return -ENOMEM;
 
 	io_ctl->num_pages = num_pages;
-	io_ctl->fs_info = btrfs_sb(inode->i_sb);
+	io_ctl->fs_info = inode_to_fs_info(inode);
 	io_ctl->inode = inode;
 
 	return 0;
@@ -2621,7 +2619,7 @@ static void steal_from_bitmap(struct btrfs_free_space_ctl *ctl,
 	}
 }
 
-int __btrfs_add_free_space(struct btrfs_block_group *block_group,
+static int __btrfs_add_free_space(struct btrfs_block_group *block_group,
 			   u64 offset, u64 bytes,
 			   enum btrfs_trim_state trim_state)
 {
@@ -4156,15 +4154,13 @@ out:
 
 int __init btrfs_free_space_init(void)
 {
-	btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space",
-			sizeof(struct btrfs_free_space), 0,
-			SLAB_MEM_SPREAD, NULL);
+	btrfs_free_space_cachep = KMEM_CACHE(btrfs_free_space, 0);
 	if (!btrfs_free_space_cachep)
 		return -ENOMEM;
 
 	btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
 							PAGE_SIZE, PAGE_SIZE,
-							SLAB_MEM_SPREAD, NULL);
+							0, NULL);
 	if (!btrfs_free_space_bitmap_cachep) {
 		kmem_cache_destroy(btrfs_free_space_cachep);
 		return -ENOMEM;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 33b4da3271b1..83774bfd7b3b 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -6,6 +6,19 @@
 #ifndef BTRFS_FREE_SPACE_CACHE_H
 #define BTRFS_FREE_SPACE_CACHE_H
 
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include "fs.h"
+
+struct inode;
+struct page;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_trans_handle;
+struct btrfs_trim_block_group;
+
 /*
  * This is the trim state of an extent or bitmap.
  *
@@ -114,8 +127,6 @@ int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
 
 void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
 			       struct btrfs_free_space_ctl *ctl);
-int __btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr,
-			   u64 size, enum btrfs_trim_state trim_state);
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
 int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 7b598b070700..90f2938bd743 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1176,12 +1176,16 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 					    BTRFS_FREE_SPACE_TREE_OBJECTID);
 	if (IS_ERR(free_space_root)) {
 		ret = PTR_ERR(free_space_root);
-		goto abort;
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		goto out_clear;
 	}
 	ret = btrfs_global_root_insert(free_space_root);
 	if (ret) {
 		btrfs_put_root(free_space_root);
-		goto abort;
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		goto out_clear;
 	}
 
 	node = rb_first_cached(&fs_info->block_group_cache_tree);
@@ -1189,8 +1193,11 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
-		if (ret)
-			goto abort;
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
+			goto out_clear;
+		}
 		node = rb_next(node);
 	}
 
@@ -1206,11 +1213,9 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 	return ret;
 
-abort:
+out_clear:
 	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
 	return ret;
 }
 
@@ -1273,12 +1278,18 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
 
 	ret = clear_free_space_tree(trans, free_space_root);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	ret = btrfs_del_root(trans, &free_space_root->root_key);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	btrfs_global_root_delete(free_space_root);
 
@@ -1295,11 +1306,6 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(free_space_root);
 
 	return btrfs_commit_transaction(trans);
-
-abort:
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
-	return ret;
 }
 
 int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
@@ -1322,8 +1328,11 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 
 	ret = clear_free_space_tree(trans, free_space_root);
-	if (ret)
-		goto abort;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
+		return ret;
+	}
 
 	node = rb_first_cached(&fs_info->block_group_cache_tree);
 	while (node) {
@@ -1332,8 +1341,11 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
 		ret = populate_free_space_tree(trans, block_group);
-		if (ret)
-			goto abort;
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
+			return ret;
+		}
 		node = rb_next(node);
 	}
 
@@ -1344,10 +1356,6 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 	ret = btrfs_commit_transaction(trans);
 	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
 	return ret;
-abort:
-	btrfs_abort_transaction(trans, ret);
-	btrfs_end_transaction(trans);
-	return ret;
 }
 
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index 6d5551d0ced8..e6c6d6f4f221 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -6,7 +6,13 @@
 #ifndef BTRFS_FREE_SPACE_TREE_H
 #define BTRFS_FREE_SPACE_TREE_H
 
+#include <linux/bits.h>
+
 struct btrfs_caching_control;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_block_group;
+struct btrfs_trans_handle;
 
 /*
  * The default size for new free space bitmap items. The last bitmap in a block
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index f8bb73d6ab68..93f5c57ea4e3 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -4,13 +4,50 @@
 #define BTRFS_FS_H
 
 #include <linux/blkdev.h>
-#include <linux/fs.h>
-#include <linux/btrfs_tree.h>
 #include <linux/sizes.h>
+#include <linux/time64.h>
+#include <linux/compiler.h>
+#include <linux/math.h>
+#include <linux/atomic.h>
+#include <linux/blkdev.h>
+#include <linux/percpu_counter.h>
+#include <linux/completion.h>
+#include <linux/lockdep.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rwlock_types.h>
+#include <linux/rwsem.h>
+#include <linux/semaphore.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/wait_bit.h>
+#include <linux/sched.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "extent-io-tree.h"
-#include "extent_map.h"
 #include "async-thread.h"
 #include "block-rsv.h"
+#include "fs.h"
+
+struct inode;
+struct super_block;
+struct kobject;
+struct reloc_control;
+struct crypto_shash;
+struct ulist;
+struct btrfs_device;
+struct btrfs_block_group;
+struct btrfs_root;
+struct btrfs_fs_devices;
+struct btrfs_transaction;
+struct btrfs_delayed_root;
+struct btrfs_balance_control;
+struct btrfs_subpage_info;
+struct btrfs_stripe_hash_table;
+struct btrfs_space_info;
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
@@ -732,10 +769,13 @@ struct btrfs_fs_info {
 
 	/* Reclaim partially filled block groups in the background */
 	struct work_struct reclaim_bgs_work;
+	/* Protected by unused_bgs_lock. */
 	struct list_head reclaim_bgs;
 	int bg_reclaim_threshold;
 
+	/* Protects the lists unused_bgs and reclaim_bgs. */
 	spinlock_t unused_bgs_lock;
+	/* Protected by unused_bgs_lock. */
 	struct list_head unused_bgs;
 	struct mutex unused_bg_unpin_mutex;
 	/* Protect block groups that are going to be deleted */
@@ -829,6 +869,17 @@ struct btrfs_fs_info {
 #endif
 };
 
+#define page_to_inode(_page)	(BTRFS_I(_Generic((_page),			\
+					  struct page *: (_page))->mapping->host))
+#define folio_to_inode(_folio)	(BTRFS_I(_Generic((_folio),			\
+					  struct folio *: (_folio))->mapping->host))
+
+#define page_to_fs_info(_page)	 (page_to_inode(_page)->root->fs_info)
+#define folio_to_fs_info(_folio) (folio_to_inode(_folio)->root->fs_info)
+
+#define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode),			\
+					   struct inode *: (_inode)))->root->fs_info)
+
 static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info)
 {
 	return READ_ONCE(fs_info->generation);
@@ -922,6 +973,8 @@ void btrfs_exclop_finish(struct btrfs_fs_info *fs_info);
 void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
 			  enum btrfs_exclusive_operation op);
 
+int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args);
+
 /* Compatibility and incompatibility defines */
 void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
 			     const char *name);
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 7d734830e514..9c1394c0a6d7 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -9,7 +9,6 @@
 #include "inode-item.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "space-info.h"
 #include "accessors.h"
 #include "extent-tree.h"
diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h
index 4337bb26f419..c4aded82709b 100644
--- a/fs/btrfs/inode-item.h
+++ b/fs/btrfs/inode-item.h
@@ -6,14 +6,15 @@
 #include <linux/types.h>
 #include <linux/crc32c.h>
 
+struct fscrypt_str;
+struct extent_buffer;
 struct btrfs_trans_handle;
 struct btrfs_root;
 struct btrfs_path;
 struct btrfs_key;
 struct btrfs_inode_extref;
 struct btrfs_inode;
-struct extent_buffer;
-struct fscrypt_str;
+struct btrfs_truncate_control;
 
 /*
  * Return this if we need to call truncate_block for the last bit of the
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1eb93d3962aa..37701531eeb1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -39,14 +39,12 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "ordered-data.h"
 #include "xattr.h"
 #include "tree-log.h"
 #include "bio.h"
 #include "compression.h"
 #include "locking.h"
-#include "free-space-cache.h"
 #include "props.h"
 #include "qgroup.h"
 #include "delalloc-space.h"
@@ -740,7 +738,8 @@ static noinline int add_async_extent(struct async_chunk *cow,
 	struct async_extent *async_extent;
 
 	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
-	BUG_ON(!async_extent); /* -ENOMEM */
+	if (!async_extent)
+		return -ENOMEM;
 	async_extent->start = start;
 	async_extent->ram_size = ram_size;
 	async_extent->compressed_size = compressed_size;
@@ -1027,8 +1026,9 @@ again:
 	 * The async work queues will take care of doing actual allocation on
 	 * disk for these compressed pages, and will submit the bios.
 	 */
-	add_async_extent(async_chunk, start, total_in, total_compressed, pages,
-			 nr_pages, compress_type);
+	ret = add_async_extent(async_chunk, start, total_in, total_compressed, pages,
+			       nr_pages, compress_type);
+	BUG_ON(ret);
 	if (start + total_in < end) {
 		start += total_in;
 		cond_resched();
@@ -1040,8 +1040,9 @@ mark_incompressible:
 	if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) && !inode->prop_compress)
 		inode->flags |= BTRFS_INODE_NOCOMPRESS;
 cleanup_and_bail_uncompressed:
-	add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
-			 BTRFS_COMPRESS_NONE);
+	ret = add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
+			       BTRFS_COMPRESS_NONE);
+	BUG_ON(ret);
 free_pages:
 	if (pages) {
 		for (i = 0; i < nr_pages; i++) {
@@ -2302,6 +2303,8 @@ void btrfs_split_delalloc_extent(struct btrfs_inode *inode,
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 size;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	/* not delalloc, ignore it */
 	if (!(orig->state & EXTENT_DELALLOC))
 		return;
@@ -2340,6 +2343,8 @@ void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state
 	u64 new_size, old_size;
 	u32 num_extents;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
@@ -2387,55 +2392,50 @@ void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state
 	spin_unlock(&inode->lock);
 }
 
-static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
-				      struct btrfs_inode *inode)
+static void btrfs_add_delalloc_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	spin_lock(&root->delalloc_lock);
-	if (list_empty(&inode->delalloc_inodes)) {
-		list_add_tail(&inode->delalloc_inodes, &root->delalloc_inodes);
-		set_bit(BTRFS_INODE_IN_DELALLOC_LIST, &inode->runtime_flags);
-		root->nr_delalloc_inodes++;
-		if (root->nr_delalloc_inodes == 1) {
-			spin_lock(&fs_info->delalloc_root_lock);
-			BUG_ON(!list_empty(&root->delalloc_root));
-			list_add_tail(&root->delalloc_root,
-				      &fs_info->delalloc_roots);
-			spin_unlock(&fs_info->delalloc_root_lock);
-		}
+	ASSERT(list_empty(&inode->delalloc_inodes));
+	list_add_tail(&inode->delalloc_inodes, &root->delalloc_inodes);
+	root->nr_delalloc_inodes++;
+	if (root->nr_delalloc_inodes == 1) {
+		spin_lock(&fs_info->delalloc_root_lock);
+		ASSERT(list_empty(&root->delalloc_root));
+		list_add_tail(&root->delalloc_root, &fs_info->delalloc_roots);
+		spin_unlock(&fs_info->delalloc_root_lock);
 	}
 	spin_unlock(&root->delalloc_lock);
 }
 
-void __btrfs_del_delalloc_inode(struct btrfs_root *root,
-				struct btrfs_inode *inode)
+void btrfs_del_delalloc_inode(struct btrfs_inode *inode)
 {
+	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
+	lockdep_assert_held(&root->delalloc_lock);
+
+	/*
+	 * We may be called after the inode was already deleted from the list,
+	 * namely in the transaction abort path btrfs_destroy_delalloc_inodes(),
+	 * and then later through btrfs_clear_delalloc_extent() while the inode
+	 * still has ->delalloc_bytes > 0.
+	 */
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
-		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &inode->runtime_flags);
 		root->nr_delalloc_inodes--;
 		if (!root->nr_delalloc_inodes) {
 			ASSERT(list_empty(&root->delalloc_inodes));
 			spin_lock(&fs_info->delalloc_root_lock);
-			BUG_ON(list_empty(&root->delalloc_root));
+			ASSERT(!list_empty(&root->delalloc_root));
 			list_del_init(&root->delalloc_root);
 			spin_unlock(&fs_info->delalloc_root_lock);
 		}
 	}
 }
 
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct btrfs_inode *inode)
-{
-	spin_lock(&root->delalloc_lock);
-	__btrfs_del_delalloc_inode(root, inode);
-	spin_unlock(&root->delalloc_lock);
-}
-
 /*
  * Properly track delayed allocation bytes in the inode and to maintain the
  * list of inodes that have pending delalloc work to be done.
@@ -2445,6 +2445,8 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	if ((bits & EXTENT_DEFRAG) && !(bits & EXTENT_DELALLOC))
 		WARN_ON(1);
 	/*
@@ -2453,10 +2455,9 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if (!(state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
-		struct btrfs_root *root = inode->root;
 		u64 len = state->end + 1 - state->start;
+		u64 prev_delalloc_bytes;
 		u32 num_extents = count_max_extents(fs_info, len);
-		bool do_list = !btrfs_is_free_space_inode(inode);
 
 		spin_lock(&inode->lock);
 		btrfs_mod_outstanding_extents(inode, num_extents);
@@ -2469,13 +2470,20 @@ void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *s
 		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
 					 fs_info->delalloc_batch);
 		spin_lock(&inode->lock);
+		prev_delalloc_bytes = inode->delalloc_bytes;
 		inode->delalloc_bytes += len;
 		if (bits & EXTENT_DEFRAG)
 			inode->defrag_bytes += len;
-		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-					 &inode->runtime_flags))
-			btrfs_add_delalloc_inodes(root, inode);
 		spin_unlock(&inode->lock);
+
+		/*
+		 * We don't need to be under the protection of the inode's lock,
+		 * because we are called while holding the inode's io_tree lock
+		 * and are therefore protected against concurrent calls of this
+		 * function and btrfs_clear_delalloc_extent().
+		 */
+		if (!btrfs_is_free_space_inode(inode) && prev_delalloc_bytes == 0)
+			btrfs_add_delalloc_inode(inode);
 	}
 
 	if (!(state->state & EXTENT_DELALLOC_NEW) &&
@@ -2497,6 +2505,8 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 	u64 len = state->end + 1 - state->start;
 	u32 num_extents = count_max_extents(fs_info, len);
 
+	lockdep_assert_held(&inode->io_tree.lock);
+
 	if ((state->state & EXTENT_DEFRAG) && (bits & EXTENT_DEFRAG)) {
 		spin_lock(&inode->lock);
 		inode->defrag_bytes -= len;
@@ -2510,7 +2520,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = inode->root;
-		bool do_list = !btrfs_is_free_space_inode(inode);
+		u64 new_delalloc_bytes;
 
 		spin_lock(&inode->lock);
 		btrfs_mod_outstanding_extents(inode, -num_extents);
@@ -2530,7 +2540,8 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 			return;
 
 		if (!btrfs_is_data_reloc_root(root) &&
-		    do_list && !(state->state & EXTENT_NORESERVE) &&
+		    !btrfs_is_free_space_inode(inode) &&
+		    !(state->state & EXTENT_NORESERVE) &&
 		    (bits & EXTENT_CLEAR_DATA_RESV))
 			btrfs_free_reserved_data_space_noquota(fs_info, len);
 
@@ -2538,11 +2549,20 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
 					 fs_info->delalloc_batch);
 		spin_lock(&inode->lock);
 		inode->delalloc_bytes -= len;
-		if (do_list && inode->delalloc_bytes == 0 &&
-		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-					&inode->runtime_flags))
-			btrfs_del_delalloc_inode(root, inode);
+		new_delalloc_bytes = inode->delalloc_bytes;
 		spin_unlock(&inode->lock);
+
+		/*
+		 * We don't need to be under the protection of the inode's lock,
+		 * because we are called while holding the inode's io_tree lock
+		 * and are therefore protected against concurrent calls of this
+		 * function and btrfs_set_delalloc_extent().
+		 */
+		if (!btrfs_is_free_space_inode(inode) && new_delalloc_bytes == 0) {
+			spin_lock(&root->delalloc_lock);
+			btrfs_del_delalloc_inode(inode);
+			spin_unlock(&root->delalloc_lock);
+		}
 	}
 
 	if ((state->state & EXTENT_DELALLOC_NEW) &&
@@ -2632,7 +2652,7 @@ static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
 		u64 em_len;
 		int ret = 0;
 
-		em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
+		em = btrfs_get_extent(inode, NULL, search_start, search_len);
 		if (IS_ERR(em))
 			return PTR_ERR(em);
 
@@ -2829,7 +2849,7 @@ out_page:
 int btrfs_writepage_cow_fixup(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_writepage_fixup *fixup;
 
 	/* This page has ordered extent covering it already */
@@ -3127,8 +3147,13 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 						ordered_extent->disk_num_bytes);
 		}
 	}
-	unpin_extent_cache(inode, ordered_extent->file_offset,
-			   ordered_extent->num_bytes, trans->transid);
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, ret);
+		goto out;
+	}
+
+	ret = unpin_extent_cache(inode, ordered_extent->file_offset,
+				 ordered_extent->num_bytes, trans->transid);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -3184,8 +3209,23 @@ out:
 			unwritten_start += logical_len;
 		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
 
-		/* Drop extent maps for the part of the extent we didn't write. */
-		btrfs_drop_extent_map_range(inode, unwritten_start, end, false);
+		/*
+		 * Drop extent maps for the part of the extent we didn't write.
+		 *
+		 * We have an exception here for the free_space_inode, this is
+		 * because when we do btrfs_get_extent() on the free space inode
+		 * we will search the commit root.  If this is a new block group
+		 * we won't find anything, and we will trip over the assert in
+		 * writepage where we do ASSERT(em->block_start !=
+		 * EXTENT_MAP_HOLE).
+		 *
+		 * Theoretically we could also skip this for any NOCOW extent as
+		 * we don't mess with the extent map tree in the NOCOW case, but
+		 * for now simply skip this if we are the free space inode.
+		 */
+		if (!btrfs_is_free_space_inode(inode))
+			btrfs_drop_extent_map_range(inode, unwritten_start,
+						    end, false);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
@@ -3239,7 +3279,7 @@ out:
 
 int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered)
 {
-	if (btrfs_is_zoned(btrfs_sb(ordered->inode->i_sb)) &&
+	if (btrfs_is_zoned(inode_to_fs_info(ordered->inode)) &&
 	    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
 	    list_empty(&ordered->bioc_list))
 		btrfs_finish_ordered_zoned(ordered);
@@ -3724,7 +3764,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
 static int btrfs_read_locked_inode(struct inode *inode,
 				   struct btrfs_path *in_path)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_path *path = in_path;
 	struct extent_buffer *leaf;
 	struct btrfs_inode_item *inode_item;
@@ -4368,7 +4408,14 @@ static noinline int may_destroy_subvol(struct btrfs_root *root)
 	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
-	BUG_ON(ret == 0);
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of valid range.
+		 */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = 0;
 	if (path->slots[0] > 0) {
@@ -4449,8 +4496,8 @@ again:
 
 int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
 	struct btrfs_root *root = dir->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode *inode = d_inode(dentry);
 	struct btrfs_root *dest = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
@@ -4680,7 +4727,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
 	unsigned offset = from & (blocksize - 1);
-	struct page *page;
+	struct folio *folio;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	size_t write_bytes = blocksize;
 	int ret = 0;
@@ -4712,8 +4759,9 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 		goto out;
 	}
 again:
-	page = find_or_create_page(mapping, index, mask);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+	if (IS_ERR(folio)) {
 		btrfs_delalloc_release_space(inode, data_reserved, block_start,
 					     blocksize, true);
 		btrfs_delalloc_release_extents(inode, blocksize);
@@ -4721,15 +4769,15 @@ again:
 		goto out;
 	}
 
-	if (!PageUptodate(page)) {
-		ret = btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (page->mapping != mapping) {
-			unlock_page(page);
-			put_page(page);
+	if (!folio_test_uptodate(folio)) {
+		ret = btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (folio->mapping != mapping) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
-		if (!PageUptodate(page)) {
+		if (!folio_test_uptodate(folio)) {
 			ret = -EIO;
 			goto out_unlock;
 		}
@@ -4741,19 +4789,19 @@ again:
 	 * folio private, but left the page in the mapping.  Set the page mapped
 	 * here to make sure it's properly set for the subpage stuff.
 	 */
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0)
 		goto out_unlock;
 
-	wait_on_page_writeback(page);
+	folio_wait_writeback(folio);
 
 	lock_extent(io_tree, block_start, block_end, &cached_state);
 
 	ordered = btrfs_lookup_ordered_extent(inode, block_start);
 	if (ordered) {
 		unlock_extent(io_tree, block_start, block_end, &cached_state);
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 		goto again;
@@ -4774,15 +4822,16 @@ again:
 		if (!len)
 			len = blocksize - offset;
 		if (front)
-			memzero_page(page, (block_start - page_offset(page)),
-				     offset);
+			folio_zero_range(folio, block_start - folio_pos(folio),
+					 offset);
 		else
-			memzero_page(page, (block_start - page_offset(page)) + offset,
-				     len);
+			folio_zero_range(folio,
+					 (block_start - folio_pos(folio)) + offset,
+					 len);
 	}
-	btrfs_folio_clear_checked(fs_info, page_folio(page), block_start,
+	btrfs_folio_clear_checked(fs_info, folio, block_start,
 				  block_end + 1 - block_start);
-	btrfs_folio_set_dirty(fs_info, page_folio(page), block_start,
+	btrfs_folio_set_dirty(fs_info, folio, block_start,
 			      block_end + 1 - block_start);
 	unlock_extent(io_tree, block_start, block_end, &cached_state);
 
@@ -4799,8 +4848,8 @@ out_unlock:
 					block_start, blocksize, true);
 	}
 	btrfs_delalloc_release_extents(inode, blocksize);
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 out:
 	if (only_release_metadata)
 		btrfs_check_nocow_unlock(inode);
@@ -4892,8 +4941,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 					   &cached_state);
 	cur_offset = hole_start;
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
-				      block_end - cur_offset);
+		em = btrfs_get_extent(inode, NULL, cur_offset, block_end - cur_offset);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
 			em = NULL;
@@ -5004,7 +5052,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		btrfs_drew_write_unlock(&root->snapshot_lock);
 		btrfs_end_transaction(trans);
 	} else {
-		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+		struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 
 		if (btrfs_is_zoned(fs_info)) {
 			ret = btrfs_wait_ordered_range(inode,
@@ -5207,7 +5255,7 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
 
 void btrfs_evict_inode(struct inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_block_rsv *rsv = NULL;
@@ -5221,6 +5269,7 @@ void btrfs_evict_inode(struct inode *inode)
 		return;
 	}
 
+	fs_info = inode_to_fs_info(inode);
 	evict_inode_truncate_pages(inode);
 
 	if (inode->i_nlink &&
@@ -5518,7 +5567,6 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
 	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
 	BTRFS_I(inode)->location.offset = 0;
 	BTRFS_I(inode)->root = btrfs_grab_root(args->root);
-	BUG_ON(args->root && !BTRFS_I(inode)->root);
 
 	if (args->root && args->root == args->root->fs_info->tree_root &&
 	    args->ino != BTRFS_BTREE_INODE_OBJECTID)
@@ -5646,7 +5694,7 @@ static inline u8 btrfs_inode_type(struct inode *inode)
 
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct inode *inode;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *sub_root = root;
@@ -6185,7 +6233,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	struct inode *dir = args->dir;
 	struct inode *inode = args->inode;
 	const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name;
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_root *root;
 	struct btrfs_inode_item *inode_item;
 	struct btrfs_key *location;
@@ -6507,7 +6555,7 @@ fail_dir_item:
 static int btrfs_create_common(struct inode *dir, struct dentry *dentry,
 			       struct inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_new_inode_args new_inode_args = {
 		.dir = dir,
@@ -6577,7 +6625,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	struct btrfs_trans_handle *trans = NULL;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = d_inode(old_dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct fscrypt_name fname;
 	u64 index;
 	int err;
@@ -6741,7 +6789,6 @@ static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path
  *
  * @inode:	file to search in
  * @page:	page to read extent data into if the extent is inline
- * @pg_offset:	offset into @page to copy to
  * @start:	file offset
  * @len:	length of range starting at @start
  *
@@ -6755,8 +6802,7 @@ static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path
  * Return: ERR_PTR on error, non-NULL extent_map on success.
  */
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
-				    struct page *page, size_t pg_offset,
-				    u64 start, u64 len)
+				    struct page *page, u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret = 0;
@@ -6899,7 +6945,6 @@ next:
 		 * ensured by tree-checker and inline extent creation path.
 		 * Thus all members representing file offsets should be zero.
 		 */
-		ASSERT(pg_offset == 0);
 		ASSERT(extent_start == 0);
 		ASSERT(em->start == 0);
 
@@ -7063,7 +7108,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes, bool nowait, bool strict)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct can_nocow_file_extent_args nocow_args = { 0 };
 	struct btrfs_path *path;
 	int ret;
@@ -7302,7 +7347,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					 unsigned int iomap_flags)
 {
 	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em = *map;
 	int type;
 	u64 block_start, orig_start, orig_block_len, ram_bytes;
@@ -7442,7 +7487,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 		struct iomap *srcmap)
 {
 	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_dio_data *dio_data = iter->private;
@@ -7540,7 +7585,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	if (ret < 0)
 		goto err;
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto unlock_err;
@@ -7820,6 +7865,7 @@ struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			u64 start, u64 len)
 {
+	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
 	int	ret;
 
 	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
@@ -7845,7 +7891,26 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return ret;
 	}
 
-	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
+	btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	/*
+	 * We did an initial flush to avoid holding the inode's lock while
+	 * triggering writeback and waiting for the completion of IO and ordered
+	 * extents. Now after we locked the inode we do it again, because it's
+	 * possible a new write may have happened in between those two steps.
+	 */
+	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
+		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
+		if (ret) {
+			btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+			return ret;
+		}
+	}
+
+	ret = extent_fiemap(btrfs_inode, fieinfo, start, len);
+	btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED);
+
+	return ret;
 }
 
 static int btrfs_writepages(struct address_space *mapping,
@@ -7868,7 +7933,7 @@ static void btrfs_readahead(struct readahead_control *rac)
  */
 static void wait_subpage_spinlock(struct page *page)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(page);
 	struct folio *folio = page_folio(page);
 	struct btrfs_subpage *subpage;
 
@@ -7935,7 +8000,7 @@ static int btrfs_migrate_folio(struct address_space *mapping,
 static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
 				 size_t length)
 {
-	struct btrfs_inode *inode = BTRFS_I(folio->mapping->host);
+	struct btrfs_inode *inode = folio_to_inode(folio);
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_io_tree *tree = &inode->io_tree;
 	struct extent_state *cached_state = NULL;
@@ -8119,7 +8184,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct folio *folio = page_folio(page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
@@ -8665,7 +8730,7 @@ int __init btrfs_init_cachep(void)
 {
 	btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
 			sizeof(struct btrfs_inode), 0,
-			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT,
+			SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
 			init_once);
 	if (!btrfs_inode_cachep)
 		goto fail;
@@ -8688,7 +8753,7 @@ static int btrfs_getattr(struct mnt_idmap *idmap,
 	u64 delalloc_bytes;
 	u64 inode_bytes;
 	struct inode *inode = d_inode(path->dentry);
-	u32 blocksize = inode->i_sb->s_blocksize;
+	u32 blocksize = btrfs_sb(inode->i_sb)->sectorsize;
 	u32 bi_flags = BTRFS_I(inode)->flags;
 	u32 bi_ro_flags = BTRFS_I(inode)->ro_flags;
 
@@ -8728,7 +8793,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 			      struct inode *new_dir,
 			      struct dentry *new_dentry)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir);
 	struct btrfs_trans_handle *trans;
 	unsigned int trans_num_items;
 	struct btrfs_root *root = BTRFS_I(old_dir)->root;
@@ -8980,7 +9045,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir);
 	struct btrfs_new_inode_args whiteout_args = {
 		.dir = old_dir,
 		.dentry = old_dentry,
@@ -9422,7 +9487,7 @@ out:
 static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 			 struct dentry *dentry, const char *symname)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
@@ -9603,7 +9668,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 				       loff_t actual_len, u64 *alloc_hint,
 				       struct btrfs_trans_handle *trans)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key ins;
@@ -9755,7 +9820,7 @@ static int btrfs_permission(struct mnt_idmap *idmap,
 static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 			 struct file *file, umode_t mode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode;
@@ -10129,7 +10194,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		cond_resched();
 	}
 
-	em = btrfs_get_extent(inode, NULL, 0, start, lockend - start + 1);
+	em = btrfs_get_extent(inode, NULL, start, lockend - start + 1);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto out_unlock_extent;
@@ -10273,6 +10338,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
 		return -EINVAL;
 
+	/*
+	 * Compressed extents should always have checksums, so error out if we
+	 * have a NOCOW file or inode was created while mounted with NODATASUM.
+	 */
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		return -EINVAL;
+
 	orig_count = iov_iter_count(from);
 
 	/* The extent size must be sane. */
@@ -10702,7 +10774,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		struct btrfs_block_group *bg;
 		u64 len = isize - start;
 
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dfed9dd9c2d7..294e31edec9d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -34,11 +34,9 @@
 #include "export.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
 #include "backref.h"
-#include "rcu-string.h"
 #include "send.h"
 #include "dev-replace.h"
 #include "props.h"
@@ -47,9 +45,7 @@
 #include "tree-log.h"
 #include "compression.h"
 #include "space-info.h"
-#include "delalloc-space.h"
 #include "block-group.h"
-#include "subpage.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
@@ -231,6 +227,20 @@ static int check_fsflags_compatible(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args)
+{
+	if (memchr(vol_args->name, 0, sizeof(vol_args->name)) == NULL)
+		return -ENAMETOOLONG;
+	return 0;
+}
+
+static int btrfs_check_ioctl_vol_args2_subvol_name(const struct btrfs_ioctl_vol_args_v2 *vol_args2)
+{
+	if (memchr(vol_args2->name, 0, sizeof(vol_args2->name)) == NULL)
+		return -ENAMETOOLONG;
+	return 0;
+}
+
 /*
  * Set flags/xflags from the internal inode flags. The remaining items of
  * fsxattr are zeroed.
@@ -247,7 +257,7 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap,
 		       struct dentry *dentry, struct fileattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_inode *binode = BTRFS_I(inode);
 	struct btrfs_root *root = binode->root;
 	struct btrfs_trans_handle *trans;
@@ -528,7 +538,7 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
 	 * block group is in the logical address space, which can be any
 	 * sectorsize aligned bytenr in  the range [0, U64_MAX].
 	 */
-	if (range.len < fs_info->sb->s_blocksize)
+	if (range.len < fs_info->sectorsize)
 		return -EINVAL;
 
 	range.minlen = max(range.minlen, minlen);
@@ -584,7 +594,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 				  struct inode *dir, struct dentry *dentry,
 				  struct btrfs_qgroup_inherit *inherit)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_key key;
 	struct btrfs_root_item *root_item;
@@ -721,7 +731,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
+	new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev);
 	if (IS_ERR(new_root)) {
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
@@ -776,7 +786,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 			   struct dentry *dentry, bool readonly,
 			   struct btrfs_qgroup_inherit *inherit)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct inode *inode;
 	struct btrfs_pending_snapshot *pending_snapshot;
 	unsigned int trans_num_items;
@@ -910,7 +920,9 @@ static int btrfs_may_delete(struct mnt_idmap *idmap,
 	if (d_really_is_negative(victim))
 		return -ENOENT;
 
-	BUG_ON(d_inode(victim->d_parent) != dir);
+	/* The @victim is not inside @dir. */
+	if (d_inode(victim->d_parent) != dir)
+		return -EINVAL;
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	error = inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC);
@@ -962,7 +974,7 @@ static noinline int btrfs_mksubvol(const struct path *parent,
 				   struct btrfs_qgroup_inherit *inherit)
 {
 	struct inode *dir = d_inode(parent->dentry);
-	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct dentry *dentry;
 	struct fscrypt_str name_str = FSTR_INIT((char *)name, namelen);
 	int error;
@@ -1097,7 +1109,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 {
 	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	u64 new_size;
 	u64 old_size;
 	u64 devid = 1;
@@ -1128,7 +1140,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		ret = PTR_ERR(vol_args);
 		goto out_drop;
 	}
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	sizestr = vol_args->name;
 	cancel = (strcmp("cancel", sizestr) == 0);
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_RESIZE, cancel);
@@ -1328,12 +1343,15 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out;
 
 	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
 					vol_args->name, vol_args->fd, subvol,
 					false, NULL);
 
+out:
 	kfree(vol_args);
 	return ret;
 }
@@ -1352,7 +1370,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
-	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args);
+	if (ret < 0)
+		goto free_args;
 
 	if (vol_args->flags & ~BTRFS_SUBVOL_CREATE_ARGS_MASK) {
 		ret = -EOPNOTSUPP;
@@ -1362,7 +1382,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
 		readonly = true;
 	if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
-		u64 nums;
+		struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file));
 
 		if (vol_args->size < sizeof(*inherit) ||
 		    vol_args->size > PAGE_SIZE) {
@@ -1375,19 +1395,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 			goto free_args;
 		}
 
-		if (inherit->num_qgroups > PAGE_SIZE ||
-		    inherit->num_ref_copies > PAGE_SIZE ||
-		    inherit->num_excl_copies > PAGE_SIZE) {
-			ret = -EINVAL;
-			goto free_inherit;
-		}
-
-		nums = inherit->num_qgroups + 2 * inherit->num_ref_copies +
-		       2 * inherit->num_excl_copies;
-		if (vol_args->size != struct_size(inherit, qgroups, nums)) {
-			ret = -EINVAL;
+		ret = btrfs_qgroup_check_inherit(fs_info, inherit, vol_args->size);
+		if (ret < 0)
 			goto free_inherit;
-		}
 	}
 
 	ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file),
@@ -1405,7 +1415,7 @@ free_args:
 static noinline int btrfs_ioctl_subvol_getflags(struct inode *inode,
 						void __user *arg)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret = 0;
 	u64 flags = 0;
@@ -1428,7 +1438,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 					      void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	u64 root_flags;
@@ -1675,7 +1685,7 @@ static noinline int search_ioctl(struct inode *inode,
 				 u64 *buf_size,
 				 char __user *ubuf)
 {
-	struct btrfs_fs_info *info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *info = inode_to_fs_info(inode);
 	struct btrfs_root *root;
 	struct btrfs_key key;
 	struct btrfs_path *path;
@@ -2346,9 +2356,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 					     bool destroy_v2)
 {
 	struct dentry *parent = file->f_path.dentry;
-	struct btrfs_fs_info *fs_info = btrfs_sb(parent->d_sb);
 	struct dentry *dentry;
 	struct inode *dir = d_inode(parent);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dir);
 	struct inode *inode;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *dest = NULL;
@@ -2382,7 +2392,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		 * name, same as v1 currently does.
 		 */
 		if (!(vol_args2->flags & BTRFS_SUBVOL_SPEC_BY_ID)) {
-			vol_args2->name[BTRFS_SUBVOL_NAME_MAX] = 0;
+			err = btrfs_check_ioctl_vol_args2_subvol_name(vol_args2);
+			if (err < 0)
+				goto out;
 			subvol_name = vol_args2->name;
 
 			err = mnt_want_write_file(file);
@@ -2466,7 +2478,10 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		if (IS_ERR(vol_args))
 			return PTR_ERR(vol_args);
 
-		vol_args->name[BTRFS_PATH_NAME_MAX] = 0;
+		err = btrfs_check_ioctl_vol_args_path(vol_args);
+		if (err < 0)
+			goto out;
+
 		subvol_name = vol_args->name;
 
 		err = mnt_want_write_file(file);
@@ -2677,12 +2692,16 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 		goto out;
 	}
 
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	ret = btrfs_init_new_device(fs_info, vol_args->name);
 
 	if (!ret)
 		btrfs_info(fs_info, "disk added %s", vol_args->name);
 
+out_free:
 	kfree(vol_args);
 out:
 	if (restore_op)
@@ -2696,9 +2715,9 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 {
 	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_vol_args_v2 *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2714,7 +2733,10 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args2_subvol_name(vol_args);
+	if (ret < 0)
+		goto out;
+
 	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
 		args.devid = vol_args->devid;
 	} else if (!strcmp("cancel", vol_args->name)) {
@@ -2735,7 +2757,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		goto err_drop;
 
 	/* Exclusive operation is now claimed */
-	ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+	ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 
 	btrfs_exclop_finish(fs_info);
 
@@ -2749,8 +2771,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	}
 err_drop:
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
 	kfree(vol_args);
@@ -2761,9 +2783,9 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 {
 	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_vol_args *vol_args;
-	struct bdev_handle *bdev_handle = NULL;
+	struct file *bdev_file = NULL;
 	int ret;
 	bool cancel = false;
 
@@ -2774,7 +2796,10 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
 
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol_args);
+	if (ret < 0)
+		goto out_free;
+
 	if (!strcmp("cancel", vol_args->name)) {
 		cancel = true;
 	} else {
@@ -2790,17 +2815,18 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
 					   cancel);
 	if (ret == 0) {
-		ret = btrfs_rm_device(fs_info, &args, &bdev_handle);
+		ret = btrfs_rm_device(fs_info, &args, &bdev_file);
 		if (!ret)
 			btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 		btrfs_exclop_finish(fs_info);
 	}
 
 	mnt_drop_write_file(file);
-	if (bdev_handle)
-		bdev_release(bdev_handle);
+	if (bdev_file)
+		fput(bdev_file);
 out:
 	btrfs_put_dev_args_from_path(&args);
+out_free:
 	kfree(vol_args);
 	return ret;
 }
@@ -2904,7 +2930,7 @@ out:
 static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_root *new_root;
 	struct btrfs_dir_item *di;
@@ -3178,7 +3204,7 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info,
 
 static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(file_inode(file)->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file));
 	struct btrfs_ioctl_scrub_args *sa;
 	int ret;
 
@@ -3696,7 +3722,7 @@ out:
 static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_quota_ctl_args *sa;
 	int ret;
 
@@ -3738,7 +3764,7 @@ drop_write:
 static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_assign_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -3815,6 +3841,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
+	if (sa->create && is_fstree(sa->qgroupid)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
@@ -3889,7 +3920,7 @@ drop_write:
 static long btrfs_ioctl_quota_rescan(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_ioctl_quota_rescan_args *qsa;
 	int ret;
 
@@ -3953,7 +3984,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 					    struct btrfs_ioctl_received_subvol_args *sa)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_root_item *root_item = &root->root_item;
 	struct btrfs_trans_handle *trans;
@@ -4141,7 +4172,7 @@ static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info,
 static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_super_block *super_block = fs_info->super_copy;
 	struct btrfs_trans_handle *trans;
@@ -4284,7 +4315,7 @@ check_feature_bits(fs_info, FEAT_##mask_base, change_mask, flags,	\
 static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_super_block *super_block = fs_info->super_copy;
 	struct btrfs_ioctl_feature_flags flags[2];
@@ -4575,7 +4606,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	void __user *argp = (void __user *)arg;
 
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index d51b9a2f2f6e..2c5dc25ec670 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -3,6 +3,15 @@
 #ifndef BTRFS_IOCTL_H
 #define BTRFS_IOCTL_H
 
+#include <linux/types.h>
+
+struct file;
+struct dentry;
+struct mnt_idmap;
+struct fileattr;
+struct btrfs_fs_info;
+struct btrfs_ioctl_balance_args;
+
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 74d8e2003f58..99ccab86bb86 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -13,7 +13,6 @@
 #include "ctree.h"
 #include "extent_io.h"
 #include "locking.h"
-#include "accessors.h"
 
 /*
  * Lockdep class keys for extent_buffer->lock's in this root.  For a given
@@ -85,7 +84,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int
 {
 	struct btrfs_lockdep_keyset *ks;
 
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
+	ASSERT(level < ARRAY_SIZE(ks->keys));
 
 	/* Find the matching keyset, id 0 is the default entry */
 	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 7d6ee1e609bf..9576f485a300 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -8,8 +8,14 @@
 
 #include <linux/atomic.h>
 #include <linux/wait.h>
+#include <linux/lockdep.h>
 #include <linux/percpu_counter.h>
 #include "extent_io.h"
+#include "locking.h"
+
+struct extent_buffer;
+struct btrfs_path;
+struct btrfs_root;
 
 #define BTRFS_WRITE_LOCK 1
 #define BTRFS_READ_LOCK 2
@@ -157,8 +163,6 @@ enum btrfs_lockdep_trans_states {
 static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
 	      "too many lock subclasses defined");
 
-struct btrfs_path;
-
 void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
 void btrfs_tree_lock(struct extent_buffer *eb);
 void btrfs_tree_unlock(struct extent_buffer *eb);
diff --git a/fs/btrfs/lru_cache.h b/fs/btrfs/lru_cache.h
index 00328c856be6..e32906ab6faa 100644
--- a/fs/btrfs/lru_cache.h
+++ b/fs/btrfs/lru_cache.h
@@ -3,8 +3,10 @@
 #ifndef BTRFS_LRU_CACHE_H
 #define BTRFS_LRU_CACHE_H
 
+#include <linux/types.h>
 #include <linux/maple_tree.h>
 #include <linux/list.h>
+#include "lru_cache.h"
 
 /*
  * A cache entry. This is meant to be embedded in a structure of a user of
@@ -50,11 +52,6 @@ struct btrfs_lru_cache {
 #define btrfs_lru_cache_for_each_entry_safe(cache, entry, tmp)		\
 	list_for_each_entry_safe_reverse((entry), (tmp), &(cache)->lru_list, lru_list)
 
-static inline unsigned int btrfs_lru_cache_size(const struct btrfs_lru_cache *cache)
-{
-	return cache->size;
-}
-
 static inline struct btrfs_lru_cache_entry *btrfs_lru_cache_lru_entry(
 					      struct btrfs_lru_cache *cache)
 {
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index e43bc0fdc74e..3e5d3b7028e8 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -214,7 +214,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize;
+	const u32 sectorsize = inode_to_fs_info(mapping->host)->sectorsize;
 	struct page *page_in = NULL;
 	char *sizes_ptr;
 	const unsigned long max_nr_page = *out_pages;
@@ -429,7 +429,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page);
 	const u32 sectorsize = fs_info->sectorsize;
 	size_t in_len;
 	size_t out_len;
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index cdada4865837..c96dd66fd0f7 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -3,8 +3,6 @@
 #include "fs.h"
 #include "messages.h"
 #include "discard.h"
-#include "transaction.h"
-#include "space-info.h"
 #include "super.h"
 
 #ifdef CONFIG_PRINTK
diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
index 40f2d9f1a17a..dde4904aead9 100644
--- a/fs/btrfs/misc.h
+++ b/fs/btrfs/misc.h
@@ -3,6 +3,8 @@
 #ifndef BTRFS_MISC_H
 #define BTRFS_MISC_H
 
+#include <linux/types.h>
+#include <linux/bitmap.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/math64.h>
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 59850dc17b22..b749ba45da2b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -19,7 +19,6 @@
 #include "qgroup.h"
 #include "subpage.h"
 #include "file.h"
-#include "super.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -1236,10 +1235,7 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent(
 
 int __init ordered_data_init(void)
 {
-	btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
-				     sizeof(struct btrfs_ordered_extent), 0,
-				     SLAB_MEM_SPREAD,
-				     NULL);
+	btrfs_ordered_extent_cache = KMEM_CACHE(btrfs_ordered_extent, 0);
 	if (!btrfs_ordered_extent_cache)
 		return -ENOMEM;
 
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 127ef8bf0ffd..34413fc5b4bd 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -6,6 +6,21 @@
 #ifndef BTRFS_ORDERED_DATA_H
 #define BTRFS_ORDERED_DATA_H
 
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/refcount.h>
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+#include <linux/wait.h>
+#include "async-thread.h"
+
+struct inode;
+struct page;
+struct extent_state;
+struct btrfs_inode;
+struct btrfs_root;
+struct btrfs_fs_info;
+
 struct btrfs_ordered_sum {
 	/*
 	 * Logical start address and length for of the blocks covered by
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index 7a1b021b5669..6195a2215b8f 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -4,7 +4,6 @@
  */
 
 #include "ctree.h"
-#include "disk-io.h"
 #include "orphan.h"
 
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/orphan.h b/fs/btrfs/orphan.h
index 3faab5cbb59a..aa54a88a60de 100644
--- a/fs/btrfs/orphan.h
+++ b/fs/btrfs/orphan.h
@@ -3,6 +3,11 @@
 #ifndef BTRFS_ORPHAN_H
 #define BTRFS_ORPHAN_H
 
+#include <linux/types.h>
+
+struct btrfs_trans_handle;
+struct btrfs_root;
+
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 offset);
 int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index c42bc666d5ee..8504bf1702c7 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -9,6 +9,9 @@
 /* Buffer size to contain tree name and possibly additional data (offset) */
 #define BTRFS_ROOT_NAME_BUF_LEN				48
 
+struct extent_buffer;
+struct btrfs_key;
+
 void btrfs_print_leaf(const struct extent_buffer *l);
 void btrfs_print_tree(const struct extent_buffer *c, bool follow);
 const char *btrfs_root_name(const struct btrfs_key *key, char *buf);
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index f9bf591a0718..2a9b7b029eeb 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/hashtable.h>
+#include <linux/xattr.h>
 #include "messages.h"
 #include "props.h"
 #include "btrfs_inode.h"
@@ -302,7 +303,7 @@ static int prop_compression_validate(const struct btrfs_inode *inode,
 static int prop_compression_apply(struct inode *inode, const char *value,
 				  size_t len)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	int type;
 
 	/* Reset to defaults */
diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h
index 6e283196e38a..f60cd89feb29 100644
--- a/fs/btrfs/props.h
+++ b/fs/btrfs/props.h
@@ -6,7 +6,12 @@
 #ifndef BTRFS_PROPS_H
 #define BTRFS_PROPS_H
 
-#include "ctree.h"
+#include <linux/compiler_types.h>
+
+struct inode;
+struct btrfs_inode;
+struct btrfs_path;
+struct btrfs_trans_handle;
 
 int __init btrfs_props_init(void);
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 63b426cc7798..5f90f0605b12 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1324,7 +1324,7 @@ static int flush_reservations(struct btrfs_fs_info *fs_info)
 	trans = btrfs_join_transaction(fs_info->tree_root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	btrfs_commit_transaction(trans);
+	ret = btrfs_commit_transaction(trans);
 
 	return ret;
 }
@@ -1736,6 +1736,15 @@ out:
 	return ret;
 }
 
+static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
+{
+	return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
+		qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
+		qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
+}
+
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1755,6 +1764,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 		goto out;
 	}
 
+	if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/* Check if there are no children of this qgroup */
 	if (!list_empty(&qgroup->members)) {
 		ret = -EBUSY;
@@ -2491,8 +2505,8 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	struct extent_buffer *eb = root_eb;
 	struct btrfs_path *path = NULL;
 
-	BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL);
-	BUG_ON(root_eb == NULL);
+	ASSERT(0 <= root_level && root_level < BTRFS_MAX_LEVEL);
+	ASSERT(root_eb != NULL);
 
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
@@ -2847,8 +2861,6 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	if (nr_old_roots == 0 && nr_new_roots == 0)
 		goto out_free;
 
-	BUG_ON(!fs_info->quota_root);
-
 	trace_btrfs_qgroup_account_extent(fs_info, trans->transid, bytenr,
 					num_bytes, nr_old_roots, nr_new_roots);
 
@@ -2945,11 +2957,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 				ctx.roots = NULL;
 			}
 
-			/* Free the reserved data space */
-			btrfs_qgroup_free_refroot(fs_info,
-					record->data_rsv_refroot,
-					record->data_rsv,
-					BTRFS_QGROUP_RSV_DATA);
 			/*
 			 * Use BTRFS_SEQ_LAST as time_seq to do special search,
 			 * which doesn't lock tree or delayed_refs and search
@@ -2973,6 +2980,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 			record->old_roots = NULL;
 			new_roots = NULL;
 		}
+		/* Free the reserved data space */
+		btrfs_qgroup_free_refroot(fs_info,
+				record->data_rsv_refroot,
+				record->data_rsv,
+				BTRFS_QGROUP_RSV_DATA);
 cleanup:
 		ulist_free(record->old_roots);
 		ulist_free(new_roots);
@@ -3034,6 +3046,57 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 	return ret;
 }
 
+int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
+			       struct btrfs_qgroup_inherit *inherit,
+			       size_t size)
+{
+	if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP)
+		return -EOPNOTSUPP;
+	if (size < sizeof(*inherit) || size > PAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * In the past we allowed btrfs_qgroup_inherit to specify to copy
+	 * rfer/excl numbers directly from other qgroups.  This behavior has
+	 * been disabled in userspace for a very long time, but here we should
+	 * also disable it in kernel, as this behavior is known to mark qgroup
+	 * inconsistent, and a rescan would wipe out the changes anyway.
+	 *
+	 * Reject any btrfs_qgroup_inherit with num_ref_copies or num_excl_copies.
+	 */
+	if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0)
+		return -EINVAL;
+
+	if (inherit->num_qgroups > PAGE_SIZE)
+		return -EINVAL;
+
+	if (size != struct_size(inherit, qgroups, inherit->num_qgroups))
+		return -EINVAL;
+
+	/*
+	 * Now check all the remaining qgroups, they should all:
+	 *
+	 * - Exist
+	 * - Be higher level qgroups.
+	 */
+	for (int i = 0; i < inherit->num_qgroups; i++) {
+		struct btrfs_qgroup *qgroup;
+		u64 qgroupid = inherit->qgroups[i];
+
+		if (btrfs_qgroup_level(qgroupid) == 0)
+			return -EINVAL;
+
+		spin_lock(&fs_info->qgroup_lock);
+		qgroup = find_qgroup_rb(fs_info, qgroupid);
+		if (!qgroup) {
+			spin_unlock(&fs_info->qgroup_lock);
+			return -ENOENT;
+		}
+		spin_unlock(&fs_info->qgroup_lock);
+	}
+	return 0;
+}
+
 static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 			       u64 inode_rootid,
 			       struct btrfs_qgroup_inherit **inherit)
@@ -3076,6 +3139,62 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 }
 
 /*
+ * Check if we can skip rescan when inheriting qgroups.  If @src has a single
+ * @parent, and that @parent is owning all its bytes exclusively, we can skip
+ * the full rescan, by just adding nodesize to the @parent's excl/rfer.
+ *
+ * Return <0 for fatal errors (like srcid/parentid has no qgroup).
+ * Return 0 if a quick inherit is done.
+ * Return >0 if a quick inherit is not possible, and a full rescan is needed.
+ */
+static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
+					 u64 srcid, u64 parentid)
+{
+	struct btrfs_qgroup *src;
+	struct btrfs_qgroup *parent;
+	struct btrfs_qgroup_list *list;
+	int nr_parents = 0;
+
+	src = find_qgroup_rb(fs_info, srcid);
+	if (!src)
+		return -ENOENT;
+	parent = find_qgroup_rb(fs_info, parentid);
+	if (!parent)
+		return -ENOENT;
+
+	/*
+	 * Source has no parent qgroup, but our new qgroup would have one.
+	 * Qgroup numbers would become inconsistent.
+	 */
+	if (list_empty(&src->groups))
+		return 1;
+
+	list_for_each_entry(list, &src->groups, next_group) {
+		/* The parent is not the same, quick update is not possible. */
+		if (list->group->qgroupid != parentid)
+			return 1;
+		nr_parents++;
+		/*
+		 * More than one parent qgroup, we can't be sure about accounting
+		 * consistency.
+		 */
+		if (nr_parents > 1)
+			return 1;
+	}
+
+	/*
+	 * The parent is not exclusively owning all its bytes.  We're not sure
+	 * if the source has any bytes not fully owned by the parent.
+	 */
+	if (parent->excl != parent->rfer)
+		return 1;
+
+	parent->excl += fs_info->nodesize;
+	parent->rfer += fs_info->nodesize;
+	return 0;
+}
+
+/*
  * Copy the accounting information between qgroups. This is necessary
  * when a snapshot or a subvolume is created. Throwing an error will
  * cause a transaction abort so we take extra care here to only error
@@ -3243,6 +3362,13 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 		qgroup_dirty(fs_info, dstgroup);
 		qgroup_dirty(fs_info, srcgroup);
+
+		/*
+		 * If the source qgroup has parent but the new one doesn't,
+		 * we need a full rescan.
+		 */
+		if (!inherit && !list_empty(&srcgroup->groups))
+			need_rescan = true;
 	}
 
 	if (!inherit)
@@ -3257,14 +3383,16 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 			if (ret)
 				goto unlock;
 		}
+		if (srcid) {
+			/* Check if we can do a quick inherit. */
+			ret = qgroup_snapshot_quick_inherit(fs_info, srcid, *i_qgroups);
+			if (ret < 0)
+				goto unlock;
+			if (ret > 0)
+				need_rescan = true;
+			ret = 0;
+		}
 		++i_qgroups;
-
-		/*
-		 * If we're doing a snapshot, and adding the snapshot to a new
-		 * qgroup, the numbers are guaranteed to be incorrect.
-		 */
-		if (srcid)
-			need_rescan = true;
 	}
 
 	for (i = 0; i <  inherit->num_ref_copies; ++i, i_qgroups += 2) {
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index be18c862e64e..706640be0ec2 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -6,12 +6,22 @@
 #ifndef BTRFS_QGROUP_H
 #define BTRFS_QGROUP_H
 
+#include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
 #include <linux/kobject.h>
-#include "ulist.h"
-#include "delayed-ref.h"
-#include "misc.h"
+#include <linux/list.h>
+#include <uapi/linux/btrfs_tree.h>
+
+struct extent_buffer;
+struct extent_changeset;
+struct btrfs_delayed_extent_op;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_ioctl_quota_ctl_args;
+struct btrfs_trans_handle;
+struct btrfs_delayed_ref_root;
+struct btrfs_inode;
 
 /*
  * Btrfs qgroup overview
@@ -321,7 +331,6 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
-struct btrfs_delayed_extent_op;
 
 int btrfs_qgroup_trace_extent_nolock(
 		struct btrfs_fs_info *fs_info,
@@ -341,6 +350,9 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
 int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
+int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
+			       struct btrfs_qgroup_inherit *inherit,
+			       size_t size);
 int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 			 u64 objectid, u64 inode_rootid,
 			 struct btrfs_qgroup_inherit *inherit);
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 9589362acfbf..6af6b4b9a32e 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -11,7 +11,6 @@
 #include "disk-io.h"
 #include "raid-stripe-tree.h"
 #include "volumes.h"
-#include "misc.h"
 #include "print-tree.h"
 
 int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length)
diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h
index cdb58b38fcb5..c9c258f84903 100644
--- a/fs/btrfs/raid-stripe-tree.h
+++ b/fs/btrfs/raid-stripe-tree.h
@@ -6,6 +6,10 @@
 #ifndef BTRFS_RAID_STRIPE_TREE_H
 #define BTRFS_RAID_STRIPE_TREE_H
 
+#include <linux/types.h>
+#include <uapi/linux/btrfs_tree.h>
+#include "fs.h"
+
 #define BTRFS_RST_SUPP_BLOCK_GROUP_MASK    (BTRFS_BLOCK_GROUP_DUP |		\
 					    BTRFS_BLOCK_GROUP_RAID1_MASK |	\
 					    BTRFS_BLOCK_GROUP_RAID0 |		\
@@ -13,6 +17,7 @@
 
 struct btrfs_io_context;
 struct btrfs_io_stripe;
+struct btrfs_fs_info;
 struct btrfs_ordered_extent;
 struct btrfs_trans_handle;
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 792c8e17c31d..6f4a9cfeea44 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -14,7 +14,6 @@
 #include <linux/raid/xor.h>
 #include <linux/mm.h>
 #include "messages.h"
-#include "misc.h"
 #include "ctree.h"
 #include "disk-io.h"
 #include "volumes.h"
@@ -918,6 +917,13 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	 */
 	ASSERT(stripe_nsectors <= BITS_PER_LONG);
 
+	/*
+	 * Real stripes must be between 2 (2 disks RAID5, aka RAID1) and 256
+	 * (limited by u8).
+	 */
+	ASSERT(real_stripes >= 2);
+	ASSERT(real_stripes <= U8_MAX);
+
 	rbio = kzalloc(sizeof(*rbio), GFP_NOFS);
 	if (!rbio)
 		return ERR_PTR(-ENOMEM);
@@ -955,6 +961,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 
 	ASSERT(btrfs_nr_parity_stripes(bioc->map_type));
 	rbio->nr_data = real_stripes - btrfs_nr_parity_stripes(bioc->map_type);
+	ASSERT(rbio->nr_data > 0);
 
 	return rbio;
 }
@@ -1181,6 +1188,26 @@ static inline void bio_list_put(struct bio_list *bio_list)
 		bio_put(bio);
 }
 
+static void assert_rbio(struct btrfs_raid_bio *rbio)
+{
+	if (!IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+	    !IS_ENABLED(CONFIG_BTRFS_ASSERT))
+		return;
+
+	/*
+	 * At least two stripes (2 disks RAID5), and since real_stripes is U8,
+	 * we won't go beyond 256 disks anyway.
+	 */
+	ASSERT(rbio->real_stripes >= 2);
+	ASSERT(rbio->nr_data > 0);
+
+	/*
+	 * This is another check to make sure nr data stripes is smaller
+	 * than total stripes.
+	 */
+	ASSERT(rbio->nr_data < rbio->real_stripes);
+}
+
 /* Generate PQ for one vertical stripe. */
 static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 {
@@ -1212,6 +1239,7 @@ static void generate_pq_vertical(struct btrfs_raid_bio *rbio, int sectornr)
 		pointers[stripe++] = kmap_local_page(sector->page) +
 				     sector->pgoff;
 
+		assert_rbio(rbio);
 		raid6_call.gen_syndrome(rbio->real_stripes, sectorsize,
 					pointers);
 	} else {
@@ -2473,6 +2501,7 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio)
 		}
 
 		if (has_qstripe) {
+			assert_rbio(rbio);
 			/* RAID6, call the library function to fill in our P/Q */
 			raid6_call.gen_syndrome(rbio->real_stripes, sectorsize,
 						pointers);
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 470213688872..0d7b4c2fb6ae 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -7,9 +7,18 @@
 #ifndef BTRFS_RAID56_H
 #define BTRFS_RAID56_H
 
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/bio.h>
+#include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include "volumes.h"
 
+struct page;
+struct sector_ptr;
+struct btrfs_fs_info;
+
 enum btrfs_rbio_ops {
 	BTRFS_RBIO_WRITE,
 	BTRFS_RBIO_READ_REBUILD,
diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h
index 5c2b66d155ef..1c2d7cb1fe6f 100644
--- a/fs/btrfs/rcu-string.h
+++ b/fs/btrfs/rcu-string.h
@@ -6,6 +6,12 @@
 #ifndef BTRFS_RCU_STRING_H
 #define BTRFS_RCU_STRING_H
 
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/printk.h>
+
 struct rcu_string {
 	struct rcu_head rcu;
 	char str[];
diff --git a/fs/btrfs/ref-verify.h b/fs/btrfs/ref-verify.h
index 855de37719b5..3511e1a5c96b 100644
--- a/fs/btrfs/ref-verify.h
+++ b/fs/btrfs/ref-verify.h
@@ -6,7 +6,16 @@
 #ifndef BTRFS_REF_VERIFY_H
 #define BTRFS_REF_VERIFY_H
 
+#include <linux/types.h>
+#include <linux/rbtree_types.h>
+
+struct btrfs_fs_info;
+struct btrfs_ref;
+
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
+
+#include <linux/spinlock.h>
+
 int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info);
 void btrfs_free_ref_cache(struct btrfs_fs_info *fs_info);
 int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index ae90894dc7dc..08d0fb46ceec 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -174,7 +174,7 @@ static int clone_copy_inline_extent(struct inode *dst,
 				    char *inline_data,
 				    struct btrfs_trans_handle **trans_out)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(dst->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(dst);
 	struct btrfs_root *root = BTRFS_I(dst)->root;
 	const u64 aligned_end = ALIGN(new_key->offset + datal,
 				      fs_info->sectorsize);
@@ -337,7 +337,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		       const u64 off, const u64 olen, const u64 olen_aligned,
 		       const u64 destoff, int no_time_update)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct btrfs_path *path = NULL;
 	struct extent_buffer *leaf;
 	struct btrfs_trans_handle *trans;
@@ -663,7 +663,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
 				   struct inode *dst, u64 dst_loff)
 {
 	struct btrfs_fs_info *fs_info = BTRFS_I(src)->root->fs_info;
-	const u64 bs = fs_info->sb->s_blocksize;
+	const u64 bs = fs_info->sectorsize;
 	int ret;
 
 	/*
@@ -726,11 +726,11 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 {
 	struct inode *inode = file_inode(file);
 	struct inode *src = file_inode(file_src);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	int ret;
 	int wb_ret;
 	u64 len = olen;
-	u64 bs = fs_info->sb->s_blocksize;
+	u64 bs = fs_info->sectorsize;
 
 	/*
 	 * VFS's generic_remap_file_range_prep() protects us from cloning the
@@ -796,7 +796,7 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
-	u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize;
+	u64 bs = BTRFS_I(inode_out)->root->fs_info->sectorsize;
 	u64 wb_len;
 	int ret;
 
diff --git a/fs/btrfs/reflink.h b/fs/btrfs/reflink.h
index ecb309b4dad0..1e291f7d85c4 100644
--- a/fs/btrfs/reflink.h
+++ b/fs/btrfs/reflink.h
@@ -3,7 +3,9 @@
 #ifndef BTRFS_REFLINK_H
 #define BTRFS_REFLINK_H
 
-#include <linux/fs.h>
+#include <linux/types.h>
+
+struct file;
 
 loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
 			      struct file *file_out, loff_t pos_out,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index abe594f77f99..f96f267fb4aa 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -523,7 +523,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
 	if (handle_useless_nodes(rc, node))
 		node = NULL;
 out:
-	btrfs_backref_iter_free(iter);
+	btrfs_free_path(iter->path);
+	kfree(iter);
 	btrfs_free_path(path);
 	if (err) {
 		btrfs_backref_error_cleanup(cache, node);
@@ -2987,7 +2988,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 			     const struct file_extent_cluster *cluster,
 			     int *cluster_nr, unsigned long page_index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	u64 offset = BTRFS_I(inode)->index_cnt;
 	const unsigned long last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
diff --git a/fs/btrfs/relocation.h b/fs/btrfs/relocation.h
index 5fb60f2deb53..788c86d8633a 100644
--- a/fs/btrfs/relocation.h
+++ b/fs/btrfs/relocation.h
@@ -3,6 +3,15 @@
 #ifndef BTRFS_RELOCATION_H
 #define BTRFS_RELOCATION_H
 
+#include <linux/types.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_trans_handle;
+struct btrfs_ordered_extent;
+struct btrfs_pending_snapshot;
+
 int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start);
 int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root);
 int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 603ad1459368..4bb538a372ce 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -10,7 +10,6 @@
 #include "messages.h"
 #include "transaction.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "qgroup.h"
 #include "space-info.h"
 #include "accessors.h"
@@ -82,7 +81,14 @@ int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
 		if (ret > 0)
 			goto out;
 	} else {
-		BUG_ON(ret == 0);		/* Logical error */
+		/*
+		 * Key with offset -1 found, there would have to exist a root
+		 * with such id, but this is out of the valid range.
+		 */
+		if (ret == 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
 		if (path->slots[0] == 0)
 			goto out;
 		path->slots[0]--;
@@ -323,8 +329,11 @@ int btrfs_del_root(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, key, path, -1, 1);
 	if (ret < 0)
 		goto out;
-
-	BUG_ON(ret != 0);
+	if (ret != 0) {
+		/* The root must exist but we did not find it by the key. */
+		ret = -EUCLEAN;
+		goto out;
+	}
 
 	ret = btrfs_del_item(trans, root, path);
 out:
diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h
index 8b2c3859e464..6f929cf3bd49 100644
--- a/fs/btrfs/root-tree.h
+++ b/fs/btrfs/root-tree.h
@@ -3,7 +3,17 @@
 #ifndef BTRFS_ROOT_TREE_H
 #define BTRFS_ROOT_TREE_H
 
+#include <linux/types.h>
+
 struct fscrypt_str;
+struct extent_buffer;
+struct btrfs_key;
+struct btrfs_root;
+struct btrfs_root_item;
+struct btrfs_path;
+struct btrfs_fs_info;
+struct btrfs_block_rsv;
+struct btrfs_trans_handle;
 
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 0123d2728923..c4bd0e60db59 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1390,8 +1390,15 @@ static int find_first_extent_item(struct btrfs_root *extent_root,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		btrfs_release_path(path);
+		return -EUCLEAN;
+	}
 
-	ASSERT(ret > 0);
 	/*
 	 * Here we intentionally pass 0 as @min_objectid, as there could be
 	 * an extent item starting before @search_start.
diff --git a/fs/btrfs/scrub.h b/fs/btrfs/scrub.h
index 7639103ebf9d..f0df597b75c7 100644
--- a/fs/btrfs/scrub.h
+++ b/fs/btrfs/scrub.h
@@ -3,6 +3,12 @@
 #ifndef BTRFS_SCRUB_H
 #define BTRFS_SCRUB_H
 
+#include <linux/types.h>
+
+struct btrfs_fs_info;
+struct btrfs_device;
+struct btrfs_scrub_progress;
+
 int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		    u64 end, struct btrfs_scrub_progress *progress,
 		    int readonly, int is_dev_replace);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2d7519a6ce72..50b4a76ac88e 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -25,7 +25,6 @@
 #include "btrfs_inode.h"
 #include "transaction.h"
 #include "compression.h"
-#include "xattr.h"
 #include "print-tree.h"
 #include "accessors.h"
 #include "dir-item.h"
@@ -777,7 +776,12 @@ static int begin_cmd(struct send_ctx *sctx, int cmd)
 	if (WARN_ON(!sctx->send_buf))
 		return -EINVAL;
 
-	BUG_ON(sctx->send_size);
+	if (unlikely(sctx->send_size != 0)) {
+		btrfs_err(sctx->send_root->fs_info,
+			  "send: command header buffer not empty cmd %d offset %llu",
+			  cmd, sctx->send_off);
+		return -EINVAL;
+	}
 
 	sctx->send_size += sizeof(*hdr);
 	hdr = (struct btrfs_cmd_header *)sctx->send_buf;
@@ -1070,7 +1074,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path,
 					ret = PTR_ERR(start);
 					goto out;
 				}
-				BUG_ON(start < p->buf);
+				if (unlikely(start < p->buf)) {
+					btrfs_err(root->fs_info,
+			"send: path ref buffer underflow for key (%llu %u %llu)",
+						  found_key->objectid,
+						  found_key->type,
+						  found_key->offset);
+					ret = -EINVAL;
+					goto out;
+				}
 			}
 			p->start = start;
 		} else {
@@ -1406,7 +1418,7 @@ static bool lookup_backref_cache(u64 leaf_bytenr, void *ctx,
 	struct btrfs_lru_cache_entry *raw_entry;
 	struct backref_cache_entry *entry;
 
-	if (btrfs_lru_cache_size(&sctx->backref_cache) == 0)
+	if (sctx->backref_cache.size == 0)
 		return false;
 
 	/*
@@ -1504,7 +1516,7 @@ static void store_backref_cache(u64 leaf_bytenr, const struct ulist *root_ids,
 	 * transaction handle or holding fs_info->commit_root_sem, so no need
 	 * to take any lock here.
 	 */
-	if (btrfs_lru_cache_size(&sctx->backref_cache) == 1)
+	if (sctx->backref_cache.size == 1)
 		sctx->backref_cache_last_reloc_trans = fs_info->last_reloc_trans;
 }
 
@@ -2809,8 +2821,7 @@ static int cache_dir_utimes(struct send_ctx *sctx, u64 dir, u64 gen)
 
 static int trim_dir_utimes_cache(struct send_ctx *sctx)
 {
-	while (btrfs_lru_cache_size(&sctx->dir_utimes_cache) >
-	       SEND_MAX_DIR_UTIMES_CACHE_SIZE) {
+	while (sctx->dir_utimes_cache.size > SEND_MAX_DIR_UTIMES_CACHE_SIZE) {
 		struct btrfs_lru_cache_entry *lru;
 		int ret;
 
@@ -4182,7 +4193,13 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	 * This should never happen as the root dir always has the same ref
 	 * which is always '..'
 	 */
-	BUG_ON(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID);
+	if (unlikely(sctx->cur_ino <= BTRFS_FIRST_FREE_OBJECTID)) {
+		btrfs_err(fs_info,
+			  "send: unexpected inode %llu in process_recorded_refs()",
+			  sctx->cur_ino);
+		ret = -EINVAL;
+		goto out;
+	}
 
 	valid_path = fs_path_alloc();
 	if (!valid_path) {
@@ -6140,7 +6157,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 	int ret = 0;
 	u64 offset = key->offset;
 	u64 end;
-	u64 bs = sctx->send_root->fs_info->sb->s_blocksize;
+	u64 bs = sctx->send_root->fs_info->sectorsize;
 
 	end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size);
 	if (offset >= end)
@@ -6458,21 +6475,18 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 	if (sctx->cur_ino != key->objectid || !need_send_hole(sctx))
 		return 0;
 
-	if (sctx->cur_inode_last_extent == (u64)-1) {
-		ret = get_last_extent(sctx, key->offset - 1);
-		if (ret)
-			return ret;
-	}
-
-	if (path->slots[0] == 0 &&
-	    sctx->cur_inode_last_extent < key->offset) {
-		/*
-		 * We might have skipped entire leafs that contained only
-		 * file extent items for our current inode. These leafs have
-		 * a generation number smaller (older) than the one in the
-		 * current leaf and the leaf our last extent came from, and
-		 * are located between these 2 leafs.
-		 */
+	/*
+	 * Get last extent's end offset (exclusive) if we haven't determined it
+	 * yet (we're processing the first file extent item that is new), or if
+	 * we're at the first slot of a leaf and the last extent's end is less
+	 * than the current extent's offset, because we might have skipped
+	 * entire leaves that contained only file extent items for our current
+	 * inode. These leaves have a generation number smaller (older) than the
+	 * one in the current leaf and the leaf our last extent came from, and
+	 * are located between these 2 leaves.
+	 */
+	if ((sctx->cur_inode_last_extent == (u64)-1) ||
+	    (path->slots[0] == 0 && sctx->cur_inode_last_extent < key->offset)) {
 		ret = get_last_extent(sctx, key->offset - 1);
 		if (ret)
 			return ret;
@@ -6705,11 +6719,20 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 				if (ret)
 					goto out;
 			}
-			if (sctx->cur_inode_last_extent <
-			    sctx->cur_inode_size) {
-				ret = send_hole(sctx, sctx->cur_inode_size);
-				if (ret)
+			if (sctx->cur_inode_last_extent < sctx->cur_inode_size) {
+				ret = range_is_hole_in_parent(sctx,
+						      sctx->cur_inode_last_extent,
+						      sctx->cur_inode_size);
+				if (ret < 0) {
 					goto out;
+				} else if (ret == 0) {
+					ret = send_hole(sctx, sctx->cur_inode_size);
+					if (ret < 0)
+						goto out;
+				} else {
+					/* Range is already a hole, skip. */
+					ret = 0;
+				}
 			}
 		}
 		if (need_truncate) {
@@ -7420,8 +7443,8 @@ static int tree_move_down(struct btrfs_path *path, int *level, u64 reada_min_gen
 	u64 reada_done = 0;
 
 	lockdep_assert_held_read(&parent->fs_info->commit_root_sem);
+	ASSERT(*level != 0);
 
-	BUG_ON(*level == 0);
 	eb = btrfs_read_node_slot(parent, slot);
 	if (IS_ERR(eb))
 		return PTR_ERR(eb);
@@ -8111,7 +8134,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
-		ret = -EINVAL;
+		ret = -EOPNOTSUPP;
 		goto out;
 	}
 
diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h
index 4f5509cb1803..dd1c9f02b011 100644
--- a/fs/btrfs/send.h
+++ b/fs/btrfs/send.h
@@ -8,6 +8,11 @@
 #define BTRFS_SEND_H
 
 #include <linux/types.h>
+#include <linux/sizes.h>
+#include <linux/align.h>
+
+struct inode;
+struct btrfs_ioctl_send_args;
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 /* Conditional support for the upcoming protocol version. */
@@ -25,9 +30,6 @@
 #define BTRFS_SEND_BUF_SIZE_V1				SZ_64K
 #define BTRFS_SEND_BUF_SIZE_V2	ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED, PAGE_SIZE)
 
-struct inode;
-struct btrfs_ioctl_send_args;
-
 enum btrfs_tlv_type {
 	BTRFS_TLV_U8,
 	BTRFS_TLV_U16,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 571bb13587d5..d620323d08ea 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -9,7 +9,6 @@
 #include "ordered-data.h"
 #include "transaction.h"
 #include "block-group.h"
-#include "zoned.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
@@ -856,7 +855,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info)
 {
-	u64 global_rsv_size = fs_info->global_block_rsv.reserved;
+	const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv);
 	u64 ordered, delalloc;
 	u64 thresh;
 	u64 used;
@@ -956,8 +955,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 	ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1;
 	delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes);
 	if (ordered >= delalloc)
-		used += fs_info->delayed_refs_rsv.reserved +
-			fs_info->delayed_block_rsv.reserved;
+		used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv);
 	else
 		used += space_info->bytes_may_use - global_rsv_size;
 
@@ -1173,7 +1172,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		enum btrfs_flush_state flush;
 		u64 delalloc_size = 0;
 		u64 to_reclaim, block_rsv_size;
-		u64 global_rsv_size = global_rsv->reserved;
+		const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv);
 
 		loops++;
 
@@ -1185,9 +1184,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		 * assume it's tied up in delalloc reservations.
 		 */
 		block_rsv_size = global_rsv_size +
-			delayed_block_rsv->reserved +
-			delayed_refs_rsv->reserved +
-			trans_rsv->reserved;
+			btrfs_block_rsv_reserved(delayed_block_rsv) +
+			btrfs_block_rsv_reserved(delayed_refs_rsv) +
+			btrfs_block_rsv_reserved(trans_rsv);
 		if (block_rsv_size < space_info->bytes_may_use)
 			delalloc_size = space_info->bytes_may_use - block_rsv_size;
 
@@ -1207,16 +1206,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 			to_reclaim = delalloc_size;
 			flush = FLUSH_DELALLOC;
 		} else if (space_info->bytes_pinned >
-			   (delayed_block_rsv->reserved +
-			    delayed_refs_rsv->reserved)) {
+			   (btrfs_block_rsv_reserved(delayed_block_rsv) +
+			    btrfs_block_rsv_reserved(delayed_refs_rsv))) {
 			to_reclaim = space_info->bytes_pinned;
 			flush = COMMIT_TRANS;
-		} else if (delayed_block_rsv->reserved >
-			   delayed_refs_rsv->reserved) {
-			to_reclaim = delayed_block_rsv->reserved;
+		} else if (btrfs_block_rsv_reserved(delayed_block_rsv) >
+			   btrfs_block_rsv_reserved(delayed_refs_rsv)) {
+			to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv);
 			flush = FLUSH_DELAYED_ITEMS_NR;
 		} else {
-			to_reclaim = delayed_refs_rsv->reserved;
+			to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv);
 			flush = FLUSH_DELAYED_REFS_NR;
 		}
 
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 92c595fed1b0..a733458fd13b 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -4,8 +4,17 @@
 #define BTRFS_SPACE_INFO_H
 
 #include <trace/events/btrfs.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/kobject.h>
+#include <linux/lockdep.h>
+#include <linux/wait.h>
+#include <linux/rwsem.h>
 #include "volumes.h"
 
+struct btrfs_fs_info;
+struct btrfs_block_group;
+
 /*
  * Different levels for to flush space when doing space reservations.
  *
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 0e49dab8dad2..54736f6238e6 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -111,6 +111,9 @@ void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sector
 	subpage_info->checked_offset = cur;
 	cur += nr_bits;
 
+	subpage_info->locked_offset = cur;
+	cur += nr_bits;
+
 	subpage_info->total_nr_bits = cur;
 }
 
@@ -237,28 +240,58 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
 		       start + len <= folio_pos(folio) + PAGE_SIZE);
 }
 
+#define subpage_calc_start_bit(fs_info, folio, name, start, len)	\
+({									\
+	unsigned int start_bit;						\
+									\
+	btrfs_subpage_assert(fs_info, folio, start, len);		\
+	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
+	start_bit += fs_info->subpage_info->name##_offset;		\
+	start_bit;							\
+})
+
 void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
 				struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = len >> fs_info->sectorsize_bits;
+	unsigned long flags;
+
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
+	/*
+	 * Even though it's just for reading the page, no one should have
+	 * locked the subpage range.
+	 */
+	ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits));
+	bitmap_set(subpage->bitmaps, start_bit, nbits);
 	atomic_add(nbits, &subpage->readers);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 			      struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = len >> fs_info->sectorsize_bits;
+	unsigned long flags;
 	bool is_data;
 	bool last;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 	is_data = is_data_inode(folio->mapping->host);
+
+	spin_lock_irqsave(&subpage->lock, flags);
+
+	/* The range should have already been locked. */
+	ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits));
 	ASSERT(atomic_read(&subpage->readers) >= nbits);
+
+	bitmap_clear(subpage->bitmaps, start_bit, nbits);
 	last = atomic_sub_and_test(nbits, &subpage->readers);
 
 	/*
@@ -270,6 +303,7 @@ void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 	 */
 	if (is_data && last)
 		folio_unlock(folio);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
 static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
@@ -290,28 +324,38 @@ static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len)
 			     orig_start + orig_len) - *start;
 }
 
-void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-				struct folio *folio, u64 start, u32 len)
+static void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
+				       struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = (len >> fs_info->sectorsize_bits);
+	unsigned long flags;
 	int ret;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
 	ASSERT(atomic_read(&subpage->readers) == 0);
+	ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits));
+	bitmap_set(subpage->bitmaps, start_bit, nbits);
 	ret = atomic_add_return(nbits, &subpage->writers);
 	ASSERT(ret == nbits);
+	spin_unlock_irqrestore(&subpage->lock, flags);
 }
 
-bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-				       struct folio *folio, u64 start, u32 len)
+static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
+					      struct folio *folio, u64 start, u32 len)
 {
 	struct btrfs_subpage *subpage = folio_get_private(folio);
+	const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len);
 	const int nbits = (len >> fs_info->sectorsize_bits);
+	unsigned long flags;
+	bool last;
 
 	btrfs_subpage_assert(fs_info, folio, start, len);
 
+	spin_lock_irqsave(&subpage->lock, flags);
 	/*
 	 * We have call sites passing @lock_page into
 	 * extent_clear_unlock_delalloc() for compression path.
@@ -319,11 +363,18 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
 	 * This @locked_page is locked by plain lock_page(), thus its
 	 * subpage::writers is 0.  Handle them in a special way.
 	 */
-	if (atomic_read(&subpage->writers) == 0)
+	if (atomic_read(&subpage->writers) == 0) {
+		spin_unlock_irqrestore(&subpage->lock, flags);
 		return true;
+	}
 
 	ASSERT(atomic_read(&subpage->writers) >= nbits);
-	return atomic_sub_and_test(nbits, &subpage->writers);
+	/* The target range should have been locked. */
+	ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits));
+	bitmap_clear(subpage->bitmaps, start_bit, nbits);
+	last = atomic_sub_and_test(nbits, &subpage->writers);
+	spin_unlock_irqrestore(&subpage->lock, flags);
+	return last;
 }
 
 /*
@@ -365,16 +416,6 @@ void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
 		folio_unlock(folio);
 }
 
-#define subpage_calc_start_bit(fs_info, folio, name, start, len)	\
-({									\
-	unsigned int start_bit;						\
-									\
-	btrfs_subpage_assert(fs_info, folio, start, len);		\
-	start_bit = offset_in_page(start) >> fs_info->sectorsize_bits;	\
-	start_bit += fs_info->subpage_info->name##_offset;		\
-	start_bit;							\
-})
-
 #define subpage_test_bitmap_all_set(fs_info, subpage, name)		\
 	bitmap_test_range_all_set(subpage->bitmaps,			\
 			fs_info->subpage_info->name##_offset,		\
@@ -751,6 +792,7 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, writeback, &writeback_bitmap);
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, ordered, &ordered_bitmap);
 	GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap);
+	GET_SUBPAGE_BITMAP(subpage, subpage_info, locked, &checked_bitmap);
 	spin_unlock_irqrestore(&subpage->lock, flags);
 
 	dump_page(folio_page(folio, 0), "btrfs subpage dump");
diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h
index 793c2b314a58..b6dc013b0fdc 100644
--- a/fs/btrfs/subpage.h
+++ b/fs/btrfs/subpage.h
@@ -4,6 +4,11 @@
 #define BTRFS_SUBPAGE_H
 
 #include <linux/spinlock.h>
+#include <linux/atomic.h>
+
+struct address_space;
+struct folio;
+struct btrfs_fs_info;
 
 /*
  * Extra info for subpapge bitmap.
@@ -28,7 +33,7 @@ struct btrfs_subpage_info {
 	unsigned int total_nr_bits;
 
 	/*
-	 * *_start indicates where the bitmap starts, the length is always
+	 * *_offset indicates where the bitmap starts, the length is always
 	 * @bitmap_size, which is calculated from PAGE_SIZE / sectorsize.
 	 */
 	unsigned int uptodate_offset;
@@ -36,6 +41,16 @@ struct btrfs_subpage_info {
 	unsigned int writeback_offset;
 	unsigned int ordered_offset;
 	unsigned int checked_offset;
+
+	/*
+	 * For locked bitmaps, normally it's subpage representation for folio
+	 * Locked flag, but metadata is different:
+	 *
+	 * - Metadata doesn't really lock the folio
+	 *   It's just to prevent page::private get cleared before the last
+	 *   end_page_read().
+	 */
+	unsigned int locked_offset;
 };
 
 /*
@@ -93,10 +108,6 @@ void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info,
 void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info,
 			      struct folio *folio, u64 start, u32 len);
 
-void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info,
-				struct folio *folio, u64 start, u32 len);
-bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
-				       struct folio *folio, u64 start, u32 len);
 int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info,
 				  struct folio *folio, u64 start, u32 len);
 void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 101f786963d4..7e44ccaf348f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -34,13 +34,11 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "print-tree.h"
 #include "props.h"
 #include "xattr.h"
 #include "bio.h"
 #include "export.h"
 #include "compression.h"
-#include "rcu-string.h"
 #include "dev-replace.h"
 #include "free-space-cache.h"
 #include "backref.h"
@@ -1767,7 +1765,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		buf->f_bavail = 0;
 
 	buf->f_type = BTRFS_SUPER_MAGIC;
-	buf->f_bsize = dentry->d_sb->s_blocksize;
+	buf->f_bsize = fs_info->sectorsize;
 	buf->f_namelen = BTRFS_NAME_LEN;
 
 	/* We treat it as constant endianness (it doesn't matter _which_)
@@ -2203,7 +2201,9 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	vol = memdup_user((void __user *)arg, sizeof(*vol));
 	if (IS_ERR(vol))
 		return PTR_ERR(vol);
-	vol->name[BTRFS_PATH_NAME_MAX] = '\0';
+	ret = btrfs_check_ioctl_vol_args_path(vol);
+	if (ret < 0)
+		goto out;
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
@@ -2245,6 +2245,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		break;
 	}
 
+out:
 	kfree(vol);
 	return ret;
 }
diff --git a/fs/btrfs/super.h b/fs/btrfs/super.h
index f18253ca280d..cbcab434b5ec 100644
--- a/fs/btrfs/super.h
+++ b/fs/btrfs/super.h
@@ -3,6 +3,13 @@
 #ifndef BTRFS_SUPER_H
 #define BTRFS_SUPER_H
 
+#include <linux/types.h>
+#include <linux/fs.h>
+#include "fs.h"
+
+struct super_block;
+struct btrfs_fs_info;
+
 bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
 			 unsigned long flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 84c05246ffd8..c6387a8ddb94 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -421,7 +421,7 @@ BTRFS_ATTR(static_feature, supported_sectorsizes,
 
 static ssize_t acl_show(struct kobject *kobj, struct kobj_attribute *a, char *buf)
 {
-	return sysfs_emit(buf, "%d\n", !!IS_ENABLED(CONFIG_BTRFS_FS_POSIX_ACL));
+	return sysfs_emit(buf, "%d\n", IS_ENABLED(CONFIG_BTRFS_FS_POSIX_ACL));
 }
 BTRFS_ATTR(static_feature, acl, acl_show);
 
@@ -1228,11 +1228,12 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj,
 				      struct kobj_attribute *a, char *buf)
 {
 	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	const enum btrfs_read_policy policy = READ_ONCE(fs_devices->read_policy);
 	ssize_t ret = 0;
 	int i;
 
 	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
-		if (fs_devices->read_policy == i)
+		if (policy == i)
 			ret += sysfs_emit_at(buf, ret, "%s[%s]",
 					 (ret == 0 ? "" : " "),
 					 btrfs_read_policy_name[i]);
@@ -1256,8 +1257,8 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
 
 	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
 		if (sysfs_streq(buf, btrfs_read_policy_name[i])) {
-			if (i != fs_devices->read_policy) {
-				fs_devices->read_policy = i;
+			if (i != READ_ONCE(fs_devices->read_policy)) {
+				WRITE_ONCE(fs_devices->read_policy, i);
 				btrfs_info(fs_devices->fs_info,
 					   "read policy set to '%s'",
 					   btrfs_read_policy_name[i]);
@@ -1306,6 +1307,47 @@ static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj,
 BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show,
 	      btrfs_bg_reclaim_threshold_store);
 
+#ifdef CONFIG_BTRFS_DEBUG
+static ssize_t btrfs_offload_csum_show(struct kobject *kobj,
+				       struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+
+	switch (READ_ONCE(fs_devices->offload_csum_mode)) {
+	case BTRFS_OFFLOAD_CSUM_AUTO:
+		return sysfs_emit(buf, "auto\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_ON:
+		return sysfs_emit(buf, "1\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_OFF:
+		return sysfs_emit(buf, "0\n");
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
+static ssize_t btrfs_offload_csum_store(struct kobject *kobj,
+					struct kobj_attribute *a, const char *buf,
+					size_t len)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	int ret;
+	bool val;
+
+	ret = kstrtobool(buf, &val);
+	if (ret == 0)
+		WRITE_ONCE(fs_devices->offload_csum_mode,
+			   val ? BTRFS_OFFLOAD_CSUM_FORCE_ON : BTRFS_OFFLOAD_CSUM_FORCE_OFF);
+	else if (ret == -EINVAL && sysfs_streq(buf, "auto"))
+		WRITE_ONCE(fs_devices->offload_csum_mode, BTRFS_OFFLOAD_CSUM_AUTO);
+	else
+		return -EINVAL;
+
+	return len;
+}
+BTRFS_ATTR_RW(, offload_csum, btrfs_offload_csum_show, btrfs_offload_csum_store);
+#endif
+
 /*
  * Per-filesystem information and stats.
  *
@@ -1325,6 +1367,9 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
 	BTRFS_ATTR_PTR(, commit_stats),
 	BTRFS_ATTR_PTR(, temp_fsid),
+#ifdef CONFIG_BTRFS_DEBUG
+	BTRFS_ATTR_PTR(, offload_csum),
+#endif
 	NULL,
 };
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 86c7eef12873..e6a284c59809 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -3,8 +3,17 @@
 #ifndef BTRFS_SYSFS_H
 #define BTRFS_SYSFS_H
 
+#include <linux/types.h>
+#include <linux/compiler_types.h>
 #include <linux/kobject.h>
 
+struct btrfs_fs_info;
+struct btrfs_device;
+struct btrfs_fs_devices;
+struct btrfs_block_group;
+struct btrfs_space_info;
+struct btrfs_qgroup;
+
 enum btrfs_feature_set {
 	FEAT_COMPAT,
 	FEAT_COMPAT_RO,
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 25b3349595e0..865d4af4b303 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -11,6 +11,7 @@
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../extent_io.h"
+#include "../disk-io.h"
 #include "../btrfs_inode.h"
 
 #define PROCESS_UNLOCK		(1 << 0)
@@ -105,9 +106,11 @@ static void dump_extent_io_tree(const struct extent_io_tree *tree)
 	}
 }
 
-static int test_find_delalloc(u32 sectorsize)
+static int test_find_delalloc(u32 sectorsize, u32 nodesize)
 {
-	struct inode *inode;
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_root *root = NULL;
+	struct inode *inode = NULL;
 	struct extent_io_tree *tmp;
 	struct page *page;
 	struct page *locked_page = NULL;
@@ -121,12 +124,27 @@ static int test_find_delalloc(u32 sectorsize)
 
 	test_msg("running find delalloc tests");
 
+	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
+	if (!fs_info) {
+		test_std_err(TEST_ALLOC_FS_INFO);
+		return -ENOMEM;
+	}
+
+	root = btrfs_alloc_dummy_root(fs_info);
+	if (IS_ERR(root)) {
+		test_std_err(TEST_ALLOC_ROOT);
+		ret = PTR_ERR(root);
+		goto out;
+	}
+
 	inode = btrfs_new_test_inode();
 	if (!inode) {
 		test_std_err(TEST_ALLOC_INODE);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 	tmp = &BTRFS_I(inode)->io_tree;
+	BTRFS_I(inode)->root = root;
 
 	/*
 	 * Passing NULL as we don't have fs_info but tracepoints are not used
@@ -316,6 +334,8 @@ out:
 	process_page_range(inode, 0, total_dirty - 1,
 			   PROCESS_UNLOCK | PROCESS_RELEASE);
 	iput(inode);
+	btrfs_free_dummy_root(root);
+	btrfs_free_dummy_fs_info(fs_info);
 	return ret;
 }
 
@@ -794,7 +814,7 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 
 	test_msg("running extent I/O tests");
 
-	ret = test_find_delalloc(sectorsize);
+	ret = test_find_delalloc(sectorsize, nodesize);
 	if (ret)
 		goto out;
 
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 9957de9f7806..99da9d34b77a 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -258,7 +258,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_err("got an error when we shouldn't have");
@@ -278,7 +278,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	 */
 	setup_file_extents(root, sectorsize);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, (u64)-1);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -316,7 +316,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -339,7 +339,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -367,7 +367,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -396,7 +396,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -418,7 +418,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -452,7 +452,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -481,7 +481,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -511,7 +511,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -544,7 +544,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -579,7 +579,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -613,7 +613,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -648,7 +648,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -675,7 +675,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -710,7 +710,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset + 6, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -737,7 +737,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, SZ_4M);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, SZ_4M);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -770,7 +770,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, offset, sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -850,7 +850,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	insert_inode_item_key(root);
 	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 2 * sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
@@ -872,7 +872,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize, 2 * sectorsize);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, sectorsize, 2 * sectorsize);
 	if (IS_ERR(em)) {
 		test_err("got an error when we shouldn't have");
 		goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b3333ceef04..46e8426adf4f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -23,12 +23,10 @@
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
-#include "zoned.h"
 #include "fs.h"
 #include "accessors.h"
 #include "extent-tree.h"
 #include "root-tree.h"
-#include "defrag.h"
 #include "dir-item.h"
 #include "uuid-tree.h"
 #include "ioctl.h"
@@ -564,56 +562,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
 					u64 num_bytes,
 					u64 *delayed_refs_bytes)
 {
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
 	struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info;
-	u64 extra_delayed_refs_bytes = 0;
-	u64 bytes;
+	u64 bytes = num_bytes + *delayed_refs_bytes;
 	int ret;
 
 	/*
-	 * If there's a gap between the size of the delayed refs reserve and
-	 * its reserved space, than some tasks have added delayed refs or bumped
-	 * its size otherwise (due to block group creation or removal, or block
-	 * group item update). Also try to allocate that gap in order to prevent
-	 * using (and possibly abusing) the global reserve when committing the
-	 * transaction.
-	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL &&
-	    !btrfs_block_rsv_full(delayed_refs_rsv)) {
-		spin_lock(&delayed_refs_rsv->lock);
-		if (delayed_refs_rsv->size > delayed_refs_rsv->reserved)
-			extra_delayed_refs_bytes = delayed_refs_rsv->size -
-				delayed_refs_rsv->reserved;
-		spin_unlock(&delayed_refs_rsv->lock);
-	}
-
-	bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes;
-
-	/*
 	 * We want to reserve all the bytes we may need all at once, so we only
 	 * do 1 enospc flushing cycle per transaction start.
 	 */
 	ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-	if (ret == 0) {
-		if (extra_delayed_refs_bytes > 0)
-			btrfs_migrate_to_delayed_refs_rsv(fs_info,
-							  extra_delayed_refs_bytes);
-		return 0;
-	}
-
-	if (extra_delayed_refs_bytes > 0) {
-		bytes -= extra_delayed_refs_bytes;
-		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-		if (ret == 0)
-			return 0;
-	}
 
 	/*
 	 * If we are an emergency flush, which can steal from the global block
 	 * reserve, then attempt to not reserve space for the delayed refs, as
 	 * we will consume space for them from the global block reserve.
 	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
+	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
 		bytes -= *delayed_refs_bytes;
 		*delayed_refs_bytes = 0;
 		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
@@ -1868,7 +1832,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	}
 
 	key.offset = (u64)-1;
-	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
+	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
 		pending->snap = NULL;
@@ -1993,19 +1957,6 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 		super->uuid_tree_generation = root_item->generation;
 }
 
-int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
-{
-	struct btrfs_transaction *trans;
-	int ret = 0;
-
-	spin_lock(&info->trans_lock);
-	trans = info->running_transaction;
-	if (trans)
-		ret = (trans->state >= TRANS_STATE_COMMIT_START);
-	spin_unlock(&info->trans_lock);
-	return ret;
-}
-
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
 	struct btrfs_transaction *trans;
@@ -2720,9 +2671,7 @@ void __cold __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 
 int __init btrfs_transaction_init(void)
 {
-	btrfs_trans_handle_cachep = kmem_cache_create("btrfs_trans_handle",
-			sizeof(struct btrfs_trans_handle), 0,
-			SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
+	btrfs_trans_handle_cachep = KMEM_CACHE(btrfs_trans_handle, SLAB_TEMPORARY);
 	if (!btrfs_trans_handle_cachep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 2bf8bbdfd0b3..4e451ab173b1 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -6,12 +6,27 @@
 #ifndef BTRFS_TRANSACTION_H
 #define BTRFS_TRANSACTION_H
 
+#include <linux/atomic.h>
 #include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/time64.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
 #include "btrfs_inode.h"
 #include "delayed-ref.h"
-#include "ctree.h"
+#include "extent-io-tree.h"
+#include "block-rsv.h"
+#include "messages.h"
 #include "misc.h"
 
+struct dentry;
+struct inode;
+struct btrfs_pending_snapshot;
+struct btrfs_fs_info;
+struct btrfs_root_item;
+struct btrfs_root;
+struct btrfs_path;
+
 /* Radix-tree tag for roots that are part of the trasaction. */
 #define BTRFS_ROOT_TRANS_TAG			0
 
@@ -262,7 +277,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
 				struct extent_io_tree *dirty_pages, int mark);
 int btrfs_wait_tree_log_extents(struct btrfs_root *root, int mark);
 int btrfs_transaction_blocked(struct btrfs_fs_info *info);
-int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
 void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 6eccf8496486..c8fbcae4e88e 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -21,7 +21,6 @@
 #include "messages.h"
 #include "ctree.h"
 #include "tree-checker.h"
-#include "disk-io.h"
 #include "compression.h"
 #include "volumes.h"
 #include "misc.h"
@@ -30,7 +29,6 @@
 #include "file-item.h"
 #include "inode-item.h"
 #include "dir-item.h"
-#include "raid-stripe-tree.h"
 #include "extent-tree.h"
 
 /*
@@ -67,6 +65,7 @@ static void generic_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 		"corrupt %s: root=%llu block=%llu slot=%d, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -94,6 +93,7 @@ static void file_extent_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu file_offset=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -154,6 +154,7 @@ static void dir_item_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 		"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -649,6 +650,7 @@ static void block_group_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -1005,6 +1007,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(eb->fs_info,
 	"corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
@@ -1260,6 +1263,7 @@ static void extent_err(const struct extent_buffer *eb, int slot,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
+	dump_page(folio_page(eb->folios[0], 0), "eb page dump");
 	btrfs_crit(eb->fs_info,
 	"corrupt %s: block=%llu slot=%d extent bytenr=%llu len=%llu %pV",
 		btrfs_header_level(eb) == 0 ? "leaf" : "node",
diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h
index 14b9fbe82da4..5c809b50b2d0 100644
--- a/fs/btrfs/tree-checker.h
+++ b/fs/btrfs/tree-checker.h
@@ -6,10 +6,12 @@
 #ifndef BTRFS_TREE_CHECKER_H
 #define BTRFS_TREE_CHECKER_H
 
+#include <linux/types.h>
 #include <uapi/linux/btrfs_tree.h>
 
 struct extent_buffer;
 struct btrfs_chunk;
+struct btrfs_key;
 
 /* All the extra info needed to verify the parentness of a tree block. */
 struct btrfs_tree_parent_check {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 331fc7429952..472918a5bc73 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -13,13 +13,11 @@
 #include "tree-log.h"
 #include "disk-io.h"
 #include "locking.h"
-#include "print-tree.h"
 #include "backref.h"
 #include "compression.h"
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
-#include "zoned.h"
 #include "inode-item.h"
 #include "fs.h"
 #include "accessors.h"
@@ -2820,6 +2818,52 @@ static void wait_for_writer(struct btrfs_root *root)
 	finish_wait(&root->log_writer_wait, &wait);
 }
 
+void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode)
+{
+	ctx->log_ret = 0;
+	ctx->log_transid = 0;
+	ctx->log_new_dentries = false;
+	ctx->logging_new_name = false;
+	ctx->logging_new_delayed_dentries = false;
+	ctx->logged_before = false;
+	ctx->inode = inode;
+	INIT_LIST_HEAD(&ctx->list);
+	INIT_LIST_HEAD(&ctx->ordered_extents);
+	INIT_LIST_HEAD(&ctx->conflict_inodes);
+	ctx->num_conflict_inodes = 0;
+	ctx->logging_conflict_inodes = false;
+	ctx->scratch_eb = NULL;
+}
+
+void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+
+	if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) &&
+	    !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags))
+		return;
+
+	/*
+	 * Don't care about allocation failure. This is just for optimization,
+	 * if we fail to allocate here, we will try again later if needed.
+	 */
+	ctx->scratch_eb = alloc_dummy_extent_buffer(inode->root->fs_info, 0);
+}
+
+void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_ordered_extent *ordered;
+	struct btrfs_ordered_extent *tmp;
+
+	ASSERT(inode_is_locked(ctx->inode));
+
+	list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
+		list_del_init(&ordered->log_list);
+		btrfs_put_ordered_extent(ordered);
+	}
+}
+
+
 static inline void btrfs_remove_log_ctx(struct btrfs_root *root,
 					struct btrfs_log_ctx *ctx)
 {
@@ -3619,6 +3663,30 @@ out:
 	return ret;
 }
 
+static int clone_leaf(struct btrfs_path *path, struct btrfs_log_ctx *ctx)
+{
+	const int slot = path->slots[0];
+
+	if (ctx->scratch_eb) {
+		copy_extent_buffer_full(ctx->scratch_eb, path->nodes[0]);
+	} else {
+		ctx->scratch_eb = btrfs_clone_extent_buffer(path->nodes[0]);
+		if (!ctx->scratch_eb)
+			return -ENOMEM;
+	}
+
+	btrfs_release_path(path);
+	path->nodes[0] = ctx->scratch_eb;
+	path->slots[0] = slot;
+	/*
+	 * Add extra ref to scratch eb so that it is not freed when callers
+	 * release the path, so we can reuse it later if needed.
+	 */
+	atomic_inc(&ctx->scratch_eb->refs);
+
+	return 0;
+}
+
 static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 				  struct btrfs_inode *inode,
 				  struct btrfs_path *path,
@@ -3633,23 +3701,20 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 	bool last_found = false;
 	int batch_start = 0;
 	int batch_size = 0;
-	int i;
+	int ret;
 
 	/*
 	 * We need to clone the leaf, release the read lock on it, and use the
 	 * clone before modifying the log tree. See the comment at copy_items()
 	 * about why we need to do this.
 	 */
-	src = btrfs_clone_extent_buffer(path->nodes[0]);
-	if (!src)
-		return -ENOMEM;
+	ret = clone_leaf(path, ctx);
+	if (ret < 0)
+		return ret;
 
-	i = path->slots[0];
-	btrfs_release_path(path);
-	path->nodes[0] = src;
-	path->slots[0] = i;
+	src = path->nodes[0];
 
-	for (; i < nritems; i++) {
+	for (int i = path->slots[0]; i < nritems; i++) {
 		struct btrfs_dir_item *di;
 		struct btrfs_key key;
 		int ret;
@@ -4259,17 +4324,16 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_path *dst_path,
 			       struct btrfs_path *src_path,
 			       int start_slot, int nr, int inode_only,
-			       u64 logged_isize)
+			       u64 logged_isize, struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *log = inode->root->log_root;
 	struct btrfs_file_extent_item *extent;
 	struct extent_buffer *src;
-	int ret = 0;
+	int ret;
 	struct btrfs_key *ins_keys;
 	u32 *ins_sizes;
 	struct btrfs_item_batch batch;
 	char *ins_data;
-	int i;
 	int dst_index;
 	const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM);
 	const u64 i_size = i_size_read(&inode->vfs_inode);
@@ -4302,14 +4366,11 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	 * while the other is holding the delayed node's mutex and wants to
 	 * write lock the same subvolume leaf for flushing delayed items.
 	 */
-	src = btrfs_clone_extent_buffer(src_path->nodes[0]);
-	if (!src)
-		return -ENOMEM;
+	ret = clone_leaf(src_path, ctx);
+	if (ret < 0)
+		return ret;
 
-	i = src_path->slots[0];
-	btrfs_release_path(src_path);
-	src_path->nodes[0] = src;
-	src_path->slots[0] = i;
+	src = src_path->nodes[0];
 
 	ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
 			   nr * sizeof(u32), GFP_NOFS);
@@ -4324,7 +4385,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	batch.nr = 0;
 
 	dst_index = 0;
-	for (i = 0; i < nr; i++) {
+	for (int i = 0; i < nr; i++) {
 		const int src_slot = start_slot + i;
 		struct btrfs_root *csum_root;
 		struct btrfs_ordered_sum *sums;
@@ -4431,7 +4492,7 @@ add_to_batch:
 		goto out;
 
 	dst_index = 0;
-	for (i = 0; i < nr; i++) {
+	for (int i = 0; i < nr; i++) {
 		const int src_slot = start_slot + i;
 		const int dst_slot = dst_path->slots[0] + dst_index;
 		struct btrfs_key key;
@@ -4704,7 +4765,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
  */
 static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_inode *inode,
-				      struct btrfs_path *path)
+				      struct btrfs_path *path,
+				      struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_key key;
@@ -4770,7 +4832,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 start_slot, ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0, ctx);
 				if (ret < 0)
 					goto out;
 				ins_nr = 0;
@@ -4820,7 +4882,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	}
 	if (ins_nr > 0)
 		ret = copy_items(trans, inode, dst_path, path,
-				 start_slot, ins_nr, 1, 0);
+				 start_slot, ins_nr, 1, 0, ctx);
 out:
 	btrfs_release_path(path);
 	btrfs_free_path(dst_path);
@@ -4899,7 +4961,7 @@ process:
 	write_unlock(&tree->lock);
 
 	if (!ret)
-		ret = btrfs_log_prealloc_extents(trans, inode, path);
+		ret = btrfs_log_prealloc_extents(trans, inode, path, ctx);
 	if (ret)
 		return ret;
 
@@ -4980,7 +5042,8 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 				struct btrfs_inode *inode,
 				struct btrfs_path *path,
-				struct btrfs_path *dst_path)
+				struct btrfs_path *dst_path,
+				struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *root = inode->root;
 	int ret;
@@ -5009,7 +5072,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 		if (slot >= nritems) {
 			if (ins_nr > 0) {
 				ret = copy_items(trans, inode, dst_path, path,
-						 start_slot, ins_nr, 1, 0);
+						 start_slot, ins_nr, 1, 0, ctx);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;
@@ -5035,7 +5098,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 	}
 	if (ins_nr > 0) {
 		ret = copy_items(trans, inode, dst_path, path,
-				 start_slot, ins_nr, 1, 0);
+				 start_slot, ins_nr, 1, 0, ctx);
 		if (ret < 0)
 			return ret;
 	}
@@ -5847,7 +5910,7 @@ again:
 				}
 				ret = copy_items(trans, inode, dst_path, path,
 						 ins_start_slot, ins_nr,
-						 inode_only, logged_isize);
+						 inode_only, logged_isize, ctx);
 				if (ret < 0)
 					return ret;
 				ins_nr = 0;
@@ -5866,7 +5929,7 @@ again:
 				goto next_slot;
 			ret = copy_items(trans, inode, dst_path, path,
 					 ins_start_slot,
-					 ins_nr, inode_only, logged_isize);
+					 ins_nr, inode_only, logged_isize, ctx);
 			if (ret < 0)
 				return ret;
 			ins_nr = 0;
@@ -5883,7 +5946,7 @@ again:
 		}
 
 		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
-				 ins_nr, inode_only, logged_isize);
+				 ins_nr, inode_only, logged_isize, ctx);
 		if (ret < 0)
 			return ret;
 		ins_nr = 1;
@@ -5898,7 +5961,7 @@ next_slot:
 		if (ins_nr) {
 			ret = copy_items(trans, inode, dst_path, path,
 					 ins_start_slot, ins_nr, inode_only,
-					 logged_isize);
+					 logged_isize, ctx);
 			if (ret < 0)
 				return ret;
 			ins_nr = 0;
@@ -5923,7 +5986,7 @@ next_key:
 	}
 	if (ins_nr) {
 		ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
-				 ins_nr, inode_only, logged_isize);
+				 ins_nr, inode_only, logged_isize, ctx);
 		if (ret)
 			return ret;
 	}
@@ -5934,7 +5997,7 @@ next_key:
 		 * lock the same leaf with btrfs_log_prealloc_extents() below.
 		 */
 		btrfs_release_path(path);
-		ret = btrfs_log_prealloc_extents(trans, inode, dst_path);
+		ret = btrfs_log_prealloc_extents(trans, inode, dst_path, ctx);
 	}
 
 	return ret;
@@ -6526,7 +6589,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
-	ret = btrfs_log_all_xattrs(trans, inode, path, dst_path);
+	ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx);
 	if (ret)
 		goto out_unlock;
 	xattrs_logged = true;
@@ -6553,7 +6616,7 @@ log_extents:
 		 * BTRFS_INODE_COPY_EVERYTHING set.
 		 */
 		if (!xattrs_logged && inode->logged_trans < trans->transid) {
-			ret = btrfs_log_all_xattrs(trans, inode, path, dst_path);
+			ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx);
 			if (ret)
 				goto out_unlock;
 			btrfs_release_path(path);
@@ -7502,6 +7565,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 
 	btrfs_init_log_ctx(&ctx, &inode->vfs_inode);
 	ctx.logging_new_name = true;
+	btrfs_init_log_ctx_scratch_eb(&ctx);
 	/*
 	 * We don't care about the return value. If we fail to log the new name
 	 * then we know the next attempt to sync the log will fallback to a full
@@ -7510,6 +7574,7 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * inconsistent state after a rename operation.
 	 */
 	btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx);
+	free_extent_buffer(ctx.scratch_eb);
 	ASSERT(list_empty(&ctx.conflict_inodes));
 out:
 	/*
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index a550a8a375cd..22e9cbc81577 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -6,10 +6,18 @@
 #ifndef BTRFS_TREE_LOG_H
 #define BTRFS_TREE_LOG_H
 
+#include <linux/list.h>
+#include <linux/fs.h>
 #include "messages.h"
 #include "ctree.h"
 #include "transaction.h"
 
+struct inode;
+struct dentry;
+struct btrfs_ordered_extent;
+struct btrfs_root;
+struct btrfs_trans_handle;
+
 /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
 #define BTRFS_NO_LOG_SYNC 256
 
@@ -36,37 +44,20 @@ struct btrfs_log_ctx {
 	struct list_head conflict_inodes;
 	int num_conflict_inodes;
 	bool logging_conflict_inodes;
+	/*
+	 * Used for fsyncs that need to copy items from the subvolume tree to
+	 * the log tree (full sync flag set or copy everything flag set) to
+	 * avoid allocating a temporary extent buffer while holding a lock on
+	 * an extent buffer of the subvolume tree and under the log transaction.
+	 * Also helps to avoid allocating and freeing a temporary extent buffer
+	 * in case we need to process multiple leaves from the subvolume tree.
+	 */
+	struct extent_buffer *scratch_eb;
 };
 
-static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
-				      struct inode *inode)
-{
-	ctx->log_ret = 0;
-	ctx->log_transid = 0;
-	ctx->log_new_dentries = false;
-	ctx->logging_new_name = false;
-	ctx->logging_new_delayed_dentries = false;
-	ctx->logged_before = false;
-	ctx->inode = inode;
-	INIT_LIST_HEAD(&ctx->list);
-	INIT_LIST_HEAD(&ctx->ordered_extents);
-	INIT_LIST_HEAD(&ctx->conflict_inodes);
-	ctx->num_conflict_inodes = 0;
-	ctx->logging_conflict_inodes = false;
-}
-
-static inline void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx)
-{
-	struct btrfs_ordered_extent *ordered;
-	struct btrfs_ordered_extent *tmp;
-
-	ASSERT(inode_is_locked(ctx->inode));
-
-	list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
-		list_del_init(&ordered->log_list);
-		btrfs_put_ordered_extent(ordered);
-	}
-}
+void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct inode *inode);
+void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx);
+void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx);
 
 static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans)
 {
diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
index 3df6153d5d5a..43b3accbed7a 100644
--- a/fs/btrfs/tree-mod-log.c
+++ b/fs/btrfs/tree-mod-log.c
@@ -44,7 +44,7 @@ struct tree_mod_elem {
 /*
  * Pull a new tree mod seq number for our operation.
  */
-static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
+static u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
 {
 	return atomic64_inc_return(&fs_info->tree_mod_seq);
 }
@@ -170,8 +170,7 @@ static noinline int tree_mod_log_insert(struct btrfs_fs_info *fs_info,
  * this until all tree mod log insertions are recorded in the rb tree and then
  * write unlock fs_info::tree_mod_log_lock.
  */
-static inline bool tree_mod_dont_log(struct btrfs_fs_info *fs_info,
-				    struct extent_buffer *eb)
+static bool tree_mod_dont_log(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
 {
 	if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
 		return true;
@@ -188,7 +187,7 @@ static inline bool tree_mod_dont_log(struct btrfs_fs_info *fs_info,
 }
 
 /* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
-static inline bool tree_mod_need_log(const struct btrfs_fs_info *fs_info,
+static bool tree_mod_need_log(const struct btrfs_fs_info *fs_info,
 				    struct extent_buffer *eb)
 {
 	if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
@@ -367,9 +366,9 @@ free_tms:
 	return ret;
 }
 
-static inline int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
-				       struct tree_mod_elem **tm_list,
-				       int nritems)
+static int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+				struct tree_mod_elem **tm_list,
+				int nritems)
 {
 	int i, j;
 	int ret;
diff --git a/fs/btrfs/tree-mod-log.h b/fs/btrfs/tree-mod-log.h
index 94f10afeee97..ff00c8e8a393 100644
--- a/fs/btrfs/tree-mod-log.h
+++ b/fs/btrfs/tree-mod-log.h
@@ -3,7 +3,13 @@
 #ifndef BTRFS_TREE_MOD_LOG_H
 #define BTRFS_TREE_MOD_LOG_H
 
-#include "ctree.h"
+#include <linux/list.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_root;
+struct btrfs_seq_list;
 
 /* Represents a tree mod log user. */
 struct btrfs_seq_list {
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index b4ac2b0cd235..183863f4bfa4 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -7,7 +7,6 @@
 #include <linux/slab.h>
 #include "messages.h"
 #include "ulist.h"
-#include "ctree.h"
 
 /*
  * ulist is a generic data structure to hold a collection of unique u64
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index b2cef187ea8e..8e200fe1a2dd 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -7,6 +7,7 @@
 #ifndef BTRFS_ULIST_H
 #define BTRFS_ULIST_H
 
+#include <linux/types.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 5be74f9e47eb..b0aff297d67d 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -9,7 +9,6 @@
 #include "ctree.h"
 #include "transaction.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "fs.h"
 #include "accessors.h"
 #include "uuid-tree.h"
@@ -114,7 +113,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 
 	ret = btrfs_insert_empty_item(trans, uuid_root, path, &key,
 				      sizeof(subid_le));
-	if (ret >= 0) {
+	if (ret == 0) {
 		/* Add an item for the type for the first time */
 		eb = path->nodes[0];
 		slot = path->slots[0];
diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h
index 5350c87fe2ca..080ede0227ae 100644
--- a/fs/btrfs/uuid-tree.h
+++ b/fs/btrfs/uuid-tree.h
@@ -3,6 +3,11 @@
 #ifndef BTRFS_UUID_TREE_H
 #define BTRFS_UUID_TREE_H
 
+#include <linux/types.h>
+
+struct btrfs_trans_handle;
+struct btrfs_fs_info;
+
 int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 			u64 subid);
 int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c
index 66e2270b0dae..4042dd6437ae 100644
--- a/fs/btrfs/verity.c
+++ b/fs/btrfs/verity.c
@@ -14,7 +14,6 @@
 #include "ctree.h"
 #include "btrfs_inode.h"
 #include "transaction.h"
-#include "disk-io.h"
 #include "locking.h"
 #include "fs.h"
 #include "accessors.h"
diff --git a/fs/btrfs/verity.h b/fs/btrfs/verity.h
index 91c10f7d0a46..d696659e43e4 100644
--- a/fs/btrfs/verity.h
+++ b/fs/btrfs/verity.h
@@ -3,8 +3,13 @@
 #ifndef BTRFS_VERITY_H
 #define BTRFS_VERITY_H
 
+struct inode;
+struct btrfs_inode;
+
 #ifdef CONFIG_FS_VERITY
 
+#include <linux/fsverity.h>
+
 extern const struct fsverity_operations btrfs_verityops;
 
 int btrfs_drop_verity_items(struct btrfs_inode *inode);
@@ -12,6 +17,8 @@ int btrfs_get_verity_descriptor(struct inode *inode, void *buf, size_t buf_size)
 
 #else
 
+#include <linux/errno.h>
+
 static inline int btrfs_drop_verity_items(struct btrfs_inode *inode)
 {
 	return 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d67785be2c77..a2d07fa3cfdf 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -14,10 +14,8 @@
 #include <linux/namei.h>
 #include "misc.h"
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "rcu-string.h"
@@ -468,39 +466,39 @@ static noinline struct btrfs_fs_devices *find_fsid(
 
 static int
 btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
-		      int flush, struct bdev_handle **bdev_handle,
+		      int flush, struct file **bdev_file,
 		      struct btrfs_super_block **disk_super)
 {
 	struct block_device *bdev;
 	int ret;
 
-	*bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL);
+	*bdev_file = bdev_file_open_by_path(device_path, flags, holder, NULL);
 
-	if (IS_ERR(*bdev_handle)) {
-		ret = PTR_ERR(*bdev_handle);
+	if (IS_ERR(*bdev_file)) {
+		ret = PTR_ERR(*bdev_file);
 		goto error;
 	}
-	bdev = (*bdev_handle)->bdev;
+	bdev = file_bdev(*bdev_file);
 
 	if (flush)
 		sync_blockdev(bdev);
 	ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE);
 	if (ret) {
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 	invalidate_bdev(bdev);
 	*disk_super = btrfs_read_dev_super(bdev);
 	if (IS_ERR(*disk_super)) {
 		ret = PTR_ERR(*disk_super);
-		bdev_release(*bdev_handle);
+		fput(*bdev_file);
 		goto error;
 	}
 
 	return 0;
 
 error:
-	*bdev_handle = NULL;
+	*bdev_file = NULL;
 	return ret;
 }
 
@@ -643,7 +641,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 			struct btrfs_device *device, blk_mode_t flags,
 			void *holder)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct btrfs_super_block *disk_super;
 	u64 devid;
 	int ret;
@@ -654,7 +652,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		return -EINVAL;
 
 	ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret)
 		return ret;
 
@@ -678,20 +676,20 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 		clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		fs_devices->seeding = true;
 	} else {
-		if (bdev_read_only(bdev_handle->bdev))
+		if (bdev_read_only(file_bdev(bdev_file)))
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 		else
 			set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	}
 
-	if (!bdev_nonrot(bdev_handle->bdev))
+	if (!bdev_nonrot(file_bdev(bdev_file)))
 		fs_devices->rotating = true;
 
-	if (bdev_max_discard_sectors(bdev_handle->bdev))
+	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
 		fs_devices->discardable = true;
 
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 
 	fs_devices->open_devices++;
@@ -706,7 +704,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 
 error_free_page:
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return -EINVAL;
 }
@@ -769,8 +767,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (same_fsid_diff_dev) {
 			generate_random_uuid(fs_devices->fsid);
 			fs_devices->temp_fsid = true;
-			pr_info("BTRFS: device %s using temp-fsid %pU\n",
-				path, fs_devices->fsid);
+		pr_info("BTRFS: device %s (%d:%d) using temp-fsid %pU\n",
+				path, MAJOR(path_devt), MINOR(path_devt),
+				fs_devices->fsid);
 		}
 
 		mutex_lock(&fs_devices->device_list_mutex);
@@ -799,8 +798,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (fs_devices->opened) {
 			btrfs_err(NULL,
-"device %s belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
-				  path, fs_devices->fsid, current->comm,
+"device %s (%d:%d) belongs to fsid %pU, and the fs is already mounted, scanned by %s (%d)",
+				  path, MAJOR(path_devt), MINOR(path_devt),
+				  fs_devices->fsid, current->comm,
 				  task_pid_nr(current));
 			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
@@ -826,13 +826,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 		if (disk_super->label[0])
 			pr_info(
-	"BTRFS: device label %s devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device label %s devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->label, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 		else
 			pr_info(
-	"BTRFS: device fsid %pU devid %llu transid %llu %s scanned by %s (%d)\n",
+"BTRFS: device fsid %pU devid %llu transid %llu %s (%d:%d) scanned by %s (%d)\n",
 				disk_super->fsid, devid, found_transid, path,
+				MAJOR(path_devt), MINOR(path_devt),
 				current->comm, task_pid_nr(current));
 
 	} else if (!device->name || strcmp(device->name->str, path)) {
@@ -1015,10 +1017,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
 		if (device->devid == BTRFS_DEV_REPLACE_DEVID)
 			continue;
 
-		if (device->bdev_handle) {
-			bdev_release(device->bdev_handle);
+		if (device->bdev_file) {
+			fput(device->bdev_file);
 			device->bdev = NULL;
-			device->bdev_handle = NULL;
+			device->bdev_file = NULL;
 			fs_devices->open_devices--;
 		}
 		if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
@@ -1063,7 +1065,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 		invalidate_bdev(device->bdev);
 	}
 
-	bdev_release(device->bdev_handle);
+	fput(device->bdev_file);
 }
 
 static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1316,7 +1318,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	u64 bytenr, bytenr_orig;
 	int ret;
 
@@ -1339,18 +1341,18 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev_handle = bdev_open_by_path(path, flags, NULL, NULL);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = bdev_file_open_by_path(path, flags, NULL, NULL);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
 	bytenr_orig = btrfs_sb_offset(0);
-	ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr);
+	ret = btrfs_sb_log_location_bdev(file_bdev(bdev_file), 0, READ, &bytenr);
 	if (ret) {
 		device = ERR_PTR(ret);
 		goto error_bdev_put;
 	}
 
-	disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr,
+	disk_super = btrfs_read_disk_super(file_bdev(bdev_file), bytenr,
 					   bytenr_orig);
 	if (IS_ERR(disk_super)) {
 		device = ERR_CAST(disk_super);
@@ -1368,7 +1370,8 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
 		else
 			btrfs_free_stale_devices(devt, NULL);
 
-		pr_debug("BTRFS: skip registering single non-seed device %s\n", path);
+	pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n",
+			path, MAJOR(devt), MINOR(devt));
 		device = NULL;
 		goto free_disk_super;
 	}
@@ -1381,7 +1384,7 @@ free_disk_super:
 	btrfs_release_disk_super(disk_super);
 
 error_bdev_put:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	return device;
 }
@@ -1403,7 +1406,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start,
 
 		if (in_range(physical_start, *start, len) ||
 		    in_range(*start, physical_start,
-			     physical_end - physical_start)) {
+			     physical_end + 1 - physical_start)) {
 			*start = physical_end + 1;
 			return true;
 		}
@@ -2032,11 +2035,10 @@ static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
 			copy_num, ret);
 }
 
-void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
-			       struct block_device *bdev,
-			       const char *device_path)
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct btrfs_device *device)
 {
 	int copy_num;
+	struct block_device *bdev = device->bdev;
 
 	if (!bdev)
 		return;
@@ -2052,12 +2054,12 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 	/* Update ctime/mtime for device path for libblkid */
-	update_dev_time(device_path);
+	update_dev_time(device->name->str);
 }
 
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle)
+		    struct file **bdev_file)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
@@ -2166,7 +2168,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 
 	btrfs_assign_next_active_device(device, NULL);
 
-	if (device->bdev_handle) {
+	if (device->bdev_file) {
 		cur_devices->open_devices--;
 		/* remove sysfs entry */
 		btrfs_sysfs_remove_device(device);
@@ -2182,20 +2184,19 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 	 * free the device.
 	 *
 	 * We cannot call btrfs_close_bdev() here because we're holding the sb
-	 * write lock, and bdev_release() will pull in the ->open_mutex on
-	 * the block device and it's dependencies.  Instead just flush the
-	 * device and let the caller do the final bdev_release.
+	 * write lock, and fput() on the block device will pull in the
+	 * ->open_mutex on the block device and it's dependencies.  Instead
+	 *  just flush the device and let the caller do the final bdev_release.
 	 */
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
-		btrfs_scratch_superblocks(fs_info, device->bdev,
-					  device->name->str);
+		btrfs_scratch_superblocks(fs_info, device);
 		if (device->bdev) {
 			sync_blockdev(device->bdev);
 			invalidate_bdev(device->bdev);
 		}
 	}
 
-	*bdev_handle = device->bdev_handle;
+	*bdev_file = device->bdev_file;
 	synchronize_rcu();
 	btrfs_free_device(device);
 
@@ -2301,8 +2302,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev->bdev,
-				  tgtdev->name->str);
+	btrfs_scratch_superblocks(tgtdev->fs_info, tgtdev);
 
 	btrfs_close_bdev(tgtdev);
 	synchronize_rcu();
@@ -2332,7 +2332,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 				 const char *path)
 {
 	struct btrfs_super_block *disk_super;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int ret;
 
 	if (!path || !path[0])
@@ -2350,7 +2350,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
-				    &bdev_handle, &disk_super);
+				    &bdev_file, &disk_super);
 	if (ret) {
 		btrfs_put_dev_args_from_path(args);
 		return ret;
@@ -2363,7 +2363,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 	else
 		memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
 	btrfs_release_disk_super(disk_super);
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return 0;
 }
 
@@ -2583,7 +2583,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct super_block *sb = fs_info->sb;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_fs_devices *seed_devices = NULL;
@@ -2596,12 +2596,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
-	bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(device_path, BLK_OPEN_WRITE,
 					fs_info->bdev_holder, NULL);
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
 
-	if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) {
+	if (!btrfs_check_device_zone_type(fs_info, file_bdev(bdev_file))) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -2613,11 +2613,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		locked = true;
 	}
 
-	sync_blockdev(bdev_handle->bdev);
+	sync_blockdev(file_bdev(bdev_file));
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
-		if (device->bdev == bdev_handle->bdev) {
+		if (device->bdev == file_bdev(bdev_file)) {
 			ret = -EEXIST;
 			rcu_read_unlock();
 			goto error;
@@ -2633,8 +2633,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 
 	device->fs_info = fs_info;
-	device->bdev_handle = bdev_handle;
-	device->bdev = bdev_handle->bdev;
+	device->bdev_file = bdev_file;
+	device->bdev = file_bdev(bdev_file);
 	ret = lookup_bdev(device_path, &device->devt);
 	if (ret)
 		goto error_free_device;
@@ -2817,7 +2817,7 @@ error_free_zone:
 error_free_device:
 	btrfs_free_device(device);
 error:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	if (locked) {
 		mutex_unlock(&uuid_mutex);
 		up_write(&sb->s_umount);
@@ -3393,7 +3393,17 @@ again:
 			mutex_unlock(&fs_info->reclaim_bgs_lock);
 			goto error;
 		}
-		BUG_ON(ret == 0); /* Corruption */
+		if (ret == 0) {
+			/*
+			 * On the first search we would find chunk tree with
+			 * offset -1, which is not possible. On subsequent
+			 * loops this would find an existing item on an invalid
+			 * offset (one less than the previous one, wrong
+			 * alignment and size).
+			 */
+			ret = -EUCLEAN;
+			goto error;
+		}
 
 		ret = btrfs_previous_item(chunk_root, path, key.objectid,
 					  key.type);
@@ -3480,6 +3490,44 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
+					   const struct btrfs_disk_balance_args *disk)
+{
+	memset(cpu, 0, sizeof(*cpu));
+
+	cpu->profiles = le64_to_cpu(disk->profiles);
+	cpu->usage = le64_to_cpu(disk->usage);
+	cpu->devid = le64_to_cpu(disk->devid);
+	cpu->pstart = le64_to_cpu(disk->pstart);
+	cpu->pend = le64_to_cpu(disk->pend);
+	cpu->vstart = le64_to_cpu(disk->vstart);
+	cpu->vend = le64_to_cpu(disk->vend);
+	cpu->target = le64_to_cpu(disk->target);
+	cpu->flags = le64_to_cpu(disk->flags);
+	cpu->limit = le64_to_cpu(disk->limit);
+	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
+	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
+}
+
+static void btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
+					   const struct btrfs_balance_args *cpu)
+{
+	memset(disk, 0, sizeof(*disk));
+
+	disk->profiles = cpu_to_le64(cpu->profiles);
+	disk->usage = cpu_to_le64(cpu->usage);
+	disk->devid = cpu_to_le64(cpu->devid);
+	disk->pstart = cpu_to_le64(cpu->pstart);
+	disk->pend = cpu_to_le64(cpu->pend);
+	disk->vstart = cpu_to_le64(cpu->vstart);
+	disk->vend = cpu_to_le64(cpu->vend);
+	disk->target = cpu_to_le64(cpu->target);
+	disk->flags = cpu_to_le64(cpu->flags);
+	disk->limit = cpu_to_le64(cpu->limit);
+	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
+	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
+}
+
 static int insert_balance_item(struct btrfs_fs_info *fs_info,
 			       struct btrfs_balance_control *bctl)
 {
@@ -3624,7 +3672,7 @@ static void reset_balance_state(struct btrfs_fs_info *fs_info)
 	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 	int ret;
 
-	BUG_ON(!fs_info->balance_ctl);
+	ASSERT(fs_info->balance_ctl);
 
 	spin_lock(&fs_info->balance_lock);
 	fs_info->balance_ctl = NULL;
@@ -5944,6 +5992,7 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 			    struct btrfs_chunk_map *map, int first,
 			    int dev_replace_is_ongoing)
 {
+	const enum btrfs_read_policy policy = READ_ONCE(fs_info->fs_devices->read_policy);
 	int i;
 	int num_stripes;
 	int preferred_mirror;
@@ -5958,13 +6007,12 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	else
 		num_stripes = map->num_stripes;
 
-	switch (fs_info->fs_devices->read_policy) {
+	switch (policy) {
 	default:
 		/* Shouldn't happen, just warn and use pid instead of failing */
-		btrfs_warn_rl(fs_info,
-			      "unknown read_policy type %u, reset to pid",
-			      fs_info->fs_devices->read_policy);
-		fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID;
+		btrfs_warn_rl(fs_info, "unknown read_policy type %u, reset to pid",
+			      policy);
+		WRITE_ONCE(fs_info->fs_devices->read_policy, BTRFS_READ_POLICY_PID);
 		fallthrough;
 	case BTRFS_READ_POLICY_PID:
 		preferred_mirror = first + (current->pid % num_stripes);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 53f87f398da7..93854609a4d5 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -6,13 +6,28 @@
 #ifndef BTRFS_VOLUMES_H
 #define BTRFS_VOLUMES_H
 
+#include <linux/blk_types.h>
+#include <linux/sizes.h>
+#include <linux/atomic.h>
 #include <linux/sort.h>
-#include <linux/btrfs.h>
-#include "async-thread.h"
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/log2.h>
+#include <linux/kobject.h>
+#include <linux/refcount.h>
+#include <linux/completion.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs.h>
 #include "messages.h"
-#include "tree-checker.h"
 #include "rcu-string.h"
 
+struct block_device;
+struct bdev_handle;
+struct btrfs_fs_info;
+struct btrfs_block_group;
+struct btrfs_trans_handle;
+struct btrfs_zoned_device_info;
+
 #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
 
 extern struct mutex uuid_mutex;
@@ -77,7 +92,7 @@ enum btrfs_raid_types {
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 #define BTRFS_DEV_STATE_NO_READA	(5)
 
-struct btrfs_zoned_device_info;
+struct btrfs_fs_devices;
 
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
@@ -90,7 +105,7 @@ struct btrfs_device {
 
 	u64 generation;
 
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 
 	struct btrfs_zoned_device_info *zone_info;
@@ -276,6 +291,25 @@ enum btrfs_read_policy {
 	BTRFS_NR_READ_POLICY,
 };
 
+#ifdef CONFIG_BTRFS_DEBUG
+/*
+ * Checksum mode - offload it to workqueues or do it synchronously in
+ * btrfs_submit_chunk().
+ */
+enum btrfs_offload_csum_mode {
+	/*
+	 * Choose offloading checksum or do it synchronously automatically.
+	 * Do it synchronously if the checksum is fast, or offload to workqueues
+	 * otherwise.
+	 */
+	BTRFS_OFFLOAD_CSUM_AUTO,
+	/* Always offload checksum to workqueues. */
+	BTRFS_OFFLOAD_CSUM_FORCE_ON,
+	/* Never offload checksum to workqueues. */
+	BTRFS_OFFLOAD_CSUM_FORCE_OFF,
+};
+#endif
+
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 
@@ -380,6 +414,11 @@ struct btrfs_fs_devices {
 
 	/* Policy used to read the mirrored stripes. */
 	enum btrfs_read_policy read_policy;
+
+#ifdef CONFIG_BTRFS_DEBUG
+	/* Checksum mode - offload it or do it synchronously. */
+	enum btrfs_offload_csum_mode offload_csum_mode;
+#endif
 };
 
 #define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info)	\
@@ -557,8 +596,6 @@ static inline void btrfs_free_chunk_map(struct btrfs_chunk_map *map)
 	}
 }
 
-struct btrfs_balance_args;
-struct btrfs_balance_progress;
 struct btrfs_balance_control {
 	struct btrfs_balance_args data;
 	struct btrfs_balance_args meta;
@@ -661,7 +698,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
 		    struct btrfs_dev_lookup_args *args,
-		    struct bdev_handle **bdev_handle);
+		    struct file **bdev_file);
 void __exit btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
@@ -780,9 +817,7 @@ void btrfs_commit_device_sizes(struct btrfs_transaction *trans);
 struct list_head * __attribute_const__ btrfs_get_fs_uuids(void);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
-void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
-			       struct block_device *bdev,
-			       const char *device_path);
+void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct btrfs_device *device);
 
 enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags);
 int btrfs_bg_type_to_factor(u64 flags);
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 118118ca3e1d..b9376ea258ff 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -6,7 +6,11 @@
 #ifndef BTRFS_XATTR_H
 #define BTRFS_XATTR_H
 
-#include <linux/xattr.h>
+struct dentry;
+struct inode;
+struct qstr;
+struct xattr_handler;
+struct btrfs_trans_handle;
 
 extern const struct xattr_handler * const btrfs_xattr_handlers[];
 
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 8da66ea699e8..e5b3f2003896 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -398,7 +398,7 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in,
 
 out:
 	if (unlikely(to_copy != destlen)) {
-		pr_warn_ratelimited("BTRFS: infalte failed, decompressed=%lu expected=%zu\n",
+		pr_warn_ratelimited("BTRFS: inflate failed, decompressed=%lu expected=%zu\n",
 					to_copy, destlen);
 		ret = -EIO;
 	} else {
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 168af9d000d1..5a3d5ec75c5a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -12,10 +12,8 @@
 #include "rcu-string.h"
 #include "disk-io.h"
 #include "block-group.h"
-#include "transaction.h"
 #include "dev-replace.h"
 #include "space-info.h"
-#include "super.h"
 #include "fs.h"
 #include "accessors.h"
 #include "bio.h"
@@ -824,11 +822,14 @@ static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
 			reset = &zones[1];
 
 		if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
+			unsigned int nofs_flags;
+
 			ASSERT(sb_zone_is_full(reset));
 
+			nofs_flags = memalloc_nofs_save();
 			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-					       reset->start, reset->len,
-					       GFP_NOFS);
+					       reset->start, reset->len);
+			memalloc_nofs_restore(nofs_flags);
 			if (ret)
 				return ret;
 
@@ -974,11 +975,14 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 			 * explicit ZONE_FINISH is not necessary.
 			 */
 			if (zone->wp != zone->start + zone->capacity) {
+				unsigned int nofs_flags;
 				int ret;
 
+				nofs_flags = memalloc_nofs_save();
 				ret = blkdev_zone_mgmt(device->bdev,
 						REQ_OP_ZONE_FINISH, zone->start,
-						zone->len, GFP_NOFS);
+						zone->len);
+				memalloc_nofs_restore(nofs_flags);
 				if (ret)
 					return ret;
 			}
@@ -996,11 +1000,13 @@ int btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
 
 int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 {
+	unsigned int nofs_flags;
 	sector_t zone_sectors;
 	sector_t nr_sectors;
 	u8 zone_sectors_shift;
 	u32 sb_zone;
 	u32 nr_zones;
+	int ret;
 
 	zone_sectors = bdev_zone_sectors(bdev);
 	zone_sectors_shift = ilog2(zone_sectors);
@@ -1011,9 +1017,12 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
 	if (sb_zone + 1 >= nr_zones)
 		return -ENOENT;
 
-	return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-				zone_start_sector(sb_zone, bdev),
-				zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
+	nofs_flags = memalloc_nofs_save();
+	ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+			       zone_start_sector(sb_zone, bdev),
+			       zone_sectors * BTRFS_NR_SB_LOG_ZONES);
+	memalloc_nofs_restore(nofs_flags);
+	return ret;
 }
 
 /*
@@ -1124,12 +1133,14 @@ static void btrfs_dev_clear_active_zone(struct btrfs_device *device, u64 pos)
 int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 			    u64 length, u64 *bytes)
 {
+	unsigned int nofs_flags;
 	int ret;
 
 	*bytes = 0;
+	nofs_flags = memalloc_nofs_save();
 	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET,
-			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT,
-			       GFP_NOFS);
+			       physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT);
+	memalloc_nofs_restore(nofs_flags);
 	if (ret)
 		return ret;
 
@@ -1639,6 +1650,15 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
+	/* Reject non SINGLE data profiles without RST */
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) &&
+	    (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
+	    !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
@@ -1670,6 +1690,7 @@ out:
 	}
 	bitmap_free(active);
 	kfree(zone_info);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }
@@ -2234,14 +2255,16 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 		struct btrfs_device *device = map->stripes[i].dev;
 		const u64 physical = map->stripes[i].physical;
 		struct btrfs_zoned_device_info *zinfo = device->zone_info;
+		unsigned int nofs_flags;
 
 		if (zinfo->max_active_zones == 0)
 			continue;
 
+		nofs_flags = memalloc_nofs_save();
 		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
 				       physical >> SECTOR_SHIFT,
-				       zinfo->zone_size >> SECTOR_SHIFT,
-				       GFP_NOFS);
+				       zinfo->zone_size >> SECTOR_SHIFT);
+		memalloc_nofs_restore(nofs_flags);
 
 		if (ret)
 			return ret;
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index f573bda496fb..77c4321e331f 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -4,12 +4,27 @@
 #define BTRFS_ZONED_H
 
 #include <linux/types.h>
+#include <linux/atomic.h>
 #include <linux/blkdev.h>
+#include <linux/blkzoned.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include "messages.h"
 #include "volumes.h"
 #include "disk-io.h"
 #include "block-group.h"
 #include "btrfs_inode.h"
+#include "fs.h"
+
+struct block_device;
+struct extent_buffer;
+struct btrfs_bio;
+struct btrfs_ordered_extent;
+struct btrfs_fs_info;
+struct btrfs_space_info;
+struct btrfs_eb_write_context;
+struct btrfs_fs_devices;
 
 #define BTRFS_DEFAULT_RECLAIM_THRESH           			(75)
 
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 0d66db8bc1d4..92b3744b819b 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -18,8 +18,9 @@
 #include <linux/slab.h>
 #include <linux/zstd.h>
 #include "misc.h"
+#include "fs.h"
 #include "compression.h"
-#include "ctree.h"
+#include "super.h"
 
 #define ZSTD_BTRFS_MAX_WINDOWLOG 17
 #define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
@@ -618,80 +619,48 @@ done:
 }
 
 int zstd_decompress(struct list_head *ws, const u8 *data_in,
-		struct page *dest_page, unsigned long start_byte, size_t srclen,
+		struct page *dest_page, unsigned long dest_pgoff, size_t srclen,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb);
+	const u32 sectorsize = fs_info->sectorsize;
 	zstd_dstream *stream;
 	int ret = 0;
-	size_t ret2;
-	unsigned long total_out = 0;
-	unsigned long pg_offset = 0;
+	unsigned long to_copy = 0;
 
 	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
 		pr_warn("BTRFS: zstd_init_dstream failed\n");
-		ret = -EIO;
 		goto finish;
 	}
 
-	destlen = min_t(size_t, destlen, PAGE_SIZE);
-
 	workspace->in_buf.src = data_in;
 	workspace->in_buf.pos = 0;
 	workspace->in_buf.size = srclen;
 
 	workspace->out_buf.dst = workspace->buf;
 	workspace->out_buf.pos = 0;
-	workspace->out_buf.size = PAGE_SIZE;
-
-	ret2 = 1;
-	while (pg_offset < destlen
-	       && workspace->in_buf.pos < workspace->in_buf.size) {
-		unsigned long buf_start;
-		unsigned long buf_offset;
-		unsigned long bytes;
-
-		/* Check if the frame is over and we still need more input */
-		if (ret2 == 0) {
-			pr_debug("BTRFS: zstd_decompress_stream ended early\n");
-			ret = -EIO;
-			goto finish;
-		}
-		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
-				&workspace->in_buf);
-		if (zstd_is_error(ret2)) {
-			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
-					zstd_get_error_code(ret2));
-			ret = -EIO;
-			goto finish;
-		}
-
-		buf_start = total_out;
-		total_out += workspace->out_buf.pos;
-		workspace->out_buf.pos = 0;
-
-		if (total_out <= start_byte)
-			continue;
-
-		if (total_out > start_byte && buf_start < start_byte)
-			buf_offset = start_byte - buf_start;
-		else
-			buf_offset = 0;
-
-		bytes = min_t(unsigned long, destlen - pg_offset,
-				workspace->out_buf.size - buf_offset);
-
-		memcpy_to_page(dest_page, pg_offset,
-			       workspace->out_buf.dst + buf_offset, bytes);
-
-		pg_offset += bytes;
+	workspace->out_buf.size = sectorsize;
+
+	/*
+	 * Since both input and output buffers should not exceed one sector,
+	 * one call should end the decompression.
+	 */
+	ret = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf);
+	if (zstd_is_error(ret)) {
+		pr_warn_ratelimited("BTRFS: zstd_decompress_stream return %d\n",
+				    zstd_get_error_code(ret));
+		goto finish;
 	}
-	ret = 0;
+	to_copy = workspace->out_buf.pos;
+	memcpy_to_page(dest_page, dest_pgoff, workspace->out_buf.dst, to_copy);
 finish:
-	if (pg_offset < destlen) {
-		memzero_page(dest_page, pg_offset, destlen - pg_offset);
+	/* Error or early end. */
+	if (unlikely(to_copy < destlen)) {
+		ret = -EIO;
+		memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy);
 	}
 	return ret;
 }
diff --git a/fs/buffer.c b/fs/buffer.c
index d3bcf601d3e5..4f73d23c2c46 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -55,7 +55,7 @@
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
-			  struct writeback_control *wbc);
+			  enum rw_hint hint, struct writeback_control *wbc);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
@@ -464,7 +464,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  * a successful fsync().  For example, ext2 indirect blocks need to be
  * written back and waited upon before fsync() returns.
  *
- * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
+ * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(),
  * inode_has_buffers() and invalidate_inode_buffers() are provided for the
  * management of a list of dependent buffers at ->i_mapping->i_private_list.
  *
@@ -1889,7 +1889,8 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+				      inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1944,7 +1945,8 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+				      inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -2756,6 +2758,7 @@ static void end_bio_bh_io_sync(struct bio *bio)
 }
 
 static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
+			  enum rw_hint write_hint,
 			  struct writeback_control *wbc)
 {
 	const enum req_op op = opf & REQ_OP_MASK;
@@ -2783,6 +2786,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_write_hint = write_hint;
 
 	__bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
 
@@ -2802,7 +2806,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 
 void submit_bh(blk_opf_t opf, struct buffer_head *bh)
 {
-	submit_bh_wbc(opf, bh, NULL);
+	submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
@@ -3121,12 +3125,8 @@ void __init buffer_init(void)
 	unsigned long nrpages;
 	int ret;
 
-	bh_cachep = kmem_cache_create("buffer_head",
-			sizeof(struct buffer_head), 0,
-				(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
-				SLAB_MEM_SPREAD),
-				NULL);
-
+	bh_cachep = KMEM_CACHE(buffer_head,
+				SLAB_RECLAIM_ACCOUNT|SLAB_PANIC);
 	/*
 	 * Limit the bh occupancy to 10% of ZONE_NORMAL
 	 */
diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c
index 7077f72e6f47..f449f7340aad 100644
--- a/fs/cachefiles/cache.c
+++ b/fs/cachefiles/cache.c
@@ -168,6 +168,8 @@ error_unsupported:
 	dput(root);
 error_open_root:
 	cachefiles_end_secure(cache, saved_cred);
+	put_cred(cache->cache_cred);
+	cache->cache_cred = NULL;
 error_getsec:
 	fscache_relinquish_cache(cache_cookie);
 	cache->cache = NULL;
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 3f24905f4066..6465e2574230 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
 	cachefiles_put_directory(cache->graveyard);
 	cachefiles_put_directory(cache->store);
 	mntput(cache->mnt);
+	put_cred(cache->cache_cred);
 
 	kfree(cache->rootdirname);
 	kfree(cache->secctx);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 9c02f328c966..7fb4aae97412 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1452,7 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
 	if (flushing & CEPH_CAP_XATTR_EXCL) {
 		arg->old_xattr_buf = __ceph_build_xattrs_blob(ci);
 		arg->xattr_version = ci->i_xattrs.version;
-		arg->xattr_buf = ci->i_xattrs.blob;
+		arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob);
 	} else {
 		arg->xattr_buf = NULL;
 		arg->old_xattr_buf = NULL;
@@ -1553,6 +1553,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
 	encode_cap_msg(msg, arg);
 	ceph_con_send(&arg->session->s_con, msg);
 	ceph_buffer_put(arg->old_xattr_buf);
+	ceph_buffer_put(arg->xattr_buf);
 	if (arg->wake)
 		wake_up_all(&ci->i_cap_wq);
 }
@@ -2155,6 +2156,30 @@ retry:
 		      ceph_cap_string(cap->implemented),
 		      ceph_cap_string(revoking));
 
+		/* completed revocation? going down and there are no caps? */
+		if (revoking) {
+			if ((revoking & cap_used) == 0) {
+				doutc(cl, "completed revocation of %s\n",
+				      ceph_cap_string(cap->implemented & ~cap->issued));
+				goto ack;
+			}
+
+			/*
+			 * If the "i_wrbuffer_ref" was increased by mmap or generic
+			 * cache write just before the ceph_check_caps() is called,
+			 * the Fb capability revoking will fail this time. Then we
+			 * must wait for the BDI's delayed work to flush the dirty
+			 * pages and to release the "i_wrbuffer_ref", which will cost
+			 * at most 5 seconds. That means the MDS needs to wait at
+			 * most 5 seconds to finished the Fb capability's revocation.
+			 *
+			 * Let's queue a writeback for it.
+			 */
+			if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
+			    (revoking & CEPH_CAP_FILE_BUFFER))
+				queue_writeback = true;
+		}
+
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
 			/* request larger max_size from MDS? */
@@ -2182,30 +2207,6 @@ retry:
 			}
 		}
 
-		/* completed revocation? going down and there are no caps? */
-		if (revoking) {
-			if ((revoking & cap_used) == 0) {
-				doutc(cl, "completed revocation of %s\n",
-				      ceph_cap_string(cap->implemented & ~cap->issued));
-				goto ack;
-			}
-
-			/*
-			 * If the "i_wrbuffer_ref" was increased by mmap or generic
-			 * cache write just before the ceph_check_caps() is called,
-			 * the Fb capability revoking will fail this time. Then we
-			 * must wait for the BDI's delayed work to flush the dirty
-			 * pages and to release the "i_wrbuffer_ref", which will cost
-			 * at most 5 seconds. That means the MDS needs to wait at
-			 * most 5 seconds to finished the Fb capability's revocation.
-			 *
-			 * Let's queue a writeback for it.
-			 */
-			if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
-			    (revoking & CEPH_CAP_FILE_BUFFER))
-				queue_writeback = true;
-		}
-
 		/* want more caps from mds? */
 		if (want & ~cap->mds_wanted) {
 			if (want & ~(cap->mds_wanted | cap->issued))
@@ -3215,7 +3216,6 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
 
 enum put_cap_refs_mode {
 	PUT_CAP_REFS_SYNC = 0,
-	PUT_CAP_REFS_NO_CHECK,
 	PUT_CAP_REFS_ASYNC,
 };
 
@@ -3331,11 +3331,6 @@ void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had)
 	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_ASYNC);
 }
 
-void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
-{
-	__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_NO_CHECK);
-}
-
 /*
  * Release @nr WRBUFFER refs on dirty pages for the given @snapc snap
  * context.  Adjust per-snap dirty page accounting as appropriate.
@@ -4777,7 +4772,22 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
 		if (__ceph_caps_dirty(ci)) {
 			struct ceph_mds_client *mdsc =
 				ceph_inode_to_fs_client(inode)->mdsc;
-			__cap_delay_requeue_front(mdsc, ci);
+
+			doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode,
+			      ceph_vinop(inode));
+			spin_lock(&mdsc->cap_unlink_delay_lock);
+			ci->i_ceph_flags |= CEPH_I_FLUSH;
+			if (!list_empty(&ci->i_cap_delay_list))
+				list_del_init(&ci->i_cap_delay_list);
+			list_add_tail(&ci->i_cap_delay_list,
+				      &mdsc->cap_unlink_delay_list);
+			spin_unlock(&mdsc->cap_unlink_delay_lock);
+
+			/*
+			 * Fire the work immediately, because the MDS maybe
+			 * waiting for caps release.
+			 */
+			ceph_queue_cap_unlink_work(mdsc);
 		}
 	}
 	spin_unlock(&ci->i_ceph_lock);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0c25d326afc4..7b2e77517f23 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,6 +78,8 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+
 	if (!S_ISLNK(*mode)) {
 		err = ceph_pre_init_acls(dir, mode, as_ctx);
 		if (err < 0)
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index e07ad29ff8b9..ebf4ac0055dd 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -33,7 +33,7 @@ void __init ceph_flock_init(void)
 
 static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
 {
-	struct inode *inode = file_inode(dst->fl_file);
+	struct inode *inode = file_inode(dst->c.flc_file);
 	atomic_inc(&ceph_inode(inode)->i_filelock_ref);
 	dst->fl_u.ceph.inode = igrab(inode);
 }
@@ -110,17 +110,18 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 	else
 		length = fl->fl_end - fl->fl_start + 1;
 
-	owner = secure_addr(fl->fl_owner);
+	owner = secure_addr(fl->c.flc_owner);
 
 	doutc(cl, "rule: %d, op: %d, owner: %llx, pid: %llu, "
 		    "start: %llu, length: %llu, wait: %d, type: %d\n",
-		    (int)lock_type, (int)operation, owner, (u64)fl->fl_pid,
-		    fl->fl_start, length, wait, fl->fl_type);
+		    (int)lock_type, (int)operation, owner,
+		    (u64) fl->c.flc_pid,
+		    fl->fl_start, length, wait, fl->c.flc_type);
 
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
 	req->r_args.filelock_change.owner = cpu_to_le64(owner);
-	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
+	req->r_args.filelock_change.pid = cpu_to_le64((u64) fl->c.flc_pid);
 	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
 	req->r_args.filelock_change.length = cpu_to_le64(length);
 	req->r_args.filelock_change.wait = wait;
@@ -130,13 +131,13 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 		err = ceph_mdsc_wait_request(mdsc, req, wait ?
 					ceph_lock_wait_for_completion : NULL);
 	if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
-		fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+		fl->c.flc_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
-			fl->fl_type = F_RDLCK;
+			fl->c.flc_type = F_RDLCK;
 		else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
-			fl->fl_type = F_WRLCK;
+			fl->c.flc_type = F_WRLCK;
 		else
-			fl->fl_type = F_UNLCK;
+			fl->c.flc_type = F_UNLCK;
 
 		fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
 		length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
@@ -150,8 +151,8 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 	ceph_mdsc_put_request(req);
 	doutc(cl, "rule: %d, op: %d, pid: %llu, start: %llu, "
 	      "length: %llu, wait: %d, type: %d, err code %d\n",
-	      (int)lock_type, (int)operation, (u64)fl->fl_pid,
-	      fl->fl_start, length, wait, fl->fl_type, err);
+	      (int)lock_type, (int)operation, (u64) fl->c.flc_pid,
+	      fl->fl_start, length, wait, fl->c.flc_type, err);
 	return err;
 }
 
@@ -227,10 +228,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 static int try_unlock_file(struct file *file, struct file_lock *fl)
 {
 	int err;
-	unsigned int orig_flags = fl->fl_flags;
-	fl->fl_flags |= FL_EXISTS;
+	unsigned int orig_flags = fl->c.flc_flags;
+	fl->c.flc_flags |= FL_EXISTS;
 	err = locks_lock_file_wait(file, fl);
-	fl->fl_flags = orig_flags;
+	fl->c.flc_flags = orig_flags;
 	if (err == -ENOENT) {
 		if (!(orig_flags & FL_EXISTS))
 			err = 0;
@@ -253,13 +254,13 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	u8 wait = 0;
 	u8 lock_cmd;
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	doutc(cl, "fl_owner: %p\n", fl->fl_owner);
+	doutc(cl, "fl_owner: %p\n", fl->c.flc_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
 	if (IS_GETLK(cmd))
@@ -273,19 +274,19 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	if (err < 0) {
-		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type)
+		if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl))
 			posix_lock_file(file, fl, NULL);
 		return err;
 	}
 
-	if (F_RDLCK == fl->fl_type)
+	if (lock_is_read(fl))
 		lock_cmd = CEPH_LOCK_SHARED;
-	else if (F_WRLCK == fl->fl_type)
+	else if (lock_is_write(fl))
 		lock_cmd = CEPH_LOCK_EXCL;
 	else
 		lock_cmd = CEPH_LOCK_UNLOCK;
 
-	if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type) {
+	if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl)) {
 		err = try_unlock_file(file, fl);
 		if (err <= 0)
 			return err;
@@ -293,7 +294,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl);
 	if (!err) {
-		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->fl_type) {
+		if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->c.flc_type) {
 			doutc(cl, "locking locally\n");
 			err = posix_lock_file(file, fl, NULL);
 			if (err) {
@@ -319,13 +320,13 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	u8 wait = 0;
 	u8 lock_cmd;
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	doutc(cl, "fl_file: %p\n", fl->fl_file);
+	doutc(cl, "fl_file: %p\n", fl->c.flc_file);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) {
@@ -333,7 +334,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	if (err < 0) {
-		if (F_UNLCK == fl->fl_type)
+		if (lock_is_unlock(fl))
 			locks_lock_file_wait(file, fl);
 		return err;
 	}
@@ -341,14 +342,14 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (IS_SETLKW(cmd))
 		wait = 1;
 
-	if (F_RDLCK == fl->fl_type)
+	if (lock_is_read(fl))
 		lock_cmd = CEPH_LOCK_SHARED;
-	else if (F_WRLCK == fl->fl_type)
+	else if (lock_is_write(fl))
 		lock_cmd = CEPH_LOCK_EXCL;
 	else
 		lock_cmd = CEPH_LOCK_UNLOCK;
 
-	if (F_UNLCK == fl->fl_type) {
+	if (lock_is_unlock(fl)) {
 		err = try_unlock_file(file, fl);
 		if (err <= 0)
 			return err;
@@ -356,7 +357,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
 				inode, lock_cmd, wait, fl);
-	if (!err && F_UNLCK != fl->fl_type) {
+	if (!err && F_UNLCK != fl->c.flc_type) {
 		err = locks_lock_file_wait(file, fl);
 		if (err) {
 			ceph_lock_message(CEPH_LOCK_FLOCK,
@@ -385,9 +386,9 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 	ctx = locks_inode_context(inode);
 	if (ctx) {
 		spin_lock(&ctx->flc_lock);
-		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
+		for_each_file_lock(lock, &ctx->flc_posix)
 			++(*fcntl_count);
-		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
+		for_each_file_lock(lock, &ctx->flc_flock)
 			++(*flock_count);
 		spin_unlock(&ctx->flc_lock);
 	}
@@ -408,10 +409,10 @@ static int lock_to_ceph_filelock(struct inode *inode,
 	cephlock->start = cpu_to_le64(lock->fl_start);
 	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
 	cephlock->client = cpu_to_le64(0);
-	cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
-	cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
+	cephlock->pid = cpu_to_le64((u64) lock->c.flc_pid);
+	cephlock->owner = cpu_to_le64(secure_addr(lock->c.flc_owner));
 
-	switch (lock->fl_type) {
+	switch (lock->c.flc_type) {
 	case F_RDLCK:
 		cephlock->type = CEPH_LOCK_SHARED;
 		break;
@@ -422,7 +423,8 @@ static int lock_to_ceph_filelock(struct inode *inode,
 		cephlock->type = CEPH_LOCK_UNLOCK;
 		break;
 	default:
-		doutc(cl, "Have unknown lock type %d\n", lock->fl_type);
+		doutc(cl, "Have unknown lock type %d\n",
+		      lock->c.flc_type);
 		err = -EINVAL;
 	}
 
@@ -453,7 +455,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
+	for_each_file_lock(lock, &ctx->flc_posix) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
@@ -464,7 +466,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 			goto fail;
 		++l;
 	}
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	for_each_file_lock(lock, &ctx->flc_flock) {
 		++seen_flock;
 		if (seen_flock > num_flock_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 548d1de379f3..3ab9c268a8bb 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1089,7 +1089,7 @@ void ceph_mdsc_release_request(struct kref *kref)
 	struct ceph_mds_request *req = container_of(kref,
 						    struct ceph_mds_request,
 						    r_kref);
-	ceph_mdsc_release_dir_caps_no_check(req);
+	ceph_mdsc_release_dir_caps_async(req);
 	destroy_reply_info(&req->r_reply_info);
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
@@ -2484,6 +2484,50 @@ void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr)
 	}
 }
 
+void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc)
+{
+	struct ceph_client *cl = mdsc->fsc->client;
+	if (mdsc->stopping)
+		return;
+
+        if (queue_work(mdsc->fsc->cap_wq, &mdsc->cap_unlink_work)) {
+                doutc(cl, "caps unlink work queued\n");
+        } else {
+                doutc(cl, "failed to queue caps unlink work\n");
+        }
+}
+
+static void ceph_cap_unlink_work(struct work_struct *work)
+{
+	struct ceph_mds_client *mdsc =
+		container_of(work, struct ceph_mds_client, cap_unlink_work);
+	struct ceph_client *cl = mdsc->fsc->client;
+
+	doutc(cl, "begin\n");
+	spin_lock(&mdsc->cap_unlink_delay_lock);
+	while (!list_empty(&mdsc->cap_unlink_delay_list)) {
+		struct ceph_inode_info *ci;
+		struct inode *inode;
+
+		ci = list_first_entry(&mdsc->cap_unlink_delay_list,
+				      struct ceph_inode_info,
+				      i_cap_delay_list);
+		list_del_init(&ci->i_cap_delay_list);
+
+		inode = igrab(&ci->netfs.inode);
+		if (inode) {
+			spin_unlock(&mdsc->cap_unlink_delay_lock);
+			doutc(cl, "on %p %llx.%llx\n", inode,
+			      ceph_vinop(inode));
+			ceph_check_caps(ci, CHECK_CAPS_FLUSH);
+			iput(inode);
+			spin_lock(&mdsc->cap_unlink_delay_lock);
+		}
+	}
+	spin_unlock(&mdsc->cap_unlink_delay_lock);
+	doutc(cl, "done\n");
+}
+
 /*
  * requests
  */
@@ -4261,7 +4305,7 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
 	}
 }
 
-void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
+void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req)
 {
 	struct ceph_client *cl = req->r_mdsc->fsc->client;
 	int dcaps;
@@ -4269,8 +4313,7 @@ void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
 	dcaps = xchg(&req->r_dir_caps, 0);
 	if (dcaps) {
 		doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
-		ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
-						dcaps);
+		ceph_put_cap_refs_async(ceph_inode(req->r_parent), dcaps);
 	}
 }
 
@@ -4306,7 +4349,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 		if (req->r_session->s_mds != session->s_mds)
 			continue;
 
-		ceph_mdsc_release_dir_caps_no_check(req);
+		ceph_mdsc_release_dir_caps_async(req);
 
 		__send_request(session, req, true);
 	}
@@ -5360,6 +5403,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	INIT_LIST_HEAD(&mdsc->cap_delay_list);
 	INIT_LIST_HEAD(&mdsc->cap_wait_list);
 	spin_lock_init(&mdsc->cap_delay_lock);
+	INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
+	spin_lock_init(&mdsc->cap_unlink_delay_lock);
 	INIT_LIST_HEAD(&mdsc->snap_flush_list);
 	spin_lock_init(&mdsc->snap_flush_lock);
 	mdsc->last_cap_flush_tid = 1;
@@ -5368,6 +5413,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	spin_lock_init(&mdsc->cap_dirty_lock);
 	init_waitqueue_head(&mdsc->cap_flushing_wq);
 	INIT_WORK(&mdsc->cap_reclaim_work, ceph_cap_reclaim_work);
+	INIT_WORK(&mdsc->cap_unlink_work, ceph_cap_unlink_work);
 	err = ceph_metric_init(&mdsc->metric);
 	if (err)
 		goto err_mdsmap;
@@ -5641,6 +5687,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 	ceph_cleanup_global_and_empty_realms(mdsc);
 
 	cancel_work_sync(&mdsc->cap_reclaim_work);
+	cancel_work_sync(&mdsc->cap_unlink_work);
 	cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
 
 	doutc(cl, "done\n");
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 2e6ddaa13d72..03f8ff00874f 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -462,6 +462,8 @@ struct ceph_mds_client {
 	unsigned long    last_renew_caps;  /* last time we renewed our caps */
 	struct list_head cap_delay_list;   /* caps with delayed release */
 	spinlock_t       cap_delay_lock;   /* protects cap_delay_list */
+	struct list_head cap_unlink_delay_list;  /* caps with delayed release for unlink */
+	spinlock_t       cap_unlink_delay_lock;  /* protects cap_unlink_delay_list */
 	struct list_head snap_flush_list;  /* cap_snaps ready to flush */
 	spinlock_t       snap_flush_lock;
 
@@ -475,6 +477,8 @@ struct ceph_mds_client {
 	struct work_struct cap_reclaim_work;
 	atomic_t	   cap_reclaim_pending;
 
+	struct work_struct cap_unlink_work;
+
 	/*
 	 * Cap reservations
 	 *
@@ -552,7 +556,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 				struct inode *dir,
 				struct ceph_mds_request *req);
 extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
-extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
+extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req);
 static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
 {
 	kref_get(&req->r_kref);
@@ -574,6 +578,7 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
 				    struct ceph_mds_session *session);
 extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
 extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
+extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc);
 extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
 				     int (*cb)(struct inode *, int mds, void *),
 				     void *arg);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index fae97c25ce58..8109aba66e02 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -380,10 +380,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p,
 		ceph_decode_skip_8(p, end, bad_ext);
 		/* required_client_features */
 		ceph_decode_skip_set(p, end, 64, bad_ext);
+		/* bal_rank_mask */
+		ceph_decode_skip_string(p, end, bad_ext);
+	}
+	if (mdsmap_ev >= 18) {
 		ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext);
-	} else {
-		/* This forces the usage of the (sync) SETXATTR Op */
-		m->m_max_xattr_size = 0;
 	}
 bad_ext:
 	doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n",
diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h
index 89f1931f1ba6..1f2171dd01bf 100644
--- a/fs/ceph/mdsmap.h
+++ b/fs/ceph/mdsmap.h
@@ -27,7 +27,11 @@ struct ceph_mdsmap {
 	u32 m_session_timeout;          /* seconds */
 	u32 m_session_autoclose;        /* seconds */
 	u64 m_max_file_size;
-	u64 m_max_xattr_size;		/* maximum size for xattrs blob */
+	/*
+	 * maximum size for xattrs blob.
+	 * Zeroed by default to force the usage of the (sync) SETXATTR Op.
+	 */
+	u64 m_max_xattr_size;
 	u32 m_max_mds;			/* expected up:active mds number */
 	u32 m_num_active_mds;		/* actual up:active mds number */
 	u32 possible_max_rank;		/* possible max rank index */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b06e2bc86221..b63b4cd9b5b6 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1255,8 +1255,6 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
 extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
 extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
 extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had);
-extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
-					    int had);
 extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void __ceph_remove_capsnap(struct inode *inode,
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 0c7c2528791e..a50356c541f6 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -24,6 +24,8 @@
 #include <linux/pid_namespace.h>
 #include <linux/uaccess.h>
 #include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/vmalloc.h>
 
 #include <linux/coda.h>
@@ -87,10 +89,10 @@ void coda_destroy_inodecache(void)
 	kmem_cache_destroy(coda_inode_cachep);
 }
 
-static int coda_remount(struct super_block *sb, int *flags, char *data)
+static int coda_reconfigure(struct fs_context *fc)
 {
-	sync_filesystem(sb);
-	*flags |= SB_NOATIME;
+	sync_filesystem(fc->root->d_sb);
+	fc->sb_flags |= SB_NOATIME;
 	return 0;
 }
 
@@ -102,78 +104,102 @@ static const struct super_operations coda_super_operations =
 	.evict_inode	= coda_evict_inode,
 	.put_super	= coda_put_super,
 	.statfs		= coda_statfs,
-	.remount_fs	= coda_remount,
 };
 
-static int get_device_index(struct coda_mount_data *data)
+struct coda_fs_context {
+	int	idx;
+};
+
+enum {
+	Opt_fd,
+};
+
+static const struct fs_parameter_spec coda_param_specs[] = {
+	fsparam_fd	("fd",	Opt_fd),
+	{}
+};
+
+static int coda_parse_fd(struct fs_context *fc, int fd)
 {
+	struct coda_fs_context *ctx = fc->fs_private;
 	struct fd f;
 	struct inode *inode;
 	int idx;
 
-	if (data == NULL) {
-		pr_warn("%s: Bad mount data\n", __func__);
-		return -1;
-	}
-
-	if (data->version != CODA_MOUNT_VERSION) {
-		pr_warn("%s: Bad mount version\n", __func__);
-		return -1;
-	}
-
-	f = fdget(data->fd);
+	f = fdget(fd);
 	if (!f.file)
-		goto Ebadf;
+		return -EBADF;
 	inode = file_inode(f.file);
 	if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) {
 		fdput(f);
-		goto Ebadf;
+		return invalf(fc, "code: Not coda psdev");
 	}
 
 	idx = iminor(inode);
 	fdput(f);
 
-	if (idx < 0 || idx >= MAX_CODADEVS) {
-		pr_warn("%s: Bad minor number\n", __func__);
-		return -1;
+	if (idx < 0 || idx >= MAX_CODADEVS)
+		return invalf(fc, "coda: Bad minor number");
+	ctx->idx = idx;
+	return 0;
+}
+
+static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, coda_param_specs, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_fd:
+		return coda_parse_fd(fc, result.uint_32);
 	}
 
-	return idx;
-Ebadf:
-	pr_warn("%s: Bad file\n", __func__);
-	return -1;
+	return 0;
+}
+
+/*
+ * Parse coda's binary mount data form.  We ignore any errors and go with index
+ * 0 if we get one for backward compatibility.
+ */
+static int coda_parse_monolithic(struct fs_context *fc, void *_data)
+{
+	struct coda_mount_data *data = _data;
+
+	if (!data)
+		return invalf(fc, "coda: Bad mount data");
+
+	if (data->version != CODA_MOUNT_VERSION)
+		return invalf(fc, "coda: Bad mount version");
+
+	coda_parse_fd(fc, data->fd);
+	return 0;
 }
 
-static int coda_fill_super(struct super_block *sb, void *data, int silent)
+static int coda_fill_super(struct super_block *sb, struct fs_context *fc)
 {
+	struct coda_fs_context *ctx = fc->fs_private;
 	struct inode *root = NULL;
 	struct venus_comm *vc;
 	struct CodaFid fid;
 	int error;
-	int idx;
-
-	if (task_active_pid_ns(current) != &init_pid_ns)
-		return -EINVAL;
-
-	idx = get_device_index((struct coda_mount_data *) data);
 
-	/* Ignore errors in data, for backward compatibility */
-	if(idx == -1)
-		idx = 0;
-	
-	pr_info("%s: device index: %i\n", __func__,  idx);
+	infof(fc, "coda: device index: %i\n", ctx->idx);
 
-	vc = &coda_comms[idx];
+	vc = &coda_comms[ctx->idx];
 	mutex_lock(&vc->vc_mutex);
 
 	if (!vc->vc_inuse) {
-		pr_warn("%s: No pseudo device\n", __func__);
+		errorf(fc, "coda: No pseudo device");
 		error = -EINVAL;
 		goto unlock_out;
 	}
 
 	if (vc->vc_sb) {
-		pr_warn("%s: Device already mounted\n", __func__);
+		errorf(fc, "coda: Device already mounted");
 		error = -EBUSY;
 		goto unlock_out;
 	}
@@ -313,18 +339,45 @@ static int coda_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0; 
 }
 
-/* init_coda: used by filesystems.c to register coda */
+static int coda_get_tree(struct fs_context *fc)
+{
+	if (task_active_pid_ns(current) != &init_pid_ns)
+		return -EINVAL;
 
-static struct dentry *coda_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+	return get_tree_nodev(fc, coda_fill_super);
+}
+
+static void coda_free_fc(struct fs_context *fc)
 {
-	return mount_nodev(fs_type, flags, data, coda_fill_super);
+	kfree(fc->fs_private);
+}
+
+static const struct fs_context_operations coda_context_ops = {
+	.free		= coda_free_fc,
+	.parse_param	= coda_parse_param,
+	.parse_monolithic = coda_parse_monolithic,
+	.get_tree	= coda_get_tree,
+	.reconfigure	= coda_reconfigure,
+};
+
+static int coda_init_fs_context(struct fs_context *fc)
+{
+	struct coda_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct coda_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	fc->fs_private = ctx;
+	fc->ops = &coda_context_ops;
+	return 0;
 }
 
 struct file_system_type coda_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "coda",
-	.mount		= coda_mount,
+	.init_fs_context = coda_init_fs_context,
+	.parameters	= coda_param_specs,
 	.kill_sb	= kill_anon_super,
 	.fs_flags	= FS_BINARY_MOUNTDATA,
 };
diff --git a/fs/coredump.c b/fs/coredump.c
index f258c17c1841..be6403b4b14b 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -872,6 +872,9 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	loff_t pos;
 	ssize_t n;
 
+	if (!page)
+		return 0;
+
 	if (cprm->to_skip) {
 		if (!__dump_skip(cprm, cprm->to_skip))
 			return 0;
@@ -884,7 +887,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	pos = file->f_pos;
 	bvec_set_page(&bvec, page, PAGE_SIZE, 0);
 	iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE);
-	iov_iter_set_copy_mc(&iter);
 	n = __kernel_write_iter(cprm->file, &iter, &pos);
 	if (n != PAGE_SIZE)
 		return 0;
@@ -895,10 +897,44 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	return 1;
 }
 
+/*
+ * If we might get machine checks from kernel accesses during the
+ * core dump, let's get those errors early rather than during the
+ * IO. This is not performance-critical enough to warrant having
+ * all the machine check logic in the iovec paths.
+ */
+#ifdef copy_mc_to_kernel
+
+#define dump_page_alloc() alloc_page(GFP_KERNEL)
+#define dump_page_free(x) __free_page(x)
+static struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+	void *buf = kmap_local_page(src);
+	size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE);
+	kunmap_local(buf);
+	return left ? NULL : dst;
+}
+
+#else
+
+/* We just want to return non-NULL; it's never used. */
+#define dump_page_alloc() ERR_PTR(-EINVAL)
+#define dump_page_free(x) ((void)(x))
+static inline struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+	return src;
+}
+#endif
+
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len)
 {
 	unsigned long addr;
+	struct page *dump_page;
+
+	dump_page = dump_page_alloc();
+	if (!dump_page)
+		return 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
@@ -912,14 +948,17 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		 */
 		page = get_dump_page(addr);
 		if (page) {
-			int stop = !dump_emit_page(cprm, page);
+			int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page));
 			put_page(page);
-			if (stop)
+			if (stop) {
+				dump_page_free(dump_page);
 				return 0;
+			}
 		} else {
 			dump_skip(cprm, PAGE_SIZE);
 		}
 	}
+	dump_page_free(dump_page);
 	return 1;
 }
 #endif
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 60dbfa0f8805..39e75131fd5a 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb)
 		sb->s_mtd = NULL;
 	} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 	kfree(sbi);
 }
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 7b3fc189593a..0ad52fbe51c9 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -74,13 +74,7 @@ struct fscrypt_nokey_name {
 
 static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
 {
-	if (str->len == 1 && str->name[0] == '.')
-		return true;
-
-	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
-		return true;
-
-	return false;
+	return is_dot_dotdot(str->name, str->len);
 }
 
 /**
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 1892356cf924..8371e4e1f596 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -222,16 +222,19 @@ struct fscrypt_inode_info {
 	struct fscrypt_prepared_key ci_enc_key;
 
 	/* True if ci_enc_key should be freed when this struct is freed */
-	bool ci_owns_key;
+	u8 ci_owns_key : 1;
 
 #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
 	/*
 	 * True if this inode will use inline encryption (blk-crypto) instead of
 	 * the traditional filesystem-layer encryption.
 	 */
-	bool ci_inlinecrypt;
+	u8 ci_inlinecrypt : 1;
 #endif
 
+	/* True if ci_dirhash_key is initialized */
+	u8 ci_dirhash_key_initialized : 1;
+
 	/*
 	 * log2 of the data unit size (granularity of contents encryption) of
 	 * this file.  This is computable from ci_policy and ci_inode but is
@@ -242,6 +245,9 @@ struct fscrypt_inode_info {
 	/* Cached value: log2 of number of data units per FS block */
 	u8 ci_data_units_per_block_bits;
 
+	/* Hashed inode number.  Only set for IV_INO_LBLK_32 */
+	u32 ci_hashed_ino;
+
 	/*
 	 * Encryption mode used for this inode.  It corresponds to either the
 	 * contents or filenames encryption mode, depending on the inode type.
@@ -276,16 +282,12 @@ struct fscrypt_inode_info {
 	 * the plaintext filenames -- currently just casefolded directories.
 	 */
 	siphash_key_t ci_dirhash_key;
-	bool ci_dirhash_key_initialized;
 
 	/* The encryption policy used by this inode */
 	union fscrypt_policy ci_policy;
 
 	/* This inode's nonce, copied from the fscrypt_context */
 	u8 ci_nonce[FSCRYPT_FILE_NONCE_SIZE];
-
-	/* Hashed inode number.  Only set for IV_INO_LBLK_32 */
-	u32 ci_hashed_ino;
 };
 
 typedef enum {
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 52504dd478d3..104771c3d3f6 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -102,11 +102,8 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 	if (err && err != -ENOENT)
 		return err;
 
-	if (fname->is_nokey_name) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_NOKEY_NAME;
-		spin_unlock(&dentry->d_lock);
-	}
+	fscrypt_prepare_dentry(dentry, fname->is_nokey_name);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
@@ -131,12 +128,10 @@ EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup);
 int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry)
 {
 	int err = fscrypt_get_encryption_info(dir, true);
+	bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir));
+
+	fscrypt_prepare_dentry(dentry, is_nokey_name);
 
-	if (!err && !fscrypt_has_encryption_key(dir)) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_NOKEY_NAME;
-		spin_unlock(&dentry->d_lock);
-	}
 	return err;
 }
 EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial);
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 0edf0b58daa7..6681a71625f0 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -74,8 +74,12 @@ void fscrypt_put_master_key(struct fscrypt_master_key *mk)
 	 * that concurrent keyring lookups can no longer find it.
 	 */
 	WARN_ON_ONCE(refcount_read(&mk->mk_active_refs) != 0);
-	key_put(mk->mk_users);
-	mk->mk_users = NULL;
+	if (mk->mk_users) {
+		/* Clear the keyring so the quota gets released right away. */
+		keyring_clear(mk->mk_users);
+		key_put(mk->mk_users);
+		mk->mk_users = NULL;
+	}
 	call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key);
 }
 
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index d71f7c799e79..b4fe01ea4bd4 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -23,7 +23,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_256_XTS,
 	},
 	[FSCRYPT_MODE_AES_256_CTS] = {
-		.friendly_name = "AES-256-CTS-CBC",
+		.friendly_name = "AES-256-CBC-CTS",
 		.cipher_str = "cts(cbc(aes))",
 		.keysize = 32,
 		.security_strength = 32,
@@ -38,7 +38,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.blk_crypto_mode = BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV,
 	},
 	[FSCRYPT_MODE_AES_128_CTS] = {
-		.friendly_name = "AES-128-CTS-CBC",
+		.friendly_name = "AES-128-CBC-CTS",
 		.cipher_str = "cts(cbc(aes))",
 		.keysize = 16,
 		.security_strength = 16,
@@ -53,7 +53,7 @@ struct fscrypt_mode fscrypt_modes[] = {
 		.blk_crypto_mode = BLK_ENCRYPTION_MODE_SM4_XTS,
 	},
 	[FSCRYPT_MODE_SM4_CTS] = {
-		.friendly_name = "SM4-CTS-CBC",
+		.friendly_name = "SM4-CBC-CTS",
 		.cipher_str = "cts(cbc(sm4))",
 		.keysize = 16,
 		.security_strength = 16,
@@ -687,7 +687,7 @@ int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported)
 /**
  * fscrypt_prepare_new_inode() - prepare to create a new inode in a directory
  * @dir: a possibly-encrypted directory
- * @inode: the new inode.  ->i_mode must be set already.
+ * @inode: the new inode.  ->i_mode and ->i_blkbits must be set already.
  *	   ->i_ino doesn't need to be set yet.
  * @encrypt_ret: (output) set to %true if the new inode will be encrypted
  *
@@ -717,6 +717,9 @@ int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 	if (IS_ERR(policy))
 		return PTR_ERR(policy);
 
+	if (WARN_ON_ONCE(inode->i_blkbits == 0))
+		return -EINVAL;
+
 	if (WARN_ON_ONCE(inode->i_mode == 0))
 		return -EINVAL;
 
diff --git a/fs/dcache.c b/fs/dcache.c
index b813528fb147..71a8e943a0fa 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3061,7 +3061,10 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
 		if (d_unhashed(dentry) || !dentry->d_inode)
 			return D_WALK_SKIP;
 
-		dentry->d_lockref.count--;
+		if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
+			dentry->d_flags |= DCACHE_GENOCIDE;
+			dentry->d_lockref.count--;
+		}
 	}
 	return D_WALK_CONTINUE;
 }
@@ -3136,7 +3139,7 @@ static void __init dcache_init(void)
 	 * of the dcache.
 	 */
 	dentry_cache = KMEM_CACHE_USERCOPY(dentry,
-		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
 		d_iname);
 
 	/* Hash may have been set up in dcache_init_early */
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 60456263a338..62c97ff9e852 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -410,6 +410,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 		bio->bi_end_io = dio_bio_end_io;
 	if (dio->is_pinned)
 		bio_set_flag(bio, BIO_PAGE_PINNED);
+	bio->bi_write_hint = file_inode(dio->iocb->ki_filp)->i_write_hint;
+
 	sdio->bio = bio;
 	sdio->logical_offset_in_bio = sdio->cur_page_fs_offset;
 }
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index d814c5121367..9ca83ef70ed1 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -138,14 +138,14 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_LOCK;
-	op->info.pid		= fl->fl_pid;
-	op->info.ex		= (fl->fl_type == F_WRLCK);
-	op->info.wait		= !!(fl->fl_flags & FL_SLEEP);
+	op->info.pid		= fl->c.flc_pid;
+	op->info.ex		= lock_is_write(fl);
+	op->info.wait		= !!(fl->c.flc_flags & FL_SLEEP);
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 	/* async handling */
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
 		op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
@@ -258,7 +258,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	}
 
 	/* got fs lock; bookkeep locally as well: */
-	flc->fl_flags &= ~FL_SLEEP;
+	flc->c.flc_flags &= ~FL_SLEEP;
 	if (posix_lock_file(file, flc, NULL)) {
 		/*
 		 * This can only happen in the case of kmalloc() failure.
@@ -291,7 +291,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	struct dlm_ls *ls;
 	struct plock_op *op;
 	int rv;
-	unsigned char fl_flags = fl->fl_flags;
+	unsigned char saved_flags = fl->c.flc_flags;
 
 	ls = dlm_find_lockspace_local(lockspace);
 	if (!ls)
@@ -304,7 +304,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	/* cause the vfs unlock to return ENOENT if lock is not found */
-	fl->fl_flags |= FL_EXISTS;
+	fl->c.flc_flags |= FL_EXISTS;
 
 	rv = locks_lock_file_wait(file, fl);
 	if (rv == -ENOENT) {
@@ -317,14 +317,14 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_UNLOCK;
-	op->info.pid		= fl->fl_pid;
+	op->info.pid		= fl->c.flc_pid;
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 
-	if (fl->fl_flags & FL_CLOSE) {
+	if (fl->c.flc_flags & FL_CLOSE) {
 		op->info.flags |= DLM_PLOCK_FL_CLOSE;
 		send_op(op);
 		rv = 0;
@@ -345,7 +345,7 @@ out_free:
 	dlm_release_plock_op(op);
 out:
 	dlm_put_lockspace(ls);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = saved_flags;
 	return rv;
 }
 EXPORT_SYMBOL_GPL(dlm_posix_unlock);
@@ -375,14 +375,14 @@ int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		return -EINVAL;
 
 	memset(&info, 0, sizeof(info));
-	info.pid = fl->fl_pid;
-	info.ex = (fl->fl_type == F_WRLCK);
+	info.pid = fl->c.flc_pid;
+	info.ex = lock_is_write(fl);
 	info.fsid = ls->ls_global_id;
 	dlm_put_lockspace(ls);
 	info.number = number;
 	info.start = fl->fl_start;
 	info.end = fl->fl_end;
-	info.owner = (__u64)(long)fl->fl_owner;
+	info.owner = (__u64)(long) fl->c.flc_owner;
 
 	rv = do_lock_cancel(&info);
 	switch (rv) {
@@ -437,13 +437,13 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	}
 
 	op->info.optype		= DLM_PLOCK_OP_GET;
-	op->info.pid		= fl->fl_pid;
-	op->info.ex		= (fl->fl_type == F_WRLCK);
+	op->info.pid		= fl->c.flc_pid;
+	op->info.ex		= lock_is_write(fl);
 	op->info.fsid		= ls->ls_global_id;
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
-	op->info.owner = (__u64)(long)fl->fl_owner;
+	op->info.owner = (__u64)(long) fl->c.flc_owner;
 
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
@@ -455,16 +455,16 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 
 	rv = op->info.rv;
 
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 	if (rv == -ENOENT)
 		rv = 0;
 	else if (rv > 0) {
 		locks_init_lock(fl);
-		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
-		fl->fl_flags = FL_POSIX;
-		fl->fl_pid = op->info.pid;
+		fl->c.flc_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+		fl->c.flc_flags = FL_POSIX;
+		fl->c.flc_pid = op->info.pid;
 		if (op->info.nodeid != dlm_our_nodeid())
-			fl->fl_pid = -fl->fl_pid;
+			fl->c.flc_pid = -fl->c.flc_pid;
 		fl->fl_start = op->info.start;
 		fl->fl_end = op->info.end;
 		rv = 0;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 03bd55069d86..2fe0f3af1a08 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1949,16 +1949,6 @@ out:
 	return rc;
 }
 
-static bool is_dot_dotdot(const char *name, size_t name_size)
-{
-	if (name_size == 1 && name[0] == '.')
-		return true;
-	else if (name_size == 2 && name[0] == '.' && name[1] == '.')
-		return true;
-
-	return false;
-}
-
 /**
  * ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext
  * @plaintext_name: The plaintext name
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index 169252e6dc46..f7206158ee81 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -38,7 +38,7 @@ struct efivar_entry {
 
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			    struct list_head *),
-		void *data, bool duplicates, struct list_head *head);
+		void *data, struct list_head *head);
 
 int efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
 void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head);
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 6038dd39367a..bb14462f6d99 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -343,12 +343,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	err = efivar_init(efivarfs_callback, (void *)sb, true,
-			  &sfi->efivarfs_list);
-	if (err)
-		efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL);
-
-	return err;
+	return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list);
 }
 
 static int efivarfs_get_tree(struct fs_context *fc)
diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c
index 114ff0fd4e55..4d722af1014f 100644
--- a/fs/efivarfs/vars.c
+++ b/fs/efivarfs/vars.c
@@ -361,7 +361,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
  * efivar_init - build the initial list of EFI variables
  * @func: callback function to invoke for every variable
  * @data: function-specific data to pass to @func
- * @duplicates: error if we encounter duplicates on @head?
  * @head: initialised head of variable list
  *
  * Get every EFI variable from the firmware and invoke @func. @func
@@ -371,9 +370,9 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
  */
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			    struct list_head *),
-		void *data, bool duplicates, struct list_head *head)
+		void *data, struct list_head *head)
 {
-	unsigned long variable_name_size = 1024;
+	unsigned long variable_name_size = 512;
 	efi_char16_t *variable_name;
 	efi_status_t status;
 	efi_guid_t vendor_guid;
@@ -390,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 		goto free;
 
 	/*
-	 * Per EFI spec, the maximum storage allocated for both
-	 * the variable name and variable data is 1024 bytes.
+	 * A small set of old UEFI implementations reject sizes
+	 * above a certain threshold, the lowest seen in the wild
+	 * is 512.
 	 */
 
 	do {
-		variable_name_size = 1024;
+		variable_name_size = 512;
 
 		status = efivar_get_next_variable(&variable_name_size,
 						  variable_name,
@@ -413,8 +413,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			 * we'll ever see a different variable name,
 			 * and may end up looping here forever.
 			 */
-			if (duplicates &&
-			    variable_is_present(variable_name, &vendor_guid,
+			if (variable_is_present(variable_name, &vendor_guid,
 						head)) {
 				dup_variable_bug(variable_name, &vendor_guid,
 						 variable_name_size);
@@ -432,9 +431,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *,
 			break;
 		case EFI_NOT_FOUND:
 			break;
+		case EFI_BUFFER_TOO_SMALL:
+			pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n",
+				variable_name_size);
+			status = EFI_NOT_FOUND;
+			break;
 		default:
-			printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n",
-				status);
+			pr_warn("efivars: get_next_variable: status=%lx\n", status);
 			status = EFI_NOT_FOUND;
 			break;
 		}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index f17fdac76b2e..e4421c10caeb 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -14,19 +14,14 @@
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/blkdev.h>
-
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include "efs.h"
 #include <linux/efs_vh.h>
 #include <linux/efs_fs_sb.h>
 
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf);
-static int efs_fill_super(struct super_block *s, void *d, int silent);
-
-static struct dentry *efs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, efs_fill_super);
-}
+static int efs_init_fs_context(struct fs_context *fc);
 
 static void efs_kill_sb(struct super_block *s)
 {
@@ -35,15 +30,6 @@ static void efs_kill_sb(struct super_block *s)
 	kfree(sbi);
 }
 
-static struct file_system_type efs_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "efs",
-	.mount		= efs_mount,
-	.kill_sb	= efs_kill_sb,
-	.fs_flags	= FS_REQUIRES_DEV,
-};
-MODULE_ALIAS_FS("efs");
-
 static struct pt_types sgi_pt_types[] = {
 	{0x00,		"SGI vh"},
 	{0x01,		"SGI trkrepl"},
@@ -63,6 +49,27 @@ static struct pt_types sgi_pt_types[] = {
 	{0,		NULL}
 };
 
+enum {
+	Opt_explicit_open,
+};
+
+static const struct fs_parameter_spec efs_param_spec[] = {
+	fsparam_flag    ("explicit-open",       Opt_explicit_open),
+	{}
+};
+
+/*
+ * File system definition and registration.
+ */
+static struct file_system_type efs_fs_type = {
+	.owner			= THIS_MODULE,
+	.name			= "efs",
+	.kill_sb		= efs_kill_sb,
+	.fs_flags		= FS_REQUIRES_DEV,
+	.init_fs_context	= efs_init_fs_context,
+	.parameters		= efs_param_spec,
+};
+MODULE_ALIAS_FS("efs");
 
 static struct kmem_cache * efs_inode_cachep;
 
@@ -91,8 +98,8 @@ static int __init init_inodecache(void)
 {
 	efs_inode_cachep = kmem_cache_create("efs_inode_cache",
 				sizeof(struct efs_inode_info), 0,
-				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
-				SLAB_ACCOUNT, init_once);
+				SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
+				init_once);
 	if (efs_inode_cachep == NULL)
 		return -ENOMEM;
 	return 0;
@@ -108,18 +115,10 @@ static void destroy_inodecache(void)
 	kmem_cache_destroy(efs_inode_cachep);
 }
 
-static int efs_remount(struct super_block *sb, int *flags, char *data)
-{
-	sync_filesystem(sb);
-	*flags |= SB_RDONLY;
-	return 0;
-}
-
 static const struct super_operations efs_superblock_operations = {
 	.alloc_inode	= efs_alloc_inode,
 	.free_inode	= efs_free_inode,
 	.statfs		= efs_statfs,
-	.remount_fs	= efs_remount,
 };
 
 static const struct export_operations efs_export_ops = {
@@ -249,26 +248,26 @@ static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) {
 	return 0;    
 }
 
-static int efs_fill_super(struct super_block *s, void *d, int silent)
+static int efs_fill_super(struct super_block *s, struct fs_context *fc)
 {
 	struct efs_sb_info *sb;
 	struct buffer_head *bh;
 	struct inode *root;
 
- 	sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL);
+	sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL);
 	if (!sb)
 		return -ENOMEM;
 	s->s_fs_info = sb;
 	s->s_time_min = 0;
 	s->s_time_max = U32_MAX;
- 
+
 	s->s_magic		= EFS_SUPER_MAGIC;
 	if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
 		pr_err("device does not support %d byte blocks\n",
 			EFS_BLOCKSIZE);
 		return -EINVAL;
 	}
-  
+
 	/* read the vh (volume header) block */
 	bh = sb_bread(s, 0);
 
@@ -294,7 +293,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
 		pr_err("cannot read superblock\n");
 		return -EIO;
 	}
-		
+
 	if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) {
 #ifdef DEBUG
 		pr_warn("invalid superblock at block %u\n",
@@ -328,6 +327,61 @@ static int efs_fill_super(struct super_block *s, void *d, int silent)
 	return 0;
 }
 
+static void efs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->fs_private);
+}
+
+static int efs_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, efs_fill_super);
+}
+
+static int efs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	int token;
+	struct fs_parse_result result;
+
+	token = fs_parse(fc, efs_param_spec, param, &result);
+	if (token < 0)
+		return token;
+	return 0;
+}
+
+static int efs_reconfigure(struct fs_context *fc)
+{
+	sync_filesystem(fc->root->d_sb);
+
+	return 0;
+}
+
+struct efs_context {
+	unsigned long s_mount_opts;
+};
+
+static const struct fs_context_operations efs_context_opts = {
+	.parse_param	= efs_parse_param,
+	.get_tree	= efs_get_tree,
+	.reconfigure	= efs_reconfigure,
+	.free		= efs_free_fc,
+};
+
+/*
+ * Set up the filesystem mount context.
+ */
+static int efs_init_fs_context(struct fs_context *fc)
+{
+	struct efs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct efs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	fc->fs_private = ctx;
+	fc->ops = &efs_context_opts;
+
+	return 0;
+}
+
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
 	struct super_block *sb = dentry->d_sb;
 	struct efs_sb_info *sbi = SUPER_INFO(sb);
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 279933e007d2..333587ba6183 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -11,13 +11,12 @@
 struct z_erofs_decompress_req {
 	struct super_block *sb;
 	struct page **in, **out;
-
 	unsigned short pageofs_in, pageofs_out;
 	unsigned int inputsize, outputsize;
 
-	/* indicate the algorithm will be used for decompression */
-	unsigned int alg;
+	unsigned int alg;       /* the algorithm for decompression */
 	bool inplace_io, partial_decoding, fillgaps;
+	gfp_t gfp;      /* allocation flags for extra temporary buffers */
 };
 
 struct z_erofs_decompressor {
@@ -82,13 +81,6 @@ static inline bool z_erofs_put_shortlivedpage(struct page **pagepool,
 	return true;
 }
 
-#define MNGD_MAPPING(sbi)	((sbi)->managed_cache->i_mapping)
-static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi,
-					 struct page *page)
-{
-	return page->mapping == MNGD_MAPPING(sbi);
-}
-
 int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
 			 unsigned int padbufsize);
 extern const struct z_erofs_decompressor erofs_decompressors[];
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index c98aeda8abb2..52524bd9698b 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -220,7 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			up_read(&devs->rwsem);
 			return 0;
 		}
-		map->m_bdev = dif->bdev_handle ? dif->bdev_handle->bdev : NULL;
+		map->m_bdev = dif->bdev_file ? file_bdev(dif->bdev_file) : NULL;
 		map->m_daxdev = dif->dax_dev;
 		map->m_dax_part_off = dif->dax_part_off;
 		map->m_fscache = dif->fscache;
@@ -238,8 +238,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 			if (map->m_pa >= startoff &&
 			    map->m_pa < startoff + length) {
 				map->m_pa -= startoff;
-				map->m_bdev = dif->bdev_handle ?
-					      dif->bdev_handle->bdev : NULL;
+				map->m_bdev = dif->bdev_file ?
+					      file_bdev(dif->bdev_file) : NULL;
 				map->m_daxdev = dif->dax_dev;
 				map->m_dax_part_off = dif->dax_part_off;
 				map->m_fscache = dif->fscache;
@@ -447,5 +447,6 @@ const struct file_operations erofs_file_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= erofs_file_read_iter,
 	.mmap		= erofs_file_mmap,
+	.get_unmapped_area = thp_get_unmapped_area,
 	.splice_read	= filemap_splice_read,
 };
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 072ef6a66823..2ec9b2bb628d 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -111,8 +111,9 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
 			victim = availables[--top];
 			get_page(victim);
 		} else {
-			victim = erofs_allocpage(pagepool,
-						 GFP_KERNEL | __GFP_NOFAIL);
+			victim = erofs_allocpage(pagepool, rq->gfp);
+			if (!victim)
+				return -ENOMEM;
 			set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE);
 		}
 		rq->out[i] = victim;
@@ -322,7 +323,8 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 	unsigned int cur = 0, ni = 0, no, pi, po, insz, cnt;
 	u8 *kin;
 
-	DBG_BUGON(rq->outputsize > rq->inputsize);
+	if (rq->outputsize > rq->inputsize)
+		return -EOPNOTSUPP;
 	if (rq->alg == Z_EROFS_COMPRESSION_INTERLACED) {
 		cur = bs - (rq->pageofs_out & (bs - 1));
 		pi = (rq->pageofs_in + rq->inputsize - cur) & ~PAGE_MASK;
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index 4a64a9c91dd3..81e65c453ef0 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -95,7 +95,7 @@ int z_erofs_load_deflate_config(struct super_block *sb,
 }
 
 int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
-			       struct page **pagepool)
+			       struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -158,8 +158,12 @@ again:
 			strm->z.avail_out = min_t(u32, outsz, PAGE_SIZE - pofs);
 			outsz -= strm->z.avail_out;
 			if (!rq->out[no]) {
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					kout = NULL;
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -208,11 +212,11 @@ again:
 
 			if (rq->out[no] != rq->in[j])
 				continue;
-
-			DBG_BUGON(erofs_page_is_managed(EROFS_SB(sb),
-							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -230,7 +234,7 @@ again:
 			break;
 		}
 	}
-
+failed:
 	if (zlib_inflateEnd(&strm->z) != Z_OK && !err)
 		err = -EIO;
 	if (kout)
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 2dd14f99c1dc..4b28dc130c9f 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -148,7 +148,7 @@ again:
 }
 
 int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
-			    struct page **pagepool)
+			    struct page **pgpl)
 {
 	const unsigned int nrpages_out =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
@@ -215,8 +215,11 @@ again:
 						   PAGE_SIZE - pageofs);
 			outlen -= strm->buf.out_size;
 			if (!rq->out[no] && rq->fillgaps) {	/* deduped */
-				rq->out[no] = erofs_allocpage(pagepool,
-						GFP_KERNEL | __GFP_NOFAIL);
+				rq->out[no] = erofs_allocpage(pgpl, rq->gfp);
+				if (!rq->out[no]) {
+					err = -ENOMEM;
+					break;
+				}
 				set_page_private(rq->out[no],
 						 Z_EROFS_SHORTLIVED_PAGE);
 			}
@@ -255,11 +258,11 @@ again:
 
 			if (rq->out[no] != rq->in[j])
 				continue;
-
-			DBG_BUGON(erofs_page_is_managed(EROFS_SB(rq->sb),
-							rq->in[j]));
-			tmppage = erofs_allocpage(pagepool,
-						  GFP_KERNEL | __GFP_NOFAIL);
+			tmppage = erofs_allocpage(pgpl, rq->gfp);
+			if (!tmppage) {
+				err = -ENOMEM;
+				goto failed;
+			}
 			set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE);
 			copy_highpage(tmppage, rq->in[j]);
 			rq->in[j] = tmppage;
@@ -277,6 +280,7 @@ again:
 			break;
 		}
 	}
+failed:
 	if (no < nrpages_out && strm->buf.out)
 		kunmap(rq->out[no]);
 	if (ni < nrpages_in)
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index bc12030393b2..8aff1a724805 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2022, Alibaba Cloud
  * Copyright (C) 2022, Bytedance Inc. All rights reserved.
  */
+#include <linux/pseudo_fs.h>
 #include <linux/fscache.h>
 #include "internal.h"
 
@@ -12,9 +13,27 @@ static LIST_HEAD(erofs_domain_list);
 static LIST_HEAD(erofs_domain_cookies_list);
 static struct vfsmount *erofs_pseudo_mnt;
 
-struct erofs_fscache_request {
-	struct erofs_fscache_request *primary;
-	struct netfs_cache_resources cache_resources;
+static int erofs_anon_init_fs_context(struct fs_context *fc)
+{
+	return init_pseudo(fc, EROFS_SUPER_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type erofs_anon_fs_type = {
+	.owner		= THIS_MODULE,
+	.name           = "pseudo_erofs",
+	.init_fs_context = erofs_anon_init_fs_context,
+	.kill_sb        = kill_anon_super,
+};
+
+struct erofs_fscache_io {
+	struct netfs_cache_resources cres;
+	struct iov_iter		iter;
+	netfs_io_terminated_t	end_io;
+	void			*private;
+	refcount_t		ref;
+};
+
+struct erofs_fscache_rq {
 	struct address_space	*mapping;	/* The mapping being accessed */
 	loff_t			start;		/* Start position */
 	size_t			len;		/* Length of the request */
@@ -23,44 +42,17 @@ struct erofs_fscache_request {
 	refcount_t		ref;
 };
 
-static struct erofs_fscache_request *erofs_fscache_req_alloc(struct address_space *mapping,
-					     loff_t start, size_t len)
+static bool erofs_fscache_io_put(struct erofs_fscache_io *io)
 {
-	struct erofs_fscache_request *req;
-
-	req = kzalloc(sizeof(struct erofs_fscache_request), GFP_KERNEL);
-	if (!req)
-		return ERR_PTR(-ENOMEM);
-
-	req->mapping = mapping;
-	req->start   = start;
-	req->len     = len;
-	refcount_set(&req->ref, 1);
-
-	return req;
+	if (!refcount_dec_and_test(&io->ref))
+		return false;
+	if (io->cres.ops)
+		io->cres.ops->end_operation(&io->cres);
+	kfree(io);
+	return true;
 }
 
-static struct erofs_fscache_request *erofs_fscache_req_chain(struct erofs_fscache_request *primary,
-					     size_t len)
-{
-	struct erofs_fscache_request *req;
-
-	/* use primary request for the first submission */
-	if (!primary->submitted) {
-		refcount_inc(&primary->ref);
-		return primary;
-	}
-
-	req = erofs_fscache_req_alloc(primary->mapping,
-			primary->start + primary->submitted, len);
-	if (!IS_ERR(req)) {
-		req->primary = primary;
-		refcount_inc(&primary->ref);
-	}
-	return req;
-}
-
-static void erofs_fscache_req_complete(struct erofs_fscache_request *req)
+static void erofs_fscache_req_complete(struct erofs_fscache_rq *req)
 {
 	struct folio *folio;
 	bool failed = req->error;
@@ -80,120 +72,196 @@ static void erofs_fscache_req_complete(struct erofs_fscache_request *req)
 	rcu_read_unlock();
 }
 
-static void erofs_fscache_req_put(struct erofs_fscache_request *req)
+static void erofs_fscache_req_put(struct erofs_fscache_rq *req)
 {
-	if (refcount_dec_and_test(&req->ref)) {
-		if (req->cache_resources.ops)
-			req->cache_resources.ops->end_operation(&req->cache_resources);
-		if (!req->primary)
-			erofs_fscache_req_complete(req);
-		else
-			erofs_fscache_req_put(req->primary);
-		kfree(req);
-	}
+	if (!refcount_dec_and_test(&req->ref))
+		return;
+	erofs_fscache_req_complete(req);
+	kfree(req);
 }
 
-static void erofs_fscache_subreq_complete(void *priv,
+static struct erofs_fscache_rq *erofs_fscache_req_alloc(struct address_space *mapping,
+						loff_t start, size_t len)
+{
+	struct erofs_fscache_rq *req = kzalloc(sizeof(*req), GFP_KERNEL);
+
+	if (!req)
+		return NULL;
+	req->mapping = mapping;
+	req->start = start;
+	req->len = len;
+	refcount_set(&req->ref, 1);
+	return req;
+}
+
+static void erofs_fscache_req_io_put(struct erofs_fscache_io *io)
+{
+	struct erofs_fscache_rq *req = io->private;
+
+	if (erofs_fscache_io_put(io))
+		erofs_fscache_req_put(req);
+}
+
+static void erofs_fscache_req_end_io(void *priv,
 		ssize_t transferred_or_error, bool was_async)
 {
-	struct erofs_fscache_request *req = priv;
+	struct erofs_fscache_io *io = priv;
+	struct erofs_fscache_rq *req = io->private;
 
-	if (IS_ERR_VALUE(transferred_or_error)) {
-		if (req->primary)
-			req->primary->error = transferred_or_error;
-		else
-			req->error = transferred_or_error;
-	}
-	erofs_fscache_req_put(req);
+	if (IS_ERR_VALUE(transferred_or_error))
+		req->error = transferred_or_error;
+	erofs_fscache_req_io_put(io);
+}
+
+static struct erofs_fscache_io *erofs_fscache_req_io_alloc(struct erofs_fscache_rq *req)
+{
+	struct erofs_fscache_io *io = kzalloc(sizeof(*io), GFP_KERNEL);
+
+	if (!io)
+		return NULL;
+	io->end_io = erofs_fscache_req_end_io;
+	io->private = req;
+	refcount_inc(&req->ref);
+	refcount_set(&io->ref, 1);
+	return io;
 }
 
 /*
- * Read data from fscache (cookie, pstart, len), and fill the read data into
- * page cache described by (req->mapping, lstart, len). @pstart describeis the
- * start physical address in the cache file.
+ * Read data from fscache described by cookie at pstart physical address
+ * offset, and fill the read data into buffer described by io->iter.
  */
-static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie,
-		struct erofs_fscache_request *req, loff_t pstart, size_t len)
+static int erofs_fscache_read_io_async(struct fscache_cookie *cookie,
+		loff_t pstart, struct erofs_fscache_io *io)
 {
 	enum netfs_io_source source;
-	struct super_block *sb = req->mapping->host->i_sb;
-	struct netfs_cache_resources *cres = &req->cache_resources;
-	struct iov_iter iter;
-	loff_t lstart = req->start + req->submitted;
-	size_t done = 0;
+	struct netfs_cache_resources *cres = &io->cres;
+	struct iov_iter *iter = &io->iter;
 	int ret;
 
-	DBG_BUGON(len > req->len - req->submitted);
-
 	ret = fscache_begin_read_operation(cres, cookie);
 	if (ret)
 		return ret;
 
-	while (done < len) {
-		loff_t sstart = pstart + done;
-		size_t slen = len - done;
+	while (iov_iter_count(iter)) {
+		size_t orig_count = iov_iter_count(iter), len = orig_count;
 		unsigned long flags = 1 << NETFS_SREQ_ONDEMAND;
 
 		source = cres->ops->prepare_ondemand_read(cres,
-				sstart, &slen, LLONG_MAX, &flags, 0);
-		if (WARN_ON(slen == 0))
+				pstart, &len, LLONG_MAX, &flags, 0);
+		if (WARN_ON(len == 0))
 			source = NETFS_INVALID_READ;
 		if (source != NETFS_READ_FROM_CACHE) {
-			erofs_err(sb, "failed to fscache prepare_read (source %d)", source);
+			erofs_err(NULL, "prepare_read failed (source %d)", source);
 			return -EIO;
 		}
 
-		refcount_inc(&req->ref);
-		iov_iter_xarray(&iter, ITER_DEST, &req->mapping->i_pages,
-				lstart + done, slen);
-
-		ret = fscache_read(cres, sstart, &iter, NETFS_READ_HOLE_FAIL,
-				   erofs_fscache_subreq_complete, req);
+		iov_iter_truncate(iter, len);
+		refcount_inc(&io->ref);
+		ret = fscache_read(cres, pstart, iter, NETFS_READ_HOLE_FAIL,
+				   io->end_io, io);
 		if (ret == -EIOCBQUEUED)
 			ret = 0;
 		if (ret) {
-			erofs_err(sb, "failed to fscache_read (ret %d)", ret);
+			erofs_err(NULL, "fscache_read failed (ret %d)", ret);
 			return ret;
 		}
+		if (WARN_ON(iov_iter_count(iter)))
+			return -EIO;
 
-		done += slen;
+		iov_iter_reexpand(iter, orig_count - len);
+		pstart += len;
 	}
-	DBG_BUGON(done != len);
 	return 0;
 }
 
-static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
+struct erofs_fscache_bio {
+	struct erofs_fscache_io io;
+	struct bio bio;		/* w/o bdev to share bio_add_page/endio() */
+	struct bio_vec bvecs[BIO_MAX_VECS];
+};
+
+static void erofs_fscache_bio_endio(void *priv,
+		ssize_t transferred_or_error, bool was_async)
+{
+	struct erofs_fscache_bio *io = priv;
+
+	if (IS_ERR_VALUE(transferred_or_error))
+		io->bio.bi_status = errno_to_blk_status(transferred_or_error);
+	io->bio.bi_end_io(&io->bio);
+	BUILD_BUG_ON(offsetof(struct erofs_fscache_bio, io) != 0);
+	erofs_fscache_io_put(&io->io);
+}
+
+struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev)
 {
+	struct erofs_fscache_bio *io;
+
+	io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL);
+	bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ);
+	io->io.private = mdev->m_fscache->cookie;
+	io->io.end_io = erofs_fscache_bio_endio;
+	refcount_set(&io->io.ref, 1);
+	return &io->bio;
+}
+
+void erofs_fscache_submit_bio(struct bio *bio)
+{
+	struct erofs_fscache_bio *io = container_of(bio,
+			struct erofs_fscache_bio, bio);
 	int ret;
+
+	iov_iter_bvec(&io->io.iter, ITER_DEST, io->bvecs, bio->bi_vcnt,
+		      bio->bi_iter.bi_size);
+	ret = erofs_fscache_read_io_async(io->io.private,
+				bio->bi_iter.bi_sector << 9, &io->io);
+	erofs_fscache_io_put(&io->io);
+	if (!ret)
+		return;
+	bio->bi_status = errno_to_blk_status(ret);
+	bio->bi_end_io(bio);
+}
+
+static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
+{
 	struct erofs_fscache *ctx = folio->mapping->host->i_private;
-	struct erofs_fscache_request *req;
+	int ret = -ENOMEM;
+	struct erofs_fscache_rq *req;
+	struct erofs_fscache_io *io;
 
 	req = erofs_fscache_req_alloc(folio->mapping,
 				folio_pos(folio), folio_size(folio));
-	if (IS_ERR(req)) {
+	if (!req) {
 		folio_unlock(folio);
-		return PTR_ERR(req);
+		return ret;
 	}
 
-	ret = erofs_fscache_read_folios_async(ctx->cookie, req,
-				folio_pos(folio), folio_size(folio));
+	io = erofs_fscache_req_io_alloc(req);
+	if (!io) {
+		req->error = ret;
+		goto out;
+	}
+	iov_iter_xarray(&io->iter, ITER_DEST, &folio->mapping->i_pages,
+			folio_pos(folio), folio_size(folio));
+
+	ret = erofs_fscache_read_io_async(ctx->cookie, folio_pos(folio), io);
 	if (ret)
 		req->error = ret;
 
+	erofs_fscache_req_io_put(io);
+out:
 	erofs_fscache_req_put(req);
 	return ret;
 }
 
-static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
+static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req)
 {
-	struct address_space *mapping = primary->mapping;
+	struct address_space *mapping = req->mapping;
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
-	struct erofs_fscache_request *req;
+	struct erofs_fscache_io *io;
 	struct erofs_map_blocks map;
 	struct erofs_map_dev mdev;
-	struct iov_iter iter;
-	loff_t pos = primary->start + primary->submitted;
+	loff_t pos = req->start + req->submitted;
 	size_t count;
 	int ret;
 
@@ -204,6 +272,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
 
 	if (map.m_flags & EROFS_MAP_META) {
 		struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+		struct iov_iter iter;
 		erofs_blk_t blknr;
 		size_t offset, size;
 		void *src;
@@ -224,15 +293,17 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
 		}
 		iov_iter_zero(PAGE_SIZE - size, &iter);
 		erofs_put_metabuf(&buf);
-		primary->submitted += PAGE_SIZE;
+		req->submitted += PAGE_SIZE;
 		return 0;
 	}
 
-	count = primary->len - primary->submitted;
+	count = req->len - req->submitted;
 	if (!(map.m_flags & EROFS_MAP_MAPPED)) {
+		struct iov_iter iter;
+
 		iov_iter_xarray(&iter, ITER_DEST, &mapping->i_pages, pos, count);
 		iov_iter_zero(count, &iter);
-		primary->submitted += count;
+		req->submitted += count;
 		return 0;
 	}
 
@@ -247,18 +318,19 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary)
 	if (ret)
 		return ret;
 
-	req = erofs_fscache_req_chain(primary, count);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
+	io = erofs_fscache_req_io_alloc(req);
+	if (!io)
+		return -ENOMEM;
+	iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count);
+	ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie,
+			mdev.m_pa + (pos - map.m_la), io);
+	erofs_fscache_req_io_put(io);
 
-	ret = erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
-			req, mdev.m_pa + (pos - map.m_la), count);
-	erofs_fscache_req_put(req);
-	primary->submitted += count;
+	req->submitted += count;
 	return ret;
 }
 
-static int erofs_fscache_data_read(struct erofs_fscache_request *req)
+static int erofs_fscache_data_read(struct erofs_fscache_rq *req)
 {
 	int ret;
 
@@ -267,20 +339,19 @@ static int erofs_fscache_data_read(struct erofs_fscache_request *req)
 		if (ret)
 			req->error = ret;
 	} while (!ret && req->submitted < req->len);
-
 	return ret;
 }
 
 static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 {
-	struct erofs_fscache_request *req;
+	struct erofs_fscache_rq *req;
 	int ret;
 
 	req = erofs_fscache_req_alloc(folio->mapping,
 			folio_pos(folio), folio_size(folio));
-	if (IS_ERR(req)) {
+	if (!req) {
 		folio_unlock(folio);
-		return PTR_ERR(req);
+		return -ENOMEM;
 	}
 
 	ret = erofs_fscache_data_read(req);
@@ -290,14 +361,14 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 
 static void erofs_fscache_readahead(struct readahead_control *rac)
 {
-	struct erofs_fscache_request *req;
+	struct erofs_fscache_rq *req;
 
 	if (!readahead_count(rac))
 		return;
 
 	req = erofs_fscache_req_alloc(rac->mapping,
 			readahead_pos(rac), readahead_length(rac));
-	if (IS_ERR(req))
+	if (!req)
 		return;
 
 	/* The request completion will drop refs on the folios. */
@@ -381,11 +452,12 @@ static int erofs_fscache_init_domain(struct super_block *sb)
 		goto out;
 
 	if (!erofs_pseudo_mnt) {
-		erofs_pseudo_mnt = kern_mount(&erofs_fs_type);
-		if (IS_ERR(erofs_pseudo_mnt)) {
-			err = PTR_ERR(erofs_pseudo_mnt);
+		struct vfsmount *mnt = kern_mount(&erofs_anon_fs_type);
+		if (IS_ERR(mnt)) {
+			err = PTR_ERR(mnt);
 			goto out;
 		}
+		erofs_pseudo_mnt = mnt;
 	}
 
 	domain->volume = sbi->volume;
@@ -459,7 +531,7 @@ static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb
 
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &erofs_fscache_meta_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	inode->i_blkbits = EROFS_SB(sb)->blkszbits;
 	inode->i_private = ctx;
 
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 3d616dea55dc..0eb0e6f933c3 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -60,7 +60,7 @@ static void *erofs_read_inode(struct erofs_buf *buf,
 		} else {
 			const unsigned int gotten = sb->s_blocksize - *ofs;
 
-			copied = kmalloc(vi->inode_isize, GFP_NOFS);
+			copied = kmalloc(vi->inode_isize, GFP_KERNEL);
 			if (!copied) {
 				err = -ENOMEM;
 				goto err_out;
@@ -259,14 +259,12 @@ static int erofs_fill_inode(struct inode *inode)
 
 	if (erofs_inode_is_data_compressed(vi->datalayout)) {
 #ifdef CONFIG_EROFS_FS_ZIP
-		if (!erofs_is_fscache_mode(inode->i_sb)) {
-			DO_ONCE_LITE_IF(inode->i_sb->s_blocksize != PAGE_SIZE,
-				  erofs_info, inode->i_sb,
-				  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
-			inode->i_mapping->a_ops = &z_erofs_aops;
-			err = 0;
-			goto out_unlock;
-		}
+		DO_ONCE_LITE_IF(inode->i_blkbits != PAGE_SHIFT,
+			  erofs_info, inode->i_sb,
+			  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
+		inode->i_mapping->a_ops = &z_erofs_aops;
+		err = 0;
+		goto out_unlock;
 #endif
 		err = -EOPNOTSUPP;
 		goto out_unlock;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index b0409badb017..39c67119f43b 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -49,7 +49,7 @@ typedef u32 erofs_blk_t;
 struct erofs_device_info {
 	char *path;
 	struct erofs_fscache *fscache;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct dax_device *dax_dev;
 	u64 dax_part_off;
 
@@ -385,7 +385,6 @@ struct erofs_map_dev {
 	unsigned int m_deviceid;
 };
 
-extern struct file_system_type erofs_fs_type;
 extern const struct super_operations erofs_sops;
 
 extern const struct address_space_operations erofs_raw_access_aops;
@@ -467,8 +466,8 @@ int __init erofs_init_shrinker(void);
 void erofs_exit_shrinker(void);
 int __init z_erofs_init_zip_subsystem(void);
 void z_erofs_exit_zip_subsystem(void);
-int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
-				       struct erofs_workgroup *egrp);
+int erofs_try_to_free_all_cached_folios(struct erofs_sb_info *sbi,
+					struct erofs_workgroup *egrp);
 int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			    int flags);
 void *erofs_get_pcpubuf(unsigned int requiredpages);
@@ -513,6 +512,8 @@ void erofs_fscache_unregister_fs(struct super_block *sb);
 struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
 					char *name, unsigned int flags);
 void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache);
+struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev);
+void erofs_fscache_submit_bio(struct bio *bio);
 #else
 static inline int erofs_fscache_register_fs(struct super_block *sb)
 {
@@ -530,6 +531,8 @@ struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb,
 static inline void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache)
 {
 }
+static inline struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) { return NULL; }
+static inline void erofs_fscache_submit_bio(struct bio *bio) {}
 #endif
 
 #define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */
diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c
index d4f631d39f0f..f0110a78acb2 100644
--- a/fs/erofs/namei.c
+++ b/fs/erofs/namei.c
@@ -130,24 +130,24 @@ static void *erofs_find_target_block(struct erofs_buf *target,
 			/* string comparison without already matched prefix */
 			diff = erofs_dirnamecmp(name, &dname, &matched);
 
-			if (!diff) {
-				*_ndirents = 0;
-				goto out;
-			} else if (diff > 0) {
-				head = mid + 1;
-				startprfx = matched;
-
-				if (!IS_ERR(candidate))
-					erofs_put_metabuf(target);
-				*target = buf;
-				candidate = de;
-				*_ndirents = ndirents;
-			} else {
+			if (diff < 0) {
 				erofs_put_metabuf(&buf);
-
 				back = mid - 1;
 				endprfx = matched;
+				continue;
+			}
+
+			if (!IS_ERR(candidate))
+				erofs_put_metabuf(target);
+			*target = buf;
+			if (!diff) {
+				*_ndirents = 0;
+				return de;
 			}
+			head = mid + 1;
+			startprfx = matched;
+			candidate = de;
+			*_ndirents = ndirents;
 			continue;
 		}
 out:		/* free if the candidate is valid */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 5f60f163bd56..6fbb1fba2d31 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -177,7 +177,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 	struct erofs_fscache *fscache;
 	struct erofs_deviceslot *dis;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	void *ptr;
 
 	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP);
@@ -201,12 +201,12 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 			return PTR_ERR(fscache);
 		dif->fscache = fscache;
 	} else if (!sbi->devs->flatdev) {
-		bdev_handle = bdev_open_by_path(dif->path, BLK_OPEN_READ,
+		bdev_file = bdev_file_open_by_path(dif->path, BLK_OPEN_READ,
 						sb->s_type, NULL);
-		if (IS_ERR(bdev_handle))
-			return PTR_ERR(bdev_handle);
-		dif->bdev_handle = bdev_handle;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev,
+		if (IS_ERR(bdev_file))
+			return PTR_ERR(bdev_file);
+		dif->bdev_file = bdev_file;
+		dif->dax_dev = fs_dax_get_by_bdev(file_bdev(bdev_file),
 				&dif->dax_part_off, NULL, NULL);
 	}
 
@@ -579,13 +579,6 @@ static const struct export_operations erofs_export_ops = {
 	.get_parent = erofs_get_parent,
 };
 
-static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc)
-{
-	static const struct tree_descr empty_descr = {""};
-
-	return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr);
-}
-
 static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct inode *inode;
@@ -712,11 +705,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	return 0;
 }
 
-static int erofs_fc_anon_get_tree(struct fs_context *fc)
-{
-	return get_tree_nodev(fc, erofs_fc_fill_pseudo_super);
-}
-
 static int erofs_fc_get_tree(struct fs_context *fc)
 {
 	struct erofs_fs_context *ctx = fc->fs_private;
@@ -754,8 +742,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 	struct erofs_device_info *dif = ptr;
 
 	fs_put_dax(dif->dax_dev, NULL);
-	if (dif->bdev_handle)
-		bdev_release(dif->bdev_handle);
+	if (dif->bdev_file)
+		fput(dif->bdev_file);
 	erofs_fscache_unregister_cookie(dif->fscache);
 	dif->fscache = NULL;
 	kfree(dif->path);
@@ -789,20 +777,10 @@ static const struct fs_context_operations erofs_context_ops = {
 	.free		= erofs_fc_free,
 };
 
-static const struct fs_context_operations erofs_anon_context_ops = {
-	.get_tree       = erofs_fc_anon_get_tree,
-};
-
 static int erofs_init_fs_context(struct fs_context *fc)
 {
 	struct erofs_fs_context *ctx;
 
-	/* pseudo mount for anon inodes */
-	if (fc->sb_flags & SB_KERNMOUNT) {
-		fc->ops = &erofs_anon_context_ops;
-		return 0;
-	}
-
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
@@ -824,12 +802,6 @@ static void erofs_kill_sb(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi;
 
-	/* pseudo mount for anon inodes */
-	if (sb->s_flags & SB_KERNMOUNT) {
-		kill_anon_super(sb);
-		return;
-	}
-
 	if (erofs_is_fscache_mode(sb))
 		kill_anon_super(sb);
 	else
@@ -868,7 +840,7 @@ static void erofs_put_super(struct super_block *sb)
 	erofs_fscache_unregister_fs(sb);
 }
 
-struct file_system_type erofs_fs_type = {
+static struct file_system_type erofs_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "erofs",
 	.init_fs_context = erofs_init_fs_context,
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 5dea308764b4..518bdd69c823 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -81,7 +81,7 @@ struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
 repeat:
 	xa_lock(&sbi->managed_pslots);
 	pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index,
-			   NULL, grp, GFP_NOFS);
+			   NULL, grp, GFP_KERNEL);
 	if (pre) {
 		if (xa_is_err(pre)) {
 			pre = ERR_PTR(xa_err(pre));
@@ -129,7 +129,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
 	 * the XArray. Otherwise some cached pages could be still attached to
 	 * the orphan old workgroup when the new one is available in the tree.
 	 */
-	if (erofs_try_to_free_all_cached_pages(sbi, grp))
+	if (erofs_try_to_free_all_cached_folios(sbi, grp))
 		goto out;
 
 	/*
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 692c0c39be63..3216b920d369 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -19,7 +19,10 @@
 typedef void *z_erofs_next_pcluster_t;
 
 struct z_erofs_bvec {
-	struct page *page;
+	union {
+		struct page *page;
+		struct folio *folio;
+	};
 	int offset;
 	unsigned int end;
 };
@@ -82,6 +85,9 @@ struct z_erofs_pcluster {
 	/* L: indicate several pageofs_outs or not */
 	bool multibases;
 
+	/* L: whether extra buffer allocations are best-effort */
+	bool besteffort;
+
 	/* A: compressed bvecs (can be cached or inplaced pages) */
 	struct z_erofs_bvec compressed_bvecs[];
 };
@@ -113,47 +119,46 @@ static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl)
 	return PAGE_ALIGN(pcl->pclustersize) >> PAGE_SHIFT;
 }
 
+#define MNGD_MAPPING(sbi)	((sbi)->managed_cache->i_mapping)
+static bool erofs_folio_is_managed(struct erofs_sb_info *sbi, struct folio *fo)
+{
+	return fo->mapping == MNGD_MAPPING(sbi);
+}
+
 /*
- * bit 30: I/O error occurred on this page
- * bit 0 - 29: remaining parts to complete this page
+ * bit 30: I/O error occurred on this folio
+ * bit 0 - 29: remaining parts to complete this folio
  */
-#define Z_EROFS_PAGE_EIO			(1 << 30)
+#define Z_EROFS_FOLIO_EIO			(1 << 30)
 
-static inline void z_erofs_onlinepage_init(struct page *page)
+static void z_erofs_onlinefolio_init(struct folio *folio)
 {
 	union {
 		atomic_t o;
-		unsigned long v;
+		void *v;
 	} u = { .o = ATOMIC_INIT(1) };
 
-	set_page_private(page, u.v);
-	smp_wmb();
-	SetPagePrivate(page);
+	folio->private = u.v;	/* valid only if file-backed folio is locked */
 }
 
-static inline void z_erofs_onlinepage_split(struct page *page)
+static void z_erofs_onlinefolio_split(struct folio *folio)
 {
-	atomic_inc((atomic_t *)&page->private);
+	atomic_inc((atomic_t *)&folio->private);
 }
 
-static void z_erofs_onlinepage_endio(struct page *page, int err)
+static void z_erofs_onlinefolio_end(struct folio *folio, int err)
 {
 	int orig, v;
 
-	DBG_BUGON(!PagePrivate(page));
-
 	do {
-		orig = atomic_read((atomic_t *)&page->private);
-		v = (orig - 1) | (err ? Z_EROFS_PAGE_EIO : 0);
-	} while (atomic_cmpxchg((atomic_t *)&page->private, orig, v) != orig);
-
-	if (!(v & ~Z_EROFS_PAGE_EIO)) {
-		set_page_private(page, 0);
-		ClearPagePrivate(page);
-		if (!(v & Z_EROFS_PAGE_EIO))
-			SetPageUptodate(page);
-		unlock_page(page);
-	}
+		orig = atomic_read((atomic_t *)&folio->private);
+		v = (orig - 1) | (err ? Z_EROFS_FOLIO_EIO : 0);
+	} while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig);
+
+	if (v & ~Z_EROFS_FOLIO_EIO)
+		return;
+	folio->private = 0;
+	folio_end_read(folio, !(v & Z_EROFS_FOLIO_EIO));
 }
 
 #define Z_EROFS_ONSTACK_PAGES		32
@@ -230,7 +235,7 @@ static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
 		struct page *nextpage = *candidate_bvpage;
 
 		if (!nextpage) {
-			nextpage = erofs_allocpage(pagepool, GFP_NOFS);
+			nextpage = erofs_allocpage(pagepool, GFP_KERNEL);
 			if (!nextpage)
 				return -ENOMEM;
 			set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE);
@@ -302,7 +307,7 @@ static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int size)
 		if (nrpages > pcs->maxpages)
 			continue;
 
-		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
+		pcl = kmem_cache_zalloc(pcs->slab, GFP_KERNEL);
 		if (!pcl)
 			return ERR_PTR(-ENOMEM);
 		pcl->pclustersize = size;
@@ -563,25 +568,19 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 	unsigned int i;
 
-	if (i_blocksize(fe->inode) != PAGE_SIZE)
-		return;
-	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
+	if (i_blocksize(fe->inode) != PAGE_SIZE ||
+	    fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
 		return;
 
 	for (i = 0; i < pclusterpages; ++i) {
 		struct page *page, *newpage;
-		void *t;	/* mark pages just found for debugging */
 
-		/* the compressed page was loaded before */
+		/* Inaccurate check w/o locking to avoid unneeded lookups */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
 			continue;
 
 		page = find_get_page(mc, pcl->obj.index + i);
-
-		if (page) {
-			t = (void *)((unsigned long)page | 1);
-			newpage = NULL;
-		} else {
+		if (!page) {
 			/* I/O is needed, no possible to decompress directly */
 			standalone = false;
 			if (!shouldalloc)
@@ -595,11 +594,14 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 			if (!newpage)
 				continue;
 			set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
-			t = (void *)((unsigned long)newpage | 1);
 		}
-
-		if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, t))
+		spin_lock(&pcl->obj.lockref.lock);
+		if (!pcl->compressed_bvecs[i].page) {
+			pcl->compressed_bvecs[i].page = page ? page : newpage;
+			spin_unlock(&pcl->obj.lockref.lock);
 			continue;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
 
 		if (page)
 			put_page(page);
@@ -615,9 +617,9 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
 }
 
-/* called by erofs_shrinker to get rid of all compressed_pages */
-int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
-				       struct erofs_workgroup *grp)
+/* called by erofs_shrinker to get rid of all cached compressed bvecs */
+int erofs_try_to_free_all_cached_folios(struct erofs_sb_info *sbi,
+					struct erofs_workgroup *grp)
 {
 	struct z_erofs_pcluster *const pcl =
 		container_of(grp, struct z_erofs_pcluster, obj);
@@ -625,27 +627,22 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 	int i;
 
 	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
-	/*
-	 * refcount of workgroup is now freezed as 0,
-	 * therefore no need to worry about available decompression users.
-	 */
+	/* There is no actice user since the pcluster is now freezed */
 	for (i = 0; i < pclusterpages; ++i) {
-		struct page *page = pcl->compressed_bvecs[i].page;
+		struct folio *folio = pcl->compressed_bvecs[i].folio;
 
-		if (!page)
+		if (!folio)
 			continue;
 
-		/* block other users from reclaiming or migrating the page */
-		if (!trylock_page(page))
+		/* Avoid reclaiming or migrating this folio */
+		if (!folio_trylock(folio))
 			return -EBUSY;
 
-		if (!erofs_page_is_managed(sbi, page))
+		if (!erofs_folio_is_managed(sbi, folio))
 			continue;
-
-		/* barrier is implied in the following 'unlock_page' */
-		WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
-		detach_page_private(page);
-		unlock_page(page);
+		pcl->compressed_bvecs[i].folio = NULL;
+		folio_detach_private(folio);
+		folio_unlock(folio);
 	}
 	return 0;
 }
@@ -662,20 +659,17 @@ static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
 
 	ret = false;
 	spin_lock(&pcl->obj.lockref.lock);
-	if (pcl->obj.lockref.count > 0)
-		goto out;
-
-	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
-	for (i = 0; i < pclusterpages; ++i) {
-		if (pcl->compressed_bvecs[i].page == &folio->page) {
-			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
-			ret = true;
-			break;
+	if (pcl->obj.lockref.count <= 0) {
+		DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
+		for (i = 0; i < pclusterpages; ++i) {
+			if (pcl->compressed_bvecs[i].folio == folio) {
+				pcl->compressed_bvecs[i].folio = NULL;
+				folio_detach_private(folio);
+				ret = true;
+				break;
+			}
 		}
 	}
-	if (ret)
-		folio_detach_private(folio);
-out:
 	spin_unlock(&pcl->obj.lockref.lock);
 	return ret;
 }
@@ -694,7 +688,7 @@ static void z_erofs_cache_invalidate_folio(struct folio *folio,
 	DBG_BUGON(stop > folio_size(folio) || stop < length);
 
 	if (offset == 0 && stop == folio_size(folio))
-		while (!z_erofs_cache_release_folio(folio, GFP_NOFS))
+		while (!z_erofs_cache_release_folio(folio, 0))
 			cond_resched();
 }
 
@@ -713,36 +707,30 @@ int erofs_init_managed_cache(struct super_block *sb)
 	set_nlink(inode, 1);
 	inode->i_size = OFFSET_MAX;
 	inode->i_mapping->a_ops = &z_erofs_cache_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 	EROFS_SB(sb)->managed_cache = inode;
 	return 0;
 }
 
-static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
-				   struct z_erofs_bvec *bvec)
-{
-	struct z_erofs_pcluster *const pcl = fe->pcl;
-
-	while (fe->icur > 0) {
-		if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
-			     NULL, bvec->page)) {
-			pcl->compressed_bvecs[fe->icur] = *bvec;
-			return true;
-		}
-	}
-	return false;
-}
-
 /* callers must be with pcluster lock held */
 static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
 			       struct z_erofs_bvec *bvec, bool exclusive)
 {
+	struct z_erofs_pcluster *pcl = fe->pcl;
 	int ret;
 
 	if (exclusive) {
 		/* give priority for inplaceio to use file pages first */
-		if (z_erofs_try_inplace_io(fe, bvec))
+		spin_lock(&pcl->obj.lockref.lock);
+		while (fe->icur > 0) {
+			if (pcl->compressed_bvecs[--fe->icur].page)
+				continue;
+			pcl->compressed_bvecs[fe->icur] = *bvec;
+			spin_unlock(&pcl->obj.lockref.lock);
 			return 0;
+		}
+		spin_unlock(&pcl->obj.lockref.lock);
+
 		/* otherwise, check if it can be used as a bvpage */
 		if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
 		    !fe->candidate_bvpage)
@@ -963,20 +951,20 @@ static int z_erofs_read_fragment(struct super_block *sb, struct page *page,
 	return 0;
 }
 
-static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
-				struct page *page)
+static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *fe,
+			      struct folio *folio, bool ra)
 {
 	struct inode *const inode = fe->inode;
 	struct erofs_map_blocks *const map = &fe->map;
-	const loff_t offset = page_offset(page);
-	const unsigned int bs = i_blocksize(inode);
+	const loff_t offset = folio_pos(folio);
+	const unsigned int bs = i_blocksize(inode), fs = folio_size(folio);
 	bool tight = true, exclusive;
 	unsigned int cur, end, len, split;
 	int err = 0;
 
-	z_erofs_onlinepage_init(page);
+	z_erofs_onlinefolio_init(folio);
 	split = 0;
-	end = PAGE_SIZE;
+	end = fs;
 repeat:
 	if (offset + end - 1 < map->m_la ||
 	    offset + end - 1 >= map->m_la + map->m_llen) {
@@ -993,7 +981,7 @@ repeat:
 	++split;
 
 	if (!(map->m_flags & EROFS_MAP_MAPPED)) {
-		zero_user_segment(page, cur, end);
+		folio_zero_segment(folio, cur, end);
 		tight = false;
 		goto next_part;
 	}
@@ -1002,8 +990,8 @@ repeat:
 		erofs_off_t fpos = offset + cur - map->m_la;
 
 		len = min_t(unsigned int, map->m_llen - fpos, end - cur);
-		err = z_erofs_read_fragment(inode->i_sb, page, cur, cur + len,
-				EROFS_I(inode)->z_fragmentoff + fpos);
+		err = z_erofs_read_fragment(inode->i_sb, &folio->page, cur,
+			cur + len, EROFS_I(inode)->z_fragmentoff + fpos);
 		if (err)
 			goto out;
 		tight = false;
@@ -1014,28 +1002,29 @@ repeat:
 		err = z_erofs_pcluster_begin(fe);
 		if (err)
 			goto out;
+		fe->pcl->besteffort |= !ra;
 	}
 
 	/*
-	 * Ensure the current partial page belongs to this submit chain rather
+	 * Ensure the current partial folio belongs to this submit chain rather
 	 * than other concurrent submit chains or the noio(bypass) chain since
-	 * those chains are handled asynchronously thus the page cannot be used
+	 * those chains are handled asynchronously thus the folio cannot be used
 	 * for inplace I/O or bvpage (should be processed in a strict order.)
 	 */
 	tight &= (fe->mode > Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE);
-	exclusive = (!cur && ((split <= 1) || (tight && bs == PAGE_SIZE)));
+	exclusive = (!cur && ((split <= 1) || (tight && bs == fs)));
 	if (cur)
 		tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED);
 
 	err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) {
-					.page = page,
+					.page = &folio->page,
 					.offset = offset - map->m_la,
 					.end = end,
 				  }), exclusive);
 	if (err)
 		goto out;
 
-	z_erofs_onlinepage_split(page);
+	z_erofs_onlinefolio_split(folio);
 	if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
 		fe->pcl->multibases = true;
 	if (fe->pcl->length < offset + end - map->m_la) {
@@ -1056,7 +1045,7 @@ next_part:
 		goto repeat;
 
 out:
-	z_erofs_onlinepage_endio(page, err);
+	z_erofs_onlinefolio_end(folio, err);
 	return err;
 }
 
@@ -1159,7 +1148,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
 			cur += len;
 		}
 		kunmap_local(dst);
-		z_erofs_onlinepage_endio(bvi->bvec.page, err);
+		z_erofs_onlinefolio_end(page_folio(bvi->bvec.page), err);
 		list_del(p);
 		kfree(bvi);
 	}
@@ -1210,7 +1199,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
 		be->compressed_pages[i] = page;
 
 		if (z_erofs_is_inline_pcluster(pcl) ||
-		    erofs_page_is_managed(EROFS_SB(be->sb), page)) {
+		    erofs_folio_is_managed(EROFS_SB(be->sb), page_folio(page))) {
 			if (!PageUptodate(page))
 				err = -EIO;
 			continue;
@@ -1280,6 +1269,9 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 					.inplace_io = overlapped,
 					.partial_decoding = pcl->partial,
 					.fillgaps = pcl->multibases,
+					.gfp = pcl->besteffort ?
+						GFP_KERNEL | __GFP_NOFAIL :
+						GFP_NOWAIT | __GFP_NORETRY
 				 }, be->pagepool);
 
 	/* must handle all compressed pages before actual file pages */
@@ -1292,7 +1284,8 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 			/* consider shortlived pages added when decompressing */
 			page = be->compressed_pages[i];
 
-			if (!page || erofs_page_is_managed(sbi, page))
+			if (!page ||
+			    erofs_folio_is_managed(sbi, page_folio(page)))
 				continue;
 			(void)z_erofs_put_shortlivedpage(be->pagepool, page);
 			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
@@ -1313,7 +1306,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 		/* recycle all individual short-lived pages */
 		if (z_erofs_put_shortlivedpage(be->pagepool, page))
 			continue;
-		z_erofs_onlinepage_endio(page, err);
+		z_erofs_onlinefolio_end(page_folio(page), err);
 	}
 
 	if (be->decompressed_pages != be->onstack_pages)
@@ -1322,6 +1315,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	pcl->length = 0;
 	pcl->partial = true;
 	pcl->multibases = false;
+	pcl->besteffort = false;
 	pcl->bvset.nextpage = NULL;
 	pcl->vcnt = 0;
 
@@ -1423,69 +1417,61 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
 {
 	gfp_t gfp = mapping_gfp_mask(mc);
 	bool tocache = false;
-	struct z_erofs_bvec *zbv = pcl->compressed_bvecs + nr;
+	struct z_erofs_bvec zbv;
 	struct address_space *mapping;
-	struct page *page, *oldpage;
-	int justfound, bs = i_blocksize(f->inode);
+	struct page *page;
+	int bs = i_blocksize(f->inode);
 
-	/* Except for inplace pages, the entire page can be used for I/Os */
+	/* Except for inplace folios, the entire folio can be used for I/Os */
 	bvec->bv_offset = 0;
 	bvec->bv_len = PAGE_SIZE;
 repeat:
-	oldpage = READ_ONCE(zbv->page);
-	if (!oldpage)
-		goto out_allocpage;
-
-	justfound = (unsigned long)oldpage & 1UL;
-	page = (struct page *)((unsigned long)oldpage & ~1UL);
-	bvec->bv_page = page;
+	spin_lock(&pcl->obj.lockref.lock);
+	zbv = pcl->compressed_bvecs[nr];
+	spin_unlock(&pcl->obj.lockref.lock);
+	if (!zbv.folio)
+		goto out_allocfolio;
 
-	DBG_BUGON(z_erofs_is_shortlived_page(page));
+	bvec->bv_page = &zbv.folio->page;
+	DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page));
 	/*
-	 * Handle preallocated cached pages.  We tried to allocate such pages
+	 * Handle preallocated cached folios.  We tried to allocate such folios
 	 * without triggering direct reclaim.  If allocation failed, inplace
-	 * file-backed pages will be used instead.
+	 * file-backed folios will be used instead.
 	 */
-	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
-		set_page_private(page, 0);
-		WRITE_ONCE(zbv->page, page);
+	if (zbv.folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) {
+		zbv.folio->private = 0;
 		tocache = true;
 		goto out_tocache;
 	}
 
-	mapping = READ_ONCE(page->mapping);
+	mapping = READ_ONCE(zbv.folio->mapping);
 	/*
-	 * File-backed pages for inplace I/Os are all locked steady,
+	 * File-backed folios for inplace I/Os are all locked steady,
 	 * therefore it is impossible for `mapping` to be NULL.
 	 */
 	if (mapping && mapping != mc) {
-		if (zbv->offset < 0)
-			bvec->bv_offset = round_up(-zbv->offset, bs);
-		bvec->bv_len = round_up(zbv->end, bs) - bvec->bv_offset;
+		if (zbv.offset < 0)
+			bvec->bv_offset = round_up(-zbv.offset, bs);
+		bvec->bv_len = round_up(zbv.end, bs) - bvec->bv_offset;
 		return;
 	}
 
-	lock_page(page);
-	/* only true if page reclaim goes wrong, should never happen */
-	DBG_BUGON(justfound && PagePrivate(page));
-
-	/* the cached page is still in managed cache */
-	if (page->mapping == mc) {
-		WRITE_ONCE(zbv->page, page);
+	folio_lock(zbv.folio);
+	if (zbv.folio->mapping == mc) {
 		/*
-		 * The cached page is still available but without a valid
-		 * `->private` pcluster hint.  Let's reconnect them.
+		 * The cached folio is still in managed cache but without
+		 * a valid `->private` pcluster hint.  Let's reconnect them.
 		 */
-		if (!PagePrivate(page)) {
-			DBG_BUGON(!justfound);
-			/* compressed_bvecs[] already takes a ref */
-			attach_page_private(page, pcl);
-			put_page(page);
+		if (!folio_test_private(zbv.folio)) {
+			folio_attach_private(zbv.folio, pcl);
+			/* compressed_bvecs[] already takes a ref before */
+			folio_put(zbv.folio);
 		}
 
 		/* no need to submit if it is already up-to-date */
-		if (PageUptodate(page)) {
-			unlock_page(page);
+		if (folio_test_uptodate(zbv.folio)) {
+			folio_unlock(zbv.folio);
 			bvec->bv_page = NULL;
 		}
 		return;
@@ -1495,30 +1481,32 @@ repeat:
 	 * It has been truncated, so it's unsafe to reuse this one. Let's
 	 * allocate a new page for compressed data.
 	 */
-	DBG_BUGON(page->mapping);
-	DBG_BUGON(!justfound);
-
+	DBG_BUGON(zbv.folio->mapping);
 	tocache = true;
-	unlock_page(page);
-	put_page(page);
-out_allocpage:
+	folio_unlock(zbv.folio);
+	folio_put(zbv.folio);
+out_allocfolio:
 	page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
-	if (oldpage != cmpxchg(&zbv->page, oldpage, page)) {
+	spin_lock(&pcl->obj.lockref.lock);
+	if (pcl->compressed_bvecs[nr].folio) {
 		erofs_pagepool_add(&f->pagepool, page);
+		spin_unlock(&pcl->obj.lockref.lock);
 		cond_resched();
 		goto repeat;
 	}
+	pcl->compressed_bvecs[nr].folio = zbv.folio = page_folio(page);
+	spin_unlock(&pcl->obj.lockref.lock);
 	bvec->bv_page = page;
 out_tocache:
 	if (!tocache || bs != PAGE_SIZE ||
-	    add_to_page_cache_lru(page, mc, pcl->obj.index + nr, gfp)) {
-		/* turn into a temporary shortlived page (1 ref) */
-		set_page_private(page, Z_EROFS_SHORTLIVED_PAGE);
+	    filemap_add_folio(mc, zbv.folio, pcl->obj.index + nr, gfp)) {
+		/* turn into a temporary shortlived folio (1 ref) */
+		zbv.folio->private = (void *)Z_EROFS_SHORTLIVED_PAGE;
 		return;
 	}
-	attach_page_private(page, pcl);
+	folio_attach_private(zbv.folio, pcl);
 	/* drop a refcount added by allocpage (then 2 refs in total here) */
-	put_page(page);
+	folio_put(zbv.folio);
 }
 
 static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb,
@@ -1573,28 +1561,29 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
 	qtail[JQ_BYPASS] = &pcl->next;
 }
 
-static void z_erofs_submissionqueue_endio(struct bio *bio)
+static void z_erofs_endio(struct bio *bio)
 {
 	struct z_erofs_decompressqueue *q = bio->bi_private;
 	blk_status_t err = bio->bi_status;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
 
-		DBG_BUGON(PageUptodate(page));
-		DBG_BUGON(z_erofs_page_is_invalidated(page));
-		if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
-			if (!err)
-				SetPageUptodate(page);
-			unlock_page(page);
-		}
+		DBG_BUGON(folio_test_uptodate(folio));
+		DBG_BUGON(z_erofs_page_is_invalidated(&folio->page));
+		if (!erofs_folio_is_managed(EROFS_SB(q->sb), folio))
+			continue;
+
+		if (!err)
+			folio_mark_uptodate(folio);
+		folio_unlock(folio);
 	}
 	if (err)
 		q->eio = true;
 	z_erofs_decompress_kickoff(q, -1);
-	bio_put(bio);
+	if (bio->bi_bdev)
+		bio_put(bio);
 }
 
 static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
@@ -1608,7 +1597,6 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	z_erofs_next_pcluster_t owned_head = f->owned_head;
 	/* bio is NULL initially, so no need to initialize last_{index,bdev} */
 	erofs_off_t last_pa;
-	struct block_device *last_bdev;
 	unsigned int nr_bios = 0;
 	struct bio *bio = NULL;
 	unsigned long pflags;
@@ -1655,9 +1643,13 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 				continue;
 
 			if (bio && (cur != last_pa ||
-				    last_bdev != mdev.m_bdev)) {
-submit_bio_retry:
-				submit_bio(bio);
+				    bio->bi_bdev != mdev.m_bdev)) {
+io_retry:
+				if (!erofs_is_fscache_mode(sb))
+					submit_bio(bio);
+				else
+					erofs_fscache_submit_bio(bio);
+
 				if (memstall) {
 					psi_memstall_leave(&pflags);
 					memstall = 0;
@@ -1672,22 +1664,24 @@ submit_bio_retry:
 			}
 
 			if (!bio) {
-				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
-						REQ_OP_READ, GFP_NOIO);
-				bio->bi_end_io = z_erofs_submissionqueue_endio;
+				bio = erofs_is_fscache_mode(sb) ?
+					erofs_fscache_bio_alloc(&mdev) :
+					bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
+						  REQ_OP_READ, GFP_NOIO);
+				bio->bi_end_io = z_erofs_endio;
 				bio->bi_iter.bi_sector = cur >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
 				if (readahead)
 					bio->bi_opf |= REQ_RAHEAD;
 				++nr_bios;
-				last_bdev = mdev.m_bdev;
 			}
 
 			if (cur + bvec.bv_len > end)
 				bvec.bv_len = end - cur;
+			DBG_BUGON(bvec.bv_len < sb->s_blocksize);
 			if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
 					  bvec.bv_offset))
-				goto submit_bio_retry;
+				goto io_retry;
 
 			last_pa = cur + bvec.bv_len;
 			bypass = false;
@@ -1700,7 +1694,10 @@ submit_bio_retry:
 	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
 
 	if (bio) {
-		submit_bio(bio);
+		if (!erofs_is_fscache_mode(sb))
+			submit_bio(bio);
+		else
+			erofs_fscache_submit_bio(bio);
 		if (memstall)
 			psi_memstall_leave(&pflags);
 	}
@@ -1785,7 +1782,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
 			if (PageUptodate(page))
 				unlock_page(page);
 			else
-				(void)z_erofs_do_read_page(f, page);
+				z_erofs_scan_folio(f, page_folio(page), !!rac);
 			put_page(page);
 		}
 
@@ -1806,7 +1803,7 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 	f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT;
 
 	z_erofs_pcluster_readmore(&f, NULL, true);
-	err = z_erofs_do_read_page(&f, &folio->page);
+	err = z_erofs_scan_folio(&f, folio, false);
 	z_erofs_pcluster_readmore(&f, NULL, false);
 	z_erofs_pcluster_end(&f);
 
@@ -1847,7 +1844,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 		folio = head;
 		head = folio_get_private(folio);
 
-		err = z_erofs_do_read_page(&f, &folio->page);
+		err = z_erofs_scan_folio(&f, folio, true);
 		if (err && err != -EINTR)
 			erofs_err(inode->i_sb, "readahead error at folio %lu @ nid %llu",
 				  folio->index, EROFS_I(inode)->nid);
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ad8186d47ba7..9afdb722fa92 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -251,7 +251,7 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 	ssize_t res;
 	__u64 ucnt;
 
-	if (count < sizeof(ucnt))
+	if (count != sizeof(ucnt))
 		return -EINVAL;
 	if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
 		return -EFAULT;
@@ -283,13 +283,18 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c
 static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct eventfd_ctx *ctx = f->private_data;
+	__u64 cnt;
 
 	spin_lock_irq(&ctx->wqh.lock);
-	seq_printf(m, "eventfd-count: %16llx\n",
-		   (unsigned long long)ctx->count);
+	cnt = ctx->count;
 	spin_unlock_irq(&ctx->wqh.lock);
-	seq_printf(m, "eventfd-id: %d\n", ctx->id);
-	seq_printf(m, "eventfd-semaphore: %d\n",
+
+	seq_printf(m,
+		   "eventfd-count: %16llx\n"
+		   "eventfd-id: %d\n"
+		   "eventfd-semaphore: %d\n",
+		   cnt,
+		   ctx->id,
 		   !!(ctx->flags & EFD_SEMAPHORE));
 }
 #endif
@@ -383,6 +388,7 @@ static int do_eventfd(unsigned int count, int flags)
 	/* Check the EFD_* constants for consistency.  */
 	BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+	BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0));
 
 	if (flags & ~EFD_FLAGS_SET)
 		return -EINVAL;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3534d36a1474..39ac6fdf8bca 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -206,7 +206,7 @@ struct eventpoll {
 	 */
 	struct epitem *ovflist;
 
-	/* wakeup_source used when ep_scan_ready_list is running */
+	/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
 	struct wakeup_source *ws;
 
 	/* The user that created the eventpoll descriptor */
@@ -678,12 +678,6 @@ static void ep_done_scan(struct eventpoll *ep,
 	write_unlock_irq(&ep->lock);
 }
 
-static void epi_rcu_free(struct rcu_head *head)
-{
-	struct epitem *epi = container_of(head, struct epitem, rcu);
-	kmem_cache_free(epi_cache, epi);
-}
-
 static void ep_get(struct eventpoll *ep)
 {
 	refcount_inc(&ep->refcount);
@@ -767,7 +761,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	 * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
 	 * use of the rbn field.
 	 */
-	call_rcu(&epi->rcu, epi_rcu_free);
+	kfree_rcu(epi, rcu);
 
 	percpu_counter_dec(&ep->user->epoll_watches);
 	return ep_refcount_dec_and_test(ep);
@@ -1153,7 +1147,7 @@ static inline bool chain_epi_lockless(struct epitem *epi)
  * This callback takes a read lock in order not to contend with concurrent
  * events from another file descriptor, thus all modifications to ->rdllist
  * or ->ovflist are lockless.  Read lock is paired with the write lock from
- * ep_scan_ready_list(), which stops all list modifications and guarantees
+ * ep_start/done_scan(), which stops all list modifications and guarantees
  * that lists state is seen correctly.
  *
  * Another thing worth to mention is that ep_poll_callback() can be called
@@ -1751,7 +1745,7 @@ static int ep_send_events(struct eventpoll *ep,
 			 * availability. At this point, no one can insert
 			 * into ep->rdllist besides us. The epoll_ctl()
 			 * callers are locked out by
-			 * ep_scan_ready_list() holding "mtx" and the
+			 * ep_send_events() holding "mtx" and the
 			 * poll callback will queue them in ep->ovflist.
 			 */
 			list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1904,7 +1898,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		/*
-		 * Do the final check under the lock. ep_scan_ready_list()
+		 * Do the final check under the lock. ep_start/done_scan()
 		 * plays with two lists (->rdllist and ->ovflist) and there
 		 * is always a race when both lists are empty for short
 		 * period of time although events are pending, so lock is
diff --git a/fs/exec.c b/fs/exec.c
index e7d9d6ad980b..ff6f26671cfc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1158,7 +1158,6 @@ static int de_thread(struct task_struct *tsk)
 
 		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
 		leader->exit_state = EXIT_DEAD;
-
 		/*
 		 * We are going to release_task()->ptrace_unlink() silently,
 		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 9474cd50da6d..361595433480 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -275,6 +275,7 @@ struct exfat_sb_info {
 
 	spinlock_t inode_hash_lock;
 	struct hlist_head inode_hashtable[EXFAT_HASH_SIZE];
+	struct rcu_head rcu;
 };
 
 #define EXFAT_CACHE_VALID	0
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index d25a96a148af..cc00f1a7a1e1 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -35,13 +35,18 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 	if (new_num_clusters == num_clusters)
 		goto out;
 
-	exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags);
-	ret = exfat_find_last_cluster(sb, &clu, &last_clu);
-	if (ret)
-		return ret;
+	if (num_clusters) {
+		exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags);
+		ret = exfat_find_last_cluster(sb, &clu, &last_clu);
+		if (ret)
+			return ret;
+
+		clu.dir = last_clu + 1;
+	} else {
+		last_clu = EXFAT_EOF_CLUSTER;
+		clu.dir = EXFAT_EOF_CLUSTER;
+	}
 
-	clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ?
-			EXFAT_EOF_CLUSTER : last_clu + 1;
 	clu.size = 0;
 	clu.flags = ei->flags;
 
@@ -51,17 +56,19 @@ static int exfat_cont_expand(struct inode *inode, loff_t size)
 		return ret;
 
 	/* Append new clusters to chain */
-	if (clu.flags != ei->flags) {
-		exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters);
-		ei->flags = ALLOC_FAT_CHAIN;
-	}
-	if (clu.flags == ALLOC_FAT_CHAIN)
-		if (exfat_ent_set(sb, last_clu, clu.dir))
-			goto free_clu;
-
-	if (num_clusters == 0)
+	if (num_clusters) {
+		if (clu.flags != ei->flags)
+			if (exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters))
+				goto free_clu;
+
+		if (clu.flags == ALLOC_FAT_CHAIN)
+			if (exfat_ent_set(sb, last_clu, clu.dir))
+				goto free_clu;
+	} else
 		ei->start_clu = clu.dir;
 
+	ei->flags = clu.flags;
+
 out:
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	/* Expanded range not zeroed, do not update valid_size */
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 522edcbb2ce4..0687f952956c 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -501,7 +501,7 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	loff_t pos = iocb->ki_pos;
-	loff_t size = iocb->ki_pos + iov_iter_count(iter);
+	loff_t size = pos + iov_iter_count(iter);
 	int rw = iov_iter_rw(iter);
 	ssize_t ret;
 
@@ -525,11 +525,10 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block);
 	if (ret < 0) {
-		if (rw == WRITE)
+		if (rw == WRITE && ret != -EIOCBQUEUED)
 			exfat_write_failed(mapping, size);
 
-		if (ret != -EIOCBQUEUED)
-			return ret;
+		return ret;
 	} else
 		size = pos + ret;
 
diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
index 705710f93e2d..afdf13c34ff5 100644
--- a/fs/exfat/nls.c
+++ b/fs/exfat/nls.c
@@ -655,7 +655,6 @@ static int exfat_load_upcase_table(struct super_block *sb,
 	unsigned int sect_size = sb->s_blocksize;
 	unsigned int i, index = 0;
 	u32 chksum = 0;
-	int ret;
 	unsigned char skip = false;
 	unsigned short *upcase_table;
 
@@ -673,8 +672,7 @@ static int exfat_load_upcase_table(struct super_block *sb,
 		if (!bh) {
 			exfat_err(sb, "failed to read sector(0x%llx)",
 				  (unsigned long long)sector);
-			ret = -EIO;
-			goto free_table;
+			return -EIO;
 		}
 		sector++;
 		for (i = 0; i < sect_size && index <= 0xFFFF; i += 2) {
@@ -701,15 +699,12 @@ static int exfat_load_upcase_table(struct super_block *sb,
 
 	exfat_err(sb, "failed to load upcase table (idx : 0x%08x, chksum : 0x%08x, utbl_chksum : 0x%08x)",
 		  index, chksum, utbl_checksum);
-	ret = -EINVAL;
-free_table:
-	exfat_free_upcase_table(sbi);
-	return ret;
+	return -EINVAL;
 }
 
 static int exfat_load_default_upcase_table(struct super_block *sb)
 {
-	int i, ret = -EIO;
+	int i;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 	unsigned char skip = false;
 	unsigned short uni = 0, *upcase_table;
@@ -740,8 +735,7 @@ static int exfat_load_default_upcase_table(struct super_block *sb)
 		return 0;
 
 	/* FATAL error: default upcase table has error */
-	exfat_free_upcase_table(sbi);
-	return ret;
+	return -EIO;
 }
 
 int exfat_create_upcase_table(struct super_block *sb)
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index d9d4fa91010b..fcb658267765 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -39,9 +39,6 @@ static void exfat_put_super(struct super_block *sb)
 	exfat_free_bitmap(sbi);
 	brelse(sbi->boot_bh);
 	mutex_unlock(&sbi->s_lock);
-
-	unload_nls(sbi->nls_io);
-	exfat_free_upcase_table(sbi);
 }
 
 static int exfat_sync_fs(struct super_block *sb, int wait)
@@ -600,7 +597,7 @@ static int __exfat_fill_super(struct super_block *sb)
 	ret = exfat_load_bitmap(sb);
 	if (ret) {
 		exfat_err(sb, "failed to load alloc-bitmap");
-		goto free_upcase_table;
+		goto free_bh;
 	}
 
 	ret = exfat_count_used_clusters(sb, &sbi->used_clusters);
@@ -613,8 +610,6 @@ static int __exfat_fill_super(struct super_block *sb)
 
 free_alloc_bitmap:
 	exfat_free_bitmap(sbi);
-free_upcase_table:
-	exfat_free_upcase_table(sbi);
 free_bh:
 	brelse(sbi->boot_bh);
 	return ret;
@@ -701,12 +696,10 @@ put_inode:
 	sb->s_root = NULL;
 
 free_table:
-	exfat_free_upcase_table(sbi);
 	exfat_free_bitmap(sbi);
 	brelse(sbi->boot_bh);
 
 check_nls_io:
-	unload_nls(sbi->nls_io);
 	return err;
 }
 
@@ -771,13 +764,22 @@ static int exfat_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu);
+
+	unload_nls(sbi->nls_io);
+	exfat_free_upcase_table(sbi);
+	exfat_free_sbi(sbi);
+}
+
 static void exfat_kill_sb(struct super_block *sb)
 {
 	struct exfat_sb_info *sbi = sb->s_fs_info;
 
 	kill_block_super(sb);
 	if (sbi)
-		exfat_free_sbi(sbi);
+		call_rcu(&sbi->rcu, delayed_free);
 }
 
 static struct file_system_type exfat_fs_type = {
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 3ae0154c5680..07ea3d62b298 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -255,7 +255,7 @@ static bool filldir_one(struct dir_context *ctx, const char *name, int len,
 		container_of(ctx, struct getdents_callback, ctx);
 
 	buf->sequence++;
-	if (buf->ino == ino && len <= NAME_MAX) {
+	if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) {
 		memcpy(buf->name, name, len);
 		buf->name[len] = '\0';
 		buf->found = 1;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a5d784872303..3c0d7d143036 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -252,8 +252,10 @@ struct ext4_allocation_request {
 #define EXT4_MAP_MAPPED		BIT(BH_Mapped)
 #define EXT4_MAP_UNWRITTEN	BIT(BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	BIT(BH_Boundary)
+#define EXT4_MAP_DELAYED	BIT(BH_Delay)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
-				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+				 EXT4_MAP_DELAYED)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
@@ -1548,7 +1550,7 @@ struct ext4_sb_info {
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
-	struct bdev_handle *s_journal_bdev_handle;
+	struct file *s_journal_bdev_file;
 #ifdef CONFIG_QUOTA
 	/* Names of quota files with journalled quota */
 	char __rcu *s_qf_names[EXT4_MAXQUOTAS];
@@ -2912,10 +2914,10 @@ extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
 extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
 extern int ext4_mb_init(struct super_block *);
-extern int ext4_mb_release(struct super_block *);
+extern void ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
-extern void ext4_discard_preallocations(struct inode *, unsigned int);
+extern void ext4_discard_preallocations(struct inode *);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
 extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01299b55a567..7669d154c05e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
@@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode,
 
 
 /*
- * ext4_ext_determine_hole - determine hole around given block
+ * ext4_ext_find_hole - find hole around given block according to the given path
  * @inode:	inode we lookup in
  * @path:	path in extent tree to @lblk
  * @lblk:	pointer to logical block around which we want to determine hole
@@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode,
  * The function returns the length of a hole starting at @lblk. We update @lblk
  * to the beginning of the hole if we managed to find it.
  */
-static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
-					   struct ext4_ext_path *path,
-					   ext4_lblk_t *lblk)
+static ext4_lblk_t ext4_ext_find_hole(struct inode *inode,
+				      struct ext4_ext_path *path,
+				      ext4_lblk_t *lblk)
 {
 	int depth = ext_depth(inode);
 	struct ext4_extent *ex;
@@ -2271,30 +2271,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
 }
 
 /*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
- */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
-			  ext4_lblk_t hole_len)
-{
-	struct extent_status es;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
-				  hole_start + hole_len - 1, &es);
-	if (es.es_len) {
-		/* There's delayed extent containing lblock? */
-		if (es.es_lblk <= hole_start)
-			return;
-		hole_len = min(es.es_lblk - hole_start, hole_len);
-	}
-	ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
-	ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
-			      EXTENT_STATUS_HOLE);
-}
-
-/*
  * ext4_ext_rm_idx:
  * removes index from the index block.
  */
@@ -4062,6 +4038,72 @@ static int get_implied_cluster_alloc(struct super_block *sb,
 	return 0;
 }
 
+/*
+ * Determine hole length around the given logical block, first try to
+ * locate and expand the hole from the given @path, and then adjust it
+ * if it's partially or completely converted to delayed extents, insert
+ * it into the extent cache tree if it's indeed a hole, finally return
+ * the length of the determined extent.
+ */
+static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
+						  struct ext4_ext_path *path,
+						  ext4_lblk_t lblk)
+{
+	ext4_lblk_t hole_start, len;
+	struct extent_status es;
+
+	hole_start = lblk;
+	len = ext4_ext_find_hole(inode, path, &hole_start);
+again:
+	ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
+				  hole_start + len - 1, &es);
+	if (!es.es_len)
+		goto insert_hole;
+
+	/*
+	 * There's a delalloc extent in the hole, handle it if the delalloc
+	 * extent is in front of, behind and straddle the queried range.
+	 */
+	if (lblk >= es.es_lblk + es.es_len) {
+		/*
+		 * The delalloc extent is in front of the queried range,
+		 * find again from the queried start block.
+		 */
+		len -= lblk - hole_start;
+		hole_start = lblk;
+		goto again;
+	} else if (in_range(lblk, es.es_lblk, es.es_len)) {
+		/*
+		 * The delalloc extent containing lblk, it must have been
+		 * added after ext4_map_blocks() checked the extent status
+		 * tree so we are not holding i_rwsem and delalloc info is
+		 * only stabilized by i_data_sem we are going to release
+		 * soon. Don't modify the extent status tree and report
+		 * extent as a hole, just adjust the length to the delalloc
+		 * extent's after lblk.
+		 */
+		len = es.es_lblk + es.es_len - lblk;
+		return len;
+	} else {
+		/*
+		 * The delalloc extent is partially or completely behind
+		 * the queried range, update hole length until the
+		 * beginning of the delalloc extent.
+		 */
+		len = min(es.es_lblk - hole_start, len);
+	}
+
+insert_hole:
+	/* Put just found gap into cache to speed up subsequent requests */
+	ext_debug(inode, " -> %u:%u\n", hole_start, len);
+	ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE);
+
+	/* Update hole_len to reflect hole size after lblk */
+	if (hole_start != lblk)
+		len -= lblk - hole_start;
+
+	return len;
+}
 
 /*
  * Block allocation/map/preallocation routine for extents based files
@@ -4179,22 +4221,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 * we couldn't try to create block if create flag is zero
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
-		ext4_lblk_t hole_start, hole_len;
+		ext4_lblk_t len;
 
-		hole_start = map->m_lblk;
-		hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
-		/*
-		 * put just found gap into cache to speed up
-		 * subsequent requests
-		 */
-		ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+		len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk);
 
-		/* Update hole_len to reflect hole size after map->m_lblk */
-		if (hole_start != map->m_lblk)
-			hole_len -= map->m_lblk - hole_start;
 		map->m_pblk = 0;
-		map->m_len = min_t(unsigned int, map->m_len, hole_len);
-
+		map->m_len = min_t(unsigned int, map->m_len, len);
 		goto out;
 	}
 
@@ -4313,7 +4345,7 @@ got_allocated_blocks:
 			 * not a good idea to call discard here directly,
 			 * but otherwise we'd need to call it every free().
 			 */
-			ext4_discard_preallocations(inode, 0);
+			ext4_discard_preallocations(inode);
 			if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 				fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
 			ext4_free_blocks(handle, inode, NULL, newblock,
@@ -5357,7 +5389,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 	ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start);
 
 	ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
@@ -5365,7 +5397,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
 		up_write(&EXT4_I(inode)->i_data_sem);
 		goto out_stop;
 	}
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
 				     punch_stop - punch_start, SHIFT_LEFT);
@@ -5497,7 +5529,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6aa15dafc677..54d6ff22585c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -174,7 +174,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 			(atomic_read(&inode->i_writecount) == 1) &&
 			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 11e6f33677a2..df853c4d3a8c 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -576,9 +576,9 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb,
 	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
 	    fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev))
 		return true;
-	if (EXT4_SB(sb)->s_journal_bdev_handle &&
+	if (EXT4_SB(sb)->s_journal_bdev_file &&
 	    fm->fmr_device ==
-	    new_encode_dev(EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev))
+	    new_encode_dev(file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev))
 		return true;
 	return false;
 }
@@ -648,9 +648,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
 	memset(handlers, 0, sizeof(handlers));
 	handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev);
 	handlers[0].gfd_fn = ext4_getfsmap_datadev;
-	if (EXT4_SB(sb)->s_journal_bdev_handle) {
+	if (EXT4_SB(sb)->s_journal_bdev_file) {
 		handlers[1].gfd_dev = new_encode_dev(
-			EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev);
+			file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev);
 		handlers[1].gfd_fn = ext4_getfsmap_logdev;
 	}
 
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index a9f3716119d3..d8ca7f64f952 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -714,7 +714,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
 	 * i_rwsem. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5af1b0b8680e..2ccf3b5e3a7c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -371,7 +371,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
 	    !inode_is_open_for_write(inode))
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 }
 
 static int __check_block_validity(struct inode *inode, const char *func,
@@ -515,6 +515,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			map->m_len = retval;
 		} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
 			map->m_pblk = 0;
+			map->m_flags |= ext4_es_is_delayed(&es) ?
+					EXT4_MAP_DELAYED : 0;
 			retval = es.es_len - (map->m_lblk - es.es_lblk);
 			if (retval > map->m_len)
 				retval = map->m_len;
@@ -1703,11 +1705,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
-		if (ext4_es_is_hole(&es)) {
-			retval = 0;
-			down_read(&EXT4_I(inode)->i_data_sem);
+		if (ext4_es_is_hole(&es))
 			goto add_delayed;
-		}
 
 		/*
 		 * Delayed extent could be allocated by fallocate.
@@ -1749,26 +1748,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
 		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-
-add_delayed:
-	if (retval == 0) {
-		int ret;
-
-		/*
-		 * XXX: __block_prepare_write() unmaps passed block,
-		 * is it OK?
-		 */
-
-		ret = ext4_insert_delayed_block(inode, map->m_lblk);
-		if (ret != 0) {
-			retval = ret;
-			goto out_unlock;
-		}
-
-		map_bh(bh, inode->i_sb, invalid_block);
-		set_buffer_new(bh);
-		set_buffer_delay(bh);
-	} else if (retval > 0) {
+	if (retval < 0) {
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
+	}
+	if (retval > 0) {
 		unsigned int status;
 
 		if (unlikely(retval != map->m_len)) {
@@ -1783,11 +1767,21 @@ add_delayed:
 				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
 				      map->m_pblk, status);
+		up_read(&EXT4_I(inode)->i_data_sem);
+		return retval;
 	}
+	up_read(&EXT4_I(inode)->i_data_sem);
 
-out_unlock:
-	up_read((&EXT4_I(inode)->i_data_sem));
+add_delayed:
+	down_write(&EXT4_I(inode)->i_data_sem);
+	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	up_write(&EXT4_I(inode)->i_data_sem);
+	if (retval)
+		return retval;
 
+	map_bh(bh, inode->i_sb, invalid_block);
+	set_buffer_new(bh);
+	set_buffer_delay(bh);
 	return retval;
 }
 
@@ -3268,6 +3262,9 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 		iomap->addr = (u64) map->m_pblk << blkbits;
 		if (flags & IOMAP_DAX)
 			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
+	} else if (map->m_flags & EXT4_MAP_DELAYED) {
+		iomap->type = IOMAP_DELALLOC;
+		iomap->addr = IOMAP_NULL_ADDR;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3430,35 +3427,11 @@ const struct iomap_ops ext4_iomap_overwrite_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
-static bool ext4_iomap_is_delalloc(struct inode *inode,
-				   struct ext4_map_blocks *map)
-{
-	struct extent_status es;
-	ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
-
-	ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
-				  map->m_lblk, end, &es);
-
-	if (!es.es_len || es.es_lblk > end)
-		return false;
-
-	if (es.es_lblk > map->m_lblk) {
-		map->m_len = es.es_lblk - map->m_lblk;
-		return false;
-	}
-
-	offset = map->m_lblk - es.es_lblk;
-	map->m_len = es.es_len - offset;
-
-	return true;
-}
-
 static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 				   loff_t length, unsigned int flags,
 				   struct iomap *iomap, struct iomap *srcmap)
 {
 	int ret;
-	bool delalloc = false;
 	struct ext4_map_blocks map;
 	u8 blkbits = inode->i_blkbits;
 
@@ -3499,13 +3472,8 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 	ret = ext4_map_blocks(NULL, inode, &map, 0);
 	if (ret < 0)
 		return ret;
-	if (ret == 0)
-		delalloc = ext4_iomap_is_delalloc(inode, &map);
-
 set_iomap:
 	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
-	if (delalloc && iomap->type == IOMAP_HOLE)
-		iomap->type = IOMAP_DELALLOC;
 
 	return 0;
 }
@@ -4015,12 +3983,12 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 
 	/* If there are blocks to remove, do it */
 	if (stop_block > first_block) {
+		ext4_lblk_t hole_len = stop_block - first_block;
 
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode, 0);
+		ext4_discard_preallocations(inode);
 
-		ext4_es_remove_extent(inode, first_block,
-				      stop_block - first_block);
+		ext4_es_remove_extent(inode, first_block, hole_len);
 
 		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 			ret = ext4_ext_remove_space(inode, first_block,
@@ -4029,6 +3997,8 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
 			ret = ext4_ind_remove_space(handle, inode, first_block,
 						    stop_block);
 
+		ext4_es_insert_extent(inode, first_block, hole_len, ~0,
+				      EXTENT_STATUS_HOLE);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	ext4_fc_track_range(handle, inode, first_block, stop_block);
@@ -4170,7 +4140,7 @@ int ext4_truncate(struct inode *inode)
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		err = ext4_ext_truncate(handle, inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index aa6be510eb8f..7160a71044c8 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -467,7 +467,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_reset_inode_seed(inode);
 	ext4_reset_inode_seed(inode_bl);
 
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f44f668e407f..e4f7cf9d89c4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 			blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
 					      "freeing block already freed "
 					      "(bit %u)",
 					      first + i);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
 		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
 	}
@@ -677,7 +677,7 @@ do {									\
 	}								\
 } while (0)
 
-static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+static void __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 				const char *function, int line)
 {
 	struct super_block *sb = e4b->bd_sb;
@@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	void *buddy2;
 
 	if (e4b->bd_info->bb_check_counter++ % 10)
-		return 0;
+		return;
 
 	while (order > 1) {
 		buddy = mb_find_buddy(e4b, order, &max);
@@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
 	if (!grp)
-		return NULL;
+		return;
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 		for (i = 0; i < pa->pa_len; i++)
 			MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
 	}
-	return 0;
 }
 #undef MB_CHECK_ASSERT
 #define mb_check_buddy(e4b) __mb_check_buddy(e4b,	\
@@ -842,7 +841,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int new_order;
 
-	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
 		return;
 
 	new_order = mb_avg_fragment_size_order(sb,
@@ -871,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
  * cr level needs an update.
  */
 static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac,
-			enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+			enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *iter;
@@ -945,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o
  * order. Updates *new_cr if cr level needs an update.
  */
 static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -990,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *
  * much and fall to CR_GOAL_LEN_SLOW in that case.
  */
 static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -1125,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 	}
 
 	if (*new_cr == CR_POWER2_ALIGNED) {
-		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group);
 	} else if (*new_cr == CR_GOAL_LEN_FAST) {
-		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group);
 	} else if (*new_cr == CR_BEST_AVAIL_LEN) {
-		ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
 	} else {
 		/*
 		 * TODO: For CR=2, we can arrange groups in an rb tree sorted by
@@ -1233,6 +1232,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	atomic64_add(period, &sbi->s_mb_generation_time);
 }
 
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+	int count;
+	int order = 1;
+	void *buddy;
+
+	while ((buddy = mb_find_buddy(e4b, order++, &count)))
+		mb_set_bits(buddy, 0, count);
+
+	e4b->bd_info->bb_fragments = 0;
+	memset(e4b->bd_info->bb_counters, 0,
+		sizeof(*e4b->bd_info->bb_counters) *
+		(e4b->bd_sb->s_blocksize_bits + 2));
+
+	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+		e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -1891,11 +1908,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
-	this_cpu_inc(discard_pa_seq);
-	e4b->bd_info->bb_free += count;
-	if (first < e4b->bd_info->bb_first_free)
-		e4b->bd_info->bb_first_free = first;
-
 	/* access memory sequentially: check left neighbour,
 	 * clear range and then check right neighbour
 	 */
@@ -1909,21 +1921,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
+		/*
+		 * Fastcommit replay can free already freed blocks which
+		 * corrupts allocation info. Regenerate it.
+		 */
+		if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+			mb_regenerate_buddy(e4b);
+			goto check;
+		}
+
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
-			ext4_grp_locked_error(sb, e4b->bd_group,
-					      inode ? inode->i_ino : 0,
-					      blocknr,
-					      "freeing already freed block (bit %u); block bitmap corrupt.",
-					      block);
-			ext4_mark_group_bitmap_corrupted(
-				sb, e4b->bd_group,
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
-		}
-		goto done;
+		ext4_grp_locked_error(sb, e4b->bd_group,
+				      inode ? inode->i_ino : 0, blocknr,
+				      "freeing already freed block (bit %u); block bitmap corrupt.",
+				      block);
+		return;
 	}
 
+	this_cpu_inc(discard_pa_seq);
+	e4b->bd_info->bb_free += count;
+	if (first < e4b->bd_info->bb_first_free)
+		e4b->bd_info->bb_first_free = first;
+
 	/* let's maintain fragments counter */
 	if (left_is_free && right_is_free)
 		e4b->bd_info->bb_fragments--;
@@ -1948,9 +1970,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	if (first <= last)
 		mb_buddy_mark_free(e4b, first >> 1, last >> 1);
 
-done:
 	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
 	mb_check_buddy(e4b);
 }
 
@@ -2276,6 +2298,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		return;
 
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
 
 	if (max > 0) {
@@ -2283,6 +2308,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		ext4_mb_use_best_found(ac, e4b);
 	}
 
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 }
@@ -2309,12 +2335,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	if (err)
 		return err;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
-		ext4_mb_unload_buddy(e4b);
-		return 0;
-	}
-
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
 	ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -2347,6 +2371,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 		ac->ac_b_ex = ex;
 		ext4_mb_use_best_found(ac, e4b);
 	}
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 
@@ -2380,12 +2405,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 
 		k = mb_find_next_zero_bit(buddy, max, 0);
 		if (k >= max) {
+			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
+					e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0,
 				"%d free clusters of order %d. But found 0",
 				grp->bb_counters[i], i);
-			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
-					 e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 		ac->ac_found++;
@@ -2436,12 +2461,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 			 * free blocks even though group info says we
 			 * have free blocks
 			 */
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 
@@ -2467,12 +2492,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		if (WARN_ON(ex.fe_len <= 0))
 			break;
 		if (free < ex.fe_len) {
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			/*
 			 * The number of free blocks differs. This mostly
 			 * indicate that the bitmap is corrupt. So exit
@@ -3725,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 	return count;
 }
 
-int ext4_mb_release(struct super_block *sb)
+void ext4_mb_release(struct super_block *sb)
 {
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
@@ -3801,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-
-	return 0;
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
@@ -5284,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
  * the caller MUST hold group/inode locks.
  * TODO: optimize the case when there are no in-core structures yet
  */
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			struct ext4_prealloc_space *pa)
 {
@@ -5334,11 +5357,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		 */
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
-
-	return 0;
 }
 
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 				struct ext4_prealloc_space *pa)
 {
@@ -5352,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
 		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
 			     e4b->bd_group, group, pa->pa_pstart);
-		return 0;
+		return;
 	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
-
-	return 0;
 }
 
 /*
@@ -5479,7 +5498,7 @@ out_dbg:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
+void ext4_discard_preallocations(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -5491,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	struct rb_node *iter;
 	int err;
 
-	if (!S_ISREG(inode->i_mode)) {
+	if (!S_ISREG(inode->i_mode))
 		return;
-	}
 
 	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
@@ -5501,15 +5519,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
-			atomic_read(&ei->i_prealloc_active), needed);
-
-	if (needed == 0)
-		needed = UINT_MAX;
+			atomic_read(&ei->i_prealloc_active));
 
 repeat:
 	/* first, collect all pa's in the inode */
 	write_lock(&ei->i_prealloc_lock);
-	for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+	for (iter = rb_first(&ei->i_prealloc_node); iter;
 	     iter = rb_next(iter)) {
 		pa = rb_entry(iter, struct ext4_prealloc_space,
 			      pa_node.inode_node);
@@ -5533,7 +5548,6 @@ repeat:
 			spin_unlock(&pa->pa_lock);
 			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
 			list_add(&pa->u.pa_tmp_list, &list);
-			needed--;
 			continue;
 		}
 
@@ -5943,7 +5957,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 /*
  * release all resource we used in allocation
  */
-static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+static void ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
@@ -5980,7 +5994,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
-	return 0;
 }
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
@@ -6761,6 +6774,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 	bool set_trimmed = false;
 	void *bitmap;
 
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		return 0;
+
 	last = ext4_last_grp_cluster(sb, e4b->bd_group);
 	bitmap = e4b->bd_bitmap;
 	if (start == 0 && max >= last)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d7aeb5da7d86..56938532b4ce 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -192,7 +192,6 @@ struct ext4_allocation_context {
 	 */
 	ext4_grpblk_t	ac_orig_goal_len;
 
-	__u32 ac_groups_considered;
 	__u32 ac_flags;		/* allocation hints */
 	__u16 ac_groups_scanned;
 	__u16 ac_groups_linear_remaining;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3aa57376d9c2..7cd4afa4de1d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -618,6 +618,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		goto out;
 	o_end = o_start + len;
 
+	*moved_len = 0;
 	while (o_start < o_end) {
 		struct ext4_extent *ex;
 		ext4_lblk_t cur_blk, next_blk;
@@ -672,7 +673,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		 */
 		ext4_double_up_write_data_sem(orig_inode, donor_inode);
 		/* Swap original branches with new branches */
-		move_extent_per_page(o_filp, donor_inode,
+		*moved_len += move_extent_per_page(o_filp, donor_inode,
 				     orig_page_index, donor_page_index,
 				     offset_in_page, cur_len,
 				     unwritten, &ret);
@@ -682,14 +683,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
 		o_start += cur_len;
 		d_start += cur_len;
 	}
-	*moved_len = o_start - orig_blk;
-	if (*moved_len > len)
-		*moved_len = len;
 
 out:
 	if (*moved_len) {
-		ext4_discard_preallocations(orig_inode, 0);
-		ext4_discard_preallocations(donor_inode, 0);
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
 	}
 
 	ext4_free_ext_path(path);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 05b647e6bc19..5e4f65c14dfb 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1762,7 +1762,6 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
 	struct buffer_head *bh;
 
 	err = ext4_fname_prepare_lookup(dir, dentry, &fname);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return NULL;
 	if (err)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dcba0f85dfe2..a8ba84eabab2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1359,14 +1359,14 @@ static void ext4_put_super(struct super_block *sb)
 
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
-	if (sbi->s_journal_bdev_handle) {
+	if (sbi->s_journal_bdev_file) {
 		/*
 		 * Invalidate the journal device's buffers.  We don't want them
 		 * floating about in memory - the physical journal device may
 		 * hotswapped, and it breaks the `ro-after' testing code.
 		 */
-		sync_blockdev(sbi->s_journal_bdev_handle->bdev);
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
+		sync_blockdev(file_bdev(sbi->s_journal_bdev_file));
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
 	}
 
 	ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
@@ -1525,7 +1525,7 @@ void ext4_clear_inode(struct inode *inode)
 	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode, 0);
+	ext4_discard_preallocations(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
@@ -4233,7 +4233,7 @@ int ext4_calculate_overhead(struct super_block *sb)
 	 * Add the internal journal blocks whether the journal has been
 	 * loaded or not
 	 */
-	if (sbi->s_journal && !sbi->s_journal_bdev_handle)
+	if (sbi->s_journal && !sbi->s_journal_bdev_file)
 		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
@@ -5346,7 +5346,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		sb->s_qcop = &ext4_qctl_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
-	memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+	super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid));
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
@@ -5484,6 +5484,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount4;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");
@@ -5670,9 +5671,9 @@ failed_mount:
 #endif
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 	brelse(sbi->s_sbh);
-	if (sbi->s_journal_bdev_handle) {
-		invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
-		bdev_release(sbi->s_journal_bdev_handle);
+	if (sbi->s_journal_bdev_file) {
+		invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
+		fput(sbi->s_journal_bdev_file);
 	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
@@ -5842,30 +5843,30 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb,
 	return journal;
 }
 
-static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
+static struct file *ext4_get_journal_blkdev(struct super_block *sb,
 					dev_t j_dev, ext4_fsblk_t *j_start,
 					ext4_fsblk_t *j_len)
 {
 	struct buffer_head *bh;
 	struct block_device *bdev;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int hblock, blocksize;
 	ext4_fsblk_t sb_block;
 	unsigned long offset;
 	struct ext4_super_block *es;
 	int errno;
 
-	bdev_handle = bdev_open_by_dev(j_dev,
+	bdev_file = bdev_file_open_by_dev(j_dev,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
 		sb, &fs_holder_ops);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		ext4_msg(sb, KERN_ERR,
 			 "failed to open journal device unknown-block(%u,%u) %ld",
-			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle));
-		return bdev_handle;
+			 MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file));
+		return bdev_file;
 	}
 
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 	blocksize = sb->s_blocksize;
 	hblock = bdev_logical_block_size(bdev);
 	if (blocksize < hblock) {
@@ -5912,12 +5913,12 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
 	*j_start = sb_block + 1;
 	*j_len = ext4_blocks_count(es);
 	brelse(bh);
-	return bdev_handle;
+	return bdev_file;
 
 out_bh:
 	brelse(bh);
 out_bdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -5927,14 +5928,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 	journal_t *journal;
 	ext4_fsblk_t j_start;
 	ext4_fsblk_t j_len;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int errno = 0;
 
-	bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
-	if (IS_ERR(bdev_handle))
-		return ERR_CAST(bdev_handle);
+	bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
+	if (IS_ERR(bdev_file))
+		return ERR_CAST(bdev_file);
 
-	journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start,
+	journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start,
 					j_len, sb->s_blocksize);
 	if (IS_ERR(journal)) {
 		ext4_msg(sb, KERN_ERR, "failed to create device journal");
@@ -5949,14 +5950,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
 		goto out_journal;
 	}
 	journal->j_private = sb;
-	EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle;
+	EXT4_SB(sb)->s_journal_bdev_file = bdev_file;
 	ext4_init_journal_params(sb, journal);
 	return journal;
 
 out_journal:
 	jbd2_journal_destroy(journal);
 out_bdev:
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 	return ERR_PTR(errno);
 }
 
@@ -7314,12 +7315,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
 static void ext4_kill_sb(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL;
+	struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL;
 
 	kill_block_super(sb);
 
-	if (handle)
-		bdev_release(handle);
+	if (bdev_file)
+		fput(bdev_file);
 }
 
 static struct file_system_type ext4_fs_type = {
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 75bf1f88843c..645240cc0229 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -92,10 +92,12 @@ static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
 
 	if (!dentry) {
 		bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
-		if (IS_ERR(bh))
-			return ERR_CAST(bh);
-		if (!bh || !ext4_buffer_uptodate(bh))
+		if (IS_ERR(bh) || !bh)
 			return ERR_PTR(-ECHILD);
+		if (!ext4_buffer_uptodate(bh)) {
+			brelse(bh);
+			return ERR_PTR(-ECHILD);
+		}
 	} else {
 		bh = ext4_bread(NULL, inode, 0, 0);
 		if (IS_ERR(bh))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 65294e3b0bef..4c77e8ce5c75 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -24,6 +24,7 @@
 #include <linux/blkdev.h>
 #include <linux/quotaops.h>
 #include <linux/part_stat.h>
+#include <linux/rw_hint.h>
 #include <crypto/hash.h>
 
 #include <linux/fscrypt.h>
@@ -1239,7 +1240,7 @@ struct f2fs_bio_info {
 #define FDEV(i)				(sbi->devs[i])
 #define RDEV(i)				(raw_super->devs[i])
 struct f2fs_dev_info {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 	char path[MAX_PATH_LEN];
 	unsigned int total_segments;
@@ -3364,17 +3365,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
 	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
 }
 
-static inline bool is_dot_dotdot(const u8 *name, size_t len)
-{
-	if (len == 1 && name[0] == '.')
-		return true;
-
-	if (len == 2 && name[0] == '.' && name[1] == '.')
-		return true;
-
-	return false;
-}
-
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index b3bb815fc6aa..f7f63a567d86 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -531,7 +531,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = f2fs_prepare_lookup(dir, dentry, &fname);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		goto out_splice;
 	if (err)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4c8836ded90f..e1065ba70207 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1971,9 +1971,15 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 		}
 
 		if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) {
+			unsigned int nofs_flags;
+			int ret;
+
 			trace_f2fs_issue_reset_zone(bdev, blkstart);
-			return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
-						sector, nr_sects, GFP_NOFS);
+			nofs_flags = memalloc_nofs_save();
+			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+						sector, nr_sects);
+			memalloc_nofs_restore(nofs_flags);
+			return ret;
 		}
 
 		__queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen);
@@ -4865,6 +4871,7 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 	block_t zone_block, valid_block_cnt;
 	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
 	int ret;
+	unsigned int nofs_flags;
 
 	if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
 		return 0;
@@ -4912,8 +4919,10 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
 		    "pointer: valid block[0x%x,0x%x] cond[0x%x]",
 		    zone_segno, valid_block_cnt, zone->cond);
 
+	nofs_flags = memalloc_nofs_save();
 	ret = blkdev_zone_mgmt(fdev->bdev, REQ_OP_ZONE_FINISH,
-				zone->start, zone->len, GFP_NOFS);
+				zone->start, zone->len);
+	memalloc_nofs_restore(nofs_flags);
 	if (ret == -EOPNOTSUPP) {
 		ret = blkdev_issue_zeroout(fdev->bdev, zone->wp,
 					zone->len - (zone->wp - zone->start),
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d45ab0992ae5..b880b746f226 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1605,7 +1605,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		if (i > 0)
-			bdev_release(FDEV(i).bdev_handle);
+			fput(FDEV(i).bdev_file);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -4247,7 +4247,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < max_devices; i++) {
 		if (i == 0)
-			FDEV(0).bdev_handle = sbi->sb->s_bdev_handle;
+			FDEV(0).bdev_file = sbi->sb->s_bdev_file;
 		else if (!RDEV(i).path[0])
 			break;
 
@@ -4267,14 +4267,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 				FDEV(i).end_blk = FDEV(i).start_blk +
 					(FDEV(i).total_segments <<
 					sbi->log_blocks_per_seg) - 1;
-				FDEV(i).bdev_handle = bdev_open_by_path(
+				FDEV(i).bdev_file = bdev_file_open_by_path(
 					FDEV(i).path, mode, sbi->sb, NULL);
 			}
 		}
-		if (IS_ERR(FDEV(i).bdev_handle))
-			return PTR_ERR(FDEV(i).bdev_handle);
+		if (IS_ERR(FDEV(i).bdev_file))
+			return PTR_ERR(FDEV(i).bdev_file);
 
-		FDEV(i).bdev = FDEV(i).bdev_handle->bdev;
+		FDEV(i).bdev = file_bdev(FDEV(i).bdev_file);
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
@@ -4496,7 +4496,7 @@ try_onemore:
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
-	memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+	super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	/* init f2fs-specific super block info */
@@ -4660,6 +4660,7 @@ try_onemore:
 		goto free_node_inode;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root); /* allocate root dentry */
 	if (!sb->s_root) {
 		err = -ENOMEM;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 1fac3dabf130..5c813696d1ff 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1762,6 +1762,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	else /* fat 16 or 12 */
 		sbi->vol_id = bpb.fat16_vol_id;
 
+	__le32 vol_id_le = cpu_to_le32(sbi->vol_id);
+	super_set_uuid(sb, (void *) &vol_id_le, sizeof(vol_id_le));
+
 	sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
 	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
 
diff --git a/fs/fcntl.c b/fs/fcntl.c
index c80a6acad742..54cc85d3338e 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -27,6 +27,7 @@
 #include <linux/memfd.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/rw_hint.h>
 
 #include <linux/poll.h>
 #include <asm/siginfo.h>
@@ -268,8 +269,15 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 }
 #endif
 
-static bool rw_hint_valid(enum rw_hint hint)
+static bool rw_hint_valid(u64 hint)
 {
+	BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
+	BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
+	BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
+	BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
+	BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
+	BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
+
 	switch (hint) {
 	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
@@ -283,34 +291,40 @@ static bool rw_hint_valid(enum rw_hint hint)
 	}
 }
 
-static long fcntl_rw_hint(struct file *file, unsigned int cmd,
-			  unsigned long arg)
+static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
 {
 	struct inode *inode = file_inode(file);
 	u64 __user *argp = (u64 __user *)arg;
-	enum rw_hint hint;
-	u64 h;
+	u64 hint = READ_ONCE(inode->i_write_hint);
 
-	switch (cmd) {
-	case F_GET_RW_HINT:
-		h = inode->i_write_hint;
-		if (copy_to_user(argp, &h, sizeof(*argp)))
-			return -EFAULT;
-		return 0;
-	case F_SET_RW_HINT:
-		if (copy_from_user(&h, argp, sizeof(h)))
-			return -EFAULT;
-		hint = (enum rw_hint) h;
-		if (!rw_hint_valid(hint))
-			return -EINVAL;
+	if (copy_to_user(argp, &hint, sizeof(*argp)))
+		return -EFAULT;
+	return 0;
+}
 
-		inode_lock(inode);
-		inode->i_write_hint = hint;
-		inode_unlock(inode);
-		return 0;
-	default:
+static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	struct inode *inode = file_inode(file);
+	u64 __user *argp = (u64 __user *)arg;
+	u64 hint;
+
+	if (copy_from_user(&hint, argp, sizeof(hint)))
+		return -EFAULT;
+	if (!rw_hint_valid(hint))
 		return -EINVAL;
-	}
+
+	WRITE_ONCE(inode->i_write_hint, hint);
+
+	/*
+	 * file->f_mapping->host may differ from inode. As an example,
+	 * blkdev_open() modifies file->f_mapping.
+	 */
+	if (file->f_mapping->host != inode)
+		WRITE_ONCE(file->f_mapping->host->i_write_hint, hint);
+
+	return 0;
 }
 
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
@@ -416,8 +430,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = memfd_fcntl(filp, cmd, argi);
 		break;
 	case F_GET_RW_HINT:
+		err = fcntl_get_rw_hint(filp, cmd, arg);
+		break;
 	case F_SET_RW_HINT:
-		err = fcntl_rw_hint(filp, cmd, arg);
+		err = fcntl_set_rw_hint(filp, cmd, arg);
 		break;
 	default:
 		break;
@@ -846,12 +862,6 @@ int send_sigurg(struct fown_struct *fown)
 static DEFINE_SPINLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __ro_after_init;
 
-static void fasync_free_rcu(struct rcu_head *head)
-{
-	kmem_cache_free(fasync_cache,
-			container_of(head, struct fasync_struct, fa_rcu));
-}
-
 /*
  * Remove a fasync entry. If successfully removed, return
  * positive and clear the FASYNC flag. If no entry exists,
@@ -877,7 +887,7 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 		write_unlock_irq(&fa->fa_lock);
 
 		*fp = fa->fa_next;
-		call_rcu(&fa->fa_rcu, fasync_free_rcu);
+		kfree_rcu(fa, fa_rcu);
 		filp->f_flags &= ~FASYNC;
 		result = 1;
 		break;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 18b3ba8dc8ea..57a12614addf 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path,
 	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
 		return -EINVAL;
 
-	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+	handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
 			 GFP_KERNEL);
 	if (!handle)
 		return -ENOMEM;
diff --git a/fs/file_table.c b/fs/file_table.c
index b991f90571b4..6925522faa0a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -276,21 +276,15 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 }
 
 /**
- * alloc_file - allocate and initialize a 'struct file'
+ * file_init_path - initialize a 'struct file' based on path
  *
+ * @file: the file to set up
  * @path: the (dentry, vfsmount) pair for the new file
- * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-static struct file *alloc_file(const struct path *path, int flags,
-		const struct file_operations *fop)
+static void file_init_path(struct file *file, const struct path *path,
+			   const struct file_operations *fop)
 {
-	struct file *file;
-
-	file = alloc_empty_file(flags, current_cred());
-	if (IS_ERR(file))
-		return file;
-
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
@@ -309,22 +303,51 @@ static struct file *alloc_file(const struct path *path, int flags,
 	file->f_op = fop;
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
+}
+
+/**
+ * alloc_file - allocate and initialize a 'struct file'
+ *
+ * @path: the (dentry, vfsmount) pair for the new file
+ * @flags: O_... flags with which the new file will be opened
+ * @fop: the 'struct file_operations' for the new file
+ */
+static struct file *alloc_file(const struct path *path, int flags,
+		const struct file_operations *fop)
+{
+	struct file *file;
+
+	file = alloc_empty_file(flags, current_cred());
+	if (!IS_ERR(file))
+		file_init_path(file, path, fop);
 	return file;
 }
 
-struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
-				const char *name, int flags,
-				const struct file_operations *fops)
+static inline int alloc_path_pseudo(const char *name, struct inode *inode,
+				    struct vfsmount *mnt, struct path *path)
 {
 	struct qstr this = QSTR_INIT(name, strlen(name));
+
+	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path->dentry)
+		return -ENOMEM;
+	path->mnt = mntget(mnt);
+	d_instantiate(path->dentry, inode);
+	return 0;
+}
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+			       const char *name, int flags,
+			       const struct file_operations *fops)
+{
+	int ret;
 	struct path path;
 	struct file *file;
 
-	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
-	if (!path.dentry)
-		return ERR_PTR(-ENOMEM);
-	path.mnt = mntget(mnt);
-	d_instantiate(path.dentry, inode);
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
 	file = alloc_file(&path, flags, fops);
 	if (IS_ERR(file)) {
 		ihold(inode);
@@ -334,6 +357,30 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(alloc_file_pseudo);
 
+struct file *alloc_file_pseudo_noaccount(struct inode *inode,
+					 struct vfsmount *mnt, const char *name,
+					 int flags,
+					 const struct file_operations *fops)
+{
+	int ret;
+	struct path path;
+	struct file *file;
+
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	file = alloc_empty_file_noaccount(flags, current_cred());
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+		return file;
+	}
+	file_init_path(file, &path, fops);
+	return file;
+}
+EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
+
 struct file *alloc_file_clone(struct file *base, int flags,
 				const struct file_operations *fops)
 {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3d84fcc471c6..e4f17c53ddfc 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -141,6 +141,31 @@ static void wb_wakeup(struct bdi_writeback *wb)
 	spin_unlock_irq(&wb->work_lock);
 }
 
+/*
+ * This function is used when the first inode for this wb is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
+ */
+static void wb_wakeup_delayed(struct bdi_writeback *wb)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	spin_lock_irq(&wb->work_lock);
+	if (test_bit(WB_registered, &wb->state))
+		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
+	spin_unlock_irq(&wb->work_lock);
+}
+
 static void finish_writeback_work(struct bdi_writeback *wb,
 				  struct wb_writeback_work *work)
 {
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index edb3712dcfa5..a4d6ca0b8971 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -83,8 +83,8 @@ static const struct fs_parameter_spec *fs_lookup_key(
 }
 
 /*
- * fs_parse - Parse a filesystem configuration parameter
- * @fc: The filesystem context to log errors through.
+ * __fs_parse - Parse a filesystem configuration parameter
+ * @log: The filesystem context to log errors through.
  * @desc: The parameter description to use.
  * @param: The parameter.
  * @result: Where to place the result of the parse
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 91e89e68177e..b6cad106c37e 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -474,8 +474,7 @@ err:
 
 static void cuse_fc_release(struct fuse_conn *fc)
 {
-	struct cuse_conn *cc = fc_to_cc(fc);
-	kfree_rcu(cc, fc.rcu);
+	kfree(fc_to_cc(fc));
 }
 
 /**
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 148a71b8b4d0..c007b0f0c3a7 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2509,14 +2509,14 @@ static int convert_fuse_file_lock(struct fuse_conn *fc,
 		 * translate it into the caller's pid namespace.
 		 */
 		rcu_read_lock();
-		fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
+		fl->c.flc_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
 		rcu_read_unlock();
 		break;
 
 	default:
 		return -EIO;
 	}
-	fl->fl_type = ffl->type;
+	fl->c.flc_type = ffl->type;
 	return 0;
 }
 
@@ -2530,10 +2530,10 @@ static void fuse_lk_fill(struct fuse_args *args, struct file *file,
 
 	memset(inarg, 0, sizeof(*inarg));
 	inarg->fh = ff->fh;
-	inarg->owner = fuse_lock_owner_id(fc, fl->fl_owner);
+	inarg->owner = fuse_lock_owner_id(fc, fl->c.flc_owner);
 	inarg->lk.start = fl->fl_start;
 	inarg->lk.end = fl->fl_end;
-	inarg->lk.type = fl->fl_type;
+	inarg->lk.type = fl->c.flc_type;
 	inarg->lk.pid = pid;
 	if (flock)
 		inarg->lk_flags |= FUSE_LK_FLOCK;
@@ -2570,8 +2570,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	struct fuse_mount *fm = get_fuse_mount(inode);
 	FUSE_ARGS(args);
 	struct fuse_lk_in inarg;
-	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
-	struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+	int opcode = (fl->c.flc_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
+	struct pid *pid = fl->c.flc_type != F_UNLCK ? task_tgid(current) : NULL;
 	pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns);
 	int err;
 
@@ -2581,7 +2581,7 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	}
 
 	/* Unlock on close is handled by the flush method */
-	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
+	if ((fl->c.flc_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
 		return 0;
 
 	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1df83eebda92..bcbe34488862 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -888,6 +888,7 @@ struct fuse_mount {
 
 	/* Entry on fc->mounts */
 	struct list_head fc_entry;
+	struct rcu_head rcu;
 };
 
 static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2a6d44f91729..516ea2979a90 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -930,6 +930,14 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
+static void delayed_release(struct rcu_head *p)
+{
+	struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu);
+
+	put_user_ns(fc->user_ns);
+	fc->release(fc);
+}
+
 void fuse_conn_put(struct fuse_conn *fc)
 {
 	if (refcount_dec_and_test(&fc->count)) {
@@ -941,13 +949,12 @@ void fuse_conn_put(struct fuse_conn *fc)
 		if (fiq->ops->release)
 			fiq->ops->release(fiq);
 		put_pid_ns(fc->pid_ns);
-		put_user_ns(fc->user_ns);
 		bucket = rcu_dereference_protected(fc->curr_bucket, 1);
 		if (bucket) {
 			WARN_ON(atomic_read(&bucket->count) != 1);
 			kfree(bucket);
 		}
-		fc->release(fc);
+		call_rcu(&fc->rcu, delayed_release);
 	}
 }
 EXPORT_SYMBOL_GPL(fuse_conn_put);
@@ -1366,7 +1373,7 @@ EXPORT_SYMBOL_GPL(fuse_send_init);
 void fuse_free_conn(struct fuse_conn *fc)
 {
 	WARN_ON(!list_empty(&fc->devices));
-	kfree_rcu(fc, rcu);
+	kfree(fc);
 }
 EXPORT_SYMBOL_GPL(fuse_free_conn);
 
@@ -1902,7 +1909,7 @@ static void fuse_sb_destroy(struct super_block *sb)
 void fuse_mount_destroy(struct fuse_mount *fm)
 {
 	fuse_conn_put(fm->fc);
-	kfree(fm);
+	kfree_rcu(fm, rcu);
 }
 EXPORT_SYMBOL(fuse_mount_destroy);
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index d9ccfd27e4f1..789af5c8fade 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2465,7 +2465,7 @@ out:
 }
 
 static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
-		loff_t offset)
+		loff_t offset, unsigned int len)
 {
 	int ret;
 
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 177f1f41f225..2e215e8c3c88 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -32,25 +32,21 @@
 
 static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent = NULL;
+	struct dentry *parent;
 	struct gfs2_sbd *sdp;
 	struct gfs2_inode *dip;
-	struct inode *dinode, *inode;
+	struct inode *inode;
 	struct gfs2_holder d_gh;
 	struct gfs2_inode *ip = NULL;
 	int error, valid = 0;
 	int had_lock = 0;
 
-	if (flags & LOOKUP_RCU) {
-		dinode = d_inode_rcu(READ_ONCE(dentry->d_parent));
-		if (!dinode)
-			return -ECHILD;
-	} else {
-		parent = dget_parent(dentry);
-		dinode = d_inode(parent);
-	}
-	sdp = GFS2_SB(dinode);
-	dip = GFS2_I(dinode);
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	parent = dget_parent(dentry);
+	sdp = GFS2_SB(d_inode(parent));
+	dip = GFS2_I(d_inode(parent));
 	inode = d_inode(dentry);
 
 	if (inode) {
@@ -66,8 +62,7 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
 	if (!had_lock) {
-		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED,
-					   flags & LOOKUP_RCU ? GL_NOBLOCK : 0, &d_gh);
+		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
 		if (error)
 			goto out;
 	}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 992ca4effb50..4c42ada60ae7 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1440,10 +1440,10 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 	struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 	if (gfs2_withdrawing_or_withdrawn(sdp)) {
-		if (fl->fl_type == F_UNLCK)
+		if (lock_is_unlock(fl))
 			locks_lock_file_wait(file, fl);
 		return -EIO;
 	}
@@ -1451,7 +1451,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 		return dlm_posix_cancel(ls->ls_dlm, ip->i_no_addr, file, fl);
 	else if (IS_GETLK(cmd))
 		return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
 	else
 		return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
@@ -1483,7 +1483,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 	int sleeptime;
 
-	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
+	state = lock_is_write(fl) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
 	flags = GL_EXACT | GL_NOPID;
 	if (!IS_SETLKW(cmd))
 		flags |= LM_FLAG_TRY_1CB;
@@ -1495,8 +1495,8 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 		if (fl_gh->gh_state == state)
 			goto out;
 		locks_init_lock(&request);
-		request.fl_type = F_UNLCK;
-		request.fl_flags = FL_FLOCK;
+		request.c.flc_type = F_UNLCK;
+		request.c.flc_flags = FL_FLOCK;
 		locks_lock_file_wait(file, &request);
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
@@ -1557,10 +1557,10 @@ static void do_unflock(struct file *file, struct file_lock *fl)
 
 static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 {
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
-	if (fl->fl_type == F_UNLCK) {
+	if (lock_is_unlock(fl)) {
 		do_unflock(file, fl);
 		return 0;
 	} else {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6bfc9383b7b8..1b95db2c3aac 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1882,10 +1882,10 @@ int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode,
 		WARN_ON_ONCE(!may_not_block);
 		return -ECHILD;
         }
-	if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
-		int noblock = may_not_block ? GL_NOBLOCK : 0;
-		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_ANY | noblock, &i_gh);
+	if (gfs2_glock_is_locked_by_me(gl) == NULL) {
+		if (may_not_block)
+			return -ECHILD;
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
 		if (error)
 			return error;
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1281e60be639..572d58e86296 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -214,7 +214,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
 
 	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
 	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
-	memcpy(&s->s_uuid, str->sb_uuid, 16);
+	super_set_uuid(s, str->sb_uuid, 16);
 }
 
 /**
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 7ededcb720c1..012a3d003fbe 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -190,6 +190,7 @@ struct hfsplus_sb_info {
 	int work_queued;               /* non-zero delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock;          /* protects sync_work and work_queued */
+	struct rcu_head rcu;
 };
 
 #define HFSPLUS_SB_WRITEBACKUP	0
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 1986b4f18a90..97920202790f 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -277,6 +277,14 @@ void hfsplus_mark_mdb_dirty(struct super_block *sb)
 	spin_unlock(&sbi->work_lock);
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct hfsplus_sb_info *sbi = container_of(p, struct hfsplus_sb_info, rcu);
+
+	unload_nls(sbi->nls);
+	kfree(sbi);
+}
+
 static void hfsplus_put_super(struct super_block *sb)
 {
 	struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
@@ -302,9 +310,7 @@ static void hfsplus_put_super(struct super_block *sb)
 	hfs_btree_close(sbi->ext_tree);
 	kfree(sbi->s_vhdr_buf);
 	kfree(sbi->s_backup_vhdr_buf);
-	unload_nls(sbi->nls);
-	kfree(sb->s_fs_info);
-	sb->s_fs_info = NULL;
+	call_rcu(&sbi->rcu, delayed_free);
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index b0cb70400996..ce9346099c72 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -30,7 +30,7 @@ struct hfsplus_wd {
  * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
  * @buf: buffer for I/O
  * @data: output pointer for location of requested data
- * @opf: request op flags
+ * @opf: I/O operation type and flags
  *
  * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
  * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ea5b8e57d904..6502c7e776d1 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
+	vm_flags_t vm_flags;
 
 	/*
 	 * vma address alignment (but not the pgoff alignment) has
@@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
+
+	vm_flags = vma->vm_flags;
+	/*
+	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+	 * reserving here. Note: only for SHM hugetlbfs file, the inode
+	 * flag S_PRIVATE is set.
+	 */
+	if (inode->i_flags & S_PRIVATE)
+		vm_flags |= VM_NORESERVE;
+
 	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
-				vma->vm_flags))
+				vm_flags))
 		goto out;
 
 	ret = 0;
@@ -340,7 +351,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		} else {
 			folio_unlock(folio);
 
-			if (!folio_test_has_hwpoisoned(folio))
+			if (!folio_test_hwpoison(folio))
 				want = nr;
 			else {
 				/*
@@ -922,7 +933,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	error = setattr_prepare(idmap, dentry, attr);
 	if (error)
 		return error;
 
@@ -939,7 +950,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
 		hugetlb_vmtruncate(inode, newsize);
 	}
 
-	setattr_copy(&nop_mnt_idmap, inode, attr);
+	setattr_copy(idmap, inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -974,6 +985,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
+					struct mnt_idmap *idmap,
 					struct inode *dir,
 					umode_t mode, dev_t dev)
 {
@@ -995,7 +1007,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
 		inode->i_ino = get_next_ino();
-		inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+		inode_init_owner(idmap, inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
@@ -1039,7 +1051,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1051,7 +1063,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			   struct dentry *dentry, umode_t mode)
 {
-	int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry,
+	int retval = hugetlbfs_mknod(idmap, dir, dentry,
 				     mode | S_IFDIR, 0);
 	if (!retval)
 		inc_nlink(dir);
@@ -1062,7 +1074,7 @@ static int hugetlbfs_create(struct mnt_idmap *idmap,
 			    struct inode *dir, struct dentry *dentry,
 			    umode_t mode, bool excl)
 {
-	return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
+	return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0);
 }
 
 static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
@@ -1071,7 +1083,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
 {
 	struct inode *inode;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0);
 	if (!inode)
 		return -ENOSPC;
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -1083,10 +1095,11 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap,
 			     struct inode *dir, struct dentry *dentry,
 			     const char *symname)
 {
+	const umode_t mode = S_IFLNK|S_IRWXUGO;
 	struct inode *inode;
 	int error = -ENOSPC;
 
-	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0);
 	if (inode) {
 		int l = strlen(symname)+1;
 		error = page_symlink(inode, symname, l);
@@ -1354,6 +1367,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 {
 	struct hugetlbfs_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
+	struct hstate *h;
 	char *rest;
 	unsigned long ps;
 	int opt;
@@ -1398,11 +1412,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_pagesize:
 		ps = memparse(param->string, &rest);
-		ctx->hstate = size_to_hstate(ps);
-		if (!ctx->hstate) {
+		h = size_to_hstate(ps);
+		if (!h) {
 			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
 			return -EINVAL;
 		}
+		ctx->hstate = h;
 		return 0;
 
 	case Opt_min_size:
@@ -1553,6 +1568,7 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.init_fs_context	= hugetlbfs_init_fs_context,
 	.parameters		= hugetlb_fs_parameters,
 	.kill_sb		= kill_litter_super,
+	.fs_flags               = FS_ALLOW_IDMAP,
 };
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -1606,7 +1622,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	}
 
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	/* hugetlbfs_vfsmount[] mounts do not use idmapped mounts.  */
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL,
+				    S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
diff --git a/fs/inode.c b/fs/inode.c
index 91048c4c9c9e..d290f007b3d1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -20,6 +20,7 @@
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
 #include <linux/iversion.h>
+#include <linux/rw_hint.h>
 #include <trace/events/writeback.h>
 #include "internal.h"
 
@@ -588,7 +589,8 @@ void dump_mapping(const struct address_space *mapping)
 	}
 
 	dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
-	if (get_kernel_nofault(dentry, dentry_ptr)) {
+	if (get_kernel_nofault(dentry, dentry_ptr) ||
+	    !dentry.d_parent || !dentry.d_name.name) {
 		pr_warn("aops:%ps ino:%lx invalid dentry:%px\n",
 				a_ops, ino, dentry_ptr);
 		return;
@@ -2285,7 +2287,7 @@ void __init inode_init(void)
 					 sizeof(struct inode),
 					 0,
 					 (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
-					 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+					 SLAB_ACCOUNT),
 					 init_once);
 
 	/* Hash may have been set up in inode_init_early */
@@ -2509,7 +2511,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
 	struct timespec64 now = current_time(inode);
 
-	inode_set_ctime(inode, now.tv_sec, now.tv_nsec);
+	inode_set_ctime_to_ts(inode, now);
 	return now;
 }
 EXPORT_SYMBOL(inode_set_ctime_current);
diff --git a/fs/internal.h b/fs/internal.h
index b67406435fc0..49c1fcfee4b3 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -183,6 +183,7 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 struct file *file_close_fd_locked(struct files_struct *files, unsigned fd);
 
+long do_ftruncate(struct file *file, loff_t length, int small);
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
@@ -310,3 +311,10 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po
 struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns);
 struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
 void mnt_idmap_put(struct mnt_idmap *idmap);
+struct stashed_operations {
+	void (*put_data)(void *data);
+	void (*init_inode)(struct inode *inode, void *data);
+};
+int path_from_stashed(struct dentry **stashed, unsigned long ino,
+		      struct vfsmount *mnt, void *data, struct path *path);
+void stashed_dentry_prune(struct dentry *dentry);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 76cf22ac97d7..1d5abfdf0f22 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -763,6 +763,33 @@ static int ioctl_fssetxattr(struct file *file, void __user *argp)
 	return err;
 }
 
+static int ioctl_getfsuuid(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+	struct fsuuid2 u = { .len = sb->s_uuid_len, };
+
+	if (!sb->s_uuid_len)
+		return -ENOIOCTLCMD;
+
+	memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
+static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+
+	if (!strlen(sb->s_sysfs_name))
+		return -ENOIOCTLCMD;
+
+	struct fs_sysfs_path u = {};
+
+	u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
 /*
  * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
  * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
@@ -845,6 +872,12 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
 	case FS_IOC_FSSETXATTR:
 		return ioctl_fssetxattr(filp, argp);
 
+	case FS_IOC_GETFSUUID:
+		return ioctl_getfsuuid(filp, argp);
+
+	case FS_IOC_GETFSSYSFSPATH:
+		return ioctl_get_fs_sysfs_path(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			return file_ioctl(filp, cmd, argp);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 093c4515b22a..4e8e41c8b3c0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (C) 2016-2019 Christoph Hellwig.
+ * Copyright (C) 2016-2023 Christoph Hellwig.
  */
 #include <linux/module.h>
 #include <linux/compiler.h>
@@ -95,6 +95,44 @@ static inline bool ifs_block_is_dirty(struct folio *folio,
 	return test_bit(block + blks_per_folio, ifs->state);
 }
 
+static unsigned ifs_find_dirty_range(struct folio *folio,
+		struct iomap_folio_state *ifs, u64 *range_start, u64 range_end)
+{
+	struct inode *inode = folio->mapping->host;
+	unsigned start_blk =
+		offset_in_folio(folio, *range_start) >> inode->i_blkbits;
+	unsigned end_blk = min_not_zero(
+		offset_in_folio(folio, range_end) >> inode->i_blkbits,
+		i_blocks_per_folio(inode, folio));
+	unsigned nblks = 1;
+
+	while (!ifs_block_is_dirty(folio, ifs, start_blk))
+		if (++start_blk == end_blk)
+			return 0;
+
+	while (start_blk + nblks < end_blk) {
+		if (!ifs_block_is_dirty(folio, ifs, start_blk + nblks))
+			break;
+		nblks++;
+	}
+
+	*range_start = folio_pos(folio) + (start_blk << inode->i_blkbits);
+	return nblks << inode->i_blkbits;
+}
+
+static unsigned iomap_find_dirty_range(struct folio *folio, u64 *range_start,
+		u64 range_end)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	if (*range_start >= range_end)
+		return 0;
+
+	if (ifs)
+		return ifs_find_dirty_range(folio, ifs, range_start, range_end);
+	return range_end - *range_start;
+}
+
 static void ifs_clear_range_dirty(struct folio *folio,
 		struct iomap_folio_state *ifs, size_t off, size_t len)
 {
@@ -1454,15 +1492,10 @@ out_unlock:
 EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 
 static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
-		size_t len, int error)
+		size_t len)
 {
 	struct iomap_folio_state *ifs = folio->private;
 
-	if (error) {
-		folio_set_error(folio);
-		mapping_set_error(inode->i_mapping, error);
-	}
-
 	WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs);
 	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) <= 0);
 
@@ -1479,40 +1512,29 @@ static u32
 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 {
 	struct inode *inode = ioend->io_inode;
-	struct bio *bio = &ioend->io_inline_bio;
-	struct bio *last = ioend->io_bio, *next;
-	u64 start = bio->bi_iter.bi_sector;
-	loff_t offset = ioend->io_offset;
-	bool quiet = bio_flagged(bio, BIO_QUIET);
+	struct bio *bio = &ioend->io_bio;
+	struct folio_iter fi;
 	u32 folio_count = 0;
 
-	for (bio = &ioend->io_inline_bio; bio; bio = next) {
-		struct folio_iter fi;
-
-		/*
-		 * For the last bio, bi_private points to the ioend, so we
-		 * need to explicitly end the iteration here.
-		 */
-		if (bio == last)
-			next = NULL;
-		else
-			next = bio->bi_private;
-
-		/* walk all folios in bio, ending page IO on them */
-		bio_for_each_folio_all(fi, bio) {
-			iomap_finish_folio_write(inode, fi.folio, fi.length,
-					error);
-			folio_count++;
+	if (error) {
+		mapping_set_error(inode->i_mapping, error);
+		if (!bio_flagged(bio, BIO_QUIET)) {
+			pr_err_ratelimited(
+"%s: writeback error on inode %lu, offset %lld, sector %llu",
+				inode->i_sb->s_id, inode->i_ino,
+				ioend->io_offset, ioend->io_sector);
 		}
-		bio_put(bio);
 	}
-	/* The ioend has been freed by bio_put() */
 
-	if (unlikely(error && !quiet)) {
-		printk_ratelimited(KERN_ERR
-"%s: writeback error on inode %lu, offset %lld, sector %llu",
-			inode->i_sb->s_id, inode->i_ino, offset, start);
+	/* walk all folios in bio, ending page IO on them */
+	bio_for_each_folio_all(fi, bio) {
+		if (error)
+			folio_set_error(fi.folio);
+		iomap_finish_folio_write(inode, fi.folio, fi.length);
+		folio_count++;
 	}
+
+	bio_put(bio);	/* frees the ioend */
 	return folio_count;
 }
 
@@ -1553,7 +1575,7 @@ EXPORT_SYMBOL_GPL(iomap_finish_ioends);
 static bool
 iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
 {
-	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
+	if (ioend->io_bio.bi_status != next->io_bio.bi_status)
 		return false;
 	if ((ioend->io_flags & IOMAP_F_SHARED) ^
 	    (next->io_flags & IOMAP_F_SHARED))
@@ -1618,47 +1640,46 @@ EXPORT_SYMBOL_GPL(iomap_sort_ioends);
 
 static void iomap_writepage_end_bio(struct bio *bio)
 {
-	struct iomap_ioend *ioend = bio->bi_private;
-
-	iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status));
+	iomap_finish_ioend(iomap_ioend_from_bio(bio),
+			blk_status_to_errno(bio->bi_status));
 }
 
 /*
  * Submit the final bio for an ioend.
  *
  * If @error is non-zero, it means that we have a situation where some part of
- * the submission process has failed after we've marked pages for writeback
- * and unlocked them.  In this situation, we need to fail the bio instead of
- * submitting it.  This typically only happens on a filesystem shutdown.
+ * the submission process has failed after we've marked pages for writeback.
+ * We cannot cancel ioend directly in that case, so call the bio end I/O handler
+ * with the error status here to run the normal I/O completion handler to clear
+ * the writeback bit and let the file system proess the errors.
  */
-static int
-iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend,
-		int error)
+static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
 {
-	ioend->io_bio->bi_private = ioend;
-	ioend->io_bio->bi_end_io = iomap_writepage_end_bio;
+	if (!wpc->ioend)
+		return error;
 
+	/*
+	 * Let the file systems prepare the I/O submission and hook in an I/O
+	 * comletion handler.  This also needs to happen in case after a
+	 * failure happened so that the file system end I/O handler gets called
+	 * to clean up.
+	 */
 	if (wpc->ops->prepare_ioend)
-		error = wpc->ops->prepare_ioend(ioend, error);
+		error = wpc->ops->prepare_ioend(wpc->ioend, error);
+
 	if (error) {
-		/*
-		 * If we're failing the IO now, just mark the ioend with an
-		 * error and finish it.  This will run IO completion immediately
-		 * as there is only one reference to the ioend at this point in
-		 * time.
-		 */
-		ioend->io_bio->bi_status = errno_to_blk_status(error);
-		bio_endio(ioend->io_bio);
-		return error;
+		wpc->ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&wpc->ioend->io_bio);
+	} else {
+		submit_bio(&wpc->ioend->io_bio);
 	}
 
-	submit_bio(ioend->io_bio);
-	return 0;
+	wpc->ioend = NULL;
+	return error;
 }
 
-static struct iomap_ioend *
-iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
-		loff_t offset, sector_t sector, struct writeback_control *wbc)
+static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct inode *inode, loff_t pos)
 {
 	struct iomap_ioend *ioend;
 	struct bio *bio;
@@ -1666,63 +1687,42 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
 	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
 			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
 			       GFP_NOFS, &iomap_ioend_bioset);
-	bio->bi_iter.bi_sector = sector;
+	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
+	bio->bi_end_io = iomap_writepage_end_bio;
 	wbc_init_bio(wbc, bio);
+	bio->bi_write_hint = inode->i_write_hint;
 
-	ioend = container_of(bio, struct iomap_ioend, io_inline_bio);
+	ioend = iomap_ioend_from_bio(bio);
 	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_type = wpc->iomap.type;
 	ioend->io_flags = wpc->iomap.flags;
 	ioend->io_inode = inode;
 	ioend->io_size = 0;
-	ioend->io_folios = 0;
-	ioend->io_offset = offset;
-	ioend->io_bio = bio;
-	ioend->io_sector = sector;
-	return ioend;
-}
-
-/*
- * Allocate a new bio, and chain the old bio to the new one.
- *
- * Note that we have to perform the chaining in this unintuitive order
- * so that the bi_private linkage is set up in the right direction for the
- * traversal in iomap_finish_ioend().
- */
-static struct bio *
-iomap_chain_bio(struct bio *prev)
-{
-	struct bio *new;
-
-	new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS);
-	bio_clone_blkg_association(new, prev);
-	new->bi_iter.bi_sector = bio_end_sector(prev);
+	ioend->io_offset = pos;
+	ioend->io_sector = bio->bi_iter.bi_sector;
 
-	bio_chain(prev, new);
-	bio_get(prev);		/* for iomap_finish_ioend */
-	submit_bio(prev);
-	return new;
+	wpc->nr_folios = 0;
+	return ioend;
 }
 
-static bool
-iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
-		sector_t sector)
+static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
 {
 	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
 	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
 		return false;
 	if (wpc->iomap.type != wpc->ioend->io_type)
 		return false;
-	if (offset != wpc->ioend->io_offset + wpc->ioend->io_size)
+	if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
 		return false;
-	if (sector != bio_end_sector(wpc->ioend->io_bio))
+	if (iomap_sector(&wpc->iomap, pos) !=
+	    bio_end_sector(&wpc->ioend->io_bio))
 		return false;
 	/*
 	 * Limit ioend bio chain lengths to minimise IO completion latency. This
 	 * also prevents long tight loops ending page writeback on all the
 	 * folios in the ioend.
 	 */
-	if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE)
+	if (wpc->nr_folios >= IOEND_BATCH_SIZE)
 		return false;
 	return true;
 }
@@ -1730,255 +1730,238 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
 /*
  * Test to see if we have an existing ioend structure that we could append to
  * first; otherwise finish off the current ioend and start another.
+ *
+ * If a new ioend is created and cached, the old ioend is submitted to the block
+ * layer instantly.  Batching optimisations are provided by higher level block
+ * plugging.
+ *
+ * At the end of a writeback pass, there will be a cached ioend remaining on the
+ * writepage context that the caller will need to submit.
  */
-static void
-iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio,
-		struct iomap_folio_state *ifs, struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct list_head *iolist)
+static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio,
+		struct inode *inode, loff_t pos, unsigned len)
 {
-	sector_t sector = iomap_sector(&wpc->iomap, pos);
-	unsigned len = i_blocksize(inode);
+	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
+	int error;
 
-	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, sector)) {
-		if (wpc->ioend)
-			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = iomap_alloc_ioend(inode, wpc, pos, sector, wbc);
+	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos)) {
+new_ioend:
+		error = iomap_submit_ioend(wpc, 0);
+		if (error)
+			return error;
+		wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos);
 	}
 
-	if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) {
-		wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio);
-		bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff);
-	}
+	if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
+		goto new_ioend;
 
 	if (ifs)
 		atomic_add(len, &ifs->write_bytes_pending);
 	wpc->ioend->io_size += len;
 	wbc_account_cgroup_owner(wbc, &folio->page, len);
+	return 0;
 }
 
-/*
- * We implement an immediate ioend submission policy here to avoid needing to
- * chain multiple ioends and hence nest mempool allocations which can violate
- * the forward progress guarantees we need to provide. The current ioend we're
- * adding blocks to is cached in the writepage context, and if the new block
- * doesn't append to the cached ioend, it will create a new ioend and cache that
- * instead.
- *
- * If a new ioend is created and cached, the old ioend is returned and queued
- * locally for submission once the entire page is processed or an error has been
- * detected.  While ioends are submitted immediately after they are completed,
- * batching optimisations are provided by higher level block plugging.
- *
- * At the end of a writeback pass, there will be a cached ioend remaining on the
- * writepage context that the caller will need to submit.
- */
-static int
-iomap_writepage_map(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct inode *inode,
-		struct folio *folio, u64 end_pos)
+static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio,
+		struct inode *inode, u64 pos, unsigned dirty_len,
+		unsigned *count)
 {
-	struct iomap_folio_state *ifs = folio->private;
-	struct iomap_ioend *ioend, *next;
-	unsigned len = i_blocksize(inode);
-	unsigned nblocks = i_blocks_per_folio(inode, folio);
-	u64 pos = folio_pos(folio);
-	int error = 0, count = 0, i;
-	LIST_HEAD(submit_list);
-
-	WARN_ON_ONCE(end_pos <= pos);
-
-	if (!ifs && nblocks > 1) {
-		ifs = ifs_alloc(inode, folio, 0);
-		iomap_set_range_dirty(folio, 0, end_pos - pos);
-	}
+	int error;
 
-	WARN_ON_ONCE(ifs && atomic_read(&ifs->write_bytes_pending) != 0);
-
-	/*
-	 * Walk through the folio to find areas to write back. If we
-	 * run off the end of the current map or find the current map
-	 * invalid, grab a new one.
-	 */
-	for (i = 0; i < nblocks && pos < end_pos; i++, pos += len) {
-		if (ifs && !ifs_block_is_dirty(folio, ifs, i))
-			continue;
+	do {
+		unsigned map_len;
 
-		error = wpc->ops->map_blocks(wpc, inode, pos);
+		error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len);
 		if (error)
 			break;
-		trace_iomap_writepage_map(inode, &wpc->iomap);
-		if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
-			continue;
-		if (wpc->iomap.type == IOMAP_HOLE)
-			continue;
-		iomap_add_to_ioend(inode, pos, folio, ifs, wpc, wbc,
-				 &submit_list);
-		count++;
-	}
-	if (count)
-		wpc->ioend->io_folios++;
+		trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap);
 
-	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
-	WARN_ON_ONCE(!folio_test_locked(folio));
-	WARN_ON_ONCE(folio_test_writeback(folio));
-	WARN_ON_ONCE(folio_test_dirty(folio));
+		map_len = min_t(u64, dirty_len,
+			wpc->iomap.offset + wpc->iomap.length - pos);
+		WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+
+		switch (wpc->iomap.type) {
+		case IOMAP_INLINE:
+			WARN_ON_ONCE(1);
+			error = -EIO;
+			break;
+		case IOMAP_HOLE:
+			break;
+		default:
+			error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos,
+					map_len);
+			if (!error)
+				(*count)++;
+			break;
+		}
+		dirty_len -= map_len;
+		pos += map_len;
+	} while (dirty_len && !error);
 
 	/*
 	 * We cannot cancel the ioend directly here on error.  We may have
 	 * already set other pages under writeback and hence we have to run I/O
 	 * completion to mark the error state of the pages under writeback
 	 * appropriately.
+	 *
+	 * Just let the file system know what portion of the folio failed to
+	 * map.
 	 */
-	if (unlikely(error)) {
-		/*
-		 * Let the filesystem know what portion of the current page
-		 * failed to map. If the page hasn't been added to ioend, it
-		 * won't be affected by I/O completion and we must unlock it
-		 * now.
-		 */
-		if (wpc->ops->discard_folio)
-			wpc->ops->discard_folio(folio, pos);
-		if (!count) {
-			folio_unlock(folio);
-			goto done;
-		}
-	}
-
-	/*
-	 * We can have dirty bits set past end of file in page_mkwrite path
-	 * while mapping the last partial folio. Hence it's better to clear
-	 * all the dirty bits in the folio here.
-	 */
-	iomap_clear_range_dirty(folio, 0, folio_size(folio));
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-
-	/*
-	 * Preserve the original error if there was one; catch
-	 * submission errors here and propagate into subsequent ioend
-	 * submissions.
-	 */
-	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-		int error2;
-
-		list_del_init(&ioend->io_list);
-		error2 = iomap_submit_ioend(wpc, ioend, error);
-		if (error2 && !error)
-			error = error2;
-	}
-
-	/*
-	 * We can end up here with no error and nothing to write only if we race
-	 * with a partial page truncate on a sub-page block sized filesystem.
-	 */
-	if (!count)
-		folio_end_writeback(folio);
-done:
-	mapping_set_error(inode->i_mapping, error);
+	if (error && wpc->ops->discard_folio)
+		wpc->ops->discard_folio(folio, pos);
 	return error;
 }
 
 /*
- * Write out a dirty page.
+ * Check interaction of the folio with the file end.
  *
- * For delalloc space on the page, we need to allocate space and flush it.
- * For unwritten space on the page, we need to start the conversion to
- * regular allocated space.
+ * If the folio is entirely beyond i_size, return false.  If it straddles
+ * i_size, adjust end_pos and zero all data beyond i_size.
  */
-static int iomap_do_writepage(struct folio *folio,
-		struct writeback_control *wbc, void *data)
+static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
+		u64 *end_pos)
 {
-	struct iomap_writepage_ctx *wpc = data;
-	struct inode *inode = folio->mapping->host;
-	u64 end_pos, isize;
-
-	trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio));
+	u64 isize = i_size_read(inode);
 
-	/*
-	 * Refuse to write the folio out if we're called from reclaim context.
-	 *
-	 * This avoids stack overflows when called from deeply used stacks in
-	 * random callers for direct reclaim or memcg reclaim.  We explicitly
-	 * allow reclaim from kswapd as the stack usage there is relatively low.
-	 *
-	 * This should never happen except in the case of a VM regression so
-	 * warn about it.
-	 */
-	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
-			PF_MEMALLOC))
-		goto redirty;
-
-	/*
-	 * Is this folio beyond the end of the file?
-	 *
-	 * The folio index is less than the end_index, adjust the end_pos
-	 * to the highest offset that this folio should represent.
-	 * -----------------------------------------------------
-	 * |			file mapping	       | <EOF> |
-	 * -----------------------------------------------------
-	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
-	 * ^--------------------------------^----------|--------
-	 * |     desired writeback range    |      see else    |
-	 * ---------------------------------^------------------|
-	 */
-	isize = i_size_read(inode);
-	end_pos = folio_pos(folio) + folio_size(folio);
-	if (end_pos > isize) {
-		/*
-		 * Check whether the page to write out is beyond or straddles
-		 * i_size or not.
-		 * -------------------------------------------------------
-		 * |		file mapping		        | <EOF>  |
-		 * -------------------------------------------------------
-		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
-		 * ^--------------------------------^-----------|---------
-		 * |				    |      Straddles     |
-		 * ---------------------------------^-----------|--------|
-		 */
+	if (*end_pos > isize) {
 		size_t poff = offset_in_folio(folio, isize);
 		pgoff_t end_index = isize >> PAGE_SHIFT;
 
 		/*
-		 * Skip the page if it's fully outside i_size, e.g.
-		 * due to a truncate operation that's in progress.  We've
-		 * cleaned this page and truncate will finish things off for
-		 * us.
+		 * If the folio is entirely ouside of i_size, skip it.
+		 *
+		 * This can happen due to a truncate operation that is in
+		 * progress and in that case truncate will finish it off once
+		 * we've dropped the folio lock.
 		 *
-		 * Note that the end_index is unsigned long.  If the given
-		 * offset is greater than 16TB on a 32-bit system then if we
-		 * checked if the page is fully outside i_size with
-		 * "if (page->index >= end_index + 1)", "end_index + 1" would
-		 * overflow and evaluate to 0.  Hence this page would be
+		 * Note that the pgoff_t used for end_index is an unsigned long.
+		 * If the given offset is greater than 16TB on a 32-bit system,
+		 * then if we checked if the folio is fully outside i_size with
+		 * "if (folio->index >= end_index + 1)", "end_index + 1" would
+		 * overflow and evaluate to 0.  Hence this folio would be
 		 * redirtied and written out repeatedly, which would result in
 		 * an infinite loop; the user program performing this operation
 		 * would hang.  Instead, we can detect this situation by
-		 * checking if the page is totally beyond i_size or if its
+		 * checking if the folio is totally beyond i_size or if its
 		 * offset is just equal to the EOF.
 		 */
 		if (folio->index > end_index ||
 		    (folio->index == end_index && poff == 0))
-			goto unlock;
+			return false;
 
 		/*
-		 * The page straddles i_size.  It must be zeroed out on each
-		 * and every writepage invocation because it may be mmapped.
-		 * "A file is mapped in multiples of the page size.  For a file
-		 * that is not a multiple of the page size, the remaining
-		 * memory is zeroed when mapped, and writes to that region are
-		 * not written out to the file."
+		 * The folio straddles i_size.
+		 *
+		 * It must be zeroed out on each and every writepage invocation
+		 * because it may be mmapped:
+		 *
+		 *    A file is mapped in multiples of the page size.  For a
+		 *    file that is not a multiple of the page size, the
+		 *    remaining memory is zeroed when mapped, and writes to that
+		 *    region are not written out to the file.
+		 *
+		 * Also adjust the writeback range to skip all blocks entirely
+		 * beyond i_size.
 		 */
 		folio_zero_segment(folio, poff, folio_size(folio));
-		end_pos = isize;
+		*end_pos = round_up(isize, i_blocksize(inode));
+	}
+
+	return true;
+}
+
+static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
+		struct writeback_control *wbc, struct folio *folio)
+{
+	struct iomap_folio_state *ifs = folio->private;
+	struct inode *inode = folio->mapping->host;
+	u64 pos = folio_pos(folio);
+	u64 end_pos = pos + folio_size(folio);
+	unsigned count = 0;
+	int error = 0;
+	u32 rlen;
+
+	WARN_ON_ONCE(!folio_test_locked(folio));
+	WARN_ON_ONCE(folio_test_dirty(folio));
+	WARN_ON_ONCE(folio_test_writeback(folio));
+
+	trace_iomap_writepage(inode, pos, folio_size(folio));
+
+	if (!iomap_writepage_handle_eof(folio, inode, &end_pos)) {
+		folio_unlock(folio);
+		return 0;
+	}
+	WARN_ON_ONCE(end_pos <= pos);
+
+	if (i_blocks_per_folio(inode, folio) > 1) {
+		if (!ifs) {
+			ifs = ifs_alloc(inode, folio, 0);
+			iomap_set_range_dirty(folio, 0, end_pos - pos);
+		}
+
+		/*
+		 * Keep the I/O completion handler from clearing the writeback
+		 * bit until we have submitted all blocks by adding a bias to
+		 * ifs->write_bytes_pending, which is dropped after submitting
+		 * all blocks.
+		 */
+		WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0);
+		atomic_inc(&ifs->write_bytes_pending);
 	}
 
-	return iomap_writepage_map(wpc, wbc, inode, folio, end_pos);
+	/*
+	 * Set the writeback bit ASAP, as the I/O completion for the single
+	 * block per folio case happen hit as soon as we're submitting the bio.
+	 */
+	folio_start_writeback(folio);
 
-redirty:
-	folio_redirty_for_writepage(wbc, folio);
-unlock:
+	/*
+	 * Walk through the folio to find dirty areas to write back.
+	 */
+	while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) {
+		error = iomap_writepage_map_blocks(wpc, wbc, folio, inode,
+				pos, rlen, &count);
+		if (error)
+			break;
+		pos += rlen;
+	}
+
+	if (count)
+		wpc->nr_folios++;
+
+	/*
+	 * We can have dirty bits set past end of file in page_mkwrite path
+	 * while mapping the last partial folio. Hence it's better to clear
+	 * all the dirty bits in the folio here.
+	 */
+	iomap_clear_range_dirty(folio, 0, folio_size(folio));
+
+	/*
+	 * Usually the writeback bit is cleared by the I/O completion handler.
+	 * But we may end up either not actually writing any blocks, or (when
+	 * there are multiple blocks in a folio) all I/O might have finished
+	 * already at this point.  In that case we need to clear the writeback
+	 * bit ourselves right after unlocking the page.
+	 */
 	folio_unlock(folio);
-	return 0;
+	if (ifs) {
+		if (atomic_dec_and_test(&ifs->write_bytes_pending))
+			folio_end_writeback(folio);
+	} else {
+		if (!count)
+			folio_end_writeback(folio);
+	}
+	mapping_set_error(inode->i_mapping, error);
+	return error;
+}
+
+static int iomap_do_writepage(struct folio *folio,
+		struct writeback_control *wbc, void *data)
+{
+	return iomap_writepage_map(data, wbc, folio);
 }
 
 int
@@ -1988,18 +1971,24 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 {
 	int			ret;
 
+	/*
+	 * Writeback from reclaim context should never happen except in the case
+	 * of a VM regression so warn about it and refuse to write the data.
+	 */
+	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC | PF_KSWAPD)) ==
+			PF_MEMALLOC))
+		return -EIO;
+
 	wpc->ops = ops;
 	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
-	if (!wpc->ioend)
-		return ret;
-	return iomap_submit_ioend(wpc, wpc->ioend, ret);
+	return iomap_submit_ioend(wpc, ret);
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
 static int __init iomap_init(void)
 {
 	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
-			   offsetof(struct iomap_ioend, io_inline_bio),
+			   offsetof(struct iomap_ioend, io_bio),
 			   BIOSET_NEED_BVECS);
 }
 fs_initcall(iomap_init);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index bcd3f8cf5ea4..f3b43d223a46 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -380,6 +380,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
 					  GFP_KERNEL);
 		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
+		bio->bi_write_hint = inode->i_write_hint;
 		bio->bi_ioprio = dio->iocb->ki_ioprio;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index c16fd55f5595..0a991c4ce87d 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -154,7 +154,48 @@ DEFINE_EVENT(iomap_class, name,	\
 	TP_ARGS(inode, iomap))
 DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
 DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
-DEFINE_IOMAP_EVENT(iomap_writepage_map);
+
+TRACE_EVENT(iomap_writepage_map,
+	TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len,
+		 struct iomap *iomap),
+	TP_ARGS(inode, pos, dirty_len, iomap),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(u64, ino)
+		__field(u64, pos)
+		__field(u64, dirty_len)
+		__field(u64, addr)
+		__field(loff_t, offset)
+		__field(u64, length)
+		__field(u16, type)
+		__field(u16, flags)
+		__field(dev_t, bdev)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pos = pos;
+		__entry->dirty_len = dirty_len;
+		__entry->addr = iomap->addr;
+		__entry->offset = iomap->offset;
+		__entry->length = iomap->length;
+		__entry->type = iomap->type;
+		__entry->flags = iomap->flags;
+		__entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0;
+	),
+	TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx "
+		  "addr 0x%llx offset 0x%llx length 0x%llx type %s flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  MAJOR(__entry->bdev), MINOR(__entry->bdev),
+		  __entry->pos,
+		  __entry->dirty_len,
+		  __entry->addr,
+		  __entry->offset,
+		  __entry->length,
+		  __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS),
+		  __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS))
+);
 
 TRACE_EVENT(iomap_iter,
 	TP_PROTO(struct iomap_iter *iter, const void *ops,
@@ -165,6 +206,7 @@ TRACE_EVENT(iomap_iter,
 		__field(u64, ino)
 		__field(loff_t, pos)
 		__field(u64, length)
+		__field(s64, processed)
 		__field(unsigned int, flags)
 		__field(const void *, ops)
 		__field(unsigned long, caller)
@@ -174,15 +216,17 @@ TRACE_EVENT(iomap_iter,
 		__entry->ino = iter->inode->i_ino;
 		__entry->pos = iter->pos;
 		__entry->length = iomap_length(iter);
+		__entry->processed = iter->processed;
 		__entry->flags = iter->flags;
 		__entry->ops = ops;
 		__entry->caller = caller;
 	),
-	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx flags %s (0x%x) ops %ps caller %pS",
+	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx processed %lld flags %s (0x%x) ops %ps caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		   __entry->ino,
 		   __entry->pos,
 		   __entry->length,
+		   __entry->processed,
 		   __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
 		   __entry->flags,
 		   __entry->ops,
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index 8eec84c651bf..cb3cda1390ad 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -2763,9 +2763,7 @@ static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl)
  *	leafno	- the number of the leaf to be updated.
  *	newval	- the new value for the leaf.
  *
- * RETURN VALUES:
- *  0		- success
- *	-EIO	- i/o error
+ * RETURN VALUES: none
  */
 static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 {
@@ -2792,10 +2790,6 @@ static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 		 * get the buddy size (number of words covered) of
 		 * the new value.
 		 */
-
-		if ((newval - tp->dmt_budmin) > BUDMIN)
-			return -EIO;
-
 		budsz = BUDSIZE(newval, tp->dmt_budmin);
 
 		/* try to join.
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index cb6d1fda66a7..73389c68e251 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1058,7 +1058,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync)
 int lmLogOpen(struct super_block *sb)
 {
 	int rc;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct jfs_log *log;
 	struct jfs_sb_info *sbi = JFS_SBI(sb);
 
@@ -1070,7 +1070,7 @@ int lmLogOpen(struct super_block *sb)
 
 	mutex_lock(&jfs_log_mutex);
 	list_for_each_entry(log, &jfs_external_logs, journal_list) {
-		if (log->bdev_handle->bdev->bd_dev == sbi->logdev) {
+		if (file_bdev(log->bdev_file)->bd_dev == sbi->logdev) {
 			if (!uuid_equal(&log->uuid, &sbi->loguuid)) {
 				jfs_warn("wrong uuid on JFS journal");
 				mutex_unlock(&jfs_log_mutex);
@@ -1100,14 +1100,14 @@ int lmLogOpen(struct super_block *sb)
 	 * file systems to log may have n-to-1 relationship;
 	 */
 
-	bdev_handle = bdev_open_by_dev(sbi->logdev,
+	bdev_file = bdev_file_open_by_dev(sbi->logdev,
 			BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL);
-	if (IS_ERR(bdev_handle)) {
-		rc = PTR_ERR(bdev_handle);
+	if (IS_ERR(bdev_file)) {
+		rc = PTR_ERR(bdev_file);
 		goto free;
 	}
 
-	log->bdev_handle = bdev_handle;
+	log->bdev_file = bdev_file;
 	uuid_copy(&log->uuid, &sbi->loguuid);
 
 	/*
@@ -1141,7 +1141,7 @@ journal_found:
 	lbmLogShutdown(log);
 
       close:		/* close external log device */
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
       free:		/* free log descriptor */
 	mutex_unlock(&jfs_log_mutex);
@@ -1162,7 +1162,7 @@ static int open_inline_log(struct super_block *sb)
 	init_waitqueue_head(&log->syncwait);
 
 	set_bit(log_INLINELOG, &log->flag);
-	log->bdev_handle = sb->s_bdev_handle;
+	log->bdev_file = sb->s_bdev_file;
 	log->base = addressPXD(&JFS_SBI(sb)->logpxd);
 	log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >>
 	    (L2LOGPSIZE - sb->s_blocksize_bits);
@@ -1436,7 +1436,7 @@ int lmLogClose(struct super_block *sb)
 {
 	struct jfs_sb_info *sbi = JFS_SBI(sb);
 	struct jfs_log *log = sbi->log;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	int rc = 0;
 
 	jfs_info("lmLogClose: log:0x%p", log);
@@ -1482,10 +1482,10 @@ int lmLogClose(struct super_block *sb)
 	 *	external log as separate logical volume
 	 */
 	list_del(&log->journal_list);
-	bdev_handle = log->bdev_handle;
+	bdev_file = log->bdev_file;
 	rc = lmLogShutdown(log);
 
-	bdev_release(bdev_handle);
+	fput(bdev_file);
 
 	kfree(log);
 
@@ -1972,7 +1972,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
 
 	bp->l_flag |= lbmREAD;
 
-	bio = bio_alloc(log->bdev_handle->bdev, 1, REQ_OP_READ, GFP_NOFS);
+	bio = bio_alloc(file_bdev(log->bdev_file), 1, REQ_OP_READ, GFP_NOFS);
 	bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
 	__bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
 	BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
@@ -2115,7 +2115,7 @@ static void lbmStartIO(struct lbuf * bp)
 	jfs_info("lbmStartIO");
 
 	if (!log->no_integrity)
-		bdev = log->bdev_handle->bdev;
+		bdev = file_bdev(log->bdev_file);
 
 	bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC,
 			GFP_NOFS);
diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h
index 84aa2d253907..8b8994e48cd0 100644
--- a/fs/jfs/jfs_logmgr.h
+++ b/fs/jfs/jfs_logmgr.h
@@ -356,7 +356,7 @@ struct jfs_log {
 				 *    before writing syncpt.
 				 */
 	struct list_head journal_list; /* Global list */
-	struct bdev_handle *bdev_handle; /* 4: log lv pointer */
+	struct file *bdev_file;	/* 4: log lv pointer */
 	int serial;		/* 4: log mount serial number */
 
 	s64 base;		/* @8: log extent address (inline log ) */
diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c
index 9b5c6a20b30c..98f9a432c336 100644
--- a/fs/jfs/jfs_mount.c
+++ b/fs/jfs/jfs_mount.c
@@ -431,7 +431,7 @@ int updateSuper(struct super_block *sb, uint state)
 	if (state == FM_MOUNT) {
 		/* record log's dev_t and mount serial number */
 		j_sb->s_logdev = cpu_to_le32(
-			new_encode_dev(sbi->log->bdev_handle->bdev->bd_dev));
+			new_encode_dev(file_bdev(sbi->log->bdev_file)->bd_dev));
 		j_sb->s_logserial = cpu_to_le32(sbi->log->serial);
 	} else if (state == FM_CLEAN) {
 		/*
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 8d8e556bd610..73f09a762b79 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -932,7 +932,7 @@ static int __init init_jfs_fs(void)
 
 	jfs_inode_cachep =
 	    kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info),
-			0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+			0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
 			offsetof(struct jfs_inode_info, i_inline_all),
 			sizeof_field(struct jfs_inode_info, i_inline_all),
 			init_once);
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0c93cad0f0ac..e29f4edf9572 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -358,7 +358,9 @@ int kernfs_get_tree(struct fs_context *fc)
 		}
 		sb->s_flags |= SB_ACTIVE;
 
-		uuid_gen(&sb->s_uuid);
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 		down_write(&root->kernfs_supers_rwsem);
 		list_add(&info->node, &info->root->supers);
diff --git a/fs/libfs.c b/fs/libfs.c
index eec6031b0155..0d14ae808fcf 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -23,6 +23,7 @@
 #include <linux/fsnotify.h>
 #include <linux/unicode.h>
 #include <linux/fscrypt.h>
+#include <linux/pidfs.h>
 
 #include <linux/uaccess.h>
 
@@ -240,17 +241,22 @@ const struct inode_operations simple_dir_inode_operations = {
 };
 EXPORT_SYMBOL(simple_dir_inode_operations);
 
-static void offset_set(struct dentry *dentry, u32 offset)
+/* 0 is '.', 1 is '..', so always start with offset 2 or more */
+enum {
+	DIR_OFFSET_MIN	= 2,
+};
+
+static void offset_set(struct dentry *dentry, long offset)
 {
-	dentry->d_fsdata = (void *)((uintptr_t)(offset));
+	dentry->d_fsdata = (void *)offset;
 }
 
-static u32 dentry2offset(struct dentry *dentry)
+static long dentry2offset(struct dentry *dentry)
 {
-	return (u32)((uintptr_t)(dentry->d_fsdata));
+	return (long)dentry->d_fsdata;
 }
 
-static struct lock_class_key simple_offset_xa_lock;
+static struct lock_class_key simple_offset_lock_class;
 
 /**
  * simple_offset_init - initialize an offset_ctx
@@ -259,11 +265,9 @@ static struct lock_class_key simple_offset_xa_lock;
  */
 void simple_offset_init(struct offset_ctx *octx)
 {
-	xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1);
-	lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock);
-
-	/* 0 is '.', 1 is '..', so always start with offset 2 */
-	octx->next_offset = 2;
+	mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE);
+	lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class);
+	octx->next_offset = DIR_OFFSET_MIN;
 }
 
 /**
@@ -271,20 +275,19 @@ void simple_offset_init(struct offset_ctx *octx)
  * @octx: directory offset ctx to be updated
  * @dentry: new dentry being added
  *
- * Returns zero on success. @so_ctx and the dentry offset are updated.
+ * Returns zero on success. @octx and the dentry's offset are updated.
  * Otherwise, a negative errno value is returned.
  */
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
 {
-	static const struct xa_limit limit = XA_LIMIT(2, U32_MAX);
-	u32 offset;
+	unsigned long offset;
 	int ret;
 
 	if (dentry2offset(dentry) != 0)
 		return -EBUSY;
 
-	ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit,
-			      &octx->next_offset, GFP_KERNEL);
+	ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
+				 LONG_MAX, &octx->next_offset, GFP_KERNEL);
 	if (ret < 0)
 		return ret;
 
@@ -300,17 +303,49 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
  */
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
 {
-	u32 offset;
+	long offset;
 
 	offset = dentry2offset(dentry);
 	if (offset == 0)
 		return;
 
-	xa_erase(&octx->xa, offset);
+	mtree_erase(&octx->mt, offset);
 	offset_set(dentry, 0);
 }
 
 /**
+ * simple_offset_empty - Check if a dentry can be unlinked
+ * @dentry: dentry to be tested
+ *
+ * Returns 0 if @dentry is a non-empty directory; otherwise returns 1.
+ */
+int simple_offset_empty(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	struct offset_ctx *octx;
+	struct dentry *child;
+	unsigned long index;
+	int ret = 1;
+
+	if (!inode || !S_ISDIR(inode->i_mode))
+		return ret;
+
+	index = DIR_OFFSET_MIN;
+	octx = inode->i_op->get_offset_ctx(inode);
+	mt_for_each(&octx->mt, child, index, LONG_MAX) {
+		spin_lock(&child->d_lock);
+		if (simple_positive(child)) {
+			spin_unlock(&child->d_lock);
+			ret = 0;
+			break;
+		}
+		spin_unlock(&child->d_lock);
+	}
+
+	return ret;
+}
+
+/**
  * simple_offset_rename_exchange - exchange rename with directory offsets
  * @old_dir: parent of dentry being moved
  * @old_dentry: dentry being moved
@@ -327,8 +362,8 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 {
 	struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
 	struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
-	u32 old_index = dentry2offset(old_dentry);
-	u32 new_index = dentry2offset(new_dentry);
+	long old_index = dentry2offset(old_dentry);
+	long new_index = dentry2offset(new_dentry);
 	int ret;
 
 	simple_offset_remove(old_ctx, old_dentry);
@@ -354,9 +389,9 @@ int simple_offset_rename_exchange(struct inode *old_dir,
 
 out_restore:
 	offset_set(old_dentry, old_index);
-	xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL);
+	mtree_store(&old_ctx->mt, old_index, old_dentry, GFP_KERNEL);
 	offset_set(new_dentry, new_index);
-	xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL);
+	mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL);
 	return ret;
 }
 
@@ -369,7 +404,7 @@ out_restore:
  */
 void simple_offset_destroy(struct offset_ctx *octx)
 {
-	xa_destroy(&octx->xa);
+	mtree_destroy(&octx->mt);
 }
 
 /**
@@ -399,15 +434,16 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
 
 	/* In this case, ->private_data is protected by f_pos_lock */
 	file->private_data = NULL;
-	return vfs_setpos(file, offset, U32_MAX);
+	return vfs_setpos(file, offset, LONG_MAX);
 }
 
-static struct dentry *offset_find_next(struct xa_state *xas)
+static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset)
 {
+	MA_STATE(mas, &octx->mt, offset, offset);
 	struct dentry *child, *found = NULL;
 
 	rcu_read_lock();
-	child = xas_next_entry(xas, U32_MAX);
+	child = mas_find(&mas, LONG_MAX);
 	if (!child)
 		goto out;
 	spin_lock(&child->d_lock);
@@ -421,8 +457,8 @@ out:
 
 static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 {
-	u32 offset = dentry2offset(dentry);
 	struct inode *inode = d_inode(dentry);
+	long offset = dentry2offset(dentry);
 
 	return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset,
 			  inode->i_ino, fs_umode_to_dtype(inode->i_mode));
@@ -430,12 +466,11 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
 
 static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 {
-	struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode);
-	XA_STATE(xas, &so_ctx->xa, ctx->pos);
+	struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
 	struct dentry *dentry;
 
 	while (true) {
-		dentry = offset_find_next(&xas);
+		dentry = offset_find_next(octx, ctx->pos);
 		if (!dentry)
 			return ERR_PTR(-ENOENT);
 
@@ -444,8 +479,8 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
 			break;
 		}
 
+		ctx->pos = dentry2offset(dentry) + 1;
 		dput(dentry);
-		ctx->pos = xas.xa_index + 1;
 	}
 	return NULL;
 }
@@ -481,7 +516,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx)
 		return 0;
 
 	/* In this case, ->private_data is protected by f_pos_lock */
-	if (ctx->pos == 2)
+	if (ctx->pos == DIR_OFFSET_MIN)
 		file->private_data = NULL;
 	else if (file->private_data == ERR_PTR(-ENOENT))
 		return 0;
@@ -1580,7 +1615,7 @@ EXPORT_SYMBOL(alloc_anon_inode);
  * All arguments are ignored and it just returns -EINVAL.
  */
 int
-simple_nosetlease(struct file *filp, int arg, struct file_lock **flp,
+simple_nosetlease(struct file *filp, int arg, struct file_lease **flp,
 		  void **priv)
 {
 	return -EINVAL;
@@ -1704,16 +1739,28 @@ bool is_empty_dir_inode(struct inode *inode)
 static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 				const char *str, const struct qstr *name)
 {
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct super_block *sb = dentry->d_sb;
-	const struct unicode_map *um = sb->s_encoding;
-	struct qstr qstr = QSTR_INIT(str, len);
+	const struct dentry *parent;
+	const struct inode *dir;
 	char strbuf[DNAME_INLINE_LEN];
-	int ret;
+	struct qstr qstr;
+
+	/*
+	 * Attempt a case-sensitive match first. It is cheaper and
+	 * should cover most lookups, including all the sane
+	 * applications that expect a case-sensitive filesystem.
+	 *
+	 * This comparison is safe under RCU because the caller
+	 * guarantees the consistency between str and len. See
+	 * __d_lookup_rcu_op_compare() for details.
+	 */
+	if (len == name->len && !memcmp(str, name->name, len))
+		return 0;
 
+	parent = READ_ONCE(dentry->d_parent);
+	dir = READ_ONCE(parent->d_inode);
 	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
+		return 1;
+
 	/*
 	 * If the dentry name is stored in-line, then it may be concurrently
 	 * modified by a rename.  If this happens, the VFS will eventually retry
@@ -1724,20 +1771,14 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 	if (len <= DNAME_INLINE_LEN - 1) {
 		memcpy(strbuf, str, len);
 		strbuf[len] = 0;
-		qstr.name = strbuf;
+		str = strbuf;
 		/* prevent compiler from optimizing out the temporary buffer */
 		barrier();
 	}
-	ret = utf8_strncasecmp(um, name, &qstr);
-	if (ret >= 0)
-		return ret;
+	qstr.len = len;
+	qstr.name = str;
 
-	if (sb_has_strict_encoding(sb))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
+	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
 
 /**
@@ -1752,7 +1793,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 	const struct inode *dir = READ_ONCE(dentry->d_inode);
 	struct super_block *sb = dentry->d_sb;
 	const struct unicode_map *um = sb->s_encoding;
-	int ret = 0;
+	int ret;
 
 	if (!dir || !IS_CASEFOLDED(dir))
 		return 0;
@@ -1766,73 +1807,45 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_hash = generic_ci_d_hash,
 	.d_compare = generic_ci_d_compare,
-};
-#endif
-
 #ifdef CONFIG_FS_ENCRYPTION
-static const struct dentry_operations generic_encrypted_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
+#endif
 };
 #endif
 
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
-	.d_hash = generic_ci_d_hash,
-	.d_compare = generic_ci_d_compare,
+#ifdef CONFIG_FS_ENCRYPTION
+static const struct dentry_operations generic_encrypted_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 };
 #endif
 
 /**
- * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry
- * @dentry:	dentry to set ops on
- *
- * Casefolded directories need d_hash and d_compare set, so that the dentries
- * contained in them are handled case-insensitively.  Note that these operations
- * are needed on the parent directory rather than on the dentries in it, and
- * while the casefolding flag can be toggled on and off on an empty directory,
- * dentry_operations can't be changed later.  As a result, if the filesystem has
- * casefolding support enabled at all, we have to give all dentries the
- * casefolding operations even if their inode doesn't have the casefolding flag
- * currently (and thus the casefolding ops would be no-ops for now).
- *
- * Encryption works differently in that the only dentry operation it needs is
- * d_revalidate, which it only needs on dentries that have the no-key name flag.
- * The no-key flag can't be set "later", so we don't have to worry about that.
+ * generic_set_sb_d_ops - helper for choosing the set of
+ * filesystem-wide dentry operations for the enabled features
+ * @sb: superblock to be configured
  *
- * Finally, to maximize compatibility with overlayfs (which isn't compatible
- * with certain dentry operations) and to avoid taking an unnecessary
- * performance hit, we use custom dentry_operations for each possible
- * combination rather than always installing all operations.
+ * Filesystems supporting casefolding and/or fscrypt can call this
+ * helper at mount-time to configure sb->s_d_op to best set of dentry
+ * operations required for the enabled features. The helper must be
+ * called after these have been configured, but before the root dentry
+ * is created.
  */
-void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
+void generic_set_sb_d_ops(struct super_block *sb)
 {
-#ifdef CONFIG_FS_ENCRYPTION
-	bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
-#endif
 #if IS_ENABLED(CONFIG_UNICODE)
-	bool needs_ci_ops = dentry->d_sb->s_encoding;
-#endif
-#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
-	if (needs_encrypt_ops && needs_ci_ops) {
-		d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
+	if (sb->s_encoding) {
+		sb->s_d_op = &generic_ci_dentry_ops;
 		return;
 	}
 #endif
 #ifdef CONFIG_FS_ENCRYPTION
-	if (needs_encrypt_ops) {
-		d_set_d_op(dentry, &generic_encrypted_dentry_ops);
-		return;
-	}
-#endif
-#if IS_ENABLED(CONFIG_UNICODE)
-	if (needs_ci_ops) {
-		d_set_d_op(dentry, &generic_ci_dentry_ops);
+	if (sb->s_cop) {
+		sb->s_d_op = &generic_encrypted_dentry_ops;
 		return;
 	}
 #endif
 }
-EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops);
+EXPORT_SYMBOL(generic_set_sb_d_ops);
 
 /**
  * inode_maybe_inc_iversion - increments i_version
@@ -1973,3 +1986,144 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
 	return ts;
 }
 EXPORT_SYMBOL(simple_inode_init_ts);
+
+static inline struct dentry *get_stashed_dentry(struct dentry *stashed)
+{
+	struct dentry *dentry;
+
+	guard(rcu)();
+	dentry = READ_ONCE(stashed);
+	if (!dentry)
+		return NULL;
+	if (!lockref_get_not_dead(&dentry->d_lockref))
+		return NULL;
+	return dentry;
+}
+
+static struct dentry *prepare_anon_dentry(struct dentry **stashed,
+					  unsigned long ino,
+					  struct super_block *sb,
+					  void *data)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+	const struct stashed_operations *sops = sb->s_fs_info;
+
+	dentry = d_alloc_anon(sb);
+	if (!dentry)
+		return ERR_PTR(-ENOMEM);
+
+	inode = new_inode_pseudo(sb);
+	if (!inode) {
+		dput(dentry);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inode->i_ino = ino;
+	inode->i_flags |= S_IMMUTABLE;
+	inode->i_mode = S_IFREG;
+	simple_inode_init_ts(inode);
+	sops->init_inode(inode, data);
+
+	/* Notice when this is changed. */
+	WARN_ON_ONCE(!S_ISREG(inode->i_mode));
+	WARN_ON_ONCE(!IS_IMMUTABLE(inode));
+
+	/* Store address of location where dentry's supposed to be stashed. */
+	dentry->d_fsdata = stashed;
+
+	/* @data is now owned by the fs */
+	d_instantiate(dentry, inode);
+	return dentry;
+}
+
+static struct dentry *stash_dentry(struct dentry **stashed,
+				   struct dentry *dentry)
+{
+	guard(rcu)();
+	for (;;) {
+		struct dentry *old;
+
+		/* Assume any old dentry was cleared out. */
+		old = cmpxchg(stashed, NULL, dentry);
+		if (likely(!old))
+			return dentry;
+
+		/* Check if somebody else installed a reusable dentry. */
+		if (lockref_get_not_dead(&old->d_lockref))
+			return old;
+
+		/* There's an old dead dentry there, try to take it over. */
+		if (likely(try_cmpxchg(stashed, &old, dentry)))
+			return dentry;
+	}
+}
+
+/**
+ * path_from_stashed - create path from stashed or new dentry
+ * @stashed:    where to retrieve or stash dentry
+ * @ino:        inode number to use
+ * @mnt:        mnt of the filesystems to use
+ * @data:       data to store in inode->i_private
+ * @path:       path to create
+ *
+ * The function tries to retrieve a stashed dentry from @stashed. If the dentry
+ * is still valid then it will be reused. If the dentry isn't able the function
+ * will allocate a new dentry and inode. It will then check again whether it
+ * can reuse an existing dentry in case one has been added in the meantime or
+ * update @stashed with the newly added dentry.
+ *
+ * Special-purpose helper for nsfs and pidfs.
+ *
+ * Return: On success zero and on failure a negative error is returned.
+ */
+int path_from_stashed(struct dentry **stashed, unsigned long ino,
+		      struct vfsmount *mnt, void *data, struct path *path)
+{
+	struct dentry *dentry;
+	const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
+
+	/* See if dentry can be reused. */
+	path->dentry = get_stashed_dentry(*stashed);
+	if (path->dentry) {
+		sops->put_data(data);
+		goto out_path;
+	}
+
+	/* Allocate a new dentry. */
+	dentry = prepare_anon_dentry(stashed, ino, mnt->mnt_sb, data);
+	if (IS_ERR(dentry)) {
+		sops->put_data(data);
+		return PTR_ERR(dentry);
+	}
+
+	/* Added a new dentry. @data is now owned by the filesystem. */
+	path->dentry = stash_dentry(stashed, dentry);
+	if (path->dentry != dentry)
+		dput(dentry);
+
+out_path:
+	WARN_ON_ONCE(path->dentry->d_fsdata != stashed);
+	WARN_ON_ONCE(d_inode(path->dentry)->i_private != data);
+	path->mnt = mntget(mnt);
+	return 0;
+}
+
+void stashed_dentry_prune(struct dentry *dentry)
+{
+	struct dentry **stashed = dentry->d_fsdata;
+	struct inode *inode = d_inode(dentry);
+
+	if (WARN_ON_ONCE(!stashed))
+		return;
+
+	if (!inode)
+		return;
+
+	/*
+	 * Only replace our own @dentry as someone else might've
+	 * already cleared out @dentry and stashed their own
+	 * dentry in there.
+	 */
+	cmpxchg(stashed, dentry, NULL);
+}
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 8161667c976f..527458db4525 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -243,7 +243,7 @@ static void encode_nlm4_holder(struct xdr_stream *xdr,
 	u64 l_offset, l_len;
 	__be32 *p;
 
-	encode_bool(xdr, lock->fl.fl_type == F_RDLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_RDLCK);
 	encode_int32(xdr, lock->svid);
 	encode_netobj(xdr, lock->oh.data, lock->oh.len);
 
@@ -270,7 +270,7 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result)
 		goto out_overflow;
 	exclusive = be32_to_cpup(p++);
 	lock->svid = be32_to_cpup(p);
-	fl->fl_pid = (pid_t)lock->svid;
+	fl->c.flc_pid = (pid_t)lock->svid;
 
 	error = decode_netobj(xdr, &lock->oh);
 	if (unlikely(error))
@@ -280,8 +280,8 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result)
 	if (unlikely(p == NULL))
 		goto out_overflow;
 
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
 	p = xdr_decode_hyper(p, &l_offset);
 	xdr_decode_hyper(p, &l_len);
 	nlm4svc_set_file_lock_range(fl, l_offset, l_len);
@@ -357,7 +357,7 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req,
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 }
 
@@ -380,7 +380,7 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 	encode_bool(xdr, args->reclaim);
 	encode_int32(xdr, args->state);
@@ -403,7 +403,7 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm4_lock(xdr, lock);
 }
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 5d85715be763..a7e0519ec024 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -185,7 +185,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 			continue;
 		if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
 			continue;
-		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->fl_file)), fh) != 0)
+		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->c.flc_file)), fh) != 0)
 			continue;
 		/* Alright, we found a lock. Set the return status
 		 * and wake up the caller
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index fba6c7fa7474..cebcc283b7ce 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -133,7 +133,8 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	char *nodename = req->a_host->h_rpcclnt->cl_nodename;
 
 	nlmclnt_next_cookie(&argp->cookie);
-	memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
+	memcpy(&lock->fh, NFS_FH(file_inode(fl->c.flc_file)),
+	       sizeof(struct nfs_fh));
 	lock->caller  = nodename;
 	lock->oh.data = req->a_owner;
 	lock->oh.len  = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
@@ -142,7 +143,7 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	lock->svid = fl->fl_u.nfs_fl.owner->pid;
 	lock->fl.fl_start = fl->fl_start;
 	lock->fl.fl_end = fl->fl_end;
-	lock->fl.fl_type = fl->fl_type;
+	lock->fl.c.flc_type = fl->c.flc_type;
 }
 
 static void nlmclnt_release_lockargs(struct nlm_rqst *req)
@@ -182,7 +183,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *dat
 	call->a_callback_data = data;
 
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
-		if (fl->fl_type != F_UNLCK) {
+		if (fl->c.flc_type != F_UNLCK) {
 			call->a_args.block = IS_SETLKW(cmd) ? 1 : 0;
 			status = nlmclnt_lock(call, fl);
 		} else
@@ -432,13 +433,14 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 {
 	int	status;
 
-	status = nlmclnt_call(nfs_file_cred(fl->fl_file), req, NLMPROC_TEST);
+	status = nlmclnt_call(nfs_file_cred(fl->c.flc_file), req,
+			      NLMPROC_TEST);
 	if (status < 0)
 		goto out;
 
 	switch (req->a_res.status) {
 		case nlm_granted:
-			fl->fl_type = F_UNLCK;
+			fl->c.flc_type = F_UNLCK;
 			break;
 		case nlm_lck_denied:
 			/*
@@ -446,8 +448,8 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 			 */
 			fl->fl_start = req->a_res.lock.fl.fl_start;
 			fl->fl_end = req->a_res.lock.fl.fl_end;
-			fl->fl_type = req->a_res.lock.fl.fl_type;
-			fl->fl_pid = -req->a_res.lock.fl.fl_pid;
+			fl->c.flc_type = req->a_res.lock.fl.c.flc_type;
+			fl->c.flc_pid = -req->a_res.lock.fl.c.flc_pid;
 			break;
 		default:
 			status = nlm_stat_to_errno(req->a_res.status);
@@ -485,14 +487,15 @@ static const struct file_lock_operations nlmclnt_lock_ops = {
 static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host)
 {
 	fl->fl_u.nfs_fl.state = 0;
-	fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->fl_owner);
+	fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host,
+						       fl->c.flc_owner);
 	INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list);
 	fl->fl_ops = &nlmclnt_lock_ops;
 }
 
 static int do_vfs_lock(struct file_lock *fl)
 {
-	return locks_lock_file_wait(fl->fl_file, fl);
+	return locks_lock_file_wait(fl->c.flc_file, fl);
 }
 
 /*
@@ -518,12 +521,12 @@ static int do_vfs_lock(struct file_lock *fl)
 static int
 nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 {
-	const struct cred *cred = nfs_file_cred(fl->fl_file);
+	const struct cred *cred = nfs_file_cred(fl->c.flc_file);
 	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	struct nlm_wait block;
-	unsigned char fl_flags = fl->fl_flags;
-	unsigned char fl_type;
+	unsigned char flags = fl->c.flc_flags;
+	unsigned char type;
 	__be32 b_status;
 	int status = -ENOLCK;
 
@@ -531,9 +534,9 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 		goto out;
 	req->a_args.state = nsm_local_state;
 
-	fl->fl_flags |= FL_ACCESS;
+	fl->c.flc_flags |= FL_ACCESS;
 	status = do_vfs_lock(fl);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = flags;
 	if (status < 0)
 		goto out;
 
@@ -591,11 +594,11 @@ again:
 			goto again;
 		}
 		/* Ensure the resulting lock will get added to granted list */
-		fl->fl_flags |= FL_SLEEP;
+		fl->c.flc_flags |= FL_SLEEP;
 		if (do_vfs_lock(fl) < 0)
 			printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n", __func__);
 		up_read(&host->h_rwsem);
-		fl->fl_flags = fl_flags;
+		fl->c.flc_flags = flags;
 		status = 0;
 	}
 	if (status < 0)
@@ -605,7 +608,7 @@ again:
 	 * cases NLM_LCK_DENIED is returned for a permanent error.  So
 	 * turn it into an ENOLCK.
 	 */
-	if (resp->status == nlm_lck_denied && (fl_flags & FL_SLEEP))
+	if (resp->status == nlm_lck_denied && (flags & FL_SLEEP))
 		status = -ENOLCK;
 	else
 		status = nlm_stat_to_errno(resp->status);
@@ -622,13 +625,13 @@ out_unlock:
 			   req->a_host->h_addrlen, req->a_res.status);
 	dprintk("lockd: lock attempt ended in fatal error.\n"
 		"       Attempting to unlock.\n");
-	fl_type = fl->fl_type;
-	fl->fl_type = F_UNLCK;
+	type = fl->c.flc_type;
+	fl->c.flc_type = F_UNLCK;
 	down_read(&host->h_rwsem);
 	do_vfs_lock(fl);
 	up_read(&host->h_rwsem);
-	fl->fl_type = fl_type;
-	fl->fl_flags = fl_flags;
+	fl->c.flc_type = type;
+	fl->c.flc_flags = flags;
 	nlmclnt_async_call(cred, req, NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
 	return status;
 }
@@ -651,12 +654,14 @@ nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl,
 	nlmclnt_setlockargs(req, fl);
 	req->a_args.reclaim = 1;
 
-	status = nlmclnt_call(nfs_file_cred(fl->fl_file), req, NLMPROC_LOCK);
+	status = nlmclnt_call(nfs_file_cred(fl->c.flc_file), req,
+			      NLMPROC_LOCK);
 	if (status >= 0 && req->a_res.status == nlm_granted)
 		return 0;
 
 	printk(KERN_WARNING "lockd: failed to reclaim lock for pid %d "
-				"(errno %d, status %d)\n", fl->fl_pid,
+				"(errno %d, status %d)\n",
+				fl->c.flc_pid,
 				status, ntohl(req->a_res.status));
 
 	/*
@@ -683,26 +688,26 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl)
 	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	int status;
-	unsigned char fl_flags = fl->fl_flags;
+	unsigned char flags = fl->c.flc_flags;
 
 	/*
 	 * Note: the server is supposed to either grant us the unlock
 	 * request, or to deny it with NLM_LCK_DENIED_GRACE_PERIOD. In either
 	 * case, we want to unlock.
 	 */
-	fl->fl_flags |= FL_EXISTS;
+	fl->c.flc_flags |= FL_EXISTS;
 	down_read(&host->h_rwsem);
 	status = do_vfs_lock(fl);
 	up_read(&host->h_rwsem);
-	fl->fl_flags = fl_flags;
+	fl->c.flc_flags = flags;
 	if (status == -ENOENT) {
 		status = 0;
 		goto out;
 	}
 
 	refcount_inc(&req->a_count);
-	status = nlmclnt_async_call(nfs_file_cred(fl->fl_file), req,
-			NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
+	status = nlmclnt_async_call(nfs_file_cred(fl->c.flc_file), req,
+				    NLMPROC_UNLOCK, &nlmclnt_unlock_ops);
 	if (status < 0)
 		goto out;
 
@@ -795,8 +800,8 @@ static int nlmclnt_cancel(struct nlm_host *host, int block, struct file_lock *fl
 	req->a_args.block = block;
 
 	refcount_inc(&req->a_count);
-	status = nlmclnt_async_call(nfs_file_cred(fl->fl_file), req,
-			NLMPROC_CANCEL, &nlmclnt_cancel_ops);
+	status = nlmclnt_async_call(nfs_file_cred(fl->c.flc_file), req,
+				    NLMPROC_CANCEL, &nlmclnt_cancel_ops);
 	if (status == 0 && req->a_res.status == nlm_lck_denied)
 		status = -ENOLCK;
 	nlmclnt_release_call(req);
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 4df62f635529..a3e97278b997 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -238,7 +238,7 @@ static void encode_nlm_holder(struct xdr_stream *xdr,
 	u32 l_offset, l_len;
 	__be32 *p;
 
-	encode_bool(xdr, lock->fl.fl_type == F_RDLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_RDLCK);
 	encode_int32(xdr, lock->svid);
 	encode_netobj(xdr, lock->oh.data, lock->oh.len);
 
@@ -265,7 +265,7 @@ static int decode_nlm_holder(struct xdr_stream *xdr, struct nlm_res *result)
 		goto out_overflow;
 	exclusive = be32_to_cpup(p++);
 	lock->svid = be32_to_cpup(p);
-	fl->fl_pid = (pid_t)lock->svid;
+	fl->c.flc_pid = (pid_t)lock->svid;
 
 	error = decode_netobj(xdr, &lock->oh);
 	if (unlikely(error))
@@ -275,8 +275,8 @@ static int decode_nlm_holder(struct xdr_stream *xdr, struct nlm_res *result)
 	if (unlikely(p == NULL))
 		goto out_overflow;
 
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = exclusive != 0 ? F_WRLCK : F_RDLCK;
 	l_offset = be32_to_cpup(p++);
 	l_len = be32_to_cpup(p);
 	end = l_offset + l_len - 1;
@@ -357,7 +357,7 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req,
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 }
 
@@ -380,7 +380,7 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 	encode_bool(xdr, args->reclaim);
 	encode_int32(xdr, args->state);
@@ -403,7 +403,7 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req,
 
 	encode_cookie(xdr, &args->cookie);
 	encode_bool(xdr, args->block);
-	encode_bool(xdr, lock->fl.fl_type == F_WRLCK);
+	encode_bool(xdr, lock->fl.c.flc_type == F_WRLCK);
 	encode_nlm_lock(xdr, lock);
 }
 
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index ce5862482097..ab8042a5b895 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -710,8 +710,6 @@ static const struct svc_version *nlmsvc_version[] = {
 #endif
 };
 
-static struct svc_stat		nlmsvc_stats;
-
 #define NLM_NRVERS	ARRAY_SIZE(nlmsvc_version)
 static struct svc_program	nlmsvc_program = {
 	.pg_prog		= NLM_PROGRAM,		/* program number */
@@ -719,7 +717,6 @@ static struct svc_program	nlmsvc_program = {
 	.pg_vers		= nlmsvc_version,	/* version table */
 	.pg_name		= "lockd",		/* service name */
 	.pg_class		= "nfsd",		/* share authentication with nfsd */
-	.pg_stats		= &nlmsvc_stats,	/* stats table */
 	.pg_authenticate	= &lockd_authenticate,	/* export authentication */
 	.pg_init_request	= svc_generic_init_request,
 	.pg_rpcbind_set		= svc_generic_rpcbind_set,
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index b72023a6b4c1..8a72c418cdcc 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -52,16 +52,16 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 		*filp = file;
 
 		/* Set up the missing parts of the file_lock structure */
-		lock->fl.fl_flags = FL_POSIX;
-		lock->fl.fl_file  = file->f_file[mode];
-		lock->fl.fl_pid = current->tgid;
+		lock->fl.c.flc_flags = FL_POSIX;
+		lock->fl.c.flc_file  = file->f_file[mode];
+		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_start = (loff_t)lock->lock_start;
 		lock->fl.fl_end = lock->lock_len ?
 				   (loff_t)(lock->lock_start + lock->lock_len - 1) :
 				   OFFSET_MAX;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
-		if (!lock->fl.fl_owner) {
+		if (!lock->fl.c.flc_owner) {
 			/* lockowner allocation has failed */
 			nlmsvc_release_host(host);
 			return nlm_lck_denied_nolocks;
@@ -106,7 +106,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-	test_owner = argp->lock.fl.fl_owner;
+	test_owner = argp->lock.fl.c.flc_owner;
 	/* Now check for conflicting locks */
 	resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie);
 	if (resp->status == nlm_drop_reply)
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 2dc10900ad1c..1f2149db10f2 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -150,16 +150,17 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock)
 	struct file_lock	*fl;
 
 	dprintk("lockd: nlmsvc_lookup_block f=%p pd=%d %Ld-%Ld ty=%d\n",
-				file, lock->fl.fl_pid,
+				file, lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
-				(long long)lock->fl.fl_end, lock->fl.fl_type);
+				(long long)lock->fl.fl_end,
+				lock->fl.c.flc_type);
 	spin_lock(&nlm_blocked_lock);
 	list_for_each_entry(block, &nlm_blocked, b_list) {
 		fl = &block->b_call->a_args.lock.fl;
 		dprintk("lockd: check f=%p pd=%d %Ld-%Ld ty=%d cookie=%s\n",
-				block->b_file, fl->fl_pid,
+				block->b_file, fl->c.flc_pid,
 				(long long)fl->fl_start,
-				(long long)fl->fl_end, fl->fl_type,
+				(long long)fl->fl_end, fl->c.flc_type,
 				nlmdbg_cookie2a(&block->b_call->a_args.cookie));
 		if (block->b_file == file && nlm_compare_locks(fl, &lock->fl)) {
 			kref_get(&block->b_count);
@@ -244,7 +245,7 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 		goto failed_free;
 
 	/* Set notifier function for VFS, and init args */
-	call->a_args.lock.fl.fl_flags |= FL_SLEEP;
+	call->a_args.lock.fl.c.flc_flags |= FL_SLEEP;
 	call->a_args.lock.fl.fl_lmops = &nlmsvc_lock_operations;
 	nlmclnt_next_cookie(&call->a_args.cookie);
 
@@ -402,14 +403,14 @@ static struct nlm_lockowner *nlmsvc_find_lockowner(struct nlm_host *host, pid_t
 void
 nlmsvc_release_lockowner(struct nlm_lock *lock)
 {
-	if (lock->fl.fl_owner)
-		nlmsvc_put_lockowner(lock->fl.fl_owner);
+	if (lock->fl.c.flc_owner)
+		nlmsvc_put_lockowner(lock->fl.c.flc_owner);
 }
 
 void nlmsvc_locks_init_private(struct file_lock *fl, struct nlm_host *host,
 						pid_t pid)
 {
-	fl->fl_owner = nlmsvc_find_lockowner(host, pid);
+	fl->c.flc_owner = nlmsvc_find_lockowner(host, pid);
 }
 
 /*
@@ -425,7 +426,7 @@ static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock)
 
 	/* set default data area */
 	call->a_args.lock.oh.data = call->a_owner;
-	call->a_args.lock.svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid;
+	call->a_args.lock.svid = ((struct nlm_lockowner *) lock->fl.c.flc_owner)->pid;
 
 	if (lock->oh.len > NLMCLNT_OHSIZE) {
 		void *data = kmalloc(lock->oh.len, GFP_KERNEL);
@@ -489,7 +490,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 
 	dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
 				inode->i_sb->s_id, inode->i_ino,
-				lock->fl.fl_type, lock->fl.fl_pid,
+				lock->fl.c.flc_type,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end,
 				wait);
@@ -512,7 +514,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			goto out;
 		lock = &block->b_call->a_args.lock;
 	} else
-		lock->fl.fl_flags &= ~FL_SLEEP;
+		lock->fl.c.flc_flags &= ~FL_SLEEP;
 
 	if (block->b_flags & B_QUEUED) {
 		dprintk("lockd: nlmsvc_lock deferred block %p flags %d\n",
@@ -560,10 +562,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	spin_unlock(&nlm_blocked_lock);
 
 	if (!wait)
-		lock->fl.fl_flags &= ~FL_SLEEP;
+		lock->fl.c.flc_flags &= ~FL_SLEEP;
 	mode = lock_to_openmode(&lock->fl);
 	error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL);
-	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.c.flc_flags &= ~FL_SLEEP;
 
 	dprintk("lockd: vfs_lock_file returned %d\n", error);
 	switch (error) {
@@ -616,7 +618,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_type,
+				lock->fl.c.flc_type,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
@@ -636,19 +638,19 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
-	if (lock->fl.fl_type == F_UNLCK) {
+	if (lock->fl.c.flc_type == F_UNLCK) {
 		ret = nlm_granted;
 		goto out;
 	}
 
 	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
-		lock->fl.fl_type, (long long)lock->fl.fl_start,
+		lock->fl.c.flc_type, (long long)lock->fl.fl_start,
 		(long long)lock->fl.fl_end);
 	conflock->caller = "somehost";	/* FIXME */
 	conflock->len = strlen(conflock->caller);
 	conflock->oh.len = 0;		/* don't return OH info */
-	conflock->svid = lock->fl.fl_pid;
-	conflock->fl.fl_type = lock->fl.fl_type;
+	conflock->svid = lock->fl.c.flc_pid;
+	conflock->fl.c.flc_type = lock->fl.c.flc_type;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
 	locks_release_private(&lock->fl);
@@ -673,21 +675,21 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 	dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_pid,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
 	/* First, cancel any lock that might be there */
 	nlmsvc_cancel_blocked(net, file, lock);
 
-	lock->fl.fl_type = F_UNLCK;
-	lock->fl.fl_file = file->f_file[O_RDONLY];
-	if (lock->fl.fl_file)
-		error = vfs_lock_file(lock->fl.fl_file, F_SETLK,
+	lock->fl.c.flc_type = F_UNLCK;
+	lock->fl.c.flc_file = file->f_file[O_RDONLY];
+	if (lock->fl.c.flc_file)
+		error = vfs_lock_file(lock->fl.c.flc_file, F_SETLK,
 					&lock->fl, NULL);
-	lock->fl.fl_file = file->f_file[O_WRONLY];
-	if (lock->fl.fl_file)
-		error |= vfs_lock_file(lock->fl.fl_file, F_SETLK,
+	lock->fl.c.flc_file = file->f_file[O_WRONLY];
+	if (lock->fl.c.flc_file)
+		error |= vfs_lock_file(lock->fl.c.flc_file, F_SETLK,
 					&lock->fl, NULL);
 
 	return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
@@ -710,7 +712,7 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
 	dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
 				nlmsvc_file_inode(file)->i_sb->s_id,
 				nlmsvc_file_inode(file)->i_ino,
-				lock->fl.fl_pid,
+				lock->fl.c.flc_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
@@ -863,12 +865,12 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 	/* vfs_lock_file() can mangle fl_start and fl_end, but we need
 	 * them unchanged for the GRANT_MSG
 	 */
-	lock->fl.fl_flags |= FL_SLEEP;
+	lock->fl.c.flc_flags |= FL_SLEEP;
 	fl_start = lock->fl.fl_start;
 	fl_end = lock->fl.fl_end;
 	mode = lock_to_openmode(&lock->fl);
 	error = vfs_lock_file(file->f_file[mode], F_SETLK, &lock->fl, NULL);
-	lock->fl.fl_flags &= ~FL_SLEEP;
+	lock->fl.c.flc_flags &= ~FL_SLEEP;
 	lock->fl.fl_start = fl_start;
 	lock->fl.fl_end = fl_end;
 
@@ -993,8 +995,8 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
 		/* Client doesn't want it, just unlock it */
 		nlmsvc_unlink_block(block);
 		fl = &block->b_call->a_args.lock.fl;
-		fl->fl_type = F_UNLCK;
-		error = vfs_lock_file(fl->fl_file, F_SETLK, fl, NULL);
+		fl->c.flc_type = F_UNLCK;
+		error = vfs_lock_file(fl->c.flc_file, F_SETLK, fl, NULL);
 		if (error)
 			pr_warn("lockd: unable to unlock lock rejected by client!\n");
 		break;
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 32784f508c81..a03220e66ce0 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -77,12 +77,12 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 		/* Set up the missing parts of the file_lock structure */
 		mode = lock_to_openmode(&lock->fl);
-		lock->fl.fl_flags = FL_POSIX;
-		lock->fl.fl_file  = file->f_file[mode];
-		lock->fl.fl_pid = current->tgid;
+		lock->fl.c.flc_flags = FL_POSIX;
+		lock->fl.c.flc_file  = file->f_file[mode];
+		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
-		if (!lock->fl.fl_owner) {
+		if (!lock->fl.c.flc_owner) {
 			/* lockowner allocation has failed */
 			nlmsvc_release_host(host);
 			return nlm_lck_denied_nolocks;
@@ -127,7 +127,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
-	test_owner = argp->lock.fl.fl_owner;
+	test_owner = argp->lock.fl.c.flc_owner;
 
 	/* Now check for conflicting locks */
 	resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock, &resp->cookie));
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index e3b6229e7ae5..9103896164f6 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -73,7 +73,7 @@ static inline unsigned int file_hash(struct nfs_fh *f)
 
 int lock_to_openmode(struct file_lock *lock)
 {
-	return (lock->fl_type == F_WRLCK) ? O_WRONLY : O_RDONLY;
+	return lock_is_write(lock) ? O_WRONLY : O_RDONLY;
 }
 
 /*
@@ -181,18 +181,18 @@ static int nlm_unlock_files(struct nlm_file *file, const struct file_lock *fl)
 	struct file_lock lock;
 
 	locks_init_lock(&lock);
-	lock.fl_type  = F_UNLCK;
+	lock.c.flc_type  = F_UNLCK;
 	lock.fl_start = 0;
 	lock.fl_end   = OFFSET_MAX;
-	lock.fl_owner = fl->fl_owner;
-	lock.fl_pid   = fl->fl_pid;
-	lock.fl_flags = FL_POSIX;
+	lock.c.flc_owner = fl->c.flc_owner;
+	lock.c.flc_pid   = fl->c.flc_pid;
+	lock.c.flc_flags = FL_POSIX;
 
-	lock.fl_file = file->f_file[O_RDONLY];
-	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
+	lock.c.flc_file = file->f_file[O_RDONLY];
+	if (lock.c.flc_file && vfs_lock_file(lock.c.flc_file, F_SETLK, &lock, NULL))
 		goto out_err;
-	lock.fl_file = file->f_file[O_WRONLY];
-	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
+	lock.c.flc_file = file->f_file[O_WRONLY];
+	if (lock.c.flc_file && vfs_lock_file(lock.c.flc_file, F_SETLK, &lock, NULL))
 		goto out_err;
 	return 0;
 out_err:
@@ -218,14 +218,14 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 again:
 	file->f_locks = 0;
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+	for_each_file_lock(fl, &flctx->flc_posix) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
 
 		/* update current lock count */
 		file->f_locks++;
 
-		lockhost = ((struct nlm_lockowner *)fl->fl_owner)->host;
+		lockhost = ((struct nlm_lockowner *) fl->c.flc_owner)->host;
 		if (match(lockhost, host)) {
 
 			spin_unlock(&flctx->flc_lock);
@@ -272,7 +272,7 @@ nlm_file_inuse(struct nlm_file *file)
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
 		spin_lock(&flctx->flc_lock);
-		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+		for_each_file_lock(fl, &flctx->flc_posix) {
 			if (fl->fl_lmops == &nlmsvc_lock_operations) {
 				spin_unlock(&flctx->flc_lock);
 				return 1;
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 2fb5748dae0c..adfcce2bf11b 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -88,8 +88,8 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 
 	locks_init_lock(fl);
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = F_RDLCK;
 	end = start + len - 1;
 	fl->fl_start = s32_to_loff_t(start);
 	if (len == 0 || end < 0)
@@ -107,7 +107,7 @@ svcxdr_encode_holder(struct xdr_stream *xdr, const struct nlm_lock *lock)
 	s32 start, len;
 
 	/* exclusive */
-	if (xdr_stream_encode_bool(xdr, fl->fl_type != F_RDLCK) < 0)
+	if (xdr_stream_encode_bool(xdr, fl->c.flc_type != F_RDLCK) < 0)
 		return false;
 	if (xdr_stream_encode_u32(xdr, lock->svid) < 0)
 		return false;
@@ -164,7 +164,7 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -184,7 +184,7 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 	if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
 		return false;
 	if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
@@ -209,7 +209,7 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -223,7 +223,7 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		return false;
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
-	argp->lock.fl.fl_type = F_UNLCK;
+	argp->lock.fl.c.flc_type = F_UNLCK;
 
 	return true;
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 5fcbf30cd275..3d28b9c3ed15 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -89,8 +89,8 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock)
 		return false;
 
 	locks_init_lock(fl);
-	fl->fl_flags = FL_POSIX;
-	fl->fl_type  = F_RDLCK;
+	fl->c.flc_flags = FL_POSIX;
+	fl->c.flc_type  = F_RDLCK;
 	nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len);
 	return true;
 }
@@ -102,7 +102,7 @@ svcxdr_encode_holder(struct xdr_stream *xdr, const struct nlm_lock *lock)
 	s64 start, len;
 
 	/* exclusive */
-	if (xdr_stream_encode_bool(xdr, fl->fl_type != F_RDLCK) < 0)
+	if (xdr_stream_encode_bool(xdr, fl->c.flc_type != F_RDLCK) < 0)
 		return false;
 	if (xdr_stream_encode_u32(xdr, lock->svid) < 0)
 		return false;
@@ -159,7 +159,7 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -179,7 +179,7 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 	if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0)
 		return false;
 	if (xdr_stream_decode_u32(xdr, &argp->state) < 0)
@@ -204,7 +204,7 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
 	if (exclusive)
-		argp->lock.fl.fl_type = F_WRLCK;
+		argp->lock.fl.c.flc_type = F_WRLCK;
 
 	return true;
 }
@@ -218,7 +218,7 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		return false;
 	if (!svcxdr_decode_lock(xdr, &argp->lock))
 		return false;
-	argp->lock.fl.fl_type = F_UNLCK;
+	argp->lock.fl.c.flc_type = F_UNLCK;
 
 	return true;
 }
diff --git a/fs/locks.c b/fs/locks.c
index cc7c117ee192..90c8746874de 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -48,7 +48,6 @@
  * children.
  *
  */
-
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
@@ -70,24 +69,28 @@
 
 #include <linux/uaccess.h>
 
-#define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
-#define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
-#define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
-#define IS_REMOTELCK(fl)	(fl->fl_pid <= 0)
+static struct file_lock *file_lock(struct file_lock_core *flc)
+{
+	return container_of(flc, struct file_lock, c);
+}
+
+static struct file_lease *file_lease(struct file_lock_core *flc)
+{
+	return container_of(flc, struct file_lease, c);
+}
 
-static bool lease_breaking(struct file_lock *fl)
+static bool lease_breaking(struct file_lease *fl)
 {
-	return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
+	return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
 }
 
-static int target_leasetype(struct file_lock *fl)
+static int target_leasetype(struct file_lease *fl)
 {
-	if (fl->fl_flags & FL_UNLOCK_PENDING)
+	if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 		return F_UNLCK;
-	if (fl->fl_flags & FL_DOWNGRADE_PENDING)
+	if (fl->c.flc_flags & FL_DOWNGRADE_PENDING)
 		return F_RDLCK;
-	return fl->fl_type;
+	return fl->c.flc_type;
 }
 
 static int leases_enable = 1;
@@ -168,6 +171,7 @@ static DEFINE_SPINLOCK(blocked_lock_lock);
 
 static struct kmem_cache *flctx_cache __ro_after_init;
 static struct kmem_cache *filelock_cache __ro_after_init;
+static struct kmem_cache *filelease_cache __ro_after_init;
 
 static struct file_lock_context *
 locks_get_lock_context(struct inode *inode, int type)
@@ -204,11 +208,12 @@ out:
 static void
 locks_dump_ctx_list(struct list_head *list, char *list_type)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
-	list_for_each_entry(fl, list, fl_list) {
-		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
-	}
+	list_for_each_entry(flc, list, flc_list)
+		pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
+			list_type, flc->flc_owner, flc->flc_flags,
+			flc->flc_type, flc->flc_pid);
 }
 
 static void
@@ -229,19 +234,19 @@ locks_check_ctx_lists(struct inode *inode)
 }
 
 static void
-locks_check_ctx_file_list(struct file *filp, struct list_head *list,
-				char *list_type)
+locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 	struct inode *inode = file_inode(filp);
 
-	list_for_each_entry(fl, list, fl_list)
-		if (fl->fl_file == filp)
+	list_for_each_entry(flc, list, flc_list)
+		if (flc->flc_file == filp)
 			pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx "
 				" fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
 				list_type, MAJOR(inode->i_sb->s_dev),
 				MINOR(inode->i_sb->s_dev), inode->i_ino,
-				fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
+				flc->flc_owner, flc->flc_flags,
+				flc->flc_type, flc->flc_pid);
 }
 
 void
@@ -255,13 +260,13 @@ locks_free_lock_context(struct inode *inode)
 	}
 }
 
-static void locks_init_lock_heads(struct file_lock *fl)
+static void locks_init_lock_heads(struct file_lock_core *flc)
 {
-	INIT_HLIST_NODE(&fl->fl_link);
-	INIT_LIST_HEAD(&fl->fl_list);
-	INIT_LIST_HEAD(&fl->fl_blocked_requests);
-	INIT_LIST_HEAD(&fl->fl_blocked_member);
-	init_waitqueue_head(&fl->fl_wait);
+	INIT_HLIST_NODE(&flc->flc_link);
+	INIT_LIST_HEAD(&flc->flc_list);
+	INIT_LIST_HEAD(&flc->flc_blocked_requests);
+	INIT_LIST_HEAD(&flc->flc_blocked_member);
+	init_waitqueue_head(&flc->flc_wait);
 }
 
 /* Allocate an empty lock structure. */
@@ -270,19 +275,33 @@ struct file_lock *locks_alloc_lock(void)
 	struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL);
 
 	if (fl)
-		locks_init_lock_heads(fl);
+		locks_init_lock_heads(&fl->c);
 
 	return fl;
 }
 EXPORT_SYMBOL_GPL(locks_alloc_lock);
 
+/* Allocate an empty lock structure. */
+struct file_lease *locks_alloc_lease(void)
+{
+	struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL);
+
+	if (fl)
+		locks_init_lock_heads(&fl->c);
+
+	return fl;
+}
+EXPORT_SYMBOL_GPL(locks_alloc_lease);
+
 void locks_release_private(struct file_lock *fl)
 {
-	BUG_ON(waitqueue_active(&fl->fl_wait));
-	BUG_ON(!list_empty(&fl->fl_list));
-	BUG_ON(!list_empty(&fl->fl_blocked_requests));
-	BUG_ON(!list_empty(&fl->fl_blocked_member));
-	BUG_ON(!hlist_unhashed(&fl->fl_link));
+	struct file_lock_core *flc = &fl->c;
+
+	BUG_ON(waitqueue_active(&flc->flc_wait));
+	BUG_ON(!list_empty(&flc->flc_list));
+	BUG_ON(!list_empty(&flc->flc_blocked_requests));
+	BUG_ON(!list_empty(&flc->flc_blocked_member));
+	BUG_ON(!hlist_unhashed(&flc->flc_link));
 
 	if (fl->fl_ops) {
 		if (fl->fl_ops->fl_release_private)
@@ -292,8 +311,8 @@ void locks_release_private(struct file_lock *fl)
 
 	if (fl->fl_lmops) {
 		if (fl->fl_lmops->lm_put_owner) {
-			fl->fl_lmops->lm_put_owner(fl->fl_owner);
-			fl->fl_owner = NULL;
+			fl->fl_lmops->lm_put_owner(flc->flc_owner);
+			flc->flc_owner = NULL;
 		}
 		fl->fl_lmops = NULL;
 	}
@@ -309,16 +328,15 @@ EXPORT_SYMBOL_GPL(locks_release_private);
  *   %true: @owner has at least one blocker
  *   %false: @owner has no blockers
  */
-bool locks_owner_has_blockers(struct file_lock_context *flctx,
-		fl_owner_t owner)
+bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
-		if (fl->fl_owner != owner)
+	list_for_each_entry(flc, &flctx->flc_posix, flc_list) {
+		if (flc->flc_owner != owner)
 			continue;
-		if (!list_empty(&fl->fl_blocked_requests)) {
+		if (!list_empty(&flc->flc_blocked_requests)) {
 			spin_unlock(&flctx->flc_lock);
 			return true;
 		}
@@ -336,35 +354,52 @@ void locks_free_lock(struct file_lock *fl)
 }
 EXPORT_SYMBOL(locks_free_lock);
 
+/* Free a lease which is not in use. */
+void locks_free_lease(struct file_lease *fl)
+{
+	kmem_cache_free(filelease_cache, fl);
+}
+EXPORT_SYMBOL(locks_free_lease);
+
 static void
 locks_dispose_list(struct list_head *dispose)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	while (!list_empty(dispose)) {
-		fl = list_first_entry(dispose, struct file_lock, fl_list);
-		list_del_init(&fl->fl_list);
-		locks_free_lock(fl);
+		flc = list_first_entry(dispose, struct file_lock_core, flc_list);
+		list_del_init(&flc->flc_list);
+		if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
+			locks_free_lease(file_lease(flc));
+		else
+			locks_free_lock(file_lock(flc));
 	}
 }
 
 void locks_init_lock(struct file_lock *fl)
 {
 	memset(fl, 0, sizeof(struct file_lock));
-	locks_init_lock_heads(fl);
+	locks_init_lock_heads(&fl->c);
 }
 EXPORT_SYMBOL(locks_init_lock);
 
+void locks_init_lease(struct file_lease *fl)
+{
+	memset(fl, 0, sizeof(*fl));
+	locks_init_lock_heads(&fl->c);
+}
+EXPORT_SYMBOL(locks_init_lease);
+
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
 void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
-	new->fl_owner = fl->fl_owner;
-	new->fl_pid = fl->fl_pid;
-	new->fl_file = NULL;
-	new->fl_flags = fl->fl_flags;
-	new->fl_type = fl->fl_type;
+	new->c.flc_owner = fl->c.flc_owner;
+	new->c.flc_pid = fl->c.flc_pid;
+	new->c.flc_file = NULL;
+	new->c.flc_flags = fl->c.flc_flags;
+	new->c.flc_type = fl->c.flc_type;
 	new->fl_start = fl->fl_start;
 	new->fl_end = fl->fl_end;
 	new->fl_lmops = fl->fl_lmops;
@@ -372,7 +407,7 @@ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 
 	if (fl->fl_lmops) {
 		if (fl->fl_lmops->lm_get_owner)
-			fl->fl_lmops->lm_get_owner(fl->fl_owner);
+			fl->fl_lmops->lm_get_owner(fl->c.flc_owner);
 	}
 }
 EXPORT_SYMBOL(locks_copy_conflock);
@@ -384,7 +419,7 @@ void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 
 	locks_copy_conflock(new, fl);
 
-	new->fl_file = fl->fl_file;
+	new->c.flc_file = fl->c.flc_file;
 	new->fl_ops = fl->fl_ops;
 
 	if (fl->fl_ops) {
@@ -400,15 +435,17 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
 
 	/*
 	 * As ctx->flc_lock is held, new requests cannot be added to
-	 * ->fl_blocked_requests, so we don't need a lock to check if it
+	 * ->flc_blocked_requests, so we don't need a lock to check if it
 	 * is empty.
 	 */
-	if (list_empty(&fl->fl_blocked_requests))
+	if (list_empty(&fl->c.flc_blocked_requests))
 		return;
 	spin_lock(&blocked_lock_lock);
-	list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests);
-	list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member)
-		f->fl_blocker = new;
+	list_splice_init(&fl->c.flc_blocked_requests,
+			 &new->c.flc_blocked_requests);
+	list_for_each_entry(f, &new->c.flc_blocked_requests,
+			    c.flc_blocked_member)
+		f->c.flc_blocker = &new->c;
 	spin_unlock(&blocked_lock_lock);
 }
 
@@ -429,21 +466,21 @@ static void flock_make_lock(struct file *filp, struct file_lock *fl, int type)
 {
 	locks_init_lock(fl);
 
-	fl->fl_file = filp;
-	fl->fl_owner = filp;
-	fl->fl_pid = current->tgid;
-	fl->fl_flags = FL_FLOCK;
-	fl->fl_type = type;
+	fl->c.flc_file = filp;
+	fl->c.flc_owner = filp;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_flags = FL_FLOCK;
+	fl->c.flc_type = type;
 	fl->fl_end = OFFSET_MAX;
 }
 
-static int assign_type(struct file_lock *fl, int type)
+static int assign_type(struct file_lock_core *flc, int type)
 {
 	switch (type) {
 	case F_RDLCK:
 	case F_WRLCK:
 	case F_UNLCK:
-		fl->fl_type = type;
+		flc->flc_type = type;
 		break;
 	default:
 		return -EINVAL;
@@ -488,14 +525,14 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
 	} else
 		fl->fl_end = OFFSET_MAX;
 
-	fl->fl_owner = current->files;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = filp;
-	fl->fl_flags = FL_POSIX;
+	fl->c.flc_owner = current->files;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = filp;
+	fl->c.flc_flags = FL_POSIX;
 	fl->fl_ops = NULL;
 	fl->fl_lmops = NULL;
 
-	return assign_type(fl, l->l_type);
+	return assign_type(&fl->c, l->l_type);
 }
 
 /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX
@@ -516,16 +553,16 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
 
 /* default lease lock manager operations */
 static bool
-lease_break_callback(struct file_lock *fl)
+lease_break_callback(struct file_lease *fl)
 {
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
 	return false;
 }
 
 static void
-lease_setup(struct file_lock *fl, void **priv)
+lease_setup(struct file_lease *fl, void **priv)
 {
-	struct file *filp = fl->fl_file;
+	struct file *filp = fl->c.flc_file;
 	struct fasync_struct *fa = *priv;
 
 	/*
@@ -539,7 +576,7 @@ lease_setup(struct file_lock *fl, void **priv)
 	__f_setown(filp, task_pid(current), PIDTYPE_TGID, 0);
 }
 
-static const struct lock_manager_operations lease_manager_ops = {
+static const struct lease_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
 	.lm_change = lease_modify,
 	.lm_setup = lease_setup,
@@ -548,27 +585,24 @@ static const struct lock_manager_operations lease_manager_ops = {
 /*
  * Initialize a lease, use the default lock manager operations
  */
-static int lease_init(struct file *filp, int type, struct file_lock *fl)
+static int lease_init(struct file *filp, int type, struct file_lease *fl)
 {
-	if (assign_type(fl, type) != 0)
+	if (assign_type(&fl->c, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = filp;
-	fl->fl_pid = current->tgid;
+	fl->c.flc_owner = filp;
+	fl->c.flc_pid = current->tgid;
 
-	fl->fl_file = filp;
-	fl->fl_flags = FL_LEASE;
-	fl->fl_start = 0;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_ops = NULL;
+	fl->c.flc_file = filp;
+	fl->c.flc_flags = FL_LEASE;
 	fl->fl_lmops = &lease_manager_ops;
 	return 0;
 }
 
 /* Allocate a file_lock initialised to this type of lease */
-static struct file_lock *lease_alloc(struct file *filp, int type)
+static struct file_lease *lease_alloc(struct file *filp, int type)
 {
-	struct file_lock *fl = locks_alloc_lock();
+	struct file_lease *fl = locks_alloc_lease();
 	int error = -ENOMEM;
 
 	if (fl == NULL)
@@ -576,7 +610,7 @@ static struct file_lock *lease_alloc(struct file *filp, int type)
 
 	error = lease_init(filp, type, fl);
 	if (error) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return ERR_PTR(error);
 	}
 	return fl;
@@ -593,26 +627,26 @@ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2)
 /*
  * Check whether two locks have the same owner.
  */
-static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
+static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2)
 {
-	return fl1->fl_owner == fl2->fl_owner;
+	return fl1->flc_owner == fl2->flc_owner;
 }
 
 /* Must be called with the flc_lock held! */
-static void locks_insert_global_locks(struct file_lock *fl)
+static void locks_insert_global_locks(struct file_lock_core *flc)
 {
 	struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);
 
 	percpu_rwsem_assert_held(&file_rwsem);
 
 	spin_lock(&fll->lock);
-	fl->fl_link_cpu = smp_processor_id();
-	hlist_add_head(&fl->fl_link, &fll->hlist);
+	flc->flc_link_cpu = smp_processor_id();
+	hlist_add_head(&flc->flc_link, &fll->hlist);
 	spin_unlock(&fll->lock);
 }
 
 /* Must be called with the flc_lock held! */
-static void locks_delete_global_locks(struct file_lock *fl)
+static void locks_delete_global_locks(struct file_lock_core *flc)
 {
 	struct file_lock_list_struct *fll;
 
@@ -623,33 +657,33 @@ static void locks_delete_global_locks(struct file_lock *fl)
 	 * is done while holding the flc_lock, and new insertions into the list
 	 * also require that it be held.
 	 */
-	if (hlist_unhashed(&fl->fl_link))
+	if (hlist_unhashed(&flc->flc_link))
 		return;
 
-	fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu);
+	fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu);
 	spin_lock(&fll->lock);
-	hlist_del_init(&fl->fl_link);
+	hlist_del_init(&flc->flc_link);
 	spin_unlock(&fll->lock);
 }
 
 static unsigned long
-posix_owner_key(struct file_lock *fl)
+posix_owner_key(struct file_lock_core *flc)
 {
-	return (unsigned long)fl->fl_owner;
+	return (unsigned long) flc->flc_owner;
 }
 
-static void locks_insert_global_blocked(struct file_lock *waiter)
+static void locks_insert_global_blocked(struct file_lock_core *waiter)
 {
 	lockdep_assert_held(&blocked_lock_lock);
 
-	hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter));
+	hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter));
 }
 
-static void locks_delete_global_blocked(struct file_lock *waiter)
+static void locks_delete_global_blocked(struct file_lock_core *waiter)
 {
 	lockdep_assert_held(&blocked_lock_lock);
 
-	hash_del(&waiter->fl_link);
+	hash_del(&waiter->flc_link);
 }
 
 /* Remove waiter from blocker's block list.
@@ -657,41 +691,39 @@ static void locks_delete_global_blocked(struct file_lock *waiter)
  *
  * Must be called with blocked_lock_lock held.
  */
-static void __locks_delete_block(struct file_lock *waiter)
+static void __locks_unlink_block(struct file_lock_core *waiter)
 {
 	locks_delete_global_blocked(waiter);
-	list_del_init(&waiter->fl_blocked_member);
+	list_del_init(&waiter->flc_blocked_member);
 }
 
-static void __locks_wake_up_blocks(struct file_lock *blocker)
+static void __locks_wake_up_blocks(struct file_lock_core *blocker)
 {
-	while (!list_empty(&blocker->fl_blocked_requests)) {
-		struct file_lock *waiter;
+	while (!list_empty(&blocker->flc_blocked_requests)) {
+		struct file_lock_core *waiter;
+		struct file_lock *fl;
 
-		waiter = list_first_entry(&blocker->fl_blocked_requests,
-					  struct file_lock, fl_blocked_member);
-		__locks_delete_block(waiter);
-		if (waiter->fl_lmops && waiter->fl_lmops->lm_notify)
-			waiter->fl_lmops->lm_notify(waiter);
+		waiter = list_first_entry(&blocker->flc_blocked_requests,
+					  struct file_lock_core, flc_blocked_member);
+
+		fl = file_lock(waiter);
+		__locks_unlink_block(waiter);
+		if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) &&
+		    fl->fl_lmops && fl->fl_lmops->lm_notify)
+			fl->fl_lmops->lm_notify(fl);
 		else
-			wake_up(&waiter->fl_wait);
+			locks_wake_up(fl);
 
 		/*
-		 * The setting of fl_blocker to NULL marks the "done"
+		 * The setting of flc_blocker to NULL marks the "done"
 		 * point in deleting a block. Paired with acquire at the top
 		 * of locks_delete_block().
 		 */
-		smp_store_release(&waiter->fl_blocker, NULL);
+		smp_store_release(&waiter->flc_blocker, NULL);
 	}
 }
 
-/**
- *	locks_delete_block - stop waiting for a file lock
- *	@waiter: the lock which was waiting
- *
- *	lockd/nfsd need to disconnect the lock while working on it.
- */
-int locks_delete_block(struct file_lock *waiter)
+static int __locks_delete_block(struct file_lock_core *waiter)
 {
 	int status = -ENOENT;
 
@@ -716,24 +748,35 @@ int locks_delete_block(struct file_lock *waiter)
 	 * no new locks can be inserted into its fl_blocked_requests list, and
 	 * can avoid doing anything further if the list is empty.
 	 */
-	if (!smp_load_acquire(&waiter->fl_blocker) &&
-	    list_empty(&waiter->fl_blocked_requests))
+	if (!smp_load_acquire(&waiter->flc_blocker) &&
+	    list_empty(&waiter->flc_blocked_requests))
 		return status;
 
 	spin_lock(&blocked_lock_lock);
-	if (waiter->fl_blocker)
+	if (waiter->flc_blocker)
 		status = 0;
 	__locks_wake_up_blocks(waiter);
-	__locks_delete_block(waiter);
+	__locks_unlink_block(waiter);
 
 	/*
 	 * The setting of fl_blocker to NULL marks the "done" point in deleting
 	 * a block. Paired with acquire at the top of this function.
 	 */
-	smp_store_release(&waiter->fl_blocker, NULL);
+	smp_store_release(&waiter->flc_blocker, NULL);
 	spin_unlock(&blocked_lock_lock);
 	return status;
 }
+
+/**
+ *	locks_delete_block - stop waiting for a file lock
+ *	@waiter: the lock which was waiting
+ *
+ *	lockd/nfsd need to disconnect the lock while working on it.
+ */
+int locks_delete_block(struct file_lock *waiter)
+{
+	return __locks_delete_block(&waiter->c);
+}
 EXPORT_SYMBOL(locks_delete_block);
 
 /* Insert waiter into blocker's block list.
@@ -751,26 +794,28 @@ EXPORT_SYMBOL(locks_delete_block);
  * waiters, and add beneath any waiter that blocks the new waiter.
  * Thus wakeups don't happen until needed.
  */
-static void __locks_insert_block(struct file_lock *blocker,
-				 struct file_lock *waiter,
-				 bool conflict(struct file_lock *,
-					       struct file_lock *))
+static void __locks_insert_block(struct file_lock_core *blocker,
+				 struct file_lock_core *waiter,
+				 bool conflict(struct file_lock_core *,
+					       struct file_lock_core *))
 {
-	struct file_lock *fl;
-	BUG_ON(!list_empty(&waiter->fl_blocked_member));
+	struct file_lock_core *flc;
 
+	BUG_ON(!list_empty(&waiter->flc_blocked_member));
 new_blocker:
-	list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member)
-		if (conflict(fl, waiter)) {
-			blocker =  fl;
+	list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member)
+		if (conflict(flc, waiter)) {
+			blocker =  flc;
 			goto new_blocker;
 		}
-	waiter->fl_blocker = blocker;
-	list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests);
-	if (IS_POSIX(blocker) && !IS_OFDLCK(blocker))
+	waiter->flc_blocker = blocker;
+	list_add_tail(&waiter->flc_blocked_member,
+		      &blocker->flc_blocked_requests);
+
+	if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX)
 		locks_insert_global_blocked(waiter);
 
-	/* The requests in waiter->fl_blocked are known to conflict with
+	/* The requests in waiter->flc_blocked are known to conflict with
 	 * waiter, but might not conflict with blocker, or the requests
 	 * and lock which block it.  So they all need to be woken.
 	 */
@@ -778,10 +823,10 @@ new_blocker:
 }
 
 /* Must be called with flc_lock held. */
-static void locks_insert_block(struct file_lock *blocker,
-			       struct file_lock *waiter,
-			       bool conflict(struct file_lock *,
-					     struct file_lock *))
+static void locks_insert_block(struct file_lock_core *blocker,
+			       struct file_lock_core *waiter,
+			       bool conflict(struct file_lock_core *,
+					     struct file_lock_core *))
 {
 	spin_lock(&blocked_lock_lock);
 	__locks_insert_block(blocker, waiter, conflict);
@@ -793,7 +838,7 @@ static void locks_insert_block(struct file_lock *blocker,
  *
  * Must be called with the inode->flc_lock held!
  */
-static void locks_wake_up_blocks(struct file_lock *blocker)
+static void locks_wake_up_blocks(struct file_lock_core *blocker)
 {
 	/*
 	 * Avoid taking global lock if list is empty. This is safe since new
@@ -802,7 +847,7 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 	 * fl_blocked_requests list does not require the flc_lock, so we must
 	 * recheck list_empty() after acquiring the blocked_lock_lock.
 	 */
-	if (list_empty(&blocker->fl_blocked_requests))
+	if (list_empty(&blocker->flc_blocked_requests))
 		return;
 
 	spin_lock(&blocked_lock_lock);
@@ -811,39 +856,39 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 }
 
 static void
-locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
+locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before)
 {
-	list_add_tail(&fl->fl_list, before);
+	list_add_tail(&fl->flc_list, before);
 	locks_insert_global_locks(fl);
 }
 
 static void
-locks_unlink_lock_ctx(struct file_lock *fl)
+locks_unlink_lock_ctx(struct file_lock_core *fl)
 {
 	locks_delete_global_locks(fl);
-	list_del_init(&fl->fl_list);
+	list_del_init(&fl->flc_list);
 	locks_wake_up_blocks(fl);
 }
 
 static void
-locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
+locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose)
 {
 	locks_unlink_lock_ctx(fl);
 	if (dispose)
-		list_add(&fl->fl_list, dispose);
+		list_add(&fl->flc_list, dispose);
 	else
-		locks_free_lock(fl);
+		locks_free_lock(file_lock(fl));
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. Common functionality
  * checks for shared/exclusive status of overlapping locks.
  */
-static bool locks_conflict(struct file_lock *caller_fl,
-			   struct file_lock *sys_fl)
+static bool locks_conflict(struct file_lock_core *caller_flc,
+			   struct file_lock_core *sys_flc)
 {
-	if (sys_fl->fl_type == F_WRLCK)
+	if (sys_flc->flc_type == F_WRLCK)
 		return true;
-	if (caller_fl->fl_type == F_WRLCK)
+	if (caller_flc->flc_type == F_WRLCK)
 		return true;
 	return false;
 }
@@ -851,20 +896,23 @@ static bool locks_conflict(struct file_lock *caller_fl,
 /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific
  * checking before calling the locks_conflict().
  */
-static bool posix_locks_conflict(struct file_lock *caller_fl,
-				 struct file_lock *sys_fl)
+static bool posix_locks_conflict(struct file_lock_core *caller_flc,
+				 struct file_lock_core *sys_flc)
 {
+	struct file_lock *caller_fl = file_lock(caller_flc);
+	struct file_lock *sys_fl = file_lock(sys_flc);
+
 	/* POSIX locks owned by the same process do not conflict with
 	 * each other.
 	 */
-	if (posix_same_owner(caller_fl, sys_fl))
+	if (posix_same_owner(caller_flc, sys_flc))
 		return false;
 
 	/* Check whether they overlap */
 	if (!locks_overlap(caller_fl, sys_fl))
 		return false;
 
-	return locks_conflict(caller_fl, sys_fl);
+	return locks_conflict(caller_flc, sys_flc);
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK
@@ -873,28 +921,31 @@ static bool posix_locks_conflict(struct file_lock *caller_fl,
 static bool posix_test_locks_conflict(struct file_lock *caller_fl,
 				      struct file_lock *sys_fl)
 {
+	struct file_lock_core *caller = &caller_fl->c;
+	struct file_lock_core *sys = &sys_fl->c;
+
 	/* F_UNLCK checks any locks on the same fd. */
-	if (caller_fl->fl_type == F_UNLCK) {
-		if (!posix_same_owner(caller_fl, sys_fl))
+	if (lock_is_unlock(caller_fl)) {
+		if (!posix_same_owner(caller, sys))
 			return false;
 		return locks_overlap(caller_fl, sys_fl);
 	}
-	return posix_locks_conflict(caller_fl, sys_fl);
+	return posix_locks_conflict(caller, sys);
 }
 
 /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
  * checking before calling the locks_conflict().
  */
-static bool flock_locks_conflict(struct file_lock *caller_fl,
-				 struct file_lock *sys_fl)
+static bool flock_locks_conflict(struct file_lock_core *caller_flc,
+				 struct file_lock_core *sys_flc)
 {
 	/* FLOCK locks referring to the same filp do not conflict with
 	 * each other.
 	 */
-	if (caller_fl->fl_file == sys_fl->fl_file)
+	if (caller_flc->flc_file == sys_flc->flc_file)
 		return false;
 
-	return locks_conflict(caller_fl, sys_fl);
+	return locks_conflict(caller_flc, sys_flc);
 }
 
 void
@@ -908,13 +959,13 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 
 	ctx = locks_inode_context(inode);
 	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
-		fl->fl_type = F_UNLCK;
+		fl->c.flc_type = F_UNLCK;
 		return;
 	}
 
 retry:
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
+	list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) {
 		if (!posix_test_locks_conflict(fl, cfl))
 			continue;
 		if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable
@@ -930,7 +981,7 @@ retry:
 		locks_copy_conflock(fl, cfl);
 		goto out;
 	}
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 out:
 	spin_unlock(&ctx->flc_lock);
 	return;
@@ -972,25 +1023,27 @@ EXPORT_SYMBOL(posix_test_lock);
 
 #define MAX_DEADLK_ITERATIONS 10
 
-/* Find a lock that the owner of the given block_fl is blocking on. */
-static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
+/* Find a lock that the owner of the given @blocker is blocking on. */
+static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker)
 {
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
-	hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) {
-		if (posix_same_owner(fl, block_fl)) {
-			while (fl->fl_blocker)
-				fl = fl->fl_blocker;
-			return fl;
+	hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) {
+		if (posix_same_owner(flc, blocker)) {
+			while (flc->flc_blocker)
+				flc = flc->flc_blocker;
+			return flc;
 		}
 	}
 	return NULL;
 }
 
 /* Must be called with the blocked_lock_lock held! */
-static int posix_locks_deadlock(struct file_lock *caller_fl,
-				struct file_lock *block_fl)
+static bool posix_locks_deadlock(struct file_lock *caller_fl,
+				 struct file_lock *block_fl)
 {
+	struct file_lock_core *caller = &caller_fl->c;
+	struct file_lock_core *blocker = &block_fl->c;
 	int i = 0;
 
 	lockdep_assert_held(&blocked_lock_lock);
@@ -999,16 +1052,16 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 	 * This deadlock detector can't reasonably detect deadlocks with
 	 * FL_OFDLCK locks, since they aren't owned by a process, per-se.
 	 */
-	if (IS_OFDLCK(caller_fl))
-		return 0;
+	if (caller->flc_flags & FL_OFDLCK)
+		return false;
 
-	while ((block_fl = what_owner_is_waiting_for(block_fl))) {
+	while ((blocker = what_owner_is_waiting_for(blocker))) {
 		if (i++ > MAX_DEADLK_ITERATIONS)
-			return 0;
-		if (posix_same_owner(caller_fl, block_fl))
-			return 1;
+			return false;
+		if (posix_same_owner(caller, blocker))
+			return true;
 	}
-	return 0;
+	return false;
 }
 
 /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks
@@ -1027,14 +1080,14 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 	bool found = false;
 	LIST_HEAD(dispose);
 
-	ctx = locks_get_lock_context(inode, request->fl_type);
+	ctx = locks_get_lock_context(inode, request->c.flc_type);
 	if (!ctx) {
-		if (request->fl_type != F_UNLCK)
+		if (request->c.flc_type != F_UNLCK)
 			return -ENOMEM;
-		return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0;
+		return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0;
 	}
 
-	if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
+	if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) {
 		new_fl = locks_alloc_lock();
 		if (!new_fl)
 			return -ENOMEM;
@@ -1042,41 +1095,41 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto find_conflict;
 
-	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
-		if (request->fl_file != fl->fl_file)
+	list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
+		if (request->c.flc_file != fl->c.flc_file)
 			continue;
-		if (request->fl_type == fl->fl_type)
+		if (request->c.flc_type == fl->c.flc_type)
 			goto out;
 		found = true;
-		locks_delete_lock_ctx(fl, &dispose);
+		locks_delete_lock_ctx(&fl->c, &dispose);
 		break;
 	}
 
-	if (request->fl_type == F_UNLCK) {
-		if ((request->fl_flags & FL_EXISTS) && !found)
+	if (lock_is_unlock(request)) {
+		if ((request->c.flc_flags & FL_EXISTS) && !found)
 			error = -ENOENT;
 		goto out;
 	}
 
 find_conflict:
-	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
-		if (!flock_locks_conflict(request, fl))
+	list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) {
+		if (!flock_locks_conflict(&request->c, &fl->c))
 			continue;
 		error = -EAGAIN;
-		if (!(request->fl_flags & FL_SLEEP))
+		if (!(request->c.flc_flags & FL_SLEEP))
 			goto out;
 		error = FILE_LOCK_DEFERRED;
-		locks_insert_block(fl, request, flock_locks_conflict);
+		locks_insert_block(&fl->c, &request->c, flock_locks_conflict);
 		goto out;
 	}
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
 	locks_move_blocks(new_fl, request);
-	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
+	locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
 
@@ -1105,9 +1158,9 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	void *owner;
 	void (*func)(void);
 
-	ctx = locks_get_lock_context(inode, request->fl_type);
+	ctx = locks_get_lock_context(inode, request->c.flc_type);
 	if (!ctx)
-		return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM;
+		return lock_is_unlock(request) ? 0 : -ENOMEM;
 
 	/*
 	 * We may need two file_lock structures for this operation,
@@ -1115,8 +1168,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 	 *
 	 * In some cases we can be sure, that no new locks will be needed
 	 */
-	if (!(request->fl_flags & FL_ACCESS) &&
-	    (request->fl_type != F_UNLCK ||
+	if (!(request->c.flc_flags & FL_ACCESS) &&
+	    (request->c.flc_type != F_UNLCK ||
 	     request->fl_start != 0 || request->fl_end != OFFSET_MAX)) {
 		new_fl = locks_alloc_lock();
 		new_fl2 = locks_alloc_lock();
@@ -1130,9 +1183,9 @@ retry:
 	 * there are any, either return error or put the request on the
 	 * blocker's list of waiters and the global blocked_hash.
 	 */
-	if (request->fl_type != F_UNLCK) {
-		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
-			if (!posix_locks_conflict(request, fl))
+	if (request->c.flc_type != F_UNLCK) {
+		list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
+			if (!posix_locks_conflict(&request->c, &fl->c))
 				continue;
 			if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable
 				&& (*fl->fl_lmops->lm_lock_expirable)(fl)) {
@@ -1148,7 +1201,7 @@ retry:
 			if (conflock)
 				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
-			if (!(request->fl_flags & FL_SLEEP))
+			if (!(request->c.flc_flags & FL_SLEEP))
 				goto out;
 			/*
 			 * Deadlock detection and insertion into the blocked
@@ -1160,10 +1213,10 @@ retry:
 			 * Ensure that we don't find any locks blocked on this
 			 * request during deadlock detection.
 			 */
-			__locks_wake_up_blocks(request);
+			__locks_wake_up_blocks(&request->c);
 			if (likely(!posix_locks_deadlock(request, fl))) {
 				error = FILE_LOCK_DEFERRED;
-				__locks_insert_block(fl, request,
+				__locks_insert_block(&fl->c, &request->c,
 						     posix_locks_conflict);
 			}
 			spin_unlock(&blocked_lock_lock);
@@ -1173,22 +1226,22 @@ retry:
 
 	/* If we're just looking for a conflict, we're done. */
 	error = 0;
-	if (request->fl_flags & FL_ACCESS)
+	if (request->c.flc_flags & FL_ACCESS)
 		goto out;
 
 	/* Find the first old lock with the same owner as the new lock */
-	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
-		if (posix_same_owner(request, fl))
+	list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) {
+		if (posix_same_owner(&request->c, &fl->c))
 			break;
 	}
 
 	/* Process locks with this owner. */
-	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
-		if (!posix_same_owner(request, fl))
+	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) {
+		if (!posix_same_owner(&request->c, &fl->c))
 			break;
 
 		/* Detect adjacent or overlapping regions (if same lock type) */
-		if (request->fl_type == fl->fl_type) {
+		if (request->c.flc_type == fl->c.flc_type) {
 			/* In all comparisons of start vs end, use
 			 * "start - 1" rather than "end + 1". If end
 			 * is OFFSET_MAX, end + 1 will become negative.
@@ -1215,7 +1268,7 @@ retry:
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_delete_lock_ctx(&fl->c, &dispose);
 				continue;
 			}
 			request = fl;
@@ -1228,7 +1281,7 @@ retry:
 				continue;
 			if (fl->fl_start > request->fl_end)
 				break;
-			if (request->fl_type == F_UNLCK)
+			if (lock_is_unlock(request))
 				added = true;
 			if (fl->fl_start < request->fl_start)
 				left = fl;
@@ -1244,7 +1297,7 @@ retry:
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock_ctx(fl, &dispose);
+					locks_delete_lock_ctx(&fl->c, &dispose);
 					continue;
 				}
 				/*
@@ -1261,8 +1314,9 @@ retry:
 				locks_move_blocks(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_insert_lock_ctx(request, &fl->fl_list);
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_insert_lock_ctx(&request->c,
+						      &fl->c.flc_list);
+				locks_delete_lock_ctx(&fl->c, &dispose);
 				added = true;
 			}
 		}
@@ -1279,8 +1333,8 @@ retry:
 
 	error = 0;
 	if (!added) {
-		if (request->fl_type == F_UNLCK) {
-			if (request->fl_flags & FL_EXISTS)
+		if (lock_is_unlock(request)) {
+			if (request->c.flc_flags & FL_EXISTS)
 				error = -ENOENT;
 			goto out;
 		}
@@ -1291,7 +1345,7 @@ retry:
 		}
 		locks_copy_lock(new_fl, request);
 		locks_move_blocks(new_fl, request);
-		locks_insert_lock_ctx(new_fl, &fl->fl_list);
+		locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list);
 		fl = new_fl;
 		new_fl = NULL;
 	}
@@ -1303,14 +1357,14 @@ retry:
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock_ctx(left, &fl->fl_list);
+			locks_insert_lock_ctx(&left->c, &fl->c.flc_list);
 		}
 		right->fl_start = request->fl_end + 1;
-		locks_wake_up_blocks(right);
+		locks_wake_up_blocks(&right->c);
 	}
 	if (left) {
 		left->fl_end = request->fl_start - 1;
-		locks_wake_up_blocks(left);
+		locks_wake_up_blocks(&left->c);
 	}
  out:
 	spin_unlock(&ctx->flc_lock);
@@ -1364,8 +1418,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = posix_lock_inode(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-					list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -1373,37 +1427,37 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 	return error;
 }
 
-static void lease_clear_pending(struct file_lock *fl, int arg)
+static void lease_clear_pending(struct file_lease *fl, int arg)
 {
 	switch (arg) {
 	case F_UNLCK:
-		fl->fl_flags &= ~FL_UNLOCK_PENDING;
+		fl->c.flc_flags &= ~FL_UNLOCK_PENDING;
 		fallthrough;
 	case F_RDLCK:
-		fl->fl_flags &= ~FL_DOWNGRADE_PENDING;
+		fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING;
 	}
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
+int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose)
 {
-	int error = assign_type(fl, arg);
+	int error = assign_type(&fl->c, arg);
 
 	if (error)
 		return error;
 	lease_clear_pending(fl, arg);
-	locks_wake_up_blocks(fl);
+	locks_wake_up_blocks(&fl->c);
 	if (arg == F_UNLCK) {
-		struct file *filp = fl->fl_file;
+		struct file *filp = fl->c.flc_file;
 
 		f_delown(filp);
 		filp->f_owner.signum = 0;
-		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
+		fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync);
 		if (fl->fl_fasync != NULL) {
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock_ctx(fl, dispose);
+		locks_delete_lock_ctx(&fl->c, dispose);
 	}
 	return 0;
 }
@@ -1420,11 +1474,11 @@ static bool past_time(unsigned long then)
 static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
 	struct file_lock_context *ctx = inode->i_flctx;
-	struct file_lock *fl, *tmp;
+	struct file_lease *fl, *tmp;
 
 	lockdep_assert_held(&ctx->flc_lock);
 
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
 			lease_modify(fl, F_RDLCK, dispose);
@@ -1433,38 +1487,40 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 	}
 }
 
-static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc)
 {
 	bool rc;
+	struct file_lease *lease = file_lease(lc);
+	struct file_lease *breaker = file_lease(bc);
 
 	if (lease->fl_lmops->lm_breaker_owns_lease
 			&& lease->fl_lmops->lm_breaker_owns_lease(lease))
 		return false;
-	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) {
+	if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) {
 		rc = false;
 		goto trace;
 	}
-	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) {
+	if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) {
 		rc = false;
 		goto trace;
 	}
 
-	rc = locks_conflict(breaker, lease);
+	rc = locks_conflict(bc, lc);
 trace:
 	trace_leases_conflict(rc, lease, breaker);
 	return rc;
 }
 
 static bool
-any_leases_conflict(struct inode *inode, struct file_lock *breaker)
+any_leases_conflict(struct inode *inode, struct file_lease *breaker)
 {
 	struct file_lock_context *ctx = inode->i_flctx;
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	lockdep_assert_held(&ctx->flc_lock);
 
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (leases_conflict(fl, breaker))
+	list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+		if (leases_conflict(flc, &breaker->c))
 			return true;
 	}
 	return false;
@@ -1487,7 +1543,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock_context *ctx;
-	struct file_lock *new_fl, *fl, *tmp;
+	struct file_lease *new_fl, *fl, *tmp;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1495,7 +1551,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
-	new_fl->fl_flags = type;
+	new_fl->c.flc_flags = type;
 
 	/* typically we will check that ctx is non-NULL before calling */
 	ctx = locks_inode_context(inode);
@@ -1519,22 +1575,22 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
-		if (!leases_conflict(fl, new_fl))
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
+		if (!leases_conflict(&fl->c, &new_fl->c))
 			continue;
 		if (want_write) {
-			if (fl->fl_flags & FL_UNLOCK_PENDING)
+			if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 				continue;
-			fl->fl_flags |= FL_UNLOCK_PENDING;
+			fl->c.flc_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
 			if (lease_breaking(fl))
 				continue;
-			fl->fl_flags |= FL_DOWNGRADE_PENDING;
+			fl->c.flc_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock_ctx(fl, &dispose);
+			locks_delete_lock_ctx(&fl->c, &dispose);
 	}
 
 	if (list_empty(&ctx->flc_lease))
@@ -1547,26 +1603,26 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	}
 
 restart:
-	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
+	fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list);
 	break_time = fl->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(fl, new_fl, leases_conflict);
+	locks_insert_block(&fl->c, &new_fl->c, leases_conflict);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&ctx->flc_lock);
 	percpu_up_read(&file_rwsem);
 
 	locks_dispose_list(&dispose);
-	error = wait_event_interruptible_timeout(new_fl->fl_wait,
-					list_empty(&new_fl->fl_blocked_member),
-					break_time);
+	error = wait_event_interruptible_timeout(new_fl->c.flc_wait,
+						 list_empty(&new_fl->c.flc_blocked_member),
+						 break_time);
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
-	locks_delete_block(new_fl);
+	__locks_delete_block(&new_fl->c);
 	if (error >= 0) {
 		/*
 		 * Wait for the next conflicting lease that has not been
@@ -1583,7 +1639,7 @@ out:
 	percpu_up_read(&file_rwsem);
 	locks_dispose_list(&dispose);
 free_lock:
-	locks_free_lock(new_fl);
+	locks_free_lease(new_fl);
 	return error;
 }
 EXPORT_SYMBOL(__break_lease);
@@ -1601,14 +1657,14 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time)
 {
 	bool has_lease = false;
 	struct file_lock_context *ctx;
-	struct file_lock *fl;
+	struct file_lock_core *flc;
 
 	ctx = locks_inode_context(inode);
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
 		spin_lock(&ctx->flc_lock);
-		fl = list_first_entry_or_null(&ctx->flc_lease,
-					      struct file_lock, fl_list);
-		if (fl && (fl->fl_type == F_WRLCK))
+		flc = list_first_entry_or_null(&ctx->flc_lease,
+					       struct file_lock_core, flc_list);
+		if (flc && flc->flc_type == F_WRLCK)
 			has_lease = true;
 		spin_unlock(&ctx->flc_lock);
 	}
@@ -1643,7 +1699,7 @@ EXPORT_SYMBOL(lease_get_mtime);
  */
 int fcntl_getlease(struct file *filp)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	int type = F_UNLCK;
@@ -1654,8 +1710,8 @@ int fcntl_getlease(struct file *filp)
 		percpu_down_read(&file_rwsem);
 		spin_lock(&ctx->flc_lock);
 		time_out_leases(inode, &dispose);
-		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-			if (fl->fl_file != filp)
+		list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+			if (fl->c.flc_file != filp)
 				continue;
 			type = target_leasetype(fl);
 			break;
@@ -1715,12 +1771,12 @@ check_conflicting_open(struct file *filp, const int arg, int flags)
 }
 
 static int
-generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **priv)
+generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv)
 {
-	struct file_lock *fl, *my_fl = NULL, *lease;
+	struct file_lease *fl, *my_fl = NULL, *lease;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
-	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
+	bool is_deleg = (*flp)->c.flc_flags & FL_DELEG;
 	int error;
 	LIST_HEAD(dispose);
 
@@ -1746,7 +1802,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(filp, arg, lease->fl_flags);
+	error = check_conflicting_open(filp, arg, lease->c.flc_flags);
 	if (error)
 		goto out;
 
@@ -1759,9 +1815,9 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	 * except for this filp.
 	 */
 	error = -EAGAIN;
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp &&
-		    fl->fl_owner == lease->fl_owner) {
+	list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+		if (fl->c.flc_file == filp &&
+		    fl->c.flc_owner == lease->c.flc_owner) {
 			my_fl = fl;
 			continue;
 		}
@@ -1776,7 +1832,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 		 * Modifying our existing lease is OK, but no getting a
 		 * new lease if someone else is opening for write:
 		 */
-		if (fl->fl_flags & FL_UNLOCK_PENDING)
+		if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 			goto out;
 	}
 
@@ -1792,7 +1848,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock_ctx(lease, &ctx->flc_lease);
+	locks_insert_lock_ctx(&lease->c, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1803,9 +1859,9 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(filp, arg, lease->fl_flags);
+	error = check_conflicting_open(filp, arg, lease->c.flc_flags);
 	if (error) {
-		locks_unlink_lock_ctx(lease);
+		locks_unlink_lock_ctx(&lease->c);
 		goto out;
 	}
 
@@ -1826,7 +1882,7 @@ out:
 static int generic_delete_lease(struct file *filp, void *owner)
 {
 	int error = -EAGAIN;
-	struct file_lock *fl, *victim = NULL;
+	struct file_lease *fl, *victim = NULL;
 	struct inode *inode = file_inode(filp);
 	struct file_lock_context *ctx;
 	LIST_HEAD(dispose);
@@ -1839,9 +1895,9 @@ static int generic_delete_lease(struct file *filp, void *owner)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp &&
-		    fl->fl_owner == owner) {
+	list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+		if (fl->c.flc_file == filp &&
+		    fl->c.flc_owner == owner) {
 			victim = fl;
 			break;
 		}
@@ -1866,21 +1922,9 @@ static int generic_delete_lease(struct file *filp, void *owner)
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
  */
-int generic_setlease(struct file *filp, int arg, struct file_lock **flp,
+int generic_setlease(struct file *filp, int arg, struct file_lease **flp,
 			void **priv)
 {
-	struct inode *inode = file_inode(filp);
-	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
-	int error;
-
-	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
-		return -EACCES;
-	if (!S_ISREG(inode->i_mode))
-		return -EINVAL;
-	error = security_file_lock(filp, arg);
-	if (error)
-		return error;
-
 	switch (arg) {
 	case F_UNLCK:
 		return generic_delete_lease(filp, *priv);
@@ -1913,7 +1957,7 @@ lease_notifier_chain_init(void)
 }
 
 static inline void
-setlease_notifier(int arg, struct file_lock *lease)
+setlease_notifier(int arg, struct file_lease *lease)
 {
 	if (arg != F_UNLCK)
 		srcu_notifier_call_chain(&lease_notifier_chain, arg, lease);
@@ -1931,6 +1975,19 @@ void lease_unregister_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(lease_unregister_notifier);
 
+
+int
+kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
+{
+	if (lease)
+		setlease_notifier(arg, *lease);
+	if (filp->f_op->setlease)
+		return filp->f_op->setlease(filp, arg, lease, priv);
+	else
+		return generic_setlease(filp, arg, lease, priv);
+}
+EXPORT_SYMBOL_GPL(kernel_setlease);
+
 /**
  * vfs_setlease        -       sets a lease on an open file
  * @filp:	file pointer
@@ -1949,20 +2006,26 @@ EXPORT_SYMBOL_GPL(lease_unregister_notifier);
  * may be NULL if the lm_setup operation doesn't require it.
  */
 int
-vfs_setlease(struct file *filp, int arg, struct file_lock **lease, void **priv)
+vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
 {
-	if (lease)
-		setlease_notifier(arg, *lease);
-	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease, priv);
-	else
-		return generic_setlease(filp, arg, lease, priv);
+	struct inode *inode = file_inode(filp);
+	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode);
+	int error;
+
+	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
+		return -EACCES;
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+	error = security_file_lock(filp, arg);
+	if (error)
+		return error;
+	return kernel_setlease(filp, arg, lease, priv);
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct fasync_struct *new;
 	int error;
 
@@ -1972,14 +2035,14 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg)
 
 	new = fasync_alloc();
 	if (!new) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return -ENOMEM;
 	}
 	new->fa_fd = fd;
 
 	error = vfs_setlease(filp, arg, &fl, (void **)&new);
 	if (fl)
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 	if (new)
 		fasync_free(new);
 	return error;
@@ -2017,8 +2080,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 		error = flock_lock_inode(inode, fl);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-				list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -2036,7 +2099,7 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 {
 	int res = 0;
-	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
+	switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) {
 		case FL_POSIX:
 			res = posix_lock_inode_wait(inode, fl);
 			break;
@@ -2098,13 +2161,13 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 
 	flock_make_lock(f.file, &fl, type);
 
-	error = security_file_lock(f.file, fl.fl_type);
+	error = security_file_lock(f.file, fl.c.flc_type);
 	if (error)
 		goto out_putf;
 
 	can_sleep = !(cmd & LOCK_NB);
 	if (can_sleep)
-		fl.fl_flags |= FL_SLEEP;
+		fl.c.flc_flags |= FL_SLEEP;
 
 	if (f.file->f_op->flock)
 		error = f.file->f_op->flock(f.file,
@@ -2130,7 +2193,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
  */
 int vfs_test_lock(struct file *filp, struct file_lock *fl)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_GETLK, fl);
 	posix_test_lock(filp, fl);
@@ -2145,25 +2208,28 @@ EXPORT_SYMBOL_GPL(vfs_test_lock);
  *
  * Used to translate a fl_pid into a namespace virtual pid number
  */
-static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
+static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns)
 {
 	pid_t vnr;
 	struct pid *pid;
 
-	if (IS_OFDLCK(fl))
+	if (fl->flc_flags & FL_OFDLCK)
 		return -1;
-	if (IS_REMOTELCK(fl))
-		return fl->fl_pid;
+
+	/* Remote locks report a negative pid value */
+	if (fl->flc_pid <= 0)
+		return fl->flc_pid;
+
 	/*
 	 * If the flock owner process is dead and its pid has been already
 	 * freed, the translation below won't work, but we still want to show
 	 * flock owner pid number in init pidns.
 	 */
 	if (ns == &init_pid_ns)
-		return (pid_t)fl->fl_pid;
+		return (pid_t) fl->flc_pid;
 
 	rcu_read_lock();
-	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
+	pid = find_pid_ns(fl->flc_pid, &init_pid_ns);
 	vnr = pid_nr_ns(pid, ns);
 	rcu_read_unlock();
 	return vnr;
@@ -2171,7 +2237,7 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
 
 static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 {
-	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
+	flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
 #if BITS_PER_LONG == 32
 	/*
 	 * Make sure we can represent the posix lock via
@@ -2186,19 +2252,19 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
 		fl->fl_end - fl->fl_start + 1;
 	flock->l_whence = 0;
-	flock->l_type = fl->fl_type;
+	flock->l_type = fl->c.flc_type;
 	return 0;
 }
 
 #if BITS_PER_LONG == 32
 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 {
-	flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
+	flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current));
 	flock->l_start = fl->fl_start;
 	flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
 		fl->fl_end - fl->fl_start + 1;
 	flock->l_whence = 0;
-	flock->l_type = fl->fl_type;
+	flock->l_type = fl->c.flc_type;
 }
 #endif
 
@@ -2227,16 +2293,16 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
 		if (flock->l_pid != 0)
 			goto out;
 
-		fl->fl_flags |= FL_OFDLCK;
-		fl->fl_owner = filp;
+		fl->c.flc_flags |= FL_OFDLCK;
+		fl->c.flc_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, fl);
 	if (error)
 		goto out;
 
-	flock->l_type = fl->fl_type;
-	if (fl->fl_type != F_UNLCK) {
+	flock->l_type = fl->c.flc_type;
+	if (fl->c.flc_type != F_UNLCK) {
 		error = posix_lock_to_flock(flock, fl);
 		if (error)
 			goto out;
@@ -2283,7 +2349,7 @@ out:
  */
 int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, cmd, fl);
 	else
@@ -2296,7 +2362,7 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 {
 	int error;
 
-	error = security_file_lock(filp, fl->fl_type);
+	error = security_file_lock(filp, fl->c.flc_type);
 	if (error)
 		return error;
 
@@ -2304,8 +2370,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 		error = vfs_lock_file(filp, cmd, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
-		error = wait_event_interruptible(fl->fl_wait,
-					list_empty(&fl->fl_blocked_member));
+		error = wait_event_interruptible(fl->c.flc_wait,
+						 list_empty(&fl->c.flc_blocked_member));
 		if (error)
 			break;
 	}
@@ -2318,13 +2384,13 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 static int
 check_fmode_for_setlk(struct file_lock *fl)
 {
-	switch (fl->fl_type) {
+	switch (fl->c.flc_type) {
 	case F_RDLCK:
-		if (!(fl->fl_file->f_mode & FMODE_READ))
+		if (!(fl->c.flc_file->f_mode & FMODE_READ))
 			return -EBADF;
 		break;
 	case F_WRLCK:
-		if (!(fl->fl_file->f_mode & FMODE_WRITE))
+		if (!(fl->c.flc_file->f_mode & FMODE_WRITE))
 			return -EBADF;
 	}
 	return 0;
@@ -2363,8 +2429,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLK;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2372,11 +2438,11 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLKW;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		fallthrough;
 	case F_SETLKW:
-		file_lock->fl_flags |= FL_SLEEP;
+		file_lock->c.flc_flags |= FL_SLEEP;
 	}
 
 	error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2386,8 +2452,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	 * lock that was just acquired. There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
-	if (!error && file_lock->fl_type != F_UNLCK &&
-	    !(file_lock->fl_flags & FL_OFDLCK)) {
+	if (!error && file_lock->c.flc_type != F_UNLCK &&
+	    !(file_lock->c.flc_flags & FL_OFDLCK)) {
 		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
@@ -2398,7 +2464,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->fl_type = F_UNLCK;
+			file_lock->c.flc_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
 			WARN_ON_ONCE(error);
 			error = -EBADF;
@@ -2437,16 +2503,16 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
 		if (flock->l_pid != 0)
 			goto out;
 
-		fl->fl_flags |= FL_OFDLCK;
-		fl->fl_owner = filp;
+		fl->c.flc_flags |= FL_OFDLCK;
+		fl->c.flc_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, fl);
 	if (error)
 		goto out;
 
-	flock->l_type = fl->fl_type;
-	if (fl->fl_type != F_UNLCK)
+	flock->l_type = fl->c.flc_type;
+	if (fl->c.flc_type != F_UNLCK)
 		posix_lock_to_flock64(flock, fl);
 
 out:
@@ -2486,8 +2552,8 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLK64;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2495,11 +2561,11 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 			goto out;
 
 		cmd = F_SETLKW64;
-		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = filp;
+		file_lock->c.flc_flags |= FL_OFDLCK;
+		file_lock->c.flc_owner = filp;
 		fallthrough;
 	case F_SETLKW64:
-		file_lock->fl_flags |= FL_SLEEP;
+		file_lock->c.flc_flags |= FL_SLEEP;
 	}
 
 	error = do_lock_file_wait(filp, cmd, file_lock);
@@ -2509,8 +2575,8 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 	 * lock that was just acquired. There is no need to do that when we're
 	 * unlocking though, or for OFD locks.
 	 */
-	if (!error && file_lock->fl_type != F_UNLCK &&
-	    !(file_lock->fl_flags & FL_OFDLCK)) {
+	if (!error && file_lock->c.flc_type != F_UNLCK &&
+	    !(file_lock->c.flc_flags & FL_OFDLCK)) {
 		struct files_struct *files = current->files;
 		/*
 		 * We need that spin_lock here - it prevents reordering between
@@ -2521,7 +2587,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		f = files_lookup_fd_locked(files, fd);
 		spin_unlock(&files->file_lock);
 		if (f != filp) {
-			file_lock->fl_type = F_UNLCK;
+			file_lock->c.flc_type = F_UNLCK;
 			error = do_lock_file_wait(filp, cmd, file_lock);
 			WARN_ON_ONCE(error);
 			error = -EBADF;
@@ -2555,13 +2621,13 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner)
 		return;
 
 	locks_init_lock(&lock);
-	lock.fl_type = F_UNLCK;
-	lock.fl_flags = FL_POSIX | FL_CLOSE;
+	lock.c.flc_type = F_UNLCK;
+	lock.c.flc_flags = FL_POSIX | FL_CLOSE;
 	lock.fl_start = 0;
 	lock.fl_end = OFFSET_MAX;
-	lock.fl_owner = owner;
-	lock.fl_pid = current->tgid;
-	lock.fl_file = filp;
+	lock.c.flc_owner = owner;
+	lock.c.flc_pid = current->tgid;
+	lock.c.flc_file = filp;
 	lock.fl_ops = NULL;
 	lock.fl_lmops = NULL;
 
@@ -2584,7 +2650,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 		return;
 
 	flock_make_lock(filp, &fl, F_UNLCK);
-	fl.fl_flags |= FL_CLOSE;
+	fl.c.flc_flags |= FL_CLOSE;
 
 	if (filp->f_op->flock)
 		filp->f_op->flock(filp, F_SETLKW, &fl);
@@ -2599,7 +2665,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 static void
 locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
 {
-	struct file_lock *fl, *tmp;
+	struct file_lease *fl, *tmp;
 	LIST_HEAD(dispose);
 
 	if (list_empty(&ctx->flc_lease))
@@ -2607,8 +2673,8 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
 
 	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
-		if (filp == fl->fl_file)
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list)
+		if (filp == fl->c.flc_file)
 			lease_modify(fl, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
 	percpu_up_read(&file_rwsem);
@@ -2652,7 +2718,7 @@ void locks_remove_file(struct file *filp)
  */
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
 {
-	WARN_ON_ONCE(filp != fl->fl_file);
+	WARN_ON_ONCE(filp != fl->c.flc_file);
 	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_CANCELLK, fl);
 	return 0;
@@ -2691,69 +2757,73 @@ struct locks_iterator {
 	loff_t	li_pos;
 };
 
-static void lock_get_status(struct seq_file *f, struct file_lock *fl,
+static void lock_get_status(struct seq_file *f, struct file_lock_core *flc,
 			    loff_t id, char *pfx, int repeat)
 {
 	struct inode *inode = NULL;
-	unsigned int fl_pid;
+	unsigned int pid;
 	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
-	int type;
+	int type = flc->flc_type;
+	struct file_lock *fl = file_lock(flc);
+
+	pid = locks_translate_pid(flc, proc_pidns);
 
-	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
 	 * If lock owner is dead (and pid is freed) or not visible in current
 	 * pidns, zero is shown as a pid value. Check lock info from
 	 * init_pid_ns to get saved lock pid value.
 	 */
-
-	if (fl->fl_file != NULL)
-		inode = file_inode(fl->fl_file);
+	if (flc->flc_file != NULL)
+		inode = file_inode(flc->flc_file);
 
 	seq_printf(f, "%lld: ", id);
 
 	if (repeat)
 		seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);
 
-	if (IS_POSIX(fl)) {
-		if (fl->fl_flags & FL_ACCESS)
+	if (flc->flc_flags & FL_POSIX) {
+		if (flc->flc_flags & FL_ACCESS)
 			seq_puts(f, "ACCESS");
-		else if (IS_OFDLCK(fl))
+		else if (flc->flc_flags & FL_OFDLCK)
 			seq_puts(f, "OFDLCK");
 		else
 			seq_puts(f, "POSIX ");
 
 		seq_printf(f, " %s ",
 			     (inode == NULL) ? "*NOINODE*" : "ADVISORY ");
-	} else if (IS_FLOCK(fl)) {
+	} else if (flc->flc_flags & FL_FLOCK) {
 		seq_puts(f, "FLOCK  ADVISORY  ");
-	} else if (IS_LEASE(fl)) {
-		if (fl->fl_flags & FL_DELEG)
+	} else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) {
+		struct file_lease *lease = file_lease(flc);
+
+		type = target_leasetype(lease);
+
+		if (flc->flc_flags & FL_DELEG)
 			seq_puts(f, "DELEG  ");
 		else
 			seq_puts(f, "LEASE  ");
 
-		if (lease_breaking(fl))
+		if (lease_breaking(lease))
 			seq_puts(f, "BREAKING  ");
-		else if (fl->fl_file)
+		else if (flc->flc_file)
 			seq_puts(f, "ACTIVE    ");
 		else
 			seq_puts(f, "BREAKER   ");
 	} else {
 		seq_puts(f, "UNKNOWN UNKNOWN  ");
 	}
-	type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
 
 	seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
 			     (type == F_RDLCK) ? "READ" : "UNLCK");
 	if (inode) {
 		/* userspace relies on this representation of dev_t */
-		seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
+		seq_printf(f, "%d %02x:%02x:%lu ", pid,
 				MAJOR(inode->i_sb->s_dev),
 				MINOR(inode->i_sb->s_dev), inode->i_ino);
 	} else {
-		seq_printf(f, "%d <none>:0 ", fl_pid);
+		seq_printf(f, "%d <none>:0 ", pid);
 	}
-	if (IS_POSIX(fl)) {
+	if (flc->flc_flags & FL_POSIX) {
 		if (fl->fl_end == OFFSET_MAX)
 			seq_printf(f, "%Ld EOF\n", fl->fl_start);
 		else
@@ -2763,17 +2833,18 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 	}
 }
 
-static struct file_lock *get_next_blocked_member(struct file_lock *node)
+static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node)
 {
-	struct file_lock *tmp;
+	struct file_lock_core *tmp;
 
 	/* NULL node or root node */
-	if (node == NULL || node->fl_blocker == NULL)
+	if (node == NULL || node->flc_blocker == NULL)
 		return NULL;
 
 	/* Next member in the linked list could be itself */
-	tmp = list_next_entry(node, fl_blocked_member);
-	if (list_entry_is_head(tmp, &node->fl_blocker->fl_blocked_requests, fl_blocked_member)
+	tmp = list_next_entry(node, flc_blocked_member);
+	if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests,
+			       flc_blocked_member)
 		|| tmp == node) {
 		return NULL;
 	}
@@ -2784,18 +2855,18 @@ static struct file_lock *get_next_blocked_member(struct file_lock *node)
 static int locks_show(struct seq_file *f, void *v)
 {
 	struct locks_iterator *iter = f->private;
-	struct file_lock *cur, *tmp;
+	struct file_lock_core *cur, *tmp;
 	struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
 	int level = 0;
 
-	cur = hlist_entry(v, struct file_lock, fl_link);
+	cur = hlist_entry(v, struct file_lock_core, flc_link);
 
 	if (locks_translate_pid(cur, proc_pidns) == 0)
 		return 0;
 
-	/* View this crossed linked list as a binary tree, the first member of fl_blocked_requests
-	 * is the left child of current node, the next silibing in fl_blocked_member is the
-	 * right child, we can alse get the parent of current node from fl_blocker, so this
+	/* View this crossed linked list as a binary tree, the first member of flc_blocked_requests
+	 * is the left child of current node, the next silibing in flc_blocked_member is the
+	 * right child, we can alse get the parent of current node from flc_blocker, so this
 	 * question becomes traversal of a binary tree
 	 */
 	while (cur != NULL) {
@@ -2804,17 +2875,18 @@ static int locks_show(struct seq_file *f, void *v)
 		else
 			lock_get_status(f, cur, iter->li_pos, "", level);
 
-		if (!list_empty(&cur->fl_blocked_requests)) {
+		if (!list_empty(&cur->flc_blocked_requests)) {
 			/* Turn left */
-			cur = list_first_entry_or_null(&cur->fl_blocked_requests,
-				struct file_lock, fl_blocked_member);
+			cur = list_first_entry_or_null(&cur->flc_blocked_requests,
+						       struct file_lock_core,
+						       flc_blocked_member);
 			level++;
 		} else {
 			/* Turn right */
 			tmp = get_next_blocked_member(cur);
 			/* Fall back to parent node */
-			while (tmp == NULL && cur->fl_blocker != NULL) {
-				cur = cur->fl_blocker;
+			while (tmp == NULL && cur->flc_blocker != NULL) {
+				cur = cur->flc_blocker;
 				level--;
 				tmp = get_next_blocked_member(cur);
 			}
@@ -2829,14 +2901,13 @@ static void __show_fd_locks(struct seq_file *f,
 			struct list_head *head, int *id,
 			struct file *filp, struct files_struct *files)
 {
-	struct file_lock *fl;
+	struct file_lock_core *fl;
 
-	list_for_each_entry(fl, head, fl_list) {
+	list_for_each_entry(fl, head, flc_list) {
 
-		if (filp != fl->fl_file)
+		if (filp != fl->flc_file)
 			continue;
-		if (fl->fl_owner != files &&
-		    fl->fl_owner != filp)
+		if (fl->flc_owner != files && fl->flc_owner != filp)
 			continue;
 
 		(*id)++;
@@ -2915,6 +2986,9 @@ static int __init filelock_init(void)
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 
+	filelease_cache = kmem_cache_create("file_lock_cache",
+			sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
+
 	for_each_possible_cpu(i) {
 		struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
 
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 82aa7a35db26..e60a840999aa 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -426,9 +426,7 @@ EXPORT_SYMBOL(mb_cache_destroy);
 
 static int __init mbcache_init(void)
 {
-	mb_entry_cache = kmem_cache_create("mbcache",
-				sizeof(struct mb_cache_entry), 0,
-				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
+	mb_entry_cache = KMEM_CACHE(mb_cache_entry, SLAB_RECLAIM_ACCOUNT);
 	if (!mb_entry_cache)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 73f37f298087..7cbd2b9f4d11 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -87,7 +87,7 @@ static int __init init_inodecache(void)
 	minix_inode_cachep = kmem_cache_create("minix_inode_cache",
 					     sizeof(struct minix_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+						SLAB_ACCOUNT),
 					     init_once);
 	if (minix_inode_cachep == NULL)
 		return -ENOMEM;
diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 64c5205e2b5e..3c60f1eaca61 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -214,7 +214,7 @@ static int copy_mnt_idmap(struct uid_gid_map *map_from,
 	 * anything at all.
 	 */
 	if (nr_extents == 0)
-		return 0;
+		return -EINVAL;
 
 	/*
 	 * Here we know that nr_extents is greater than zero which means
diff --git a/fs/mpage.c b/fs/mpage.c
index 738882e0766d..fa8b99a199fa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -605,6 +605,7 @@ alloc_new:
 				GFP_NOFS);
 		bio->bi_iter.bi_sector = first_block << (blkbits - 9);
 		wbc_init_bio(wbc, bio);
+		bio->bi_write_hint = inode->i_write_hint;
 	}
 
 	/*
diff --git a/fs/namei.c b/fs/namei.c
index 4e0de939fea1..d0c4a3e9278e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1717,7 +1717,11 @@ static inline int may_lookup(struct mnt_idmap *idmap,
 {
 	if (nd->flags & LOOKUP_RCU) {
 		int err = inode_permission(idmap, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
-		if (err != -ECHILD || !try_to_unlazy(nd))
+		if (!err)		// success, keep going
+			return 0;
+		if (!try_to_unlazy(nd))
+			return -ECHILD;	// redo it all non-lazy
+		if (err != -ECHILD)	// hard error
 			return err;
 	}
 	return inode_permission(idmap, nd->inode, MAY_EXEC);
@@ -2676,10 +2680,8 @@ static int lookup_one_common(struct mnt_idmap *idmap,
 	if (!len)
 		return -EACCES;
 
-	if (unlikely(name[0] == '.')) {
-		if (len < 2 || (len == 2 && name[1] == '.'))
-			return -EACCES;
-	}
+	if (is_dot_dotdot(name, len))
+		return -EACCES;
 
 	while (len--) {
 		unsigned int c = *(const unsigned char *)name++;
diff --git a/fs/namespace.c b/fs/namespace.c
index 437f60e96d40..5a51315c6678 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4472,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 	/*
 	 * If this is an attached mount make sure it's located in the callers
 	 * mount namespace. If it's not don't let the caller interact with it.
-	 * If this is a detached mount make sure it has an anonymous mount
-	 * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE.
+	 *
+	 * If this mount doesn't have a parent it's most often simply a
+	 * detached mount with an anonymous mount namespace. IOW, something
+	 * that's simply not attached yet. But there are apparently also users
+	 * that do change mount properties on the rootfs itself. That obviously
+	 * neither has a parent nor is it a detached mount so we cannot
+	 * unconditionally check for detached mounts.
 	 */
-	if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns)))
+	if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
 		goto out;
 
 	/*
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index a3059b3168fd..9a0d32e4b422 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -477,6 +477,9 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
 
+	if (!iov_iter_count(from))
+		return 0;
+
 	if ((iocb->ki_flags & IOCB_DIRECT) ||
 	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
 		return netfs_unbuffered_write_iter(iocb, from);
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 60a40d293c87..bee047e20f5d 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -139,6 +139,9 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
 
+	if (!iov_iter_count(from))
+		return 0;
+
 	trace_netfs_write_iter(iocb, from);
 	netfs_stat(&netfs_n_rh_dio_write);
 
@@ -146,7 +149,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret < 0)
 		return ret;
 	ret = generic_write_checks(iocb, from);
-	if (ret < 0)
+	if (ret <= 0)
 		goto out;
 	ret = file_remove_privs(file);
 	if (ret < 0)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e8ff1e61ce79..4261ad6c55b6 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -748,6 +748,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	if (!rreq->submitted) {
 		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		if (rreq->origin == NETFS_DIO_READ)
+			inode_dio_end(rreq->inode);
 		ret = 0;
 		goto out;
 	}
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index b4294a8aa2d4..f1eeb4914199 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -108,7 +108,7 @@ struct pnfs_block_dev {
 	struct pnfs_block_dev		*children;
 	u64				chunk_size;
 
-	struct bdev_handle		*bdev_handle;
+	struct file			*bdev_file;
 	u64				disk_offset;
 
 	u64				pr_key;
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index c97ebc42ec0f..93ef7f864980 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -25,17 +25,17 @@ bl_free_device(struct pnfs_block_dev *dev)
 	} else {
 		if (dev->pr_registered) {
 			const struct pr_ops *ops =
-				dev->bdev_handle->bdev->bd_disk->fops->pr_ops;
+				file_bdev(dev->bdev_file)->bd_disk->fops->pr_ops;
 			int error;
 
-			error = ops->pr_register(dev->bdev_handle->bdev,
+			error = ops->pr_register(file_bdev(dev->bdev_file),
 				dev->pr_key, 0, false);
 			if (error)
 				pr_err("failed to unregister PR key.\n");
 		}
 
-		if (dev->bdev_handle)
-			bdev_release(dev->bdev_handle);
+		if (dev->bdev_file)
+			fput(dev->bdev_file);
 	}
 }
 
@@ -169,7 +169,7 @@ static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
 	map->start = dev->start;
 	map->len = dev->len;
 	map->disk_offset = dev->disk_offset;
-	map->bdev = dev->bdev_handle->bdev;
+	map->bdev = file_bdev(dev->bdev_file);
 	return true;
 }
 
@@ -236,26 +236,26 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	dev_t dev;
 
 	dev = bl_resolve_deviceid(server, v, gfp_mask);
 	if (!dev)
 		return -EIO;
 
-	bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
 				       NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
-			MAJOR(dev), MINOR(dev), PTR_ERR(bdev_handle));
-		return PTR_ERR(bdev_handle);
+			MAJOR(dev), MINOR(dev), PTR_ERR(bdev_file));
+		return PTR_ERR(bdev_file);
 	}
-	d->bdev_handle = bdev_handle;
-	d->len = bdev_nr_bytes(bdev_handle->bdev);
+	d->bdev_file = bdev_file;
+	d->len = bdev_nr_bytes(file_bdev(bdev_file));
 	d->map = bl_map_simple;
 
 	printk(KERN_INFO "pNFS: using block device %s\n",
-		bdev_handle->bdev->bd_disk->disk_name);
+		file_bdev(bdev_file)->bd_disk->disk_name);
 	return 0;
 }
 
@@ -300,10 +300,10 @@ bl_validate_designator(struct pnfs_block_volume *v)
 	}
 }
 
-static struct bdev_handle *
+static struct file *
 bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 {
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	const char *devname;
 
 	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN",
@@ -311,15 +311,15 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 	if (!devname)
 		return ERR_PTR(-ENOMEM);
 
-	bdev_handle = bdev_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
+	bdev_file = bdev_file_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
 					NULL, NULL);
-	if (IS_ERR(bdev_handle)) {
+	if (IS_ERR(bdev_file)) {
 		pr_warn("pNFS: failed to open device %s (%ld)\n",
-			devname, PTR_ERR(bdev_handle));
+			devname, PTR_ERR(bdev_file));
 	}
 
 	kfree(devname);
-	return bdev_handle;
+	return bdev_file;
 }
 
 static int
@@ -327,7 +327,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	const struct pr_ops *ops;
 	int error;
 
@@ -340,14 +340,14 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	 * On other distributions like Debian, the default SCSI by-id path will
 	 * point to the dm-multipath device if one exists.
 	 */
-	bdev_handle = bl_open_path(v, "dm-uuid-mpath-0x");
-	if (IS_ERR(bdev_handle))
-		bdev_handle = bl_open_path(v, "wwn-0x");
-	if (IS_ERR(bdev_handle))
-		return PTR_ERR(bdev_handle);
-	d->bdev_handle = bdev_handle;
-
-	d->len = bdev_nr_bytes(d->bdev_handle->bdev);
+	bdev_file = bl_open_path(v, "dm-uuid-mpath-0x");
+	if (IS_ERR(bdev_file))
+		bdev_file = bl_open_path(v, "wwn-0x");
+	if (IS_ERR(bdev_file))
+		return PTR_ERR(bdev_file);
+	d->bdev_file = bdev_file;
+
+	d->len = bdev_nr_bytes(file_bdev(d->bdev_file));
 	d->map = bl_map_simple;
 	d->pr_key = v->scsi.pr_key;
 
@@ -355,20 +355,20 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		return -ENODEV;
 
 	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
-		d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key);
+		file_bdev(d->bdev_file)->bd_disk->disk_name, d->pr_key);
 
-	ops = d->bdev_handle->bdev->bd_disk->fops->pr_ops;
+	ops = file_bdev(d->bdev_file)->bd_disk->fops->pr_ops;
 	if (!ops) {
 		pr_err("pNFS: block device %s does not support reservations.",
-				d->bdev_handle->bdev->bd_disk->disk_name);
+				file_bdev(d->bdev_file)->bd_disk->disk_name);
 		error = -EINVAL;
 		goto out_blkdev_put;
 	}
 
-	error = ops->pr_register(d->bdev_handle->bdev, 0, d->pr_key, true);
+	error = ops->pr_register(file_bdev(d->bdev_file), 0, d->pr_key, true);
 	if (error) {
 		pr_err("pNFS: failed to register key for block device %s.",
-				d->bdev_handle->bdev->bd_disk->disk_name);
+				file_bdev(d->bdev_file)->bd_disk->disk_name);
 		goto out_blkdev_put;
 	}
 
@@ -376,7 +376,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	return 0;
 
 out_blkdev_put:
-	bdev_release(d->bdev_handle);
+	fput(d->bdev_file);
 	return error;
 }
 
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 760d27dd7225..8adfcd4c8c1a 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -356,15 +356,12 @@ static const struct svc_version *nfs4_callback_version[] = {
 	[4] = &nfs4_callback_version4,
 };
 
-static struct svc_stat nfs4_callback_stats;
-
 static struct svc_program nfs4_callback_program = {
 	.pg_prog = NFS4_CALLBACK,			/* RPC service number */
 	.pg_nvers = ARRAY_SIZE(nfs4_callback_version),	/* Number of entries */
 	.pg_vers = nfs4_callback_version,		/* version table */
 	.pg_name = "NFSv4 callback",			/* service name */
 	.pg_class = "nfs",				/* authentication class */
-	.pg_stats = &nfs4_callback_stats,
 	.pg_authenticate = nfs_callback_authenticate,
 	.pg_init_request = svc_generic_init_request,
 	.pg_rpcbind_set	= svc_generic_rpcbind_set,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 44eca51b2808..fbdc9ca80f71 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -246,7 +246,7 @@ void nfs_free_client(struct nfs_client *clp)
 	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
 	kfree(clp->cl_acceptor);
-	kfree(clp);
+	kfree_rcu(clp, rcu);
 }
 EXPORT_SYMBOL_GPL(nfs_free_client);
 
@@ -1006,6 +1006,14 @@ struct nfs_server *nfs_alloc_server(void)
 }
 EXPORT_SYMBOL_GPL(nfs_alloc_server);
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct nfs_server *server = container_of(p, struct nfs_server, rcu);
+
+	nfs_free_iostats(server->io_stats);
+	kfree(server);
+}
+
 /*
  * Free up a server record
  */
@@ -1031,10 +1039,9 @@ void nfs_free_server(struct nfs_server *server)
 
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
-	nfs_free_iostats(server->io_stats);
 	put_cred(server->cred);
-	kfree(server);
 	nfs_release_automount_timer();
+	call_rcu(&server->rcu, delayed_free);
 }
 EXPORT_SYMBOL_GPL(nfs_free_server);
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index fa1a14def45c..d4a42ce0c7e3 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -156,8 +156,8 @@ static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_state
 	list = &flctx->flc_posix;
 	spin_lock(&flctx->flc_lock);
 restart:
-	list_for_each_entry(fl, list, fl_list) {
-		if (nfs_file_open_context(fl->fl_file)->state != state)
+	for_each_file_lock(fl, list) {
+		if (nfs_file_open_context(fl->c.flc_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c8ecbe999059..ac505671efbd 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1431,9 +1431,9 @@ static bool nfs_verifier_is_delegated(struct dentry *dentry)
 static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
 {
 	struct inode *inode = d_inode(dentry);
-	struct inode *dir = d_inode(dentry->d_parent);
+	struct inode *dir = d_inode_rcu(dentry->d_parent);
 
-	if (!nfs_verify_change_attribute(dir, verf))
+	if (!dir || !nfs_verify_change_attribute(dir, verf))
 		return;
 	if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		nfs_set_verifier_delegated(&verf);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 8577ccf621f5..407c6e15afe2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -720,15 +720,15 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status = 0;
-	unsigned int saved_type = fl->fl_type;
+	unsigned int saved_type = fl->c.flc_type;
 
 	/* Try local locking first */
 	posix_test_lock(filp, fl);
-	if (fl->fl_type != F_UNLCK) {
+	if (fl->c.flc_type != F_UNLCK) {
 		/* found a conflict */
 		goto out;
 	}
-	fl->fl_type = saved_type;
+	fl->c.flc_type = saved_type;
 
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
@@ -740,7 +740,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 out:
 	return status;
 out_noconflict:
-	fl->fl_type = F_UNLCK;
+	fl->c.flc_type = F_UNLCK;
 	goto out;
 }
 
@@ -765,7 +765,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 		 * 	If we're signalled while cleaning up locks on process exit, we
 		 * 	still need to complete the unlock.
 		 */
-		if (status < 0 && !(fl->fl_flags & FL_CLOSE))
+		if (status < 0 && !(fl->c.flc_flags & FL_CLOSE))
 			return status;
 	}
 
@@ -832,12 +832,12 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 	int is_local = 0;
 
 	dprintk("NFS: lock(%pD2, t=%x, fl=%x, r=%lld:%lld)\n",
-			filp, fl->fl_type, fl->fl_flags,
+			filp, fl->c.flc_type, fl->c.flc_flags,
 			(long long)fl->fl_start, (long long)fl->fl_end);
 
 	nfs_inc_stats(inode, NFSIOS_VFSLOCK);
 
-	if (fl->fl_flags & FL_RECLAIM)
+	if (fl->c.flc_flags & FL_RECLAIM)
 		return -ENOGRACE;
 
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
@@ -851,7 +851,7 @@ int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 
 	if (IS_GETLK(cmd))
 		ret = do_getlk(filp, cmd, fl, is_local);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		ret = do_unlk(filp, cmd, fl, is_local);
 	else
 		ret = do_setlk(filp, cmd, fl, is_local);
@@ -869,16 +869,16 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	int is_local = 0;
 
 	dprintk("NFS: flock(%pD2, t=%x, fl=%x)\n",
-			filp, fl->fl_type, fl->fl_flags);
+			filp, fl->c.flc_type, fl->c.flc_flags);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
 	/* We're simulating flock() locks using posix locks on the server */
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		return do_unlk(filp, cmd, fl, is_local);
 	return do_setlk(filp, cmd, fl, is_local);
 }
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 2de66e4e8280..cbbe3f0193b8 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -963,7 +963,7 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	struct nfs_open_context *ctx = nfs_file_open_context(filp);
 	int status;
 
-	if (fl->fl_flags & FL_CLOSE) {
+	if (fl->c.flc_flags & FL_CLOSE) {
 		l_ctx = nfs_get_lock_context(ctx);
 		if (IS_ERR(l_ctx))
 			l_ctx = NULL;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 581698f1b7b2..6ff41ceb9f1c 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -330,7 +330,7 @@ extern int update_open_stateid(struct nfs4_state *state,
 				const nfs4_stateid *deleg_stateid,
 				fmode_t fmode);
 extern int nfs4_proc_setlease(struct file *file, int arg,
-			      struct file_lock **lease, void **priv);
+			      struct file_lease **lease, void **priv);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
 extern void nfs4_update_changeattr(struct inode *dir,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e238abc78a13..1cd9652f3c28 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -439,7 +439,7 @@ void nfs42_ssc_unregister_ops(void)
 }
 #endif /* CONFIG_NFS_V4_2 */
 
-static int nfs4_setlease(struct file *file, int arg, struct file_lock **lease,
+static int nfs4_setlease(struct file *file, int arg, struct file_lease **lease,
 			 void **priv)
 {
 	return nfs4_proc_setlease(file, arg, lease, priv);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 23819a756508..815996cb27fc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6800,7 +6800,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	switch (status) {
 		case 0:
-			request->fl_type = F_UNLCK;
+			request->c.flc_type = F_UNLCK;
 			break;
 		case -NFS4ERR_DENIED:
 			status = 0;
@@ -7018,8 +7018,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 	/* Ensure this is an unlock - when canceling a lock, the
 	 * canceled lock is passed in, and it won't be an unlock.
 	 */
-	fl->fl_type = F_UNLCK;
-	if (fl->fl_flags & FL_CLOSE)
+	fl->c.flc_type = F_UNLCK;
+	if (fl->c.flc_flags & FL_CLOSE)
 		set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
 
 	data = nfs4_alloc_unlockdata(fl, ctx, lsp, seqid);
@@ -7045,11 +7045,11 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	struct rpc_task *task;
 	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
 	int status = 0;
-	unsigned char fl_flags = request->fl_flags;
+	unsigned char saved_flags = request->c.flc_flags;
 
 	status = nfs4_set_lock_state(state, request);
 	/* Unlock _before_ we do the RPC call */
-	request->fl_flags |= FL_EXISTS;
+	request->c.flc_flags |= FL_EXISTS;
 	/* Exclude nfs_delegation_claim_locks() */
 	mutex_lock(&sp->so_delegreturn_mutex);
 	/* Exclude nfs4_reclaim_open_stateid() - note nesting! */
@@ -7073,14 +7073,16 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	status = -ENOMEM;
 	if (IS_ERR(seqid))
 		goto out;
-	task = nfs4_do_unlck(request, nfs_file_open_context(request->fl_file), lsp, seqid);
+	task = nfs4_do_unlck(request,
+			     nfs_file_open_context(request->c.flc_file),
+			     lsp, seqid);
 	status = PTR_ERR(task);
 	if (IS_ERR(task))
 		goto out;
 	status = rpc_wait_for_completion_task(task);
 	rpc_put_task(task);
 out:
-	request->fl_flags = fl_flags;
+	request->c.flc_flags = saved_flags;
 	trace_nfs4_unlock(request, state, F_SETLK, status);
 	return status;
 }
@@ -7191,7 +7193,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 		renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)),
 				data->timestamp);
 		if (data->arg.new_lock && !data->cancelled) {
-			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
+			data->fl.c.flc_flags &= ~(FL_SLEEP | FL_ACCESS);
 			if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
 				goto out_restart;
 		}
@@ -7292,7 +7294,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 	if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
 		task_setup_data.flags |= RPC_TASK_MOVEABLE;
 
-	data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
+	data = nfs4_alloc_lockdata(fl,
+				   nfs_file_open_context(fl->c.flc_file),
 				   fl->fl_u.nfs4_fl.owner, GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
@@ -7398,10 +7401,10 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs4_state_owner *sp = state->owner;
-	unsigned char fl_flags = request->fl_flags;
+	unsigned char flags = request->c.flc_flags;
 	int status;
 
-	request->fl_flags |= FL_ACCESS;
+	request->c.flc_flags |= FL_ACCESS;
 	status = locks_lock_inode_wait(state->inode, request);
 	if (status < 0)
 		goto out;
@@ -7410,7 +7413,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 	if (test_bit(NFS_DELEGATED_STATE, &state->flags)) {
 		/* Yes: cache locks! */
 		/* ...but avoid races with delegation recall... */
-		request->fl_flags = fl_flags & ~FL_SLEEP;
+		request->c.flc_flags = flags & ~FL_SLEEP;
 		status = locks_lock_inode_wait(state->inode, request);
 		up_read(&nfsi->rwsem);
 		mutex_unlock(&sp->so_delegreturn_mutex);
@@ -7420,7 +7423,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 	mutex_unlock(&sp->so_delegreturn_mutex);
 	status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
 out:
-	request->fl_flags = fl_flags;
+	request->c.flc_flags = flags;
 	return status;
 }
 
@@ -7562,7 +7565,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	if (!(IS_SETLK(cmd) || IS_SETLKW(cmd)))
 		return -EINVAL;
 
-	if (request->fl_type == F_UNLCK) {
+	if (lock_is_unlock(request)) {
 		if (state != NULL)
 			return nfs4_proc_unlck(state, cmd, request);
 		return 0;
@@ -7571,7 +7574,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	if (state == NULL)
 		return -ENOLCK;
 
-	if ((request->fl_flags & FL_POSIX) &&
+	if ((request->c.flc_flags & FL_POSIX) &&
 	    !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
 		return -ENOLCK;
 
@@ -7579,7 +7582,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	 * Don't rely on the VFS having checked the file open mode,
 	 * since it won't do this for flock() locks.
 	 */
-	switch (request->fl_type) {
+	switch (request->c.flc_type) {
 	case F_RDLCK:
 		if (!(filp->f_mode & FMODE_READ))
 			return -EBADF;
@@ -7601,7 +7604,7 @@ static int nfs4_delete_lease(struct file *file, void **priv)
 	return generic_setlease(file, F_UNLCK, NULL, priv);
 }
 
-static int nfs4_add_lease(struct file *file, int arg, struct file_lock **lease,
+static int nfs4_add_lease(struct file *file, int arg, struct file_lease **lease,
 			  void **priv)
 {
 	struct inode *inode = file_inode(file);
@@ -7619,7 +7622,7 @@ static int nfs4_add_lease(struct file *file, int arg, struct file_lock **lease,
 	return -EAGAIN;
 }
 
-int nfs4_proc_setlease(struct file *file, int arg, struct file_lock **lease,
+int nfs4_proc_setlease(struct file *file, int arg, struct file_lease **lease,
 		       void **priv)
 {
 	switch (arg) {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9a5d911a7edc..8cfabdbda336 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -847,15 +847,15 @@ void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
  */
 static struct nfs4_lock_state *
 __nfs4_find_lock_state(struct nfs4_state *state,
-		       fl_owner_t fl_owner, fl_owner_t fl_owner2)
+		       fl_owner_t owner, fl_owner_t owner2)
 {
 	struct nfs4_lock_state *pos, *ret = NULL;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (pos->ls_owner == fl_owner) {
+		if (pos->ls_owner == owner) {
 			ret = pos;
 			break;
 		}
-		if (pos->ls_owner == fl_owner2)
+		if (pos->ls_owner == owner2)
 			ret = pos;
 	}
 	if (ret)
@@ -868,7 +868,7 @@ __nfs4_find_lock_state(struct nfs4_state *state,
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t owner)
 {
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = state->owner->so_server;
@@ -879,7 +879,7 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
 	refcount_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
-	lsp->ls_owner = fl_owner;
+	lsp->ls_owner = owner;
 	lsp->ls_seqid.owner_id = ida_alloc(&server->lockowner_id, GFP_KERNEL_ACCOUNT);
 	if (lsp->ls_seqid.owner_id < 0)
 		goto out_free;
@@ -980,7 +980,7 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 
 	if (fl->fl_ops != NULL)
 		return 0;
-	lsp = nfs4_get_lock_state(state, fl->fl_owner);
+	lsp = nfs4_get_lock_state(state, fl->c.flc_owner);
 	if (lsp == NULL)
 		return -ENOMEM;
 	fl->fl_u.nfs4_fl.owner = lsp;
@@ -993,7 +993,7 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 		const struct nfs_lock_context *l_ctx)
 {
 	struct nfs4_lock_state *lsp;
-	fl_owner_t fl_owner, fl_flock_owner;
+	fl_owner_t owner, fl_flock_owner;
 	int ret = -ENOENT;
 
 	if (l_ctx == NULL)
@@ -1002,11 +1002,11 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 	if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
 		goto out;
 
-	fl_owner = l_ctx->lockowner;
+	owner = l_ctx->lockowner;
 	fl_flock_owner = l_ctx->open_context->flock_owner;
 
 	spin_lock(&state->state_lock);
-	lsp = __nfs4_find_lock_state(state, fl_owner, fl_flock_owner);
+	lsp = __nfs4_find_lock_state(state, owner, fl_flock_owner);
 	if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
 		ret = -EIO;
 	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
@@ -1529,8 +1529,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	down_write(&nfsi->rwsem);
 	spin_lock(&flctx->flc_lock);
 restart:
-	list_for_each_entry(fl, list, fl_list) {
-		if (nfs_file_open_context(fl->fl_file)->state != state)
+	for_each_file_lock(fl, list) {
+		if (nfs_file_open_context(fl->c.flc_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index d27919d7241d..fd7cb15b08b2 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -699,7 +699,7 @@ DECLARE_EVENT_CLASS(nfs4_lock_event,
 
 			__entry->error = error < 0 ? -error : 0;
 			__entry->cmd = cmd;
-			__entry->type = request->fl_type;
+			__entry->type = request->c.flc_type;
 			__entry->start = request->fl_start;
 			__entry->end = request->fl_end;
 			__entry->dev = inode->i_sb->s_dev;
@@ -771,7 +771,7 @@ TRACE_EVENT(nfs4_set_lock,
 
 			__entry->error = error < 0 ? -error : 0;
 			__entry->cmd = cmd;
-			__entry->type = request->fl_type;
+			__entry->type = request->c.flc_type;
 			__entry->start = request->fl_start;
 			__entry->end = request->fl_end;
 			__entry->dev = inode->i_sb->s_dev;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 69406e60f391..1416099dfcd1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1305,7 +1305,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
 {
-	if (fl->fl_type == F_RDLCK)
+	if (lock_is_read(fl))
 		return block ? NFS4_READW_LT : NFS4_READ_LT;
 	return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT;
 }
@@ -5052,10 +5052,10 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
 		fl->fl_end = fl->fl_start + (loff_t)length - 1;
 		if (length == ~(uint64_t)0)
 			fl->fl_end = OFFSET_MAX;
-		fl->fl_type = F_WRLCK;
+		fl->c.flc_type = F_WRLCK;
 		if (type & 1)
-			fl->fl_type = F_RDLCK;
-		fl->fl_pid = 0;
+			fl->c.flc_type = F_RDLCK;
+		fl->c.flc_pid = 0;
 	}
 	p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */
 	namelen = be32_to_cpup(p); /* read 4 bytes */  /* have read all 32 bytes now */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index bb79d3a886ae..84bb85264572 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1301,7 +1301,7 @@ static bool
 is_whole_file_wrlock(struct file_lock *fl)
 {
 	return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
-			fl->fl_type == F_WRLCK;
+			lock_is_write(fl);
 }
 
 /* If we know the page is up to date, and we're not using byte range locks (or
@@ -1335,13 +1335,13 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
 	spin_lock(&flctx->flc_lock);
 	if (!list_empty(&flctx->flc_posix)) {
 		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
-					fl_list);
+					c.flc_list);
 		if (is_whole_file_wrlock(fl))
 			ret = 1;
 	} else if (!list_empty(&flctx->flc_flock)) {
 		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
-					fl_list);
-		if (fl->fl_type == F_WRLCK)
+					c.flc_list);
+		if (lock_is_write(fl))
 			ret = 1;
 	}
 	spin_unlock(&flctx->flc_lock);
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 46fd74d91ea9..3c040c81c77d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -328,10 +328,10 @@ nfsd4_scsi_proc_layoutcommit(struct inode *inode,
 }
 
 static void
-nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
+nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
 {
 	struct nfs4_client *clp = ls->ls_stid.sc_client;
-	struct block_device *bdev = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_bdev;
+	struct block_device *bdev = file->nf_file->f_path.mnt->mnt_sb->s_bdev;
 
 	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
 			nfsd4_scsi_pr_key(clp), 0, true);
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 4cbe0434cbb8..66a05fefae98 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -80,8 +80,6 @@ enum {
 
 int	nfsd_drc_slab_create(void);
 void	nfsd_drc_slab_free(void);
-int	nfsd_net_reply_cache_init(struct nfsd_net *nn);
-void	nfsd_net_reply_cache_destroy(struct nfsd_net *nn);
 int	nfsd_reply_cache_init(struct nfsd_net *);
 void	nfsd_reply_cache_shutdown(struct nfsd_net *);
 int	nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 9cb7f0c33df5..ddd3e0d9cfa6 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -61,13 +61,10 @@ static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions);
 
 struct nfsd_fcache_disposal {
-	struct work_struct work;
 	spinlock_t lock;
 	struct list_head freeme;
 };
 
-static struct workqueue_struct *nfsd_filecache_wq __read_mostly;
-
 static struct kmem_cache		*nfsd_file_slab;
 static struct kmem_cache		*nfsd_file_mark_slab;
 static struct list_lru			nfsd_file_lru;
@@ -283,7 +280,7 @@ nfsd_file_free(struct nfsd_file *nf)
 		nfsd_file_mark_put(nf->nf_mark);
 	if (nf->nf_file) {
 		nfsd_file_check_write_error(nf);
-		filp_close(nf->nf_file, NULL);
+		nfsd_filp_close(nf->nf_file);
 	}
 
 	/*
@@ -421,7 +418,37 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
 		spin_lock(&l->lock);
 		list_move_tail(&nf->nf_lru, &l->freeme);
 		spin_unlock(&l->lock);
-		queue_work(nfsd_filecache_wq, &l->work);
+		svc_wake_up(nn->nfsd_serv);
+	}
+}
+
+/**
+ * nfsd_file_net_dispose - deal with nfsd_files waiting to be disposed.
+ * @nn: nfsd_net in which to find files to be disposed.
+ *
+ * When files held open for nfsv3 are removed from the filecache, whether
+ * due to memory pressure or garbage collection, they are queued to
+ * a per-net-ns queue.  This function completes the disposal, either
+ * directly or by waking another nfsd thread to help with the work.
+ */
+void nfsd_file_net_dispose(struct nfsd_net *nn)
+{
+	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
+
+	if (!list_empty(&l->freeme)) {
+		LIST_HEAD(dispose);
+		int i;
+
+		spin_lock(&l->lock);
+		for (i = 0; i < 8 && !list_empty(&l->freeme); i++)
+			list_move(l->freeme.next, &dispose);
+		spin_unlock(&l->lock);
+		if (!list_empty(&l->freeme))
+			/* Wake up another thread to share the work
+			 * *before* doing any actual disposing.
+			 */
+			svc_wake_up(nn->nfsd_serv);
+		nfsd_file_dispose_list(&dispose);
 	}
 }
 
@@ -631,28 +658,6 @@ nfsd_file_close_inode_sync(struct inode *inode)
 		list_del_init(&nf->nf_lru);
 		nfsd_file_free(nf);
 	}
-	flush_delayed_fput();
-}
-
-/**
- * nfsd_file_delayed_close - close unused nfsd_files
- * @work: dummy
- *
- * Scrape the freeme list for this nfsd_net, and then dispose of them
- * all.
- */
-static void
-nfsd_file_delayed_close(struct work_struct *work)
-{
-	LIST_HEAD(head);
-	struct nfsd_fcache_disposal *l = container_of(work,
-			struct nfsd_fcache_disposal, work);
-
-	spin_lock(&l->lock);
-	list_splice_init(&l->freeme, &head);
-	spin_unlock(&l->lock);
-
-	nfsd_file_dispose_list(&head);
 }
 
 static int
@@ -662,8 +667,8 @@ nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg,
 	struct file_lock *fl = data;
 
 	/* Only close files for F_SETLEASE leases */
-	if (fl->fl_flags & FL_LEASE)
-		nfsd_file_close_inode(file_inode(fl->fl_file));
+	if (fl->c.flc_flags & FL_LEASE)
+		nfsd_file_close_inode(file_inode(fl->c.flc_file));
 	return 0;
 }
 
@@ -717,25 +722,18 @@ nfsd_file_cache_init(void)
 		return ret;
 
 	ret = -ENOMEM;
-	nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", WQ_UNBOUND, 0);
-	if (!nfsd_filecache_wq)
-		goto out;
-
-	nfsd_file_slab = kmem_cache_create("nfsd_file",
-				sizeof(struct nfsd_file), 0, 0, NULL);
+	nfsd_file_slab = KMEM_CACHE(nfsd_file, 0);
 	if (!nfsd_file_slab) {
 		pr_err("nfsd: unable to create nfsd_file_slab\n");
 		goto out_err;
 	}
 
-	nfsd_file_mark_slab = kmem_cache_create("nfsd_file_mark",
-					sizeof(struct nfsd_file_mark), 0, 0, NULL);
+	nfsd_file_mark_slab = KMEM_CACHE(nfsd_file_mark, 0);
 	if (!nfsd_file_mark_slab) {
 		pr_err("nfsd: unable to create nfsd_file_mark_slab\n");
 		goto out_err;
 	}
 
-
 	ret = list_lru_init(&nfsd_file_lru);
 	if (ret) {
 		pr_err("nfsd: failed to init nfsd_file_lru: %d\n", ret);
@@ -785,8 +783,6 @@ out_err:
 	nfsd_file_slab = NULL;
 	kmem_cache_destroy(nfsd_file_mark_slab);
 	nfsd_file_mark_slab = NULL;
-	destroy_workqueue(nfsd_filecache_wq);
-	nfsd_filecache_wq = NULL;
 	rhltable_destroy(&nfsd_file_rhltable);
 	goto out;
 }
@@ -832,7 +828,6 @@ nfsd_alloc_fcache_disposal(void)
 	l = kmalloc(sizeof(*l), GFP_KERNEL);
 	if (!l)
 		return NULL;
-	INIT_WORK(&l->work, nfsd_file_delayed_close);
 	spin_lock_init(&l->lock);
 	INIT_LIST_HEAD(&l->freeme);
 	return l;
@@ -841,7 +836,6 @@ nfsd_alloc_fcache_disposal(void)
 static void
 nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l)
 {
-	cancel_work_sync(&l->work);
 	nfsd_file_dispose_list(&l->freeme);
 	kfree(l);
 }
@@ -910,8 +904,6 @@ nfsd_file_cache_shutdown(void)
 	fsnotify_wait_marks_destroyed();
 	kmem_cache_destroy(nfsd_file_mark_slab);
 	nfsd_file_mark_slab = NULL;
-	destroy_workqueue(nfsd_filecache_wq);
-	nfsd_filecache_wq = NULL;
 	rhltable_destroy(&nfsd_file_rhltable);
 
 	for_each_possible_cpu(i) {
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index e54165a3224f..c61884def906 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -56,6 +56,7 @@ void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
+void nfsd_file_net_dispose(struct nfsd_net *nn);
 bool nfsd_file_is_cached(struct inode *inode);
 __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 74b4360779a1..d4be519b5734 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -11,8 +11,10 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <linux/filelock.h>
+#include <linux/nfs4.h>
 #include <linux/percpu_counter.h>
 #include <linux/siphash.h>
+#include <linux/sunrpc/stats.h>
 
 /* Hash tables for nfs4_clientid state */
 #define CLIENT_HASH_BITS                 4
@@ -26,10 +28,22 @@ struct nfsd4_client_tracking_ops;
 
 enum {
 	/* cache misses due only to checksum comparison failures */
-	NFSD_NET_PAYLOAD_MISSES,
+	NFSD_STATS_PAYLOAD_MISSES,
 	/* amount of memory (in bytes) currently consumed by the DRC */
-	NFSD_NET_DRC_MEM_USAGE,
-	NFSD_NET_COUNTERS_NUM
+	NFSD_STATS_DRC_MEM_USAGE,
+	NFSD_STATS_RC_HITS,		/* repcache hits */
+	NFSD_STATS_RC_MISSES,		/* repcache misses */
+	NFSD_STATS_RC_NOCACHE,		/* uncached reqs */
+	NFSD_STATS_FH_STALE,		/* FH stale error */
+	NFSD_STATS_IO_READ,		/* bytes returned to read requests */
+	NFSD_STATS_IO_WRITE,		/* bytes passed in write requests */
+#ifdef CONFIG_NFSD_V4
+	NFSD_STATS_FIRST_NFS4_OP,	/* count of individual nfsv4 operations */
+	NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP,
+#define NFSD_STATS_NFS4_OP(op)	(NFSD_STATS_FIRST_NFS4_OP + (op))
+	NFSD_STATS_WDELEG_GETATTR,	/* count of getattr conflict with wdeleg */
+#endif
+	NFSD_STATS_COUNTERS_NUM
 };
 
 /*
@@ -164,7 +178,10 @@ struct nfsd_net {
 	atomic_t                 num_drc_entries;
 
 	/* Per-netns stats counters */
-	struct percpu_counter    counter[NFSD_NET_COUNTERS_NUM];
+	struct percpu_counter    counter[NFSD_STATS_COUNTERS_NUM];
+
+	/* sunrpc svc stats */
+	struct svc_stat          nfsd_svcstats;
 
 	/* longest hash chain seen */
 	unsigned int             longest_chain;
@@ -192,6 +209,10 @@ struct nfsd_net {
 	atomic_t		nfsd_courtesy_clients;
 	struct shrinker		*nfsd_client_shrinker;
 	struct work_struct	nfsd_shrinker_work;
+
+	/* last time an admin-revoke happened for NFSv4.0 */
+	time64_t		nfs40_last_revoke;
+
 };
 
 /* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index b78eceebd945..dfcc957e460d 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -71,13 +71,15 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp)
 	struct nfsd_attrs attrs = {
 		.na_iattr	= &argp->attrs,
 	};
+	const struct timespec64 *guardtime = NULL;
 
 	dprintk("nfsd: SETATTR(3)  %s\n",
 				SVCFH_fmt(&argp->fh));
 
 	fh_copy(&resp->fh, &argp->fh);
-	resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs,
-				    argp->check_guard, argp->guardtime);
+	if (argp->check_guard)
+		guardtime = &argp->guardtime;
+	resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, guardtime);
 	return rpc_success;
 }
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index f32128955ec8..a7a07470c1f8 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -295,17 +295,14 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 static bool
 svcxdr_decode_sattrguard3(struct xdr_stream *xdr, struct nfsd3_sattrargs *args)
 {
-	__be32 *p;
 	u32 check;
 
 	if (xdr_stream_decode_bool(xdr, &check) < 0)
 		return false;
 	if (check) {
-		p = xdr_inline_decode(xdr, XDR_UNIT * 2);
-		if (!p)
+		if (!svcxdr_decode_nfstime3(xdr, &args->guardtime))
 			return false;
 		args->check_guard = 1;
-		args->guardtime = be32_to_cpup(p);
 	} else
 		args->check_guard = 0;
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 926c29879c6a..87c9547989f6 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -45,7 +45,7 @@
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
-static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
+static void nfsd4_mark_cb_fault(struct nfs4_client *clp);
 
 #define NFSPROC4_CB_NULL 0
 #define NFSPROC4_CB_COMPOUND 1
@@ -85,7 +85,21 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n)
 static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
 			   size_t len)
 {
-	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
+	xdr_stream_encode_uint32_array(xdr, bitmap, len);
+}
+
+static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
+				struct nfs4_cb_fattr *fattr)
+{
+	fattr->ncf_cb_change = 0;
+	fattr->ncf_cb_fsize = 0;
+	if (bitmap[0] & FATTR4_WORD0_CHANGE)
+		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
+			return -NFSERR_BAD_XDR;
+	if (bitmap[0] & FATTR4_WORD0_SIZE)
+		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
+			return -NFSERR_BAD_XDR;
+	return 0;
 }
 
 static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
@@ -334,6 +348,30 @@ encode_cb_recallany4args(struct xdr_stream *xdr,
 }
 
 /*
+ * CB_GETATTR4args
+ *	struct CB_GETATTR4args {
+ *	   nfs_fh4 fh;
+ *	   bitmap4 attr_request;
+ *	};
+ *
+ * The size and change attributes are the only one
+ * guaranteed to be serviced by the client.
+ */
+static void
+encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
+			struct nfs4_cb_fattr *fattr)
+{
+	struct nfs4_delegation *dp =
+		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
+	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
+
+	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
+	encode_nfs_fh4(xdr, fh);
+	encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
+	hdr->nops++;
+}
+
+/*
  * CB_SEQUENCE4args
  *
  *	struct CB_SEQUENCE4args {
@@ -469,6 +507,26 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
+ * 20.1.  Operation 3: CB_GETATTR - Get Attributes
+ */
+static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req,
+		struct xdr_stream *xdr, const void *data)
+{
+	const struct nfsd4_callback *cb = data;
+	struct nfs4_cb_fattr *ncf =
+		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = cb->cb_clp->cl_cb_ident,
+		.minorversion = cb->cb_clp->cl_minorversion,
+	};
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_getattr4args(xdr, &hdr, ncf);
+	encode_cb_nops(&hdr);
+}
+
+/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -524,6 +582,42 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
+ * 20.1.  Operation 3: CB_GETATTR - Get Attributes
+ */
+static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfsd4_callback *cb = data;
+	struct nfs4_cb_compound_hdr hdr;
+	int status;
+	u32 bitmap[3] = {0};
+	u32 attrlen;
+	struct nfs4_cb_fattr *ncf =
+		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		return status;
+
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
+	status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
+	if (status)
+		return status;
+	if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
+		return -NFSERR_BAD_XDR;
+	if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
+		return -NFSERR_BAD_XDR;
+	if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
+		return -NFSERR_BAD_XDR;
+	status = decode_cb_fattr4(xdr, bitmap, ncf);
+	return status;
+}
+
+/*
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
@@ -674,7 +768,7 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
 	const struct nfsd4_callback *cb = data;
 	const struct nfsd4_blocked_lock *nbl =
 		container_of(cb, struct nfsd4_blocked_lock, nbl_cb);
-	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner;
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.c.flc_owner;
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = 0,
 		.minorversion = cb->cb_clp->cl_minorversion,
@@ -831,6 +925,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
 	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
+	PROC(CB_GETATTR,	COMPOUND,	cb_getattr,	cb_getattr),
 };
 
 static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
@@ -887,7 +982,16 @@ static struct workqueue_struct *callback_wq;
 
 static bool nfsd4_queue_cb(struct nfsd4_callback *cb)
 {
-	return queue_work(callback_wq, &cb->cb_work);
+	trace_nfsd_cb_queue(cb->cb_clp, cb);
+	return queue_delayed_work(callback_wq, &cb->cb_work, 0);
+}
+
+static void nfsd4_queue_cb_delayed(struct nfsd4_callback *cb,
+				   unsigned long msecs)
+{
+	trace_nfsd_cb_queue(cb->cb_clp, cb);
+	queue_delayed_work(callback_wq, &cb->cb_work,
+			   msecs_to_jiffies(msecs));
 }
 
 static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
@@ -999,18 +1103,18 @@ static void nfsd4_mark_cb_state(struct nfs4_client *clp, int newstate)
 {
 	if (clp->cl_cb_state != newstate) {
 		clp->cl_cb_state = newstate;
-		trace_nfsd_cb_state(clp);
+		trace_nfsd_cb_new_state(clp);
 	}
 }
 
-static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason)
+static void nfsd4_mark_cb_down(struct nfs4_client *clp)
 {
 	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
 		return;
 	nfsd4_mark_cb_state(clp, NFSD4_CB_DOWN);
 }
 
-static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason)
+static void nfsd4_mark_cb_fault(struct nfs4_client *clp)
 {
 	if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags))
 		return;
@@ -1022,7 +1126,7 @@ static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
 	struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null);
 
 	if (task->tk_status)
-		nfsd4_mark_cb_down(clp, task->tk_status);
+		nfsd4_mark_cb_down(clp);
 	else
 		nfsd4_mark_cb_state(clp, NFSD4_CB_UP);
 }
@@ -1106,6 +1210,7 @@ static void nfsd41_destroy_cb(struct nfsd4_callback *cb)
 {
 	struct nfs4_client *clp = cb->cb_clp;
 
+	trace_nfsd_cb_destroy(clp, cb);
 	nfsd41_cb_release_slot(cb);
 	if (cb->cb_ops && cb->cb_ops->release)
 		cb->cb_ops->release(cb);
@@ -1158,6 +1263,8 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 	if (!cb->cb_holds_slot)
 		goto need_restart;
 
+	/* This is the operation status code for CB_SEQUENCE */
+	trace_nfsd_cb_seq_status(task, cb);
 	switch (cb->cb_seq_status) {
 	case 0:
 		/*
@@ -1171,13 +1278,23 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		break;
 	case -ESERVERFAULT:
 		++session->se_cb_seq_nr;
-		fallthrough;
+		nfsd4_mark_cb_fault(cb->cb_clp);
+		ret = false;
+		break;
 	case 1:
+		/*
+		 * cb_seq_status remains 1 if an RPC Reply was never
+		 * received. NFSD can't know if the client processed
+		 * the CB_SEQUENCE operation. Ask the client to send a
+		 * DESTROY_SESSION to recover.
+		 */
+		fallthrough;
 	case -NFS4ERR_BADSESSION:
-		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
+		nfsd4_mark_cb_fault(cb->cb_clp);
 		ret = false;
-		break;
+		goto need_restart;
 	case -NFS4ERR_DELAY:
+		cb->cb_seq_status = 1;
 		if (!rpc_restart_call(task))
 			goto out;
 
@@ -1192,14 +1309,11 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		}
 		break;
 	default:
-		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
-		dprintk("%s: unprocessed error %d\n", __func__,
-			cb->cb_seq_status);
+		nfsd4_mark_cb_fault(cb->cb_clp);
 	}
-
 	nfsd41_cb_release_slot(cb);
-	dprintk("%s: freed slot, new seqid=%d\n", __func__,
-		clp->cl_cb_session->se_cb_seq_nr);
+
+	trace_nfsd_cb_free_slot(task, cb);
 
 	if (RPC_SIGNALLED(task))
 		goto need_restart;
@@ -1211,6 +1325,7 @@ retry_nowait:
 	goto out;
 need_restart:
 	if (!test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags)) {
+		trace_nfsd_cb_restart(clp, cb);
 		task->tk_status = 0;
 		cb->cb_need_restart = true;
 	}
@@ -1240,7 +1355,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		case -EIO:
 		case -ETIMEDOUT:
 		case -EACCES:
-			nfsd4_mark_cb_down(clp, task->tk_status);
+			nfsd4_mark_cb_down(clp);
 		}
 		break;
 	default:
@@ -1295,12 +1410,13 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
 	nfsd41_cb_inflight_wait_complete(clp);
 }
 
-/* requires cl_lock: */
 static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
 {
 	struct nfsd4_session *s;
 	struct nfsd4_conn *c;
 
+	lockdep_assert_held(&clp->cl_lock);
+
 	list_for_each_entry(s, &clp->cl_sessions, se_perclnt) {
 		list_for_each_entry(c, &s->se_conns, cn_persession) {
 			if (c->cn_flags & NFS4_CDFC4_BACK)
@@ -1324,11 +1440,14 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	struct nfsd4_conn *c;
 	int err;
 
+	trace_nfsd_cb_bc_update(clp, cb);
+
 	/*
 	 * This is either an update, or the client dying; in either case,
 	 * kill the old client:
 	 */
 	if (clp->cl_cb_client) {
+		trace_nfsd_cb_bc_shutdown(clp, cb);
 		rpc_shutdown_client(clp->cl_cb_client);
 		clp->cl_cb_client = NULL;
 		put_cred(clp->cl_cb_cred);
@@ -1340,13 +1459,15 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	}
 	if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
 		return;
+
 	spin_lock(&clp->cl_lock);
 	/*
 	 * Only serialized callback code is allowed to clear these
 	 * flags; main nfsd code can only set them:
 	 */
-	BUG_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK));
+	WARN_ON(!(clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK));
 	clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
+
 	memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn));
 	c = __nfsd4_find_backchannel(clp);
 	if (c) {
@@ -1358,7 +1479,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 
 	err = setup_callback_client(clp, &conn, ses);
 	if (err) {
-		nfsd4_mark_cb_down(clp, err);
+		nfsd4_mark_cb_down(clp);
 		if (c)
 			svc_xprt_put(c->cn_xprt);
 		return;
@@ -1369,25 +1490,28 @@ static void
 nfsd4_run_cb_work(struct work_struct *work)
 {
 	struct nfsd4_callback *cb =
-		container_of(work, struct nfsd4_callback, cb_work);
+		container_of(work, struct nfsd4_callback, cb_work.work);
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
 	int flags;
 
-	if (cb->cb_need_restart) {
-		cb->cb_need_restart = false;
-	} else {
-		if (cb->cb_ops && cb->cb_ops->prepare)
-			cb->cb_ops->prepare(cb);
-	}
+	trace_nfsd_cb_start(clp);
 
 	if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
 		nfsd4_process_cb_update(cb);
 
 	clnt = clp->cl_cb_client;
 	if (!clnt) {
-		/* Callback channel broken, or client killed; give up: */
-		nfsd41_destroy_cb(cb);
+		if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
+			nfsd41_destroy_cb(cb);
+		else {
+			/*
+			 * XXX: Ideally, we could wait for the client to
+			 *	reconnect, but I haven't figured out how
+			 *	to do that yet.
+			 */
+			nfsd4_queue_cb_delayed(cb, 25);
+		}
 		return;
 	}
 
@@ -1400,6 +1524,12 @@ nfsd4_run_cb_work(struct work_struct *work)
 		return;
 	}
 
+	if (cb->cb_need_restart) {
+		cb->cb_need_restart = false;
+	} else {
+		if (cb->cb_ops && cb->cb_ops->prepare)
+			cb->cb_ops->prepare(cb);
+	}
 	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
 	flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN;
 	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags,
@@ -1414,8 +1544,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	cb->cb_msg.rpc_argp = cb;
 	cb->cb_msg.rpc_resp = cb;
 	cb->cb_ops = ops;
-	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
-	cb->cb_seq_status = 1;
+	INIT_DELAYED_WORK(&cb->cb_work, nfsd4_run_cb_work);
 	cb->cb_status = 0;
 	cb->cb_need_restart = false;
 	cb->cb_holds_slot = false;
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 5e8096bc5eaa..4f3072b5979a 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -25,7 +25,7 @@ static struct kmem_cache *nfs4_layout_cache;
 static struct kmem_cache *nfs4_layout_stateid_cache;
 
 static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
-static const struct lock_manager_operations nfsd4_layouts_lm_ops;
+static const struct lease_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
 #ifdef CONFIG_NFSD_FLEXFILELAYOUT
@@ -152,6 +152,23 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 #endif
 }
 
+void nfsd4_close_layout(struct nfs4_layout_stateid *ls)
+{
+	struct nfsd_file *fl;
+
+	spin_lock(&ls->ls_stid.sc_file->fi_lock);
+	fl = ls->ls_file;
+	ls->ls_file = NULL;
+	spin_unlock(&ls->ls_stid.sc_file->fi_lock);
+
+	if (fl) {
+		if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
+			kernel_setlease(fl->nf_file, F_UNLCK, NULL,
+					(void **)&ls);
+		nfsd_file_put(fl);
+	}
+}
+
 static void
 nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 {
@@ -169,9 +186,7 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 	list_del_init(&ls->ls_perfile);
 	spin_unlock(&fp->fi_lock);
 
-	if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
-		vfs_setlease(ls->ls_file->nf_file, F_UNLCK, NULL, (void **)&ls);
-	nfsd_file_put(ls->ls_file);
+	nfsd4_close_layout(ls);
 
 	if (ls->ls_recalled)
 		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
@@ -182,27 +197,26 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 static int
 nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 	int status;
 
 	if (nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
 		return 0;
 
-	fl = locks_alloc_lock();
+	fl = locks_alloc_lease();
 	if (!fl)
 		return -ENOMEM;
-	locks_init_lock(fl);
+	locks_init_lease(fl);
 	fl->fl_lmops = &nfsd4_layouts_lm_ops;
-	fl->fl_flags = FL_LAYOUT;
-	fl->fl_type = F_RDLCK;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_owner = ls;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = ls->ls_file->nf_file;
-
-	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
+	fl->c.flc_flags = FL_LAYOUT;
+	fl->c.flc_type = F_RDLCK;
+	fl->c.flc_owner = ls;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = ls->ls_file->nf_file;
+
+	status = kernel_setlease(fl->c.flc_file, fl->c.flc_type, &fl, NULL);
 	if (status) {
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 		return status;
 	}
 	BUG_ON(fl != NULL);
@@ -236,7 +250,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
 			NFSPROC4_CLNT_CB_LAYOUT);
 
-	if (parent->sc_type == NFS4_DELEG_STID)
+	if (parent->sc_type == SC_TYPE_DELEG)
 		ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
 	else
 		ls->ls_file = find_any_file(fp);
@@ -250,7 +264,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	}
 
 	spin_lock(&clp->cl_lock);
-	stp->sc_type = NFS4_LAYOUT_STID;
+	stp->sc_type = SC_TYPE_LAYOUT;
 	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
 	spin_unlock(&clp->cl_lock);
 
@@ -269,13 +283,13 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 {
 	struct nfs4_layout_stateid *ls;
 	struct nfs4_stid *stid;
-	unsigned char typemask = NFS4_LAYOUT_STID;
+	unsigned short typemask = SC_TYPE_LAYOUT;
 	__be32 status;
 
 	if (create)
-		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+		typemask |= (SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG);
 
-	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, 0, &stid,
 			net_generic(SVC_NET(rqstp), nfsd_net_id));
 	if (status)
 		goto out;
@@ -286,7 +300,7 @@ nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		goto out_put_stid;
 	}
 
-	if (stid->sc_type != NFS4_LAYOUT_STID) {
+	if (stid->sc_type != SC_TYPE_LAYOUT) {
 		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
 		nfs4_put_stid(stid);
 
@@ -518,7 +532,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp,
 		lrp->lrs_present = true;
 	} else {
 		trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid);
-		nfs4_unhash_stid(&ls->ls_stid);
+		ls->ls_stid.sc_status |= SC_STATUS_CLOSED;
 		lrp->lrs_present = false;
 	}
 	spin_unlock(&ls->ls_lock);
@@ -605,7 +619,7 @@ nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
 }
 
 static void
-nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
+nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
 {
 	struct nfs4_client *clp = ls->ls_stid.sc_client;
 	char addr_str[INET6_ADDRSTRLEN];
@@ -627,7 +641,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	argv[0] = (char *)nfsd_recall_failed;
 	argv[1] = addr_str;
-	argv[2] = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_id;
+	argv[2] = file->nf_file->f_path.mnt->mnt_sb->s_id;
 	argv[3] = NULL;
 
 	error = call_usermodehelper(nfsd_recall_failed, argv, envp,
@@ -657,6 +671,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 	struct nfsd_net *nn;
 	ktime_t now, cutoff;
 	const struct nfsd4_layout_ops *ops;
+	struct nfsd_file *fl;
 
 	trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task);
 	switch (task->tk_status) {
@@ -688,12 +703,17 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 		 * Unknown error or non-responding client, we'll need to fence.
 		 */
 		trace_nfsd_layout_recall_fail(&ls->ls_stid.sc_stateid);
-
-		ops = nfsd4_layout_ops[ls->ls_layout_type];
-		if (ops->fence_client)
-			ops->fence_client(ls);
-		else
-			nfsd4_cb_layout_fail(ls);
+		rcu_read_lock();
+		fl = nfsd_file_get(ls->ls_file);
+		rcu_read_unlock();
+		if (fl) {
+			ops = nfsd4_layout_ops[ls->ls_layout_type];
+			if (ops->fence_client)
+				ops->fence_client(ls, fl);
+			else
+				nfsd4_cb_layout_fail(ls, fl);
+			nfsd_file_put(fl);
+		}
 		return 1;
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		trace_nfsd_layout_recall_done(&ls->ls_stid.sc_stateid);
@@ -723,7 +743,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
 };
 
 static bool
-nfsd4_layout_lm_break(struct file_lock *fl)
+nfsd4_layout_lm_break(struct file_lease *fl)
 {
 	/*
 	 * We don't want the locks code to timeout the lease for us;
@@ -731,19 +751,19 @@ nfsd4_layout_lm_break(struct file_lock *fl)
 	 * in time:
 	 */
 	fl->fl_break_time = 0;
-	nfsd4_recall_file_layout(fl->fl_owner);
+	nfsd4_recall_file_layout(fl->c.flc_owner);
 	return false;
 }
 
 static int
-nfsd4_layout_lm_change(struct file_lock *onlist, int arg,
+nfsd4_layout_lm_change(struct file_lease *onlist, int arg,
 		struct list_head *dispose)
 {
 	BUG_ON(!(arg & F_UNLCK));
 	return lease_modify(onlist, arg, dispose);
 }
 
-static const struct lock_manager_operations nfsd4_layouts_lm_ops = {
+static const struct lease_manager_operations nfsd4_layouts_lm_ops = {
 	.lm_break	= nfsd4_layout_lm_break,
 	.lm_change	= nfsd4_layout_lm_change,
 };
@@ -756,13 +776,11 @@ nfsd4_init_pnfs(void)
 	for (i = 0; i < DEVID_HASH_SIZE; i++)
 		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
 
-	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
-			sizeof(struct nfs4_layout), 0, 0, NULL);
+	nfs4_layout_cache = KMEM_CACHE(nfs4_layout, 0);
 	if (!nfs4_layout_cache)
 		return -ENOMEM;
 
-	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
-			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	nfs4_layout_stateid_cache = KMEM_CACHE(nfs4_layout_stateid, 0);
 	if (!nfs4_layout_stateid_cache) {
 		kmem_cache_destroy(nfs4_layout_cache);
 		return -ENOMEM;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 14712fa08f76..2927b1263f08 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1143,6 +1143,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	};
 	struct inode *inode;
 	__be32 status = nfs_ok;
+	bool save_no_wcc;
 	int err;
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
@@ -1168,8 +1169,10 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (status)
 		goto out;
-	status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs,
-				0, (time64_t)0);
+	save_no_wcc = cstate->current_fh.fh_no_wcc;
+	cstate->current_fh.fh_no_wcc = true;
+	status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, NULL);
+	cstate->current_fh.fh_no_wcc = save_no_wcc;
 	if (!status)
 		status = nfserrno(attrs.na_labelerr);
 	if (!status)
@@ -2490,10 +2493,10 @@ nfsd4_proc_null(struct svc_rqst *rqstp)
 	return rpc_success;
 }
 
-static inline void nfsd4_increment_op_stats(u32 opnum)
+static inline void nfsd4_increment_op_stats(struct nfsd_net *nn, u32 opnum)
 {
 	if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP)
-		percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_NFS4_OP(opnum)]);
+		percpu_counter_inc(&nn->counter[NFSD_STATS_NFS4_OP(opnum)]);
 }
 
 static const struct nfsd4_operation nfsd4_ops[];
@@ -2768,7 +2771,7 @@ encode_op:
 					   status, nfsd4_op_name(op->opnum));
 
 		nfsd4_cstate_clear_replay(cstate);
-		nfsd4_increment_op_stats(op->opnum);
+		nfsd4_increment_op_stats(nn, op->opnum);
 	}
 
 	fh_put(current_fh);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6dc6340e2852..1a93c7fcf76c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -87,6 +87,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
 void nfsd4_end_grace(struct nfsd_net *nn);
 static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
 static void nfsd4_file_hash_remove(struct nfs4_file *fi);
+static void deleg_reaper(struct nfsd_net *nn);
 
 /* Locking: */
 
@@ -127,6 +128,7 @@ static void free_session(struct nfsd4_session *);
 
 static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
 
 static struct workqueue_struct *laundry_wq;
 
@@ -318,6 +320,7 @@ free_nbl(struct kref *kref)
 	struct nfsd4_blocked_lock *nbl;
 
 	nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref);
+	locks_release_private(&nbl->nbl_lock);
 	kfree(nbl);
 }
 
@@ -325,7 +328,6 @@ static void
 free_blocked_lock(struct nfsd4_blocked_lock *nbl)
 {
 	locks_delete_block(&nbl->nbl_lock);
-	locks_release_private(&nbl->nbl_lock);
 	kref_put(&nbl->nbl_kref, free_nbl);
 }
 
@@ -1189,6 +1191,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	dp->dl_recalled = false;
 	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
 		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
+	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
+			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
+	dp->dl_cb_fattr.ncf_file_modified = false;
+	dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
 	get_nfs4_file(fp);
 	dp->dl_stid.sc_file = fp;
 	return dp;
@@ -1210,6 +1216,8 @@ nfs4_put_stid(struct nfs4_stid *s)
 		return;
 	}
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+	if (s->sc_status & SC_STATUS_ADMIN_REVOKED)
+		atomic_dec(&s->sc_client->cl_admin_revoked);
 	nfs4_free_cpntf_statelist(clp->net, s);
 	spin_unlock(&clp->cl_lock);
 	s->sc_free(s);
@@ -1249,7 +1257,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
 
 	WARN_ON_ONCE(!fp->fi_delegees);
 
-	vfs_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
 	put_deleg_file(fp);
 }
 
@@ -1260,11 +1268,6 @@ static void destroy_unhashed_deleg(struct nfs4_delegation *dp)
 	nfs4_put_stid(&dp->dl_stid);
 }
 
-void nfs4_unhash_stid(struct nfs4_stid *s)
-{
-	s->sc_type = 0;
-}
-
 /**
  * nfs4_delegation_exists - Discover if this delegation already exists
  * @clp:     a pointer to the nfs4_client we're granting a delegation to
@@ -1312,11 +1315,12 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
 
 	lockdep_assert_held(&state_lock);
 	lockdep_assert_held(&fp->fi_lock);
+	lockdep_assert_held(&clp->cl_lock);
 
 	if (nfs4_delegation_exists(clp, fp))
 		return -EAGAIN;
 	refcount_inc(&dp->dl_stid.sc_count);
-	dp->dl_stid.sc_type = NFS4_DELEG_STID;
+	dp->dl_stid.sc_type = SC_TYPE_DELEG;
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
 	list_add(&dp->dl_perclnt, &clp->cl_delegations);
 	return 0;
@@ -1328,7 +1332,7 @@ static bool delegation_hashed(struct nfs4_delegation *dp)
 }
 
 static bool
-unhash_delegation_locked(struct nfs4_delegation *dp)
+unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
 
@@ -1337,7 +1341,13 @@ unhash_delegation_locked(struct nfs4_delegation *dp)
 	if (!delegation_hashed(dp))
 		return false;
 
-	dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
+	if (statusmask == SC_STATUS_REVOKED &&
+	    dp->dl_stid.sc_client->cl_minorversion == 0)
+		statusmask = SC_STATUS_CLOSED;
+	dp->dl_stid.sc_status |= statusmask;
+	if (statusmask & SC_STATUS_ADMIN_REVOKED)
+		atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked);
+
 	/* Ensure that deleg break won't try to requeue it */
 	++dp->dl_time;
 	spin_lock(&fp->fi_lock);
@@ -1353,7 +1363,7 @@ static void destroy_delegation(struct nfs4_delegation *dp)
 	bool unhashed;
 
 	spin_lock(&state_lock);
-	unhashed = unhash_delegation_locked(dp);
+	unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED);
 	spin_unlock(&state_lock);
 	if (unhashed)
 		destroy_unhashed_deleg(dp);
@@ -1367,9 +1377,9 @@ static void revoke_delegation(struct nfs4_delegation *dp)
 
 	trace_nfsd_stid_revoke(&dp->dl_stid);
 
-	if (clp->cl_minorversion) {
+	if (dp->dl_stid.sc_status &
+	    (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)) {
 		spin_lock(&clp->cl_lock);
-		dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
 		refcount_inc(&dp->dl_stid.sc_count);
 		list_add(&dp->dl_recall_lru, &clp->cl_revoked);
 		spin_unlock(&clp->cl_lock);
@@ -1377,8 +1387,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)
 	destroy_unhashed_deleg(dp);
 }
 
-/* 
- * SETCLIENTID state 
+/*
+ * SETCLIENTID state
  */
 
 static unsigned int clientid_hashval(u32 id)
@@ -1531,6 +1541,8 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
 	}
 
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+	if (s->sc_status & SC_STATUS_ADMIN_REVOKED)
+		atomic_dec(&s->sc_client->cl_admin_revoked);
 	list_add(&stp->st_locks, reaplist);
 }
 
@@ -1541,7 +1553,7 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 	if (!unhash_ol_stateid(stp))
 		return false;
 	list_del_init(&stp->st_locks);
-	nfs4_unhash_stid(&stp->st_stid);
+	stp->st_stid.sc_status |= SC_STATUS_CLOSED;
 	return true;
 }
 
@@ -1599,7 +1611,7 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 	while (!list_empty(&open_stp->st_locks)) {
 		stp = list_entry(open_stp->st_locks.next,
 				struct nfs4_ol_stateid, st_locks);
-		WARN_ON(!unhash_lock_stateid(stp));
+		unhash_lock_stateid(stp);
 		put_ol_stateid_locked(stp, reaplist);
 	}
 }
@@ -1620,6 +1632,7 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
 	LIST_HEAD(reaplist);
 
 	spin_lock(&stp->st_stid.sc_client->cl_lock);
+	stp->st_stid.sc_status |= SC_STATUS_CLOSED;
 	if (unhash_open_stateid(stp, &reaplist))
 		put_ol_stateid_locked(stp, &reaplist);
 	spin_unlock(&stp->st_stid.sc_client->cl_lock);
@@ -1675,6 +1688,136 @@ static void release_openowner(struct nfs4_openowner *oo)
 	nfs4_put_stateowner(&oo->oo_owner);
 }
 
+static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp,
+					  struct super_block *sb,
+					  unsigned int sc_types)
+{
+	unsigned long id, tmp;
+	struct nfs4_stid *stid;
+
+	spin_lock(&clp->cl_lock);
+	idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id)
+		if ((stid->sc_type & sc_types) &&
+		    stid->sc_status == 0 &&
+		    stid->sc_file->fi_inode->i_sb == sb) {
+			refcount_inc(&stid->sc_count);
+			break;
+		}
+	spin_unlock(&clp->cl_lock);
+	return stid;
+}
+
+/**
+ * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem
+ * @net:  used to identify instance of nfsd (there is one per net namespace)
+ * @sb:   super_block used to identify target filesystem
+ *
+ * All nfs4 states (open, lock, delegation, layout) held by the server instance
+ * and associated with a file on the given filesystem will be revoked resulting
+ * in any files being closed and so all references from nfsd to the filesystem
+ * being released.  Thus nfsd will no longer prevent the filesystem from being
+ * unmounted.
+ *
+ * The clients which own the states will subsequently being notified that the
+ * states have been "admin-revoked".
+ */
+void nfsd4_revoke_states(struct net *net, struct super_block *sb)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	unsigned int idhashval;
+	unsigned int sc_types;
+
+	sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT;
+
+	spin_lock(&nn->client_lock);
+	for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) {
+		struct list_head *head = &nn->conf_id_hashtbl[idhashval];
+		struct nfs4_client *clp;
+	retry:
+		list_for_each_entry(clp, head, cl_idhash) {
+			struct nfs4_stid *stid = find_one_sb_stid(clp, sb,
+								  sc_types);
+			if (stid) {
+				struct nfs4_ol_stateid *stp;
+				struct nfs4_delegation *dp;
+				struct nfs4_layout_stateid *ls;
+
+				spin_unlock(&nn->client_lock);
+				switch (stid->sc_type) {
+				case SC_TYPE_OPEN:
+					stp = openlockstateid(stid);
+					mutex_lock_nested(&stp->st_mutex,
+							  OPEN_STATEID_MUTEX);
+
+					spin_lock(&clp->cl_lock);
+					if (stid->sc_status == 0) {
+						stid->sc_status |=
+							SC_STATUS_ADMIN_REVOKED;
+						atomic_inc(&clp->cl_admin_revoked);
+						spin_unlock(&clp->cl_lock);
+						release_all_access(stp);
+					} else
+						spin_unlock(&clp->cl_lock);
+					mutex_unlock(&stp->st_mutex);
+					break;
+				case SC_TYPE_LOCK:
+					stp = openlockstateid(stid);
+					mutex_lock_nested(&stp->st_mutex,
+							  LOCK_STATEID_MUTEX);
+					spin_lock(&clp->cl_lock);
+					if (stid->sc_status == 0) {
+						struct nfs4_lockowner *lo =
+							lockowner(stp->st_stateowner);
+						struct nfsd_file *nf;
+
+						stid->sc_status |=
+							SC_STATUS_ADMIN_REVOKED;
+						atomic_inc(&clp->cl_admin_revoked);
+						spin_unlock(&clp->cl_lock);
+						nf = find_any_file(stp->st_stid.sc_file);
+						if (nf) {
+							get_file(nf->nf_file);
+							filp_close(nf->nf_file,
+								   (fl_owner_t)lo);
+							nfsd_file_put(nf);
+						}
+						release_all_access(stp);
+					} else
+						spin_unlock(&clp->cl_lock);
+					mutex_unlock(&stp->st_mutex);
+					break;
+				case SC_TYPE_DELEG:
+					dp = delegstateid(stid);
+					spin_lock(&state_lock);
+					if (!unhash_delegation_locked(
+						    dp, SC_STATUS_ADMIN_REVOKED))
+						dp = NULL;
+					spin_unlock(&state_lock);
+					if (dp)
+						revoke_delegation(dp);
+					break;
+				case SC_TYPE_LAYOUT:
+					ls = layoutstateid(stid);
+					nfsd4_close_layout(ls);
+					break;
+				}
+				nfs4_put_stid(stid);
+				spin_lock(&nn->client_lock);
+				if (clp->cl_minorversion == 0)
+					/* Allow cleanup after a lease period.
+					 * store_release ensures cleanup will
+					 * see any newly revoked states if it
+					 * sees the time updated.
+					 */
+					nn->nfs40_last_revoke =
+						ktime_get_boottime_seconds();
+				goto retry;
+			}
+		}
+	}
+	spin_unlock(&nn->client_lock);
+}
+
 static inline int
 hash_sessionid(struct nfs4_sessionid *sessionid)
 {
@@ -2228,7 +2371,7 @@ __destroy_client(struct nfs4_client *clp)
 	spin_lock(&state_lock);
 	while (!list_empty(&clp->cl_delegations)) {
 		dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
-		WARN_ON(!unhash_delegation_locked(dp));
+		unhash_delegation_locked(dp, SC_STATUS_CLOSED);
 		list_add(&dp->dl_recall_lru, &reaplist);
 	}
 	spin_unlock(&state_lock);
@@ -2460,14 +2603,16 @@ find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
 }
 
 static struct nfs4_stid *
-find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
+find_stateid_by_type(struct nfs4_client *cl, stateid_t *t,
+		     unsigned short typemask, unsigned short ok_states)
 {
 	struct nfs4_stid *s;
 
 	spin_lock(&cl->cl_lock);
 	s = find_stateid_locked(cl, t);
 	if (s != NULL) {
-		if (typemask & s->sc_type)
+		if ((s->sc_status & ~ok_states) == 0 &&
+		    (typemask & s->sc_type))
 			refcount_inc(&s->sc_count);
 		else
 			s = NULL;
@@ -2487,9 +2632,9 @@ static struct nfs4_client *get_nfsdfs_clp(struct inode *inode)
 
 static void seq_quote_mem(struct seq_file *m, char *data, int len)
 {
-	seq_printf(m, "\"");
+	seq_puts(m, "\"");
 	seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\");
-	seq_printf(m, "\"");
+	seq_puts(m, "\"");
 }
 
 static const char *cb_state2str(int state)
@@ -2530,20 +2675,22 @@ static int client_info_show(struct seq_file *m, void *v)
 		seq_puts(m, "status: unconfirmed\n");
 	seq_printf(m, "seconds from last renew: %lld\n",
 		ktime_get_boottime_seconds() - clp->cl_time);
-	seq_printf(m, "name: ");
+	seq_puts(m, "name: ");
 	seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
 	seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
 	if (clp->cl_nii_domain.data) {
-		seq_printf(m, "Implementation domain: ");
+		seq_puts(m, "Implementation domain: ");
 		seq_quote_mem(m, clp->cl_nii_domain.data,
 					clp->cl_nii_domain.len);
-		seq_printf(m, "\nImplementation name: ");
+		seq_puts(m, "\nImplementation name: ");
 		seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len);
 		seq_printf(m, "\nImplementation time: [%lld, %ld]\n",
 			clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec);
 	}
 	seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state));
 	seq_printf(m, "callback address: %pISpc\n", &clp->cl_cb_conn.cb_addr);
+	seq_printf(m, "admin-revoked states: %d\n",
+		   atomic_read(&clp->cl_admin_revoked));
 	drop_client(clp);
 
 	return 0;
@@ -2602,7 +2749,7 @@ static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f)
 
 static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo)
 {
-	seq_printf(s, "owner: ");
+	seq_puts(s, "owner: ");
 	seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len);
 }
 
@@ -2620,20 +2767,13 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
 	struct nfs4_stateowner *oo;
 	unsigned int access, deny;
 
-	if (st->sc_type != NFS4_OPEN_STID && st->sc_type != NFS4_LOCK_STID)
-		return 0; /* XXX: or SEQ_SKIP? */
 	ols = openlockstateid(st);
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
 
-	spin_lock(&nf->fi_lock);
-	file = find_any_file_locked(nf);
-	if (!file)
-		goto out;
-
-	seq_printf(s, "- ");
+	seq_puts(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
-	seq_printf(s, ": { type: open, ");
+	seq_puts(s, ": { type: open, ");
 
 	access = bmap_to_share_mode(ols->st_access_bmap);
 	deny   = bmap_to_share_mode(ols->st_deny_bmap);
@@ -2645,14 +2785,19 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
 		deny & NFS4_SHARE_ACCESS_READ ? "r" : "-",
 		deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
 
-	nfs4_show_superblock(s, file);
-	seq_printf(s, ", ");
-	nfs4_show_fname(s, file);
-	seq_printf(s, ", ");
-	nfs4_show_owner(s, oo);
-	seq_printf(s, " }\n");
-out:
+	spin_lock(&nf->fi_lock);
+	file = find_any_file_locked(nf);
+	if (file) {
+		nfs4_show_superblock(s, file);
+		seq_puts(s, ", ");
+		nfs4_show_fname(s, file);
+		seq_puts(s, ", ");
+	}
 	spin_unlock(&nf->fi_lock);
+	nfs4_show_owner(s, oo);
+	if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
+		seq_puts(s, ", admin-revoked");
+	seq_puts(s, " }\n");
 	return 0;
 }
 
@@ -2666,30 +2811,31 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
 	ols = openlockstateid(st);
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
-	spin_lock(&nf->fi_lock);
-	file = find_any_file_locked(nf);
-	if (!file)
-		goto out;
 
-	seq_printf(s, "- ");
+	seq_puts(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
-	seq_printf(s, ": { type: lock, ");
+	seq_puts(s, ": { type: lock, ");
 
-	/*
-	 * Note: a lock stateid isn't really the same thing as a lock,
-	 * it's the locking state held by one owner on a file, and there
-	 * may be multiple (or no) lock ranges associated with it.
-	 * (Same for the matter is true of open stateids.)
-	 */
+	spin_lock(&nf->fi_lock);
+	file = find_any_file_locked(nf);
+	if (file) {
+		/*
+		 * Note: a lock stateid isn't really the same thing as a lock,
+		 * it's the locking state held by one owner on a file, and there
+		 * may be multiple (or no) lock ranges associated with it.
+		 * (Same for the matter is true of open stateids.)
+		 */
 
-	nfs4_show_superblock(s, file);
-	/* XXX: open stateid? */
-	seq_printf(s, ", ");
-	nfs4_show_fname(s, file);
-	seq_printf(s, ", ");
+		nfs4_show_superblock(s, file);
+		/* XXX: open stateid? */
+		seq_puts(s, ", ");
+		nfs4_show_fname(s, file);
+		seq_puts(s, ", ");
+	}
 	nfs4_show_owner(s, oo);
-	seq_printf(s, " }\n");
-out:
+	if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
+		seq_puts(s, ", admin-revoked");
+	seq_puts(s, " }\n");
 	spin_unlock(&nf->fi_lock);
 	return 0;
 }
@@ -2702,27 +2848,28 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 
 	ds = delegstateid(st);
 	nf = st->sc_file;
-	spin_lock(&nf->fi_lock);
-	file = nf->fi_deleg_file;
-	if (!file)
-		goto out;
 
-	seq_printf(s, "- ");
+	seq_puts(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
-	seq_printf(s, ": { type: deleg, ");
+	seq_puts(s, ": { type: deleg, ");
 
-	/* Kinda dead code as long as we only support read delegs: */
-	seq_printf(s, "access: %s, ",
-		ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w");
+	seq_printf(s, "access: %s",
+		   ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w");
 
 	/* XXX: lease time, whether it's being recalled. */
 
-	nfs4_show_superblock(s, file);
-	seq_printf(s, ", ");
-	nfs4_show_fname(s, file);
-	seq_printf(s, " }\n");
-out:
+	spin_lock(&nf->fi_lock);
+	file = nf->fi_deleg_file;
+	if (file) {
+		seq_puts(s, ", ");
+		nfs4_show_superblock(s, file);
+		seq_puts(s, ", ");
+		nfs4_show_fname(s, file);
+	}
 	spin_unlock(&nf->fi_lock);
+	if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
+		seq_puts(s, ", admin-revoked");
+	seq_puts(s, " }\n");
 	return 0;
 }
 
@@ -2732,18 +2879,25 @@ static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st)
 	struct nfsd_file *file;
 
 	ls = container_of(st, struct nfs4_layout_stateid, ls_stid);
-	file = ls->ls_file;
 
-	seq_printf(s, "- ");
+	seq_puts(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
-	seq_printf(s, ": { type: layout, ");
+	seq_puts(s, ": { type: layout");
 
 	/* XXX: What else would be useful? */
 
-	nfs4_show_superblock(s, file);
-	seq_printf(s, ", ");
-	nfs4_show_fname(s, file);
-	seq_printf(s, " }\n");
+	spin_lock(&ls->ls_stid.sc_file->fi_lock);
+	file = ls->ls_file;
+	if (file) {
+		seq_puts(s, ", ");
+		nfs4_show_superblock(s, file);
+		seq_puts(s, ", ");
+		nfs4_show_fname(s, file);
+	}
+	spin_unlock(&ls->ls_stid.sc_file->fi_lock);
+	if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
+		seq_puts(s, ", admin-revoked");
+	seq_puts(s, " }\n");
 
 	return 0;
 }
@@ -2753,13 +2907,13 @@ static int states_show(struct seq_file *s, void *v)
 	struct nfs4_stid *st = v;
 
 	switch (st->sc_type) {
-	case NFS4_OPEN_STID:
+	case SC_TYPE_OPEN:
 		return nfs4_show_open(s, st);
-	case NFS4_LOCK_STID:
+	case SC_TYPE_LOCK:
 		return nfs4_show_lock(s, st);
-	case NFS4_DELEG_STID:
+	case SC_TYPE_DELEG:
 		return nfs4_show_deleg(s, st);
-	case NFS4_LAYOUT_STID:
+	case SC_TYPE_LAYOUT:
 		return nfs4_show_layout(s, st);
 	default:
 		return 0; /* XXX: or SEQ_SKIP? */
@@ -2896,11 +3050,59 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
 	spin_unlock(&nn->client_lock);
 }
 
+static int
+nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task)
+{
+	struct nfs4_cb_fattr *ncf =
+			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+
+	ncf->ncf_cb_status = task->tk_status;
+	switch (task->tk_status) {
+	case -NFS4ERR_DELAY:
+		rpc_delay(task, 2 * HZ);
+		return 0;
+	default:
+		return 1;
+	}
+}
+
+static void
+nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_cb_fattr *ncf =
+			container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
+	struct nfs4_delegation *dp =
+			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
+
+	nfs4_put_stid(&dp->dl_stid);
+	clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
+	wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
+}
+
 static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
 	.done		= nfsd4_cb_recall_any_done,
 	.release	= nfsd4_cb_recall_any_release,
 };
 
+static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
+	.done		= nfsd4_cb_getattr_done,
+	.release	= nfsd4_cb_getattr_release,
+};
+
+static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
+{
+	struct nfs4_delegation *dp =
+			container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
+
+	if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags))
+		return;
+	/* set to proper status when nfsd4_cb_getattr_done runs */
+	ncf->ncf_cb_status = NFS4ERR_IO;
+
+	refcount_inc(&dp->dl_stid.sc_count);
+	nfsd4_run_cb(&ncf->ncf_getattr);
+}
+
 static struct nfs4_client *create_client(struct xdr_netobj name,
 		struct svc_rqst *rqstp, nfs4_verifier *verf)
 {
@@ -3414,6 +3616,9 @@ out_new:
 	new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0];
 	new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1];
 
+	/* Contrived initial CREATE_SESSION response */
+	new->cl_cs_slot.sl_status = nfserr_seq_misordered;
+
 	add_to_unconfirmed(new);
 	swap(new, conf);
 out_copy:
@@ -3584,10 +3789,10 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	struct nfsd4_create_session *cr_ses = &u->create_session;
 	struct sockaddr *sa = svc_addr(rqstp);
 	struct nfs4_client *conf, *unconf;
+	struct nfsd4_clid_slot *cs_slot;
 	struct nfs4_client *old = NULL;
 	struct nfsd4_session *new;
 	struct nfsd4_conn *conn;
-	struct nfsd4_clid_slot *cs_slot = NULL;
 	__be32 status = 0;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
@@ -3611,53 +3816,60 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		goto out_free_session;
 
 	spin_lock(&nn->client_lock);
+
+	/* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */
 	unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn);
 	conf = find_confirmed_client(&cr_ses->clientid, true, nn);
-	WARN_ON_ONCE(conf && unconf);
+	if (!conf && !unconf) {
+		status = nfserr_stale_clientid;
+		goto out_free_conn;
+	}
 
-	if (conf) {
-		status = nfserr_wrong_cred;
-		if (!nfsd4_mach_creds_match(conf, rqstp))
-			goto out_free_conn;
+	/* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */
+	if (conf)
 		cs_slot = &conf->cl_cs_slot;
-		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
-		if (status) {
-			if (status == nfserr_replay_cache)
-				status = nfsd4_replay_create_session(cr_ses, cs_slot);
+	else
+		cs_slot = &unconf->cl_cs_slot;
+	status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
+	if (status) {
+		if (status == nfserr_replay_cache) {
+			status = nfsd4_replay_create_session(cr_ses, cs_slot);
 			goto out_free_conn;
 		}
-	} else if (unconf) {
+		goto out_cache_error;
+	}
+	cs_slot->sl_seqid++;
+	cr_ses->seqid = cs_slot->sl_seqid;
+
+	/* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */
+	if (conf) {
+		status = nfserr_wrong_cred;
+		if (!nfsd4_mach_creds_match(conf, rqstp))
+			goto out_cache_error;
+	} else {
 		status = nfserr_clid_inuse;
 		if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
 		    !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
 			trace_nfsd_clid_cred_mismatch(unconf, rqstp);
-			goto out_free_conn;
+			goto out_cache_error;
 		}
 		status = nfserr_wrong_cred;
 		if (!nfsd4_mach_creds_match(unconf, rqstp))
-			goto out_free_conn;
-		cs_slot = &unconf->cl_cs_slot;
-		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
-		if (status) {
-			/* an unconfirmed replay returns misordered */
-			status = nfserr_seq_misordered;
-			goto out_free_conn;
-		}
+			goto out_cache_error;
 		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
 		if (old) {
 			status = mark_client_expired_locked(old);
 			if (status) {
 				old = NULL;
-				goto out_free_conn;
+				goto out_cache_error;
 			}
 			trace_nfsd_clid_replaced(&old->cl_clientid);
 		}
 		move_to_confirmed(unconf);
 		conf = unconf;
-	} else {
-		status = nfserr_stale_clientid;
-		goto out_free_conn;
 	}
+
+	/* RFC 8881 Section 18.36.4 Phase 4: Session creation. */
 	status = nfs_ok;
 	/* Persistent sessions are not supported */
 	cr_ses->flags &= ~SESSION4_PERSIST;
@@ -3669,8 +3881,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 
 	memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
 	       NFS4_MAX_SESSIONID_LEN);
-	cs_slot->sl_seqid++;
-	cr_ses->seqid = cs_slot->sl_seqid;
 
 	/* cache solo and embedded create sessions under the client_lock */
 	nfsd4_cache_create_session(cr_ses, cs_slot, status);
@@ -3683,6 +3893,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	if (old)
 		expire_client(old);
 	return status;
+
+out_cache_error:
+	nfsd4_cache_create_session(cr_ses, cs_slot, status);
 out_free_conn:
 	spin_unlock(&nn->client_lock);
 	free_conn(conn);
@@ -4058,6 +4271,9 @@ out:
 	}
 	if (!list_empty(&clp->cl_revoked))
 		seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED;
+	if (atomic_read(&clp->cl_admin_revoked))
+		seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED;
+	trace_nfsd_seq4_status(rqstp, seq);
 out_no_session:
 	if (conn)
 		free_conn(conn);
@@ -4352,32 +4568,25 @@ nfsd4_free_slabs(void)
 int
 nfsd4_init_slabs(void)
 {
-	client_slab = kmem_cache_create("nfsd4_clients",
-			sizeof(struct nfs4_client), 0, 0, NULL);
+	client_slab = KMEM_CACHE(nfs4_client, 0);
 	if (client_slab == NULL)
 		goto out;
-	openowner_slab = kmem_cache_create("nfsd4_openowners",
-			sizeof(struct nfs4_openowner), 0, 0, NULL);
+	openowner_slab = KMEM_CACHE(nfs4_openowner, 0);
 	if (openowner_slab == NULL)
 		goto out_free_client_slab;
-	lockowner_slab = kmem_cache_create("nfsd4_lockowners",
-			sizeof(struct nfs4_lockowner), 0, 0, NULL);
+	lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0);
 	if (lockowner_slab == NULL)
 		goto out_free_openowner_slab;
-	file_slab = kmem_cache_create("nfsd4_files",
-			sizeof(struct nfs4_file), 0, 0, NULL);
+	file_slab = KMEM_CACHE(nfs4_file, 0);
 	if (file_slab == NULL)
 		goto out_free_lockowner_slab;
-	stateid_slab = kmem_cache_create("nfsd4_stateids",
-			sizeof(struct nfs4_ol_stateid), 0, 0, NULL);
+	stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0);
 	if (stateid_slab == NULL)
 		goto out_free_file_slab;
-	deleg_slab = kmem_cache_create("nfsd4_delegations",
-			sizeof(struct nfs4_delegation), 0, 0, NULL);
+	deleg_slab = KMEM_CACHE(nfs4_delegation, 0);
 	if (deleg_slab == NULL)
 		goto out_free_stateid_slab;
-	odstate_slab = kmem_cache_create("nfsd4_odstate",
-			sizeof(struct nfs4_clnt_odstate), 0, 0, NULL);
+	odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0);
 	if (odstate_slab == NULL)
 		goto out_free_deleg_slab;
 	return 0;
@@ -4531,7 +4740,8 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 			continue;
 		if (local->st_stateowner != &oo->oo_owner)
 			continue;
-		if (local->st_stid.sc_type == NFS4_OPEN_STID) {
+		if (local->st_stid.sc_type == SC_TYPE_OPEN &&
+		    !local->st_stid.sc_status) {
 			ret = local;
 			refcount_inc(&ret->st_stid.sc_count);
 			break;
@@ -4540,22 +4750,75 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 	return ret;
 }
 
-static __be32
-nfsd4_verify_open_stid(struct nfs4_stid *s)
+static void nfsd4_drop_revoked_stid(struct nfs4_stid *s)
+	__releases(&s->sc_client->cl_lock)
 {
-	__be32 ret = nfs_ok;
+	struct nfs4_client *cl = s->sc_client;
+	LIST_HEAD(reaplist);
+	struct nfs4_ol_stateid *stp;
+	struct nfs4_delegation *dp;
+	bool unhashed;
 
 	switch (s->sc_type) {
-	default:
+	case SC_TYPE_OPEN:
+		stp = openlockstateid(s);
+		if (unhash_open_stateid(stp, &reaplist))
+			put_ol_stateid_locked(stp, &reaplist);
+		spin_unlock(&cl->cl_lock);
+		free_ol_stateid_reaplist(&reaplist);
 		break;
-	case 0:
-	case NFS4_CLOSED_STID:
-	case NFS4_CLOSED_DELEG_STID:
-		ret = nfserr_bad_stateid;
+	case SC_TYPE_LOCK:
+		stp = openlockstateid(s);
+		unhashed = unhash_lock_stateid(stp);
+		spin_unlock(&cl->cl_lock);
+		if (unhashed)
+			nfs4_put_stid(s);
 		break;
-	case NFS4_REVOKED_DELEG_STID:
-		ret = nfserr_deleg_revoked;
+	case SC_TYPE_DELEG:
+		dp = delegstateid(s);
+		list_del_init(&dp->dl_recall_lru);
+		spin_unlock(&cl->cl_lock);
+		nfs4_put_stid(s);
+		break;
+	default:
+		spin_unlock(&cl->cl_lock);
 	}
+}
+
+static void nfsd40_drop_revoked_stid(struct nfs4_client *cl,
+				    stateid_t *stid)
+{
+	/* NFSv4.0 has no way for the client to tell the server
+	 * that it can forget an admin-revoked stateid.
+	 * So we keep it around until the first time that the
+	 * client uses it, and drop it the first time
+	 * nfserr_admin_revoked is returned.
+	 * For v4.1 and later we wait until explicitly told
+	 * to free the stateid.
+	 */
+	if (cl->cl_minorversion == 0) {
+		struct nfs4_stid *st;
+
+		spin_lock(&cl->cl_lock);
+		st = find_stateid_locked(cl, stid);
+		if (st)
+			nfsd4_drop_revoked_stid(st);
+		else
+			spin_unlock(&cl->cl_lock);
+	}
+}
+
+static __be32
+nfsd4_verify_open_stid(struct nfs4_stid *s)
+{
+	__be32 ret = nfs_ok;
+
+	if (s->sc_status & SC_STATUS_ADMIN_REVOKED)
+		ret = nfserr_admin_revoked;
+	else if (s->sc_status & SC_STATUS_REVOKED)
+		ret = nfserr_deleg_revoked;
+	else if (s->sc_status & SC_STATUS_CLOSED)
+		ret = nfserr_bad_stateid;
 	return ret;
 }
 
@@ -4567,6 +4830,10 @@ nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
 
 	mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX);
 	ret = nfsd4_verify_open_stid(&stp->st_stid);
+	if (ret == nfserr_admin_revoked)
+		nfsd40_drop_revoked_stid(stp->st_stid.sc_client,
+					&stp->st_stid.sc_stateid);
+
 	if (ret != nfs_ok)
 		mutex_unlock(&stp->st_mutex);
 	return ret;
@@ -4641,7 +4908,7 @@ retry:
 
 	open->op_stp = NULL;
 	refcount_inc(&stp->st_stid.sc_count);
-	stp->st_stid.sc_type = NFS4_OPEN_STID;
+	stp->st_stid.sc_type = SC_TYPE_OPEN;
 	INIT_LIST_HEAD(&stp->st_locks);
 	stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner);
 	get_nfs4_file(fp);
@@ -4868,9 +5135,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
 
 	trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task);
 
-	if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID ||
-	    dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID)
-	        return 1;
+	if (dp->dl_stid.sc_status)
+		/* CLOSED or REVOKED */
+		return 1;
 
 	switch (task->tk_status) {
 	case 0:
@@ -4922,9 +5189,9 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 
 /* Called from break_lease() with flc_lock held. */
 static bool
-nfsd_break_deleg_cb(struct file_lock *fl)
+nfsd_break_deleg_cb(struct file_lease *fl)
 {
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
+	struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner;
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
 	struct nfsd_net *nn;
@@ -4945,10 +5212,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	 */
 	fl->fl_break_time = 0;
 
-	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
-	spin_unlock(&fp->fi_lock);
 	return false;
 }
 
@@ -4960,9 +5225,9 @@ nfsd_break_deleg_cb(struct file_lock *fl)
  *   %true: Lease conflict was resolved
  *   %false: Lease conflict was not resolved.
  */
-static bool nfsd_breaker_owns_lease(struct file_lock *fl)
+static bool nfsd_breaker_owns_lease(struct file_lease *fl)
 {
-	struct nfs4_delegation *dl = fl->fl_owner;
+	struct nfs4_delegation *dl = fl->c.flc_owner;
 	struct svc_rqst *rqst;
 	struct nfs4_client *clp;
 
@@ -4977,10 +5242,10 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl)
 }
 
 static int
-nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
+nfsd_change_deleg_cb(struct file_lease *onlist, int arg,
 		     struct list_head *dispose)
 {
-	struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner;
+	struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner;
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
 
 	if (arg & F_UNLCK) {
@@ -4991,7 +5256,7 @@ nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
 		return -EAGAIN;
 }
 
-static const struct lock_manager_operations nfsd_lease_mng_ops = {
+static const struct lease_manager_operations nfsd_lease_mng_ops = {
 	.lm_breaker_owns_lease = nfsd_breaker_owns_lease,
 	.lm_break = nfsd_break_deleg_cb,
 	.lm_change = nfsd_change_deleg_cb,
@@ -5115,12 +5380,12 @@ static int share_access_to_flags(u32 share_access)
 	return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE;
 }
 
-static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s)
+static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl,
+						  stateid_t *s)
 {
 	struct nfs4_stid *ret;
 
-	ret = find_stateid_by_type(cl, s,
-				NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID);
+	ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED);
 	if (!ret)
 		return NULL;
 	return delegstateid(ret);
@@ -5143,10 +5408,15 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open,
 	deleg = find_deleg_stateid(cl, &open->op_delegate_stateid);
 	if (deleg == NULL)
 		goto out;
-	if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) {
+	if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) {
+		nfs4_put_stid(&deleg->dl_stid);
+		status = nfserr_admin_revoked;
+		goto out;
+	}
+	if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) {
 		nfs4_put_stid(&deleg->dl_stid);
-		if (cl->cl_minorversion)
-			status = nfserr_deleg_revoked;
+		nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid);
+		status = nfserr_deleg_revoked;
 		goto out;
 	}
 	flags = share_access_to_flags(open->op_share_access);
@@ -5191,7 +5461,7 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
 		return 0;
 	if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
 		return nfserr_inval;
-	return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0);
+	return nfsd_setattr(rqstp, fh, &attrs, NULL);
 }
 
 static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
@@ -5331,21 +5601,20 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
 	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
 }
 
-static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
+static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 						int flag)
 {
-	struct file_lock *fl;
+	struct file_lease *fl;
 
-	fl = locks_alloc_lock();
+	fl = locks_alloc_lease();
 	if (!fl)
 		return NULL;
 	fl->fl_lmops = &nfsd_lease_mng_ops;
-	fl->fl_flags = FL_DELEG;
-	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
-	fl->fl_end = OFFSET_MAX;
-	fl->fl_owner = (fl_owner_t)dp;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+	fl->c.flc_flags = FL_DELEG;
+	fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
+	fl->c.flc_owner = (fl_owner_t)dp;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
 	return fl;
 }
 
@@ -5463,7 +5732,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate;
 	struct nfs4_delegation *dp;
 	struct nfsd_file *nf = NULL;
-	struct file_lock *fl;
+	struct file_lease *fl;
 	u32 dl_type;
 
 	/*
@@ -5533,9 +5802,10 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (!fl)
 		goto out_clnt_odstate;
 
-	status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
+	status = kernel_setlease(fp->fi_deleg_file->nf_file,
+				      fl->c.flc_type, &fl, NULL);
 	if (fl)
-		locks_free_lock(fl);
+		locks_free_lease(fl);
 	if (status)
 		goto out_clnt_odstate;
 
@@ -5557,13 +5827,16 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (status)
 		goto out_unlock;
 
+	status = -EAGAIN;
+	if (fp->fi_had_conflict)
+		goto out_unlock;
+
 	spin_lock(&state_lock);
+	spin_lock(&clp->cl_lock);
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_had_conflict)
-		status = -EAGAIN;
-	else
-		status = hash_delegation_locked(dp, fp);
+	status = hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
+	spin_unlock(&clp->cl_lock);
 	spin_unlock(&state_lock);
 
 	if (status)
@@ -5571,7 +5844,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 
 	return dp;
 out_unlock:
-	vfs_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
 out_clnt_odstate:
 	put_clnt_odstate(dp->dl_clnt_odstate);
 	nfs4_put_stid(&dp->dl_stid);
@@ -5635,6 +5908,8 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	struct svc_fh *parent = NULL;
 	int cb_up;
 	int status = 0;
+	struct kstat stat;
+	struct path path;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	open->op_recall = false;
@@ -5672,6 +5947,18 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
+		path.mnt = currentfh->fh_export->ex_path.mnt;
+		path.dentry = currentfh->fh_dentry;
+		if (vfs_getattr(&path, &stat,
+				(STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
+				AT_STATX_SYNC_AS_STAT)) {
+			nfs4_put_stid(&dp->dl_stid);
+			destroy_delegation(dp);
+			goto out_no_deleg;
+		}
+		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
+		dp->dl_cb_fattr.ncf_initial_cinfo =
+			nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
 	} else {
 		open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
 		trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
@@ -5775,7 +6062,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	} else {
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true);
 		if (status) {
-			stp->st_stid.sc_type = NFS4_CLOSED_STID;
 			release_open_stateid(stp);
 			mutex_unlock(&stp->st_mutex);
 			goto out;
@@ -6129,6 +6415,43 @@ nfs4_process_client_reaplist(struct list_head *reaplist)
 	}
 }
 
+static void nfs40_clean_admin_revoked(struct nfsd_net *nn,
+				      struct laundry_time *lt)
+{
+	struct nfs4_client *clp;
+
+	spin_lock(&nn->client_lock);
+	if (nn->nfs40_last_revoke == 0 ||
+	    nn->nfs40_last_revoke > lt->cutoff) {
+		spin_unlock(&nn->client_lock);
+		return;
+	}
+	nn->nfs40_last_revoke = 0;
+
+retry:
+	list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+		unsigned long id, tmp;
+		struct nfs4_stid *stid;
+
+		if (atomic_read(&clp->cl_admin_revoked) == 0)
+			continue;
+
+		spin_lock(&clp->cl_lock);
+		idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id)
+			if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) {
+				refcount_inc(&stid->sc_count);
+				spin_unlock(&nn->client_lock);
+				/* this function drops ->cl_lock */
+				nfsd4_drop_revoked_stid(stid);
+				nfs4_put_stid(stid);
+				spin_lock(&nn->client_lock);
+				goto retry;
+			}
+		spin_unlock(&clp->cl_lock);
+	}
+	spin_unlock(&nn->client_lock);
+}
+
 static time64_t
 nfs4_laundromat(struct nfsd_net *nn)
 {
@@ -6162,12 +6485,14 @@ nfs4_laundromat(struct nfsd_net *nn)
 	nfs4_get_client_reaplist(nn, &reaplist, &lt);
 	nfs4_process_client_reaplist(&reaplist);
 
+	nfs40_clean_admin_revoked(nn, &lt);
+
 	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		if (!state_expired(&lt, dp->dl_time))
 			break;
-		WARN_ON(!unhash_delegation_locked(dp));
+		unhash_delegation_locked(dp, SC_STATUS_REVOKED);
 		list_add(&dp->dl_recall_lru, &reaplist);
 	}
 	spin_unlock(&state_lock);
@@ -6226,6 +6551,8 @@ nfs4_laundromat(struct nfsd_net *nn)
 	/* service the server-to-server copy delayed unmount list */
 	nfsd4_ssc_expire_umount(nn);
 #endif
+	if (atomic_long_read(&num_delegations) >= max_delegations)
+		deleg_reaper(nn);
 out:
 	return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
 }
@@ -6287,6 +6614,8 @@ deleg_reaper(struct nfsd_net *nn)
 		list_del_init(&clp->cl_ra_cblist);
 		clp->cl_ra->ra_keep = 0;
 		clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG);
+		clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) |
+						BIT(RCA4_TYPE_MASK_WDATA_DLG);
 		trace_nfsd_cb_recall_any(clp->cl_ra);
 		nfsd4_run_cb(&clp->cl_ra->ra_cb);
 	}
@@ -6380,6 +6709,9 @@ static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_sti
 	if (ret == nfs_ok)
 		ret = check_stateid_generation(in, &s->sc_stateid, has_session);
 	spin_unlock(&s->sc_lock);
+	if (ret == nfserr_admin_revoked)
+		nfsd40_drop_revoked_stid(s->sc_client,
+					&s->sc_stateid);
 	return ret;
 }
 
@@ -6406,32 +6738,33 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	status = nfsd4_stid_check_stateid_generation(stateid, s, 1);
 	if (status)
 		goto out_unlock;
+	status = nfsd4_verify_open_stid(s);
+	if (status)
+		goto out_unlock;
+
 	switch (s->sc_type) {
-	case NFS4_DELEG_STID:
+	case SC_TYPE_DELEG:
 		status = nfs_ok;
 		break;
-	case NFS4_REVOKED_DELEG_STID:
-		status = nfserr_deleg_revoked;
-		break;
-	case NFS4_OPEN_STID:
-	case NFS4_LOCK_STID:
+	case SC_TYPE_OPEN:
+	case SC_TYPE_LOCK:
 		status = nfsd4_check_openowner_confirmed(openlockstateid(s));
 		break;
 	default:
 		printk("unknown stateid type %x\n", s->sc_type);
-		fallthrough;
-	case NFS4_CLOSED_STID:
-	case NFS4_CLOSED_DELEG_STID:
 		status = nfserr_bad_stateid;
 	}
 out_unlock:
 	spin_unlock(&cl->cl_lock);
+	if (status == nfserr_admin_revoked)
+		nfsd40_drop_revoked_stid(cl, stateid);
 	return status;
 }
 
 __be32
 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
-		     stateid_t *stateid, unsigned char typemask,
+		     stateid_t *stateid,
+		     unsigned short typemask, unsigned short statusmask,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
 {
 	__be32 status;
@@ -6442,10 +6775,15 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	 *  only return revoked delegations if explicitly asked.
 	 *  otherwise we report revoked or bad_stateid status.
 	 */
-	if (typemask & NFS4_REVOKED_DELEG_STID)
+	if (statusmask & SC_STATUS_REVOKED)
 		return_revoked = true;
-	else if (typemask & NFS4_DELEG_STID)
-		typemask |= NFS4_REVOKED_DELEG_STID;
+	if (typemask & SC_TYPE_DELEG)
+		/* Always allow REVOKED for DELEG so we can
+		 * retturn the appropriate error.
+		 */
+		statusmask |= SC_STATUS_REVOKED;
+
+	statusmask |= SC_STATUS_ADMIN_REVOKED;
 
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
 		CLOSE_STATEID(stateid))
@@ -6458,14 +6796,17 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 	}
 	if (status)
 		return status;
-	stid = find_stateid_by_type(cstate->clp, stateid, typemask);
+	stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask);
 	if (!stid)
 		return nfserr_bad_stateid;
-	if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) {
+	if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) {
 		nfs4_put_stid(stid);
-		if (cstate->minorversion)
-			return nfserr_deleg_revoked;
-		return nfserr_bad_stateid;
+		return nfserr_deleg_revoked;
+	}
+	if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) {
+		nfsd40_drop_revoked_stid(cstate->clp, stateid);
+		nfs4_put_stid(stid);
+		return nfserr_admin_revoked;
 	}
 	*s = stid;
 	return nfs_ok;
@@ -6476,17 +6817,17 @@ nfs4_find_file(struct nfs4_stid *s, int flags)
 {
 	struct nfsd_file *ret = NULL;
 
-	if (!s)
+	if (!s || s->sc_status)
 		return NULL;
 
 	switch (s->sc_type) {
-	case NFS4_DELEG_STID:
+	case SC_TYPE_DELEG:
 		spin_lock(&s->sc_file->fi_lock);
 		ret = nfsd_file_get(s->sc_file->fi_deleg_file);
 		spin_unlock(&s->sc_file->fi_lock);
 		break;
-	case NFS4_OPEN_STID:
-	case NFS4_LOCK_STID:
+	case SC_TYPE_OPEN:
+	case SC_TYPE_LOCK:
 		if (flags & RD_STATE)
 			ret = find_readable_file(s->sc_file);
 		else
@@ -6599,7 +6940,8 @@ static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st,
 		goto out;
 
 	*stid = find_stateid_by_type(found, &cps->cp_p_stateid,
-			NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID);
+				     SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK,
+				     0);
 	if (*stid)
 		status = nfs_ok;
 	else
@@ -6656,8 +6998,8 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 	}
 
 	status = nfsd4_lookup_stateid(cstate, stateid,
-				NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
-				&s, nn);
+				SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK,
+				0, &s, nn);
 	if (status == nfserr_bad_stateid)
 		status = find_cpntf_state(nn, stateid, &s);
 	if (status)
@@ -6668,16 +7010,13 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		goto out;
 
 	switch (s->sc_type) {
-	case NFS4_DELEG_STID:
+	case SC_TYPE_DELEG:
 		status = nfs4_check_delegmode(delegstateid(s), flags);
 		break;
-	case NFS4_OPEN_STID:
-	case NFS4_LOCK_STID:
+	case SC_TYPE_OPEN:
+	case SC_TYPE_LOCK:
 		status = nfs4_check_olstateid(openlockstateid(s), flags);
 		break;
-	default:
-		status = nfserr_bad_stateid;
-		break;
 	}
 	if (status)
 		goto out;
@@ -6756,34 +7095,39 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	spin_lock(&cl->cl_lock);
 	s = find_stateid_locked(cl, stateid);
-	if (!s)
+	if (!s || s->sc_status & SC_STATUS_CLOSED)
 		goto out_unlock;
+	if (s->sc_status & SC_STATUS_ADMIN_REVOKED) {
+		nfsd4_drop_revoked_stid(s);
+		ret = nfs_ok;
+		goto out;
+	}
 	spin_lock(&s->sc_lock);
 	switch (s->sc_type) {
-	case NFS4_DELEG_STID:
+	case SC_TYPE_DELEG:
+		if (s->sc_status & SC_STATUS_REVOKED) {
+			spin_unlock(&s->sc_lock);
+			dp = delegstateid(s);
+			list_del_init(&dp->dl_recall_lru);
+			spin_unlock(&cl->cl_lock);
+			nfs4_put_stid(s);
+			ret = nfs_ok;
+			goto out;
+		}
 		ret = nfserr_locks_held;
 		break;
-	case NFS4_OPEN_STID:
+	case SC_TYPE_OPEN:
 		ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
 		if (ret)
 			break;
 		ret = nfserr_locks_held;
 		break;
-	case NFS4_LOCK_STID:
+	case SC_TYPE_LOCK:
 		spin_unlock(&s->sc_lock);
 		refcount_inc(&s->sc_count);
 		spin_unlock(&cl->cl_lock);
 		ret = nfsd4_free_lock_stateid(stateid, s);
 		goto out;
-	case NFS4_REVOKED_DELEG_STID:
-		spin_unlock(&s->sc_lock);
-		dp = delegstateid(s);
-		list_del_init(&dp->dl_recall_lru);
-		spin_unlock(&cl->cl_lock);
-		nfs4_put_stid(s);
-		ret = nfs_ok;
-		goto out;
-	/* Default falls through and returns nfserr_bad_stateid */
 	}
 	spin_unlock(&s->sc_lock);
 out_unlock:
@@ -6825,6 +7169,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
  * @seqid: seqid (provided by client)
  * @stateid: stateid (provided by client)
  * @typemask: mask of allowable types for this operation
+ * @statusmask: mask of allowed states: 0 or STID_CLOSED
  * @stpp: return pointer for the stateid found
  * @nn: net namespace for request
  *
@@ -6834,7 +7179,8 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
  */
 static __be32
 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
-			 stateid_t *stateid, char typemask,
+			 stateid_t *stateid,
+			 unsigned short typemask, unsigned short statusmask,
 			 struct nfs4_ol_stateid **stpp,
 			 struct nfsd_net *nn)
 {
@@ -6845,7 +7191,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
 	trace_nfsd_preprocess(seqid, stateid);
 
 	*stpp = NULL;
-	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn);
+	status = nfsd4_lookup_stateid(cstate, stateid,
+				      typemask, statusmask, &s, nn);
 	if (status)
 		return status;
 	stp = openlockstateid(s);
@@ -6867,7 +7214,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 	struct nfs4_ol_stateid *stp;
 
 	status = nfs4_preprocess_seqid_op(cstate, seqid, stateid,
-						NFS4_OPEN_STID, &stp, nn);
+					  SC_TYPE_OPEN, 0, &stp, nn);
 	if (status)
 		return status;
 	oo = openowner(stp->st_stateowner);
@@ -6898,8 +7245,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return status;
 
 	status = nfs4_preprocess_seqid_op(cstate,
-					oc->oc_seqid, &oc->oc_req_stateid,
-					NFS4_OPEN_STID, &stp, nn);
+					  oc->oc_seqid, &oc->oc_req_stateid,
+					  SC_TYPE_OPEN, 0, &stp, nn);
 	if (status)
 		goto out;
 	oo = openowner(stp->st_stateowner);
@@ -7029,18 +7376,20 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	dprintk("NFSD: nfsd4_close on file %pd\n", 
+	dprintk("NFSD: nfsd4_close on file %pd\n",
 			cstate->current_fh.fh_dentry);
 
 	status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid,
-					&close->cl_stateid,
-					NFS4_OPEN_STID|NFS4_CLOSED_STID,
-					&stp, nn);
+					  &close->cl_stateid,
+					  SC_TYPE_OPEN, SC_STATUS_CLOSED,
+					  &stp, nn);
 	nfsd4_bump_seqid(cstate, status);
 	if (status)
-		goto out; 
+		goto out;
 
-	stp->st_stid.sc_type = NFS4_CLOSED_STID;
+	spin_lock(&stp->st_stid.sc_client->cl_lock);
+	stp->st_stid.sc_status |= SC_STATUS_CLOSED;
+	spin_unlock(&stp->st_stid.sc_client->cl_lock);
 
 	/*
 	 * Technically we don't _really_ have to increment or copy it, since
@@ -7082,7 +7431,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
 		return status;
 
-	status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn);
+	status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, 0, &s, nn);
 	if (status)
 		goto out;
 	dp = delegstateid(s);
@@ -7149,7 +7498,7 @@ nfsd4_lm_put_owner(fl_owner_t owner)
 static bool
 nfsd4_lm_lock_expirable(struct file_lock *cfl)
 {
-	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner;
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner;
 	struct nfs4_client *clp = lo->lo_owner.so_client;
 	struct nfsd_net *nn;
 
@@ -7171,7 +7520,7 @@ nfsd4_lm_expire_lock(void)
 static void
 nfsd4_lm_notify(struct file_lock *fl)
 {
-	struct nfs4_lockowner		*lo = (struct nfs4_lockowner *)fl->fl_owner;
+	struct nfs4_lockowner		*lo = (struct nfs4_lockowner *) fl->c.flc_owner;
 	struct net			*net = lo->lo_owner.so_client->net;
 	struct nfsd_net			*nn = net_generic(net, nfsd_net_id);
 	struct nfsd4_blocked_lock	*nbl = container_of(fl,
@@ -7208,7 +7557,7 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny)
 	struct nfs4_lockowner *lo;
 
 	if (fl->fl_lmops == &nfsd_posix_mng_ops) {
-		lo = (struct nfs4_lockowner *) fl->fl_owner;
+		lo = (struct nfs4_lockowner *) fl->c.flc_owner;
 		xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner,
 						GFP_KERNEL);
 		if (!deny->ld_owner.data)
@@ -7227,7 +7576,7 @@ nevermind:
 	if (fl->fl_end != NFS4_MAX_UINT64)
 		deny->ld_length = fl->fl_end - fl->fl_start + 1;        
 	deny->ld_type = NFS4_READ_LT;
-	if (fl->fl_type != F_RDLCK)
+	if (fl->c.flc_type != F_RDLCK)
 		deny->ld_type = NFS4_WRITE_LT;
 }
 
@@ -7349,7 +7698,7 @@ retry:
 	if (retstp)
 		goto out_found;
 	refcount_inc(&stp->st_stid.sc_count);
-	stp->st_stid.sc_type = NFS4_LOCK_STID;
+	stp->st_stid.sc_type = SC_TYPE_LOCK;
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
@@ -7493,8 +7842,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	int lkflg;
 	int err;
 	bool new = false;
-	unsigned char fl_type;
-	unsigned int fl_flags = FL_POSIX;
+	unsigned char type;
+	unsigned int flags = FL_POSIX;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
@@ -7536,9 +7885,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 							&lock_stp, &new);
 	} else {
 		status = nfs4_preprocess_seqid_op(cstate,
-				       lock->lk_old_lock_seqid,
-				       &lock->lk_old_lock_stateid,
-				       NFS4_LOCK_STID, &lock_stp, nn);
+						  lock->lk_old_lock_seqid,
+						  &lock->lk_old_lock_stateid,
+						  SC_TYPE_LOCK, 0, &lock_stp,
+						  nn);
 	}
 	if (status)
 		goto out;
@@ -7557,14 +7907,14 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 
 	if (lock->lk_reclaim)
-		fl_flags |= FL_RECLAIM;
+		flags |= FL_RECLAIM;
 
 	fp = lock_stp->st_stid.sc_file;
 	switch (lock->lk_type) {
 		case NFS4_READW_LT:
 			if (nfsd4_has_session(cstate) ||
 			    exportfs_lock_op_is_async(sb->s_export_op))
-				fl_flags |= FL_SLEEP;
+				flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_READ_LT:
 			spin_lock(&fp->fi_lock);
@@ -7572,12 +7922,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			if (nf)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ);
 			spin_unlock(&fp->fi_lock);
-			fl_type = F_RDLCK;
+			type = F_RDLCK;
 			break;
 		case NFS4_WRITEW_LT:
 			if (nfsd4_has_session(cstate) ||
 			    exportfs_lock_op_is_async(sb->s_export_op))
-				fl_flags |= FL_SLEEP;
+				flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_WRITE_LT:
 			spin_lock(&fp->fi_lock);
@@ -7585,7 +7935,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			if (nf)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE);
 			spin_unlock(&fp->fi_lock);
-			fl_type = F_WRLCK;
+			type = F_WRLCK;
 			break;
 		default:
 			status = nfserr_inval;
@@ -7605,7 +7955,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * on those filesystems:
 	 */
 	if (!exportfs_lock_op_is_async(sb->s_export_op))
-		fl_flags &= ~FL_SLEEP;
+		flags &= ~FL_SLEEP;
 
 	nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
 	if (!nbl) {
@@ -7615,11 +7965,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	file_lock = &nbl->nbl_lock;
-	file_lock->fl_type = fl_type;
-	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_file = nf->nf_file;
-	file_lock->fl_flags = fl_flags;
+	file_lock->c.flc_type = type;
+	file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_file = nf->nf_file;
+	file_lock->c.flc_flags = flags;
 	file_lock->fl_lmops = &nfsd_posix_mng_ops;
 	file_lock->fl_start = lock->lk_offset;
 	file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length);
@@ -7632,7 +7982,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 	}
 
-	if (fl_flags & FL_SLEEP) {
+	if (flags & FL_SLEEP) {
 		nbl->nbl_time = ktime_get_boottime_seconds();
 		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
@@ -7669,7 +8019,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	if (nbl) {
 		/* dequeue it if we queued it before */
-		if (fl_flags & FL_SLEEP) {
+		if (flags & FL_SLEEP) {
 			spin_lock(&nn->blocked_locks_lock);
 			if (!list_empty(&nbl->nbl_list) &&
 			    !list_empty(&nbl->nbl_lru)) {
@@ -7737,9 +8087,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct
 	err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
 	if (err)
 		goto out;
-	lock->fl_file = nf->nf_file;
+	lock->c.flc_file = nf->nf_file;
 	err = nfserrno(vfs_test_lock(nf->nf_file, lock));
-	lock->fl_file = NULL;
+	lock->c.flc_file = NULL;
 out:
 	inode_unlock(inode);
 	nfsd_file_put(nf);
@@ -7784,11 +8134,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	switch (lockt->lt_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
-			file_lock->fl_type = F_RDLCK;
+			file_lock->c.flc_type = F_RDLCK;
 			break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
-			file_lock->fl_type = F_WRLCK;
+			file_lock->c.flc_type = F_WRLCK;
 			break;
 		default:
 			dprintk("NFSD: nfs4_lockt: bad lock type!\n");
@@ -7798,9 +8148,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	lo = find_lockowner_str(cstate->clp, &lockt->lt_owner);
 	if (lo)
-		file_lock->fl_owner = (fl_owner_t)lo;
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_flags = FL_POSIX;
+		file_lock->c.flc_owner = (fl_owner_t)lo;
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_flags = FL_POSIX;
 
 	file_lock->fl_start = lockt->lt_offset;
 	file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
@@ -7811,7 +8161,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 
-	if (file_lock->fl_type != F_UNLCK) {
+	if (file_lock->c.flc_type != F_UNLCK) {
 		status = nfserr_denied;
 		nfs4_set_lock_denied(file_lock, &lockt->lt_denied);
 	}
@@ -7851,8 +8201,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		 return nfserr_inval;
 
 	status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid,
-					&locku->lu_stateid, NFS4_LOCK_STID,
-					&stp, nn);
+					  &locku->lu_stateid, SC_TYPE_LOCK, 0,
+					  &stp, nn);
 	if (status)
 		goto out;
 	nf = find_any_file(stp->st_stid.sc_file);
@@ -7867,11 +8217,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto put_file;
 	}
 
-	file_lock->fl_type = F_UNLCK;
-	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
-	file_lock->fl_pid = current->tgid;
-	file_lock->fl_file = nf->nf_file;
-	file_lock->fl_flags = FL_POSIX;
+	file_lock->c.flc_type = F_UNLCK;
+	file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
+	file_lock->c.flc_pid = current->tgid;
+	file_lock->c.flc_file = nf->nf_file;
+	file_lock->c.flc_flags = FL_POSIX;
 	file_lock->fl_lmops = &nfsd_posix_mng_ops;
 	file_lock->fl_start = locku->lu_offset;
 
@@ -7928,8 +8278,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
 		spin_lock(&flctx->flc_lock);
-		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
-			if (fl->fl_owner == (fl_owner_t)lowner) {
+		for_each_file_lock(fl, &flctx->flc_posix) {
+			if (fl->c.flc_owner == (fl_owner_t)lowner) {
 				status = true;
 				break;
 			}
@@ -7997,7 +8347,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		stp = list_first_entry(&lo->lo_owner.so_stateids,
 				       struct nfs4_ol_stateid,
 				       st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
+		unhash_lock_stateid(stp);
 		put_ol_stateid_locked(stp, &reaplist);
 	}
 	spin_unlock(&clp->cl_lock);
@@ -8290,7 +8640,7 @@ nfs4_state_shutdown_net(struct net *net)
 	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
-		WARN_ON(!unhash_delegation_locked(dp));
+		unhash_delegation_locked(dp, SC_STATUS_CLOSED);
 		list_add(&dp->dl_recall_lru, &reaplist);
 	}
 	spin_unlock(&state_lock);
@@ -8432,6 +8782,8 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
  * @rqstp: RPC transaction context
  * @inode: file to be checked for a conflict
+ * @modified: return true if file was modified
+ * @size: new size of file if modified is true
  *
  * This function is called when there is a conflict between a write
  * delegation and a change/size GETATTR from another client. The server
@@ -8440,27 +8792,30 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
  * delegation before replying to the GETATTR. See RFC 8881 section
  * 18.7.4.
  *
- * The current implementation does not support CB_GETATTR yet. However
- * this can avoid recalling the delegation could be added in follow up
- * work.
- *
  * Returns 0 if there is no conflict; otherwise an nfs_stat
  * code is returned.
  */
 __be32
-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
+nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
+				bool *modified, u64 *size)
 {
 	__be32 status;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct file_lock_context *ctx;
-	struct file_lock *fl;
+	struct file_lease *fl;
 	struct nfs4_delegation *dp;
+	struct iattr attrs;
+	struct nfs4_cb_fattr *ncf;
 
+	*modified = false;
 	ctx = locks_inode_context(inode);
 	if (!ctx)
 		return 0;
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_flags == FL_LAYOUT)
+	for_each_file_lock(fl, &ctx->flc_lease) {
+		unsigned char type = fl->c.flc_type;
+
+		if (fl->c.flc_flags == FL_LAYOUT)
 			continue;
 		if (fl->fl_lmops != &nfsd_lease_mng_ops) {
 			/*
@@ -8468,23 +8823,49 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode)
 			 * we are done; there isn't any write delegation
 			 * on this inode
 			 */
-			if (fl->fl_type == F_RDLCK)
+			if (type == F_RDLCK)
 				break;
 			goto break_lease;
 		}
-		if (fl->fl_type == F_WRLCK) {
-			dp = fl->fl_owner;
+		if (type == F_WRLCK) {
+			dp = fl->c.flc_owner;
 			if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
 				spin_unlock(&ctx->flc_lock);
 				return 0;
 			}
 break_lease:
+			nfsd_stats_wdeleg_getattr_inc(nn);
+			dp = fl->c.flc_owner;
+			ncf = &dp->dl_cb_fattr;
+			nfs4_cb_getattr(&dp->dl_cb_fattr);
 			spin_unlock(&ctx->flc_lock);
-			nfsd_stats_wdeleg_getattr_inc();
-			status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
-			if (status != nfserr_jukebox ||
-					!nfsd_wait_for_delegreturn(rqstp, inode))
-				return status;
+			wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY,
+					TASK_INTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT);
+			if (ncf->ncf_cb_status) {
+				/* Recall delegation only if client didn't respond */
+				status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+				if (status != nfserr_jukebox ||
+						!nfsd_wait_for_delegreturn(rqstp, inode))
+					return status;
+			}
+			if (!ncf->ncf_file_modified &&
+					(ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
+					ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
+				ncf->ncf_file_modified = true;
+			if (ncf->ncf_file_modified) {
+				/*
+				 * Per section 10.4.3 of RFC 8881, the server would
+				 * not update the file's metadata with the client's
+				 * modified size
+				 */
+				attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
+				attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
+				setattr_copy(&nop_mnt_idmap, inode, &attrs);
+				mark_inode_dirty(inode);
+				ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
+				*size = ncf->ncf_cur_fsize;
+				*modified = true;
+			}
 			return 0;
 		}
 		break;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c719c475a068..fac938f563ad 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3507,6 +3507,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		unsigned long	mask[2];
 	} u;
 	unsigned long bit;
+	bool file_modified = false;
+	u64 size = 0;
 
 	WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
 	WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -3533,7 +3535,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	}
 	args.size = 0;
 	if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
-		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry));
+		status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
+					&file_modified, &size);
 		if (status)
 			goto out;
 	}
@@ -3543,7 +3546,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 			  AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
-	args.size = args.stat.size;
+	if (file_modified)
+		args.size = size;
+	else
+		args.size = args.stat.size;
 
 	if (!(args.stat.result_mask & STATX_BTIME))
 		/* underlying FS does not offer btime so we can't share it */
@@ -5386,16 +5392,11 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs,
 
 	/*
 	 * If the cookie is larger than the maximum number we can fit
-	 * in either the buffer we just got back from vfs_listxattr, or,
-	 * XDR-encoded, in the return buffer, it's invalid.
+	 * in the buffer we just got back from vfs_listxattr, it's invalid.
 	 */
 	if (cookie > (listxattrs->lsxa_len) / (XATTR_USER_PREFIX_LEN + 2))
 		return nfserr_badcookie;
 
-	if (cookie > (listxattrs->lsxa_maxcount /
-		      (XDR_QUADLEN(XATTR_USER_PREFIX_LEN + 2) + 4)))
-		return nfserr_badcookie;
-
 	*offsetp = (u32)cookie;
 	return 0;
 }
@@ -5412,6 +5413,7 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
 	u64 cookie;
 	char *sp;
 	__be32 status, tmp;
+	__be64 wire_cookie;
 	__be32 *p;
 	u32 nuser;
 
@@ -5427,7 +5429,7 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
 	 */
 	cookie_offset = xdr->buf->len;
 	count_offset = cookie_offset + 8;
-	p = xdr_reserve_space(xdr, 12);
+	p = xdr_reserve_space(xdr, XDR_UNIT * 3);
 	if (!p) {
 		status = nfserr_resource;
 		goto out;
@@ -5438,7 +5440,8 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
 	sp = listxattrs->lsxa_buf;
 	nuser = 0;
 
-	xdrleft = listxattrs->lsxa_maxcount;
+	/* Bytes left is maxcount - 8 (cookie) - 4 (array count) */
+	xdrleft = listxattrs->lsxa_maxcount - XDR_UNIT * 3;
 
 	while (left > 0 && xdrleft > 0) {
 		slen = strlen(sp);
@@ -5451,7 +5454,8 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 		slen -= XATTR_USER_PREFIX_LEN;
 		xdrlen = 4 + ((slen + 3) & ~3);
-		if (xdrlen > xdrleft) {
+		/* Check if both entry and eof can fit in the XDR buffer */
+		if (xdrlen + XDR_UNIT > xdrleft) {
 			if (count == 0) {
 				/*
 				 * Can't even fit the first attribute name.
@@ -5503,7 +5507,8 @@ wreof:
 
 	cookie = offset + count;
 
-	write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &cookie, 8);
+	wire_cookie = cpu_to_be64(cookie);
+	write_bytes_to_xdr_buf(xdr->buf, cookie_offset, &wire_cookie, 8);
 	tmp = cpu_to_be32(count);
 	write_bytes_to_xdr_buf(xdr->buf, count_offset, &tmp, 4);
 out:
@@ -5727,27 +5732,24 @@ release:
 	rqstp->rq_next_page = xdr->page_ptr + 1;
 }
 
-/* 
- * Encode the reply stored in the stateowner reply cache 
- * 
- * XDR note: do not encode rp->rp_buflen: the buffer contains the
- * previously sent already encoded operation.
+/**
+ * nfsd4_encode_replay - encode a result stored in the stateowner reply cache
+ * @xdr: send buffer's XDR stream
+ * @op: operation being replayed
+ *
+ * @op->replay->rp_buf contains the previously-sent already-encoded result.
  */
-void
-nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
+void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 {
-	__be32 *p;
 	struct nfs4_replay *rp = op->replay;
 
-	p = xdr_reserve_space(xdr, 8 + rp->rp_buflen);
-	if (!p) {
-		WARN_ON_ONCE(1);
-		return;
-	}
-	*p++ = cpu_to_be32(op->opnum);
-	*p++ = rp->rp_status;  /* already xdr'ed */
+	trace_nfsd_stateowner_replay(op->opnum, rp);
 
-	p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen);
+	if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT)
+		return;
+	if (xdr_stream_encode_be32(xdr, rp->rp_status) != XDR_UNIT)
+		return;
+	xdr_stream_encode_opaque_fixed(xdr, rp->rp_buf, rp->rp_buflen);
 }
 
 void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 5c1a4a0aa605..ba9d326b3de6 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -166,8 +166,7 @@ nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp,
 
 int nfsd_drc_slab_create(void)
 {
-	drc_slab = kmem_cache_create("nfsd_drc",
-				sizeof(struct nfsd_cacherep), 0, 0, NULL);
+	drc_slab = KMEM_CACHE(nfsd_cacherep, 0);
 	return drc_slab ? 0: -ENOMEM;
 }
 
@@ -176,27 +175,6 @@ void nfsd_drc_slab_free(void)
 	kmem_cache_destroy(drc_slab);
 }
 
-/**
- * nfsd_net_reply_cache_init - per net namespace reply cache set-up
- * @nn: nfsd_net being initialized
- *
- * Returns zero on succes; otherwise a negative errno is returned.
- */
-int nfsd_net_reply_cache_init(struct nfsd_net *nn)
-{
-	return nfsd_percpu_counters_init(nn->counter, NFSD_NET_COUNTERS_NUM);
-}
-
-/**
- * nfsd_net_reply_cache_destroy - per net namespace reply cache tear-down
- * @nn: nfsd_net being freed
- *
- */
-void nfsd_net_reply_cache_destroy(struct nfsd_net *nn)
-{
-	nfsd_percpu_counters_destroy(nn->counter, NFSD_NET_COUNTERS_NUM);
-}
-
 int nfsd_reply_cache_init(struct nfsd_net *nn)
 {
 	unsigned int hashsize;
@@ -501,7 +479,7 @@ out:
 int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
 		      unsigned int len, struct nfsd_cacherep **cacherep)
 {
-	struct nfsd_net		*nn;
+	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfsd_cacherep	*rp, *found;
 	__wsum			csum;
 	struct nfsd_drc_bucket	*b;
@@ -510,7 +488,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
 	int rtn = RC_DOIT;
 
 	if (type == RC_NOCACHE) {
-		nfsd_stats_rc_nocache_inc();
+		nfsd_stats_rc_nocache_inc(nn);
 		goto out;
 	}
 
@@ -520,7 +498,6 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
 	 * Since the common case is a cache miss followed by an insert,
 	 * preallocate an entry.
 	 */
-	nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	rp = nfsd_cacherep_alloc(rqstp, csum, nn);
 	if (!rp)
 		goto out;
@@ -537,7 +514,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
 
 	nfsd_cacherep_dispose(&dispose);
 
-	nfsd_stats_rc_misses_inc();
+	nfsd_stats_rc_misses_inc(nn);
 	atomic_inc(&nn->num_drc_entries);
 	nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
 	goto out;
@@ -545,7 +522,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
 found_entry:
 	/* We found a matching entry which is either in progress or done. */
 	nfsd_reply_cache_free_locked(NULL, rp, nn);
-	nfsd_stats_rc_hits_inc();
+	nfsd_stats_rc_hits_inc(nn);
 	rtn = RC_DROPIT;
 	rp = found;
 
@@ -687,15 +664,15 @@ int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&nn->num_drc_entries));
 	seq_printf(m, "hash buckets:          %u\n", 1 << nn->maskbits);
 	seq_printf(m, "mem usage:             %lld\n",
-		   percpu_counter_sum_positive(&nn->counter[NFSD_NET_DRC_MEM_USAGE]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_DRC_MEM_USAGE]));
 	seq_printf(m, "cache hits:            %lld\n",
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]));
 	seq_printf(m, "cache misses:          %lld\n",
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]));
 	seq_printf(m, "not cached:            %lld\n",
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]));
 	seq_printf(m, "payload misses:        %lld\n",
-		   percpu_counter_sum_positive(&nn->counter[NFSD_NET_PAYLOAD_MISSES]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]));
 	seq_printf(m, "longest chain len:     %u\n", nn->longest_chain);
 	seq_printf(m, "cachesize at longest:  %u\n", nn->longest_chain_cachesize);
 	return 0;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index f206ca32e7f5..ecd18bffeebc 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -281,6 +281,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size)
 	 * 3.  Is that directory the root of an exported file system?
 	 */
 	error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb);
+	nfsd4_revoke_states(netns(file), path.dentry->d_sb);
 
 	path_put(&path);
 	return error;
@@ -1671,14 +1672,17 @@ static __net_init int nfsd_net_init(struct net *net)
 	retval = nfsd_idmap_init(net);
 	if (retval)
 		goto out_idmap_error;
-	retval = nfsd_net_reply_cache_init(nn);
+	retval = nfsd_stat_counters_init(nn);
 	if (retval)
 		goto out_repcache_error;
+	memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats));
+	nn->nfsd_svcstats.program = &nfsd_program;
 	nn->nfsd_versions = NULL;
 	nn->nfsd4_minorversions = NULL;
 	nfsd4_init_leases_net(nn);
 	get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
 	seqlock_init(&nn->writeverf_lock);
+	nfsd_proc_stat_init(net);
 
 	return 0;
 
@@ -1699,7 +1703,8 @@ static __net_exit void nfsd_net_exit(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	nfsd_net_reply_cache_destroy(nn);
+	nfsd_proc_stat_shutdown(net);
+	nfsd_stat_counters_destroy(nn);
 	nfsd_idmap_shutdown(net);
 	nfsd_export_shutdown(net);
 	nfsd_netns_free_versions(nn);
@@ -1722,12 +1727,9 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
-	retval = nfsd_stat_init();	/* Statistics */
-	if (retval)
-		goto out_free_pnfs;
 	retval = nfsd_drc_slab_create();
 	if (retval)
-		goto out_free_stat;
+		goto out_free_pnfs;
 	nfsd_lockd_init();	/* lockd->nfsd callbacks */
 	retval = create_proc_exports_entry();
 	if (retval)
@@ -1761,8 +1763,6 @@ out_free_exports:
 out_free_lockd:
 	nfsd_lockd_shutdown();
 	nfsd_drc_slab_free();
-out_free_stat:
-	nfsd_stat_shutdown();
 out_free_pnfs:
 	nfsd4_exit_pnfs();
 out_free_slabs:
@@ -1780,7 +1780,6 @@ static void __exit exit_nfsd(void)
 	nfsd_drc_slab_free();
 	remove_proc_entry("fs/nfs/exports", NULL);
 	remove_proc_entry("fs/nfs", NULL);
-	nfsd_stat_shutdown();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
 	nfsd4_exit_pnfs();
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 304e9728b929..16c5a05f340e 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -86,6 +86,7 @@ extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
 extern unsigned long		nfsd_drc_max_mem;
 extern unsigned long		nfsd_drc_mem_used;
+extern atomic_t			nfsd_th_cnt;		/* number of available threads */
 
 extern const struct seq_operations nfs_exports_op;
 
@@ -274,6 +275,7 @@ void		nfsd_lockd_shutdown(void);
 #define	nfserr_no_grace		cpu_to_be32(NFSERR_NO_GRACE)
 #define	nfserr_reclaim_bad	cpu_to_be32(NFSERR_RECLAIM_BAD)
 #define	nfserr_badname		cpu_to_be32(NFSERR_BADNAME)
+#define	nfserr_admin_revoked	cpu_to_be32(NFS4ERR_ADMIN_REVOKED)
 #define	nfserr_cb_path_down	cpu_to_be32(NFSERR_CB_PATH_DOWN)
 #define	nfserr_locked		cpu_to_be32(NFSERR_LOCKED)
 #define	nfserr_wrongsec		cpu_to_be32(NFSERR_WRONGSEC)
@@ -365,6 +367,7 @@ void		nfsd_lockd_shutdown(void);
 #define	NFSD_CLIENT_MAX_TRIM_PER_RUN	128
 #define	NFS4_CLIENTS_PER_GB		1024
 #define NFSD_DELEGRETURN_TIMEOUT	(HZ / 34)	/* 30ms */
+#define	NFSD_CB_GETATTR_TIMEOUT		NFSD_DELEGRETURN_TIMEOUT
 
 /*
  * The following attributes are currently not supported by the NFSv4 server:
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index dbfa0ac13564..40fecf7b224f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -327,6 +327,7 @@ out:
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 {
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct svc_export *exp = NULL;
 	struct dentry	*dentry;
 	__be32		error;
@@ -395,7 +396,7 @@ skip_pseudoflavor_check:
 out:
 	trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error);
 	if (error == nfserr_stale)
-		nfsd_stats_fh_stale_inc(exp);
+		nfsd_stats_fh_stale_inc(nn, exp);
 	return error;
 }
 
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a7315928a760..36370b957b63 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -103,7 +103,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp)
 		}
 	}
 
-	resp->status = nfsd_setattr(rqstp, fhp, &attrs, 0, (time64_t)0);
+	resp->status = nfsd_setattr(rqstp, fhp, &attrs, NULL);
 	if (resp->status != nfs_ok)
 		goto out;
 
@@ -390,8 +390,8 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 		 */
 		attr->ia_valid &= ATTR_SIZE;
 		if (attr->ia_valid)
-			resp->status = nfsd_setattr(rqstp, newfhp, &attrs, 0,
-						    (time64_t)0);
+			resp->status = nfsd_setattr(rqstp, newfhp, &attrs,
+						    NULL);
 	}
 
 out_unlock:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index a667802e08e7..c0d17b92b249 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -34,6 +34,7 @@
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
+atomic_t			nfsd_th_cnt = ATOMIC_INIT(0);
 extern struct svc_program	nfsd_program;
 static int			nfsd(void *vrqstp);
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
@@ -80,7 +81,6 @@ unsigned long	nfsd_drc_max_mem;
 unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-static struct svc_stat	nfsd_acl_svcstats;
 static const struct svc_version *nfsd_acl_version[] = {
 # if defined(CONFIG_NFSD_V2_ACL)
 	[2] = &nfsd_acl_version2,
@@ -99,15 +99,11 @@ static struct svc_program	nfsd_acl_program = {
 	.pg_vers		= nfsd_acl_version,
 	.pg_name		= "nfsacl",
 	.pg_class		= "nfsd",
-	.pg_stats		= &nfsd_acl_svcstats,
 	.pg_authenticate	= &svc_set_client,
 	.pg_init_request	= nfsd_acl_init_request,
 	.pg_rpcbind_set		= nfsd_acl_rpcbind_set,
 };
 
-static struct svc_stat	nfsd_acl_svcstats = {
-	.program	= &nfsd_acl_program,
-};
 #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
 
 static const struct svc_version *nfsd_version[] = {
@@ -132,7 +128,6 @@ struct svc_program		nfsd_program = {
 	.pg_vers		= nfsd_version,		/* version table */
 	.pg_name		= "nfsd",		/* program name */
 	.pg_class		= "nfsd",		/* authentication class */
-	.pg_stats		= &nfsd_svcstats,	/* version table */
 	.pg_authenticate	= &svc_set_client,	/* export authentication */
 	.pg_init_request	= nfsd_init_request,
 	.pg_rpcbind_set		= nfsd_rpcbind_set,
@@ -666,7 +661,8 @@ int nfsd_create_serv(struct net *net)
 	if (nfsd_max_blksize == 0)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions(nn);
-	serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, nfsd);
+	serv = svc_create_pooled(&nfsd_program, &nn->nfsd_svcstats,
+				 nfsd_max_blksize, nfsd);
 	if (serv == NULL)
 		return -ENOMEM;
 
@@ -929,7 +925,7 @@ nfsd(void *vrqstp)
 
 	current->fs->umask = 0;
 
-	atomic_inc(&nfsdstats.th_cnt);
+	atomic_inc(&nfsd_th_cnt);
 
 	set_freezable();
 
@@ -941,9 +937,11 @@ nfsd(void *vrqstp)
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
 		svc_recv(rqstp);
+
+		nfsd_file_net_dispose(nn);
 	}
 
-	atomic_dec(&nfsdstats.th_cnt);
+	atomic_dec(&nfsd_th_cnt);
 
 out:
 	/* Release the thread */
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
index de1e0dfed06a..925817f66917 100644
--- a/fs/nfsd/pnfs.h
+++ b/fs/nfsd/pnfs.h
@@ -37,7 +37,8 @@ struct nfsd4_layout_ops {
 	__be32 (*proc_layoutcommit)(struct inode *inode,
 			struct nfsd4_layoutcommit *lcp);
 
-	void (*fence_client)(struct nfs4_layout_stateid *ls);
+	void (*fence_client)(struct nfs4_layout_stateid *ls,
+			     struct nfsd_file *file);
 };
 
 extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
@@ -72,11 +73,13 @@ void nfsd4_setup_layout_type(struct svc_export *exp);
 void nfsd4_return_all_client_layouts(struct nfs4_client *);
 void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
 		struct nfs4_file *fp);
+void nfsd4_close_layout(struct nfs4_layout_stateid *ls);
 int nfsd4_init_pnfs(void);
 void nfsd4_exit_pnfs(void);
 #else
 struct nfs4_client;
 struct nfs4_file;
+struct nfs4_layout_stateid;
 
 static inline void nfsd4_setup_layout_type(struct svc_export *exp)
 {
@@ -89,6 +92,9 @@ static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
 		struct nfs4_file *fp)
 {
 }
+static inline void nfsd4_close_layout(struct nfs4_layout_stateid *ls)
+{
+}
 static inline void nfsd4_exit_pnfs(void)
 {
 }
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 41bdc913fa71..01c6f3445646 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -68,7 +68,7 @@ struct nfsd4_callback {
 	struct nfs4_client *cb_clp;
 	struct rpc_message cb_msg;
 	const struct nfsd4_callback_ops *cb_ops;
-	struct work_struct cb_work;
+	struct delayed_work cb_work;
 	int cb_seq_status;
 	int cb_status;
 	bool cb_need_restart;
@@ -88,17 +88,34 @@ struct nfsd4_callback_ops {
  */
 struct nfs4_stid {
 	refcount_t		sc_count;
-#define NFS4_OPEN_STID 1
-#define NFS4_LOCK_STID 2
-#define NFS4_DELEG_STID 4
-/* For an open stateid kept around *only* to process close replays: */
-#define NFS4_CLOSED_STID 8
+
+	/* A new stateid is added to the cl_stateids idr early before it
+	 * is fully initialised.  Its sc_type is then zero.  After
+	 * initialisation the sc_type it set under cl_lock, and then
+	 * never changes.
+	 */
+#define SC_TYPE_OPEN		BIT(0)
+#define SC_TYPE_LOCK		BIT(1)
+#define SC_TYPE_DELEG		BIT(2)
+#define SC_TYPE_LAYOUT		BIT(3)
+	unsigned short		sc_type;
+
+/* state_lock protects sc_status for delegation stateids.
+ * ->cl_lock protects sc_status for open and lock stateids.
+ * ->st_mutex also protect sc_status for open stateids.
+ * ->ls_lock protects sc_status for layout stateids.
+ */
+/*
+ * For an open stateid kept around *only* to process close replays.
+ * For deleg stateid, kept in idr until last reference is dropped.
+ */
+#define SC_STATUS_CLOSED	BIT(0)
 /* For a deleg stateid kept around only to process free_stateid's: */
-#define NFS4_REVOKED_DELEG_STID 16
-#define NFS4_CLOSED_DELEG_STID 32
-#define NFS4_LAYOUT_STID 64
+#define SC_STATUS_REVOKED	BIT(1)
+#define SC_STATUS_ADMIN_REVOKED	BIT(2)
+	unsigned short		sc_status;
+
 	struct list_head	sc_cp_list;
-	unsigned char		sc_type;
 	stateid_t		sc_stateid;
 	spinlock_t		sc_lock;
 	struct nfs4_client	*sc_client;
@@ -117,6 +134,24 @@ struct nfs4_cpntf_state {
 	time64_t		cpntf_time;	/* last time stateid used */
 };
 
+struct nfs4_cb_fattr {
+	struct nfsd4_callback ncf_getattr;
+	u32 ncf_cb_status;
+	u32 ncf_cb_bmap[1];
+
+	/* from CB_GETATTR reply */
+	u64 ncf_cb_change;
+	u64 ncf_cb_fsize;
+
+	unsigned long ncf_cb_flags;
+	bool ncf_file_modified;
+	u64 ncf_initial_cinfo;
+	u64 ncf_cur_fsize;
+};
+
+/* bits for ncf_cb_flags */
+#define	CB_GETATTR_BUSY		0
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -150,6 +185,9 @@ struct nfs4_delegation {
 	int			dl_retries;
 	struct nfsd4_callback	dl_recall;
 	bool			dl_recalled;
+
+	/* for CB_GETATTR */
+	struct nfs4_cb_fattr    dl_cb_fattr;
 };
 
 #define cb_to_delegation(cb) \
@@ -317,8 +355,9 @@ enum {
  * 0. If they are not renewed within a lease period, they become eligible for
  * destruction by the laundromat.
  *
- * These objects can also be destroyed prematurely by the fault injection code,
- * or if the client sends certain forms of SETCLIENTID or EXCHANGE_ID updates.
+ * These objects can also be destroyed if the client sends certain forms of
+ * SETCLIENTID or EXCHANGE_ID operations.
+ *
  * Care is taken *not* to do this however when the objects have an elevated
  * refcount.
  *
@@ -326,7 +365,7 @@ enum {
  *
  * o Each nfs4_clients is also hashed by name (the opaque quantity initially
  *   sent by the client to identify itself).
- * 	  
+ *
  * o cl_perclient list is used to ensure no dangling stateowner references
  *   when we expire the nfs4_client
  */
@@ -351,6 +390,7 @@ struct nfs4_client {
 	clientid_t		cl_clientid;	/* generated by server */
 	nfs4_verifier		cl_confirm;	/* generated by server */
 	u32			cl_minorversion;
+	atomic_t		cl_admin_revoked; /* count of admin-revoked states */
 	/* NFSv4.1 client implementation id: */
 	struct xdr_netobj	cl_nii_domain;
 	struct xdr_netobj	cl_nii_name;
@@ -640,6 +680,7 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_SEQUENCE,
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
 	NFSPROC4_CLNT_CB_RECALL_ANY,
+	NFSPROC4_CLNT_CB_GETATTR,
 };
 
 /* Returns true iff a is later than b: */
@@ -672,15 +713,15 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		stateid_t *stateid, int flags, struct nfsd_file **filp,
 		struct nfs4_stid **cstid);
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
-		     stateid_t *stateid, unsigned char typemask,
-		     struct nfs4_stid **s, struct nfsd_net *nn);
+			    stateid_t *stateid, unsigned short typemask,
+			    unsigned short statusmask,
+			    struct nfs4_stid **s, struct nfsd_net *nn);
 struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
 				  void (*sc_free)(struct nfs4_stid *));
 int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
 void nfs4_free_copy_state(struct nfsd4_copy *copy);
 struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
 			struct nfs4_stid *p_stid);
-void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
 void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
@@ -714,6 +755,14 @@ static inline void get_nfs4_file(struct nfs4_file *fi)
 }
 struct nfsd_file *find_any_file(struct nfs4_file *f);
 
+#ifdef CONFIG_NFSD_V4
+void nfsd4_revoke_states(struct net *net, struct super_block *sb);
+#else
+static inline void nfsd4_revoke_states(struct net *net, struct super_block *sb)
+{
+}
+#endif
+
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);
 
@@ -732,5 +781,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 }
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
-				struct inode *inode);
+		struct inode *inode, bool *file_modified, u64 *size);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 12d79f5d4eb1..be52fb1e928e 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -27,25 +27,22 @@
 
 #include "nfsd.h"
 
-struct nfsd_stats	nfsdstats;
-struct svc_stat		nfsd_svcstats = {
-	.program	= &nfsd_program,
-};
-
 static int nfsd_show(struct seq_file *seq, void *v)
 {
+	struct net *net = pde_data(file_inode(seq->file));
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	int i;
 
 	seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n",
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS]),
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES]),
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]),
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_FH_STALE]),
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_READ]),
-		   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE]));
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE]));
 
 	/* thread usage: */
-	seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt));
+	seq_printf(seq, "th %u 0", atomic_read(&nfsd_th_cnt));
 
 	/* deprecated thread usage histogram stats */
 	for (i = 0; i < 10; i++)
@@ -55,7 +52,7 @@ static int nfsd_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n");
 
 	/* show my rpc info */
-	svc_seq_show(seq, &nfsd_svcstats);
+	svc_seq_show(seq, &nn->nfsd_svcstats);
 
 #ifdef CONFIG_NFSD_V4
 	/* Show count for individual nfsv4 operations */
@@ -63,10 +60,10 @@ static int nfsd_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1);
 	for (i = 0; i <= LAST_NFS4_OP; i++) {
 		seq_printf(seq, " %lld",
-			   percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)]));
+			   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)]));
 	}
 	seq_printf(seq, "\nwdeleg_getattr %lld",
-		percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR]));
+		percpu_counter_sum_positive(&nn->counter[NFSD_STATS_WDELEG_GETATTR]));
 
 	seq_putc(seq, '\n');
 #endif
@@ -108,31 +105,24 @@ void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num)
 		percpu_counter_destroy(&counters[i]);
 }
 
-static int nfsd_stat_counters_init(void)
+int nfsd_stat_counters_init(struct nfsd_net *nn)
 {
-	return nfsd_percpu_counters_init(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM);
+	return nfsd_percpu_counters_init(nn->counter, NFSD_STATS_COUNTERS_NUM);
 }
 
-static void nfsd_stat_counters_destroy(void)
+void nfsd_stat_counters_destroy(struct nfsd_net *nn)
 {
-	nfsd_percpu_counters_destroy(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM);
+	nfsd_percpu_counters_destroy(nn->counter, NFSD_STATS_COUNTERS_NUM);
 }
 
-int nfsd_stat_init(void)
+void nfsd_proc_stat_init(struct net *net)
 {
-	int err;
-
-	err = nfsd_stat_counters_init();
-	if (err)
-		return err;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops);
-
-	return 0;
+	svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops);
 }
 
-void nfsd_stat_shutdown(void)
+void nfsd_proc_stat_shutdown(struct net *net)
 {
-	nfsd_stat_counters_destroy();
-	svc_proc_unregister(&init_net, "nfsd");
+	svc_proc_unregister(net, "nfsd");
 }
diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h
index 14f50c660b61..d2753e975dfd 100644
--- a/fs/nfsd/stats.h
+++ b/fs/nfsd/stats.h
@@ -10,94 +10,72 @@
 #include <uapi/linux/nfsd/stats.h>
 #include <linux/percpu_counter.h>
 
-
-enum {
-	NFSD_STATS_RC_HITS,		/* repcache hits */
-	NFSD_STATS_RC_MISSES,		/* repcache misses */
-	NFSD_STATS_RC_NOCACHE,		/* uncached reqs */
-	NFSD_STATS_FH_STALE,		/* FH stale error */
-	NFSD_STATS_IO_READ,		/* bytes returned to read requests */
-	NFSD_STATS_IO_WRITE,		/* bytes passed in write requests */
-#ifdef CONFIG_NFSD_V4
-	NFSD_STATS_FIRST_NFS4_OP,	/* count of individual nfsv4 operations */
-	NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP,
-#define NFSD_STATS_NFS4_OP(op)	(NFSD_STATS_FIRST_NFS4_OP + (op))
-	NFSD_STATS_WDELEG_GETATTR,	/* count of getattr conflict with wdeleg */
-#endif
-	NFSD_STATS_COUNTERS_NUM
-};
-
-struct nfsd_stats {
-	struct percpu_counter	counter[NFSD_STATS_COUNTERS_NUM];
-
-	atomic_t	th_cnt;		/* number of available threads */
-};
-
-extern struct nfsd_stats	nfsdstats;
-
-extern struct svc_stat		nfsd_svcstats;
-
 int nfsd_percpu_counters_init(struct percpu_counter *counters, int num);
 void nfsd_percpu_counters_reset(struct percpu_counter *counters, int num);
 void nfsd_percpu_counters_destroy(struct percpu_counter *counters, int num);
-int nfsd_stat_init(void);
-void nfsd_stat_shutdown(void);
+int nfsd_stat_counters_init(struct nfsd_net *nn);
+void nfsd_stat_counters_destroy(struct nfsd_net *nn);
+void nfsd_proc_stat_init(struct net *net);
+void nfsd_proc_stat_shutdown(struct net *net);
 
-static inline void nfsd_stats_rc_hits_inc(void)
+static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn)
 {
-	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_HITS]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_HITS]);
 }
 
-static inline void nfsd_stats_rc_misses_inc(void)
+static inline void nfsd_stats_rc_misses_inc(struct nfsd_net *nn)
 {
-	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_MISSES]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_MISSES]);
 }
 
-static inline void nfsd_stats_rc_nocache_inc(void)
+static inline void nfsd_stats_rc_nocache_inc(struct nfsd_net *nn)
 {
-	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_NOCACHE]);
 }
 
-static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp)
+static inline void nfsd_stats_fh_stale_inc(struct nfsd_net *nn,
+					   struct svc_export *exp)
 {
-	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_FH_STALE]);
 	if (exp && exp->ex_stats)
 		percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]);
 }
 
-static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount)
+static inline void nfsd_stats_io_read_add(struct nfsd_net *nn,
+					  struct svc_export *exp, s64 amount)
 {
-	percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount);
+	percpu_counter_add(&nn->counter[NFSD_STATS_IO_READ], amount);
 	if (exp && exp->ex_stats)
 		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount);
 }
 
-static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount)
+static inline void nfsd_stats_io_write_add(struct nfsd_net *nn,
+					   struct svc_export *exp, s64 amount)
 {
-	percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount);
+	percpu_counter_add(&nn->counter[NFSD_STATS_IO_WRITE], amount);
 	if (exp && exp->ex_stats)
 		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount);
 }
 
 static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn)
 {
-	percpu_counter_inc(&nn->counter[NFSD_NET_PAYLOAD_MISSES]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]);
 }
 
 static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount)
 {
-	percpu_counter_add(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount);
+	percpu_counter_add(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount);
 }
 
 static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount)
 {
-	percpu_counter_sub(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount);
+	percpu_counter_sub(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount);
 }
 
 #ifdef CONFIG_NFSD_V4
-static inline void nfsd_stats_wdeleg_getattr_inc(void)
+static inline void nfsd_stats_wdeleg_getattr_inc(struct nfsd_net *nn)
 {
-	percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR]);
+	percpu_counter_inc(&nn->counter[NFSD_STATS_WDELEG_GETATTR]);
 }
 #endif
 #endif /* _NFSD_STATS_H */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index d1e8cf079b0f..e545e92c4408 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -9,8 +9,10 @@
 #define _NFSD_TRACE_H
 
 #include <linux/tracepoint.h>
+#include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprt.h>
 #include <trace/misc/nfs.h>
+#include <trace/misc/sunrpc.h>
 
 #include "export.h"
 #include "nfsfh.h"
@@ -641,23 +643,18 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \
 DEFINE_STATESEQID_EVENT(preprocess);
 DEFINE_STATESEQID_EVENT(open_confirm);
 
-TRACE_DEFINE_ENUM(NFS4_OPEN_STID);
-TRACE_DEFINE_ENUM(NFS4_LOCK_STID);
-TRACE_DEFINE_ENUM(NFS4_DELEG_STID);
-TRACE_DEFINE_ENUM(NFS4_CLOSED_STID);
-TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID);
-TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID);
-TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID);
-
 #define show_stid_type(x)						\
 	__print_flags(x, "|",						\
-		{ NFS4_OPEN_STID,		"OPEN" },		\
-		{ NFS4_LOCK_STID,		"LOCK" },		\
-		{ NFS4_DELEG_STID,		"DELEG" },		\
-		{ NFS4_CLOSED_STID,		"CLOSED" },		\
-		{ NFS4_REVOKED_DELEG_STID,	"REVOKED" },		\
-		{ NFS4_CLOSED_DELEG_STID,	"CLOSED_DELEG" },	\
-		{ NFS4_LAYOUT_STID,		"LAYOUT" })
+		{ SC_TYPE_OPEN,		"OPEN" },		\
+		{ SC_TYPE_LOCK,		"LOCK" },		\
+		{ SC_TYPE_DELEG,		"DELEG" },		\
+		{ SC_TYPE_LAYOUT,		"LAYOUT" })
+
+#define show_stid_status(x)						\
+	__print_flags(x, "|",						\
+		{ SC_STATUS_CLOSED,		"CLOSED" },		\
+		{ SC_STATUS_REVOKED,		"REVOKED" },		\
+		{ SC_STATUS_ADMIN_REVOKED,	"ADMIN_REVOKED" })
 
 DECLARE_EVENT_CLASS(nfsd_stid_class,
 	TP_PROTO(
@@ -666,6 +663,7 @@ DECLARE_EVENT_CLASS(nfsd_stid_class,
 	TP_ARGS(stid),
 	TP_STRUCT__entry(
 		__field(unsigned long, sc_type)
+		__field(unsigned long, sc_status)
 		__field(int, sc_count)
 		__field(u32, cl_boot)
 		__field(u32, cl_id)
@@ -676,16 +674,18 @@ DECLARE_EVENT_CLASS(nfsd_stid_class,
 		const stateid_t *stp = &stid->sc_stateid;
 
 		__entry->sc_type = stid->sc_type;
+		__entry->sc_status = stid->sc_status;
 		__entry->sc_count = refcount_read(&stid->sc_count);
 		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
 		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
 		__entry->si_id = stp->si_opaque.so_id;
 		__entry->si_generation = stp->si_generation;
 	),
-	TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s",
+	TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s state=%s",
 		__entry->cl_boot, __entry->cl_id,
 		__entry->si_id, __entry->si_generation,
-		__entry->sc_count, show_stid_type(__entry->sc_type)
+		__entry->sc_count, show_stid_type(__entry->sc_type),
+		show_stid_status(__entry->sc_status)
 	)
 );
 
@@ -696,6 +696,59 @@ DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name,			\
 
 DEFINE_STID_EVENT(revoke);
 
+TRACE_EVENT(nfsd_stateowner_replay,
+	TP_PROTO(
+		u32 opnum,
+		const struct nfs4_replay *rp
+	),
+	TP_ARGS(opnum, rp),
+	TP_STRUCT__entry(
+		__field(unsigned long, status)
+		__field(u32, opnum)
+	),
+	TP_fast_assign(
+		__entry->status = be32_to_cpu(rp->rp_status);
+		__entry->opnum = opnum;
+	),
+	TP_printk("opnum=%u status=%lu",
+		__entry->opnum, __entry->status)
+);
+
+TRACE_EVENT_CONDITION(nfsd_seq4_status,
+	TP_PROTO(
+		const struct svc_rqst *rqstp,
+		const struct nfsd4_sequence *sequence
+	),
+	TP_ARGS(rqstp, sequence),
+	TP_CONDITION(sequence->status_flags),
+	TP_STRUCT__entry(
+		__field(unsigned int, netns_ino)
+		__field(u32, xid)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, seqno)
+		__field(u32, reserved)
+		__field(unsigned long, status_flags)
+	),
+	TP_fast_assign(
+		const struct nfsd4_sessionid *sid =
+			(struct nfsd4_sessionid *)&sequence->sessionid;
+
+		__entry->netns_ino = SVC_NET(rqstp)->ns.inum;
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->cl_boot = sid->clientid.cl_boot;
+		__entry->cl_id = sid->clientid.cl_id;
+		__entry->seqno = sid->sequence;
+		__entry->reserved = sid->reserved;
+		__entry->status_flags = sequence->status_flags;
+	),
+	TP_printk("xid=0x%08x sessionid=%08x:%08x:%08x:%08x status_flags=%s",
+		__entry->xid, __entry->cl_boot, __entry->cl_id,
+		__entry->seqno, __entry->reserved,
+		show_nfs4_seq4_status(__entry->status_flags)
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_clientid_class,
 	TP_PROTO(const clientid_t *clid),
 	TP_ARGS(clid),
@@ -1334,7 +1387,8 @@ DEFINE_EVENT(nfsd_cb_class, nfsd_cb_##name,		\
 	TP_PROTO(const struct nfs4_client *clp),	\
 	TP_ARGS(clp))
 
-DEFINE_NFSD_CB_EVENT(state);
+DEFINE_NFSD_CB_EVENT(start);
+DEFINE_NFSD_CB_EVENT(new_state);
 DEFINE_NFSD_CB_EVENT(probe);
 DEFINE_NFSD_CB_EVENT(lost);
 DEFINE_NFSD_CB_EVENT(shutdown);
@@ -1405,6 +1459,128 @@ TRACE_EVENT(nfsd_cb_setup_err,
 		__entry->error)
 );
 
+DECLARE_EVENT_CLASS(nfsd_cb_lifetime_class,
+	TP_PROTO(
+		const struct nfs4_client *clp,
+		const struct nfsd4_callback *cb
+	),
+	TP_ARGS(clp, cb),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(const void *, cb)
+		__field(bool, need_restart)
+		__sockaddr(addr, clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = clp->cl_clientid.cl_boot;
+		__entry->cl_id = clp->cl_clientid.cl_id;
+		__entry->cb = cb;
+		__entry->need_restart = cb->cb_need_restart;
+		__assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr,
+				  clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_printk("addr=%pISpc client %08x:%08x cb=%p%s",
+		__get_sockaddr(addr), __entry->cl_boot, __entry->cl_id,
+		__entry->cb, __entry->need_restart ?
+			" (need restart)" : " (first try)"
+	)
+);
+
+#define DEFINE_NFSD_CB_LIFETIME_EVENT(name)		\
+DEFINE_EVENT(nfsd_cb_lifetime_class, nfsd_cb_##name,	\
+	TP_PROTO(					\
+		const struct nfs4_client *clp,		\
+		const struct nfsd4_callback *cb		\
+	),						\
+	TP_ARGS(clp, cb))
+
+DEFINE_NFSD_CB_LIFETIME_EVENT(queue);
+DEFINE_NFSD_CB_LIFETIME_EVENT(destroy);
+DEFINE_NFSD_CB_LIFETIME_EVENT(restart);
+DEFINE_NFSD_CB_LIFETIME_EVENT(bc_update);
+DEFINE_NFSD_CB_LIFETIME_EVENT(bc_shutdown);
+
+TRACE_EVENT(nfsd_cb_seq_status,
+	TP_PROTO(
+		const struct rpc_task *task,
+		const struct nfsd4_callback *cb
+	),
+	TP_ARGS(task, cb),
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, seqno)
+		__field(u32, reserved)
+		__field(int, tk_status)
+		__field(int, seq_status)
+	),
+	TP_fast_assign(
+		const struct nfs4_client *clp = cb->cb_clp;
+		const struct nfsd4_session *session = clp->cl_cb_session;
+		const struct nfsd4_sessionid *sid =
+			(struct nfsd4_sessionid *)&session->se_sessionid;
+
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client ?
+				     task->tk_client->cl_clid : -1;
+		__entry->cl_boot = sid->clientid.cl_boot;
+		__entry->cl_id = sid->clientid.cl_id;
+		__entry->seqno = sid->sequence;
+		__entry->reserved = sid->reserved;
+		__entry->tk_status = task->tk_status;
+		__entry->seq_status = cb->cb_seq_status;
+	),
+	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
+		" sessionid=%08x:%08x:%08x:%08x tk_status=%d seq_status=%d\n",
+		__entry->task_id, __entry->client_id,
+		__entry->cl_boot, __entry->cl_id,
+		__entry->seqno, __entry->reserved,
+		__entry->tk_status, __entry->seq_status
+	)
+);
+
+TRACE_EVENT(nfsd_cb_free_slot,
+	TP_PROTO(
+		const struct rpc_task *task,
+		const struct nfsd4_callback *cb
+	),
+	TP_ARGS(task, cb),
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, seqno)
+		__field(u32, reserved)
+		__field(u32, slot_seqno)
+	),
+	TP_fast_assign(
+		const struct nfs4_client *clp = cb->cb_clp;
+		const struct nfsd4_session *session = clp->cl_cb_session;
+		const struct nfsd4_sessionid *sid =
+			(struct nfsd4_sessionid *)&session->se_sessionid;
+
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client ?
+				     task->tk_client->cl_clid : -1;
+		__entry->cl_boot = sid->clientid.cl_boot;
+		__entry->cl_id = sid->clientid.cl_id;
+		__entry->seqno = sid->sequence;
+		__entry->reserved = sid->reserved;
+		__entry->slot_seqno = session->se_cb_seq_nr;
+	),
+	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER
+		" sessionid=%08x:%08x:%08x:%08x new slot seqno=%u\n",
+		__entry->task_id, __entry->client_id,
+		__entry->cl_boot, __entry->cl_id,
+		__entry->seqno, __entry->reserved,
+		__entry->slot_seqno
+	)
+);
+
 TRACE_EVENT_CONDITION(nfsd_cb_recall,
 	TP_PROTO(
 		const struct nfs4_stid *stid
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b7c7a9273ea0..6a4c506038e0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -476,7 +476,6 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
  * @rqstp: controlling RPC transaction
  * @fhp: filehandle of target
  * @attr: attributes to set
- * @check_guard: set to 1 if guardtime is a valid timestamp
  * @guardtime: do not act if ctime.tv_sec does not match this timestamp
  *
  * This call may adjust the contents of @attr (in particular, this
@@ -488,8 +487,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
  */
 __be32
 nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
-	     struct nfsd_attrs *attr,
-	     int check_guard, time64_t guardtime)
+	     struct nfsd_attrs *attr, const struct timespec64 *guardtime)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -497,7 +495,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int		accmode = NFSD_MAY_SATTR;
 	umode_t		ftype = 0;
 	__be32		err;
-	int		host_err;
+	int		host_err = 0;
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 	int		retries;
@@ -538,9 +536,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	nfsd_sanitize_attrs(inode, iap);
 
-	if (check_guard && guardtime != inode_get_ctime_sec(inode))
-		return nfserr_notsync;
-
 	/*
 	 * The size case is special, it changes the file in addition to the
 	 * attributes, and file systems don't expect it to be mixed with
@@ -555,6 +550,19 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	}
 
 	inode_lock(inode);
+	err = fh_fill_pre_attrs(fhp);
+	if (err)
+		goto out_unlock;
+
+	if (guardtime) {
+		struct timespec64 ctime = inode_get_ctime(inode);
+		if ((u32)guardtime->tv_sec != (u32)ctime.tv_sec ||
+		    guardtime->tv_nsec != ctime.tv_nsec) {
+			err = nfserr_notsync;
+			goto out_fill_attrs;
+		}
+	}
+
 	for (retries = 1;;) {
 		struct iattr attrs;
 
@@ -582,13 +590,23 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		attr->na_aclerr = set_posix_acl(&nop_mnt_idmap,
 						dentry, ACL_TYPE_DEFAULT,
 						attr->na_dpacl);
+out_fill_attrs:
+	/*
+	 * RFC 1813 Section 3.3.2 does not mandate that an NFS server
+	 * returns wcc_data for SETATTR. Some client implementations
+	 * depend on receiving wcc_data, however, to sort out partial
+	 * updates (eg., the client requested that size and mode be
+	 * modified, but the server changed only the file mode).
+	 */
+	fh_fill_post_attrs(fhp);
+out_unlock:
 	inode_unlock(inode);
 	if (size_change)
 		put_write_access(inode);
 out:
 	if (!host_err)
 		host_err = commit_metadata(fhp);
-	return nfserrno(host_err);
+	return err != 0 ? err : nfserrno(host_err);
 }
 
 #if defined(CONFIG_NFSD_V4)
@@ -1002,7 +1020,9 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			       unsigned long *count, u32 *eof, ssize_t host_err)
 {
 	if (host_err >= 0) {
-		nfsd_stats_io_read_add(fhp->fh_export, host_err);
+		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+		nfsd_stats_io_read_add(nn, fhp->fh_export, host_err);
 		*eof = nfsd_eof_on_read(file, offset, host_err, *count);
 		*count = host_err;
 		fsnotify_access(file);
@@ -1185,7 +1205,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 		goto out_nfserr;
 	}
 	*cnt = host_err;
-	nfsd_stats_io_write_add(exp, *cnt);
+	nfsd_stats_io_write_add(nn, exp, *cnt);
 	fsnotify_modify(file);
 	host_err = filemap_check_wb_err(file->f_mapping, since);
 	if (host_err < 0)
@@ -1404,7 +1424,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 * if the attributes have not changed.
 	 */
 	if (iap->ia_valid)
-		status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0);
+		status = nfsd_setattr(rqstp, resfhp, attrs, NULL);
 	else
 		status = nfserrno(commit_metadata(resfhp));
 
@@ -1906,10 +1926,10 @@ out_unlock:
 	fh_drop_write(ffhp);
 
 	/*
-	 * If the target dentry has cached open files, then we need to try to
-	 * close them prior to doing the rename. Flushing delayed fput
-	 * shouldn't be done with locks held however, so we delay it until this
-	 * point and then reattempt the whole shebang.
+	 * If the target dentry has cached open files, then we need to
+	 * try to close them prior to doing the rename.  Final fput
+	 * shouldn't be done with locks held however, so we delay it
+	 * until this point and then reattempt the whole shebang.
 	 */
 	if (close_cached) {
 		close_cached = false;
@@ -2177,11 +2197,43 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
 	if (err == nfserr_eof || err == nfserr_toosmall)
 		err = nfs_ok; /* can still be found in ->err */
 out_close:
-	fput(file);
+	nfsd_filp_close(file);
 out:
 	return err;
 }
 
+/**
+ * nfsd_filp_close: close a file synchronously
+ * @fp: the file to close
+ *
+ * nfsd_filp_close() is similar in behaviour to filp_close().
+ * The difference is that if this is the final close on the
+ * file, the that finalisation happens immediately, rather then
+ * being handed over to a work_queue, as it the case for
+ * filp_close().
+ * When a user-space process closes a file (even when using
+ * filp_close() the finalisation happens before returning to
+ * userspace, so it is effectively synchronous.  When a kernel thread
+ * uses file_close(), on the other hand, the handling is completely
+ * asynchronous.  This means that any cost imposed by that finalisation
+ * is not imposed on the nfsd thread, and nfsd could potentually
+ * close files more quickly than the work queue finalises the close,
+ * which would lead to unbounded growth in the queue.
+ *
+ * In some contexts is it not safe to synchronously wait for
+ * close finalisation (see comment for __fput_sync()), but nfsd
+ * does not match those contexts.  In partcilarly it does not, at the
+ * time that this function is called, hold and locks and no finalisation
+ * of any file, socket, or device driver would have any cause to wait
+ * for nfsd to make progress.
+ */
+void nfsd_filp_close(struct file *fp)
+{
+	get_file(fp);
+	filp_close(fp, NULL);
+	__fput_sync(fp);
+}
+
 /*
  * Get file system stats
  * N.B. After this call fhp needs an fh_put
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 702fbc4483bf..c60fdb6200fd 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -69,7 +69,7 @@ __be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
 				const char *, unsigned int,
 				struct svc_export **, struct dentry **);
 __be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
-				struct nfsd_attrs *, int, time64_t);
+			     struct nfsd_attrs *, const struct timespec64 *);
 int nfsd_mountpoint(struct dentry *, struct svc_export *);
 #ifdef CONFIG_NFSD_V4
 __be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
@@ -148,6 +148,8 @@ __be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
 				struct dentry *, int);
 
+void		nfsd_filp_close(struct file *fp);
+
 static inline int fh_want_write(struct svc_fh *fh)
 {
 	int ret;
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 03fe4e21306c..522067b7fd75 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -14,7 +14,7 @@ struct nfsd3_sattrargs {
 	struct svc_fh		fh;
 	struct iattr		attrs;
 	int			check_guard;
-	time64_t		guardtime;
+	struct timespec64	guardtime;
 };
 
 struct nfsd3_diropargs {
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index 0d39af1b00a0..e8b00309c449 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -54,3 +54,21 @@
 #define NFS4_dec_cb_recall_any_sz	(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
+
+/*
+ * 1: CB_GETATTR opcode (32-bit)
+ * N: file_handle
+ * 1: number of entry in attribute array (32-bit)
+ * 1: entry 0 in attribute array (32-bit)
+ */
+#define NFS4_enc_cb_getattr_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + enc_nfs4_fh_sz + 1 + 1)
+/*
+ * 4: fattr_bitmap_maxsz
+ * 1: attribute array len
+ * 2: change attr (64-bit)
+ * 2: size (64-bit)
+ */
+#define NFS4_dec_cb_getattr_sz		(cb_compound_dec_hdr_sz  +      \
+			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz)
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index bec33b89a075..0e3fc5ba33c7 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	folio_wait_stable(folio);
+	/*
+	 * Since checksumming including data blocks is performed to determine
+	 * the validity of the log to be written and used for recovery, it is
+	 * necessary to wait for writeback to finish here, regardless of the
+	 * stable write requirement of the backing device.
+	 */
+	folio_wait_writeback(folio);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return vmf_fs_error(ret);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0955b657938f..a9b8d77c8c1d 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
 
 static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 				     struct nilfs_recovery_block *rb,
-				     struct page *page)
+				     loff_t pos, struct page *page)
 {
 	struct buffer_head *bh_org;
+	size_t from = pos & ~PAGE_MASK;
 	void *kaddr;
 
 	bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
@@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 		return -EIO;
 
 	kaddr = kmap_atomic(page);
-	memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
+	memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
 	kunmap_atomic(kaddr);
 	brelse(bh_org);
 	return 0;
@@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 			goto failed_inode;
 		}
 
-		err = nilfs_recovery_copy_block(nilfs, rb, page);
+		err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
 		if (unlikely(err))
 			goto failed_page;
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 2590a0860eab..2bfb08052d39 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			set_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_folio != bd_folio) {
 					folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 				}
 				break;
 			}
+			set_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_begin_folio_io(fs_folio);
 				fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
 				clear_buffer_uptodate(bh);
 				if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				}
 				break;
 			}
+			clear_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, err);
 				fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
 				 BIT(BH_NILFS_Redirected));
 
-			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh == segbuf->sb_super_root) {
+				set_buffer_uptodate(bh);
+				clear_buffer_dirty(bh);
 				if (bh->b_folio != bd_folio) {
 					folio_end_writeback(bd_folio);
 					bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 				update_sr = true;
 				break;
 			}
+			set_mask_bits(&bh->b_state, clear_bits, set_bits);
 			if (bh->b_folio != fs_folio) {
 				nilfs_end_folio_io(fs_folio, 0);
 				fs_folio = bh->b_folio;
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 34e1e3e36733..7aaafb5cb9fc 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -27,26 +27,17 @@ static const struct file_operations ns_file_operations = {
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	return dynamic_dname(buffer, buflen, "%s:[%lu]",
 		ns_ops->name, inode->i_ino);
 }
 
-static void ns_prune_dentry(struct dentry *dentry)
-{
-	struct inode *inode = d_inode(dentry);
-	if (inode) {
-		struct ns_common *ns = inode->i_private;
-		atomic_long_set(&ns->stashed, 0);
-	}
-}
-
-const struct dentry_operations ns_dentry_operations =
-{
-	.d_prune	= ns_prune_dentry,
+const struct dentry_operations ns_dentry_operations = {
 	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
+	.d_prune	= stashed_dentry_prune,
 };
 
 static void nsfs_evict(struct inode *inode)
@@ -56,67 +47,16 @@ static void nsfs_evict(struct inode *inode)
 	ns->ops->put(ns);
 }
 
-static int __ns_get_path(struct path *path, struct ns_common *ns)
-{
-	struct vfsmount *mnt = nsfs_mnt;
-	struct dentry *dentry;
-	struct inode *inode;
-	unsigned long d;
-
-	rcu_read_lock();
-	d = atomic_long_read(&ns->stashed);
-	if (!d)
-		goto slow;
-	dentry = (struct dentry *)d;
-	if (!lockref_get_not_dead(&dentry->d_lockref))
-		goto slow;
-	rcu_read_unlock();
-	ns->ops->put(ns);
-got_it:
-	path->mnt = mntget(mnt);
-	path->dentry = dentry;
-	return 0;
-slow:
-	rcu_read_unlock();
-	inode = new_inode_pseudo(mnt->mnt_sb);
-	if (!inode) {
-		ns->ops->put(ns);
-		return -ENOMEM;
-	}
-	inode->i_ino = ns->inum;
-	simple_inode_init_ts(inode);
-	inode->i_flags |= S_IMMUTABLE;
-	inode->i_mode = S_IFREG | S_IRUGO;
-	inode->i_fop = &ns_file_operations;
-	inode->i_private = ns;
-
-	dentry = d_make_root(inode);	/* not the normal use, but... */
-	if (!dentry)
-		return -ENOMEM;
-	dentry->d_fsdata = (void *)ns->ops;
-	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
-	if (d) {
-		d_delete(dentry);	/* make sure ->d_prune() does nothing */
-		dput(dentry);
-		cpu_relax();
-		return -EAGAIN;
-	}
-	goto got_it;
-}
-
 int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
 		     void *private_data)
 {
-	int ret;
+	struct ns_common *ns;
 
-	do {
-		struct ns_common *ns = ns_get_cb(private_data);
-		if (!ns)
-			return -ENOENT;
-		ret = __ns_get_path(path, ns);
-	} while (ret == -EAGAIN);
+	ns = ns_get_cb(private_data);
+	if (!ns)
+		return -ENOENT;
 
-	return ret;
+	return path_from_stashed(&ns->stashed, ns->inum, nsfs_mnt, ns, path);
 }
 
 struct ns_get_path_task_args {
@@ -146,6 +86,7 @@ int open_related_ns(struct ns_common *ns,
 		   struct ns_common *(*get_ns)(struct ns_common *ns))
 {
 	struct path path = {};
+	struct ns_common *relative;
 	struct file *f;
 	int err;
 	int fd;
@@ -154,19 +95,15 @@ int open_related_ns(struct ns_common *ns,
 	if (fd < 0)
 		return fd;
 
-	do {
-		struct ns_common *relative;
-
-		relative = get_ns(ns);
-		if (IS_ERR(relative)) {
-			put_unused_fd(fd);
-			return PTR_ERR(relative);
-		}
-
-		err = __ns_get_path(&path, relative);
-	} while (err == -EAGAIN);
+	relative = get_ns(ns);
+	if (IS_ERR(relative)) {
+		put_unused_fd(fd);
+		return PTR_ERR(relative);
+	}
 
-	if (err) {
+	err = path_from_stashed(&relative->stashed, relative->inum, nsfs_mnt,
+				relative, &path);
+	if (err < 0) {
 		put_unused_fd(fd);
 		return err;
 	}
@@ -249,7 +186,8 @@ bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino)
 static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
-	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
+	const struct ns_common *ns = inode->i_private;
+	const struct proc_ns_operations *ns_ops = ns->ops;
 
 	seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
 	return 0;
@@ -261,6 +199,24 @@ static const struct super_operations nsfs_ops = {
 	.show_path = nsfs_show_path,
 };
 
+static void nsfs_init_inode(struct inode *inode, void *data)
+{
+	inode->i_private = data;
+	inode->i_mode |= S_IRUGO;
+	inode->i_fop = &ns_file_operations;
+}
+
+static void nsfs_put_data(void *data)
+{
+	struct ns_common *ns = data;
+	ns->ops->put(ns);
+}
+
+static const struct stashed_operations nsfs_stashed_ops = {
+	.init_inode = nsfs_init_inode,
+	.put_data = nsfs_put_data,
+};
+
 static int nsfs_init_fs_context(struct fs_context *fc)
 {
 	struct pseudo_fs_context *ctx = init_pseudo(fc, NSFS_MAGIC);
@@ -268,6 +224,7 @@ static int nsfs_init_fs_context(struct fs_context *fc)
 		return -ENOMEM;
 	ctx->ops = &nsfs_ops;
 	ctx->dops = &ns_dentry_operations;
+	fc->s_fs_info = (void *)&nsfs_stashed_ops;
 	return 0;
 }
 
diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig
deleted file mode 100644
index 7b2509741735..000000000000
--- a/fs/ntfs/Kconfig
+++ /dev/null
@@ -1,81 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config NTFS_FS
-	tristate "NTFS file system support"
-	select BUFFER_HEAD
-	select NLS
-	help
-	  NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003.
-
-	  Saying Y or M here enables read support.  There is partial, but
-	  safe, write support available.  For write support you must also
-	  say Y to "NTFS write support" below.
-
-	  There are also a number of user-space tools available, called
-	  ntfsprogs.  These include ntfsundelete and ntfsresize, that work
-	  without NTFS support enabled in the kernel.
-
-	  This is a rewrite from scratch of Linux NTFS support and replaced
-	  the old NTFS code starting with Linux 2.5.11.  A backport to
-	  the Linux 2.4 kernel series is separately available as a patch
-	  from the project web site.
-
-	  For more information see <file:Documentation/filesystems/ntfs.rst>
-	  and <http://www.linux-ntfs.org/>.
-
-	  To compile this file system support as a module, choose M here: the
-	  module will be called ntfs.
-
-	  If you are not using Windows NT, 2000, XP or 2003 in addition to
-	  Linux on your computer it is safe to say N.
-
-config NTFS_DEBUG
-	bool "NTFS debugging support"
-	depends on NTFS_FS
-	help
-	  If you are experiencing any problems with the NTFS file system, say
-	  Y here.  This will result in additional consistency checks to be
-	  performed by the driver as well as additional debugging messages to
-	  be written to the system log.  Note that debugging messages are
-	  disabled by default.  To enable them, supply the option debug_msgs=1
-	  at the kernel command line when booting the kernel or as an option
-	  to insmod when loading the ntfs module.  Once the driver is active,
-	  you can enable debugging messages by doing (as root):
-	  echo 1 > /proc/sys/fs/ntfs-debug
-	  Replacing the "1" with "0" would disable debug messages.
-
-	  If you leave debugging messages disabled, this results in little
-	  overhead, but enabling debug messages results in very significant
-	  slowdown of the system.
-
-	  When reporting bugs, please try to have available a full dump of
-	  debugging messages while the misbehaviour was occurring.
-
-config NTFS_RW
-	bool "NTFS write support"
-	depends on NTFS_FS
-	depends on PAGE_SIZE_LESS_THAN_64KB
-	help
-	  This enables the partial, but safe, write support in the NTFS driver.
-
-	  The only supported operation is overwriting existing files, without
-	  changing the file length.  No file or directory creation, deletion or
-	  renaming is possible.  Note only non-resident files can be written to
-	  so you may find that some very small files (<500 bytes or so) cannot
-	  be written to.
-
-	  While we cannot guarantee that it will not damage any data, we have
-	  so far not received a single report where the driver would have
-	  damaged someones data so we assume it is perfectly safe to use.
-
-	  Note:  While write support is safe in this version (a rewrite from
-	  scratch of the NTFS support), it should be noted that the old NTFS
-	  write support, included in Linux 2.5.10 and before (since 1997),
-	  is not safe.
-
-	  This is currently useful with TopologiLinux.  TopologiLinux is run
-	  on top of any DOS/Microsoft Windows system without partitioning your
-	  hard disk.  Unlike other Linux distributions TopologiLinux does not
-	  need its own partition.  For more information see
-	  <http://topologi-linux.sourceforge.net/>
-
-	  It is perfectly safe to say N here.
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
deleted file mode 100644
index 3e736572ed00..000000000000
--- a/fs/ntfs/Makefile
+++ /dev/null
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# Rules for making the NTFS driver.
-
-obj-$(CONFIG_NTFS_FS) += ntfs.o
-
-ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
-	  index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
-	  unistr.o upcase.o
-
-ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
-
-ccflags-y := -DNTFS_VERSION=\"2.1.32\"
-ccflags-$(CONFIG_NTFS_DEBUG)	+= -DDEBUG
-ccflags-$(CONFIG_NTFS_RW)	+= -DNTFS_RW
-
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
deleted file mode 100644
index 2d01517a2d59..000000000000
--- a/fs/ntfs/aops.c
+++ /dev/null
@@ -1,1744 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * aops.c - NTFS kernel address space operations and page cache handling.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <linux/buffer_head.h>
-#include <linux/writeback.h>
-#include <linux/bit_spinlock.h>
-#include <linux/bio.h>
-
-#include "aops.h"
-#include "attrib.h"
-#include "debug.h"
-#include "inode.h"
-#include "mft.h"
-#include "runlist.h"
-#include "types.h"
-#include "ntfs.h"
-
-/**
- * ntfs_end_buffer_async_read - async io completion for reading attributes
- * @bh:		buffer head on which io is completed
- * @uptodate:	whether @bh is now uptodate or not
- *
- * Asynchronous I/O completion handler for reading pages belonging to the
- * attribute address space of an inode.  The inodes can either be files or
- * directories or they can be fake inodes describing some attribute.
- *
- * If NInoMstProtected(), perform the post read mst fixups when all IO on the
- * page has been completed and mark the page uptodate or set the error bit on
- * the page.  To determine the size of the records that need fixing up, we
- * cheat a little bit by setting the index_block_size in ntfs_inode to the ntfs
- * record size, and index_block_size_bits, to the log(base 2) of the ntfs
- * record size.
- */
-static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
-{
-	unsigned long flags;
-	struct buffer_head *first, *tmp;
-	struct page *page;
-	struct inode *vi;
-	ntfs_inode *ni;
-	int page_uptodate = 1;
-
-	page = bh->b_page;
-	vi = page->mapping->host;
-	ni = NTFS_I(vi);
-
-	if (likely(uptodate)) {
-		loff_t i_size;
-		s64 file_ofs, init_size;
-
-		set_buffer_uptodate(bh);
-
-		file_ofs = ((s64)page->index << PAGE_SHIFT) +
-				bh_offset(bh);
-		read_lock_irqsave(&ni->size_lock, flags);
-		init_size = ni->initialized_size;
-		i_size = i_size_read(vi);
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (unlikely(init_size > i_size)) {
-			/* Race with shrinking truncate. */
-			init_size = i_size;
-		}
-		/* Check for the current buffer head overflowing. */
-		if (unlikely(file_ofs + bh->b_size > init_size)) {
-			int ofs;
-			void *kaddr;
-
-			ofs = 0;
-			if (file_ofs < init_size)
-				ofs = init_size - file_ofs;
-			kaddr = kmap_atomic(page);
-			memset(kaddr + bh_offset(bh) + ofs, 0,
-					bh->b_size - ofs);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr);
-		}
-	} else {
-		clear_buffer_uptodate(bh);
-		SetPageError(page);
-		ntfs_error(ni->vol->sb, "Buffer I/O error, logical block "
-				"0x%llx.", (unsigned long long)bh->b_blocknr);
-	}
-	first = page_buffers(page);
-	spin_lock_irqsave(&first->b_uptodate_lock, flags);
-	clear_buffer_async_read(bh);
-	unlock_buffer(bh);
-	tmp = bh;
-	do {
-		if (!buffer_uptodate(tmp))
-			page_uptodate = 0;
-		if (buffer_async_read(tmp)) {
-			if (likely(buffer_locked(tmp)))
-				goto still_busy;
-			/* Async buffers must be locked. */
-			BUG();
-		}
-		tmp = tmp->b_this_page;
-	} while (tmp != bh);
-	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	/*
-	 * If none of the buffers had errors then we can set the page uptodate,
-	 * but we first have to perform the post read mst fixups, if the
-	 * attribute is mst protected, i.e. if NInoMstProteced(ni) is true.
-	 * Note we ignore fixup errors as those are detected when
-	 * map_mft_record() is called which gives us per record granularity
-	 * rather than per page granularity.
-	 */
-	if (!NInoMstProtected(ni)) {
-		if (likely(page_uptodate && !PageError(page)))
-			SetPageUptodate(page);
-	} else {
-		u8 *kaddr;
-		unsigned int i, recs;
-		u32 rec_size;
-
-		rec_size = ni->itype.index.block_size;
-		recs = PAGE_SIZE / rec_size;
-		/* Should have been verified before we got here... */
-		BUG_ON(!recs);
-		kaddr = kmap_atomic(page);
-		for (i = 0; i < recs; i++)
-			post_read_mst_fixup((NTFS_RECORD*)(kaddr +
-					i * rec_size), rec_size);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(page);
-		if (likely(page_uptodate && !PageError(page)))
-			SetPageUptodate(page);
-	}
-	unlock_page(page);
-	return;
-still_busy:
-	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
-	return;
-}
-
-/**
- * ntfs_read_block - fill a @folio of an address space with data
- * @folio:	page cache folio to fill with data
- *
- * We read each buffer asynchronously and when all buffers are read in, our io
- * completion handler ntfs_end_buffer_read_async(), if required, automatically
- * applies the mst fixups to the folio before finally marking it uptodate and
- * unlocking it.
- *
- * We only enforce allocated_size limit because i_size is checked for in
- * generic_file_read().
- *
- * Return 0 on success and -errno on error.
- *
- * Contains an adapted version of fs/buffer.c::block_read_full_folio().
- */
-static int ntfs_read_block(struct folio *folio)
-{
-	loff_t i_size;
-	VCN vcn;
-	LCN lcn;
-	s64 init_size;
-	struct inode *vi;
-	ntfs_inode *ni;
-	ntfs_volume *vol;
-	runlist_element *rl;
-	struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
-	sector_t iblock, lblock, zblock;
-	unsigned long flags;
-	unsigned int blocksize, vcn_ofs;
-	int i, nr;
-	unsigned char blocksize_bits;
-
-	vi = folio->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-
-	/* $MFT/$DATA must have its complete runlist in memory at all times. */
-	BUG_ON(!ni->runlist.rl && !ni->mft_no && !NInoAttr(ni));
-
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-
-	head = folio_buffers(folio);
-	if (!head)
-		head = create_empty_buffers(folio, blocksize, 0);
-	bh = head;
-
-	/*
-	 * We may be racing with truncate.  To avoid some of the problems we
-	 * now take a snapshot of the various sizes and use those for the whole
-	 * of the function.  In case of an extending truncate it just means we
-	 * may leave some buffers unmapped which are now allocated.  This is
-	 * not a problem since these buffers will just get mapped when a write
-	 * occurs.  In case of a shrinking truncate, we will detect this later
-	 * on due to the runlist being incomplete and if the folio is being
-	 * fully truncated, truncate will throw it away as soon as we unlock
-	 * it so no need to worry what we do with it.
-	 */
-	iblock = (s64)folio->index << (PAGE_SHIFT - blocksize_bits);
-	read_lock_irqsave(&ni->size_lock, flags);
-	lblock = (ni->allocated_size + blocksize - 1) >> blocksize_bits;
-	init_size = ni->initialized_size;
-	i_size = i_size_read(vi);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (unlikely(init_size > i_size)) {
-		/* Race with shrinking truncate. */
-		init_size = i_size;
-	}
-	zblock = (init_size + blocksize - 1) >> blocksize_bits;
-
-	/* Loop through all the buffers in the folio. */
-	rl = NULL;
-	nr = i = 0;
-	do {
-		int err = 0;
-
-		if (unlikely(buffer_uptodate(bh)))
-			continue;
-		if (unlikely(buffer_mapped(bh))) {
-			arr[nr++] = bh;
-			continue;
-		}
-		bh->b_bdev = vol->sb->s_bdev;
-		/* Is the block within the allowed limits? */
-		if (iblock < lblock) {
-			bool is_retry = false;
-
-			/* Convert iblock into corresponding vcn and offset. */
-			vcn = (VCN)iblock << blocksize_bits >>
-					vol->cluster_size_bits;
-			vcn_ofs = ((VCN)iblock << blocksize_bits) &
-					vol->cluster_size_mask;
-			if (!rl) {
-lock_retry_remap:
-				down_read(&ni->runlist.lock);
-				rl = ni->runlist.rl;
-			}
-			if (likely(rl != NULL)) {
-				/* Seek to element containing target vcn. */
-				while (rl->length && rl[1].vcn <= vcn)
-					rl++;
-				lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			} else
-				lcn = LCN_RL_NOT_MAPPED;
-			/* Successful remap. */
-			if (lcn >= 0) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn << vol->cluster_size_bits)
-						+ vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-				/* Only read initialized data blocks. */
-				if (iblock < zblock) {
-					arr[nr++] = bh;
-					continue;
-				}
-				/* Fully non-initialized data block, zero it. */
-				goto handle_zblock;
-			}
-			/* It is a hole, need to zero it. */
-			if (lcn == LCN_HOLE)
-				goto handle_hole;
-			/* If first try and runlist unmapped, map and retry. */
-			if (!is_retry && lcn == LCN_RL_NOT_MAPPED) {
-				is_retry = true;
-				/*
-				 * Attempt to map runlist, dropping lock for
-				 * the duration.
-				 */
-				up_read(&ni->runlist.lock);
-				err = ntfs_map_runlist(ni, vcn);
-				if (likely(!err))
-					goto lock_retry_remap;
-				rl = NULL;
-			} else if (!rl)
-				up_read(&ni->runlist.lock);
-			/*
-			 * If buffer is outside the runlist, treat it as a
-			 * hole.  This can happen due to concurrent truncate
-			 * for example.
-			 */
-			if (err == -ENOENT || lcn == LCN_ENOENT) {
-				err = 0;
-				goto handle_hole;
-			}
-			/* Hard error, zero out region. */
-			if (!err)
-				err = -EIO;
-			bh->b_blocknr = -1;
-			folio_set_error(folio);
-			ntfs_error(vol->sb, "Failed to read from inode 0x%lx, "
-					"attribute type 0x%x, vcn 0x%llx, "
-					"offset 0x%x because its location on "
-					"disk could not be determined%s "
-					"(error code %i).", ni->mft_no,
-					ni->type, (unsigned long long)vcn,
-					vcn_ofs, is_retry ? " even after "
-					"retrying" : "", err);
-		}
-		/*
-		 * Either iblock was outside lblock limits or
-		 * ntfs_rl_vcn_to_lcn() returned error.  Just zero that portion
-		 * of the folio and set the buffer uptodate.
-		 */
-handle_hole:
-		bh->b_blocknr = -1UL;
-		clear_buffer_mapped(bh);
-handle_zblock:
-		folio_zero_range(folio, i * blocksize, blocksize);
-		if (likely(!err))
-			set_buffer_uptodate(bh);
-	} while (i++, iblock++, (bh = bh->b_this_page) != head);
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* Check we have at least one buffer ready for i/o. */
-	if (nr) {
-		struct buffer_head *tbh;
-
-		/* Lock the buffers. */
-		for (i = 0; i < nr; i++) {
-			tbh = arr[i];
-			lock_buffer(tbh);
-			tbh->b_end_io = ntfs_end_buffer_async_read;
-			set_buffer_async_read(tbh);
-		}
-		/* Finally, start i/o on the buffers. */
-		for (i = 0; i < nr; i++) {
-			tbh = arr[i];
-			if (likely(!buffer_uptodate(tbh)))
-				submit_bh(REQ_OP_READ, tbh);
-			else
-				ntfs_end_buffer_async_read(tbh, 1);
-		}
-		return 0;
-	}
-	/* No i/o was scheduled on any of the buffers. */
-	if (likely(!folio_test_error(folio)))
-		folio_mark_uptodate(folio);
-	else /* Signal synchronous i/o error. */
-		nr = -EIO;
-	folio_unlock(folio);
-	return nr;
-}
-
-/**
- * ntfs_read_folio - fill a @folio of a @file with data from the device
- * @file:	open file to which the folio @folio belongs or NULL
- * @folio:	page cache folio to fill with data
- *
- * For non-resident attributes, ntfs_read_folio() fills the @folio of the open
- * file @file by calling the ntfs version of the generic block_read_full_folio()
- * function, ntfs_read_block(), which in turn creates and reads in the buffers
- * associated with the folio asynchronously.
- *
- * For resident attributes, OTOH, ntfs_read_folio() fills @folio by copying the
- * data from the mft record (which at this stage is most likely in memory) and
- * fills the remainder with zeroes. Thus, in this case, I/O is synchronous, as
- * even if the mft record is not cached at this point in time, we need to wait
- * for it to be read in before we can do the copy.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_read_folio(struct file *file, struct folio *folio)
-{
-	struct page *page = &folio->page;
-	loff_t i_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	u8 *addr;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *mrec;
-	unsigned long flags;
-	u32 attr_len;
-	int err = 0;
-
-retry_readpage:
-	BUG_ON(!PageLocked(page));
-	vi = page->mapping->host;
-	i_size = i_size_read(vi);
-	/* Is the page fully outside i_size? (truncate in progress) */
-	if (unlikely(page->index >= (i_size + PAGE_SIZE - 1) >>
-			PAGE_SHIFT)) {
-		zero_user(page, 0, PAGE_SIZE);
-		ntfs_debug("Read outside i_size - truncated?");
-		goto done;
-	}
-	/*
-	 * This can potentially happen because we clear PageUptodate() during
-	 * ntfs_writepage() of MstProtected() attributes.
-	 */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		return 0;
-	}
-	ni = NTFS_I(vi);
-	/*
-	 * Only $DATA attributes can be encrypted and only unnamed $DATA
-	 * attributes can be compressed.  Index root can have the flags set but
-	 * this means to create compressed/encrypted files, not that the
-	 * attribute is compressed/encrypted.  Note we need to check for
-	 * AT_INDEX_ALLOCATION since this is the type of both directory and
-	 * index inodes.
-	 */
-	if (ni->type != AT_INDEX_ALLOCATION) {
-		/* If attribute is encrypted, deny access, just like NT4. */
-		if (NInoEncrypted(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			err = -EACCES;
-			goto err_out;
-		}
-		/* Compressed data streams are handled in compress.c. */
-		if (NInoNonResident(ni) && NInoCompressed(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			BUG_ON(ni->name_len);
-			return ntfs_read_compressed_block(page);
-		}
-	}
-	/* NInoNonResident() == NInoIndexAllocPresent() */
-	if (NInoNonResident(ni)) {
-		/* Normal, non-resident data stream. */
-		return ntfs_read_block(folio);
-	}
-	/*
-	 * Attribute is resident, implying it is not compressed or encrypted.
-	 * This also means the attribute is smaller than an mft record and
-	 * hence smaller than a page, so can simply zero out any pages with
-	 * index above 0.  Note the attribute can actually be marked compressed
-	 * but if it is resident the actual data is not compressed so we are
-	 * ok to ignore the compressed flag here.
-	 */
-	if (unlikely(page->index > 0)) {
-		zero_user(page, 0, PAGE_SIZE);
-		goto done;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	mrec = map_mft_record(base_ni);
-	if (IS_ERR(mrec)) {
-		err = PTR_ERR(mrec);
-		goto err_out;
-	}
-	/*
-	 * If a parallel write made the attribute non-resident, drop the mft
-	 * record and retry the read_folio.
-	 */
-	if (unlikely(NInoNonResident(ni))) {
-		unmap_mft_record(base_ni);
-		goto retry_readpage;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, mrec);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto put_unm_err_out;
-	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
-	read_lock_irqsave(&ni->size_lock, flags);
-	if (unlikely(attr_len > ni->initialized_size))
-		attr_len = ni->initialized_size;
-	i_size = i_size_read(vi);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (unlikely(attr_len > i_size)) {
-		/* Race with shrinking truncate. */
-		attr_len = i_size;
-	}
-	addr = kmap_atomic(page);
-	/* Copy the data to the page. */
-	memcpy(addr, (u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset),
-			attr_len);
-	/* Zero the remainder of the page. */
-	memset(addr + attr_len, 0, PAGE_SIZE - attr_len);
-	flush_dcache_page(page);
-	kunmap_atomic(addr);
-put_unm_err_out:
-	ntfs_attr_put_search_ctx(ctx);
-unm_err_out:
-	unmap_mft_record(base_ni);
-done:
-	SetPageUptodate(page);
-err_out:
-	unlock_page(page);
-	return err;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_write_block - write a @folio to the backing store
- * @folio:	page cache folio to write out
- * @wbc:	writeback control structure
- *
- * This function is for writing folios belonging to non-resident, non-mst
- * protected attributes to their backing store.
- *
- * For a folio with buffers, map and write the dirty buffers asynchronously
- * under folio writeback. For a folio without buffers, create buffers for the
- * folio, then proceed as above.
- *
- * If a folio doesn't have buffers the folio dirty state is definitive. If
- * a folio does have buffers, the folio dirty state is just a hint,
- * and the buffer dirty state is definitive. (A hint which has rules:
- * dirty buffers against a clean folio is illegal. Other combinations are
- * legal and need to be handled. In particular a dirty folio containing
- * clean buffers for example.)
- *
- * Return 0 on success and -errno on error.
- *
- * Based on ntfs_read_block() and __block_write_full_folio().
- */
-static int ntfs_write_block(struct folio *folio, struct writeback_control *wbc)
-{
-	VCN vcn;
-	LCN lcn;
-	s64 initialized_size;
-	loff_t i_size;
-	sector_t block, dblock, iblock;
-	struct inode *vi;
-	ntfs_inode *ni;
-	ntfs_volume *vol;
-	runlist_element *rl;
-	struct buffer_head *bh, *head;
-	unsigned long flags;
-	unsigned int blocksize, vcn_ofs;
-	int err;
-	bool need_end_writeback;
-	unsigned char blocksize_bits;
-
-	vi = folio->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-			"0x%lx.", ni->mft_no, ni->type, folio->index);
-
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(NInoMstProtected(ni));
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	head = folio_buffers(folio);
-	if (!head) {
-		BUG_ON(!folio_test_uptodate(folio));
-		head = create_empty_buffers(folio, blocksize,
-				(1 << BH_Uptodate) | (1 << BH_Dirty));
-	}
-	bh = head;
-
-	/* NOTE: Different naming scheme to ntfs_read_block()! */
-
-	/* The first block in the folio. */
-	block = (s64)folio->index << (PAGE_SHIFT - blocksize_bits);
-
-	read_lock_irqsave(&ni->size_lock, flags);
-	i_size = i_size_read(vi);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-
-	/* The first out of bounds block for the data size. */
-	dblock = (i_size + blocksize - 1) >> blocksize_bits;
-
-	/* The last (fully or partially) initialized block. */
-	iblock = initialized_size >> blocksize_bits;
-
-	/*
-	 * Be very careful.  We have no exclusion from block_dirty_folio
-	 * here, and the (potentially unmapped) buffers may become dirty at
-	 * any time.  If a buffer becomes dirty here after we've inspected it
-	 * then we just miss that fact, and the folio stays dirty.
-	 *
-	 * Buffers outside i_size may be dirtied by block_dirty_folio;
-	 * handle that here by just cleaning them.
-	 */
-
-	/*
-	 * Loop through all the buffers in the folio, mapping all the dirty
-	 * buffers to disk addresses and handling any aliases from the
-	 * underlying block device's mapping.
-	 */
-	rl = NULL;
-	err = 0;
-	do {
-		bool is_retry = false;
-
-		if (unlikely(block >= dblock)) {
-			/*
-			 * Mapped buffers outside i_size will occur, because
-			 * this folio can be outside i_size when there is a
-			 * truncate in progress. The contents of such buffers
-			 * were zeroed by ntfs_writepage().
-			 *
-			 * FIXME: What about the small race window where
-			 * ntfs_writepage() has not done any clearing because
-			 * the folio was within i_size but before we get here,
-			 * vmtruncate() modifies i_size?
-			 */
-			clear_buffer_dirty(bh);
-			set_buffer_uptodate(bh);
-			continue;
-		}
-
-		/* Clean buffers are not written out, so no need to map them. */
-		if (!buffer_dirty(bh))
-			continue;
-
-		/* Make sure we have enough initialized size. */
-		if (unlikely((block >= iblock) &&
-				(initialized_size < i_size))) {
-			/*
-			 * If this folio is fully outside initialized
-			 * size, zero out all folios between the current
-			 * initialized size and the current folio. Just
-			 * use ntfs_read_folio() to do the zeroing
-			 * transparently.
-			 */
-			if (block > iblock) {
-				// TODO:
-				// For each folio do:
-				// - read_cache_folio()
-				// Again for each folio do:
-				// - wait_on_folio_locked()
-				// - Check (folio_test_uptodate(folio) &&
-				//		!folio_test_error(folio))
-				// Update initialized size in the attribute and
-				// in the inode.
-				// Again, for each folio do:
-				//	block_dirty_folio();
-				// folio_put()
-				// We don't need to wait on the writes.
-				// Update iblock.
-			}
-			/*
-			 * The current folio straddles initialized size. Zero
-			 * all non-uptodate buffers and set them uptodate (and
-			 * dirty?). Note, there aren't any non-uptodate buffers
-			 * if the folio is uptodate.
-			 * FIXME: For an uptodate folio, the buffers may need to
-			 * be written out because they were not initialized on
-			 * disk before.
-			 */
-			if (!folio_test_uptodate(folio)) {
-				// TODO:
-				// Zero any non-uptodate buffers up to i_size.
-				// Set them uptodate and dirty.
-			}
-			// TODO:
-			// Update initialized size in the attribute and in the
-			// inode (up to i_size).
-			// Update iblock.
-			// FIXME: This is inefficient. Try to batch the two
-			// size changes to happen in one go.
-			ntfs_error(vol->sb, "Writing beyond initialized size "
-					"is not supported yet. Sorry.");
-			err = -EOPNOTSUPP;
-			break;
-			// Do NOT set_buffer_new() BUT DO clear buffer range
-			// outside write request range.
-			// set_buffer_uptodate() on complete buffers as well as
-			// set_buffer_dirty().
-		}
-
-		/* No need to map buffers that are already mapped. */
-		if (buffer_mapped(bh))
-			continue;
-
-		/* Unmapped, dirty buffer. Need to map it. */
-		bh->b_bdev = vol->sb->s_bdev;
-
-		/* Convert block into corresponding vcn and offset. */
-		vcn = (VCN)block << blocksize_bits;
-		vcn_ofs = vcn & vol->cluster_size_mask;
-		vcn >>= vol->cluster_size_bits;
-		if (!rl) {
-lock_retry_remap:
-			down_read(&ni->runlist.lock);
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		/* Successful remap. */
-		if (lcn >= 0) {
-			/* Setup buffer head to point to correct block. */
-			bh->b_blocknr = ((lcn << vol->cluster_size_bits) +
-					vcn_ofs) >> blocksize_bits;
-			set_buffer_mapped(bh);
-			continue;
-		}
-		/* It is a hole, need to instantiate it. */
-		if (lcn == LCN_HOLE) {
-			u8 *kaddr;
-			unsigned long *bpos, *bend;
-
-			/* Check if the buffer is zero. */
-			kaddr = kmap_local_folio(folio, bh_offset(bh));
-			bpos = (unsigned long *)kaddr;
-			bend = (unsigned long *)(kaddr + blocksize);
-			do {
-				if (unlikely(*bpos))
-					break;
-			} while (likely(++bpos < bend));
-			kunmap_local(kaddr);
-			if (bpos == bend) {
-				/*
-				 * Buffer is zero and sparse, no need to write
-				 * it.
-				 */
-				bh->b_blocknr = -1;
-				clear_buffer_dirty(bh);
-				continue;
-			}
-			// TODO: Instantiate the hole.
-			// clear_buffer_new(bh);
-			// clean_bdev_bh_alias(bh);
-			ntfs_error(vol->sb, "Writing into sparse regions is "
-					"not supported yet. Sorry.");
-			err = -EOPNOTSUPP;
-			break;
-		}
-		/* If first try and runlist unmapped, map and retry. */
-		if (!is_retry && lcn == LCN_RL_NOT_MAPPED) {
-			is_retry = true;
-			/*
-			 * Attempt to map runlist, dropping lock for
-			 * the duration.
-			 */
-			up_read(&ni->runlist.lock);
-			err = ntfs_map_runlist(ni, vcn);
-			if (likely(!err))
-				goto lock_retry_remap;
-			rl = NULL;
-		} else if (!rl)
-			up_read(&ni->runlist.lock);
-		/*
-		 * If buffer is outside the runlist, truncate has cut it out
-		 * of the runlist.  Just clean and clear the buffer and set it
-		 * uptodate so it can get discarded by the VM.
-		 */
-		if (err == -ENOENT || lcn == LCN_ENOENT) {
-			bh->b_blocknr = -1;
-			clear_buffer_dirty(bh);
-			folio_zero_range(folio, bh_offset(bh), blocksize);
-			set_buffer_uptodate(bh);
-			err = 0;
-			continue;
-		}
-		/* Failed to map the buffer, even after retrying. */
-		if (!err)
-			err = -EIO;
-		bh->b_blocknr = -1;
-		ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
-				"attribute type 0x%x, vcn 0x%llx, offset 0x%x "
-				"because its location on disk could not be "
-				"determined%s (error code %i).", ni->mft_no,
-				ni->type, (unsigned long long)vcn,
-				vcn_ofs, is_retry ? " even after "
-				"retrying" : "", err);
-		break;
-	} while (block++, (bh = bh->b_this_page) != head);
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* For the error case, need to reset bh to the beginning. */
-	bh = head;
-
-	/* Just an optimization, so ->read_folio() is not called later. */
-	if (unlikely(!folio_test_uptodate(folio))) {
-		int uptodate = 1;
-		do {
-			if (!buffer_uptodate(bh)) {
-				uptodate = 0;
-				bh = head;
-				break;
-			}
-		} while ((bh = bh->b_this_page) != head);
-		if (uptodate)
-			folio_mark_uptodate(folio);
-	}
-
-	/* Setup all mapped, dirty buffers for async write i/o. */
-	do {
-		if (buffer_mapped(bh) && buffer_dirty(bh)) {
-			lock_buffer(bh);
-			if (test_clear_buffer_dirty(bh)) {
-				BUG_ON(!buffer_uptodate(bh));
-				mark_buffer_async_write(bh);
-			} else
-				unlock_buffer(bh);
-		} else if (unlikely(err)) {
-			/*
-			 * For the error case. The buffer may have been set
-			 * dirty during attachment to a dirty folio.
-			 */
-			if (err != -ENOMEM)
-				clear_buffer_dirty(bh);
-		}
-	} while ((bh = bh->b_this_page) != head);
-
-	if (unlikely(err)) {
-		// TODO: Remove the -EOPNOTSUPP check later on...
-		if (unlikely(err == -EOPNOTSUPP))
-			err = 0;
-		else if (err == -ENOMEM) {
-			ntfs_warning(vol->sb, "Error allocating memory. "
-					"Redirtying folio so we try again "
-					"later.");
-			/*
-			 * Put the folio back on mapping->dirty_pages, but
-			 * leave its buffer's dirty state as-is.
-			 */
-			folio_redirty_for_writepage(wbc, folio);
-			err = 0;
-		} else
-			folio_set_error(folio);
-	}
-
-	BUG_ON(folio_test_writeback(folio));
-	folio_start_writeback(folio);	/* Keeps try_to_free_buffers() away. */
-
-	/* Submit the prepared buffers for i/o. */
-	need_end_writeback = true;
-	do {
-		struct buffer_head *next = bh->b_this_page;
-		if (buffer_async_write(bh)) {
-			submit_bh(REQ_OP_WRITE, bh);
-			need_end_writeback = false;
-		}
-		bh = next;
-	} while (bh != head);
-	folio_unlock(folio);
-
-	/* If no i/o was started, need to end writeback here. */
-	if (unlikely(need_end_writeback))
-		folio_end_writeback(folio);
-
-	ntfs_debug("Done.");
-	return err;
-}
-
-/**
- * ntfs_write_mst_block - write a @page to the backing store
- * @page:	page cache page to write out
- * @wbc:	writeback control structure
- *
- * This function is for writing pages belonging to non-resident, mst protected
- * attributes to their backing store.  The only supported attributes are index
- * allocation and $MFT/$DATA.  Both directory inodes and index inodes are
- * supported for the index allocation case.
- *
- * The page must remain locked for the duration of the write because we apply
- * the mst fixups, write, and then undo the fixups, so if we were to unlock the
- * page before undoing the fixups, any other user of the page will see the
- * page contents as corrupt.
- *
- * We clear the page uptodate flag for the duration of the function to ensure
- * exclusion for the $MFT/$DATA case against someone mapping an mft record we
- * are about to apply the mst fixups to.
- *
- * Return 0 on success and -errno on error.
- *
- * Based on ntfs_write_block(), ntfs_mft_writepage(), and
- * write_mft_record_nolock().
- */
-static int ntfs_write_mst_block(struct page *page,
-		struct writeback_control *wbc)
-{
-	sector_t block, dblock, rec_block;
-	struct inode *vi = page->mapping->host;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	u8 *kaddr;
-	unsigned int rec_size = ni->itype.index.block_size;
-	ntfs_inode *locked_nis[PAGE_SIZE / NTFS_BLOCK_SIZE];
-	struct buffer_head *bh, *head, *tbh, *rec_start_bh;
-	struct buffer_head *bhs[MAX_BUF_PER_PAGE];
-	runlist_element *rl;
-	int i, nr_locked_nis, nr_recs, nr_bhs, max_bhs, bhs_per_rec, err, err2;
-	unsigned bh_size, rec_size_bits;
-	bool sync, is_mft, page_is_dirty, rec_is_dirty;
-	unsigned char bh_size_bits;
-
-	if (WARN_ON(rec_size < NTFS_BLOCK_SIZE))
-		return -EINVAL;
-
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, page index "
-			"0x%lx.", vi->i_ino, ni->type, page->index);
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(!NInoMstProtected(ni));
-	is_mft = (S_ISREG(vi->i_mode) && !vi->i_ino);
-	/*
-	 * NOTE: ntfs_write_mst_block() would be called for $MFTMirr if a page
-	 * in its page cache were to be marked dirty.  However this should
-	 * never happen with the current driver and considering we do not
-	 * handle this case here we do want to BUG(), at least for now.
-	 */
-	BUG_ON(!(is_mft || S_ISDIR(vi->i_mode) ||
-			(NInoAttr(ni) && ni->type == AT_INDEX_ALLOCATION)));
-	bh_size = vol->sb->s_blocksize;
-	bh_size_bits = vol->sb->s_blocksize_bits;
-	max_bhs = PAGE_SIZE / bh_size;
-	BUG_ON(!max_bhs);
-	BUG_ON(max_bhs > MAX_BUF_PER_PAGE);
-
-	/* Were we called for sync purposes? */
-	sync = (wbc->sync_mode == WB_SYNC_ALL);
-
-	/* Make sure we have mapped buffers. */
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-
-	rec_size_bits = ni->itype.index.block_size_bits;
-	BUG_ON(!(PAGE_SIZE >> rec_size_bits));
-	bhs_per_rec = rec_size >> bh_size_bits;
-	BUG_ON(!bhs_per_rec);
-
-	/* The first block in the page. */
-	rec_block = block = (sector_t)page->index <<
-			(PAGE_SHIFT - bh_size_bits);
-
-	/* The first out of bounds block for the data size. */
-	dblock = (i_size_read(vi) + bh_size - 1) >> bh_size_bits;
-
-	rl = NULL;
-	err = err2 = nr_bhs = nr_recs = nr_locked_nis = 0;
-	page_is_dirty = rec_is_dirty = false;
-	rec_start_bh = NULL;
-	do {
-		bool is_retry = false;
-
-		if (likely(block < rec_block)) {
-			if (unlikely(block >= dblock)) {
-				clear_buffer_dirty(bh);
-				set_buffer_uptodate(bh);
-				continue;
-			}
-			/*
-			 * This block is not the first one in the record.  We
-			 * ignore the buffer's dirty state because we could
-			 * have raced with a parallel mark_ntfs_record_dirty().
-			 */
-			if (!rec_is_dirty)
-				continue;
-			if (unlikely(err2)) {
-				if (err2 != -ENOMEM)
-					clear_buffer_dirty(bh);
-				continue;
-			}
-		} else /* if (block == rec_block) */ {
-			BUG_ON(block > rec_block);
-			/* This block is the first one in the record. */
-			rec_block += bhs_per_rec;
-			err2 = 0;
-			if (unlikely(block >= dblock)) {
-				clear_buffer_dirty(bh);
-				continue;
-			}
-			if (!buffer_dirty(bh)) {
-				/* Clean records are not written out. */
-				rec_is_dirty = false;
-				continue;
-			}
-			rec_is_dirty = true;
-			rec_start_bh = bh;
-		}
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = (VCN)block << bh_size_bits;
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-lock_retry_remap:
-				down_read(&ni->runlist.lock);
-				rl = ni->runlist.rl;
-			}
-			if (likely(rl != NULL)) {
-				/* Seek to element containing target vcn. */
-				while (rl->length && rl[1].vcn <= vcn)
-					rl++;
-				lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			} else
-				lcn = LCN_RL_NOT_MAPPED;
-			/* Successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> bh_size_bits;
-				set_buffer_mapped(bh);
-			} else {
-				/*
-				 * Remap failed.  Retry to map the runlist once
-				 * unless we are working on $MFT which always
-				 * has the whole of its runlist in memory.
-				 */
-				if (!is_mft && !is_retry &&
-						lcn == LCN_RL_NOT_MAPPED) {
-					is_retry = true;
-					/*
-					 * Attempt to map runlist, dropping
-					 * lock for the duration.
-					 */
-					up_read(&ni->runlist.lock);
-					err2 = ntfs_map_runlist(ni, vcn);
-					if (likely(!err2))
-						goto lock_retry_remap;
-					if (err2 == -ENOMEM)
-						page_is_dirty = true;
-					lcn = err2;
-				} else {
-					err2 = -EIO;
-					if (!rl)
-						up_read(&ni->runlist.lock);
-				}
-				/* Hard error.  Abort writing this record. */
-				if (!err || err == -ENOMEM)
-					err = err2;
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write ntfs record "
-						"0x%llx (inode 0x%lx, "
-						"attribute type 0x%x) because "
-						"its location on disk could "
-						"not be determined (error "
-						"code %lli).",
-						(long long)block <<
-						bh_size_bits >>
-						vol->mft_record_size_bits,
-						ni->mft_no, ni->type,
-						(long long)lcn);
-				/*
-				 * If this is not the first buffer, remove the
-				 * buffers in this record from the list of
-				 * buffers to write and clear their dirty bit
-				 * if not error -ENOMEM.
-				 */
-				if (rec_start_bh != bh) {
-					while (bhs[--nr_bhs] != rec_start_bh)
-						;
-					if (err2 != -ENOMEM) {
-						do {
-							clear_buffer_dirty(
-								rec_start_bh);
-						} while ((rec_start_bh =
-								rec_start_bh->
-								b_this_page) !=
-								bh);
-					}
-				}
-				continue;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-	} while (block++, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&ni->runlist.lock);
-	/* If there were no dirty buffers, we are done. */
-	if (!nr_bhs)
-		goto done;
-	/* Map the page so we can access its contents. */
-	kaddr = kmap(page);
-	/* Clear the page uptodate flag whilst the mst fixups are applied. */
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	for (i = 0; i < nr_bhs; i++) {
-		unsigned int ofs;
-
-		/* Skip buffers which are not at the beginning of records. */
-		if (i % bhs_per_rec)
-			continue;
-		tbh = bhs[i];
-		ofs = bh_offset(tbh);
-		if (is_mft) {
-			ntfs_inode *tni;
-			unsigned long mft_no;
-
-			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
-					>> rec_size_bits;
-			/* Check whether to write this mft record. */
-			tni = NULL;
-			if (!ntfs_may_write_mft_record(vol, mft_no,
-					(MFT_RECORD*)(kaddr + ofs), &tni)) {
-				/*
-				 * The record should not be written.  This
-				 * means we need to redirty the page before
-				 * returning.
-				 */
-				page_is_dirty = true;
-				/*
-				 * Remove the buffers in this mft record from
-				 * the list of buffers to write.
-				 */
-				do {
-					bhs[i] = NULL;
-				} while (++i % bhs_per_rec);
-				continue;
-			}
-			/*
-			 * The record should be written.  If a locked ntfs
-			 * inode was returned, add it to the array of locked
-			 * ntfs inodes.
-			 */
-			if (tni)
-				locked_nis[nr_locked_nis++] = tni;
-		}
-		/* Apply the mst protection fixups. */
-		err2 = pre_write_mst_fixup((NTFS_RECORD*)(kaddr + ofs),
-				rec_size);
-		if (unlikely(err2)) {
-			if (!err || err == -ENOMEM)
-				err = -EIO;
-			ntfs_error(vol->sb, "Failed to apply mst fixups "
-					"(inode 0x%lx, attribute type 0x%x, "
-					"page index 0x%lx, page offset 0x%x)!"
-					"  Unmount and run chkdsk.", vi->i_ino,
-					ni->type, page->index, ofs);
-			/*
-			 * Mark all the buffers in this record clean as we do
-			 * not want to write corrupt data to disk.
-			 */
-			do {
-				clear_buffer_dirty(bhs[i]);
-				bhs[i] = NULL;
-			} while (++i % bhs_per_rec);
-			continue;
-		}
-		nr_recs++;
-	}
-	/* If no records are to be written out, we are done. */
-	if (!nr_recs)
-		goto unm_done;
-	flush_dcache_page(page);
-	/* Lock buffers and start synchronous write i/o on them. */
-	for (i = 0; i < nr_bhs; i++) {
-		tbh = bhs[i];
-		if (!tbh)
-			continue;
-		if (!trylock_buffer(tbh))
-			BUG();
-		/* The buffer dirty state is now irrelevant, just clean it. */
-		clear_buffer_dirty(tbh);
-		BUG_ON(!buffer_uptodate(tbh));
-		BUG_ON(!buffer_mapped(tbh));
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, tbh);
-	}
-	/* Synchronize the mft mirror now if not @sync. */
-	if (is_mft && !sync)
-		goto do_mirror;
-do_wait:
-	/* Wait on i/o completion of buffers. */
-	for (i = 0; i < nr_bhs; i++) {
-		tbh = bhs[i];
-		if (!tbh)
-			continue;
-		wait_on_buffer(tbh);
-		if (unlikely(!buffer_uptodate(tbh))) {
-			ntfs_error(vol->sb, "I/O error while writing ntfs "
-					"record buffer (inode 0x%lx, "
-					"attribute type 0x%x, page index "
-					"0x%lx, page offset 0x%lx)!  Unmount "
-					"and run chkdsk.", vi->i_ino, ni->type,
-					page->index, bh_offset(tbh));
-			if (!err || err == -ENOMEM)
-				err = -EIO;
-			/*
-			 * Set the buffer uptodate so the page and buffer
-			 * states do not become out of sync.
-			 */
-			set_buffer_uptodate(tbh);
-		}
-	}
-	/* If @sync, now synchronize the mft mirror. */
-	if (is_mft && sync) {
-do_mirror:
-		for (i = 0; i < nr_bhs; i++) {
-			unsigned long mft_no;
-			unsigned int ofs;
-
-			/*
-			 * Skip buffers which are not at the beginning of
-			 * records.
-			 */
-			if (i % bhs_per_rec)
-				continue;
-			tbh = bhs[i];
-			/* Skip removed buffers (and hence records). */
-			if (!tbh)
-				continue;
-			ofs = bh_offset(tbh);
-			/* Get the mft record number. */
-			mft_no = (((s64)page->index << PAGE_SHIFT) + ofs)
-					>> rec_size_bits;
-			if (mft_no < vol->mftmirr_size)
-				ntfs_sync_mft_mirror(vol, mft_no,
-						(MFT_RECORD*)(kaddr + ofs),
-						sync);
-		}
-		if (!sync)
-			goto do_wait;
-	}
-	/* Remove the mst protection fixups again. */
-	for (i = 0; i < nr_bhs; i++) {
-		if (!(i % bhs_per_rec)) {
-			tbh = bhs[i];
-			if (!tbh)
-				continue;
-			post_write_mst_fixup((NTFS_RECORD*)(kaddr +
-					bh_offset(tbh)));
-		}
-	}
-	flush_dcache_page(page);
-unm_done:
-	/* Unlock any locked inodes. */
-	while (nr_locked_nis-- > 0) {
-		ntfs_inode *tni, *base_tni;
-		
-		tni = locked_nis[nr_locked_nis];
-		/* Get the base inode. */
-		mutex_lock(&tni->extent_lock);
-		if (tni->nr_extents >= 0)
-			base_tni = tni;
-		else {
-			base_tni = tni->ext.base_ntfs_ino;
-			BUG_ON(!base_tni);
-		}
-		mutex_unlock(&tni->extent_lock);
-		ntfs_debug("Unlocking %s inode 0x%lx.",
-				tni == base_tni ? "base" : "extent",
-				tni->mft_no);
-		mutex_unlock(&tni->mrec_lock);
-		atomic_dec(&tni->count);
-		iput(VFS_I(base_tni));
-	}
-	SetPageUptodate(page);
-	kunmap(page);
-done:
-	if (unlikely(err && err != -ENOMEM)) {
-		/*
-		 * Set page error if there is only one ntfs record in the page.
-		 * Otherwise we would loose per-record granularity.
-		 */
-		if (ni->itype.index.block_size == PAGE_SIZE)
-			SetPageError(page);
-		NVolSetErrors(vol);
-	}
-	if (page_is_dirty) {
-		ntfs_debug("Page still contains one or more dirty ntfs "
-				"records.  Redirtying the page starting at "
-				"record 0x%lx.", page->index <<
-				(PAGE_SHIFT - rec_size_bits));
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-	} else {
-		/*
-		 * Keep the VM happy.  This must be done otherwise the
-		 * radix-tree tag PAGECACHE_TAG_DIRTY remains set even though
-		 * the page is clean.
-		 */
-		BUG_ON(PageWriteback(page));
-		set_page_writeback(page);
-		unlock_page(page);
-		end_page_writeback(page);
-	}
-	if (likely(!err))
-		ntfs_debug("Done.");
-	return err;
-}
-
-/**
- * ntfs_writepage - write a @page to the backing store
- * @page:	page cache page to write out
- * @wbc:	writeback control structure
- *
- * This is called from the VM when it wants to have a dirty ntfs page cache
- * page cleaned.  The VM has already locked the page and marked it clean.
- *
- * For non-resident attributes, ntfs_writepage() writes the @page by calling
- * the ntfs version of the generic block_write_full_folio() function,
- * ntfs_write_block(), which in turn if necessary creates and writes the
- * buffers associated with the page asynchronously.
- *
- * For resident attributes, OTOH, ntfs_writepage() writes the @page by copying
- * the data to the mft record (which at this stage is most likely in memory).
- * The mft record is then marked dirty and written out asynchronously via the
- * vfs inode dirty code path for the inode the mft record belongs to or via the
- * vm page dirty code path for the page the mft record is in.
- *
- * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_folio().
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	loff_t i_size;
-	struct inode *vi = folio->mapping->host;
-	ntfs_inode *base_ni = NULL, *ni = NTFS_I(vi);
-	char *addr;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *m = NULL;
-	u32 attr_len;
-	int err;
-
-retry_writepage:
-	BUG_ON(!folio_test_locked(folio));
-	i_size = i_size_read(vi);
-	/* Is the folio fully outside i_size? (truncate in progress) */
-	if (unlikely(folio->index >= (i_size + PAGE_SIZE - 1) >>
-			PAGE_SHIFT)) {
-		/*
-		 * The folio may have dirty, unmapped buffers.  Make them
-		 * freeable here, so the page does not leak.
-		 */
-		block_invalidate_folio(folio, 0, folio_size(folio));
-		folio_unlock(folio);
-		ntfs_debug("Write outside i_size - truncated?");
-		return 0;
-	}
-	/*
-	 * Only $DATA attributes can be encrypted and only unnamed $DATA
-	 * attributes can be compressed.  Index root can have the flags set but
-	 * this means to create compressed/encrypted files, not that the
-	 * attribute is compressed/encrypted.  Note we need to check for
-	 * AT_INDEX_ALLOCATION since this is the type of both directory and
-	 * index inodes.
-	 */
-	if (ni->type != AT_INDEX_ALLOCATION) {
-		/* If file is encrypted, deny access, just like NT4. */
-		if (NInoEncrypted(ni)) {
-			folio_unlock(folio);
-			BUG_ON(ni->type != AT_DATA);
-			ntfs_debug("Denying write access to encrypted file.");
-			return -EACCES;
-		}
-		/* Compressed data streams are handled in compress.c. */
-		if (NInoNonResident(ni) && NInoCompressed(ni)) {
-			BUG_ON(ni->type != AT_DATA);
-			BUG_ON(ni->name_len);
-			// TODO: Implement and replace this with
-			// return ntfs_write_compressed_block(page);
-			folio_unlock(folio);
-			ntfs_error(vi->i_sb, "Writing to compressed files is "
-					"not supported yet.  Sorry.");
-			return -EOPNOTSUPP;
-		}
-		// TODO: Implement and remove this check.
-		if (NInoNonResident(ni) && NInoSparse(ni)) {
-			folio_unlock(folio);
-			ntfs_error(vi->i_sb, "Writing to sparse files is not "
-					"supported yet.  Sorry.");
-			return -EOPNOTSUPP;
-		}
-	}
-	/* NInoNonResident() == NInoIndexAllocPresent() */
-	if (NInoNonResident(ni)) {
-		/* We have to zero every time due to mmap-at-end-of-file. */
-		if (folio->index >= (i_size >> PAGE_SHIFT)) {
-			/* The folio straddles i_size. */
-			unsigned int ofs = i_size & (folio_size(folio) - 1);
-			folio_zero_segment(folio, ofs, folio_size(folio));
-		}
-		/* Handle mst protected attributes. */
-		if (NInoMstProtected(ni))
-			return ntfs_write_mst_block(page, wbc);
-		/* Normal, non-resident data stream. */
-		return ntfs_write_block(folio, wbc);
-	}
-	/*
-	 * Attribute is resident, implying it is not compressed, encrypted, or
-	 * mst protected.  This also means the attribute is smaller than an mft
-	 * record and hence smaller than a folio, so can simply return error on
-	 * any folios with index above 0.  Note the attribute can actually be
-	 * marked compressed but if it is resident the actual data is not
-	 * compressed so we are ok to ignore the compressed flag here.
-	 */
-	BUG_ON(folio_buffers(folio));
-	BUG_ON(!folio_test_uptodate(folio));
-	if (unlikely(folio->index > 0)) {
-		ntfs_error(vi->i_sb, "BUG()! folio->index (0x%lx) > 0.  "
-				"Aborting write.", folio->index);
-		BUG_ON(folio_test_writeback(folio));
-		folio_start_writeback(folio);
-		folio_unlock(folio);
-		folio_end_writeback(folio);
-		return -EIO;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	/*
-	 * If a parallel write made the attribute non-resident, drop the mft
-	 * record and retry the writepage.
-	 */
-	if (unlikely(NInoNonResident(ni))) {
-		unmap_mft_record(base_ni);
-		goto retry_writepage;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto err_out;
-	/*
-	 * Keep the VM happy.  This must be done otherwise
-	 * PAGECACHE_TAG_DIRTY remains set even though the folio is clean.
-	 */
-	BUG_ON(folio_test_writeback(folio));
-	folio_start_writeback(folio);
-	folio_unlock(folio);
-	attr_len = le32_to_cpu(ctx->attr->data.resident.value_length);
-	i_size = i_size_read(vi);
-	if (unlikely(attr_len > i_size)) {
-		/* Race with shrinking truncate or a failed truncate. */
-		attr_len = i_size;
-		/*
-		 * If the truncate failed, fix it up now.  If a concurrent
-		 * truncate, we do its job, so it does not have to do anything.
-		 */
-		err = ntfs_resident_attr_value_resize(ctx->mrec, ctx->attr,
-				attr_len);
-		/* Shrinking cannot fail. */
-		BUG_ON(err);
-	}
-	addr = kmap_local_folio(folio, 0);
-	/* Copy the data from the folio to the mft record. */
-	memcpy((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset),
-			addr, attr_len);
-	/* Zero out of bounds area in the page cache folio. */
-	memset(addr + attr_len, 0, folio_size(folio) - attr_len);
-	kunmap_local(addr);
-	flush_dcache_folio(folio);
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	/* We are done with the folio. */
-	folio_end_writeback(folio);
-	/* Finally, mark the mft record dirty, so it gets written back. */
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	return 0;
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Error allocating memory. Redirtying "
-				"page so we try again later.");
-		/*
-		 * Put the folio back on mapping->dirty_pages, but leave its
-		 * buffers' dirty state as-is.
-		 */
-		folio_redirty_for_writepage(wbc, folio);
-		err = 0;
-	} else {
-		ntfs_error(vi->i_sb, "Resident attribute write failed with "
-				"error %i.", err);
-		folio_set_error(folio);
-		NVolSetErrors(ni->vol);
-	}
-	folio_unlock(folio);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-}
-
-#endif	/* NTFS_RW */
-
-/**
- * ntfs_bmap - map logical file block to physical device block
- * @mapping:	address space mapping to which the block to be mapped belongs
- * @block:	logical block to map to its physical device block
- *
- * For regular, non-resident files (i.e. not compressed and not encrypted), map
- * the logical @block belonging to the file described by the address space
- * mapping @mapping to its physical device block.
- *
- * The size of the block is equal to the @s_blocksize field of the super block
- * of the mounted file system which is guaranteed to be smaller than or equal
- * to the cluster size thus the block is guaranteed to fit entirely inside the
- * cluster which means we do not need to care how many contiguous bytes are
- * available after the beginning of the block.
- *
- * Return the physical device block if the mapping succeeded or 0 if the block
- * is sparse or there was an error.
- *
- * Note: This is a problem if someone tries to run bmap() on $Boot system file
- * as that really is in block zero but there is nothing we can do.  bmap() is
- * just broken in that respect (just like it cannot distinguish sparse from
- * not available or error).
- */
-static sector_t ntfs_bmap(struct address_space *mapping, sector_t block)
-{
-	s64 ofs, size;
-	loff_t i_size;
-	LCN lcn;
-	unsigned long blocksize, flags;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	ntfs_volume *vol = ni->vol;
-	unsigned delta;
-	unsigned char blocksize_bits, cluster_size_shift;
-
-	ntfs_debug("Entering for mft_no 0x%lx, logical block 0x%llx.",
-			ni->mft_no, (unsigned long long)block);
-	if (ni->type != AT_DATA || !NInoNonResident(ni) || NInoEncrypted(ni)) {
-		ntfs_error(vol->sb, "BMAP does not make sense for %s "
-				"attributes, returning 0.",
-				(ni->type != AT_DATA) ? "non-data" :
-				(!NInoNonResident(ni) ? "resident" :
-				"encrypted"));
-		return 0;
-	}
-	/* None of these can happen. */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoMstProtected(ni));
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	ofs = (s64)block << blocksize_bits;
-	read_lock_irqsave(&ni->size_lock, flags);
-	size = ni->initialized_size;
-	i_size = i_size_read(VFS_I(ni));
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * If the offset is outside the initialized size or the block straddles
-	 * the initialized size then pretend it is a hole unless the
-	 * initialized size equals the file size.
-	 */
-	if (unlikely(ofs >= size || (ofs + blocksize > size && size < i_size)))
-		goto hole;
-	cluster_size_shift = vol->cluster_size_bits;
-	down_read(&ni->runlist.lock);
-	lcn = ntfs_attr_vcn_to_lcn_nolock(ni, ofs >> cluster_size_shift, false);
-	up_read(&ni->runlist.lock);
-	if (unlikely(lcn < LCN_HOLE)) {
-		/*
-		 * Step down to an integer to avoid gcc doing a long long
-		 * comparision in the switch when we know @lcn is between
-		 * LCN_HOLE and LCN_EIO (i.e. -1 to -5).
-		 *
-		 * Otherwise older gcc (at least on some architectures) will
-		 * try to use __cmpdi2() which is of course not available in
-		 * the kernel.
-		 */
-		switch ((int)lcn) {
-		case LCN_ENOENT:
-			/*
-			 * If the offset is out of bounds then pretend it is a
-			 * hole.
-			 */
-			goto hole;
-		case LCN_ENOMEM:
-			ntfs_error(vol->sb, "Not enough memory to complete "
-					"mapping for inode 0x%lx.  "
-					"Returning 0.", ni->mft_no);
-			break;
-		default:
-			ntfs_error(vol->sb, "Failed to complete mapping for "
-					"inode 0x%lx.  Run chkdsk.  "
-					"Returning 0.", ni->mft_no);
-			break;
-		}
-		return 0;
-	}
-	if (lcn < 0) {
-		/* It is a hole. */
-hole:
-		ntfs_debug("Done (returning hole).");
-		return 0;
-	}
-	/*
-	 * The block is really allocated and fullfils all our criteria.
-	 * Convert the cluster to units of block size and return the result.
-	 */
-	delta = ofs & vol->cluster_size_mask;
-	if (unlikely(sizeof(block) < sizeof(lcn))) {
-		block = lcn = ((lcn << cluster_size_shift) + delta) >>
-				blocksize_bits;
-		/* If the block number was truncated return 0. */
-		if (unlikely(block != lcn)) {
-			ntfs_error(vol->sb, "Physical block 0x%llx is too "
-					"large to be returned, returning 0.",
-					(long long)lcn);
-			return 0;
-		}
-	} else
-		block = ((lcn << cluster_size_shift) + delta) >>
-				blocksize_bits;
-	ntfs_debug("Done (returning block 0x%llx).", (unsigned long long)lcn);
-	return block;
-}
-
-/*
- * ntfs_normal_aops - address space operations for normal inodes and attributes
- *
- * Note these are not used for compressed or mst protected inodes and
- * attributes.
- */
-const struct address_space_operations ntfs_normal_aops = {
-	.read_folio	= ntfs_read_folio,
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,
-	.dirty_folio	= block_dirty_folio,
-#endif /* NTFS_RW */
-	.bmap		= ntfs_bmap,
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-/*
- * ntfs_compressed_aops - address space operations for compressed inodes
- */
-const struct address_space_operations ntfs_compressed_aops = {
-	.read_folio	= ntfs_read_folio,
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,
-	.dirty_folio	= block_dirty_folio,
-#endif /* NTFS_RW */
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-/*
- * ntfs_mst_aops - general address space operations for mst protecteed inodes
- *			  and attributes
- */
-const struct address_space_operations ntfs_mst_aops = {
-	.read_folio	= ntfs_read_folio,	/* Fill page with data. */
-#ifdef NTFS_RW
-	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
-	.dirty_folio	= filemap_dirty_folio,
-#endif /* NTFS_RW */
-	.migrate_folio	= buffer_migrate_folio,
-	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_folio = generic_error_remove_folio,
-};
-
-#ifdef NTFS_RW
-
-/**
- * mark_ntfs_record_dirty - mark an ntfs record dirty
- * @page:	page containing the ntfs record to mark dirty
- * @ofs:	byte offset within @page at which the ntfs record begins
- *
- * Set the buffers and the page in which the ntfs record is located dirty.
- *
- * The latter also marks the vfs inode the ntfs record belongs to dirty
- * (I_DIRTY_PAGES only).
- *
- * If the page does not have buffers, we create them and set them uptodate.
- * The page may not be locked which is why we need to handle the buffers under
- * the mapping->i_private_lock.  Once the buffers are marked dirty we no longer
- * need the lock since try_to_free_buffers() does not free dirty buffers.
- */
-void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
-	struct address_space *mapping = page->mapping;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	struct buffer_head *bh, *head, *buffers_to_free = NULL;
-	unsigned int end, bh_size, bh_ofs;
-
-	BUG_ON(!PageUptodate(page));
-	end = ofs + ni->itype.index.block_size;
-	bh_size = VFS_I(ni)->i_sb->s_blocksize;
-	spin_lock(&mapping->i_private_lock);
-	if (unlikely(!page_has_buffers(page))) {
-		spin_unlock(&mapping->i_private_lock);
-		bh = head = alloc_page_buffers(page, bh_size, true);
-		spin_lock(&mapping->i_private_lock);
-		if (likely(!page_has_buffers(page))) {
-			struct buffer_head *tail;
-
-			do {
-				set_buffer_uptodate(bh);
-				tail = bh;
-				bh = bh->b_this_page;
-			} while (bh);
-			tail->b_this_page = head;
-			attach_page_private(page, head);
-		} else
-			buffers_to_free = bh;
-	}
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	do {
-		bh_ofs = bh_offset(bh);
-		if (bh_ofs + bh_size <= ofs)
-			continue;
-		if (unlikely(bh_ofs >= end))
-			break;
-		set_buffer_dirty(bh);
-	} while ((bh = bh->b_this_page) != head);
-	spin_unlock(&mapping->i_private_lock);
-	filemap_dirty_folio(mapping, page_folio(page));
-	if (unlikely(buffers_to_free)) {
-		do {
-			bh = buffers_to_free->b_this_page;
-			free_buffer_head(buffers_to_free);
-			buffers_to_free = bh;
-		} while (buffers_to_free);
-	}
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h
deleted file mode 100644
index 8d0958a149cb..000000000000
--- a/fs/ntfs/aops.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * aops.h - Defines for NTFS kernel address space operations and page cache
- *	    handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_AOPS_H
-#define _LINUX_NTFS_AOPS_H
-
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-#include <linux/fs.h>
-
-#include "inode.h"
-
-/**
- * ntfs_unmap_page - release a page that was mapped using ntfs_map_page()
- * @page:	the page to release
- *
- * Unpin, unmap and release a page that was obtained from ntfs_map_page().
- */
-static inline void ntfs_unmap_page(struct page *page)
-{
-	kunmap(page);
-	put_page(page);
-}
-
-/**
- * ntfs_map_page - map a page into accessible memory, reading it if necessary
- * @mapping:	address space for which to obtain the page
- * @index:	index into the page cache for @mapping of the page to map
- *
- * Read a page from the page cache of the address space @mapping at position
- * @index, where @index is in units of PAGE_SIZE, and not in bytes.
- *
- * If the page is not in memory it is loaded from disk first using the
- * read_folio method defined in the address space operations of @mapping
- * and the page is added to the page cache of @mapping in the process.
- *
- * If the page belongs to an mst protected attribute and it is marked as such
- * in its ntfs inode (NInoMstProtected()) the mst fixups are applied but no
- * error checking is performed.  This means the caller has to verify whether
- * the ntfs record(s) contained in the page are valid or not using one of the
- * ntfs_is_XXXX_record{,p}() macros, where XXXX is the record type you are
- * expecting to see.  (For details of the macros, see fs/ntfs/layout.h.)
- *
- * If the page is in high memory it is mapped into memory directly addressible
- * by the kernel.
- *
- * Finally the page count is incremented, thus pinning the page into place.
- *
- * The above means that page_address(page) can be used on all pages obtained
- * with ntfs_map_page() to get the kernel virtual address of the page.
- *
- * When finished with the page, the caller has to call ntfs_unmap_page() to
- * unpin, unmap and release the page.
- *
- * Note this does not grant exclusive access. If such is desired, the caller
- * must provide it independently of the ntfs_{un}map_page() calls by using
- * a {rw_}semaphore or other means of serialization. A spin lock cannot be
- * used as ntfs_map_page() can block.
- *
- * The unlocked and uptodate page is returned on success or an encoded error
- * on failure. Caller has to test for error using the IS_ERR() macro on the
- * return value. If that evaluates to 'true', the negative error code can be
- * obtained using PTR_ERR() on the return value of ntfs_map_page().
- */
-static inline struct page *ntfs_map_page(struct address_space *mapping,
-		unsigned long index)
-{
-	struct page *page = read_mapping_page(mapping, index, NULL);
-
-	if (!IS_ERR(page))
-		kmap(page);
-	return page;
-}
-
-#ifdef NTFS_RW
-
-extern void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_AOPS_H */
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
deleted file mode 100644
index f79408f9127a..000000000000
--- a/fs/ntfs/attrib.c
+++ /dev/null
@@ -1,2624 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
-#include <linux/writeback.h>
-
-#include "attrib.h"
-#include "debug.h"
-#include "layout.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-#include "types.h"
-
-/**
- * ntfs_map_runlist_nolock - map (a part of) a runlist of an ntfs inode
- * @ni:		ntfs inode for which to map (part of) a runlist
- * @vcn:	map runlist part containing this vcn
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_map_runlist_nolock() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and ntfs_map_runlist_nolock()
- * will perform the necessary mapping and unmapping.
- *
- * Note, ntfs_map_runlist_nolock() saves the state of @ctx on entry and
- * restores it before returning.  Thus, @ctx will be left pointing to the same
- * attribute on return as on entry.  However, the actual pointers in @ctx may
- * point to different memory locations on return, so you must remember to reset
- * any cached pointers from the @ctx, i.e. after the call to
- * ntfs_map_runlist_nolock(), you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * Return 0 on success and -errno on error.  There is one special error code
- * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
- * of bounds of the runlist.
- *
- * Note the runlist can be NULL after this function returns if @vcn is zero and
- * the attribute has zero allocated size, i.e. there simply is no runlist.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist will be modified.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
-{
-	VCN end_vcn;
-	unsigned long flags;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	runlist_element *rl;
-	struct page *put_this_page = NULL;
-	int err = 0;
-	bool ctx_is_temporary, ctx_needs_reset;
-	ntfs_attr_search_ctx old_ctx = { NULL, };
-
-	ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
-			(unsigned long long)vcn);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	if (!ctx) {
-		ctx_is_temporary = ctx_needs_reset = true;
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m))
-			return PTR_ERR(m);
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-	} else {
-		VCN allocated_size_vcn;
-
-		BUG_ON(IS_ERR(ctx->mrec));
-		a = ctx->attr;
-		BUG_ON(!a->non_resident);
-		ctx_is_temporary = false;
-		end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size_vcn = ni->allocated_size >>
-				ni->vol->cluster_size_bits;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
-			end_vcn = allocated_size_vcn - 1;
-		/*
-		 * If we already have the attribute extent containing @vcn in
-		 * @ctx, no need to look it up again.  We slightly cheat in
-		 * that if vcn exceeds the allocated size, we will refuse to
-		 * map the runlist below, so there is definitely no need to get
-		 * the right attribute extent.
-		 */
-		if (vcn >= allocated_size_vcn || (a->type == ni->type &&
-				a->name_length == ni->name_len &&
-				!memcmp((u8*)a + le16_to_cpu(a->name_offset),
-				ni->name, ni->name_len) &&
-				sle64_to_cpu(a->data.non_resident.lowest_vcn)
-				<= vcn && end_vcn >= vcn))
-			ctx_needs_reset = false;
-		else {
-			/* Save the old search context. */
-			old_ctx = *ctx;
-			/*
-			 * If the currently mapped (extent) inode is not the
-			 * base inode we will unmap it when we reinitialize the
-			 * search context which means we need to get a
-			 * reference to the page containing the mapped mft
-			 * record so we do not accidentally drop changes to the
-			 * mft record when it has not been marked dirty yet.
-			 */
-			if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
-					old_ctx.base_ntfs_ino) {
-				put_this_page = old_ctx.ntfs_ino->page;
-				get_page(put_this_page);
-			}
-			/*
-			 * Reinitialize the search context so we can lookup the
-			 * needed attribute extent.
-			 */
-			ntfs_attr_reinit_search_ctx(ctx);
-			ctx_needs_reset = true;
-		}
-	}
-	if (ctx_needs_reset) {
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, vcn, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			goto err_out;
-		}
-		BUG_ON(!ctx->attr->non_resident);
-	}
-	a = ctx->attr;
-	/*
-	 * Only decompress the mapping pairs if @vcn is inside it.  Otherwise
-	 * we get into problems when we try to map an out of bounds vcn because
-	 * we then try to map the already mapped runlist fragment and
-	 * ntfs_mapping_pairs_decompress() fails.
-	 */
-	end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
-	if (unlikely(vcn && vcn >= end_vcn)) {
-		err = -ENOENT;
-		goto err_out;
-	}
-	rl = ntfs_mapping_pairs_decompress(ni->vol, a, ni->runlist.rl);
-	if (IS_ERR(rl))
-		err = PTR_ERR(rl);
-	else
-		ni->runlist.rl = rl;
-err_out:
-	if (ctx_is_temporary) {
-		if (likely(ctx))
-			ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-	} else if (ctx_needs_reset) {
-		/*
-		 * If there is no attribute list, restoring the search context
-		 * is accomplished simply by copying the saved context back over
-		 * the caller supplied context.  If there is an attribute list,
-		 * things are more complicated as we need to deal with mapping
-		 * of mft records and resulting potential changes in pointers.
-		 */
-		if (NInoAttrList(base_ni)) {
-			/*
-			 * If the currently mapped (extent) inode is not the
-			 * one we had before, we need to unmap it and map the
-			 * old one.
-			 */
-			if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
-				/*
-				 * If the currently mapped inode is not the
-				 * base inode, unmap it.
-				 */
-				if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
-						ctx->base_ntfs_ino) {
-					unmap_extent_mft_record(ctx->ntfs_ino);
-					ctx->mrec = ctx->base_mrec;
-					BUG_ON(!ctx->mrec);
-				}
-				/*
-				 * If the old mapped inode is not the base
-				 * inode, map it.
-				 */
-				if (old_ctx.base_ntfs_ino &&
-						old_ctx.ntfs_ino !=
-						old_ctx.base_ntfs_ino) {
-retry_map:
-					ctx->mrec = map_mft_record(
-							old_ctx.ntfs_ino);
-					/*
-					 * Something bad has happened.  If out
-					 * of memory retry till it succeeds.
-					 * Any other errors are fatal and we
-					 * return the error code in ctx->mrec.
-					 * Let the caller deal with it...  We
-					 * just need to fudge things so the
-					 * caller can reinit and/or put the
-					 * search context safely.
-					 */
-					if (IS_ERR(ctx->mrec)) {
-						if (PTR_ERR(ctx->mrec) ==
-								-ENOMEM) {
-							schedule();
-							goto retry_map;
-						} else
-							old_ctx.ntfs_ino =
-								old_ctx.
-								base_ntfs_ino;
-					}
-				}
-			}
-			/* Update the changed pointers in the saved context. */
-			if (ctx->mrec != old_ctx.mrec) {
-				if (!IS_ERR(ctx->mrec))
-					old_ctx.attr = (ATTR_RECORD*)(
-							(u8*)ctx->mrec +
-							((u8*)old_ctx.attr -
-							(u8*)old_ctx.mrec));
-				old_ctx.mrec = ctx->mrec;
-			}
-		}
-		/* Restore the search context to the saved one. */
-		*ctx = old_ctx;
-		/*
-		 * We drop the reference on the page we took earlier.  In the
-		 * case that IS_ERR(ctx->mrec) is true this means we might lose
-		 * some changes to the mft record that had been made between
-		 * the last time it was marked dirty/written out and now.  This
-		 * at this stage is not a problem as the mapping error is fatal
-		 * enough that the mft record cannot be written out anyway and
-		 * the caller is very likely to shutdown the whole inode
-		 * immediately and mark the volume dirty for chkdsk to pick up
-		 * the pieces anyway.
-		 */
-		if (put_this_page)
-			put_page(put_this_page);
-	}
-	return err;
-}
-
-/**
- * ntfs_map_runlist - map (a part of) a runlist of an ntfs inode
- * @ni:		ntfs inode for which to map (part of) a runlist
- * @vcn:	map runlist part containing this vcn
- *
- * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
- *
- * Return 0 on success and -errno on error.  There is one special error code
- * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
- * of bounds of the runlist.
- *
- * Locking: - The runlist must be unlocked on entry and is unlocked on return.
- *	    - This function takes the runlist lock for writing and may modify
- *	      the runlist.
- */
-int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
-{
-	int err = 0;
-
-	down_write(&ni->runlist.lock);
-	/* Make sure someone else didn't do the work while we were sleeping. */
-	if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
-			LCN_RL_NOT_MAPPED))
-		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
-	up_write(&ni->runlist.lock);
-	return err;
-}
-
-/**
- * ntfs_attr_vcn_to_lcn_nolock - convert a vcn into a lcn given an ntfs inode
- * @ni:			ntfs inode of the attribute whose runlist to search
- * @vcn:		vcn to convert
- * @write_locked:	true if the runlist is locked for writing
- *
- * Find the virtual cluster number @vcn in the runlist of the ntfs attribute
- * described by the ntfs inode @ni and return the corresponding logical cluster
- * number (lcn).
- *
- * If the @vcn is not mapped yet, the attempt is made to map the attribute
- * extent containing the @vcn and the vcn to lcn conversion is retried.
- *
- * If @write_locked is true the caller has locked the runlist for writing and
- * if false for reading.
- *
- * Since lcns must be >= 0, we use negative return codes with special meaning:
- *
- * Return code	Meaning / Description
- * ==========================================
- *  LCN_HOLE	Hole / not allocated on disk.
- *  LCN_ENOENT	There is no such vcn in the runlist, i.e. @vcn is out of bounds.
- *  LCN_ENOMEM	Not enough memory to map runlist.
- *  LCN_EIO	Critical error (runlist/file is corrupt, i/o error, etc).
- *
- * Locking: - The runlist must be locked on entry and is left locked on return.
- *	    - If @write_locked is 'false', i.e. the runlist is locked for reading,
- *	      the lock may be dropped inside the function so you cannot rely on
- *	      the runlist still being the same when this function returns.
- */
-LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
-		const bool write_locked)
-{
-	LCN lcn;
-	unsigned long flags;
-	bool is_retry = false;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
-			ni->mft_no, (unsigned long long)vcn,
-			write_locked ? "write" : "read");
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(vcn < 0);
-	if (!ni->runlist.rl) {
-		read_lock_irqsave(&ni->size_lock, flags);
-		if (!ni->allocated_size) {
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			return LCN_ENOENT;
-		}
-		read_unlock_irqrestore(&ni->size_lock, flags);
-	}
-retry_remap:
-	/* Convert vcn to lcn.  If that fails map the runlist and retry once. */
-	lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
-	if (likely(lcn >= LCN_HOLE)) {
-		ntfs_debug("Done, lcn 0x%llx.", (long long)lcn);
-		return lcn;
-	}
-	if (lcn != LCN_RL_NOT_MAPPED) {
-		if (lcn != LCN_ENOENT)
-			lcn = LCN_EIO;
-	} else if (!is_retry) {
-		int err;
-
-		if (!write_locked) {
-			up_read(&ni->runlist.lock);
-			down_write(&ni->runlist.lock);
-			if (unlikely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) !=
-					LCN_RL_NOT_MAPPED)) {
-				up_write(&ni->runlist.lock);
-				down_read(&ni->runlist.lock);
-				goto retry_remap;
-			}
-		}
-		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
-		if (!write_locked) {
-			up_write(&ni->runlist.lock);
-			down_read(&ni->runlist.lock);
-		}
-		if (likely(!err)) {
-			is_retry = true;
-			goto retry_remap;
-		}
-		if (err == -ENOENT)
-			lcn = LCN_ENOENT;
-		else if (err == -ENOMEM)
-			lcn = LCN_ENOMEM;
-		else
-			lcn = LCN_EIO;
-	}
-	if (lcn != LCN_ENOENT)
-		ntfs_error(ni->vol->sb, "Failed with error code %lli.",
-				(long long)lcn);
-	return lcn;
-}
-
-/**
- * ntfs_attr_find_vcn_nolock - find a vcn in the runlist of an ntfs inode
- * @ni:		ntfs inode describing the runlist to search
- * @vcn:	vcn to find
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Find the virtual cluster number @vcn in the runlist described by the ntfs
- * inode @ni and return the address of the runlist element containing the @vcn.
- *
- * If the @vcn is not mapped yet, the attempt is made to map the attribute
- * extent containing the @vcn and the vcn to lcn conversion is retried.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_attr_find_vcn_nolock() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and ntfs_attr_find_vcn_nolock()
- * will perform the necessary mapping and unmapping.
- *
- * Note, ntfs_attr_find_vcn_nolock() saves the state of @ctx on entry and
- * restores it before returning.  Thus, @ctx will be left pointing to the same
- * attribute on return as on entry.  However, the actual pointers in @ctx may
- * point to different memory locations on return, so you must remember to reset
- * any cached pointers from the @ctx, i.e. after the call to
- * ntfs_attr_find_vcn_nolock(), you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- * Note you need to distinguish between the lcn of the returned runlist element
- * being >= 0 and LCN_HOLE.  In the later case you have to return zeroes on
- * read and allocate clusters on write.
- *
- * Return the runlist element containing the @vcn on success and
- * ERR_PTR(-errno) on error.  You need to test the return value with IS_ERR()
- * to decide if the return is success or failure and PTR_ERR() to get to the
- * error code if IS_ERR() is true.
- *
- * The possible error return codes are:
- *	-ENOENT - No such vcn in the runlist, i.e. @vcn is out of bounds.
- *	-ENOMEM - Not enough memory to map runlist.
- *	-EIO	- Critical error (runlist/file is corrupt, i/o error, etc).
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
-		ntfs_attr_search_ctx *ctx)
-{
-	unsigned long flags;
-	runlist_element *rl;
-	int err = 0;
-	bool is_retry = false;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
-			ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
-	BUG_ON(!NInoNonResident(ni));
-	BUG_ON(vcn < 0);
-	if (!ni->runlist.rl) {
-		read_lock_irqsave(&ni->size_lock, flags);
-		if (!ni->allocated_size) {
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			return ERR_PTR(-ENOENT);
-		}
-		read_unlock_irqrestore(&ni->size_lock, flags);
-	}
-retry_remap:
-	rl = ni->runlist.rl;
-	if (likely(rl && vcn >= rl[0].vcn)) {
-		while (likely(rl->length)) {
-			if (unlikely(vcn < rl[1].vcn)) {
-				if (likely(rl->lcn >= LCN_HOLE)) {
-					ntfs_debug("Done.");
-					return rl;
-				}
-				break;
-			}
-			rl++;
-		}
-		if (likely(rl->lcn != LCN_RL_NOT_MAPPED)) {
-			if (likely(rl->lcn == LCN_ENOENT))
-				err = -ENOENT;
-			else
-				err = -EIO;
-		}
-	}
-	if (!err && !is_retry) {
-		/*
-		 * If the search context is invalid we cannot map the unmapped
-		 * region.
-		 */
-		if (IS_ERR(ctx->mrec))
-			err = PTR_ERR(ctx->mrec);
-		else {
-			/*
-			 * The @vcn is in an unmapped region, map the runlist
-			 * and retry.
-			 */
-			err = ntfs_map_runlist_nolock(ni, vcn, ctx);
-			if (likely(!err)) {
-				is_retry = true;
-				goto retry_remap;
-			}
-		}
-		if (err == -EINVAL)
-			err = -EIO;
-	} else if (!err)
-		err = -EIO;
-	if (err != -ENOENT)
-		ntfs_error(ni->vol->sb, "Failed with error code %i.", err);
-	return ERR_PTR(err);
-}
-
-/**
- * ntfs_attr_find - find (next) attribute in mft record
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * You should not need to call this function directly.  Use ntfs_attr_lookup()
- * instead.
- *
- * ntfs_attr_find() takes a search context @ctx as parameter and searches the
- * mft record specified by @ctx->mrec, beginning at @ctx->attr, for an
- * attribute of @type, optionally @name and @val.
- *
- * If the attribute is found, ntfs_attr_find() returns 0 and @ctx->attr will
- * point to the found attribute.
- *
- * If the attribute is not found, ntfs_attr_find() returns -ENOENT and
- * @ctx->attr will point to the attribute before which the attribute being
- * searched for would need to be inserted if such an action were to be desired.
- *
- * On actual error, ntfs_attr_find() returns -EIO.  In this case @ctx->attr is
- * undefined and in particular do not rely on it not changing.
- *
- * If @ctx->is_first is 'true', the search begins with @ctx->attr itself.  If it
- * is 'false', the search begins after @ctx->attr.
- *
- * If @ic is IGNORE_CASE, the @name comparisson is not case sensitive and
- * @ctx->ntfs_ino must be set to the ntfs inode to which the mft record
- * @ctx->mrec belongs.  This is so we can get at the ntfs volume and hence at
- * the upcase table.  If @ic is CASE_SENSITIVE, the comparison is case
- * sensitive.  When @name is present, @name_len is the @name length in Unicode
- * characters.
- *
- * If @name is not present (NULL), we assume that the unnamed attribute is
- * being searched for.
- *
- * Finally, the resident attribute value @val is looked for, if present.  If
- * @val is not present (NULL), @val_len is ignored.
- *
- * ntfs_attr_find() only searches the specified mft record and it ignores the
- * presence of an attribute list attribute (unless it is the one being searched
- * for, obviously).  If you need to take attribute lists into consideration,
- * use ntfs_attr_lookup() instead (see below).  This also means that you cannot
- * use ntfs_attr_find() to search for extent records of non-resident
- * attributes, as extents with lowest_vcn != 0 are usually described by the
- * attribute list attribute only. - Note that it is possible that the first
- * extent is only in the attribute list while the last extent is in the base
- * mft record, so do not rely on being able to find the first extent in the
- * base mft record.
- *
- * Warning: Never use @val when looking for attribute types which can be
- *	    non-resident as this most likely will result in a crash!
- */
-static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
-{
-	ATTR_RECORD *a;
-	ntfs_volume *vol = ctx->ntfs_ino->vol;
-	ntfschar *upcase = vol->upcase;
-	u32 upcase_len = vol->upcase_len;
-
-	/*
-	 * Iterate over attributes in mft record starting at @ctx->attr, or the
-	 * attribute following that, if @ctx->is_first is 'true'.
-	 */
-	if (ctx->is_first) {
-		a = ctx->attr;
-		ctx->is_first = false;
-	} else
-		a = (ATTR_RECORD*)((u8*)ctx->attr +
-				le32_to_cpu(ctx->attr->length));
-	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
-		u8 *mrec_end = (u8 *)ctx->mrec +
-		               le32_to_cpu(ctx->mrec->bytes_allocated);
-		u8 *name_end;
-
-		/* check whether ATTR_RECORD wrap */
-		if ((u8 *)a < (u8 *)ctx->mrec)
-			break;
-
-		/* check whether Attribute Record Header is within bounds */
-		if ((u8 *)a > mrec_end ||
-		    (u8 *)a + sizeof(ATTR_RECORD) > mrec_end)
-			break;
-
-		/* check whether ATTR_RECORD's name is within bounds */
-		name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
-			   a->name_length * sizeof(ntfschar);
-		if (name_end > mrec_end)
-			break;
-
-		ctx->attr = a;
-		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
-				a->type == AT_END))
-			return -ENOENT;
-		if (unlikely(!a->length))
-			break;
-
-		/* check whether ATTR_RECORD's length wrap */
-		if ((u8 *)a + le32_to_cpu(a->length) < (u8 *)a)
-			break;
-		/* check whether ATTR_RECORD's length is within bounds */
-		if ((u8 *)a + le32_to_cpu(a->length) > mrec_end)
-			break;
-
-		if (a->type != type)
-			continue;
-		/*
-		 * If @name is present, compare the two names.  If @name is
-		 * missing, assume we want an unnamed attribute.
-		 */
-		if (!name) {
-			/* The search failed if the found attribute is named. */
-			if (a->name_length)
-				return -ENOENT;
-		} else if (!ntfs_are_names_equal(name, name_len,
-			    (ntfschar*)((u8*)a + le16_to_cpu(a->name_offset)),
-			    a->name_length, ic, upcase, upcase_len)) {
-			register int rc;
-
-			rc = ntfs_collate_names(name, name_len,
-					(ntfschar*)((u8*)a +
-					le16_to_cpu(a->name_offset)),
-					a->name_length, 1, IGNORE_CASE,
-					upcase, upcase_len);
-			/*
-			 * If @name collates before a->name, there is no
-			 * matching attribute.
-			 */
-			if (rc == -1)
-				return -ENOENT;
-			/* If the strings are not equal, continue search. */
-			if (rc)
-				continue;
-			rc = ntfs_collate_names(name, name_len,
-					(ntfschar*)((u8*)a +
-					le16_to_cpu(a->name_offset)),
-					a->name_length, 1, CASE_SENSITIVE,
-					upcase, upcase_len);
-			if (rc == -1)
-				return -ENOENT;
-			if (rc)
-				continue;
-		}
-		/*
-		 * The names match or @name not present and attribute is
-		 * unnamed.  If no @val specified, we have found the attribute
-		 * and are done.
-		 */
-		if (!val)
-			return 0;
-		/* @val is present; compare values. */
-		else {
-			register int rc;
-
-			rc = memcmp(val, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					min_t(u32, val_len, le32_to_cpu(
-					a->data.resident.value_length)));
-			/*
-			 * If @val collates before the current attribute's
-			 * value, there is no matching attribute.
-			 */
-			if (!rc) {
-				register u32 avl;
-
-				avl = le32_to_cpu(
-						a->data.resident.value_length);
-				if (val_len == avl)
-					return 0;
-				if (val_len < avl)
-					return -ENOENT;
-			} else if (rc < 0)
-				return -ENOENT;
-		}
-	}
-	ntfs_error(vol->sb, "Inode is corrupt.  Run chkdsk.");
-	NVolSetErrors(vol);
-	return -EIO;
-}
-
-/**
- * load_attribute_list - load an attribute list into memory
- * @vol:		ntfs volume from which to read
- * @runlist:		runlist of the attribute list
- * @al_start:		destination buffer
- * @size:		size of the destination buffer in bytes
- * @initialized_size:	initialized size of the attribute list
- *
- * Walk the runlist @runlist and load all clusters from it copying them into
- * the linear buffer @al. The maximum number of bytes copied to @al is @size
- * bytes. Note, @size does not need to be a multiple of the cluster size. If
- * @initialized_size is less than @size, the region in @al between
- * @initialized_size and @size will be zeroed and not read from disk.
- *
- * Return 0 on success or -errno on error.
- */
-int load_attribute_list(ntfs_volume *vol, runlist *runlist, u8 *al_start,
-		const s64 size, const s64 initialized_size)
-{
-	LCN lcn;
-	u8 *al = al_start;
-	u8 *al_end = al + initialized_size;
-	runlist_element *rl;
-	struct buffer_head *bh;
-	struct super_block *sb;
-	unsigned long block_size;
-	unsigned long block, max_block;
-	int err = 0;
-	unsigned char block_size_bits;
-
-	ntfs_debug("Entering.");
-	if (!vol || !runlist || !al || size <= 0 || initialized_size < 0 ||
-			initialized_size > size)
-		return -EINVAL;
-	if (!initialized_size) {
-		memset(al, 0, size);
-		return 0;
-	}
-	sb = vol->sb;
-	block_size = sb->s_blocksize;
-	block_size_bits = sb->s_blocksize_bits;
-	down_read(&runlist->lock);
-	rl = runlist->rl;
-	if (!rl) {
-		ntfs_error(sb, "Cannot read attribute list since runlist is "
-				"missing.");
-		goto err_out;	
-	}
-	/* Read all clusters specified by the runlist one run at a time. */
-	while (rl->length) {
-		lcn = ntfs_rl_vcn_to_lcn(rl, rl->vcn);
-		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
-				(unsigned long long)rl->vcn,
-				(unsigned long long)lcn);
-		/* The attribute list cannot be sparse. */
-		if (lcn < 0) {
-			ntfs_error(sb, "ntfs_rl_vcn_to_lcn() failed.  Cannot "
-					"read attribute list.");
-			goto err_out;
-		}
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		/* Read the run from device in chunks of block_size bytes. */
-		max_block = block + (rl->length << vol->cluster_size_bits >>
-				block_size_bits);
-		ntfs_debug("max_block = 0x%lx.", max_block);
-		do {
-			ntfs_debug("Reading block = 0x%lx.", block);
-			bh = sb_bread(sb, block);
-			if (!bh) {
-				ntfs_error(sb, "sb_bread() failed. Cannot "
-						"read attribute list.");
-				goto err_out;
-			}
-			if (al + block_size >= al_end)
-				goto do_final;
-			memcpy(al, bh->b_data, block_size);
-			brelse(bh);
-			al += block_size;
-		} while (++block < max_block);
-		rl++;
-	}
-	if (initialized_size < size) {
-initialize:
-		memset(al_start + initialized_size, 0, size - initialized_size);
-	}
-done:
-	up_read(&runlist->lock);
-	return err;
-do_final:
-	if (al < al_end) {
-		/*
-		 * Partial block.
-		 *
-		 * Note: The attribute list can be smaller than its allocation
-		 * by multiple clusters.  This has been encountered by at least
-		 * two people running Windows XP, thus we cannot do any
-		 * truncation sanity checking here. (AIA)
-		 */
-		memcpy(al, bh->b_data, al_end - al);
-		brelse(bh);
-		if (initialized_size < size)
-			goto initialize;
-		goto done;
-	}
-	brelse(bh);
-	/* Real overflow! */
-	ntfs_error(sb, "Attribute list buffer overflow. Read attribute list "
-			"is truncated.");
-err_out:
-	err = -EIO;
-	goto done;
-}
-
-/**
- * ntfs_external_attr_find - find an attribute in the attribute list of an inode
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * You should not need to call this function directly.  Use ntfs_attr_lookup()
- * instead.
- *
- * Find an attribute by searching the attribute list for the corresponding
- * attribute list entry.  Having found the entry, map the mft record if the
- * attribute is in a different mft record/inode, ntfs_attr_find() the attribute
- * in there and return it.
- *
- * On first search @ctx->ntfs_ino must be the base mft record and @ctx must
- * have been obtained from a call to ntfs_attr_get_search_ctx().  On subsequent
- * calls @ctx->ntfs_ino can be any extent inode, too (@ctx->base_ntfs_ino is
- * then the base inode).
- *
- * After finishing with the attribute/mft record you need to call
- * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
- * mapped inodes, etc).
- *
- * If the attribute is found, ntfs_external_attr_find() returns 0 and
- * @ctx->attr will point to the found attribute.  @ctx->mrec will point to the
- * mft record in which @ctx->attr is located and @ctx->al_entry will point to
- * the attribute list entry for the attribute.
- *
- * If the attribute is not found, ntfs_external_attr_find() returns -ENOENT and
- * @ctx->attr will point to the attribute in the base mft record before which
- * the attribute being searched for would need to be inserted if such an action
- * were to be desired.  @ctx->mrec will point to the mft record in which
- * @ctx->attr is located and @ctx->al_entry will point to the attribute list
- * entry of the attribute before which the attribute being searched for would
- * need to be inserted if such an action were to be desired.
- *
- * Thus to insert the not found attribute, one wants to add the attribute to
- * @ctx->mrec (the base mft record) and if there is not enough space, the
- * attribute should be placed in a newly allocated extent mft record.  The
- * attribute list entry for the inserted attribute should be inserted in the
- * attribute list attribute at @ctx->al_entry.
- *
- * On actual error, ntfs_external_attr_find() returns -EIO.  In this case
- * @ctx->attr is undefined and in particular do not rely on it not changing.
- */
-static int ntfs_external_attr_find(const ATTR_TYPE type,
-		const ntfschar *name, const u32 name_len,
-		const IGNORE_CASE_BOOL ic, const VCN lowest_vcn,
-		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
-{
-	ntfs_inode *base_ni, *ni;
-	ntfs_volume *vol;
-	ATTR_LIST_ENTRY *al_entry, *next_al_entry;
-	u8 *al_start, *al_end;
-	ATTR_RECORD *a;
-	ntfschar *al_name;
-	u32 al_name_len;
-	int err = 0;
-	static const char *es = " Unmount and run chkdsk.";
-
-	ni = ctx->ntfs_ino;
-	base_ni = ctx->base_ntfs_ino;
-	ntfs_debug("Entering for inode 0x%lx, type 0x%x.", ni->mft_no, type);
-	if (!base_ni) {
-		/* First call happens with the base mft record. */
-		base_ni = ctx->base_ntfs_ino = ctx->ntfs_ino;
-		ctx->base_mrec = ctx->mrec;
-	}
-	if (ni == base_ni)
-		ctx->base_attr = ctx->attr;
-	if (type == AT_END)
-		goto not_found;
-	vol = base_ni->vol;
-	al_start = base_ni->attr_list;
-	al_end = al_start + base_ni->attr_list_size;
-	if (!ctx->al_entry)
-		ctx->al_entry = (ATTR_LIST_ENTRY*)al_start;
-	/*
-	 * Iterate over entries in attribute list starting at @ctx->al_entry,
-	 * or the entry following that, if @ctx->is_first is 'true'.
-	 */
-	if (ctx->is_first) {
-		al_entry = ctx->al_entry;
-		ctx->is_first = false;
-	} else
-		al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry +
-				le16_to_cpu(ctx->al_entry->length));
-	for (;; al_entry = next_al_entry) {
-		/* Out of bounds check. */
-		if ((u8*)al_entry < base_ni->attr_list ||
-				(u8*)al_entry > al_end)
-			break;	/* Inode is corrupt. */
-		ctx->al_entry = al_entry;
-		/* Catch the end of the attribute list. */
-		if ((u8*)al_entry == al_end)
-			goto not_found;
-		if (!al_entry->length)
-			break;
-		if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
-				le16_to_cpu(al_entry->length) > al_end)
-			break;
-		next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
-				le16_to_cpu(al_entry->length));
-		if (le32_to_cpu(al_entry->type) > le32_to_cpu(type))
-			goto not_found;
-		if (type != al_entry->type)
-			continue;
-		/*
-		 * If @name is present, compare the two names.  If @name is
-		 * missing, assume we want an unnamed attribute.
-		 */
-		al_name_len = al_entry->name_length;
-		al_name = (ntfschar*)((u8*)al_entry + al_entry->name_offset);
-		if (!name) {
-			if (al_name_len)
-				goto not_found;
-		} else if (!ntfs_are_names_equal(al_name, al_name_len, name,
-				name_len, ic, vol->upcase, vol->upcase_len)) {
-			register int rc;
-
-			rc = ntfs_collate_names(name, name_len, al_name,
-					al_name_len, 1, IGNORE_CASE,
-					vol->upcase, vol->upcase_len);
-			/*
-			 * If @name collates before al_name, there is no
-			 * matching attribute.
-			 */
-			if (rc == -1)
-				goto not_found;
-			/* If the strings are not equal, continue search. */
-			if (rc)
-				continue;
-			/*
-			 * FIXME: Reverse engineering showed 0, IGNORE_CASE but
-			 * that is inconsistent with ntfs_attr_find().  The
-			 * subsequent rc checks were also different.  Perhaps I
-			 * made a mistake in one of the two.  Need to recheck
-			 * which is correct or at least see what is going on...
-			 * (AIA)
-			 */
-			rc = ntfs_collate_names(name, name_len, al_name,
-					al_name_len, 1, CASE_SENSITIVE,
-					vol->upcase, vol->upcase_len);
-			if (rc == -1)
-				goto not_found;
-			if (rc)
-				continue;
-		}
-		/*
-		 * The names match or @name not present and attribute is
-		 * unnamed.  Now check @lowest_vcn.  Continue search if the
-		 * next attribute list entry still fits @lowest_vcn.  Otherwise
-		 * we have reached the right one or the search has failed.
-		 */
-		if (lowest_vcn && (u8*)next_al_entry >= al_start	    &&
-				(u8*)next_al_entry + 6 < al_end		    &&
-				(u8*)next_al_entry + le16_to_cpu(
-					next_al_entry->length) <= al_end    &&
-				sle64_to_cpu(next_al_entry->lowest_vcn) <=
-					lowest_vcn			    &&
-				next_al_entry->type == al_entry->type	    &&
-				next_al_entry->name_length == al_name_len   &&
-				ntfs_are_names_equal((ntfschar*)((u8*)
-					next_al_entry +
-					next_al_entry->name_offset),
-					next_al_entry->name_length,
-					al_name, al_name_len, CASE_SENSITIVE,
-					vol->upcase, vol->upcase_len))
-			continue;
-		if (MREF_LE(al_entry->mft_reference) == ni->mft_no) {
-			if (MSEQNO_LE(al_entry->mft_reference) != ni->seq_no) {
-				ntfs_error(vol->sb, "Found stale mft "
-						"reference in attribute list "
-						"of base inode 0x%lx.%s",
-						base_ni->mft_no, es);
-				err = -EIO;
-				break;
-			}
-		} else { /* Mft references do not match. */
-			/* If there is a mapped record unmap it first. */
-			if (ni != base_ni)
-				unmap_extent_mft_record(ni);
-			/* Do we want the base record back? */
-			if (MREF_LE(al_entry->mft_reference) ==
-					base_ni->mft_no) {
-				ni = ctx->ntfs_ino = base_ni;
-				ctx->mrec = ctx->base_mrec;
-			} else {
-				/* We want an extent record. */
-				ctx->mrec = map_extent_mft_record(base_ni,
-						le64_to_cpu(
-						al_entry->mft_reference), &ni);
-				if (IS_ERR(ctx->mrec)) {
-					ntfs_error(vol->sb, "Failed to map "
-							"extent mft record "
-							"0x%lx of base inode "
-							"0x%lx.%s",
-							MREF_LE(al_entry->
-							mft_reference),
-							base_ni->mft_no, es);
-					err = PTR_ERR(ctx->mrec);
-					if (err == -ENOENT)
-						err = -EIO;
-					/* Cause @ctx to be sanitized below. */
-					ni = NULL;
-					break;
-				}
-				ctx->ntfs_ino = ni;
-			}
-			ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-					le16_to_cpu(ctx->mrec->attrs_offset));
-		}
-		/*
-		 * ctx->vfs_ino, ctx->mrec, and ctx->attr now point to the
-		 * mft record containing the attribute represented by the
-		 * current al_entry.
-		 */
-		/*
-		 * We could call into ntfs_attr_find() to find the right
-		 * attribute in this mft record but this would be less
-		 * efficient and not quite accurate as ntfs_attr_find() ignores
-		 * the attribute instance numbers for example which become
-		 * important when one plays with attribute lists.  Also,
-		 * because a proper match has been found in the attribute list
-		 * entry above, the comparison can now be optimized.  So it is
-		 * worth re-implementing a simplified ntfs_attr_find() here.
-		 */
-		a = ctx->attr;
-		/*
-		 * Use a manual loop so we can still use break and continue
-		 * with the same meanings as above.
-		 */
-do_next_attr_loop:
-		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_allocated))
-			break;
-		if (a->type == AT_END)
-			break;
-		if (!a->length)
-			break;
-		if (al_entry->instance != a->instance)
-			goto do_next_attr;
-		/*
-		 * If the type and/or the name are mismatched between the
-		 * attribute list entry and the attribute record, there is
-		 * corruption so we break and return error EIO.
-		 */
-		if (al_entry->type != a->type)
-			break;
-		if (!ntfs_are_names_equal((ntfschar*)((u8*)a +
-				le16_to_cpu(a->name_offset)), a->name_length,
-				al_name, al_name_len, CASE_SENSITIVE,
-				vol->upcase, vol->upcase_len))
-			break;
-		ctx->attr = a;
-		/*
-		 * If no @val specified or @val specified and it matches, we
-		 * have found it!
-		 */
-		if (!val || (!a->non_resident && le32_to_cpu(
-				a->data.resident.value_length) == val_len &&
-				!memcmp((u8*)a +
-				le16_to_cpu(a->data.resident.value_offset),
-				val, val_len))) {
-			ntfs_debug("Done, found.");
-			return 0;
-		}
-do_next_attr:
-		/* Proceed to the next attribute in the current mft record. */
-		a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length));
-		goto do_next_attr_loop;
-	}
-	if (!err) {
-		ntfs_error(vol->sb, "Base inode 0x%lx contains corrupt "
-				"attribute list attribute.%s", base_ni->mft_no,
-				es);
-		err = -EIO;
-	}
-	if (ni != base_ni) {
-		if (ni)
-			unmap_extent_mft_record(ni);
-		ctx->ntfs_ino = base_ni;
-		ctx->mrec = ctx->base_mrec;
-		ctx->attr = ctx->base_attr;
-	}
-	if (err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-not_found:
-	/*
-	 * If we were looking for AT_END, we reset the search context @ctx and
-	 * use ntfs_attr_find() to seek to the end of the base mft record.
-	 */
-	if (type == AT_END) {
-		ntfs_attr_reinit_search_ctx(ctx);
-		return ntfs_attr_find(AT_END, name, name_len, ic, val, val_len,
-				ctx);
-	}
-	/*
-	 * The attribute was not found.  Before we return, we want to ensure
-	 * @ctx->mrec and @ctx->attr indicate the position at which the
-	 * attribute should be inserted in the base mft record.  Since we also
-	 * want to preserve @ctx->al_entry we cannot reinitialize the search
-	 * context using ntfs_attr_reinit_search_ctx() as this would set
-	 * @ctx->al_entry to NULL.  Thus we do the necessary bits manually (see
-	 * ntfs_attr_init_search_ctx() below).  Note, we _only_ preserve
-	 * @ctx->al_entry as the remaining fields (base_*) are identical to
-	 * their non base_ counterparts and we cannot set @ctx->base_attr
-	 * correctly yet as we do not know what @ctx->attr will be set to by
-	 * the call to ntfs_attr_find() below.
-	 */
-	if (ni != base_ni)
-		unmap_extent_mft_record(ni);
-	ctx->mrec = ctx->base_mrec;
-	ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-			le16_to_cpu(ctx->mrec->attrs_offset));
-	ctx->is_first = true;
-	ctx->ntfs_ino = base_ni;
-	ctx->base_ntfs_ino = NULL;
-	ctx->base_mrec = NULL;
-	ctx->base_attr = NULL;
-	/*
-	 * In case there are multiple matches in the base mft record, need to
-	 * keep enumerating until we get an attribute not found response (or
-	 * another error), otherwise we would keep returning the same attribute
-	 * over and over again and all programs using us for enumeration would
-	 * lock up in a tight loop.
-	 */
-	do {
-		err = ntfs_attr_find(type, name, name_len, ic, val, val_len,
-				ctx);
-	} while (!err);
-	ntfs_debug("Done, not found.");
-	return err;
-}
-
-/**
- * ntfs_attr_lookup - find an attribute in an ntfs inode
- * @type:	attribute type to find
- * @name:	attribute name to find (optional, i.e. NULL means don't care)
- * @name_len:	attribute name length (only needed if @name present)
- * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
- * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
- * @val:	attribute value to find (optional, resident attributes only)
- * @val_len:	attribute value length
- * @ctx:	search context with mft record and attribute to search from
- *
- * Find an attribute in an ntfs inode.  On first search @ctx->ntfs_ino must
- * be the base mft record and @ctx must have been obtained from a call to
- * ntfs_attr_get_search_ctx().
- *
- * This function transparently handles attribute lists and @ctx is used to
- * continue searches where they were left off at.
- *
- * After finishing with the attribute/mft record you need to call
- * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
- * mapped inodes, etc).
- *
- * Return 0 if the search was successful and -errno if not.
- *
- * When 0, @ctx->attr is the found attribute and it is in mft record
- * @ctx->mrec.  If an attribute list attribute is present, @ctx->al_entry is
- * the attribute list entry of the found attribute.
- *
- * When -ENOENT, @ctx->attr is the attribute which collates just after the
- * attribute being searched for, i.e. if one wants to add the attribute to the
- * mft record this is the correct place to insert it into.  If an attribute
- * list attribute is present, @ctx->al_entry is the attribute list entry which
- * collates just after the attribute list entry of the attribute being searched
- * for, i.e. if one wants to add the attribute to the mft record this is the
- * correct place to insert its attribute list entry into.
- *
- * When -errno != -ENOENT, an error occurred during the lookup.  @ctx->attr is
- * then undefined and in particular you should not rely on it not changing.
- */
-int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const VCN lowest_vcn, const u8 *val, const u32 val_len,
-		ntfs_attr_search_ctx *ctx)
-{
-	ntfs_inode *base_ni;
-
-	ntfs_debug("Entering.");
-	BUG_ON(IS_ERR(ctx->mrec));
-	if (ctx->base_ntfs_ino)
-		base_ni = ctx->base_ntfs_ino;
-	else
-		base_ni = ctx->ntfs_ino;
-	/* Sanity check, just for debugging really. */
-	BUG_ON(!base_ni);
-	if (!NInoAttrList(base_ni) || type == AT_ATTRIBUTE_LIST)
-		return ntfs_attr_find(type, name, name_len, ic, val, val_len,
-				ctx);
-	return ntfs_external_attr_find(type, name, name_len, ic, lowest_vcn,
-			val, val_len, ctx);
-}
-
-/**
- * ntfs_attr_init_search_ctx - initialize an attribute search context
- * @ctx:	attribute search context to initialize
- * @ni:		ntfs inode with which to initialize the search context
- * @mrec:	mft record with which to initialize the search context
- *
- * Initialize the attribute search context @ctx with @ni and @mrec.
- */
-static inline void ntfs_attr_init_search_ctx(ntfs_attr_search_ctx *ctx,
-		ntfs_inode *ni, MFT_RECORD *mrec)
-{
-	*ctx = (ntfs_attr_search_ctx) {
-		.mrec = mrec,
-		/* Sanity checks are performed elsewhere. */
-		.attr = (ATTR_RECORD*)((u8*)mrec +
-				le16_to_cpu(mrec->attrs_offset)),
-		.is_first = true,
-		.ntfs_ino = ni,
-	};
-}
-
-/**
- * ntfs_attr_reinit_search_ctx - reinitialize an attribute search context
- * @ctx:	attribute search context to reinitialize
- *
- * Reinitialize the attribute search context @ctx, unmapping an associated
- * extent mft record if present, and initialize the search context again.
- *
- * This is used when a search for a new attribute is being started to reset
- * the search context to the beginning.
- */
-void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx)
-{
-	if (likely(!ctx->base_ntfs_ino)) {
-		/* No attribute list. */
-		ctx->is_first = true;
-		/* Sanity checks are performed elsewhere. */
-		ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
-				le16_to_cpu(ctx->mrec->attrs_offset));
-		/*
-		 * This needs resetting due to ntfs_external_attr_find() which
-		 * can leave it set despite having zeroed ctx->base_ntfs_ino.
-		 */
-		ctx->al_entry = NULL;
-		return;
-	} /* Attribute list. */
-	if (ctx->ntfs_ino != ctx->base_ntfs_ino)
-		unmap_extent_mft_record(ctx->ntfs_ino);
-	ntfs_attr_init_search_ctx(ctx, ctx->base_ntfs_ino, ctx->base_mrec);
-	return;
-}
-
-/**
- * ntfs_attr_get_search_ctx - allocate/initialize a new attribute search context
- * @ni:		ntfs inode with which to initialize the search context
- * @mrec:	mft record with which to initialize the search context
- *
- * Allocate a new attribute search context, initialize it with @ni and @mrec,
- * and return it. Return NULL if allocation failed.
- */
-ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni, MFT_RECORD *mrec)
-{
-	ntfs_attr_search_ctx *ctx;
-
-	ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, GFP_NOFS);
-	if (ctx)
-		ntfs_attr_init_search_ctx(ctx, ni, mrec);
-	return ctx;
-}
-
-/**
- * ntfs_attr_put_search_ctx - release an attribute search context
- * @ctx:	attribute search context to free
- *
- * Release the attribute search context @ctx, unmapping an associated extent
- * mft record if present.
- */
-void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx)
-{
-	if (ctx->base_ntfs_ino && ctx->ntfs_ino != ctx->base_ntfs_ino)
-		unmap_extent_mft_record(ctx->ntfs_ino);
-	kmem_cache_free(ntfs_attr_ctx_cache, ctx);
-	return;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_attr_find_in_attrdef - find an attribute in the $AttrDef system file
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to find
- *
- * Search for the attribute definition record corresponding to the attribute
- * @type in the $AttrDef system file.
- *
- * Return the attribute type definition record if found and NULL if not found.
- */
-static ATTR_DEF *ntfs_attr_find_in_attrdef(const ntfs_volume *vol,
-		const ATTR_TYPE type)
-{
-	ATTR_DEF *ad;
-
-	BUG_ON(!vol->attrdef);
-	BUG_ON(!type);
-	for (ad = vol->attrdef; (u8*)ad - (u8*)vol->attrdef <
-			vol->attrdef_size && ad->type; ++ad) {
-		/* We have not found it yet, carry on searching. */
-		if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type)))
-			continue;
-		/* We found the attribute; return it. */
-		if (likely(ad->type == type))
-			return ad;
-		/* We have gone too far already.  No point in continuing. */
-		break;
-	}
-	/* Attribute not found. */
-	ntfs_debug("Attribute type 0x%x not found in $AttrDef.",
-			le32_to_cpu(type));
-	return NULL;
-}
-
-/**
- * ntfs_attr_size_bounds_check - check a size of an attribute type for validity
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- * @size:	size which to check
- *
- * Check whether the @size in bytes is valid for an attribute of @type on the
- * ntfs volume @vol.  This information is obtained from $AttrDef system file.
- *
- * Return 0 if valid, -ERANGE if not valid, or -ENOENT if the attribute is not
- * listed in $AttrDef.
- */
-int ntfs_attr_size_bounds_check(const ntfs_volume *vol, const ATTR_TYPE type,
-		const s64 size)
-{
-	ATTR_DEF *ad;
-
-	BUG_ON(size < 0);
-	/*
-	 * $ATTRIBUTE_LIST has a maximum size of 256kiB, but this is not
-	 * listed in $AttrDef.
-	 */
-	if (unlikely(type == AT_ATTRIBUTE_LIST && size > 256 * 1024))
-		return -ERANGE;
-	/* Get the $AttrDef entry for the attribute @type. */
-	ad = ntfs_attr_find_in_attrdef(vol, type);
-	if (unlikely(!ad))
-		return -ENOENT;
-	/* Do the bounds check. */
-	if (((sle64_to_cpu(ad->min_size) > 0) &&
-			size < sle64_to_cpu(ad->min_size)) ||
-			((sle64_to_cpu(ad->max_size) > 0) && size >
-			sle64_to_cpu(ad->max_size)))
-		return -ERANGE;
-	return 0;
-}
-
-/**
- * ntfs_attr_can_be_non_resident - check if an attribute can be non-resident
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- *
- * Check whether the attribute of @type on the ntfs volume @vol is allowed to
- * be non-resident.  This information is obtained from $AttrDef system file.
- *
- * Return 0 if the attribute is allowed to be non-resident, -EPERM if not, and
- * -ENOENT if the attribute is not listed in $AttrDef.
- */
-int ntfs_attr_can_be_non_resident(const ntfs_volume *vol, const ATTR_TYPE type)
-{
-	ATTR_DEF *ad;
-
-	/* Find the attribute definition record in $AttrDef. */
-	ad = ntfs_attr_find_in_attrdef(vol, type);
-	if (unlikely(!ad))
-		return -ENOENT;
-	/* Check the flags and return the result. */
-	if (ad->flags & ATTR_DEF_RESIDENT)
-		return -EPERM;
-	return 0;
-}
-
-/**
- * ntfs_attr_can_be_resident - check if an attribute can be resident
- * @vol:	ntfs volume to which the attribute belongs
- * @type:	attribute type which to check
- *
- * Check whether the attribute of @type on the ntfs volume @vol is allowed to
- * be resident.  This information is derived from our ntfs knowledge and may
- * not be completely accurate, especially when user defined attributes are
- * present.  Basically we allow everything to be resident except for index
- * allocation and $EA attributes.
- *
- * Return 0 if the attribute is allowed to be non-resident and -EPERM if not.
- *
- * Warning: In the system file $MFT the attribute $Bitmap must be non-resident
- *	    otherwise windows will not boot (blue screen of death)!  We cannot
- *	    check for this here as we do not know which inode's $Bitmap is
- *	    being asked about so the caller needs to special case this.
- */
-int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
-{
-	if (type == AT_INDEX_ALLOCATION)
-		return -EPERM;
-	return 0;
-}
-
-/**
- * ntfs_attr_record_resize - resize an attribute record
- * @m:		mft record containing attribute record
- * @a:		attribute record to resize
- * @new_size:	new size in bytes to which to resize the attribute record @a
- *
- * Resize the attribute record @a, i.e. the resident part of the attribute, in
- * the mft record @m to @new_size bytes.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
- *
- * Note: On error, no modifications have been performed whatsoever.
- *
- * Warning: If you make a record smaller without having copied all the data you
- *	    are interested in the data may be overwritten.
- */
-int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size)
-{
-	ntfs_debug("Entering for new_size %u.", new_size);
-	/* Align to 8 bytes if it is not already done. */
-	if (new_size & 7)
-		new_size = (new_size + 7) & ~7;
-	/* If the actual attribute length has changed, move things around. */
-	if (new_size != le32_to_cpu(a->length)) {
-		u32 new_muse = le32_to_cpu(m->bytes_in_use) -
-				le32_to_cpu(a->length) + new_size;
-		/* Not enough space in this mft record. */
-		if (new_muse > le32_to_cpu(m->bytes_allocated))
-			return -ENOSPC;
-		/* Move attributes following @a to their new location. */
-		memmove((u8*)a + new_size, (u8*)a + le32_to_cpu(a->length),
-				le32_to_cpu(m->bytes_in_use) - ((u8*)a -
-				(u8*)m) - le32_to_cpu(a->length));
-		/* Adjust @m to reflect the change in used space. */
-		m->bytes_in_use = cpu_to_le32(new_muse);
-		/* Adjust @a to reflect the new size. */
-		if (new_size >= offsetof(ATTR_REC, length) + sizeof(a->length))
-			a->length = cpu_to_le32(new_size);
-	}
-	return 0;
-}
-
-/**
- * ntfs_resident_attr_value_resize - resize the value of a resident attribute
- * @m:		mft record containing attribute record
- * @a:		attribute record whose value to resize
- * @new_size:	new size in bytes to which to resize the attribute value of @a
- *
- * Resize the value of the attribute @a in the mft record @m to @new_size bytes.
- * If the value is made bigger, the newly allocated space is cleared.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
- *
- * Note: On error, no modifications have been performed whatsoever.
- *
- * Warning: If you make a record smaller without having copied all the data you
- *	    are interested in the data may be overwritten.
- */
-int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
-		const u32 new_size)
-{
-	u32 old_size;
-
-	/* Resize the resident part of the attribute record. */
-	if (ntfs_attr_record_resize(m, a,
-			le16_to_cpu(a->data.resident.value_offset) + new_size))
-		return -ENOSPC;
-	/*
-	 * The resize succeeded!  If we made the attribute value bigger, clear
-	 * the area between the old size and @new_size.
-	 */
-	old_size = le32_to_cpu(a->data.resident.value_length);
-	if (new_size > old_size)
-		memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
-				old_size, 0, new_size - old_size);
-	/* Finally update the length of the attribute value. */
-	a->data.resident.value_length = cpu_to_le32(new_size);
-	return 0;
-}
-
-/**
- * ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
- * @ni:		ntfs inode describing the attribute to convert
- * @data_size:	size of the resident data to copy to the non-resident attribute
- *
- * Convert the resident ntfs attribute described by the ntfs inode @ni to a
- * non-resident one.
- *
- * @data_size must be equal to the attribute value size.  This is needed since
- * we need to know the size before we can map the mft record and our callers
- * always know it.  The reason we cannot simply read the size from the vfs
- * inode i_size is that this is not necessarily uptodate.  This happens when
- * ntfs_attr_make_non_resident() is called in the ->truncate call path(s).
- *
- * Return 0 on success and -errno on error.  The following error return codes
- * are defined:
- *	-EPERM	- The attribute is not allowed to be non-resident.
- *	-ENOMEM	- Not enough memory.
- *	-ENOSPC	- Not enough disk space.
- *	-EINVAL	- Attribute not defined on the volume.
- *	-EIO	- I/o error or other error.
- * Note that -ENOSPC is also returned in the case that there is not enough
- * space in the mft record to do the conversion.  This can happen when the mft
- * record is already very full.  The caller is responsible for trying to make
- * space in the mft record and trying again.  FIXME: Do we need a separate
- * error return code for this kind of -ENOSPC or is it always worth trying
- * again in case the attribute may then fit in a resident state so no need to
- * make it non-resident at all?  Ho-hum...  (AIA)
- *
- * NOTE to self: No changes in the attribute list are required to move from
- *		 a resident to a non-resident attribute.
- *
- * Locking: - The caller must hold i_mutex on the inode.
- */
-int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
-{
-	s64 new_size;
-	struct inode *vi = VFS_I(ni);
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	struct page *page;
-	runlist_element *rl;
-	u8 *kaddr;
-	unsigned long flags;
-	int mp_size, mp_ofs, name_ofs, arec_size, err, err2;
-	u32 attr_size;
-	u8 old_res_attr_flags;
-
-	/* Check that the attribute is allowed to be non-resident. */
-	err = ntfs_attr_can_be_non_resident(vol, ni->type);
-	if (unlikely(err)) {
-		if (err == -EPERM)
-			ntfs_debug("Attribute is not allowed to be "
-					"non-resident.");
-		else
-			ntfs_debug("Attribute not defined on the NTFS "
-					"volume!");
-		return err;
-	}
-	/*
-	 * FIXME: Compressed and encrypted attributes are not supported when
-	 * writing and we should never have gotten here for them.
-	 */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoEncrypted(ni));
-	/*
-	 * The size needs to be aligned to a cluster boundary for allocation
-	 * purposes.
-	 */
-	new_size = (data_size + vol->cluster_size - 1) &
-			~(vol->cluster_size - 1);
-	if (new_size > 0) {
-		/*
-		 * Will need the page later and since the page lock nests
-		 * outside all ntfs locks, we need to get the page now.
-		 */
-		page = find_or_create_page(vi->i_mapping, 0,
-				mapping_gfp_mask(vi->i_mapping));
-		if (unlikely(!page))
-			return -ENOMEM;
-		/* Start by allocating clusters to hold the attribute value. */
-		rl = ntfs_cluster_alloc(vol, 0, new_size >>
-				vol->cluster_size_bits, -1, DATA_ZONE, true);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			ntfs_debug("Failed to allocate cluster%s, error code "
-					"%i.", (new_size >>
-					vol->cluster_size_bits) > 1 ? "s" : "",
-					err);
-			goto page_err_out;
-		}
-	} else {
-		rl = NULL;
-		page = NULL;
-	}
-	/* Determine the size of the mapping pairs array. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl, 0, -1);
-	if (unlikely(mp_size < 0)) {
-		err = mp_size;
-		ntfs_debug("Failed to get size for mapping pairs array, error "
-				"code %i.", err);
-		goto rl_err_out;
-	}
-	down_write(&ni->runlist.lock);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(NInoNonResident(ni));
-	BUG_ON(a->non_resident);
-	/*
-	 * Calculate new offsets for the name and the mapping pairs array.
-	 */
-	if (NInoSparse(ni) || NInoCompressed(ni))
-		name_ofs = (offsetof(ATTR_REC,
-				data.non_resident.compressed_size) +
-				sizeof(a->data.non_resident.compressed_size) +
-				7) & ~7;
-	else
-		name_ofs = (offsetof(ATTR_REC,
-				data.non_resident.compressed_size) + 7) & ~7;
-	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
-	/*
-	 * Determine the size of the resident part of the now non-resident
-	 * attribute record.
-	 */
-	arec_size = (mp_ofs + mp_size + 7) & ~7;
-	/*
-	 * If the page is not uptodate bring it uptodate by copying from the
-	 * attribute value.
-	 */
-	attr_size = le32_to_cpu(a->data.resident.value_length);
-	BUG_ON(attr_size != data_size);
-	if (page && !PageUptodate(page)) {
-		kaddr = kmap_atomic(page);
-		memcpy(kaddr, (u8*)a +
-				le16_to_cpu(a->data.resident.value_offset),
-				attr_size);
-		memset(kaddr + attr_size, 0, PAGE_SIZE - attr_size);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(page);
-		SetPageUptodate(page);
-	}
-	/* Backup the attribute flag. */
-	old_res_attr_flags = a->data.resident.flags;
-	/* Resize the resident part of the attribute record. */
-	err = ntfs_attr_record_resize(m, a, arec_size);
-	if (unlikely(err))
-		goto err_out;
-	/*
-	 * Convert the resident part of the attribute record to describe a
-	 * non-resident attribute.
-	 */
-	a->non_resident = 1;
-	/* Move the attribute name if it exists and update the offset. */
-	if (a->name_length)
-		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
-				a->name_length * sizeof(ntfschar));
-	a->name_offset = cpu_to_le16(name_ofs);
-	/* Setup the fields specific to non-resident attributes. */
-	a->data.non_resident.lowest_vcn = 0;
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_size - 1) >>
-			vol->cluster_size_bits);
-	a->data.non_resident.mapping_pairs_offset = cpu_to_le16(mp_ofs);
-	memset(&a->data.non_resident.reserved, 0,
-			sizeof(a->data.non_resident.reserved));
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_size);
-	a->data.non_resident.data_size =
-			a->data.non_resident.initialized_size =
-			cpu_to_sle64(attr_size);
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		a->data.non_resident.compression_unit = 0;
-		if (NInoCompressed(ni) || vol->major_ver < 3)
-			a->data.non_resident.compression_unit = 4;
-		a->data.non_resident.compressed_size =
-				a->data.non_resident.allocated_size;
-	} else
-		a->data.non_resident.compression_unit = 0;
-	/* Generate the mapping pairs array into the attribute record. */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a + mp_ofs,
-			arec_size - mp_ofs, rl, 0, -1, NULL);
-	if (unlikely(err)) {
-		ntfs_debug("Failed to build mapping pairs, error code %i.",
-				err);
-		goto undo_err_out;
-	}
-	/* Setup the in-memory attribute structure to be non-resident. */
-	ni->runlist.rl = rl;
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_size;
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		ni->itype.compressed.size = ni->allocated_size;
-		if (a->data.non_resident.compression_unit) {
-			ni->itype.compressed.block_size = 1U << (a->data.
-					non_resident.compression_unit +
-					vol->cluster_size_bits);
-			ni->itype.compressed.block_size_bits =
-					ffs(ni->itype.compressed.block_size) -
-					1;
-			ni->itype.compressed.block_clusters = 1U <<
-					a->data.non_resident.compression_unit;
-		} else {
-			ni->itype.compressed.block_size = 0;
-			ni->itype.compressed.block_size_bits = 0;
-			ni->itype.compressed.block_clusters = 0;
-		}
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	} else
-		vi->i_blocks = ni->allocated_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * This needs to be last since the address space operations ->read_folio
-	 * and ->writepage can run concurrently with us as they are not
-	 * serialized on i_mutex.  Note, we are not allowed to fail once we flip
-	 * this switch, which is another reason to do this last.
-	 */
-	NInoSetNonResident(ni);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	if (page) {
-		set_page_dirty(page);
-		unlock_page(page);
-		put_page(page);
-	}
-	ntfs_debug("Done.");
-	return 0;
-undo_err_out:
-	/* Convert the attribute back into a resident attribute. */
-	a->non_resident = 0;
-	/* Move the attribute name if it exists and update the offset. */
-	name_ofs = (offsetof(ATTR_RECORD, data.resident.reserved) +
-			sizeof(a->data.resident.reserved) + 7) & ~7;
-	if (a->name_length)
-		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
-				a->name_length * sizeof(ntfschar));
-	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
-	a->name_offset = cpu_to_le16(name_ofs);
-	arec_size = (mp_ofs + attr_size + 7) & ~7;
-	/* Resize the resident part of the attribute record. */
-	err2 = ntfs_attr_record_resize(m, a, arec_size);
-	if (unlikely(err2)) {
-		/*
-		 * This cannot happen (well if memory corruption is at work it
-		 * could happen in theory), but deal with it as well as we can.
-		 * If the old size is too small, truncate the attribute,
-		 * otherwise simply give it a larger allocated size.
-		 * FIXME: Should check whether chkdsk complains when the
-		 * allocated size is much bigger than the resident value size.
-		 */
-		arec_size = le32_to_cpu(a->length);
-		if ((mp_ofs + attr_size) > arec_size) {
-			err2 = attr_size;
-			attr_size = arec_size - mp_ofs;
-			ntfs_error(vol->sb, "Failed to undo partial resident "
-					"to non-resident attribute "
-					"conversion.  Truncating inode 0x%lx, "
-					"attribute type 0x%x from %i bytes to "
-					"%i bytes to maintain metadata "
-					"consistency.  THIS MEANS YOU ARE "
-					"LOSING %i BYTES DATA FROM THIS %s.",
-					vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type),
-					err2, attr_size, err2 - attr_size,
-					((ni->type == AT_DATA) &&
-					!ni->name_len) ? "FILE": "ATTRIBUTE");
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->initialized_size = attr_size;
-			i_size_write(vi, attr_size);
-			write_unlock_irqrestore(&ni->size_lock, flags);
-		}
-	}
-	/* Setup the fields specific to resident attributes. */
-	a->data.resident.value_length = cpu_to_le32(attr_size);
-	a->data.resident.value_offset = cpu_to_le16(mp_ofs);
-	a->data.resident.flags = old_res_attr_flags;
-	memset(&a->data.resident.reserved, 0,
-			sizeof(a->data.resident.reserved));
-	/* Copy the data from the page back to the attribute value. */
-	if (page) {
-		kaddr = kmap_atomic(page);
-		memcpy((u8*)a + mp_ofs, kaddr, attr_size);
-		kunmap_atomic(kaddr);
-	}
-	/* Setup the allocated size in the ntfs inode in case it changed. */
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = arec_size - mp_ofs;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ni->runlist.rl = NULL;
-	up_write(&ni->runlist.lock);
-rl_err_out:
-	if (rl) {
-		if (ntfs_cluster_free_from_rl(vol, rl) < 0) {
-			ntfs_error(vol->sb, "Failed to release allocated "
-					"cluster(s) in error code path.  Run "
-					"chkdsk to recover the lost "
-					"cluster(s).");
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl);
-page_err_out:
-		unlock_page(page);
-		put_page(page);
-	}
-	if (err == -EINVAL)
-		err = -EIO;
-	return err;
-}
-
-/**
- * ntfs_attr_extend_allocation - extend the allocated space of an attribute
- * @ni:			ntfs inode of the attribute whose allocation to extend
- * @new_alloc_size:	new size in bytes to which to extend the allocation to
- * @new_data_size:	new size in bytes to which to extend the data to
- * @data_start:		beginning of region which is required to be non-sparse
- *
- * Extend the allocated space of an attribute described by the ntfs inode @ni
- * to @new_alloc_size bytes.  If @data_start is -1, the whole extension may be
- * implemented as a hole in the file (as long as both the volume and the ntfs
- * inode @ni have sparse support enabled).  If @data_start is >= 0, then the
- * region between the old allocated size and @data_start - 1 may be made sparse
- * but the regions between @data_start and @new_alloc_size must be backed by
- * actual clusters.
- *
- * If @new_data_size is -1, it is ignored.  If it is >= 0, then the data size
- * of the attribute is extended to @new_data_size.  Note that the i_size of the
- * vfs inode is not updated.  Only the data size in the base attribute record
- * is updated.  The caller has to update i_size separately if this is required.
- * WARNING: It is a BUG() for @new_data_size to be smaller than the old data
- * size as well as for @new_data_size to be greater than @new_alloc_size.
- *
- * For resident attributes this involves resizing the attribute record and if
- * necessary moving it and/or other attributes into extent mft records and/or
- * converting the attribute to a non-resident attribute which in turn involves
- * extending the allocation of a non-resident attribute as described below.
- *
- * For non-resident attributes this involves allocating clusters in the data
- * zone on the volume (except for regions that are being made sparse) and
- * extending the run list to describe the allocated clusters as well as
- * updating the mapping pairs array of the attribute.  This in turn involves
- * resizing the attribute record and if necessary moving it and/or other
- * attributes into extent mft records and/or splitting the attribute record
- * into multiple extent attribute records.
- *
- * Also, the attribute list attribute is updated if present and in some of the
- * above cases (the ones where extent mft records/attributes come into play),
- * an attribute list attribute is created if not already present.
- *
- * Return the new allocated size on success and -errno on error.  In the case
- * that an error is encountered but a partial extension at least up to
- * @data_start (if present) is possible, the allocation is partially extended
- * and this is returned.  This means the caller must check the returned size to
- * determine if the extension was partial.  If @data_start is -1 then partial
- * allocations are not performed.
- *
- * WARNING: Do not call ntfs_attr_extend_allocation() for $MFT/$DATA.
- *
- * Locking: This function takes the runlist lock of @ni for writing as well as
- * locking the mft record of the base ntfs inode.  These locks are maintained
- * throughout execution of the function.  These locks are required so that the
- * attribute can be resized safely and so that it can for example be converted
- * from resident to non-resident safely.
- *
- * TODO: At present attribute list attribute handling is not implemented.
- *
- * TODO: At present it is not safe to call this function for anything other
- * than the $DATA attribute(s) of an uncompressed and unencrypted file.
- */
-s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
-		const s64 new_data_size, const s64 data_start)
-{
-	VCN vcn;
-	s64 ll, allocated_size, start = data_start;
-	struct inode *vi = VFS_I(ni);
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	runlist_element *rl, *rl2;
-	unsigned long flags;
-	int err, mp_size;
-	u32 attr_len = 0; /* Silence stupid gcc warning. */
-	bool mp_rebuilt;
-
-#ifdef DEBUG
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
-			"old_allocated_size 0x%llx, "
-			"new_allocated_size 0x%llx, new_data_size 0x%llx, "
-			"data_start 0x%llx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)allocated_size,
-			(unsigned long long)new_alloc_size,
-			(unsigned long long)new_data_size,
-			(unsigned long long)start);
-#endif
-retry_extend:
-	/*
-	 * For non-resident attributes, @start and @new_size need to be aligned
-	 * to cluster boundaries for allocation purposes.
-	 */
-	if (NInoNonResident(ni)) {
-		if (start > 0)
-			start &= ~(s64)vol->cluster_size_mask;
-		new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
-				~(s64)vol->cluster_size_mask;
-	}
-	BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
-	/* Check if new size is allowed in $AttrDef. */
-	err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
-	if (unlikely(err)) {
-		/* Only emit errors when the write will fail completely. */
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (start < 0 || start >= allocated_size) {
-			if (err == -ERANGE) {
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because the new "
-						"allocation would exceed the "
-						"maximum allowed size for "
-						"this attribute type.",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-			} else {
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because this "
-						"attribute type is not "
-						"defined on the NTFS volume.  "
-						"Possible corruption!  You "
-						"should run chkdsk!",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-			}
-		}
-		/* Translate error code to be POSIX conformant for write(2). */
-		if (err == -ERANGE)
-			err = -EFBIG;
-		else
-			err = -EIO;
-		return err;
-	}
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/*
-	 * We will be modifying both the runlist (if non-resident) and the mft
-	 * record so lock them both down.
-	 */
-	down_write(&ni->runlist.lock);
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * If non-resident, seek to the last extent.  If resident, there is
-	 * only one extent, so seek to that.
-	 */
-	vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
-			0;
-	/*
-	 * Abort if someone did the work whilst we waited for the locks.  If we
-	 * just converted the attribute from resident to non-resident it is
-	 * likely that exactly this has happened already.  We cannot quite
-	 * abort if we need to update the data size.
-	 */
-	if (unlikely(new_alloc_size <= allocated_size)) {
-		ntfs_debug("Allocated size already exceeds requested size.");
-		new_alloc_size = allocated_size;
-		if (new_data_size < 0)
-			goto done;
-		/*
-		 * We want the first attribute extent so that we can update the
-		 * data size.
-		 */
-		vcn = 0;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, vcn, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/* Use goto to reduce indentation. */
-	if (a->non_resident)
-		goto do_non_resident_extend;
-	BUG_ON(NInoNonResident(ni));
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	/*
-	 * Extend the attribute record to be able to store the new attribute
-	 * size.  ntfs_attr_record_resize() will not do anything if the size is
-	 * not changing.
-	 */
-	if (new_alloc_size < vol->mft_record_size &&
-			!ntfs_attr_record_resize(m, a,
-			le16_to_cpu(a->data.resident.value_offset) +
-			new_alloc_size)) {
-		/* The resize succeeded! */
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		if (new_data_size >= 0) {
-			BUG_ON(new_data_size < attr_len);
-			a->data.resident.value_length =
-					cpu_to_le32((u32)new_data_size);
-		}
-		goto flush_done;
-	}
-	/*
-	 * We have to drop all the locks so we can call
-	 * ntfs_attr_make_non_resident().  This could be optimised by try-
-	 * locking the first page cache page and only if that fails dropping
-	 * the locks, locking the page, and redoing all the locking and
-	 * lookups.  While this would be a huge optimisation, it is not worth
-	 * it as this is definitely a slow code path.
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	/*
-	 * Not enough space in the mft record, try to make the attribute
-	 * non-resident and if successful restart the extension process.
-	 */
-	err = ntfs_attr_make_non_resident(ni, attr_len);
-	if (likely(!err))
-		goto retry_extend;
-	/*
-	 * Could not make non-resident.  If this is due to this not being
-	 * permitted for this attribute type or there not being enough space,
-	 * try to make other attributes non-resident.  Otherwise fail.
-	 */
-	if (unlikely(err != -EPERM && err != -ENOSPC)) {
-		/* Only emit errors when the write will fail completely. */
-		read_lock_irqsave(&ni->size_lock, flags);
-		allocated_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the conversion from resident "
-					"to non-resident attribute failed "
-					"with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		goto conv_err_out;
-	}
-	/* TODO: Not implemented from here, abort. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	allocated_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (start < 0 || start >= allocated_size) {
-		if (err == -ENOSPC)
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record/on disk for the non-resident "
-					"attribute value.  This case is not "
-					"implemented yet.");
-		else /* if (err == -EPERM) */
-			ntfs_error(vol->sb, "This attribute type may not be "
-					"non-resident.  This case is not "
-					"implemented yet.");
-	}
-	err = -EOPNOTSUPP;
-	goto conv_err_out;
-#if 0
-	// TODO: Attempt to make other attributes non-resident.
-	if (!err)
-		goto do_resident_extend;
-	/*
-	 * Both the attribute list attribute and the standard information
-	 * attribute must remain in the base inode.  Thus, if this is one of
-	 * these attributes, we have to try to move other attributes out into
-	 * extent mft records instead.
-	 */
-	if (ni->type == AT_ATTRIBUTE_LIST ||
-			ni->type == AT_STANDARD_INFORMATION) {
-		// TODO: Attempt to move other attributes into extent mft
-		// records.
-		err = -EOPNOTSUPP;
-		if (!err)
-			goto do_resident_extend;
-		goto err_out;
-	}
-	// TODO: Attempt to move this attribute to an extent mft record, but
-	// only if it is not already the only attribute in an mft record in
-	// which case there would be nothing to gain.
-	err = -EOPNOTSUPP;
-	if (!err)
-		goto do_resident_extend;
-	/* There is nothing we can do to make enough space. )-: */
-	goto err_out;
-#endif
-do_non_resident_extend:
-	BUG_ON(!NInoNonResident(ni));
-	if (new_alloc_size == allocated_size) {
-		BUG_ON(vcn);
-		goto alloc_done;
-	}
-	/*
-	 * If the data starts after the end of the old allocation, this is a
-	 * $DATA attribute and sparse attributes are enabled on the volume and
-	 * for this inode, then create a sparse region between the old
-	 * allocated size and the start of the data.  Otherwise simply proceed
-	 * with filling the whole space between the old allocated size and the
-	 * new allocated size with clusters.
-	 */
-	if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
-			!NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
-		goto skip_sparse;
-	// TODO: This is not implemented yet.  We just fill in with real
-	// clusters for now...
-	ntfs_debug("Inserting holes is not-implemented yet.  Falling back to "
-			"allocating real clusters instead.");
-skip_sparse:
-	rl = ni->runlist.rl;
-	if (likely(rl)) {
-		/* Seek to the end of the runlist. */
-		while (rl->length)
-			rl++;
-	}
-	/* If this attribute extent is not mapped, map it now. */
-	if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
-			(rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
-			(rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
-		if (!rl && !allocated_size)
-			goto first_alloc;
-		rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			if (start < 0 || start >= allocated_size)
-				ntfs_error(vol->sb, "Cannot extend allocation "
-						"of inode 0x%lx, attribute "
-						"type 0x%x, because the "
-						"mapping of a runlist "
-						"fragment failed with error "
-						"code %i.", vi->i_ino,
-						(unsigned)le32_to_cpu(ni->type),
-						err);
-			if (err != -ENOMEM)
-				err = -EIO;
-			goto err_out;
-		}
-		ni->runlist.rl = rl;
-		/* Seek to the end of the runlist. */
-		while (rl->length)
-			rl++;
-	}
-	/*
-	 * We now know the runlist of the last extent is mapped and @rl is at
-	 * the end of the runlist.  We want to begin allocating clusters
-	 * starting at the last allocated cluster to reduce fragmentation.  If
-	 * there are no valid LCNs in the attribute we let the cluster
-	 * allocator choose the starting cluster.
-	 */
-	/* If the last LCN is a hole or simillar seek back to last real LCN. */
-	while (rl->lcn < 0 && rl > ni->runlist.rl)
-		rl--;
-first_alloc:
-	// FIXME: Need to implement partial allocations so at least part of the
-	// write can be performed when start >= 0.  (Needed for POSIX write(2)
-	// conformance.)
-	rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
-			(new_alloc_size - allocated_size) >>
-			vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
-			rl->lcn + rl->length : -1, DATA_ZONE, true);
-	if (IS_ERR(rl2)) {
-		err = PTR_ERR(rl2);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the allocation of clusters "
-					"failed with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM && err != -ENOSPC)
-			err = -EIO;
-		goto err_out;
-	}
-	rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
-	if (IS_ERR(rl)) {
-		err = PTR_ERR(rl);
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because the runlist merge failed "
-					"with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		if (ntfs_cluster_free_from_rl(vol, rl2)) {
-			ntfs_error(vol->sb, "Failed to release allocated "
-					"cluster(s) in error code path.  Run "
-					"chkdsk to recover the lost "
-					"cluster(s).");
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl2);
-		goto err_out;
-	}
-	ni->runlist.rl = rl;
-	ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
-			allocated_size) >> vol->cluster_size_bits);
-	/* Find the runlist element with which the attribute extent starts. */
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
-	BUG_ON(!rl2);
-	BUG_ON(!rl2->length);
-	BUG_ON(rl2->lcn < LCN_HOLE);
-	mp_rebuilt = false;
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		err = mp_size;
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because determining the size for the "
-					"mapping pairs failed with error code "
-					"%i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		err = -EIO;
-		goto undo_alloc;
-	}
-	/* Extend the attribute record to fit the bigger mapping pairs array. */
-	attr_len = le32_to_cpu(a->length);
-	err = ntfs_attr_record_resize(m, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(err)) {
-		BUG_ON(err != -ENOSPC);
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record,
-		// possibly by extending this extent partially and filling it
-		// and creating a new extent for the remainder, or by making
-		// other attributes non-resident and/or by moving other
-		// attributes out of this mft record.
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record for the extended attribute "
-					"record.  This case is not "
-					"implemented yet.");
-		err = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	mp_rebuilt = true;
-	/* Generate the mapping pairs array directly into the attr record. */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(err)) {
-		if (start < 0 || start >= allocated_size)
-			ntfs_error(vol->sb, "Cannot extend allocation of "
-					"inode 0x%lx, attribute type 0x%x, "
-					"because building the mapping pairs "
-					"failed with error code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-		err = -EIO;
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
-			vol->cluster_size_bits) - 1);
-	/*
-	 * We now have extended the allocated size of the attribute.  Reflect
-	 * this in the ntfs_inode structure and the attribute record.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err))
-			goto restore_undo_alloc;
-		/* @m is not used any more so no need to set it. */
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_alloc_size;
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
-	/*
-	 * FIXME: This would fail if @ni is a directory, $MFT, or an index,
-	 * since those can have sparse/compressed set.  For example can be
-	 * set compressed even though it is not compressed itself and in that
-	 * case the bit means that files are to be created compressed in the
-	 * directory...  At present this is ok as this code is only called for
-	 * regular files, and only for their $DATA attribute(s).
-	 * FIXME: The calculation is wrong if we created a hole above.  For now
-	 * it does not matter as we never create holes.
-	 */
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		ni->itype.compressed.size += new_alloc_size - allocated_size;
-		a->data.non_resident.compressed_size =
-				cpu_to_sle64(ni->itype.compressed.size);
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	} else
-		vi->i_blocks = new_alloc_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-alloc_done:
-	if (new_data_size >= 0) {
-		BUG_ON(new_data_size <
-				sle64_to_cpu(a->data.non_resident.data_size));
-		a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
-	}
-flush_done:
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-done:
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	ntfs_debug("Done, new_allocated_size 0x%llx.",
-			(unsigned long long)new_alloc_size);
-	return new_alloc_size;
-restore_undo_alloc:
-	if (start < 0 || start >= allocated_size)
-		ntfs_error(vol->sb, "Cannot complete extension of allocation "
-				"of inode 0x%lx, attribute type 0x%x, because "
-				"lookup of first attribute extent failed with "
-				"error code %i.", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), err);
-	if (err == -ENOENT)
-		err = -EIO;
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
-			allocated_size >> vol->cluster_size_bits, NULL, 0,
-			ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"attribute in error code path.  Run chkdsk to "
-				"recover.");
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->allocated_size = new_alloc_size;
-		/*
-		 * FIXME: This would fail if @ni is a directory...  See above.
-		 * FIXME: The calculation is wrong if we created a hole above.
-		 * For now it does not matter as we never create holes.
-		 */
-		if (NInoSparse(ni) || NInoCompressed(ni)) {
-			ni->itype.compressed.size += new_alloc_size -
-					allocated_size;
-			vi->i_blocks = ni->itype.compressed.size >> 9;
-		} else
-			vi->i_blocks = new_alloc_size >> 9;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		up_write(&ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is the allocated size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return err;
-	}
-	ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
-			(allocated_size >> vol->cluster_size_bits) - 1);
-undo_alloc:
-	ll = allocated_size >> vol->cluster_size_bits;
-	if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
-		ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
-				"in error code path.  Run chkdsk to recover "
-				"the lost cluster(s).");
-		NVolSetErrors(vol);
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/*
-	 * If the runlist truncation fails and/or the search context is no
-	 * longer valid, we cannot resize the attribute record or build the
-	 * mapping pairs array thus we mark the inode bad so that no access to
-	 * the freed clusters can happen.
-	 */
-	if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
-		ntfs_error(vol->sb, "Failed to %s in error code path.  Run "
-				"chkdsk to recover.", IS_ERR(m) ?
-				"restore attribute search context" :
-				"truncate attribute runlist");
-		NVolSetErrors(vol);
-	} else if (mp_rebuilt) {
-		if (ntfs_attr_record_resize(m, a, attr_len)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record in error code path.  Run "
-					"chkdsk to recover.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-					a->data.non_resident.
-					mapping_pairs_offset), attr_len -
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), rl2, ll, -1,
-					NULL)) {
-				ntfs_error(vol->sb, "Failed to restore "
-						"mapping pairs array in error "
-						"code path.  Run chkdsk to "
-						"recover.");
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		}
-	}
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-conv_err_out:
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-}
-
-/**
- * ntfs_attr_set - fill (a part of) an attribute with a byte
- * @ni:		ntfs inode describing the attribute to fill
- * @ofs:	offset inside the attribute at which to start to fill
- * @cnt:	number of bytes to fill
- * @val:	the unsigned 8-bit value with which to fill the attribute
- *
- * Fill @cnt bytes of the attribute described by the ntfs inode @ni starting at
- * byte offset @ofs inside the attribute with the constant byte @val.
- *
- * This function is effectively like memset() applied to an ntfs attribute.
- * Note this function actually only operates on the page cache pages belonging
- * to the ntfs attribute and it marks them dirty after doing the memset().
- * Thus it relies on the vm dirty page write code paths to cause the modified
- * pages to be written to the mft record/disk.
- *
- * Return 0 on success and -errno on error.  An error code of -ESPIPE means
- * that @ofs + @cnt were outside the end of the attribute and no write was
- * performed.
- */
-int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
-{
-	ntfs_volume *vol = ni->vol;
-	struct address_space *mapping;
-	struct page *page;
-	u8 *kaddr;
-	pgoff_t idx, end;
-	unsigned start_ofs, end_ofs, size;
-
-	ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
-			(long long)ofs, (long long)cnt, val);
-	BUG_ON(ofs < 0);
-	BUG_ON(cnt < 0);
-	if (!cnt)
-		goto done;
-	/*
-	 * FIXME: Compressed and encrypted attributes are not supported when
-	 * writing and we should never have gotten here for them.
-	 */
-	BUG_ON(NInoCompressed(ni));
-	BUG_ON(NInoEncrypted(ni));
-	mapping = VFS_I(ni)->i_mapping;
-	/* Work out the starting index and page offset. */
-	idx = ofs >> PAGE_SHIFT;
-	start_ofs = ofs & ~PAGE_MASK;
-	/* Work out the ending index and page offset. */
-	end = ofs + cnt;
-	end_ofs = end & ~PAGE_MASK;
-	/* If the end is outside the inode size return -ESPIPE. */
-	if (unlikely(end > i_size_read(VFS_I(ni)))) {
-		ntfs_error(vol->sb, "Request exceeds end of attribute.");
-		return -ESPIPE;
-	}
-	end >>= PAGE_SHIFT;
-	/* If there is a first partial page, need to do it the slow way. */
-	if (start_ofs) {
-		page = read_mapping_page(mapping, idx, NULL);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read first partial "
-					"page (error, index 0x%lx).", idx);
-			return PTR_ERR(page);
-		}
-		/*
-		 * If the last page is the same as the first page, need to
-		 * limit the write to the end offset.
-		 */
-		size = PAGE_SIZE;
-		if (idx == end)
-			size = end_ofs;
-		kaddr = kmap_atomic(page);
-		memset(kaddr + start_ofs, val, size - start_ofs);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		set_page_dirty(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-		if (idx == end)
-			goto done;
-		idx++;
-	}
-	/* Do the whole pages the fast way. */
-	for (; idx < end; idx++) {
-		/* Find or create the current page.  (The page is locked.) */
-		page = grab_cache_page(mapping, idx);
-		if (unlikely(!page)) {
-			ntfs_error(vol->sb, "Insufficient memory to grab "
-					"page (index 0x%lx).", idx);
-			return -ENOMEM;
-		}
-		kaddr = kmap_atomic(page);
-		memset(kaddr, val, PAGE_SIZE);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		/*
-		 * If the page has buffers, mark them uptodate since buffer
-		 * state and not page state is definitive in 2.6 kernels.
-		 */
-		if (page_has_buffers(page)) {
-			struct buffer_head *bh, *head;
-
-			bh = head = page_buffers(page);
-			do {
-				set_buffer_uptodate(bh);
-			} while ((bh = bh->b_this_page) != head);
-		}
-		/* Now that buffers are uptodate, set the page uptodate, too. */
-		SetPageUptodate(page);
-		/*
-		 * Set the page and all its buffers dirty and mark the inode
-		 * dirty, too.  The VM will write the page later on.
-		 */
-		set_page_dirty(page);
-		/* Finally unlock and release the page. */
-		unlock_page(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	}
-	/* If there is a last partial page, need to do it the slow way. */
-	if (end_ofs) {
-		page = read_mapping_page(mapping, idx, NULL);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read last partial page "
-					"(error, index 0x%lx).", idx);
-			return PTR_ERR(page);
-		}
-		kaddr = kmap_atomic(page);
-		memset(kaddr, val, end_ofs);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr);
-		set_page_dirty(page);
-		put_page(page);
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	}
-done:
-	ntfs_debug("Done.");
-	return 0;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h
deleted file mode 100644
index fe0890d3d072..000000000000
--- a/fs/ntfs/attrib.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * attrib.h - Defines for attribute handling in NTFS Linux kernel driver.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_ATTRIB_H
-#define _LINUX_NTFS_ATTRIB_H
-
-#include "endian.h"
-#include "types.h"
-#include "layout.h"
-#include "inode.h"
-#include "runlist.h"
-#include "volume.h"
-
-/**
- * ntfs_attr_search_ctx - used in attribute search functions
- * @mrec:	buffer containing mft record to search
- * @attr:	attribute record in @mrec where to begin/continue search
- * @is_first:	if true ntfs_attr_lookup() begins search with @attr, else after
- *
- * Structure must be initialized to zero before the first call to one of the
- * attribute search functions. Initialize @mrec to point to the mft record to
- * search, and @attr to point to the first attribute within @mrec (not necessary
- * if calling the _first() functions), and set @is_first to 'true' (not necessary
- * if calling the _first() functions).
- *
- * If @is_first is 'true', the search begins with @attr. If @is_first is 'false',
- * the search begins after @attr. This is so that, after the first call to one
- * of the search attribute functions, we can call the function again, without
- * any modification of the search context, to automagically get the next
- * matching attribute.
- */
-typedef struct {
-	MFT_RECORD *mrec;
-	ATTR_RECORD *attr;
-	bool is_first;
-	ntfs_inode *ntfs_ino;
-	ATTR_LIST_ENTRY *al_entry;
-	ntfs_inode *base_ntfs_ino;
-	MFT_RECORD *base_mrec;
-	ATTR_RECORD *base_attr;
-} ntfs_attr_search_ctx;
-
-extern int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn,
-		ntfs_attr_search_ctx *ctx);
-extern int ntfs_map_runlist(ntfs_inode *ni, VCN vcn);
-
-extern LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
-		const bool write_locked);
-
-extern runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni,
-		const VCN vcn, ntfs_attr_search_ctx *ctx);
-
-int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
-		const u32 name_len, const IGNORE_CASE_BOOL ic,
-		const VCN lowest_vcn, const u8 *val, const u32 val_len,
-		ntfs_attr_search_ctx *ctx);
-
-extern int load_attribute_list(ntfs_volume *vol, runlist *rl, u8 *al_start,
-		const s64 size, const s64 initialized_size);
-
-static inline s64 ntfs_attr_size(const ATTR_RECORD *a)
-{
-	if (!a->non_resident)
-		return (s64)le32_to_cpu(a->data.resident.value_length);
-	return sle64_to_cpu(a->data.non_resident.data_size);
-}
-
-extern void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx);
-extern ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni,
-		MFT_RECORD *mrec);
-extern void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx);
-
-#ifdef NTFS_RW
-
-extern int ntfs_attr_size_bounds_check(const ntfs_volume *vol,
-		const ATTR_TYPE type, const s64 size);
-extern int ntfs_attr_can_be_non_resident(const ntfs_volume *vol,
-		const ATTR_TYPE type);
-extern int ntfs_attr_can_be_resident(const ntfs_volume *vol,
-		const ATTR_TYPE type);
-
-extern int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size);
-extern int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
-		const u32 new_size);
-
-extern int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size);
-
-extern s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
-		const s64 new_data_size, const s64 data_start);
-
-extern int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt,
-		const u8 val);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_ATTRIB_H */
diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c
deleted file mode 100644
index 0675b2400873..000000000000
--- a/fs/ntfs/bitmap.c
+++ /dev/null
@@ -1,179 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * bitmap.c - NTFS kernel bitmap handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/pagemap.h>
-
-#include "bitmap.h"
-#include "debug.h"
-#include "aops.h"
-#include "ntfs.h"
-
-/**
- * __ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
- * @vi:			vfs inode describing the bitmap
- * @start_bit:		first bit to set
- * @count:		number of bits to set
- * @value:		value to set the bits to (i.e. 0 or 1)
- * @is_rollback:	if 'true' this is a rollback operation
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi to @value, where @value is either 0 or 1.
- *
- * @is_rollback should always be 'false', it is for internal use to rollback
- * errors.  You probably want to use ntfs_bitmap_set_bits_in_run() instead.
- *
- * Return 0 on success and -errno on error.
- */
-int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
-		const s64 count, const u8 value, const bool is_rollback)
-{
-	s64 cnt = count;
-	pgoff_t index, end_index;
-	struct address_space *mapping;
-	struct page *page;
-	u8 *kaddr;
-	int pos, len;
-	u8 bit;
-
-	BUG_ON(!vi);
-	ntfs_debug("Entering for i_ino 0x%lx, start_bit 0x%llx, count 0x%llx, "
-			"value %u.%s", vi->i_ino, (unsigned long long)start_bit,
-			(unsigned long long)cnt, (unsigned int)value,
-			is_rollback ? " (rollback)" : "");
-	BUG_ON(start_bit < 0);
-	BUG_ON(cnt < 0);
-	BUG_ON(value > 1);
-	/*
-	 * Calculate the indices for the pages containing the first and last
-	 * bits, i.e. @start_bit and @start_bit + @cnt - 1, respectively.
-	 */
-	index = start_bit >> (3 + PAGE_SHIFT);
-	end_index = (start_bit + cnt - 1) >> (3 + PAGE_SHIFT);
-
-	/* Get the page containing the first bit (@start_bit). */
-	mapping = vi->i_mapping;
-	page = ntfs_map_page(mapping, index);
-	if (IS_ERR(page)) {
-		if (!is_rollback)
-			ntfs_error(vi->i_sb, "Failed to map first page (error "
-					"%li), aborting.", PTR_ERR(page));
-		return PTR_ERR(page);
-	}
-	kaddr = page_address(page);
-
-	/* Set @pos to the position of the byte containing @start_bit. */
-	pos = (start_bit >> 3) & ~PAGE_MASK;
-
-	/* Calculate the position of @start_bit in the first byte. */
-	bit = start_bit & 7;
-
-	/* If the first byte is partial, modify the appropriate bits in it. */
-	if (bit) {
-		u8 *byte = kaddr + pos;
-		while ((bit & 7) && cnt) {
-			cnt--;
-			if (value)
-				*byte |= 1 << bit++;
-			else
-				*byte &= ~(1 << bit++);
-		}
-		/* If we are done, unmap the page and return success. */
-		if (!cnt)
-			goto done;
-
-		/* Update @pos to the new position. */
-		pos++;
-	}
-	/*
-	 * Depending on @value, modify all remaining whole bytes in the page up
-	 * to @cnt.
-	 */
-	len = min_t(s64, cnt >> 3, PAGE_SIZE - pos);
-	memset(kaddr + pos, value ? 0xff : 0, len);
-	cnt -= len << 3;
-
-	/* Update @len to point to the first not-done byte in the page. */
-	if (cnt < 8)
-		len += pos;
-
-	/* If we are not in the last page, deal with all subsequent pages. */
-	while (index < end_index) {
-		BUG_ON(cnt <= 0);
-
-		/* Update @index and get the next page. */
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		ntfs_unmap_page(page);
-		page = ntfs_map_page(mapping, ++index);
-		if (IS_ERR(page))
-			goto rollback;
-		kaddr = page_address(page);
-		/*
-		 * Depending on @value, modify all remaining whole bytes in the
-		 * page up to @cnt.
-		 */
-		len = min_t(s64, cnt >> 3, PAGE_SIZE);
-		memset(kaddr, value ? 0xff : 0, len);
-		cnt -= len << 3;
-	}
-	/*
-	 * The currently mapped page is the last one.  If the last byte is
-	 * partial, modify the appropriate bits in it.  Note, @len is the
-	 * position of the last byte inside the page.
-	 */
-	if (cnt) {
-		u8 *byte;
-
-		BUG_ON(cnt > 7);
-
-		bit = cnt;
-		byte = kaddr + len;
-		while (bit--) {
-			if (value)
-				*byte |= 1 << bit;
-			else
-				*byte &= ~(1 << bit);
-		}
-	}
-done:
-	/* We are done.  Unmap the page and return success. */
-	flush_dcache_page(page);
-	set_page_dirty(page);
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return 0;
-rollback:
-	/*
-	 * Current state:
-	 *	- no pages are mapped
-	 *	- @count - @cnt is the number of bits that have been modified
-	 */
-	if (is_rollback)
-		return PTR_ERR(page);
-	if (count != cnt)
-		pos = __ntfs_bitmap_set_bits_in_run(vi, start_bit, count - cnt,
-				value ? 0 : 1, true);
-	else
-		pos = 0;
-	if (!pos) {
-		/* Rollback was successful. */
-		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
-				"%li), aborting.", PTR_ERR(page));
-	} else {
-		/* Rollback failed. */
-		ntfs_error(vi->i_sb, "Failed to map subsequent page (error "
-				"%li) and rollback failed (error %i).  "
-				"Aborting and leaving inconsistent metadata.  "
-				"Unmount and run chkdsk.", PTR_ERR(page), pos);
-		NVolSetErrors(NTFS_SB(vi->i_sb));
-	}
-	return PTR_ERR(page);
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/bitmap.h b/fs/ntfs/bitmap.h
deleted file mode 100644
index 9dd2224ca9c4..000000000000
--- a/fs/ntfs/bitmap.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * bitmap.h - Defines for NTFS kernel bitmap handling.  Part of the Linux-NTFS
- *	      project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_BITMAP_H
-#define _LINUX_NTFS_BITMAP_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "types.h"
-
-extern int __ntfs_bitmap_set_bits_in_run(struct inode *vi, const s64 start_bit,
-		const s64 count, const u8 value, const bool is_rollback);
-
-/**
- * ntfs_bitmap_set_bits_in_run - set a run of bits in a bitmap to a value
- * @vi:			vfs inode describing the bitmap
- * @start_bit:		first bit to set
- * @count:		number of bits to set
- * @value:		value to set the bits to (i.e. 0 or 1)
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi to @value, where @value is either 0 or 1.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_bits_in_run(struct inode *vi,
-		const s64 start_bit, const s64 count, const u8 value)
-{
-	return __ntfs_bitmap_set_bits_in_run(vi, start_bit, count, value,
-			false);
-}
-
-/**
- * ntfs_bitmap_set_run - set a run of bits in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @start_bit:	first bit to set
- * @count:	number of bits to set
- *
- * Set @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_run(struct inode *vi, const s64 start_bit,
-		const s64 count)
-{
-	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 1);
-}
-
-/**
- * ntfs_bitmap_clear_run - clear a run of bits in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @start_bit:	first bit to clear
- * @count:	number of bits to clear
- *
- * Clear @count bits starting at bit @start_bit in the bitmap described by the
- * vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_clear_run(struct inode *vi, const s64 start_bit,
-		const s64 count)
-{
-	return ntfs_bitmap_set_bits_in_run(vi, start_bit, count, 0);
-}
-
-/**
- * ntfs_bitmap_set_bit - set a bit in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @bit:	bit to set
- *
- * Set bit @bit in the bitmap described by the vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_set_bit(struct inode *vi, const s64 bit)
-{
-	return ntfs_bitmap_set_run(vi, bit, 1);
-}
-
-/**
- * ntfs_bitmap_clear_bit - clear a bit in a bitmap
- * @vi:		vfs inode describing the bitmap
- * @bit:	bit to clear
- *
- * Clear bit @bit in the bitmap described by the vfs inode @vi.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_bitmap_clear_bit(struct inode *vi, const s64 bit)
-{
-	return ntfs_bitmap_clear_run(vi, bit, 1);
-}
-
-#endif /* NTFS_RW */
-
-#endif /* defined _LINUX_NTFS_BITMAP_H */
diff --git a/fs/ntfs/collate.c b/fs/ntfs/collate.c
deleted file mode 100644
index 3ab6ec96abfe..000000000000
--- a/fs/ntfs/collate.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * collate.c - NTFS kernel collation handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#include "collate.h"
-#include "debug.h"
-#include "ntfs.h"
-
-static int ntfs_collate_binary(ntfs_volume *vol,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len)
-{
-	int rc;
-
-	ntfs_debug("Entering.");
-	rc = memcmp(data1, data2, min(data1_len, data2_len));
-	if (!rc && (data1_len != data2_len)) {
-		if (data1_len < data2_len)
-			rc = -1;
-		else
-			rc = 1;
-	}
-	ntfs_debug("Done, returning %i", rc);
-	return rc;
-}
-
-static int ntfs_collate_ntofs_ulong(ntfs_volume *vol,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len)
-{
-	int rc;
-	u32 d1, d2;
-
-	ntfs_debug("Entering.");
-	// FIXME:  We don't really want to bug here.
-	BUG_ON(data1_len != data2_len);
-	BUG_ON(data1_len != 4);
-	d1 = le32_to_cpup(data1);
-	d2 = le32_to_cpup(data2);
-	if (d1 < d2)
-		rc = -1;
-	else {
-		if (d1 == d2)
-			rc = 0;
-		else
-			rc = 1;
-	}
-	ntfs_debug("Done, returning %i", rc);
-	return rc;
-}
-
-typedef int (*ntfs_collate_func_t)(ntfs_volume *, const void *, const int,
-		const void *, const int);
-
-static ntfs_collate_func_t ntfs_do_collate0x0[3] = {
-	ntfs_collate_binary,
-	NULL/*ntfs_collate_file_name*/,
-	NULL/*ntfs_collate_unicode_string*/,
-};
-
-static ntfs_collate_func_t ntfs_do_collate0x1[4] = {
-	ntfs_collate_ntofs_ulong,
-	NULL/*ntfs_collate_ntofs_sid*/,
-	NULL/*ntfs_collate_ntofs_security_hash*/,
-	NULL/*ntfs_collate_ntofs_ulongs*/,
-};
-
-/**
- * ntfs_collate - collate two data items using a specified collation rule
- * @vol:	ntfs volume to which the data items belong
- * @cr:		collation rule to use when comparing the items
- * @data1:	first data item to collate
- * @data1_len:	length in bytes of @data1
- * @data2:	second data item to collate
- * @data2_len:	length in bytes of @data2
- *
- * Collate the two data items @data1 and @data2 using the collation rule @cr
- * and return -1, 0, ir 1 if @data1 is found, respectively, to collate before,
- * to match, or to collate after @data2.
- *
- * For speed we use the collation rule @cr as an index into two tables of
- * function pointers to call the appropriate collation function.
- */
-int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len) {
-	int i;
-
-	ntfs_debug("Entering.");
-	/*
-	 * FIXME:  At the moment we only support COLLATION_BINARY and
-	 * COLLATION_NTOFS_ULONG, so we BUG() for everything else for now.
-	 */
-	BUG_ON(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG);
-	i = le32_to_cpu(cr);
-	BUG_ON(i < 0);
-	if (i <= 0x02)
-		return ntfs_do_collate0x0[i](vol, data1, data1_len,
-				data2, data2_len);
-	BUG_ON(i < 0x10);
-	i -= 0x10;
-	if (likely(i <= 3))
-		return ntfs_do_collate0x1[i](vol, data1, data1_len,
-				data2, data2_len);
-	BUG();
-	return 0;
-}
diff --git a/fs/ntfs/collate.h b/fs/ntfs/collate.h
deleted file mode 100644
index f2255619b4f4..000000000000
--- a/fs/ntfs/collate.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * collate.h - Defines for NTFS kernel collation handling.  Part of the
- *	       Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_COLLATE_H
-#define _LINUX_NTFS_COLLATE_H
-
-#include "types.h"
-#include "volume.h"
-
-static inline bool ntfs_is_collation_rule_supported(COLLATION_RULE cr) {
-	int i;
-
-	/*
-	 * FIXME:  At the moment we only support COLLATION_BINARY and
-	 * COLLATION_NTOFS_ULONG, so we return false for everything else for
-	 * now.
-	 */
-	if (unlikely(cr != COLLATION_BINARY && cr != COLLATION_NTOFS_ULONG))
-		return false;
-	i = le32_to_cpu(cr);
-	if (likely(((i >= 0) && (i <= 0x02)) ||
-			((i >= 0x10) && (i <= 0x13))))
-		return true;
-	return false;
-}
-
-extern int ntfs_collate(ntfs_volume *vol, COLLATION_RULE cr,
-		const void *data1, const int data1_len,
-		const void *data2, const int data2_len);
-
-#endif /* _LINUX_NTFS_COLLATE_H */
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
deleted file mode 100644
index 761aaa0195d6..000000000000
--- a/fs/ntfs/compress.c
+++ /dev/null
@@ -1,950 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * compress.c - NTFS kernel compressed attributes handling.
- *		Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/fs.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-
-#include "attrib.h"
-#include "inode.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/**
- * ntfs_compression_constants - enum of constants used in the compression code
- */
-typedef enum {
-	/* Token types and access mask. */
-	NTFS_SYMBOL_TOKEN	=	0,
-	NTFS_PHRASE_TOKEN	=	1,
-	NTFS_TOKEN_MASK		=	1,
-
-	/* Compression sub-block constants. */
-	NTFS_SB_SIZE_MASK	=	0x0fff,
-	NTFS_SB_SIZE		=	0x1000,
-	NTFS_SB_IS_COMPRESSED	=	0x8000,
-
-	/*
-	 * The maximum compression block size is by definition 16 * the cluster
-	 * size, with the maximum supported cluster size being 4kiB. Thus the
-	 * maximum compression buffer size is 64kiB, so we use this when
-	 * initializing the compression buffer.
-	 */
-	NTFS_MAX_CB_SIZE	= 64 * 1024,
-} ntfs_compression_constants;
-
-/*
- * ntfs_compression_buffer - one buffer for the decompression engine
- */
-static u8 *ntfs_compression_buffer;
-
-/*
- * ntfs_cb_lock - spinlock which protects ntfs_compression_buffer
- */
-static DEFINE_SPINLOCK(ntfs_cb_lock);
-
-/**
- * allocate_compression_buffers - allocate the decompression buffers
- *
- * Caller has to hold the ntfs_lock mutex.
- *
- * Return 0 on success or -ENOMEM if the allocations failed.
- */
-int allocate_compression_buffers(void)
-{
-	BUG_ON(ntfs_compression_buffer);
-
-	ntfs_compression_buffer = vmalloc(NTFS_MAX_CB_SIZE);
-	if (!ntfs_compression_buffer)
-		return -ENOMEM;
-	return 0;
-}
-
-/**
- * free_compression_buffers - free the decompression buffers
- *
- * Caller has to hold the ntfs_lock mutex.
- */
-void free_compression_buffers(void)
-{
-	BUG_ON(!ntfs_compression_buffer);
-	vfree(ntfs_compression_buffer);
-	ntfs_compression_buffer = NULL;
-}
-
-/**
- * zero_partial_compressed_page - zero out of bounds compressed page region
- */
-static void zero_partial_compressed_page(struct page *page,
-		const s64 initialized_size)
-{
-	u8 *kp = page_address(page);
-	unsigned int kp_ofs;
-
-	ntfs_debug("Zeroing page region outside initialized size.");
-	if (((s64)page->index << PAGE_SHIFT) >= initialized_size) {
-		clear_page(kp);
-		return;
-	}
-	kp_ofs = initialized_size & ~PAGE_MASK;
-	memset(kp + kp_ofs, 0, PAGE_SIZE - kp_ofs);
-	return;
-}
-
-/**
- * handle_bounds_compressed_page - test for&handle out of bounds compressed page
- */
-static inline void handle_bounds_compressed_page(struct page *page,
-		const loff_t i_size, const s64 initialized_size)
-{
-	if ((page->index >= (initialized_size >> PAGE_SHIFT)) &&
-			(initialized_size < i_size))
-		zero_partial_compressed_page(page, initialized_size);
-	return;
-}
-
-/**
- * ntfs_decompress - decompress a compression block into an array of pages
- * @dest_pages:		destination array of pages
- * @completed_pages:	scratch space to track completed pages
- * @dest_index:		current index into @dest_pages (IN/OUT)
- * @dest_ofs:		current offset within @dest_pages[@dest_index] (IN/OUT)
- * @dest_max_index:	maximum index into @dest_pages (IN)
- * @dest_max_ofs:	maximum offset within @dest_pages[@dest_max_index] (IN)
- * @xpage:		the target page (-1 if none) (IN)
- * @xpage_done:		set to 1 if xpage was completed successfully (IN/OUT)
- * @cb_start:		compression block to decompress (IN)
- * @cb_size:		size of compression block @cb_start in bytes (IN)
- * @i_size:		file size when we started the read (IN)
- * @initialized_size:	initialized file size when we started the read (IN)
- *
- * The caller must have disabled preemption. ntfs_decompress() reenables it when
- * the critical section is finished.
- *
- * This decompresses the compression block @cb_start into the array of
- * destination pages @dest_pages starting at index @dest_index into @dest_pages
- * and at offset @dest_pos into the page @dest_pages[@dest_index].
- *
- * When the page @dest_pages[@xpage] is completed, @xpage_done is set to 1.
- * If xpage is -1 or @xpage has not been completed, @xpage_done is not modified.
- *
- * @cb_start is a pointer to the compression block which needs decompressing
- * and @cb_size is the size of @cb_start in bytes (8-64kiB).
- *
- * Return 0 if success or -EOVERFLOW on error in the compressed stream.
- * @xpage_done indicates whether the target page (@dest_pages[@xpage]) was
- * completed during the decompression of the compression block (@cb_start).
- *
- * Warning: This function *REQUIRES* PAGE_SIZE >= 4096 or it will blow up
- * unpredicatbly! You have been warned!
- *
- * Note to hackers: This function may not sleep until it has finished accessing
- * the compression block @cb_start as it is a per-CPU buffer.
- */
-static int ntfs_decompress(struct page *dest_pages[], int completed_pages[],
-		int *dest_index, int *dest_ofs, const int dest_max_index,
-		const int dest_max_ofs, const int xpage, char *xpage_done,
-		u8 *const cb_start, const u32 cb_size, const loff_t i_size,
-		const s64 initialized_size)
-{
-	/*
-	 * Pointers into the compressed data, i.e. the compression block (cb),
-	 * and the therein contained sub-blocks (sb).
-	 */
-	u8 *cb_end = cb_start + cb_size; /* End of cb. */
-	u8 *cb = cb_start;	/* Current position in cb. */
-	u8 *cb_sb_start;	/* Beginning of the current sb in the cb. */
-	u8 *cb_sb_end;		/* End of current sb / beginning of next sb. */
-
-	/* Variables for uncompressed data / destination. */
-	struct page *dp;	/* Current destination page being worked on. */
-	u8 *dp_addr;		/* Current pointer into dp. */
-	u8 *dp_sb_start;	/* Start of current sub-block in dp. */
-	u8 *dp_sb_end;		/* End of current sb in dp (dp_sb_start +
-				   NTFS_SB_SIZE). */
-	u16 do_sb_start;	/* @dest_ofs when starting this sub-block. */
-	u16 do_sb_end;		/* @dest_ofs of end of this sb (do_sb_start +
-				   NTFS_SB_SIZE). */
-
-	/* Variables for tag and token parsing. */
-	u8 tag;			/* Current tag. */
-	int token;		/* Loop counter for the eight tokens in tag. */
-	int nr_completed_pages = 0;
-
-	/* Default error code. */
-	int err = -EOVERFLOW;
-
-	ntfs_debug("Entering, cb_size = 0x%x.", cb_size);
-do_next_sb:
-	ntfs_debug("Beginning sub-block at offset = 0x%zx in the cb.",
-			cb - cb_start);
-	/*
-	 * Have we reached the end of the compression block or the end of the
-	 * decompressed data?  The latter can happen for example if the current
-	 * position in the compression block is one byte before its end so the
-	 * first two checks do not detect it.
-	 */
-	if (cb == cb_end || !le16_to_cpup((le16*)cb) ||
-			(*dest_index == dest_max_index &&
-			*dest_ofs == dest_max_ofs)) {
-		int i;
-
-		ntfs_debug("Completed. Returning success (0).");
-		err = 0;
-return_error:
-		/* We can sleep from now on, so we drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		/* Second stage: finalize completed pages. */
-		if (nr_completed_pages > 0) {
-			for (i = 0; i < nr_completed_pages; i++) {
-				int di = completed_pages[i];
-
-				dp = dest_pages[di];
-				/*
-				 * If we are outside the initialized size, zero
-				 * the out of bounds page range.
-				 */
-				handle_bounds_compressed_page(dp, i_size,
-						initialized_size);
-				flush_dcache_page(dp);
-				kunmap(dp);
-				SetPageUptodate(dp);
-				unlock_page(dp);
-				if (di == xpage)
-					*xpage_done = 1;
-				else
-					put_page(dp);
-				dest_pages[di] = NULL;
-			}
-		}
-		return err;
-	}
-
-	/* Setup offsets for the current sub-block destination. */
-	do_sb_start = *dest_ofs;
-	do_sb_end = do_sb_start + NTFS_SB_SIZE;
-
-	/* Check that we are still within allowed boundaries. */
-	if (*dest_index == dest_max_index && do_sb_end > dest_max_ofs)
-		goto return_overflow;
-
-	/* Does the minimum size of a compressed sb overflow valid range? */
-	if (cb + 6 > cb_end)
-		goto return_overflow;
-
-	/* Setup the current sub-block source pointers and validate range. */
-	cb_sb_start = cb;
-	cb_sb_end = cb_sb_start + (le16_to_cpup((le16*)cb) & NTFS_SB_SIZE_MASK)
-			+ 3;
-	if (cb_sb_end > cb_end)
-		goto return_overflow;
-
-	/* Get the current destination page. */
-	dp = dest_pages[*dest_index];
-	if (!dp) {
-		/* No page present. Skip decompression of this sub-block. */
-		cb = cb_sb_end;
-
-		/* Advance destination position to next sub-block. */
-		*dest_ofs = (*dest_ofs + NTFS_SB_SIZE) & ~PAGE_MASK;
-		if (!*dest_ofs && (++*dest_index > dest_max_index))
-			goto return_overflow;
-		goto do_next_sb;
-	}
-
-	/* We have a valid destination page. Setup the destination pointers. */
-	dp_addr = (u8*)page_address(dp) + do_sb_start;
-
-	/* Now, we are ready to process the current sub-block (sb). */
-	if (!(le16_to_cpup((le16*)cb) & NTFS_SB_IS_COMPRESSED)) {
-		ntfs_debug("Found uncompressed sub-block.");
-		/* This sb is not compressed, just copy it into destination. */
-
-		/* Advance source position to first data byte. */
-		cb += 2;
-
-		/* An uncompressed sb must be full size. */
-		if (cb_sb_end - cb != NTFS_SB_SIZE)
-			goto return_overflow;
-
-		/* Copy the block and advance the source position. */
-		memcpy(dp_addr, cb, NTFS_SB_SIZE);
-		cb += NTFS_SB_SIZE;
-
-		/* Advance destination position to next sub-block. */
-		*dest_ofs += NTFS_SB_SIZE;
-		if (!(*dest_ofs &= ~PAGE_MASK)) {
-finalize_page:
-			/*
-			 * First stage: add current page index to array of
-			 * completed pages.
-			 */
-			completed_pages[nr_completed_pages++] = *dest_index;
-			if (++*dest_index > dest_max_index)
-				goto return_overflow;
-		}
-		goto do_next_sb;
-	}
-	ntfs_debug("Found compressed sub-block.");
-	/* This sb is compressed, decompress it into destination. */
-
-	/* Setup destination pointers. */
-	dp_sb_start = dp_addr;
-	dp_sb_end = dp_sb_start + NTFS_SB_SIZE;
-
-	/* Forward to the first tag in the sub-block. */
-	cb += 2;
-do_next_tag:
-	if (cb == cb_sb_end) {
-		/* Check if the decompressed sub-block was not full-length. */
-		if (dp_addr < dp_sb_end) {
-			int nr_bytes = do_sb_end - *dest_ofs;
-
-			ntfs_debug("Filling incomplete sub-block with "
-					"zeroes.");
-			/* Zero remainder and update destination position. */
-			memset(dp_addr, 0, nr_bytes);
-			*dest_ofs += nr_bytes;
-		}
-		/* We have finished the current sub-block. */
-		if (!(*dest_ofs &= ~PAGE_MASK))
-			goto finalize_page;
-		goto do_next_sb;
-	}
-
-	/* Check we are still in range. */
-	if (cb > cb_sb_end || dp_addr > dp_sb_end)
-		goto return_overflow;
-
-	/* Get the next tag and advance to first token. */
-	tag = *cb++;
-
-	/* Parse the eight tokens described by the tag. */
-	for (token = 0; token < 8; token++, tag >>= 1) {
-		u16 lg, pt, length, max_non_overlap;
-		register u16 i;
-		u8 *dp_back_addr;
-
-		/* Check if we are done / still in range. */
-		if (cb >= cb_sb_end || dp_addr > dp_sb_end)
-			break;
-
-		/* Determine token type and parse appropriately.*/
-		if ((tag & NTFS_TOKEN_MASK) == NTFS_SYMBOL_TOKEN) {
-			/*
-			 * We have a symbol token, copy the symbol across, and
-			 * advance the source and destination positions.
-			 */
-			*dp_addr++ = *cb++;
-			++*dest_ofs;
-
-			/* Continue with the next token. */
-			continue;
-		}
-
-		/*
-		 * We have a phrase token. Make sure it is not the first tag in
-		 * the sb as this is illegal and would confuse the code below.
-		 */
-		if (dp_addr == dp_sb_start)
-			goto return_overflow;
-
-		/*
-		 * Determine the number of bytes to go back (p) and the number
-		 * of bytes to copy (l). We use an optimized algorithm in which
-		 * we first calculate log2(current destination position in sb),
-		 * which allows determination of l and p in O(1) rather than
-		 * O(n). We just need an arch-optimized log2() function now.
-		 */
-		lg = 0;
-		for (i = *dest_ofs - do_sb_start - 1; i >= 0x10; i >>= 1)
-			lg++;
-
-		/* Get the phrase token into i. */
-		pt = le16_to_cpup((le16*)cb);
-
-		/*
-		 * Calculate starting position of the byte sequence in
-		 * the destination using the fact that p = (pt >> (12 - lg)) + 1
-		 * and make sure we don't go too far back.
-		 */
-		dp_back_addr = dp_addr - (pt >> (12 - lg)) - 1;
-		if (dp_back_addr < dp_sb_start)
-			goto return_overflow;
-
-		/* Now calculate the length of the byte sequence. */
-		length = (pt & (0xfff >> lg)) + 3;
-
-		/* Advance destination position and verify it is in range. */
-		*dest_ofs += length;
-		if (*dest_ofs > do_sb_end)
-			goto return_overflow;
-
-		/* The number of non-overlapping bytes. */
-		max_non_overlap = dp_addr - dp_back_addr;
-
-		if (length <= max_non_overlap) {
-			/* The byte sequence doesn't overlap, just copy it. */
-			memcpy(dp_addr, dp_back_addr, length);
-
-			/* Advance destination pointer. */
-			dp_addr += length;
-		} else {
-			/*
-			 * The byte sequence does overlap, copy non-overlapping
-			 * part and then do a slow byte by byte copy for the
-			 * overlapping part. Also, advance the destination
-			 * pointer.
-			 */
-			memcpy(dp_addr, dp_back_addr, max_non_overlap);
-			dp_addr += max_non_overlap;
-			dp_back_addr += max_non_overlap;
-			length -= max_non_overlap;
-			while (length--)
-				*dp_addr++ = *dp_back_addr++;
-		}
-
-		/* Advance source position and continue with the next token. */
-		cb += 2;
-	}
-
-	/* No tokens left in the current tag. Continue with the next tag. */
-	goto do_next_tag;
-
-return_overflow:
-	ntfs_error(NULL, "Failed. Returning -EOVERFLOW.");
-	goto return_error;
-}
-
-/**
- * ntfs_read_compressed_block - read a compressed block into the page cache
- * @page:	locked page in the compression block(s) we need to read
- *
- * When we are called the page has already been verified to be locked and the
- * attribute is known to be non-resident, not encrypted, but compressed.
- *
- * 1. Determine which compression block(s) @page is in.
- * 2. Get hold of all pages corresponding to this/these compression block(s).
- * 3. Read the (first) compression block.
- * 4. Decompress it into the corresponding pages.
- * 5. Throw the compressed data away and proceed to 3. for the next compression
- *    block or return success if no more compression blocks left.
- *
- * Warning: We have to be careful what we do about existing pages. They might
- * have been written to so that we would lose data if we were to just overwrite
- * them with the out-of-date uncompressed data.
- *
- * FIXME: For PAGE_SIZE > cb_size we are not doing the Right Thing(TM) at
- * the end of the file I think. We need to detect this case and zero the out
- * of bounds remainder of the page in question and mark it as handled. At the
- * moment we would just return -EIO on such a page. This bug will only become
- * apparent if pages are above 8kiB and the NTFS volume only uses 512 byte
- * clusters so is probably not going to be seen by anyone. Still this should
- * be fixed. (AIA)
- *
- * FIXME: Again for PAGE_SIZE > cb_size we are screwing up both in
- * handling sparse and compressed cbs. (AIA)
- *
- * FIXME: At the moment we don't do any zeroing out in the case that
- * initialized_size is less than data_size. This should be safe because of the
- * nature of the compression algorithm used. Just in case we check and output
- * an error message in read inode if the two sizes are not equal for a
- * compressed file. (AIA)
- */
-int ntfs_read_compressed_block(struct page *page)
-{
-	loff_t i_size;
-	s64 initialized_size;
-	struct address_space *mapping = page->mapping;
-	ntfs_inode *ni = NTFS_I(mapping->host);
-	ntfs_volume *vol = ni->vol;
-	struct super_block *sb = vol->sb;
-	runlist_element *rl;
-	unsigned long flags, block_size = sb->s_blocksize;
-	unsigned char block_size_bits = sb->s_blocksize_bits;
-	u8 *cb, *cb_pos, *cb_end;
-	struct buffer_head **bhs;
-	unsigned long offset, index = page->index;
-	u32 cb_size = ni->itype.compressed.block_size;
-	u64 cb_size_mask = cb_size - 1UL;
-	VCN vcn;
-	LCN lcn;
-	/* The first wanted vcn (minimum alignment is PAGE_SIZE). */
-	VCN start_vcn = (((s64)index << PAGE_SHIFT) & ~cb_size_mask) >>
-			vol->cluster_size_bits;
-	/*
-	 * The first vcn after the last wanted vcn (minimum alignment is again
-	 * PAGE_SIZE.
-	 */
-	VCN end_vcn = ((((s64)(index + 1UL) << PAGE_SHIFT) + cb_size - 1)
-			& ~cb_size_mask) >> vol->cluster_size_bits;
-	/* Number of compression blocks (cbs) in the wanted vcn range. */
-	unsigned int nr_cbs = (end_vcn - start_vcn) << vol->cluster_size_bits
-			>> ni->itype.compressed.block_size_bits;
-	/*
-	 * Number of pages required to store the uncompressed data from all
-	 * compression blocks (cbs) overlapping @page. Due to alignment
-	 * guarantees of start_vcn and end_vcn, no need to round up here.
-	 */
-	unsigned int nr_pages = (end_vcn - start_vcn) <<
-			vol->cluster_size_bits >> PAGE_SHIFT;
-	unsigned int xpage, max_page, cur_page, cur_ofs, i;
-	unsigned int cb_clusters, cb_max_ofs;
-	int block, max_block, cb_max_page, bhs_size, nr_bhs, err = 0;
-	struct page **pages;
-	int *completed_pages;
-	unsigned char xpage_done = 0;
-
-	ntfs_debug("Entering, page->index = 0x%lx, cb_size = 0x%x, nr_pages = "
-			"%i.", index, cb_size, nr_pages);
-	/*
-	 * Bad things happen if we get here for anything that is not an
-	 * unnamed $DATA attribute.
-	 */
-	BUG_ON(ni->type != AT_DATA);
-	BUG_ON(ni->name_len);
-
-	pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_NOFS);
-	completed_pages = kmalloc_array(nr_pages + 1, sizeof(int), GFP_NOFS);
-
-	/* Allocate memory to store the buffer heads we need. */
-	bhs_size = cb_size / block_size * sizeof(struct buffer_head *);
-	bhs = kmalloc(bhs_size, GFP_NOFS);
-
-	if (unlikely(!pages || !bhs || !completed_pages)) {
-		kfree(bhs);
-		kfree(pages);
-		kfree(completed_pages);
-		unlock_page(page);
-		ntfs_error(vol->sb, "Failed to allocate internal buffers.");
-		return -ENOMEM;
-	}
-
-	/*
-	 * We have already been given one page, this is the one we must do.
-	 * Once again, the alignment guarantees keep it simple.
-	 */
-	offset = start_vcn << vol->cluster_size_bits >> PAGE_SHIFT;
-	xpage = index - offset;
-	pages[xpage] = page;
-	/*
-	 * The remaining pages need to be allocated and inserted into the page
-	 * cache, alignment guarantees keep all the below much simpler. (-8
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	i_size = i_size_read(VFS_I(ni));
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	max_page = ((i_size + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-			offset;
-	/* Is the page fully outside i_size? (truncate in progress) */
-	if (xpage >= max_page) {
-		kfree(bhs);
-		kfree(pages);
-		kfree(completed_pages);
-		zero_user(page, 0, PAGE_SIZE);
-		ntfs_debug("Compressed read outside i_size - truncated?");
-		SetPageUptodate(page);
-		unlock_page(page);
-		return 0;
-	}
-	if (nr_pages < max_page)
-		max_page = nr_pages;
-	for (i = 0; i < max_page; i++, offset++) {
-		if (i != xpage)
-			pages[i] = grab_cache_page_nowait(mapping, offset);
-		page = pages[i];
-		if (page) {
-			/*
-			 * We only (re)read the page if it isn't already read
-			 * in and/or dirty or we would be losing data or at
-			 * least wasting our time.
-			 */
-			if (!PageDirty(page) && (!PageUptodate(page) ||
-					PageError(page))) {
-				ClearPageError(page);
-				kmap(page);
-				continue;
-			}
-			unlock_page(page);
-			put_page(page);
-			pages[i] = NULL;
-		}
-	}
-
-	/*
-	 * We have the runlist, and all the destination pages we need to fill.
-	 * Now read the first compression block.
-	 */
-	cur_page = 0;
-	cur_ofs = 0;
-	cb_clusters = ni->itype.compressed.block_clusters;
-do_next_cb:
-	nr_cbs--;
-	nr_bhs = 0;
-
-	/* Read all cb buffer heads one cluster at a time. */
-	rl = NULL;
-	for (vcn = start_vcn, start_vcn += cb_clusters; vcn < start_vcn;
-			vcn++) {
-		bool is_retry = false;
-
-		if (!rl) {
-lock_retry_remap:
-			down_read(&ni->runlist.lock);
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
-				(unsigned long long)vcn,
-				(unsigned long long)lcn);
-		if (lcn < 0) {
-			/*
-			 * When we reach the first sparse cluster we have
-			 * finished with the cb.
-			 */
-			if (lcn == LCN_HOLE)
-				break;
-			if (is_retry || lcn != LCN_RL_NOT_MAPPED)
-				goto rl_err;
-			is_retry = true;
-			/*
-			 * Attempt to map runlist, dropping lock for the
-			 * duration.
-			 */
-			up_read(&ni->runlist.lock);
-			if (!ntfs_map_runlist(ni, vcn))
-				goto lock_retry_remap;
-			goto map_rl_err;
-		}
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		/* Read the lcn from device in chunks of block_size bytes. */
-		max_block = block + (vol->cluster_size >> block_size_bits);
-		do {
-			ntfs_debug("block = 0x%x.", block);
-			if (unlikely(!(bhs[nr_bhs] = sb_getblk(sb, block))))
-				goto getblk_err;
-			nr_bhs++;
-		} while (++block < max_block);
-	}
-
-	/* Release the lock if we took it. */
-	if (rl)
-		up_read(&ni->runlist.lock);
-
-	/* Setup and initiate io on all buffer heads. */
-	for (i = 0; i < nr_bhs; i++) {
-		struct buffer_head *tbh = bhs[i];
-
-		if (!trylock_buffer(tbh))
-			continue;
-		if (unlikely(buffer_uptodate(tbh))) {
-			unlock_buffer(tbh);
-			continue;
-		}
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, tbh);
-	}
-
-	/* Wait for io completion on all buffer heads. */
-	for (i = 0; i < nr_bhs; i++) {
-		struct buffer_head *tbh = bhs[i];
-
-		if (buffer_uptodate(tbh))
-			continue;
-		wait_on_buffer(tbh);
-		/*
-		 * We need an optimization barrier here, otherwise we start
-		 * hitting the below fixup code when accessing a loopback
-		 * mounted ntfs partition. This indicates either there is a
-		 * race condition in the loop driver or, more likely, gcc
-		 * overoptimises the code without the barrier and it doesn't
-		 * do the Right Thing(TM).
-		 */
-		barrier();
-		if (unlikely(!buffer_uptodate(tbh))) {
-			ntfs_warning(vol->sb, "Buffer is unlocked but not "
-					"uptodate! Unplugging the disk queue "
-					"and rescheduling.");
-			get_bh(tbh);
-			io_schedule();
-			put_bh(tbh);
-			if (unlikely(!buffer_uptodate(tbh)))
-				goto read_err;
-			ntfs_warning(vol->sb, "Buffer is now uptodate. Good.");
-		}
-	}
-
-	/*
-	 * Get the compression buffer. We must not sleep any more
-	 * until we are finished with it.
-	 */
-	spin_lock(&ntfs_cb_lock);
-	cb = ntfs_compression_buffer;
-
-	BUG_ON(!cb);
-
-	cb_pos = cb;
-	cb_end = cb + cb_size;
-
-	/* Copy the buffer heads into the contiguous buffer. */
-	for (i = 0; i < nr_bhs; i++) {
-		memcpy(cb_pos, bhs[i]->b_data, block_size);
-		cb_pos += block_size;
-	}
-
-	/* Just a precaution. */
-	if (cb_pos + 2 <= cb + cb_size)
-		*(u16*)cb_pos = 0;
-
-	/* Reset cb_pos back to the beginning. */
-	cb_pos = cb;
-
-	/* We now have both source (if present) and destination. */
-	ntfs_debug("Successfully read the compression block.");
-
-	/* The last page and maximum offset within it for the current cb. */
-	cb_max_page = (cur_page << PAGE_SHIFT) + cur_ofs + cb_size;
-	cb_max_ofs = cb_max_page & ~PAGE_MASK;
-	cb_max_page >>= PAGE_SHIFT;
-
-	/* Catch end of file inside a compression block. */
-	if (cb_max_page > max_page)
-		cb_max_page = max_page;
-
-	if (vcn == start_vcn - cb_clusters) {
-		/* Sparse cb, zero out page range overlapping the cb. */
-		ntfs_debug("Found sparse compression block.");
-		/* We can sleep from now on, so we drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		if (cb_max_ofs)
-			cb_max_page--;
-		for (; cur_page < cb_max_page; cur_page++) {
-			page = pages[cur_page];
-			if (page) {
-				if (likely(!cur_ofs))
-					clear_page(page_address(page));
-				else
-					memset(page_address(page) + cur_ofs, 0,
-							PAGE_SIZE -
-							cur_ofs);
-				flush_dcache_page(page);
-				kunmap(page);
-				SetPageUptodate(page);
-				unlock_page(page);
-				if (cur_page == xpage)
-					xpage_done = 1;
-				else
-					put_page(page);
-				pages[cur_page] = NULL;
-			}
-			cb_pos += PAGE_SIZE - cur_ofs;
-			cur_ofs = 0;
-			if (cb_pos >= cb_end)
-				break;
-		}
-		/* If we have a partial final page, deal with it now. */
-		if (cb_max_ofs && cb_pos < cb_end) {
-			page = pages[cur_page];
-			if (page)
-				memset(page_address(page) + cur_ofs, 0,
-						cb_max_ofs - cur_ofs);
-			/*
-			 * No need to update cb_pos at this stage:
-			 *	cb_pos += cb_max_ofs - cur_ofs;
-			 */
-			cur_ofs = cb_max_ofs;
-		}
-	} else if (vcn == start_vcn) {
-		/* We can't sleep so we need two stages. */
-		unsigned int cur2_page = cur_page;
-		unsigned int cur_ofs2 = cur_ofs;
-		u8 *cb_pos2 = cb_pos;
-
-		ntfs_debug("Found uncompressed compression block.");
-		/* Uncompressed cb, copy it to the destination pages. */
-		/*
-		 * TODO: As a big optimization, we could detect this case
-		 * before we read all the pages and use block_read_full_folio()
-		 * on all full pages instead (we still have to treat partial
-		 * pages especially but at least we are getting rid of the
-		 * synchronous io for the majority of pages.
-		 * Or if we choose not to do the read-ahead/-behind stuff, we
-		 * could just return block_read_full_folio(pages[xpage]) as long
-		 * as PAGE_SIZE <= cb_size.
-		 */
-		if (cb_max_ofs)
-			cb_max_page--;
-		/* First stage: copy data into destination pages. */
-		for (; cur_page < cb_max_page; cur_page++) {
-			page = pages[cur_page];
-			if (page)
-				memcpy(page_address(page) + cur_ofs, cb_pos,
-						PAGE_SIZE - cur_ofs);
-			cb_pos += PAGE_SIZE - cur_ofs;
-			cur_ofs = 0;
-			if (cb_pos >= cb_end)
-				break;
-		}
-		/* If we have a partial final page, deal with it now. */
-		if (cb_max_ofs && cb_pos < cb_end) {
-			page = pages[cur_page];
-			if (page)
-				memcpy(page_address(page) + cur_ofs, cb_pos,
-						cb_max_ofs - cur_ofs);
-			cb_pos += cb_max_ofs - cur_ofs;
-			cur_ofs = cb_max_ofs;
-		}
-		/* We can sleep from now on, so drop lock. */
-		spin_unlock(&ntfs_cb_lock);
-		/* Second stage: finalize pages. */
-		for (; cur2_page < cb_max_page; cur2_page++) {
-			page = pages[cur2_page];
-			if (page) {
-				/*
-				 * If we are outside the initialized size, zero
-				 * the out of bounds page range.
-				 */
-				handle_bounds_compressed_page(page, i_size,
-						initialized_size);
-				flush_dcache_page(page);
-				kunmap(page);
-				SetPageUptodate(page);
-				unlock_page(page);
-				if (cur2_page == xpage)
-					xpage_done = 1;
-				else
-					put_page(page);
-				pages[cur2_page] = NULL;
-			}
-			cb_pos2 += PAGE_SIZE - cur_ofs2;
-			cur_ofs2 = 0;
-			if (cb_pos2 >= cb_end)
-				break;
-		}
-	} else {
-		/* Compressed cb, decompress it into the destination page(s). */
-		unsigned int prev_cur_page = cur_page;
-
-		ntfs_debug("Found compressed compression block.");
-		err = ntfs_decompress(pages, completed_pages, &cur_page,
-				&cur_ofs, cb_max_page, cb_max_ofs, xpage,
-				&xpage_done, cb_pos, cb_size - (cb_pos - cb),
-				i_size, initialized_size);
-		/*
-		 * We can sleep from now on, lock already dropped by
-		 * ntfs_decompress().
-		 */
-		if (err) {
-			ntfs_error(vol->sb, "ntfs_decompress() failed in inode "
-					"0x%lx with error code %i. Skipping "
-					"this compression block.",
-					ni->mft_no, -err);
-			/* Release the unfinished pages. */
-			for (; prev_cur_page < cur_page; prev_cur_page++) {
-				page = pages[prev_cur_page];
-				if (page) {
-					flush_dcache_page(page);
-					kunmap(page);
-					unlock_page(page);
-					if (prev_cur_page != xpage)
-						put_page(page);
-					pages[prev_cur_page] = NULL;
-				}
-			}
-		}
-	}
-
-	/* Release the buffer heads. */
-	for (i = 0; i < nr_bhs; i++)
-		brelse(bhs[i]);
-
-	/* Do we have more work to do? */
-	if (nr_cbs)
-		goto do_next_cb;
-
-	/* We no longer need the list of buffer heads. */
-	kfree(bhs);
-
-	/* Clean up if we have any pages left. Should never happen. */
-	for (cur_page = 0; cur_page < max_page; cur_page++) {
-		page = pages[cur_page];
-		if (page) {
-			ntfs_error(vol->sb, "Still have pages left! "
-					"Terminating them with extreme "
-					"prejudice.  Inode 0x%lx, page index "
-					"0x%lx.", ni->mft_no, page->index);
-			flush_dcache_page(page);
-			kunmap(page);
-			unlock_page(page);
-			if (cur_page != xpage)
-				put_page(page);
-			pages[cur_page] = NULL;
-		}
-	}
-
-	/* We no longer need the list of pages. */
-	kfree(pages);
-	kfree(completed_pages);
-
-	/* If we have completed the requested page, we return success. */
-	if (likely(xpage_done))
-		return 0;
-
-	ntfs_debug("Failed. Returning error code %s.", err == -EOVERFLOW ?
-			"EOVERFLOW" : (!err ? "EIO" : "unknown error"));
-	return err < 0 ? err : -EIO;
-
-read_err:
-	ntfs_error(vol->sb, "IO error while reading compressed data.");
-	/* Release the buffer heads. */
-	for (i = 0; i < nr_bhs; i++)
-		brelse(bhs[i]);
-	goto err_out;
-
-map_rl_err:
-	ntfs_error(vol->sb, "ntfs_map_runlist() failed. Cannot read "
-			"compression block.");
-	goto err_out;
-
-rl_err:
-	up_read(&ni->runlist.lock);
-	ntfs_error(vol->sb, "ntfs_rl_vcn_to_lcn() failed. Cannot read "
-			"compression block.");
-	goto err_out;
-
-getblk_err:
-	up_read(&ni->runlist.lock);
-	ntfs_error(vol->sb, "getblk() failed. Cannot read compression block.");
-
-err_out:
-	kfree(bhs);
-	for (i = cur_page; i < max_page; i++) {
-		page = pages[i];
-		if (page) {
-			flush_dcache_page(page);
-			kunmap(page);
-			unlock_page(page);
-			if (i != xpage)
-				put_page(page);
-		}
-	}
-	kfree(pages);
-	kfree(completed_pages);
-	return -EIO;
-}
diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c
deleted file mode 100644
index a3c1c5656f8f..000000000000
--- a/fs/ntfs/debug.c
+++ /dev/null
@@ -1,159 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * debug.c - NTFS kernel debug support. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include "debug.h"
-
-/**
- * __ntfs_warning - output a warning to the syslog
- * @function:	name of function outputting the warning
- * @sb:		super block of mounted ntfs filesystem
- * @fmt:	warning string containing format specifications
- * @...:	a variable number of arguments specified in @fmt
- *
- * Outputs a warning to the syslog for the mounted ntfs filesystem described
- * by @sb.
- *
- * @fmt and the corresponding @... is printf style format string containing
- * the warning string and the corresponding format arguments, respectively.
- *
- * @function is the name of the function from which __ntfs_warning is being
- * called.
- *
- * Note, you should be using debug.h::ntfs_warning(@sb, @fmt, @...) instead
- * as this provides the @function parameter automatically.
- */
-void __ntfs_warning(const char *function, const struct super_block *sb,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-#ifndef DEBUG
-	if (!printk_ratelimit())
-		return;
-#endif
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	if (sb)
-		pr_warn("(device %s): %s(): %pV\n",
-			sb->s_id, flen ? function : "", &vaf);
-	else
-		pr_warn("%s(): %pV\n", flen ? function : "", &vaf);
-	va_end(args);
-}
-
-/**
- * __ntfs_error - output an error to the syslog
- * @function:	name of function outputting the error
- * @sb:		super block of mounted ntfs filesystem
- * @fmt:	error string containing format specifications
- * @...:	a variable number of arguments specified in @fmt
- *
- * Outputs an error to the syslog for the mounted ntfs filesystem described
- * by @sb.
- *
- * @fmt and the corresponding @... is printf style format string containing
- * the error string and the corresponding format arguments, respectively.
- *
- * @function is the name of the function from which __ntfs_error is being
- * called.
- *
- * Note, you should be using debug.h::ntfs_error(@sb, @fmt, @...) instead
- * as this provides the @function parameter automatically.
- */
-void __ntfs_error(const char *function, const struct super_block *sb,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-#ifndef DEBUG
-	if (!printk_ratelimit())
-		return;
-#endif
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	if (sb)
-		pr_err("(device %s): %s(): %pV\n",
-		       sb->s_id, flen ? function : "", &vaf);
-	else
-		pr_err("%s(): %pV\n", flen ? function : "", &vaf);
-	va_end(args);
-}
-
-#ifdef DEBUG
-
-/* If 1, output debug messages, and if 0, don't. */
-int debug_msgs = 0;
-
-void __ntfs_debug(const char *file, int line, const char *function,
-		const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-	int flen = 0;
-
-	if (!debug_msgs)
-		return;
-	if (function)
-		flen = strlen(function);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	pr_debug("(%s, %d): %s(): %pV", file, line, flen ? function : "", &vaf);
-	va_end(args);
-}
-
-/* Dump a runlist. Caller has to provide synchronisation for @rl. */
-void ntfs_debug_dump_runlist(const runlist_element *rl)
-{
-	int i;
-	const char *lcn_str[5] = { "LCN_HOLE         ", "LCN_RL_NOT_MAPPED",
-				   "LCN_ENOENT       ", "LCN_unknown      " };
-
-	if (!debug_msgs)
-		return;
-	pr_debug("Dumping runlist (values in hex):\n");
-	if (!rl) {
-		pr_debug("Run list not present.\n");
-		return;
-	}
-	pr_debug("VCN              LCN               Run length\n");
-	for (i = 0; ; i++) {
-		LCN lcn = (rl + i)->lcn;
-
-		if (lcn < (LCN)0) {
-			int index = -lcn - 1;
-
-			if (index > -LCN_ENOENT - 1)
-				index = 3;
-			pr_debug("%-16Lx %s %-16Lx%s\n",
-					(long long)(rl + i)->vcn, lcn_str[index],
-					(long long)(rl + i)->length,
-					(rl + i)->length ? "" :
-						" (runlist end)");
-		} else
-			pr_debug("%-16Lx %-16Lx  %-16Lx%s\n",
-					(long long)(rl + i)->vcn,
-					(long long)(rl + i)->lcn,
-					(long long)(rl + i)->length,
-					(rl + i)->length ? "" :
-						" (runlist end)");
-		if (!(rl + i)->length)
-			break;
-	}
-}
-
-#endif
diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h
deleted file mode 100644
index 6fdef388f129..000000000000
--- a/fs/ntfs/debug.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * debug.h - NTFS kernel debug support. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_DEBUG_H
-#define _LINUX_NTFS_DEBUG_H
-
-#include <linux/fs.h>
-
-#include "runlist.h"
-
-#ifdef DEBUG
-
-extern int debug_msgs;
-
-extern __printf(4, 5)
-void __ntfs_debug(const char *file, int line, const char *function,
-		  const char *format, ...);
-/**
- * ntfs_debug - write a debug level message to syslog
- * @f:		a printf format string containing the message
- * @...:	the variables to substitute into @f
- *
- * ntfs_debug() writes a DEBUG level message to the syslog but only if the
- * driver was compiled with -DDEBUG. Otherwise, the call turns into a NOP.
- */
-#define ntfs_debug(f, a...)						\
-	__ntfs_debug(__FILE__, __LINE__, __func__, f, ##a)
-
-extern void ntfs_debug_dump_runlist(const runlist_element *rl);
-
-#else	/* !DEBUG */
-
-#define ntfs_debug(fmt, ...)						\
-do {									\
-	if (0)								\
-		no_printk(fmt, ##__VA_ARGS__);				\
-} while (0)
-
-#define ntfs_debug_dump_runlist(rl)	do {} while (0)
-
-#endif	/* !DEBUG */
-
-extern  __printf(3, 4)
-void __ntfs_warning(const char *function, const struct super_block *sb,
-		    const char *fmt, ...);
-#define ntfs_warning(sb, f, a...)	__ntfs_warning(__func__, sb, f, ##a)
-
-extern  __printf(3, 4)
-void __ntfs_error(const char *function, const struct super_block *sb,
-		  const char *fmt, ...);
-#define ntfs_error(sb, f, a...)		__ntfs_error(__func__, sb, f, ##a)
-
-#endif /* _LINUX_NTFS_DEBUG_H */
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
deleted file mode 100644
index 629723a8d712..000000000000
--- a/fs/ntfs/dir.c
+++ /dev/null
@@ -1,1540 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * dir.c - NTFS kernel directory operations. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/blkdev.h>
-
-#include "dir.h"
-#include "aops.h"
-#include "attrib.h"
-#include "mft.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/*
- * The little endian Unicode string $I30 as a global constant.
- */
-ntfschar I30[5] = { cpu_to_le16('$'), cpu_to_le16('I'),
-		cpu_to_le16('3'),	cpu_to_le16('0'), 0 };
-
-/**
- * ntfs_lookup_inode_by_name - find an inode in a directory given its name
- * @dir_ni:	ntfs inode of the directory in which to search for the name
- * @uname:	Unicode name for which to search in the directory
- * @uname_len:	length of the name @uname in Unicode characters
- * @res:	return the found file name if necessary (see below)
- *
- * Look for an inode with name @uname in the directory with inode @dir_ni.
- * ntfs_lookup_inode_by_name() walks the contents of the directory looking for
- * the Unicode name. If the name is found in the directory, the corresponding
- * inode number (>= 0) is returned as a mft reference in cpu format, i.e. it
- * is a 64-bit number containing the sequence number.
- *
- * On error, a negative value is returned corresponding to the error code. In
- * particular if the inode is not found -ENOENT is returned. Note that you
- * can't just check the return value for being negative, you have to check the
- * inode number for being negative which you can extract using MREC(return
- * value).
- *
- * Note, @uname_len does not include the (optional) terminating NULL character.
- *
- * Note, we look for a case sensitive match first but we also look for a case
- * insensitive match at the same time. If we find a case insensitive match, we
- * save that for the case that we don't find an exact match, where we return
- * the case insensitive match and setup @res (which we allocate!) with the mft
- * reference, the file name type, length and with a copy of the little endian
- * Unicode file name itself. If we match a file name which is in the DOS name
- * space, we only return the mft reference and file name type in @res.
- * ntfs_lookup() then uses this to find the long file name in the inode itself.
- * This is to avoid polluting the dcache with short file names. We want them to
- * work but we don't care for how quickly one can access them. This also fixes
- * the dcache aliasing issues.
- *
- * Locking:  - Caller must hold i_mutex on the directory.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-MFT_REF ntfs_lookup_inode_by_name(ntfs_inode *dir_ni, const ntfschar *uname,
-		const int uname_len, ntfs_name **res)
-{
-	ntfs_volume *vol = dir_ni->vol;
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end;
-	u64 mref;
-	ntfs_attr_search_ctx *ctx;
-	int err, rc;
-	VCN vcn, old_vcn;
-	struct address_space *ia_mapping;
-	struct page *page;
-	u8 *kaddr;
-	ntfs_name *name = NULL;
-
-	BUG_ON(!S_ISDIR(VFS_I(dir_ni)->i_mode));
-	BUG_ON(NInoAttr(dir_ni));
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(dir_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return ERR_MREF(PTR_ERR(m));
-	}
-	ctx = ntfs_attr_get_search_ctx(dir_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it's been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ctx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end)
-			goto dir_err_out;
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * We perform a case sensitive comparison and if that matches
-		 * we are done and return the mft reference of the inode (i.e.
-		 * the inode number together with the sequence number for
-		 * consistency checking). We convert it to cpu format before
-		 * returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len)) {
-found_it:
-			/*
-			 * We have a perfect match, so we don't need to care
-			 * about having matched imperfectly before, so we can
-			 * free name and set *res to NULL.
-			 * However, if the perfect match is a short file name,
-			 * we need to signal this through *res, so that
-			 * ntfs_lookup() can fix dcache aliasing issues.
-			 * As an optimization we just reuse an existing
-			 * allocation of *res.
-			 */
-			if (ie->key.file_name.file_name_type == FILE_NAME_DOS) {
-				if (!name) {
-					name = kmalloc(sizeof(ntfs_name),
-							GFP_NOFS);
-					if (!name) {
-						err = -ENOMEM;
-						goto err_out;
-					}
-				}
-				name->mref = le64_to_cpu(
-						ie->data.dir.indexed_file);
-				name->type = FILE_NAME_DOS;
-				name->len = 0;
-				*res = name;
-			} else {
-				kfree(name);
-				*res = NULL;
-			}
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return mref;
-		}
-		/*
-		 * For a case insensitive mount, we also perform a case
-		 * insensitive comparison (provided the file name is not in the
-		 * POSIX namespace). If the comparison matches, and the name is
-		 * in the WIN32 namespace, we cache the filename in *res so
-		 * that the caller, ntfs_lookup(), can work on it. If the
-		 * comparison matches, and the name is in the DOS namespace, we
-		 * only cache the mft reference and the file name type (we set
-		 * the name length to zero for simplicity).
-		 */
-		if (!NVolCaseSensitive(vol) &&
-				ie->key.file_name.file_name_type &&
-				ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				IGNORE_CASE, vol->upcase, vol->upcase_len)) {
-			int name_size = sizeof(ntfs_name);
-			u8 type = ie->key.file_name.file_name_type;
-			u8 len = ie->key.file_name.file_name_length;
-
-			/* Only one case insensitive matching name allowed. */
-			if (name) {
-				ntfs_error(sb, "Found already allocated name "
-						"in phase 1. Please run chkdsk "
-						"and if that doesn't find any "
-						"errors please report you saw "
-						"this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net.");
-				goto dir_err_out;
-			}
-
-			if (type != FILE_NAME_DOS)
-				name_size += len * sizeof(ntfschar);
-			name = kmalloc(name_size, GFP_NOFS);
-			if (!name) {
-				err = -ENOMEM;
-				goto err_out;
-			}
-			name->mref = le64_to_cpu(ie->data.dir.indexed_file);
-			name->type = type;
-			if (type != FILE_NAME_DOS) {
-				name->len = len;
-				memcpy(name->name, ie->key.file_name.file_name,
-						len * sizeof(ntfschar));
-			} else
-				name->len = 0;
-			*res = name;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it;
-	}
-	/*
-	 * We have finished with this index without success. Check for the
-	 * presence of a child node and if not present return -ENOENT, unless
-	 * we have got a matching name cached in name in which case return the
-	 * mft reference associated with it.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		if (name) {
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return name->mref;
-		}
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto err_out;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(dir_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one. Directory inode 0x%lx is "
-				"corrupt or driver bug.", dir_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	ia_mapping = VFS_I(dir_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record. Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(dir_ni);
-	m = NULL;
-	ctx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map directory index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug.", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)vcn, dir_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				dir_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds check. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end) {
-			ntfs_error(sb, "Index entry out of bounds in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * We perform a case sensitive comparison and if that matches
-		 * we are done and return the mft reference of the inode (i.e.
-		 * the inode number together with the sequence number for
-		 * consistency checking). We convert it to cpu format before
-		 * returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len)) {
-found_it2:
-			/*
-			 * We have a perfect match, so we don't need to care
-			 * about having matched imperfectly before, so we can
-			 * free name and set *res to NULL.
-			 * However, if the perfect match is a short file name,
-			 * we need to signal this through *res, so that
-			 * ntfs_lookup() can fix dcache aliasing issues.
-			 * As an optimization we just reuse an existing
-			 * allocation of *res.
-			 */
-			if (ie->key.file_name.file_name_type == FILE_NAME_DOS) {
-				if (!name) {
-					name = kmalloc(sizeof(ntfs_name),
-							GFP_NOFS);
-					if (!name) {
-						err = -ENOMEM;
-						goto unm_err_out;
-					}
-				}
-				name->mref = le64_to_cpu(
-						ie->data.dir.indexed_file);
-				name->type = FILE_NAME_DOS;
-				name->len = 0;
-				*res = name;
-			} else {
-				kfree(name);
-				*res = NULL;
-			}
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			return mref;
-		}
-		/*
-		 * For a case insensitive mount, we also perform a case
-		 * insensitive comparison (provided the file name is not in the
-		 * POSIX namespace). If the comparison matches, and the name is
-		 * in the WIN32 namespace, we cache the filename in *res so
-		 * that the caller, ntfs_lookup(), can work on it. If the
-		 * comparison matches, and the name is in the DOS namespace, we
-		 * only cache the mft reference and the file name type (we set
-		 * the name length to zero for simplicity).
-		 */
-		if (!NVolCaseSensitive(vol) &&
-				ie->key.file_name.file_name_type &&
-				ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length,
-				IGNORE_CASE, vol->upcase, vol->upcase_len)) {
-			int name_size = sizeof(ntfs_name);
-			u8 type = ie->key.file_name.file_name_type;
-			u8 len = ie->key.file_name.file_name_length;
-
-			/* Only one case insensitive matching name allowed. */
-			if (name) {
-				ntfs_error(sb, "Found already allocated name "
-						"in phase 2. Please run chkdsk "
-						"and if that doesn't find any "
-						"errors please report you saw "
-						"this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net.");
-				unlock_page(page);
-				ntfs_unmap_page(page);
-				goto dir_err_out;
-			}
-
-			if (type != FILE_NAME_DOS)
-				name_size += len * sizeof(ntfschar);
-			name = kmalloc(name_size, GFP_NOFS);
-			if (!name) {
-				err = -ENOMEM;
-				goto unm_err_out;
-			}
-			name->mref = le64_to_cpu(ie->data.dir.indexed_file);
-			name->type = type;
-			if (type != FILE_NAME_DOS) {
-				name->len = len;
-				memcpy(name->name, ie->key.file_name.file_name,
-						len * sizeof(ntfschar));
-			} else
-				name->len = 0;
-			*res = name;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it2;
-	}
-	/*
-	 * We have finished with this index buffer without success. Check for
-	 * the presence of a child node.
-	 */
-	if (ie->flags & INDEX_ENTRY_NODE) {
-		if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-			ntfs_error(sb, "Index entry with child node found in "
-					"a leaf node in directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* Child node present, descend into it. */
-		old_vcn = vcn;
-		vcn = sle64_to_cpup((sle64*)((u8*)ie +
-				le16_to_cpu(ie->length) - 8));
-		if (vcn >= 0) {
-			/* If vcn is in the same page cache page as old_vcn we
-			 * recycle the mapped page. */
-			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_SHIFT == vcn <<
-					vol->cluster_size_bits >>
-					PAGE_SHIFT)
-				goto fast_descend_into_child_node;
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto descend_into_child_node;
-		}
-		ntfs_error(sb, "Negative child node vcn in directory inode "
-				"0x%lx.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/*
-	 * No child node present, return -ENOENT, unless we have got a matching
-	 * name cached in name in which case return the mft reference
-	 * associated with it.
-	 */
-	if (name) {
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		return name->mref;
-	}
-	ntfs_debug("Entry not found.");
-	err = -ENOENT;
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(dir_ni);
-	if (name) {
-		kfree(name);
-		*res = NULL;
-	}
-	return ERR_MREF(err);
-dir_err_out:
-	ntfs_error(sb, "Corrupt directory.  Aborting lookup.");
-	goto err_out;
-}
-
-#if 0
-
-// TODO: (AIA)
-// The algorithm embedded in this code will be required for the time when we
-// want to support adding of entries to directories, where we require correct
-// collation of file names in order not to cause corruption of the filesystem.
-
-/**
- * ntfs_lookup_inode_by_name - find an inode in a directory given its name
- * @dir_ni:	ntfs inode of the directory in which to search for the name
- * @uname:	Unicode name for which to search in the directory
- * @uname_len:	length of the name @uname in Unicode characters
- *
- * Look for an inode with name @uname in the directory with inode @dir_ni.
- * ntfs_lookup_inode_by_name() walks the contents of the directory looking for
- * the Unicode name. If the name is found in the directory, the corresponding
- * inode number (>= 0) is returned as a mft reference in cpu format, i.e. it
- * is a 64-bit number containing the sequence number.
- *
- * On error, a negative value is returned corresponding to the error code. In
- * particular if the inode is not found -ENOENT is returned. Note that you
- * can't just check the return value for being negative, you have to check the
- * inode number for being negative which you can extract using MREC(return
- * value).
- *
- * Note, @uname_len does not include the (optional) terminating NULL character.
- */
-u64 ntfs_lookup_inode_by_name(ntfs_inode *dir_ni, const ntfschar *uname,
-		const int uname_len)
-{
-	ntfs_volume *vol = dir_ni->vol;
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end;
-	u64 mref;
-	ntfs_attr_search_ctx *ctx;
-	int err, rc;
-	IGNORE_CASE_BOOL ic;
-	VCN vcn, old_vcn;
-	struct address_space *ia_mapping;
-	struct page *page;
-	u8 *kaddr;
-
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(dir_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return ERR_MREF(PTR_ERR(m));
-	}
-	ctx = ntfs_attr_get_search_ctx(dir_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it's been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ctx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end)
-			goto dir_err_out;
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * If the current entry has a name type of POSIX, the name is
-		 * case sensitive and not otherwise. This has the effect of us
-		 * not being able to access any POSIX file names which collate
-		 * after the non-POSIX one when they only differ in case, but
-		 * anyone doing screwy stuff like that deserves to burn in
-		 * hell... Doing that kind of stuff on NT4 actually causes
-		 * corruption on the partition even when using SP6a and Linux
-		 * is not involved at all.
-		 */
-		ic = ie->key.file_name.file_name_type ? IGNORE_CASE :
-				CASE_SENSITIVE;
-		/*
-		 * If the names match perfectly, we are done and return the
-		 * mft reference of the inode (i.e. the inode number together
-		 * with the sequence number for consistency checking. We
-		 * convert it to cpu format before returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, ic,
-				vol->upcase, vol->upcase_len)) {
-found_it:
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(dir_ni);
-			return mref;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it;
-	}
-	/*
-	 * We have finished with this index without success. Check for the
-	 * presence of a child node.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		/* No child node, return -ENOENT. */
-		err = -ENOENT;
-		goto err_out;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(dir_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one. Directory inode 0x%lx is "
-				"corrupt or driver bug.", dir_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((u8*)ie + le16_to_cpu(ie->length) - 8);
-	ia_mapping = VFS_I(dir_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record. Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(dir_ni);
-	m = NULL;
-	ctx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			dir_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map directory index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			dir_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug.", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)vcn, dir_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				dir_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + dir_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + dir_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds check. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end) {
-			ntfs_error(sb, "Index entry out of bounds in "
-					"directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a name. It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/*
-		 * If the current entry has a name type of POSIX, the name is
-		 * case sensitive and not otherwise. This has the effect of us
-		 * not being able to access any POSIX file names which collate
-		 * after the non-POSIX one when they only differ in case, but
-		 * anyone doing screwy stuff like that deserves to burn in
-		 * hell... Doing that kind of stuff on NT4 actually causes
-		 * corruption on the partition even when using SP6a and Linux
-		 * is not involved at all.
-		 */
-		ic = ie->key.file_name.file_name_type ? IGNORE_CASE :
-				CASE_SENSITIVE;
-		/*
-		 * If the names match perfectly, we are done and return the
-		 * mft reference of the inode (i.e. the inode number together
-		 * with the sequence number for consistency checking. We
-		 * convert it to cpu format before returning.
-		 */
-		if (ntfs_are_names_equal(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, ic,
-				vol->upcase, vol->upcase_len)) {
-found_it2:
-			mref = le64_to_cpu(ie->data.dir.indexed_file);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			return mref;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				IGNORE_CASE, vol->upcase, vol->upcase_len);
-		/*
-		 * If uname collates before the name of the current entry, there
-		 * is definitely no such name in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/* The names are not equal, continue the search. */
-		if (rc)
-			continue;
-		/*
-		 * Names match with case insensitive comparison, now try the
-		 * case sensitive comparison, which is required for proper
-		 * collation.
-		 */
-		rc = ntfs_collate_names(uname, uname_len,
-				(ntfschar*)&ie->key.file_name.file_name,
-				ie->key.file_name.file_name_length, 1,
-				CASE_SENSITIVE, vol->upcase, vol->upcase_len);
-		if (rc == -1)
-			break;
-		if (rc)
-			continue;
-		/*
-		 * Perfect match, this will never happen as the
-		 * ntfs_are_names_equal() call will have gotten a match but we
-		 * still treat it correctly.
-		 */
-		goto found_it2;
-	}
-	/*
-	 * We have finished with this index buffer without success. Check for
-	 * the presence of a child node.
-	 */
-	if (ie->flags & INDEX_ENTRY_NODE) {
-		if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-			ntfs_error(sb, "Index entry with child node found in "
-					"a leaf node in directory inode 0x%lx.",
-					dir_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* Child node present, descend into it. */
-		old_vcn = vcn;
-		vcn = sle64_to_cpup((u8*)ie + le16_to_cpu(ie->length) - 8);
-		if (vcn >= 0) {
-			/* If vcn is in the same page cache page as old_vcn we
-			 * recycle the mapped page. */
-			if (old_vcn << vol->cluster_size_bits >>
-					PAGE_SHIFT == vcn <<
-					vol->cluster_size_bits >>
-					PAGE_SHIFT)
-				goto fast_descend_into_child_node;
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto descend_into_child_node;
-		}
-		ntfs_error(sb, "Negative child node vcn in directory inode "
-				"0x%lx.", dir_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* No child node, return -ENOENT. */
-	ntfs_debug("Entry not found.");
-	err = -ENOENT;
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(dir_ni);
-	return ERR_MREF(err);
-dir_err_out:
-	ntfs_error(sb, "Corrupt directory. Aborting lookup.");
-	goto err_out;
-}
-
-#endif
-
-/**
- * ntfs_filldir - ntfs specific filldir method
- * @vol:	current ntfs volume
- * @ndir:	ntfs inode of current directory
- * @ia_page:	page in which the index allocation buffer @ie is in resides
- * @ie:		current index entry
- * @name:	buffer to use for the converted name
- * @actor:	what to feed the entries to
- *
- * Convert the Unicode @name to the loaded NLS and pass it to the @filldir
- * callback.
- *
- * If @ia_page is not NULL it is the locked page containing the index
- * allocation block containing the index entry @ie.
- *
- * Note, we drop (and then reacquire) the page lock on @ia_page across the
- * @filldir() call otherwise we would deadlock with NFSd when it calls ->lookup
- * since ntfs_lookup() will lock the same page.  As an optimization, we do not
- * retake the lock if we are returning a non-zero value as ntfs_readdir()
- * would need to drop the lock immediately anyway.
- */
-static inline int ntfs_filldir(ntfs_volume *vol,
-		ntfs_inode *ndir, struct page *ia_page, INDEX_ENTRY *ie,
-		u8 *name, struct dir_context *actor)
-{
-	unsigned long mref;
-	int name_len;
-	unsigned dt_type;
-	FILE_NAME_TYPE_FLAGS name_type;
-
-	name_type = ie->key.file_name.file_name_type;
-	if (name_type == FILE_NAME_DOS) {
-		ntfs_debug("Skipping DOS name space entry.");
-		return 0;
-	}
-	if (MREF_LE(ie->data.dir.indexed_file) == FILE_root) {
-		ntfs_debug("Skipping root directory self reference entry.");
-		return 0;
-	}
-	if (MREF_LE(ie->data.dir.indexed_file) < FILE_first_user &&
-			!NVolShowSystemFiles(vol)) {
-		ntfs_debug("Skipping system file.");
-		return 0;
-	}
-	name_len = ntfs_ucstonls(vol, (ntfschar*)&ie->key.file_name.file_name,
-			ie->key.file_name.file_name_length, &name,
-			NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1);
-	if (name_len <= 0) {
-		ntfs_warning(vol->sb, "Skipping unrepresentable inode 0x%llx.",
-				(long long)MREF_LE(ie->data.dir.indexed_file));
-		return 0;
-	}
-	if (ie->key.file_name.file_attributes &
-			FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT)
-		dt_type = DT_DIR;
-	else
-		dt_type = DT_REG;
-	mref = MREF_LE(ie->data.dir.indexed_file);
-	/*
-	 * Drop the page lock otherwise we deadlock with NFS when it calls
-	 * ->lookup since ntfs_lookup() will lock the same page.
-	 */
-	if (ia_page)
-		unlock_page(ia_page);
-	ntfs_debug("Calling filldir for %s with len %i, fpos 0x%llx, inode "
-			"0x%lx, DT_%s.", name, name_len, actor->pos, mref,
-			dt_type == DT_DIR ? "DIR" : "REG");
-	if (!dir_emit(actor, name, name_len, mref, dt_type))
-		return 1;
-	/* Relock the page but not if we are aborting ->readdir. */
-	if (ia_page)
-		lock_page(ia_page);
-	return 0;
-}
-
-/*
- * We use the same basic approach as the old NTFS driver, i.e. we parse the
- * index root entries and then the index allocation entries that are marked
- * as in use in the index bitmap.
- *
- * While this will return the names in random order this doesn't matter for
- * ->readdir but OTOH results in a faster ->readdir.
- *
- * VFS calls ->readdir without BKL but with i_mutex held. This protects the VFS
- * parts (e.g. ->f_pos and ->i_size, and it also protects against directory
- * modifications).
- *
- * Locking:  - Caller must hold i_mutex on the directory.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-static int ntfs_readdir(struct file *file, struct dir_context *actor)
-{
-	s64 ia_pos, ia_start, prev_ia_pos, bmp_pos;
-	loff_t i_size;
-	struct inode *bmp_vi, *vdir = file_inode(file);
-	struct super_block *sb = vdir->i_sb;
-	ntfs_inode *ndir = NTFS_I(vdir);
-	ntfs_volume *vol = NTFS_SB(sb);
-	MFT_RECORD *m;
-	INDEX_ROOT *ir = NULL;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *name = NULL;
-	int rc, err, ir_pos, cur_bmp_pos;
-	struct address_space *ia_mapping, *bmp_mapping;
-	struct page *bmp_page = NULL, *ia_page = NULL;
-	u8 *kaddr, *bmp, *index_end;
-	ntfs_attr_search_ctx *ctx;
-
-	ntfs_debug("Entering for inode 0x%lx, fpos 0x%llx.",
-			vdir->i_ino, actor->pos);
-	rc = err = 0;
-	/* Are we at end of dir yet? */
-	i_size = i_size_read(vdir);
-	if (actor->pos >= i_size + vol->mft_record_size)
-		return 0;
-	/* Emulate . and .. for all directories. */
-	if (!dir_emit_dots(file, actor))
-		return 0;
-	m = NULL;
-	ctx = NULL;
-	/*
-	 * Allocate a buffer to store the current name being processed
-	 * converted to format determined by current NLS.
-	 */
-	name = kmalloc(NTFS_MAX_NAME_LEN * NLS_MAX_CHARSET_SIZE + 1, GFP_NOFS);
-	if (unlikely(!name)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Are we jumping straight into the index allocation attribute? */
-	if (actor->pos >= vol->mft_record_size)
-		goto skip_index_root;
-	/* Get hold of the mft record for the directory. */
-	m = map_mft_record(ndir);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ndir, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Get the offset into the index root attribute. */
-	ir_pos = (s64)actor->pos;
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		ntfs_error(sb, "Index root attribute missing in directory "
-				"inode 0x%lx.", vdir->i_ino);
-		goto err_out;
-	}
-	/*
-	 * Copy the index root attribute value to a buffer so that we can put
-	 * the search context and unmap the mft record before calling the
-	 * filldir() callback.  We need to do this because of NFSd which calls
-	 * ->lookup() from its filldir callback() and this causes NTFS to
-	 * deadlock as ntfs_lookup() maps the mft record of the directory and
-	 * we have got it mapped here already.  The only solution is for us to
-	 * unmap the mft record here so that a call to ntfs_lookup() is able to
-	 * map the mft record without deadlocking.
-	 */
-	rc = le32_to_cpu(ctx->attr->data.resident.value_length);
-	ir = kmalloc(rc, GFP_NOFS);
-	if (unlikely(!ir)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Copy the index root value (it has been verified in read_inode). */
-	memcpy(ir, (u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset), rc);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ndir);
-	ctx = NULL;
-	m = NULL;
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry or until filldir tells us it has had enough
-	 * or signals an error (both covered by the rc test).
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		ntfs_debug("In index root, offset 0x%zx.", (u8*)ie - (u8*)ir);
-		/* Bounds checks. */
-		if (unlikely((u8*)ie < (u8*)ir || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end))
-			goto err_out;
-		/* The last entry cannot contain a name. */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Skip index root entry if continuing previous readdir. */
-		if (ir_pos > (u8*)ie - (u8*)ir)
-			continue;
-		/* Advance the position even if going to skip the entry. */
-		actor->pos = (u8*)ie - (u8*)ir;
-		/* Submit the name to the filldir callback. */
-		rc = ntfs_filldir(vol, ndir, NULL, ie, name, actor);
-		if (rc) {
-			kfree(ir);
-			goto abort;
-		}
-	}
-	/* We are done with the index root and can free the buffer. */
-	kfree(ir);
-	ir = NULL;
-	/* If there is no index allocation attribute we are finished. */
-	if (!NInoIndexAllocPresent(ndir))
-		goto EOD;
-	/* Advance fpos to the beginning of the index allocation. */
-	actor->pos = vol->mft_record_size;
-skip_index_root:
-	kaddr = NULL;
-	prev_ia_pos = -1LL;
-	/* Get the offset into the index allocation attribute. */
-	ia_pos = (s64)actor->pos - vol->mft_record_size;
-	ia_mapping = vdir->i_mapping;
-	ntfs_debug("Inode 0x%lx, getting index bitmap.", vdir->i_ino);
-	bmp_vi = ntfs_attr_iget(vdir, AT_BITMAP, I30, 4);
-	if (IS_ERR(bmp_vi)) {
-		ntfs_error(sb, "Failed to get bitmap attribute.");
-		err = PTR_ERR(bmp_vi);
-		goto err_out;
-	}
-	bmp_mapping = bmp_vi->i_mapping;
-	/* Get the starting bitmap bit position and sanity check it. */
-	bmp_pos = ia_pos >> ndir->itype.index.block_size_bits;
-	if (unlikely(bmp_pos >> 3 >= i_size_read(bmp_vi))) {
-		ntfs_error(sb, "Current index allocation position exceeds "
-				"index bitmap size.");
-		goto iput_err_out;
-	}
-	/* Get the starting bit position in the current bitmap page. */
-	cur_bmp_pos = bmp_pos & ((PAGE_SIZE * 8) - 1);
-	bmp_pos &= ~(u64)((PAGE_SIZE * 8) - 1);
-get_next_bmp_page:
-	ntfs_debug("Reading bitmap with page index 0x%llx, bit ofs 0x%llx",
-			(unsigned long long)bmp_pos >> (3 + PAGE_SHIFT),
-			(unsigned long long)bmp_pos &
-			(unsigned long long)((PAGE_SIZE * 8) - 1));
-	bmp_page = ntfs_map_page(bmp_mapping,
-			bmp_pos >> (3 + PAGE_SHIFT));
-	if (IS_ERR(bmp_page)) {
-		ntfs_error(sb, "Reading index bitmap failed.");
-		err = PTR_ERR(bmp_page);
-		bmp_page = NULL;
-		goto iput_err_out;
-	}
-	bmp = (u8*)page_address(bmp_page);
-	/* Find next index block in use. */
-	while (!(bmp[cur_bmp_pos >> 3] & (1 << (cur_bmp_pos & 7)))) {
-find_next_index_buffer:
-		cur_bmp_pos++;
-		/*
-		 * If we have reached the end of the bitmap page, get the next
-		 * page, and put away the old one.
-		 */
-		if (unlikely((cur_bmp_pos >> 3) >= PAGE_SIZE)) {
-			ntfs_unmap_page(bmp_page);
-			bmp_pos += PAGE_SIZE * 8;
-			cur_bmp_pos = 0;
-			goto get_next_bmp_page;
-		}
-		/* If we have reached the end of the bitmap, we are done. */
-		if (unlikely(((bmp_pos + cur_bmp_pos) >> 3) >= i_size))
-			goto unm_EOD;
-		ia_pos = (bmp_pos + cur_bmp_pos) <<
-				ndir->itype.index.block_size_bits;
-	}
-	ntfs_debug("Handling index buffer 0x%llx.",
-			(unsigned long long)bmp_pos + cur_bmp_pos);
-	/* If the current index buffer is in the same page we reuse the page. */
-	if ((prev_ia_pos & (s64)PAGE_MASK) !=
-			(ia_pos & (s64)PAGE_MASK)) {
-		prev_ia_pos = ia_pos;
-		if (likely(ia_page != NULL)) {
-			unlock_page(ia_page);
-			ntfs_unmap_page(ia_page);
-		}
-		/*
-		 * Map the page cache page containing the current ia_pos,
-		 * reading it from disk if necessary.
-		 */
-		ia_page = ntfs_map_page(ia_mapping, ia_pos >> PAGE_SHIFT);
-		if (IS_ERR(ia_page)) {
-			ntfs_error(sb, "Reading index allocation data failed.");
-			err = PTR_ERR(ia_page);
-			ia_page = NULL;
-			goto err_out;
-		}
-		lock_page(ia_page);
-		kaddr = (u8*)page_address(ia_page);
-	}
-	/* Get the current index buffer. */
-	ia = (INDEX_ALLOCATION*)(kaddr + (ia_pos & ~PAGE_MASK &
-					  ~(s64)(ndir->itype.index.block_size - 1)));
-	/* Bounds checks. */
-	if (unlikely((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE)) {
-		ntfs_error(sb, "Out of bounds check failed. Corrupt directory "
-				"inode 0x%lx or driver bug.", vdir->i_ino);
-		goto err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Directory index record with vcn 0x%llx is "
-				"corrupt.  Corrupt inode 0x%lx.  Run chkdsk.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	if (unlikely(sle64_to_cpu(ia->index_block_vcn) != (ia_pos &
-			~(s64)(ndir->itype.index.block_size - 1)) >>
-			ndir->itype.index.vcn_size_bits)) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx). "
-				"Directory inode 0x%lx is corrupt or driver "
-				"bug. ", (unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	if (unlikely(le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			ndir->itype.index.block_size)) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx has a size (%u) differing from the "
-				"directory specified size (%u). Directory "
-				"inode is corrupt or driver bug.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				ndir->itype.index.block_size);
-		goto err_out;
-	}
-	index_end = (u8*)ia + ndir->itype.index.block_size;
-	if (unlikely(index_end > kaddr + PAGE_SIZE)) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of directory inode "
-				"0x%lx crosses page boundary. Impossible! "
-				"Cannot access! This is probably a bug in the "
-				"driver.", (unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	ia_start = ia_pos & ~(s64)(ndir->itype.index.block_size - 1);
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (unlikely(index_end > (u8*)ia + ndir->itype.index.block_size)) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of directory "
-				"inode 0x%lx exceeds maximum size.",
-				(unsigned long long)ia_pos >>
-				ndir->itype.index.vcn_size_bits, vdir->i_ino);
-		goto err_out;
-	}
-	/* The first index entry in this index buffer. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry or until filldir tells us it has had enough
-	 * or signals an error (both covered by the rc test).
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		ntfs_debug("In index allocation, offset 0x%llx.",
-				(unsigned long long)ia_start +
-				(unsigned long long)((u8*)ie - (u8*)ia));
-		/* Bounds checks. */
-		if (unlikely((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->key_length) >
-				index_end))
-			goto err_out;
-		/* The last entry cannot contain a name. */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Skip index block entry if continuing previous readdir. */
-		if (ia_pos - ia_start > (u8*)ie - (u8*)ia)
-			continue;
-		/* Advance the position even if going to skip the entry. */
-		actor->pos = (u8*)ie - (u8*)ia +
-				(sle64_to_cpu(ia->index_block_vcn) <<
-				ndir->itype.index.vcn_size_bits) +
-				vol->mft_record_size;
-		/*
-		 * Submit the name to the @filldir callback.  Note,
-		 * ntfs_filldir() drops the lock on @ia_page but it retakes it
-		 * before returning, unless a non-zero value is returned in
-		 * which case the page is left unlocked.
-		 */
-		rc = ntfs_filldir(vol, ndir, ia_page, ie, name, actor);
-		if (rc) {
-			/* @ia_page is already unlocked in this case. */
-			ntfs_unmap_page(ia_page);
-			ntfs_unmap_page(bmp_page);
-			iput(bmp_vi);
-			goto abort;
-		}
-	}
-	goto find_next_index_buffer;
-unm_EOD:
-	if (ia_page) {
-		unlock_page(ia_page);
-		ntfs_unmap_page(ia_page);
-	}
-	ntfs_unmap_page(bmp_page);
-	iput(bmp_vi);
-EOD:
-	/* We are finished, set fpos to EOD. */
-	actor->pos = i_size + vol->mft_record_size;
-abort:
-	kfree(name);
-	return 0;
-err_out:
-	if (bmp_page) {
-		ntfs_unmap_page(bmp_page);
-iput_err_out:
-		iput(bmp_vi);
-	}
-	if (ia_page) {
-		unlock_page(ia_page);
-		ntfs_unmap_page(ia_page);
-	}
-	kfree(ir);
-	kfree(name);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ndir);
-	if (!err)
-		err = -EIO;
-	ntfs_debug("Failed. Returning error code %i.", -err);
-	return err;
-}
-
-/**
- * ntfs_dir_open - called when an inode is about to be opened
- * @vi:		inode to be opened
- * @filp:	file structure describing the inode
- *
- * Limit directory size to the page cache limit on architectures where unsigned
- * long is 32-bits. This is the most we can do for now without overflowing the
- * page cache page index. Doing it this way means we don't run into problems
- * because of existing too large directories. It would be better to allow the
- * user to read the accessible part of the directory but I doubt very much
- * anyone is going to hit this check on a 32-bit architecture, so there is no
- * point in adding the extra complexity required to support this.
- *
- * On 64-bit architectures, the check is hopefully optimized away by the
- * compiler.
- */
-static int ntfs_dir_open(struct inode *vi, struct file *filp)
-{
-	if (sizeof(unsigned long) < 8) {
-		if (i_size_read(vi) > MAX_LFS_FILESIZE)
-			return -EFBIG;
-	}
-	return 0;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_dir_fsync - sync a directory to disk
- * @filp:	directory to be synced
- * @start:	offset in bytes of the beginning of data range to sync
- * @end:	offset in bytes of the end of data range (inclusive)
- * @datasync:	if non-zero only flush user data and not metadata
- *
- * Data integrity sync of a directory to disk.  Used for fsync, fdatasync, and
- * msync system calls.  This function is based on file.c::ntfs_file_fsync().
- *
- * Write the mft record and all associated extent mft records as well as the
- * $INDEX_ALLOCATION and $BITMAP attributes and then sync the block device.
- *
- * If @datasync is true, we do not wait on the inode(s) to be written out
- * but we always wait on the page cache pages to be written out.
- *
- * Note: In the past @filp could be NULL so we ignore it as we don't need it
- * anyway.
- *
- * Locking: Caller must hold i_mutex on the inode.
- *
- * TODO: We should probably also write all attribute/index inodes associated
- * with this inode but since we have no simple way of getting to them we ignore
- * this problem for now.  We do write the $BITMAP attribute if it is present
- * which is the important one for a directory so things are not too bad.
- */
-static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end,
-			  int datasync)
-{
-	struct inode *bmp_vi, *vi = filp->f_mapping->host;
-	int err, ret;
-	ntfs_attr na;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-
-	err = file_write_and_wait_range(filp, start, end);
-	if (err)
-		return err;
-	inode_lock(vi);
-
-	BUG_ON(!S_ISDIR(vi->i_mode));
-	/* If the bitmap attribute inode is in memory sync it, too. */
-	na.mft_no = vi->i_ino;
-	na.type = AT_BITMAP;
-	na.name = I30;
-	na.name_len = 4;
-	bmp_vi = ilookup5(vi->i_sb, vi->i_ino, ntfs_test_inode, &na);
-	if (bmp_vi) {
- 		write_inode_now(bmp_vi, !datasync);
-		iput(bmp_vi);
-	}
-	ret = __ntfs_write_inode(vi, 1);
-	write_inode_now(vi, !datasync);
-	err = sync_blockdev(vi->i_sb->s_bdev);
-	if (unlikely(err && !ret))
-		ret = err;
-	if (likely(!ret))
-		ntfs_debug("Done.");
-	else
-		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
-				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	inode_unlock(vi);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-WRAP_DIR_ITER(ntfs_readdir) // FIXME!
-const struct file_operations ntfs_dir_ops = {
-	.llseek		= generic_file_llseek,	/* Seek inside directory. */
-	.read		= generic_read_dir,	/* Return -EISDIR. */
-	.iterate_shared	= shared_ntfs_readdir,	/* Read directory contents. */
-#ifdef NTFS_RW
-	.fsync		= ntfs_dir_fsync,	/* Sync a directory to disk. */
-#endif /* NTFS_RW */
-	/*.ioctl	= ,*/			/* Perform function on the
-						   mounted filesystem. */
-	.open		= ntfs_dir_open,	/* Open directory. */
-};
diff --git a/fs/ntfs/dir.h b/fs/ntfs/dir.h
deleted file mode 100644
index 0e326753df40..000000000000
--- a/fs/ntfs/dir.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * dir.h - Defines for directory handling in NTFS Linux kernel driver. Part of
- *	   the Linux-NTFS project.
- *
- * Copyright (c) 2002-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_DIR_H
-#define _LINUX_NTFS_DIR_H
-
-#include "layout.h"
-#include "inode.h"
-#include "types.h"
-
-/*
- * ntfs_name is used to return the file name to the caller of
- * ntfs_lookup_inode_by_name() in order for the caller (namei.c::ntfs_lookup())
- * to be able to deal with dcache aliasing issues.
- */
-typedef struct {
-	MFT_REF mref;
-	FILE_NAME_TYPE_FLAGS type;
-	u8 len;
-	ntfschar name[0];
-} __attribute__ ((__packed__)) ntfs_name;
-
-/* The little endian Unicode string $I30 as a global constant. */
-extern ntfschar I30[5];
-
-extern MFT_REF ntfs_lookup_inode_by_name(ntfs_inode *dir_ni,
-		const ntfschar *uname, const int uname_len, ntfs_name **res);
-
-#endif /* _LINUX_NTFS_FS_DIR_H */
diff --git a/fs/ntfs/endian.h b/fs/ntfs/endian.h
deleted file mode 100644
index f30c139bf9ae..000000000000
--- a/fs/ntfs/endian.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * endian.h - Defines for endianness handling in NTFS Linux kernel driver.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_ENDIAN_H
-#define _LINUX_NTFS_ENDIAN_H
-
-#include <asm/byteorder.h>
-#include "types.h"
-
-/*
- * Signed endianness conversion functions.
- */
-
-static inline s16 sle16_to_cpu(sle16 x)
-{
-	return le16_to_cpu((__force le16)x);
-}
-
-static inline s32 sle32_to_cpu(sle32 x)
-{
-	return le32_to_cpu((__force le32)x);
-}
-
-static inline s64 sle64_to_cpu(sle64 x)
-{
-	return le64_to_cpu((__force le64)x);
-}
-
-static inline s16 sle16_to_cpup(sle16 *x)
-{
-	return le16_to_cpu(*(__force le16*)x);
-}
-
-static inline s32 sle32_to_cpup(sle32 *x)
-{
-	return le32_to_cpu(*(__force le32*)x);
-}
-
-static inline s64 sle64_to_cpup(sle64 *x)
-{
-	return le64_to_cpu(*(__force le64*)x);
-}
-
-static inline sle16 cpu_to_sle16(s16 x)
-{
-	return (__force sle16)cpu_to_le16(x);
-}
-
-static inline sle32 cpu_to_sle32(s32 x)
-{
-	return (__force sle32)cpu_to_le32(x);
-}
-
-static inline sle64 cpu_to_sle64(s64 x)
-{
-	return (__force sle64)cpu_to_le64(x);
-}
-
-static inline sle16 cpu_to_sle16p(s16 *x)
-{
-	return (__force sle16)cpu_to_le16(*x);
-}
-
-static inline sle32 cpu_to_sle32p(s32 *x)
-{
-	return (__force sle32)cpu_to_le32(*x);
-}
-
-static inline sle64 cpu_to_sle64p(s64 *x)
-{
-	return (__force sle64)cpu_to_le64(*x);
-}
-
-#endif /* _LINUX_NTFS_ENDIAN_H */
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
deleted file mode 100644
index 297c0b9db621..000000000000
--- a/fs/ntfs/file.c
+++ /dev/null
@@ -1,1997 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc.
- */
-
-#include <linux/blkdev.h>
-#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
-#include <linux/gfp.h>
-#include <linux/pagemap.h>
-#include <linux/pagevec.h>
-#include <linux/sched/signal.h>
-#include <linux/swap.h>
-#include <linux/uio.h>
-#include <linux/writeback.h>
-
-#include <asm/page.h>
-#include <linux/uaccess.h>
-
-#include "attrib.h"
-#include "bitmap.h"
-#include "inode.h"
-#include "debug.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-
-/**
- * ntfs_file_open - called when an inode is about to be opened
- * @vi:		inode to be opened
- * @filp:	file structure describing the inode
- *
- * Limit file size to the page cache limit on architectures where unsigned long
- * is 32-bits. This is the most we can do for now without overflowing the page
- * cache page index. Doing it this way means we don't run into problems because
- * of existing too large files. It would be better to allow the user to read
- * the beginning of the file but I doubt very much anyone is going to hit this
- * check on a 32-bit architecture, so there is no point in adding the extra
- * complexity required to support this.
- *
- * On 64-bit architectures, the check is hopefully optimized away by the
- * compiler.
- *
- * After the check passes, just call generic_file_open() to do its work.
- */
-static int ntfs_file_open(struct inode *vi, struct file *filp)
-{
-	if (sizeof(unsigned long) < 8) {
-		if (i_size_read(vi) > MAX_LFS_FILESIZE)
-			return -EOVERFLOW;
-	}
-	return generic_file_open(vi, filp);
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_attr_extend_initialized - extend the initialized size of an attribute
- * @ni:			ntfs inode of the attribute to extend
- * @new_init_size:	requested new initialized size in bytes
- *
- * Extend the initialized size of an attribute described by the ntfs inode @ni
- * to @new_init_size bytes.  This involves zeroing any non-sparse space between
- * the old initialized size and @new_init_size both in the page cache and on
- * disk (if relevant complete pages are already uptodate in the page cache then
- * these are simply marked dirty).
- *
- * As a side-effect, the file size (vfs inode->i_size) may be incremented as,
- * in the resident attribute case, it is tied to the initialized size and, in
- * the non-resident attribute case, it may not fall below the initialized size.
- *
- * Note that if the attribute is resident, we do not need to touch the page
- * cache at all.  This is because if the page cache page is not uptodate we
- * bring it uptodate later, when doing the write to the mft record since we
- * then already have the page mapped.  And if the page is uptodate, the
- * non-initialized region will already have been zeroed when the page was
- * brought uptodate and the region may in fact already have been overwritten
- * with new data via mmap() based writes, so we cannot just zero it.  And since
- * POSIX specifies that the behaviour of resizing a file whilst it is mmap()ped
- * is unspecified, we choose not to do zeroing and thus we do not need to touch
- * the page at all.  For a more detailed explanation see ntfs_truncate() in
- * fs/ntfs/inode.c.
- *
- * Return 0 on success and -errno on error.  In the case that an error is
- * encountered it is possible that the initialized size will already have been
- * incremented some way towards @new_init_size but it is guaranteed that if
- * this is the case, the necessary zeroing will also have happened and that all
- * metadata is self-consistent.
- *
- * Locking: i_mutex on the vfs inode corrseponsind to the ntfs inode @ni must be
- *	    held by the caller.
- */
-static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size)
-{
-	s64 old_init_size;
-	loff_t old_i_size;
-	pgoff_t index, end_index;
-	unsigned long flags;
-	struct inode *vi = VFS_I(ni);
-	ntfs_inode *base_ni;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx = NULL;
-	struct address_space *mapping;
-	struct page *page = NULL;
-	u8 *kattr;
-	int err;
-	u32 attr_len;
-
-	read_lock_irqsave(&ni->size_lock, flags);
-	old_init_size = ni->initialized_size;
-	old_i_size = i_size_read(vi);
-	BUG_ON(new_init_size > ni->allocated_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
-			"old_initialized_size 0x%llx, "
-			"new_initialized_size 0x%llx, i_size 0x%llx.",
-			vi->i_ino, (unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)old_init_size,
-			(unsigned long long)new_init_size, old_i_size);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Use goto to reduce indentation and we need the label below anyway. */
-	if (NInoNonResident(ni))
-		goto do_non_resident_extend;
-	BUG_ON(old_init_size != old_i_size);
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(a->non_resident);
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	BUG_ON(old_i_size != (loff_t)attr_len);
-	/*
-	 * Do the zeroing in the mft record and update the attribute size in
-	 * the mft record.
-	 */
-	kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
-	memset(kattr + attr_len, 0, new_init_size - attr_len);
-	a->data.resident.value_length = cpu_to_le32((u32)new_init_size);
-	/* Finally, update the sizes in the vfs and ntfs inodes. */
-	write_lock_irqsave(&ni->size_lock, flags);
-	i_size_write(vi, new_init_size);
-	ni->initialized_size = new_init_size;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	goto done;
-do_non_resident_extend:
-	/*
-	 * If the new initialized size @new_init_size exceeds the current file
-	 * size (vfs inode->i_size), we need to extend the file size to the
-	 * new initialized size.
-	 */
-	if (new_init_size > old_i_size) {
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			m = NULL;
-			goto err_out;
-		}
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			goto err_out;
-		}
-		m = ctx->mrec;
-		a = ctx->attr;
-		BUG_ON(!a->non_resident);
-		BUG_ON(old_i_size != (loff_t)
-				sle64_to_cpu(a->data.non_resident.data_size));
-		a->data.non_resident.data_size = cpu_to_sle64(new_init_size);
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		/* Update the file size in the vfs inode. */
-		i_size_write(vi, new_init_size);
-		ntfs_attr_put_search_ctx(ctx);
-		ctx = NULL;
-		unmap_mft_record(base_ni);
-		m = NULL;
-	}
-	mapping = vi->i_mapping;
-	index = old_init_size >> PAGE_SHIFT;
-	end_index = (new_init_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	do {
-		/*
-		 * Read the page.  If the page is not present, this will zero
-		 * the uninitialized regions for us.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			goto init_err_out;
-		}
-		/*
-		 * Update the initialized size in the ntfs inode.  This is
-		 * enough to make ntfs_writepage() work.
-		 */
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = (s64)(index + 1) << PAGE_SHIFT;
-		if (ni->initialized_size > new_init_size)
-			ni->initialized_size = new_init_size;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		/* Set the page dirty so it gets written out. */
-		set_page_dirty(page);
-		put_page(page);
-		/*
-		 * Play nice with the vm and the rest of the system.  This is
-		 * very much needed as we can potentially be modifying the
-		 * initialised size from a very small value to a really huge
-		 * value, e.g.
-		 *	f = open(somefile, O_TRUNC);
-		 *	truncate(f, 10GiB);
-		 *	seek(f, 10GiB);
-		 *	write(f, 1);
-		 * And this would mean we would be marking dirty hundreds of
-		 * thousands of pages or as in the above example more than
-		 * two and a half million pages!
-		 *
-		 * TODO: For sparse pages could optimize this workload by using
-		 * the FsMisc / MiscFs page bit as a "PageIsSparse" bit.  This
-		 * would be set in read_folio for sparse pages and here we would
-		 * not need to mark dirty any pages which have this bit set.
-		 * The only caveat is that we have to clear the bit everywhere
-		 * where we allocate any clusters that lie in the page or that
-		 * contain the page.
-		 *
-		 * TODO: An even greater optimization would be for us to only
-		 * call read_folio() on pages which are not in sparse regions as
-		 * determined from the runlist.  This would greatly reduce the
-		 * number of pages we read and make dirty in the case of sparse
-		 * files.
-		 */
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-	} while (++index < end_index);
-	read_lock_irqsave(&ni->size_lock, flags);
-	BUG_ON(ni->initialized_size != new_init_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/* Now bring in sync the initialized_size in the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		goto init_err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto init_err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto init_err_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	BUG_ON(!a->non_resident);
-	a->data.non_resident.initialized_size = cpu_to_sle64(new_init_size);
-done:
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_debug("Done, initialized_size 0x%llx, i_size 0x%llx.",
-			(unsigned long long)new_init_size, i_size_read(vi));
-	return 0;
-init_err_out:
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->initialized_size = old_init_size;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-}
-
-static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb,
-		struct iov_iter *from)
-{
-	loff_t pos;
-	s64 end, ll;
-	ssize_t err;
-	unsigned long flags;
-	struct file *file = iocb->ki_filp;
-	struct inode *vi = file_inode(file);
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
-			"0x%llx, count 0x%zx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)iocb->ki_pos,
-			iov_iter_count(from));
-	err = generic_write_checks(iocb, from);
-	if (unlikely(err <= 0))
-		goto out;
-	/*
-	 * All checks have passed.  Before we start doing any writing we want
-	 * to abort any totally illegal writes.
-	 */
-	BUG_ON(NInoMstProtected(ni));
-	BUG_ON(ni->type != AT_DATA);
-	/* If file is encrypted, deny access, just like NT4. */
-	if (NInoEncrypted(ni)) {
-		/* Only $DATA attributes can be encrypted. */
-		/*
-		 * Reminder for later: Encrypted files are _always_
-		 * non-resident so that the content can always be encrypted.
-		 */
-		ntfs_debug("Denying write access to encrypted file.");
-		err = -EACCES;
-		goto out;
-	}
-	if (NInoCompressed(ni)) {
-		/* Only unnamed $DATA attribute can be compressed. */
-		BUG_ON(ni->name_len);
-		/*
-		 * Reminder for later: If resident, the data is not actually
-		 * compressed.  Only on the switch to non-resident does
-		 * compression kick in.  This is in contrast to encrypted files
-		 * (see above).
-		 */
-		ntfs_error(vi->i_sb, "Writing to compressed files is not "
-				"implemented yet.  Sorry.");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-	err = file_remove_privs(file);
-	if (unlikely(err))
-		goto out;
-	/*
-	 * Our ->update_time method always succeeds thus file_update_time()
-	 * cannot fail either so there is no need to check the return code.
-	 */
-	file_update_time(file);
-	pos = iocb->ki_pos;
-	/* The first byte after the last cluster being written to. */
-	end = (pos + iov_iter_count(from) + vol->cluster_size_mask) &
-			~(u64)vol->cluster_size_mask;
-	/*
-	 * If the write goes beyond the allocated size, extend the allocation
-	 * to cover the whole of the write, rounded up to the nearest cluster.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (end > ll) {
-		/*
-		 * Extend the allocation without changing the data size.
-		 *
-		 * Note we ensure the allocation is big enough to at least
-		 * write some data but we do not require the allocation to be
-		 * complete, i.e. it may be partial.
-		 */
-		ll = ntfs_attr_extend_allocation(ni, end, -1, pos);
-		if (likely(ll >= 0)) {
-			BUG_ON(pos >= ll);
-			/* If the extension was partial truncate the write. */
-			if (end > ll) {
-				ntfs_debug("Truncating write to inode 0x%lx, "
-						"attribute type 0x%x, because "
-						"the allocation was only "
-						"partially extended.",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type));
-				iov_iter_truncate(from, ll - pos);
-			}
-		} else {
-			err = ll;
-			read_lock_irqsave(&ni->size_lock, flags);
-			ll = ni->allocated_size;
-			read_unlock_irqrestore(&ni->size_lock, flags);
-			/* Perform a partial write if possible or fail. */
-			if (pos < ll) {
-				ntfs_debug("Truncating write to inode 0x%lx "
-						"attribute type 0x%x, because "
-						"extending the allocation "
-						"failed (error %d).",
-						vi->i_ino, (unsigned)
-						le32_to_cpu(ni->type),
-						(int)-err);
-				iov_iter_truncate(from, ll - pos);
-			} else {
-				if (err != -ENOSPC)
-					ntfs_error(vi->i_sb, "Cannot perform "
-							"write to inode "
-							"0x%lx, attribute "
-							"type 0x%x, because "
-							"extending the "
-							"allocation failed "
-							"(error %ld).",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type),
-							(long)-err);
-				else
-					ntfs_debug("Cannot perform write to "
-							"inode 0x%lx, "
-							"attribute type 0x%x, "
-							"because there is not "
-							"space left.",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type));
-				goto out;
-			}
-		}
-	}
-	/*
-	 * If the write starts beyond the initialized size, extend it up to the
-	 * beginning of the write and initialize all non-sparse space between
-	 * the old initialized size and the new one.  This automatically also
-	 * increments the vfs inode->i_size to keep it above or equal to the
-	 * initialized_size.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	ll = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (pos > ll) {
-		/*
-		 * Wait for ongoing direct i/o to complete before proceeding.
-		 * New direct i/o cannot start as we hold i_mutex.
-		 */
-		inode_dio_wait(vi);
-		err = ntfs_attr_extend_initialized(ni, pos);
-		if (unlikely(err < 0))
-			ntfs_error(vi->i_sb, "Cannot perform write to inode "
-					"0x%lx, attribute type 0x%x, because "
-					"extending the initialized size "
-					"failed (error %d).", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type),
-					(int)-err);
-	}
-out:
-	return err;
-}
-
-/**
- * __ntfs_grab_cache_pages - obtain a number of locked pages
- * @mapping:	address space mapping from which to obtain page cache pages
- * @index:	starting index in @mapping at which to begin obtaining pages
- * @nr_pages:	number of page cache pages to obtain
- * @pages:	array of pages in which to return the obtained page cache pages
- * @cached_page: allocated but as yet unused page
- *
- * Obtain @nr_pages locked page cache pages from the mapping @mapping and
- * starting at index @index.
- *
- * If a page is newly created, add it to lru list
- *
- * Note, the page locks are obtained in ascending page index order.
- */
-static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
-		pgoff_t index, const unsigned nr_pages, struct page **pages,
-		struct page **cached_page)
-{
-	int err, nr;
-
-	BUG_ON(!nr_pages);
-	err = nr = 0;
-	do {
-		pages[nr] = find_get_page_flags(mapping, index, FGP_LOCK |
-				FGP_ACCESSED);
-		if (!pages[nr]) {
-			if (!*cached_page) {
-				*cached_page = page_cache_alloc(mapping);
-				if (unlikely(!*cached_page)) {
-					err = -ENOMEM;
-					goto err_out;
-				}
-			}
-			err = add_to_page_cache_lru(*cached_page, mapping,
-				   index,
-				   mapping_gfp_constraint(mapping, GFP_KERNEL));
-			if (unlikely(err)) {
-				if (err == -EEXIST)
-					continue;
-				goto err_out;
-			}
-			pages[nr] = *cached_page;
-			*cached_page = NULL;
-		}
-		index++;
-		nr++;
-	} while (nr < nr_pages);
-out:
-	return err;
-err_out:
-	while (nr > 0) {
-		unlock_page(pages[--nr]);
-		put_page(pages[nr]);
-	}
-	goto out;
-}
-
-static inline void ntfs_submit_bh_for_read(struct buffer_head *bh)
-{
-	lock_buffer(bh);
-	get_bh(bh);
-	bh->b_end_io = end_buffer_read_sync;
-	submit_bh(REQ_OP_READ, bh);
-}
-
-/**
- * ntfs_prepare_pages_for_non_resident_write - prepare pages for receiving data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * This is called for non-resident attributes from ntfs_file_buffered_write()
- * with i_mutex held on the inode (@pages[0]->mapping->host).  There are
- * @nr_pages pages in @pages which are locked but not kmap()ped.  The source
- * data has not yet been copied into the @pages.
- * 
- * Need to fill any holes with actual clusters, allocate buffers if necessary,
- * ensure all the buffers are mapped, and bring uptodate any buffers that are
- * only partially being written to.
- *
- * If @nr_pages is greater than one, we are guaranteed that the cluster size is
- * greater than PAGE_SIZE, that all pages in @pages are entirely inside
- * the same cluster and that they are the entirety of that cluster, and that
- * the cluster is sparse, i.e. we need to allocate a cluster to fill the hole.
- *
- * i_size is not to be modified yet.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_prepare_pages_for_non_resident_write(struct page **pages,
-		unsigned nr_pages, s64 pos, size_t bytes)
-{
-	VCN vcn, highest_vcn = 0, cpos, cend, bh_cpos, bh_cend;
-	LCN lcn;
-	s64 bh_pos, vcn_len, end, initialized_size;
-	sector_t lcn_block;
-	struct folio *folio;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni = NULL;
-	ntfs_volume *vol;
-	runlist_element *rl, *rl2;
-	struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a = NULL;
-	unsigned long flags;
-	u32 attr_rec_len = 0;
-	unsigned blocksize, u;
-	int err, mp_size;
-	bool rl_write_locked, was_hole, is_retry;
-	unsigned char blocksize_bits;
-	struct {
-		u8 runlist_merged:1;
-		u8 mft_attr_mapped:1;
-		u8 mp_rebuilt:1;
-		u8 attr_switched:1;
-	} status = { 0, 0, 0, 0 };
-
-	BUG_ON(!nr_pages);
-	BUG_ON(!pages);
-	BUG_ON(!*pages);
-	vi = pages[0]->mapping->host;
-	ni = NTFS_I(vi);
-	vol = ni->vol;
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
-			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
-			vi->i_ino, ni->type, pages[0]->index, nr_pages,
-			(long long)pos, bytes);
-	blocksize = vol->sb->s_blocksize;
-	blocksize_bits = vol->sb->s_blocksize_bits;
-	rl_write_locked = false;
-	rl = NULL;
-	err = 0;
-	vcn = lcn = -1;
-	vcn_len = 0;
-	lcn_block = -1;
-	was_hole = false;
-	cpos = pos >> vol->cluster_size_bits;
-	end = pos + bytes;
-	cend = (end + vol->cluster_size - 1) >> vol->cluster_size_bits;
-	/*
-	 * Loop over each buffer in each folio.  Use goto to
-	 * reduce indentation.
-	 */
-	u = 0;
-do_next_folio:
-	folio = page_folio(pages[u]);
-	bh_pos = folio_pos(folio);
-	head = folio_buffers(folio);
-	if (!head)
-		/*
-		 * create_empty_buffers() will create uptodate/dirty
-		 * buffers if the folio is uptodate/dirty.
-		 */
-		head = create_empty_buffers(folio, blocksize, 0);
-	bh = head;
-	do {
-		VCN cdelta;
-		s64 bh_end;
-		unsigned bh_cofs;
-
-		/* Clear buffer_new on all buffers to reinitialise state. */
-		if (buffer_new(bh))
-			clear_buffer_new(bh);
-		bh_end = bh_pos + blocksize;
-		bh_cpos = bh_pos >> vol->cluster_size_bits;
-		bh_cofs = bh_pos & vol->cluster_size_mask;
-		if (buffer_mapped(bh)) {
-			/*
-			 * The buffer is already mapped.  If it is uptodate,
-			 * ignore it.
-			 */
-			if (buffer_uptodate(bh))
-				continue;
-			/*
-			 * The buffer is not uptodate.  If the folio is uptodate
-			 * set the buffer uptodate and otherwise ignore it.
-			 */
-			if (folio_test_uptodate(folio)) {
-				set_buffer_uptodate(bh);
-				continue;
-			}
-			/*
-			 * Neither the folio nor the buffer are uptodate.  If
-			 * the buffer is only partially being written to, we
-			 * need to read it in before the write, i.e. now.
-			 */
-			if ((bh_pos < pos && bh_end > pos) ||
-					(bh_pos < end && bh_end > end)) {
-				/*
-				 * If the buffer is fully or partially within
-				 * the initialized size, do an actual read.
-				 * Otherwise, simply zero the buffer.
-				 */
-				read_lock_irqsave(&ni->size_lock, flags);
-				initialized_size = ni->initialized_size;
-				read_unlock_irqrestore(&ni->size_lock, flags);
-				if (bh_pos < initialized_size) {
-					ntfs_submit_bh_for_read(bh);
-					*wait_bh++ = bh;
-				} else {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-			}
-			continue;
-		}
-		/* Unmapped buffer.  Need to map it. */
-		bh->b_bdev = vol->sb->s_bdev;
-		/*
-		 * If the current buffer is in the same clusters as the map
-		 * cache, there is no need to check the runlist again.  The
-		 * map cache is made up of @vcn, which is the first cached file
-		 * cluster, @vcn_len which is the number of cached file
-		 * clusters, @lcn is the device cluster corresponding to @vcn,
-		 * and @lcn_block is the block number corresponding to @lcn.
-		 */
-		cdelta = bh_cpos - vcn;
-		if (likely(!cdelta || (cdelta > 0 && cdelta < vcn_len))) {
-map_buffer_cached:
-			BUG_ON(lcn < 0);
-			bh->b_blocknr = lcn_block +
-					(cdelta << (vol->cluster_size_bits -
-					blocksize_bits)) +
-					(bh_cofs >> blocksize_bits);
-			set_buffer_mapped(bh);
-			/*
-			 * If the folio is uptodate so is the buffer.  If the
-			 * buffer is fully outside the write, we ignore it if
-			 * it was already allocated and we mark it dirty so it
-			 * gets written out if we allocated it.  On the other
-			 * hand, if we allocated the buffer but we are not
-			 * marking it dirty we set buffer_new so we can do
-			 * error recovery.
-			 */
-			if (folio_test_uptodate(folio)) {
-				if (!buffer_uptodate(bh))
-					set_buffer_uptodate(bh);
-				if (unlikely(was_hole)) {
-					/* We allocated the buffer. */
-					clean_bdev_bh_alias(bh);
-					if (bh_end <= pos || bh_pos >= end)
-						mark_buffer_dirty(bh);
-					else
-						set_buffer_new(bh);
-				}
-				continue;
-			}
-			/* Page is _not_ uptodate. */
-			if (likely(!was_hole)) {
-				/*
-				 * Buffer was already allocated.  If it is not
-				 * uptodate and is only partially being written
-				 * to, we need to read it in before the write,
-				 * i.e. now.
-				 */
-				if (!buffer_uptodate(bh) && bh_pos < end &&
-						bh_end > pos &&
-						(bh_pos < pos ||
-						bh_end > end)) {
-					/*
-					 * If the buffer is fully or partially
-					 * within the initialized size, do an
-					 * actual read.  Otherwise, simply zero
-					 * the buffer.
-					 */
-					read_lock_irqsave(&ni->size_lock,
-							flags);
-					initialized_size = ni->initialized_size;
-					read_unlock_irqrestore(&ni->size_lock,
-							flags);
-					if (bh_pos < initialized_size) {
-						ntfs_submit_bh_for_read(bh);
-						*wait_bh++ = bh;
-					} else {
-						folio_zero_range(folio,
-								bh_offset(bh),
-								blocksize);
-						set_buffer_uptodate(bh);
-					}
-				}
-				continue;
-			}
-			/* We allocated the buffer. */
-			clean_bdev_bh_alias(bh);
-			/*
-			 * If the buffer is fully outside the write, zero it,
-			 * set it uptodate, and mark it dirty so it gets
-			 * written out.  If it is partially being written to,
-			 * zero region surrounding the write but leave it to
-			 * commit write to do anything else.  Finally, if the
-			 * buffer is fully being overwritten, do nothing.
-			 */
-			if (bh_end <= pos || bh_pos >= end) {
-				if (!buffer_uptodate(bh)) {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-				mark_buffer_dirty(bh);
-				continue;
-			}
-			set_buffer_new(bh);
-			if (!buffer_uptodate(bh) &&
-					(bh_pos < pos || bh_end > end)) {
-				u8 *kaddr;
-				unsigned pofs;
-					
-				kaddr = kmap_local_folio(folio, 0);
-				if (bh_pos < pos) {
-					pofs = bh_pos & ~PAGE_MASK;
-					memset(kaddr + pofs, 0, pos - bh_pos);
-				}
-				if (bh_end > end) {
-					pofs = end & ~PAGE_MASK;
-					memset(kaddr + pofs, 0, bh_end - end);
-				}
-				kunmap_local(kaddr);
-				flush_dcache_folio(folio);
-			}
-			continue;
-		}
-		/*
-		 * Slow path: this is the first buffer in the cluster.  If it
-		 * is outside allocated size and is not uptodate, zero it and
-		 * set it uptodate.
-		 */
-		read_lock_irqsave(&ni->size_lock, flags);
-		initialized_size = ni->allocated_size;
-		read_unlock_irqrestore(&ni->size_lock, flags);
-		if (bh_pos > initialized_size) {
-			if (folio_test_uptodate(folio)) {
-				if (!buffer_uptodate(bh))
-					set_buffer_uptodate(bh);
-			} else if (!buffer_uptodate(bh)) {
-				folio_zero_range(folio, bh_offset(bh),
-						blocksize);
-				set_buffer_uptodate(bh);
-			}
-			continue;
-		}
-		is_retry = false;
-		if (!rl) {
-			down_read(&ni->runlist.lock);
-retry_remap:
-			rl = ni->runlist.rl;
-		}
-		if (likely(rl != NULL)) {
-			/* Seek to element containing target cluster. */
-			while (rl->length && rl[1].vcn <= bh_cpos)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, bh_cpos);
-			if (likely(lcn >= 0)) {
-				/*
-				 * Successful remap, setup the map cache and
-				 * use that to deal with the buffer.
-				 */
-				was_hole = false;
-				vcn = bh_cpos;
-				vcn_len = rl[1].vcn - vcn;
-				lcn_block = lcn << (vol->cluster_size_bits -
-						blocksize_bits);
-				cdelta = 0;
-				/*
-				 * If the number of remaining clusters touched
-				 * by the write is smaller or equal to the
-				 * number of cached clusters, unlock the
-				 * runlist as the map cache will be used from
-				 * now on.
-				 */
-				if (likely(vcn + vcn_len >= cend)) {
-					if (rl_write_locked) {
-						up_write(&ni->runlist.lock);
-						rl_write_locked = false;
-					} else
-						up_read(&ni->runlist.lock);
-					rl = NULL;
-				}
-				goto map_buffer_cached;
-			}
-		} else
-			lcn = LCN_RL_NOT_MAPPED;
-		/*
-		 * If it is not a hole and not out of bounds, the runlist is
-		 * probably unmapped so try to map it now.
-		 */
-		if (unlikely(lcn != LCN_HOLE && lcn != LCN_ENOENT)) {
-			if (likely(!is_retry && lcn == LCN_RL_NOT_MAPPED)) {
-				/* Attempt to map runlist. */
-				if (!rl_write_locked) {
-					/*
-					 * We need the runlist locked for
-					 * writing, so if it is locked for
-					 * reading relock it now and retry in
-					 * case it changed whilst we dropped
-					 * the lock.
-					 */
-					up_read(&ni->runlist.lock);
-					down_write(&ni->runlist.lock);
-					rl_write_locked = true;
-					goto retry_remap;
-				}
-				err = ntfs_map_runlist_nolock(ni, bh_cpos,
-						NULL);
-				if (likely(!err)) {
-					is_retry = true;
-					goto retry_remap;
-				}
-				/*
-				 * If @vcn is out of bounds, pretend @lcn is
-				 * LCN_ENOENT.  As long as the buffer is out
-				 * of bounds this will work fine.
-				 */
-				if (err == -ENOENT) {
-					lcn = LCN_ENOENT;
-					err = 0;
-					goto rl_not_mapped_enoent;
-				}
-			} else
-				err = -EIO;
-			/* Failed to map the buffer, even after retrying. */
-			bh->b_blocknr = -1;
-			ntfs_error(vol->sb, "Failed to write to inode 0x%lx, "
-					"attribute type 0x%x, vcn 0x%llx, "
-					"vcn offset 0x%x, because its "
-					"location on disk could not be "
-					"determined%s (error code %i).",
-					ni->mft_no, ni->type,
-					(unsigned long long)bh_cpos,
-					(unsigned)bh_pos &
-					vol->cluster_size_mask,
-					is_retry ? " even after retrying" : "",
-					err);
-			break;
-		}
-rl_not_mapped_enoent:
-		/*
-		 * The buffer is in a hole or out of bounds.  We need to fill
-		 * the hole, unless the buffer is in a cluster which is not
-		 * touched by the write, in which case we just leave the buffer
-		 * unmapped.  This can only happen when the cluster size is
-		 * less than the page cache size.
-		 */
-		if (unlikely(vol->cluster_size < PAGE_SIZE)) {
-			bh_cend = (bh_end + vol->cluster_size - 1) >>
-					vol->cluster_size_bits;
-			if ((bh_cend <= cpos || bh_cpos >= cend)) {
-				bh->b_blocknr = -1;
-				/*
-				 * If the buffer is uptodate we skip it.  If it
-				 * is not but the folio is uptodate, we can set
-				 * the buffer uptodate.  If the folio is not
-				 * uptodate, we can clear the buffer and set it
-				 * uptodate.  Whether this is worthwhile is
-				 * debatable and this could be removed.
-				 */
-				if (folio_test_uptodate(folio)) {
-					if (!buffer_uptodate(bh))
-						set_buffer_uptodate(bh);
-				} else if (!buffer_uptodate(bh)) {
-					folio_zero_range(folio, bh_offset(bh),
-						blocksize);
-					set_buffer_uptodate(bh);
-				}
-				continue;
-			}
-		}
-		/*
-		 * Out of bounds buffer is invalid if it was not really out of
-		 * bounds.
-		 */
-		BUG_ON(lcn != LCN_HOLE);
-		/*
-		 * We need the runlist locked for writing, so if it is locked
-		 * for reading relock it now and retry in case it changed
-		 * whilst we dropped the lock.
-		 */
-		BUG_ON(!rl);
-		if (!rl_write_locked) {
-			up_read(&ni->runlist.lock);
-			down_write(&ni->runlist.lock);
-			rl_write_locked = true;
-			goto retry_remap;
-		}
-		/* Find the previous last allocated cluster. */
-		BUG_ON(rl->lcn != LCN_HOLE);
-		lcn = -1;
-		rl2 = rl;
-		while (--rl2 >= ni->runlist.rl) {
-			if (rl2->lcn >= 0) {
-				lcn = rl2->lcn + rl2->length;
-				break;
-			}
-		}
-		rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE,
-				false);
-		if (IS_ERR(rl2)) {
-			err = PTR_ERR(rl2);
-			ntfs_debug("Failed to allocate cluster, error code %i.",
-					err);
-			break;
-		}
-		lcn = rl2->lcn;
-		rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
-		if (IS_ERR(rl)) {
-			err = PTR_ERR(rl);
-			if (err != -ENOMEM)
-				err = -EIO;
-			if (ntfs_cluster_free_from_rl(vol, rl2)) {
-				ntfs_error(vol->sb, "Failed to release "
-						"allocated cluster in error "
-						"code path.  Run chkdsk to "
-						"recover the lost cluster.");
-				NVolSetErrors(vol);
-			}
-			ntfs_free(rl2);
-			break;
-		}
-		ni->runlist.rl = rl;
-		status.runlist_merged = 1;
-		ntfs_debug("Allocated cluster, lcn 0x%llx.",
-				(unsigned long long)lcn);
-		/* Map and lock the mft record and get the attribute record. */
-		if (!NInoAttr(ni))
-			base_ni = ni;
-		else
-			base_ni = ni->ext.base_ntfs_ino;
-		m = map_mft_record(base_ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			break;
-		}
-		ctx = ntfs_attr_get_search_ctx(base_ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			unmap_mft_record(base_ni);
-			break;
-		}
-		status.mft_attr_mapped = 1;
-		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				err = -EIO;
-			break;
-		}
-		m = ctx->mrec;
-		a = ctx->attr;
-		/*
-		 * Find the runlist element with which the attribute extent
-		 * starts.  Note, we cannot use the _attr_ version because we
-		 * have mapped the mft record.  That is ok because we know the
-		 * runlist fragment must be mapped already to have ever gotten
-		 * here, so we can just use the _rl_ version.
-		 */
-		vcn = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-		rl2 = ntfs_rl_find_vcn_nolock(rl, vcn);
-		BUG_ON(!rl2);
-		BUG_ON(!rl2->length);
-		BUG_ON(rl2->lcn < LCN_HOLE);
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		/*
-		 * If @highest_vcn is zero, calculate the real highest_vcn
-		 * (which can really be zero).
-		 */
-		if (!highest_vcn)
-			highest_vcn = (sle64_to_cpu(
-					a->data.non_resident.allocated_size) >>
-					vol->cluster_size_bits) - 1;
-		/*
-		 * Determine the size of the mapping pairs array for the new
-		 * extent, i.e. the old extent with the hole filled.
-		 */
-		mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, vcn,
-				highest_vcn);
-		if (unlikely(mp_size <= 0)) {
-			if (!(err = mp_size))
-				err = -EIO;
-			ntfs_debug("Failed to get size for mapping pairs "
-					"array, error code %i.", err);
-			break;
-		}
-		/*
-		 * Resize the attribute record to fit the new mapping pairs
-		 * array.
-		 */
-		attr_rec_len = le32_to_cpu(a->length);
-		err = ntfs_attr_record_resize(m, a, mp_size + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset));
-		if (unlikely(err)) {
-			BUG_ON(err != -ENOSPC);
-			// TODO: Deal with this by using the current attribute
-			// and fill it with as much of the mapping pairs
-			// array as possible.  Then loop over each attribute
-			// extent rewriting the mapping pairs arrays as we go
-			// along and if when we reach the end we have not
-			// enough space, try to resize the last attribute
-			// extent and if even that fails, add a new attribute
-			// extent.
-			// We could also try to resize at each step in the hope
-			// that we will not need to rewrite every single extent.
-			// Note, we may need to decompress some extents to fill
-			// the runlist as we are walking the extents...
-			ntfs_error(vol->sb, "Not enough space in the mft "
-					"record for the extended attribute "
-					"record.  This case is not "
-					"implemented yet.");
-			err = -EOPNOTSUPP;
-			break ;
-		}
-		status.mp_rebuilt = 1;
-		/*
-		 * Generate the mapping pairs array directly into the attribute
-		 * record.
-		 */
-		err = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				mp_size, rl2, vcn, highest_vcn, NULL);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Cannot fill hole in inode 0x%lx, "
-					"attribute type 0x%x, because building "
-					"the mapping pairs failed with error "
-					"code %i.", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-			err = -EIO;
-			break;
-		}
-		/* Update the highest_vcn but only if it was not set. */
-		if (unlikely(!a->data.non_resident.highest_vcn))
-			a->data.non_resident.highest_vcn =
-					cpu_to_sle64(highest_vcn);
-		/*
-		 * If the attribute is sparse/compressed, update the compressed
-		 * size in the ntfs_inode structure and the attribute record.
-		 */
-		if (likely(NInoSparse(ni) || NInoCompressed(ni))) {
-			/*
-			 * If we are not in the first attribute extent, switch
-			 * to it, but first ensure the changes will make it to
-			 * disk later.
-			 */
-			if (a->data.non_resident.lowest_vcn) {
-				flush_dcache_mft_record_page(ctx->ntfs_ino);
-				mark_mft_record_dirty(ctx->ntfs_ino);
-				ntfs_attr_reinit_search_ctx(ctx);
-				err = ntfs_attr_lookup(ni->type, ni->name,
-						ni->name_len, CASE_SENSITIVE,
-						0, NULL, 0, ctx);
-				if (unlikely(err)) {
-					status.attr_switched = 1;
-					break;
-				}
-				/* @m is not used any more so do not set it. */
-				a = ctx->attr;
-			}
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->itype.compressed.size += vol->cluster_size;
-			a->data.non_resident.compressed_size =
-					cpu_to_sle64(ni->itype.compressed.size);
-			write_unlock_irqrestore(&ni->size_lock, flags);
-		}
-		/* Ensure the changes make it to disk. */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		/* Successfully filled the hole. */
-		status.runlist_merged = 0;
-		status.mft_attr_mapped = 0;
-		status.mp_rebuilt = 0;
-		/* Setup the map cache and use that to deal with the buffer. */
-		was_hole = true;
-		vcn = bh_cpos;
-		vcn_len = 1;
-		lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits);
-		cdelta = 0;
-		/*
-		 * If the number of remaining clusters in the @pages is smaller
-		 * or equal to the number of cached clusters, unlock the
-		 * runlist as the map cache will be used from now on.
-		 */
-		if (likely(vcn + vcn_len >= cend)) {
-			up_write(&ni->runlist.lock);
-			rl_write_locked = false;
-			rl = NULL;
-		}
-		goto map_buffer_cached;
-	} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
-	/* If there are no errors, do the next page. */
-	if (likely(!err && ++u < nr_pages))
-		goto do_next_folio;
-	/* If there are no errors, release the runlist lock if we took it. */
-	if (likely(!err)) {
-		if (unlikely(rl_write_locked)) {
-			up_write(&ni->runlist.lock);
-			rl_write_locked = false;
-		} else if (unlikely(rl))
-			up_read(&ni->runlist.lock);
-		rl = NULL;
-	}
-	/* If we issued read requests, let them complete. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	while (wait_bh > wait) {
-		bh = *--wait_bh;
-		wait_on_buffer(bh);
-		if (likely(buffer_uptodate(bh))) {
-			folio = bh->b_folio;
-			bh_pos = folio_pos(folio) + bh_offset(bh);
-			/*
-			 * If the buffer overflows the initialized size, need
-			 * to zero the overflowing region.
-			 */
-			if (unlikely(bh_pos + blocksize > initialized_size)) {
-				int ofs = 0;
-
-				if (likely(bh_pos < initialized_size))
-					ofs = initialized_size - bh_pos;
-				folio_zero_segment(folio, bh_offset(bh) + ofs,
-						blocksize);
-			}
-		} else /* if (unlikely(!buffer_uptodate(bh))) */
-			err = -EIO;
-	}
-	if (likely(!err)) {
-		/* Clear buffer_new on all buffers. */
-		u = 0;
-		do {
-			bh = head = page_buffers(pages[u]);
-			do {
-				if (buffer_new(bh))
-					clear_buffer_new(bh);
-			} while ((bh = bh->b_this_page) != head);
-		} while (++u < nr_pages);
-		ntfs_debug("Done.");
-		return err;
-	}
-	if (status.attr_switched) {
-		/* Get back to the attribute extent we modified. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx)) {
-			ntfs_error(vol->sb, "Failed to find required "
-					"attribute extent of attribute in "
-					"error code path.  Run chkdsk to "
-					"recover.");
-			write_lock_irqsave(&ni->size_lock, flags);
-			ni->itype.compressed.size += vol->cluster_size;
-			write_unlock_irqrestore(&ni->size_lock, flags);
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-			/*
-			 * The only thing that is now wrong is the compressed
-			 * size of the base attribute extent which chkdsk
-			 * should be able to fix.
-			 */
-			NVolSetErrors(vol);
-		} else {
-			m = ctx->mrec;
-			a = ctx->attr;
-			status.attr_switched = 0;
-		}
-	}
-	/*
-	 * If the runlist has been modified, need to restore it by punching a
-	 * hole into it and we then need to deallocate the on-disk cluster as
-	 * well.  Note, we only modify the runlist if we are able to generate a
-	 * new mapping pairs array, i.e. only when the mapped attribute extent
-	 * is not switched.
-	 */
-	if (status.runlist_merged && !status.attr_switched) {
-		BUG_ON(!rl_write_locked);
-		/* Make the file cluster we allocated sparse in the runlist. */
-		if (ntfs_rl_punch_nolock(vol, &ni->runlist, bh_cpos, 1)) {
-			ntfs_error(vol->sb, "Failed to punch hole into "
-					"attribute runlist in error code "
-					"path.  Run chkdsk to recover the "
-					"lost cluster.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			status.runlist_merged = 0;
-			/*
-			 * Deallocate the on-disk cluster we allocated but only
-			 * if we succeeded in punching its vcn out of the
-			 * runlist.
-			 */
-			down_write(&vol->lcnbmp_lock);
-			if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
-				ntfs_error(vol->sb, "Failed to release "
-						"allocated cluster in error "
-						"code path.  Run chkdsk to "
-						"recover the lost cluster.");
-				NVolSetErrors(vol);
-			}
-			up_write(&vol->lcnbmp_lock);
-		}
-	}
-	/*
-	 * Resize the attribute record to its old size and rebuild the mapping
-	 * pairs array.  Note, we only can do this if the runlist has been
-	 * restored to its old state which also implies that the mapped
-	 * attribute extent is not switched.
-	 */
-	if (status.mp_rebuilt && !status.runlist_merged) {
-		if (ntfs_attr_record_resize(m, a, attr_rec_len)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record in error code path.  Run "
-					"chkdsk to recover.");
-			NVolSetErrors(vol);
-		} else /* if (success) */ {
-			if (ntfs_mapping_pairs_build(vol, (u8*)a +
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), attr_rec_len -
-					le16_to_cpu(a->data.non_resident.
-					mapping_pairs_offset), ni->runlist.rl,
-					vcn, highest_vcn, NULL)) {
-				ntfs_error(vol->sb, "Failed to restore "
-						"mapping pairs array in error "
-						"code path.  Run chkdsk to "
-						"recover.");
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		}
-	}
-	/* Release the mft record and the attribute. */
-	if (status.mft_attr_mapped) {
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-	}
-	/* Release the runlist lock. */
-	if (rl_write_locked)
-		up_write(&ni->runlist.lock);
-	else if (rl)
-		up_read(&ni->runlist.lock);
-	/*
-	 * Zero out any newly allocated blocks to avoid exposing stale data.
-	 * If BH_New is set, we know that the block was newly allocated above
-	 * and that it has not been fully zeroed and marked dirty yet.
-	 */
-	nr_pages = u;
-	u = 0;
-	end = bh_cpos << vol->cluster_size_bits;
-	do {
-		folio = page_folio(pages[u]);
-		bh = head = folio_buffers(folio);
-		do {
-			if (u == nr_pages &&
-			    folio_pos(folio) + bh_offset(bh) >= end)
-				break;
-			if (!buffer_new(bh))
-				continue;
-			clear_buffer_new(bh);
-			if (!buffer_uptodate(bh)) {
-				if (folio_test_uptodate(folio))
-					set_buffer_uptodate(bh);
-				else {
-					folio_zero_range(folio, bh_offset(bh),
-							blocksize);
-					set_buffer_uptodate(bh);
-				}
-			}
-			mark_buffer_dirty(bh);
-		} while ((bh = bh->b_this_page) != head);
-	} while (++u <= nr_pages);
-	ntfs_error(vol->sb, "Failed.  Returning error code %i.", err);
-	return err;
-}
-
-static inline void ntfs_flush_dcache_pages(struct page **pages,
-		unsigned nr_pages)
-{
-	BUG_ON(!nr_pages);
-	/*
-	 * Warning: Do not do the decrement at the same time as the call to
-	 * flush_dcache_page() because it is a NULL macro on i386 and hence the
-	 * decrement never happens so the loop never terminates.
-	 */
-	do {
-		--nr_pages;
-		flush_dcache_page(pages[nr_pages]);
-	} while (nr_pages > 0);
-}
-
-/**
- * ntfs_commit_pages_after_non_resident_write - commit the received data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * See description of ntfs_commit_pages_after_write(), below.
- */
-static inline int ntfs_commit_pages_after_non_resident_write(
-		struct page **pages, const unsigned nr_pages,
-		s64 pos, size_t bytes)
-{
-	s64 end, initialized_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	struct buffer_head *bh, *head;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	unsigned long flags;
-	unsigned blocksize, u;
-	int err;
-
-	vi = pages[0]->mapping->host;
-	ni = NTFS_I(vi);
-	blocksize = vi->i_sb->s_blocksize;
-	end = pos + bytes;
-	u = 0;
-	do {
-		s64 bh_pos;
-		struct page *page;
-		bool partial;
-
-		page = pages[u];
-		bh_pos = (s64)page->index << PAGE_SHIFT;
-		bh = head = page_buffers(page);
-		partial = false;
-		do {
-			s64 bh_end;
-
-			bh_end = bh_pos + blocksize;
-			if (bh_end <= pos || bh_pos >= end) {
-				if (!buffer_uptodate(bh))
-					partial = true;
-			} else {
-				set_buffer_uptodate(bh);
-				mark_buffer_dirty(bh);
-			}
-		} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
-		/*
-		 * If all buffers are now uptodate but the page is not, set the
-		 * page uptodate.
-		 */
-		if (!partial && !PageUptodate(page))
-			SetPageUptodate(page);
-	} while (++u < nr_pages);
-	/*
-	 * Finally, if we do not need to update initialized_size or i_size we
-	 * are finished.
-	 */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	if (end <= initialized_size) {
-		ntfs_debug("Done.");
-		return 0;
-	}
-	/*
-	 * Update initialized_size/i_size as appropriate, both in the inode and
-	 * the mft record.
-	 */
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	BUG_ON(!NInoNonResident(ni));
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	a = ctx->attr;
-	BUG_ON(!a->non_resident);
-	write_lock_irqsave(&ni->size_lock, flags);
-	BUG_ON(end > ni->allocated_size);
-	ni->initialized_size = end;
-	a->data.non_resident.initialized_size = cpu_to_sle64(end);
-	if (end > i_size_read(vi)) {
-		i_size_write(vi, end);
-		a->data.non_resident.data_size =
-				a->data.non_resident.initialized_size;
-	}
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	ntfs_debug("Done.");
-	return 0;
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error "
-			"code %i).", err);
-	if (err != -ENOMEM)
-		NVolSetErrors(ni->vol);
-	return err;
-}
-
-/**
- * ntfs_commit_pages_after_write - commit the received data
- * @pages:	array of destination pages
- * @nr_pages:	number of pages in @pages
- * @pos:	byte position in file at which the write begins
- * @bytes:	number of bytes to be written
- *
- * This is called from ntfs_file_buffered_write() with i_mutex held on the inode
- * (@pages[0]->mapping->host).  There are @nr_pages pages in @pages which are
- * locked but not kmap()ped.  The source data has already been copied into the
- * @page.  ntfs_prepare_pages_for_non_resident_write() has been called before
- * the data was copied (for non-resident attributes only) and it returned
- * success.
- *
- * Need to set uptodate and mark dirty all buffers within the boundary of the
- * write.  If all buffers in a page are uptodate we set the page uptodate, too.
- *
- * Setting the buffers dirty ensures that they get written out later when
- * ntfs_writepage() is invoked by the VM.
- *
- * Finally, we need to update i_size and initialized_size as appropriate both
- * in the inode and the mft record.
- *
- * This is modelled after fs/buffer.c::generic_commit_write(), which marks
- * buffers uptodate and dirty, sets the page uptodate if all buffers in the
- * page are uptodate, and updates i_size if the end of io is beyond i_size.  In
- * that case, it also marks the inode dirty.
- *
- * If things have gone as outlined in
- * ntfs_prepare_pages_for_non_resident_write(), we do not need to do any page
- * content modifications here for non-resident attributes.  For resident
- * attributes we need to do the uptodate bringing here which we combine with
- * the copying into the mft record which means we save one atomic kmap.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_commit_pages_after_write(struct page **pages,
-		const unsigned nr_pages, s64 pos, size_t bytes)
-{
-	s64 end, initialized_size;
-	loff_t i_size;
-	struct inode *vi;
-	ntfs_inode *ni, *base_ni;
-	struct page *page;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	char *kattr, *kaddr;
-	unsigned long flags;
-	u32 attr_len;
-	int err;
-
-	BUG_ON(!nr_pages);
-	BUG_ON(!pages);
-	page = pages[0];
-	BUG_ON(!page);
-	vi = page->mapping->host;
-	ni = NTFS_I(vi);
-	ntfs_debug("Entering for inode 0x%lx, attribute type 0x%x, start page "
-			"index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.",
-			vi->i_ino, ni->type, page->index, nr_pages,
-			(long long)pos, bytes);
-	if (NInoNonResident(ni))
-		return ntfs_commit_pages_after_non_resident_write(pages,
-				nr_pages, pos, bytes);
-	BUG_ON(nr_pages > 1);
-	/*
-	 * Attribute is resident, implying it is not compressed, encrypted, or
-	 * sparse.
-	 */
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	BUG_ON(NInoNonResident(ni));
-	/* Map, pin, and lock the mft record. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		m = NULL;
-		ctx = NULL;
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			err = -EIO;
-		goto err_out;
-	}
-	a = ctx->attr;
-	BUG_ON(a->non_resident);
-	/* The total length of the attribute value. */
-	attr_len = le32_to_cpu(a->data.resident.value_length);
-	i_size = i_size_read(vi);
-	BUG_ON(attr_len != i_size);
-	BUG_ON(pos > attr_len);
-	end = pos + bytes;
-	BUG_ON(end > le32_to_cpu(a->length) -
-			le16_to_cpu(a->data.resident.value_offset));
-	kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset);
-	kaddr = kmap_atomic(page);
-	/* Copy the received data from the page to the mft record. */
-	memcpy(kattr + pos, kaddr + pos, bytes);
-	/* Update the attribute length if necessary. */
-	if (end > attr_len) {
-		attr_len = end;
-		a->data.resident.value_length = cpu_to_le32(attr_len);
-	}
-	/*
-	 * If the page is not uptodate, bring the out of bounds area(s)
-	 * uptodate by copying data from the mft record to the page.
-	 */
-	if (!PageUptodate(page)) {
-		if (pos > 0)
-			memcpy(kaddr, kattr, pos);
-		if (end < attr_len)
-			memcpy(kaddr + end, kattr + end, attr_len - end);
-		/* Zero the region outside the end of the attribute value. */
-		memset(kaddr + attr_len, 0, PAGE_SIZE - attr_len);
-		flush_dcache_page(page);
-		SetPageUptodate(page);
-	}
-	kunmap_atomic(kaddr);
-	/* Update initialized_size/i_size if necessary. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	initialized_size = ni->initialized_size;
-	BUG_ON(end > ni->allocated_size);
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	BUG_ON(initialized_size != i_size);
-	if (end > initialized_size) {
-		write_lock_irqsave(&ni->size_lock, flags);
-		ni->initialized_size = end;
-		i_size_write(vi, end);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-	}
-	/* Mark the mft record dirty, so it gets written back. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	ntfs_debug("Done.");
-	return 0;
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Error allocating memory required to "
-				"commit the write.");
-		if (PageUptodate(page)) {
-			ntfs_warning(vi->i_sb, "Page is uptodate, setting "
-					"dirty so the write will be retried "
-					"later on by the VM.");
-			/*
-			 * Put the page on mapping->dirty_pages, but leave its
-			 * buffers' dirty state as-is.
-			 */
-			__set_page_dirty_nobuffers(page);
-			err = 0;
-		} else
-			ntfs_error(vi->i_sb, "Page is not uptodate.  Written "
-					"data has been lost.");
-	} else {
-		ntfs_error(vi->i_sb, "Resident attribute commit write failed "
-				"with error %i.", err);
-		NVolSetErrors(ni->vol);
-	}
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-}
-
-/*
- * Copy as much as we can into the pages and return the number of bytes which
- * were successfully copied.  If a fault is encountered then clear the pages
- * out to (ofs + bytes) and return the number of bytes which were copied.
- */
-static size_t ntfs_copy_from_user_iter(struct page **pages, unsigned nr_pages,
-		unsigned ofs, struct iov_iter *i, size_t bytes)
-{
-	struct page **last_page = pages + nr_pages;
-	size_t total = 0;
-	unsigned len, copied;
-
-	do {
-		len = PAGE_SIZE - ofs;
-		if (len > bytes)
-			len = bytes;
-		copied = copy_page_from_iter_atomic(*pages, ofs, len, i);
-		total += copied;
-		bytes -= copied;
-		if (!bytes)
-			break;
-		if (copied < len)
-			goto err;
-		ofs = 0;
-	} while (++pages < last_page);
-out:
-	return total;
-err:
-	/* Zero the rest of the target like __copy_from_user(). */
-	len = PAGE_SIZE - copied;
-	do {
-		if (len > bytes)
-			len = bytes;
-		zero_user(*pages, copied, len);
-		bytes -= len;
-		copied = 0;
-		len = PAGE_SIZE;
-	} while (++pages < last_page);
-	goto out;
-}
-
-/**
- * ntfs_perform_write - perform buffered write to a file
- * @file:	file to write to
- * @i:		iov_iter with data to write
- * @pos:	byte offset in file at which to begin writing to
- */
-static ssize_t ntfs_perform_write(struct file *file, struct iov_iter *i,
-		loff_t pos)
-{
-	struct address_space *mapping = file->f_mapping;
-	struct inode *vi = mapping->host;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	struct page *pages[NTFS_MAX_PAGES_PER_CLUSTER];
-	struct page *cached_page = NULL;
-	VCN last_vcn;
-	LCN lcn;
-	size_t bytes;
-	ssize_t status, written = 0;
-	unsigned nr_pages;
-
-	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, pos "
-			"0x%llx, count 0x%lx.", vi->i_ino,
-			(unsigned)le32_to_cpu(ni->type),
-			(unsigned long long)pos,
-			(unsigned long)iov_iter_count(i));
-	/*
-	 * If a previous ntfs_truncate() failed, repeat it and abort if it
-	 * fails again.
-	 */
-	if (unlikely(NInoTruncateFailed(ni))) {
-		int err;
-
-		inode_dio_wait(vi);
-		err = ntfs_truncate(vi);
-		if (err || NInoTruncateFailed(ni)) {
-			if (!err)
-				err = -EIO;
-			ntfs_error(vol->sb, "Cannot perform write to inode "
-					"0x%lx, attribute type 0x%x, because "
-					"ntfs_truncate() failed (error code "
-					"%i).", vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type), err);
-			return err;
-		}
-	}
-	/*
-	 * Determine the number of pages per cluster for non-resident
-	 * attributes.
-	 */
-	nr_pages = 1;
-	if (vol->cluster_size > PAGE_SIZE && NInoNonResident(ni))
-		nr_pages = vol->cluster_size >> PAGE_SHIFT;
-	last_vcn = -1;
-	do {
-		VCN vcn;
-		pgoff_t start_idx;
-		unsigned ofs, do_pages, u;
-		size_t copied;
-
-		start_idx = pos >> PAGE_SHIFT;
-		ofs = pos & ~PAGE_MASK;
-		bytes = PAGE_SIZE - ofs;
-		do_pages = 1;
-		if (nr_pages > 1) {
-			vcn = pos >> vol->cluster_size_bits;
-			if (vcn != last_vcn) {
-				last_vcn = vcn;
-				/*
-				 * Get the lcn of the vcn the write is in.  If
-				 * it is a hole, need to lock down all pages in
-				 * the cluster.
-				 */
-				down_read(&ni->runlist.lock);
-				lcn = ntfs_attr_vcn_to_lcn_nolock(ni, pos >>
-						vol->cluster_size_bits, false);
-				up_read(&ni->runlist.lock);
-				if (unlikely(lcn < LCN_HOLE)) {
-					if (lcn == LCN_ENOMEM)
-						status = -ENOMEM;
-					else {
-						status = -EIO;
-						ntfs_error(vol->sb, "Cannot "
-							"perform write to "
-							"inode 0x%lx, "
-							"attribute type 0x%x, "
-							"because the attribute "
-							"is corrupt.",
-							vi->i_ino, (unsigned)
-							le32_to_cpu(ni->type));
-					}
-					break;
-				}
-				if (lcn == LCN_HOLE) {
-					start_idx = (pos & ~(s64)
-							vol->cluster_size_mask)
-							>> PAGE_SHIFT;
-					bytes = vol->cluster_size - (pos &
-							vol->cluster_size_mask);
-					do_pages = nr_pages;
-				}
-			}
-		}
-		if (bytes > iov_iter_count(i))
-			bytes = iov_iter_count(i);
-again:
-		/*
-		 * Bring in the user page(s) that we will copy from _first_.
-		 * Otherwise there is a nasty deadlock on copying from the same
-		 * page(s) as we are writing to, without it/them being marked
-		 * up-to-date.  Note, at present there is nothing to stop the
-		 * pages being swapped out between us bringing them into memory
-		 * and doing the actual copying.
-		 */
-		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
-			status = -EFAULT;
-			break;
-		}
-		/* Get and lock @do_pages starting at index @start_idx. */
-		status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages,
-				pages, &cached_page);
-		if (unlikely(status))
-			break;
-		/*
-		 * For non-resident attributes, we need to fill any holes with
-		 * actual clusters and ensure all bufferes are mapped.  We also
-		 * need to bring uptodate any buffers that are only partially
-		 * being written to.
-		 */
-		if (NInoNonResident(ni)) {
-			status = ntfs_prepare_pages_for_non_resident_write(
-					pages, do_pages, pos, bytes);
-			if (unlikely(status)) {
-				do {
-					unlock_page(pages[--do_pages]);
-					put_page(pages[do_pages]);
-				} while (do_pages);
-				break;
-			}
-		}
-		u = (pos >> PAGE_SHIFT) - pages[0]->index;
-		copied = ntfs_copy_from_user_iter(pages + u, do_pages - u, ofs,
-					i, bytes);
-		ntfs_flush_dcache_pages(pages + u, do_pages - u);
-		status = 0;
-		if (likely(copied == bytes)) {
-			status = ntfs_commit_pages_after_write(pages, do_pages,
-					pos, bytes);
-		}
-		do {
-			unlock_page(pages[--do_pages]);
-			put_page(pages[do_pages]);
-		} while (do_pages);
-		if (unlikely(status < 0)) {
-			iov_iter_revert(i, copied);
-			break;
-		}
-		cond_resched();
-		if (unlikely(copied < bytes)) {
-			iov_iter_revert(i, copied);
-			if (copied)
-				bytes = copied;
-			else if (bytes > PAGE_SIZE - ofs)
-				bytes = PAGE_SIZE - ofs;
-			goto again;
-		}
-		pos += copied;
-		written += copied;
-		balance_dirty_pages_ratelimited(mapping);
-		if (fatal_signal_pending(current)) {
-			status = -EINTR;
-			break;
-		}
-	} while (iov_iter_count(i));
-	if (cached_page)
-		put_page(cached_page);
-	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
-			written ? "written" : "status", (unsigned long)written,
-			(long)status);
-	return written ? written : status;
-}
-
-/**
- * ntfs_file_write_iter - simple wrapper for ntfs_file_write_iter_nolock()
- * @iocb:	IO state structure
- * @from:	iov_iter with data to write
- *
- * Basically the same as generic_file_write_iter() except that it ends up
- * up calling ntfs_perform_write() instead of generic_perform_write() and that
- * O_DIRECT is not implemented.
- */
-static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *vi = file_inode(file);
-	ssize_t written = 0;
-	ssize_t err;
-
-	inode_lock(vi);
-	/* We can write back this queue in page reclaim. */
-	err = ntfs_prepare_file_for_write(iocb, from);
-	if (iov_iter_count(from) && !err)
-		written = ntfs_perform_write(file, from, iocb->ki_pos);
-	inode_unlock(vi);
-	iocb->ki_pos += written;
-	if (likely(written > 0))
-		written = generic_write_sync(iocb, written);
-	return written ? written : err;
-}
-
-/**
- * ntfs_file_fsync - sync a file to disk
- * @filp:	file to be synced
- * @datasync:	if non-zero only flush user data and not metadata
- *
- * Data integrity sync of a file to disk.  Used for fsync, fdatasync, and msync
- * system calls.  This function is inspired by fs/buffer.c::file_fsync().
- *
- * If @datasync is false, write the mft record and all associated extent mft
- * records as well as the $DATA attribute and then sync the block device.
- *
- * If @datasync is true and the attribute is non-resident, we skip the writing
- * of the mft record and all associated extent mft records (this might still
- * happen due to the write_inode_now() call).
- *
- * Also, if @datasync is true, we do not wait on the inode to be written out
- * but we always wait on the page cache pages to be written out.
- *
- * Locking: Caller must hold i_mutex on the inode.
- *
- * TODO: We should probably also write all attribute/index inodes associated
- * with this inode but since we have no simple way of getting to them we ignore
- * this problem for now.
- */
-static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
-			   int datasync)
-{
-	struct inode *vi = filp->f_mapping->host;
-	int err, ret = 0;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-
-	err = file_write_and_wait_range(filp, start, end);
-	if (err)
-		return err;
-	inode_lock(vi);
-
-	BUG_ON(S_ISDIR(vi->i_mode));
-	if (!datasync || !NInoNonResident(NTFS_I(vi)))
-		ret = __ntfs_write_inode(vi, 1);
-	write_inode_now(vi, !datasync);
-	/*
-	 * NOTE: If we were to use mapping->private_list (see ext2 and
-	 * fs/buffer.c) for dirty blocks then we could optimize the below to be
-	 * sync_mapping_buffers(vi->i_mapping).
-	 */
-	err = sync_blockdev(vi->i_sb->s_bdev);
-	if (unlikely(err && !ret))
-		ret = err;
-	if (likely(!ret))
-		ntfs_debug("Done.");
-	else
-		ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx.  Error "
-				"%u.", datasync ? "data" : "", vi->i_ino, -ret);
-	inode_unlock(vi);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-const struct file_operations ntfs_file_ops = {
-	.llseek		= generic_file_llseek,
-	.read_iter	= generic_file_read_iter,
-#ifdef NTFS_RW
-	.write_iter	= ntfs_file_write_iter,
-	.fsync		= ntfs_file_fsync,
-#endif /* NTFS_RW */
-	.mmap		= generic_file_mmap,
-	.open		= ntfs_file_open,
-	.splice_read	= filemap_splice_read,
-};
-
-const struct inode_operations ntfs_file_inode_ops = {
-#ifdef NTFS_RW
-	.setattr	= ntfs_setattr,
-#endif /* NTFS_RW */
-};
-
-const struct file_operations ntfs_empty_file_ops = {};
-
-const struct inode_operations ntfs_empty_inode_ops = {};
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
deleted file mode 100644
index d46c2c03a032..000000000000
--- a/fs/ntfs/index.c
+++ /dev/null
@@ -1,440 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * index.c - NTFS kernel index handling.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#include <linux/slab.h>
-
-#include "aops.h"
-#include "collate.h"
-#include "debug.h"
-#include "index.h"
-#include "ntfs.h"
-
-/**
- * ntfs_index_ctx_get - allocate and initialize a new index context
- * @idx_ni:	ntfs index inode with which to initialize the context
- *
- * Allocate a new index context, initialize it with @idx_ni and return it.
- * Return NULL if allocation failed.
- *
- * Locking:  Caller must hold i_mutex on the index inode.
- */
-ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni)
-{
-	ntfs_index_context *ictx;
-
-	ictx = kmem_cache_alloc(ntfs_index_ctx_cache, GFP_NOFS);
-	if (ictx)
-		*ictx = (ntfs_index_context){ .idx_ni = idx_ni };
-	return ictx;
-}
-
-/**
- * ntfs_index_ctx_put - release an index context
- * @ictx:	index context to free
- *
- * Release the index context @ictx, releasing all associated resources.
- *
- * Locking:  Caller must hold i_mutex on the index inode.
- */
-void ntfs_index_ctx_put(ntfs_index_context *ictx)
-{
-	if (ictx->entry) {
-		if (ictx->is_in_root) {
-			if (ictx->actx)
-				ntfs_attr_put_search_ctx(ictx->actx);
-			if (ictx->base_ni)
-				unmap_mft_record(ictx->base_ni);
-		} else {
-			struct page *page = ictx->page;
-			if (page) {
-				BUG_ON(!PageLocked(page));
-				unlock_page(page);
-				ntfs_unmap_page(page);
-			}
-		}
-	}
-	kmem_cache_free(ntfs_index_ctx_cache, ictx);
-	return;
-}
-
-/**
- * ntfs_index_lookup - find a key in an index and return its index entry
- * @key:	[IN] key for which to search in the index
- * @key_len:	[IN] length of @key in bytes
- * @ictx:	[IN/OUT] context describing the index and the returned entry
- *
- * Before calling ntfs_index_lookup(), @ictx must have been obtained from a
- * call to ntfs_index_ctx_get().
- *
- * Look for the @key in the index specified by the index lookup context @ictx.
- * ntfs_index_lookup() walks the contents of the index looking for the @key.
- *
- * If the @key is found in the index, 0 is returned and @ictx is setup to
- * describe the index entry containing the matching @key.  @ictx->entry is the
- * index entry and @ictx->data and @ictx->data_len are the index entry data and
- * its length in bytes, respectively.
- *
- * If the @key is not found in the index, -ENOENT is returned and @ictx is
- * setup to describe the index entry whose key collates immediately after the
- * search @key, i.e. this is the position in the index at which an index entry
- * with a key of @key would need to be inserted.
- *
- * If an error occurs return the negative error code and @ictx is left
- * untouched.
- *
- * When finished with the entry and its data, call ntfs_index_ctx_put() to free
- * the context and other associated resources.
- *
- * If the index entry was modified, call flush_dcache_index_entry_page()
- * immediately after the modification and either ntfs_index_entry_mark_dirty()
- * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
- * ensure that the changes are written to disk.
- *
- * Locking:  - Caller must hold i_mutex on the index inode.
- *	     - Each page cache page in the index allocation mapping must be
- *	       locked whilst being accessed otherwise we may find a corrupt
- *	       page due to it being under ->writepage at the moment which
- *	       applies the mst protection fixups before writing out and then
- *	       removes them again after the write is complete after which it 
- *	       unlocks the page.
- */
-int ntfs_index_lookup(const void *key, const int key_len,
-		ntfs_index_context *ictx)
-{
-	VCN vcn, old_vcn;
-	ntfs_inode *idx_ni = ictx->idx_ni;
-	ntfs_volume *vol = idx_ni->vol;
-	struct super_block *sb = vol->sb;
-	ntfs_inode *base_ni = idx_ni->ext.base_ntfs_ino;
-	MFT_RECORD *m;
-	INDEX_ROOT *ir;
-	INDEX_ENTRY *ie;
-	INDEX_ALLOCATION *ia;
-	u8 *index_end, *kaddr;
-	ntfs_attr_search_ctx *actx;
-	struct address_space *ia_mapping;
-	struct page *page;
-	int rc, err = 0;
-
-	ntfs_debug("Entering.");
-	BUG_ON(!NInoAttr(idx_ni));
-	BUG_ON(idx_ni->type != AT_INDEX_ALLOCATION);
-	BUG_ON(idx_ni->nr_extents != -1);
-	BUG_ON(!base_ni);
-	BUG_ON(!key);
-	BUG_ON(key_len <= 0);
-	if (!ntfs_is_collation_rule_supported(
-			idx_ni->itype.index.collation_rule)) {
-		ntfs_error(sb, "Index uses unsupported collation rule 0x%x.  "
-				"Aborting lookup.", le32_to_cpu(
-				idx_ni->itype.index.collation_rule));
-		return -EOPNOTSUPP;
-	}
-	/* Get hold of the mft record for the index inode. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(sb, "map_mft_record() failed with error code %ld.",
-				-PTR_ERR(m));
-		return PTR_ERR(m);
-	}
-	actx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!actx)) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	/* Find the index root attribute in the mft record. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, idx_ni->name, idx_ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, actx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(sb, "Index root attribute missing in inode "
-					"0x%lx.", idx_ni->mft_no);
-			err = -EIO;
-		}
-		goto err_out;
-	}
-	/* Get to the index root value (it has been verified in read_inode). */
-	ir = (INDEX_ROOT*)((u8*)actx->attr +
-			le16_to_cpu(actx->attr->data.resident.value_offset));
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ir->index +
-			le32_to_cpu(ir->index.entries_offset));
-	/*
-	 * Loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)actx->mrec || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->length) > index_end)
-			goto idx_err_out;
-		/*
-		 * The last entry cannot contain a key.  It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Further bounds checks. */
-		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
-				le16_to_cpu(ie->key_length) >
-				le16_to_cpu(ie->data.vi.data_offset) ||
-				(u32)le16_to_cpu(ie->data.vi.data_offset) +
-				le16_to_cpu(ie->data.vi.data_length) >
-				le16_to_cpu(ie->length))
-			goto idx_err_out;
-		/* If the keys match perfectly, we setup @ictx and return 0. */
-		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
-				&ie->key, key_len)) {
-ir_done:
-			ictx->is_in_root = true;
-			ictx->ir = ir;
-			ictx->actx = actx;
-			ictx->base_ni = base_ni;
-			ictx->ia = NULL;
-			ictx->page = NULL;
-done:
-			ictx->entry = ie;
-			ictx->data = (u8*)ie +
-					le16_to_cpu(ie->data.vi.data_offset);
-			ictx->data_len = le16_to_cpu(ie->data.vi.data_length);
-			ntfs_debug("Done.");
-			return err;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
-				key_len, &ie->key, le16_to_cpu(ie->key_length));
-		/*
-		 * If @key collates before the key of the current entry, there
-		 * is definitely no such key in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/*
-		 * A match should never happen as the memcmp() call should have
-		 * cought it, but we still treat it correctly.
-		 */
-		if (!rc)
-			goto ir_done;
-		/* The keys are not equal, continue the search. */
-	}
-	/*
-	 * We have finished with this index without success.  Check for the
-	 * presence of a child node and if not present setup @ictx and return
-	 * -ENOENT.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto ir_done;
-	} /* Child node present, descend into it. */
-	/* Consistency check: Verify that an index allocation exists. */
-	if (!NInoIndexAllocPresent(idx_ni)) {
-		ntfs_error(sb, "No index allocation attribute but index entry "
-				"requires one.  Inode 0x%lx is corrupt or "
-				"driver bug.", idx_ni->mft_no);
-		goto err_out;
-	}
-	/* Get the starting vcn of the index_block holding the child node. */
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	ia_mapping = VFS_I(idx_ni)->i_mapping;
-	/*
-	 * We are done with the index root and the mft record.  Release them,
-	 * otherwise we deadlock with ntfs_map_page().
-	 */
-	ntfs_attr_put_search_ctx(actx);
-	unmap_mft_record(base_ni);
-	m = NULL;
-	actx = NULL;
-descend_into_child_node:
-	/*
-	 * Convert vcn to index into the index allocation attribute in units
-	 * of PAGE_SIZE and map the page cache page, reading it from
-	 * disk if necessary.
-	 */
-	page = ntfs_map_page(ia_mapping, vcn <<
-			idx_ni->itype.index.vcn_size_bits >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		ntfs_error(sb, "Failed to map index page, error %ld.",
-				-PTR_ERR(page));
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	kaddr = (u8*)page_address(page);
-fast_descend_into_child_node:
-	/* Get to the index allocation block. */
-	ia = (INDEX_ALLOCATION*)(kaddr + ((vcn <<
-			idx_ni->itype.index.vcn_size_bits) & ~PAGE_MASK));
-	/* Bounds checks. */
-	if ((u8*)ia < kaddr || (u8*)ia > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Out of bounds check failed.  Corrupt inode "
-				"0x%lx or driver bug.", idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Catch multi sector transfer fixup errors. */
-	if (unlikely(!ntfs_is_indx_record(ia->magic))) {
-		ntfs_error(sb, "Index record with vcn 0x%llx is corrupt.  "
-				"Corrupt inode 0x%lx.  Run chkdsk.",
-				(long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (sle64_to_cpu(ia->index_block_vcn) != vcn) {
-		ntfs_error(sb, "Actual VCN (0x%llx) of index buffer is "
-				"different from expected VCN (0x%llx).  Inode "
-				"0x%lx is corrupt or driver bug.",
-				(unsigned long long)
-				sle64_to_cpu(ia->index_block_vcn),
-				(unsigned long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	if (le32_to_cpu(ia->index.allocated_size) + 0x18 !=
-			idx_ni->itype.index.block_size) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx has "
-				"a size (%u) differing from the index "
-				"specified size (%u).  Inode is corrupt or "
-				"driver bug.", (unsigned long long)vcn,
-				idx_ni->mft_no,
-				le32_to_cpu(ia->index.allocated_size) + 0x18,
-				idx_ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	index_end = (u8*)ia + idx_ni->itype.index.block_size;
-	if (index_end > kaddr + PAGE_SIZE) {
-		ntfs_error(sb, "Index buffer (VCN 0x%llx) of inode 0x%lx "
-				"crosses page boundary.  Impossible!  Cannot "
-				"access!  This is probably a bug in the "
-				"driver.", (unsigned long long)vcn,
-				idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ia->index + le32_to_cpu(ia->index.index_length);
-	if (index_end > (u8*)ia + idx_ni->itype.index.block_size) {
-		ntfs_error(sb, "Size of index buffer (VCN 0x%llx) of inode "
-				"0x%lx exceeds maximum size.",
-				(unsigned long long)vcn, idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* The first index entry. */
-	ie = (INDEX_ENTRY*)((u8*)&ia->index +
-			le32_to_cpu(ia->index.entries_offset));
-	/*
-	 * Iterate similar to above big loop but applied to index buffer, thus
-	 * loop until we exceed valid memory (corruption case) or until we
-	 * reach the last entry.
-	 */
-	for (;; ie = (INDEX_ENTRY*)((u8*)ie + le16_to_cpu(ie->length))) {
-		/* Bounds checks. */
-		if ((u8*)ie < (u8*)ia || (u8*)ie +
-				sizeof(INDEX_ENTRY_HEADER) > index_end ||
-				(u8*)ie + le16_to_cpu(ie->length) > index_end) {
-			ntfs_error(sb, "Index entry out of bounds in inode "
-					"0x%lx.", idx_ni->mft_no);
-			goto unm_err_out;
-		}
-		/*
-		 * The last entry cannot contain a key.  It can however contain
-		 * a pointer to a child node in the B+tree so we just break out.
-		 */
-		if (ie->flags & INDEX_ENTRY_END)
-			break;
-		/* Further bounds checks. */
-		if ((u32)sizeof(INDEX_ENTRY_HEADER) +
-				le16_to_cpu(ie->key_length) >
-				le16_to_cpu(ie->data.vi.data_offset) ||
-				(u32)le16_to_cpu(ie->data.vi.data_offset) +
-				le16_to_cpu(ie->data.vi.data_length) >
-				le16_to_cpu(ie->length)) {
-			ntfs_error(sb, "Index entry out of bounds in inode "
-					"0x%lx.", idx_ni->mft_no);
-			goto unm_err_out;
-		}
-		/* If the keys match perfectly, we setup @ictx and return 0. */
-		if ((key_len == le16_to_cpu(ie->key_length)) && !memcmp(key,
-				&ie->key, key_len)) {
-ia_done:
-			ictx->is_in_root = false;
-			ictx->actx = NULL;
-			ictx->base_ni = NULL;
-			ictx->ia = ia;
-			ictx->page = page;
-			goto done;
-		}
-		/*
-		 * Not a perfect match, need to do full blown collation so we
-		 * know which way in the B+tree we have to go.
-		 */
-		rc = ntfs_collate(vol, idx_ni->itype.index.collation_rule, key,
-				key_len, &ie->key, le16_to_cpu(ie->key_length));
-		/*
-		 * If @key collates before the key of the current entry, there
-		 * is definitely no such key in this index but we might need to
-		 * descend into the B+tree so we just break out of the loop.
-		 */
-		if (rc == -1)
-			break;
-		/*
-		 * A match should never happen as the memcmp() call should have
-		 * cought it, but we still treat it correctly.
-		 */
-		if (!rc)
-			goto ia_done;
-		/* The keys are not equal, continue the search. */
-	}
-	/*
-	 * We have finished with this index buffer without success.  Check for
-	 * the presence of a child node and if not present return -ENOENT.
-	 */
-	if (!(ie->flags & INDEX_ENTRY_NODE)) {
-		ntfs_debug("Entry not found.");
-		err = -ENOENT;
-		goto ia_done;
-	}
-	if ((ia->index.flags & NODE_MASK) == LEAF_NODE) {
-		ntfs_error(sb, "Index entry with child node found in a leaf "
-				"node in inode 0x%lx.", idx_ni->mft_no);
-		goto unm_err_out;
-	}
-	/* Child node present, descend into it. */
-	old_vcn = vcn;
-	vcn = sle64_to_cpup((sle64*)((u8*)ie + le16_to_cpu(ie->length) - 8));
-	if (vcn >= 0) {
-		/*
-		 * If vcn is in the same page cache page as old_vcn we recycle
-		 * the mapped page.
-		 */
-		if (old_vcn << vol->cluster_size_bits >>
-				PAGE_SHIFT == vcn <<
-				vol->cluster_size_bits >>
-				PAGE_SHIFT)
-			goto fast_descend_into_child_node;
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		goto descend_into_child_node;
-	}
-	ntfs_error(sb, "Negative child node vcn in inode 0x%lx.",
-			idx_ni->mft_no);
-unm_err_out:
-	unlock_page(page);
-	ntfs_unmap_page(page);
-err_out:
-	if (!err)
-		err = -EIO;
-	if (actx)
-		ntfs_attr_put_search_ctx(actx);
-	if (m)
-		unmap_mft_record(base_ni);
-	return err;
-idx_err_out:
-	ntfs_error(sb, "Corrupt index.  Aborting lookup.");
-	goto err_out;
-}
diff --git a/fs/ntfs/index.h b/fs/ntfs/index.h
deleted file mode 100644
index bb3c3ae55138..000000000000
--- a/fs/ntfs/index.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * index.h - Defines for NTFS kernel index handling.  Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_INDEX_H
-#define _LINUX_NTFS_INDEX_H
-
-#include <linux/fs.h>
-
-#include "types.h"
-#include "layout.h"
-#include "inode.h"
-#include "attrib.h"
-#include "mft.h"
-#include "aops.h"
-
-/**
- * @idx_ni:	index inode containing the @entry described by this context
- * @entry:	index entry (points into @ir or @ia)
- * @data:	index entry data (points into @entry)
- * @data_len:	length in bytes of @data
- * @is_in_root:	'true' if @entry is in @ir and 'false' if it is in @ia
- * @ir:		index root if @is_in_root and NULL otherwise
- * @actx:	attribute search context if @is_in_root and NULL otherwise
- * @base_ni:	base inode if @is_in_root and NULL otherwise
- * @ia:		index block if @is_in_root is 'false' and NULL otherwise
- * @page:	page if @is_in_root is 'false' and NULL otherwise
- *
- * @idx_ni is the index inode this context belongs to.
- *
- * @entry is the index entry described by this context.  @data and @data_len
- * are the index entry data and its length in bytes, respectively.  @data
- * simply points into @entry.  This is probably what the user is interested in.
- *
- * If @is_in_root is 'true', @entry is in the index root attribute @ir described
- * by the attribute search context @actx and the base inode @base_ni.  @ia and
- * @page are NULL in this case.
- *
- * If @is_in_root is 'false', @entry is in the index allocation attribute and @ia
- * and @page point to the index allocation block and the mapped, locked page it
- * is in, respectively.  @ir, @actx and @base_ni are NULL in this case.
- *
- * To obtain a context call ntfs_index_ctx_get().
- *
- * We use this context to allow ntfs_index_lookup() to return the found index
- * @entry and its @data without having to allocate a buffer and copy the @entry
- * and/or its @data into it.
- *
- * When finished with the @entry and its @data, call ntfs_index_ctx_put() to
- * free the context and other associated resources.
- *
- * If the index entry was modified, call flush_dcache_index_entry_page()
- * immediately after the modification and either ntfs_index_entry_mark_dirty()
- * or ntfs_index_entry_write() before the call to ntfs_index_ctx_put() to
- * ensure that the changes are written to disk.
- */
-typedef struct {
-	ntfs_inode *idx_ni;
-	INDEX_ENTRY *entry;
-	void *data;
-	u16 data_len;
-	bool is_in_root;
-	INDEX_ROOT *ir;
-	ntfs_attr_search_ctx *actx;
-	ntfs_inode *base_ni;
-	INDEX_ALLOCATION *ia;
-	struct page *page;
-} ntfs_index_context;
-
-extern ntfs_index_context *ntfs_index_ctx_get(ntfs_inode *idx_ni);
-extern void ntfs_index_ctx_put(ntfs_index_context *ictx);
-
-extern int ntfs_index_lookup(const void *key, const int key_len,
-		ntfs_index_context *ictx);
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_index_entry_flush_dcache_page - flush_dcache_page() for index entries
- * @ictx:	ntfs index context describing the index entry
- *
- * Call flush_dcache_page() for the page in which an index entry resides.
- *
- * This must be called every time an index entry is modified, just after the
- * modification.
- *
- * If the index entry is in the index root attribute, simply flush the page
- * containing the mft record containing the index root attribute.
- *
- * If the index entry is in an index block belonging to the index allocation
- * attribute, simply flush the page cache page containing the index block.
- */
-static inline void ntfs_index_entry_flush_dcache_page(ntfs_index_context *ictx)
-{
-	if (ictx->is_in_root)
-		flush_dcache_mft_record_page(ictx->actx->ntfs_ino);
-	else
-		flush_dcache_page(ictx->page);
-}
-
-/**
- * ntfs_index_entry_mark_dirty - mark an index entry dirty
- * @ictx:	ntfs index context describing the index entry
- *
- * Mark the index entry described by the index entry context @ictx dirty.
- *
- * If the index entry is in the index root attribute, simply mark the mft
- * record containing the index root attribute dirty.  This ensures the mft
- * record, and hence the index root attribute, will be written out to disk
- * later.
- *
- * If the index entry is in an index block belonging to the index allocation
- * attribute, mark the buffers belonging to the index record as well as the
- * page cache page the index block is in dirty.  This automatically marks the
- * VFS inode of the ntfs index inode to which the index entry belongs dirty,
- * too (I_DIRTY_PAGES) and this in turn ensures the page buffers, and hence the
- * dirty index block, will be written out to disk later.
- */
-static inline void ntfs_index_entry_mark_dirty(ntfs_index_context *ictx)
-{
-	if (ictx->is_in_root)
-		mark_mft_record_dirty(ictx->actx->ntfs_ino);
-	else
-		mark_ntfs_record_dirty(ictx->page,
-				(u8*)ictx->ia - (u8*)page_address(ictx->page));
-}
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_INDEX_H */
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
deleted file mode 100644
index aba1e22db4e9..000000000000
--- a/fs/ntfs/inode.c
+++ /dev/null
@@ -1,3102 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * inode.c - NTFS kernel inode handling.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- */
-
-#include <linux/buffer_head.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mount.h>
-#include <linux/mutex.h>
-#include <linux/pagemap.h>
-#include <linux/quotaops.h>
-#include <linux/slab.h>
-#include <linux/log2.h>
-
-#include "aops.h"
-#include "attrib.h"
-#include "bitmap.h"
-#include "dir.h"
-#include "debug.h"
-#include "inode.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "time.h"
-#include "ntfs.h"
-
-/**
- * ntfs_test_inode - compare two (possibly fake) inodes for equality
- * @vi:		vfs inode which to test
- * @data:	data which is being tested with
- *
- * Compare the ntfs attribute embedded in the ntfs specific part of the vfs
- * inode @vi for equality with the ntfs attribute @data.
- *
- * If searching for the normal file/directory inode, set @na->type to AT_UNUSED.
- * @na->name and @na->name_len are then ignored.
- *
- * Return 1 if the attributes match and 0 if not.
- *
- * NOTE: This function runs with the inode_hash_lock spin lock held so it is not
- * allowed to sleep.
- */
-int ntfs_test_inode(struct inode *vi, void *data)
-{
-	ntfs_attr *na = (ntfs_attr *)data;
-	ntfs_inode *ni;
-
-	if (vi->i_ino != na->mft_no)
-		return 0;
-	ni = NTFS_I(vi);
-	/* If !NInoAttr(ni), @vi is a normal file or directory inode. */
-	if (likely(!NInoAttr(ni))) {
-		/* If not looking for a normal inode this is a mismatch. */
-		if (unlikely(na->type != AT_UNUSED))
-			return 0;
-	} else {
-		/* A fake inode describing an attribute. */
-		if (ni->type != na->type)
-			return 0;
-		if (ni->name_len != na->name_len)
-			return 0;
-		if (na->name_len && memcmp(ni->name, na->name,
-				na->name_len * sizeof(ntfschar)))
-			return 0;
-	}
-	/* Match! */
-	return 1;
-}
-
-/**
- * ntfs_init_locked_inode - initialize an inode
- * @vi:		vfs inode to initialize
- * @data:	data which to initialize @vi to
- *
- * Initialize the vfs inode @vi with the values from the ntfs attribute @data in
- * order to enable ntfs_test_inode() to do its work.
- *
- * If initializing the normal file/directory inode, set @na->type to AT_UNUSED.
- * In that case, @na->name and @na->name_len should be set to NULL and 0,
- * respectively. Although that is not strictly necessary as
- * ntfs_read_locked_inode() will fill them in later.
- *
- * Return 0 on success and -errno on error.
- *
- * NOTE: This function runs with the inode->i_lock spin lock held so it is not
- * allowed to sleep. (Hence the GFP_ATOMIC allocation.)
- */
-static int ntfs_init_locked_inode(struct inode *vi, void *data)
-{
-	ntfs_attr *na = (ntfs_attr *)data;
-	ntfs_inode *ni = NTFS_I(vi);
-
-	vi->i_ino = na->mft_no;
-
-	ni->type = na->type;
-	if (na->type == AT_INDEX_ALLOCATION)
-		NInoSetMstProtected(ni);
-
-	ni->name = na->name;
-	ni->name_len = na->name_len;
-
-	/* If initializing a normal inode, we are done. */
-	if (likely(na->type == AT_UNUSED)) {
-		BUG_ON(na->name);
-		BUG_ON(na->name_len);
-		return 0;
-	}
-
-	/* It is a fake inode. */
-	NInoSetAttr(ni);
-
-	/*
-	 * We have I30 global constant as an optimization as it is the name
-	 * in >99.9% of named attributes! The other <0.1% incur a GFP_ATOMIC
-	 * allocation but that is ok. And most attributes are unnamed anyway,
-	 * thus the fraction of named attributes with name != I30 is actually
-	 * absolutely tiny.
-	 */
-	if (na->name_len && na->name != I30) {
-		unsigned int i;
-
-		BUG_ON(!na->name);
-		i = na->name_len * sizeof(ntfschar);
-		ni->name = kmalloc(i + sizeof(ntfschar), GFP_ATOMIC);
-		if (!ni->name)
-			return -ENOMEM;
-		memcpy(ni->name, na->name, i);
-		ni->name[na->name_len] = 0;
-	}
-	return 0;
-}
-
-static int ntfs_read_locked_inode(struct inode *vi);
-static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi);
-static int ntfs_read_locked_index_inode(struct inode *base_vi,
-		struct inode *vi);
-
-/**
- * ntfs_iget - obtain a struct inode corresponding to a specific normal inode
- * @sb:		super block of mounted volume
- * @mft_no:	mft record number / inode number to obtain
- *
- * Obtain the struct inode corresponding to a specific normal inode (i.e. a
- * file or directory).
- *
- * If the inode is in the cache, it is just returned with an increased
- * reference count. Otherwise, a new struct inode is allocated and initialized,
- * and finally ntfs_read_locked_inode() is called to read in the inode and
- * fill in the remainder of the inode structure.
- *
- * Return the struct inode on success. Check the return value with IS_ERR() and
- * if true, the function failed and the error code is obtained from PTR_ERR().
- */
-struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	na.mft_no = mft_no;
-	na.type = AT_UNUSED;
-	na.name = NULL;
-	na.name_len = 0;
-
-	vi = iget5_locked(sb, mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_inode(vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad inodes around if the failure was
-	 * due to ENOMEM. We want to be able to retry again later.
-	 */
-	if (unlikely(err == -ENOMEM)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-/**
- * ntfs_attr_iget - obtain a struct inode corresponding to an attribute
- * @base_vi:	vfs base inode containing the attribute
- * @type:	attribute type
- * @name:	Unicode name of the attribute (NULL if unnamed)
- * @name_len:	length of @name in Unicode characters (0 if unnamed)
- *
- * Obtain the (fake) struct inode corresponding to the attribute specified by
- * @type, @name, and @name_len, which is present in the base mft record
- * specified by the vfs inode @base_vi.
- *
- * If the attribute inode is in the cache, it is just returned with an
- * increased reference count. Otherwise, a new struct inode is allocated and
- * initialized, and finally ntfs_read_locked_attr_inode() is called to read the
- * attribute and fill in the inode structure.
- *
- * Note, for index allocation attributes, you need to use ntfs_index_iget()
- * instead of ntfs_attr_iget() as working with indices is a lot more complex.
- *
- * Return the struct inode of the attribute inode on success. Check the return
- * value with IS_ERR() and if true, the function failed and the error code is
- * obtained from PTR_ERR().
- */
-struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
-		ntfschar *name, u32 name_len)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	/* Make sure no one calls ntfs_attr_iget() for indices. */
-	BUG_ON(type == AT_INDEX_ALLOCATION);
-
-	na.mft_no = base_vi->i_ino;
-	na.type = type;
-	na.name = name;
-	na.name_len = name_len;
-
-	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_attr_inode(base_vi, vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad attribute inodes around. This also
-	 * simplifies things in that we never need to check for bad attribute
-	 * inodes elsewhere.
-	 */
-	if (unlikely(err)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-/**
- * ntfs_index_iget - obtain a struct inode corresponding to an index
- * @base_vi:	vfs base inode containing the index related attributes
- * @name:	Unicode name of the index
- * @name_len:	length of @name in Unicode characters
- *
- * Obtain the (fake) struct inode corresponding to the index specified by @name
- * and @name_len, which is present in the base mft record specified by the vfs
- * inode @base_vi.
- *
- * If the index inode is in the cache, it is just returned with an increased
- * reference count.  Otherwise, a new struct inode is allocated and
- * initialized, and finally ntfs_read_locked_index_inode() is called to read
- * the index related attributes and fill in the inode structure.
- *
- * Return the struct inode of the index inode on success. Check the return
- * value with IS_ERR() and if true, the function failed and the error code is
- * obtained from PTR_ERR().
- */
-struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
-		u32 name_len)
-{
-	struct inode *vi;
-	int err;
-	ntfs_attr na;
-
-	na.mft_no = base_vi->i_ino;
-	na.type = AT_INDEX_ALLOCATION;
-	na.name = name;
-	na.name_len = name_len;
-
-	vi = iget5_locked(base_vi->i_sb, na.mft_no, ntfs_test_inode,
-			ntfs_init_locked_inode, &na);
-	if (unlikely(!vi))
-		return ERR_PTR(-ENOMEM);
-
-	err = 0;
-
-	/* If this is a freshly allocated inode, need to read it now. */
-	if (vi->i_state & I_NEW) {
-		err = ntfs_read_locked_index_inode(base_vi, vi);
-		unlock_new_inode(vi);
-	}
-	/*
-	 * There is no point in keeping bad index inodes around.  This also
-	 * simplifies things in that we never need to check for bad index
-	 * inodes elsewhere.
-	 */
-	if (unlikely(err)) {
-		iput(vi);
-		vi = ERR_PTR(err);
-	}
-	return vi;
-}
-
-struct inode *ntfs_alloc_big_inode(struct super_block *sb)
-{
-	ntfs_inode *ni;
-
-	ntfs_debug("Entering.");
-	ni = alloc_inode_sb(sb, ntfs_big_inode_cache, GFP_NOFS);
-	if (likely(ni != NULL)) {
-		ni->state = 0;
-		return VFS_I(ni);
-	}
-	ntfs_error(sb, "Allocation of NTFS big inode structure failed.");
-	return NULL;
-}
-
-void ntfs_free_big_inode(struct inode *inode)
-{
-	kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode));
-}
-
-static inline ntfs_inode *ntfs_alloc_extent_inode(void)
-{
-	ntfs_inode *ni;
-
-	ntfs_debug("Entering.");
-	ni = kmem_cache_alloc(ntfs_inode_cache, GFP_NOFS);
-	if (likely(ni != NULL)) {
-		ni->state = 0;
-		return ni;
-	}
-	ntfs_error(NULL, "Allocation of NTFS inode structure failed.");
-	return NULL;
-}
-
-static void ntfs_destroy_extent_inode(ntfs_inode *ni)
-{
-	ntfs_debug("Entering.");
-	BUG_ON(ni->page);
-	if (!atomic_dec_and_test(&ni->count))
-		BUG();
-	kmem_cache_free(ntfs_inode_cache, ni);
-}
-
-/*
- * The attribute runlist lock has separate locking rules from the
- * normal runlist lock, so split the two lock-classes:
- */
-static struct lock_class_key attr_list_rl_lock_class;
-
-/**
- * __ntfs_init_inode - initialize ntfs specific part of an inode
- * @sb:		super block of mounted volume
- * @ni:		freshly allocated ntfs inode which to initialize
- *
- * Initialize an ntfs inode to defaults.
- *
- * NOTE: ni->mft_no, ni->state, ni->type, ni->name, and ni->name_len are left
- * untouched. Make sure to initialize them elsewhere.
- *
- * Return zero on success and -ENOMEM on error.
- */
-void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni)
-{
-	ntfs_debug("Entering.");
-	rwlock_init(&ni->size_lock);
-	ni->initialized_size = ni->allocated_size = 0;
-	ni->seq_no = 0;
-	atomic_set(&ni->count, 1);
-	ni->vol = NTFS_SB(sb);
-	ntfs_init_runlist(&ni->runlist);
-	mutex_init(&ni->mrec_lock);
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	ni->attr_list_size = 0;
-	ni->attr_list = NULL;
-	ntfs_init_runlist(&ni->attr_list_rl);
-	lockdep_set_class(&ni->attr_list_rl.lock,
-				&attr_list_rl_lock_class);
-	ni->itype.index.block_size = 0;
-	ni->itype.index.vcn_size = 0;
-	ni->itype.index.collation_rule = 0;
-	ni->itype.index.block_size_bits = 0;
-	ni->itype.index.vcn_size_bits = 0;
-	mutex_init(&ni->extent_lock);
-	ni->nr_extents = 0;
-	ni->ext.base_ntfs_ino = NULL;
-}
-
-/*
- * Extent inodes get MFT-mapped in a nested way, while the base inode
- * is still mapped. Teach this nesting to the lock validator by creating
- * a separate class for nested inode's mrec_lock's:
- */
-static struct lock_class_key extent_inode_mrec_lock_key;
-
-inline ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
-		unsigned long mft_no)
-{
-	ntfs_inode *ni = ntfs_alloc_extent_inode();
-
-	ntfs_debug("Entering.");
-	if (likely(ni != NULL)) {
-		__ntfs_init_inode(sb, ni);
-		lockdep_set_class(&ni->mrec_lock, &extent_inode_mrec_lock_key);
-		ni->mft_no = mft_no;
-		ni->type = AT_UNUSED;
-		ni->name = NULL;
-		ni->name_len = 0;
-	}
-	return ni;
-}
-
-/**
- * ntfs_is_extended_system_file - check if a file is in the $Extend directory
- * @ctx:	initialized attribute search context
- *
- * Search all file name attributes in the inode described by the attribute
- * search context @ctx and check if any of the names are in the $Extend system
- * directory.
- *
- * Return values:
- *	   1: file is in $Extend directory
- *	   0: file is not in $Extend directory
- *    -errno: failed to determine if the file is in the $Extend directory
- */
-static int ntfs_is_extended_system_file(ntfs_attr_search_ctx *ctx)
-{
-	int nr_links, err;
-
-	/* Restart search. */
-	ntfs_attr_reinit_search_ctx(ctx);
-
-	/* Get number of hard links. */
-	nr_links = le16_to_cpu(ctx->mrec->link_count);
-
-	/* Loop through all hard links. */
-	while (!(err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0, NULL, 0,
-			ctx))) {
-		FILE_NAME_ATTR *file_name_attr;
-		ATTR_RECORD *attr = ctx->attr;
-		u8 *p, *p2;
-
-		nr_links--;
-		/*
-		 * Maximum sanity checking as we are called on an inode that
-		 * we suspect might be corrupt.
-		 */
-		p = (u8*)attr + le32_to_cpu(attr->length);
-		if (p < (u8*)ctx->mrec || (u8*)p > (u8*)ctx->mrec +
-				le32_to_cpu(ctx->mrec->bytes_in_use)) {
-err_corrupt_attr:
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Corrupt file name "
-					"attribute. You should run chkdsk.");
-			return -EIO;
-		}
-		if (attr->non_resident) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Non-resident file "
-					"name. You should run chkdsk.");
-			return -EIO;
-		}
-		if (attr->flags) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "File name with "
-					"invalid flags. You should run "
-					"chkdsk.");
-			return -EIO;
-		}
-		if (!(attr->data.resident.flags & RESIDENT_ATTR_IS_INDEXED)) {
-			ntfs_error(ctx->ntfs_ino->vol->sb, "Unindexed file "
-					"name. You should run chkdsk.");
-			return -EIO;
-		}
-		file_name_attr = (FILE_NAME_ATTR*)((u8*)attr +
-				le16_to_cpu(attr->data.resident.value_offset));
-		p2 = (u8 *)file_name_attr + le32_to_cpu(attr->data.resident.value_length);
-		if (p2 < (u8*)attr || p2 > p)
-			goto err_corrupt_attr;
-		/* This attribute is ok, but is it in the $Extend directory? */
-		if (MREF_LE(file_name_attr->parent_directory) == FILE_Extend)
-			return 1;	/* YES, it's an extended system file. */
-	}
-	if (unlikely(err != -ENOENT))
-		return err;
-	if (unlikely(nr_links)) {
-		ntfs_error(ctx->ntfs_ino->vol->sb, "Inode hard link count "
-				"doesn't match number of name attributes. You "
-				"should run chkdsk.");
-		return -EIO;
-	}
-	return 0;	/* NO, it is not an extended system file. */
-}
-
-/**
- * ntfs_read_locked_inode - read an inode from its device
- * @vi:		inode to read
- *
- * ntfs_read_locked_inode() is called from ntfs_iget() to read the inode
- * described by @vi into memory from the device.
- *
- * The only fields in @vi that we need to/can look at when the function is
- * called are i_sb, pointing to the mounted device's super block, and i_ino,
- * the number of the inode to load.
- *
- * ntfs_read_locked_inode() maps, pins and locks the mft record number i_ino
- * for reading and sets up the necessary @vi fields as well as initializing
- * the ntfs inode.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *    i_flags is set to 0 and we have no business touching it.  Only an ioctl()
- *    is allowed to write to them. We should of course be honouring them but
- *    we need to do that using the IS_* macros defined in include/linux/fs.h.
- *    In any case ntfs_read_locked_inode() has nothing to do with i_flags.
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- */
-static int ntfs_read_locked_inode(struct inode *vi)
-{
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni;
-	struct inode *bvi;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	STANDARD_INFORMATION *si;
-	ntfs_attr_search_ctx *ctx;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-
-	/* Setup the generic vfs inode parts now. */
-	vi->i_uid = vol->uid;
-	vi->i_gid = vol->gid;
-	vi->i_mode = 0;
-
-	/*
-	 * Initialize the ntfs specific part of @vi special casing
-	 * FILE_MFT which we need to do at mount time.
-	 */
-	if (vi->i_ino != FILE_MFT)
-		ntfs_init_big_inode(vi);
-	ni = NTFS_I(vi);
-
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-
-	if (!(m->flags & MFT_RECORD_IN_USE)) {
-		ntfs_error(vi->i_sb, "Inode is not in use!");
-		goto unm_err_out;
-	}
-	if (m->base_mft_record) {
-		ntfs_error(vi->i_sb, "Inode is an extent inode!");
-		goto unm_err_out;
-	}
-
-	/* Transfer information from mft record into vfs and ntfs inodes. */
-	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-
-	/*
-	 * FIXME: Keep in mind that link_count is two for files which have both
-	 * a long file name and a short file name as separate entries, so if
-	 * we are hiding short file names this will be too high. Either we need
-	 * to account for the short file names by subtracting them or we need
-	 * to make sure we delete files even though i_nlink is not zero which
-	 * might be tricky due to vfs interactions. Need to think about this
-	 * some more when implementing the unlink command.
-	 */
-	set_nlink(vi, le16_to_cpu(m->link_count));
-	/*
-	 * FIXME: Reparse points can have the directory bit set even though
-	 * they would be S_IFLNK. Need to deal with this further below when we
-	 * implement reparse points / symbolic links but it will do for now.
-	 * Also if not a directory, it could be something else, rather than
-	 * a regular file. But again, will do for now.
-	 */
-	/* Everyone gets all permissions. */
-	vi->i_mode |= S_IRWXUGO;
-	/* If read-only, no one gets write permissions. */
-	if (IS_RDONLY(vi))
-		vi->i_mode &= ~S_IWUGO;
-	if (m->flags & MFT_RECORD_IS_DIRECTORY) {
-		vi->i_mode |= S_IFDIR;
-		/*
-		 * Apply the directory permissions mask set in the mount
-		 * options.
-		 */
-		vi->i_mode &= ~vol->dmask;
-		/* Things break without this kludge! */
-		if (vi->i_nlink > 1)
-			set_nlink(vi, 1);
-	} else {
-		vi->i_mode |= S_IFREG;
-		/* Apply the file permissions mask set in the mount options. */
-		vi->i_mode &= ~vol->fmask;
-	}
-	/*
-	 * Find the standard information attribute in the mft record. At this
-	 * stage we haven't setup the attribute list stuff yet, so this could
-	 * in fact fail if the standard information is in an extent record, but
-	 * I don't think this actually ever happens.
-	 */
-	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			/*
-			 * TODO: We should be performing a hot fix here (if the
-			 * recover mount option is set) by creating a new
-			 * attribute.
-			 */
-			ntfs_error(vi->i_sb, "$STANDARD_INFORMATION attribute "
-					"is missing.");
-		}
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	/* Get the standard information attribute value. */
-	if ((u8 *)a + le16_to_cpu(a->data.resident.value_offset)
-			+ le32_to_cpu(a->data.resident.value_length) >
-			(u8 *)ctx->mrec + vol->mft_record_size) {
-		ntfs_error(vi->i_sb, "Corrupt standard information attribute in inode.");
-		goto unm_err_out;
-	}
-	si = (STANDARD_INFORMATION*)((u8*)a +
-			le16_to_cpu(a->data.resident.value_offset));
-
-	/* Transfer information from the standard information into vi. */
-	/*
-	 * Note: The i_?times do not quite map perfectly onto the NTFS times,
-	 * but they are close enough, and in the end it doesn't really matter
-	 * that much...
-	 */
-	/*
-	 * mtime is the last change of the data within the file. Not changed
-	 * when only metadata is changed, e.g. a rename doesn't affect mtime.
-	 */
-	inode_set_mtime_to_ts(vi, ntfs2utc(si->last_data_change_time));
-	/*
-	 * ctime is the last change of the metadata of the file. This obviously
-	 * always changes, when mtime is changed. ctime can be changed on its
-	 * own, mtime is then not changed, e.g. when a file is renamed.
-	 */
-	inode_set_ctime_to_ts(vi, ntfs2utc(si->last_mft_change_time));
-	/*
-	 * Last access to the data within the file. Not changed during a rename
-	 * for example but changed whenever the file is written to.
-	 */
-	inode_set_atime_to_ts(vi, ntfs2utc(si->last_access_time));
-
-	/* Find the attribute list attribute if present. */
-	ntfs_attr_reinit_search_ctx(ctx);
-	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
-	if (err) {
-		if (unlikely(err != -ENOENT)) {
-			ntfs_error(vi->i_sb, "Failed to lookup attribute list "
-					"attribute.");
-			goto unm_err_out;
-		}
-	} else /* if (!err) */ {
-		if (vi->i_ino == FILE_MFT)
-			goto skip_attr_list_load;
-		ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino);
-		NInoSetAttrList(ni);
-		a = ctx->attr;
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(vi->i_sb, "Attribute list attribute is "
-					"compressed.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			if (a->non_resident) {
-				ntfs_error(vi->i_sb, "Non-resident attribute "
-						"list attribute is encrypted/"
-						"sparse.");
-				goto unm_err_out;
-			}
-			ntfs_warning(vi->i_sb, "Resident attribute list "
-					"attribute in inode 0x%lx is marked "
-					"encrypted/sparse which is not true.  "
-					"However, Windows allows this and "
-					"chkdsk does not detect or correct it "
-					"so we will just ignore the invalid "
-					"flags and pretend they are not set.",
-					vi->i_ino);
-		}
-		/* Now allocate memory for the attribute list. */
-		ni->attr_list_size = (u32)ntfs_attr_size(a);
-		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
-		if (!ni->attr_list) {
-			ntfs_error(vi->i_sb, "Not enough memory to allocate "
-					"buffer for attribute list.");
-			err = -ENOMEM;
-			goto unm_err_out;
-		}
-		if (a->non_resident) {
-			NInoSetAttrListNonResident(ni);
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(vi->i_sb, "Attribute list has non "
-						"zero lowest_vcn.");
-				goto unm_err_out;
-			}
-			/*
-			 * Setup the runlist. No need for locking as we have
-			 * exclusive access to the inode at this time.
-			 */
-			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
-					a, NULL);
-			if (IS_ERR(ni->attr_list_rl.rl)) {
-				err = PTR_ERR(ni->attr_list_rl.rl);
-				ni->attr_list_rl.rl = NULL;
-				ntfs_error(vi->i_sb, "Mapping pairs "
-						"decompression failed.");
-				goto unm_err_out;
-			}
-			/* Now load the attribute list. */
-			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
-					ni->attr_list, ni->attr_list_size,
-					sle64_to_cpu(a->data.non_resident.
-					initialized_size)))) {
-				ntfs_error(vi->i_sb, "Failed to load "
-						"attribute list attribute.");
-				goto unm_err_out;
-			}
-		} else /* if (!a->non_resident) */ {
-			if ((u8*)a + le16_to_cpu(a->data.resident.value_offset)
-					+ le32_to_cpu(
-					a->data.resident.value_length) >
-					(u8*)ctx->mrec + vol->mft_record_size) {
-				ntfs_error(vi->i_sb, "Corrupt attribute list "
-						"in inode.");
-				goto unm_err_out;
-			}
-			/* Now copy the attribute list. */
-			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					le32_to_cpu(
-					a->data.resident.value_length));
-		}
-	}
-skip_attr_list_load:
-	/*
-	 * If an attribute list is present we now have the attribute list value
-	 * in ntfs_ino->attr_list and it is ntfs_ino->attr_list_size bytes.
-	 */
-	if (S_ISDIR(vi->i_mode)) {
-		loff_t bvi_size;
-		ntfs_inode *bni;
-		INDEX_ROOT *ir;
-		u8 *ir_end, *index_end;
-
-		/* It is a directory, find index root attribute. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(AT_INDEX_ROOT, I30, 4, CASE_SENSITIVE,
-				0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT) {
-				// FIXME: File is corrupt! Hot-fix with empty
-				// index root attribute if recovery option is
-				// set.
-				ntfs_error(vi->i_sb, "$INDEX_ROOT attribute "
-						"is missing.");
-			}
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		/* Set up the state. */
-		if (unlikely(a->non_resident)) {
-			ntfs_error(vol->sb, "$INDEX_ROOT attribute is not "
-					"resident.");
-			goto unm_err_out;
-		}
-		/* Ensure the attribute name is placed before the value. */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(a->data.resident.value_offset)))) {
-			ntfs_error(vol->sb, "$INDEX_ROOT attribute name is "
-					"placed after the attribute value.");
-			goto unm_err_out;
-		}
-		/*
-		 * Compressed/encrypted index root just means that the newly
-		 * created files in that directory should be created compressed/
-		 * encrypted. However index root cannot be both compressed and
-		 * encrypted.
-		 */
-		if (a->flags & ATTR_COMPRESSION_MASK)
-			NInoSetCompressed(ni);
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				ntfs_error(vi->i_sb, "Found encrypted and "
-						"compressed attribute.");
-				goto unm_err_out;
-			}
-			NInoSetEncrypted(ni);
-		}
-		if (a->flags & ATTR_IS_SPARSE)
-			NInoSetSparse(ni);
-		ir = (INDEX_ROOT*)((u8*)a +
-				le16_to_cpu(a->data.resident.value_offset));
-		ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
-		if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
-			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
-					"corrupt.");
-			goto unm_err_out;
-		}
-		index_end = (u8*)&ir->index +
-				le32_to_cpu(ir->index.index_length);
-		if (index_end > ir_end) {
-			ntfs_error(vi->i_sb, "Directory index is corrupt.");
-			goto unm_err_out;
-		}
-		if (ir->type != AT_FILE_NAME) {
-			ntfs_error(vi->i_sb, "Indexed attribute is not "
-					"$FILE_NAME.");
-			goto unm_err_out;
-		}
-		if (ir->collation_rule != COLLATION_FILE_NAME) {
-			ntfs_error(vi->i_sb, "Index collation rule is not "
-					"COLLATION_FILE_NAME.");
-			goto unm_err_out;
-		}
-		ni->itype.index.collation_rule = ir->collation_rule;
-		ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
-		if (ni->itype.index.block_size &
-				(ni->itype.index.block_size - 1)) {
-			ntfs_error(vi->i_sb, "Index block size (%u) is not a "
-					"power of two.",
-					ni->itype.index.block_size);
-			goto unm_err_out;
-		}
-		if (ni->itype.index.block_size > PAGE_SIZE) {
-			ntfs_error(vi->i_sb, "Index block size (%u) > "
-					"PAGE_SIZE (%ld) is not "
-					"supported.  Sorry.",
-					ni->itype.index.block_size,
-					PAGE_SIZE);
-			err = -EOPNOTSUPP;
-			goto unm_err_out;
-		}
-		if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
-			ntfs_error(vi->i_sb, "Index block size (%u) < "
-					"NTFS_BLOCK_SIZE (%i) is not "
-					"supported.  Sorry.",
-					ni->itype.index.block_size,
-					NTFS_BLOCK_SIZE);
-			err = -EOPNOTSUPP;
-			goto unm_err_out;
-		}
-		ni->itype.index.block_size_bits =
-				ffs(ni->itype.index.block_size) - 1;
-		/* Determine the size of a vcn in the directory index. */
-		if (vol->cluster_size <= ni->itype.index.block_size) {
-			ni->itype.index.vcn_size = vol->cluster_size;
-			ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
-		} else {
-			ni->itype.index.vcn_size = vol->sector_size;
-			ni->itype.index.vcn_size_bits = vol->sector_size_bits;
-		}
-
-		/* Setup the index allocation attribute, even if not present. */
-		NInoSetMstProtected(ni);
-		ni->type = AT_INDEX_ALLOCATION;
-		ni->name = I30;
-		ni->name_len = 4;
-
-		if (!(ir->index.flags & LARGE_INDEX)) {
-			/* No index allocation. */
-			vi->i_size = ni->initialized_size =
-					ni->allocated_size = 0;
-			/* We are done with the mft record, so we release it. */
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(ni);
-			m = NULL;
-			ctx = NULL;
-			goto skip_large_dir_stuff;
-		} /* LARGE_INDEX: Index allocation present. Setup state. */
-		NInoSetIndexAllocPresent(ni);
-		/* Find index allocation attribute. */
-		ntfs_attr_reinit_search_ctx(ctx);
-		err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, I30, 4,
-				CASE_SENSITIVE, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			if (err == -ENOENT)
-				ntfs_error(vi->i_sb, "$INDEX_ALLOCATION "
-						"attribute is not present but "
-						"$INDEX_ROOT indicated it is.");
-			else
-				ntfs_error(vi->i_sb, "Failed to lookup "
-						"$INDEX_ALLOCATION "
-						"attribute.");
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		if (!a->non_resident) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is resident.");
-			goto unm_err_out;
-		}
-		/*
-		 * Ensure the attribute name is placed before the mapping pairs
-		 * array.
-		 */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset)))) {
-			ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name "
-					"is placed after the mapping pairs "
-					"array.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is encrypted.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_SPARSE) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is sparse.");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute "
-					"is compressed.");
-			goto unm_err_out;
-		}
-		if (a->data.non_resident.lowest_vcn) {
-			ntfs_error(vi->i_sb, "First extent of "
-					"$INDEX_ALLOCATION attribute has non "
-					"zero lowest_vcn.");
-			goto unm_err_out;
-		}
-		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-		ni->initialized_size = sle64_to_cpu(
-				a->data.non_resident.initialized_size);
-		ni->allocated_size = sle64_to_cpu(
-				a->data.non_resident.allocated_size);
-		/*
-		 * We are done with the mft record, so we release it. Otherwise
-		 * we would deadlock in ntfs_attr_iget().
-		 */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		m = NULL;
-		ctx = NULL;
-		/* Get the index bitmap attribute inode. */
-		bvi = ntfs_attr_iget(vi, AT_BITMAP, I30, 4);
-		if (IS_ERR(bvi)) {
-			ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
-			err = PTR_ERR(bvi);
-			goto unm_err_out;
-		}
-		bni = NTFS_I(bvi);
-		if (NInoCompressed(bni) || NInoEncrypted(bni) ||
-				NInoSparse(bni)) {
-			ntfs_error(vi->i_sb, "$BITMAP attribute is compressed "
-					"and/or encrypted and/or sparse.");
-			goto iput_unm_err_out;
-		}
-		/* Consistency check bitmap size vs. index allocation size. */
-		bvi_size = i_size_read(bvi);
-		if ((bvi_size << 3) < (vi->i_size >>
-				ni->itype.index.block_size_bits)) {
-			ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) "
-					"for index allocation (0x%llx).",
-					bvi_size << 3, vi->i_size);
-			goto iput_unm_err_out;
-		}
-		/* No longer need the bitmap attribute inode. */
-		iput(bvi);
-skip_large_dir_stuff:
-		/* Setup the operations for this inode. */
-		vi->i_op = &ntfs_dir_inode_ops;
-		vi->i_fop = &ntfs_dir_ops;
-		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	} else {
-		/* It is a file. */
-		ntfs_attr_reinit_search_ctx(ctx);
-
-		/* Setup the data attribute, even if not present. */
-		ni->type = AT_DATA;
-		ni->name = NULL;
-		ni->name_len = 0;
-
-		/* Find first extent of the unnamed data attribute. */
-		err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, 0, NULL, 0, ctx);
-		if (unlikely(err)) {
-			vi->i_size = ni->initialized_size =
-					ni->allocated_size = 0;
-			if (err != -ENOENT) {
-				ntfs_error(vi->i_sb, "Failed to lookup $DATA "
-						"attribute.");
-				goto unm_err_out;
-			}
-			/*
-			 * FILE_Secure does not have an unnamed $DATA
-			 * attribute, so we special case it here.
-			 */
-			if (vi->i_ino == FILE_Secure)
-				goto no_data_attr_special_case;
-			/*
-			 * Most if not all the system files in the $Extend
-			 * system directory do not have unnamed data
-			 * attributes so we need to check if the parent
-			 * directory of the file is FILE_Extend and if it is
-			 * ignore this error. To do this we need to get the
-			 * name of this inode from the mft record as the name
-			 * contains the back reference to the parent directory.
-			 */
-			if (ntfs_is_extended_system_file(ctx) > 0)
-				goto no_data_attr_special_case;
-			// FIXME: File is corrupt! Hot-fix with empty data
-			// attribute if recovery option is set.
-			ntfs_error(vi->i_sb, "$DATA attribute is missing.");
-			goto unm_err_out;
-		}
-		a = ctx->attr;
-		/* Setup the state. */
-		if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
-			if (a->flags & ATTR_COMPRESSION_MASK) {
-				NInoSetCompressed(ni);
-				if (vol->cluster_size > 4096) {
-					ntfs_error(vi->i_sb, "Found "
-							"compressed data but "
-							"compression is "
-							"disabled due to "
-							"cluster size (%i) > "
-							"4kiB.",
-							vol->cluster_size);
-					goto unm_err_out;
-				}
-				if ((a->flags & ATTR_COMPRESSION_MASK)
-						!= ATTR_IS_COMPRESSED) {
-					ntfs_error(vi->i_sb, "Found unknown "
-							"compression method "
-							"or corrupt file.");
-					goto unm_err_out;
-				}
-			}
-			if (a->flags & ATTR_IS_SPARSE)
-				NInoSetSparse(ni);
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED) {
-			if (NInoCompressed(ni)) {
-				ntfs_error(vi->i_sb, "Found encrypted and "
-						"compressed data.");
-				goto unm_err_out;
-			}
-			NInoSetEncrypted(ni);
-		}
-		if (a->non_resident) {
-			NInoSetNonResident(ni);
-			if (NInoCompressed(ni) || NInoSparse(ni)) {
-				if (NInoCompressed(ni) && a->data.non_resident.
-						compression_unit != 4) {
-					ntfs_error(vi->i_sb, "Found "
-							"non-standard "
-							"compression unit (%u "
-							"instead of 4).  "
-							"Cannot handle this.",
-							a->data.non_resident.
-							compression_unit);
-					err = -EOPNOTSUPP;
-					goto unm_err_out;
-				}
-				if (a->data.non_resident.compression_unit) {
-					ni->itype.compressed.block_size = 1U <<
-							(a->data.non_resident.
-							compression_unit +
-							vol->cluster_size_bits);
-					ni->itype.compressed.block_size_bits =
-							ffs(ni->itype.
-							compressed.
-							block_size) - 1;
-					ni->itype.compressed.block_clusters =
-							1U << a->data.
-							non_resident.
-							compression_unit;
-				} else {
-					ni->itype.compressed.block_size = 0;
-					ni->itype.compressed.block_size_bits =
-							0;
-					ni->itype.compressed.block_clusters =
-							0;
-				}
-				ni->itype.compressed.size = sle64_to_cpu(
-						a->data.non_resident.
-						compressed_size);
-			}
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(vi->i_sb, "First extent of $DATA "
-						"attribute has non zero "
-						"lowest_vcn.");
-				goto unm_err_out;
-			}
-			vi->i_size = sle64_to_cpu(
-					a->data.non_resident.data_size);
-			ni->initialized_size = sle64_to_cpu(
-					a->data.non_resident.initialized_size);
-			ni->allocated_size = sle64_to_cpu(
-					a->data.non_resident.allocated_size);
-		} else { /* Resident attribute. */
-			vi->i_size = ni->initialized_size = le32_to_cpu(
-					a->data.resident.value_length);
-			ni->allocated_size = le32_to_cpu(a->length) -
-					le16_to_cpu(
-					a->data.resident.value_offset);
-			if (vi->i_size > ni->allocated_size) {
-				ntfs_error(vi->i_sb, "Resident data attribute "
-						"is corrupt (size exceeds "
-						"allocation).");
-				goto unm_err_out;
-			}
-		}
-no_data_attr_special_case:
-		/* We are done with the mft record, so we release it. */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		m = NULL;
-		ctx = NULL;
-		/* Setup the operations for this inode. */
-		vi->i_op = &ntfs_file_inode_ops;
-		vi->i_fop = &ntfs_file_ops;
-		vi->i_mapping->a_ops = &ntfs_normal_aops;
-		if (NInoMstProtected(ni))
-			vi->i_mapping->a_ops = &ntfs_mst_aops;
-		else if (NInoCompressed(ni))
-			vi->i_mapping->a_ops = &ntfs_compressed_aops;
-	}
-	/*
-	 * The number of 512-byte blocks used on disk (for stat). This is in so
-	 * far inaccurate as it doesn't account for any named streams or other
-	 * special non-resident attributes, but that is how Windows works, too,
-	 * so we are at least consistent with Windows, if not entirely
-	 * consistent with the Linux Way. Doing it the Linux Way would cause a
-	 * significant slowdown as it would involve iterating over all
-	 * attributes in the mft record and adding the allocated/compressed
-	 * sizes of all non-resident attributes present to give us the Linux
-	 * correct size that should go into i_blocks (after division by 512).
-	 */
-	if (S_ISREG(vi->i_mode) && (NInoCompressed(ni) || NInoSparse(ni)))
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	else
-		vi->i_blocks = ni->allocated_size >> 9;
-	ntfs_debug("Done.");
-	return 0;
-iput_unm_err_out:
-	iput(bvi);
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i.  Marking corrupt "
-			"inode 0x%lx as bad.  Run chkdsk.", err, vi->i_ino);
-	make_bad_inode(vi);
-	if (err != -EOPNOTSUPP && err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_read_locked_attr_inode - read an attribute inode from its base inode
- * @base_vi:	base inode
- * @vi:		attribute inode to read
- *
- * ntfs_read_locked_attr_inode() is called from ntfs_attr_iget() to read the
- * attribute inode described by @vi into memory from the base mft record
- * described by @base_ni.
- *
- * ntfs_read_locked_attr_inode() maps, pins and locks the base inode for
- * reading and looks up the attribute described by @vi before setting up the
- * necessary fields in @vi as well as initializing the ntfs inode.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- *
- * Note this cannot be called for AT_INDEX_ALLOCATION.
- */
-static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
-{
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni, *base_ni;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-
-	ntfs_init_big_inode(vi);
-
-	ni	= NTFS_I(vi);
-	base_ni = NTFS_I(base_vi);
-
-	/* Just mirror the values from the base inode. */
-	vi->i_uid	= base_vi->i_uid;
-	vi->i_gid	= base_vi->i_gid;
-	set_nlink(vi, base_vi->i_nlink);
-	inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi));
-	inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi));
-	inode_set_atime_to_ts(vi, inode_get_atime(base_vi));
-	vi->i_generation = ni->seq_no = base_ni->seq_no;
-
-	/* Set inode type to zero but preserve permissions. */
-	vi->i_mode	= base_vi->i_mode & ~S_IFMT;
-
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	/* Find the attribute. */
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err))
-		goto unm_err_out;
-	a = ctx->attr;
-	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_SPARSE)) {
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			NInoSetCompressed(ni);
-			if ((ni->type != AT_DATA) || (ni->type == AT_DATA &&
-					ni->name_len)) {
-				ntfs_error(vi->i_sb, "Found compressed "
-						"non-data or named data "
-						"attribute.  Please report "
-						"you saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				goto unm_err_out;
-			}
-			if (vol->cluster_size > 4096) {
-				ntfs_error(vi->i_sb, "Found compressed "
-						"attribute but compression is "
-						"disabled due to cluster size "
-						"(%i) > 4kiB.",
-						vol->cluster_size);
-				goto unm_err_out;
-			}
-			if ((a->flags & ATTR_COMPRESSION_MASK) !=
-					ATTR_IS_COMPRESSED) {
-				ntfs_error(vi->i_sb, "Found unknown "
-						"compression method.");
-				goto unm_err_out;
-			}
-		}
-		/*
-		 * The compressed/sparse flag set in an index root just means
-		 * to compress all files.
-		 */
-		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is %s.  Please "
-					"report you saw this message to "
-					"linux-ntfs-dev@lists.sourceforge.net",
-					NInoCompressed(ni) ? "compressed" :
-					"sparse");
-			goto unm_err_out;
-		}
-		if (a->flags & ATTR_IS_SPARSE)
-			NInoSetSparse(ni);
-	}
-	if (a->flags & ATTR_IS_ENCRYPTED) {
-		if (NInoCompressed(ni)) {
-			ntfs_error(vi->i_sb, "Found encrypted and compressed "
-					"data.");
-			goto unm_err_out;
-		}
-		/*
-		 * The encryption flag set in an index root just means to
-		 * encrypt all files.
-		 */
-		if (NInoMstProtected(ni) && ni->type != AT_INDEX_ROOT) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is encrypted.  "
-					"Please report you saw this message "
-					"to linux-ntfs-dev@lists.sourceforge."
-					"net");
-			goto unm_err_out;
-		}
-		if (ni->type != AT_DATA) {
-			ntfs_error(vi->i_sb, "Found encrypted non-data "
-					"attribute.");
-			goto unm_err_out;
-		}
-		NInoSetEncrypted(ni);
-	}
-	if (!a->non_resident) {
-		/* Ensure the attribute name is placed before the value. */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(a->data.resident.value_offset)))) {
-			ntfs_error(vol->sb, "Attribute name is placed after "
-					"the attribute value.");
-			goto unm_err_out;
-		}
-		if (NInoMstProtected(ni)) {
-			ntfs_error(vi->i_sb, "Found mst protected attribute "
-					"but the attribute is resident.  "
-					"Please report you saw this message to "
-					"linux-ntfs-dev@lists.sourceforge.net");
-			goto unm_err_out;
-		}
-		vi->i_size = ni->initialized_size = le32_to_cpu(
-				a->data.resident.value_length);
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		if (vi->i_size > ni->allocated_size) {
-			ntfs_error(vi->i_sb, "Resident attribute is corrupt "
-					"(size exceeds allocation).");
-			goto unm_err_out;
-		}
-	} else {
-		NInoSetNonResident(ni);
-		/*
-		 * Ensure the attribute name is placed before the mapping pairs
-		 * array.
-		 */
-		if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-				le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset)))) {
-			ntfs_error(vol->sb, "Attribute name is placed after "
-					"the mapping pairs array.");
-			goto unm_err_out;
-		}
-		if (NInoCompressed(ni) || NInoSparse(ni)) {
-			if (NInoCompressed(ni) && a->data.non_resident.
-					compression_unit != 4) {
-				ntfs_error(vi->i_sb, "Found non-standard "
-						"compression unit (%u instead "
-						"of 4).  Cannot handle this.",
-						a->data.non_resident.
-						compression_unit);
-				err = -EOPNOTSUPP;
-				goto unm_err_out;
-			}
-			if (a->data.non_resident.compression_unit) {
-				ni->itype.compressed.block_size = 1U <<
-						(a->data.non_resident.
-						compression_unit +
-						vol->cluster_size_bits);
-				ni->itype.compressed.block_size_bits =
-						ffs(ni->itype.compressed.
-						block_size) - 1;
-				ni->itype.compressed.block_clusters = 1U <<
-						a->data.non_resident.
-						compression_unit;
-			} else {
-				ni->itype.compressed.block_size = 0;
-				ni->itype.compressed.block_size_bits = 0;
-				ni->itype.compressed.block_clusters = 0;
-			}
-			ni->itype.compressed.size = sle64_to_cpu(
-					a->data.non_resident.compressed_size);
-		}
-		if (a->data.non_resident.lowest_vcn) {
-			ntfs_error(vi->i_sb, "First extent of attribute has "
-					"non-zero lowest_vcn.");
-			goto unm_err_out;
-		}
-		vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-		ni->initialized_size = sle64_to_cpu(
-				a->data.non_resident.initialized_size);
-		ni->allocated_size = sle64_to_cpu(
-				a->data.non_resident.allocated_size);
-	}
-	vi->i_mapping->a_ops = &ntfs_normal_aops;
-	if (NInoMstProtected(ni))
-		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	else if (NInoCompressed(ni))
-		vi->i_mapping->a_ops = &ntfs_compressed_aops;
-	if ((NInoCompressed(ni) || NInoSparse(ni)) && ni->type != AT_INDEX_ROOT)
-		vi->i_blocks = ni->itype.compressed.size >> 9;
-	else
-		vi->i_blocks = ni->allocated_size >> 9;
-	/*
-	 * Make sure the base inode does not go away and attach it to the
-	 * attribute inode.
-	 */
-	igrab(base_vi);
-	ni->ext.base_ntfs_ino = base_ni;
-	ni->nr_extents = -1;
-
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-
-	ntfs_debug("Done.");
-	return 0;
-
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i while reading attribute "
-			"inode (mft_no 0x%lx, type 0x%x, name_len %i).  "
-			"Marking corrupt inode and base inode 0x%lx as bad.  "
-			"Run chkdsk.", err, vi->i_ino, ni->type, ni->name_len,
-			base_vi->i_ino);
-	make_bad_inode(vi);
-	if (err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_read_locked_index_inode - read an index inode from its base inode
- * @base_vi:	base inode
- * @vi:		index inode to read
- *
- * ntfs_read_locked_index_inode() is called from ntfs_index_iget() to read the
- * index inode described by @vi into memory from the base mft record described
- * by @base_ni.
- *
- * ntfs_read_locked_index_inode() maps, pins and locks the base inode for
- * reading and looks up the attributes relating to the index described by @vi
- * before setting up the necessary fields in @vi as well as initializing the
- * ntfs inode.
- *
- * Note, index inodes are essentially attribute inodes (NInoAttr() is true)
- * with the attribute type set to AT_INDEX_ALLOCATION.  Apart from that, they
- * are setup like directory inodes since directories are a special case of
- * indices ao they need to be treated in much the same way.  Most importantly,
- * for small indices the index allocation attribute might not actually exist.
- * However, the index root attribute always exists but this does not need to
- * have an inode associated with it and this is why we define a new inode type
- * index.  Also, like for directories, we need to have an attribute inode for
- * the bitmap attribute corresponding to the index allocation attribute and we
- * can store this in the appropriate field of the inode, just like we do for
- * normal directory inodes.
- *
- * Q: What locks are held when the function is called?
- * A: i_state has I_NEW set, hence the inode is locked, also
- *    i_count is set to 1, so it is not going to go away
- *
- * Return 0 on success and -errno on error.  In the error case, the inode will
- * have had make_bad_inode() executed on it.
- */
-static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
-{
-	loff_t bvi_size;
-	ntfs_volume *vol = NTFS_SB(vi->i_sb);
-	ntfs_inode *ni, *base_ni, *bni;
-	struct inode *bvi;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	INDEX_ROOT *ir;
-	u8 *ir_end, *index_end;
-	int err = 0;
-
-	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
-	ntfs_init_big_inode(vi);
-	ni	= NTFS_I(vi);
-	base_ni = NTFS_I(base_vi);
-	/* Just mirror the values from the base inode. */
-	vi->i_uid	= base_vi->i_uid;
-	vi->i_gid	= base_vi->i_gid;
-	set_nlink(vi, base_vi->i_nlink);
-	inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi));
-	inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi));
-	inode_set_atime_to_ts(vi, inode_get_atime(base_vi));
-	vi->i_generation = ni->seq_no = base_ni->seq_no;
-	/* Set inode type to zero but preserve permissions. */
-	vi->i_mode	= base_vi->i_mode & ~S_IFMT;
-	/* Map the mft record for the base inode. */
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	/* Find the index root attribute. */
-	err = ntfs_attr_lookup(AT_INDEX_ROOT, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is "
-					"missing.");
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	/* Set up the state. */
-	if (unlikely(a->non_resident)) {
-		ntfs_error(vol->sb, "$INDEX_ROOT attribute is not resident.");
-		goto unm_err_out;
-	}
-	/* Ensure the attribute name is placed before the value. */
-	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-			le16_to_cpu(a->data.resident.value_offset)))) {
-		ntfs_error(vol->sb, "$INDEX_ROOT attribute name is placed "
-				"after the attribute value.");
-		goto unm_err_out;
-	}
-	/*
-	 * Compressed/encrypted/sparse index root is not allowed, except for
-	 * directories of course but those are not dealt with here.
-	 */
-	if (a->flags & (ATTR_COMPRESSION_MASK | ATTR_IS_ENCRYPTED |
-			ATTR_IS_SPARSE)) {
-		ntfs_error(vi->i_sb, "Found compressed/encrypted/sparse index "
-				"root attribute.");
-		goto unm_err_out;
-	}
-	ir = (INDEX_ROOT*)((u8*)a + le16_to_cpu(a->data.resident.value_offset));
-	ir_end = (u8*)ir + le32_to_cpu(a->data.resident.value_length);
-	if (ir_end > (u8*)ctx->mrec + vol->mft_record_size) {
-		ntfs_error(vi->i_sb, "$INDEX_ROOT attribute is corrupt.");
-		goto unm_err_out;
-	}
-	index_end = (u8*)&ir->index + le32_to_cpu(ir->index.index_length);
-	if (index_end > ir_end) {
-		ntfs_error(vi->i_sb, "Index is corrupt.");
-		goto unm_err_out;
-	}
-	if (ir->type) {
-		ntfs_error(vi->i_sb, "Index type is not 0 (type is 0x%x).",
-				le32_to_cpu(ir->type));
-		goto unm_err_out;
-	}
-	ni->itype.index.collation_rule = ir->collation_rule;
-	ntfs_debug("Index collation rule is 0x%x.",
-			le32_to_cpu(ir->collation_rule));
-	ni->itype.index.block_size = le32_to_cpu(ir->index_block_size);
-	if (!is_power_of_2(ni->itype.index.block_size)) {
-		ntfs_error(vi->i_sb, "Index block size (%u) is not a power of "
-				"two.", ni->itype.index.block_size);
-		goto unm_err_out;
-	}
-	if (ni->itype.index.block_size > PAGE_SIZE) {
-		ntfs_error(vi->i_sb, "Index block size (%u) > PAGE_SIZE "
-				"(%ld) is not supported.  Sorry.",
-				ni->itype.index.block_size, PAGE_SIZE);
-		err = -EOPNOTSUPP;
-		goto unm_err_out;
-	}
-	if (ni->itype.index.block_size < NTFS_BLOCK_SIZE) {
-		ntfs_error(vi->i_sb, "Index block size (%u) < NTFS_BLOCK_SIZE "
-				"(%i) is not supported.  Sorry.",
-				ni->itype.index.block_size, NTFS_BLOCK_SIZE);
-		err = -EOPNOTSUPP;
-		goto unm_err_out;
-	}
-	ni->itype.index.block_size_bits = ffs(ni->itype.index.block_size) - 1;
-	/* Determine the size of a vcn in the index. */
-	if (vol->cluster_size <= ni->itype.index.block_size) {
-		ni->itype.index.vcn_size = vol->cluster_size;
-		ni->itype.index.vcn_size_bits = vol->cluster_size_bits;
-	} else {
-		ni->itype.index.vcn_size = vol->sector_size;
-		ni->itype.index.vcn_size_bits = vol->sector_size_bits;
-	}
-	/* Check for presence of index allocation attribute. */
-	if (!(ir->index.flags & LARGE_INDEX)) {
-		/* No index allocation. */
-		vi->i_size = ni->initialized_size = ni->allocated_size = 0;
-		/* We are done with the mft record, so we release it. */
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(base_ni);
-		m = NULL;
-		ctx = NULL;
-		goto skip_large_index_stuff;
-	} /* LARGE_INDEX:  Index allocation present.  Setup state. */
-	NInoSetIndexAllocPresent(ni);
-	/* Find index allocation attribute. */
-	ntfs_attr_reinit_search_ctx(ctx);
-	err = ntfs_attr_lookup(AT_INDEX_ALLOCATION, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-					"not present but $INDEX_ROOT "
-					"indicated it is.");
-		else
-			ntfs_error(vi->i_sb, "Failed to lookup "
-					"$INDEX_ALLOCATION attribute.");
-		goto unm_err_out;
-	}
-	a = ctx->attr;
-	if (!a->non_resident) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"resident.");
-		goto unm_err_out;
-	}
-	/*
-	 * Ensure the attribute name is placed before the mapping pairs array.
-	 */
-	if (unlikely(a->name_length && (le16_to_cpu(a->name_offset) >=
-			le16_to_cpu(
-			a->data.non_resident.mapping_pairs_offset)))) {
-		ntfs_error(vol->sb, "$INDEX_ALLOCATION attribute name is "
-				"placed after the mapping pairs array.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_IS_ENCRYPTED) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"encrypted.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_IS_SPARSE) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is sparse.");
-		goto unm_err_out;
-	}
-	if (a->flags & ATTR_COMPRESSION_MASK) {
-		ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is "
-				"compressed.");
-		goto unm_err_out;
-	}
-	if (a->data.non_resident.lowest_vcn) {
-		ntfs_error(vi->i_sb, "First extent of $INDEX_ALLOCATION "
-				"attribute has non zero lowest_vcn.");
-		goto unm_err_out;
-	}
-	vi->i_size = sle64_to_cpu(a->data.non_resident.data_size);
-	ni->initialized_size = sle64_to_cpu(
-			a->data.non_resident.initialized_size);
-	ni->allocated_size = sle64_to_cpu(a->data.non_resident.allocated_size);
-	/*
-	 * We are done with the mft record, so we release it.  Otherwise
-	 * we would deadlock in ntfs_attr_iget().
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	m = NULL;
-	ctx = NULL;
-	/* Get the index bitmap attribute inode. */
-	bvi = ntfs_attr_iget(base_vi, AT_BITMAP, ni->name, ni->name_len);
-	if (IS_ERR(bvi)) {
-		ntfs_error(vi->i_sb, "Failed to get bitmap attribute.");
-		err = PTR_ERR(bvi);
-		goto unm_err_out;
-	}
-	bni = NTFS_I(bvi);
-	if (NInoCompressed(bni) || NInoEncrypted(bni) ||
-			NInoSparse(bni)) {
-		ntfs_error(vi->i_sb, "$BITMAP attribute is compressed and/or "
-				"encrypted and/or sparse.");
-		goto iput_unm_err_out;
-	}
-	/* Consistency check bitmap size vs. index allocation size. */
-	bvi_size = i_size_read(bvi);
-	if ((bvi_size << 3) < (vi->i_size >> ni->itype.index.block_size_bits)) {
-		ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) for "
-				"index allocation (0x%llx).", bvi_size << 3,
-				vi->i_size);
-		goto iput_unm_err_out;
-	}
-	iput(bvi);
-skip_large_index_stuff:
-	/* Setup the operations for this index inode. */
-	vi->i_mapping->a_ops = &ntfs_mst_aops;
-	vi->i_blocks = ni->allocated_size >> 9;
-	/*
-	 * Make sure the base inode doesn't go away and attach it to the
-	 * index inode.
-	 */
-	igrab(base_vi);
-	ni->ext.base_ntfs_ino = base_ni;
-	ni->nr_extents = -1;
-
-	ntfs_debug("Done.");
-	return 0;
-iput_unm_err_out:
-	iput(bvi);
-unm_err_out:
-	if (!err)
-		err = -EIO;
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-err_out:
-	ntfs_error(vi->i_sb, "Failed with error code %i while reading index "
-			"inode (mft_no 0x%lx, name_len %i.", err, vi->i_ino,
-			ni->name_len);
-	make_bad_inode(vi);
-	if (err != -EOPNOTSUPP && err != -ENOMEM)
-		NVolSetErrors(vol);
-	return err;
-}
-
-/*
- * The MFT inode has special locking, so teach the lock validator
- * about this by splitting off the locking rules of the MFT from
- * the locking rules of other inodes. The MFT inode can never be
- * accessed from the VFS side (or even internally), only by the
- * map_mft functions.
- */
-static struct lock_class_key mft_ni_runlist_lock_key, mft_ni_mrec_lock_key;
-
-/**
- * ntfs_read_inode_mount - special read_inode for mount time use only
- * @vi:		inode to read
- *
- * Read inode FILE_MFT at mount time, only called with super_block lock
- * held from within the read_super() code path.
- *
- * This function exists because when it is called the page cache for $MFT/$DATA
- * is not initialized and hence we cannot get at the contents of mft records
- * by calling map_mft_record*().
- *
- * Further it needs to cope with the circular references problem, i.e. cannot
- * load any attributes other than $ATTRIBUTE_LIST until $DATA is loaded, because
- * we do not know where the other extent mft records are yet and again, because
- * we cannot call map_mft_record*() yet.  Obviously this applies only when an
- * attribute list is actually present in $MFT inode.
- *
- * We solve these problems by starting with the $DATA attribute before anything
- * else and iterating using ntfs_attr_lookup($DATA) over all extents.  As each
- * extent is found, we ntfs_mapping_pairs_decompress() including the implied
- * ntfs_runlists_merge().  Each step of the iteration necessarily provides
- * sufficient information for the next step to complete.
- *
- * This should work but there are two possible pit falls (see inline comments
- * below), but only time will tell if they are real pits or just smoke...
- */
-int ntfs_read_inode_mount(struct inode *vi)
-{
-	VCN next_vcn, last_vcn, highest_vcn;
-	s64 block;
-	struct super_block *sb = vi->i_sb;
-	ntfs_volume *vol = NTFS_SB(sb);
-	struct buffer_head *bh;
-	ntfs_inode *ni;
-	MFT_RECORD *m = NULL;
-	ATTR_RECORD *a;
-	ntfs_attr_search_ctx *ctx;
-	unsigned int i, nr_blocks;
-	int err;
-
-	ntfs_debug("Entering.");
-
-	/* Initialize the ntfs specific part of @vi. */
-	ntfs_init_big_inode(vi);
-
-	ni = NTFS_I(vi);
-
-	/* Setup the data attribute. It is special as it is mst protected. */
-	NInoSetNonResident(ni);
-	NInoSetMstProtected(ni);
-	NInoSetSparseDisabled(ni);
-	ni->type = AT_DATA;
-	ni->name = NULL;
-	ni->name_len = 0;
-	/*
-	 * This sets up our little cheat allowing us to reuse the async read io
-	 * completion handler for directories.
-	 */
-	ni->itype.index.block_size = vol->mft_record_size;
-	ni->itype.index.block_size_bits = vol->mft_record_size_bits;
-
-	/* Very important! Needed to be able to call map_mft_record*(). */
-	vol->mft_ino = vi;
-
-	/* Allocate enough memory to read the first mft record. */
-	if (vol->mft_record_size > 64 * 1024) {
-		ntfs_error(sb, "Unsupported mft record size %i (max 64kiB).",
-				vol->mft_record_size);
-		goto err_out;
-	}
-	i = vol->mft_record_size;
-	if (i < sb->s_blocksize)
-		i = sb->s_blocksize;
-	m = (MFT_RECORD*)ntfs_malloc_nofs(i);
-	if (!m) {
-		ntfs_error(sb, "Failed to allocate buffer for $MFT record 0.");
-		goto err_out;
-	}
-
-	/* Determine the first block of the $MFT/$DATA attribute. */
-	block = vol->mft_lcn << vol->cluster_size_bits >>
-			sb->s_blocksize_bits;
-	nr_blocks = vol->mft_record_size >> sb->s_blocksize_bits;
-	if (!nr_blocks)
-		nr_blocks = 1;
-
-	/* Load $MFT/$DATA's first mft record. */
-	for (i = 0; i < nr_blocks; i++) {
-		bh = sb_bread(sb, block++);
-		if (!bh) {
-			ntfs_error(sb, "Device read failed.");
-			goto err_out;
-		}
-		memcpy((char*)m + (i << sb->s_blocksize_bits), bh->b_data,
-				sb->s_blocksize);
-		brelse(bh);
-	}
-
-	if (le32_to_cpu(m->bytes_allocated) != vol->mft_record_size) {
-		ntfs_error(sb, "Incorrect mft record size %u in superblock, should be %u.",
-				le32_to_cpu(m->bytes_allocated), vol->mft_record_size);
-		goto err_out;
-	}
-
-	/* Apply the mst fixups. */
-	if (post_read_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size)) {
-		/* FIXME: Try to use the $MFTMirr now. */
-		ntfs_error(sb, "MST fixup failed. $MFT is corrupt.");
-		goto err_out;
-	}
-
-	/* Sanity check offset to the first attribute */
-	if (le16_to_cpu(m->attrs_offset) >= le32_to_cpu(m->bytes_allocated)) {
-		ntfs_error(sb, "Incorrect mft offset to the first attribute %u in superblock.",
-			       le16_to_cpu(m->attrs_offset));
-		goto err_out;
-	}
-
-	/* Need this to sanity check attribute list references to $MFT. */
-	vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-
-	/* Provides read_folio() for map_mft_record(). */
-	vi->i_mapping->a_ops = &ntfs_mst_aops;
-
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	/* Find the attribute list attribute if present. */
-	err = ntfs_attr_lookup(AT_ATTRIBUTE_LIST, NULL, 0, 0, 0, NULL, 0, ctx);
-	if (err) {
-		if (unlikely(err != -ENOENT)) {
-			ntfs_error(sb, "Failed to lookup attribute list "
-					"attribute. You should run chkdsk.");
-			goto put_err_out;
-		}
-	} else /* if (!err) */ {
-		ATTR_LIST_ENTRY *al_entry, *next_al_entry;
-		u8 *al_end;
-		static const char *es = "  Not allowed.  $MFT is corrupt.  "
-				"You should run chkdsk.";
-
-		ntfs_debug("Attribute list attribute found in $MFT.");
-		NInoSetAttrList(ni);
-		a = ctx->attr;
-		if (a->flags & ATTR_COMPRESSION_MASK) {
-			ntfs_error(sb, "Attribute list attribute is "
-					"compressed.%s", es);
-			goto put_err_out;
-		}
-		if (a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			if (a->non_resident) {
-				ntfs_error(sb, "Non-resident attribute list "
-						"attribute is encrypted/"
-						"sparse.%s", es);
-				goto put_err_out;
-			}
-			ntfs_warning(sb, "Resident attribute list attribute "
-					"in $MFT system file is marked "
-					"encrypted/sparse which is not true.  "
-					"However, Windows allows this and "
-					"chkdsk does not detect or correct it "
-					"so we will just ignore the invalid "
-					"flags and pretend they are not set.");
-		}
-		/* Now allocate memory for the attribute list. */
-		ni->attr_list_size = (u32)ntfs_attr_size(a);
-		if (!ni->attr_list_size) {
-			ntfs_error(sb, "Attr_list_size is zero");
-			goto put_err_out;
-		}
-		ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size);
-		if (!ni->attr_list) {
-			ntfs_error(sb, "Not enough memory to allocate buffer "
-					"for attribute list.");
-			goto put_err_out;
-		}
-		if (a->non_resident) {
-			NInoSetAttrListNonResident(ni);
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(sb, "Attribute list has non zero "
-						"lowest_vcn. $MFT is corrupt. "
-						"You should run chkdsk.");
-				goto put_err_out;
-			}
-			/* Setup the runlist. */
-			ni->attr_list_rl.rl = ntfs_mapping_pairs_decompress(vol,
-					a, NULL);
-			if (IS_ERR(ni->attr_list_rl.rl)) {
-				err = PTR_ERR(ni->attr_list_rl.rl);
-				ni->attr_list_rl.rl = NULL;
-				ntfs_error(sb, "Mapping pairs decompression "
-						"failed with error code %i.",
-						-err);
-				goto put_err_out;
-			}
-			/* Now load the attribute list. */
-			if ((err = load_attribute_list(vol, &ni->attr_list_rl,
-					ni->attr_list, ni->attr_list_size,
-					sle64_to_cpu(a->data.
-					non_resident.initialized_size)))) {
-				ntfs_error(sb, "Failed to load attribute list "
-						"attribute with error code %i.",
-						-err);
-				goto put_err_out;
-			}
-		} else /* if (!ctx.attr->non_resident) */ {
-			if ((u8*)a + le16_to_cpu(
-					a->data.resident.value_offset) +
-					le32_to_cpu(
-					a->data.resident.value_length) >
-					(u8*)ctx->mrec + vol->mft_record_size) {
-				ntfs_error(sb, "Corrupt attribute list "
-						"attribute.");
-				goto put_err_out;
-			}
-			/* Now copy the attribute list. */
-			memcpy(ni->attr_list, (u8*)a + le16_to_cpu(
-					a->data.resident.value_offset),
-					le32_to_cpu(
-					a->data.resident.value_length));
-		}
-		/* The attribute list is now setup in memory. */
-		/*
-		 * FIXME: I don't know if this case is actually possible.
-		 * According to logic it is not possible but I have seen too
-		 * many weird things in MS software to rely on logic... Thus we
-		 * perform a manual search and make sure the first $MFT/$DATA
-		 * extent is in the base inode. If it is not we abort with an
-		 * error and if we ever see a report of this error we will need
-		 * to do some magic in order to have the necessary mft record
-		 * loaded and in the right place in the page cache. But
-		 * hopefully logic will prevail and this never happens...
-		 */
-		al_entry = (ATTR_LIST_ENTRY*)ni->attr_list;
-		al_end = (u8*)al_entry + ni->attr_list_size;
-		for (;; al_entry = next_al_entry) {
-			/* Out of bounds check. */
-			if ((u8*)al_entry < ni->attr_list ||
-					(u8*)al_entry > al_end)
-				goto em_put_err_out;
-			/* Catch the end of the attribute list. */
-			if ((u8*)al_entry == al_end)
-				goto em_put_err_out;
-			if (!al_entry->length)
-				goto em_put_err_out;
-			if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
-					le16_to_cpu(al_entry->length) > al_end)
-				goto em_put_err_out;
-			next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
-					le16_to_cpu(al_entry->length));
-			if (le32_to_cpu(al_entry->type) > le32_to_cpu(AT_DATA))
-				goto em_put_err_out;
-			if (AT_DATA != al_entry->type)
-				continue;
-			/* We want an unnamed attribute. */
-			if (al_entry->name_length)
-				goto em_put_err_out;
-			/* Want the first entry, i.e. lowest_vcn == 0. */
-			if (al_entry->lowest_vcn)
-				goto em_put_err_out;
-			/* First entry has to be in the base mft record. */
-			if (MREF_LE(al_entry->mft_reference) != vi->i_ino) {
-				/* MFT references do not match, logic fails. */
-				ntfs_error(sb, "BUG: The first $DATA extent "
-						"of $MFT is not in the base "
-						"mft record. Please report "
-						"you saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				goto put_err_out;
-			} else {
-				/* Sequence numbers must match. */
-				if (MSEQNO_LE(al_entry->mft_reference) !=
-						ni->seq_no)
-					goto em_put_err_out;
-				/* Got it. All is ok. We can stop now. */
-				break;
-			}
-		}
-	}
-
-	ntfs_attr_reinit_search_ctx(ctx);
-
-	/* Now load all attribute extents. */
-	a = NULL;
-	next_vcn = last_vcn = highest_vcn = 0;
-	while (!(err = ntfs_attr_lookup(AT_DATA, NULL, 0, 0, next_vcn, NULL, 0,
-			ctx))) {
-		runlist_element *nrl;
-
-		/* Cache the current attribute. */
-		a = ctx->attr;
-		/* $MFT must be non-resident. */
-		if (!a->non_resident) {
-			ntfs_error(sb, "$MFT must be non-resident but a "
-					"resident extent was found. $MFT is "
-					"corrupt. Run chkdsk.");
-			goto put_err_out;
-		}
-		/* $MFT must be uncompressed and unencrypted. */
-		if (a->flags & ATTR_COMPRESSION_MASK ||
-				a->flags & ATTR_IS_ENCRYPTED ||
-				a->flags & ATTR_IS_SPARSE) {
-			ntfs_error(sb, "$MFT must be uncompressed, "
-					"non-sparse, and unencrypted but a "
-					"compressed/sparse/encrypted extent "
-					"was found. $MFT is corrupt. Run "
-					"chkdsk.");
-			goto put_err_out;
-		}
-		/*
-		 * Decompress the mapping pairs array of this extent and merge
-		 * the result into the existing runlist. No need for locking
-		 * as we have exclusive access to the inode at this time and we
-		 * are a mount in progress task, too.
-		 */
-		nrl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
-		if (IS_ERR(nrl)) {
-			ntfs_error(sb, "ntfs_mapping_pairs_decompress() "
-					"failed with error code %ld.  $MFT is "
-					"corrupt.", PTR_ERR(nrl));
-			goto put_err_out;
-		}
-		ni->runlist.rl = nrl;
-
-		/* Are we in the first extent? */
-		if (!next_vcn) {
-			if (a->data.non_resident.lowest_vcn) {
-				ntfs_error(sb, "First extent of $DATA "
-						"attribute has non zero "
-						"lowest_vcn. $MFT is corrupt. "
-						"You should run chkdsk.");
-				goto put_err_out;
-			}
-			/* Get the last vcn in the $DATA attribute. */
-			last_vcn = sle64_to_cpu(
-					a->data.non_resident.allocated_size)
-					>> vol->cluster_size_bits;
-			/* Fill in the inode size. */
-			vi->i_size = sle64_to_cpu(
-					a->data.non_resident.data_size);
-			ni->initialized_size = sle64_to_cpu(
-					a->data.non_resident.initialized_size);
-			ni->allocated_size = sle64_to_cpu(
-					a->data.non_resident.allocated_size);
-			/*
-			 * Verify the number of mft records does not exceed
-			 * 2^32 - 1.
-			 */
-			if ((vi->i_size >> vol->mft_record_size_bits) >=
-					(1ULL << 32)) {
-				ntfs_error(sb, "$MFT is too big! Aborting.");
-				goto put_err_out;
-			}
-			/*
-			 * We have got the first extent of the runlist for
-			 * $MFT which means it is now relatively safe to call
-			 * the normal ntfs_read_inode() function.
-			 * Complete reading the inode, this will actually
-			 * re-read the mft record for $MFT, this time entering
-			 * it into the page cache with which we complete the
-			 * kick start of the volume. It should be safe to do
-			 * this now as the first extent of $MFT/$DATA is
-			 * already known and we would hope that we don't need
-			 * further extents in order to find the other
-			 * attributes belonging to $MFT. Only time will tell if
-			 * this is really the case. If not we will have to play
-			 * magic at this point, possibly duplicating a lot of
-			 * ntfs_read_inode() at this point. We will need to
-			 * ensure we do enough of its work to be able to call
-			 * ntfs_read_inode() on extents of $MFT/$DATA. But lets
-			 * hope this never happens...
-			 */
-			ntfs_read_locked_inode(vi);
-			if (is_bad_inode(vi)) {
-				ntfs_error(sb, "ntfs_read_inode() of $MFT "
-						"failed. BUG or corrupt $MFT. "
-						"Run chkdsk and if no errors "
-						"are found, please report you "
-						"saw this message to "
-						"linux-ntfs-dev@lists."
-						"sourceforge.net");
-				ntfs_attr_put_search_ctx(ctx);
-				/* Revert to the safe super operations. */
-				ntfs_free(m);
-				return -1;
-			}
-			/*
-			 * Re-initialize some specifics about $MFT's inode as
-			 * ntfs_read_inode() will have set up the default ones.
-			 */
-			/* Set uid and gid to root. */
-			vi->i_uid = GLOBAL_ROOT_UID;
-			vi->i_gid = GLOBAL_ROOT_GID;
-			/* Regular file. No access for anyone. */
-			vi->i_mode = S_IFREG;
-			/* No VFS initiated operations allowed for $MFT. */
-			vi->i_op = &ntfs_empty_inode_ops;
-			vi->i_fop = &ntfs_empty_file_ops;
-		}
-
-		/* Get the lowest vcn for the next extent. */
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		next_vcn = highest_vcn + 1;
-
-		/* Only one extent or error, which we catch below. */
-		if (next_vcn <= 0)
-			break;
-
-		/* Avoid endless loops due to corruption. */
-		if (next_vcn < sle64_to_cpu(
-				a->data.non_resident.lowest_vcn)) {
-			ntfs_error(sb, "$MFT has corrupt attribute list "
-					"attribute. Run chkdsk.");
-			goto put_err_out;
-		}
-	}
-	if (err != -ENOENT) {
-		ntfs_error(sb, "Failed to lookup $MFT/$DATA attribute extent. "
-				"$MFT is corrupt. Run chkdsk.");
-		goto put_err_out;
-	}
-	if (!a) {
-		ntfs_error(sb, "$MFT/$DATA attribute not found. $MFT is "
-				"corrupt. Run chkdsk.");
-		goto put_err_out;
-	}
-	if (highest_vcn && highest_vcn != last_vcn - 1) {
-		ntfs_error(sb, "Failed to load the complete runlist for "
-				"$MFT/$DATA. Driver bug or corrupt $MFT. "
-				"Run chkdsk.");
-		ntfs_debug("highest_vcn = 0x%llx, last_vcn - 1 = 0x%llx",
-				(unsigned long long)highest_vcn,
-				(unsigned long long)last_vcn - 1);
-		goto put_err_out;
-	}
-	ntfs_attr_put_search_ctx(ctx);
-	ntfs_debug("Done.");
-	ntfs_free(m);
-
-	/*
-	 * Split the locking rules of the MFT inode from the
-	 * locking rules of other inodes:
-	 */
-	lockdep_set_class(&ni->runlist.lock, &mft_ni_runlist_lock_key);
-	lockdep_set_class(&ni->mrec_lock, &mft_ni_mrec_lock_key);
-
-	return 0;
-
-em_put_err_out:
-	ntfs_error(sb, "Couldn't find first extent of $DATA attribute in "
-			"attribute list. $MFT is corrupt. Run chkdsk.");
-put_err_out:
-	ntfs_attr_put_search_ctx(ctx);
-err_out:
-	ntfs_error(sb, "Failed. Marking inode as bad.");
-	make_bad_inode(vi);
-	ntfs_free(m);
-	return -1;
-}
-
-static void __ntfs_clear_inode(ntfs_inode *ni)
-{
-	/* Free all alocated memory. */
-	down_write(&ni->runlist.lock);
-	if (ni->runlist.rl) {
-		ntfs_free(ni->runlist.rl);
-		ni->runlist.rl = NULL;
-	}
-	up_write(&ni->runlist.lock);
-
-	if (ni->attr_list) {
-		ntfs_free(ni->attr_list);
-		ni->attr_list = NULL;
-	}
-
-	down_write(&ni->attr_list_rl.lock);
-	if (ni->attr_list_rl.rl) {
-		ntfs_free(ni->attr_list_rl.rl);
-		ni->attr_list_rl.rl = NULL;
-	}
-	up_write(&ni->attr_list_rl.lock);
-
-	if (ni->name_len && ni->name != I30) {
-		/* Catch bugs... */
-		BUG_ON(!ni->name);
-		kfree(ni->name);
-	}
-}
-
-void ntfs_clear_extent_inode(ntfs_inode *ni)
-{
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(ni->nr_extents != -1);
-
-#ifdef NTFS_RW
-	if (NInoDirty(ni)) {
-		if (!is_bad_inode(VFS_I(ni->ext.base_ntfs_ino)))
-			ntfs_error(ni->vol->sb, "Clearing dirty extent inode!  "
-					"Losing data!  This is a BUG!!!");
-		// FIXME:  Do something!!!
-	}
-#endif /* NTFS_RW */
-
-	__ntfs_clear_inode(ni);
-
-	/* Bye, bye... */
-	ntfs_destroy_extent_inode(ni);
-}
-
-/**
- * ntfs_evict_big_inode - clean up the ntfs specific part of an inode
- * @vi:		vfs inode pending annihilation
- *
- * When the VFS is going to remove an inode from memory, ntfs_clear_big_inode()
- * is called, which deallocates all memory belonging to the NTFS specific part
- * of the inode and returns.
- *
- * If the MFT record is dirty, we commit it before doing anything else.
- */
-void ntfs_evict_big_inode(struct inode *vi)
-{
-	ntfs_inode *ni = NTFS_I(vi);
-
-	truncate_inode_pages_final(&vi->i_data);
-	clear_inode(vi);
-
-#ifdef NTFS_RW
-	if (NInoDirty(ni)) {
-		bool was_bad = (is_bad_inode(vi));
-
-		/* Committing the inode also commits all extent inodes. */
-		ntfs_commit_inode(vi);
-
-		if (!was_bad && (is_bad_inode(vi) || NInoDirty(ni))) {
-			ntfs_error(vi->i_sb, "Failed to commit dirty inode "
-					"0x%lx.  Losing data!", vi->i_ino);
-			// FIXME:  Do something!!!
-		}
-	}
-#endif /* NTFS_RW */
-
-	/* No need to lock at this stage as no one else has a reference. */
-	if (ni->nr_extents > 0) {
-		int i;
-
-		for (i = 0; i < ni->nr_extents; i++)
-			ntfs_clear_extent_inode(ni->ext.extent_ntfs_inos[i]);
-		kfree(ni->ext.extent_ntfs_inos);
-	}
-
-	__ntfs_clear_inode(ni);
-
-	if (NInoAttr(ni)) {
-		/* Release the base inode if we are holding it. */
-		if (ni->nr_extents == -1) {
-			iput(VFS_I(ni->ext.base_ntfs_ino));
-			ni->nr_extents = 0;
-			ni->ext.base_ntfs_ino = NULL;
-		}
-	}
-	BUG_ON(ni->page);
-	if (!atomic_dec_and_test(&ni->count))
-		BUG();
-	return;
-}
-
-/**
- * ntfs_show_options - show mount options in /proc/mounts
- * @sf:		seq_file in which to write our mount options
- * @root:	root of the mounted tree whose mount options to display
- *
- * Called by the VFS once for each mounted ntfs volume when someone reads
- * /proc/mounts in order to display the NTFS specific mount options of each
- * mount. The mount options of fs specified by @root are written to the seq file
- * @sf and success is returned.
- */
-int ntfs_show_options(struct seq_file *sf, struct dentry *root)
-{
-	ntfs_volume *vol = NTFS_SB(root->d_sb);
-	int i;
-
-	seq_printf(sf, ",uid=%i", from_kuid_munged(&init_user_ns, vol->uid));
-	seq_printf(sf, ",gid=%i", from_kgid_munged(&init_user_ns, vol->gid));
-	if (vol->fmask == vol->dmask)
-		seq_printf(sf, ",umask=0%o", vol->fmask);
-	else {
-		seq_printf(sf, ",fmask=0%o", vol->fmask);
-		seq_printf(sf, ",dmask=0%o", vol->dmask);
-	}
-	seq_printf(sf, ",nls=%s", vol->nls_map->charset);
-	if (NVolCaseSensitive(vol))
-		seq_printf(sf, ",case_sensitive");
-	if (NVolShowSystemFiles(vol))
-		seq_printf(sf, ",show_sys_files");
-	if (!NVolSparseEnabled(vol))
-		seq_printf(sf, ",disable_sparse");
-	for (i = 0; on_errors_arr[i].val; i++) {
-		if (on_errors_arr[i].val & vol->on_errors)
-			seq_printf(sf, ",errors=%s", on_errors_arr[i].str);
-	}
-	seq_printf(sf, ",mft_zone_multiplier=%i", vol->mft_zone_multiplier);
-	return 0;
-}
-
-#ifdef NTFS_RW
-
-static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
-		"chkdsk.";
-
-/**
- * ntfs_truncate - called when the i_size of an ntfs inode is changed
- * @vi:		inode for which the i_size was changed
- *
- * We only support i_size changes for normal files at present, i.e. not
- * compressed and not encrypted.  This is enforced in ntfs_setattr(), see
- * below.
- *
- * The kernel guarantees that @vi is a regular file (S_ISREG() is true) and
- * that the change is allowed.
- *
- * This implies for us that @vi is a file inode rather than a directory, index,
- * or attribute inode as well as that @vi is a base inode.
- *
- * Returns 0 on success or -errno on error.
- *
- * Called with ->i_mutex held.
- */
-int ntfs_truncate(struct inode *vi)
-{
-	s64 new_size, old_size, nr_freed, new_alloc_size, old_alloc_size;
-	VCN highest_vcn;
-	unsigned long flags;
-	ntfs_inode *base_ni, *ni = NTFS_I(vi);
-	ntfs_volume *vol = ni->vol;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	const char *te = "  Leaving file length out of sync with i_size.";
-	int err, mp_size, size_change, alloc_change;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(S_ISDIR(vi->i_mode));
-	BUG_ON(NInoMstProtected(ni));
-	BUG_ON(ni->nr_extents < 0);
-retry_truncate:
-	/*
-	 * Lock the runlist for writing and map the mft record to ensure it is
-	 * safe to mess with the attribute runlist and sizes.
-	 */
-	down_write(&ni->runlist.lock);
-	if (!NInoAttr(ni))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	m = map_mft_record(base_ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		ntfs_error(vi->i_sb, "Failed to map mft record for inode 0x%lx "
-				"(error code %d).%s", vi->i_ino, err, te);
-		ctx = NULL;
-		m = NULL;
-		goto old_bad_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(base_ni, m);
-	if (unlikely(!ctx)) {
-		ntfs_error(vi->i_sb, "Failed to allocate a search context for "
-				"inode 0x%lx (not enough memory).%s",
-				vi->i_ino, te);
-		err = -ENOMEM;
-		goto old_bad_out;
-	}
-	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		if (err == -ENOENT) {
-			ntfs_error(vi->i_sb, "Open attribute is missing from "
-					"mft record.  Inode 0x%lx is corrupt.  "
-					"Run chkdsk.%s", vi->i_ino, te);
-			err = -EIO;
-		} else
-			ntfs_error(vi->i_sb, "Failed to lookup attribute in "
-					"inode 0x%lx (error code %d).%s",
-					vi->i_ino, err, te);
-		goto old_bad_out;
-	}
-	m = ctx->mrec;
-	a = ctx->attr;
-	/*
-	 * The i_size of the vfs inode is the new size for the attribute value.
-	 */
-	new_size = i_size_read(vi);
-	/* The current size of the attribute value is the old size. */
-	old_size = ntfs_attr_size(a);
-	/* Calculate the new allocated size. */
-	if (NInoNonResident(ni))
-		new_alloc_size = (new_size + vol->cluster_size - 1) &
-				~(s64)vol->cluster_size_mask;
-	else
-		new_alloc_size = (new_size + 7) & ~7;
-	/* The current allocated size is the old allocated size. */
-	read_lock_irqsave(&ni->size_lock, flags);
-	old_alloc_size = ni->allocated_size;
-	read_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * The change in the file size.  This will be 0 if no change, >0 if the
-	 * size is growing, and <0 if the size is shrinking.
-	 */
-	size_change = -1;
-	if (new_size - old_size >= 0) {
-		size_change = 1;
-		if (new_size == old_size)
-			size_change = 0;
-	}
-	/* As above for the allocated size. */
-	alloc_change = -1;
-	if (new_alloc_size - old_alloc_size >= 0) {
-		alloc_change = 1;
-		if (new_alloc_size == old_alloc_size)
-			alloc_change = 0;
-	}
-	/*
-	 * If neither the size nor the allocation are being changed there is
-	 * nothing to do.
-	 */
-	if (!size_change && !alloc_change)
-		goto unm_done;
-	/* If the size is changing, check if new size is allowed in $AttrDef. */
-	if (size_change) {
-		err = ntfs_attr_size_bounds_check(vol, ni->type, new_size);
-		if (unlikely(err)) {
-			if (err == -ERANGE) {
-				ntfs_error(vol->sb, "Truncate would cause the "
-						"inode 0x%lx to %simum size "
-						"for its attribute type "
-						"(0x%x).  Aborting truncate.",
-						vi->i_ino,
-						new_size > old_size ? "exceed "
-						"the max" : "go under the min",
-						le32_to_cpu(ni->type));
-				err = -EFBIG;
-			} else {
-				ntfs_error(vol->sb, "Inode 0x%lx has unknown "
-						"attribute type 0x%x.  "
-						"Aborting truncate.",
-						vi->i_ino,
-						le32_to_cpu(ni->type));
-				err = -EIO;
-			}
-			/* Reset the vfs inode size to the old size. */
-			i_size_write(vi, old_size);
-			goto err_out;
-		}
-	}
-	if (NInoCompressed(ni) || NInoEncrypted(ni)) {
-		ntfs_warning(vi->i_sb, "Changes in inode size are not "
-				"supported yet for %s files, ignoring.",
-				NInoCompressed(ni) ? "compressed" :
-				"encrypted");
-		err = -EOPNOTSUPP;
-		goto bad_out;
-	}
-	if (a->non_resident)
-		goto do_non_resident_truncate;
-	BUG_ON(NInoNonResident(ni));
-	/* Resize the attribute record to best fit the new attribute size. */
-	if (new_size < vol->mft_record_size &&
-			!ntfs_resident_attr_value_resize(m, a, new_size)) {
-		/* The resize succeeded! */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		write_lock_irqsave(&ni->size_lock, flags);
-		/* Update the sizes in the ntfs inode and all is done. */
-		ni->allocated_size = le32_to_cpu(a->length) -
-				le16_to_cpu(a->data.resident.value_offset);
-		/*
-		 * Note ntfs_resident_attr_value_resize() has already done any
-		 * necessary data clearing in the attribute record.  When the
-		 * file is being shrunk vmtruncate() will already have cleared
-		 * the top part of the last partial page, i.e. since this is
-		 * the resident case this is the page with index 0.  However,
-		 * when the file is being expanded, the page cache page data
-		 * between the old data_size, i.e. old_size, and the new_size
-		 * has not been zeroed.  Fortunately, we do not need to zero it
-		 * either since on one hand it will either already be zero due
-		 * to both read_folio and writepage clearing partial page data
-		 * beyond i_size in which case there is nothing to do or in the
-		 * case of the file being mmap()ped at the same time, POSIX
-		 * specifies that the behaviour is unspecified thus we do not
-		 * have to do anything.  This means that in our implementation
-		 * in the rare case that the file is mmap()ped and a write
-		 * occurred into the mmap()ped region just beyond the file size
-		 * and writepage has not yet been called to write out the page
-		 * (which would clear the area beyond the file size) and we now
-		 * extend the file size to incorporate this dirty region
-		 * outside the file size, a write of the page would result in
-		 * this data being written to disk instead of being cleared.
-		 * Given both POSIX and the Linux mmap(2) man page specify that
-		 * this corner case is undefined, we choose to leave it like
-		 * that as this is much simpler for us as we cannot lock the
-		 * relevant page now since we are holding too many ntfs locks
-		 * which would result in a lock reversal deadlock.
-		 */
-		ni->initialized_size = new_size;
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		goto unm_done;
-	}
-	/* If the above resize failed, this must be an attribute extension. */
-	BUG_ON(size_change < 0);
-	/*
-	 * We have to drop all the locks so we can call
-	 * ntfs_attr_make_non_resident().  This could be optimised by try-
-	 * locking the first page cache page and only if that fails dropping
-	 * the locks, locking the page, and redoing all the locking and
-	 * lookups.  While this would be a huge optimisation, it is not worth
-	 * it as this is definitely a slow code path as it only ever can happen
-	 * once for any given file.
-	 */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-	/*
-	 * Not enough space in the mft record, try to make the attribute
-	 * non-resident and if successful restart the truncation process.
-	 */
-	err = ntfs_attr_make_non_resident(ni, old_size);
-	if (likely(!err))
-		goto retry_truncate;
-	/*
-	 * Could not make non-resident.  If this is due to this not being
-	 * permitted for this attribute type or there not being enough space,
-	 * try to make other attributes non-resident.  Otherwise fail.
-	 */
-	if (unlikely(err != -EPERM && err != -ENOSPC)) {
-		ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, attribute "
-				"type 0x%x, because the conversion from "
-				"resident to non-resident attribute failed "
-				"with error code %i.", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), err);
-		if (err != -ENOMEM)
-			err = -EIO;
-		goto conv_err_out;
-	}
-	/* TODO: Not implemented from here, abort. */
-	if (err == -ENOSPC)
-		ntfs_error(vol->sb, "Not enough space in the mft record/on "
-				"disk for the non-resident attribute value.  "
-				"This case is not implemented yet.");
-	else /* if (err == -EPERM) */
-		ntfs_error(vol->sb, "This attribute type may not be "
-				"non-resident.  This case is not implemented "
-				"yet.");
-	err = -EOPNOTSUPP;
-	goto conv_err_out;
-#if 0
-	// TODO: Attempt to make other attributes non-resident.
-	if (!err)
-		goto do_resident_extend;
-	/*
-	 * Both the attribute list attribute and the standard information
-	 * attribute must remain in the base inode.  Thus, if this is one of
-	 * these attributes, we have to try to move other attributes out into
-	 * extent mft records instead.
-	 */
-	if (ni->type == AT_ATTRIBUTE_LIST ||
-			ni->type == AT_STANDARD_INFORMATION) {
-		// TODO: Attempt to move other attributes into extent mft
-		// records.
-		err = -EOPNOTSUPP;
-		if (!err)
-			goto do_resident_extend;
-		goto err_out;
-	}
-	// TODO: Attempt to move this attribute to an extent mft record, but
-	// only if it is not already the only attribute in an mft record in
-	// which case there would be nothing to gain.
-	err = -EOPNOTSUPP;
-	if (!err)
-		goto do_resident_extend;
-	/* There is nothing we can do to make enough space. )-: */
-	goto err_out;
-#endif
-do_non_resident_truncate:
-	BUG_ON(!NInoNonResident(ni));
-	if (alloc_change < 0) {
-		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
-		if (highest_vcn > 0 &&
-				old_alloc_size >> vol->cluster_size_bits >
-				highest_vcn + 1) {
-			/*
-			 * This attribute has multiple extents.  Not yet
-			 * supported.
-			 */
-			ntfs_error(vol->sb, "Cannot truncate inode 0x%lx, "
-					"attribute type 0x%x, because the "
-					"attribute is highly fragmented (it "
-					"consists of multiple extents) and "
-					"this case is not implemented yet.",
-					vi->i_ino,
-					(unsigned)le32_to_cpu(ni->type));
-			err = -EOPNOTSUPP;
-			goto bad_out;
-		}
-	}
-	/*
-	 * If the size is shrinking, need to reduce the initialized_size and
-	 * the data_size before reducing the allocation.
-	 */
-	if (size_change < 0) {
-		/*
-		 * Make the valid size smaller (i_size is already up-to-date).
-		 */
-		write_lock_irqsave(&ni->size_lock, flags);
-		if (new_size < ni->initialized_size) {
-			ni->initialized_size = new_size;
-			a->data.non_resident.initialized_size =
-					cpu_to_sle64(new_size);
-		}
-		a->data.non_resident.data_size = cpu_to_sle64(new_size);
-		write_unlock_irqrestore(&ni->size_lock, flags);
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		/* If the allocated size is not changing, we are done. */
-		if (!alloc_change)
-			goto unm_done;
-		/*
-		 * If the size is shrinking it makes no sense for the
-		 * allocation to be growing.
-		 */
-		BUG_ON(alloc_change > 0);
-	} else /* if (size_change >= 0) */ {
-		/*
-		 * The file size is growing or staying the same but the
-		 * allocation can be shrinking, growing or staying the same.
-		 */
-		if (alloc_change > 0) {
-			/*
-			 * We need to extend the allocation and possibly update
-			 * the data size.  If we are updating the data size,
-			 * since we are not touching the initialized_size we do
-			 * not need to worry about the actual data on disk.
-			 * And as far as the page cache is concerned, there
-			 * will be no pages beyond the old data size and any
-			 * partial region in the last page between the old and
-			 * new data size (or the end of the page if the new
-			 * data size is outside the page) does not need to be
-			 * modified as explained above for the resident
-			 * attribute truncate case.  To do this, we simply drop
-			 * the locks we hold and leave all the work to our
-			 * friendly helper ntfs_attr_extend_allocation().
-			 */
-			ntfs_attr_put_search_ctx(ctx);
-			unmap_mft_record(base_ni);
-			up_write(&ni->runlist.lock);
-			err = ntfs_attr_extend_allocation(ni, new_size,
-					size_change > 0 ? new_size : -1, -1);
-			/*
-			 * ntfs_attr_extend_allocation() will have done error
-			 * output already.
-			 */
-			goto done;
-		}
-		if (!alloc_change)
-			goto alloc_done;
-	}
-	/* alloc_change < 0 */
-	/* Free the clusters. */
-	nr_freed = ntfs_cluster_free(ni, new_alloc_size >>
-			vol->cluster_size_bits, -1, ctx);
-	m = ctx->mrec;
-	a = ctx->attr;
-	if (unlikely(nr_freed < 0)) {
-		ntfs_error(vol->sb, "Failed to release cluster(s) (error code "
-				"%lli).  Unmount and run chkdsk to recover "
-				"the lost cluster(s).", (long long)nr_freed);
-		NVolSetErrors(vol);
-		nr_freed = 0;
-	}
-	/* Truncate the runlist. */
-	err = ntfs_rl_truncate_nolock(vol, &ni->runlist,
-			new_alloc_size >> vol->cluster_size_bits);
-	/*
-	 * If the runlist truncation failed and/or the search context is no
-	 * longer valid, we cannot resize the attribute record or build the
-	 * mapping pairs array thus we mark the inode bad so that no access to
-	 * the freed clusters can happen.
-	 */
-	if (unlikely(err || IS_ERR(m))) {
-		ntfs_error(vol->sb, "Failed to %s (error code %li).%s",
-				IS_ERR(m) ?
-				"restore attribute search context" :
-				"truncate attribute runlist",
-				IS_ERR(m) ? PTR_ERR(m) : err, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/* Get the size for the shrunk mapping pairs array for the runlist. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, ni->runlist.rl, 0, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
-				"attribute type 0x%x, because determining the "
-				"size for the mapping pairs failed with error "
-				"code %i.%s", vi->i_ino,
-				(unsigned)le32_to_cpu(ni->type), mp_size, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/*
-	 * Shrink the attribute record for the new mapping pairs array.  Note,
-	 * this cannot fail since we are making the attribute smaller thus by
-	 * definition there is enough space to do so.
-	 */
-	err = ntfs_attr_record_resize(m, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	BUG_ON(err);
-	/*
-	 * Generate the mapping pairs array directly into the attribute record.
-	 */
-	err = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, ni->runlist.rl, 0, -1, NULL);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Cannot shrink allocation of inode 0x%lx, "
-				"attribute type 0x%x, because building the "
-				"mapping pairs failed with error code %i.%s",
-				vi->i_ino, (unsigned)le32_to_cpu(ni->type),
-				err, es);
-		err = -EIO;
-		goto bad_out;
-	}
-	/* Update the allocated/compressed size as well as the highest vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
-			vol->cluster_size_bits) - 1);
-	write_lock_irqsave(&ni->size_lock, flags);
-	ni->allocated_size = new_alloc_size;
-	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
-	if (NInoSparse(ni) || NInoCompressed(ni)) {
-		if (nr_freed) {
-			ni->itype.compressed.size -= nr_freed <<
-					vol->cluster_size_bits;
-			BUG_ON(ni->itype.compressed.size < 0);
-			a->data.non_resident.compressed_size = cpu_to_sle64(
-					ni->itype.compressed.size);
-			vi->i_blocks = ni->itype.compressed.size >> 9;
-		}
-	} else
-		vi->i_blocks = new_alloc_size >> 9;
-	write_unlock_irqrestore(&ni->size_lock, flags);
-	/*
-	 * We have shrunk the allocation.  If this is a shrinking truncate we
-	 * have already dealt with the initialized_size and the data_size above
-	 * and we are done.  If the truncate is only changing the allocation
-	 * and not the data_size, we are also done.  If this is an extending
-	 * truncate, need to extend the data_size now which is ensured by the
-	 * fact that @size_change is positive.
-	 */
-alloc_done:
-	/*
-	 * If the size is growing, need to update it now.  If it is shrinking,
-	 * we have already updated it above (before the allocation change).
-	 */
-	if (size_change > 0)
-		a->data.non_resident.data_size = cpu_to_sle64(new_size);
-	/* Ensure the modified mft record is written out. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-unm_done:
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-done:
-	/* Update the mtime and ctime on the base inode. */
-	/* normally ->truncate shouldn't update ctime or mtime,
-	 * but ntfs did before so it got a copy & paste version
-	 * of file_update_time.  one day someone should fix this
-	 * for real.
-	 */
-	if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) {
-		struct timespec64 now = current_time(VFS_I(base_ni));
-		struct timespec64 ctime = inode_get_ctime(VFS_I(base_ni));
-		struct timespec64 mtime = inode_get_mtime(VFS_I(base_ni));
-		int sync_it = 0;
-
-		if (!timespec64_equal(&mtime, &now) ||
-		    !timespec64_equal(&ctime, &now))
-			sync_it = 1;
-		inode_set_ctime_to_ts(VFS_I(base_ni), now);
-		inode_set_mtime_to_ts(VFS_I(base_ni), now);
-
-		if (sync_it)
-			mark_inode_dirty_sync(VFS_I(base_ni));
-	}
-
-	if (likely(!err)) {
-		NInoClearTruncateFailed(ni);
-		ntfs_debug("Done.");
-	}
-	return err;
-old_bad_out:
-	old_size = -1;
-bad_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP)
-		NVolSetErrors(vol);
-	if (err != -EOPNOTSUPP)
-		NInoSetTruncateFailed(ni);
-	else if (old_size >= 0)
-		i_size_write(vi, old_size);
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(base_ni);
-	up_write(&ni->runlist.lock);
-out:
-	ntfs_debug("Failed.  Returning error code %i.", err);
-	return err;
-conv_err_out:
-	if (err != -ENOMEM && err != -EOPNOTSUPP)
-		NVolSetErrors(vol);
-	if (err != -EOPNOTSUPP)
-		NInoSetTruncateFailed(ni);
-	else
-		i_size_write(vi, old_size);
-	goto out;
-}
-
-/**
- * ntfs_truncate_vfs - wrapper for ntfs_truncate() that has no return value
- * @vi:		inode for which the i_size was changed
- *
- * Wrapper for ntfs_truncate() that has no return value.
- *
- * See ntfs_truncate() description above for details.
- */
-#ifdef NTFS_RW
-void ntfs_truncate_vfs(struct inode *vi) {
-	ntfs_truncate(vi);
-}
-#endif
-
-/**
- * ntfs_setattr - called from notify_change() when an attribute is being changed
- * @idmap:	idmap of the mount the inode was found from
- * @dentry:	dentry whose attributes to change
- * @attr:	structure describing the attributes and the changes
- *
- * We have to trap VFS attempts to truncate the file described by @dentry as
- * soon as possible, because we do not implement changes in i_size yet.  So we
- * abort all i_size changes here.
- *
- * We also abort all changes of user, group, and mode as we do not implement
- * the NTFS ACLs yet.
- *
- * Called with ->i_mutex held.
- */
-int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
-		 struct iattr *attr)
-{
-	struct inode *vi = d_inode(dentry);
-	int err;
-	unsigned int ia_valid = attr->ia_valid;
-
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
-	if (err)
-		goto out;
-	/* We do not support NTFS ACLs yet. */
-	if (ia_valid & (ATTR_UID | ATTR_GID | ATTR_MODE)) {
-		ntfs_warning(vi->i_sb, "Changes in user/group/mode are not "
-				"supported yet, ignoring.");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-	if (ia_valid & ATTR_SIZE) {
-		if (attr->ia_size != i_size_read(vi)) {
-			ntfs_inode *ni = NTFS_I(vi);
-			/*
-			 * FIXME: For now we do not support resizing of
-			 * compressed or encrypted files yet.
-			 */
-			if (NInoCompressed(ni) || NInoEncrypted(ni)) {
-				ntfs_warning(vi->i_sb, "Changes in inode size "
-						"are not supported yet for "
-						"%s files, ignoring.",
-						NInoCompressed(ni) ?
-						"compressed" : "encrypted");
-				err = -EOPNOTSUPP;
-			} else {
-				truncate_setsize(vi, attr->ia_size);
-				ntfs_truncate_vfs(vi);
-			}
-			if (err || ia_valid == ATTR_SIZE)
-				goto out;
-		} else {
-			/*
-			 * We skipped the truncate but must still update
-			 * timestamps.
-			 */
-			ia_valid |= ATTR_MTIME | ATTR_CTIME;
-		}
-	}
-	if (ia_valid & ATTR_ATIME)
-		inode_set_atime_to_ts(vi, attr->ia_atime);
-	if (ia_valid & ATTR_MTIME)
-		inode_set_mtime_to_ts(vi, attr->ia_mtime);
-	if (ia_valid & ATTR_CTIME)
-		inode_set_ctime_to_ts(vi, attr->ia_ctime);
-	mark_inode_dirty(vi);
-out:
-	return err;
-}
-
-/**
- * __ntfs_write_inode - write out a dirty inode
- * @vi:		inode to write out
- * @sync:	if true, write out synchronously
- *
- * Write out a dirty inode to disk including any extent inodes if present.
- *
- * If @sync is true, commit the inode to disk and wait for io completion.  This
- * is done using write_mft_record().
- *
- * If @sync is false, just schedule the write to happen but do not wait for i/o
- * completion.  In 2.6 kernels, scheduling usually happens just by virtue of
- * marking the page (and in this case mft record) dirty but we do not implement
- * this yet as write_mft_record() largely ignores the @sync parameter and
- * always performs synchronous writes.
- *
- * Return 0 on success and -errno on error.
- */
-int __ntfs_write_inode(struct inode *vi, int sync)
-{
-	sle64 nt;
-	ntfs_inode *ni = NTFS_I(vi);
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	STANDARD_INFORMATION *si;
-	int err = 0;
-	bool modified = false;
-
-	ntfs_debug("Entering for %sinode 0x%lx.", NInoAttr(ni) ? "attr " : "",
-			vi->i_ino);
-	/*
-	 * Dirty attribute inodes are written via their real inodes so just
-	 * clean them here.  Access time updates are taken care off when the
-	 * real inode is written.
-	 */
-	if (NInoAttr(ni)) {
-		NInoClearDirty(ni);
-		ntfs_debug("Done.");
-		return 0;
-	}
-	/* Map, pin, and lock the mft record belonging to the inode. */
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	/* Update the access times in the standard information attribute. */
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (unlikely(!ctx)) {
-		err = -ENOMEM;
-		goto unm_err_out;
-	}
-	err = ntfs_attr_lookup(AT_STANDARD_INFORMATION, NULL, 0,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		ntfs_attr_put_search_ctx(ctx);
-		goto unm_err_out;
-	}
-	si = (STANDARD_INFORMATION*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	/* Update the access times if they have changed. */
-	nt = utc2ntfs(inode_get_mtime(vi));
-	if (si->last_data_change_time != nt) {
-		ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino, (long long)
-				sle64_to_cpu(si->last_data_change_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_data_change_time = nt;
-		modified = true;
-	}
-	nt = utc2ntfs(inode_get_ctime(vi));
-	if (si->last_mft_change_time != nt) {
-		ntfs_debug("Updating ctime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino, (long long)
-				sle64_to_cpu(si->last_mft_change_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_mft_change_time = nt;
-		modified = true;
-	}
-	nt = utc2ntfs(inode_get_atime(vi));
-	if (si->last_access_time != nt) {
-		ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, "
-				"new = 0x%llx", vi->i_ino,
-				(long long)sle64_to_cpu(si->last_access_time),
-				(long long)sle64_to_cpu(nt));
-		si->last_access_time = nt;
-		modified = true;
-	}
-	/*
-	 * If we just modified the standard information attribute we need to
-	 * mark the mft record it is in dirty.  We do this manually so that
-	 * mark_inode_dirty() is not called which would redirty the inode and
-	 * hence result in an infinite loop of trying to write the inode.
-	 * There is no need to mark the base inode nor the base mft record
-	 * dirty, since we are going to write this mft record below in any case
-	 * and the base mft record may actually not have been modified so it
-	 * might not need to be written out.
-	 * NOTE: It is not a problem when the inode for $MFT itself is being
-	 * written out as mark_ntfs_record_dirty() will only set I_DIRTY_PAGES
-	 * on the $MFT inode and hence __ntfs_write_inode() will not be
-	 * re-invoked because of it which in turn is ok since the dirtied mft
-	 * record will be cleaned and written out to disk below, i.e. before
-	 * this function returns.
-	 */
-	if (modified) {
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		if (!NInoTestSetDirty(ctx->ntfs_ino))
-			mark_ntfs_record_dirty(ctx->ntfs_ino->page,
-					ctx->ntfs_ino->page_ofs);
-	}
-	ntfs_attr_put_search_ctx(ctx);
-	/* Now the access times are updated, write the base mft record. */
-	if (NInoDirty(ni))
-		err = write_mft_record(ni, m, sync);
-	/* Write all attached extent mft records. */
-	mutex_lock(&ni->extent_lock);
-	if (ni->nr_extents > 0) {
-		ntfs_inode **extent_nis = ni->ext.extent_ntfs_inos;
-		int i;
-
-		ntfs_debug("Writing %i extent inodes.", ni->nr_extents);
-		for (i = 0; i < ni->nr_extents; i++) {
-			ntfs_inode *tni = extent_nis[i];
-
-			if (NInoDirty(tni)) {
-				MFT_RECORD *tm = map_mft_record(tni);
-				int ret;
-
-				if (IS_ERR(tm)) {
-					if (!err || err == -ENOMEM)
-						err = PTR_ERR(tm);
-					continue;
-				}
-				ret = write_mft_record(tni, tm, sync);
-				unmap_mft_record(tni);
-				if (unlikely(ret)) {
-					if (!err || err == -ENOMEM)
-						err = ret;
-				}
-			}
-		}
-	}
-	mutex_unlock(&ni->extent_lock);
-	unmap_mft_record(ni);
-	if (unlikely(err))
-		goto err_out;
-	ntfs_debug("Done.");
-	return 0;
-unm_err_out:
-	unmap_mft_record(ni);
-err_out:
-	if (err == -ENOMEM) {
-		ntfs_warning(vi->i_sb, "Not enough memory to write inode.  "
-				"Marking the inode dirty again, so the VFS "
-				"retries later.");
-		mark_inode_dirty(vi);
-	} else {
-		ntfs_error(vi->i_sb, "Failed (error %i):  Run chkdsk.", -err);
-		NVolSetErrors(ni->vol);
-	}
-	return err;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h
deleted file mode 100644
index 147ef4ddb691..000000000000
--- a/fs/ntfs/inode.h
+++ /dev/null
@@ -1,310 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * inode.h - Defines for inode structures NTFS Linux kernel driver. Part of
- *	     the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_INODE_H
-#define _LINUX_NTFS_INODE_H
-
-#include <linux/atomic.h>
-
-#include <linux/fs.h>
-#include <linux/list.h>
-#include <linux/mm.h>
-#include <linux/mutex.h>
-#include <linux/seq_file.h>
-
-#include "layout.h"
-#include "volume.h"
-#include "types.h"
-#include "runlist.h"
-#include "debug.h"
-
-typedef struct _ntfs_inode ntfs_inode;
-
-/*
- * The NTFS in-memory inode structure. It is just used as an extension to the
- * fields already provided in the VFS inode.
- */
-struct _ntfs_inode {
-	rwlock_t size_lock;	/* Lock serializing access to inode sizes. */
-	s64 initialized_size;	/* Copy from the attribute record. */
-	s64 allocated_size;	/* Copy from the attribute record. */
-	unsigned long state;	/* NTFS specific flags describing this inode.
-				   See ntfs_inode_state_bits below. */
-	unsigned long mft_no;	/* Number of the mft record / inode. */
-	u16 seq_no;		/* Sequence number of the mft record. */
-	atomic_t count;		/* Inode reference count for book keeping. */
-	ntfs_volume *vol;	/* Pointer to the ntfs volume of this inode. */
-	/*
-	 * If NInoAttr() is true, the below fields describe the attribute which
-	 * this fake inode belongs to. The actual inode of this attribute is
-	 * pointed to by base_ntfs_ino and nr_extents is always set to -1 (see
-	 * below). For real inodes, we also set the type (AT_DATA for files and
-	 * AT_INDEX_ALLOCATION for directories), with the name = NULL and
-	 * name_len = 0 for files and name = I30 (global constant) and
-	 * name_len = 4 for directories.
-	 */
-	ATTR_TYPE type;	/* Attribute type of this fake inode. */
-	ntfschar *name;		/* Attribute name of this fake inode. */
-	u32 name_len;		/* Attribute name length of this fake inode. */
-	runlist runlist;	/* If state has the NI_NonResident bit set,
-				   the runlist of the unnamed data attribute
-				   (if a file) or of the index allocation
-				   attribute (directory) or of the attribute
-				   described by the fake inode (if NInoAttr()).
-				   If runlist.rl is NULL, the runlist has not
-				   been read in yet or has been unmapped. If
-				   NI_NonResident is clear, the attribute is
-				   resident (file and fake inode) or there is
-				   no $I30 index allocation attribute
-				   (small directory). In the latter case
-				   runlist.rl is always NULL.*/
-	/*
-	 * The following fields are only valid for real inodes and extent
-	 * inodes.
-	 */
-	struct mutex mrec_lock;	/* Lock for serializing access to the
-				   mft record belonging to this inode. */
-	struct page *page;	/* The page containing the mft record of the
-				   inode. This should only be touched by the
-				   (un)map_mft_record*() functions. */
-	int page_ofs;		/* Offset into the page at which the mft record
-				   begins. This should only be touched by the
-				   (un)map_mft_record*() functions. */
-	/*
-	 * Attribute list support (only for use by the attribute lookup
-	 * functions). Setup during read_inode for all inodes with attribute
-	 * lists. Only valid if NI_AttrList is set in state, and attr_list_rl is
-	 * further only valid if NI_AttrListNonResident is set.
-	 */
-	u32 attr_list_size;	/* Length of attribute list value in bytes. */
-	u8 *attr_list;		/* Attribute list value itself. */
-	runlist attr_list_rl;	/* Run list for the attribute list value. */
-	union {
-		struct { /* It is a directory, $MFT, or an index inode. */
-			u32 block_size;		/* Size of an index block. */
-			u32 vcn_size;		/* Size of a vcn in this
-						   index. */
-			COLLATION_RULE collation_rule; /* The collation rule
-						   for the index. */
-			u8 block_size_bits; 	/* Log2 of the above. */
-			u8 vcn_size_bits;	/* Log2 of the above. */
-		} index;
-		struct { /* It is a compressed/sparse file/attribute inode. */
-			s64 size;		/* Copy of compressed_size from
-						   $DATA. */
-			u32 block_size;		/* Size of a compression block
-						   (cb). */
-			u8 block_size_bits;	/* Log2 of the size of a cb. */
-			u8 block_clusters;	/* Number of clusters per cb. */
-		} compressed;
-	} itype;
-	struct mutex extent_lock;	/* Lock for accessing/modifying the
-					   below . */
-	s32 nr_extents;	/* For a base mft record, the number of attached extent
-			   inodes (0 if none), for extent records and for fake
-			   inodes describing an attribute this is -1. */
-	union {		/* This union is only used if nr_extents != 0. */
-		ntfs_inode **extent_ntfs_inos;	/* For nr_extents > 0, array of
-						   the ntfs inodes of the extent
-						   mft records belonging to
-						   this base inode which have
-						   been loaded. */
-		ntfs_inode *base_ntfs_ino;	/* For nr_extents == -1, the
-						   ntfs inode of the base mft
-						   record. For fake inodes, the
-						   real (base) inode to which
-						   the attribute belongs. */
-	} ext;
-};
-
-/*
- * Defined bits for the state field in the ntfs_inode structure.
- * (f) = files only, (d) = directories only, (a) = attributes/fake inodes only
- */
-typedef enum {
-	NI_Dirty,		/* 1: Mft record needs to be written to disk. */
-	NI_AttrList,		/* 1: Mft record contains an attribute list. */
-	NI_AttrListNonResident,	/* 1: Attribute list is non-resident. Implies
-				      NI_AttrList is set. */
-
-	NI_Attr,		/* 1: Fake inode for attribute i/o.
-				   0: Real inode or extent inode. */
-
-	NI_MstProtected,	/* 1: Attribute is protected by MST fixups.
-				   0: Attribute is not protected by fixups. */
-	NI_NonResident,		/* 1: Unnamed data attr is non-resident (f).
-				   1: Attribute is non-resident (a). */
-	NI_IndexAllocPresent = NI_NonResident,	/* 1: $I30 index alloc attr is
-						   present (d). */
-	NI_Compressed,		/* 1: Unnamed data attr is compressed (f).
-				   1: Create compressed files by default (d).
-				   1: Attribute is compressed (a). */
-	NI_Encrypted,		/* 1: Unnamed data attr is encrypted (f).
-				   1: Create encrypted files by default (d).
-				   1: Attribute is encrypted (a). */
-	NI_Sparse,		/* 1: Unnamed data attr is sparse (f).
-				   1: Create sparse files by default (d).
-				   1: Attribute is sparse (a). */
-	NI_SparseDisabled,	/* 1: May not create sparse regions. */
-	NI_TruncateFailed,	/* 1: Last ntfs_truncate() call failed. */
-} ntfs_inode_state_bits;
-
-/*
- * NOTE: We should be adding dirty mft records to a list somewhere and they
- * should be independent of the (ntfs/vfs) inode structure so that an inode can
- * be removed but the record can be left dirty for syncing later.
- */
-
-/*
- * Macro tricks to expand the NInoFoo(), NInoSetFoo(), and NInoClearFoo()
- * functions.
- */
-#define NINO_FNS(flag)					\
-static inline int NIno##flag(ntfs_inode *ni)		\
-{							\
-	return test_bit(NI_##flag, &(ni)->state);	\
-}							\
-static inline void NInoSet##flag(ntfs_inode *ni)	\
-{							\
-	set_bit(NI_##flag, &(ni)->state);		\
-}							\
-static inline void NInoClear##flag(ntfs_inode *ni)	\
-{							\
-	clear_bit(NI_##flag, &(ni)->state);		\
-}
-
-/*
- * As above for NInoTestSetFoo() and NInoTestClearFoo().
- */
-#define TAS_NINO_FNS(flag)					\
-static inline int NInoTestSet##flag(ntfs_inode *ni)		\
-{								\
-	return test_and_set_bit(NI_##flag, &(ni)->state);	\
-}								\
-static inline int NInoTestClear##flag(ntfs_inode *ni)		\
-{								\
-	return test_and_clear_bit(NI_##flag, &(ni)->state);	\
-}
-
-/* Emit the ntfs inode bitops functions. */
-NINO_FNS(Dirty)
-TAS_NINO_FNS(Dirty)
-NINO_FNS(AttrList)
-NINO_FNS(AttrListNonResident)
-NINO_FNS(Attr)
-NINO_FNS(MstProtected)
-NINO_FNS(NonResident)
-NINO_FNS(IndexAllocPresent)
-NINO_FNS(Compressed)
-NINO_FNS(Encrypted)
-NINO_FNS(Sparse)
-NINO_FNS(SparseDisabled)
-NINO_FNS(TruncateFailed)
-
-/*
- * The full structure containing a ntfs_inode and a vfs struct inode. Used for
- * all real and fake inodes but not for extent inodes which lack the vfs struct
- * inode.
- */
-typedef struct {
-	ntfs_inode ntfs_inode;
-	struct inode vfs_inode;		/* The vfs inode structure. */
-} big_ntfs_inode;
-
-/**
- * NTFS_I - return the ntfs inode given a vfs inode
- * @inode:	VFS inode
- *
- * NTFS_I() returns the ntfs inode associated with the VFS @inode.
- */
-static inline ntfs_inode *NTFS_I(struct inode *inode)
-{
-	return (ntfs_inode *)container_of(inode, big_ntfs_inode, vfs_inode);
-}
-
-static inline struct inode *VFS_I(ntfs_inode *ni)
-{
-	return &((big_ntfs_inode *)ni)->vfs_inode;
-}
-
-/**
- * ntfs_attr - ntfs in memory attribute structure
- * @mft_no:	mft record number of the base mft record of this attribute
- * @name:	Unicode name of the attribute (NULL if unnamed)
- * @name_len:	length of @name in Unicode characters (0 if unnamed)
- * @type:	attribute type (see layout.h)
- *
- * This structure exists only to provide a small structure for the
- * ntfs_{attr_}iget()/ntfs_test_inode()/ntfs_init_locked_inode() mechanism.
- *
- * NOTE: Elements are ordered by size to make the structure as compact as
- * possible on all architectures.
- */
-typedef struct {
-	unsigned long mft_no;
-	ntfschar *name;
-	u32 name_len;
-	ATTR_TYPE type;
-} ntfs_attr;
-
-extern int ntfs_test_inode(struct inode *vi, void *data);
-
-extern struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no);
-extern struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type,
-		ntfschar *name, u32 name_len);
-extern struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name,
-		u32 name_len);
-
-extern struct inode *ntfs_alloc_big_inode(struct super_block *sb);
-extern void ntfs_free_big_inode(struct inode *inode);
-extern void ntfs_evict_big_inode(struct inode *vi);
-
-extern void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni);
-
-static inline void ntfs_init_big_inode(struct inode *vi)
-{
-	ntfs_inode *ni = NTFS_I(vi);
-
-	ntfs_debug("Entering.");
-	__ntfs_init_inode(vi->i_sb, ni);
-	ni->mft_no = vi->i_ino;
-}
-
-extern ntfs_inode *ntfs_new_extent_inode(struct super_block *sb,
-		unsigned long mft_no);
-extern void ntfs_clear_extent_inode(ntfs_inode *ni);
-
-extern int ntfs_read_inode_mount(struct inode *vi);
-
-extern int ntfs_show_options(struct seq_file *sf, struct dentry *root);
-
-#ifdef NTFS_RW
-
-extern int ntfs_truncate(struct inode *vi);
-extern void ntfs_truncate_vfs(struct inode *vi);
-
-extern int ntfs_setattr(struct mnt_idmap *idmap,
-			struct dentry *dentry, struct iattr *attr);
-
-extern int __ntfs_write_inode(struct inode *vi, int sync);
-
-static inline void ntfs_commit_inode(struct inode *vi)
-{
-	if (!is_bad_inode(vi))
-		__ntfs_write_inode(vi, 1);
-	return;
-}
-
-#else
-
-static inline void ntfs_truncate_vfs(struct inode *vi) {}
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_INODE_H */
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
deleted file mode 100644
index 5d4bf7a3259f..000000000000
--- a/fs/ntfs/layout.h
+++ /dev/null
@@ -1,2421 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * layout.h - All NTFS associated on-disk structures. Part of the Linux-NTFS
- *	      project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_LAYOUT_H
-#define _LINUX_NTFS_LAYOUT_H
-
-#include <linux/types.h>
-#include <linux/bitops.h>
-#include <linux/list.h>
-#include <asm/byteorder.h>
-
-#include "types.h"
-
-/* The NTFS oem_id "NTFS    " */
-#define magicNTFS	cpu_to_le64(0x202020205346544eULL)
-
-/*
- * Location of bootsector on partition:
- *	The standard NTFS_BOOT_SECTOR is on sector 0 of the partition.
- *	On NT4 and above there is one backup copy of the boot sector to
- *	be found on the last sector of the partition (not normally accessible
- *	from within Windows as the bootsector contained number of sectors
- *	value is one less than the actual value!).
- *	On versions of NT 3.51 and earlier, the backup copy was located at
- *	number of sectors/2 (integer divide), i.e. in the middle of the volume.
- */
-
-/*
- * BIOS parameter block (bpb) structure.
- */
-typedef struct {
-	le16 bytes_per_sector;		/* Size of a sector in bytes. */
-	u8  sectors_per_cluster;	/* Size of a cluster in sectors. */
-	le16 reserved_sectors;		/* zero */
-	u8  fats;			/* zero */
-	le16 root_entries;		/* zero */
-	le16 sectors;			/* zero */
-	u8  media_type;			/* 0xf8 = hard disk */
-	le16 sectors_per_fat;		/* zero */
-	le16 sectors_per_track;		/* irrelevant */
-	le16 heads;			/* irrelevant */
-	le32 hidden_sectors;		/* zero */
-	le32 large_sectors;		/* zero */
-} __attribute__ ((__packed__)) BIOS_PARAMETER_BLOCK;
-
-/*
- * NTFS boot sector structure.
- */
-typedef struct {
-	u8  jump[3];			/* Irrelevant (jump to boot up code).*/
-	le64 oem_id;			/* Magic "NTFS    ". */
-	BIOS_PARAMETER_BLOCK bpb;	/* See BIOS_PARAMETER_BLOCK. */
-	u8  unused[4];			/* zero, NTFS diskedit.exe states that
-					   this is actually:
-						__u8 physical_drive;	// 0x80
-						__u8 current_head;	// zero
-						__u8 extended_boot_signature;
-									// 0x80
-						__u8 unused;		// zero
-					 */
-/*0x28*/sle64 number_of_sectors;	/* Number of sectors in volume. Gives
-					   maximum volume size of 2^63 sectors.
-					   Assuming standard sector size of 512
-					   bytes, the maximum byte size is
-					   approx. 4.7x10^21 bytes. (-; */
-	sle64 mft_lcn;			/* Cluster location of mft data. */
-	sle64 mftmirr_lcn;		/* Cluster location of copy of mft. */
-	s8  clusters_per_mft_record;	/* Mft record size in clusters. */
-	u8  reserved0[3];		/* zero */
-	s8  clusters_per_index_record;	/* Index block size in clusters. */
-	u8  reserved1[3];		/* zero */
-	le64 volume_serial_number;	/* Irrelevant (serial number). */
-	le32 checksum;			/* Boot sector checksum. */
-/*0x54*/u8  bootstrap[426];		/* Irrelevant (boot up code). */
-	le16 end_of_sector_marker;	/* End of bootsector magic. Always is
-					   0xaa55 in little endian. */
-/* sizeof() = 512 (0x200) bytes */
-} __attribute__ ((__packed__)) NTFS_BOOT_SECTOR;
-
-/*
- * Magic identifiers present at the beginning of all ntfs record containing
- * records (like mft records for example).
- */
-enum {
-	/* Found in $MFT/$DATA. */
-	magic_FILE = cpu_to_le32(0x454c4946), /* Mft entry. */
-	magic_INDX = cpu_to_le32(0x58444e49), /* Index buffer. */
-	magic_HOLE = cpu_to_le32(0x454c4f48), /* ? (NTFS 3.0+?) */
-
-	/* Found in $LogFile/$DATA. */
-	magic_RSTR = cpu_to_le32(0x52545352), /* Restart page. */
-	magic_RCRD = cpu_to_le32(0x44524352), /* Log record page. */
-
-	/* Found in $LogFile/$DATA.  (May be found in $MFT/$DATA, also?) */
-	magic_CHKD = cpu_to_le32(0x444b4843), /* Modified by chkdsk. */
-
-	/* Found in all ntfs record containing records. */
-	magic_BAAD = cpu_to_le32(0x44414142), /* Failed multi sector
-						       transfer was detected. */
-	/*
-	 * Found in $LogFile/$DATA when a page is full of 0xff bytes and is
-	 * thus not initialized.  Page must be initialized before using it.
-	 */
-	magic_empty = cpu_to_le32(0xffffffff) /* Record is empty. */
-};
-
-typedef le32 NTFS_RECORD_TYPE;
-
-/*
- * Generic magic comparison macros. Finally found a use for the ## preprocessor
- * operator! (-8
- */
-
-static inline bool __ntfs_is_magic(le32 x, NTFS_RECORD_TYPE r)
-{
-	return (x == r);
-}
-#define ntfs_is_magic(x, m)	__ntfs_is_magic(x, magic_##m)
-
-static inline bool __ntfs_is_magicp(le32 *p, NTFS_RECORD_TYPE r)
-{
-	return (*p == r);
-}
-#define ntfs_is_magicp(p, m)	__ntfs_is_magicp(p, magic_##m)
-
-/*
- * Specialised magic comparison macros for the NTFS_RECORD_TYPEs defined above.
- */
-#define ntfs_is_file_record(x)		( ntfs_is_magic (x, FILE) )
-#define ntfs_is_file_recordp(p)		( ntfs_is_magicp(p, FILE) )
-#define ntfs_is_mft_record(x)		( ntfs_is_file_record (x) )
-#define ntfs_is_mft_recordp(p)		( ntfs_is_file_recordp(p) )
-#define ntfs_is_indx_record(x)		( ntfs_is_magic (x, INDX) )
-#define ntfs_is_indx_recordp(p)		( ntfs_is_magicp(p, INDX) )
-#define ntfs_is_hole_record(x)		( ntfs_is_magic (x, HOLE) )
-#define ntfs_is_hole_recordp(p)		( ntfs_is_magicp(p, HOLE) )
-
-#define ntfs_is_rstr_record(x)		( ntfs_is_magic (x, RSTR) )
-#define ntfs_is_rstr_recordp(p)		( ntfs_is_magicp(p, RSTR) )
-#define ntfs_is_rcrd_record(x)		( ntfs_is_magic (x, RCRD) )
-#define ntfs_is_rcrd_recordp(p)		( ntfs_is_magicp(p, RCRD) )
-
-#define ntfs_is_chkd_record(x)		( ntfs_is_magic (x, CHKD) )
-#define ntfs_is_chkd_recordp(p)		( ntfs_is_magicp(p, CHKD) )
-
-#define ntfs_is_baad_record(x)		( ntfs_is_magic (x, BAAD) )
-#define ntfs_is_baad_recordp(p)		( ntfs_is_magicp(p, BAAD) )
-
-#define ntfs_is_empty_record(x)		( ntfs_is_magic (x, empty) )
-#define ntfs_is_empty_recordp(p)	( ntfs_is_magicp(p, empty) )
-
-/*
- * The Update Sequence Array (usa) is an array of the le16 values which belong
- * to the end of each sector protected by the update sequence record in which
- * this array is contained. Note that the first entry is the Update Sequence
- * Number (usn), a cyclic counter of how many times the protected record has
- * been written to disk. The values 0 and -1 (ie. 0xffff) are not used. All
- * last le16's of each sector have to be equal to the usn (during reading) or
- * are set to it (during writing). If they are not, an incomplete multi sector
- * transfer has occurred when the data was written.
- * The maximum size for the update sequence array is fixed to:
- *	maximum size = usa_ofs + (usa_count * 2) = 510 bytes
- * The 510 bytes comes from the fact that the last le16 in the array has to
- * (obviously) finish before the last le16 of the first 512-byte sector.
- * This formula can be used as a consistency check in that usa_ofs +
- * (usa_count * 2) has to be less than or equal to 510.
- */
-typedef struct {
-	NTFS_RECORD_TYPE magic;	/* A four-byte magic identifying the record
-				   type and/or status. */
-	le16 usa_ofs;		/* Offset to the Update Sequence Array (usa)
-				   from the start of the ntfs record. */
-	le16 usa_count;		/* Number of le16 sized entries in the usa
-				   including the Update Sequence Number (usn),
-				   thus the number of fixups is the usa_count
-				   minus 1. */
-} __attribute__ ((__packed__)) NTFS_RECORD;
-
-/*
- * System files mft record numbers. All these files are always marked as used
- * in the bitmap attribute of the mft; presumably in order to avoid accidental
- * allocation for random other mft records. Also, the sequence number for each
- * of the system files is always equal to their mft record number and it is
- * never modified.
- */
-typedef enum {
-	FILE_MFT       = 0,	/* Master file table (mft). Data attribute
-				   contains the entries and bitmap attribute
-				   records which ones are in use (bit==1). */
-	FILE_MFTMirr   = 1,	/* Mft mirror: copy of first four mft records
-				   in data attribute. If cluster size > 4kiB,
-				   copy of first N mft records, with
-					N = cluster_size / mft_record_size. */
-	FILE_LogFile   = 2,	/* Journalling log in data attribute. */
-	FILE_Volume    = 3,	/* Volume name attribute and volume information
-				   attribute (flags and ntfs version). Windows
-				   refers to this file as volume DASD (Direct
-				   Access Storage Device). */
-	FILE_AttrDef   = 4,	/* Array of attribute definitions in data
-				   attribute. */
-	FILE_root      = 5,	/* Root directory. */
-	FILE_Bitmap    = 6,	/* Allocation bitmap of all clusters (lcns) in
-				   data attribute. */
-	FILE_Boot      = 7,	/* Boot sector (always at cluster 0) in data
-				   attribute. */
-	FILE_BadClus   = 8,	/* Contains all bad clusters in the non-resident
-				   data attribute. */
-	FILE_Secure    = 9,	/* Shared security descriptors in data attribute
-				   and two indexes into the descriptors.
-				   Appeared in Windows 2000. Before that, this
-				   file was named $Quota but was unused. */
-	FILE_UpCase    = 10,	/* Uppercase equivalents of all 65536 Unicode
-				   characters in data attribute. */
-	FILE_Extend    = 11,	/* Directory containing other system files (eg.
-				   $ObjId, $Quota, $Reparse and $UsnJrnl). This
-				   is new to NTFS3.0. */
-	FILE_reserved12 = 12,	/* Reserved for future use (records 12-15). */
-	FILE_reserved13 = 13,
-	FILE_reserved14 = 14,
-	FILE_reserved15 = 15,
-	FILE_first_user = 16,	/* First user file, used as test limit for
-				   whether to allow opening a file or not. */
-} NTFS_SYSTEM_FILES;
-
-/*
- * These are the so far known MFT_RECORD_* flags (16-bit) which contain
- * information about the mft record in which they are present.
- */
-enum {
-	MFT_RECORD_IN_USE	= cpu_to_le16(0x0001),
-	MFT_RECORD_IS_DIRECTORY = cpu_to_le16(0x0002),
-} __attribute__ ((__packed__));
-
-typedef le16 MFT_RECORD_FLAGS;
-
-/*
- * mft references (aka file references or file record segment references) are
- * used whenever a structure needs to refer to a record in the mft.
- *
- * A reference consists of a 48-bit index into the mft and a 16-bit sequence
- * number used to detect stale references.
- *
- * For error reporting purposes we treat the 48-bit index as a signed quantity.
- *
- * The sequence number is a circular counter (skipping 0) describing how many
- * times the referenced mft record has been (re)used. This has to match the
- * sequence number of the mft record being referenced, otherwise the reference
- * is considered stale and removed (FIXME: only ntfsck or the driver itself?).
- *
- * If the sequence number is zero it is assumed that no sequence number
- * consistency checking should be performed.
- *
- * FIXME: Since inodes are 32-bit as of now, the driver needs to always check
- * for high_part being 0 and if not either BUG(), cause a panic() or handle
- * the situation in some other way. This shouldn't be a problem as a volume has
- * to become HUGE in order to need more than 32-bits worth of mft records.
- * Assuming the standard mft record size of 1kb only the records (never mind
- * the non-resident attributes, etc.) would require 4Tb of space on their own
- * for the first 32 bits worth of records. This is only if some strange person
- * doesn't decide to foul play and make the mft sparse which would be a really
- * horrible thing to do as it would trash our current driver implementation. )-:
- * Do I hear screams "we want 64-bit inodes!" ?!? (-;
- *
- * FIXME: The mft zone is defined as the first 12% of the volume. This space is
- * reserved so that the mft can grow contiguously and hence doesn't become
- * fragmented. Volume free space includes the empty part of the mft zone and
- * when the volume's free 88% are used up, the mft zone is shrunk by a factor
- * of 2, thus making more space available for more files/data. This process is
- * repeated every time there is no more free space except for the mft zone until
- * there really is no more free space.
- */
-
-/*
- * Typedef the MFT_REF as a 64-bit value for easier handling.
- * Also define two unpacking macros to get to the reference (MREF) and
- * sequence number (MSEQNO) respectively.
- * The _LE versions are to be applied on little endian MFT_REFs.
- * Note: The _LE versions will return a CPU endian formatted value!
- */
-#define MFT_REF_MASK_CPU 0x0000ffffffffffffULL
-#define MFT_REF_MASK_LE cpu_to_le64(MFT_REF_MASK_CPU)
-
-typedef u64 MFT_REF;
-typedef le64 leMFT_REF;
-
-#define MK_MREF(m, s)	((MFT_REF)(((MFT_REF)(s) << 48) |		\
-					((MFT_REF)(m) & MFT_REF_MASK_CPU)))
-#define MK_LE_MREF(m, s) cpu_to_le64(MK_MREF(m, s))
-
-#define MREF(x)		((unsigned long)((x) & MFT_REF_MASK_CPU))
-#define MSEQNO(x)	((u16)(((x) >> 48) & 0xffff))
-#define MREF_LE(x)	((unsigned long)(le64_to_cpu(x) & MFT_REF_MASK_CPU))
-#define MSEQNO_LE(x)	((u16)((le64_to_cpu(x) >> 48) & 0xffff))
-
-#define IS_ERR_MREF(x)	(((x) & 0x0000800000000000ULL) ? true : false)
-#define ERR_MREF(x)	((u64)((s64)(x)))
-#define MREF_ERR(x)	((int)((s64)(x)))
-
-/*
- * The mft record header present at the beginning of every record in the mft.
- * This is followed by a sequence of variable length attribute records which
- * is terminated by an attribute of type AT_END which is a truncated attribute
- * in that it only consists of the attribute type code AT_END and none of the
- * other members of the attribute structure are present.
- */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
-	le16 usa_count;		/* See NTFS_RECORD definition above. */
-
-/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
-				   Changed every time the record is modified. */
-/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
-				   reused. (See description for MFT_REF
-				   above.) NOTE: The increment (skipping zero)
-				   is done when the file is deleted. NOTE: If
-				   this is zero it is left zero. */
-/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
-				   directory entries referencing this record.
-				   NOTE: Only used in mft base records.
-				   NOTE: When deleting a directory entry we
-				   check the link_count and if it is 1 we
-				   delete the file. Otherwise we delete the
-				   FILE_NAME_ATTR being referenced by the
-				   directory entry from the mft record and
-				   decrement the link_count.
-				   FIXME: Careful with Win32 + DOS names! */
-/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
-				   mft record from the start of the mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
-				   is deleted, the MFT_RECORD_IN_USE flag is
-				   set to zero. */
-/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
-				   record. This should be equal to the mft
-				   record size. */
-/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
-				   When it is not zero it is a mft reference
-				   pointing to the base mft record to which
-				   this record belongs (this is then used to
-				   locate the attribute list attribute present
-				   in the base record which describes this
-				   extension record and hence might need
-				   modification when the extension record
-				   itself is modified, also locating the
-				   attribute list also means finding the other
-				   potential extents, belonging to the non-base
-				   mft record). */
-/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
-				   the next attribute added to this mft record.
-				   NOTE: Incremented each time after it is used.
-				   NOTE: Every time the mft record is reused
-				   this number is set to zero.  NOTE: The first
-				   instance number is always 0. */
-/* The below fields are specific to NTFS 3.1+ (Windows XP and above): */
-/* 42*/ le16 reserved;		/* Reserved/alignment. */
-/* 44*/ le32 mft_record_number;	/* Number of this mft record. */
-/* sizeof() = 48 bytes */
-/*
- * When (re)using the mft record, we place the update sequence array at this
- * offset, i.e. before we start with the attributes.  This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work.  As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading we obviously use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) MFT_RECORD;
-
-/* This is the version without the NTFS 3.1+ specific fields. */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
-	le16 usa_count;		/* See NTFS_RECORD definition above. */
-
-/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
-				   Changed every time the record is modified. */
-/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
-				   reused. (See description for MFT_REF
-				   above.) NOTE: The increment (skipping zero)
-				   is done when the file is deleted. NOTE: If
-				   this is zero it is left zero. */
-/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
-				   directory entries referencing this record.
-				   NOTE: Only used in mft base records.
-				   NOTE: When deleting a directory entry we
-				   check the link_count and if it is 1 we
-				   delete the file. Otherwise we delete the
-				   FILE_NAME_ATTR being referenced by the
-				   directory entry from the mft record and
-				   decrement the link_count.
-				   FIXME: Careful with Win32 + DOS names! */
-/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
-				   mft record from the start of the mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
-				   is deleted, the MFT_RECORD_IN_USE flag is
-				   set to zero. */
-/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
-				   NOTE: Must be aligned to 8-byte boundary. */
-/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
-				   record. This should be equal to the mft
-				   record size. */
-/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
-				   When it is not zero it is a mft reference
-				   pointing to the base mft record to which
-				   this record belongs (this is then used to
-				   locate the attribute list attribute present
-				   in the base record which describes this
-				   extension record and hence might need
-				   modification when the extension record
-				   itself is modified, also locating the
-				   attribute list also means finding the other
-				   potential extents, belonging to the non-base
-				   mft record). */
-/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
-				   the next attribute added to this mft record.
-				   NOTE: Incremented each time after it is used.
-				   NOTE: Every time the mft record is reused
-				   this number is set to zero.  NOTE: The first
-				   instance number is always 0. */
-/* sizeof() = 42 bytes */
-/*
- * When (re)using the mft record, we place the update sequence array at this
- * offset, i.e. before we start with the attributes.  This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work.  As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading we obviously use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) MFT_RECORD_OLD;
-
-/*
- * System defined attributes (32-bit).  Each attribute type has a corresponding
- * attribute name (Unicode string of maximum 64 character length) as described
- * by the attribute definitions present in the data attribute of the $AttrDef
- * system file.  On NTFS 3.0 volumes the names are just as the types are named
- * in the below defines exchanging AT_ for the dollar sign ($).  If that is not
- * a revealing choice of symbol I do not know what is... (-;
- */
-enum {
-	AT_UNUSED			= cpu_to_le32(         0),
-	AT_STANDARD_INFORMATION		= cpu_to_le32(      0x10),
-	AT_ATTRIBUTE_LIST		= cpu_to_le32(      0x20),
-	AT_FILE_NAME			= cpu_to_le32(      0x30),
-	AT_OBJECT_ID			= cpu_to_le32(      0x40),
-	AT_SECURITY_DESCRIPTOR		= cpu_to_le32(      0x50),
-	AT_VOLUME_NAME			= cpu_to_le32(      0x60),
-	AT_VOLUME_INFORMATION		= cpu_to_le32(      0x70),
-	AT_DATA				= cpu_to_le32(      0x80),
-	AT_INDEX_ROOT			= cpu_to_le32(      0x90),
-	AT_INDEX_ALLOCATION		= cpu_to_le32(      0xa0),
-	AT_BITMAP			= cpu_to_le32(      0xb0),
-	AT_REPARSE_POINT		= cpu_to_le32(      0xc0),
-	AT_EA_INFORMATION		= cpu_to_le32(      0xd0),
-	AT_EA				= cpu_to_le32(      0xe0),
-	AT_PROPERTY_SET			= cpu_to_le32(      0xf0),
-	AT_LOGGED_UTILITY_STREAM	= cpu_to_le32(     0x100),
-	AT_FIRST_USER_DEFINED_ATTRIBUTE	= cpu_to_le32(    0x1000),
-	AT_END				= cpu_to_le32(0xffffffff)
-};
-
-typedef le32 ATTR_TYPE;
-
-/*
- * The collation rules for sorting views/indexes/etc (32-bit).
- *
- * COLLATION_BINARY - Collate by binary compare where the first byte is most
- *	significant.
- * COLLATION_UNICODE_STRING - Collate Unicode strings by comparing their binary
- *	Unicode values, except that when a character can be uppercased, the
- *	upper case value collates before the lower case one.
- * COLLATION_FILE_NAME - Collate file names as Unicode strings. The collation
- *	is done very much like COLLATION_UNICODE_STRING. In fact I have no idea
- *	what the difference is. Perhaps the difference is that file names
- *	would treat some special characters in an odd way (see
- *	unistr.c::ntfs_collate_names() and unistr.c::legal_ansi_char_array[]
- *	for what I mean but COLLATION_UNICODE_STRING would not give any special
- *	treatment to any characters at all, but this is speculation.
- * COLLATION_NTOFS_ULONG - Sorting is done according to ascending le32 key
- *	values. E.g. used for $SII index in FILE_Secure, which sorts by
- *	security_id (le32).
- * COLLATION_NTOFS_SID - Sorting is done according to ascending SID values.
- *	E.g. used for $O index in FILE_Extend/$Quota.
- * COLLATION_NTOFS_SECURITY_HASH - Sorting is done first by ascending hash
- *	values and second by ascending security_id values. E.g. used for $SDH
- *	index in FILE_Secure.
- * COLLATION_NTOFS_ULONGS - Sorting is done according to a sequence of ascending
- *	le32 key values. E.g. used for $O index in FILE_Extend/$ObjId, which
- *	sorts by object_id (16-byte), by splitting up the object_id in four
- *	le32 values and using them as individual keys. E.g. take the following
- *	two security_ids, stored as follows on disk:
- *		1st: a1 61 65 b7 65 7b d4 11 9e 3d 00 e0 81 10 42 59
- *		2nd: 38 14 37 d2 d2 f3 d4 11 a5 21 c8 6b 79 b1 97 45
- *	To compare them, they are split into four le32 values each, like so:
- *		1st: 0xb76561a1 0x11d47b65 0xe0003d9e 0x59421081
- *		2nd: 0xd2371438 0x11d4f3d2 0x6bc821a5 0x4597b179
- *	Now, it is apparent why the 2nd object_id collates after the 1st: the
- *	first le32 value of the 1st object_id is less than the first le32 of
- *	the 2nd object_id. If the first le32 values of both object_ids were
- *	equal then the second le32 values would be compared, etc.
- */
-enum {
-	COLLATION_BINARY		= cpu_to_le32(0x00),
-	COLLATION_FILE_NAME		= cpu_to_le32(0x01),
-	COLLATION_UNICODE_STRING	= cpu_to_le32(0x02),
-	COLLATION_NTOFS_ULONG		= cpu_to_le32(0x10),
-	COLLATION_NTOFS_SID		= cpu_to_le32(0x11),
-	COLLATION_NTOFS_SECURITY_HASH	= cpu_to_le32(0x12),
-	COLLATION_NTOFS_ULONGS		= cpu_to_le32(0x13),
-};
-
-typedef le32 COLLATION_RULE;
-
-/*
- * The flags (32-bit) describing attribute properties in the attribute
- * definition structure.  FIXME: This information is based on Regis's
- * information and, according to him, it is not certain and probably
- * incomplete.  The INDEXABLE flag is fairly certainly correct as only the file
- * name attribute has this flag set and this is the only attribute indexed in
- * NT4.
- */
-enum {
-	ATTR_DEF_INDEXABLE	= cpu_to_le32(0x02), /* Attribute can be
-					indexed. */
-	ATTR_DEF_MULTIPLE	= cpu_to_le32(0x04), /* Attribute type
-					can be present multiple times in the
-					mft records of an inode. */
-	ATTR_DEF_NOT_ZERO	= cpu_to_le32(0x08), /* Attribute value
-					must contain at least one non-zero
-					byte. */
-	ATTR_DEF_INDEXED_UNIQUE	= cpu_to_le32(0x10), /* Attribute must be
-					indexed and the attribute value must be
-					unique for the attribute type in all of
-					the mft records of an inode. */
-	ATTR_DEF_NAMED_UNIQUE	= cpu_to_le32(0x20), /* Attribute must be
-					named and the name must be unique for
-					the attribute type in all of the mft
-					records of an inode. */
-	ATTR_DEF_RESIDENT	= cpu_to_le32(0x40), /* Attribute must be
-					resident. */
-	ATTR_DEF_ALWAYS_LOG	= cpu_to_le32(0x80), /* Always log
-					modifications to this attribute,
-					regardless of whether it is resident or
-					non-resident.  Without this, only log
-					modifications if the attribute is
-					resident. */
-};
-
-typedef le32 ATTR_DEF_FLAGS;
-
-/*
- * The data attribute of FILE_AttrDef contains a sequence of attribute
- * definitions for the NTFS volume. With this, it is supposed to be safe for an
- * older NTFS driver to mount a volume containing a newer NTFS version without
- * damaging it (that's the theory. In practice it's: not damaging it too much).
- * Entries are sorted by attribute type. The flags describe whether the
- * attribute can be resident/non-resident and possibly other things, but the
- * actual bits are unknown.
- */
-typedef struct {
-/*hex ofs*/
-/*  0*/	ntfschar name[0x40];		/* Unicode name of the attribute. Zero
-					   terminated. */
-/* 80*/	ATTR_TYPE type;			/* Type of the attribute. */
-/* 84*/	le32 display_rule;		/* Default display rule.
-					   FIXME: What does it mean? (AIA) */
-/* 88*/ COLLATION_RULE collation_rule;	/* Default collation rule. */
-/* 8c*/	ATTR_DEF_FLAGS flags;		/* Flags describing the attribute. */
-/* 90*/	sle64 min_size;			/* Optional minimum attribute size. */
-/* 98*/	sle64 max_size;			/* Maximum size of attribute. */
-/* sizeof() = 0xa0 or 160 bytes */
-} __attribute__ ((__packed__)) ATTR_DEF;
-
-/*
- * Attribute flags (16-bit).
- */
-enum {
-	ATTR_IS_COMPRESSED    = cpu_to_le16(0x0001),
-	ATTR_COMPRESSION_MASK = cpu_to_le16(0x00ff), /* Compression method
-							      mask.  Also, first
-							      illegal value. */
-	ATTR_IS_ENCRYPTED     = cpu_to_le16(0x4000),
-	ATTR_IS_SPARSE	      = cpu_to_le16(0x8000),
-} __attribute__ ((__packed__));
-
-typedef le16 ATTR_FLAGS;
-
-/*
- * Attribute compression.
- *
- * Only the data attribute is ever compressed in the current ntfs driver in
- * Windows. Further, compression is only applied when the data attribute is
- * non-resident. Finally, to use compression, the maximum allowed cluster size
- * on a volume is 4kib.
- *
- * The compression method is based on independently compressing blocks of X
- * clusters, where X is determined from the compression_unit value found in the
- * non-resident attribute record header (more precisely: X = 2^compression_unit
- * clusters). On Windows NT/2k, X always is 16 clusters (compression_unit = 4).
- *
- * There are three different cases of how a compression block of X clusters
- * can be stored:
- *
- *   1) The data in the block is all zero (a sparse block):
- *	  This is stored as a sparse block in the runlist, i.e. the runlist
- *	  entry has length = X and lcn = -1. The mapping pairs array actually
- *	  uses a delta_lcn value length of 0, i.e. delta_lcn is not present at
- *	  all, which is then interpreted by the driver as lcn = -1.
- *	  NOTE: Even uncompressed files can be sparse on NTFS 3.0 volumes, then
- *	  the same principles apply as above, except that the length is not
- *	  restricted to being any particular value.
- *
- *   2) The data in the block is not compressed:
- *	  This happens when compression doesn't reduce the size of the block
- *	  in clusters. I.e. if compression has a small effect so that the
- *	  compressed data still occupies X clusters, then the uncompressed data
- *	  is stored in the block.
- *	  This case is recognised by the fact that the runlist entry has
- *	  length = X and lcn >= 0. The mapping pairs array stores this as
- *	  normal with a run length of X and some specific delta_lcn, i.e.
- *	  delta_lcn has to be present.
- *
- *   3) The data in the block is compressed:
- *	  The common case. This case is recognised by the fact that the run
- *	  list entry has length L < X and lcn >= 0. The mapping pairs array
- *	  stores this as normal with a run length of X and some specific
- *	  delta_lcn, i.e. delta_lcn has to be present. This runlist entry is
- *	  immediately followed by a sparse entry with length = X - L and
- *	  lcn = -1. The latter entry is to make up the vcn counting to the
- *	  full compression block size X.
- *
- * In fact, life is more complicated because adjacent entries of the same type
- * can be coalesced. This means that one has to keep track of the number of
- * clusters handled and work on a basis of X clusters at a time being one
- * block. An example: if length L > X this means that this particular runlist
- * entry contains a block of length X and part of one or more blocks of length
- * L - X. Another example: if length L < X, this does not necessarily mean that
- * the block is compressed as it might be that the lcn changes inside the block
- * and hence the following runlist entry describes the continuation of the
- * potentially compressed block. The block would be compressed if the
- * following runlist entry describes at least X - L sparse clusters, thus
- * making up the compression block length as described in point 3 above. (Of
- * course, there can be several runlist entries with small lengths so that the
- * sparse entry does not follow the first data containing entry with
- * length < X.)
- *
- * NOTE: At the end of the compressed attribute value, there most likely is not
- * just the right amount of data to make up a compression block, thus this data
- * is not even attempted to be compressed. It is just stored as is, unless
- * the number of clusters it occupies is reduced when compressed in which case
- * it is stored as a compressed compression block, complete with sparse
- * clusters at the end.
- */
-
-/*
- * Flags of resident attributes (8-bit).
- */
-enum {
-	RESIDENT_ATTR_IS_INDEXED = 0x01, /* Attribute is referenced in an index
-					    (has implications for deleting and
-					    modifying the attribute). */
-} __attribute__ ((__packed__));
-
-typedef u8 RESIDENT_ATTR_FLAGS;
-
-/*
- * Attribute record header. Always aligned to 8-byte boundary.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ATTR_TYPE type;		/* The (32-bit) type of the attribute. */
-/*  4*/	le32 length;		/* Byte size of the resident part of the
-				   attribute (aligned to 8-byte boundary).
-				   Used to get to the next attribute. */
-/*  8*/	u8 non_resident;	/* If 0, attribute is resident.
-				   If 1, attribute is non-resident. */
-/*  9*/	u8 name_length;		/* Unicode character size of name of attribute.
-				   0 if unnamed. */
-/* 10*/	le16 name_offset;	/* If name_length != 0, the byte offset to the
-				   beginning of the name from the attribute
-				   record. Note that the name is stored as a
-				   Unicode string. When creating, place offset
-				   just at the end of the record header. Then,
-				   follow with attribute value or mapping pairs
-				   array, resident and non-resident attributes
-				   respectively, aligning to an 8-byte
-				   boundary. */
-/* 12*/	ATTR_FLAGS flags;	/* Flags describing the attribute. */
-/* 14*/	le16 instance;		/* The instance of this attribute record. This
-				   number is unique within this mft record (see
-				   MFT_RECORD/next_attribute_instance notes in
-				   mft.h for more details). */
-/* 16*/	union {
-		/* Resident attributes. */
-		struct {
-/* 16 */		le32 value_length;/* Byte size of attribute value. */
-/* 20 */		le16 value_offset;/* Byte offset of the attribute
-					     value from the start of the
-					     attribute record. When creating,
-					     align to 8-byte boundary if we
-					     have a name present as this might
-					     not have a length of a multiple
-					     of 8-bytes. */
-/* 22 */		RESIDENT_ATTR_FLAGS flags; /* See above. */
-/* 23 */		s8 reserved;	  /* Reserved/alignment to 8-byte
-					     boundary. */
-		} __attribute__ ((__packed__)) resident;
-		/* Non-resident attributes. */
-		struct {
-/* 16*/			leVCN lowest_vcn;/* Lowest valid virtual cluster number
-				for this portion of the attribute value or
-				0 if this is the only extent (usually the
-				case). - Only when an attribute list is used
-				does lowest_vcn != 0 ever occur. */
-/* 24*/			leVCN highest_vcn;/* Highest valid vcn of this extent of
-				the attribute value. - Usually there is only one
-				portion, so this usually equals the attribute
-				value size in clusters minus 1. Can be -1 for
-				zero length files. Can be 0 for "single extent"
-				attributes. */
-/* 32*/			le16 mapping_pairs_offset; /* Byte offset from the
-				beginning of the structure to the mapping pairs
-				array which contains the mappings between the
-				vcns and the logical cluster numbers (lcns).
-				When creating, place this at the end of this
-				record header aligned to 8-byte boundary. */
-/* 34*/			u8 compression_unit; /* The compression unit expressed
-				as the log to the base 2 of the number of
-				clusters in a compression unit.  0 means not
-				compressed.  (This effectively limits the
-				compression unit size to be a power of two
-				clusters.)  WinNT4 only uses a value of 4.
-				Sparse files have this set to 0 on XPSP2. */
-/* 35*/			u8 reserved[5];		/* Align to 8-byte boundary. */
-/* The sizes below are only used when lowest_vcn is zero, as otherwise it would
-   be difficult to keep them up-to-date.*/
-/* 40*/			sle64 allocated_size;	/* Byte size of disk space
-				allocated to hold the attribute value. Always
-				is a multiple of the cluster size. When a file
-				is compressed, this field is a multiple of the
-				compression block size (2^compression_unit) and
-				it represents the logically allocated space
-				rather than the actual on disk usage. For this
-				use the compressed_size (see below). */
-/* 48*/			sle64 data_size;	/* Byte size of the attribute
-				value. Can be larger than allocated_size if
-				attribute value is compressed or sparse. */
-/* 56*/			sle64 initialized_size;	/* Byte size of initialized
-				portion of the attribute value. Usually equals
-				data_size. */
-/* sizeof(uncompressed attr) = 64*/
-/* 64*/			sle64 compressed_size;	/* Byte size of the attribute
-				value after compression.  Only present when
-				compressed or sparse.  Always is a multiple of
-				the cluster size.  Represents the actual amount
-				of disk space being used on the disk. */
-/* sizeof(compressed attr) = 72*/
-		} __attribute__ ((__packed__)) non_resident;
-	} __attribute__ ((__packed__)) data;
-} __attribute__ ((__packed__)) ATTR_RECORD;
-
-typedef ATTR_RECORD ATTR_REC;
-
-/*
- * File attribute flags (32-bit) appearing in the file_attributes fields of the
- * STANDARD_INFORMATION attribute of MFT_RECORDs and the FILENAME_ATTR
- * attributes of MFT_RECORDs and directory index entries.
- *
- * All of the below flags appear in the directory index entries but only some
- * appear in the STANDARD_INFORMATION attribute whilst only some others appear
- * in the FILENAME_ATTR attribute of MFT_RECORDs.  Unless otherwise stated the
- * flags appear in all of the above.
- */
-enum {
-	FILE_ATTR_READONLY		= cpu_to_le32(0x00000001),
-	FILE_ATTR_HIDDEN		= cpu_to_le32(0x00000002),
-	FILE_ATTR_SYSTEM		= cpu_to_le32(0x00000004),
-	/* Old DOS volid. Unused in NT.	= cpu_to_le32(0x00000008), */
-
-	FILE_ATTR_DIRECTORY		= cpu_to_le32(0x00000010),
-	/* Note, FILE_ATTR_DIRECTORY is not considered valid in NT.  It is
-	   reserved for the DOS SUBDIRECTORY flag. */
-	FILE_ATTR_ARCHIVE		= cpu_to_le32(0x00000020),
-	FILE_ATTR_DEVICE		= cpu_to_le32(0x00000040),
-	FILE_ATTR_NORMAL		= cpu_to_le32(0x00000080),
-
-	FILE_ATTR_TEMPORARY		= cpu_to_le32(0x00000100),
-	FILE_ATTR_SPARSE_FILE		= cpu_to_le32(0x00000200),
-	FILE_ATTR_REPARSE_POINT		= cpu_to_le32(0x00000400),
-	FILE_ATTR_COMPRESSED		= cpu_to_le32(0x00000800),
-
-	FILE_ATTR_OFFLINE		= cpu_to_le32(0x00001000),
-	FILE_ATTR_NOT_CONTENT_INDEXED	= cpu_to_le32(0x00002000),
-	FILE_ATTR_ENCRYPTED		= cpu_to_le32(0x00004000),
-
-	FILE_ATTR_VALID_FLAGS		= cpu_to_le32(0x00007fb7),
-	/* Note, FILE_ATTR_VALID_FLAGS masks out the old DOS VolId and the
-	   FILE_ATTR_DEVICE and preserves everything else.  This mask is used
-	   to obtain all flags that are valid for reading. */
-	FILE_ATTR_VALID_SET_FLAGS	= cpu_to_le32(0x000031a7),
-	/* Note, FILE_ATTR_VALID_SET_FLAGS masks out the old DOS VolId, the
-	   F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
-	   F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
-	   is used to obtain all flags that are valid for setting. */
-	/*
-	 * The flag FILE_ATTR_DUP_FILENAME_INDEX_PRESENT is present in all
-	 * FILENAME_ATTR attributes but not in the STANDARD_INFORMATION
-	 * attribute of an mft record.
-	 */
-	FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT	= cpu_to_le32(0x10000000),
-	/* Note, this is a copy of the corresponding bit from the mft record,
-	   telling us whether this is a directory or not, i.e. whether it has
-	   an index root attribute or not. */
-	FILE_ATTR_DUP_VIEW_INDEX_PRESENT	= cpu_to_le32(0x20000000),
-	/* Note, this is a copy of the corresponding bit from the mft record,
-	   telling us whether this file has a view index present (eg. object id
-	   index, quota index, one of the security indexes or the encrypting
-	   filesystem related indexes). */
-};
-
-typedef le32 FILE_ATTR_FLAGS;
-
-/*
- * NOTE on times in NTFS: All times are in MS standard time format, i.e. they
- * are the number of 100-nanosecond intervals since 1st January 1601, 00:00:00
- * universal coordinated time (UTC). (In Linux time starts 1st January 1970,
- * 00:00:00 UTC and is stored as the number of 1-second intervals since then.)
- */
-
-/*
- * Attribute: Standard information (0x10).
- *
- * NOTE: Always resident.
- * NOTE: Present in all base file records on a volume.
- * NOTE: There is conflicting information about the meaning of each of the time
- *	 fields but the meaning as defined below has been verified to be
- *	 correct by practical experimentation on Windows NT4 SP6a and is hence
- *	 assumed to be the one and only correct interpretation.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	sle64 creation_time;		/* Time file was created. Updated when
-					   a filename is changed(?). */
-/*  8*/	sle64 last_data_change_time;	/* Time the data attribute was last
-					   modified. */
-/* 16*/	sle64 last_mft_change_time;	/* Time this mft record was last
-					   modified. */
-/* 24*/	sle64 last_access_time;		/* Approximate time when the file was
-					   last accessed (obviously this is not
-					   updated on read-only volumes). In
-					   Windows this is only updated when
-					   accessed if some time delta has
-					   passed since the last update. Also,
-					   last access time updates can be
-					   disabled altogether for speed. */
-/* 32*/	FILE_ATTR_FLAGS file_attributes; /* Flags describing the file. */
-/* 36*/	union {
-	/* NTFS 1.2 */
-		struct {
-		/* 36*/	u8 reserved12[12];	/* Reserved/alignment to 8-byte
-						   boundary. */
-		} __attribute__ ((__packed__)) v1;
-	/* sizeof() = 48 bytes */
-	/* NTFS 3.x */
-		struct {
-/*
- * If a volume has been upgraded from a previous NTFS version, then these
- * fields are present only if the file has been accessed since the upgrade.
- * Recognize the difference by comparing the length of the resident attribute
- * value. If it is 48, then the following fields are missing. If it is 72 then
- * the fields are present. Maybe just check like this:
- *	if (resident.ValueLength < sizeof(STANDARD_INFORMATION)) {
- *		Assume NTFS 1.2- format.
- *		If (volume version is 3.x)
- *			Upgrade attribute to NTFS 3.x format.
- *		else
- *			Use NTFS 1.2- format for access.
- *	} else
- *		Use NTFS 3.x format for access.
- * Only problem is that it might be legal to set the length of the value to
- * arbitrarily large values thus spoiling this check. - But chkdsk probably
- * views that as a corruption, assuming that it behaves like this for all
- * attributes.
- */
-		/* 36*/	le32 maximum_versions;	/* Maximum allowed versions for
-				file. Zero if version numbering is disabled. */
-		/* 40*/	le32 version_number;	/* This file's version (if any).
-				Set to zero if maximum_versions is zero. */
-		/* 44*/	le32 class_id;		/* Class id from bidirectional
-				class id index (?). */
-		/* 48*/	le32 owner_id;		/* Owner_id of the user owning
-				the file. Translate via $Q index in FILE_Extend
-				/$Quota to the quota control entry for the user
-				owning the file. Zero if quotas are disabled. */
-		/* 52*/	le32 security_id;	/* Security_id for the file.
-				Translate via $SII index and $SDS data stream
-				in FILE_Secure to the security descriptor. */
-		/* 56*/	le64 quota_charged;	/* Byte size of the charge to
-				the quota for all streams of the file. Note: Is
-				zero if quotas are disabled. */
-		/* 64*/	leUSN usn;		/* Last update sequence number
-				of the file.  This is a direct index into the
-				transaction log file ($UsnJrnl).  It is zero if
-				the usn journal is disabled or this file has
-				not been subject to logging yet.  See usnjrnl.h
-				for details. */
-		} __attribute__ ((__packed__)) v3;
-	/* sizeof() = 72 bytes (NTFS 3.x) */
-	} __attribute__ ((__packed__)) ver;
-} __attribute__ ((__packed__)) STANDARD_INFORMATION;
-
-/*
- * Attribute: Attribute list (0x20).
- *
- * - Can be either resident or non-resident.
- * - Value consists of a sequence of variable length, 8-byte aligned,
- * ATTR_LIST_ENTRY records.
- * - The list is not terminated by anything at all! The only way to know when
- * the end is reached is to keep track of the current offset and compare it to
- * the attribute value size.
- * - The attribute list attribute contains one entry for each attribute of
- * the file in which the list is located, except for the list attribute
- * itself. The list is sorted: first by attribute type, second by attribute
- * name (if present), third by instance number. The extents of one
- * non-resident attribute (if present) immediately follow after the initial
- * extent. They are ordered by lowest_vcn and have their instace set to zero.
- * It is not allowed to have two attributes with all sorting keys equal.
- * - Further restrictions:
- *	- If not resident, the vcn to lcn mapping array has to fit inside the
- *	  base mft record.
- *	- The attribute list attribute value has a maximum size of 256kb. This
- *	  is imposed by the Windows cache manager.
- * - Attribute lists are only used when the attributes of mft record do not
- * fit inside the mft record despite all attributes (that can be made
- * non-resident) having been made non-resident. This can happen e.g. when:
- *	- File has a large number of hard links (lots of file name
- *	  attributes present).
- *	- The mapping pairs array of some non-resident attribute becomes so
- *	  large due to fragmentation that it overflows the mft record.
- *	- The security descriptor is very complex (not applicable to
- *	  NTFS 3.0 volumes).
- *	- There are many named streams.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ATTR_TYPE type;		/* Type of referenced attribute. */
-/*  4*/	le16 length;		/* Byte size of this entry (8-byte aligned). */
-/*  6*/	u8 name_length;		/* Size in Unicode chars of the name of the
-				   attribute or 0 if unnamed. */
-/*  7*/	u8 name_offset;		/* Byte offset to beginning of attribute name
-				   (always set this to where the name would
-				   start even if unnamed). */
-/*  8*/	leVCN lowest_vcn;	/* Lowest virtual cluster number of this portion
-				   of the attribute value. This is usually 0. It
-				   is non-zero for the case where one attribute
-				   does not fit into one mft record and thus
-				   several mft records are allocated to hold
-				   this attribute. In the latter case, each mft
-				   record holds one extent of the attribute and
-				   there is one attribute list entry for each
-				   extent. NOTE: This is DEFINITELY a signed
-				   value! The windows driver uses cmp, followed
-				   by jg when comparing this, thus it treats it
-				   as signed. */
-/* 16*/	leMFT_REF mft_reference;/* The reference of the mft record holding
-				   the ATTR_RECORD for this portion of the
-				   attribute value. */
-/* 24*/	le16 instance;		/* If lowest_vcn = 0, the instance of the
-				   attribute being referenced; otherwise 0. */
-/* 26*/	ntfschar name[0];	/* Use when creating only. When reading use
-				   name_offset to determine the location of the
-				   name. */
-/* sizeof() = 26 + (attribute_name_length * 2) bytes */
-} __attribute__ ((__packed__)) ATTR_LIST_ENTRY;
-
-/*
- * The maximum allowed length for a file name.
- */
-#define MAXIMUM_FILE_NAME_LENGTH	255
-
-/*
- * Possible namespaces for filenames in ntfs (8-bit).
- */
-enum {
-	FILE_NAME_POSIX		= 0x00,
-	/* This is the largest namespace. It is case sensitive and allows all
-	   Unicode characters except for: '\0' and '/'.  Beware that in
-	   WinNT/2k/2003 by default files which eg have the same name except
-	   for their case will not be distinguished by the standard utilities
-	   and thus a "del filename" will delete both "filename" and "fileName"
-	   without warning.  However if for example Services For Unix (SFU) are
-	   installed and the case sensitive option was enabled at installation
-	   time, then you can create/access/delete such files.
-	   Note that even SFU places restrictions on the filenames beyond the
-	   '\0' and '/' and in particular the following set of characters is
-	   not allowed: '"', '/', '<', '>', '\'.  All other characters,
-	   including the ones no allowed in WIN32 namespace are allowed.
-	   Tested with SFU 3.5 (this is now free) running on Windows XP. */
-	FILE_NAME_WIN32		= 0x01,
-	/* The standard WinNT/2k NTFS long filenames. Case insensitive.  All
-	   Unicode chars except: '\0', '"', '*', '/', ':', '<', '>', '?', '\',
-	   and '|'.  Further, names cannot end with a '.' or a space. */
-	FILE_NAME_DOS		= 0x02,
-	/* The standard DOS filenames (8.3 format). Uppercase only.  All 8-bit
-	   characters greater space, except: '"', '*', '+', ',', '/', ':', ';',
-	   '<', '=', '>', '?', and '\'. */
-	FILE_NAME_WIN32_AND_DOS	= 0x03,
-	/* 3 means that both the Win32 and the DOS filenames are identical and
-	   hence have been saved in this single filename record. */
-} __attribute__ ((__packed__));
-
-typedef u8 FILE_NAME_TYPE_FLAGS;
-
-/*
- * Attribute: Filename (0x30).
- *
- * NOTE: Always resident.
- * NOTE: All fields, except the parent_directory, are only updated when the
- *	 filename is changed. Until then, they just become out of sync with
- *	 reality and the more up to date values are present in the standard
- *	 information attribute.
- * NOTE: There is conflicting information about the meaning of each of the time
- *	 fields but the meaning as defined below has been verified to be
- *	 correct by practical experimentation on Windows NT4 SP6a and is hence
- *	 assumed to be the one and only correct interpretation.
- */
-typedef struct {
-/*hex ofs*/
-/*  0*/	leMFT_REF parent_directory;	/* Directory this filename is
-					   referenced from. */
-/*  8*/	sle64 creation_time;		/* Time file was created. */
-/* 10*/	sle64 last_data_change_time;	/* Time the data attribute was last
-					   modified. */
-/* 18*/	sle64 last_mft_change_time;	/* Time this mft record was last
-					   modified. */
-/* 20*/	sle64 last_access_time;		/* Time this mft record was last
-					   accessed. */
-/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
-					   for the unnamed data attribute.  So
-					   for normal $DATA, this is the
-					   allocated_size from the unnamed
-					   $DATA attribute and for compressed
-					   and/or sparse $DATA, this is the
-					   compressed_size from the unnamed
-					   $DATA attribute.  For a directory or
-					   other inode without an unnamed $DATA
-					   attribute, this is always 0.  NOTE:
-					   This is a multiple of the cluster
-					   size. */
-/* 30*/	sle64 data_size;		/* Byte size of actual data in unnamed
-					   data attribute.  For a directory or
-					   other inode without an unnamed $DATA
-					   attribute, this is always 0. */
-/* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
-/* 3c*/	union {
-	/* 3c*/	struct {
-		/* 3c*/	le16 packed_ea_size;	/* Size of the buffer needed to
-						   pack the extended attributes
-						   (EAs), if such are present.*/
-		/* 3e*/	le16 reserved;		/* Reserved for alignment. */
-		} __attribute__ ((__packed__)) ea;
-	/* 3c*/	struct {
-		/* 3c*/	le32 reparse_point_tag;	/* Type of reparse point,
-						   present only in reparse
-						   points and only if there are
-						   no EAs. */
-		} __attribute__ ((__packed__)) rp;
-	} __attribute__ ((__packed__)) type;
-/* 40*/	u8 file_name_length;			/* Length of file name in
-						   (Unicode) characters. */
-/* 41*/	FILE_NAME_TYPE_FLAGS file_name_type;	/* Namespace of the file name.*/
-/* 42*/	ntfschar file_name[0];			/* File name in Unicode. */
-} __attribute__ ((__packed__)) FILE_NAME_ATTR;
-
-/*
- * GUID structures store globally unique identifiers (GUID). A GUID is a
- * 128-bit value consisting of one group of eight hexadecimal digits, followed
- * by three groups of four hexadecimal digits each, followed by one group of
- * twelve hexadecimal digits. GUIDs are Microsoft's implementation of the
- * distributed computing environment (DCE) universally unique identifier (UUID).
- * Example of a GUID:
- *	1F010768-5A73-BC91-0010A52216A7
- */
-typedef struct {
-	le32 data1;	/* The first eight hexadecimal digits of the GUID. */
-	le16 data2;	/* The first group of four hexadecimal digits. */
-	le16 data3;	/* The second group of four hexadecimal digits. */
-	u8 data4[8];	/* The first two bytes are the third group of four
-			   hexadecimal digits. The remaining six bytes are the
-			   final 12 hexadecimal digits. */
-} __attribute__ ((__packed__)) GUID;
-
-/*
- * FILE_Extend/$ObjId contains an index named $O. This index contains all
- * object_ids present on the volume as the index keys and the corresponding
- * mft_record numbers as the index entry data parts. The data part (defined
- * below) also contains three other object_ids:
- *	birth_volume_id - object_id of FILE_Volume on which the file was first
- *			  created. Optional (i.e. can be zero).
- *	birth_object_id - object_id of file when it was first created. Usually
- *			  equals the object_id. Optional (i.e. can be zero).
- *	domain_id	- Reserved (always zero).
- */
-typedef struct {
-	leMFT_REF mft_reference;/* Mft record containing the object_id in
-				   the index entry key. */
-	union {
-		struct {
-			GUID birth_volume_id;
-			GUID birth_object_id;
-			GUID domain_id;
-		} __attribute__ ((__packed__)) origin;
-		u8 extended_info[48];
-	} __attribute__ ((__packed__)) opt;
-} __attribute__ ((__packed__)) OBJ_ID_INDEX_DATA;
-
-/*
- * Attribute: Object id (NTFS 3.0+) (0x40).
- *
- * NOTE: Always resident.
- */
-typedef struct {
-	GUID object_id;				/* Unique id assigned to the
-						   file.*/
-	/* The following fields are optional. The attribute value size is 16
-	   bytes, i.e. sizeof(GUID), if these are not present at all. Note,
-	   the entries can be present but one or more (or all) can be zero
-	   meaning that that particular value(s) is(are) not defined. */
-	union {
-		struct {
-			GUID birth_volume_id;	/* Unique id of volume on which
-						   the file was first created.*/
-			GUID birth_object_id;	/* Unique id of file when it was
-						   first created. */
-			GUID domain_id;		/* Reserved, zero. */
-		} __attribute__ ((__packed__)) origin;
-		u8 extended_info[48];
-	} __attribute__ ((__packed__)) opt;
-} __attribute__ ((__packed__)) OBJECT_ID_ATTR;
-
-/*
- * The pre-defined IDENTIFIER_AUTHORITIES used as SID_IDENTIFIER_AUTHORITY in
- * the SID structure (see below).
- */
-//typedef enum {					/* SID string prefix. */
-//	SECURITY_NULL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 0},	/* S-1-0 */
-//	SECURITY_WORLD_SID_AUTHORITY	= {0, 0, 0, 0, 0, 1},	/* S-1-1 */
-//	SECURITY_LOCAL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 2},	/* S-1-2 */
-//	SECURITY_CREATOR_SID_AUTHORITY	= {0, 0, 0, 0, 0, 3},	/* S-1-3 */
-//	SECURITY_NON_UNIQUE_AUTHORITY	= {0, 0, 0, 0, 0, 4},	/* S-1-4 */
-//	SECURITY_NT_SID_AUTHORITY	= {0, 0, 0, 0, 0, 5},	/* S-1-5 */
-//} IDENTIFIER_AUTHORITIES;
-
-/*
- * These relative identifiers (RIDs) are used with the above identifier
- * authorities to make up universal well-known SIDs.
- *
- * Note: The relative identifier (RID) refers to the portion of a SID, which
- * identifies a user or group in relation to the authority that issued the SID.
- * For example, the universal well-known SID Creator Owner ID (S-1-3-0) is
- * made up of the identifier authority SECURITY_CREATOR_SID_AUTHORITY (3) and
- * the relative identifier SECURITY_CREATOR_OWNER_RID (0).
- */
-typedef enum {					/* Identifier authority. */
-	SECURITY_NULL_RID		  = 0,	/* S-1-0 */
-	SECURITY_WORLD_RID		  = 0,	/* S-1-1 */
-	SECURITY_LOCAL_RID		  = 0,	/* S-1-2 */
-
-	SECURITY_CREATOR_OWNER_RID	  = 0,	/* S-1-3 */
-	SECURITY_CREATOR_GROUP_RID	  = 1,	/* S-1-3 */
-
-	SECURITY_CREATOR_OWNER_SERVER_RID = 2,	/* S-1-3 */
-	SECURITY_CREATOR_GROUP_SERVER_RID = 3,	/* S-1-3 */
-
-	SECURITY_DIALUP_RID		  = 1,
-	SECURITY_NETWORK_RID		  = 2,
-	SECURITY_BATCH_RID		  = 3,
-	SECURITY_INTERACTIVE_RID	  = 4,
-	SECURITY_SERVICE_RID		  = 6,
-	SECURITY_ANONYMOUS_LOGON_RID	  = 7,
-	SECURITY_PROXY_RID		  = 8,
-	SECURITY_ENTERPRISE_CONTROLLERS_RID=9,
-	SECURITY_SERVER_LOGON_RID	  = 9,
-	SECURITY_PRINCIPAL_SELF_RID	  = 0xa,
-	SECURITY_AUTHENTICATED_USER_RID	  = 0xb,
-	SECURITY_RESTRICTED_CODE_RID	  = 0xc,
-	SECURITY_TERMINAL_SERVER_RID	  = 0xd,
-
-	SECURITY_LOGON_IDS_RID		  = 5,
-	SECURITY_LOGON_IDS_RID_COUNT	  = 3,
-
-	SECURITY_LOCAL_SYSTEM_RID	  = 0x12,
-
-	SECURITY_NT_NON_UNIQUE		  = 0x15,
-
-	SECURITY_BUILTIN_DOMAIN_RID	  = 0x20,
-
-	/*
-	 * Well-known domain relative sub-authority values (RIDs).
-	 */
-
-	/* Users. */
-	DOMAIN_USER_RID_ADMIN		  = 0x1f4,
-	DOMAIN_USER_RID_GUEST		  = 0x1f5,
-	DOMAIN_USER_RID_KRBTGT		  = 0x1f6,
-
-	/* Groups. */
-	DOMAIN_GROUP_RID_ADMINS		  = 0x200,
-	DOMAIN_GROUP_RID_USERS		  = 0x201,
-	DOMAIN_GROUP_RID_GUESTS		  = 0x202,
-	DOMAIN_GROUP_RID_COMPUTERS	  = 0x203,
-	DOMAIN_GROUP_RID_CONTROLLERS	  = 0x204,
-	DOMAIN_GROUP_RID_CERT_ADMINS	  = 0x205,
-	DOMAIN_GROUP_RID_SCHEMA_ADMINS	  = 0x206,
-	DOMAIN_GROUP_RID_ENTERPRISE_ADMINS= 0x207,
-	DOMAIN_GROUP_RID_POLICY_ADMINS	  = 0x208,
-
-	/* Aliases. */
-	DOMAIN_ALIAS_RID_ADMINS		  = 0x220,
-	DOMAIN_ALIAS_RID_USERS		  = 0x221,
-	DOMAIN_ALIAS_RID_GUESTS		  = 0x222,
-	DOMAIN_ALIAS_RID_POWER_USERS	  = 0x223,
-
-	DOMAIN_ALIAS_RID_ACCOUNT_OPS	  = 0x224,
-	DOMAIN_ALIAS_RID_SYSTEM_OPS	  = 0x225,
-	DOMAIN_ALIAS_RID_PRINT_OPS	  = 0x226,
-	DOMAIN_ALIAS_RID_BACKUP_OPS	  = 0x227,
-
-	DOMAIN_ALIAS_RID_REPLICATOR	  = 0x228,
-	DOMAIN_ALIAS_RID_RAS_SERVERS	  = 0x229,
-	DOMAIN_ALIAS_RID_PREW2KCOMPACCESS = 0x22a,
-} RELATIVE_IDENTIFIERS;
-
-/*
- * The universal well-known SIDs:
- *
- *	NULL_SID			S-1-0-0
- *	WORLD_SID			S-1-1-0
- *	LOCAL_SID			S-1-2-0
- *	CREATOR_OWNER_SID		S-1-3-0
- *	CREATOR_GROUP_SID		S-1-3-1
- *	CREATOR_OWNER_SERVER_SID	S-1-3-2
- *	CREATOR_GROUP_SERVER_SID	S-1-3-3
- *
- *	(Non-unique IDs)		S-1-4
- *
- * NT well-known SIDs:
- *
- *	NT_AUTHORITY_SID	S-1-5
- *	DIALUP_SID		S-1-5-1
- *
- *	NETWORD_SID		S-1-5-2
- *	BATCH_SID		S-1-5-3
- *	INTERACTIVE_SID		S-1-5-4
- *	SERVICE_SID		S-1-5-6
- *	ANONYMOUS_LOGON_SID	S-1-5-7		(aka null logon session)
- *	PROXY_SID		S-1-5-8
- *	SERVER_LOGON_SID	S-1-5-9		(aka domain controller account)
- *	SELF_SID		S-1-5-10	(self RID)
- *	AUTHENTICATED_USER_SID	S-1-5-11
- *	RESTRICTED_CODE_SID	S-1-5-12	(running restricted code)
- *	TERMINAL_SERVER_SID	S-1-5-13	(running on terminal server)
- *
- *	(Logon IDs)		S-1-5-5-X-Y
- *
- *	(NT non-unique IDs)	S-1-5-0x15-...
- *
- *	(Built-in domain)	S-1-5-0x20
- */
-
-/*
- * The SID_IDENTIFIER_AUTHORITY is a 48-bit value used in the SID structure.
- *
- * NOTE: This is stored as a big endian number, hence the high_part comes
- * before the low_part.
- */
-typedef union {
-	struct {
-		u16 high_part;	/* High 16-bits. */
-		u32 low_part;	/* Low 32-bits. */
-	} __attribute__ ((__packed__)) parts;
-	u8 value[6];		/* Value as individual bytes. */
-} __attribute__ ((__packed__)) SID_IDENTIFIER_AUTHORITY;
-
-/*
- * The SID structure is a variable-length structure used to uniquely identify
- * users or groups. SID stands for security identifier.
- *
- * The standard textual representation of the SID is of the form:
- *	S-R-I-S-S...
- * Where:
- *    - The first "S" is the literal character 'S' identifying the following
- *	digits as a SID.
- *    - R is the revision level of the SID expressed as a sequence of digits
- *	either in decimal or hexadecimal (if the later, prefixed by "0x").
- *    - I is the 48-bit identifier_authority, expressed as digits as R above.
- *    - S... is one or more sub_authority values, expressed as digits as above.
- *
- * Example SID; the domain-relative SID of the local Administrators group on
- * Windows NT/2k:
- *	S-1-5-32-544
- * This translates to a SID with:
- *	revision = 1,
- *	sub_authority_count = 2,
- *	identifier_authority = {0,0,0,0,0,5},	// SECURITY_NT_AUTHORITY
- *	sub_authority[0] = 32,			// SECURITY_BUILTIN_DOMAIN_RID
- *	sub_authority[1] = 544			// DOMAIN_ALIAS_RID_ADMINS
- */
-typedef struct {
-	u8 revision;
-	u8 sub_authority_count;
-	SID_IDENTIFIER_AUTHORITY identifier_authority;
-	le32 sub_authority[1];		/* At least one sub_authority. */
-} __attribute__ ((__packed__)) SID;
-
-/*
- * Current constants for SIDs.
- */
-typedef enum {
-	SID_REVISION			=  1,	/* Current revision level. */
-	SID_MAX_SUB_AUTHORITIES		= 15,	/* Maximum number of those. */
-	SID_RECOMMENDED_SUB_AUTHORITIES	=  1,	/* Will change to around 6 in
-						   a future revision. */
-} SID_CONSTANTS;
-
-/*
- * The predefined ACE types (8-bit, see below).
- */
-enum {
-	ACCESS_MIN_MS_ACE_TYPE		= 0,
-	ACCESS_ALLOWED_ACE_TYPE		= 0,
-	ACCESS_DENIED_ACE_TYPE		= 1,
-	SYSTEM_AUDIT_ACE_TYPE		= 2,
-	SYSTEM_ALARM_ACE_TYPE		= 3, /* Not implemented as of Win2k. */
-	ACCESS_MAX_MS_V2_ACE_TYPE	= 3,
-
-	ACCESS_ALLOWED_COMPOUND_ACE_TYPE= 4,
-	ACCESS_MAX_MS_V3_ACE_TYPE	= 4,
-
-	/* The following are Win2k only. */
-	ACCESS_MIN_MS_OBJECT_ACE_TYPE	= 5,
-	ACCESS_ALLOWED_OBJECT_ACE_TYPE	= 5,
-	ACCESS_DENIED_OBJECT_ACE_TYPE	= 6,
-	SYSTEM_AUDIT_OBJECT_ACE_TYPE	= 7,
-	SYSTEM_ALARM_OBJECT_ACE_TYPE	= 8,
-	ACCESS_MAX_MS_OBJECT_ACE_TYPE	= 8,
-
-	ACCESS_MAX_MS_V4_ACE_TYPE	= 8,
-
-	/* This one is for WinNT/2k. */
-	ACCESS_MAX_MS_ACE_TYPE		= 8,
-} __attribute__ ((__packed__));
-
-typedef u8 ACE_TYPES;
-
-/*
- * The ACE flags (8-bit) for audit and inheritance (see below).
- *
- * SUCCESSFUL_ACCESS_ACE_FLAG is only used with system audit and alarm ACE
- * types to indicate that a message is generated (in Windows!) for successful
- * accesses.
- *
- * FAILED_ACCESS_ACE_FLAG is only used with system audit and alarm ACE types
- * to indicate that a message is generated (in Windows!) for failed accesses.
- */
-enum {
-	/* The inheritance flags. */
-	OBJECT_INHERIT_ACE		= 0x01,
-	CONTAINER_INHERIT_ACE		= 0x02,
-	NO_PROPAGATE_INHERIT_ACE	= 0x04,
-	INHERIT_ONLY_ACE		= 0x08,
-	INHERITED_ACE			= 0x10,	/* Win2k only. */
-	VALID_INHERIT_FLAGS		= 0x1f,
-
-	/* The audit flags. */
-	SUCCESSFUL_ACCESS_ACE_FLAG	= 0x40,
-	FAILED_ACCESS_ACE_FLAG		= 0x80,
-} __attribute__ ((__packed__));
-
-typedef u8 ACE_FLAGS;
-
-/*
- * An ACE is an access-control entry in an access-control list (ACL).
- * An ACE defines access to an object for a specific user or group or defines
- * the types of access that generate system-administration messages or alarms
- * for a specific user or group. The user or group is identified by a security
- * identifier (SID).
- *
- * Each ACE starts with an ACE_HEADER structure (aligned on 4-byte boundary),
- * which specifies the type and size of the ACE. The format of the subsequent
- * data depends on the ACE type.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	ACE_TYPES type;		/* Type of the ACE. */
-/*  1*/	ACE_FLAGS flags;	/* Flags describing the ACE. */
-/*  2*/	le16 size;		/* Size in bytes of the ACE. */
-} __attribute__ ((__packed__)) ACE_HEADER;
-
-/*
- * The access mask (32-bit). Defines the access rights.
- *
- * The specific rights (bits 0 to 15).  These depend on the type of the object
- * being secured by the ACE.
- */
-enum {
-	/* Specific rights for files and directories are as follows: */
-
-	/* Right to read data from the file. (FILE) */
-	FILE_READ_DATA			= cpu_to_le32(0x00000001),
-	/* Right to list contents of a directory. (DIRECTORY) */
-	FILE_LIST_DIRECTORY		= cpu_to_le32(0x00000001),
-
-	/* Right to write data to the file. (FILE) */
-	FILE_WRITE_DATA			= cpu_to_le32(0x00000002),
-	/* Right to create a file in the directory. (DIRECTORY) */
-	FILE_ADD_FILE			= cpu_to_le32(0x00000002),
-
-	/* Right to append data to the file. (FILE) */
-	FILE_APPEND_DATA		= cpu_to_le32(0x00000004),
-	/* Right to create a subdirectory. (DIRECTORY) */
-	FILE_ADD_SUBDIRECTORY		= cpu_to_le32(0x00000004),
-
-	/* Right to read extended attributes. (FILE/DIRECTORY) */
-	FILE_READ_EA			= cpu_to_le32(0x00000008),
-
-	/* Right to write extended attributes. (FILE/DIRECTORY) */
-	FILE_WRITE_EA			= cpu_to_le32(0x00000010),
-
-	/* Right to execute a file. (FILE) */
-	FILE_EXECUTE			= cpu_to_le32(0x00000020),
-	/* Right to traverse the directory. (DIRECTORY) */
-	FILE_TRAVERSE			= cpu_to_le32(0x00000020),
-
-	/*
-	 * Right to delete a directory and all the files it contains (its
-	 * children), even if the files are read-only. (DIRECTORY)
-	 */
-	FILE_DELETE_CHILD		= cpu_to_le32(0x00000040),
-
-	/* Right to read file attributes. (FILE/DIRECTORY) */
-	FILE_READ_ATTRIBUTES		= cpu_to_le32(0x00000080),
-
-	/* Right to change file attributes. (FILE/DIRECTORY) */
-	FILE_WRITE_ATTRIBUTES		= cpu_to_le32(0x00000100),
-
-	/*
-	 * The standard rights (bits 16 to 23).  These are independent of the
-	 * type of object being secured.
-	 */
-
-	/* Right to delete the object. */
-	DELETE				= cpu_to_le32(0x00010000),
-
-	/*
-	 * Right to read the information in the object's security descriptor,
-	 * not including the information in the SACL, i.e. right to read the
-	 * security descriptor and owner.
-	 */
-	READ_CONTROL			= cpu_to_le32(0x00020000),
-
-	/* Right to modify the DACL in the object's security descriptor. */
-	WRITE_DAC			= cpu_to_le32(0x00040000),
-
-	/* Right to change the owner in the object's security descriptor. */
-	WRITE_OWNER			= cpu_to_le32(0x00080000),
-
-	/*
-	 * Right to use the object for synchronization.  Enables a process to
-	 * wait until the object is in the signalled state.  Some object types
-	 * do not support this access right.
-	 */
-	SYNCHRONIZE			= cpu_to_le32(0x00100000),
-
-	/*
-	 * The following STANDARD_RIGHTS_* are combinations of the above for
-	 * convenience and are defined by the Win32 API.
-	 */
-
-	/* These are currently defined to READ_CONTROL. */
-	STANDARD_RIGHTS_READ		= cpu_to_le32(0x00020000),
-	STANDARD_RIGHTS_WRITE		= cpu_to_le32(0x00020000),
-	STANDARD_RIGHTS_EXECUTE		= cpu_to_le32(0x00020000),
-
-	/* Combines DELETE, READ_CONTROL, WRITE_DAC, and WRITE_OWNER access. */
-	STANDARD_RIGHTS_REQUIRED	= cpu_to_le32(0x000f0000),
-
-	/*
-	 * Combines DELETE, READ_CONTROL, WRITE_DAC, WRITE_OWNER, and
-	 * SYNCHRONIZE access.
-	 */
-	STANDARD_RIGHTS_ALL		= cpu_to_le32(0x001f0000),
-
-	/*
-	 * The access system ACL and maximum allowed access types (bits 24 to
-	 * 25, bits 26 to 27 are reserved).
-	 */
-	ACCESS_SYSTEM_SECURITY		= cpu_to_le32(0x01000000),
-	MAXIMUM_ALLOWED			= cpu_to_le32(0x02000000),
-
-	/*
-	 * The generic rights (bits 28 to 31).  These map onto the standard and
-	 * specific rights.
-	 */
-
-	/* Read, write, and execute access. */
-	GENERIC_ALL			= cpu_to_le32(0x10000000),
-
-	/* Execute access. */
-	GENERIC_EXECUTE			= cpu_to_le32(0x20000000),
-
-	/*
-	 * Write access.  For files, this maps onto:
-	 *	FILE_APPEND_DATA | FILE_WRITE_ATTRIBUTES | FILE_WRITE_DATA |
-	 *	FILE_WRITE_EA | STANDARD_RIGHTS_WRITE | SYNCHRONIZE
-	 * For directories, the mapping has the same numerical value.  See
-	 * above for the descriptions of the rights granted.
-	 */
-	GENERIC_WRITE			= cpu_to_le32(0x40000000),
-
-	/*
-	 * Read access.  For files, this maps onto:
-	 *	FILE_READ_ATTRIBUTES | FILE_READ_DATA | FILE_READ_EA |
-	 *	STANDARD_RIGHTS_READ | SYNCHRONIZE
-	 * For directories, the mapping has the same numberical value.  See
-	 * above for the descriptions of the rights granted.
-	 */
-	GENERIC_READ			= cpu_to_le32(0x80000000),
-};
-
-typedef le32 ACCESS_MASK;
-
-/*
- * The generic mapping array. Used to denote the mapping of each generic
- * access right to a specific access mask.
- *
- * FIXME: What exactly is this and what is it for? (AIA)
- */
-typedef struct {
-	ACCESS_MASK generic_read;
-	ACCESS_MASK generic_write;
-	ACCESS_MASK generic_execute;
-	ACCESS_MASK generic_all;
-} __attribute__ ((__packed__)) GENERIC_MAPPING;
-
-/*
- * The predefined ACE type structures are as defined below.
- */
-
-/*
- * ACCESS_ALLOWED_ACE, ACCESS_DENIED_ACE, SYSTEM_AUDIT_ACE, SYSTEM_ALARM_ACE
- */
-typedef struct {
-/*  0	ACE_HEADER; -- Unfolded here as gcc doesn't like unnamed structs. */
-	ACE_TYPES type;		/* Type of the ACE. */
-	ACE_FLAGS flags;	/* Flags describing the ACE. */
-	le16 size;		/* Size in bytes of the ACE. */
-/*  4*/	ACCESS_MASK mask;	/* Access mask associated with the ACE. */
-
-/*  8*/	SID sid;		/* The SID associated with the ACE. */
-} __attribute__ ((__packed__)) ACCESS_ALLOWED_ACE, ACCESS_DENIED_ACE,
-			       SYSTEM_AUDIT_ACE, SYSTEM_ALARM_ACE;
-
-/*
- * The object ACE flags (32-bit).
- */
-enum {
-	ACE_OBJECT_TYPE_PRESENT			= cpu_to_le32(1),
-	ACE_INHERITED_OBJECT_TYPE_PRESENT	= cpu_to_le32(2),
-};
-
-typedef le32 OBJECT_ACE_FLAGS;
-
-typedef struct {
-/*  0	ACE_HEADER; -- Unfolded here as gcc doesn't like unnamed structs. */
-	ACE_TYPES type;		/* Type of the ACE. */
-	ACE_FLAGS flags;	/* Flags describing the ACE. */
-	le16 size;		/* Size in bytes of the ACE. */
-/*  4*/	ACCESS_MASK mask;	/* Access mask associated with the ACE. */
-
-/*  8*/	OBJECT_ACE_FLAGS object_flags;	/* Flags describing the object ACE. */
-/* 12*/	GUID object_type;
-/* 28*/	GUID inherited_object_type;
-
-/* 44*/	SID sid;		/* The SID associated with the ACE. */
-} __attribute__ ((__packed__)) ACCESS_ALLOWED_OBJECT_ACE,
-			       ACCESS_DENIED_OBJECT_ACE,
-			       SYSTEM_AUDIT_OBJECT_ACE,
-			       SYSTEM_ALARM_OBJECT_ACE;
-
-/*
- * An ACL is an access-control list (ACL).
- * An ACL starts with an ACL header structure, which specifies the size of
- * the ACL and the number of ACEs it contains. The ACL header is followed by
- * zero or more access control entries (ACEs). The ACL as well as each ACE
- * are aligned on 4-byte boundaries.
- */
-typedef struct {
-	u8 revision;	/* Revision of this ACL. */
-	u8 alignment1;
-	le16 size;	/* Allocated space in bytes for ACL. Includes this
-			   header, the ACEs and the remaining free space. */
-	le16 ace_count;	/* Number of ACEs in the ACL. */
-	le16 alignment2;
-/* sizeof() = 8 bytes */
-} __attribute__ ((__packed__)) ACL;
-
-/*
- * Current constants for ACLs.
- */
-typedef enum {
-	/* Current revision. */
-	ACL_REVISION		= 2,
-	ACL_REVISION_DS		= 4,
-
-	/* History of revisions. */
-	ACL_REVISION1		= 1,
-	MIN_ACL_REVISION	= 2,
-	ACL_REVISION2		= 2,
-	ACL_REVISION3		= 3,
-	ACL_REVISION4		= 4,
-	MAX_ACL_REVISION	= 4,
-} ACL_CONSTANTS;
-
-/*
- * The security descriptor control flags (16-bit).
- *
- * SE_OWNER_DEFAULTED - This boolean flag, when set, indicates that the SID
- *	pointed to by the Owner field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the SID with
- *	respect to inheritance of an owner.
- *
- * SE_GROUP_DEFAULTED - This boolean flag, when set, indicates that the SID in
- *	the Group field was provided by a defaulting mechanism rather than
- *	explicitly provided by the original provider of the security
- *	descriptor.  This may affect the treatment of the SID with respect to
- *	inheritance of a primary group.
- *
- * SE_DACL_PRESENT - This boolean flag, when set, indicates that the security
- *	descriptor contains a discretionary ACL.  If this flag is set and the
- *	Dacl field of the SECURITY_DESCRIPTOR is null, then a null ACL is
- *	explicitly being specified.
- *
- * SE_DACL_DEFAULTED - This boolean flag, when set, indicates that the ACL
- *	pointed to by the Dacl field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the ACL with
- *	respect to inheritance of an ACL.  This flag is ignored if the
- *	DaclPresent flag is not set.
- *
- * SE_SACL_PRESENT - This boolean flag, when set,  indicates that the security
- *	descriptor contains a system ACL pointed to by the Sacl field.  If this
- *	flag is set and the Sacl field of the SECURITY_DESCRIPTOR is null, then
- *	an empty (but present) ACL is being specified.
- *
- * SE_SACL_DEFAULTED - This boolean flag, when set, indicates that the ACL
- *	pointed to by the Sacl field was provided by a defaulting mechanism
- *	rather than explicitly provided by the original provider of the
- *	security descriptor.  This may affect the treatment of the ACL with
- *	respect to inheritance of an ACL.  This flag is ignored if the
- *	SaclPresent flag is not set.
- *
- * SE_SELF_RELATIVE - This boolean flag, when set, indicates that the security
- *	descriptor is in self-relative form.  In this form, all fields of the
- *	security descriptor are contiguous in memory and all pointer fields are
- *	expressed as offsets from the beginning of the security descriptor.
- */
-enum {
-	SE_OWNER_DEFAULTED		= cpu_to_le16(0x0001),
-	SE_GROUP_DEFAULTED		= cpu_to_le16(0x0002),
-	SE_DACL_PRESENT			= cpu_to_le16(0x0004),
-	SE_DACL_DEFAULTED		= cpu_to_le16(0x0008),
-
-	SE_SACL_PRESENT			= cpu_to_le16(0x0010),
-	SE_SACL_DEFAULTED		= cpu_to_le16(0x0020),
-
-	SE_DACL_AUTO_INHERIT_REQ	= cpu_to_le16(0x0100),
-	SE_SACL_AUTO_INHERIT_REQ	= cpu_to_le16(0x0200),
-	SE_DACL_AUTO_INHERITED		= cpu_to_le16(0x0400),
-	SE_SACL_AUTO_INHERITED		= cpu_to_le16(0x0800),
-
-	SE_DACL_PROTECTED		= cpu_to_le16(0x1000),
-	SE_SACL_PROTECTED		= cpu_to_le16(0x2000),
-	SE_RM_CONTROL_VALID		= cpu_to_le16(0x4000),
-	SE_SELF_RELATIVE		= cpu_to_le16(0x8000)
-} __attribute__ ((__packed__));
-
-typedef le16 SECURITY_DESCRIPTOR_CONTROL;
-
-/*
- * Self-relative security descriptor. Contains the owner and group SIDs as well
- * as the sacl and dacl ACLs inside the security descriptor itself.
- */
-typedef struct {
-	u8 revision;	/* Revision level of the security descriptor. */
-	u8 alignment;
-	SECURITY_DESCRIPTOR_CONTROL control; /* Flags qualifying the type of
-			   the descriptor as well as the following fields. */
-	le32 owner;	/* Byte offset to a SID representing an object's
-			   owner. If this is NULL, no owner SID is present in
-			   the descriptor. */
-	le32 group;	/* Byte offset to a SID representing an object's
-			   primary group. If this is NULL, no primary group
-			   SID is present in the descriptor. */
-	le32 sacl;	/* Byte offset to a system ACL. Only valid, if
-			   SE_SACL_PRESENT is set in the control field. If
-			   SE_SACL_PRESENT is set but sacl is NULL, a NULL ACL
-			   is specified. */
-	le32 dacl;	/* Byte offset to a discretionary ACL. Only valid, if
-			   SE_DACL_PRESENT is set in the control field. If
-			   SE_DACL_PRESENT is set but dacl is NULL, a NULL ACL
-			   (unconditionally granting access) is specified. */
-/* sizeof() = 0x14 bytes */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR_RELATIVE;
-
-/*
- * Absolute security descriptor. Does not contain the owner and group SIDs, nor
- * the sacl and dacl ACLs inside the security descriptor. Instead, it contains
- * pointers to these structures in memory. Obviously, absolute security
- * descriptors are only useful for in memory representations of security
- * descriptors. On disk, a self-relative security descriptor is used.
- */
-typedef struct {
-	u8 revision;	/* Revision level of the security descriptor. */
-	u8 alignment;
-	SECURITY_DESCRIPTOR_CONTROL control;	/* Flags qualifying the type of
-			   the descriptor as well as the following fields. */
-	SID *owner;	/* Points to a SID representing an object's owner. If
-			   this is NULL, no owner SID is present in the
-			   descriptor. */
-	SID *group;	/* Points to a SID representing an object's primary
-			   group. If this is NULL, no primary group SID is
-			   present in the descriptor. */
-	ACL *sacl;	/* Points to a system ACL. Only valid, if
-			   SE_SACL_PRESENT is set in the control field. If
-			   SE_SACL_PRESENT is set but sacl is NULL, a NULL ACL
-			   is specified. */
-	ACL *dacl;	/* Points to a discretionary ACL. Only valid, if
-			   SE_DACL_PRESENT is set in the control field. If
-			   SE_DACL_PRESENT is set but dacl is NULL, a NULL ACL
-			   (unconditionally granting access) is specified. */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR;
-
-/*
- * Current constants for security descriptors.
- */
-typedef enum {
-	/* Current revision. */
-	SECURITY_DESCRIPTOR_REVISION	= 1,
-	SECURITY_DESCRIPTOR_REVISION1	= 1,
-
-	/* The sizes of both the absolute and relative security descriptors is
-	   the same as pointers, at least on ia32 architecture are 32-bit. */
-	SECURITY_DESCRIPTOR_MIN_LENGTH	= sizeof(SECURITY_DESCRIPTOR),
-} SECURITY_DESCRIPTOR_CONSTANTS;
-
-/*
- * Attribute: Security descriptor (0x50). A standard self-relative security
- * descriptor.
- *
- * NOTE: Can be resident or non-resident.
- * NOTE: Not used in NTFS 3.0+, as security descriptors are stored centrally
- * in FILE_Secure and the correct descriptor is found using the security_id
- * from the standard information attribute.
- */
-typedef SECURITY_DESCRIPTOR_RELATIVE SECURITY_DESCRIPTOR_ATTR;
-
-/*
- * On NTFS 3.0+, all security descriptors are stored in FILE_Secure. Only one
- * referenced instance of each unique security descriptor is stored.
- *
- * FILE_Secure contains no unnamed data attribute, i.e. it has zero length. It
- * does, however, contain two indexes ($SDH and $SII) as well as a named data
- * stream ($SDS).
- *
- * Every unique security descriptor is assigned a unique security identifier
- * (security_id, not to be confused with a SID). The security_id is unique for
- * the NTFS volume and is used as an index into the $SII index, which maps
- * security_ids to the security descriptor's storage location within the $SDS
- * data attribute. The $SII index is sorted by ascending security_id.
- *
- * A simple hash is computed from each security descriptor. This hash is used
- * as an index into the $SDH index, which maps security descriptor hashes to
- * the security descriptor's storage location within the $SDS data attribute.
- * The $SDH index is sorted by security descriptor hash and is stored in a B+
- * tree. When searching $SDH (with the intent of determining whether or not a
- * new security descriptor is already present in the $SDS data stream), if a
- * matching hash is found, but the security descriptors do not match, the
- * search in the $SDH index is continued, searching for a next matching hash.
- *
- * When a precise match is found, the security_id coresponding to the security
- * descriptor in the $SDS attribute is read from the found $SDH index entry and
- * is stored in the $STANDARD_INFORMATION attribute of the file/directory to
- * which the security descriptor is being applied. The $STANDARD_INFORMATION
- * attribute is present in all base mft records (i.e. in all files and
- * directories).
- *
- * If a match is not found, the security descriptor is assigned a new unique
- * security_id and is added to the $SDS data attribute. Then, entries
- * referencing the this security descriptor in the $SDS data attribute are
- * added to the $SDH and $SII indexes.
- *
- * Note: Entries are never deleted from FILE_Secure, even if nothing
- * references an entry any more.
- */
-
-/*
- * This header precedes each security descriptor in the $SDS data stream.
- * This is also the index entry data part of both the $SII and $SDH indexes.
- */
-typedef struct {
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-	le64 offset;	  /* Byte offset of this entry in the $SDS stream. */
-	le32 length;	  /* Size in bytes of this entry in $SDS stream. */
-} __attribute__ ((__packed__)) SECURITY_DESCRIPTOR_HEADER;
-
-/*
- * The $SDS data stream contains the security descriptors, aligned on 16-byte
- * boundaries, sorted by security_id in a B+ tree. Security descriptors cannot
- * cross 256kib boundaries (this restriction is imposed by the Windows cache
- * manager). Each security descriptor is contained in a SDS_ENTRY structure.
- * Also, each security descriptor is stored twice in the $SDS stream with a
- * fixed offset of 0x40000 bytes (256kib, the Windows cache manager's max size)
- * between them; i.e. if a SDS_ENTRY specifies an offset of 0x51d0, then the
- * first copy of the security descriptor will be at offset 0x51d0 in the
- * $SDS data stream and the second copy will be at offset 0x451d0.
- */
-typedef struct {
-/*Ofs*/
-/*  0	SECURITY_DESCRIPTOR_HEADER; -- Unfolded here as gcc doesn't like
-				       unnamed structs. */
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-	le64 offset;	  /* Byte offset of this entry in the $SDS stream. */
-	le32 length;	  /* Size in bytes of this entry in $SDS stream. */
-/* 20*/	SECURITY_DESCRIPTOR_RELATIVE sid; /* The self-relative security
-					     descriptor. */
-} __attribute__ ((__packed__)) SDS_ENTRY;
-
-/*
- * The index entry key used in the $SII index. The collation type is
- * COLLATION_NTOFS_ULONG.
- */
-typedef struct {
-	le32 security_id; /* The security_id assigned to the descriptor. */
-} __attribute__ ((__packed__)) SII_INDEX_KEY;
-
-/*
- * The index entry key used in the $SDH index. The keys are sorted first by
- * hash and then by security_id. The collation rule is
- * COLLATION_NTOFS_SECURITY_HASH.
- */
-typedef struct {
-	le32 hash;	  /* Hash of the security descriptor. */
-	le32 security_id; /* The security_id assigned to the descriptor. */
-} __attribute__ ((__packed__)) SDH_INDEX_KEY;
-
-/*
- * Attribute: Volume name (0x60).
- *
- * NOTE: Always resident.
- * NOTE: Present only in FILE_Volume.
- */
-typedef struct {
-	ntfschar name[0];	/* The name of the volume in Unicode. */
-} __attribute__ ((__packed__)) VOLUME_NAME;
-
-/*
- * Possible flags for the volume (16-bit).
- */
-enum {
-	VOLUME_IS_DIRTY			= cpu_to_le16(0x0001),
-	VOLUME_RESIZE_LOG_FILE		= cpu_to_le16(0x0002),
-	VOLUME_UPGRADE_ON_MOUNT		= cpu_to_le16(0x0004),
-	VOLUME_MOUNTED_ON_NT4		= cpu_to_le16(0x0008),
-
-	VOLUME_DELETE_USN_UNDERWAY	= cpu_to_le16(0x0010),
-	VOLUME_REPAIR_OBJECT_ID		= cpu_to_le16(0x0020),
-
-	VOLUME_CHKDSK_UNDERWAY		= cpu_to_le16(0x4000),
-	VOLUME_MODIFIED_BY_CHKDSK	= cpu_to_le16(0x8000),
-
-	VOLUME_FLAGS_MASK		= cpu_to_le16(0xc03f),
-
-	/* To make our life easier when checking if we must mount read-only. */
-	VOLUME_MUST_MOUNT_RO_MASK	= cpu_to_le16(0xc027),
-} __attribute__ ((__packed__));
-
-typedef le16 VOLUME_FLAGS;
-
-/*
- * Attribute: Volume information (0x70).
- *
- * NOTE: Always resident.
- * NOTE: Present only in FILE_Volume.
- * NOTE: Windows 2000 uses NTFS 3.0 while Windows NT4 service pack 6a uses
- *	 NTFS 1.2. I haven't personally seen other values yet.
- */
-typedef struct {
-	le64 reserved;		/* Not used (yet?). */
-	u8 major_ver;		/* Major version of the ntfs format. */
-	u8 minor_ver;		/* Minor version of the ntfs format. */
-	VOLUME_FLAGS flags;	/* Bit array of VOLUME_* flags. */
-} __attribute__ ((__packed__)) VOLUME_INFORMATION;
-
-/*
- * Attribute: Data attribute (0x80).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Data contents of a file (i.e. the unnamed stream) or of a named stream.
- */
-typedef struct {
-	u8 data[0];		/* The file's data contents. */
-} __attribute__ ((__packed__)) DATA_ATTR;
-
-/*
- * Index header flags (8-bit).
- */
-enum {
-	/*
-	 * When index header is in an index root attribute:
-	 */
-	SMALL_INDEX = 0, /* The index is small enough to fit inside the index
-			    root attribute and there is no index allocation
-			    attribute present. */
-	LARGE_INDEX = 1, /* The index is too large to fit in the index root
-			    attribute and/or an index allocation attribute is
-			    present. */
-	/*
-	 * When index header is in an index block, i.e. is part of index
-	 * allocation attribute:
-	 */
-	LEAF_NODE  = 0, /* This is a leaf node, i.e. there are no more nodes
-			   branching off it. */
-	INDEX_NODE = 1, /* This node indexes other nodes, i.e. it is not a leaf
-			   node. */
-	NODE_MASK  = 1, /* Mask for accessing the *_NODE bits. */
-} __attribute__ ((__packed__));
-
-typedef u8 INDEX_HEADER_FLAGS;
-
-/*
- * This is the header for indexes, describing the INDEX_ENTRY records, which
- * follow the INDEX_HEADER. Together the index header and the index entries
- * make up a complete index.
- *
- * IMPORTANT NOTE: The offset, length and size structure members are counted
- * relative to the start of the index header structure and not relative to the
- * start of the index root or index allocation structures themselves.
- */
-typedef struct {
-	le32 entries_offset;		/* Byte offset to first INDEX_ENTRY
-					   aligned to 8-byte boundary. */
-	le32 index_length;		/* Data size of the index in bytes,
-					   i.e. bytes used from allocated
-					   size, aligned to 8-byte boundary. */
-	le32 allocated_size;		/* Byte size of this index (block),
-					   multiple of 8 bytes. */
-	/* NOTE: For the index root attribute, the above two numbers are always
-	   equal, as the attribute is resident and it is resized as needed. In
-	   the case of the index allocation attribute the attribute is not
-	   resident and hence the allocated_size is a fixed value and must
-	   equal the index_block_size specified by the INDEX_ROOT attribute
-	   corresponding to the INDEX_ALLOCATION attribute this INDEX_BLOCK
-	   belongs to. */
-	INDEX_HEADER_FLAGS flags;	/* Bit field of INDEX_HEADER_FLAGS. */
-	u8 reserved[3];			/* Reserved/align to 8-byte boundary. */
-} __attribute__ ((__packed__)) INDEX_HEADER;
-
-/*
- * Attribute: Index root (0x90).
- *
- * NOTE: Always resident.
- *
- * This is followed by a sequence of index entries (INDEX_ENTRY structures)
- * as described by the index header.
- *
- * When a directory is small enough to fit inside the index root then this
- * is the only attribute describing the directory. When the directory is too
- * large to fit in the index root, on the other hand, two additional attributes
- * are present: an index allocation attribute, containing sub-nodes of the B+
- * directory tree (see below), and a bitmap attribute, describing which virtual
- * cluster numbers (vcns) in the index allocation attribute are in use by an
- * index block.
- *
- * NOTE: The root directory (FILE_root) contains an entry for itself. Other
- * directories do not contain entries for themselves, though.
- */
-typedef struct {
-	ATTR_TYPE type;			/* Type of the indexed attribute. Is
-					   $FILE_NAME for directories, zero
-					   for view indexes. No other values
-					   allowed. */
-	COLLATION_RULE collation_rule;	/* Collation rule used to sort the
-					   index entries. If type is $FILE_NAME,
-					   this must be COLLATION_FILE_NAME. */
-	le32 index_block_size;		/* Size of each index block in bytes (in
-					   the index allocation attribute). */
-	u8 clusters_per_index_block;	/* Cluster size of each index block (in
-					   the index allocation attribute), when
-					   an index block is >= than a cluster,
-					   otherwise this will be the log of
-					   the size (like how the encoding of
-					   the mft record size and the index
-					   record size found in the boot sector
-					   work). Has to be a power of 2. */
-	u8 reserved[3];			/* Reserved/align to 8-byte boundary. */
-	INDEX_HEADER index;		/* Index header describing the
-					   following index entries. */
-} __attribute__ ((__packed__)) INDEX_ROOT;
-
-/*
- * Attribute: Index allocation (0xa0).
- *
- * NOTE: Always non-resident (doesn't make sense to be resident anyway!).
- *
- * This is an array of index blocks. Each index block starts with an
- * INDEX_BLOCK structure containing an index header, followed by a sequence of
- * index entries (INDEX_ENTRY structures), as described by the INDEX_HEADER.
- */
-typedef struct {
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-	NTFS_RECORD_TYPE magic;	/* Magic is "INDX". */
-	le16 usa_ofs;		/* See NTFS_RECORD definition. */
-	le16 usa_count;		/* See NTFS_RECORD definition. */
-
-/*  8*/	sle64 lsn;		/* $LogFile sequence number of the last
-				   modification of this index block. */
-/* 16*/	leVCN index_block_vcn;	/* Virtual cluster number of the index block.
-				   If the cluster_size on the volume is <= the
-				   index_block_size of the directory,
-				   index_block_vcn counts in units of clusters,
-				   and in units of sectors otherwise. */
-/* 24*/	INDEX_HEADER index;	/* Describes the following index entries. */
-/* sizeof()= 40 (0x28) bytes */
-/*
- * When creating the index block, we place the update sequence array at this
- * offset, i.e. before we start with the index entries. This also makes sense,
- * otherwise we could run into problems with the update sequence array
- * containing in itself the last two bytes of a sector which would mean that
- * multi sector transfer protection wouldn't work. As you can't protect data
- * by overwriting it since you then can't get it back...
- * When reading use the data from the ntfs record header.
- */
-} __attribute__ ((__packed__)) INDEX_BLOCK;
-
-typedef INDEX_BLOCK INDEX_ALLOCATION;
-
-/*
- * The system file FILE_Extend/$Reparse contains an index named $R listing
- * all reparse points on the volume. The index entry keys are as defined
- * below. Note, that there is no index data associated with the index entries.
- *
- * The index entries are sorted by the index key file_id. The collation rule is
- * COLLATION_NTOFS_ULONGS. FIXME: Verify whether the reparse_tag is not the
- * primary key / is not a key at all. (AIA)
- */
-typedef struct {
-	le32 reparse_tag;	/* Reparse point type (inc. flags). */
-	leMFT_REF file_id;	/* Mft record of the file containing the
-				   reparse point attribute. */
-} __attribute__ ((__packed__)) REPARSE_INDEX_KEY;
-
-/*
- * Quota flags (32-bit).
- *
- * The user quota flags.  Names explain meaning.
- */
-enum {
-	QUOTA_FLAG_DEFAULT_LIMITS	= cpu_to_le32(0x00000001),
-	QUOTA_FLAG_LIMIT_REACHED	= cpu_to_le32(0x00000002),
-	QUOTA_FLAG_ID_DELETED		= cpu_to_le32(0x00000004),
-
-	QUOTA_FLAG_USER_MASK		= cpu_to_le32(0x00000007),
-	/* This is a bit mask for the user quota flags. */
-
-	/*
-	 * These flags are only present in the quota defaults index entry, i.e.
-	 * in the entry where owner_id = QUOTA_DEFAULTS_ID.
-	 */
-	QUOTA_FLAG_TRACKING_ENABLED	= cpu_to_le32(0x00000010),
-	QUOTA_FLAG_ENFORCEMENT_ENABLED	= cpu_to_le32(0x00000020),
-	QUOTA_FLAG_TRACKING_REQUESTED	= cpu_to_le32(0x00000040),
-	QUOTA_FLAG_LOG_THRESHOLD	= cpu_to_le32(0x00000080),
-
-	QUOTA_FLAG_LOG_LIMIT		= cpu_to_le32(0x00000100),
-	QUOTA_FLAG_OUT_OF_DATE		= cpu_to_le32(0x00000200),
-	QUOTA_FLAG_CORRUPT		= cpu_to_le32(0x00000400),
-	QUOTA_FLAG_PENDING_DELETES	= cpu_to_le32(0x00000800),
-};
-
-typedef le32 QUOTA_FLAGS;
-
-/*
- * The system file FILE_Extend/$Quota contains two indexes $O and $Q. Quotas
- * are on a per volume and per user basis.
- *
- * The $Q index contains one entry for each existing user_id on the volume. The
- * index key is the user_id of the user/group owning this quota control entry,
- * i.e. the key is the owner_id. The user_id of the owner of a file, i.e. the
- * owner_id, is found in the standard information attribute. The collation rule
- * for $Q is COLLATION_NTOFS_ULONG.
- *
- * The $O index contains one entry for each user/group who has been assigned
- * a quota on that volume. The index key holds the SID of the user_id the
- * entry belongs to, i.e. the owner_id. The collation rule for $O is
- * COLLATION_NTOFS_SID.
- *
- * The $O index entry data is the user_id of the user corresponding to the SID.
- * This user_id is used as an index into $Q to find the quota control entry
- * associated with the SID.
- *
- * The $Q index entry data is the quota control entry and is defined below.
- */
-typedef struct {
-	le32 version;		/* Currently equals 2. */
-	QUOTA_FLAGS flags;	/* Flags describing this quota entry. */
-	le64 bytes_used;	/* How many bytes of the quota are in use. */
-	sle64 change_time;	/* Last time this quota entry was changed. */
-	sle64 threshold;	/* Soft quota (-1 if not limited). */
-	sle64 limit;		/* Hard quota (-1 if not limited). */
-	sle64 exceeded_time;	/* How long the soft quota has been exceeded. */
-	SID sid;		/* The SID of the user/object associated with
-				   this quota entry.  Equals zero for the quota
-				   defaults entry (and in fact on a WinXP
-				   volume, it is not present at all). */
-} __attribute__ ((__packed__)) QUOTA_CONTROL_ENTRY;
-
-/*
- * Predefined owner_id values (32-bit).
- */
-enum {
-	QUOTA_INVALID_ID	= cpu_to_le32(0x00000000),
-	QUOTA_DEFAULTS_ID	= cpu_to_le32(0x00000001),
-	QUOTA_FIRST_USER_ID	= cpu_to_le32(0x00000100),
-};
-
-/*
- * Current constants for quota control entries.
- */
-typedef enum {
-	/* Current version. */
-	QUOTA_VERSION	= 2,
-} QUOTA_CONTROL_ENTRY_CONSTANTS;
-
-/*
- * Index entry flags (16-bit).
- */
-enum {
-	INDEX_ENTRY_NODE = cpu_to_le16(1), /* This entry contains a
-			sub-node, i.e. a reference to an index block in form of
-			a virtual cluster number (see below). */
-	INDEX_ENTRY_END  = cpu_to_le16(2), /* This signifies the last
-			entry in an index block.  The index entry does not
-			represent a file but it can point to a sub-node. */
-
-	INDEX_ENTRY_SPACE_FILLER = cpu_to_le16(0xffff), /* gcc: Force
-			enum bit width to 16-bit. */
-} __attribute__ ((__packed__));
-
-typedef le16 INDEX_ENTRY_FLAGS;
-
-/*
- * This the index entry header (see below).
- */
-typedef struct {
-/*  0*/	union {
-		struct { /* Only valid when INDEX_ENTRY_END is not set. */
-			leMFT_REF indexed_file;	/* The mft reference of the file
-						   described by this index
-						   entry. Used for directory
-						   indexes. */
-		} __attribute__ ((__packed__)) dir;
-		struct { /* Used for views/indexes to find the entry's data. */
-			le16 data_offset;	/* Data byte offset from this
-						   INDEX_ENTRY. Follows the
-						   index key. */
-			le16 data_length;	/* Data length in bytes. */
-			le32 reservedV;		/* Reserved (zero). */
-		} __attribute__ ((__packed__)) vi;
-	} __attribute__ ((__packed__)) data;
-/*  8*/	le16 length;		 /* Byte size of this index entry, multiple of
-				    8-bytes. */
-/* 10*/	le16 key_length;	 /* Byte size of the key value, which is in the
-				    index entry. It follows field reserved. Not
-				    multiple of 8-bytes. */
-/* 12*/	INDEX_ENTRY_FLAGS flags; /* Bit field of INDEX_ENTRY_* flags. */
-/* 14*/	le16 reserved;		 /* Reserved/align to 8-byte boundary. */
-/* sizeof() = 16 bytes */
-} __attribute__ ((__packed__)) INDEX_ENTRY_HEADER;
-
-/*
- * This is an index entry. A sequence of such entries follows each INDEX_HEADER
- * structure. Together they make up a complete index. The index follows either
- * an index root attribute or an index allocation attribute.
- *
- * NOTE: Before NTFS 3.0 only filename attributes were indexed.
- */
-typedef struct {
-/*Ofs*/
-/*  0	INDEX_ENTRY_HEADER; -- Unfolded here as gcc dislikes unnamed structs. */
-	union {
-		struct { /* Only valid when INDEX_ENTRY_END is not set. */
-			leMFT_REF indexed_file;	/* The mft reference of the file
-						   described by this index
-						   entry. Used for directory
-						   indexes. */
-		} __attribute__ ((__packed__)) dir;
-		struct { /* Used for views/indexes to find the entry's data. */
-			le16 data_offset;	/* Data byte offset from this
-						   INDEX_ENTRY. Follows the
-						   index key. */
-			le16 data_length;	/* Data length in bytes. */
-			le32 reservedV;		/* Reserved (zero). */
-		} __attribute__ ((__packed__)) vi;
-	} __attribute__ ((__packed__)) data;
-	le16 length;		 /* Byte size of this index entry, multiple of
-				    8-bytes. */
-	le16 key_length;	 /* Byte size of the key value, which is in the
-				    index entry. It follows field reserved. Not
-				    multiple of 8-bytes. */
-	INDEX_ENTRY_FLAGS flags; /* Bit field of INDEX_ENTRY_* flags. */
-	le16 reserved;		 /* Reserved/align to 8-byte boundary. */
-
-/* 16*/	union {		/* The key of the indexed attribute. NOTE: Only present
-			   if INDEX_ENTRY_END bit in flags is not set. NOTE: On
-			   NTFS versions before 3.0 the only valid key is the
-			   FILE_NAME_ATTR. On NTFS 3.0+ the following
-			   additional index keys are defined: */
-		FILE_NAME_ATTR file_name;/* $I30 index in directories. */
-		SII_INDEX_KEY sii;	/* $SII index in $Secure. */
-		SDH_INDEX_KEY sdh;	/* $SDH index in $Secure. */
-		GUID object_id;		/* $O index in FILE_Extend/$ObjId: The
-					   object_id of the mft record found in
-					   the data part of the index. */
-		REPARSE_INDEX_KEY reparse;	/* $R index in
-						   FILE_Extend/$Reparse. */
-		SID sid;		/* $O index in FILE_Extend/$Quota:
-					   SID of the owner of the user_id. */
-		le32 owner_id;		/* $Q index in FILE_Extend/$Quota:
-					   user_id of the owner of the quota
-					   control entry in the data part of
-					   the index. */
-	} __attribute__ ((__packed__)) key;
-	/* The (optional) index data is inserted here when creating. */
-	// leVCN vcn;	/* If INDEX_ENTRY_NODE bit in flags is set, the last
-	//		   eight bytes of this index entry contain the virtual
-	//		   cluster number of the index block that holds the
-	//		   entries immediately preceding the current entry (the
-	//		   vcn references the corresponding cluster in the data
-	//		   of the non-resident index allocation attribute). If
-	//		   the key_length is zero, then the vcn immediately
-	//		   follows the INDEX_ENTRY_HEADER. Regardless of
-	//		   key_length, the address of the 8-byte boundary
-	//		   aligned vcn of INDEX_ENTRY{_HEADER} *ie is given by
-	//		   (char*)ie + le16_to_cpu(ie*)->length) - sizeof(VCN),
-	//		   where sizeof(VCN) can be hardcoded as 8 if wanted. */
-} __attribute__ ((__packed__)) INDEX_ENTRY;
-
-/*
- * Attribute: Bitmap (0xb0).
- *
- * Contains an array of bits (aka a bitfield).
- *
- * When used in conjunction with the index allocation attribute, each bit
- * corresponds to one index block within the index allocation attribute. Thus
- * the number of bits in the bitmap * index block size / cluster size is the
- * number of clusters in the index allocation attribute.
- */
-typedef struct {
-	u8 bitmap[0];			/* Array of bits. */
-} __attribute__ ((__packed__)) BITMAP_ATTR;
-
-/*
- * The reparse point tag defines the type of the reparse point. It also
- * includes several flags, which further describe the reparse point.
- *
- * The reparse point tag is an unsigned 32-bit value divided in three parts:
- *
- * 1. The least significant 16 bits (i.e. bits 0 to 15) specifiy the type of
- *    the reparse point.
- * 2. The 13 bits after this (i.e. bits 16 to 28) are reserved for future use.
- * 3. The most significant three bits are flags describing the reparse point.
- *    They are defined as follows:
- *	bit 29: Name surrogate bit. If set, the filename is an alias for
- *		another object in the system.
- *	bit 30: High-latency bit. If set, accessing the first byte of data will
- *		be slow. (E.g. the data is stored on a tape drive.)
- *	bit 31: Microsoft bit. If set, the tag is owned by Microsoft. User
- *		defined tags have to use zero here.
- *
- * These are the predefined reparse point tags:
- */
-enum {
-	IO_REPARSE_TAG_IS_ALIAS		= cpu_to_le32(0x20000000),
-	IO_REPARSE_TAG_IS_HIGH_LATENCY	= cpu_to_le32(0x40000000),
-	IO_REPARSE_TAG_IS_MICROSOFT	= cpu_to_le32(0x80000000),
-
-	IO_REPARSE_TAG_RESERVED_ZERO	= cpu_to_le32(0x00000000),
-	IO_REPARSE_TAG_RESERVED_ONE	= cpu_to_le32(0x00000001),
-	IO_REPARSE_TAG_RESERVED_RANGE	= cpu_to_le32(0x00000001),
-
-	IO_REPARSE_TAG_NSS		= cpu_to_le32(0x68000005),
-	IO_REPARSE_TAG_NSS_RECOVER	= cpu_to_le32(0x68000006),
-	IO_REPARSE_TAG_SIS		= cpu_to_le32(0x68000007),
-	IO_REPARSE_TAG_DFS		= cpu_to_le32(0x68000008),
-
-	IO_REPARSE_TAG_MOUNT_POINT	= cpu_to_le32(0x88000003),
-
-	IO_REPARSE_TAG_HSM		= cpu_to_le32(0xa8000004),
-
-	IO_REPARSE_TAG_SYMBOLIC_LINK	= cpu_to_le32(0xe8000000),
-
-	IO_REPARSE_TAG_VALID_VALUES	= cpu_to_le32(0xe000ffff),
-};
-
-/*
- * Attribute: Reparse point (0xc0).
- *
- * NOTE: Can be resident or non-resident.
- */
-typedef struct {
-	le32 reparse_tag;		/* Reparse point type (inc. flags). */
-	le16 reparse_data_length;	/* Byte size of reparse data. */
-	le16 reserved;			/* Align to 8-byte boundary. */
-	u8 reparse_data[0];		/* Meaning depends on reparse_tag. */
-} __attribute__ ((__packed__)) REPARSE_POINT;
-
-/*
- * Attribute: Extended attribute (EA) information (0xd0).
- *
- * NOTE: Always resident. (Is this true???)
- */
-typedef struct {
-	le16 ea_length;		/* Byte size of the packed extended
-				   attributes. */
-	le16 need_ea_count;	/* The number of extended attributes which have
-				   the NEED_EA bit set. */
-	le32 ea_query_length;	/* Byte size of the buffer required to query
-				   the extended attributes when calling
-				   ZwQueryEaFile() in Windows NT/2k. I.e. the
-				   byte size of the unpacked extended
-				   attributes. */
-} __attribute__ ((__packed__)) EA_INFORMATION;
-
-/*
- * Extended attribute flags (8-bit).
- */
-enum {
-	NEED_EA	= 0x80		/* If set the file to which the EA belongs
-				   cannot be interpreted without understanding
-				   the associates extended attributes. */
-} __attribute__ ((__packed__));
-
-typedef u8 EA_FLAGS;
-
-/*
- * Attribute: Extended attribute (EA) (0xe0).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Like the attribute list and the index buffer list, the EA attribute value is
- * a sequence of EA_ATTR variable length records.
- */
-typedef struct {
-	le32 next_entry_offset;	/* Offset to the next EA_ATTR. */
-	EA_FLAGS flags;		/* Flags describing the EA. */
-	u8 ea_name_length;	/* Length of the name of the EA in bytes
-				   excluding the '\0' byte terminator. */
-	le16 ea_value_length;	/* Byte size of the EA's value. */
-	u8 ea_name[0];		/* Name of the EA.  Note this is ASCII, not
-				   Unicode and it is zero terminated. */
-	u8 ea_value[0];		/* The value of the EA.  Immediately follows
-				   the name. */
-} __attribute__ ((__packed__)) EA_ATTR;
-
-/*
- * Attribute: Property set (0xf0).
- *
- * Intended to support Native Structure Storage (NSS) - a feature removed from
- * NTFS 3.0 during beta testing.
- */
-typedef struct {
-	/* Irrelevant as feature unused. */
-} __attribute__ ((__packed__)) PROPERTY_SET;
-
-/*
- * Attribute: Logged utility stream (0x100).
- *
- * NOTE: Can be resident or non-resident.
- *
- * Operations on this attribute are logged to the journal ($LogFile) like
- * normal metadata changes.
- *
- * Used by the Encrypting File System (EFS). All encrypted files have this
- * attribute with the name $EFS.
- */
-typedef struct {
-	/* Can be anything the creator chooses. */
-	/* EFS uses it as follows: */
-	// FIXME: Type this info, verifying it along the way. (AIA)
-} __attribute__ ((__packed__)) LOGGED_UTILITY_STREAM, EFS_ATTR;
-
-#endif /* _LINUX_NTFS_LAYOUT_H */
diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c
deleted file mode 100644
index eda9972e6159..000000000000
--- a/fs/ntfs/lcnalloc.c
+++ /dev/null
@@ -1,1000 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * lcnalloc.c - Cluster (de)allocation code.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/pagemap.h>
-
-#include "lcnalloc.h"
-#include "debug.h"
-#include "bitmap.h"
-#include "inode.h"
-#include "volume.h"
-#include "attrib.h"
-#include "malloc.h"
-#include "aops.h"
-#include "ntfs.h"
-
-/**
- * ntfs_cluster_free_from_rl_nolock - free clusters from runlist
- * @vol:	mounted ntfs volume on which to free the clusters
- * @rl:		runlist describing the clusters to free
- *
- * Free all the clusters described by the runlist @rl on the volume @vol.  In
- * the case of an error being returned, at least some of the clusters were not
- * freed.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - The volume lcn bitmap must be locked for writing on entry and is
- *	      left locked on return.
- */
-int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
-		const runlist_element *rl)
-{
-	struct inode *lcnbmp_vi = vol->lcnbmp_ino;
-	int ret = 0;
-
-	ntfs_debug("Entering.");
-	if (!rl)
-		return 0;
-	for (; rl->length; rl++) {
-		int err;
-
-		if (rl->lcn < 0)
-			continue;
-		err = ntfs_bitmap_clear_run(lcnbmp_vi, rl->lcn, rl->length);
-		if (unlikely(err && (!ret || ret == -ENOMEM) && ret != err))
-			ret = err;
-	}
-	ntfs_debug("Done.");
-	return ret;
-}
-
-/**
- * ntfs_cluster_alloc - allocate clusters on an ntfs volume
- * @vol:	mounted ntfs volume on which to allocate the clusters
- * @start_vcn:	vcn to use for the first allocated cluster
- * @count:	number of clusters to allocate
- * @start_lcn:	starting lcn at which to allocate the clusters (or -1 if none)
- * @zone:	zone from which to allocate the clusters
- * @is_extension:	if 'true', this is an attribute extension
- *
- * Allocate @count clusters preferably starting at cluster @start_lcn or at the
- * current allocator position if @start_lcn is -1, on the mounted ntfs volume
- * @vol. @zone is either DATA_ZONE for allocation of normal clusters or
- * MFT_ZONE for allocation of clusters for the master file table, i.e. the
- * $MFT/$DATA attribute.
- *
- * @start_vcn specifies the vcn of the first allocated cluster.  This makes
- * merging the resulting runlist with the old runlist easier.
- *
- * If @is_extension is 'true', the caller is allocating clusters to extend an
- * attribute and if it is 'false', the caller is allocating clusters to fill a
- * hole in an attribute.  Practically the difference is that if @is_extension
- * is 'true' the returned runlist will be terminated with LCN_ENOENT and if
- * @is_extension is 'false' the runlist will be terminated with
- * LCN_RL_NOT_MAPPED.
- *
- * You need to check the return value with IS_ERR().  If this is false, the
- * function was successful and the return value is a runlist describing the
- * allocated cluster(s).  If IS_ERR() is true, the function failed and
- * PTR_ERR() gives you the error code.
- *
- * Notes on the allocation algorithm
- * =================================
- *
- * There are two data zones.  First is the area between the end of the mft zone
- * and the end of the volume, and second is the area between the start of the
- * volume and the start of the mft zone.  On unmodified/standard NTFS 1.x
- * volumes, the second data zone does not exist due to the mft zone being
- * expanded to cover the start of the volume in order to reserve space for the
- * mft bitmap attribute.
- *
- * This is not the prettiest function but the complexity stems from the need of
- * implementing the mft vs data zoned approach and from the fact that we have
- * access to the lcn bitmap in portions of up to 8192 bytes at a time, so we
- * need to cope with crossing over boundaries of two buffers.  Further, the
- * fact that the allocator allows for caller supplied hints as to the location
- * of where allocation should begin and the fact that the allocator keeps track
- * of where in the data zones the next natural allocation should occur,
- * contribute to the complexity of the function.  But it should all be
- * worthwhile, because this allocator should: 1) be a full implementation of
- * the MFT zone approach used by Windows NT, 2) cause reduction in
- * fragmentation, and 3) be speedy in allocations (the code is not optimized
- * for speed, but the algorithm is, so further speed improvements are probably
- * possible).
- *
- * FIXME: We should be monitoring cluster allocation and increment the MFT zone
- * size dynamically but this is something for the future.  We will just cause
- * heavier fragmentation by not doing it and I am not even sure Windows would
- * grow the MFT zone dynamically, so it might even be correct not to do this.
- * The overhead in doing dynamic MFT zone expansion would be very large and
- * unlikely worth the effort. (AIA)
- *
- * TODO: I have added in double the required zone position pointer wrap around
- * logic which can be optimized to having only one of the two logic sets.
- * However, having the double logic will work fine, but if we have only one of
- * the sets and we get it wrong somewhere, then we get into trouble, so
- * removing the duplicate logic requires _very_ careful consideration of _all_
- * possible code paths.  So at least for now, I am leaving the double logic -
- * better safe than sorry... (AIA)
- *
- * Locking: - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- */
-runlist_element *ntfs_cluster_alloc(ntfs_volume *vol, const VCN start_vcn,
-		const s64 count, const LCN start_lcn,
-		const NTFS_CLUSTER_ALLOCATION_ZONES zone,
-		const bool is_extension)
-{
-	LCN zone_start, zone_end, bmp_pos, bmp_initial_pos, last_read_pos, lcn;
-	LCN prev_lcn = 0, prev_run_len = 0, mft_zone_size;
-	s64 clusters;
-	loff_t i_size;
-	struct inode *lcnbmp_vi;
-	runlist_element *rl = NULL;
-	struct address_space *mapping;
-	struct page *page = NULL;
-	u8 *buf, *byte;
-	int err = 0, rlpos, rlsize, buf_size;
-	u8 pass, done_zones, search_zone, need_writeback = 0, bit;
-
-	ntfs_debug("Entering for start_vcn 0x%llx, count 0x%llx, start_lcn "
-			"0x%llx, zone %s_ZONE.", (unsigned long long)start_vcn,
-			(unsigned long long)count,
-			(unsigned long long)start_lcn,
-			zone == MFT_ZONE ? "MFT" : "DATA");
-	BUG_ON(!vol);
-	lcnbmp_vi = vol->lcnbmp_ino;
-	BUG_ON(!lcnbmp_vi);
-	BUG_ON(start_vcn < 0);
-	BUG_ON(count < 0);
-	BUG_ON(start_lcn < -1);
-	BUG_ON(zone < FIRST_ZONE);
-	BUG_ON(zone > LAST_ZONE);
-
-	/* Return NULL if @count is zero. */
-	if (!count)
-		return NULL;
-	/* Take the lcnbmp lock for writing. */
-	down_write(&vol->lcnbmp_lock);
-	/*
-	 * If no specific @start_lcn was requested, use the current data zone
-	 * position, otherwise use the requested @start_lcn but make sure it
-	 * lies outside the mft zone.  Also set done_zones to 0 (no zones done)
-	 * and pass depending on whether we are starting inside a zone (1) or
-	 * at the beginning of a zone (2).  If requesting from the MFT_ZONE,
-	 * we either start at the current position within the mft zone or at
-	 * the specified position.  If the latter is out of bounds then we start
-	 * at the beginning of the MFT_ZONE.
-	 */
-	done_zones = 0;
-	pass = 1;
-	/*
-	 * zone_start and zone_end are the current search range.  search_zone
-	 * is 1 for mft zone, 2 for data zone 1 (end of mft zone till end of
-	 * volume) and 4 for data zone 2 (start of volume till start of mft
-	 * zone).
-	 */
-	zone_start = start_lcn;
-	if (zone_start < 0) {
-		if (zone == DATA_ZONE)
-			zone_start = vol->data1_zone_pos;
-		else
-			zone_start = vol->mft_zone_pos;
-		if (!zone_start) {
-			/*
-			 * Zone starts at beginning of volume which means a
-			 * single pass is sufficient.
-			 */
-			pass = 2;
-		}
-	} else if (zone == DATA_ZONE && zone_start >= vol->mft_zone_start &&
-			zone_start < vol->mft_zone_end) {
-		zone_start = vol->mft_zone_end;
-		/*
-		 * Starting at beginning of data1_zone which means a single
-		 * pass in this zone is sufficient.
-		 */
-		pass = 2;
-	} else if (zone == MFT_ZONE && (zone_start < vol->mft_zone_start ||
-			zone_start >= vol->mft_zone_end)) {
-		zone_start = vol->mft_lcn;
-		if (!vol->mft_zone_end)
-			zone_start = 0;
-		/*
-		 * Starting at beginning of volume which means a single pass
-		 * is sufficient.
-		 */
-		pass = 2;
-	}
-	if (zone == MFT_ZONE) {
-		zone_end = vol->mft_zone_end;
-		search_zone = 1;
-	} else /* if (zone == DATA_ZONE) */ {
-		/* Skip searching the mft zone. */
-		done_zones |= 1;
-		if (zone_start >= vol->mft_zone_end) {
-			zone_end = vol->nr_clusters;
-			search_zone = 2;
-		} else {
-			zone_end = vol->mft_zone_start;
-			search_zone = 4;
-		}
-	}
-	/*
-	 * bmp_pos is the current bit position inside the bitmap.  We use
-	 * bmp_initial_pos to determine whether or not to do a zone switch.
-	 */
-	bmp_pos = bmp_initial_pos = zone_start;
-
-	/* Loop until all clusters are allocated, i.e. clusters == 0. */
-	clusters = count;
-	rlpos = rlsize = 0;
-	mapping = lcnbmp_vi->i_mapping;
-	i_size = i_size_read(lcnbmp_vi);
-	while (1) {
-		ntfs_debug("Start of outer while loop: done_zones 0x%x, "
-				"search_zone %i, pass %i, zone_start 0x%llx, "
-				"zone_end 0x%llx, bmp_initial_pos 0x%llx, "
-				"bmp_pos 0x%llx, rlpos %i, rlsize %i.",
-				done_zones, search_zone, pass,
-				(unsigned long long)zone_start,
-				(unsigned long long)zone_end,
-				(unsigned long long)bmp_initial_pos,
-				(unsigned long long)bmp_pos, rlpos, rlsize);
-		/* Loop until we run out of free clusters. */
-		last_read_pos = bmp_pos >> 3;
-		ntfs_debug("last_read_pos 0x%llx.",
-				(unsigned long long)last_read_pos);
-		if (last_read_pos > i_size) {
-			ntfs_debug("End of attribute reached.  "
-					"Skipping to zone_pass_done.");
-			goto zone_pass_done;
-		}
-		if (likely(page)) {
-			if (need_writeback) {
-				ntfs_debug("Marking page dirty.");
-				flush_dcache_page(page);
-				set_page_dirty(page);
-				need_writeback = 0;
-			}
-			ntfs_unmap_page(page);
-		}
-		page = ntfs_map_page(mapping, last_read_pos >>
-				PAGE_SHIFT);
-		if (IS_ERR(page)) {
-			err = PTR_ERR(page);
-			ntfs_error(vol->sb, "Failed to map page.");
-			goto out;
-		}
-		buf_size = last_read_pos & ~PAGE_MASK;
-		buf = page_address(page) + buf_size;
-		buf_size = PAGE_SIZE - buf_size;
-		if (unlikely(last_read_pos + buf_size > i_size))
-			buf_size = i_size - last_read_pos;
-		buf_size <<= 3;
-		lcn = bmp_pos & 7;
-		bmp_pos &= ~(LCN)7;
-		ntfs_debug("Before inner while loop: buf_size %i, lcn 0x%llx, "
-				"bmp_pos 0x%llx, need_writeback %i.", buf_size,
-				(unsigned long long)lcn,
-				(unsigned long long)bmp_pos, need_writeback);
-		while (lcn < buf_size && lcn + bmp_pos < zone_end) {
-			byte = buf + (lcn >> 3);
-			ntfs_debug("In inner while loop: buf_size %i, "
-					"lcn 0x%llx, bmp_pos 0x%llx, "
-					"need_writeback %i, byte ofs 0x%x, "
-					"*byte 0x%x.", buf_size,
-					(unsigned long long)lcn,
-					(unsigned long long)bmp_pos,
-					need_writeback,
-					(unsigned int)(lcn >> 3),
-					(unsigned int)*byte);
-			/* Skip full bytes. */
-			if (*byte == 0xff) {
-				lcn = (lcn + 8) & ~(LCN)7;
-				ntfs_debug("Continuing while loop 1.");
-				continue;
-			}
-			bit = 1 << (lcn & 7);
-			ntfs_debug("bit 0x%x.", bit);
-			/* If the bit is already set, go onto the next one. */
-			if (*byte & bit) {
-				lcn++;
-				ntfs_debug("Continuing while loop 2.");
-				continue;
-			}
-			/*
-			 * Allocate more memory if needed, including space for
-			 * the terminator element.
-			 * ntfs_malloc_nofs() operates on whole pages only.
-			 */
-			if ((rlpos + 2) * sizeof(*rl) > rlsize) {
-				runlist_element *rl2;
-
-				ntfs_debug("Reallocating memory.");
-				if (!rl)
-					ntfs_debug("First free bit is at LCN "
-							"0x%llx.",
-							(unsigned long long)
-							(lcn + bmp_pos));
-				rl2 = ntfs_malloc_nofs(rlsize + (int)PAGE_SIZE);
-				if (unlikely(!rl2)) {
-					err = -ENOMEM;
-					ntfs_error(vol->sb, "Failed to "
-							"allocate memory.");
-					goto out;
-				}
-				memcpy(rl2, rl, rlsize);
-				ntfs_free(rl);
-				rl = rl2;
-				rlsize += PAGE_SIZE;
-				ntfs_debug("Reallocated memory, rlsize 0x%x.",
-						rlsize);
-			}
-			/* Allocate the bitmap bit. */
-			*byte |= bit;
-			/* We need to write this bitmap page to disk. */
-			need_writeback = 1;
-			ntfs_debug("*byte 0x%x, need_writeback is set.",
-					(unsigned int)*byte);
-			/*
-			 * Coalesce with previous run if adjacent LCNs.
-			 * Otherwise, append a new run.
-			 */
-			ntfs_debug("Adding run (lcn 0x%llx, len 0x%llx), "
-					"prev_lcn 0x%llx, lcn 0x%llx, "
-					"bmp_pos 0x%llx, prev_run_len 0x%llx, "
-					"rlpos %i.",
-					(unsigned long long)(lcn + bmp_pos),
-					1ULL, (unsigned long long)prev_lcn,
-					(unsigned long long)lcn,
-					(unsigned long long)bmp_pos,
-					(unsigned long long)prev_run_len,
-					rlpos);
-			if (prev_lcn == lcn + bmp_pos - prev_run_len && rlpos) {
-				ntfs_debug("Coalescing to run (lcn 0x%llx, "
-						"len 0x%llx).",
-						(unsigned long long)
-						rl[rlpos - 1].lcn,
-						(unsigned long long)
-						rl[rlpos - 1].length);
-				rl[rlpos - 1].length = ++prev_run_len;
-				ntfs_debug("Run now (lcn 0x%llx, len 0x%llx), "
-						"prev_run_len 0x%llx.",
-						(unsigned long long)
-						rl[rlpos - 1].lcn,
-						(unsigned long long)
-						rl[rlpos - 1].length,
-						(unsigned long long)
-						prev_run_len);
-			} else {
-				if (likely(rlpos)) {
-					ntfs_debug("Adding new run, (previous "
-							"run lcn 0x%llx, "
-							"len 0x%llx).",
-							(unsigned long long)
-							rl[rlpos - 1].lcn,
-							(unsigned long long)
-							rl[rlpos - 1].length);
-					rl[rlpos].vcn = rl[rlpos - 1].vcn +
-							prev_run_len;
-				} else {
-					ntfs_debug("Adding new run, is first "
-							"run.");
-					rl[rlpos].vcn = start_vcn;
-				}
-				rl[rlpos].lcn = prev_lcn = lcn + bmp_pos;
-				rl[rlpos].length = prev_run_len = 1;
-				rlpos++;
-			}
-			/* Done? */
-			if (!--clusters) {
-				LCN tc;
-				/*
-				 * Update the current zone position.  Positions
-				 * of already scanned zones have been updated
-				 * during the respective zone switches.
-				 */
-				tc = lcn + bmp_pos + 1;
-				ntfs_debug("Done. Updating current zone "
-						"position, tc 0x%llx, "
-						"search_zone %i.",
-						(unsigned long long)tc,
-						search_zone);
-				switch (search_zone) {
-				case 1:
-					ntfs_debug("Before checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					if (tc >= vol->mft_zone_end) {
-						vol->mft_zone_pos =
-								vol->mft_lcn;
-						if (!vol->mft_zone_end)
-							vol->mft_zone_pos = 0;
-					} else if ((bmp_initial_pos >=
-							vol->mft_zone_pos ||
-							tc > vol->mft_zone_pos)
-							&& tc >= vol->mft_lcn)
-						vol->mft_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					break;
-				case 2:
-					ntfs_debug("Before checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					if (tc >= vol->nr_clusters)
-						vol->data1_zone_pos =
-							     vol->mft_zone_end;
-					else if ((bmp_initial_pos >=
-						    vol->data1_zone_pos ||
-						    tc > vol->data1_zone_pos)
-						    && tc >= vol->mft_zone_end)
-						vol->data1_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					break;
-				case 4:
-					ntfs_debug("Before checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					if (tc >= vol->mft_zone_start)
-						vol->data2_zone_pos = 0;
-					else if (bmp_initial_pos >=
-						      vol->data2_zone_pos ||
-						      tc > vol->data2_zone_pos)
-						vol->data2_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					break;
-				default:
-					BUG();
-				}
-				ntfs_debug("Finished.  Going to out.");
-				goto out;
-			}
-			lcn++;
-		}
-		bmp_pos += buf_size;
-		ntfs_debug("After inner while loop: buf_size 0x%x, lcn "
-				"0x%llx, bmp_pos 0x%llx, need_writeback %i.",
-				buf_size, (unsigned long long)lcn,
-				(unsigned long long)bmp_pos, need_writeback);
-		if (bmp_pos < zone_end) {
-			ntfs_debug("Continuing outer while loop, "
-					"bmp_pos 0x%llx, zone_end 0x%llx.",
-					(unsigned long long)bmp_pos,
-					(unsigned long long)zone_end);
-			continue;
-		}
-zone_pass_done:	/* Finished with the current zone pass. */
-		ntfs_debug("At zone_pass_done, pass %i.", pass);
-		if (pass == 1) {
-			/*
-			 * Now do pass 2, scanning the first part of the zone
-			 * we omitted in pass 1.
-			 */
-			pass = 2;
-			zone_end = zone_start;
-			switch (search_zone) {
-			case 1: /* mft_zone */
-				zone_start = vol->mft_zone_start;
-				break;
-			case 2: /* data1_zone */
-				zone_start = vol->mft_zone_end;
-				break;
-			case 4: /* data2_zone */
-				zone_start = 0;
-				break;
-			default:
-				BUG();
-			}
-			/* Sanity check. */
-			if (zone_end < zone_start)
-				zone_end = zone_start;
-			bmp_pos = zone_start;
-			ntfs_debug("Continuing outer while loop, pass 2, "
-					"zone_start 0x%llx, zone_end 0x%llx, "
-					"bmp_pos 0x%llx.",
-					(unsigned long long)zone_start,
-					(unsigned long long)zone_end,
-					(unsigned long long)bmp_pos);
-			continue;
-		} /* pass == 2 */
-done_zones_check:
-		ntfs_debug("At done_zones_check, search_zone %i, done_zones "
-				"before 0x%x, done_zones after 0x%x.",
-				search_zone, done_zones,
-				done_zones | search_zone);
-		done_zones |= search_zone;
-		if (done_zones < 7) {
-			ntfs_debug("Switching zone.");
-			/* Now switch to the next zone we haven't done yet. */
-			pass = 1;
-			switch (search_zone) {
-			case 1:
-				ntfs_debug("Switching from mft zone to data1 "
-						"zone.");
-				/* Update mft zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->mft_zone_end) {
-						vol->mft_zone_pos =
-								vol->mft_lcn;
-						if (!vol->mft_zone_end)
-							vol->mft_zone_pos = 0;
-					} else if ((bmp_initial_pos >=
-							vol->mft_zone_pos ||
-							tc > vol->mft_zone_pos)
-							&& tc >= vol->mft_lcn)
-						vol->mft_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->mft_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->mft_zone_pos);
-				}
-				/* Switch from mft zone to data1 zone. */
-switch_to_data1_zone:		search_zone = 2;
-				zone_start = bmp_initial_pos =
-						vol->data1_zone_pos;
-				zone_end = vol->nr_clusters;
-				if (zone_start == vol->mft_zone_end)
-					pass = 2;
-				if (zone_start >= zone_end) {
-					vol->data1_zone_pos = zone_start =
-							vol->mft_zone_end;
-					pass = 2;
-				}
-				break;
-			case 2:
-				ntfs_debug("Switching from data1 zone to "
-						"data2 zone.");
-				/* Update data1 zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->nr_clusters)
-						vol->data1_zone_pos =
-							     vol->mft_zone_end;
-					else if ((bmp_initial_pos >=
-						    vol->data1_zone_pos ||
-						    tc > vol->data1_zone_pos)
-						    && tc >= vol->mft_zone_end)
-						vol->data1_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data1_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data1_zone_pos);
-				}
-				/* Switch from data1 zone to data2 zone. */
-				search_zone = 4;
-				zone_start = bmp_initial_pos =
-						vol->data2_zone_pos;
-				zone_end = vol->mft_zone_start;
-				if (!zone_start)
-					pass = 2;
-				if (zone_start >= zone_end) {
-					vol->data2_zone_pos = zone_start =
-							bmp_initial_pos = 0;
-					pass = 2;
-				}
-				break;
-			case 4:
-				ntfs_debug("Switching from data2 zone to "
-						"data1 zone.");
-				/* Update data2 zone position. */
-				if (rlpos) {
-					LCN tc;
-
-					ntfs_debug("Before checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-					tc = rl[rlpos - 1].lcn +
-							rl[rlpos - 1].length;
-					if (tc >= vol->mft_zone_start)
-						vol->data2_zone_pos = 0;
-					else if (bmp_initial_pos >=
-						      vol->data2_zone_pos ||
-						      tc > vol->data2_zone_pos)
-						vol->data2_zone_pos = tc;
-					ntfs_debug("After checks, "
-							"vol->data2_zone_pos "
-							"0x%llx.",
-							(unsigned long long)
-							vol->data2_zone_pos);
-				}
-				/* Switch from data2 zone to data1 zone. */
-				goto switch_to_data1_zone;
-			default:
-				BUG();
-			}
-			ntfs_debug("After zone switch, search_zone %i, "
-					"pass %i, bmp_initial_pos 0x%llx, "
-					"zone_start 0x%llx, zone_end 0x%llx.",
-					search_zone, pass,
-					(unsigned long long)bmp_initial_pos,
-					(unsigned long long)zone_start,
-					(unsigned long long)zone_end);
-			bmp_pos = zone_start;
-			if (zone_start == zone_end) {
-				ntfs_debug("Empty zone, going to "
-						"done_zones_check.");
-				/* Empty zone. Don't bother searching it. */
-				goto done_zones_check;
-			}
-			ntfs_debug("Continuing outer while loop.");
-			continue;
-		} /* done_zones == 7 */
-		ntfs_debug("All zones are finished.");
-		/*
-		 * All zones are finished!  If DATA_ZONE, shrink mft zone.  If
-		 * MFT_ZONE, we have really run out of space.
-		 */
-		mft_zone_size = vol->mft_zone_end - vol->mft_zone_start;
-		ntfs_debug("vol->mft_zone_start 0x%llx, vol->mft_zone_end "
-				"0x%llx, mft_zone_size 0x%llx.",
-				(unsigned long long)vol->mft_zone_start,
-				(unsigned long long)vol->mft_zone_end,
-				(unsigned long long)mft_zone_size);
-		if (zone == MFT_ZONE || mft_zone_size <= 0) {
-			ntfs_debug("No free clusters left, going to out.");
-			/* Really no more space left on device. */
-			err = -ENOSPC;
-			goto out;
-		} /* zone == DATA_ZONE && mft_zone_size > 0 */
-		ntfs_debug("Shrinking mft zone.");
-		zone_end = vol->mft_zone_end;
-		mft_zone_size >>= 1;
-		if (mft_zone_size > 0)
-			vol->mft_zone_end = vol->mft_zone_start + mft_zone_size;
-		else /* mft zone and data2 zone no longer exist. */
-			vol->data2_zone_pos = vol->mft_zone_start =
-					vol->mft_zone_end = 0;
-		if (vol->mft_zone_pos >= vol->mft_zone_end) {
-			vol->mft_zone_pos = vol->mft_lcn;
-			if (!vol->mft_zone_end)
-				vol->mft_zone_pos = 0;
-		}
-		bmp_pos = zone_start = bmp_initial_pos =
-				vol->data1_zone_pos = vol->mft_zone_end;
-		search_zone = 2;
-		pass = 2;
-		done_zones &= ~2;
-		ntfs_debug("After shrinking mft zone, mft_zone_size 0x%llx, "
-				"vol->mft_zone_start 0x%llx, "
-				"vol->mft_zone_end 0x%llx, "
-				"vol->mft_zone_pos 0x%llx, search_zone 2, "
-				"pass 2, dones_zones 0x%x, zone_start 0x%llx, "
-				"zone_end 0x%llx, vol->data1_zone_pos 0x%llx, "
-				"continuing outer while loop.",
-				(unsigned long long)mft_zone_size,
-				(unsigned long long)vol->mft_zone_start,
-				(unsigned long long)vol->mft_zone_end,
-				(unsigned long long)vol->mft_zone_pos,
-				done_zones, (unsigned long long)zone_start,
-				(unsigned long long)zone_end,
-				(unsigned long long)vol->data1_zone_pos);
-	}
-	ntfs_debug("After outer while loop.");
-out:
-	ntfs_debug("At out.");
-	/* Add runlist terminator element. */
-	if (likely(rl)) {
-		rl[rlpos].vcn = rl[rlpos - 1].vcn + rl[rlpos - 1].length;
-		rl[rlpos].lcn = is_extension ? LCN_ENOENT : LCN_RL_NOT_MAPPED;
-		rl[rlpos].length = 0;
-	}
-	if (likely(page && !IS_ERR(page))) {
-		if (need_writeback) {
-			ntfs_debug("Marking page dirty.");
-			flush_dcache_page(page);
-			set_page_dirty(page);
-			need_writeback = 0;
-		}
-		ntfs_unmap_page(page);
-	}
-	if (likely(!err)) {
-		up_write(&vol->lcnbmp_lock);
-		ntfs_debug("Done.");
-		return rl;
-	}
-	ntfs_error(vol->sb, "Failed to allocate clusters, aborting "
-			"(error %i).", err);
-	if (rl) {
-		int err2;
-
-		if (err == -ENOSPC)
-			ntfs_debug("Not enough space to complete allocation, "
-					"err -ENOSPC, first free lcn 0x%llx, "
-					"could allocate up to 0x%llx "
-					"clusters.",
-					(unsigned long long)rl[0].lcn,
-					(unsigned long long)(count - clusters));
-		/* Deallocate all allocated clusters. */
-		ntfs_debug("Attempting rollback...");
-		err2 = ntfs_cluster_free_from_rl_nolock(vol, rl);
-		if (err2) {
-			ntfs_error(vol->sb, "Failed to rollback (error %i).  "
-					"Leaving inconsistent metadata!  "
-					"Unmount and run chkdsk.", err2);
-			NVolSetErrors(vol);
-		}
-		/* Free the runlist. */
-		ntfs_free(rl);
-	} else if (err == -ENOSPC)
-		ntfs_debug("No space left at all, err = -ENOSPC, first free "
-				"lcn = 0x%llx.",
-				(long long)vol->data1_zone_pos);
-	up_write(&vol->lcnbmp_lock);
-	return ERR_PTR(err);
-}
-
-/**
- * __ntfs_cluster_free - free clusters on an ntfs volume
- * @ni:		ntfs inode whose runlist describes the clusters to free
- * @start_vcn:	vcn in the runlist of @ni at which to start freeing clusters
- * @count:	number of clusters to free or -1 for all clusters
- * @ctx:	active attribute search context if present or NULL if not
- * @is_rollback:	true if this is a rollback operation
- *
- * Free @count clusters starting at the cluster @start_vcn in the runlist
- * described by the vfs inode @ni.
- *
- * If @count is -1, all clusters from @start_vcn to the end of the runlist are
- * deallocated.  Thus, to completely free all clusters in a runlist, use
- * @start_vcn = 0 and @count = -1.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when __ntfs_cluster_free() encounters unmapped
- * runlist fragments and allows their mapping.  If you do not have the mft
- * record mapped, you can specify @ctx as NULL and __ntfs_cluster_free() will
- * perform the necessary mapping and unmapping.
- *
- * Note, __ntfs_cluster_free() saves the state of @ctx on entry and restores it
- * before returning.  Thus, @ctx will be left pointing to the same attribute on
- * return as on entry.  However, the actual pointers in @ctx may point to
- * different memory locations on return, so you must remember to reset any
- * cached pointers from the @ctx, i.e. after the call to __ntfs_cluster_free(),
- * you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * @is_rollback should always be 'false', it is for internal use to rollback
- * errors.  You probably want to use ntfs_cluster_free() instead.
- *
- * Note, __ntfs_cluster_free() does not modify the runlist, so you have to
- * remove from the runlist or mark sparse the freed runs later.
- *
- * Return the number of deallocated clusters (not counting sparse ones) on
- * success and -errno on error.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn, s64 count,
-		ntfs_attr_search_ctx *ctx, const bool is_rollback)
-{
-	s64 delta, to_free, total_freed, real_freed;
-	ntfs_volume *vol;
-	struct inode *lcnbmp_vi;
-	runlist_element *rl;
-	int err;
-
-	BUG_ON(!ni);
-	ntfs_debug("Entering for i_ino 0x%lx, start_vcn 0x%llx, count "
-			"0x%llx.%s", ni->mft_no, (unsigned long long)start_vcn,
-			(unsigned long long)count,
-			is_rollback ? " (rollback)" : "");
-	vol = ni->vol;
-	lcnbmp_vi = vol->lcnbmp_ino;
-	BUG_ON(!lcnbmp_vi);
-	BUG_ON(start_vcn < 0);
-	BUG_ON(count < -1);
-	/*
-	 * Lock the lcn bitmap for writing but only if not rolling back.  We
-	 * must hold the lock all the way including through rollback otherwise
-	 * rollback is not possible because once we have cleared a bit and
-	 * dropped the lock, anyone could have set the bit again, thus
-	 * allocating the cluster for another use.
-	 */
-	if (likely(!is_rollback))
-		down_write(&vol->lcnbmp_lock);
-
-	total_freed = real_freed = 0;
-
-	rl = ntfs_attr_find_vcn_nolock(ni, start_vcn, ctx);
-	if (IS_ERR(rl)) {
-		if (!is_rollback)
-			ntfs_error(vol->sb, "Failed to find first runlist "
-					"element (error %li), aborting.",
-					PTR_ERR(rl));
-		err = PTR_ERR(rl);
-		goto err_out;
-	}
-	if (unlikely(rl->lcn < LCN_HOLE)) {
-		if (!is_rollback)
-			ntfs_error(vol->sb, "First runlist element has "
-					"invalid lcn, aborting.");
-		err = -EIO;
-		goto err_out;
-	}
-	/* Find the starting cluster inside the run that needs freeing. */
-	delta = start_vcn - rl->vcn;
-
-	/* The number of clusters in this run that need freeing. */
-	to_free = rl->length - delta;
-	if (count >= 0 && to_free > count)
-		to_free = count;
-
-	if (likely(rl->lcn >= 0)) {
-		/* Do the actual freeing of the clusters in this run. */
-		err = ntfs_bitmap_set_bits_in_run(lcnbmp_vi, rl->lcn + delta,
-				to_free, likely(!is_rollback) ? 0 : 1);
-		if (unlikely(err)) {
-			if (!is_rollback)
-				ntfs_error(vol->sb, "Failed to clear first run "
-						"(error %i), aborting.", err);
-			goto err_out;
-		}
-		/* We have freed @to_free real clusters. */
-		real_freed = to_free;
-	};
-	/* Go to the next run and adjust the number of clusters left to free. */
-	++rl;
-	if (count >= 0)
-		count -= to_free;
-
-	/* Keep track of the total "freed" clusters, including sparse ones. */
-	total_freed = to_free;
-	/*
-	 * Loop over the remaining runs, using @count as a capping value, and
-	 * free them.
-	 */
-	for (; rl->length && count != 0; ++rl) {
-		if (unlikely(rl->lcn < LCN_HOLE)) {
-			VCN vcn;
-
-			/* Attempt to map runlist. */
-			vcn = rl->vcn;
-			rl = ntfs_attr_find_vcn_nolock(ni, vcn, ctx);
-			if (IS_ERR(rl)) {
-				err = PTR_ERR(rl);
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Failed to map "
-							"runlist fragment or "
-							"failed to find "
-							"subsequent runlist "
-							"element.");
-				goto err_out;
-			}
-			if (unlikely(rl->lcn < LCN_HOLE)) {
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Runlist element "
-							"has invalid lcn "
-							"(0x%llx).",
-							(unsigned long long)
-							rl->lcn);
-				err = -EIO;
-				goto err_out;
-			}
-		}
-		/* The number of clusters in this run that need freeing. */
-		to_free = rl->length;
-		if (count >= 0 && to_free > count)
-			to_free = count;
-
-		if (likely(rl->lcn >= 0)) {
-			/* Do the actual freeing of the clusters in the run. */
-			err = ntfs_bitmap_set_bits_in_run(lcnbmp_vi, rl->lcn,
-					to_free, likely(!is_rollback) ? 0 : 1);
-			if (unlikely(err)) {
-				if (!is_rollback)
-					ntfs_error(vol->sb, "Failed to clear "
-							"subsequent run.");
-				goto err_out;
-			}
-			/* We have freed @to_free real clusters. */
-			real_freed += to_free;
-		}
-		/* Adjust the number of clusters left to free. */
-		if (count >= 0)
-			count -= to_free;
-	
-		/* Update the total done clusters. */
-		total_freed += to_free;
-	}
-	if (likely(!is_rollback))
-		up_write(&vol->lcnbmp_lock);
-
-	BUG_ON(count > 0);
-
-	/* We are done.  Return the number of actually freed clusters. */
-	ntfs_debug("Done.");
-	return real_freed;
-err_out:
-	if (is_rollback)
-		return err;
-	/* If no real clusters were freed, no need to rollback. */
-	if (!real_freed) {
-		up_write(&vol->lcnbmp_lock);
-		return err;
-	}
-	/*
-	 * Attempt to rollback and if that succeeds just return the error code.
-	 * If rollback fails, set the volume errors flag, emit an error
-	 * message, and return the error code.
-	 */
-	delta = __ntfs_cluster_free(ni, start_vcn, total_freed, ctx, true);
-	if (delta < 0) {
-		ntfs_error(vol->sb, "Failed to rollback (error %i).  Leaving "
-				"inconsistent metadata!  Unmount and run "
-				"chkdsk.", (int)delta);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->lcnbmp_lock);
-	ntfs_error(vol->sb, "Aborting (error %i).", err);
-	return err;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h
deleted file mode 100644
index 1589a6d8434b..000000000000
--- a/fs/ntfs/lcnalloc.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * lcnalloc.h - Exports for NTFS kernel cluster (de)allocation.  Part of the
- *		Linux-NTFS project.
- *
- * Copyright (c) 2004-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_LCNALLOC_H
-#define _LINUX_NTFS_LCNALLOC_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "attrib.h"
-#include "types.h"
-#include "inode.h"
-#include "runlist.h"
-#include "volume.h"
-
-typedef enum {
-	FIRST_ZONE	= 0,	/* For sanity checking. */
-	MFT_ZONE	= 0,	/* Allocate from $MFT zone. */
-	DATA_ZONE	= 1,	/* Allocate from $DATA zone. */
-	LAST_ZONE	= 1,	/* For sanity checking. */
-} NTFS_CLUSTER_ALLOCATION_ZONES;
-
-extern runlist_element *ntfs_cluster_alloc(ntfs_volume *vol,
-		const VCN start_vcn, const s64 count, const LCN start_lcn,
-		const NTFS_CLUSTER_ALLOCATION_ZONES zone,
-		const bool is_extension);
-
-extern s64 __ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-		s64 count, ntfs_attr_search_ctx *ctx, const bool is_rollback);
-
-/**
- * ntfs_cluster_free - free clusters on an ntfs volume
- * @ni:		ntfs inode whose runlist describes the clusters to free
- * @start_vcn:	vcn in the runlist of @ni at which to start freeing clusters
- * @count:	number of clusters to free or -1 for all clusters
- * @ctx:	active attribute search context if present or NULL if not
- *
- * Free @count clusters starting at the cluster @start_vcn in the runlist
- * described by the ntfs inode @ni.
- *
- * If @count is -1, all clusters from @start_vcn to the end of the runlist are
- * deallocated.  Thus, to completely free all clusters in a runlist, use
- * @start_vcn = 0 and @count = -1.
- *
- * If @ctx is specified, it is an active search context of @ni and its base mft
- * record.  This is needed when ntfs_cluster_free() encounters unmapped runlist
- * fragments and allows their mapping.  If you do not have the mft record
- * mapped, you can specify @ctx as NULL and ntfs_cluster_free() will perform
- * the necessary mapping and unmapping.
- *
- * Note, ntfs_cluster_free() saves the state of @ctx on entry and restores it
- * before returning.  Thus, @ctx will be left pointing to the same attribute on
- * return as on entry.  However, the actual pointers in @ctx may point to
- * different memory locations on return, so you must remember to reset any
- * cached pointers from the @ctx, i.e. after the call to ntfs_cluster_free(),
- * you will probably want to do:
- *	m = ctx->mrec;
- *	a = ctx->attr;
- * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
- * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
- *
- * Note, ntfs_cluster_free() does not modify the runlist, so you have to remove
- * from the runlist or mark sparse the freed runs later.
- *
- * Return the number of deallocated clusters (not counting sparse ones) on
- * success and -errno on error.
- *
- * WARNING: If @ctx is supplied, regardless of whether success or failure is
- *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
- *	    is no longer valid, i.e. you need to either call
- *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
- *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
- *	    why the mapping of the old inode failed.
- *
- * Locking: - The runlist described by @ni must be locked for writing on entry
- *	      and is locked on return.  Note the runlist may be modified when
- *	      needed runlist fragments need to be mapped.
- *	    - The volume lcn bitmap must be unlocked on entry and is unlocked
- *	      on return.
- *	    - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
- *	      entry and it will be left unmapped on return.
- *	    - If @ctx is not NULL, the base mft record must be mapped on entry
- *	      and it will be left mapped on return.
- */
-static inline s64 ntfs_cluster_free(ntfs_inode *ni, const VCN start_vcn,
-		s64 count, ntfs_attr_search_ctx *ctx)
-{
-	return __ntfs_cluster_free(ni, start_vcn, count, ctx, false);
-}
-
-extern int ntfs_cluster_free_from_rl_nolock(ntfs_volume *vol,
-		const runlist_element *rl);
-
-/**
- * ntfs_cluster_free_from_rl - free clusters from runlist
- * @vol:	mounted ntfs volume on which to free the clusters
- * @rl:		runlist describing the clusters to free
- *
- * Free all the clusters described by the runlist @rl on the volume @vol.  In
- * the case of an error being returned, at least some of the clusters were not
- * freed.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - This function takes the volume lcn bitmap lock for writing and
- *	      modifies the bitmap contents.
- *	    - The caller must have locked the runlist @rl for reading or
- *	      writing.
- */
-static inline int ntfs_cluster_free_from_rl(ntfs_volume *vol,
-		const runlist_element *rl)
-{
-	int ret;
-
-	down_write(&vol->lcnbmp_lock);
-	ret = ntfs_cluster_free_from_rl_nolock(vol, rl);
-	up_write(&vol->lcnbmp_lock);
-	return ret;
-}
-
-#endif /* NTFS_RW */
-
-#endif /* defined _LINUX_NTFS_LCNALLOC_H */
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
deleted file mode 100644
index 6ce60ffc6ac0..000000000000
--- a/fs/ntfs/logfile.c
+++ /dev/null
@@ -1,849 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2002-2007 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/buffer_head.h>
-#include <linux/bitops.h>
-#include <linux/log2.h>
-#include <linux/bio.h>
-
-#include "attrib.h"
-#include "aops.h"
-#include "debug.h"
-#include "logfile.h"
-#include "malloc.h"
-#include "volume.h"
-#include "ntfs.h"
-
-/**
- * ntfs_check_restart_page_header - check the page header for consistency
- * @vi:		$LogFile inode to which the restart page header belongs
- * @rp:		restart page header to check
- * @pos:	position in @vi at which the restart page header resides
- *
- * Check the restart page header @rp for consistency and return 'true' if it is
- * consistent and 'false' otherwise.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- */
-static bool ntfs_check_restart_page_header(struct inode *vi,
-		RESTART_PAGE_HEADER *rp, s64 pos)
-{
-	u32 logfile_system_page_size, logfile_log_page_size;
-	u16 ra_ofs, usa_count, usa_ofs, usa_end = 0;
-	bool have_usa = true;
-
-	ntfs_debug("Entering.");
-	/*
-	 * If the system or log page sizes are smaller than the ntfs block size
-	 * or either is not a power of 2 we cannot handle this log file.
-	 */
-	logfile_system_page_size = le32_to_cpu(rp->system_page_size);
-	logfile_log_page_size = le32_to_cpu(rp->log_page_size);
-	if (logfile_system_page_size < NTFS_BLOCK_SIZE ||
-			logfile_log_page_size < NTFS_BLOCK_SIZE ||
-			logfile_system_page_size &
-			(logfile_system_page_size - 1) ||
-			!is_power_of_2(logfile_log_page_size)) {
-		ntfs_error(vi->i_sb, "$LogFile uses unsupported page size.");
-		return false;
-	}
-	/*
-	 * We must be either at !pos (1st restart page) or at pos = system page
-	 * size (2nd restart page).
-	 */
-	if (pos && pos != logfile_system_page_size) {
-		ntfs_error(vi->i_sb, "Found restart area in incorrect "
-				"position in $LogFile.");
-		return false;
-	}
-	/* We only know how to handle version 1.1. */
-	if (sle16_to_cpu(rp->major_ver) != 1 ||
-			sle16_to_cpu(rp->minor_ver) != 1) {
-		ntfs_error(vi->i_sb, "$LogFile version %i.%i is not "
-				"supported.  (This driver supports version "
-				"1.1 only.)", (int)sle16_to_cpu(rp->major_ver),
-				(int)sle16_to_cpu(rp->minor_ver));
-		return false;
-	}
-	/*
-	 * If chkdsk has been run the restart page may not be protected by an
-	 * update sequence array.
-	 */
-	if (ntfs_is_chkd_record(rp->magic) && !le16_to_cpu(rp->usa_count)) {
-		have_usa = false;
-		goto skip_usa_checks;
-	}
-	/* Verify the size of the update sequence array. */
-	usa_count = 1 + (logfile_system_page_size >> NTFS_BLOCK_SIZE_BITS);
-	if (usa_count != le16_to_cpu(rp->usa_count)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent update sequence array count.");
-		return false;
-	}
-	/* Verify the position of the update sequence array. */
-	usa_ofs = le16_to_cpu(rp->usa_ofs);
-	usa_end = usa_ofs + usa_count * sizeof(u16);
-	if (usa_ofs < sizeof(RESTART_PAGE_HEADER) ||
-			usa_end > NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent update sequence array offset.");
-		return false;
-	}
-skip_usa_checks:
-	/*
-	 * Verify the position of the restart area.  It must be:
-	 *	- aligned to 8-byte boundary,
-	 *	- after the update sequence array, and
-	 *	- within the system page size.
-	 */
-	ra_ofs = le16_to_cpu(rp->restart_area_offset);
-	if (ra_ofs & 7 || (have_usa ? ra_ofs < usa_end :
-			ra_ofs < sizeof(RESTART_PAGE_HEADER)) ||
-			ra_ofs > logfile_system_page_size) {
-		ntfs_error(vi->i_sb, "$LogFile restart page specifies "
-				"inconsistent restart area offset.");
-		return false;
-	}
-	/*
-	 * Only restart pages modified by chkdsk are allowed to have chkdsk_lsn
-	 * set.
-	 */
-	if (!ntfs_is_chkd_record(rp->magic) && sle64_to_cpu(rp->chkdsk_lsn)) {
-		ntfs_error(vi->i_sb, "$LogFile restart page is not modified "
-				"by chkdsk but a chkdsk LSN is specified.");
-		return false;
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * ntfs_check_restart_area - check the restart area for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page whose restart area to check
- *
- * Check the restart area of the restart page @rp for consistency and return
- * 'true' if it is consistent and 'false' otherwise.
- *
- * This function assumes that the restart page header has already been
- * consistency checked.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- */
-static bool ntfs_check_restart_area(struct inode *vi, RESTART_PAGE_HEADER *rp)
-{
-	u64 file_size;
-	RESTART_AREA *ra;
-	u16 ra_ofs, ra_len, ca_ofs;
-	u8 fs_bits;
-
-	ntfs_debug("Entering.");
-	ra_ofs = le16_to_cpu(rp->restart_area_offset);
-	ra = (RESTART_AREA*)((u8*)rp + ra_ofs);
-	/*
-	 * Everything before ra->file_size must be before the first word
-	 * protected by an update sequence number.  This ensures that it is
-	 * safe to access ra->client_array_offset.
-	 */
-	if (ra_ofs + offsetof(RESTART_AREA, file_size) >
-			NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent file offset.");
-		return false;
-	}
-	/*
-	 * Now that we can access ra->client_array_offset, make sure everything
-	 * up to the log client array is before the first word protected by an
-	 * update sequence number.  This ensures we can access all of the
-	 * restart area elements safely.  Also, the client array offset must be
-	 * aligned to an 8-byte boundary.
-	 */
-	ca_ofs = le16_to_cpu(ra->client_array_offset);
-	if (((ca_ofs + 7) & ~7) != ca_ofs ||
-			ra_ofs + ca_ofs > NTFS_BLOCK_SIZE - sizeof(u16)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent client array offset.");
-		return false;
-	}
-	/*
-	 * The restart area must end within the system page size both when
-	 * calculated manually and as specified by ra->restart_area_length.
-	 * Also, the calculated length must not exceed the specified length.
-	 */
-	ra_len = ca_ofs + le16_to_cpu(ra->log_clients) *
-			sizeof(LOG_CLIENT_RECORD);
-	if (ra_ofs + ra_len > le32_to_cpu(rp->system_page_size) ||
-			ra_ofs + le16_to_cpu(ra->restart_area_length) >
-			le32_to_cpu(rp->system_page_size) ||
-			ra_len > le16_to_cpu(ra->restart_area_length)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area is out of bounds "
-				"of the system page size specified by the "
-				"restart page header and/or the specified "
-				"restart area length is inconsistent.");
-		return false;
-	}
-	/*
-	 * The ra->client_free_list and ra->client_in_use_list must be either
-	 * LOGFILE_NO_CLIENT or less than ra->log_clients or they are
-	 * overflowing the client array.
-	 */
-	if ((ra->client_free_list != LOGFILE_NO_CLIENT &&
-			le16_to_cpu(ra->client_free_list) >=
-			le16_to_cpu(ra->log_clients)) ||
-			(ra->client_in_use_list != LOGFILE_NO_CLIENT &&
-			le16_to_cpu(ra->client_in_use_list) >=
-			le16_to_cpu(ra->log_clients))) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"overflowing client free and/or in use lists.");
-		return false;
-	}
-	/*
-	 * Check ra->seq_number_bits against ra->file_size for consistency.
-	 * We cannot just use ffs() because the file size is not a power of 2.
-	 */
-	file_size = (u64)sle64_to_cpu(ra->file_size);
-	fs_bits = 0;
-	while (file_size) {
-		file_size >>= 1;
-		fs_bits++;
-	}
-	if (le32_to_cpu(ra->seq_number_bits) != 67 - fs_bits) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent sequence number bits.");
-		return false;
-	}
-	/* The log record header length must be a multiple of 8. */
-	if (((le16_to_cpu(ra->log_record_header_length) + 7) & ~7) !=
-			le16_to_cpu(ra->log_record_header_length)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent log record header length.");
-		return false;
-	}
-	/* Dito for the log page data offset. */
-	if (((le16_to_cpu(ra->log_page_data_offset) + 7) & ~7) !=
-			le16_to_cpu(ra->log_page_data_offset)) {
-		ntfs_error(vi->i_sb, "$LogFile restart area specifies "
-				"inconsistent log page data offset.");
-		return false;
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * ntfs_check_log_client_array - check the log client array for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page whose log client array to check
- *
- * Check the log client array of the restart page @rp for consistency and
- * return 'true' if it is consistent and 'false' otherwise.
- *
- * This function assumes that the restart page header and the restart area have
- * already been consistency checked.
- *
- * Unlike ntfs_check_restart_page_header() and ntfs_check_restart_area(), this
- * function needs @rp->system_page_size bytes in @rp, i.e. it requires the full
- * restart page and the page must be multi sector transfer deprotected.
- */
-static bool ntfs_check_log_client_array(struct inode *vi,
-		RESTART_PAGE_HEADER *rp)
-{
-	RESTART_AREA *ra;
-	LOG_CLIENT_RECORD *ca, *cr;
-	u16 nr_clients, idx;
-	bool in_free_list, idx_is_first;
-
-	ntfs_debug("Entering.");
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	ca = (LOG_CLIENT_RECORD*)((u8*)ra +
-			le16_to_cpu(ra->client_array_offset));
-	/*
-	 * Check the ra->client_free_list first and then check the
-	 * ra->client_in_use_list.  Check each of the log client records in
-	 * each of the lists and check that the array does not overflow the
-	 * ra->log_clients value.  Also keep track of the number of records
-	 * visited as there cannot be more than ra->log_clients records and
-	 * that way we detect eventual loops in within a list.
-	 */
-	nr_clients = le16_to_cpu(ra->log_clients);
-	idx = le16_to_cpu(ra->client_free_list);
-	in_free_list = true;
-check_list:
-	for (idx_is_first = true; idx != LOGFILE_NO_CLIENT_CPU; nr_clients--,
-			idx = le16_to_cpu(cr->next_client)) {
-		if (!nr_clients || idx >= le16_to_cpu(ra->log_clients))
-			goto err_out;
-		/* Set @cr to the current log client record. */
-		cr = ca + idx;
-		/* The first log client record must not have a prev_client. */
-		if (idx_is_first) {
-			if (cr->prev_client != LOGFILE_NO_CLIENT)
-				goto err_out;
-			idx_is_first = false;
-		}
-	}
-	/* Switch to and check the in use list if we just did the free list. */
-	if (in_free_list) {
-		in_free_list = false;
-		idx = le16_to_cpu(ra->client_in_use_list);
-		goto check_list;
-	}
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	ntfs_error(vi->i_sb, "$LogFile log client array is corrupt.");
-	return false;
-}
-
-/**
- * ntfs_check_and_load_restart_page - check the restart page for consistency
- * @vi:		$LogFile inode to which the restart page belongs
- * @rp:		restart page to check
- * @pos:	position in @vi at which the restart page resides
- * @wrp:	[OUT] copy of the multi sector transfer deprotected restart page
- * @lsn:	[OUT] set to the current logfile lsn on success
- *
- * Check the restart page @rp for consistency and return 0 if it is consistent
- * and -errno otherwise.  The restart page may have been modified by chkdsk in
- * which case its magic is CHKD instead of RSTR.
- *
- * This function only needs NTFS_BLOCK_SIZE bytes in @rp, i.e. it does not
- * require the full restart page.
- *
- * If @wrp is not NULL, on success, *@wrp will point to a buffer containing a
- * copy of the complete multi sector transfer deprotected page.  On failure,
- * *@wrp is undefined.
- *
- * Simillarly, if @lsn is not NULL, on success *@lsn will be set to the current
- * logfile lsn according to this restart page.  On failure, *@lsn is undefined.
- *
- * The following error codes are defined:
- *	-EINVAL	- The restart page is inconsistent.
- *	-ENOMEM	- Not enough memory to load the restart page.
- *	-EIO	- Failed to reading from $LogFile.
- */
-static int ntfs_check_and_load_restart_page(struct inode *vi,
-		RESTART_PAGE_HEADER *rp, s64 pos, RESTART_PAGE_HEADER **wrp,
-		LSN *lsn)
-{
-	RESTART_AREA *ra;
-	RESTART_PAGE_HEADER *trp;
-	int size, err;
-
-	ntfs_debug("Entering.");
-	/* Check the restart page header for consistency. */
-	if (!ntfs_check_restart_page_header(vi, rp, pos)) {
-		/* Error output already done inside the function. */
-		return -EINVAL;
-	}
-	/* Check the restart area for consistency. */
-	if (!ntfs_check_restart_area(vi, rp)) {
-		/* Error output already done inside the function. */
-		return -EINVAL;
-	}
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	/*
-	 * Allocate a buffer to store the whole restart page so we can multi
-	 * sector transfer deprotect it.
-	 */
-	trp = ntfs_malloc_nofs(le32_to_cpu(rp->system_page_size));
-	if (!trp) {
-		ntfs_error(vi->i_sb, "Failed to allocate memory for $LogFile "
-				"restart page buffer.");
-		return -ENOMEM;
-	}
-	/*
-	 * Read the whole of the restart page into the buffer.  If it fits
-	 * completely inside @rp, just copy it from there.  Otherwise map all
-	 * the required pages and copy the data from them.
-	 */
-	size = PAGE_SIZE - (pos & ~PAGE_MASK);
-	if (size >= le32_to_cpu(rp->system_page_size)) {
-		memcpy(trp, rp, le32_to_cpu(rp->system_page_size));
-	} else {
-		pgoff_t idx;
-		struct page *page;
-		int have_read, to_read;
-
-		/* First copy what we already have in @rp. */
-		memcpy(trp, rp, size);
-		/* Copy the remaining data one page at a time. */
-		have_read = size;
-		to_read = le32_to_cpu(rp->system_page_size) - size;
-		idx = (pos + size) >> PAGE_SHIFT;
-		BUG_ON((pos + size) & ~PAGE_MASK);
-		do {
-			page = ntfs_map_page(vi->i_mapping, idx);
-			if (IS_ERR(page)) {
-				ntfs_error(vi->i_sb, "Error mapping $LogFile "
-						"page (index %lu).", idx);
-				err = PTR_ERR(page);
-				if (err != -EIO && err != -ENOMEM)
-					err = -EIO;
-				goto err_out;
-			}
-			size = min_t(int, to_read, PAGE_SIZE);
-			memcpy((u8*)trp + have_read, page_address(page), size);
-			ntfs_unmap_page(page);
-			have_read += size;
-			to_read -= size;
-			idx++;
-		} while (to_read > 0);
-	}
-	/*
-	 * Perform the multi sector transfer deprotection on the buffer if the
-	 * restart page is protected.
-	 */
-	if ((!ntfs_is_chkd_record(trp->magic) || le16_to_cpu(trp->usa_count))
-			&& post_read_mst_fixup((NTFS_RECORD*)trp,
-			le32_to_cpu(rp->system_page_size))) {
-		/*
-		 * A multi sector tranfer error was detected.  We only need to
-		 * abort if the restart page contents exceed the multi sector
-		 * transfer fixup of the first sector.
-		 */
-		if (le16_to_cpu(rp->restart_area_offset) +
-				le16_to_cpu(ra->restart_area_length) >
-				NTFS_BLOCK_SIZE - sizeof(u16)) {
-			ntfs_error(vi->i_sb, "Multi sector transfer error "
-					"detected in $LogFile restart page.");
-			err = -EINVAL;
-			goto err_out;
-		}
-	}
-	/*
-	 * If the restart page is modified by chkdsk or there are no active
-	 * logfile clients, the logfile is consistent.  Otherwise, need to
-	 * check the log client records for consistency, too.
-	 */
-	err = 0;
-	if (ntfs_is_rstr_record(rp->magic) &&
-			ra->client_in_use_list != LOGFILE_NO_CLIENT) {
-		if (!ntfs_check_log_client_array(vi, trp)) {
-			err = -EINVAL;
-			goto err_out;
-		}
-	}
-	if (lsn) {
-		if (ntfs_is_rstr_record(rp->magic))
-			*lsn = sle64_to_cpu(ra->current_lsn);
-		else /* if (ntfs_is_chkd_record(rp->magic)) */
-			*lsn = sle64_to_cpu(rp->chkdsk_lsn);
-	}
-	ntfs_debug("Done.");
-	if (wrp)
-		*wrp = trp;
-	else {
-err_out:
-		ntfs_free(trp);
-	}
-	return err;
-}
-
-/**
- * ntfs_check_logfile - check the journal for consistency
- * @log_vi:	struct inode of loaded journal $LogFile to check
- * @rp:		[OUT] on success this is a copy of the current restart page
- *
- * Check the $LogFile journal for consistency and return 'true' if it is
- * consistent and 'false' if not.  On success, the current restart page is
- * returned in *@rp.  Caller must call ntfs_free(*@rp) when finished with it.
- *
- * At present we only check the two restart pages and ignore the log record
- * pages.
- *
- * Note that the MstProtected flag is not set on the $LogFile inode and hence
- * when reading pages they are not deprotected.  This is because we do not know
- * if the $LogFile was created on a system with a different page size to ours
- * yet and mst deprotection would fail if our page size is smaller.
- */
-bool ntfs_check_logfile(struct inode *log_vi, RESTART_PAGE_HEADER **rp)
-{
-	s64 size, pos;
-	LSN rstr1_lsn, rstr2_lsn;
-	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
-	struct address_space *mapping = log_vi->i_mapping;
-	struct page *page = NULL;
-	u8 *kaddr = NULL;
-	RESTART_PAGE_HEADER *rstr1_ph = NULL;
-	RESTART_PAGE_HEADER *rstr2_ph = NULL;
-	int log_page_size, err;
-	bool logfile_is_empty = true;
-	u8 log_page_bits;
-
-	ntfs_debug("Entering.");
-	/* An empty $LogFile must have been clean before it got emptied. */
-	if (NVolLogFileEmpty(vol))
-		goto is_empty;
-	size = i_size_read(log_vi);
-	/* Make sure the file doesn't exceed the maximum allowed size. */
-	if (size > MaxLogFileSize)
-		size = MaxLogFileSize;
-	/*
-	 * Truncate size to a multiple of the page cache size or the default
-	 * log page size if the page cache size is between the default log page
-	 * log page size if the page cache size is between the default log page
-	 * size and twice that.
-	 */
-	if (PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <=
-			DefaultLogPageSize * 2)
-		log_page_size = DefaultLogPageSize;
-	else
-		log_page_size = PAGE_SIZE;
-	/*
-	 * Use ntfs_ffs() instead of ffs() to enable the compiler to
-	 * optimize log_page_size and log_page_bits into constants.
-	 */
-	log_page_bits = ntfs_ffs(log_page_size) - 1;
-	size &= ~(s64)(log_page_size - 1);
-	/*
-	 * Ensure the log file is big enough to store at least the two restart
-	 * pages and the minimum number of log record pages.
-	 */
-	if (size < log_page_size * 2 || (size - log_page_size * 2) >>
-			log_page_bits < MinLogRecordPages) {
-		ntfs_error(vol->sb, "$LogFile is too small.");
-		return false;
-	}
-	/*
-	 * Read through the file looking for a restart page.  Since the restart
-	 * page header is at the beginning of a page we only need to search at
-	 * what could be the beginning of a page (for each page size) rather
-	 * than scanning the whole file byte by byte.  If all potential places
-	 * contain empty and uninitialzed records, the log file can be assumed
-	 * to be empty.
-	 */
-	for (pos = 0; pos < size; pos <<= 1) {
-		pgoff_t idx = pos >> PAGE_SHIFT;
-		if (!page || page->index != idx) {
-			if (page)
-				ntfs_unmap_page(page);
-			page = ntfs_map_page(mapping, idx);
-			if (IS_ERR(page)) {
-				ntfs_error(vol->sb, "Error mapping $LogFile "
-						"page (index %lu).", idx);
-				goto err_out;
-			}
-		}
-		kaddr = (u8*)page_address(page) + (pos & ~PAGE_MASK);
-		/*
-		 * A non-empty block means the logfile is not empty while an
-		 * empty block after a non-empty block has been encountered
-		 * means we are done.
-		 */
-		if (!ntfs_is_empty_recordp((le32*)kaddr))
-			logfile_is_empty = false;
-		else if (!logfile_is_empty)
-			break;
-		/*
-		 * A log record page means there cannot be a restart page after
-		 * this so no need to continue searching.
-		 */
-		if (ntfs_is_rcrd_recordp((le32*)kaddr))
-			break;
-		/* If not a (modified by chkdsk) restart page, continue. */
-		if (!ntfs_is_rstr_recordp((le32*)kaddr) &&
-				!ntfs_is_chkd_recordp((le32*)kaddr)) {
-			if (!pos)
-				pos = NTFS_BLOCK_SIZE >> 1;
-			continue;
-		}
-		/*
-		 * Check the (modified by chkdsk) restart page for consistency
-		 * and get a copy of the complete multi sector transfer
-		 * deprotected restart page.
-		 */
-		err = ntfs_check_and_load_restart_page(log_vi,
-				(RESTART_PAGE_HEADER*)kaddr, pos,
-				!rstr1_ph ? &rstr1_ph : &rstr2_ph,
-				!rstr1_ph ? &rstr1_lsn : &rstr2_lsn);
-		if (!err) {
-			/*
-			 * If we have now found the first (modified by chkdsk)
-			 * restart page, continue looking for the second one.
-			 */
-			if (!pos) {
-				pos = NTFS_BLOCK_SIZE >> 1;
-				continue;
-			}
-			/*
-			 * We have now found the second (modified by chkdsk)
-			 * restart page, so we can stop looking.
-			 */
-			break;
-		}
-		/*
-		 * Error output already done inside the function.  Note, we do
-		 * not abort if the restart page was invalid as we might still
-		 * find a valid one further in the file.
-		 */
-		if (err != -EINVAL) {
-			ntfs_unmap_page(page);
-			goto err_out;
-		}
-		/* Continue looking. */
-		if (!pos)
-			pos = NTFS_BLOCK_SIZE >> 1;
-	}
-	if (page)
-		ntfs_unmap_page(page);
-	if (logfile_is_empty) {
-		NVolSetLogFileEmpty(vol);
-is_empty:
-		ntfs_debug("Done.  ($LogFile is empty.)");
-		return true;
-	}
-	if (!rstr1_ph) {
-		BUG_ON(rstr2_ph);
-		ntfs_error(vol->sb, "Did not find any restart pages in "
-				"$LogFile and it was not empty.");
-		return false;
-	}
-	/* If both restart pages were found, use the more recent one. */
-	if (rstr2_ph) {
-		/*
-		 * If the second restart area is more recent, switch to it.
-		 * Otherwise just throw it away.
-		 */
-		if (rstr2_lsn > rstr1_lsn) {
-			ntfs_debug("Using second restart page as it is more "
-					"recent.");
-			ntfs_free(rstr1_ph);
-			rstr1_ph = rstr2_ph;
-			/* rstr1_lsn = rstr2_lsn; */
-		} else {
-			ntfs_debug("Using first restart page as it is more "
-					"recent.");
-			ntfs_free(rstr2_ph);
-		}
-		rstr2_ph = NULL;
-	}
-	/* All consistency checks passed. */
-	if (rp)
-		*rp = rstr1_ph;
-	else
-		ntfs_free(rstr1_ph);
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	if (rstr1_ph)
-		ntfs_free(rstr1_ph);
-	return false;
-}
-
-/**
- * ntfs_is_logfile_clean - check in the journal if the volume is clean
- * @log_vi:	struct inode of loaded journal $LogFile to check
- * @rp:		copy of the current restart page
- *
- * Analyze the $LogFile journal and return 'true' if it indicates the volume was
- * shutdown cleanly and 'false' if not.
- *
- * At present we only look at the two restart pages and ignore the log record
- * pages.  This is a little bit crude in that there will be a very small number
- * of cases where we think that a volume is dirty when in fact it is clean.
- * This should only affect volumes that have not been shutdown cleanly but did
- * not have any pending, non-check-pointed i/o, i.e. they were completely idle
- * at least for the five seconds preceding the unclean shutdown.
- *
- * This function assumes that the $LogFile journal has already been consistency
- * checked by a call to ntfs_check_logfile() and in particular if the $LogFile
- * is empty this function requires that NVolLogFileEmpty() is true otherwise an
- * empty volume will be reported as dirty.
- */
-bool ntfs_is_logfile_clean(struct inode *log_vi, const RESTART_PAGE_HEADER *rp)
-{
-	ntfs_volume *vol = NTFS_SB(log_vi->i_sb);
-	RESTART_AREA *ra;
-
-	ntfs_debug("Entering.");
-	/* An empty $LogFile must have been clean before it got emptied. */
-	if (NVolLogFileEmpty(vol)) {
-		ntfs_debug("Done.  ($LogFile is empty.)");
-		return true;
-	}
-	BUG_ON(!rp);
-	if (!ntfs_is_rstr_record(rp->magic) &&
-			!ntfs_is_chkd_record(rp->magic)) {
-		ntfs_error(vol->sb, "Restart page buffer is invalid.  This is "
-				"probably a bug in that the $LogFile should "
-				"have been consistency checked before calling "
-				"this function.");
-		return false;
-	}
-	ra = (RESTART_AREA*)((u8*)rp + le16_to_cpu(rp->restart_area_offset));
-	/*
-	 * If the $LogFile has active clients, i.e. it is open, and we do not
-	 * have the RESTART_VOLUME_IS_CLEAN bit set in the restart area flags,
-	 * we assume there was an unclean shutdown.
-	 */
-	if (ra->client_in_use_list != LOGFILE_NO_CLIENT &&
-			!(ra->flags & RESTART_VOLUME_IS_CLEAN)) {
-		ntfs_debug("Done.  $LogFile indicates a dirty shutdown.");
-		return false;
-	}
-	/* $LogFile indicates a clean shutdown. */
-	ntfs_debug("Done.  $LogFile indicates a clean shutdown.");
-	return true;
-}
-
-/**
- * ntfs_empty_logfile - empty the contents of the $LogFile journal
- * @log_vi:	struct inode of loaded journal $LogFile to empty
- *
- * Empty the contents of the $LogFile journal @log_vi and return 'true' on
- * success and 'false' on error.
- *
- * This function assumes that the $LogFile journal has already been consistency
- * checked by a call to ntfs_check_logfile() and that ntfs_is_logfile_clean()
- * has been used to ensure that the $LogFile is clean.
- */
-bool ntfs_empty_logfile(struct inode *log_vi)
-{
-	VCN vcn, end_vcn;
-	ntfs_inode *log_ni = NTFS_I(log_vi);
-	ntfs_volume *vol = log_ni->vol;
-	struct super_block *sb = vol->sb;
-	runlist_element *rl;
-	unsigned long flags;
-	unsigned block_size, block_size_bits;
-	int err;
-	bool should_wait = true;
-
-	ntfs_debug("Entering.");
-	if (NVolLogFileEmpty(vol)) {
-		ntfs_debug("Done.");
-		return true;
-	}
-	/*
-	 * We cannot use ntfs_attr_set() because we may be still in the middle
-	 * of a mount operation.  Thus we do the emptying by hand by first
-	 * zapping the page cache pages for the $LogFile/$DATA attribute and
-	 * then emptying each of the buffers in each of the clusters specified
-	 * by the runlist by hand.
-	 */
-	block_size = sb->s_blocksize;
-	block_size_bits = sb->s_blocksize_bits;
-	vcn = 0;
-	read_lock_irqsave(&log_ni->size_lock, flags);
-	end_vcn = (log_ni->initialized_size + vol->cluster_size_mask) >>
-			vol->cluster_size_bits;
-	read_unlock_irqrestore(&log_ni->size_lock, flags);
-	truncate_inode_pages(log_vi->i_mapping, 0);
-	down_write(&log_ni->runlist.lock);
-	rl = log_ni->runlist.rl;
-	if (unlikely(!rl || vcn < rl->vcn || !rl->length)) {
-map_vcn:
-		err = ntfs_map_runlist_nolock(log_ni, vcn, NULL);
-		if (err) {
-			ntfs_error(sb, "Failed to map runlist fragment (error "
-					"%d).", -err);
-			goto err;
-		}
-		rl = log_ni->runlist.rl;
-		BUG_ON(!rl || vcn < rl->vcn || !rl->length);
-	}
-	/* Seek to the runlist element containing @vcn. */
-	while (rl->length && vcn >= rl[1].vcn)
-		rl++;
-	do {
-		LCN lcn;
-		sector_t block, end_block;
-		s64 len;
-
-		/*
-		 * If this run is not mapped map it now and start again as the
-		 * runlist will have been updated.
-		 */
-		lcn = rl->lcn;
-		if (unlikely(lcn == LCN_RL_NOT_MAPPED)) {
-			vcn = rl->vcn;
-			goto map_vcn;
-		}
-		/* If this run is not valid abort with an error. */
-		if (unlikely(!rl->length || lcn < LCN_HOLE))
-			goto rl_err;
-		/* Skip holes. */
-		if (lcn == LCN_HOLE)
-			continue;
-		block = lcn << vol->cluster_size_bits >> block_size_bits;
-		len = rl->length;
-		if (rl[1].vcn > end_vcn)
-			len = end_vcn - rl->vcn;
-		end_block = (lcn + len) << vol->cluster_size_bits >>
-				block_size_bits;
-		/* Iterate over the blocks in the run and empty them. */
-		do {
-			struct buffer_head *bh;
-
-			/* Obtain the buffer, possibly not uptodate. */
-			bh = sb_getblk(sb, block);
-			BUG_ON(!bh);
-			/* Setup buffer i/o submission. */
-			lock_buffer(bh);
-			bh->b_end_io = end_buffer_write_sync;
-			get_bh(bh);
-			/* Set the entire contents of the buffer to 0xff. */
-			memset(bh->b_data, -1, block_size);
-			if (!buffer_uptodate(bh))
-				set_buffer_uptodate(bh);
-			if (buffer_dirty(bh))
-				clear_buffer_dirty(bh);
-			/*
-			 * Submit the buffer and wait for i/o to complete but
-			 * only for the first buffer so we do not miss really
-			 * serious i/o errors.  Once the first buffer has
-			 * completed ignore errors afterwards as we can assume
-			 * that if one buffer worked all of them will work.
-			 */
-			submit_bh(REQ_OP_WRITE, bh);
-			if (should_wait) {
-				should_wait = false;
-				wait_on_buffer(bh);
-				if (unlikely(!buffer_uptodate(bh)))
-					goto io_err;
-			}
-			brelse(bh);
-		} while (++block < end_block);
-	} while ((++rl)->vcn < end_vcn);
-	up_write(&log_ni->runlist.lock);
-	/*
-	 * Zap the pages again just in case any got instantiated whilst we were
-	 * emptying the blocks by hand.  FIXME: We may not have completed
-	 * writing to all the buffer heads yet so this may happen too early.
-	 * We really should use a kernel thread to do the emptying
-	 * asynchronously and then we can also set the volume dirty and output
-	 * an error message if emptying should fail.
-	 */
-	truncate_inode_pages(log_vi->i_mapping, 0);
-	/* Set the flag so we do not have to do it again on remount. */
-	NVolSetLogFileEmpty(vol);
-	ntfs_debug("Done.");
-	return true;
-io_err:
-	ntfs_error(sb, "Failed to write buffer.  Unmount and run chkdsk.");
-	goto dirty_err;
-rl_err:
-	ntfs_error(sb, "Runlist is corrupt.  Unmount and run chkdsk.");
-dirty_err:
-	NVolSetErrors(vol);
-	err = -EIO;
-err:
-	up_write(&log_ni->runlist.lock);
-	ntfs_error(sb, "Failed to fill $LogFile with 0xff bytes (error %d).",
-			-err);
-	return false;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/logfile.h b/fs/ntfs/logfile.h
deleted file mode 100644
index 429d4909cc72..000000000000
--- a/fs/ntfs/logfile.h
+++ /dev/null
@@ -1,295 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * logfile.h - Defines for NTFS kernel journal ($LogFile) handling.  Part of
- *	       the Linux-NTFS project.
- *
- * Copyright (c) 2000-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_LOGFILE_H
-#define _LINUX_NTFS_LOGFILE_H
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-
-#include "types.h"
-#include "endian.h"
-#include "layout.h"
-
-/*
- * Journal ($LogFile) organization:
- *
- * Two restart areas present in the first two pages (restart pages, one restart
- * area in each page).  When the volume is dismounted they should be identical,
- * except for the update sequence array which usually has a different update
- * sequence number.
- *
- * These are followed by log records organized in pages headed by a log record
- * header going up to log file size.  Not all pages contain log records when a
- * volume is first formatted, but as the volume ages, all records will be used.
- * When the log file fills up, the records at the beginning are purged (by
- * modifying the oldest_lsn to a higher value presumably) and writing begins
- * at the beginning of the file.  Effectively, the log file is viewed as a
- * circular entity.
- *
- * NOTE: Windows NT, 2000, and XP all use log file version 1.1 but they accept
- * versions <= 1.x, including 0.-1.  (Yes, that is a minus one in there!)  We
- * probably only want to support 1.1 as this seems to be the current version
- * and we don't know how that differs from the older versions.  The only
- * exception is if the journal is clean as marked by the two restart pages
- * then it doesn't matter whether we are on an earlier version.  We can just
- * reinitialize the logfile and start again with version 1.1.
- */
-
-/* Some $LogFile related constants. */
-#define MaxLogFileSize		0x100000000ULL
-#define DefaultLogPageSize	4096
-#define MinLogRecordPages	48
-
-/*
- * Log file restart page header (begins the restart area).
- */
-typedef struct {
-/*Ofs*/
-/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
-/*  0*/	NTFS_RECORD_TYPE magic;	/* The magic is "RSTR". */
-/*  4*/	le16 usa_ofs;		/* See NTFS_RECORD definition in layout.h.
-				   When creating, set this to be immediately
-				   after this header structure (without any
-				   alignment). */
-/*  6*/	le16 usa_count;		/* See NTFS_RECORD definition in layout.h. */
-
-/*  8*/	leLSN chkdsk_lsn;	/* The last log file sequence number found by
-				   chkdsk.  Only used when the magic is changed
-				   to "CHKD".  Otherwise this is zero. */
-/* 16*/	le32 system_page_size;	/* Byte size of system pages when the log file
-				   was created, has to be >= 512 and a power of
-				   2.  Use this to calculate the required size
-				   of the usa (usa_count) and add it to usa_ofs.
-				   Then verify that the result is less than the
-				   value of the restart_area_offset. */
-/* 20*/	le32 log_page_size;	/* Byte size of log file pages, has to be >=
-				   512 and a power of 2.  The default is 4096
-				   and is used when the system page size is
-				   between 4096 and 8192.  Otherwise this is
-				   set to the system page size instead. */
-/* 24*/	le16 restart_area_offset;/* Byte offset from the start of this header to
-				   the RESTART_AREA.  Value has to be aligned
-				   to 8-byte boundary.  When creating, set this
-				   to be after the usa. */
-/* 26*/	sle16 minor_ver;	/* Log file minor version.  Only check if major
-				   version is 1. */
-/* 28*/	sle16 major_ver;	/* Log file major version.  We only support
-				   version 1.1. */
-/* sizeof() = 30 (0x1e) bytes */
-} __attribute__ ((__packed__)) RESTART_PAGE_HEADER;
-
-/*
- * Constant for the log client indices meaning that there are no client records
- * in this particular client array.  Also inside the client records themselves,
- * this means that there are no client records preceding or following this one.
- */
-#define LOGFILE_NO_CLIENT	cpu_to_le16(0xffff)
-#define LOGFILE_NO_CLIENT_CPU	0xffff
-
-/*
- * These are the so far known RESTART_AREA_* flags (16-bit) which contain
- * information about the log file in which they are present.
- */
-enum {
-	RESTART_VOLUME_IS_CLEAN	= cpu_to_le16(0x0002),
-	RESTART_SPACE_FILLER	= cpu_to_le16(0xffff), /* gcc: Force enum bit width to 16. */
-} __attribute__ ((__packed__));
-
-typedef le16 RESTART_AREA_FLAGS;
-
-/*
- * Log file restart area record.  The offset of this record is found by adding
- * the offset of the RESTART_PAGE_HEADER to the restart_area_offset value found
- * in it.  See notes at restart_area_offset above.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	leLSN current_lsn;	/* The current, i.e. last LSN inside the log
-				   when the restart area was last written.
-				   This happens often but what is the interval?
-				   Is it just fixed time or is it every time a
-				   check point is written or somethine else?
-				   On create set to 0. */
-/*  8*/	le16 log_clients;	/* Number of log client records in the array of
-				   log client records which follows this
-				   restart area.  Must be 1.  */
-/* 10*/	le16 client_free_list;	/* The index of the first free log client record
-				   in the array of log client records.
-				   LOGFILE_NO_CLIENT means that there are no
-				   free log client records in the array.
-				   If != LOGFILE_NO_CLIENT, check that
-				   log_clients > client_free_list.  On Win2k
-				   and presumably earlier, on a clean volume
-				   this is != LOGFILE_NO_CLIENT, and it should
-				   be 0, i.e. the first (and only) client
-				   record is free and thus the logfile is
-				   closed and hence clean.  A dirty volume
-				   would have left the logfile open and hence
-				   this would be LOGFILE_NO_CLIENT.  On WinXP
-				   and presumably later, the logfile is always
-				   open, even on clean shutdown so this should
-				   always be LOGFILE_NO_CLIENT. */
-/* 12*/	le16 client_in_use_list;/* The index of the first in-use log client
-				   record in the array of log client records.
-				   LOGFILE_NO_CLIENT means that there are no
-				   in-use log client records in the array.  If
-				   != LOGFILE_NO_CLIENT check that log_clients
-				   > client_in_use_list.  On Win2k and
-				   presumably earlier, on a clean volume this
-				   is LOGFILE_NO_CLIENT, i.e. there are no
-				   client records in use and thus the logfile
-				   is closed and hence clean.  A dirty volume
-				   would have left the logfile open and hence
-				   this would be != LOGFILE_NO_CLIENT, and it
-				   should be 0, i.e. the first (and only)
-				   client record is in use.  On WinXP and
-				   presumably later, the logfile is always
-				   open, even on clean shutdown so this should
-				   always be 0. */
-/* 14*/	RESTART_AREA_FLAGS flags;/* Flags modifying LFS behaviour.  On Win2k
-				   and presumably earlier this is always 0.  On
-				   WinXP and presumably later, if the logfile
-				   was shutdown cleanly, the second bit,
-				   RESTART_VOLUME_IS_CLEAN, is set.  This bit
-				   is cleared when the volume is mounted by
-				   WinXP and set when the volume is dismounted,
-				   thus if the logfile is dirty, this bit is
-				   clear.  Thus we don't need to check the
-				   Windows version to determine if the logfile
-				   is clean.  Instead if the logfile is closed,
-				   we know it must be clean.  If it is open and
-				   this bit is set, we also know it must be
-				   clean.  If on the other hand the logfile is
-				   open and this bit is clear, we can be almost
-				   certain that the logfile is dirty. */
-/* 16*/	le32 seq_number_bits;	/* How many bits to use for the sequence
-				   number.  This is calculated as 67 - the
-				   number of bits required to store the logfile
-				   size in bytes and this can be used in with
-				   the specified file_size as a consistency
-				   check. */
-/* 20*/	le16 restart_area_length;/* Length of the restart area including the
-				   client array.  Following checks required if
-				   version matches.  Otherwise, skip them.
-				   restart_area_offset + restart_area_length
-				   has to be <= system_page_size.  Also,
-				   restart_area_length has to be >=
-				   client_array_offset + (log_clients *
-				   sizeof(log client record)). */
-/* 22*/	le16 client_array_offset;/* Offset from the start of this record to
-				   the first log client record if versions are
-				   matched.  When creating, set this to be
-				   after this restart area structure, aligned
-				   to 8-bytes boundary.  If the versions do not
-				   match, this is ignored and the offset is
-				   assumed to be (sizeof(RESTART_AREA) + 7) &
-				   ~7, i.e. rounded up to first 8-byte
-				   boundary.  Either way, client_array_offset
-				   has to be aligned to an 8-byte boundary.
-				   Also, restart_area_offset +
-				   client_array_offset has to be <= 510.
-				   Finally, client_array_offset + (log_clients
-				   * sizeof(log client record)) has to be <=
-				   system_page_size.  On Win2k and presumably
-				   earlier, this is 0x30, i.e. immediately
-				   following this record.  On WinXP and
-				   presumably later, this is 0x40, i.e. there
-				   are 16 extra bytes between this record and
-				   the client array.  This probably means that
-				   the RESTART_AREA record is actually bigger
-				   in WinXP and later. */
-/* 24*/	sle64 file_size;	/* Usable byte size of the log file.  If the
-				   restart_area_offset + the offset of the
-				   file_size are > 510 then corruption has
-				   occurred.  This is the very first check when
-				   starting with the restart_area as if it
-				   fails it means that some of the above values
-				   will be corrupted by the multi sector
-				   transfer protection.  The file_size has to
-				   be rounded down to be a multiple of the
-				   log_page_size in the RESTART_PAGE_HEADER and
-				   then it has to be at least big enough to
-				   store the two restart pages and 48 (0x30)
-				   log record pages. */
-/* 32*/	le32 last_lsn_data_length;/* Length of data of last LSN, not including
-				   the log record header.  On create set to
-				   0. */
-/* 36*/	le16 log_record_header_length;/* Byte size of the log record header.
-				   If the version matches then check that the
-				   value of log_record_header_length is a
-				   multiple of 8, i.e.
-				   (log_record_header_length + 7) & ~7 ==
-				   log_record_header_length.  When creating set
-				   it to sizeof(LOG_RECORD_HEADER), aligned to
-				   8 bytes. */
-/* 38*/	le16 log_page_data_offset;/* Offset to the start of data in a log record
-				   page.  Must be a multiple of 8.  On create
-				   set it to immediately after the update
-				   sequence array of the log record page. */
-/* 40*/	le32 restart_log_open_count;/* A counter that gets incremented every
-				   time the logfile is restarted which happens
-				   at mount time when the logfile is opened.
-				   When creating set to a random value.  Win2k
-				   sets it to the low 32 bits of the current
-				   system time in NTFS format (see time.h). */
-/* 44*/	le32 reserved;		/* Reserved/alignment to 8-byte boundary. */
-/* sizeof() = 48 (0x30) bytes */
-} __attribute__ ((__packed__)) RESTART_AREA;
-
-/*
- * Log client record.  The offset of this record is found by adding the offset
- * of the RESTART_AREA to the client_array_offset value found in it.
- */
-typedef struct {
-/*Ofs*/
-/*  0*/	leLSN oldest_lsn;	/* Oldest LSN needed by this client.  On create
-				   set to 0. */
-/*  8*/	leLSN client_restart_lsn;/* LSN at which this client needs to restart
-				   the volume, i.e. the current position within
-				   the log file.  At present, if clean this
-				   should = current_lsn in restart area but it
-				   probably also = current_lsn when dirty most
-				   of the time.  At create set to 0. */
-/* 16*/	le16 prev_client;	/* The offset to the previous log client record
-				   in the array of log client records.
-				   LOGFILE_NO_CLIENT means there is no previous
-				   client record, i.e. this is the first one.
-				   This is always LOGFILE_NO_CLIENT. */
-/* 18*/	le16 next_client;	/* The offset to the next log client record in
-				   the array of log client records.
-				   LOGFILE_NO_CLIENT means there are no next
-				   client records, i.e. this is the last one.
-				   This is always LOGFILE_NO_CLIENT. */
-/* 20*/	le16 seq_number;	/* On Win2k and presumably earlier, this is set
-				   to zero every time the logfile is restarted
-				   and it is incremented when the logfile is
-				   closed at dismount time.  Thus it is 0 when
-				   dirty and 1 when clean.  On WinXP and
-				   presumably later, this is always 0. */
-/* 22*/	u8 reserved[6];		/* Reserved/alignment. */
-/* 28*/	le32 client_name_length;/* Length of client name in bytes.  Should
-				   always be 8. */
-/* 32*/	ntfschar client_name[64];/* Name of the client in Unicode.  Should
-				   always be "NTFS" with the remaining bytes
-				   set to 0. */
-/* sizeof() = 160 (0xa0) bytes */
-} __attribute__ ((__packed__)) LOG_CLIENT_RECORD;
-
-extern bool ntfs_check_logfile(struct inode *log_vi,
-		RESTART_PAGE_HEADER **rp);
-
-extern bool ntfs_is_logfile_clean(struct inode *log_vi,
-		const RESTART_PAGE_HEADER *rp);
-
-extern bool ntfs_empty_logfile(struct inode *log_vi);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_LOGFILE_H */
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
deleted file mode 100644
index 7068425735f1..000000000000
--- a/fs/ntfs/malloc.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_MALLOC_H
-#define _LINUX_NTFS_MALLOC_H
-
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-#include <linux/highmem.h>
-
-/**
- * __ntfs_malloc - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- * @gfp_mask:	extra flags for the allocator
- *
- * Internal function.  You probably want ntfs_malloc_nofs()...
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * If there was insufficient memory to complete the request, return NULL.
- * Depending on @gfp_mask the allocation may be guaranteed to succeed.
- */
-static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
-{
-	if (likely(size <= PAGE_SIZE)) {
-		BUG_ON(!size);
-		/* kmalloc() has per-CPU caches so is faster for now. */
-		return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
-		/* return (void *)__get_free_page(gfp_mask); */
-	}
-	if (likely((size >> PAGE_SHIFT) < totalram_pages()))
-		return __vmalloc(size, gfp_mask);
-	return NULL;
-}
-
-/**
- * ntfs_malloc_nofs - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * If there was insufficient memory to complete the request, return NULL.
- */
-static inline void *ntfs_malloc_nofs(unsigned long size)
-{
-	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM);
-}
-
-/**
- * ntfs_malloc_nofs_nofail - allocate memory in multiples of pages
- * @size:	number of bytes to allocate
- *
- * Allocates @size bytes of memory, rounded up to multiples of PAGE_SIZE and
- * returns a pointer to the allocated memory.
- *
- * This function guarantees that the allocation will succeed.  It will sleep
- * for as long as it takes to complete the allocation.
- *
- * If there was insufficient memory to complete the request, return NULL.
- */
-static inline void *ntfs_malloc_nofs_nofail(unsigned long size)
-{
-	return __ntfs_malloc(size, GFP_NOFS | __GFP_HIGHMEM | __GFP_NOFAIL);
-}
-
-static inline void ntfs_free(void *addr)
-{
-	kvfree(addr);
-}
-
-#endif /* _LINUX_NTFS_MALLOC_H */
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
deleted file mode 100644
index 6fd1dc4b08c8..000000000000
--- a/fs/ntfs/mft.c
+++ /dev/null
@@ -1,2907 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2002 Richard Russon
- */
-
-#include <linux/buffer_head.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
-#include <linux/bio.h>
-
-#include "attrib.h"
-#include "aops.h"
-#include "bitmap.h"
-#include "debug.h"
-#include "dir.h"
-#include "lcnalloc.h"
-#include "malloc.h"
-#include "mft.h"
-#include "ntfs.h"
-
-#define MAX_BHS	(PAGE_SIZE / NTFS_BLOCK_SIZE)
-
-/**
- * map_mft_record_page - map the page in which a specific mft record resides
- * @ni:		ntfs inode whose mft record page to map
- *
- * This maps the page in which the mft record of the ntfs inode @ni is situated
- * and returns a pointer to the mft record within the mapped page.
- *
- * Return value needs to be checked with IS_ERR() and if that is true PTR_ERR()
- * contains the negative error code returned.
- */
-static inline MFT_RECORD *map_mft_record_page(ntfs_inode *ni)
-{
-	loff_t i_size;
-	ntfs_volume *vol = ni->vol;
-	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
-	unsigned long index, end_index;
-	unsigned ofs;
-
-	BUG_ON(ni->page);
-	/*
-	 * The index into the page cache and the offset within the page cache
-	 * page of the wanted mft record. FIXME: We need to check for
-	 * overflowing the unsigned long, but I don't think we would ever get
-	 * here if the volume was that big...
-	 */
-	index = (u64)ni->mft_no << vol->mft_record_size_bits >>
-			PAGE_SHIFT;
-	ofs = (ni->mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-
-	i_size = i_size_read(mft_vi);
-	/* The maximum valid index into the page cache for $MFT's data. */
-	end_index = i_size >> PAGE_SHIFT;
-
-	/* If the wanted index is out of bounds the mft record doesn't exist. */
-	if (unlikely(index >= end_index)) {
-		if (index > end_index || (i_size & ~PAGE_MASK) < ofs +
-				vol->mft_record_size) {
-			page = ERR_PTR(-ENOENT);
-			ntfs_error(vol->sb, "Attempt to read mft record 0x%lx, "
-					"which is beyond the end of the mft.  "
-					"This is probably a bug in the ntfs "
-					"driver.", ni->mft_no);
-			goto err_out;
-		}
-	}
-	/* Read, map, and pin the page. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (!IS_ERR(page)) {
-		/* Catch multi sector transfer fixup errors. */
-		if (likely(ntfs_is_mft_recordp((le32*)(page_address(page) +
-				ofs)))) {
-			ni->page = page;
-			ni->page_ofs = ofs;
-			return page_address(page) + ofs;
-		}
-		ntfs_error(vol->sb, "Mft record 0x%lx is corrupt.  "
-				"Run chkdsk.", ni->mft_no);
-		ntfs_unmap_page(page);
-		page = ERR_PTR(-EIO);
-		NVolSetErrors(vol);
-	}
-err_out:
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return (void*)page;
-}
-
-/**
- * map_mft_record - map, pin and lock an mft record
- * @ni:		ntfs inode whose MFT record to map
- *
- * First, take the mrec_lock mutex.  We might now be sleeping, while waiting
- * for the mutex if it was already locked by someone else.
- *
- * The page of the record is mapped using map_mft_record_page() before being
- * returned to the caller.
- *
- * This in turn uses ntfs_map_page() to get the page containing the wanted mft
- * record (it in turn calls read_cache_page() which reads it in from disk if
- * necessary, increments the use count on the page so that it cannot disappear
- * under us and returns a reference to the page cache page).
- *
- * If read_cache_page() invokes ntfs_readpage() to load the page from disk, it
- * sets PG_locked and clears PG_uptodate on the page. Once I/O has completed
- * and the post-read mst fixups on each mft record in the page have been
- * performed, the page gets PG_uptodate set and PG_locked cleared (this is done
- * in our asynchronous I/O completion handler end_buffer_read_mft_async()).
- * ntfs_map_page() waits for PG_locked to become clear and checks if
- * PG_uptodate is set and returns an error code if not. This provides
- * sufficient protection against races when reading/using the page.
- *
- * However there is the write mapping to think about. Doing the above described
- * checking here will be fine, because when initiating the write we will set
- * PG_locked and clear PG_uptodate making sure nobody is touching the page
- * contents. Doing the locking this way means that the commit to disk code in
- * the page cache code paths is automatically sufficiently locked with us as
- * we will not touch a page that has been locked or is not uptodate. The only
- * locking problem then is them locking the page while we are accessing it.
- *
- * So that code will end up having to own the mrec_lock of all mft
- * records/inodes present in the page before I/O can proceed. In that case we
- * wouldn't need to bother with PG_locked and PG_uptodate as nobody will be
- * accessing anything without owning the mrec_lock mutex.  But we do need to
- * use them because of the read_cache_page() invocation and the code becomes so
- * much simpler this way that it is well worth it.
- *
- * The mft record is now ours and we return a pointer to it. You need to check
- * the returned pointer with IS_ERR() and if that is true, PTR_ERR() will return
- * the error code.
- *
- * NOTE: Caller is responsible for setting the mft record dirty before calling
- * unmap_mft_record(). This is obviously only necessary if the caller really
- * modified the mft record...
- * Q: Do we want to recycle one of the VFS inode state bits instead?
- * A: No, the inode ones mean we want to change the mft record, not we want to
- * write it out.
- */
-MFT_RECORD *map_mft_record(ntfs_inode *ni)
-{
-	MFT_RECORD *m;
-
-	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
-
-	/* Make sure the ntfs inode doesn't go away. */
-	atomic_inc(&ni->count);
-
-	/* Serialize access to this mft record. */
-	mutex_lock(&ni->mrec_lock);
-
-	m = map_mft_record_page(ni);
-	if (!IS_ERR(m))
-		return m;
-
-	mutex_unlock(&ni->mrec_lock);
-	atomic_dec(&ni->count);
-	ntfs_error(ni->vol->sb, "Failed with error code %lu.", -PTR_ERR(m));
-	return m;
-}
-
-/**
- * unmap_mft_record_page - unmap the page in which a specific mft record resides
- * @ni:		ntfs inode whose mft record page to unmap
- *
- * This unmaps the page in which the mft record of the ntfs inode @ni is
- * situated and returns. This is a NOOP if highmem is not configured.
- *
- * The unmap happens via ntfs_unmap_page() which in turn decrements the use
- * count on the page thus releasing it from the pinned state.
- *
- * We do not actually unmap the page from memory of course, as that will be
- * done by the page cache code itself when memory pressure increases or
- * whatever.
- */
-static inline void unmap_mft_record_page(ntfs_inode *ni)
-{
-	BUG_ON(!ni->page);
-
-	// TODO: If dirty, blah...
-	ntfs_unmap_page(ni->page);
-	ni->page = NULL;
-	ni->page_ofs = 0;
-	return;
-}
-
-/**
- * unmap_mft_record - release a mapped mft record
- * @ni:		ntfs inode whose MFT record to unmap
- *
- * We release the page mapping and the mrec_lock mutex which unmaps the mft
- * record and releases it for others to get hold of. We also release the ntfs
- * inode by decrementing the ntfs inode reference count.
- *
- * NOTE: If caller has modified the mft record, it is imperative to set the mft
- * record dirty BEFORE calling unmap_mft_record().
- */
-void unmap_mft_record(ntfs_inode *ni)
-{
-	struct page *page = ni->page;
-
-	BUG_ON(!page);
-
-	ntfs_debug("Entering for mft_no 0x%lx.", ni->mft_no);
-
-	unmap_mft_record_page(ni);
-	mutex_unlock(&ni->mrec_lock);
-	atomic_dec(&ni->count);
-	/*
-	 * If pure ntfs_inode, i.e. no vfs inode attached, we leave it to
-	 * ntfs_clear_extent_inode() in the extent inode case, and to the
-	 * caller in the non-extent, yet pure ntfs inode case, to do the actual
-	 * tear down of all structures and freeing of all allocated memory.
-	 */
-	return;
-}
-
-/**
- * map_extent_mft_record - load an extent inode and attach it to its base
- * @base_ni:	base ntfs inode
- * @mref:	mft reference of the extent inode to load
- * @ntfs_ino:	on successful return, pointer to the ntfs_inode structure
- *
- * Load the extent mft record @mref and attach it to its base inode @base_ni.
- * Return the mapped extent mft record if IS_ERR(result) is false.  Otherwise
- * PTR_ERR(result) gives the negative error code.
- *
- * On successful return, @ntfs_ino contains a pointer to the ntfs_inode
- * structure of the mapped extent inode.
- */
-MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
-		ntfs_inode **ntfs_ino)
-{
-	MFT_RECORD *m;
-	ntfs_inode *ni = NULL;
-	ntfs_inode **extent_nis = NULL;
-	int i;
-	unsigned long mft_no = MREF(mref);
-	u16 seq_no = MSEQNO(mref);
-	bool destroy_ni = false;
-
-	ntfs_debug("Mapping extent mft record 0x%lx (base mft record 0x%lx).",
-			mft_no, base_ni->mft_no);
-	/* Make sure the base ntfs inode doesn't go away. */
-	atomic_inc(&base_ni->count);
-	/*
-	 * Check if this extent inode has already been added to the base inode,
-	 * in which case just return it. If not found, add it to the base
-	 * inode before returning it.
-	 */
-	mutex_lock(&base_ni->extent_lock);
-	if (base_ni->nr_extents > 0) {
-		extent_nis = base_ni->ext.extent_ntfs_inos;
-		for (i = 0; i < base_ni->nr_extents; i++) {
-			if (mft_no != extent_nis[i]->mft_no)
-				continue;
-			ni = extent_nis[i];
-			/* Make sure the ntfs inode doesn't go away. */
-			atomic_inc(&ni->count);
-			break;
-		}
-	}
-	if (likely(ni != NULL)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		/* We found the record; just have to map and return it. */
-		m = map_mft_record(ni);
-		/* map_mft_record() has incremented this on success. */
-		atomic_dec(&ni->count);
-		if (!IS_ERR(m)) {
-			/* Verify the sequence number. */
-			if (likely(le16_to_cpu(m->sequence_number) == seq_no)) {
-				ntfs_debug("Done 1.");
-				*ntfs_ino = ni;
-				return m;
-			}
-			unmap_mft_record(ni);
-			ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-					"reference! Corrupt filesystem. "
-					"Run chkdsk.");
-			return ERR_PTR(-EIO);
-		}
-map_err_out:
-		ntfs_error(base_ni->vol->sb, "Failed to map extent "
-				"mft record, error code %ld.", -PTR_ERR(m));
-		return m;
-	}
-	/* Record wasn't there. Get a new ntfs inode and initialize it. */
-	ni = ntfs_new_extent_inode(base_ni->vol->sb, mft_no);
-	if (unlikely(!ni)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		return ERR_PTR(-ENOMEM);
-	}
-	ni->vol = base_ni->vol;
-	ni->seq_no = seq_no;
-	ni->nr_extents = -1;
-	ni->ext.base_ntfs_ino = base_ni;
-	/* Now map the record. */
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		mutex_unlock(&base_ni->extent_lock);
-		atomic_dec(&base_ni->count);
-		ntfs_clear_extent_inode(ni);
-		goto map_err_out;
-	}
-	/* Verify the sequence number if it is present. */
-	if (seq_no && (le16_to_cpu(m->sequence_number) != seq_no)) {
-		ntfs_error(base_ni->vol->sb, "Found stale extent mft "
-				"reference! Corrupt filesystem. Run chkdsk.");
-		destroy_ni = true;
-		m = ERR_PTR(-EIO);
-		goto unm_err_out;
-	}
-	/* Attach extent inode to base inode, reallocating memory if needed. */
-	if (!(base_ni->nr_extents & 3)) {
-		ntfs_inode **tmp;
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode *);
-
-		tmp = kmalloc(new_size, GFP_NOFS);
-		if (unlikely(!tmp)) {
-			ntfs_error(base_ni->vol->sb, "Failed to allocate "
-					"internal buffer.");
-			destroy_ni = true;
-			m = ERR_PTR(-ENOMEM);
-			goto unm_err_out;
-		}
-		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
-			memcpy(tmp, base_ni->ext.extent_ntfs_inos, new_size -
-					4 * sizeof(ntfs_inode *));
-			kfree(base_ni->ext.extent_ntfs_inos);
-		}
-		base_ni->ext.extent_ntfs_inos = tmp;
-	}
-	base_ni->ext.extent_ntfs_inos[base_ni->nr_extents++] = ni;
-	mutex_unlock(&base_ni->extent_lock);
-	atomic_dec(&base_ni->count);
-	ntfs_debug("Done 2.");
-	*ntfs_ino = ni;
-	return m;
-unm_err_out:
-	unmap_mft_record(ni);
-	mutex_unlock(&base_ni->extent_lock);
-	atomic_dec(&base_ni->count);
-	/*
-	 * If the extent inode was not attached to the base inode we need to
-	 * release it or we will leak memory.
-	 */
-	if (destroy_ni)
-		ntfs_clear_extent_inode(ni);
-	return m;
-}
-
-#ifdef NTFS_RW
-
-/**
- * __mark_mft_record_dirty - set the mft record and the page containing it dirty
- * @ni:		ntfs inode describing the mapped mft record
- *
- * Internal function.  Users should call mark_mft_record_dirty() instead.
- *
- * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
- * as well as the page containing the mft record, dirty.  Also, mark the base
- * vfs inode dirty.  This ensures that any changes to the mft record are
- * written out to disk.
- *
- * NOTE:  We only set I_DIRTY_DATASYNC (and not I_DIRTY_PAGES)
- * on the base vfs inode, because even though file data may have been modified,
- * it is dirty in the inode meta data rather than the data page cache of the
- * inode, and thus there are no data pages that need writing out.  Therefore, a
- * full mark_inode_dirty() is overkill.  A mark_inode_dirty_sync(), on the
- * other hand, is not sufficient, because ->write_inode needs to be called even
- * in case of fdatasync. This needs to happen or the file data would not
- * necessarily hit the device synchronously, even though the vfs inode has the
- * O_SYNC flag set.  Also, I_DIRTY_DATASYNC simply "feels" better than just
- * I_DIRTY_SYNC, since the file data has not actually hit the block device yet,
- * which is not what I_DIRTY_SYNC on its own would suggest.
- */
-void __mark_mft_record_dirty(ntfs_inode *ni)
-{
-	ntfs_inode *base_ni;
-
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	mark_ntfs_record_dirty(ni->page, ni->page_ofs);
-	/* Determine the base vfs inode and mark it dirty, too. */
-	mutex_lock(&ni->extent_lock);
-	if (likely(ni->nr_extents >= 0))
-		base_ni = ni;
-	else
-		base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
-	__mark_inode_dirty(VFS_I(base_ni), I_DIRTY_DATASYNC);
-}
-
-static const char *ntfs_please_email = "Please email "
-		"linux-ntfs-dev@lists.sourceforge.net and say that you saw "
-		"this message.  Thank you.";
-
-/**
- * ntfs_sync_mft_mirror_umount - synchronise an mft record to the mft mirror
- * @vol:	ntfs volume on which the mft record to synchronize resides
- * @mft_no:	mft record number of mft record to synchronize
- * @m:		mapped, mst protected (extent) mft record to synchronize
- *
- * Write the mapped, mst protected (extent) mft record @m with mft record
- * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol,
- * bypassing the page cache and the $MFTMirr inode itself.
- *
- * This function is only for use at umount time when the mft mirror inode has
- * already been disposed off.  We BUG() if we are called while the mft mirror
- * inode is still attached to the volume.
- *
- * On success return 0.  On error return -errno.
- *
- * NOTE:  This function is not implemented yet as I am not convinced it can
- * actually be triggered considering the sequence of commits we do in super.c::
- * ntfs_put_super().  But just in case we provide this place holder as the
- * alternative would be either to BUG() or to get a NULL pointer dereference
- * and Oops.
- */
-static int ntfs_sync_mft_mirror_umount(ntfs_volume *vol,
-		const unsigned long mft_no, MFT_RECORD *m)
-{
-	BUG_ON(vol->mftmirr_ino);
-	ntfs_error(vol->sb, "Umount time mft mirror syncing is not "
-			"implemented yet.  %s", ntfs_please_email);
-	return -EOPNOTSUPP;
-}
-
-/**
- * ntfs_sync_mft_mirror - synchronize an mft record to the mft mirror
- * @vol:	ntfs volume on which the mft record to synchronize resides
- * @mft_no:	mft record number of mft record to synchronize
- * @m:		mapped, mst protected (extent) mft record to synchronize
- * @sync:	if true, wait for i/o completion
- *
- * Write the mapped, mst protected (extent) mft record @m with mft record
- * number @mft_no to the mft mirror ($MFTMirr) of the ntfs volume @vol.
- *
- * On success return 0.  On error return -errno and set the volume errors flag
- * in the ntfs volume @vol.
- *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
- */
-int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
-		MFT_RECORD *m, int sync)
-{
-	struct page *page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	u8 *kmirr;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end, page_ofs;
-	int i_bhs, nr_bhs, err = 0;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
-
-	ntfs_debug("Entering for inode 0x%lx.", mft_no);
-	BUG_ON(!max_bhs);
-	if (WARN_ON(max_bhs > MAX_BHS))
-		return -EINVAL;
-	if (unlikely(!vol->mftmirr_ino)) {
-		/* This could happen during umount... */
-		err = ntfs_sync_mft_mirror_umount(vol, mft_no, m);
-		if (likely(!err))
-			return err;
-		goto err_out;
-	}
-	/* Get the page containing the mirror copy of the mft record @m. */
-	page = ntfs_map_page(vol->mftmirr_ino->i_mapping, mft_no >>
-			(PAGE_SHIFT - vol->mft_record_size_bits));
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map mft mirror page.");
-		err = PTR_ERR(page);
-		goto err_out;
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	/* Offset of the mft mirror record inside the page. */
-	page_ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* The address in the page of the mirror copy of the mft record @m. */
-	kmirr = page_address(page) + page_ofs;
-	/* Copy the mst protected mft record to the mirror. */
-	memcpy(kmirr, m, vol->mft_record_size);
-	/* Create uptodate buffers if not present. */
-	if (unlikely(!page_has_buffers(page))) {
-		struct buffer_head *tail;
-
-		bh = head = alloc_page_buffers(page, blocksize, true);
-		do {
-			set_buffer_uptodate(bh);
-			tail = bh;
-			bh = bh->b_this_page;
-		} while (bh);
-		tail->b_this_page = head;
-		attach_page_private(page, head);
-	}
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = kmirr - (u8*)page_address(page);
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mftmirr_ino)->
-						runlist.lock);
-				rl = NTFS_I(vol->mftmirr_ino)->runlist.rl;
-				/*
-				 * $MFTMirr always has the whole of its runlist
-				 * in memory.
-				 */
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFTMirr, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft mirror "
-						"record 0x%lx because its "
-						"location on disk could not "
-						"be determined (error code "
-						"%lli).", mft_no,
-						(long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mftmirr_ino)->runlist.lock);
-	if (likely(!err)) {
-		/* Lock buffers and start synchronous write i/o on them. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
-
-			if (!trylock_buffer(tbh))
-				BUG();
-			BUG_ON(!buffer_uptodate(tbh));
-			clear_buffer_dirty(tbh);
-			get_bh(tbh);
-			tbh->b_end_io = end_buffer_write_sync;
-			submit_bh(REQ_OP_WRITE, tbh);
-		}
-		/* Wait on i/o completion of buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-			struct buffer_head *tbh = bhs[i_bhs];
-
-			wait_on_buffer(tbh);
-			if (unlikely(!buffer_uptodate(tbh))) {
-				err = -EIO;
-				/*
-				 * Set the buffer uptodate so the page and
-				 * buffer states do not become out of sync.
-				 */
-				set_buffer_uptodate(tbh);
-			}
-		}
-	} else /* if (unlikely(err)) */ {
-		/* Clean the buffers. */
-		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-			clear_buffer_dirty(bhs[i_bhs]);
-	}
-	/* Current state: all buffers are clean, unlocked, and uptodate. */
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)kmirr);
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	ntfs_unmap_page(page);
-	if (likely(!err)) {
-		ntfs_debug("Done.");
-	} else {
-		ntfs_error(vol->sb, "I/O error while writing mft mirror "
-				"record 0x%lx!", mft_no);
-err_out:
-		ntfs_error(vol->sb, "Failed to synchronize $MFTMirr (error "
-				"code %i).  Volume will be left marked dirty "
-				"on umount.  Run ntfsfix on the partition "
-				"after umounting to correct this.", -err);
-		NVolSetErrors(vol);
-	}
-	return err;
-}
-
-/**
- * write_mft_record_nolock - write out a mapped (extent) mft record
- * @ni:		ntfs inode describing the mapped (extent) mft record
- * @m:		mapped (extent) mft record to write
- * @sync:	if true, wait for i/o completion
- *
- * Write the mapped (extent) mft record @m described by the (regular or extent)
- * ntfs inode @ni to backing store.  If the mft record @m has a counterpart in
- * the mft mirror, that is also updated.
- *
- * We only write the mft record if the ntfs inode @ni is dirty and the first
- * buffer belonging to its mft record is dirty, too.  We ignore the dirty state
- * of subsequent buffers because we could have raced with
- * fs/ntfs/aops.c::mark_ntfs_record_dirty().
- *
- * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.
- *
- * NOTE:  We always perform synchronous i/o and ignore the @sync parameter.
- * However, if the mft record has a counterpart in the mft mirror and @sync is
- * true, we write the mft record, wait for i/o completion, and only then write
- * the mft mirror copy.  This ensures that if the system crashes either the mft
- * or the mft mirror will contain a self-consistent mft record @m.  If @sync is
- * false on the other hand, we start i/o on both and then wait for completion
- * on them.  This provides a speedup but no longer guarantees that you will end
- * up with a self-consistent mft record in the case of a crash but if you asked
- * for asynchronous writing you probably do not care about that anyway.
- *
- * TODO:  If @sync is false, want to do truly asynchronous i/o, i.e. just
- * schedule i/o via ->writepage or do it via kntfsd or whatever.
- */
-int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
-{
-	ntfs_volume *vol = ni->vol;
-	struct page *page = ni->page;
-	unsigned int blocksize = vol->sb->s_blocksize;
-	unsigned char blocksize_bits = vol->sb->s_blocksize_bits;
-	int max_bhs = vol->mft_record_size / blocksize;
-	struct buffer_head *bhs[MAX_BHS];
-	struct buffer_head *bh, *head;
-	runlist_element *rl;
-	unsigned int block_start, block_end, m_start, m_end;
-	int i_bhs, nr_bhs, err = 0;
-
-	ntfs_debug("Entering for inode 0x%lx.", ni->mft_no);
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(!max_bhs);
-	BUG_ON(!PageLocked(page));
-	if (WARN_ON(max_bhs > MAX_BHS)) {
-		err = -EINVAL;
-		goto err_out;
-	}
-	/*
-	 * If the ntfs_inode is clean no need to do anything.  If it is dirty,
-	 * mark it as clean now so that it can be redirtied later on if needed.
-	 * There is no danger of races since the caller is holding the locks
-	 * for the mft record @m and the page it is in.
-	 */
-	if (!NInoTestClearDirty(ni))
-		goto done;
-	bh = head = page_buffers(page);
-	BUG_ON(!bh);
-	rl = NULL;
-	nr_bhs = 0;
-	block_start = 0;
-	m_start = ni->page_ofs;
-	m_end = m_start + vol->mft_record_size;
-	do {
-		block_end = block_start + blocksize;
-		/* If the buffer is outside the mft record, skip it. */
-		if (block_end <= m_start)
-			continue;
-		if (unlikely(block_start >= m_end))
-			break;
-		/*
-		 * If this block is not the first one in the record, we ignore
-		 * the buffer's dirty state because we could have raced with a
-		 * parallel mark_ntfs_record_dirty().
-		 */
-		if (block_start == m_start) {
-			/* This block is the first one in the record. */
-			if (!buffer_dirty(bh)) {
-				BUG_ON(nr_bhs);
-				/* Clean records are not written out. */
-				break;
-			}
-		}
-		/* Need to map the buffer if it is not mapped already. */
-		if (unlikely(!buffer_mapped(bh))) {
-			VCN vcn;
-			LCN lcn;
-			unsigned int vcn_ofs;
-
-			bh->b_bdev = vol->sb->s_bdev;
-			/* Obtain the vcn and offset of the current block. */
-			vcn = ((VCN)ni->mft_no << vol->mft_record_size_bits) +
-					(block_start - m_start);
-			vcn_ofs = vcn & vol->cluster_size_mask;
-			vcn >>= vol->cluster_size_bits;
-			if (!rl) {
-				down_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-				rl = NTFS_I(vol->mft_ino)->runlist.rl;
-				BUG_ON(!rl);
-			}
-			/* Seek to element containing target vcn. */
-			while (rl->length && rl[1].vcn <= vcn)
-				rl++;
-			lcn = ntfs_rl_vcn_to_lcn(rl, vcn);
-			/* For $MFT, only lcn >= 0 is a successful remap. */
-			if (likely(lcn >= 0)) {
-				/* Setup buffer head to correct block. */
-				bh->b_blocknr = ((lcn <<
-						vol->cluster_size_bits) +
-						vcn_ofs) >> blocksize_bits;
-				set_buffer_mapped(bh);
-			} else {
-				bh->b_blocknr = -1;
-				ntfs_error(vol->sb, "Cannot write mft record "
-						"0x%lx because its location "
-						"on disk could not be "
-						"determined (error code %lli).",
-						ni->mft_no, (long long)lcn);
-				err = -EIO;
-			}
-		}
-		BUG_ON(!buffer_uptodate(bh));
-		BUG_ON(!nr_bhs && (m_start != block_start));
-		BUG_ON(nr_bhs >= max_bhs);
-		bhs[nr_bhs++] = bh;
-		BUG_ON((nr_bhs >= max_bhs) && (m_end != block_end));
-	} while (block_start = block_end, (bh = bh->b_this_page) != head);
-	if (unlikely(rl))
-		up_read(&NTFS_I(vol->mft_ino)->runlist.lock);
-	if (!nr_bhs)
-		goto done;
-	if (unlikely(err))
-		goto cleanup_out;
-	/* Apply the mst protection fixups. */
-	err = pre_write_mst_fixup((NTFS_RECORD*)m, vol->mft_record_size);
-	if (err) {
-		ntfs_error(vol->sb, "Failed to apply mst fixups!");
-		goto cleanup_out;
-	}
-	flush_dcache_mft_record_page(ni);
-	/* Lock buffers and start synchronous write i/o on them. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		if (!trylock_buffer(tbh))
-			BUG();
-		BUG_ON(!buffer_uptodate(tbh));
-		clear_buffer_dirty(tbh);
-		get_bh(tbh);
-		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, tbh);
-	}
-	/* Synchronize the mft mirror now if not @sync. */
-	if (!sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Wait on i/o completion of buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
-		struct buffer_head *tbh = bhs[i_bhs];
-
-		wait_on_buffer(tbh);
-		if (unlikely(!buffer_uptodate(tbh))) {
-			err = -EIO;
-			/*
-			 * Set the buffer uptodate so the page and buffer
-			 * states do not become out of sync.
-			 */
-			if (PageUptodate(page))
-				set_buffer_uptodate(tbh);
-		}
-	}
-	/* If @sync, now synchronize the mft mirror. */
-	if (sync && ni->mft_no < vol->mftmirr_size)
-		ntfs_sync_mft_mirror(vol, ni->mft_no, m, sync);
-	/* Remove the mst protection fixups again. */
-	post_write_mst_fixup((NTFS_RECORD*)m);
-	flush_dcache_mft_record_page(ni);
-	if (unlikely(err)) {
-		/* I/O error during writing.  This is really bad! */
-		ntfs_error(vol->sb, "I/O error while writing mft record "
-				"0x%lx!  Marking base inode as bad.  You "
-				"should unmount the volume and run chkdsk.",
-				ni->mft_no);
-		goto err_out;
-	}
-done:
-	ntfs_debug("Done.");
-	return 0;
-cleanup_out:
-	/* Clean the buffers. */
-	for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++)
-		clear_buffer_dirty(bhs[i_bhs]);
-err_out:
-	/*
-	 * Current state: all buffers are clean, unlocked, and uptodate.
-	 * The caller should mark the base inode as bad so that no more i/o
-	 * happens.  ->clear_inode() will still be invoked so all extent inodes
-	 * and other allocated memory will be freed.
-	 */
-	if (err == -ENOMEM) {
-		ntfs_error(vol->sb, "Not enough memory to write mft record.  "
-				"Redirtying so the write is retried later.");
-		mark_mft_record_dirty(ni);
-		err = 0;
-	} else
-		NVolSetErrors(vol);
-	return err;
-}
-
-/**
- * ntfs_may_write_mft_record - check if an mft record may be written out
- * @vol:	[IN]  ntfs volume on which the mft record to check resides
- * @mft_no:	[IN]  mft record number of the mft record to check
- * @m:		[IN]  mapped mft record to check
- * @locked_ni:	[OUT] caller has to unlock this ntfs inode if one is returned
- *
- * Check if the mapped (base or extent) mft record @m with mft record number
- * @mft_no belonging to the ntfs volume @vol may be written out.  If necessary
- * and possible the ntfs inode of the mft record is locked and the base vfs
- * inode is pinned.  The locked ntfs inode is then returned in @locked_ni.  The
- * caller is responsible for unlocking the ntfs inode and unpinning the base
- * vfs inode.
- *
- * Return 'true' if the mft record may be written out and 'false' if not.
- *
- * The caller has locked the page and cleared the uptodate flag on it which
- * means that we can safely write out any dirty mft records that do not have
- * their inodes in icache as determined by ilookup5() as anyone
- * opening/creating such an inode would block when attempting to map the mft
- * record in read_cache_page() until we are finished with the write out.
- *
- * Here is a description of the tests we perform:
- *
- * If the inode is found in icache we know the mft record must be a base mft
- * record.  If it is dirty, we do not write it and return 'false' as the vfs
- * inode write paths will result in the access times being updated which would
- * cause the base mft record to be redirtied and written out again.  (We know
- * the access time update will modify the base mft record because Windows
- * chkdsk complains if the standard information attribute is not in the base
- * mft record.)
- *
- * If the inode is in icache and not dirty, we attempt to lock the mft record
- * and if we find the lock was already taken, it is not safe to write the mft
- * record and we return 'false'.
- *
- * If we manage to obtain the lock we have exclusive access to the mft record,
- * which also allows us safe writeout of the mft record.  We then set
- * @locked_ni to the locked ntfs inode and return 'true'.
- *
- * Note we cannot just lock the mft record and sleep while waiting for the lock
- * because this would deadlock due to lock reversal (normally the mft record is
- * locked before the page is locked but we already have the page locked here
- * when we try to lock the mft record).
- *
- * If the inode is not in icache we need to perform further checks.
- *
- * If the mft record is not a FILE record or it is a base mft record, we can
- * safely write it and return 'true'.
- *
- * We now know the mft record is an extent mft record.  We check if the inode
- * corresponding to its base mft record is in icache and obtain a reference to
- * it if it is.  If it is not, we can safely write it and return 'true'.
- *
- * We now have the base inode for the extent mft record.  We check if it has an
- * ntfs inode for the extent mft record attached and if not it is safe to write
- * the extent mft record and we return 'true'.
- *
- * The ntfs inode for the extent mft record is attached to the base inode so we
- * attempt to lock the extent mft record and if we find the lock was already
- * taken, it is not safe to write the extent mft record and we return 'false'.
- *
- * If we manage to obtain the lock we have exclusive access to the extent mft
- * record, which also allows us safe writeout of the extent mft record.  We
- * set the ntfs inode of the extent mft record clean and then set @locked_ni to
- * the now locked ntfs inode and return 'true'.
- *
- * Note, the reason for actually writing dirty mft records here and not just
- * relying on the vfs inode dirty code paths is that we can have mft records
- * modified without them ever having actual inodes in memory.  Also we can have
- * dirty mft records with clean ntfs inodes in memory.  None of the described
- * cases would result in the dirty mft records being written out if we only
- * relied on the vfs inode dirty code paths.  And these cases can really occur
- * during allocation of new mft records and in particular when the
- * initialized_size of the $MFT/$DATA attribute is extended and the new space
- * is initialized using ntfs_mft_record_format().  The clean inode can then
- * appear if the mft record is reused for a new inode before it got written
- * out.
- */
-bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no,
-		const MFT_RECORD *m, ntfs_inode **locked_ni)
-{
-	struct super_block *sb = vol->sb;
-	struct inode *mft_vi = vol->mft_ino;
-	struct inode *vi;
-	ntfs_inode *ni, *eni, **extent_nis;
-	int i;
-	ntfs_attr na;
-
-	ntfs_debug("Entering for inode 0x%lx.", mft_no);
-	/*
-	 * Normally we do not return a locked inode so set @locked_ni to NULL.
-	 */
-	BUG_ON(!locked_ni);
-	*locked_ni = NULL;
-	/*
-	 * Check if the inode corresponding to this mft record is in the VFS
-	 * inode cache and obtain a reference to it if it is.
-	 */
-	ntfs_debug("Looking for inode 0x%lx in icache.", mft_no);
-	na.mft_no = mft_no;
-	na.name = NULL;
-	na.name_len = 0;
-	na.type = AT_UNUSED;
-	/*
-	 * Optimize inode 0, i.e. $MFT itself, since we have it in memory and
-	 * we get here for it rather often.
-	 */
-	if (!mft_no) {
-		/* Balance the below iput(). */
-		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
-	} else {
-		/*
-		 * Have to use ilookup5_nowait() since ilookup5() waits for the
-		 * inode lock which causes ntfs to deadlock when a concurrent
-		 * inode write via the inode dirty code paths and the page
-		 * dirty code path of the inode dirty code path when writing
-		 * $MFT occurs.
-		 */
-		vi = ilookup5_nowait(sb, mft_no, ntfs_test_inode, &na);
-	}
-	if (vi) {
-		ntfs_debug("Base inode 0x%lx is in icache.", mft_no);
-		/* The inode is in icache. */
-		ni = NTFS_I(vi);
-		/* Take a reference to the ntfs inode. */
-		atomic_inc(&ni->count);
-		/* If the inode is dirty, do not write this record. */
-		if (NInoDirty(ni)) {
-			ntfs_debug("Inode 0x%lx is dirty, do not write it.",
-					mft_no);
-			atomic_dec(&ni->count);
-			iput(vi);
-			return false;
-		}
-		ntfs_debug("Inode 0x%lx is not dirty.", mft_no);
-		/* The inode is not dirty, try to take the mft record lock. */
-		if (unlikely(!mutex_trylock(&ni->mrec_lock))) {
-			ntfs_debug("Mft record 0x%lx is already locked, do "
-					"not write it.", mft_no);
-			atomic_dec(&ni->count);
-			iput(vi);
-			return false;
-		}
-		ntfs_debug("Managed to lock mft record 0x%lx, write it.",
-				mft_no);
-		/*
-		 * The write has to occur while we hold the mft record lock so
-		 * return the locked ntfs inode.
-		 */
-		*locked_ni = ni;
-		return true;
-	}
-	ntfs_debug("Inode 0x%lx is not in icache.", mft_no);
-	/* The inode is not in icache. */
-	/* Write the record if it is not a mft record (type "FILE"). */
-	if (!ntfs_is_mft_record(m->magic)) {
-		ntfs_debug("Mft record 0x%lx is not a FILE record, write it.",
-				mft_no);
-		return true;
-	}
-	/* Write the mft record if it is a base inode. */
-	if (!m->base_mft_record) {
-		ntfs_debug("Mft record 0x%lx is a base record, write it.",
-				mft_no);
-		return true;
-	}
-	/*
-	 * This is an extent mft record.  Check if the inode corresponding to
-	 * its base mft record is in icache and obtain a reference to it if it
-	 * is.
-	 */
-	na.mft_no = MREF_LE(m->base_mft_record);
-	ntfs_debug("Mft record 0x%lx is an extent record.  Looking for base "
-			"inode 0x%lx in icache.", mft_no, na.mft_no);
-	if (!na.mft_no) {
-		/* Balance the below iput(). */
-		vi = igrab(mft_vi);
-		BUG_ON(vi != mft_vi);
-	} else
-		vi = ilookup5_nowait(sb, na.mft_no, ntfs_test_inode,
-				&na);
-	if (!vi) {
-		/*
-		 * The base inode is not in icache, write this extent mft
-		 * record.
-		 */
-		ntfs_debug("Base inode 0x%lx is not in icache, write the "
-				"extent record.", na.mft_no);
-		return true;
-	}
-	ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no);
-	/*
-	 * The base inode is in icache.  Check if it has the extent inode
-	 * corresponding to this extent mft record attached.
-	 */
-	ni = NTFS_I(vi);
-	mutex_lock(&ni->extent_lock);
-	if (ni->nr_extents <= 0) {
-		/*
-		 * The base inode has no attached extent inodes, write this
-		 * extent mft record.
-		 */
-		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Base inode 0x%lx has no attached extent inodes, "
-				"write the extent record.", na.mft_no);
-		return true;
-	}
-	/* Iterate over the attached extent inodes. */
-	extent_nis = ni->ext.extent_ntfs_inos;
-	for (eni = NULL, i = 0; i < ni->nr_extents; ++i) {
-		if (mft_no == extent_nis[i]->mft_no) {
-			/*
-			 * Found the extent inode corresponding to this extent
-			 * mft record.
-			 */
-			eni = extent_nis[i];
-			break;
-		}
-	}
-	/*
-	 * If the extent inode was not attached to the base inode, write this
-	 * extent mft record.
-	 */
-	if (!eni) {
-		mutex_unlock(&ni->extent_lock);
-		iput(vi);
-		ntfs_debug("Extent inode 0x%lx is not attached to its base "
-				"inode 0x%lx, write the extent record.",
-				mft_no, na.mft_no);
-		return true;
-	}
-	ntfs_debug("Extent inode 0x%lx is attached to its base inode 0x%lx.",
-			mft_no, na.mft_no);
-	/* Take a reference to the extent ntfs inode. */
-	atomic_inc(&eni->count);
-	mutex_unlock(&ni->extent_lock);
-	/*
-	 * Found the extent inode coresponding to this extent mft record.
-	 * Try to take the mft record lock.
-	 */
-	if (unlikely(!mutex_trylock(&eni->mrec_lock))) {
-		atomic_dec(&eni->count);
-		iput(vi);
-		ntfs_debug("Extent mft record 0x%lx is already locked, do "
-				"not write it.", mft_no);
-		return false;
-	}
-	ntfs_debug("Managed to lock extent mft record 0x%lx, write it.",
-			mft_no);
-	if (NInoTestClearDirty(eni))
-		ntfs_debug("Extent inode 0x%lx is dirty, marking it clean.",
-				mft_no);
-	/*
-	 * The write has to occur while we hold the mft record lock so return
-	 * the locked extent ntfs inode.
-	 */
-	*locked_ni = eni;
-	return true;
-}
-
-static const char *es = "  Leaving inconsistent metadata.  Unmount and run "
-		"chkdsk.";
-
-/**
- * ntfs_mft_bitmap_find_and_alloc_free_rec_nolock - see name
- * @vol:	volume on which to search for a free mft record
- * @base_ni:	open base inode if allocating an extent mft record or NULL
- *
- * Search for a free mft record in the mft bitmap attribute on the ntfs volume
- * @vol.
- *
- * If @base_ni is NULL start the search at the default allocator position.
- *
- * If @base_ni is not NULL start the search at the mft record after the base
- * mft record @base_ni.
- *
- * Return the free mft record on success and -errno on error.  An error code of
- * -ENOSPC means that there are no free mft records in the currently
- * initialized mft bitmap.
- *
- * Locking: Caller must hold vol->mftbmp_lock for writing.
- */
-static int ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(ntfs_volume *vol,
-		ntfs_inode *base_ni)
-{
-	s64 pass_end, ll, data_pos, pass_start, ofs, bit;
-	unsigned long flags;
-	struct address_space *mftbmp_mapping;
-	u8 *buf, *byte;
-	struct page *page;
-	unsigned int page_ofs, size;
-	u8 pass, b;
-
-	ntfs_debug("Searching for free mft record in the currently "
-			"initialized mft bitmap.");
-	mftbmp_mapping = vol->mftbmp_ino->i_mapping;
-	/*
-	 * Set the end of the pass making sure we do not overflow the mft
-	 * bitmap.
-	 */
-	read_lock_irqsave(&NTFS_I(vol->mft_ino)->size_lock, flags);
-	pass_end = NTFS_I(vol->mft_ino)->allocated_size >>
-			vol->mft_record_size_bits;
-	read_unlock_irqrestore(&NTFS_I(vol->mft_ino)->size_lock, flags);
-	read_lock_irqsave(&NTFS_I(vol->mftbmp_ino)->size_lock, flags);
-	ll = NTFS_I(vol->mftbmp_ino)->initialized_size << 3;
-	read_unlock_irqrestore(&NTFS_I(vol->mftbmp_ino)->size_lock, flags);
-	if (pass_end > ll)
-		pass_end = ll;
-	pass = 1;
-	if (!base_ni)
-		data_pos = vol->mft_data_pos;
-	else
-		data_pos = base_ni->mft_no + 1;
-	if (data_pos < 24)
-		data_pos = 24;
-	if (data_pos >= pass_end) {
-		data_pos = 24;
-		pass = 2;
-		/* This happens on a freshly formatted volume. */
-		if (data_pos >= pass_end)
-			return -ENOSPC;
-	}
-	pass_start = data_pos;
-	ntfs_debug("Starting bitmap search: pass %u, pass_start 0x%llx, "
-			"pass_end 0x%llx, data_pos 0x%llx.", pass,
-			(long long)pass_start, (long long)pass_end,
-			(long long)data_pos);
-	/* Loop until a free mft record is found. */
-	for (; pass <= 2;) {
-		/* Cap size to pass_end. */
-		ofs = data_pos >> 3;
-		page_ofs = ofs & ~PAGE_MASK;
-		size = PAGE_SIZE - page_ofs;
-		ll = ((pass_end + 7) >> 3) - ofs;
-		if (size > ll)
-			size = ll;
-		size <<= 3;
-		/*
-		 * If we are still within the active pass, search the next page
-		 * for a zero bit.
-		 */
-		if (size) {
-			page = ntfs_map_page(mftbmp_mapping,
-					ofs >> PAGE_SHIFT);
-			if (IS_ERR(page)) {
-				ntfs_error(vol->sb, "Failed to read mft "
-						"bitmap, aborting.");
-				return PTR_ERR(page);
-			}
-			buf = (u8*)page_address(page) + page_ofs;
-			bit = data_pos & 7;
-			data_pos &= ~7ull;
-			ntfs_debug("Before inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
-			for (; bit < size && data_pos + bit < pass_end;
-					bit &= ~7ull, bit += 8) {
-				byte = buf + (bit >> 3);
-				if (*byte == 0xff)
-					continue;
-				b = ffz((unsigned long)*byte);
-				if (b < 8 && b >= (bit & 7)) {
-					ll = data_pos + (bit & ~7ull) + b;
-					if (unlikely(ll > (1ll << 32))) {
-						ntfs_unmap_page(page);
-						return -ENOSPC;
-					}
-					*byte |= 1 << b;
-					flush_dcache_page(page);
-					set_page_dirty(page);
-					ntfs_unmap_page(page);
-					ntfs_debug("Done.  (Found and "
-							"allocated mft record "
-							"0x%llx.)",
-							(long long)ll);
-					return ll;
-				}
-			}
-			ntfs_debug("After inner for loop: size 0x%x, "
-					"data_pos 0x%llx, bit 0x%llx", size,
-					(long long)data_pos, (long long)bit);
-			data_pos += size;
-			ntfs_unmap_page(page);
-			/*
-			 * If the end of the pass has not been reached yet,
-			 * continue searching the mft bitmap for a zero bit.
-			 */
-			if (data_pos < pass_end)
-				continue;
-		}
-		/* Do the next pass. */
-		if (++pass == 2) {
-			/*
-			 * Starting the second pass, in which we scan the first
-			 * part of the zone which we omitted earlier.
-			 */
-			pass_end = pass_start;
-			data_pos = pass_start = 24;
-			ntfs_debug("pass %i, pass_start 0x%llx, pass_end "
-					"0x%llx.", pass, (long long)pass_start,
-					(long long)pass_end);
-			if (data_pos >= pass_end)
-				break;
-		}
-	}
-	/* No free mft records in currently initialized mft bitmap. */
-	ntfs_debug("Done.  (No free mft records left in currently initialized "
-			"mft bitmap.)");
-	return -ENOSPC;
-}
-
-/**
- * ntfs_mft_bitmap_extend_allocation_nolock - extend mft bitmap by a cluster
- * @vol:	volume on which to extend the mft bitmap attribute
- *
- * Extend the mft bitmap attribute on the ntfs volume @vol by one cluster.
- *
- * Note: Only changes allocated_size, i.e. does not touch initialized_size or
- * data_size.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - Caller must hold vol->mftbmp_lock for writing.
- *	    - This function takes NTFS_I(vol->mftbmp_ino)->runlist.lock for
- *	      writing and releases it before returning.
- *	    - This function takes vol->lcnbmp_lock for writing and releases it
- *	      before returning.
- */
-static int ntfs_mft_bitmap_extend_allocation_nolock(ntfs_volume *vol)
-{
-	LCN lcn;
-	s64 ll;
-	unsigned long flags;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	runlist_element *rl, *rl2 = NULL;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
-	int ret, mp_size;
-	u32 old_alen = 0;
-	u8 *b, tb;
-	struct {
-		u8 added_cluster:1;
-		u8 added_run:1;
-		u8 mp_rebuilt:1;
-	} status = { 0, 0, 0 };
-
-	ntfs_debug("Extending mft bitmap allocation.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_ni = NTFS_I(vol->mftbmp_ino);
-	/*
-	 * Determine the last lcn of the mft bitmap.  The allocated size of the
-	 * mft bitmap cannot be zero so we are ok to do this.
-	 */
-	down_write(&mftbmp_ni->runlist.lock);
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ll = mftbmp_ni->allocated_size;
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	rl = ntfs_attr_find_vcn_nolock(mftbmp_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
-	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
-		up_write(&mftbmp_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft bitmap attribute.");
-		if (!IS_ERR(rl))
-			ret = -EIO;
-		else
-			ret = PTR_ERR(rl);
-		return ret;
-	}
-	lcn = rl->lcn + rl->length;
-	ntfs_debug("Last lcn of mft bitmap attribute is 0x%llx.",
-			(long long)lcn);
-	/*
-	 * Attempt to get the cluster following the last allocated cluster by
-	 * hand as it may be in the MFT zone so the allocator would not give it
-	 * to us.
-	 */
-	ll = lcn >> 3;
-	page = ntfs_map_page(vol->lcnbmp_ino->i_mapping,
-			ll >> PAGE_SHIFT);
-	if (IS_ERR(page)) {
-		up_write(&mftbmp_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to read from lcn bitmap.");
-		return PTR_ERR(page);
-	}
-	b = (u8*)page_address(page) + (ll & ~PAGE_MASK);
-	tb = 1 << (lcn & 7ull);
-	down_write(&vol->lcnbmp_lock);
-	if (*b != 0xff && !(*b & tb)) {
-		/* Next cluster is free, allocate it. */
-		*b |= tb;
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
-		/* Update the mft bitmap runlist. */
-		rl->length++;
-		rl[1].vcn++;
-		status.added_cluster = 1;
-		ntfs_debug("Appending one cluster to mft bitmap.");
-	} else {
-		up_write(&vol->lcnbmp_lock);
-		ntfs_unmap_page(page);
-		/* Allocate a cluster from the DATA_ZONE. */
-		rl2 = ntfs_cluster_alloc(vol, rl[1].vcn, 1, lcn, DATA_ZONE,
-				true);
-		if (IS_ERR(rl2)) {
-			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to allocate a cluster for "
-					"the mft bitmap.");
-			return PTR_ERR(rl2);
-		}
-		rl = ntfs_runlists_merge(mftbmp_ni->runlist.rl, rl2);
-		if (IS_ERR(rl)) {
-			up_write(&mftbmp_ni->runlist.lock);
-			ntfs_error(vol->sb, "Failed to merge runlists for mft "
-					"bitmap.");
-			if (ntfs_cluster_free_from_rl(vol, rl2)) {
-				ntfs_error(vol->sb, "Failed to deallocate "
-						"allocated cluster.%s", es);
-				NVolSetErrors(vol);
-			}
-			ntfs_free(rl2);
-			return PTR_ERR(rl);
-		}
-		mftbmp_ni->runlist.rl = rl;
-		status.added_run = 1;
-		ntfs_debug("Adding one run to mft bitmap.");
-		/* Find the last run in the new runlist. */
-		for (; rl[1].length; rl++)
-			;
-	}
-	/*
-	 * Update the attribute record as well.  Note: @rl is the last
-	 * (non-terminator) runlist element of mft bitmap.
-	 */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		ret = PTR_ERR(mrec);
-		goto undo_alloc;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto undo_alloc;
-	}
-	ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
-			0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	/* Search back for the previous last allocated cluster of mft bitmap. */
-	for (rl2 = rl; rl2 > mftbmp_ni->runlist.rl; rl2--) {
-		if (ll >= rl2->vcn)
-			break;
-	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft bitmap attribute extent.");
-		ret = mp_size;
-		if (!ret)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	/* Expand the attribute record if necessary. */
-	old_alen = le32_to_cpu(a->length);
-	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft bitmap attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: It will need to be a special mft record and if none of
-		// those are available it gets rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft bitmap attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	status.mp_rebuilt = 1;
-	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array for "
-				"mft bitmap attribute.");
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
-	/*
-	 * We now have extended the mft bitmap allocated_size by one cluster.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-				mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL,
-				0, ctx);
-		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft bitmap attribute.");
-			goto restore_undo_alloc;
-		}
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	mftbmp_ni->allocated_size += vol->cluster_size;
-	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mftbmp_ni->allocated_size);
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	up_write(&mftbmp_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return 0;
-restore_undo_alloc:
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, rl[1].vcn, NULL,
-			0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft bitmap attribute.%s", es);
-		write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-		mftbmp_ni->allocated_size += vol->cluster_size;
-		write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		up_write(&mftbmp_ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is ->allocated_size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return ret;
-	}
-	a = ctx->attr;
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 2);
-undo_alloc:
-	if (status.added_cluster) {
-		/* Truncate the last run in the runlist by one cluster. */
-		rl->length--;
-		rl[1].vcn--;
-	} else if (status.added_run) {
-		lcn = rl->lcn;
-		/* Remove the last run from the runlist. */
-		rl->lcn = rl[1].lcn;
-		rl->length = 0;
-	}
-	/* Deallocate the cluster. */
-	down_write(&vol->lcnbmp_lock);
-	if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
-		ntfs_error(vol->sb, "Failed to free allocated cluster.%s", es);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->lcnbmp_lock);
-	if (status.mp_rebuilt) {
-		if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				old_alen - le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-			ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
-			NVolSetErrors(vol);
-		}
-		if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-			ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
-			NVolSetErrors(vol);
-		}
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-	}
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (!IS_ERR(mrec))
-		unmap_mft_record(mft_ni);
-	up_write(&mftbmp_ni->runlist.lock);
-	return ret;
-}
-
-/**
- * ntfs_mft_bitmap_extend_initialized_nolock - extend mftbmp initialized data
- * @vol:	volume on which to extend the mft bitmap attribute
- *
- * Extend the initialized portion of the mft bitmap attribute on the ntfs
- * volume @vol by 8 bytes.
- *
- * Note:  Only changes initialized_size and data_size, i.e. requires that
- * allocated_size is big enough to fit the new initialized_size.
- *
- * Return 0 on success and -error on error.
- *
- * Locking: Caller must hold vol->mftbmp_lock for writing.
- */
-static int ntfs_mft_bitmap_extend_initialized_nolock(ntfs_volume *vol)
-{
-	s64 old_data_size, old_initialized_size;
-	unsigned long flags;
-	struct inode *mftbmp_vi;
-	ntfs_inode *mft_ni, *mftbmp_ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a;
-	int ret;
-
-	ntfs_debug("Extending mft bitmap initiailized (and data) size.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_vi = vol->mftbmp_ino;
-	mftbmp_ni = NTFS_I(mftbmp_vi);
-	/* Get the attribute record. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		return PTR_ERR(mrec);
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto unm_err_out;
-	}
-	ret = ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto put_err_out;
-	}
-	a = ctx->attr;
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_size = i_size_read(mftbmp_vi);
-	old_initialized_size = mftbmp_ni->initialized_size;
-	/*
-	 * We can simply update the initialized_size before filling the space
-	 * with zeroes because the caller is holding the mft bitmap lock for
-	 * writing which ensures that no one else is trying to access the data.
-	 */
-	mftbmp_ni->initialized_size += 8;
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mftbmp_ni->initialized_size);
-	if (mftbmp_ni->initialized_size > old_data_size) {
-		i_size_write(mftbmp_vi, mftbmp_ni->initialized_size);
-		a->data.non_resident.data_size =
-				cpu_to_sle64(mftbmp_ni->initialized_size);
-	}
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	/* Initialize the mft bitmap attribute value with zeroes. */
-	ret = ntfs_attr_set(mftbmp_ni, old_initialized_size, 8, 0);
-	if (likely(!ret)) {
-		ntfs_debug("Done.  (Wrote eight initialized bytes to mft "
-				"bitmap.");
-		return 0;
-	}
-	ntfs_error(vol->sb, "Failed to write to mft bitmap.");
-	/* Try to recover from the error. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.%s", es);
-		NVolSetErrors(vol);
-		return ret;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.%s", es);
-		NVolSetErrors(vol);
-		goto unm_err_out;
-	}
-	if (ntfs_attr_lookup(mftbmp_ni->type, mftbmp_ni->name,
-			mftbmp_ni->name_len, CASE_SENSITIVE, 0, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft bitmap attribute.%s", es);
-		NVolSetErrors(vol);
-put_err_out:
-		ntfs_attr_put_search_ctx(ctx);
-unm_err_out:
-		unmap_mft_record(mft_ni);
-		goto err_out;
-	}
-	a = ctx->attr;
-	write_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	mftbmp_ni->initialized_size = old_initialized_size;
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(old_initialized_size);
-	if (i_size_read(mftbmp_vi) != old_data_size) {
-		i_size_write(mftbmp_vi, old_data_size);
-		a->data.non_resident.data_size = cpu_to_sle64(old_data_size);
-	}
-	write_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-#ifdef DEBUG
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Restored status of mftbmp: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(mftbmp_vi),
-			(long long)mftbmp_ni->initialized_size);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-err_out:
-	return ret;
-}
-
-/**
- * ntfs_mft_data_extend_allocation_nolock - extend mft data attribute
- * @vol:	volume on which to extend the mft data attribute
- *
- * Extend the mft data attribute on the ntfs volume @vol by 16 mft records
- * worth of clusters or if not enough space for this by one mft record worth
- * of clusters.
- *
- * Note:  Only changes allocated_size, i.e. does not touch initialized_size or
- * data_size.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: - Caller must hold vol->mftbmp_lock for writing.
- *	    - This function takes NTFS_I(vol->mft_ino)->runlist.lock for
- *	      writing and releases it before returning.
- *	    - This function calls functions which take vol->lcnbmp_lock for
- *	      writing and release it before returning.
- */
-static int ntfs_mft_data_extend_allocation_nolock(ntfs_volume *vol)
-{
-	LCN lcn;
-	VCN old_last_vcn;
-	s64 min_nr, nr, ll;
-	unsigned long flags;
-	ntfs_inode *mft_ni;
-	runlist_element *rl, *rl2;
-	ntfs_attr_search_ctx *ctx = NULL;
-	MFT_RECORD *mrec;
-	ATTR_RECORD *a = NULL;
-	int ret, mp_size;
-	u32 old_alen = 0;
-	bool mp_rebuilt = false;
-
-	ntfs_debug("Extending mft data allocation.");
-	mft_ni = NTFS_I(vol->mft_ino);
-	/*
-	 * Determine the preferred allocation location, i.e. the last lcn of
-	 * the mft data attribute.  The allocated size of the mft data
-	 * attribute cannot be zero so we are ok to do this.
-	 */
-	down_write(&mft_ni->runlist.lock);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->allocated_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	rl = ntfs_attr_find_vcn_nolock(mft_ni,
-			(ll - 1) >> vol->cluster_size_bits, NULL);
-	if (IS_ERR(rl) || unlikely(!rl->length || rl->lcn < 0)) {
-		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to determine last allocated "
-				"cluster of mft data attribute.");
-		if (!IS_ERR(rl))
-			ret = -EIO;
-		else
-			ret = PTR_ERR(rl);
-		return ret;
-	}
-	lcn = rl->lcn + rl->length;
-	ntfs_debug("Last lcn of mft data attribute is 0x%llx.", (long long)lcn);
-	/* Minimum allocation is one mft record worth of clusters. */
-	min_nr = vol->mft_record_size >> vol->cluster_size_bits;
-	if (!min_nr)
-		min_nr = 1;
-	/* Want to allocate 16 mft records worth of clusters. */
-	nr = vol->mft_record_size << 4 >> vol->cluster_size_bits;
-	if (!nr)
-		nr = min_nr;
-	/* Ensure we do not go above 2^32-1 mft records. */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->allocated_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
-			vol->mft_record_size_bits >= (1ll << 32))) {
-		nr = min_nr;
-		if (unlikely((ll + (nr << vol->cluster_size_bits)) >>
-				vol->mft_record_size_bits >= (1ll << 32))) {
-			ntfs_warning(vol->sb, "Cannot allocate mft record "
-					"because the maximum number of inodes "
-					"(2^32) has already been reached.");
-			up_write(&mft_ni->runlist.lock);
-			return -ENOSPC;
-		}
-	}
-	ntfs_debug("Trying mft data allocation with %s cluster count %lli.",
-			nr > min_nr ? "default" : "minimal", (long long)nr);
-	old_last_vcn = rl[1].vcn;
-	do {
-		rl2 = ntfs_cluster_alloc(vol, old_last_vcn, nr, lcn, MFT_ZONE,
-				true);
-		if (!IS_ERR(rl2))
-			break;
-		if (PTR_ERR(rl2) != -ENOSPC || nr == min_nr) {
-			ntfs_error(vol->sb, "Failed to allocate the minimal "
-					"number of clusters (%lli) for the "
-					"mft data attribute.", (long long)nr);
-			up_write(&mft_ni->runlist.lock);
-			return PTR_ERR(rl2);
-		}
-		/*
-		 * There is not enough space to do the allocation, but there
-		 * might be enough space to do a minimal allocation so try that
-		 * before failing.
-		 */
-		nr = min_nr;
-		ntfs_debug("Retrying mft data allocation with minimal cluster "
-				"count %lli.", (long long)nr);
-	} while (1);
-	rl = ntfs_runlists_merge(mft_ni->runlist.rl, rl2);
-	if (IS_ERR(rl)) {
-		up_write(&mft_ni->runlist.lock);
-		ntfs_error(vol->sb, "Failed to merge runlists for mft data "
-				"attribute.");
-		if (ntfs_cluster_free_from_rl(vol, rl2)) {
-			ntfs_error(vol->sb, "Failed to deallocate clusters "
-					"from the mft data attribute.%s", es);
-			NVolSetErrors(vol);
-		}
-		ntfs_free(rl2);
-		return PTR_ERR(rl);
-	}
-	mft_ni->runlist.rl = rl;
-	ntfs_debug("Allocated %lli clusters.", (long long)nr);
-	/* Find the last run in the new runlist. */
-	for (; rl[1].length; rl++)
-		;
-	/* Update the attribute record as well. */
-	mrec = map_mft_record(mft_ni);
-	if (IS_ERR(mrec)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		ret = PTR_ERR(mrec);
-		goto undo_alloc;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, mrec);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		ret = -ENOMEM;
-		goto undo_alloc;
-	}
-	ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.");
-		if (ret == -ENOENT)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	a = ctx->attr;
-	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
-	/* Search back for the previous last allocated cluster of mft bitmap. */
-	for (rl2 = rl; rl2 > mft_ni->runlist.rl; rl2--) {
-		if (ll >= rl2->vcn)
-			break;
-	}
-	BUG_ON(ll < rl2->vcn);
-	BUG_ON(ll >= rl2->vcn + rl2->length);
-	/* Get the size for the new mapping pairs array for this extent. */
-	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
-	if (unlikely(mp_size <= 0)) {
-		ntfs_error(vol->sb, "Get size for mapping pairs failed for "
-				"mft data attribute extent.");
-		ret = mp_size;
-		if (!ret)
-			ret = -EIO;
-		goto undo_alloc;
-	}
-	/* Expand the attribute record if necessary. */
-	old_alen = le32_to_cpu(a->length);
-	ret = ntfs_attr_record_resize(ctx->mrec, a, mp_size +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
-	if (unlikely(ret)) {
-		if (ret != -ENOSPC) {
-			ntfs_error(vol->sb, "Failed to resize attribute "
-					"record for mft data attribute.");
-			goto undo_alloc;
-		}
-		// TODO: Deal with this by moving this extent to a new mft
-		// record or by starting a new extent in a new mft record or by
-		// moving other attributes out of this mft record.
-		// Note: Use the special reserved mft records and ensure that
-		// this extent is not required to find the mft record in
-		// question.  If no free special records left we would need to
-		// move an existing record away, insert ours in its place, and
-		// then place the moved record into the newly allocated space
-		// and we would then need to update all references to this mft
-		// record appropriately.  This is rather complicated...
-		ntfs_error(vol->sb, "Not enough space in this mft record to "
-				"accommodate extended mft data attribute "
-				"extent.  Cannot handle this yet.");
-		ret = -EOPNOTSUPP;
-		goto undo_alloc;
-	}
-	mp_rebuilt = true;
-	/* Generate the mapping pairs array directly into the attr record. */
-	ret = ntfs_mapping_pairs_build(vol, (u8*)a +
-			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
-			mp_size, rl2, ll, -1, NULL);
-	if (unlikely(ret)) {
-		ntfs_error(vol->sb, "Failed to build mapping pairs array of "
-				"mft data attribute.");
-		goto undo_alloc;
-	}
-	/* Update the highest_vcn. */
-	a->data.non_resident.highest_vcn = cpu_to_sle64(rl[1].vcn - 1);
-	/*
-	 * We now have extended the mft data allocated_size by nr clusters.
-	 * Reflect this in the ntfs_inode structure and the attribute record.
-	 * @rl is the last (non-terminator) runlist element of mft data
-	 * attribute.
-	 */
-	if (a->data.non_resident.lowest_vcn) {
-		/*
-		 * We are not in the first attribute extent, switch to it, but
-		 * first ensure the changes will make it to disk later.
-		 */
-		flush_dcache_mft_record_page(ctx->ntfs_ino);
-		mark_mft_record_dirty(ctx->ntfs_ino);
-		ntfs_attr_reinit_search_ctx(ctx);
-		ret = ntfs_attr_lookup(mft_ni->type, mft_ni->name,
-				mft_ni->name_len, CASE_SENSITIVE, 0, NULL, 0,
-				ctx);
-		if (unlikely(ret)) {
-			ntfs_error(vol->sb, "Failed to find first attribute "
-					"extent of mft data attribute.");
-			goto restore_undo_alloc;
-		}
-		a = ctx->attr;
-	}
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	mft_ni->allocated_size += nr << vol->cluster_size_bits;
-	a->data.non_resident.allocated_size =
-			cpu_to_sle64(mft_ni->allocated_size);
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return 0;
-restore_undo_alloc:
-	ntfs_attr_reinit_search_ctx(ctx);
-	if (ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, rl[1].vcn, NULL, 0, ctx)) {
-		ntfs_error(vol->sb, "Failed to find last attribute extent of "
-				"mft data attribute.%s", es);
-		write_lock_irqsave(&mft_ni->size_lock, flags);
-		mft_ni->allocated_size += nr << vol->cluster_size_bits;
-		write_unlock_irqrestore(&mft_ni->size_lock, flags);
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		up_write(&mft_ni->runlist.lock);
-		/*
-		 * The only thing that is now wrong is ->allocated_size of the
-		 * base attribute extent which chkdsk should be able to fix.
-		 */
-		NVolSetErrors(vol);
-		return ret;
-	}
-	ctx->attr->data.non_resident.highest_vcn =
-			cpu_to_sle64(old_last_vcn - 1);
-undo_alloc:
-	if (ntfs_cluster_free(mft_ni, old_last_vcn, -1, ctx) < 0) {
-		ntfs_error(vol->sb, "Failed to free clusters from mft data "
-				"attribute.%s", es);
-		NVolSetErrors(vol);
-	}
-
-	if (ntfs_rl_truncate_nolock(vol, &mft_ni->runlist, old_last_vcn)) {
-		ntfs_error(vol->sb, "Failed to truncate mft data attribute "
-				"runlist.%s", es);
-		NVolSetErrors(vol);
-	}
-	if (ctx) {
-		a = ctx->attr;
-		if (mp_rebuilt && !IS_ERR(ctx->mrec)) {
-			if (ntfs_mapping_pairs_build(vol, (u8 *)a + le16_to_cpu(
-				a->data.non_resident.mapping_pairs_offset),
-				old_alen - le16_to_cpu(
-					a->data.non_resident.mapping_pairs_offset),
-				rl2, ll, -1, NULL)) {
-				ntfs_error(vol->sb, "Failed to restore mapping pairs "
-					"array.%s", es);
-				NVolSetErrors(vol);
-			}
-			if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) {
-				ntfs_error(vol->sb, "Failed to restore attribute "
-					"record.%s", es);
-				NVolSetErrors(vol);
-			}
-			flush_dcache_mft_record_page(ctx->ntfs_ino);
-			mark_mft_record_dirty(ctx->ntfs_ino);
-		} else if (IS_ERR(ctx->mrec)) {
-			ntfs_error(vol->sb, "Failed to restore attribute search "
-				"context.%s", es);
-			NVolSetErrors(vol);
-		}
-		ntfs_attr_put_search_ctx(ctx);
-	}
-	if (!IS_ERR(mrec))
-		unmap_mft_record(mft_ni);
-	up_write(&mft_ni->runlist.lock);
-	return ret;
-}
-
-/**
- * ntfs_mft_record_layout - layout an mft record into a memory buffer
- * @vol:	volume to which the mft record will belong
- * @mft_no:	mft reference specifying the mft record number
- * @m:		destination buffer of size >= @vol->mft_record_size bytes
- *
- * Layout an empty, unused mft record with the mft record number @mft_no into
- * the buffer @m.  The volume @vol is needed because the mft record structure
- * was modified in NTFS 3.1 so we need to know which volume version this mft
- * record will be used on.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_mft_record_layout(const ntfs_volume *vol, const s64 mft_no,
-		MFT_RECORD *m)
-{
-	ATTR_RECORD *a;
-
-	ntfs_debug("Entering for mft record 0x%llx.", (long long)mft_no);
-	if (mft_no >= (1ll << 32)) {
-		ntfs_error(vol->sb, "Mft record number 0x%llx exceeds "
-				"maximum of 2^32.", (long long)mft_no);
-		return -ERANGE;
-	}
-	/* Start by clearing the whole mft record to gives us a clean slate. */
-	memset(m, 0, vol->mft_record_size);
-	/* Aligned to 2-byte boundary. */
-	if (vol->major_ver < 3 || (vol->major_ver == 3 && !vol->minor_ver))
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD_OLD) + 1) & ~1);
-	else {
-		m->usa_ofs = cpu_to_le16((sizeof(MFT_RECORD) + 1) & ~1);
-		/*
-		 * Set the NTFS 3.1+ specific fields while we know that the
-		 * volume version is 3.1+.
-		 */
-		m->reserved = 0;
-		m->mft_record_number = cpu_to_le32((u32)mft_no);
-	}
-	m->magic = magic_FILE;
-	if (vol->mft_record_size >= NTFS_BLOCK_SIZE)
-		m->usa_count = cpu_to_le16(vol->mft_record_size /
-				NTFS_BLOCK_SIZE + 1);
-	else {
-		m->usa_count = cpu_to_le16(1);
-		ntfs_warning(vol->sb, "Sector size is bigger than mft record "
-				"size.  Setting usa_count to 1.  If chkdsk "
-				"reports this as corruption, please email "
-				"linux-ntfs-dev@lists.sourceforge.net stating "
-				"that you saw this message and that the "
-				"modified filesystem created was corrupt.  "
-				"Thank you.");
-	}
-	/* Set the update sequence number to 1. */
-	*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = cpu_to_le16(1);
-	m->lsn = 0;
-	m->sequence_number = cpu_to_le16(1);
-	m->link_count = 0;
-	/*
-	 * Place the attributes straight after the update sequence array,
-	 * aligned to 8-byte boundary.
-	 */
-	m->attrs_offset = cpu_to_le16((le16_to_cpu(m->usa_ofs) +
-			(le16_to_cpu(m->usa_count) << 1) + 7) & ~7);
-	m->flags = 0;
-	/*
-	 * Using attrs_offset plus eight bytes (for the termination attribute).
-	 * attrs_offset is already aligned to 8-byte boundary, so no need to
-	 * align again.
-	 */
-	m->bytes_in_use = cpu_to_le32(le16_to_cpu(m->attrs_offset) + 8);
-	m->bytes_allocated = cpu_to_le32(vol->mft_record_size);
-	m->base_mft_record = 0;
-	m->next_attr_instance = 0;
-	/* Add the termination attribute. */
-	a = (ATTR_RECORD*)((u8*)m + le16_to_cpu(m->attrs_offset));
-	a->type = AT_END;
-	a->length = 0;
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_mft_record_format - format an mft record on an ntfs volume
- * @vol:	volume on which to format the mft record
- * @mft_no:	mft record number to format
- *
- * Format the mft record @mft_no in $MFT/$DATA, i.e. lay out an empty, unused
- * mft record into the appropriate place of the mft data attribute.  This is
- * used when extending the mft data attribute.
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_mft_record_format(const ntfs_volume *vol, const s64 mft_no)
-{
-	loff_t i_size;
-	struct inode *mft_vi = vol->mft_ino;
-	struct page *page;
-	MFT_RECORD *m;
-	pgoff_t index, end_index;
-	unsigned int ofs;
-	int err;
-
-	ntfs_debug("Entering for mft record 0x%llx.", (long long)mft_no);
-	/*
-	 * The index into the page cache and the offset within the page cache
-	 * page of the wanted mft record.
-	 */
-	index = mft_no << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (mft_no << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* The maximum valid index into the page cache for $MFT's data. */
-	i_size = i_size_read(mft_vi);
-	end_index = i_size >> PAGE_SHIFT;
-	if (unlikely(index >= end_index)) {
-		if (unlikely(index > end_index || ofs + vol->mft_record_size >=
-				(i_size & ~PAGE_MASK))) {
-			ntfs_error(vol->sb, "Tried to format non-existing mft "
-					"record 0x%llx.", (long long)mft_no);
-			return -ENOENT;
-		}
-	}
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(mft_vi->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing mft record "
-				"to format 0x%llx.", (long long)mft_no);
-		return PTR_ERR(page);
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
-	err = ntfs_mft_record_layout(vol, mft_no, m);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to layout mft record 0x%llx.",
-				(long long)mft_no);
-		SetPageUptodate(page);
-		unlock_page(page);
-		ntfs_unmap_page(page);
-		return err;
-	}
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	unlock_page(page);
-	/*
-	 * Make sure the mft record is written out to disk.  We could use
-	 * ilookup5() to check if an inode is in icache and so on but this is
-	 * unnecessary as ntfs_writepage() will write the dirty record anyway.
-	 */
-	mark_ntfs_record_dirty(page, ofs);
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_mft_record_alloc - allocate an mft record on an ntfs volume
- * @vol:	[IN]  volume on which to allocate the mft record
- * @mode:	[IN]  mode if want a file or directory, i.e. base inode or 0
- * @base_ni:	[IN]  open base inode if allocating an extent mft record or NULL
- * @mrec:	[OUT] on successful return this is the mapped mft record
- *
- * Allocate an mft record in $MFT/$DATA of an open ntfs volume @vol.
- *
- * If @base_ni is NULL make the mft record a base mft record, i.e. a file or
- * direvctory inode, and allocate it at the default allocator position.  In
- * this case @mode is the file mode as given to us by the caller.  We in
- * particular use @mode to distinguish whether a file or a directory is being
- * created (S_IFDIR(mode) and S_IFREG(mode), respectively).
- *
- * If @base_ni is not NULL make the allocated mft record an extent record,
- * allocate it starting at the mft record after the base mft record and attach
- * the allocated and opened ntfs inode to the base inode @base_ni.  In this
- * case @mode must be 0 as it is meaningless for extent inodes.
- *
- * You need to check the return value with IS_ERR().  If false, the function
- * was successful and the return value is the now opened ntfs inode of the
- * allocated mft record.  *@mrec is then set to the allocated, mapped, pinned,
- * and locked mft record.  If IS_ERR() is true, the function failed and the
- * error code is obtained from PTR_ERR(return value).  *@mrec is undefined in
- * this case.
- *
- * Allocation strategy:
- *
- * To find a free mft record, we scan the mft bitmap for a zero bit.  To
- * optimize this we start scanning at the place specified by @base_ni or if
- * @base_ni is NULL we start where we last stopped and we perform wrap around
- * when we reach the end.  Note, we do not try to allocate mft records below
- * number 24 because numbers 0 to 15 are the defined system files anyway and 16
- * to 24 are special in that they are used for storing extension mft records
- * for the $DATA attribute of $MFT.  This is required to avoid the possibility
- * of creating a runlist with a circular dependency which once written to disk
- * can never be read in again.  Windows will only use records 16 to 24 for
- * normal files if the volume is completely out of space.  We never use them
- * which means that when the volume is really out of space we cannot create any
- * more files while Windows can still create up to 8 small files.  We can start
- * doing this at some later time, it does not matter much for now.
- *
- * When scanning the mft bitmap, we only search up to the last allocated mft
- * record.  If there are no free records left in the range 24 to number of
- * allocated mft records, then we extend the $MFT/$DATA attribute in order to
- * create free mft records.  We extend the allocated size of $MFT/$DATA by 16
- * records at a time or one cluster, if cluster size is above 16kiB.  If there
- * is not sufficient space to do this, we try to extend by a single mft record
- * or one cluster, if cluster size is above the mft record size.
- *
- * No matter how many mft records we allocate, we initialize only the first
- * allocated mft record, incrementing mft data size and initialized size
- * accordingly, open an ntfs_inode for it and return it to the caller, unless
- * there are less than 24 mft records, in which case we allocate and initialize
- * mft records until we reach record 24 which we consider as the first free mft
- * record for use by normal files.
- *
- * If during any stage we overflow the initialized data in the mft bitmap, we
- * extend the initialized size (and data size) by 8 bytes, allocating another
- * cluster if required.  The bitmap data size has to be at least equal to the
- * number of mft records in the mft, but it can be bigger, in which case the
- * superflous bits are padded with zeroes.
- *
- * Thus, when we return successfully (IS_ERR() is false), we will have:
- *	- initialized / extended the mft bitmap if necessary,
- *	- initialized / extended the mft data if necessary,
- *	- set the bit corresponding to the mft record being allocated in the
- *	  mft bitmap,
- *	- opened an ntfs_inode for the allocated mft record, and we will have
- *	- returned the ntfs_inode as well as the allocated mapped, pinned, and
- *	  locked mft record.
- *
- * On error, the volume will be left in a consistent state and no record will
- * be allocated.  If rolling back a partial operation fails, we may leave some
- * inconsistent metadata in which case we set NVolErrors() so the volume is
- * left dirty when unmounted.
- *
- * Note, this function cannot make use of most of the normal functions, like
- * for example for attribute resizing, etc, because when the run list overflows
- * the base mft record and an attribute list is used, it is very important that
- * the extension mft records used to store the $DATA attribute of $MFT can be
- * reached without having to read the information contained inside them, as
- * this would make it impossible to find them in the first place after the
- * volume is unmounted.  $MFT/$BITMAP probably does not need to follow this
- * rule because the bitmap is not essential for finding the mft records, but on
- * the other hand, handling the bitmap in this special way would make life
- * easier because otherwise there might be circular invocations of functions
- * when reading the bitmap.
- */
-ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
-		ntfs_inode *base_ni, MFT_RECORD **mrec)
-{
-	s64 ll, bit, old_data_initialized, old_data_size;
-	unsigned long flags;
-	struct inode *vi;
-	struct page *page;
-	ntfs_inode *mft_ni, *mftbmp_ni, *ni;
-	ntfs_attr_search_ctx *ctx;
-	MFT_RECORD *m;
-	ATTR_RECORD *a;
-	pgoff_t index;
-	unsigned int ofs;
-	int err;
-	le16 seq_no, usn;
-	bool record_formatted = false;
-
-	if (base_ni) {
-		ntfs_debug("Entering (allocating an extent mft record for "
-				"base mft record 0x%llx).",
-				(long long)base_ni->mft_no);
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(mode);
-	} else
-		ntfs_debug("Entering (allocating a base mft record).");
-	if (mode) {
-		/* @mode and @base_ni are mutually exclusive. */
-		BUG_ON(base_ni);
-		/* We only support creation of normal files and directories. */
-		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			return ERR_PTR(-EOPNOTSUPP);
-	}
-	BUG_ON(!mrec);
-	mft_ni = NTFS_I(vol->mft_ino);
-	mftbmp_ni = NTFS_I(vol->mftbmp_ino);
-	down_write(&vol->mftbmp_lock);
-	bit = ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(vol, base_ni);
-	if (bit >= 0) {
-		ntfs_debug("Found and allocated free record (#1), bit 0x%llx.",
-				(long long)bit);
-		goto have_alloc_rec;
-	}
-	if (bit != -ENOSPC) {
-		up_write(&vol->mftbmp_lock);
-		return ERR_PTR(bit);
-	}
-	/*
-	 * No free mft records left.  If the mft bitmap already covers more
-	 * than the currently used mft records, the next records are all free,
-	 * so we can simply allocate the first unused mft record.
-	 * Note: We also have to make sure that the mft bitmap at least covers
-	 * the first 24 mft records as they are special and whilst they may not
-	 * be in use, we do not allocate from them.
-	 */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ll = mft_ni->initialized_size >> vol->mft_record_size_bits;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_initialized = mftbmp_ni->initialized_size;
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	if (old_data_initialized << 3 > ll && old_data_initialized > 3) {
-		bit = ll;
-		if (bit < 24)
-			bit = 24;
-		if (unlikely(bit >= (1ll << 32)))
-			goto max_err_out;
-		ntfs_debug("Found free record (#2), bit 0x%llx.",
-				(long long)bit);
-		goto found_free_rec;
-	}
-	/*
-	 * The mft bitmap needs to be expanded until it covers the first unused
-	 * mft record that we can allocate.
-	 * Note: The smallest mft record we allocate is mft record 24.
-	 */
-	bit = old_data_initialized << 3;
-	if (unlikely(bit >= (1ll << 32)))
-		goto max_err_out;
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	old_data_size = mftbmp_ni->allocated_size;
-	ntfs_debug("Status of mftbmp before extension: allocated_size 0x%llx, "
-			"data_size 0x%llx, initialized_size 0x%llx.",
-			(long long)old_data_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)old_data_initialized);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-	if (old_data_initialized + 8 > old_data_size) {
-		/* Need to extend bitmap by one more cluster. */
-		ntfs_debug("mftbmp: initialized_size + 8 > allocated_size.");
-		err = ntfs_mft_bitmap_extend_allocation_nolock(vol);
-		if (unlikely(err)) {
-			up_write(&vol->mftbmp_lock);
-			goto err_out;
-		}
-#ifdef DEBUG
-		read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-		ntfs_debug("Status of mftbmp after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mftbmp_ni->allocated_size,
-				(long long)i_size_read(vol->mftbmp_ino),
-				(long long)mftbmp_ni->initialized_size);
-		read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-	}
-	/*
-	 * We now have sufficient allocated space, extend the initialized_size
-	 * as well as the data_size if necessary and fill the new space with
-	 * zeroes.
-	 */
-	err = ntfs_mft_bitmap_extend_initialized_nolock(vol);
-	if (unlikely(err)) {
-		up_write(&vol->mftbmp_lock);
-		goto err_out;
-	}
-#ifdef DEBUG
-	read_lock_irqsave(&mftbmp_ni->size_lock, flags);
-	ntfs_debug("Status of mftbmp after initialized extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mftbmp_ni->allocated_size,
-			(long long)i_size_read(vol->mftbmp_ino),
-			(long long)mftbmp_ni->initialized_size);
-	read_unlock_irqrestore(&mftbmp_ni->size_lock, flags);
-#endif /* DEBUG */
-	ntfs_debug("Found free record (#3), bit 0x%llx.", (long long)bit);
-found_free_rec:
-	/* @bit is the found free mft record, allocate it in the mft bitmap. */
-	ntfs_debug("At found_free_rec.");
-	err = ntfs_bitmap_set_bit(vol->mftbmp_ino, bit);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to allocate bit in mft bitmap.");
-		up_write(&vol->mftbmp_lock);
-		goto err_out;
-	}
-	ntfs_debug("Set bit 0x%llx in mft bitmap.", (long long)bit);
-have_alloc_rec:
-	/*
-	 * The mft bitmap is now uptodate.  Deal with mft data attribute now.
-	 * Note, we keep hold of the mft bitmap lock for writing until all
-	 * modifications to the mft data attribute are complete, too, as they
-	 * will impact decisions for mft bitmap and mft record allocation done
-	 * by a parallel allocation and if the lock is not maintained a
-	 * parallel allocation could allocate the same mft record as this one.
-	 */
-	ll = (bit + 1) << vol->mft_record_size_bits;
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	old_data_initialized = mft_ni->initialized_size;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	if (ll <= old_data_initialized) {
-		ntfs_debug("Allocated mft record already initialized.");
-		goto mft_rec_already_initialized;
-	}
-	ntfs_debug("Initializing allocated mft record.");
-	/*
-	 * The mft record is outside the initialized data.  Extend the mft data
-	 * attribute until it covers the allocated record.  The loop is only
-	 * actually traversed more than once when a freshly formatted volume is
-	 * first written to so it optimizes away nicely in the common case.
-	 */
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data before extension: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	while (ll > mft_ni->allocated_size) {
-		read_unlock_irqrestore(&mft_ni->size_lock, flags);
-		err = ntfs_mft_data_extend_allocation_nolock(vol);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to extend mft data "
-					"allocation.");
-			goto undo_mftbmp_alloc_nolock;
-		}
-		read_lock_irqsave(&mft_ni->size_lock, flags);
-		ntfs_debug("Status of mft data after allocation extension: "
-				"allocated_size 0x%llx, data_size 0x%llx, "
-				"initialized_size 0x%llx.",
-				(long long)mft_ni->allocated_size,
-				(long long)i_size_read(vol->mft_ino),
-				(long long)mft_ni->initialized_size);
-	}
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/*
-	 * Extend mft data initialized size (and data size of course) to reach
-	 * the allocated mft record, formatting the mft records allong the way.
-	 * Note: We only modify the ntfs_inode structure as that is all that is
-	 * needed by ntfs_mft_record_format().  We will update the attribute
-	 * record itself in one fell swoop later on.
-	 */
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	old_data_initialized = mft_ni->initialized_size;
-	old_data_size = vol->mft_ino->i_size;
-	while (ll > mft_ni->initialized_size) {
-		s64 new_initialized_size, mft_no;
-		
-		new_initialized_size = mft_ni->initialized_size +
-				vol->mft_record_size;
-		mft_no = mft_ni->initialized_size >> vol->mft_record_size_bits;
-		if (new_initialized_size > i_size_read(vol->mft_ino))
-			i_size_write(vol->mft_ino, new_initialized_size);
-		write_unlock_irqrestore(&mft_ni->size_lock, flags);
-		ntfs_debug("Initializing mft record 0x%llx.",
-				(long long)mft_no);
-		err = ntfs_mft_record_format(vol, mft_no);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to format mft record.");
-			goto undo_data_init;
-		}
-		write_lock_irqsave(&mft_ni->size_lock, flags);
-		mft_ni->initialized_size = new_initialized_size;
-	}
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	record_formatted = true;
-	/* Update the mft data attribute record to reflect the new sizes. */
-	m = map_mft_record(mft_ni);
-	if (IS_ERR(m)) {
-		ntfs_error(vol->sb, "Failed to map mft record.");
-		err = PTR_ERR(m);
-		goto undo_data_init;
-	}
-	ctx = ntfs_attr_get_search_ctx(mft_ni, m);
-	if (unlikely(!ctx)) {
-		ntfs_error(vol->sb, "Failed to get search context.");
-		err = -ENOMEM;
-		unmap_mft_record(mft_ni);
-		goto undo_data_init;
-	}
-	err = ntfs_attr_lookup(mft_ni->type, mft_ni->name, mft_ni->name_len,
-			CASE_SENSITIVE, 0, NULL, 0, ctx);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to find first attribute extent of "
-				"mft data attribute.");
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(mft_ni);
-		goto undo_data_init;
-	}
-	a = ctx->attr;
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	a->data.non_resident.initialized_size =
-			cpu_to_sle64(mft_ni->initialized_size);
-	a->data.non_resident.data_size =
-			cpu_to_sle64(i_size_read(vol->mft_ino));
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Ensure the changes make it to disk. */
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(mft_ni);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	ntfs_debug("Status of mft data after mft record initialization: "
-			"allocated_size 0x%llx, data_size 0x%llx, "
-			"initialized_size 0x%llx.",
-			(long long)mft_ni->allocated_size,
-			(long long)i_size_read(vol->mft_ino),
-			(long long)mft_ni->initialized_size);
-	BUG_ON(i_size_read(vol->mft_ino) > mft_ni->allocated_size);
-	BUG_ON(mft_ni->initialized_size > i_size_read(vol->mft_ino));
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-mft_rec_already_initialized:
-	/*
-	 * We can finally drop the mft bitmap lock as the mft data attribute
-	 * has been fully updated.  The only disparity left is that the
-	 * allocated mft record still needs to be marked as in use to match the
-	 * set bit in the mft bitmap but this is actually not a problem since
-	 * this mft record is not referenced from anywhere yet and the fact
-	 * that it is allocated in the mft bitmap means that no-one will try to
-	 * allocate it either.
-	 */
-	up_write(&vol->mftbmp_lock);
-	/*
-	 * We now have allocated and initialized the mft record.  Calculate the
-	 * index of and the offset within the page cache page the record is in.
-	 */
-	index = bit << vol->mft_record_size_bits >> PAGE_SHIFT;
-	ofs = (bit << vol->mft_record_size_bits) & ~PAGE_MASK;
-	/* Read, map, and pin the page containing the mft record. */
-	page = ntfs_map_page(vol->mft_ino->i_mapping, index);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to map page containing allocated "
-				"mft record 0x%llx.", (long long)bit);
-		err = PTR_ERR(page);
-		goto undo_mftbmp_alloc;
-	}
-	lock_page(page);
-	BUG_ON(!PageUptodate(page));
-	ClearPageUptodate(page);
-	m = (MFT_RECORD*)((u8*)page_address(page) + ofs);
-	/* If we just formatted the mft record no need to do it again. */
-	if (!record_formatted) {
-		/* Sanity check that the mft record is really not in use. */
-		if (ntfs_is_file_record(m->magic) &&
-				(m->flags & MFT_RECORD_IN_USE)) {
-			ntfs_error(vol->sb, "Mft record 0x%llx was marked "
-					"free in mft bitmap but is marked "
-					"used itself.  Corrupt filesystem.  "
-					"Unmount and run chkdsk.",
-					(long long)bit);
-			err = -EIO;
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			NVolSetErrors(vol);
-			goto undo_mftbmp_alloc;
-		}
-		/*
-		 * We need to (re-)format the mft record, preserving the
-		 * sequence number if it is not zero as well as the update
-		 * sequence number if it is not zero or -1 (0xffff).  This
-		 * means we do not need to care whether or not something went
-		 * wrong with the previous mft record.
-		 */
-		seq_no = m->sequence_number;
-		usn = *(le16*)((u8*)m + le16_to_cpu(m->usa_ofs));
-		err = ntfs_mft_record_layout(vol, bit, m);
-		if (unlikely(err)) {
-			ntfs_error(vol->sb, "Failed to layout allocated mft "
-					"record 0x%llx.", (long long)bit);
-			SetPageUptodate(page);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		if (seq_no)
-			m->sequence_number = seq_no;
-		if (usn && le16_to_cpu(usn) != 0xffff)
-			*(le16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = usn;
-	}
-	/* Set the mft record itself in use. */
-	m->flags |= MFT_RECORD_IN_USE;
-	if (S_ISDIR(mode))
-		m->flags |= MFT_RECORD_IS_DIRECTORY;
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	if (base_ni) {
-		MFT_RECORD *m_tmp;
-
-		/*
-		 * Setup the base mft record in the extent mft record.  This
-		 * completes initialization of the allocated extent mft record
-		 * and we can simply use it with map_extent_mft_record().
-		 */
-		m->base_mft_record = MK_LE_MREF(base_ni->mft_no,
-				base_ni->seq_no);
-		/*
-		 * Allocate an extent inode structure for the new mft record,
-		 * attach it to the base inode @base_ni and map, pin, and lock
-		 * its, i.e. the allocated, mft record.
-		 */
-		m_tmp = map_extent_mft_record(base_ni, bit, &ni);
-		if (IS_ERR(m_tmp)) {
-			ntfs_error(vol->sb, "Failed to map allocated extent "
-					"mft record 0x%llx.", (long long)bit);
-			err = PTR_ERR(m_tmp);
-			/* Set the mft record itself not in use. */
-			m->flags &= cpu_to_le16(
-					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
-			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		BUG_ON(m != m_tmp);
-		/*
-		 * Make sure the allocated mft record is written out to disk.
-		 * No need to set the inode dirty because the caller is going
-		 * to do that anyway after finishing with the new extent mft
-		 * record (e.g. at a minimum a new attribute will be added to
-		 * the mft record.
-		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
-		/*
-		 * Need to unmap the page since map_extent_mft_record() mapped
-		 * it as well so we have it mapped twice at the moment.
-		 */
-		ntfs_unmap_page(page);
-	} else {
-		/*
-		 * Allocate a new VFS inode and set it up.  NOTE: @vi->i_nlink
-		 * is set to 1 but the mft record->link_count is 0.  The caller
-		 * needs to bear this in mind.
-		 */
-		vi = new_inode(vol->sb);
-		if (unlikely(!vi)) {
-			err = -ENOMEM;
-			/* Set the mft record itself not in use. */
-			m->flags &= cpu_to_le16(
-					~le16_to_cpu(MFT_RECORD_IN_USE));
-			flush_dcache_page(page);
-			/* Make sure the mft record is written out to disk. */
-			mark_ntfs_record_dirty(page, ofs);
-			unlock_page(page);
-			ntfs_unmap_page(page);
-			goto undo_mftbmp_alloc;
-		}
-		vi->i_ino = bit;
-
-		/* The owner and group come from the ntfs volume. */
-		vi->i_uid = vol->uid;
-		vi->i_gid = vol->gid;
-
-		/* Initialize the ntfs specific part of @vi. */
-		ntfs_init_big_inode(vi);
-		ni = NTFS_I(vi);
-		/*
-		 * Set the appropriate mode, attribute type, and name.  For
-		 * directories, also setup the index values to the defaults.
-		 */
-		if (S_ISDIR(mode)) {
-			vi->i_mode = S_IFDIR | S_IRWXUGO;
-			vi->i_mode &= ~vol->dmask;
-
-			NInoSetMstProtected(ni);
-			ni->type = AT_INDEX_ALLOCATION;
-			ni->name = I30;
-			ni->name_len = 4;
-
-			ni->itype.index.block_size = 4096;
-			ni->itype.index.block_size_bits = ntfs_ffs(4096) - 1;
-			ni->itype.index.collation_rule = COLLATION_FILE_NAME;
-			if (vol->cluster_size <= ni->itype.index.block_size) {
-				ni->itype.index.vcn_size = vol->cluster_size;
-				ni->itype.index.vcn_size_bits =
-						vol->cluster_size_bits;
-			} else {
-				ni->itype.index.vcn_size = vol->sector_size;
-				ni->itype.index.vcn_size_bits =
-						vol->sector_size_bits;
-			}
-		} else {
-			vi->i_mode = S_IFREG | S_IRWXUGO;
-			vi->i_mode &= ~vol->fmask;
-
-			ni->type = AT_DATA;
-			ni->name = NULL;
-			ni->name_len = 0;
-		}
-		if (IS_RDONLY(vi))
-			vi->i_mode &= ~S_IWUGO;
-
-		/* Set the inode times to the current time. */
-		simple_inode_init_ts(vi);
-		/*
-		 * Set the file size to 0, the ntfs inode sizes are set to 0 by
-		 * the call to ntfs_init_big_inode() below.
-		 */
-		vi->i_size = 0;
-		vi->i_blocks = 0;
-
-		/* Set the sequence number. */
-		vi->i_generation = ni->seq_no = le16_to_cpu(m->sequence_number);
-		/*
-		 * Manually map, pin, and lock the mft record as we already
-		 * have its page mapped and it is very easy to do.
-		 */
-		atomic_inc(&ni->count);
-		mutex_lock(&ni->mrec_lock);
-		ni->page = page;
-		ni->page_ofs = ofs;
-		/*
-		 * Make sure the allocated mft record is written out to disk.
-		 * NOTE: We do not set the ntfs inode dirty because this would
-		 * fail in ntfs_write_inode() because the inode does not have a
-		 * standard information attribute yet.  Also, there is no need
-		 * to set the inode dirty because the caller is going to do
-		 * that anyway after finishing with the new mft record (e.g. at
-		 * a minimum some new attributes will be added to the mft
-		 * record.
-		 */
-		mark_ntfs_record_dirty(page, ofs);
-		unlock_page(page);
-
-		/* Add the inode to the inode hash for the superblock. */
-		insert_inode_hash(vi);
-
-		/* Update the default mft allocation position. */
-		vol->mft_data_pos = bit + 1;
-	}
-	/*
-	 * Return the opened, allocated inode of the allocated mft record as
-	 * well as the mapped, pinned, and locked mft record.
-	 */
-	ntfs_debug("Returning opened, allocated %sinode 0x%llx.",
-			base_ni ? "extent " : "", (long long)bit);
-	*mrec = m;
-	return ni;
-undo_data_init:
-	write_lock_irqsave(&mft_ni->size_lock, flags);
-	mft_ni->initialized_size = old_data_initialized;
-	i_size_write(vol->mft_ino, old_data_size);
-	write_unlock_irqrestore(&mft_ni->size_lock, flags);
-	goto undo_mftbmp_alloc_nolock;
-undo_mftbmp_alloc:
-	down_write(&vol->mftbmp_lock);
-undo_mftbmp_alloc_nolock:
-	if (ntfs_bitmap_clear_bit(vol->mftbmp_ino, bit)) {
-		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
-		NVolSetErrors(vol);
-	}
-	up_write(&vol->mftbmp_lock);
-err_out:
-	return ERR_PTR(err);
-max_err_out:
-	ntfs_warning(vol->sb, "Cannot allocate mft record because the maximum "
-			"number of inodes (2^32) has already been reached.");
-	up_write(&vol->mftbmp_lock);
-	return ERR_PTR(-ENOSPC);
-}
-
-/**
- * ntfs_extent_mft_record_free - free an extent mft record on an ntfs volume
- * @ni:		ntfs inode of the mapped extent mft record to free
- * @m:		mapped extent mft record of the ntfs inode @ni
- *
- * Free the mapped extent mft record @m of the extent ntfs inode @ni.
- *
- * Note that this function unmaps the mft record and closes and destroys @ni
- * internally and hence you cannot use either @ni nor @m any more after this
- * function returns success.
- *
- * On success return 0 and on error return -errno.  @ni and @m are still valid
- * in this case and have not been freed.
- *
- * For some errors an error message is displayed and the success code 0 is
- * returned and the volume is then left dirty on umount.  This makes sense in
- * case we could not rollback the changes that were already done since the
- * caller no longer wants to reference this mft record so it does not matter to
- * the caller if something is wrong with it as long as it is properly detached
- * from the base inode.
- */
-int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m)
-{
-	unsigned long mft_no = ni->mft_no;
-	ntfs_volume *vol = ni->vol;
-	ntfs_inode *base_ni;
-	ntfs_inode **extent_nis;
-	int i, err;
-	le16 old_seq_no;
-	u16 seq_no;
-	
-	BUG_ON(NInoAttr(ni));
-	BUG_ON(ni->nr_extents != -1);
-
-	mutex_lock(&ni->extent_lock);
-	base_ni = ni->ext.base_ntfs_ino;
-	mutex_unlock(&ni->extent_lock);
-
-	BUG_ON(base_ni->nr_extents <= 0);
-
-	ntfs_debug("Entering for extent inode 0x%lx, base inode 0x%lx.\n",
-			mft_no, base_ni->mft_no);
-
-	mutex_lock(&base_ni->extent_lock);
-
-	/* Make sure we are holding the only reference to the extent inode. */
-	if (atomic_read(&ni->count) > 2) {
-		ntfs_error(vol->sb, "Tried to free busy extent inode 0x%lx, "
-				"not freeing.", base_ni->mft_no);
-		mutex_unlock(&base_ni->extent_lock);
-		return -EBUSY;
-	}
-
-	/* Dissociate the ntfs inode from the base inode. */
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	err = -ENOENT;
-	for (i = 0; i < base_ni->nr_extents; i++) {
-		if (ni != extent_nis[i])
-			continue;
-		extent_nis += i;
-		base_ni->nr_extents--;
-		memmove(extent_nis, extent_nis + 1, (base_ni->nr_extents - i) *
-				sizeof(ntfs_inode*));
-		err = 0;
-		break;
-	}
-
-	mutex_unlock(&base_ni->extent_lock);
-
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Extent inode 0x%lx is not attached to "
-				"its base inode 0x%lx.", mft_no,
-				base_ni->mft_no);
-		BUG();
-	}
-
-	/*
-	 * The extent inode is no longer attached to the base inode so no one
-	 * can get a reference to it any more.
-	 */
-
-	/* Mark the mft record as not in use. */
-	m->flags &= ~MFT_RECORD_IN_USE;
-
-	/* Increment the sequence number, skipping zero, if it is not zero. */
-	old_seq_no = m->sequence_number;
-	seq_no = le16_to_cpu(old_seq_no);
-	if (seq_no == 0xffff)
-		seq_no = 1;
-	else if (seq_no)
-		seq_no++;
-	m->sequence_number = cpu_to_le16(seq_no);
-
-	/*
-	 * Set the ntfs inode dirty and write it out.  We do not need to worry
-	 * about the base inode here since whatever caused the extent mft
-	 * record to be freed is guaranteed to do it already.
-	 */
-	NInoSetDirty(ni);
-	err = write_mft_record(ni, m, 0);
-	if (unlikely(err)) {
-		ntfs_error(vol->sb, "Failed to write mft record 0x%lx, not "
-				"freeing.", mft_no);
-		goto rollback;
-	}
-rollback_error:
-	/* Unmap and throw away the now freed extent inode. */
-	unmap_extent_mft_record(ni);
-	ntfs_clear_extent_inode(ni);
-
-	/* Clear the bit in the $MFT/$BITMAP corresponding to this record. */
-	down_write(&vol->mftbmp_lock);
-	err = ntfs_bitmap_clear_bit(vol->mftbmp_ino, mft_no);
-	up_write(&vol->mftbmp_lock);
-	if (unlikely(err)) {
-		/*
-		 * The extent inode is gone but we failed to deallocate it in
-		 * the mft bitmap.  Just emit a warning and leave the volume
-		 * dirty on umount.
-		 */
-		ntfs_error(vol->sb, "Failed to clear bit in mft bitmap.%s", es);
-		NVolSetErrors(vol);
-	}
-	return 0;
-rollback:
-	/* Rollback what we did... */
-	mutex_lock(&base_ni->extent_lock);
-	extent_nis = base_ni->ext.extent_ntfs_inos;
-	if (!(base_ni->nr_extents & 3)) {
-		int new_size = (base_ni->nr_extents + 4) * sizeof(ntfs_inode*);
-
-		extent_nis = kmalloc(new_size, GFP_NOFS);
-		if (unlikely(!extent_nis)) {
-			ntfs_error(vol->sb, "Failed to allocate internal "
-					"buffer during rollback.%s", es);
-			mutex_unlock(&base_ni->extent_lock);
-			NVolSetErrors(vol);
-			goto rollback_error;
-		}
-		if (base_ni->nr_extents) {
-			BUG_ON(!base_ni->ext.extent_ntfs_inos);
-			memcpy(extent_nis, base_ni->ext.extent_ntfs_inos,
-					new_size - 4 * sizeof(ntfs_inode*));
-			kfree(base_ni->ext.extent_ntfs_inos);
-		}
-		base_ni->ext.extent_ntfs_inos = extent_nis;
-	}
-	m->flags |= MFT_RECORD_IN_USE;
-	m->sequence_number = old_seq_no;
-	extent_nis[base_ni->nr_extents++] = ni;
-	mutex_unlock(&base_ni->extent_lock);
-	mark_mft_record_dirty(ni);
-	return err;
-}
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h
deleted file mode 100644
index 49c001af16ed..000000000000
--- a/fs/ntfs/mft.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * mft.h - Defines for mft record handling in NTFS Linux kernel driver.
- *	   Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_MFT_H
-#define _LINUX_NTFS_MFT_H
-
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-
-#include "inode.h"
-
-extern MFT_RECORD *map_mft_record(ntfs_inode *ni);
-extern void unmap_mft_record(ntfs_inode *ni);
-
-extern MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
-		ntfs_inode **ntfs_ino);
-
-static inline void unmap_extent_mft_record(ntfs_inode *ni)
-{
-	unmap_mft_record(ni);
-	return;
-}
-
-#ifdef NTFS_RW
-
-/**
- * flush_dcache_mft_record_page - flush_dcache_page() for mft records
- * @ni:		ntfs inode structure of mft record
- *
- * Call flush_dcache_page() for the page in which an mft record resides.
- *
- * This must be called every time an mft record is modified, just after the
- * modification.
- */
-static inline void flush_dcache_mft_record_page(ntfs_inode *ni)
-{
-	flush_dcache_page(ni->page);
-}
-
-extern void __mark_mft_record_dirty(ntfs_inode *ni);
-
-/**
- * mark_mft_record_dirty - set the mft record and the page containing it dirty
- * @ni:		ntfs inode describing the mapped mft record
- *
- * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni,
- * as well as the page containing the mft record, dirty.  Also, mark the base
- * vfs inode dirty.  This ensures that any changes to the mft record are
- * written out to disk.
- *
- * NOTE:  Do not do anything if the mft record is already marked dirty.
- */
-static inline void mark_mft_record_dirty(ntfs_inode *ni)
-{
-	if (!NInoTestSetDirty(ni))
-		__mark_mft_record_dirty(ni);
-}
-
-extern int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
-		MFT_RECORD *m, int sync);
-
-extern int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync);
-
-/**
- * write_mft_record - write out a mapped (extent) mft record
- * @ni:		ntfs inode describing the mapped (extent) mft record
- * @m:		mapped (extent) mft record to write
- * @sync:	if true, wait for i/o completion
- *
- * This is just a wrapper for write_mft_record_nolock() (see mft.c), which
- * locks the page for the duration of the write.  This ensures that there are
- * no race conditions between writing the mft record via the dirty inode code
- * paths and via the page cache write back code paths or between writing
- * neighbouring mft records residing in the same page.
- *
- * Locking the page also serializes us against ->read_folio() if the page is not
- * uptodate.
- *
- * On success, clean the mft record and return 0.  On error, leave the mft
- * record dirty and return -errno.
- */
-static inline int write_mft_record(ntfs_inode *ni, MFT_RECORD *m, int sync)
-{
-	struct page *page = ni->page;
-	int err;
-
-	BUG_ON(!page);
-	lock_page(page);
-	err = write_mft_record_nolock(ni, m, sync);
-	unlock_page(page);
-	return err;
-}
-
-extern bool ntfs_may_write_mft_record(ntfs_volume *vol,
-		const unsigned long mft_no, const MFT_RECORD *m,
-		ntfs_inode **locked_ni);
-
-extern ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode,
-		ntfs_inode *base_ni, MFT_RECORD **mrec);
-extern int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_MFT_H */
diff --git a/fs/ntfs/mst.c b/fs/ntfs/mst.c
deleted file mode 100644
index 16b3c884abfc..000000000000
--- a/fs/ntfs/mst.c
+++ /dev/null
@@ -1,189 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * mst.c - NTFS multi sector transfer protection handling code. Part of the
- *	   Linux-NTFS project.
- *
- * Copyright (c) 2001-2004 Anton Altaparmakov
- */
-
-#include "ntfs.h"
-
-/**
- * post_read_mst_fixup - deprotect multi sector transfer protected data
- * @b:		pointer to the data to deprotect
- * @size:	size in bytes of @b
- *
- * Perform the necessary post read multi sector transfer fixup and detect the
- * presence of incomplete multi sector transfers. - In that case, overwrite the
- * magic of the ntfs record header being processed with "BAAD" (in memory only!)
- * and abort processing.
- *
- * Return 0 on success and -EINVAL on error ("BAAD" magic will be present).
- *
- * NOTE: We consider the absence / invalidity of an update sequence array to
- * mean that the structure is not protected at all and hence doesn't need to
- * be fixed up. Thus, we return success and not failure in this case. This is
- * in contrast to pre_write_mst_fixup(), see below.
- */
-int post_read_mst_fixup(NTFS_RECORD *b, const u32 size)
-{
-	u16 usa_ofs, usa_count, usn;
-	u16 *usa_pos, *data_pos;
-
-	/* Setup the variables. */
-	usa_ofs = le16_to_cpu(b->usa_ofs);
-	/* Decrement usa_count to get number of fixups. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
-		return 0;
-	/* Position of usn in update sequence array. */
-	usa_pos = (u16*)b + usa_ofs/sizeof(u16);
-	/*
-	 * The update sequence number which has to be equal to each of the
-	 * u16 values before they are fixed up. Note no need to care for
-	 * endianness since we are comparing and moving data for on disk
-	 * structures which means the data is consistent. - If it is
-	 * consistenty the wrong endianness it doesn't make any difference.
-	 */
-	usn = *usa_pos;
-	/*
-	 * Position in protected data of first u16 that needs fixing up.
-	 */
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
-	/*
-	 * Check for incomplete multi sector transfer(s).
-	 */
-	while (usa_count--) {
-		if (*data_pos != usn) {
-			/*
-			 * Incomplete multi sector transfer detected! )-:
-			 * Set the magic to "BAAD" and return failure.
-			 * Note that magic_BAAD is already converted to le32.
-			 */
-			b->magic = magic_BAAD;
-			return -EINVAL;
-		}
-		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
-	}
-	/* Re-setup the variables. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	data_pos = (u16*)b + NTFS_BLOCK_SIZE/sizeof(u16) - 1;
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment position in usa and restore original data from
-		 * the usa into the data buffer.
-		 */
-		*data_pos = *(++usa_pos);
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(u16);
-	}
-	return 0;
-}
-
-/**
- * pre_write_mst_fixup - apply multi sector transfer protection
- * @b:		pointer to the data to protect
- * @size:	size in bytes of @b
- *
- * Perform the necessary pre write multi sector transfer fixup on the data
- * pointer to by @b of @size.
- *
- * Return 0 if fixup applied (success) or -EINVAL if no fixup was performed
- * (assumed not needed). This is in contrast to post_read_mst_fixup() above.
- *
- * NOTE: We consider the absence / invalidity of an update sequence array to
- * mean that the structure is not subject to protection and hence doesn't need
- * to be fixed up. This means that you have to create a valid update sequence
- * array header in the ntfs record before calling this function, otherwise it
- * will fail (the header needs to contain the position of the update sequence
- * array together with the number of elements in the array). You also need to
- * initialise the update sequence number before calling this function
- * otherwise a random word will be used (whatever was in the record at that
- * position at that time).
- */
-int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size)
-{
-	le16 *usa_pos, *data_pos;
-	u16 usa_ofs, usa_count, usn;
-	le16 le_usn;
-
-	/* Sanity check + only fixup if it makes sense. */
-	if (!b || ntfs_is_baad_record(b->magic) ||
-			ntfs_is_hole_record(b->magic))
-		return -EINVAL;
-	/* Setup the variables. */
-	usa_ofs = le16_to_cpu(b->usa_ofs);
-	/* Decrement usa_count to get number of fixups. */
-	usa_count = le16_to_cpu(b->usa_count) - 1;
-	/* Size and alignment checks. */
-	if ( size & (NTFS_BLOCK_SIZE - 1)	||
-	     usa_ofs & 1			||
-	     usa_ofs + (usa_count * 2) > size	||
-	     (size >> NTFS_BLOCK_SIZE_BITS) != usa_count)
-		return -EINVAL;
-	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)((u8*)b + usa_ofs);
-	/*
-	 * Cyclically increment the update sequence number
-	 * (skipping 0 and -1, i.e. 0xffff).
-	 */
-	usn = le16_to_cpup(usa_pos) + 1;
-	if (usn == 0xffff || !usn)
-		usn = 1;
-	le_usn = cpu_to_le16(usn);
-	*usa_pos = le_usn;
-	/* Position in data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment the position in the usa and save the
-		 * original data from the data buffer into the usa.
-		 */
-		*(++usa_pos) = *data_pos;
-		/* Apply fixup to data. */
-		*data_pos = le_usn;
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
-	}
-	return 0;
-}
-
-/**
- * post_write_mst_fixup - fast deprotect multi sector transfer protected data
- * @b:		pointer to the data to deprotect
- *
- * Perform the necessary post write multi sector transfer fixup, not checking
- * for any errors, because we assume we have just used pre_write_mst_fixup(),
- * thus the data will be fine or we would never have gotten here.
- */
-void post_write_mst_fixup(NTFS_RECORD *b)
-{
-	le16 *usa_pos, *data_pos;
-
-	u16 usa_ofs = le16_to_cpu(b->usa_ofs);
-	u16 usa_count = le16_to_cpu(b->usa_count) - 1;
-
-	/* Position of usn in update sequence array. */
-	usa_pos = (le16*)b + usa_ofs/sizeof(le16);
-
-	/* Position in protected data of first u16 that needs fixing up. */
-	data_pos = (le16*)b + NTFS_BLOCK_SIZE/sizeof(le16) - 1;
-
-	/* Fixup all sectors. */
-	while (usa_count--) {
-		/*
-		 * Increment position in usa and restore original data from
-		 * the usa into the data buffer.
-		 */
-		*data_pos = *(++usa_pos);
-
-		/* Increment position in data as well. */
-		data_pos += NTFS_BLOCK_SIZE/sizeof(le16);
-	}
-}
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
deleted file mode 100644
index d7498ddc4a72..000000000000
--- a/fs/ntfs/namei.c
+++ /dev/null
@@ -1,392 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * namei.c - NTFS kernel directory inode operations. Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include <linux/dcache.h>
-#include <linux/exportfs.h>
-#include <linux/security.h>
-#include <linux/slab.h>
-
-#include "attrib.h"
-#include "debug.h"
-#include "dir.h"
-#include "mft.h"
-#include "ntfs.h"
-
-/**
- * ntfs_lookup - find the inode represented by a dentry in a directory inode
- * @dir_ino:	directory inode in which to look for the inode
- * @dent:	dentry representing the inode to look for
- * @flags:	lookup flags
- *
- * In short, ntfs_lookup() looks for the inode represented by the dentry @dent
- * in the directory inode @dir_ino and if found attaches the inode to the
- * dentry @dent.
- *
- * In more detail, the dentry @dent specifies which inode to look for by
- * supplying the name of the inode in @dent->d_name.name. ntfs_lookup()
- * converts the name to Unicode and walks the contents of the directory inode
- * @dir_ino looking for the converted Unicode name. If the name is found in the
- * directory, the corresponding inode is loaded by calling ntfs_iget() on its
- * inode number and the inode is associated with the dentry @dent via a call to
- * d_splice_alias().
- *
- * If the name is not found in the directory, a NULL inode is inserted into the
- * dentry @dent via a call to d_add(). The dentry is then termed a negative
- * dentry.
- *
- * Only if an actual error occurs, do we return an error via ERR_PTR().
- *
- * In order to handle the case insensitivity issues of NTFS with regards to the
- * dcache and the dcache requiring only one dentry per directory, we deal with
- * dentry aliases that only differ in case in ->ntfs_lookup() while maintaining
- * a case sensitive dcache. This means that we get the full benefit of dcache
- * speed when the file/directory is looked up with the same case as returned by
- * ->ntfs_readdir() but that a lookup for any other case (or for the short file
- * name) will not find anything in dcache and will enter ->ntfs_lookup()
- * instead, where we search the directory for a fully matching file name
- * (including case) and if that is not found, we search for a file name that
- * matches with different case and if that has non-POSIX semantics we return
- * that. We actually do only one search (case sensitive) and keep tabs on
- * whether we have found a case insensitive match in the process.
- *
- * To simplify matters for us, we do not treat the short vs long filenames as
- * two hard links but instead if the lookup matches a short filename, we
- * return the dentry for the corresponding long filename instead.
- *
- * There are three cases we need to distinguish here:
- *
- * 1) @dent perfectly matches (i.e. including case) a directory entry with a
- *    file name in the WIN32 or POSIX namespaces. In this case
- *    ntfs_lookup_inode_by_name() will return with name set to NULL and we
- *    just d_splice_alias() @dent.
- * 2) @dent matches (not including case) a directory entry with a file name in
- *    the WIN32 namespace. In this case ntfs_lookup_inode_by_name() will return
- *    with name set to point to a kmalloc()ed ntfs_name structure containing
- *    the properly cased little endian Unicode name. We convert the name to the
- *    current NLS code page, search if a dentry with this name already exists
- *    and if so return that instead of @dent.  At this point things are
- *    complicated by the possibility of 'disconnected' dentries due to NFS
- *    which we deal with appropriately (see the code comments).  The VFS will
- *    then destroy the old @dent and use the one we returned.  If a dentry is
- *    not found, we allocate a new one, d_splice_alias() it, and return it as
- *    above.
- * 3) @dent matches either perfectly or not (i.e. we don't care about case) a
- *    directory entry with a file name in the DOS namespace. In this case
- *    ntfs_lookup_inode_by_name() will return with name set to point to a
- *    kmalloc()ed ntfs_name structure containing the mft reference (cpu endian)
- *    of the inode. We use the mft reference to read the inode and to find the
- *    file name in the WIN32 namespace corresponding to the matched short file
- *    name. We then convert the name to the current NLS code page, and proceed
- *    searching for a dentry with this name, etc, as in case 2), above.
- *
- * Locking: Caller must hold i_mutex on the directory.
- */
-static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
-		unsigned int flags)
-{
-	ntfs_volume *vol = NTFS_SB(dir_ino->i_sb);
-	struct inode *dent_inode;
-	ntfschar *uname;
-	ntfs_name *name = NULL;
-	MFT_REF mref;
-	unsigned long dent_ino;
-	int uname_len;
-
-	ntfs_debug("Looking up %pd in directory inode 0x%lx.",
-			dent, dir_ino->i_ino);
-	/* Convert the name of the dentry to Unicode. */
-	uname_len = ntfs_nlstoucs(vol, dent->d_name.name, dent->d_name.len,
-			&uname);
-	if (uname_len < 0) {
-		if (uname_len != -ENAMETOOLONG)
-			ntfs_error(vol->sb, "Failed to convert name to "
-					"Unicode.");
-		return ERR_PTR(uname_len);
-	}
-	mref = ntfs_lookup_inode_by_name(NTFS_I(dir_ino), uname, uname_len,
-			&name);
-	kmem_cache_free(ntfs_name_cache, uname);
-	if (!IS_ERR_MREF(mref)) {
-		dent_ino = MREF(mref);
-		ntfs_debug("Found inode 0x%lx. Calling ntfs_iget.", dent_ino);
-		dent_inode = ntfs_iget(vol->sb, dent_ino);
-		if (!IS_ERR(dent_inode)) {
-			/* Consistency check. */
-			if (is_bad_inode(dent_inode) || MSEQNO(mref) ==
-					NTFS_I(dent_inode)->seq_no ||
-					dent_ino == FILE_MFT) {
-				/* Perfect WIN32/POSIX match. -- Case 1. */
-				if (!name) {
-					ntfs_debug("Done.  (Case 1.)");
-					return d_splice_alias(dent_inode, dent);
-				}
-				/*
-				 * We are too indented.  Handle imperfect
-				 * matches and short file names further below.
-				 */
-				goto handle_name;
-			}
-			ntfs_error(vol->sb, "Found stale reference to inode "
-					"0x%lx (reference sequence number = "
-					"0x%x, inode sequence number = 0x%x), "
-					"returning -EIO. Run chkdsk.",
-					dent_ino, MSEQNO(mref),
-					NTFS_I(dent_inode)->seq_no);
-			iput(dent_inode);
-			dent_inode = ERR_PTR(-EIO);
-		} else
-			ntfs_error(vol->sb, "ntfs_iget(0x%lx) failed with "
-					"error code %li.", dent_ino,
-					PTR_ERR(dent_inode));
-		kfree(name);
-		/* Return the error code. */
-		return ERR_CAST(dent_inode);
-	}
-	/* It is guaranteed that @name is no longer allocated at this point. */
-	if (MREF_ERR(mref) == -ENOENT) {
-		ntfs_debug("Entry was not found, adding negative dentry.");
-		/* The dcache will handle negative entries. */
-		d_add(dent, NULL);
-		ntfs_debug("Done.");
-		return NULL;
-	}
-	ntfs_error(vol->sb, "ntfs_lookup_ino_by_name() failed with error "
-			"code %i.", -MREF_ERR(mref));
-	return ERR_PTR(MREF_ERR(mref));
-	// TODO: Consider moving this lot to a separate function! (AIA)
-handle_name:
-   {
-	MFT_RECORD *m;
-	ntfs_attr_search_ctx *ctx;
-	ntfs_inode *ni = NTFS_I(dent_inode);
-	int err;
-	struct qstr nls_name;
-
-	nls_name.name = NULL;
-	if (name->type != FILE_NAME_DOS) {			/* Case 2. */
-		ntfs_debug("Case 2.");
-		nls_name.len = (unsigned)ntfs_ucstonls(vol,
-				(ntfschar*)&name->name, name->len,
-				(unsigned char**)&nls_name.name, 0);
-		kfree(name);
-	} else /* if (name->type == FILE_NAME_DOS) */ {		/* Case 3. */
-		FILE_NAME_ATTR *fn;
-
-		ntfs_debug("Case 3.");
-		kfree(name);
-
-		/* Find the WIN32 name corresponding to the matched DOS name. */
-		ni = NTFS_I(dent_inode);
-		m = map_mft_record(ni);
-		if (IS_ERR(m)) {
-			err = PTR_ERR(m);
-			m = NULL;
-			ctx = NULL;
-			goto err_out;
-		}
-		ctx = ntfs_attr_get_search_ctx(ni, m);
-		if (unlikely(!ctx)) {
-			err = -ENOMEM;
-			goto err_out;
-		}
-		do {
-			ATTR_RECORD *a;
-			u32 val_len;
-
-			err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, 0, 0,
-					NULL, 0, ctx);
-			if (unlikely(err)) {
-				ntfs_error(vol->sb, "Inode corrupt: No WIN32 "
-						"namespace counterpart to DOS "
-						"file name. Run chkdsk.");
-				if (err == -ENOENT)
-					err = -EIO;
-				goto err_out;
-			}
-			/* Consistency checks. */
-			a = ctx->attr;
-			if (a->non_resident || a->flags)
-				goto eio_err_out;
-			val_len = le32_to_cpu(a->data.resident.value_length);
-			if (le16_to_cpu(a->data.resident.value_offset) +
-					val_len > le32_to_cpu(a->length))
-				goto eio_err_out;
-			fn = (FILE_NAME_ATTR*)((u8*)ctx->attr + le16_to_cpu(
-					ctx->attr->data.resident.value_offset));
-			if ((u32)(fn->file_name_length * sizeof(ntfschar) +
-					sizeof(FILE_NAME_ATTR)) > val_len)
-				goto eio_err_out;
-		} while (fn->file_name_type != FILE_NAME_WIN32);
-
-		/* Convert the found WIN32 name to current NLS code page. */
-		nls_name.len = (unsigned)ntfs_ucstonls(vol,
-				(ntfschar*)&fn->file_name, fn->file_name_length,
-				(unsigned char**)&nls_name.name, 0);
-
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-	}
-	m = NULL;
-	ctx = NULL;
-
-	/* Check if a conversion error occurred. */
-	if ((signed)nls_name.len < 0) {
-		err = (signed)nls_name.len;
-		goto err_out;
-	}
-	nls_name.hash = full_name_hash(dent, nls_name.name, nls_name.len);
-
-	dent = d_add_ci(dent, dent_inode, &nls_name);
-	kfree(nls_name.name);
-	return dent;
-
-eio_err_out:
-	ntfs_error(vol->sb, "Illegal file name attribute. Run chkdsk.");
-	err = -EIO;
-err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	if (m)
-		unmap_mft_record(ni);
-	iput(dent_inode);
-	ntfs_error(vol->sb, "Failed, returning error code %i.", err);
-	return ERR_PTR(err);
-   }
-}
-
-/*
- * Inode operations for directories.
- */
-const struct inode_operations ntfs_dir_inode_ops = {
-	.lookup	= ntfs_lookup,	/* VFS: Lookup directory. */
-};
-
-/**
- * ntfs_get_parent - find the dentry of the parent of a given directory dentry
- * @child_dent:		dentry of the directory whose parent directory to find
- *
- * Find the dentry for the parent directory of the directory specified by the
- * dentry @child_dent.  This function is called from
- * fs/exportfs/expfs.c::find_exported_dentry() which in turn is called from the
- * default ->decode_fh() which is export_decode_fh() in the same file.
- *
- * The code is based on the ext3 ->get_parent() implementation found in
- * fs/ext3/namei.c::ext3_get_parent().
- *
- * Note: ntfs_get_parent() is called with @d_inode(child_dent)->i_mutex down.
- *
- * Return the dentry of the parent directory on success or the error code on
- * error (IS_ERR() is true).
- */
-static struct dentry *ntfs_get_parent(struct dentry *child_dent)
-{
-	struct inode *vi = d_inode(child_dent);
-	ntfs_inode *ni = NTFS_I(vi);
-	MFT_RECORD *mrec;
-	ntfs_attr_search_ctx *ctx;
-	ATTR_RECORD *attr;
-	FILE_NAME_ATTR *fn;
-	unsigned long parent_ino;
-	int err;
-
-	ntfs_debug("Entering for inode 0x%lx.", vi->i_ino);
-	/* Get the mft record of the inode belonging to the child dentry. */
-	mrec = map_mft_record(ni);
-	if (IS_ERR(mrec))
-		return ERR_CAST(mrec);
-	/* Find the first file name attribute in the mft record. */
-	ctx = ntfs_attr_get_search_ctx(ni, mrec);
-	if (unlikely(!ctx)) {
-		unmap_mft_record(ni);
-		return ERR_PTR(-ENOMEM);
-	}
-try_next:
-	err = ntfs_attr_lookup(AT_FILE_NAME, NULL, 0, CASE_SENSITIVE, 0, NULL,
-			0, ctx);
-	if (unlikely(err)) {
-		ntfs_attr_put_search_ctx(ctx);
-		unmap_mft_record(ni);
-		if (err == -ENOENT)
-			ntfs_error(vi->i_sb, "Inode 0x%lx does not have a "
-					"file name attribute.  Run chkdsk.",
-					vi->i_ino);
-		return ERR_PTR(err);
-	}
-	attr = ctx->attr;
-	if (unlikely(attr->non_resident))
-		goto try_next;
-	fn = (FILE_NAME_ATTR *)((u8 *)attr +
-			le16_to_cpu(attr->data.resident.value_offset));
-	if (unlikely((u8 *)fn + le32_to_cpu(attr->data.resident.value_length) >
-			(u8*)attr + le32_to_cpu(attr->length)))
-		goto try_next;
-	/* Get the inode number of the parent directory. */
-	parent_ino = MREF_LE(fn->parent_directory);
-	/* Release the search context and the mft record of the child. */
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-
-	return d_obtain_alias(ntfs_iget(vi->i_sb, parent_ino));
-}
-
-static struct inode *ntfs_nfs_get_inode(struct super_block *sb,
-		u64 ino, u32 generation)
-{
-	struct inode *inode;
-
-	inode = ntfs_iget(sb, ino);
-	if (!IS_ERR(inode)) {
-		if (is_bad_inode(inode) || inode->i_generation != generation) {
-			iput(inode);
-			inode = ERR_PTR(-ESTALE);
-		}
-	}
-
-	return inode;
-}
-
-static struct dentry *ntfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    ntfs_nfs_get_inode);
-}
-
-static struct dentry *ntfs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
-{
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    ntfs_nfs_get_inode);
-}
-
-/*
- * Export operations allowing NFS exporting of mounted NTFS partitions.
- *
- * We use the default ->encode_fh() for now.  Note that they
- * use 32 bits to store the inode number which is an unsigned long so on 64-bit
- * architectures is usually 64 bits so it would all fail horribly on huge
- * volumes.  I guess we need to define our own encode and decode fh functions
- * that store 64-bit inode numbers at some point but for now we will ignore the
- * problem...
- *
- * We also use the default ->get_name() helper (used by ->decode_fh() via
- * fs/exportfs/expfs.c::find_exported_dentry()) as that is completely fs
- * independent.
- *
- * The default ->get_parent() just returns -EACCES so we have to provide our
- * own and the default ->get_dentry() is incompatible with NTFS due to not
- * allowing the inode number 0 which is used in NTFS for the system file $MFT
- * and due to using iget() whereas NTFS needs ntfs_iget().
- */
-const struct export_operations ntfs_export_ops = {
-	.encode_fh	= generic_encode_ino32_fh,
-	.get_parent	= ntfs_get_parent,	/* Find the parent of a given
-						   directory. */
-	.fh_to_dentry	= ntfs_fh_to_dentry,
-	.fh_to_parent	= ntfs_fh_to_parent,
-};
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
deleted file mode 100644
index e81376ea9152..000000000000
--- a/fs/ntfs/ntfs.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * ntfs.h - Defines for NTFS Linux kernel driver.
- *
- * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
- * Copyright (C) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_H
-#define _LINUX_NTFS_H
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/compiler.h>
-#include <linux/fs.h>
-#include <linux/nls.h>
-#include <linux/smp.h>
-#include <linux/pagemap.h>
-
-#include "types.h"
-#include "volume.h"
-#include "layout.h"
-
-typedef enum {
-	NTFS_BLOCK_SIZE		= 512,
-	NTFS_BLOCK_SIZE_BITS	= 9,
-	NTFS_SB_MAGIC		= 0x5346544e,	/* 'NTFS' */
-	NTFS_MAX_NAME_LEN	= 255,
-	NTFS_MAX_ATTR_NAME_LEN	= 255,
-	NTFS_MAX_CLUSTER_SIZE	= 64 * 1024,	/* 64kiB */
-	NTFS_MAX_PAGES_PER_CLUSTER = NTFS_MAX_CLUSTER_SIZE / PAGE_SIZE,
-} NTFS_CONSTANTS;
-
-/* Global variables. */
-
-/* Slab caches (from super.c). */
-extern struct kmem_cache *ntfs_name_cache;
-extern struct kmem_cache *ntfs_inode_cache;
-extern struct kmem_cache *ntfs_big_inode_cache;
-extern struct kmem_cache *ntfs_attr_ctx_cache;
-extern struct kmem_cache *ntfs_index_ctx_cache;
-
-/* The various operations structs defined throughout the driver files. */
-extern const struct address_space_operations ntfs_normal_aops;
-extern const struct address_space_operations ntfs_compressed_aops;
-extern const struct address_space_operations ntfs_mst_aops;
-
-extern const struct  file_operations ntfs_file_ops;
-extern const struct inode_operations ntfs_file_inode_ops;
-
-extern const struct  file_operations ntfs_dir_ops;
-extern const struct inode_operations ntfs_dir_inode_ops;
-
-extern const struct  file_operations ntfs_empty_file_ops;
-extern const struct inode_operations ntfs_empty_inode_ops;
-
-extern const struct export_operations ntfs_export_ops;
-
-/**
- * NTFS_SB - return the ntfs volume given a vfs super block
- * @sb:		VFS super block
- *
- * NTFS_SB() returns the ntfs volume associated with the VFS super block @sb.
- */
-static inline ntfs_volume *NTFS_SB(struct super_block *sb)
-{
-	return sb->s_fs_info;
-}
-
-/* Declarations of functions and global variables. */
-
-/* From fs/ntfs/compress.c */
-extern int ntfs_read_compressed_block(struct page *page);
-extern int allocate_compression_buffers(void);
-extern void free_compression_buffers(void);
-
-/* From fs/ntfs/super.c */
-#define default_upcase_len 0x10000
-extern struct mutex ntfs_lock;
-
-typedef struct {
-	int val;
-	char *str;
-} option_t;
-extern const option_t on_errors_arr[];
-
-/* From fs/ntfs/mst.c */
-extern int post_read_mst_fixup(NTFS_RECORD *b, const u32 size);
-extern int pre_write_mst_fixup(NTFS_RECORD *b, const u32 size);
-extern void post_write_mst_fixup(NTFS_RECORD *b);
-
-/* From fs/ntfs/unistr.c */
-extern bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
-		const ntfschar *s2, size_t s2_len,
-		const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_size);
-extern int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
-		const ntfschar *name2, const u32 name2_len,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n);
-extern int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
-		const ntfschar *upcase, const u32 upcase_size);
-extern void ntfs_upcase_name(ntfschar *name, u32 name_len,
-		const ntfschar *upcase, const u32 upcase_len);
-extern void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
-		FILE_NAME_ATTR *file_name_attr2,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len);
-extern int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
-		const int ins_len, ntfschar **outs);
-extern int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
-		const int ins_len, unsigned char **outs, int outs_len);
-
-/* From fs/ntfs/upcase.c */
-extern ntfschar *generate_default_upcase(void);
-
-static inline int ntfs_ffs(int x)
-{
-	int r = 1;
-
-	if (!x)
-		return 0;
-	if (!(x & 0xffff)) {
-		x >>= 16;
-		r += 16;
-	}
-	if (!(x & 0xff)) {
-		x >>= 8;
-		r += 8;
-	}
-	if (!(x & 0xf)) {
-		x >>= 4;
-		r += 4;
-	}
-	if (!(x & 3)) {
-		x >>= 2;
-		r += 2;
-	}
-	if (!(x & 1)) {
-		x >>= 1;
-		r += 1;
-	}
-	return r;
-}
-
-#endif /* _LINUX_NTFS_H */
diff --git a/fs/ntfs/quota.c b/fs/ntfs/quota.c
deleted file mode 100644
index 9160480222fd..000000000000
--- a/fs/ntfs/quota.c
+++ /dev/null
@@ -1,103 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * quota.c - NTFS kernel quota ($Quota) handling.  Part of the Linux-NTFS
- *	     project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include "index.h"
-#include "quota.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/**
- * ntfs_mark_quotas_out_of_date - mark the quotas out of date on an ntfs volume
- * @vol:	ntfs volume on which to mark the quotas out of date
- *
- * Mark the quotas out of date on the ntfs volume @vol and return 'true' on
- * success and 'false' on error.
- */
-bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol)
-{
-	ntfs_index_context *ictx;
-	QUOTA_CONTROL_ENTRY *qce;
-	const le32 qid = QUOTA_DEFAULTS_ID;
-	int err;
-
-	ntfs_debug("Entering.");
-	if (NVolQuotaOutOfDate(vol))
-		goto done;
-	if (!vol->quota_ino || !vol->quota_q_ino) {
-		ntfs_error(vol->sb, "Quota inodes are not open.");
-		return false;
-	}
-	inode_lock(vol->quota_q_ino);
-	ictx = ntfs_index_ctx_get(NTFS_I(vol->quota_q_ino));
-	if (!ictx) {
-		ntfs_error(vol->sb, "Failed to get index context.");
-		goto err_out;
-	}
-	err = ntfs_index_lookup(&qid, sizeof(qid), ictx);
-	if (err) {
-		if (err == -ENOENT)
-			ntfs_error(vol->sb, "Quota defaults entry is not "
-					"present.");
-		else
-			ntfs_error(vol->sb, "Lookup of quota defaults entry "
-					"failed.");
-		goto err_out;
-	}
-	if (ictx->data_len < offsetof(QUOTA_CONTROL_ENTRY, sid)) {
-		ntfs_error(vol->sb, "Quota defaults entry size is invalid.  "
-				"Run chkdsk.");
-		goto err_out;
-	}
-	qce = (QUOTA_CONTROL_ENTRY*)ictx->data;
-	if (le32_to_cpu(qce->version) != QUOTA_VERSION) {
-		ntfs_error(vol->sb, "Quota defaults entry version 0x%x is not "
-				"supported.", le32_to_cpu(qce->version));
-		goto err_out;
-	}
-	ntfs_debug("Quota defaults flags = 0x%x.", le32_to_cpu(qce->flags));
-	/* If quotas are already marked out of date, no need to do anything. */
-	if (qce->flags & QUOTA_FLAG_OUT_OF_DATE)
-		goto set_done;
-	/*
-	 * If quota tracking is neither requested, nor enabled and there are no
-	 * pending deletes, no need to mark the quotas out of date.
-	 */
-	if (!(qce->flags & (QUOTA_FLAG_TRACKING_ENABLED |
-			QUOTA_FLAG_TRACKING_REQUESTED |
-			QUOTA_FLAG_PENDING_DELETES)))
-		goto set_done;
-	/*
-	 * Set the QUOTA_FLAG_OUT_OF_DATE bit thus marking quotas out of date.
-	 * This is verified on WinXP to be sufficient to cause windows to
-	 * rescan the volume on boot and update all quota entries.
-	 */
-	qce->flags |= QUOTA_FLAG_OUT_OF_DATE;
-	/* Ensure the modified flags are written to disk. */
-	ntfs_index_entry_flush_dcache_page(ictx);
-	ntfs_index_entry_mark_dirty(ictx);
-set_done:
-	ntfs_index_ctx_put(ictx);
-	inode_unlock(vol->quota_q_ino);
-	/*
-	 * We set the flag so we do not try to mark the quotas out of date
-	 * again on remount.
-	 */
-	NVolSetQuotaOutOfDate(vol);
-done:
-	ntfs_debug("Done.");
-	return true;
-err_out:
-	if (ictx)
-		ntfs_index_ctx_put(ictx);
-	inode_unlock(vol->quota_q_ino);
-	return false;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/quota.h b/fs/ntfs/quota.h
deleted file mode 100644
index fe3132a3d6d2..000000000000
--- a/fs/ntfs/quota.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * quota.h - Defines for NTFS kernel quota ($Quota) handling.  Part of the
- *	     Linux-NTFS project.
- *
- * Copyright (c) 2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_QUOTA_H
-#define _LINUX_NTFS_QUOTA_H
-
-#ifdef NTFS_RW
-
-#include "types.h"
-#include "volume.h"
-
-extern bool ntfs_mark_quotas_out_of_date(ntfs_volume *vol);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_QUOTA_H */
diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c
deleted file mode 100644
index 0d448e9881f7..000000000000
--- a/fs/ntfs/runlist.c
+++ /dev/null
@@ -1,1893 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * runlist.c - NTFS runlist handling code.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2007 Anton Altaparmakov
- * Copyright (c) 2002-2005 Richard Russon
- */
-
-#include "debug.h"
-#include "dir.h"
-#include "endian.h"
-#include "malloc.h"
-#include "ntfs.h"
-
-/**
- * ntfs_rl_mm - runlist memmove
- *
- * It is up to the caller to serialize access to the runlist @base.
- */
-static inline void ntfs_rl_mm(runlist_element *base, int dst, int src,
-		int size)
-{
-	if (likely((dst != src) && (size > 0)))
-		memmove(base + dst, base + src, size * sizeof(*base));
-}
-
-/**
- * ntfs_rl_mc - runlist memory copy
- *
- * It is up to the caller to serialize access to the runlists @dstbase and
- * @srcbase.
- */
-static inline void ntfs_rl_mc(runlist_element *dstbase, int dst,
-		runlist_element *srcbase, int src, int size)
-{
-	if (likely(size > 0))
-		memcpy(dstbase + dst, srcbase + src, size * sizeof(*dstbase));
-}
-
-/**
- * ntfs_rl_realloc - Reallocate memory for runlists
- * @rl:		original runlist
- * @old_size:	number of runlist elements in the original runlist @rl
- * @new_size:	number of runlist elements we need space for
- *
- * As the runlists grow, more memory will be required.  To prevent the
- * kernel having to allocate and reallocate large numbers of small bits of
- * memory, this function returns an entire page of memory.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * N.B.  If the new allocation doesn't require a different number of pages in
- *       memory, the function will return the original pointer.
- *
- * On success, return a pointer to the newly allocated, or recycled, memory.
- * On error, return -errno. The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_realloc(runlist_element *rl,
-		int old_size, int new_size)
-{
-	runlist_element *new_rl;
-
-	old_size = PAGE_ALIGN(old_size * sizeof(*rl));
-	new_size = PAGE_ALIGN(new_size * sizeof(*rl));
-	if (old_size == new_size)
-		return rl;
-
-	new_rl = ntfs_malloc_nofs(new_size);
-	if (unlikely(!new_rl))
-		return ERR_PTR(-ENOMEM);
-
-	if (likely(rl != NULL)) {
-		if (unlikely(old_size > new_size))
-			old_size = new_size;
-		memcpy(new_rl, rl, old_size);
-		ntfs_free(rl);
-	}
-	return new_rl;
-}
-
-/**
- * ntfs_rl_realloc_nofail - Reallocate memory for runlists
- * @rl:		original runlist
- * @old_size:	number of runlist elements in the original runlist @rl
- * @new_size:	number of runlist elements we need space for
- *
- * As the runlists grow, more memory will be required.  To prevent the
- * kernel having to allocate and reallocate large numbers of small bits of
- * memory, this function returns an entire page of memory.
- *
- * This function guarantees that the allocation will succeed.  It will sleep
- * for as long as it takes to complete the allocation.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * N.B.  If the new allocation doesn't require a different number of pages in
- *       memory, the function will return the original pointer.
- *
- * On success, return a pointer to the newly allocated, or recycled, memory.
- * On error, return -errno. The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_realloc_nofail(runlist_element *rl,
-		int old_size, int new_size)
-{
-	runlist_element *new_rl;
-
-	old_size = PAGE_ALIGN(old_size * sizeof(*rl));
-	new_size = PAGE_ALIGN(new_size * sizeof(*rl));
-	if (old_size == new_size)
-		return rl;
-
-	new_rl = ntfs_malloc_nofs_nofail(new_size);
-	BUG_ON(!new_rl);
-
-	if (likely(rl != NULL)) {
-		if (unlikely(old_size > new_size))
-			old_size = new_size;
-		memcpy(new_rl, rl, old_size);
-		ntfs_free(rl);
-	}
-	return new_rl;
-}
-
-/**
- * ntfs_are_rl_mergeable - test if two runlists can be joined together
- * @dst:	original runlist
- * @src:	new runlist to test for mergeability with @dst
- *
- * Test if two runlists can be joined together. For this, their VCNs and LCNs
- * must be adjacent.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * Return: true   Success, the runlists can be merged.
- *	   false  Failure, the runlists cannot be merged.
- */
-static inline bool ntfs_are_rl_mergeable(runlist_element *dst,
-		runlist_element *src)
-{
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* We can merge unmapped regions even if they are misaligned. */
-	if ((dst->lcn == LCN_RL_NOT_MAPPED) && (src->lcn == LCN_RL_NOT_MAPPED))
-		return true;
-	/* If the runs are misaligned, we cannot merge them. */
-	if ((dst->vcn + dst->length) != src->vcn)
-		return false;
-	/* If both runs are non-sparse and contiguous, we can merge them. */
-	if ((dst->lcn >= 0) && (src->lcn >= 0) &&
-			((dst->lcn + dst->length) == src->lcn))
-		return true;
-	/* If we are merging two holes, we can merge them. */
-	if ((dst->lcn == LCN_HOLE) && (src->lcn == LCN_HOLE))
-		return true;
-	/* Cannot merge. */
-	return false;
-}
-
-/**
- * __ntfs_rl_merge - merge two runlists without testing if they can be merged
- * @dst:	original, destination runlist
- * @src:	new runlist to merge with @dst
- *
- * Merge the two runlists, writing into the destination runlist @dst. The
- * caller must make sure the runlists can be merged or this will corrupt the
- * destination runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- */
-static inline void __ntfs_rl_merge(runlist_element *dst, runlist_element *src)
-{
-	dst->length += src->length;
-}
-
-/**
- * ntfs_rl_append - append a runlist after a given element
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	runlist to be inserted into @dst
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	append the new runlist @src after this element in @dst
- *
- * Append the runlist @src after element @loc in @dst.  Merge the right end of
- * the new runlist, if necessary. Adjust the size of the hole before the
- * appended runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_append(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	bool right = false;	/* Right end of @src needs merging. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* First, check if the right hand end needs merging. */
-	if ((loc + 1) < dsize)
-		right = ntfs_are_rl_mergeable(src + ssize - 1, dst + loc + 1);
-
-	/* Space required: @dst size + @src size, less one if we merged. */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize - right);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* First, merge the right hand end, if necessary. */
-	if (right)
-		__ntfs_rl_merge(src + ssize - 1, dst + loc + 1);
-
-	/* First run after the @src runs that have been inserted. */
-	marker = loc + ssize + 1;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, loc + 1 + right, dsize - (loc + 1 + right));
-	ntfs_rl_mc(dst, loc + 1, src, 0, ssize);
-
-	/* Adjust the size of the preceding hole. */
-	dst[loc].length = dst[loc + 1].vcn - dst[loc].vcn;
-
-	/* We may have changed the length of the file, so fix the end marker */
-	if (dst[marker].lcn == LCN_ENOENT)
-		dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-
-	return dst;
-}
-
-/**
- * ntfs_rl_insert - insert a runlist into another
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	insert the new runlist @src before this element in @dst
- *
- * Insert the runlist @src before element @loc in the runlist @dst. Merge the
- * left end of the new runlist, if necessary. Adjust the size of the hole
- * after the inserted runlist.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_insert(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	bool left = false;	/* Left end of @src needs merging. */
-	bool disc = false;	/* Discontinuity between @dst and @src. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/*
-	 * disc => Discontinuity between the end of @dst and the start of @src.
-	 *	   This means we might need to insert a "not mapped" run.
-	 */
-	if (loc == 0)
-		disc = (src[0].vcn > 0);
-	else {
-		s64 merged_length;
-
-		left = ntfs_are_rl_mergeable(dst + loc - 1, src);
-
-		merged_length = dst[loc - 1].length;
-		if (left)
-			merged_length += src->length;
-
-		disc = (src[0].vcn > dst[loc - 1].vcn + merged_length);
-	}
-	/*
-	 * Space required: @dst size + @src size, less one if we merged, plus
-	 * one if there was a discontinuity.
-	 */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize - left + disc);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlist.
-	 */
-	if (left)
-		__ntfs_rl_merge(dst + loc - 1, src);
-	/*
-	 * First run after the @src runs that have been inserted.
-	 * Nominally,  @marker equals @loc + @ssize, i.e. location + number of
-	 * runs in @src.  However, if @left, then the first run in @src has
-	 * been merged with one in @dst.  And if @disc, then @dst and @src do
-	 * not meet and we need an extra run to fill the gap.
-	 */
-	marker = loc + ssize - left + disc;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, loc, dsize - loc);
-	ntfs_rl_mc(dst, loc + disc, src, left, ssize - left);
-
-	/* Adjust the VCN of the first run after the insertion... */
-	dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-	/* ... and the length. */
-	if (dst[marker].lcn == LCN_HOLE || dst[marker].lcn == LCN_RL_NOT_MAPPED)
-		dst[marker].length = dst[marker + 1].vcn - dst[marker].vcn;
-
-	/* Writing beyond the end of the file and there is a discontinuity. */
-	if (disc) {
-		if (loc > 0) {
-			dst[loc].vcn = dst[loc - 1].vcn + dst[loc - 1].length;
-			dst[loc].length = dst[loc + 1].vcn - dst[loc].vcn;
-		} else {
-			dst[loc].vcn = 0;
-			dst[loc].length = dst[loc + 1].vcn;
-		}
-		dst[loc].lcn = LCN_RL_NOT_MAPPED;
-	}
-	return dst;
-}
-
-/**
- * ntfs_rl_replace - overwrite a runlist element with another runlist
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	index in runlist @dst to overwrite with @src
- *
- * Replace the runlist element @dst at @loc with @src. Merge the left and
- * right ends of the inserted runlist, if necessary.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_replace(runlist_element *dst,
-		int dsize, runlist_element *src, int ssize, int loc)
-{
-	signed delta;
-	bool left = false;	/* Left end of @src needs merging. */
-	bool right = false;	/* Right end of @src needs merging. */
-	int tail;		/* Start of tail of @dst. */
-	int marker;		/* End of the inserted runs. */
-
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* First, see if the left and right ends need merging. */
-	if ((loc + 1) < dsize)
-		right = ntfs_are_rl_mergeable(src + ssize - 1, dst + loc + 1);
-	if (loc > 0)
-		left = ntfs_are_rl_mergeable(dst + loc - 1, src);
-	/*
-	 * Allocate some space.  We will need less if the left, right, or both
-	 * ends get merged.  The -1 accounts for the run being replaced.
-	 */
-	delta = ssize - 1 - left - right;
-	if (delta > 0) {
-		dst = ntfs_rl_realloc(dst, dsize, dsize + delta);
-		if (IS_ERR(dst))
-			return dst;
-	}
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* First, merge the left and right ends, if necessary. */
-	if (right)
-		__ntfs_rl_merge(src + ssize - 1, dst + loc + 1);
-	if (left)
-		__ntfs_rl_merge(dst + loc - 1, src);
-	/*
-	 * Offset of the tail of @dst.  This needs to be moved out of the way
-	 * to make space for the runs to be copied from @src, i.e. the first
-	 * run of the tail of @dst.
-	 * Nominally, @tail equals @loc + 1, i.e. location, skipping the
-	 * replaced run.  However, if @right, then one of @dst's runs is
-	 * already merged into @src.
-	 */
-	tail = loc + right + 1;
-	/*
-	 * First run after the @src runs that have been inserted, i.e. where
-	 * the tail of @dst needs to be moved to.
-	 * Nominally, @marker equals @loc + @ssize, i.e. location + number of
-	 * runs in @src.  However, if @left, then the first run in @src has
-	 * been merged with one in @dst.
-	 */
-	marker = loc + ssize - left;
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, marker, tail, dsize - tail);
-	ntfs_rl_mc(dst, loc, src, left, ssize - left);
-
-	/* We may have changed the length of the file, so fix the end marker. */
-	if (dsize - tail > 0 && dst[marker].lcn == LCN_ENOENT)
-		dst[marker].vcn = dst[marker - 1].vcn + dst[marker - 1].length;
-	return dst;
-}
-
-/**
- * ntfs_rl_split - insert a runlist into the centre of a hole
- * @dst:	original runlist to be worked on
- * @dsize:	number of elements in @dst (including end marker)
- * @src:	new runlist to be inserted
- * @ssize:	number of elements in @src (excluding end marker)
- * @loc:	index in runlist @dst at which to split and insert @src
- *
- * Split the runlist @dst at @loc into two and insert @new in between the two
- * fragments. No merging of runlists is necessary. Adjust the size of the
- * holes either side.
- *
- * It is up to the caller to serialize access to the runlists @dst and @src.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @dst and @src are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- */
-static inline runlist_element *ntfs_rl_split(runlist_element *dst, int dsize,
-		runlist_element *src, int ssize, int loc)
-{
-	BUG_ON(!dst);
-	BUG_ON(!src);
-
-	/* Space required: @dst size + @src size + one new hole. */
-	dst = ntfs_rl_realloc(dst, dsize, dsize + ssize + 1);
-	if (IS_ERR(dst))
-		return dst;
-	/*
-	 * We are guaranteed to succeed from here so can start modifying the
-	 * original runlists.
-	 */
-
-	/* Move the tail of @dst out of the way, then copy in @src. */
-	ntfs_rl_mm(dst, loc + 1 + ssize, loc, dsize - loc);
-	ntfs_rl_mc(dst, loc + 1, src, 0, ssize);
-
-	/* Adjust the size of the holes either size of @src. */
-	dst[loc].length		= dst[loc+1].vcn       - dst[loc].vcn;
-	dst[loc+ssize+1].vcn    = dst[loc+ssize].vcn   + dst[loc+ssize].length;
-	dst[loc+ssize+1].length = dst[loc+ssize+2].vcn - dst[loc+ssize+1].vcn;
-
-	return dst;
-}
-
-/**
- * ntfs_runlists_merge - merge two runlists into one
- * @drl:	original runlist to be worked on
- * @srl:	new runlist to be merged into @drl
- *
- * First we sanity check the two runlists @srl and @drl to make sure that they
- * are sensible and can be merged. The runlist @srl must be either after the
- * runlist @drl or completely within a hole (or unmapped region) in @drl.
- *
- * It is up to the caller to serialize access to the runlists @drl and @srl.
- *
- * Merging of runlists is necessary in two cases:
- *   1. When attribute lists are used and a further extent is being mapped.
- *   2. When new clusters are allocated to fill a hole or extend a file.
- *
- * There are four possible ways @srl can be merged. It can:
- *	- be inserted at the beginning of a hole,
- *	- split the hole in two and be inserted between the two fragments,
- *	- be appended at the end of a hole, or it can
- *	- replace the whole hole.
- * It can also be appended to the end of the runlist, which is just a variant
- * of the insert case.
- *
- * On success, return a pointer to the new, combined, runlist. Note, both
- * runlists @drl and @srl are deallocated before returning so you cannot use
- * the pointers for anything any more. (Strictly speaking the returned runlist
- * may be the same as @dst but this is irrelevant.)
- *
- * On error, return -errno. Both runlists are left unmodified. The following
- * error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EINVAL	- Invalid parameters were passed in.
- *	-ERANGE	- The runlists overlap and cannot be merged.
- */
-runlist_element *ntfs_runlists_merge(runlist_element *drl,
-		runlist_element *srl)
-{
-	int di, si;		/* Current index into @[ds]rl. */
-	int sstart;		/* First index with lcn > LCN_RL_NOT_MAPPED. */
-	int dins;		/* Index into @drl at which to insert @srl. */
-	int dend, send;		/* Last index into @[ds]rl. */
-	int dfinal, sfinal;	/* The last index into @[ds]rl with
-				   lcn >= LCN_HOLE. */
-	int marker = 0;
-	VCN marker_vcn = 0;
-
-#ifdef DEBUG
-	ntfs_debug("dst:");
-	ntfs_debug_dump_runlist(drl);
-	ntfs_debug("src:");
-	ntfs_debug_dump_runlist(srl);
-#endif
-
-	/* Check for silly calling... */
-	if (unlikely(!srl))
-		return drl;
-	if (IS_ERR(srl) || IS_ERR(drl))
-		return ERR_PTR(-EINVAL);
-
-	/* Check for the case where the first mapping is being done now. */
-	if (unlikely(!drl)) {
-		drl = srl;
-		/* Complete the source runlist if necessary. */
-		if (unlikely(drl[0].vcn)) {
-			/* Scan to the end of the source runlist. */
-			for (dend = 0; likely(drl[dend].length); dend++)
-				;
-			dend++;
-			drl = ntfs_rl_realloc(drl, dend, dend + 1);
-			if (IS_ERR(drl))
-				return drl;
-			/* Insert start element at the front of the runlist. */
-			ntfs_rl_mm(drl, 1, 0, dend);
-			drl[0].vcn = 0;
-			drl[0].lcn = LCN_RL_NOT_MAPPED;
-			drl[0].length = drl[1].vcn;
-		}
-		goto finished;
-	}
-
-	si = di = 0;
-
-	/* Skip any unmapped start element(s) in the source runlist. */
-	while (srl[si].length && srl[si].lcn < LCN_HOLE)
-		si++;
-
-	/* Can't have an entirely unmapped source runlist. */
-	BUG_ON(!srl[si].length);
-
-	/* Record the starting points. */
-	sstart = si;
-
-	/*
-	 * Skip forward in @drl until we reach the position where @srl needs to
-	 * be inserted. If we reach the end of @drl, @srl just needs to be
-	 * appended to @drl.
-	 */
-	for (; drl[di].length; di++) {
-		if (drl[di].vcn + drl[di].length > srl[sstart].vcn)
-			break;
-	}
-	dins = di;
-
-	/* Sanity check for illegal overlaps. */
-	if ((drl[di].vcn == srl[si].vcn) && (drl[di].lcn >= 0) &&
-			(srl[si].lcn >= 0)) {
-		ntfs_error(NULL, "Run lists overlap. Cannot merge!");
-		return ERR_PTR(-ERANGE);
-	}
-
-	/* Scan to the end of both runlists in order to know their sizes. */
-	for (send = si; srl[send].length; send++)
-		;
-	for (dend = di; drl[dend].length; dend++)
-		;
-
-	if (srl[send].lcn == LCN_ENOENT)
-		marker_vcn = srl[marker = send].vcn;
-
-	/* Scan to the last element with lcn >= LCN_HOLE. */
-	for (sfinal = send; sfinal >= 0 && srl[sfinal].lcn < LCN_HOLE; sfinal--)
-		;
-	for (dfinal = dend; dfinal >= 0 && drl[dfinal].lcn < LCN_HOLE; dfinal--)
-		;
-
-	{
-	bool start;
-	bool finish;
-	int ds = dend + 1;		/* Number of elements in drl & srl */
-	int ss = sfinal - sstart + 1;
-
-	start  = ((drl[dins].lcn <  LCN_RL_NOT_MAPPED) ||    /* End of file   */
-		  (drl[dins].vcn == srl[sstart].vcn));	     /* Start of hole */
-	finish = ((drl[dins].lcn >= LCN_RL_NOT_MAPPED) &&    /* End of file   */
-		 ((drl[dins].vcn + drl[dins].length) <=      /* End of hole   */
-		  (srl[send - 1].vcn + srl[send - 1].length)));
-
-	/* Or we will lose an end marker. */
-	if (finish && !drl[dins].length)
-		ss++;
-	if (marker && (drl[dins].vcn + drl[dins].length > srl[send - 1].vcn))
-		finish = false;
-#if 0
-	ntfs_debug("dfinal = %i, dend = %i", dfinal, dend);
-	ntfs_debug("sstart = %i, sfinal = %i, send = %i", sstart, sfinal, send);
-	ntfs_debug("start = %i, finish = %i", start, finish);
-	ntfs_debug("ds = %i, ss = %i, dins = %i", ds, ss, dins);
-#endif
-	if (start) {
-		if (finish)
-			drl = ntfs_rl_replace(drl, ds, srl + sstart, ss, dins);
-		else
-			drl = ntfs_rl_insert(drl, ds, srl + sstart, ss, dins);
-	} else {
-		if (finish)
-			drl = ntfs_rl_append(drl, ds, srl + sstart, ss, dins);
-		else
-			drl = ntfs_rl_split(drl, ds, srl + sstart, ss, dins);
-	}
-	if (IS_ERR(drl)) {
-		ntfs_error(NULL, "Merge failed.");
-		return drl;
-	}
-	ntfs_free(srl);
-	if (marker) {
-		ntfs_debug("Triggering marker code.");
-		for (ds = dend; drl[ds].length; ds++)
-			;
-		/* We only need to care if @srl ended after @drl. */
-		if (drl[ds].vcn <= marker_vcn) {
-			int slots = 0;
-
-			if (drl[ds].vcn == marker_vcn) {
-				ntfs_debug("Old marker = 0x%llx, replacing "
-						"with LCN_ENOENT.",
-						(unsigned long long)
-						drl[ds].lcn);
-				drl[ds].lcn = LCN_ENOENT;
-				goto finished;
-			}
-			/*
-			 * We need to create an unmapped runlist element in
-			 * @drl or extend an existing one before adding the
-			 * ENOENT terminator.
-			 */
-			if (drl[ds].lcn == LCN_ENOENT) {
-				ds--;
-				slots = 1;
-			}
-			if (drl[ds].lcn != LCN_RL_NOT_MAPPED) {
-				/* Add an unmapped runlist element. */
-				if (!slots) {
-					drl = ntfs_rl_realloc_nofail(drl, ds,
-							ds + 2);
-					slots = 2;
-				}
-				ds++;
-				/* Need to set vcn if it isn't set already. */
-				if (slots != 1)
-					drl[ds].vcn = drl[ds - 1].vcn +
-							drl[ds - 1].length;
-				drl[ds].lcn = LCN_RL_NOT_MAPPED;
-				/* We now used up a slot. */
-				slots--;
-			}
-			drl[ds].length = marker_vcn - drl[ds].vcn;
-			/* Finally add the ENOENT terminator. */
-			ds++;
-			if (!slots)
-				drl = ntfs_rl_realloc_nofail(drl, ds, ds + 1);
-			drl[ds].vcn = marker_vcn;
-			drl[ds].lcn = LCN_ENOENT;
-			drl[ds].length = (s64)0;
-		}
-	}
-	}
-
-finished:
-	/* The merge was completed successfully. */
-	ntfs_debug("Merged runlist:");
-	ntfs_debug_dump_runlist(drl);
-	return drl;
-}
-
-/**
- * ntfs_mapping_pairs_decompress - convert mapping pairs array to runlist
- * @vol:	ntfs volume on which the attribute resides
- * @attr:	attribute record whose mapping pairs array to decompress
- * @old_rl:	optional runlist in which to insert @attr's runlist
- *
- * It is up to the caller to serialize access to the runlist @old_rl.
- *
- * Decompress the attribute @attr's mapping pairs array into a runlist. On
- * success, return the decompressed runlist.
- *
- * If @old_rl is not NULL, decompressed runlist is inserted into the
- * appropriate place in @old_rl and the resultant, combined runlist is
- * returned. The original @old_rl is deallocated.
- *
- * On error, return -errno. @old_rl is left unmodified in that case.
- *
- * The following error codes are defined:
- *	-ENOMEM	- Not enough memory to allocate runlist array.
- *	-EIO	- Corrupt runlist.
- *	-EINVAL	- Invalid parameters were passed in.
- *	-ERANGE	- The two runlists overlap.
- *
- * FIXME: For now we take the conceptionally simplest approach of creating the
- * new runlist disregarding the already existing one and then splicing the
- * two into one, if that is possible (we check for overlap and discard the new
- * runlist if overlap present before returning ERR_PTR(-ERANGE)).
- */
-runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
-		const ATTR_RECORD *attr, runlist_element *old_rl)
-{
-	VCN vcn;		/* Current vcn. */
-	LCN lcn;		/* Current lcn. */
-	s64 deltaxcn;		/* Change in [vl]cn. */
-	runlist_element *rl;	/* The output runlist. */
-	u8 *buf;		/* Current position in mapping pairs array. */
-	u8 *attr_end;		/* End of attribute. */
-	int rlsize;		/* Size of runlist buffer. */
-	u16 rlpos;		/* Current runlist position in units of
-				   runlist_elements. */
-	u8 b;			/* Current byte offset in buf. */
-
-#ifdef DEBUG
-	/* Make sure attr exists and is non-resident. */
-	if (!attr || !attr->non_resident || sle64_to_cpu(
-			attr->data.non_resident.lowest_vcn) < (VCN)0) {
-		ntfs_error(vol->sb, "Invalid arguments.");
-		return ERR_PTR(-EINVAL);
-	}
-#endif
-	/* Start at vcn = lowest_vcn and lcn 0. */
-	vcn = sle64_to_cpu(attr->data.non_resident.lowest_vcn);
-	lcn = 0;
-	/* Get start of the mapping pairs array. */
-	buf = (u8*)attr + le16_to_cpu(
-			attr->data.non_resident.mapping_pairs_offset);
-	attr_end = (u8*)attr + le32_to_cpu(attr->length);
-	if (unlikely(buf < (u8*)attr || buf > attr_end)) {
-		ntfs_error(vol->sb, "Corrupt attribute.");
-		return ERR_PTR(-EIO);
-	}
-	/* If the mapping pairs array is valid but empty, nothing to do. */
-	if (!vcn && !*buf)
-		return old_rl;
-	/* Current position in runlist array. */
-	rlpos = 0;
-	/* Allocate first page and set current runlist size to one page. */
-	rl = ntfs_malloc_nofs(rlsize = PAGE_SIZE);
-	if (unlikely(!rl))
-		return ERR_PTR(-ENOMEM);
-	/* Insert unmapped starting element if necessary. */
-	if (vcn) {
-		rl->vcn = 0;
-		rl->lcn = LCN_RL_NOT_MAPPED;
-		rl->length = vcn;
-		rlpos++;
-	}
-	while (buf < attr_end && *buf) {
-		/*
-		 * Allocate more memory if needed, including space for the
-		 * not-mapped and terminator elements. ntfs_malloc_nofs()
-		 * operates on whole pages only.
-		 */
-		if (((rlpos + 3) * sizeof(*old_rl)) > rlsize) {
-			runlist_element *rl2;
-
-			rl2 = ntfs_malloc_nofs(rlsize + (int)PAGE_SIZE);
-			if (unlikely(!rl2)) {
-				ntfs_free(rl);
-				return ERR_PTR(-ENOMEM);
-			}
-			memcpy(rl2, rl, rlsize);
-			ntfs_free(rl);
-			rl = rl2;
-			rlsize += PAGE_SIZE;
-		}
-		/* Enter the current vcn into the current runlist element. */
-		rl[rlpos].vcn = vcn;
-		/*
-		 * Get the change in vcn, i.e. the run length in clusters.
-		 * Doing it this way ensures that we signextend negative values.
-		 * A negative run length doesn't make any sense, but hey, I
-		 * didn't make up the NTFS specs and Windows NT4 treats the run
-		 * length as a signed value so that's how it is...
-		 */
-		b = *buf & 0xf;
-		if (b) {
-			if (unlikely(buf + b > attr_end))
-				goto io_error;
-			for (deltaxcn = (s8)buf[b--]; b; b--)
-				deltaxcn = (deltaxcn << 8) + buf[b];
-		} else { /* The length entry is compulsory. */
-			ntfs_error(vol->sb, "Missing length entry in mapping "
-					"pairs array.");
-			deltaxcn = (s64)-1;
-		}
-		/*
-		 * Assume a negative length to indicate data corruption and
-		 * hence clean-up and return NULL.
-		 */
-		if (unlikely(deltaxcn < 0)) {
-			ntfs_error(vol->sb, "Invalid length in mapping pairs "
-					"array.");
-			goto err_out;
-		}
-		/*
-		 * Enter the current run length into the current runlist
-		 * element.
-		 */
-		rl[rlpos].length = deltaxcn;
-		/* Increment the current vcn by the current run length. */
-		vcn += deltaxcn;
-		/*
-		 * There might be no lcn change at all, as is the case for
-		 * sparse clusters on NTFS 3.0+, in which case we set the lcn
-		 * to LCN_HOLE.
-		 */
-		if (!(*buf & 0xf0))
-			rl[rlpos].lcn = LCN_HOLE;
-		else {
-			/* Get the lcn change which really can be negative. */
-			u8 b2 = *buf & 0xf;
-			b = b2 + ((*buf >> 4) & 0xf);
-			if (buf + b > attr_end)
-				goto io_error;
-			for (deltaxcn = (s8)buf[b--]; b > b2; b--)
-				deltaxcn = (deltaxcn << 8) + buf[b];
-			/* Change the current lcn to its new value. */
-			lcn += deltaxcn;
-#ifdef DEBUG
-			/*
-			 * On NTFS 1.2-, apparently can have lcn == -1 to
-			 * indicate a hole. But we haven't verified ourselves
-			 * whether it is really the lcn or the deltaxcn that is
-			 * -1. So if either is found give us a message so we
-			 * can investigate it further!
-			 */
-			if (vol->major_ver < 3) {
-				if (unlikely(deltaxcn == (LCN)-1))
-					ntfs_error(vol->sb, "lcn delta == -1");
-				if (unlikely(lcn == (LCN)-1))
-					ntfs_error(vol->sb, "lcn == -1");
-			}
-#endif
-			/* Check lcn is not below -1. */
-			if (unlikely(lcn < (LCN)-1)) {
-				ntfs_error(vol->sb, "Invalid LCN < -1 in "
-						"mapping pairs array.");
-				goto err_out;
-			}
-			/* Enter the current lcn into the runlist element. */
-			rl[rlpos].lcn = lcn;
-		}
-		/* Get to the next runlist element. */
-		rlpos++;
-		/* Increment the buffer position to the next mapping pair. */
-		buf += (*buf & 0xf) + ((*buf >> 4) & 0xf) + 1;
-	}
-	if (unlikely(buf >= attr_end))
-		goto io_error;
-	/*
-	 * If there is a highest_vcn specified, it must be equal to the final
-	 * vcn in the runlist - 1, or something has gone badly wrong.
-	 */
-	deltaxcn = sle64_to_cpu(attr->data.non_resident.highest_vcn);
-	if (unlikely(deltaxcn && vcn - 1 != deltaxcn)) {
-mpa_err:
-		ntfs_error(vol->sb, "Corrupt mapping pairs array in "
-				"non-resident attribute.");
-		goto err_out;
-	}
-	/* Setup not mapped runlist element if this is the base extent. */
-	if (!attr->data.non_resident.lowest_vcn) {
-		VCN max_cluster;
-
-		max_cluster = ((sle64_to_cpu(
-				attr->data.non_resident.allocated_size) +
-				vol->cluster_size - 1) >>
-				vol->cluster_size_bits) - 1;
-		/*
-		 * A highest_vcn of zero means this is a single extent
-		 * attribute so simply terminate the runlist with LCN_ENOENT).
-		 */
-		if (deltaxcn) {
-			/*
-			 * If there is a difference between the highest_vcn and
-			 * the highest cluster, the runlist is either corrupt
-			 * or, more likely, there are more extents following
-			 * this one.
-			 */
-			if (deltaxcn < max_cluster) {
-				ntfs_debug("More extents to follow; deltaxcn "
-						"= 0x%llx, max_cluster = "
-						"0x%llx",
-						(unsigned long long)deltaxcn,
-						(unsigned long long)
-						max_cluster);
-				rl[rlpos].vcn = vcn;
-				vcn += rl[rlpos].length = max_cluster -
-						deltaxcn;
-				rl[rlpos].lcn = LCN_RL_NOT_MAPPED;
-				rlpos++;
-			} else if (unlikely(deltaxcn > max_cluster)) {
-				ntfs_error(vol->sb, "Corrupt attribute.  "
-						"deltaxcn = 0x%llx, "
-						"max_cluster = 0x%llx",
-						(unsigned long long)deltaxcn,
-						(unsigned long long)
-						max_cluster);
-				goto mpa_err;
-			}
-		}
-		rl[rlpos].lcn = LCN_ENOENT;
-	} else /* Not the base extent. There may be more extents to follow. */
-		rl[rlpos].lcn = LCN_RL_NOT_MAPPED;
-
-	/* Setup terminating runlist element. */
-	rl[rlpos].vcn = vcn;
-	rl[rlpos].length = (s64)0;
-	/* If no existing runlist was specified, we are done. */
-	if (!old_rl) {
-		ntfs_debug("Mapping pairs array successfully decompressed:");
-		ntfs_debug_dump_runlist(rl);
-		return rl;
-	}
-	/* Now combine the new and old runlists checking for overlaps. */
-	old_rl = ntfs_runlists_merge(old_rl, rl);
-	if (!IS_ERR(old_rl))
-		return old_rl;
-	ntfs_free(rl);
-	ntfs_error(vol->sb, "Failed to merge runlists.");
-	return old_rl;
-io_error:
-	ntfs_error(vol->sb, "Corrupt attribute.");
-err_out:
-	ntfs_free(rl);
-	return ERR_PTR(-EIO);
-}
-
-/**
- * ntfs_rl_vcn_to_lcn - convert a vcn into a lcn given a runlist
- * @rl:		runlist to use for conversion
- * @vcn:	vcn to convert
- *
- * Convert the virtual cluster number @vcn of an attribute into a logical
- * cluster number (lcn) of a device using the runlist @rl to map vcns to their
- * corresponding lcns.
- *
- * It is up to the caller to serialize access to the runlist @rl.
- *
- * Since lcns must be >= 0, we use negative return codes with special meaning:
- *
- * Return code		Meaning / Description
- * ==================================================
- *  LCN_HOLE		Hole / not allocated on disk.
- *  LCN_RL_NOT_MAPPED	This is part of the runlist which has not been
- *			inserted into the runlist yet.
- *  LCN_ENOENT		There is no such vcn in the attribute.
- *
- * Locking: - The caller must have locked the runlist (for reading or writing).
- *	    - This function does not touch the lock, nor does it modify the
- *	      runlist.
- */
-LCN ntfs_rl_vcn_to_lcn(const runlist_element *rl, const VCN vcn)
-{
-	int i;
-
-	BUG_ON(vcn < 0);
-	/*
-	 * If rl is NULL, assume that we have found an unmapped runlist. The
-	 * caller can then attempt to map it and fail appropriately if
-	 * necessary.
-	 */
-	if (unlikely(!rl))
-		return LCN_RL_NOT_MAPPED;
-
-	/* Catch out of lower bounds vcn. */
-	if (unlikely(vcn < rl[0].vcn))
-		return LCN_ENOENT;
-
-	for (i = 0; likely(rl[i].length); i++) {
-		if (unlikely(vcn < rl[i+1].vcn)) {
-			if (likely(rl[i].lcn >= (LCN)0))
-				return rl[i].lcn + (vcn - rl[i].vcn);
-			return rl[i].lcn;
-		}
-	}
-	/*
-	 * The terminator element is setup to the correct value, i.e. one of
-	 * LCN_HOLE, LCN_RL_NOT_MAPPED, or LCN_ENOENT.
-	 */
-	if (likely(rl[i].lcn < (LCN)0))
-		return rl[i].lcn;
-	/* Just in case... We could replace this with BUG() some day. */
-	return LCN_ENOENT;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_rl_find_vcn_nolock - find a vcn in a runlist
- * @rl:		runlist to search
- * @vcn:	vcn to find
- *
- * Find the virtual cluster number @vcn in the runlist @rl and return the
- * address of the runlist element containing the @vcn on success.
- *
- * Return NULL if @rl is NULL or @vcn is in an unmapped part/out of bounds of
- * the runlist.
- *
- * Locking: The runlist must be locked on entry.
- */
-runlist_element *ntfs_rl_find_vcn_nolock(runlist_element *rl, const VCN vcn)
-{
-	BUG_ON(vcn < 0);
-	if (unlikely(!rl || vcn < rl[0].vcn))
-		return NULL;
-	while (likely(rl->length)) {
-		if (unlikely(vcn < rl[1].vcn)) {
-			if (likely(rl->lcn >= LCN_HOLE))
-				return rl;
-			return NULL;
-		}
-		rl++;
-	}
-	if (likely(rl->lcn == LCN_ENOENT))
-		return rl;
-	return NULL;
-}
-
-/**
- * ntfs_get_nr_significant_bytes - get number of bytes needed to store a number
- * @n:		number for which to get the number of bytes for
- *
- * Return the number of bytes required to store @n unambiguously as
- * a signed number.
- *
- * This is used in the context of the mapping pairs array to determine how
- * many bytes will be needed in the array to store a given logical cluster
- * number (lcn) or a specific run length.
- *
- * Return the number of bytes written.  This function cannot fail.
- */
-static inline int ntfs_get_nr_significant_bytes(const s64 n)
-{
-	s64 l = n;
-	int i;
-	s8 j;
-
-	i = 0;
-	do {
-		l >>= 8;
-		i++;
-	} while (l != 0 && l != -1);
-	j = (n >> 8 * (i - 1)) & 0xff;
-	/* If the sign bit is wrong, we need an extra byte. */
-	if ((n < 0 && j >= 0) || (n > 0 && j < 0))
-		i++;
-	return i;
-}
-
-/**
- * ntfs_get_size_for_mapping_pairs - get bytes needed for mapping pairs array
- * @vol:	ntfs volume (needed for the ntfs version)
- * @rl:		locked runlist to determine the size of the mapping pairs of
- * @first_vcn:	first vcn which to include in the mapping pairs array
- * @last_vcn:	last vcn which to include in the mapping pairs array
- *
- * Walk the locked runlist @rl and calculate the size in bytes of the mapping
- * pairs array corresponding to the runlist @rl, starting at vcn @first_vcn and
- * finishing with vcn @last_vcn.
- *
- * A @last_vcn of -1 means end of runlist and in that case the size of the
- * mapping pairs array corresponding to the runlist starting at vcn @first_vcn
- * and finishing at the end of the runlist is determined.
- *
- * This for example allows us to allocate a buffer of the right size when
- * building the mapping pairs array.
- *
- * If @rl is NULL, just return 1 (for the single terminator byte).
- *
- * Return the calculated size in bytes on success.  On error, return -errno.
- * The following error codes are defined:
- *	-EINVAL	- Run list contains unmapped elements.  Make sure to only pass
- *		  fully mapped runlists to this function.
- *	-EIO	- The runlist is corrupt.
- *
- * Locking: @rl must be locked on entry (either for reading or writing), it
- *	    remains locked throughout, and is left locked upon return.
- */
-int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol,
-		const runlist_element *rl, const VCN first_vcn,
-		const VCN last_vcn)
-{
-	LCN prev_lcn;
-	int rls;
-	bool the_end = false;
-
-	BUG_ON(first_vcn < 0);
-	BUG_ON(last_vcn < -1);
-	BUG_ON(last_vcn >= 0 && first_vcn > last_vcn);
-	if (!rl) {
-		BUG_ON(first_vcn);
-		BUG_ON(last_vcn > 0);
-		return 1;
-	}
-	/* Skip to runlist element containing @first_vcn. */
-	while (rl->length && first_vcn >= rl[1].vcn)
-		rl++;
-	if (unlikely((!rl->length && first_vcn > rl->vcn) ||
-			first_vcn < rl->vcn))
-		return -EINVAL;
-	prev_lcn = 0;
-	/* Always need the termining zero byte. */
-	rls = 1;
-	/* Do the first partial run if present. */
-	if (first_vcn > rl->vcn) {
-		s64 delta, length = rl->length;
-
-		/* We know rl->length != 0 already. */
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		delta = first_vcn - rl->vcn;
-		/* Header byte + length. */
-		rls += 1 + ntfs_get_nr_significant_bytes(length - delta);
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just store the lcn.
-		 * Note: this assumes that on NTFS 1.2-, holes are stored with
-		 * an lcn of -1 and not a delta_lcn of -1 (unless both are -1).
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			prev_lcn = rl->lcn;
-			if (likely(rl->lcn >= 0))
-				prev_lcn += delta;
-			/* Change in lcn. */
-			rls += ntfs_get_nr_significant_bytes(prev_lcn);
-		}
-		/* Go to next runlist element. */
-		rl++;
-	}
-	/* Do the full runs. */
-	for (; rl->length && !the_end; rl++) {
-		s64 length = rl->length;
-
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		/* Header byte + length. */
-		rls += 1 + ntfs_get_nr_significant_bytes(length);
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just store the lcn.
-		 * Note: this assumes that on NTFS 1.2-, holes are stored with
-		 * an lcn of -1 and not a delta_lcn of -1 (unless both are -1).
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			/* Change in lcn. */
-			rls += ntfs_get_nr_significant_bytes(rl->lcn -
-					prev_lcn);
-			prev_lcn = rl->lcn;
-		}
-	}
-	return rls;
-err_out:
-	if (rl->lcn == LCN_RL_NOT_MAPPED)
-		rls = -EINVAL;
-	else
-		rls = -EIO;
-	return rls;
-}
-
-/**
- * ntfs_write_significant_bytes - write the significant bytes of a number
- * @dst:	destination buffer to write to
- * @dst_max:	pointer to last byte of destination buffer for bounds checking
- * @n:		number whose significant bytes to write
- *
- * Store in @dst, the minimum bytes of the number @n which are required to
- * identify @n unambiguously as a signed number, taking care not to exceed
- * @dest_max, the maximum position within @dst to which we are allowed to
- * write.
- *
- * This is used when building the mapping pairs array of a runlist to compress
- * a given logical cluster number (lcn) or a specific run length to the minimum
- * size possible.
- *
- * Return the number of bytes written on success.  On error, i.e. the
- * destination buffer @dst is too small, return -ENOSPC.
- */
-static inline int ntfs_write_significant_bytes(s8 *dst, const s8 *dst_max,
-		const s64 n)
-{
-	s64 l = n;
-	int i;
-	s8 j;
-
-	i = 0;
-	do {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		*dst++ = l & 0xffll;
-		l >>= 8;
-		i++;
-	} while (l != 0 && l != -1);
-	j = (n >> 8 * (i - 1)) & 0xff;
-	/* If the sign bit is wrong, we need an extra byte. */
-	if (n < 0 && j >= 0) {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		i++;
-		*dst = (s8)-1;
-	} else if (n > 0 && j < 0) {
-		if (unlikely(dst > dst_max))
-			goto err_out;
-		i++;
-		*dst = (s8)0;
-	}
-	return i;
-err_out:
-	return -ENOSPC;
-}
-
-/**
- * ntfs_mapping_pairs_build - build the mapping pairs array from a runlist
- * @vol:	ntfs volume (needed for the ntfs version)
- * @dst:	destination buffer to which to write the mapping pairs array
- * @dst_len:	size of destination buffer @dst in bytes
- * @rl:		locked runlist for which to build the mapping pairs array
- * @first_vcn:	first vcn which to include in the mapping pairs array
- * @last_vcn:	last vcn which to include in the mapping pairs array
- * @stop_vcn:	first vcn outside destination buffer on success or -ENOSPC
- *
- * Create the mapping pairs array from the locked runlist @rl, starting at vcn
- * @first_vcn and finishing with vcn @last_vcn and save the array in @dst.
- * @dst_len is the size of @dst in bytes and it should be at least equal to the
- * value obtained by calling ntfs_get_size_for_mapping_pairs().
- *
- * A @last_vcn of -1 means end of runlist and in that case the mapping pairs
- * array corresponding to the runlist starting at vcn @first_vcn and finishing
- * at the end of the runlist is created.
- *
- * If @rl is NULL, just write a single terminator byte to @dst.
- *
- * On success or -ENOSPC error, if @stop_vcn is not NULL, *@stop_vcn is set to
- * the first vcn outside the destination buffer.  Note that on error, @dst has
- * been filled with all the mapping pairs that will fit, thus it can be treated
- * as partial success, in that a new attribute extent needs to be created or
- * the next extent has to be used and the mapping pairs build has to be
- * continued with @first_vcn set to *@stop_vcn.
- *
- * Return 0 on success and -errno on error.  The following error codes are
- * defined:
- *	-EINVAL	- Run list contains unmapped elements.  Make sure to only pass
- *		  fully mapped runlists to this function.
- *	-EIO	- The runlist is corrupt.
- *	-ENOSPC	- The destination buffer is too small.
- *
- * Locking: @rl must be locked on entry (either for reading or writing), it
- *	    remains locked throughout, and is left locked upon return.
- */
-int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
-		const int dst_len, const runlist_element *rl,
-		const VCN first_vcn, const VCN last_vcn, VCN *const stop_vcn)
-{
-	LCN prev_lcn;
-	s8 *dst_max, *dst_next;
-	int err = -ENOSPC;
-	bool the_end = false;
-	s8 len_len, lcn_len;
-
-	BUG_ON(first_vcn < 0);
-	BUG_ON(last_vcn < -1);
-	BUG_ON(last_vcn >= 0 && first_vcn > last_vcn);
-	BUG_ON(dst_len < 1);
-	if (!rl) {
-		BUG_ON(first_vcn);
-		BUG_ON(last_vcn > 0);
-		if (stop_vcn)
-			*stop_vcn = 0;
-		/* Terminator byte. */
-		*dst = 0;
-		return 0;
-	}
-	/* Skip to runlist element containing @first_vcn. */
-	while (rl->length && first_vcn >= rl[1].vcn)
-		rl++;
-	if (unlikely((!rl->length && first_vcn > rl->vcn) ||
-			first_vcn < rl->vcn))
-		return -EINVAL;
-	/*
-	 * @dst_max is used for bounds checking in
-	 * ntfs_write_significant_bytes().
-	 */
-	dst_max = dst + dst_len - 1;
-	prev_lcn = 0;
-	/* Do the first partial run if present. */
-	if (first_vcn > rl->vcn) {
-		s64 delta, length = rl->length;
-
-		/* We know rl->length != 0 already. */
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		delta = first_vcn - rl->vcn;
-		/* Write length. */
-		len_len = ntfs_write_significant_bytes(dst + 1, dst_max,
-				length - delta);
-		if (unlikely(len_len < 0))
-			goto size_err;
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just write the lcn
-		 * change.  FIXME: Do we need to write the lcn change or just
-		 * the lcn in that case?  Not sure as I have never seen this
-		 * case on NT4. - We assume that we just need to write the lcn
-		 * change until someone tells us otherwise... (AIA)
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			prev_lcn = rl->lcn;
-			if (likely(rl->lcn >= 0))
-				prev_lcn += delta;
-			/* Write change in lcn. */
-			lcn_len = ntfs_write_significant_bytes(dst + 1 +
-					len_len, dst_max, prev_lcn);
-			if (unlikely(lcn_len < 0))
-				goto size_err;
-		} else
-			lcn_len = 0;
-		dst_next = dst + len_len + lcn_len + 1;
-		if (unlikely(dst_next > dst_max))
-			goto size_err;
-		/* Update header byte. */
-		*dst = lcn_len << 4 | len_len;
-		/* Position at next mapping pairs array element. */
-		dst = dst_next;
-		/* Go to next runlist element. */
-		rl++;
-	}
-	/* Do the full runs. */
-	for (; rl->length && !the_end; rl++) {
-		s64 length = rl->length;
-
-		if (unlikely(length < 0 || rl->lcn < LCN_HOLE))
-			goto err_out;
-		/*
-		 * If @stop_vcn is given and finishes inside this run, cap the
-		 * run length.
-		 */
-		if (unlikely(last_vcn >= 0 && rl[1].vcn > last_vcn)) {
-			s64 s1 = last_vcn + 1;
-			if (unlikely(rl[1].vcn > s1))
-				length = s1 - rl->vcn;
-			the_end = true;
-		}
-		/* Write length. */
-		len_len = ntfs_write_significant_bytes(dst + 1, dst_max,
-				length);
-		if (unlikely(len_len < 0))
-			goto size_err;
-		/*
-		 * If the logical cluster number (lcn) denotes a hole and we
-		 * are on NTFS 3.0+, we don't store it at all, i.e. we need
-		 * zero space.  On earlier NTFS versions we just write the lcn
-		 * change.  FIXME: Do we need to write the lcn change or just
-		 * the lcn in that case?  Not sure as I have never seen this
-		 * case on NT4. - We assume that we just need to write the lcn
-		 * change until someone tells us otherwise... (AIA)
-		 */
-		if (likely(rl->lcn >= 0 || vol->major_ver < 3)) {
-			/* Write change in lcn. */
-			lcn_len = ntfs_write_significant_bytes(dst + 1 +
-					len_len, dst_max, rl->lcn - prev_lcn);
-			if (unlikely(lcn_len < 0))
-				goto size_err;
-			prev_lcn = rl->lcn;
-		} else
-			lcn_len = 0;
-		dst_next = dst + len_len + lcn_len + 1;
-		if (unlikely(dst_next > dst_max))
-			goto size_err;
-		/* Update header byte. */
-		*dst = lcn_len << 4 | len_len;
-		/* Position at next mapping pairs array element. */
-		dst = dst_next;
-	}
-	/* Success. */
-	err = 0;
-size_err:
-	/* Set stop vcn. */
-	if (stop_vcn)
-		*stop_vcn = rl->vcn;
-	/* Add terminator byte. */
-	*dst = 0;
-	return err;
-err_out:
-	if (rl->lcn == LCN_RL_NOT_MAPPED)
-		err = -EINVAL;
-	else
-		err = -EIO;
-	return err;
-}
-
-/**
- * ntfs_rl_truncate_nolock - truncate a runlist starting at a specified vcn
- * @vol:	ntfs volume (needed for error output)
- * @runlist:	runlist to truncate
- * @new_length:	the new length of the runlist in VCNs
- *
- * Truncate the runlist described by @runlist as well as the memory buffer
- * holding the runlist elements to a length of @new_length VCNs.
- *
- * If @new_length lies within the runlist, the runlist elements with VCNs of
- * @new_length and above are discarded.  As a special case if @new_length is
- * zero, the runlist is discarded and set to NULL.
- *
- * If @new_length lies beyond the runlist, a sparse runlist element is added to
- * the end of the runlist @runlist or if the last runlist element is a sparse
- * one already, this is extended.
- *
- * Note, no checking is done for unmapped runlist elements.  It is assumed that
- * the caller has mapped any elements that need to be mapped already.
- *
- * Return 0 on success and -errno on error.
- *
- * Locking: The caller must hold @runlist->lock for writing.
- */
-int ntfs_rl_truncate_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const s64 new_length)
-{
-	runlist_element *rl;
-	int old_size;
-
-	ntfs_debug("Entering for new_length 0x%llx.", (long long)new_length);
-	BUG_ON(!runlist);
-	BUG_ON(new_length < 0);
-	rl = runlist->rl;
-	if (!new_length) {
-		ntfs_debug("Freeing runlist.");
-		runlist->rl = NULL;
-		if (rl)
-			ntfs_free(rl);
-		return 0;
-	}
-	if (unlikely(!rl)) {
-		/*
-		 * Create a runlist consisting of a sparse runlist element of
-		 * length @new_length followed by a terminator runlist element.
-		 */
-		rl = ntfs_malloc_nofs(PAGE_SIZE);
-		if (unlikely(!rl)) {
-			ntfs_error(vol->sb, "Not enough memory to allocate "
-					"runlist element buffer.");
-			return -ENOMEM;
-		}
-		runlist->rl = rl;
-		rl[1].length = rl->vcn = 0;
-		rl->lcn = LCN_HOLE;
-		rl[1].vcn = rl->length = new_length;
-		rl[1].lcn = LCN_ENOENT;
-		return 0;
-	}
-	BUG_ON(new_length < rl->vcn);
-	/* Find @new_length in the runlist. */
-	while (likely(rl->length && new_length >= rl[1].vcn))
-		rl++;
-	/*
-	 * If not at the end of the runlist we need to shrink it.
-	 * If at the end of the runlist we need to expand it.
-	 */
-	if (rl->length) {
-		runlist_element *trl;
-		bool is_end;
-
-		ntfs_debug("Shrinking runlist.");
-		/* Determine the runlist size. */
-		trl = rl + 1;
-		while (likely(trl->length))
-			trl++;
-		old_size = trl - runlist->rl + 1;
-		/* Truncate the run. */
-		rl->length = new_length - rl->vcn;
-		/*
-		 * If a run was partially truncated, make the following runlist
-		 * element a terminator.
-		 */
-		is_end = false;
-		if (rl->length) {
-			rl++;
-			if (!rl->length)
-				is_end = true;
-			rl->vcn = new_length;
-			rl->length = 0;
-		}
-		rl->lcn = LCN_ENOENT;
-		/* Reallocate memory if necessary. */
-		if (!is_end) {
-			int new_size = rl - runlist->rl + 1;
-			rl = ntfs_rl_realloc(runlist->rl, old_size, new_size);
-			if (IS_ERR(rl))
-				ntfs_warning(vol->sb, "Failed to shrink "
-						"runlist buffer.  This just "
-						"wastes a bit of memory "
-						"temporarily so we ignore it "
-						"and return success.");
-			else
-				runlist->rl = rl;
-		}
-	} else if (likely(/* !rl->length && */ new_length > rl->vcn)) {
-		ntfs_debug("Expanding runlist.");
-		/*
-		 * If there is a previous runlist element and it is a sparse
-		 * one, extend it.  Otherwise need to add a new, sparse runlist
-		 * element.
-		 */
-		if ((rl > runlist->rl) && ((rl - 1)->lcn == LCN_HOLE))
-			(rl - 1)->length = new_length - (rl - 1)->vcn;
-		else {
-			/* Determine the runlist size. */
-			old_size = rl - runlist->rl + 1;
-			/* Reallocate memory if necessary. */
-			rl = ntfs_rl_realloc(runlist->rl, old_size,
-					old_size + 1);
-			if (IS_ERR(rl)) {
-				ntfs_error(vol->sb, "Failed to expand runlist "
-						"buffer, aborting.");
-				return PTR_ERR(rl);
-			}
-			runlist->rl = rl;
-			/*
-			 * Set @rl to the same runlist element in the new
-			 * runlist as before in the old runlist.
-			 */
-			rl += old_size - 1;
-			/* Add a new, sparse runlist element. */
-			rl->lcn = LCN_HOLE;
-			rl->length = new_length - rl->vcn;
-			/* Add a new terminator runlist element. */
-			rl++;
-			rl->length = 0;
-		}
-		rl->vcn = new_length;
-		rl->lcn = LCN_ENOENT;
-	} else /* if (unlikely(!rl->length && new_length == rl->vcn)) */ {
-		/* Runlist already has same size as requested. */
-		rl->lcn = LCN_ENOENT;
-	}
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * ntfs_rl_punch_nolock - punch a hole into a runlist
- * @vol:	ntfs volume (needed for error output)
- * @runlist:	runlist to punch a hole into
- * @start:	starting VCN of the hole to be created
- * @length:	size of the hole to be created in units of clusters
- *
- * Punch a hole into the runlist @runlist starting at VCN @start and of size
- * @length clusters.
- *
- * Return 0 on success and -errno on error, in which case @runlist has not been
- * modified.
- *
- * If @start and/or @start + @length are outside the runlist return error code
- * -ENOENT.
- *
- * If the runlist contains unmapped or error elements between @start and @start
- * + @length return error code -EINVAL.
- *
- * Locking: The caller must hold @runlist->lock for writing.
- */
-int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const VCN start, const s64 length)
-{
-	const VCN end = start + length;
-	s64 delta;
-	runlist_element *rl, *rl_end, *rl_real_end, *trl;
-	int old_size;
-	bool lcn_fixup = false;
-
-	ntfs_debug("Entering for start 0x%llx, length 0x%llx.",
-			(long long)start, (long long)length);
-	BUG_ON(!runlist);
-	BUG_ON(start < 0);
-	BUG_ON(length < 0);
-	BUG_ON(end < 0);
-	rl = runlist->rl;
-	if (unlikely(!rl)) {
-		if (likely(!start && !length))
-			return 0;
-		return -ENOENT;
-	}
-	/* Find @start in the runlist. */
-	while (likely(rl->length && start >= rl[1].vcn))
-		rl++;
-	rl_end = rl;
-	/* Find @end in the runlist. */
-	while (likely(rl_end->length && end >= rl_end[1].vcn)) {
-		/* Verify there are no unmapped or error elements. */
-		if (unlikely(rl_end->lcn < LCN_HOLE))
-			return -EINVAL;
-		rl_end++;
-	}
-	/* Check the last element. */
-	if (unlikely(rl_end->length && rl_end->lcn < LCN_HOLE))
-		return -EINVAL;
-	/* This covers @start being out of bounds, too. */
-	if (!rl_end->length && end > rl_end->vcn)
-		return -ENOENT;
-	if (!length)
-		return 0;
-	if (!rl->length)
-		return -ENOENT;
-	rl_real_end = rl_end;
-	/* Determine the runlist size. */
-	while (likely(rl_real_end->length))
-		rl_real_end++;
-	old_size = rl_real_end - runlist->rl + 1;
-	/* If @start is in a hole simply extend the hole. */
-	if (rl->lcn == LCN_HOLE) {
-		/*
-		 * If both @start and @end are in the same sparse run, we are
-		 * done.
-		 */
-		if (end <= rl[1].vcn) {
-			ntfs_debug("Done (requested hole is already sparse).");
-			return 0;
-		}
-extend_hole:
-		/* Extend the hole. */
-		rl->length = end - rl->vcn;
-		/* If @end is in a hole, merge it with the current one. */
-		if (rl_end->lcn == LCN_HOLE) {
-			rl_end++;
-			rl->length = rl_end->vcn - rl->vcn;
-		}
-		/* We have done the hole.  Now deal with the remaining tail. */
-		rl++;
-		/* Cut out all runlist elements up to @end. */
-		if (rl < rl_end)
-			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
-					sizeof(*rl));
-		/* Adjust the beginning of the tail if necessary. */
-		if (end > rl->vcn) {
-			delta = end - rl->vcn;
-			rl->vcn = end;
-			rl->length -= delta;
-			/* Only adjust the lcn if it is real. */
-			if (rl->lcn >= 0)
-				rl->lcn += delta;
-		}
-shrink_allocation:
-		/* Reallocate memory if the allocation changed. */
-		if (rl < rl_end) {
-			rl = ntfs_rl_realloc(runlist->rl, old_size,
-					old_size - (rl_end - rl));
-			if (IS_ERR(rl))
-				ntfs_warning(vol->sb, "Failed to shrink "
-						"runlist buffer.  This just "
-						"wastes a bit of memory "
-						"temporarily so we ignore it "
-						"and return success.");
-			else
-				runlist->rl = rl;
-		}
-		ntfs_debug("Done (extend hole).");
-		return 0;
-	}
-	/*
-	 * If @start is at the beginning of a run things are easier as there is
-	 * no need to split the first run.
-	 */
-	if (start == rl->vcn) {
-		/*
-		 * @start is at the beginning of a run.
-		 *
-		 * If the previous run is sparse, extend its hole.
-		 *
-		 * If @end is not in the same run, switch the run to be sparse
-		 * and extend the newly created hole.
-		 *
-		 * Thus both of these cases reduce the problem to the above
-		 * case of "@start is in a hole".
-		 */
-		if (rl > runlist->rl && (rl - 1)->lcn == LCN_HOLE) {
-			rl--;
-			goto extend_hole;
-		}
-		if (end >= rl[1].vcn) {
-			rl->lcn = LCN_HOLE;
-			goto extend_hole;
-		}
-		/*
-		 * The final case is when @end is in the same run as @start.
-		 * For this need to split the run into two.  One run for the
-		 * sparse region between the beginning of the old run, i.e.
-		 * @start, and @end and one for the remaining non-sparse
-		 * region, i.e. between @end and the end of the old run.
-		 */
-		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
-		if (IS_ERR(trl))
-			goto enomem_out;
-		old_size++;
-		if (runlist->rl != trl) {
-			rl = trl + (rl - runlist->rl);
-			rl_end = trl + (rl_end - runlist->rl);
-			rl_real_end = trl + (rl_real_end - runlist->rl);
-			runlist->rl = trl;
-		}
-split_end:
-		/* Shift all the runs up by one. */
-		memmove(rl + 1, rl, (rl_real_end - rl + 1) * sizeof(*rl));
-		/* Finally, setup the two split runs. */
-		rl->lcn = LCN_HOLE;
-		rl->length = length;
-		rl++;
-		rl->vcn += length;
-		/* Only adjust the lcn if it is real. */
-		if (rl->lcn >= 0 || lcn_fixup)
-			rl->lcn += length;
-		rl->length -= length;
-		ntfs_debug("Done (split one).");
-		return 0;
-	}
-	/*
-	 * @start is neither in a hole nor at the beginning of a run.
-	 *
-	 * If @end is in a hole, things are easier as simply truncating the run
-	 * @start is in to end at @start - 1, deleting all runs after that up
-	 * to @end, and finally extending the beginning of the run @end is in
-	 * to be @start is all that is needed.
-	 */
-	if (rl_end->lcn == LCN_HOLE) {
-		/* Truncate the run containing @start. */
-		rl->length = start - rl->vcn;
-		rl++;
-		/* Cut out all runlist elements up to @end. */
-		if (rl < rl_end)
-			memmove(rl, rl_end, (rl_real_end - rl_end + 1) *
-					sizeof(*rl));
-		/* Extend the beginning of the run @end is in to be @start. */
-		rl->vcn = start;
-		rl->length = rl[1].vcn - start;
-		goto shrink_allocation;
-	}
-	/* 
-	 * If @end is not in a hole there are still two cases to distinguish.
-	 * Either @end is or is not in the same run as @start.
-	 *
-	 * The second case is easier as it can be reduced to an already solved
-	 * problem by truncating the run @start is in to end at @start - 1.
-	 * Then, if @end is in the next run need to split the run into a sparse
-	 * run followed by a non-sparse run (already covered above) and if @end
-	 * is not in the next run switching it to be sparse, again reduces the
-	 * problem to the already covered case of "@start is in a hole".
-	 */
-	if (end >= rl[1].vcn) {
-		/*
-		 * If @end is not in the next run, reduce the problem to the
-		 * case of "@start is in a hole".
-		 */
-		if (rl[1].length && end >= rl[2].vcn) {
-			/* Truncate the run containing @start. */
-			rl->length = start - rl->vcn;
-			rl++;
-			rl->vcn = start;
-			rl->lcn = LCN_HOLE;
-			goto extend_hole;
-		}
-		trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 1);
-		if (IS_ERR(trl))
-			goto enomem_out;
-		old_size++;
-		if (runlist->rl != trl) {
-			rl = trl + (rl - runlist->rl);
-			rl_end = trl + (rl_end - runlist->rl);
-			rl_real_end = trl + (rl_real_end - runlist->rl);
-			runlist->rl = trl;
-		}
-		/* Truncate the run containing @start. */
-		rl->length = start - rl->vcn;
-		rl++;
-		/*
-		 * @end is in the next run, reduce the problem to the case
-		 * where "@start is at the beginning of a run and @end is in
-		 * the same run as @start".
-		 */
-		delta = rl->vcn - start;
-		rl->vcn = start;
-		if (rl->lcn >= 0) {
-			rl->lcn -= delta;
-			/* Need this in case the lcn just became negative. */
-			lcn_fixup = true;
-		}
-		rl->length += delta;
-		goto split_end;
-	}
-	/*
-	 * The first case from above, i.e. @end is in the same run as @start.
-	 * We need to split the run into three.  One run for the non-sparse
-	 * region between the beginning of the old run and @start, one for the
-	 * sparse region between @start and @end, and one for the remaining
-	 * non-sparse region, i.e. between @end and the end of the old run.
-	 */
-	trl = ntfs_rl_realloc(runlist->rl, old_size, old_size + 2);
-	if (IS_ERR(trl))
-		goto enomem_out;
-	old_size += 2;
-	if (runlist->rl != trl) {
-		rl = trl + (rl - runlist->rl);
-		rl_end = trl + (rl_end - runlist->rl);
-		rl_real_end = trl + (rl_real_end - runlist->rl);
-		runlist->rl = trl;
-	}
-	/* Shift all the runs up by two. */
-	memmove(rl + 2, rl, (rl_real_end - rl + 1) * sizeof(*rl));
-	/* Finally, setup the three split runs. */
-	rl->length = start - rl->vcn;
-	rl++;
-	rl->vcn = start;
-	rl->lcn = LCN_HOLE;
-	rl->length = length;
-	rl++;
-	delta = end - rl->vcn;
-	rl->vcn = end;
-	rl->lcn += delta;
-	rl->length -= delta;
-	ntfs_debug("Done (split both).");
-	return 0;
-enomem_out:
-	ntfs_error(vol->sb, "Not enough memory to extend runlist buffer.");
-	return -ENOMEM;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/runlist.h b/fs/ntfs/runlist.h
deleted file mode 100644
index 38de0a375f59..000000000000
--- a/fs/ntfs/runlist.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * runlist.h - Defines for runlist handling in NTFS Linux kernel driver.
- *	       Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_RUNLIST_H
-#define _LINUX_NTFS_RUNLIST_H
-
-#include "types.h"
-#include "layout.h"
-#include "volume.h"
-
-/**
- * runlist_element - in memory vcn to lcn mapping array element
- * @vcn:	starting vcn of the current array element
- * @lcn:	starting lcn of the current array element
- * @length:	length in clusters of the current array element
- *
- * The last vcn (in fact the last vcn + 1) is reached when length == 0.
- *
- * When lcn == -1 this means that the count vcns starting at vcn are not
- * physically allocated (i.e. this is a hole / data is sparse).
- */
-typedef struct {	/* In memory vcn to lcn mapping structure element. */
-	VCN vcn;	/* vcn = Starting virtual cluster number. */
-	LCN lcn;	/* lcn = Starting logical cluster number. */
-	s64 length;	/* Run length in clusters. */
-} runlist_element;
-
-/**
- * runlist - in memory vcn to lcn mapping array including a read/write lock
- * @rl:		pointer to an array of runlist elements
- * @lock:	read/write spinlock for serializing access to @rl
- *
- */
-typedef struct {
-	runlist_element *rl;
-	struct rw_semaphore lock;
-} runlist;
-
-static inline void ntfs_init_runlist(runlist *rl)
-{
-	rl->rl = NULL;
-	init_rwsem(&rl->lock);
-}
-
-typedef enum {
-	LCN_HOLE		= -1,	/* Keep this as highest value or die! */
-	LCN_RL_NOT_MAPPED	= -2,
-	LCN_ENOENT		= -3,
-	LCN_ENOMEM		= -4,
-	LCN_EIO			= -5,
-} LCN_SPECIAL_VALUES;
-
-extern runlist_element *ntfs_runlists_merge(runlist_element *drl,
-		runlist_element *srl);
-
-extern runlist_element *ntfs_mapping_pairs_decompress(const ntfs_volume *vol,
-		const ATTR_RECORD *attr, runlist_element *old_rl);
-
-extern LCN ntfs_rl_vcn_to_lcn(const runlist_element *rl, const VCN vcn);
-
-#ifdef NTFS_RW
-
-extern runlist_element *ntfs_rl_find_vcn_nolock(runlist_element *rl,
-		const VCN vcn);
-
-extern int ntfs_get_size_for_mapping_pairs(const ntfs_volume *vol,
-		const runlist_element *rl, const VCN first_vcn,
-		const VCN last_vcn);
-
-extern int ntfs_mapping_pairs_build(const ntfs_volume *vol, s8 *dst,
-		const int dst_len, const runlist_element *rl,
-		const VCN first_vcn, const VCN last_vcn, VCN *const stop_vcn);
-
-extern int ntfs_rl_truncate_nolock(const ntfs_volume *vol,
-		runlist *const runlist, const s64 new_length);
-
-int ntfs_rl_punch_nolock(const ntfs_volume *vol, runlist *const runlist,
-		const VCN start, const s64 length);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_RUNLIST_H */
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
deleted file mode 100644
index 56a7d5bd33e4..000000000000
--- a/fs/ntfs/super.c
+++ /dev/null
@@ -1,3202 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc.
- * Copyright (c) 2001,2002 Richard Russon
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/stddef.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/spinlock.h>
-#include <linux/blkdev.h>	/* For bdev_logical_block_size(). */
-#include <linux/backing-dev.h>
-#include <linux/buffer_head.h>
-#include <linux/vfs.h>
-#include <linux/moduleparam.h>
-#include <linux/bitmap.h>
-
-#include "sysctl.h"
-#include "logfile.h"
-#include "quota.h"
-#include "usnjrnl.h"
-#include "dir.h"
-#include "debug.h"
-#include "index.h"
-#include "inode.h"
-#include "aops.h"
-#include "layout.h"
-#include "malloc.h"
-#include "ntfs.h"
-
-/* Number of mounted filesystems which have compression enabled. */
-static unsigned long ntfs_nr_compression_users;
-
-/* A global default upcase table and a corresponding reference count. */
-static ntfschar *default_upcase;
-static unsigned long ntfs_nr_upcase_users;
-
-/* Error constants/strings used in inode.c::ntfs_show_options(). */
-typedef enum {
-	/* One of these must be present, default is ON_ERRORS_CONTINUE. */
-	ON_ERRORS_PANIC			= 0x01,
-	ON_ERRORS_REMOUNT_RO		= 0x02,
-	ON_ERRORS_CONTINUE		= 0x04,
-	/* Optional, can be combined with any of the above. */
-	ON_ERRORS_RECOVER		= 0x10,
-} ON_ERRORS_ACTIONS;
-
-const option_t on_errors_arr[] = {
-	{ ON_ERRORS_PANIC,	"panic" },
-	{ ON_ERRORS_REMOUNT_RO,	"remount-ro", },
-	{ ON_ERRORS_CONTINUE,	"continue", },
-	{ ON_ERRORS_RECOVER,	"recover" },
-	{ 0,			NULL }
-};
-
-/**
- * simple_getbool - convert input string to a boolean value
- * @s: input string to convert
- * @setval: where to store the output boolean value
- *
- * Copied from old ntfs driver (which copied from vfat driver).
- *
- * "1", "yes", "true", or an empty string are converted to %true.
- * "0", "no", and "false" are converted to %false.
- *
- * Return: %1 if the string is converted or was empty and *setval contains it;
- *	   %0 if the string was not valid.
- */
-static int simple_getbool(char *s, bool *setval)
-{
-	if (s) {
-		if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true"))
-			*setval = true;
-		else if (!strcmp(s, "0") || !strcmp(s, "no") ||
-							!strcmp(s, "false"))
-			*setval = false;
-		else
-			return 0;
-	} else
-		*setval = true;
-	return 1;
-}
-
-/**
- * parse_options - parse the (re)mount options
- * @vol:	ntfs volume
- * @opt:	string containing the (re)mount options
- *
- * Parse the recognized options in @opt for the ntfs volume described by @vol.
- */
-static bool parse_options(ntfs_volume *vol, char *opt)
-{
-	char *p, *v, *ov;
-	static char *utf8 = "utf8";
-	int errors = 0, sloppy = 0;
-	kuid_t uid = INVALID_UID;
-	kgid_t gid = INVALID_GID;
-	umode_t fmask = (umode_t)-1, dmask = (umode_t)-1;
-	int mft_zone_multiplier = -1, on_errors = -1;
-	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
-	struct nls_table *nls_map = NULL, *old_nls;
-
-	/* I am lazy... (-8 */
-#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value)	\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			variable = default_value;			\
-		else {							\
-			variable = simple_strtoul(ov = v, &v, 0);	\
-			if (*v)						\
-				goto needs_val;				\
-		}							\
-	}
-#define NTFS_GETOPT(option, variable)					\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		variable = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_UID(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		uid_t uid_value;					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		uid_value = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-		variable = make_kuid(current_user_ns(), uid_value);	\
-		if (!uid_valid(variable))				\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_GID(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		gid_t gid_value;					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		gid_value = simple_strtoul(ov = v, &v, 0);		\
-		if (*v)							\
-			goto needs_val;					\
-		variable = make_kgid(current_user_ns(), gid_value);	\
-		if (!gid_valid(variable))				\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_OCTAL(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		variable = simple_strtoul(ov = v, &v, 8);		\
-		if (*v)							\
-			goto needs_val;					\
-	}
-#define NTFS_GETOPT_BOOL(option, variable)				\
-	if (!strcmp(p, option)) {					\
-		bool val;						\
-		if (!simple_getbool(v, &val))				\
-			goto needs_bool;				\
-		variable = val;						\
-	}
-#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array)		\
-	if (!strcmp(p, option)) {					\
-		int _i;							\
-		if (!v || !*v)						\
-			goto needs_arg;					\
-		ov = v;							\
-		if (variable == -1)					\
-			variable = 0;					\
-		for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \
-			if (!strcmp(opt_array[_i].str, v)) {		\
-				variable |= opt_array[_i].val;		\
-				break;					\
-			}						\
-		if (!opt_array[_i].str || !*opt_array[_i].str)		\
-			goto needs_val;					\
-	}
-	if (!opt || !*opt)
-		goto no_mount_options;
-	ntfs_debug("Entering with mount options string: %s", opt);
-	while ((p = strsep(&opt, ","))) {
-		if ((v = strchr(p, '=')))
-			*v++ = 0;
-		NTFS_GETOPT_UID("uid", uid)
-		else NTFS_GETOPT_GID("gid", gid)
-		else NTFS_GETOPT_OCTAL("umask", fmask = dmask)
-		else NTFS_GETOPT_OCTAL("fmask", fmask)
-		else NTFS_GETOPT_OCTAL("dmask", dmask)
-		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
-		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true)
-		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
-		else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
-		else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)
-		else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,
-				on_errors_arr)
-		else if (!strcmp(p, "posix") || !strcmp(p, "show_inodes"))
-			ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
-					p);
-		else if (!strcmp(p, "nls") || !strcmp(p, "iocharset")) {
-			if (!strcmp(p, "iocharset"))
-				ntfs_warning(vol->sb, "Option iocharset is "
-						"deprecated. Please use "
-						"option nls=<charsetname> in "
-						"the future.");
-			if (!v || !*v)
-				goto needs_arg;
-use_utf8:
-			old_nls = nls_map;
-			nls_map = load_nls(v);
-			if (!nls_map) {
-				if (!old_nls) {
-					ntfs_error(vol->sb, "NLS character set "
-							"%s not found.", v);
-					return false;
-				}
-				ntfs_error(vol->sb, "NLS character set %s not "
-						"found. Using previous one %s.",
-						v, old_nls->charset);
-				nls_map = old_nls;
-			} else /* nls_map */ {
-				unload_nls(old_nls);
-			}
-		} else if (!strcmp(p, "utf8")) {
-			bool val = false;
-			ntfs_warning(vol->sb, "Option utf8 is no longer "
-				   "supported, using option nls=utf8. Please "
-				   "use option nls=utf8 in the future and "
-				   "make sure utf8 is compiled either as a "
-				   "module or into the kernel.");
-			if (!v || !*v)
-				val = true;
-			else if (!simple_getbool(v, &val))
-				goto needs_bool;
-			if (val) {
-				v = utf8;
-				goto use_utf8;
-			}
-		} else {
-			ntfs_error(vol->sb, "Unrecognized mount option %s.", p);
-			if (errors < INT_MAX)
-				errors++;
-		}
-#undef NTFS_GETOPT_OPTIONS_ARRAY
-#undef NTFS_GETOPT_BOOL
-#undef NTFS_GETOPT
-#undef NTFS_GETOPT_WITH_DEFAULT
-	}
-no_mount_options:
-	if (errors && !sloppy)
-		return false;
-	if (sloppy)
-		ntfs_warning(vol->sb, "Sloppy option given. Ignoring "
-				"unrecognized mount option(s) and continuing.");
-	/* Keep this first! */
-	if (on_errors != -1) {
-		if (!on_errors) {
-			ntfs_error(vol->sb, "Invalid errors option argument "
-					"or bug in options parser.");
-			return false;
-		}
-	}
-	if (nls_map) {
-		if (vol->nls_map && vol->nls_map != nls_map) {
-			ntfs_error(vol->sb, "Cannot change NLS character set "
-					"on remount.");
-			return false;
-		} /* else (!vol->nls_map) */
-		ntfs_debug("Using NLS character set %s.", nls_map->charset);
-		vol->nls_map = nls_map;
-	} else /* (!nls_map) */ {
-		if (!vol->nls_map) {
-			vol->nls_map = load_nls_default();
-			if (!vol->nls_map) {
-				ntfs_error(vol->sb, "Failed to load default "
-						"NLS character set.");
-				return false;
-			}
-			ntfs_debug("Using default NLS character set (%s).",
-					vol->nls_map->charset);
-		}
-	}
-	if (mft_zone_multiplier != -1) {
-		if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
-				mft_zone_multiplier) {
-			ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "
-					"on remount.");
-			return false;
-		}
-		if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) {
-			ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "
-					"Using default value, i.e. 1.");
-			mft_zone_multiplier = 1;
-		}
-		vol->mft_zone_multiplier = mft_zone_multiplier;
-	}
-	if (!vol->mft_zone_multiplier)
-		vol->mft_zone_multiplier = 1;
-	if (on_errors != -1)
-		vol->on_errors = on_errors;
-	if (!vol->on_errors || vol->on_errors == ON_ERRORS_RECOVER)
-		vol->on_errors |= ON_ERRORS_CONTINUE;
-	if (uid_valid(uid))
-		vol->uid = uid;
-	if (gid_valid(gid))
-		vol->gid = gid;
-	if (fmask != (umode_t)-1)
-		vol->fmask = fmask;
-	if (dmask != (umode_t)-1)
-		vol->dmask = dmask;
-	if (show_sys_files != -1) {
-		if (show_sys_files)
-			NVolSetShowSystemFiles(vol);
-		else
-			NVolClearShowSystemFiles(vol);
-	}
-	if (case_sensitive != -1) {
-		if (case_sensitive)
-			NVolSetCaseSensitive(vol);
-		else
-			NVolClearCaseSensitive(vol);
-	}
-	if (disable_sparse != -1) {
-		if (disable_sparse)
-			NVolClearSparseEnabled(vol);
-		else {
-			if (!NVolSparseEnabled(vol) &&
-					vol->major_ver && vol->major_ver < 3)
-				ntfs_warning(vol->sb, "Not enabling sparse "
-						"support due to NTFS volume "
-						"version %i.%i (need at least "
-						"version 3.0).", vol->major_ver,
-						vol->minor_ver);
-			else
-				NVolSetSparseEnabled(vol);
-		}
-	}
-	return true;
-needs_arg:
-	ntfs_error(vol->sb, "The %s option requires an argument.", p);
-	return false;
-needs_bool:
-	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
-	return false;
-needs_val:
-	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
-	return false;
-}
-
-#ifdef NTFS_RW
-
-/**
- * ntfs_write_volume_flags - write new flags to the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	new flags value for the volume information flags
- *
- * Internal function.  You probably want to use ntfs_{set,clear}_volume_flags()
- * instead (see below).
- *
- * Replace the volume information flags on the volume @vol with the value
- * supplied in @flags.  Note, this overwrites the volume information flags, so
- * make sure to combine the flags you want to modify with the old flags and use
- * the result when calling ntfs_write_volume_flags().
- *
- * Return 0 on success and -errno on error.
- */
-static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)
-{
-	ntfs_inode *ni = NTFS_I(vol->vol_ino);
-	MFT_RECORD *m;
-	VOLUME_INFORMATION *vi;
-	ntfs_attr_search_ctx *ctx;
-	int err;
-
-	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",
-			le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));
-	if (vol->vol_flags == flags)
-		goto done;
-	BUG_ON(!ni);
-	m = map_mft_record(ni);
-	if (IS_ERR(m)) {
-		err = PTR_ERR(m);
-		goto err_out;
-	}
-	ctx = ntfs_attr_get_search_ctx(ni, m);
-	if (!ctx) {
-		err = -ENOMEM;
-		goto put_unm_err_out;
-	}
-	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx);
-	if (err)
-		goto put_unm_err_out;
-	vi = (VOLUME_INFORMATION*)((u8*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	vol->vol_flags = vi->flags = flags;
-	flush_dcache_mft_record_page(ctx->ntfs_ino);
-	mark_mft_record_dirty(ctx->ntfs_ino);
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-done:
-	ntfs_debug("Done.");
-	return 0;
-put_unm_err_out:
-	if (ctx)
-		ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(ni);
-err_out:
-	ntfs_error(vol->sb, "Failed with error code %i.", -err);
-	return err;
-}
-
-/**
- * ntfs_set_volume_flags - set bits in the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	flags to set on the volume
- *
- * Set the bits in @flags in the volume information flags on the volume @vol.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
-{
-	flags &= VOLUME_FLAGS_MASK;
-	return ntfs_write_volume_flags(vol, vol->vol_flags | flags);
-}
-
-/**
- * ntfs_clear_volume_flags - clear bits in the volume information flags
- * @vol:	ntfs volume on which to modify the flags
- * @flags:	flags to clear on the volume
- *
- * Clear the bits in @flags in the volume information flags on the volume @vol.
- *
- * Return 0 on success and -errno on error.
- */
-static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
-{
-	flags &= VOLUME_FLAGS_MASK;
-	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));
-	return ntfs_write_volume_flags(vol, flags);
-}
-
-#endif /* NTFS_RW */
-
-/**
- * ntfs_remount - change the mount options of a mounted ntfs filesystem
- * @sb:		superblock of mounted ntfs filesystem
- * @flags:	remount flags
- * @opt:	remount options string
- *
- * Change the mount options of an already mounted ntfs filesystem.
- *
- * NOTE:  The VFS sets the @sb->s_flags remount flags to @flags after
- * ntfs_remount() returns successfully (i.e. returns 0).  Otherwise,
- * @sb->s_flags are not changed.
- */
-static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
-{
-	ntfs_volume *vol = NTFS_SB(sb);
-
-	ntfs_debug("Entering with remount options string: %s", opt);
-
-	sync_filesystem(sb);
-
-#ifndef NTFS_RW
-	/* For read-only compiled driver, enforce read-only flag. */
-	*flags |= SB_RDONLY;
-#else /* NTFS_RW */
-	/*
-	 * For the read-write compiled driver, if we are remounting read-write,
-	 * make sure there are no volume errors and that no unsupported volume
-	 * flags are set.  Also, empty the logfile journal as it would become
-	 * stale as soon as something is written to the volume and mark the
-	 * volume dirty so that chkdsk is run if the volume is not umounted
-	 * cleanly.  Finally, mark the quotas out of date so Windows rescans
-	 * the volume on boot and updates them.
-	 *
-	 * When remounting read-only, mark the volume clean if no volume errors
-	 * have occurred.
-	 */
-	if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) {
-		static const char *es = ".  Cannot remount read-write.";
-
-		/* Remounting read-write. */
-		if (NVolErrors(vol)) {
-			ntfs_error(sb, "Volume has errors and is read-only%s",
-					es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_IS_DIRTY) {
-			ntfs_error(sb, "Volume is dirty and read-only%s", es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
-			ntfs_error(sb, "Volume has been modified by chkdsk "
-					"and is read-only%s", es);
-			return -EROFS;
-		}
-		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-			ntfs_error(sb, "Volume has unsupported flags set "
-					"(0x%x) and is read-only%s",
-					(unsigned)le16_to_cpu(vol->vol_flags),
-					es);
-			return -EROFS;
-		}
-		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
-			ntfs_error(sb, "Failed to set dirty bit in volume "
-					"information flags%s", es);
-			return -EROFS;
-		}
-#if 0
-		// TODO: Enable this code once we start modifying anything that
-		//	 is different between NTFS 1.2 and 3.x...
-		/* Set NT4 compatibility flag on newer NTFS version volumes. */
-		if ((vol->major_ver > 1)) {
-			if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
-				ntfs_error(sb, "Failed to set NT4 "
-						"compatibility flag%s", es);
-				NVolSetErrors(vol);
-				return -EROFS;
-			}
-		}
-#endif
-		if (!ntfs_empty_logfile(vol->logfile_ino)) {
-			ntfs_error(sb, "Failed to empty journal $LogFile%s",
-					es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-		if (!ntfs_mark_quotas_out_of_date(vol)) {
-			ntfs_error(sb, "Failed to mark quotas out of date%s",
-					es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-		if (!ntfs_stamp_usnjrnl(vol)) {
-			ntfs_error(sb, "Failed to stamp transaction log "
-					"($UsnJrnl)%s", es);
-			NVolSetErrors(vol);
-			return -EROFS;
-		}
-	} else if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) {
-		/* Remounting read-only. */
-		if (!NVolErrors(vol)) {
-			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
-				ntfs_warning(sb, "Failed to clear dirty bit "
-						"in volume information "
-						"flags.  Run chkdsk.");
-		}
-	}
-#endif /* NTFS_RW */
-
-	// TODO: Deal with *flags.
-
-	if (!parse_options(vol, opt))
-		return -EINVAL;
-
-	ntfs_debug("Done.");
-	return 0;
-}
-
-/**
- * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector
- * @sb:		Super block of the device to which @b belongs.
- * @b:		Boot sector of device @sb to check.
- * @silent:	If 'true', all output will be silenced.
- *
- * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
- * sector. Returns 'true' if it is valid and 'false' if not.
- *
- * @sb is only needed for warning/error output, i.e. it can be NULL when silent
- * is 'true'.
- */
-static bool is_boot_sector_ntfs(const struct super_block *sb,
-		const NTFS_BOOT_SECTOR *b, const bool silent)
-{
-	/*
-	 * Check that checksum == sum of u32 values from b to the checksum
-	 * field.  If checksum is zero, no checking is done.  We will work when
-	 * the checksum test fails, since some utilities update the boot sector
-	 * ignoring the checksum which leaves the checksum out-of-date.  We
-	 * report a warning if this is the case.
-	 */
-	if ((void*)b < (void*)&b->checksum && b->checksum && !silent) {
-		le32 *u;
-		u32 i;
-
-		for (i = 0, u = (le32*)b; u < (le32*)(&b->checksum); ++u)
-			i += le32_to_cpup(u);
-		if (le32_to_cpu(b->checksum) != i)
-			ntfs_warning(sb, "Invalid boot sector checksum.");
-	}
-	/* Check OEMidentifier is "NTFS    " */
-	if (b->oem_id != magicNTFS)
-		goto not_ntfs;
-	/* Check bytes per sector value is between 256 and 4096. */
-	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 ||
-			le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)
-		goto not_ntfs;
-	/* Check sectors per cluster value is valid. */
-	switch (b->bpb.sectors_per_cluster) {
-	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:
-		break;
-	default:
-		goto not_ntfs;
-	}
-	/* Check the cluster size is not above the maximum (64kiB). */
-	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
-			b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE)
-		goto not_ntfs;
-	/* Check reserved/unused fields are really zero. */
-	if (le16_to_cpu(b->bpb.reserved_sectors) ||
-			le16_to_cpu(b->bpb.root_entries) ||
-			le16_to_cpu(b->bpb.sectors) ||
-			le16_to_cpu(b->bpb.sectors_per_fat) ||
-			le32_to_cpu(b->bpb.large_sectors) || b->bpb.fats)
-		goto not_ntfs;
-	/* Check clusters per file mft record value is valid. */
-	if ((u8)b->clusters_per_mft_record < 0xe1 ||
-			(u8)b->clusters_per_mft_record > 0xf7)
-		switch (b->clusters_per_mft_record) {
-		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
-			break;
-		default:
-			goto not_ntfs;
-		}
-	/* Check clusters per index block value is valid. */
-	if ((u8)b->clusters_per_index_record < 0xe1 ||
-			(u8)b->clusters_per_index_record > 0xf7)
-		switch (b->clusters_per_index_record) {
-		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
-			break;
-		default:
-			goto not_ntfs;
-		}
-	/*
-	 * Check for valid end of sector marker. We will work without it, but
-	 * many BIOSes will refuse to boot from a bootsector if the magic is
-	 * incorrect, so we emit a warning.
-	 */
-	if (!silent && b->end_of_sector_marker != cpu_to_le16(0xaa55))
-		ntfs_warning(sb, "Invalid end of sector marker.");
-	return true;
-not_ntfs:
-	return false;
-}
-
-/**
- * read_ntfs_boot_sector - read the NTFS boot sector of a device
- * @sb:		super block of device to read the boot sector from
- * @silent:	if true, suppress all output
- *
- * Reads the boot sector from the device and validates it. If that fails, tries
- * to read the backup boot sector, first from the end of the device a-la NT4 and
- * later and then from the middle of the device a-la NT3.51 and before.
- *
- * If a valid boot sector is found but it is not the primary boot sector, we
- * repair the primary boot sector silently (unless the device is read-only or
- * the primary boot sector is not accessible).
- *
- * NOTE: To call this function, @sb must have the fields s_dev, the ntfs super
- * block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized
- * to their respective values.
- *
- * Return the unlocked buffer head containing the boot sector or NULL on error.
- */
-static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
-		const int silent)
-{
-	const char *read_err_str = "Unable to read %s boot sector.";
-	struct buffer_head *bh_primary, *bh_backup;
-	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
-
-	/* Try to read primary boot sector. */
-	if ((bh_primary = sb_bread(sb, 0))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_primary->b_data, silent))
-			return bh_primary;
-		if (!silent)
-			ntfs_error(sb, "Primary boot sector is invalid.");
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "primary");
-	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {
-		if (bh_primary)
-			brelse(bh_primary);
-		if (!silent)
-			ntfs_error(sb, "Mount option errors=recover not used. "
-					"Aborting without trying to recover.");
-		return NULL;
-	}
-	/* Try to read NT4+ backup boot sector. */
-	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_backup->b_data, silent))
-			goto hotfix_primary_boot_sector;
-		brelse(bh_backup);
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "backup");
-	/* Try to read NT3.51- backup boot sector. */
-	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {
-		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
-				bh_backup->b_data, silent))
-			goto hotfix_primary_boot_sector;
-		if (!silent)
-			ntfs_error(sb, "Could not find a valid backup boot "
-					"sector.");
-		brelse(bh_backup);
-	} else if (!silent)
-		ntfs_error(sb, read_err_str, "backup");
-	/* We failed. Cleanup and return. */
-	if (bh_primary)
-		brelse(bh_primary);
-	return NULL;
-hotfix_primary_boot_sector:
-	if (bh_primary) {
-		/*
-		 * If we managed to read sector zero and the volume is not
-		 * read-only, copy the found, valid backup boot sector to the
-		 * primary boot sector.  Note we only copy the actual boot
-		 * sector structure, not the actual whole device sector as that
-		 * may be bigger and would potentially damage the $Boot system
-		 * file (FIXME: Would be nice to know if the backup boot sector
-		 * on a large sector device contains the whole boot loader or
-		 * just the first 512 bytes).
-		 */
-		if (!sb_rdonly(sb)) {
-			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
-					"boot sector from backup copy.");
-			memcpy(bh_primary->b_data, bh_backup->b_data,
-					NTFS_BLOCK_SIZE);
-			mark_buffer_dirty(bh_primary);
-			sync_dirty_buffer(bh_primary);
-			if (buffer_uptodate(bh_primary)) {
-				brelse(bh_backup);
-				return bh_primary;
-			}
-			ntfs_error(sb, "Hot-fix: Device write error while "
-					"recovering primary boot sector.");
-		} else {
-			ntfs_warning(sb, "Hot-fix: Recovery of primary boot "
-					"sector failed: Read-only mount.");
-		}
-		brelse(bh_primary);
-	}
-	ntfs_warning(sb, "Using backup boot sector.");
-	return bh_backup;
-}
-
-/**
- * parse_ntfs_boot_sector - parse the boot sector and store the data in @vol
- * @vol:	volume structure to initialise with data from boot sector
- * @b:		boot sector to parse
- *
- * Parse the ntfs boot sector @b and store all imporant information therein in
- * the ntfs super block @vol.  Return 'true' on success and 'false' on error.
- */
-static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
-{
-	unsigned int sectors_per_cluster_bits, nr_hidden_sects;
-	int clusters_per_mft_record, clusters_per_index_record;
-	s64 ll;
-
-	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);
-	vol->sector_size_bits = ffs(vol->sector_size) - 1;
-	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,
-			vol->sector_size);
-	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
-			vol->sector_size_bits);
-	if (vol->sector_size < vol->sb->s_blocksize) {
-		ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
-				"device block size (%lu).  This is not "
-				"supported.  Sorry.", vol->sector_size,
-				vol->sb->s_blocksize);
-		return false;
-	}
-	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
-	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
-	ntfs_debug("sectors_per_cluster_bits = 0x%x",
-			sectors_per_cluster_bits);
-	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);
-	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);
-	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;
-	vol->cluster_size_mask = vol->cluster_size - 1;
-	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;
-	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
-			vol->cluster_size);
-	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
-	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
-	if (vol->cluster_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
-				"sector size (%i).  This is not supported.  "
-				"Sorry.", vol->cluster_size, vol->sector_size);
-		return false;
-	}
-	clusters_per_mft_record = b->clusters_per_mft_record;
-	ntfs_debug("clusters_per_mft_record = %i (0x%x)",
-			clusters_per_mft_record, clusters_per_mft_record);
-	if (clusters_per_mft_record > 0)
-		vol->mft_record_size = vol->cluster_size <<
-				(ffs(clusters_per_mft_record) - 1);
-	else
-		/*
-		 * When mft_record_size < cluster_size, clusters_per_mft_record
-		 * = -log2(mft_record_size) bytes. mft_record_size normaly is
-		 * 1024 bytes, which is encoded as 0xF6 (-10 in decimal).
-		 */
-		vol->mft_record_size = 1 << -clusters_per_mft_record;
-	vol->mft_record_size_mask = vol->mft_record_size - 1;
-	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;
-	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,
-			vol->mft_record_size);
-	ntfs_debug("vol->mft_record_size_mask = 0x%x",
-			vol->mft_record_size_mask);
-	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
-			vol->mft_record_size_bits, vol->mft_record_size_bits);
-	/*
-	 * We cannot support mft record sizes above the PAGE_SIZE since
-	 * we store $MFT/$DATA, the table of mft records in the page cache.
-	 */
-	if (vol->mft_record_size > PAGE_SIZE) {
-		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
-				"PAGE_SIZE on your system (%lu).  "
-				"This is not supported.  Sorry.",
-				vol->mft_record_size, PAGE_SIZE);
-		return false;
-	}
-	/* We cannot support mft record sizes below the sector size. */
-	if (vol->mft_record_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
-				"sector size (%i).  This is not supported.  "
-				"Sorry.", vol->mft_record_size,
-				vol->sector_size);
-		return false;
-	}
-	clusters_per_index_record = b->clusters_per_index_record;
-	ntfs_debug("clusters_per_index_record = %i (0x%x)",
-			clusters_per_index_record, clusters_per_index_record);
-	if (clusters_per_index_record > 0)
-		vol->index_record_size = vol->cluster_size <<
-				(ffs(clusters_per_index_record) - 1);
-	else
-		/*
-		 * When index_record_size < cluster_size,
-		 * clusters_per_index_record = -log2(index_record_size) bytes.
-		 * index_record_size normaly equals 4096 bytes, which is
-		 * encoded as 0xF4 (-12 in decimal).
-		 */
-		vol->index_record_size = 1 << -clusters_per_index_record;
-	vol->index_record_size_mask = vol->index_record_size - 1;
-	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;
-	ntfs_debug("vol->index_record_size = %i (0x%x)",
-			vol->index_record_size, vol->index_record_size);
-	ntfs_debug("vol->index_record_size_mask = 0x%x",
-			vol->index_record_size_mask);
-	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
-			vol->index_record_size_bits,
-			vol->index_record_size_bits);
-	/* We cannot support index record sizes below the sector size. */
-	if (vol->index_record_size < vol->sector_size) {
-		ntfs_error(vol->sb, "Index record size (%i) is smaller than "
-				"the sector size (%i).  This is not "
-				"supported.  Sorry.", vol->index_record_size,
-				vol->sector_size);
-		return false;
-	}
-	/*
-	 * Get the size of the volume in clusters and check for 64-bit-ness.
-	 * Windows currently only uses 32 bits to save the clusters so we do
-	 * the same as it is much faster on 32-bit CPUs.
-	 */
-	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;
-	if ((u64)ll >= 1ULL << 32) {
-		ntfs_error(vol->sb, "Cannot handle 64-bit clusters.  Sorry.");
-		return false;
-	}
-	vol->nr_clusters = ll;
-	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);
-	/*
-	 * On an architecture where unsigned long is 32-bits, we restrict the
-	 * volume size to 2TiB (2^41). On a 64-bit architecture, the compiler
-	 * will hopefully optimize the whole check away.
-	 */
-	if (sizeof(unsigned long) < 8) {
-		if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {
-			ntfs_error(vol->sb, "Volume size (%lluTiB) is too "
-					"large for this architecture.  "
-					"Maximum supported is 2TiB.  Sorry.",
-					(unsigned long long)ll >> (40 -
-					vol->cluster_size_bits));
-			return false;
-		}
-	}
-	ll = sle64_to_cpu(b->mft_lcn);
-	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
-				"volume.  Weird.", (unsigned long long)ll,
-				(unsigned long long)ll);
-		return false;
-	}
-	vol->mft_lcn = ll;
-	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
-	ll = sle64_to_cpu(b->mftmirr_lcn);
-	if (ll >= vol->nr_clusters) {
-		ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
-				"of volume.  Weird.", (unsigned long long)ll,
-				(unsigned long long)ll);
-		return false;
-	}
-	vol->mftmirr_lcn = ll;
-	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);
-#ifdef NTFS_RW
-	/*
-	 * Work out the size of the mft mirror in number of mft records. If the
-	 * cluster size is less than or equal to the size taken by four mft
-	 * records, the mft mirror stores the first four mft records. If the
-	 * cluster size is bigger than the size taken by four mft records, the
-	 * mft mirror contains as many mft records as will fit into one
-	 * cluster.
-	 */
-	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))
-		vol->mftmirr_size = 4;
-	else
-		vol->mftmirr_size = vol->cluster_size >>
-				vol->mft_record_size_bits;
-	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);
-#endif /* NTFS_RW */
-	vol->serial_no = le64_to_cpu(b->volume_serial_number);
-	ntfs_debug("vol->serial_no = 0x%llx",
-			(unsigned long long)vol->serial_no);
-	return true;
-}
-
-/**
- * ntfs_setup_allocators - initialize the cluster and mft allocators
- * @vol:	volume structure for which to setup the allocators
- *
- * Setup the cluster (lcn) and mft allocators to the starting values.
- */
-static void ntfs_setup_allocators(ntfs_volume *vol)
-{
-#ifdef NTFS_RW
-	LCN mft_zone_size, mft_lcn;
-#endif /* NTFS_RW */
-
-	ntfs_debug("vol->mft_zone_multiplier = 0x%x",
-			vol->mft_zone_multiplier);
-#ifdef NTFS_RW
-	/* Determine the size of the MFT zone. */
-	mft_zone_size = vol->nr_clusters;
-	switch (vol->mft_zone_multiplier) {  /* % of volume size in clusters */
-	case 4:
-		mft_zone_size >>= 1;			/* 50%   */
-		break;
-	case 3:
-		mft_zone_size = (mft_zone_size +
-				(mft_zone_size >> 1)) >> 2;	/* 37.5% */
-		break;
-	case 2:
-		mft_zone_size >>= 2;			/* 25%   */
-		break;
-	/* case 1: */
-	default:
-		mft_zone_size >>= 3;			/* 12.5% */
-		break;
-	}
-	/* Setup the mft zone. */
-	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;
-	ntfs_debug("vol->mft_zone_pos = 0x%llx",
-			(unsigned long long)vol->mft_zone_pos);
-	/*
-	 * Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs
-	 * source) and if the actual mft_lcn is in the expected place or even
-	 * further to the front of the volume, extend the mft_zone to cover the
-	 * beginning of the volume as well.  This is in order to protect the
-	 * area reserved for the mft bitmap as well within the mft_zone itself.
-	 * On non-standard volumes we do not protect it as the overhead would
-	 * be higher than the speed increase we would get by doing it.
-	 */
-	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;
-	if (mft_lcn * vol->cluster_size < 16 * 1024)
-		mft_lcn = (16 * 1024 + vol->cluster_size - 1) /
-				vol->cluster_size;
-	if (vol->mft_zone_start <= mft_lcn)
-		vol->mft_zone_start = 0;
-	ntfs_debug("vol->mft_zone_start = 0x%llx",
-			(unsigned long long)vol->mft_zone_start);
-	/*
-	 * Need to cap the mft zone on non-standard volumes so that it does
-	 * not point outside the boundaries of the volume.  We do this by
-	 * halving the zone size until we are inside the volume.
-	 */
-	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
-	while (vol->mft_zone_end >= vol->nr_clusters) {
-		mft_zone_size >>= 1;
-		vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
-	}
-	ntfs_debug("vol->mft_zone_end = 0x%llx",
-			(unsigned long long)vol->mft_zone_end);
-	/*
-	 * Set the current position within each data zone to the start of the
-	 * respective zone.
-	 */
-	vol->data1_zone_pos = vol->mft_zone_end;
-	ntfs_debug("vol->data1_zone_pos = 0x%llx",
-			(unsigned long long)vol->data1_zone_pos);
-	vol->data2_zone_pos = 0;
-	ntfs_debug("vol->data2_zone_pos = 0x%llx",
-			(unsigned long long)vol->data2_zone_pos);
-
-	/* Set the mft data allocation position to mft record 24. */
-	vol->mft_data_pos = 24;
-	ntfs_debug("vol->mft_data_pos = 0x%llx",
-			(unsigned long long)vol->mft_data_pos);
-#endif /* NTFS_RW */
-}
-
-#ifdef NTFS_RW
-
-/**
- * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume
- * @vol:	ntfs super block describing device whose mft mirror to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_mft_mirror(ntfs_volume *vol)
-{
-	struct inode *tmp_ino;
-	ntfs_inode *tmp_ni;
-
-	ntfs_debug("Entering.");
-	/* Get mft mirror inode. */
-	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		/* Caller will display error message. */
-		return false;
-	}
-	/*
-	 * Re-initialize some specifics about $MFTMirr's inode as
-	 * ntfs_read_inode() will have set up the default ones.
-	 */
-	/* Set uid and gid to root. */
-	tmp_ino->i_uid = GLOBAL_ROOT_UID;
-	tmp_ino->i_gid = GLOBAL_ROOT_GID;
-	/* Regular file.  No access for anyone. */
-	tmp_ino->i_mode = S_IFREG;
-	/* No VFS initiated operations allowed for $MFTMirr. */
-	tmp_ino->i_op = &ntfs_empty_inode_ops;
-	tmp_ino->i_fop = &ntfs_empty_file_ops;
-	/* Put in our special address space operations. */
-	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;
-	tmp_ni = NTFS_I(tmp_ino);
-	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */
-	NInoSetMstProtected(tmp_ni);
-	NInoSetSparseDisabled(tmp_ni);
-	/*
-	 * Set up our little cheat allowing us to reuse the async read io
-	 * completion handler for directories.
-	 */
-	tmp_ni->itype.index.block_size = vol->mft_record_size;
-	tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits;
-	vol->mftmirr_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * check_mft_mirror - compare contents of the mft mirror with the mft
- * @vol:	ntfs super block describing device whose mft mirror to check
- *
- * Return 'true' on success or 'false' on error.
- *
- * Note, this function also results in the mft mirror runlist being completely
- * mapped into memory.  The mft mirror write code requires this and will BUG()
- * should it find an unmapped runlist element.
- */
-static bool check_mft_mirror(ntfs_volume *vol)
-{
-	struct super_block *sb = vol->sb;
-	ntfs_inode *mirr_ni;
-	struct page *mft_page, *mirr_page;
-	u8 *kmft, *kmirr;
-	runlist_element *rl, rl2[2];
-	pgoff_t index;
-	int mrecs_per_page, i;
-
-	ntfs_debug("Entering.");
-	/* Compare contents of $MFT and $MFTMirr. */
-	mrecs_per_page = PAGE_SIZE / vol->mft_record_size;
-	BUG_ON(!mrecs_per_page);
-	BUG_ON(!vol->mftmirr_size);
-	mft_page = mirr_page = NULL;
-	kmft = kmirr = NULL;
-	index = i = 0;
-	do {
-		u32 bytes;
-
-		/* Switch pages if necessary. */
-		if (!(i % mrecs_per_page)) {
-			if (index) {
-				ntfs_unmap_page(mft_page);
-				ntfs_unmap_page(mirr_page);
-			}
-			/* Get the $MFT page. */
-			mft_page = ntfs_map_page(vol->mft_ino->i_mapping,
-					index);
-			if (IS_ERR(mft_page)) {
-				ntfs_error(sb, "Failed to read $MFT.");
-				return false;
-			}
-			kmft = page_address(mft_page);
-			/* Get the $MFTMirr page. */
-			mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,
-					index);
-			if (IS_ERR(mirr_page)) {
-				ntfs_error(sb, "Failed to read $MFTMirr.");
-				goto mft_unmap_out;
-			}
-			kmirr = page_address(mirr_page);
-			++index;
-		}
-		/* Do not check the record if it is not in use. */
-		if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) {
-			/* Make sure the record is ok. */
-			if (ntfs_is_baad_recordp((le32*)kmft)) {
-				ntfs_error(sb, "Incomplete multi sector "
-						"transfer detected in mft "
-						"record %i.", i);
-mm_unmap_out:
-				ntfs_unmap_page(mirr_page);
-mft_unmap_out:
-				ntfs_unmap_page(mft_page);
-				return false;
-			}
-		}
-		/* Do not check the mirror record if it is not in use. */
-		if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) {
-			if (ntfs_is_baad_recordp((le32*)kmirr)) {
-				ntfs_error(sb, "Incomplete multi sector "
-						"transfer detected in mft "
-						"mirror record %i.", i);
-				goto mm_unmap_out;
-			}
-		}
-		/* Get the amount of data in the current record. */
-		bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);
-		if (bytes < sizeof(MFT_RECORD_OLD) ||
-				bytes > vol->mft_record_size ||
-				ntfs_is_baad_recordp((le32*)kmft)) {
-			bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);
-			if (bytes < sizeof(MFT_RECORD_OLD) ||
-					bytes > vol->mft_record_size ||
-					ntfs_is_baad_recordp((le32*)kmirr))
-				bytes = vol->mft_record_size;
-		}
-		/* Compare the two records. */
-		if (memcmp(kmft, kmirr, bytes)) {
-			ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not "
-					"match.  Run ntfsfix or chkdsk.", i);
-			goto mm_unmap_out;
-		}
-		kmft += vol->mft_record_size;
-		kmirr += vol->mft_record_size;
-	} while (++i < vol->mftmirr_size);
-	/* Release the last pages. */
-	ntfs_unmap_page(mft_page);
-	ntfs_unmap_page(mirr_page);
-
-	/* Construct the mft mirror runlist by hand. */
-	rl2[0].vcn = 0;
-	rl2[0].lcn = vol->mftmirr_lcn;
-	rl2[0].length = (vol->mftmirr_size * vol->mft_record_size +
-			vol->cluster_size - 1) / vol->cluster_size;
-	rl2[1].vcn = rl2[0].length;
-	rl2[1].lcn = LCN_ENOENT;
-	rl2[1].length = 0;
-	/*
-	 * Because we have just read all of the mft mirror, we know we have
-	 * mapped the full runlist for it.
-	 */
-	mirr_ni = NTFS_I(vol->mftmirr_ino);
-	down_read(&mirr_ni->runlist.lock);
-	rl = mirr_ni->runlist.rl;
-	/* Compare the two runlists.  They must be identical. */
-	i = 0;
-	do {
-		if (rl2[i].vcn != rl[i].vcn || rl2[i].lcn != rl[i].lcn ||
-				rl2[i].length != rl[i].length) {
-			ntfs_error(sb, "$MFTMirr location mismatch.  "
-					"Run chkdsk.");
-			up_read(&mirr_ni->runlist.lock);
-			return false;
-		}
-	} while (rl2[i++].length);
-	up_read(&mirr_ni->runlist.lock);
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_check_logfile - load and check the logfile inode for a volume
- * @vol:	ntfs super block describing device whose logfile to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_check_logfile(ntfs_volume *vol,
-		RESTART_PAGE_HEADER **rp)
-{
-	struct inode *tmp_ino;
-
-	ntfs_debug("Entering.");
-	tmp_ino = ntfs_iget(vol->sb, FILE_LogFile);
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		/* Caller will display error message. */
-		return false;
-	}
-	if (!ntfs_check_logfile(tmp_ino, rp)) {
-		iput(tmp_ino);
-		/* ntfs_check_logfile() will have displayed error output. */
-		return false;
-	}
-	NInoSetSparseDisabled(NTFS_I(tmp_ino));
-	vol->logfile_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-#define NTFS_HIBERFIL_HEADER_SIZE	4096
-
-/**
- * check_windows_hibernation_status - check if Windows is suspended on a volume
- * @vol:	ntfs super block of device to check
- *
- * Check if Windows is hibernated on the ntfs volume @vol.  This is done by
- * looking for the file hiberfil.sys in the root directory of the volume.  If
- * the file is not present Windows is definitely not suspended.
- *
- * If hiberfil.sys exists and is less than 4kiB in size it means Windows is
- * definitely suspended (this volume is not the system volume).  Caveat:  on a
- * system with many volumes it is possible that the < 4kiB check is bogus but
- * for now this should do fine.
- *
- * If hiberfil.sys exists and is larger than 4kiB in size, we need to read the
- * hiberfil header (which is the first 4kiB).  If this begins with "hibr",
- * Windows is definitely suspended.  If it is completely full of zeroes,
- * Windows is definitely not hibernated.  Any other case is treated as if
- * Windows is suspended.  This caters for the above mentioned caveat of a
- * system with many volumes where no "hibr" magic would be present and there is
- * no zero header.
- *
- * Return 0 if Windows is not hibernated on the volume, >0 if Windows is
- * hibernated on the volume, and -errno on error.
- */
-static int check_windows_hibernation_status(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *vi;
-	struct page *page;
-	u32 *kaddr, *kend;
-	ntfs_name *name = NULL;
-	int ret = 1;
-	static const ntfschar hiberfil[13] = { cpu_to_le16('h'),
-			cpu_to_le16('i'), cpu_to_le16('b'),
-			cpu_to_le16('e'), cpu_to_le16('r'),
-			cpu_to_le16('f'), cpu_to_le16('i'),
-			cpu_to_le16('l'), cpu_to_le16('.'),
-			cpu_to_le16('s'), cpu_to_le16('y'),
-			cpu_to_le16('s'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the hibernation file by looking up the
-	 * filename hiberfil.sys in the root directory.
-	 */
-	inode_lock(vol->root_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,
-			&name);
-	inode_unlock(vol->root_ino);
-	if (IS_ERR_MREF(mref)) {
-		ret = MREF_ERR(mref);
-		/* If the file does not exist, Windows is not hibernated. */
-		if (ret == -ENOENT) {
-			ntfs_debug("hiberfil.sys not present.  Windows is not "
-					"hibernated on the volume.");
-			return 0;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for "
-				"hiberfil.sys.");
-		return ret;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	vi = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(vi) || is_bad_inode(vi)) {
-		if (!IS_ERR(vi))
-			iput(vi);
-		ntfs_error(vol->sb, "Failed to load hiberfil.sys.");
-		return IS_ERR(vi) ? PTR_ERR(vi) : -EIO;
-	}
-	if (unlikely(i_size_read(vi) < NTFS_HIBERFIL_HEADER_SIZE)) {
-		ntfs_debug("hiberfil.sys is smaller than 4kiB (0x%llx).  "
-				"Windows is hibernated on the volume.  This "
-				"is not the system volume.", i_size_read(vi));
-		goto iput_out;
-	}
-	page = ntfs_map_page(vi->i_mapping, 0);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");
-		ret = PTR_ERR(page);
-		goto iput_out;
-	}
-	kaddr = (u32*)page_address(page);
-	if (*(le32*)kaddr == cpu_to_le32(0x72626968)/*'hibr'*/) {
-		ntfs_debug("Magic \"hibr\" found in hiberfil.sys.  Windows is "
-				"hibernated on the volume.  This is the "
-				"system volume.");
-		goto unm_iput_out;
-	}
-	kend = kaddr + NTFS_HIBERFIL_HEADER_SIZE/sizeof(*kaddr);
-	do {
-		if (unlikely(*kaddr)) {
-			ntfs_debug("hiberfil.sys is larger than 4kiB "
-					"(0x%llx), does not contain the "
-					"\"hibr\" magic, and does not have a "
-					"zero header.  Windows is hibernated "
-					"on the volume.  This is not the "
-					"system volume.", i_size_read(vi));
-			goto unm_iput_out;
-		}
-	} while (++kaddr < kend);
-	ntfs_debug("hiberfil.sys contains a zero header.  Windows is not "
-			"hibernated on the volume.  This is the system "
-			"volume.");
-	ret = 0;
-unm_iput_out:
-	ntfs_unmap_page(page);
-iput_out:
-	iput(vi);
-	return ret;
-}
-
-/**
- * load_and_init_quota - load and setup the quota file for a volume if present
- * @vol:	ntfs super block describing device whose quota file to load
- *
- * Return 'true' on success or 'false' on error.  If $Quota is not present, we
- * leave vol->quota_ino as NULL and return success.
- */
-static bool load_and_init_quota(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *tmp_ino;
-	ntfs_name *name = NULL;
-	static const ntfschar Quota[7] = { cpu_to_le16('$'),
-			cpu_to_le16('Q'), cpu_to_le16('u'),
-			cpu_to_le16('o'), cpu_to_le16('t'),
-			cpu_to_le16('a'), 0 };
-	static ntfschar Q[3] = { cpu_to_le16('$'),
-			cpu_to_le16('Q'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the quota file by looking up the filename
-	 * $Quota in the extended system files directory $Extend.
-	 */
-	inode_lock(vol->extend_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
-			&name);
-	inode_unlock(vol->extend_ino);
-	if (IS_ERR_MREF(mref)) {
-		/*
-		 * If the file does not exist, quotas are disabled and have
-		 * never been enabled on this volume, just return success.
-		 */
-		if (MREF_ERR(mref) == -ENOENT) {
-			ntfs_debug("$Quota not present.  Volume does not have "
-					"quotas enabled.");
-			/*
-			 * No need to try to set quotas out of date if they are
-			 * not enabled.
-			 */
-			NVolSetQuotaOutOfDate(vol);
-			return true;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for $Quota.");
-		return false;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		ntfs_error(vol->sb, "Failed to load $Quota.");
-		return false;
-	}
-	vol->quota_ino = tmp_ino;
-	/* Get the $Q index allocation attribute. */
-	tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $Quota/$Q index.");
-		return false;
-	}
-	vol->quota_q_ino = tmp_ino;
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_init_usnjrnl - load and setup the transaction log if present
- * @vol:	ntfs super block describing device whose usnjrnl file to load
- *
- * Return 'true' on success or 'false' on error.
- *
- * If $UsnJrnl is not present or in the process of being disabled, we set
- * NVolUsnJrnlStamped() and return success.
- *
- * If the $UsnJrnl $DATA/$J attribute has a size equal to the lowest valid usn,
- * i.e. transaction logging has only just been enabled or the journal has been
- * stamped and nothing has been logged since, we also set NVolUsnJrnlStamped()
- * and return success.
- */
-static bool load_and_init_usnjrnl(ntfs_volume *vol)
-{
-	MFT_REF mref;
-	struct inode *tmp_ino;
-	ntfs_inode *tmp_ni;
-	struct page *page;
-	ntfs_name *name = NULL;
-	USN_HEADER *uh;
-	static const ntfschar UsnJrnl[9] = { cpu_to_le16('$'),
-			cpu_to_le16('U'), cpu_to_le16('s'),
-			cpu_to_le16('n'), cpu_to_le16('J'),
-			cpu_to_le16('r'), cpu_to_le16('n'),
-			cpu_to_le16('l'), 0 };
-	static ntfschar Max[5] = { cpu_to_le16('$'),
-			cpu_to_le16('M'), cpu_to_le16('a'),
-			cpu_to_le16('x'), 0 };
-	static ntfschar J[3] = { cpu_to_le16('$'),
-			cpu_to_le16('J'), 0 };
-
-	ntfs_debug("Entering.");
-	/*
-	 * Find the inode number for the transaction log file by looking up the
-	 * filename $UsnJrnl in the extended system files directory $Extend.
-	 */
-	inode_lock(vol->extend_ino);
-	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,
-			&name);
-	inode_unlock(vol->extend_ino);
-	if (IS_ERR_MREF(mref)) {
-		/*
-		 * If the file does not exist, transaction logging is disabled,
-		 * just return success.
-		 */
-		if (MREF_ERR(mref) == -ENOENT) {
-			ntfs_debug("$UsnJrnl not present.  Volume does not "
-					"have transaction logging enabled.");
-not_enabled:
-			/*
-			 * No need to try to stamp the transaction log if
-			 * transaction logging is not enabled.
-			 */
-			NVolSetUsnJrnlStamped(vol);
-			return true;
-		}
-		/* A real error occurred. */
-		ntfs_error(vol->sb, "Failed to find inode number for "
-				"$UsnJrnl.");
-		return false;
-	}
-	/* We do not care for the type of match that was found. */
-	kfree(name);
-	/* Get the inode. */
-	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
-	if (IS_ERR(tmp_ino) || unlikely(is_bad_inode(tmp_ino))) {
-		if (!IS_ERR(tmp_ino))
-			iput(tmp_ino);
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl.");
-		return false;
-	}
-	vol->usnjrnl_ino = tmp_ino;
-	/*
-	 * If the transaction log is in the process of being deleted, we can
-	 * ignore it.
-	 */
-	if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) {
-		ntfs_debug("$UsnJrnl in the process of being disabled.  "
-				"Volume does not have transaction logging "
-				"enabled.");
-		goto not_enabled;
-	}
-	/* Get the $DATA/$Max attribute. */
-	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, Max, 4);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max "
-				"attribute.");
-		return false;
-	}
-	vol->usnjrnl_max_ino = tmp_ino;
-	if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {
-		ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "
-				"attribute (size is 0x%llx but should be at "
-				"least 0x%zx bytes).", i_size_read(tmp_ino),
-				sizeof(USN_HEADER));
-		return false;
-	}
-	/* Get the $DATA/$J attribute. */
-	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2);
-	if (IS_ERR(tmp_ino)) {
-		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J "
-				"attribute.");
-		return false;
-	}
-	vol->usnjrnl_j_ino = tmp_ino;
-	/* Verify $J is non-resident and sparse. */
-	tmp_ni = NTFS_I(vol->usnjrnl_j_ino);
-	if (unlikely(!NInoNonResident(tmp_ni) || !NInoSparse(tmp_ni))) {
-		ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident "
-				"and/or not sparse.");
-		return false;
-	}
-	/* Read the USN_HEADER from $DATA/$Max. */
-	page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
-	if (IS_ERR(page)) {
-		ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max "
-				"attribute.");
-		return false;
-	}
-	uh = (USN_HEADER*)page_address(page);
-	/* Sanity check the $Max. */
-	if (unlikely(sle64_to_cpu(uh->allocation_delta) >
-			sle64_to_cpu(uh->maximum_size))) {
-		ntfs_error(vol->sb, "Allocation delta (0x%llx) exceeds "
-				"maximum size (0x%llx).  $UsnJrnl is corrupt.",
-				(long long)sle64_to_cpu(uh->allocation_delta),
-				(long long)sle64_to_cpu(uh->maximum_size));
-		ntfs_unmap_page(page);
-		return false;
-	}
-	/*
-	 * If the transaction log has been stamped and nothing has been written
-	 * to it since, we do not need to stamp it.
-	 */
-	if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >=
-			i_size_read(vol->usnjrnl_j_ino))) {
-		if (likely(sle64_to_cpu(uh->lowest_valid_usn) ==
-				i_size_read(vol->usnjrnl_j_ino))) {
-			ntfs_unmap_page(page);
-			ntfs_debug("$UsnJrnl is enabled but nothing has been "
-					"logged since it was last stamped.  "
-					"Treating this as if the volume does "
-					"not have transaction logging "
-					"enabled.");
-			goto not_enabled;
-		}
-		ntfs_error(vol->sb, "$UsnJrnl has lowest valid usn (0x%llx) "
-				"which is out of bounds (0x%llx).  $UsnJrnl "
-				"is corrupt.",
-				(long long)sle64_to_cpu(uh->lowest_valid_usn),
-				i_size_read(vol->usnjrnl_j_ino));
-		ntfs_unmap_page(page);
-		return false;
-	}
-	ntfs_unmap_page(page);
-	ntfs_debug("Done.");
-	return true;
-}
-
-/**
- * load_and_init_attrdef - load the attribute definitions table for a volume
- * @vol:	ntfs super block describing device whose attrdef to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_attrdef(ntfs_volume *vol)
-{
-	loff_t i_size;
-	struct super_block *sb = vol->sb;
-	struct inode *ino;
-	struct page *page;
-	pgoff_t index, max_index;
-	unsigned int size;
-
-	ntfs_debug("Entering.");
-	/* Read attrdef table and setup vol->attrdef and vol->attrdef_size. */
-	ino = ntfs_iget(sb, FILE_AttrDef);
-	if (IS_ERR(ino) || is_bad_inode(ino)) {
-		if (!IS_ERR(ino))
-			iput(ino);
-		goto failed;
-	}
-	NInoSetSparseDisabled(NTFS_I(ino));
-	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */
-	i_size = i_size_read(ino);
-	if (i_size <= 0 || i_size > 0x7fffffff)
-		goto iput_failed;
-	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);
-	if (!vol->attrdef)
-		goto iput_failed;
-	index = 0;
-	max_index = i_size >> PAGE_SHIFT;
-	size = PAGE_SIZE;
-	while (index < max_index) {
-		/* Read the attrdef table and copy it into the linear buffer. */
-read_partial_attrdef_page:
-		page = ntfs_map_page(ino->i_mapping, index);
-		if (IS_ERR(page))
-			goto free_iput_failed;
-		memcpy((u8*)vol->attrdef + (index++ << PAGE_SHIFT),
-				page_address(page), size);
-		ntfs_unmap_page(page);
-	}
-	if (size == PAGE_SIZE) {
-		size = i_size & ~PAGE_MASK;
-		if (size)
-			goto read_partial_attrdef_page;
-	}
-	vol->attrdef_size = i_size;
-	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);
-	iput(ino);
-	return true;
-free_iput_failed:
-	ntfs_free(vol->attrdef);
-	vol->attrdef = NULL;
-iput_failed:
-	iput(ino);
-failed:
-	ntfs_error(sb, "Failed to initialize attribute definition table.");
-	return false;
-}
-
-#endif /* NTFS_RW */
-
-/**
- * load_and_init_upcase - load the upcase table for an ntfs volume
- * @vol:	ntfs super block describing device whose upcase to load
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_and_init_upcase(ntfs_volume *vol)
-{
-	loff_t i_size;
-	struct super_block *sb = vol->sb;
-	struct inode *ino;
-	struct page *page;
-	pgoff_t index, max_index;
-	unsigned int size;
-	int i, max;
-
-	ntfs_debug("Entering.");
-	/* Read upcase table and setup vol->upcase and vol->upcase_len. */
-	ino = ntfs_iget(sb, FILE_UpCase);
-	if (IS_ERR(ino) || is_bad_inode(ino)) {
-		if (!IS_ERR(ino))
-			iput(ino);
-		goto upcase_failed;
-	}
-	/*
-	 * The upcase size must not be above 64k Unicode characters, must not
-	 * be zero and must be a multiple of sizeof(ntfschar).
-	 */
-	i_size = i_size_read(ino);
-	if (!i_size || i_size & (sizeof(ntfschar) - 1) ||
-			i_size > 64ULL * 1024 * sizeof(ntfschar))
-		goto iput_upcase_failed;
-	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);
-	if (!vol->upcase)
-		goto iput_upcase_failed;
-	index = 0;
-	max_index = i_size >> PAGE_SHIFT;
-	size = PAGE_SIZE;
-	while (index < max_index) {
-		/* Read the upcase table and copy it into the linear buffer. */
-read_partial_upcase_page:
-		page = ntfs_map_page(ino->i_mapping, index);
-		if (IS_ERR(page))
-			goto iput_upcase_failed;
-		memcpy((char*)vol->upcase + (index++ << PAGE_SHIFT),
-				page_address(page), size);
-		ntfs_unmap_page(page);
-	}
-	if (size == PAGE_SIZE) {
-		size = i_size & ~PAGE_MASK;
-		if (size)
-			goto read_partial_upcase_page;
-	}
-	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;
-	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",
-			i_size, 64 * 1024 * sizeof(ntfschar));
-	iput(ino);
-	mutex_lock(&ntfs_lock);
-	if (!default_upcase) {
-		ntfs_debug("Using volume specified $UpCase since default is "
-				"not present.");
-		mutex_unlock(&ntfs_lock);
-		return true;
-	}
-	max = default_upcase_len;
-	if (max > vol->upcase_len)
-		max = vol->upcase_len;
-	for (i = 0; i < max; i++)
-		if (vol->upcase[i] != default_upcase[i])
-			break;
-	if (i == max) {
-		ntfs_free(vol->upcase);
-		vol->upcase = default_upcase;
-		vol->upcase_len = max;
-		ntfs_nr_upcase_users++;
-		mutex_unlock(&ntfs_lock);
-		ntfs_debug("Volume specified $UpCase matches default. Using "
-				"default.");
-		return true;
-	}
-	mutex_unlock(&ntfs_lock);
-	ntfs_debug("Using volume specified $UpCase since it does not match "
-			"the default.");
-	return true;
-iput_upcase_failed:
-	iput(ino);
-	ntfs_free(vol->upcase);
-	vol->upcase = NULL;
-upcase_failed:
-	mutex_lock(&ntfs_lock);
-	if (default_upcase) {
-		vol->upcase = default_upcase;
-		vol->upcase_len = default_upcase_len;
-		ntfs_nr_upcase_users++;
-		mutex_unlock(&ntfs_lock);
-		ntfs_error(sb, "Failed to load $UpCase from the volume. Using "
-				"default.");
-		return true;
-	}
-	mutex_unlock(&ntfs_lock);
-	ntfs_error(sb, "Failed to initialize upcase table.");
-	return false;
-}
-
-/*
- * The lcn and mft bitmap inodes are NTFS-internal inodes with
- * their own special locking rules:
- */
-static struct lock_class_key
-	lcnbmp_runlist_lock_key, lcnbmp_mrec_lock_key,
-	mftbmp_runlist_lock_key, mftbmp_mrec_lock_key;
-
-/**
- * load_system_files - open the system files using normal functions
- * @vol:	ntfs super block describing device whose system files to load
- *
- * Open the system files with normal access functions and complete setting up
- * the ntfs super block @vol.
- *
- * Return 'true' on success or 'false' on error.
- */
-static bool load_system_files(ntfs_volume *vol)
-{
-	struct super_block *sb = vol->sb;
-	MFT_RECORD *m;
-	VOLUME_INFORMATION *vi;
-	ntfs_attr_search_ctx *ctx;
-#ifdef NTFS_RW
-	RESTART_PAGE_HEADER *rp;
-	int err;
-#endif /* NTFS_RW */
-
-	ntfs_debug("Entering.");
-#ifdef NTFS_RW
-	/* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */
-	if (!load_and_init_mft_mirror(vol) || !check_mft_mirror(vol)) {
-		static const char *es1 = "Failed to load $MFTMirr";
-		static const char *es2 = "$MFTMirr does not match $MFT";
-		static const char *es3 = ".  Run ntfsfix and/or chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						!vol->mftmirr_ino ? es1 : es2,
-						es3);
-				goto iput_mirr_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s",
-					!vol->mftmirr_ino ? es1 : es2, es3);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s",
-					!vol->mftmirr_ino ? es1 : es2, es3);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	/* Get mft bitmap attribute inode. */
-	vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0);
-	if (IS_ERR(vol->mftbmp_ino)) {
-		ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute.");
-		goto iput_mirr_err_out;
-	}
-	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->runlist.lock,
-			   &mftbmp_runlist_lock_key);
-	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->mrec_lock,
-			   &mftbmp_mrec_lock_key);
-	/* Read upcase table and setup @vol->upcase and @vol->upcase_len. */
-	if (!load_and_init_upcase(vol))
-		goto iput_mftbmp_err_out;
-#ifdef NTFS_RW
-	/*
-	 * Read attribute definitions table and setup @vol->attrdef and
-	 * @vol->attrdef_size.
-	 */
-	if (!load_and_init_attrdef(vol))
-		goto iput_upcase_err_out;
-#endif /* NTFS_RW */
-	/*
-	 * Get the cluster allocation bitmap inode and verify the size, no
-	 * need for any locking at this stage as we are already running
-	 * exclusively as we are mount in progress task.
-	 */
-	vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap);
-	if (IS_ERR(vol->lcnbmp_ino) || is_bad_inode(vol->lcnbmp_ino)) {
-		if (!IS_ERR(vol->lcnbmp_ino))
-			iput(vol->lcnbmp_ino);
-		goto bitmap_failed;
-	}
-	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->runlist.lock,
-			   &lcnbmp_runlist_lock_key);
-	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->mrec_lock,
-			   &lcnbmp_mrec_lock_key);
-
-	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));
-	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {
-		iput(vol->lcnbmp_ino);
-bitmap_failed:
-		ntfs_error(sb, "Failed to load $Bitmap.");
-		goto iput_attrdef_err_out;
-	}
-	/*
-	 * Get the volume inode and setup our cache of the volume flags and
-	 * version.
-	 */
-	vol->vol_ino = ntfs_iget(sb, FILE_Volume);
-	if (IS_ERR(vol->vol_ino) || is_bad_inode(vol->vol_ino)) {
-		if (!IS_ERR(vol->vol_ino))
-			iput(vol->vol_ino);
-volume_failed:
-		ntfs_error(sb, "Failed to load $Volume.");
-		goto iput_lcnbmp_err_out;
-	}
-	m = map_mft_record(NTFS_I(vol->vol_ino));
-	if (IS_ERR(m)) {
-iput_volume_failed:
-		iput(vol->vol_ino);
-		goto volume_failed;
-	}
-	if (!(ctx = ntfs_attr_get_search_ctx(NTFS_I(vol->vol_ino), m))) {
-		ntfs_error(sb, "Failed to get attribute search context.");
-		goto get_ctx_vol_failed;
-	}
-	if (ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
-			ctx) || ctx->attr->non_resident || ctx->attr->flags) {
-err_put_vol:
-		ntfs_attr_put_search_ctx(ctx);
-get_ctx_vol_failed:
-		unmap_mft_record(NTFS_I(vol->vol_ino));
-		goto iput_volume_failed;
-	}
-	vi = (VOLUME_INFORMATION*)((char*)ctx->attr +
-			le16_to_cpu(ctx->attr->data.resident.value_offset));
-	/* Some bounds checks. */
-	if ((u8*)vi < (u8*)ctx->attr || (u8*)vi +
-			le32_to_cpu(ctx->attr->data.resident.value_length) >
-			(u8*)ctx->attr + le32_to_cpu(ctx->attr->length))
-		goto err_put_vol;
-	/* Copy the volume flags and version to the ntfs_volume structure. */
-	vol->vol_flags = vi->flags;
-	vol->major_ver = vi->major_ver;
-	vol->minor_ver = vi->minor_ver;
-	ntfs_attr_put_search_ctx(ctx);
-	unmap_mft_record(NTFS_I(vol->vol_ino));
-	pr_info("volume version %i.%i.\n", vol->major_ver,
-			vol->minor_ver);
-	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {
-		ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "
-				"volume version %i.%i (need at least version "
-				"3.0).", vol->major_ver, vol->minor_ver);
-		NVolClearSparseEnabled(vol);
-	}
-#ifdef NTFS_RW
-	/* Make sure that no unsupported volume flags are set. */
-	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
-		static const char *es1a = "Volume is dirty";
-		static const char *es1b = "Volume has been modified by chkdsk";
-		static const char *es1c = "Volume has unsupported flags set";
-		static const char *es2a = ".  Run chkdsk and mount in Windows.";
-		static const char *es2b = ".  Mount in Windows.";
-		const char *es1, *es2;
-
-		es2 = es2a;
-		if (vol->vol_flags & VOLUME_IS_DIRTY)
-			es1 = es1a;
-		else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
-			es1 = es1b;
-			es2 = es2b;
-		} else {
-			es1 = es1c;
-			ntfs_warning(sb, "Unsupported volume flags 0x%x "
-					"encountered.",
-					(unsigned)le16_to_cpu(vol->vol_flags));
-		}
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_vol_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/*
-		 * Do not set NVolErrors() because ntfs_remount() re-checks the
-		 * flags which we need to do in case any flags have changed.
-		 */
-	}
-	/*
-	 * Get the inode for the logfile, check it and determine if the volume
-	 * was shutdown cleanly.
-	 */
-	rp = NULL;
-	if (!load_and_check_logfile(vol, &rp) ||
-			!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {
-		static const char *es1a = "Failed to load $LogFile";
-		static const char *es1b = "$LogFile is not clean";
-		static const char *es2 = ".  Mount in Windows.";
-		const char *es1;
-
-		es1 = !vol->logfile_ino ? es1a : es1b;
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				if (vol->logfile_ino) {
-					BUG_ON(!rp);
-					ntfs_free(rp);
-				}
-				goto iput_logfile_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	ntfs_free(rp);
-#endif /* NTFS_RW */
-	/* Get the root directory inode so we can do path lookups. */
-	vol->root_ino = ntfs_iget(sb, FILE_root);
-	if (IS_ERR(vol->root_ino) || is_bad_inode(vol->root_ino)) {
-		if (!IS_ERR(vol->root_ino))
-			iput(vol->root_ino);
-		ntfs_error(sb, "Failed to load root directory.");
-		goto iput_logfile_err_out;
-	}
-#ifdef NTFS_RW
-	/*
-	 * Check if Windows is suspended to disk on the target volume.  If it
-	 * is hibernated, we must not write *anything* to the disk so set
-	 * NVolErrors() without setting the dirty volume flag and mount
-	 * read-only.  This will prevent read-write remounting and it will also
-	 * prevent all writes.
-	 */
-	err = check_windows_hibernation_status(vol);
-	if (unlikely(err)) {
-		static const char *es1a = "Failed to determine if Windows is "
-				"hibernated";
-		static const char *es1b = "Windows is hibernated";
-		static const char *es2 = ".  Run chkdsk.";
-		const char *es1;
-
-		es1 = err < 0 ? es1a : es1b;
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_root_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, mark the volume dirty. */
-	if (!sb_rdonly(sb) && ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
-		static const char *es1 = "Failed to set dirty bit in volume "
-				"information flags";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		/*
-		 * Do not set NVolErrors() because ntfs_remount() might manage
-		 * to set the dirty flag in which case all would be well.
-		 */
-	}
-#if 0
-	// TODO: Enable this code once we start modifying anything that is
-	//	 different between NTFS 1.2 and 3.x...
-	/*
-	 * If (still) a read-write mount, set the NT4 compatibility flag on
-	 * newer NTFS version volumes.
-	 */
-	if (!(sb->s_flags & SB_RDONLY) && (vol->major_ver > 1) &&
-			ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
-		static const char *es1 = "Failed to set NT4 compatibility flag";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif
-	/* If (still) a read-write mount, empty the logfile. */
-	if (!sb_rdonly(sb) && !ntfs_empty_logfile(vol->logfile_ino)) {
-		static const char *es1 = "Failed to empty $LogFile";
-		static const char *es2 = ".  Mount in Windows.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_root_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	/* If on NTFS versions before 3.0, we are done. */
-	if (unlikely(vol->major_ver < 3))
-		return true;
-	/* NTFS 3.0+ specific initialization. */
-	/* Get the security descriptors inode. */
-	vol->secure_ino = ntfs_iget(sb, FILE_Secure);
-	if (IS_ERR(vol->secure_ino) || is_bad_inode(vol->secure_ino)) {
-		if (!IS_ERR(vol->secure_ino))
-			iput(vol->secure_ino);
-		ntfs_error(sb, "Failed to load $Secure.");
-		goto iput_root_err_out;
-	}
-	// TODO: Initialize security.
-	/* Get the extended system files' directory inode. */
-	vol->extend_ino = ntfs_iget(sb, FILE_Extend);
-	if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino) ||
-	    !S_ISDIR(vol->extend_ino->i_mode)) {
-		if (!IS_ERR(vol->extend_ino))
-			iput(vol->extend_ino);
-		ntfs_error(sb, "Failed to load $Extend.");
-		goto iput_sec_err_out;
-	}
-#ifdef NTFS_RW
-	/* Find the quota file, load it if present, and set it up. */
-	if (!load_and_init_quota(vol)) {
-		static const char *es1 = "Failed to load $Quota";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_quota_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, mark the quotas out of date. */
-	if (!sb_rdonly(sb) && !ntfs_mark_quotas_out_of_date(vol)) {
-		static const char *es1 = "Failed to mark quotas out of date";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_quota_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-	/*
-	 * Find the transaction log file ($UsnJrnl), load it if present, check
-	 * it, and set it up.
-	 */
-	if (!load_and_init_usnjrnl(vol)) {
-		static const char *es1 = "Failed to load $UsnJrnl";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* If a read-write mount, convert it to a read-only mount. */
-		if (!sb_rdonly(sb)) {
-			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-					ON_ERRORS_CONTINUE))) {
-				ntfs_error(sb, "%s and neither on_errors="
-						"continue nor on_errors="
-						"remount-ro was specified%s",
-						es1, es2);
-				goto iput_usnjrnl_err_out;
-			}
-			sb->s_flags |= SB_RDONLY;
-			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		} else
-			ntfs_warning(sb, "%s.  Will not be able to remount "
-					"read-write%s", es1, es2);
-		/* This will prevent a read-write remount. */
-		NVolSetErrors(vol);
-	}
-	/* If (still) a read-write mount, stamp the transaction log. */
-	if (!sb_rdonly(sb) && !ntfs_stamp_usnjrnl(vol)) {
-		static const char *es1 = "Failed to stamp transaction log "
-				"($UsnJrnl)";
-		static const char *es2 = ".  Run chkdsk.";
-
-		/* Convert to a read-only mount. */
-		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
-				ON_ERRORS_CONTINUE))) {
-			ntfs_error(sb, "%s and neither on_errors=continue nor "
-					"on_errors=remount-ro was specified%s",
-					es1, es2);
-			goto iput_usnjrnl_err_out;
-		}
-		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
-		sb->s_flags |= SB_RDONLY;
-		NVolSetErrors(vol);
-	}
-#endif /* NTFS_RW */
-	return true;
-#ifdef NTFS_RW
-iput_usnjrnl_err_out:
-	iput(vol->usnjrnl_j_ino);
-	iput(vol->usnjrnl_max_ino);
-	iput(vol->usnjrnl_ino);
-iput_quota_err_out:
-	iput(vol->quota_q_ino);
-	iput(vol->quota_ino);
-	iput(vol->extend_ino);
-#endif /* NTFS_RW */
-iput_sec_err_out:
-	iput(vol->secure_ino);
-iput_root_err_out:
-	iput(vol->root_ino);
-iput_logfile_err_out:
-#ifdef NTFS_RW
-	iput(vol->logfile_ino);
-iput_vol_err_out:
-#endif /* NTFS_RW */
-	iput(vol->vol_ino);
-iput_lcnbmp_err_out:
-	iput(vol->lcnbmp_ino);
-iput_attrdef_err_out:
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-#ifdef NTFS_RW
-iput_upcase_err_out:
-#endif /* NTFS_RW */
-	vol->upcase_len = 0;
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-iput_mftbmp_err_out:
-	iput(vol->mftbmp_ino);
-iput_mirr_err_out:
-#ifdef NTFS_RW
-	iput(vol->mftmirr_ino);
-#endif /* NTFS_RW */
-	return false;
-}
-
-/**
- * ntfs_put_super - called by the vfs to unmount a volume
- * @sb:		vfs superblock of volume to unmount
- *
- * ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when
- * the volume is being unmounted (umount system call has been invoked) and it
- * releases all inodes and memory belonging to the NTFS specific part of the
- * super block.
- */
-static void ntfs_put_super(struct super_block *sb)
-{
-	ntfs_volume *vol = NTFS_SB(sb);
-
-	ntfs_debug("Entering.");
-
-#ifdef NTFS_RW
-	/*
-	 * Commit all inodes while they are still open in case some of them
-	 * cause others to be dirtied.
-	 */
-	ntfs_commit_inode(vol->vol_ino);
-
-	/* NTFS 3.0+ specific. */
-	if (vol->major_ver >= 3) {
-		if (vol->usnjrnl_j_ino)
-			ntfs_commit_inode(vol->usnjrnl_j_ino);
-		if (vol->usnjrnl_max_ino)
-			ntfs_commit_inode(vol->usnjrnl_max_ino);
-		if (vol->usnjrnl_ino)
-			ntfs_commit_inode(vol->usnjrnl_ino);
-		if (vol->quota_q_ino)
-			ntfs_commit_inode(vol->quota_q_ino);
-		if (vol->quota_ino)
-			ntfs_commit_inode(vol->quota_ino);
-		if (vol->extend_ino)
-			ntfs_commit_inode(vol->extend_ino);
-		if (vol->secure_ino)
-			ntfs_commit_inode(vol->secure_ino);
-	}
-
-	ntfs_commit_inode(vol->root_ino);
-
-	down_write(&vol->lcnbmp_lock);
-	ntfs_commit_inode(vol->lcnbmp_ino);
-	up_write(&vol->lcnbmp_lock);
-
-	down_write(&vol->mftbmp_lock);
-	ntfs_commit_inode(vol->mftbmp_ino);
-	up_write(&vol->mftbmp_lock);
-
-	if (vol->logfile_ino)
-		ntfs_commit_inode(vol->logfile_ino);
-
-	if (vol->mftmirr_ino)
-		ntfs_commit_inode(vol->mftmirr_ino);
-	ntfs_commit_inode(vol->mft_ino);
-
-	/*
-	 * If a read-write mount and no volume errors have occurred, mark the
-	 * volume clean.  Also, re-commit all affected inodes.
-	 */
-	if (!sb_rdonly(sb)) {
-		if (!NVolErrors(vol)) {
-			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
-				ntfs_warning(sb, "Failed to clear dirty bit "
-						"in volume information "
-						"flags.  Run chkdsk.");
-			ntfs_commit_inode(vol->vol_ino);
-			ntfs_commit_inode(vol->root_ino);
-			if (vol->mftmirr_ino)
-				ntfs_commit_inode(vol->mftmirr_ino);
-			ntfs_commit_inode(vol->mft_ino);
-		} else {
-			ntfs_warning(sb, "Volume has errors.  Leaving volume "
-					"marked dirty.  Run chkdsk.");
-		}
-	}
-#endif /* NTFS_RW */
-
-	iput(vol->vol_ino);
-	vol->vol_ino = NULL;
-
-	/* NTFS 3.0+ specific clean up. */
-	if (vol->major_ver >= 3) {
-#ifdef NTFS_RW
-		if (vol->usnjrnl_j_ino) {
-			iput(vol->usnjrnl_j_ino);
-			vol->usnjrnl_j_ino = NULL;
-		}
-		if (vol->usnjrnl_max_ino) {
-			iput(vol->usnjrnl_max_ino);
-			vol->usnjrnl_max_ino = NULL;
-		}
-		if (vol->usnjrnl_ino) {
-			iput(vol->usnjrnl_ino);
-			vol->usnjrnl_ino = NULL;
-		}
-		if (vol->quota_q_ino) {
-			iput(vol->quota_q_ino);
-			vol->quota_q_ino = NULL;
-		}
-		if (vol->quota_ino) {
-			iput(vol->quota_ino);
-			vol->quota_ino = NULL;
-		}
-#endif /* NTFS_RW */
-		if (vol->extend_ino) {
-			iput(vol->extend_ino);
-			vol->extend_ino = NULL;
-		}
-		if (vol->secure_ino) {
-			iput(vol->secure_ino);
-			vol->secure_ino = NULL;
-		}
-	}
-
-	iput(vol->root_ino);
-	vol->root_ino = NULL;
-
-	down_write(&vol->lcnbmp_lock);
-	iput(vol->lcnbmp_ino);
-	vol->lcnbmp_ino = NULL;
-	up_write(&vol->lcnbmp_lock);
-
-	down_write(&vol->mftbmp_lock);
-	iput(vol->mftbmp_ino);
-	vol->mftbmp_ino = NULL;
-	up_write(&vol->mftbmp_lock);
-
-#ifdef NTFS_RW
-	if (vol->logfile_ino) {
-		iput(vol->logfile_ino);
-		vol->logfile_ino = NULL;
-	}
-	if (vol->mftmirr_ino) {
-		/* Re-commit the mft mirror and mft just in case. */
-		ntfs_commit_inode(vol->mftmirr_ino);
-		ntfs_commit_inode(vol->mft_ino);
-		iput(vol->mftmirr_ino);
-		vol->mftmirr_ino = NULL;
-	}
-	/*
-	 * We should have no dirty inodes left, due to
-	 * mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
-	 * the underlying mft records are written out and cleaned.
-	 */
-	ntfs_commit_inode(vol->mft_ino);
-	write_inode_now(vol->mft_ino, 1);
-#endif /* NTFS_RW */
-
-	iput(vol->mft_ino);
-	vol->mft_ino = NULL;
-
-	/* Throw away the table of attribute definitions. */
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-	vol->upcase_len = 0;
-	/*
-	 * Destroy the global default upcase table if necessary.  Also decrease
-	 * the number of upcase users if we are a user.
-	 */
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	if (!ntfs_nr_upcase_users && default_upcase) {
-		ntfs_free(default_upcase);
-		default_upcase = NULL;
-	}
-	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
-		free_compression_buffers();
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-
-	unload_nls(vol->nls_map);
-
-	sb->s_fs_info = NULL;
-	kfree(vol);
-}
-
-/**
- * get_nr_free_clusters - return the number of free clusters on a volume
- * @vol:	ntfs volume for which to obtain free cluster count
- *
- * Calculate the number of free clusters on the mounted NTFS volume @vol. We
- * actually calculate the number of clusters in use instead because this
- * allows us to not care about partial pages as these will be just zero filled
- * and hence not be counted as allocated clusters.
- *
- * The only particularity is that clusters beyond the end of the logical ntfs
- * volume will be marked as allocated to prevent errors which means we have to
- * discount those at the end. This is important as the cluster bitmap always
- * has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside
- * the logical volume and marked in use when they are not as they do not exist.
- *
- * If any pages cannot be read we assume all clusters in the erroring pages are
- * in use. This means we return an underestimate on errors which is better than
- * an overestimate.
- */
-static s64 get_nr_free_clusters(ntfs_volume *vol)
-{
-	s64 nr_free = vol->nr_clusters;
-	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;
-	struct page *page;
-	pgoff_t index, max_index;
-
-	ntfs_debug("Entering.");
-	/* Serialize accesses to the cluster bitmap. */
-	down_read(&vol->lcnbmp_lock);
-	/*
-	 * Convert the number of bits into bytes rounded up, then convert into
-	 * multiples of PAGE_SIZE, rounding up so that if we have one
-	 * full and one partial page max_index = 2.
-	 */
-	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_SIZE - 1) >>
-			PAGE_SHIFT;
-	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
-	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",
-			max_index, PAGE_SIZE / 4);
-	for (index = 0; index < max_index; index++) {
-		unsigned long *kaddr;
-
-		/*
-		 * Read the page from page cache, getting it from backing store
-		 * if necessary, and increment the use count.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		/* Ignore pages which errored synchronously. */
-		if (IS_ERR(page)) {
-			ntfs_debug("read_mapping_page() error. Skipping "
-					"page (index 0x%lx).", index);
-			nr_free -= PAGE_SIZE * 8;
-			continue;
-		}
-		kaddr = kmap_atomic(page);
-		/*
-		 * Subtract the number of set bits. If this
-		 * is the last page and it is partial we don't really care as
-		 * it just means we do a little extra work but it won't affect
-		 * the result as all out of range bytes are set to zero by
-		 * ntfs_readpage().
-		 */
-		nr_free -= bitmap_weight(kaddr,
-					PAGE_SIZE * BITS_PER_BYTE);
-		kunmap_atomic(kaddr);
-		put_page(page);
-	}
-	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
-	/*
-	 * Fixup for eventual bits outside logical ntfs volume (see function
-	 * description above).
-	 */
-	if (vol->nr_clusters & 63)
-		nr_free += 64 - (vol->nr_clusters & 63);
-	up_read(&vol->lcnbmp_lock);
-	/* If errors occurred we may well have gone below zero, fix this. */
-	if (nr_free < 0)
-		nr_free = 0;
-	ntfs_debug("Exiting.");
-	return nr_free;
-}
-
-/**
- * __get_nr_free_mft_records - return the number of free inodes on a volume
- * @vol:	ntfs volume for which to obtain free inode count
- * @nr_free:	number of mft records in filesystem
- * @max_index:	maximum number of pages containing set bits
- *
- * Calculate the number of free mft records (inodes) on the mounted NTFS
- * volume @vol. We actually calculate the number of mft records in use instead
- * because this allows us to not care about partial pages as these will be just
- * zero filled and hence not be counted as allocated mft record.
- *
- * If any pages cannot be read we assume all mft records in the erroring pages
- * are in use. This means we return an underestimate on errors which is better
- * than an overestimate.
- *
- * NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.
- */
-static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
-		s64 nr_free, const pgoff_t max_index)
-{
-	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
-	struct page *page;
-	pgoff_t index;
-
-	ntfs_debug("Entering.");
-	/* Use multiples of 4 bytes, thus max_size is PAGE_SIZE / 4. */
-	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
-			"0x%lx.", max_index, PAGE_SIZE / 4);
-	for (index = 0; index < max_index; index++) {
-		unsigned long *kaddr;
-
-		/*
-		 * Read the page from page cache, getting it from backing store
-		 * if necessary, and increment the use count.
-		 */
-		page = read_mapping_page(mapping, index, NULL);
-		/* Ignore pages which errored synchronously. */
-		if (IS_ERR(page)) {
-			ntfs_debug("read_mapping_page() error. Skipping "
-					"page (index 0x%lx).", index);
-			nr_free -= PAGE_SIZE * 8;
-			continue;
-		}
-		kaddr = kmap_atomic(page);
-		/*
-		 * Subtract the number of set bits. If this
-		 * is the last page and it is partial we don't really care as
-		 * it just means we do a little extra work but it won't affect
-		 * the result as all out of range bytes are set to zero by
-		 * ntfs_readpage().
-		 */
-		nr_free -= bitmap_weight(kaddr,
-					PAGE_SIZE * BITS_PER_BYTE);
-		kunmap_atomic(kaddr);
-		put_page(page);
-	}
-	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
-			index - 1);
-	/* If errors occurred we may well have gone below zero, fix this. */
-	if (nr_free < 0)
-		nr_free = 0;
-	ntfs_debug("Exiting.");
-	return nr_free;
-}
-
-/**
- * ntfs_statfs - return information about mounted NTFS volume
- * @dentry:	dentry from mounted volume
- * @sfs:	statfs structure in which to return the information
- *
- * Return information about the mounted NTFS volume @dentry in the statfs structure
- * pointed to by @sfs (this is initialized with zeros before ntfs_statfs is
- * called). We interpret the values to be correct of the moment in time at
- * which we are called. Most values are variable otherwise and this isn't just
- * the free values but the totals as well. For example we can increase the
- * total number of file nodes if we run out and we can keep doing this until
- * there is no more space on the volume left at all.
- *
- * Called from vfs_statfs which is used to handle the statfs, fstatfs, and
- * ustat system calls.
- *
- * Return 0 on success or -errno on error.
- */
-static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
-{
-	struct super_block *sb = dentry->d_sb;
-	s64 size;
-	ntfs_volume *vol = NTFS_SB(sb);
-	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);
-	pgoff_t max_index;
-	unsigned long flags;
-
-	ntfs_debug("Entering.");
-	/* Type of filesystem. */
-	sfs->f_type   = NTFS_SB_MAGIC;
-	/* Optimal transfer block size. */
-	sfs->f_bsize  = PAGE_SIZE;
-	/*
-	 * Total data blocks in filesystem in units of f_bsize and since
-	 * inodes are also stored in data blocs ($MFT is a file) this is just
-	 * the total clusters.
-	 */
-	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
-				PAGE_SHIFT;
-	/* Free data blocks in filesystem in units of f_bsize. */
-	size	      = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
-				PAGE_SHIFT;
-	if (size < 0LL)
-		size = 0LL;
-	/* Free blocks avail to non-superuser, same as above on NTFS. */
-	sfs->f_bavail = sfs->f_bfree = size;
-	/* Serialize accesses to the inode bitmap. */
-	down_read(&vol->mftbmp_lock);
-	read_lock_irqsave(&mft_ni->size_lock, flags);
-	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;
-	/*
-	 * Convert the maximum number of set bits into bytes rounded up, then
-	 * convert into multiples of PAGE_SIZE, rounding up so that if we
-	 * have one full and one partial page max_index = 2.
-	 */
-	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)
-			+ 7) >> 3) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	read_unlock_irqrestore(&mft_ni->size_lock, flags);
-	/* Number of inodes in filesystem (at this point in time). */
-	sfs->f_files = size;
-	/* Free inodes in fs (based on current total count). */
-	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);
-	up_read(&vol->mftbmp_lock);
-	/*
-	 * File system id. This is extremely *nix flavour dependent and even
-	 * within Linux itself all fs do their own thing. I interpret this to
-	 * mean a unique id associated with the mounted fs and not the id
-	 * associated with the filesystem driver, the latter is already given
-	 * by the filesystem type in sfs->f_type. Thus we use the 64-bit
-	 * volume serial number splitting it into two 32-bit parts. We enter
-	 * the least significant 32-bits in f_fsid[0] and the most significant
-	 * 32-bits in f_fsid[1].
-	 */
-	sfs->f_fsid = u64_to_fsid(vol->serial_no);
-	/* Maximum length of filenames. */
-	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
-	return 0;
-}
-
-#ifdef NTFS_RW
-static int ntfs_write_inode(struct inode *vi, struct writeback_control *wbc)
-{
-	return __ntfs_write_inode(vi, wbc->sync_mode == WB_SYNC_ALL);
-}
-#endif
-
-/*
- * The complete super operations.
- */
-static const struct super_operations ntfs_sops = {
-	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
-	.free_inode	= ntfs_free_big_inode, /* VFS: Deallocate inode. */
-#ifdef NTFS_RW
-	.write_inode	= ntfs_write_inode,	/* VFS: Write dirty inode to
-						   disk. */
-#endif /* NTFS_RW */
-	.put_super	= ntfs_put_super,	/* Syscall: umount. */
-	.statfs		= ntfs_statfs,		/* Syscall: statfs */
-	.remount_fs	= ntfs_remount,		/* Syscall: mount -o remount. */
-	.evict_inode	= ntfs_evict_big_inode,	/* VFS: Called when an inode is
-						   removed from memory. */
-	.show_options	= ntfs_show_options,	/* Show mount options in
-						   proc. */
-};
-
-/**
- * ntfs_fill_super - mount an ntfs filesystem
- * @sb:		super block of ntfs filesystem to mount
- * @opt:	string containing the mount options
- * @silent:	silence error output
- *
- * ntfs_fill_super() is called by the VFS to mount the device described by @sb
- * with the mount otions in @data with the NTFS filesystem.
- *
- * If @silent is true, remain silent even if errors are detected. This is used
- * during bootup, when the kernel tries to mount the root filesystem with all
- * registered filesystems one after the other until one succeeds. This implies
- * that all filesystems except the correct one will quite correctly and
- * expectedly return an error, but nobody wants to see error messages when in
- * fact this is what is supposed to happen.
- *
- * NOTE: @sb->s_flags contains the mount options flags.
- */
-static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
-{
-	ntfs_volume *vol;
-	struct buffer_head *bh;
-	struct inode *tmp_ino;
-	int blocksize, result;
-
-	/*
-	 * We do a pretty difficult piece of bootstrap by reading the
-	 * MFT (and other metadata) from disk into memory. We'll only
-	 * release this metadata during umount, so the locking patterns
-	 * observed during bootstrap do not count. So turn off the
-	 * observation of locking patterns (strictly for this context
-	 * only) while mounting NTFS. [The validator is still active
-	 * otherwise, even for this context: it will for example record
-	 * lock class registrations.]
-	 */
-	lockdep_off();
-	ntfs_debug("Entering.");
-#ifndef NTFS_RW
-	sb->s_flags |= SB_RDONLY;
-#endif /* ! NTFS_RW */
-	/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */
-	sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);
-	vol = NTFS_SB(sb);
-	if (!vol) {
-		if (!silent)
-			ntfs_error(sb, "Allocation of NTFS volume structure "
-					"failed. Aborting mount...");
-		lockdep_on();
-		return -ENOMEM;
-	}
-	/* Initialize ntfs_volume structure. */
-	*vol = (ntfs_volume) {
-		.sb = sb,
-		/*
-		 * Default is group and other don't have any access to files or
-		 * directories while owner has full access. Further, files by
-		 * default are not executable but directories are of course
-		 * browseable.
-		 */
-		.fmask = 0177,
-		.dmask = 0077,
-	};
-	init_rwsem(&vol->mftbmp_lock);
-	init_rwsem(&vol->lcnbmp_lock);
-
-	/* By default, enable sparse support. */
-	NVolSetSparseEnabled(vol);
-
-	/* Important to get the mount options dealt with now. */
-	if (!parse_options(vol, (char*)opt))
-		goto err_out_now;
-
-	/* We support sector sizes up to the PAGE_SIZE. */
-	if (bdev_logical_block_size(sb->s_bdev) > PAGE_SIZE) {
-		if (!silent)
-			ntfs_error(sb, "Device has unsupported sector size "
-					"(%i).  The maximum supported sector "
-					"size on this architecture is %lu "
-					"bytes.",
-					bdev_logical_block_size(sb->s_bdev),
-					PAGE_SIZE);
-		goto err_out_now;
-	}
-	/*
-	 * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
-	 * sector size, whichever is bigger.
-	 */
-	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
-	if (blocksize < NTFS_BLOCK_SIZE) {
-		if (!silent)
-			ntfs_error(sb, "Unable to set device block size.");
-		goto err_out_now;
-	}
-	BUG_ON(blocksize != sb->s_blocksize);
-	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
-			blocksize, sb->s_blocksize_bits);
-	/* Determine the size of the device in units of block_size bytes. */
-	vol->nr_blocks = sb_bdev_nr_blocks(sb);
-	if (!vol->nr_blocks) {
-		if (!silent)
-			ntfs_error(sb, "Unable to determine device size.");
-		goto err_out_now;
-	}
-	/* Read the boot sector and return unlocked buffer head to it. */
-	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
-		if (!silent)
-			ntfs_error(sb, "Not an NTFS volume.");
-		goto err_out_now;
-	}
-	/*
-	 * Extract the data from the boot sector and setup the ntfs volume
-	 * using it.
-	 */
-	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
-	brelse(bh);
-	if (!result) {
-		if (!silent)
-			ntfs_error(sb, "Unsupported NTFS filesystem.");
-		goto err_out_now;
-	}
-	/*
-	 * If the boot sector indicates a sector size bigger than the current
-	 * device block size, switch the device block size to the sector size.
-	 * TODO: It may be possible to support this case even when the set
-	 * below fails, we would just be breaking up the i/o for each sector
-	 * into multiple blocks for i/o purposes but otherwise it should just
-	 * work.  However it is safer to leave disabled until someone hits this
-	 * error message and then we can get them to try it without the setting
-	 * so we know for sure that it works.
-	 */
-	if (vol->sector_size > blocksize) {
-		blocksize = sb_set_blocksize(sb, vol->sector_size);
-		if (blocksize != vol->sector_size) {
-			if (!silent)
-				ntfs_error(sb, "Unable to set device block "
-						"size to sector size (%i).",
-						vol->sector_size);
-			goto err_out_now;
-		}
-		BUG_ON(blocksize != sb->s_blocksize);
-		vol->nr_blocks = sb_bdev_nr_blocks(sb);
-		ntfs_debug("Changed device block size to %i bytes (block size "
-				"bits %i) to match volume sector size.",
-				blocksize, sb->s_blocksize_bits);
-	}
-	/* Initialize the cluster and mft allocators. */
-	ntfs_setup_allocators(vol);
-	/* Setup remaining fields in the super block. */
-	sb->s_magic = NTFS_SB_MAGIC;
-	/*
-	 * Ntfs allows 63 bits for the file size, i.e. correct would be:
-	 *	sb->s_maxbytes = ~0ULL >> 1;
-	 * But the kernel uses a long as the page cache page index which on
-	 * 32-bit architectures is only 32-bits. MAX_LFS_FILESIZE is kernel
-	 * defined to the maximum the page cache page index can cope with
-	 * without overflowing the index or to 2^63 - 1, whichever is smaller.
-	 */
-	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	/* Ntfs measures time in 100ns intervals. */
-	sb->s_time_gran = 100;
-	/*
-	 * Now load the metadata required for the page cache and our address
-	 * space operations to function. We do this by setting up a specialised
-	 * read_inode method and then just calling the normal iget() to obtain
-	 * the inode for $MFT which is sufficient to allow our normal inode
-	 * operations and associated address space operations to function.
-	 */
-	sb->s_op = &ntfs_sops;
-	tmp_ino = new_inode(sb);
-	if (!tmp_ino) {
-		if (!silent)
-			ntfs_error(sb, "Failed to load essential metadata.");
-		goto err_out_now;
-	}
-	tmp_ino->i_ino = FILE_MFT;
-	insert_inode_hash(tmp_ino);
-	if (ntfs_read_inode_mount(tmp_ino) < 0) {
-		if (!silent)
-			ntfs_error(sb, "Failed to load essential metadata.");
-		goto iput_tmp_ino_err_out_now;
-	}
-	mutex_lock(&ntfs_lock);
-	/*
-	 * The current mount is a compression user if the cluster size is
-	 * less than or equal 4kiB.
-	 */
-	if (vol->cluster_size <= 4096 && !ntfs_nr_compression_users++) {
-		result = allocate_compression_buffers();
-		if (result) {
-			ntfs_error(NULL, "Failed to allocate buffers "
-					"for compression engine.");
-			ntfs_nr_compression_users--;
-			mutex_unlock(&ntfs_lock);
-			goto iput_tmp_ino_err_out_now;
-		}
-	}
-	/*
-	 * Generate the global default upcase table if necessary.  Also
-	 * temporarily increment the number of upcase users to avoid race
-	 * conditions with concurrent (u)mounts.
-	 */
-	if (!default_upcase)
-		default_upcase = generate_default_upcase();
-	ntfs_nr_upcase_users++;
-	mutex_unlock(&ntfs_lock);
-	/*
-	 * From now on, ignore @silent parameter. If we fail below this line,
-	 * it will be due to a corrupt fs or a system error, so we report it.
-	 */
-	/*
-	 * Open the system files with normal access functions and complete
-	 * setting up the ntfs super block.
-	 */
-	if (!load_system_files(vol)) {
-		ntfs_error(sb, "Failed to load system files.");
-		goto unl_upcase_iput_tmp_ino_err_out_now;
-	}
-
-	/* We grab a reference, simulating an ntfs_iget(). */
-	ihold(vol->root_ino);
-	if ((sb->s_root = d_make_root(vol->root_ino))) {
-		ntfs_debug("Exiting, status successful.");
-		/* Release the default upcase if it has no users. */
-		mutex_lock(&ntfs_lock);
-		if (!--ntfs_nr_upcase_users && default_upcase) {
-			ntfs_free(default_upcase);
-			default_upcase = NULL;
-		}
-		mutex_unlock(&ntfs_lock);
-		sb->s_export_op = &ntfs_export_ops;
-		lockdep_on();
-		return 0;
-	}
-	ntfs_error(sb, "Failed to allocate root directory.");
-	/* Clean up after the successful load_system_files() call from above. */
-	// TODO: Use ntfs_put_super() instead of repeating all this code...
-	// FIXME: Should mark the volume clean as the error is most likely
-	// 	  -ENOMEM.
-	iput(vol->vol_ino);
-	vol->vol_ino = NULL;
-	/* NTFS 3.0+ specific clean up. */
-	if (vol->major_ver >= 3) {
-#ifdef NTFS_RW
-		if (vol->usnjrnl_j_ino) {
-			iput(vol->usnjrnl_j_ino);
-			vol->usnjrnl_j_ino = NULL;
-		}
-		if (vol->usnjrnl_max_ino) {
-			iput(vol->usnjrnl_max_ino);
-			vol->usnjrnl_max_ino = NULL;
-		}
-		if (vol->usnjrnl_ino) {
-			iput(vol->usnjrnl_ino);
-			vol->usnjrnl_ino = NULL;
-		}
-		if (vol->quota_q_ino) {
-			iput(vol->quota_q_ino);
-			vol->quota_q_ino = NULL;
-		}
-		if (vol->quota_ino) {
-			iput(vol->quota_ino);
-			vol->quota_ino = NULL;
-		}
-#endif /* NTFS_RW */
-		if (vol->extend_ino) {
-			iput(vol->extend_ino);
-			vol->extend_ino = NULL;
-		}
-		if (vol->secure_ino) {
-			iput(vol->secure_ino);
-			vol->secure_ino = NULL;
-		}
-	}
-	iput(vol->root_ino);
-	vol->root_ino = NULL;
-	iput(vol->lcnbmp_ino);
-	vol->lcnbmp_ino = NULL;
-	iput(vol->mftbmp_ino);
-	vol->mftbmp_ino = NULL;
-#ifdef NTFS_RW
-	if (vol->logfile_ino) {
-		iput(vol->logfile_ino);
-		vol->logfile_ino = NULL;
-	}
-	if (vol->mftmirr_ino) {
-		iput(vol->mftmirr_ino);
-		vol->mftmirr_ino = NULL;
-	}
-#endif /* NTFS_RW */
-	/* Throw away the table of attribute definitions. */
-	vol->attrdef_size = 0;
-	if (vol->attrdef) {
-		ntfs_free(vol->attrdef);
-		vol->attrdef = NULL;
-	}
-	vol->upcase_len = 0;
-	mutex_lock(&ntfs_lock);
-	if (vol->upcase == default_upcase) {
-		ntfs_nr_upcase_users--;
-		vol->upcase = NULL;
-	}
-	mutex_unlock(&ntfs_lock);
-	if (vol->upcase) {
-		ntfs_free(vol->upcase);
-		vol->upcase = NULL;
-	}
-	if (vol->nls_map) {
-		unload_nls(vol->nls_map);
-		vol->nls_map = NULL;
-	}
-	/* Error exit code path. */
-unl_upcase_iput_tmp_ino_err_out_now:
-	/*
-	 * Decrease the number of upcase users and destroy the global default
-	 * upcase table if necessary.
-	 */
-	mutex_lock(&ntfs_lock);
-	if (!--ntfs_nr_upcase_users && default_upcase) {
-		ntfs_free(default_upcase);
-		default_upcase = NULL;
-	}
-	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
-		free_compression_buffers();
-	mutex_unlock(&ntfs_lock);
-iput_tmp_ino_err_out_now:
-	iput(tmp_ino);
-	if (vol->mft_ino && vol->mft_ino != tmp_ino)
-		iput(vol->mft_ino);
-	vol->mft_ino = NULL;
-	/* Errors at this stage are irrelevant. */
-err_out_now:
-	sb->s_fs_info = NULL;
-	kfree(vol);
-	ntfs_debug("Failed, returning -EINVAL.");
-	lockdep_on();
-	return -EINVAL;
-}
-
-/*
- * This is a slab cache to optimize allocations and deallocations of Unicode
- * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
- * (255) Unicode characters + a terminating NULL Unicode character.
- */
-struct kmem_cache *ntfs_name_cache;
-
-/* Slab caches for efficient allocation/deallocation of inodes. */
-struct kmem_cache *ntfs_inode_cache;
-struct kmem_cache *ntfs_big_inode_cache;
-
-/* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(void *foo)
-{
-	ntfs_inode *ni = (ntfs_inode *)foo;
-
-	inode_init_once(VFS_I(ni));
-}
-
-/*
- * Slab caches to optimize allocations and deallocations of attribute search
- * contexts and index contexts, respectively.
- */
-struct kmem_cache *ntfs_attr_ctx_cache;
-struct kmem_cache *ntfs_index_ctx_cache;
-
-/* Driver wide mutex. */
-DEFINE_MUTEX(ntfs_lock);
-
-static struct dentry *ntfs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, ntfs_fill_super);
-}
-
-static struct file_system_type ntfs_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "ntfs",
-	.mount		= ntfs_mount,
-	.kill_sb	= kill_block_super,
-	.fs_flags	= FS_REQUIRES_DEV,
-};
-MODULE_ALIAS_FS("ntfs");
-
-/* Stable names for the slab caches. */
-static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
-static const char ntfs_attr_ctx_cache_name[] = "ntfs_attr_ctx_cache";
-static const char ntfs_name_cache_name[] = "ntfs_name_cache";
-static const char ntfs_inode_cache_name[] = "ntfs_inode_cache";
-static const char ntfs_big_inode_cache_name[] = "ntfs_big_inode_cache";
-
-static int __init init_ntfs_fs(void)
-{
-	int err = 0;
-
-	/* This may be ugly but it results in pretty output so who cares. (-8 */
-	pr_info("driver " NTFS_VERSION " [Flags: R/"
-#ifdef NTFS_RW
-			"W"
-#else
-			"O"
-#endif
-#ifdef DEBUG
-			" DEBUG"
-#endif
-#ifdef MODULE
-			" MODULE"
-#endif
-			"].\n");
-
-	ntfs_debug("Debug messages are enabled.");
-
-	ntfs_index_ctx_cache = kmem_cache_create(ntfs_index_ctx_cache_name,
-			sizeof(ntfs_index_context), 0 /* offset */,
-			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
-	if (!ntfs_index_ctx_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_index_ctx_cache_name);
-		goto ictx_err_out;
-	}
-	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,
-			sizeof(ntfs_attr_search_ctx), 0 /* offset */,
-			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
-	if (!ntfs_attr_ctx_cache) {
-		pr_crit("NTFS: Failed to create %s!\n",
-			ntfs_attr_ctx_cache_name);
-		goto actx_err_out;
-	}
-
-	ntfs_name_cache = kmem_cache_create(ntfs_name_cache_name,
-			(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,
-			SLAB_HWCACHE_ALIGN, NULL);
-	if (!ntfs_name_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_name_cache_name);
-		goto name_err_out;
-	}
-
-	ntfs_inode_cache = kmem_cache_create(ntfs_inode_cache_name,
-			sizeof(ntfs_inode), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-	if (!ntfs_inode_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_inode_cache_name);
-		goto inode_err_out;
-	}
-
-	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,
-			sizeof(big_ntfs_inode), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
-			SLAB_ACCOUNT, ntfs_big_inode_init_once);
-	if (!ntfs_big_inode_cache) {
-		pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name);
-		goto big_inode_err_out;
-	}
-
-	/* Register the ntfs sysctls. */
-	err = ntfs_sysctl(1);
-	if (err) {
-		pr_crit("Failed to register NTFS sysctls!\n");
-		goto sysctl_err_out;
-	}
-
-	err = register_filesystem(&ntfs_fs_type);
-	if (!err) {
-		ntfs_debug("NTFS driver registered successfully.");
-		return 0; /* Success! */
-	}
-	pr_crit("Failed to register NTFS filesystem driver!\n");
-
-	/* Unregister the ntfs sysctls. */
-	ntfs_sysctl(0);
-sysctl_err_out:
-	kmem_cache_destroy(ntfs_big_inode_cache);
-big_inode_err_out:
-	kmem_cache_destroy(ntfs_inode_cache);
-inode_err_out:
-	kmem_cache_destroy(ntfs_name_cache);
-name_err_out:
-	kmem_cache_destroy(ntfs_attr_ctx_cache);
-actx_err_out:
-	kmem_cache_destroy(ntfs_index_ctx_cache);
-ictx_err_out:
-	if (!err) {
-		pr_crit("Aborting NTFS filesystem driver registration...\n");
-		err = -ENOMEM;
-	}
-	return err;
-}
-
-static void __exit exit_ntfs_fs(void)
-{
-	ntfs_debug("Unregistering NTFS driver.");
-
-	unregister_filesystem(&ntfs_fs_type);
-
-	/*
-	 * Make sure all delayed rcu free inodes are flushed before we
-	 * destroy cache.
-	 */
-	rcu_barrier();
-	kmem_cache_destroy(ntfs_big_inode_cache);
-	kmem_cache_destroy(ntfs_inode_cache);
-	kmem_cache_destroy(ntfs_name_cache);
-	kmem_cache_destroy(ntfs_attr_ctx_cache);
-	kmem_cache_destroy(ntfs_index_ctx_cache);
-	/* Unregister the ntfs sysctls. */
-	ntfs_sysctl(0);
-}
-
-MODULE_AUTHOR("Anton Altaparmakov <anton@tuxera.com>");
-MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.");
-MODULE_VERSION(NTFS_VERSION);
-MODULE_LICENSE("GPL");
-#ifdef DEBUG
-module_param(debug_msgs, bint, 0);
-MODULE_PARM_DESC(debug_msgs, "Enable debug messages.");
-#endif
-
-module_init(init_ntfs_fs)
-module_exit(exit_ntfs_fs)
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
deleted file mode 100644
index 4e980170d86a..000000000000
--- a/fs/ntfs/sysctl.c
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * sysctl.c - Code for sysctl handling in NTFS Linux kernel driver. Part of
- *	      the Linux-NTFS project. Adapted from the old NTFS driver,
- *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
- *
- * Copyright (c) 2002-2005 Anton Altaparmakov
- */
-
-#ifdef DEBUG
-
-#include <linux/module.h>
-
-#ifdef CONFIG_SYSCTL
-
-#include <linux/proc_fs.h>
-#include <linux/sysctl.h>
-
-#include "sysctl.h"
-#include "debug.h"
-
-/* Definition of the ntfs sysctl. */
-static struct ctl_table ntfs_sysctls[] = {
-	{
-		.procname	= "ntfs-debug",
-		.data		= &debug_msgs,		/* Data pointer and size. */
-		.maxlen		= sizeof(debug_msgs),
-		.mode		= 0644,			/* Mode, proc handler. */
-		.proc_handler	= proc_dointvec
-	},
-};
-
-/* Storage for the sysctls header. */
-static struct ctl_table_header *sysctls_root_table;
-
-/**
- * ntfs_sysctl - add or remove the debug sysctl
- * @add:	add (1) or remove (0) the sysctl
- *
- * Add or remove the debug sysctl. Return 0 on success or -errno on error.
- */
-int ntfs_sysctl(int add)
-{
-	if (add) {
-		BUG_ON(sysctls_root_table);
-		sysctls_root_table = register_sysctl("fs", ntfs_sysctls);
-		if (!sysctls_root_table)
-			return -ENOMEM;
-	} else {
-		BUG_ON(!sysctls_root_table);
-		unregister_sysctl_table(sysctls_root_table);
-		sysctls_root_table = NULL;
-	}
-	return 0;
-}
-
-#endif /* CONFIG_SYSCTL */
-#endif /* DEBUG */
diff --git a/fs/ntfs/sysctl.h b/fs/ntfs/sysctl.h
deleted file mode 100644
index 96bb2299d2d5..000000000000
--- a/fs/ntfs/sysctl.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * sysctl.h - Defines for sysctl handling in NTFS Linux kernel driver. Part of
- *	      the Linux-NTFS project. Adapted from the old NTFS driver,
- *	      Copyright (C) 1997 Martin von Löwis, Régis Duchesne
- *
- * Copyright (c) 2002-2004 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_SYSCTL_H
-#define _LINUX_NTFS_SYSCTL_H
-
-
-#if defined(DEBUG) && defined(CONFIG_SYSCTL)
-
-extern int ntfs_sysctl(int add);
-
-#else
-
-/* Just return success. */
-static inline int ntfs_sysctl(int add)
-{
-	return 0;
-}
-
-#endif /* DEBUG && CONFIG_SYSCTL */
-#endif /* _LINUX_NTFS_SYSCTL_H */
diff --git a/fs/ntfs/time.h b/fs/ntfs/time.h
deleted file mode 100644
index 6b63261300cc..000000000000
--- a/fs/ntfs/time.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * time.h - NTFS time conversion functions.  Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_TIME_H
-#define _LINUX_NTFS_TIME_H
-
-#include <linux/time.h>		/* For current_kernel_time(). */
-#include <asm/div64.h>		/* For do_div(). */
-
-#include "endian.h"
-
-#define NTFS_TIME_OFFSET ((s64)(369 * 365 + 89) * 24 * 3600 * 10000000)
-
-/**
- * utc2ntfs - convert Linux UTC time to NTFS time
- * @ts:		Linux UTC time to convert to NTFS time
- *
- * Convert the Linux UTC time @ts to its corresponding NTFS time and return
- * that in little endian format.
- *
- * Linux stores time in a struct timespec64 consisting of a time64_t tv_sec
- * and a long tv_nsec where tv_sec is the number of 1-second intervals since
- * 1st January 1970, 00:00:00 UTC and tv_nsec is the number of 1-nano-second
- * intervals since the value of tv_sec.
- *
- * NTFS uses Microsoft's standard time format which is stored in a s64 and is
- * measured as the number of 100-nano-second intervals since 1st January 1601,
- * 00:00:00 UTC.
- */
-static inline sle64 utc2ntfs(const struct timespec64 ts)
-{
-	/*
-	 * Convert the seconds to 100ns intervals, add the nano-seconds
-	 * converted to 100ns intervals, and then add the NTFS time offset.
-	 */
-	return cpu_to_sle64((s64)ts.tv_sec * 10000000 + ts.tv_nsec / 100 +
-			NTFS_TIME_OFFSET);
-}
-
-/**
- * get_current_ntfs_time - get the current time in little endian NTFS format
- *
- * Get the current time from the Linux kernel, convert it to its corresponding
- * NTFS time and return that in little endian format.
- */
-static inline sle64 get_current_ntfs_time(void)
-{
-	struct timespec64 ts;
-
-	ktime_get_coarse_real_ts64(&ts);
-	return utc2ntfs(ts);
-}
-
-/**
- * ntfs2utc - convert NTFS time to Linux time
- * @time:	NTFS time (little endian) to convert to Linux UTC
- *
- * Convert the little endian NTFS time @time to its corresponding Linux UTC
- * time and return that in cpu format.
- *
- * Linux stores time in a struct timespec64 consisting of a time64_t tv_sec
- * and a long tv_nsec where tv_sec is the number of 1-second intervals since
- * 1st January 1970, 00:00:00 UTC and tv_nsec is the number of 1-nano-second
- * intervals since the value of tv_sec.
- *
- * NTFS uses Microsoft's standard time format which is stored in a s64 and is
- * measured as the number of 100 nano-second intervals since 1st January 1601,
- * 00:00:00 UTC.
- */
-static inline struct timespec64 ntfs2utc(const sle64 time)
-{
-	struct timespec64 ts;
-
-	/* Subtract the NTFS time offset. */
-	u64 t = (u64)(sle64_to_cpu(time) - NTFS_TIME_OFFSET);
-	/*
-	 * Convert the time to 1-second intervals and the remainder to
-	 * 1-nano-second intervals.
-	 */
-	ts.tv_nsec = do_div(t, 10000000) * 100;
-	ts.tv_sec = t;
-	return ts;
-}
-
-#endif /* _LINUX_NTFS_TIME_H */
diff --git a/fs/ntfs/types.h b/fs/ntfs/types.h
deleted file mode 100644
index 9a47859e7a06..000000000000
--- a/fs/ntfs/types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * types.h - Defines for NTFS Linux kernel driver specific types.
- *	     Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_TYPES_H
-#define _LINUX_NTFS_TYPES_H
-
-#include <linux/types.h>
-
-typedef __le16 le16;
-typedef __le32 le32;
-typedef __le64 le64;
-typedef __u16 __bitwise sle16;
-typedef __u32 __bitwise sle32;
-typedef __u64 __bitwise sle64;
-
-/* 2-byte Unicode character type. */
-typedef le16 ntfschar;
-#define UCHAR_T_SIZE_BITS 1
-
-/*
- * Clusters are signed 64-bit values on NTFS volumes. We define two types, LCN
- * and VCN, to allow for type checking and better code readability.
- */
-typedef s64 VCN;
-typedef sle64 leVCN;
-typedef s64 LCN;
-typedef sle64 leLCN;
-
-/*
- * The NTFS journal $LogFile uses log sequence numbers which are signed 64-bit
- * values.  We define our own type LSN, to allow for type checking and better
- * code readability.
- */
-typedef s64 LSN;
-typedef sle64 leLSN;
-
-/*
- * The NTFS transaction log $UsnJrnl uses usn which are signed 64-bit values.
- * We define our own type USN, to allow for type checking and better code
- * readability.
- */
-typedef s64 USN;
-typedef sle64 leUSN;
-
-typedef enum {
-	CASE_SENSITIVE = 0,
-	IGNORE_CASE = 1,
-} IGNORE_CASE_BOOL;
-
-#endif /* _LINUX_NTFS_TYPES_H */
diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c
deleted file mode 100644
index a6b6c64f14a9..000000000000
--- a/fs/ntfs/unistr.c
+++ /dev/null
@@ -1,384 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * unistr.c - NTFS Unicode string handling. Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include <linux/slab.h>
-
-#include "types.h"
-#include "debug.h"
-#include "ntfs.h"
-
-/*
- * IMPORTANT
- * =========
- *
- * All these routines assume that the Unicode characters are in little endian
- * encoding inside the strings!!!
- */
-
-/*
- * This is used by the name collation functions to quickly determine what
- * characters are (in)valid.
- */
-static const u8 legal_ansi_char_array[0x40] = {
-	0x00, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-	0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10,
-
-	0x17, 0x07, 0x18, 0x17, 0x17, 0x17, 0x17, 0x17,
-	0x17, 0x17, 0x18, 0x16, 0x16, 0x17, 0x07, 0x00,
-
-	0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17, 0x17,
-	0x17, 0x17, 0x04, 0x16, 0x18, 0x16, 0x18, 0x18,
-};
-
-/**
- * ntfs_are_names_equal - compare two Unicode names for equality
- * @s1:			name to compare to @s2
- * @s1_len:		length in Unicode characters of @s1
- * @s2:			name to compare to @s1
- * @s2_len:		length in Unicode characters of @s2
- * @ic:			ignore case bool
- * @upcase:		upcase table (only if @ic == IGNORE_CASE)
- * @upcase_size:	length in Unicode characters of @upcase (if present)
- *
- * Compare the names @s1 and @s2 and return 'true' (1) if the names are
- * identical, or 'false' (0) if they are not identical. If @ic is IGNORE_CASE,
- * the @upcase table is used to performa a case insensitive comparison.
- */
-bool ntfs_are_names_equal(const ntfschar *s1, size_t s1_len,
-		const ntfschar *s2, size_t s2_len, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_size)
-{
-	if (s1_len != s2_len)
-		return false;
-	if (ic == CASE_SENSITIVE)
-		return !ntfs_ucsncmp(s1, s2, s1_len);
-	return !ntfs_ucsncasecmp(s1, s2, s1_len, upcase, upcase_size);
-}
-
-/**
- * ntfs_collate_names - collate two Unicode names
- * @name1:	first Unicode name to compare
- * @name2:	second Unicode name to compare
- * @err_val:	if @name1 contains an invalid character return this value
- * @ic:		either CASE_SENSITIVE or IGNORE_CASE
- * @upcase:	upcase table (ignored if @ic is CASE_SENSITIVE)
- * @upcase_len:	upcase table size (ignored if @ic is CASE_SENSITIVE)
- *
- * ntfs_collate_names collates two Unicode names and returns:
- *
- *  -1 if the first name collates before the second one,
- *   0 if the names match,
- *   1 if the second name collates before the first one, or
- * @err_val if an invalid character is found in @name1 during the comparison.
- *
- * The following characters are considered invalid: '"', '*', '<', '>' and '?'.
- */
-int ntfs_collate_names(const ntfschar *name1, const u32 name1_len,
-		const ntfschar *name2, const u32 name2_len,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	u32 cnt, min_len;
-	u16 c1, c2;
-
-	min_len = name1_len;
-	if (name1_len > name2_len)
-		min_len = name2_len;
-	for (cnt = 0; cnt < min_len; ++cnt) {
-		c1 = le16_to_cpu(*name1++);
-		c2 = le16_to_cpu(*name2++);
-		if (ic) {
-			if (c1 < upcase_len)
-				c1 = le16_to_cpu(upcase[c1]);
-			if (c2 < upcase_len)
-				c2 = le16_to_cpu(upcase[c2]);
-		}
-		if (c1 < 64 && legal_ansi_char_array[c1] & 8)
-			return err_val;
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-	}
-	if (name1_len < name2_len)
-		return -1;
-	if (name1_len == name2_len)
-		return 0;
-	/* name1_len > name2_len */
-	c1 = le16_to_cpu(*name1);
-	if (c1 < 64 && legal_ansi_char_array[c1] & 8)
-		return err_val;
-	return 1;
-}
-
-/**
- * ntfs_ucsncmp - compare two little endian Unicode strings
- * @s1:		first string
- * @s2:		second string
- * @n:		maximum unicode characters to compare
- *
- * Compare the first @n characters of the Unicode strings @s1 and @s2,
- * The strings in little endian format and appropriate le16_to_cpu()
- * conversion is performed on non-little endian machines.
- *
- * The function returns an integer less than, equal to, or greater than zero
- * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
- * to be less than, to match, or be greater than @s2.
- */
-int ntfs_ucsncmp(const ntfschar *s1, const ntfschar *s2, size_t n)
-{
-	u16 c1, c2;
-	size_t i;
-
-	for (i = 0; i < n; ++i) {
-		c1 = le16_to_cpu(s1[i]);
-		c2 = le16_to_cpu(s2[i]);
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-		if (!c1)
-			break;
-	}
-	return 0;
-}
-
-/**
- * ntfs_ucsncasecmp - compare two little endian Unicode strings, ignoring case
- * @s1:			first string
- * @s2:			second string
- * @n:			maximum unicode characters to compare
- * @upcase:		upcase table
- * @upcase_size:	upcase table size in Unicode characters
- *
- * Compare the first @n characters of the Unicode strings @s1 and @s2,
- * ignoring case. The strings in little endian format and appropriate
- * le16_to_cpu() conversion is performed on non-little endian machines.
- *
- * Each character is uppercased using the @upcase table before the comparison.
- *
- * The function returns an integer less than, equal to, or greater than zero
- * if @s1 (or the first @n Unicode characters thereof) is found, respectively,
- * to be less than, to match, or be greater than @s2.
- */
-int ntfs_ucsncasecmp(const ntfschar *s1, const ntfschar *s2, size_t n,
-		const ntfschar *upcase, const u32 upcase_size)
-{
-	size_t i;
-	u16 c1, c2;
-
-	for (i = 0; i < n; ++i) {
-		if ((c1 = le16_to_cpu(s1[i])) < upcase_size)
-			c1 = le16_to_cpu(upcase[c1]);
-		if ((c2 = le16_to_cpu(s2[i])) < upcase_size)
-			c2 = le16_to_cpu(upcase[c2]);
-		if (c1 < c2)
-			return -1;
-		if (c1 > c2)
-			return 1;
-		if (!c1)
-			break;
-	}
-	return 0;
-}
-
-void ntfs_upcase_name(ntfschar *name, u32 name_len, const ntfschar *upcase,
-		const u32 upcase_len)
-{
-	u32 i;
-	u16 u;
-
-	for (i = 0; i < name_len; i++)
-		if ((u = le16_to_cpu(name[i])) < upcase_len)
-			name[i] = upcase[u];
-}
-
-void ntfs_file_upcase_value(FILE_NAME_ATTR *file_name_attr,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	ntfs_upcase_name((ntfschar*)&file_name_attr->file_name,
-			file_name_attr->file_name_length, upcase, upcase_len);
-}
-
-int ntfs_file_compare_values(FILE_NAME_ATTR *file_name_attr1,
-		FILE_NAME_ATTR *file_name_attr2,
-		const int err_val, const IGNORE_CASE_BOOL ic,
-		const ntfschar *upcase, const u32 upcase_len)
-{
-	return ntfs_collate_names((ntfschar*)&file_name_attr1->file_name,
-			file_name_attr1->file_name_length,
-			(ntfschar*)&file_name_attr2->file_name,
-			file_name_attr2->file_name_length,
-			err_val, ic, upcase, upcase_len);
-}
-
-/**
- * ntfs_nlstoucs - convert NLS string to little endian Unicode string
- * @vol:	ntfs volume which we are working with
- * @ins:	input NLS string buffer
- * @ins_len:	length of input string in bytes
- * @outs:	on return contains the allocated output Unicode string buffer
- *
- * Convert the input string @ins, which is in whatever format the loaded NLS
- * map dictates, into a little endian, 2-byte Unicode string.
- *
- * This function allocates the string and the caller is responsible for
- * calling kmem_cache_free(ntfs_name_cache, *@outs); when finished with it.
- *
- * On success the function returns the number of Unicode characters written to
- * the output string *@outs (>= 0), not counting the terminating Unicode NULL
- * character. *@outs is set to the allocated output string buffer.
- *
- * On error, a negative number corresponding to the error code is returned. In
- * that case the output string is not allocated. Both *@outs and *@outs_len
- * are then undefined.
- *
- * This might look a bit odd due to fast path optimization...
- */
-int ntfs_nlstoucs(const ntfs_volume *vol, const char *ins,
-		const int ins_len, ntfschar **outs)
-{
-	struct nls_table *nls = vol->nls_map;
-	ntfschar *ucs;
-	wchar_t wc;
-	int i, o, wc_len;
-
-	/* We do not trust outside sources. */
-	if (likely(ins)) {
-		ucs = kmem_cache_alloc(ntfs_name_cache, GFP_NOFS);
-		if (likely(ucs)) {
-			for (i = o = 0; i < ins_len; i += wc_len) {
-				wc_len = nls->char2uni(ins + i, ins_len - i,
-						&wc);
-				if (likely(wc_len >= 0 &&
-						o < NTFS_MAX_NAME_LEN)) {
-					if (likely(wc)) {
-						ucs[o++] = cpu_to_le16(wc);
-						continue;
-					} /* else if (!wc) */
-					break;
-				} /* else if (wc_len < 0 ||
-						o >= NTFS_MAX_NAME_LEN) */
-				goto name_err;
-			}
-			ucs[o] = 0;
-			*outs = ucs;
-			return o;
-		} /* else if (!ucs) */
-		ntfs_error(vol->sb, "Failed to allocate buffer for converted "
-				"name from ntfs_name_cache.");
-		return -ENOMEM;
-	} /* else if (!ins) */
-	ntfs_error(vol->sb, "Received NULL pointer.");
-	return -EINVAL;
-name_err:
-	kmem_cache_free(ntfs_name_cache, ucs);
-	if (wc_len < 0) {
-		ntfs_error(vol->sb, "Name using character set %s contains "
-				"characters that cannot be converted to "
-				"Unicode.", nls->charset);
-		i = -EILSEQ;
-	} else /* if (o >= NTFS_MAX_NAME_LEN) */ {
-		ntfs_error(vol->sb, "Name is too long (maximum length for a "
-				"name on NTFS is %d Unicode characters.",
-				NTFS_MAX_NAME_LEN);
-		i = -ENAMETOOLONG;
-	}
-	return i;
-}
-
-/**
- * ntfs_ucstonls - convert little endian Unicode string to NLS string
- * @vol:	ntfs volume which we are working with
- * @ins:	input Unicode string buffer
- * @ins_len:	length of input string in Unicode characters
- * @outs:	on return contains the (allocated) output NLS string buffer
- * @outs_len:	length of output string buffer in bytes
- *
- * Convert the input little endian, 2-byte Unicode string @ins, of length
- * @ins_len into the string format dictated by the loaded NLS.
- *
- * If *@outs is NULL, this function allocates the string and the caller is
- * responsible for calling kfree(*@outs); when finished with it. In this case
- * @outs_len is ignored and can be 0.
- *
- * On success the function returns the number of bytes written to the output
- * string *@outs (>= 0), not counting the terminating NULL byte. If the output
- * string buffer was allocated, *@outs is set to it.
- *
- * On error, a negative number corresponding to the error code is returned. In
- * that case the output string is not allocated. The contents of *@outs are
- * then undefined.
- *
- * This might look a bit odd due to fast path optimization...
- */
-int ntfs_ucstonls(const ntfs_volume *vol, const ntfschar *ins,
-		const int ins_len, unsigned char **outs, int outs_len)
-{
-	struct nls_table *nls = vol->nls_map;
-	unsigned char *ns;
-	int i, o, ns_len, wc;
-
-	/* We don't trust outside sources. */
-	if (ins) {
-		ns = *outs;
-		ns_len = outs_len;
-		if (ns && !ns_len) {
-			wc = -ENAMETOOLONG;
-			goto conversion_err;
-		}
-		if (!ns) {
-			ns_len = ins_len * NLS_MAX_CHARSET_SIZE;
-			ns = kmalloc(ns_len + 1, GFP_NOFS);
-			if (!ns)
-				goto mem_err_out;
-		}
-		for (i = o = 0; i < ins_len; i++) {
-retry:			wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
-					ns_len - o);
-			if (wc > 0) {
-				o += wc;
-				continue;
-			} else if (!wc)
-				break;
-			else if (wc == -ENAMETOOLONG && ns != *outs) {
-				unsigned char *tc;
-				/* Grow in multiples of 64 bytes. */
-				tc = kmalloc((ns_len + 64) &
-						~63, GFP_NOFS);
-				if (tc) {
-					memcpy(tc, ns, ns_len);
-					ns_len = ((ns_len + 64) & ~63) - 1;
-					kfree(ns);
-					ns = tc;
-					goto retry;
-				} /* No memory so goto conversion_error; */
-			} /* wc < 0, real error. */
-			goto conversion_err;
-		}
-		ns[o] = 0;
-		*outs = ns;
-		return o;
-	} /* else (!ins) */
-	ntfs_error(vol->sb, "Received NULL pointer.");
-	return -EINVAL;
-conversion_err:
-	ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
-			"converted to character set %s.  You might want to "
-			"try to use the mount option nls=utf8.", nls->charset);
-	if (ns != *outs)
-		kfree(ns);
-	if (wc != -ENAMETOOLONG)
-		wc = -EILSEQ;
-	return wc;
-mem_err_out:
-	ntfs_error(vol->sb, "Failed to allocate name!");
-	return -ENOMEM;
-}
diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c
deleted file mode 100644
index 4ebe84a78dea..000000000000
--- a/fs/ntfs/upcase.c
+++ /dev/null
@@ -1,73 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * upcase.c - Generate the full NTFS Unicode upcase table in little endian.
- *	      Part of the Linux-NTFS project.
- *
- * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org>
- * Copyright (c) 2001-2006 Anton Altaparmakov
- */
-
-#include "malloc.h"
-#include "ntfs.h"
-
-ntfschar *generate_default_upcase(void)
-{
-	static const int uc_run_table[][3] = { /* Start, End, Add */
-	{0x0061, 0x007B,  -32}, {0x0451, 0x045D, -80}, {0x1F70, 0x1F72,  74},
-	{0x00E0, 0x00F7,  -32}, {0x045E, 0x0460, -80}, {0x1F72, 0x1F76,  86},
-	{0x00F8, 0x00FF,  -32}, {0x0561, 0x0587, -48}, {0x1F76, 0x1F78, 100},
-	{0x0256, 0x0258, -205}, {0x1F00, 0x1F08,   8}, {0x1F78, 0x1F7A, 128},
-	{0x028A, 0x028C, -217}, {0x1F10, 0x1F16,   8}, {0x1F7A, 0x1F7C, 112},
-	{0x03AC, 0x03AD,  -38}, {0x1F20, 0x1F28,   8}, {0x1F7C, 0x1F7E, 126},
-	{0x03AD, 0x03B0,  -37}, {0x1F30, 0x1F38,   8}, {0x1FB0, 0x1FB2,   8},
-	{0x03B1, 0x03C2,  -32}, {0x1F40, 0x1F46,   8}, {0x1FD0, 0x1FD2,   8},
-	{0x03C2, 0x03C3,  -31}, {0x1F51, 0x1F52,   8}, {0x1FE0, 0x1FE2,   8},
-	{0x03C3, 0x03CC,  -32}, {0x1F53, 0x1F54,   8}, {0x1FE5, 0x1FE6,   7},
-	{0x03CC, 0x03CD,  -64}, {0x1F55, 0x1F56,   8}, {0x2170, 0x2180, -16},
-	{0x03CD, 0x03CF,  -63}, {0x1F57, 0x1F58,   8}, {0x24D0, 0x24EA, -26},
-	{0x0430, 0x0450,  -32}, {0x1F60, 0x1F68,   8}, {0xFF41, 0xFF5B, -32},
-	{0}
-	};
-
-	static const int uc_dup_table[][2] = { /* Start, End */
-	{0x0100, 0x012F}, {0x01A0, 0x01A6}, {0x03E2, 0x03EF}, {0x04CB, 0x04CC},
-	{0x0132, 0x0137}, {0x01B3, 0x01B7}, {0x0460, 0x0481}, {0x04D0, 0x04EB},
-	{0x0139, 0x0149}, {0x01CD, 0x01DD}, {0x0490, 0x04BF}, {0x04EE, 0x04F5},
-	{0x014A, 0x0178}, {0x01DE, 0x01EF}, {0x04BF, 0x04BF}, {0x04F8, 0x04F9},
-	{0x0179, 0x017E}, {0x01F4, 0x01F5}, {0x04C1, 0x04C4}, {0x1E00, 0x1E95},
-	{0x018B, 0x018B}, {0x01FA, 0x0218}, {0x04C7, 0x04C8}, {0x1EA0, 0x1EF9},
-	{0}
-	};
-
-	static const int uc_word_table[][2] = { /* Offset, Value */
-	{0x00FF, 0x0178}, {0x01AD, 0x01AC}, {0x01F3, 0x01F1}, {0x0269, 0x0196},
-	{0x0183, 0x0182}, {0x01B0, 0x01AF}, {0x0253, 0x0181}, {0x026F, 0x019C},
-	{0x0185, 0x0184}, {0x01B9, 0x01B8}, {0x0254, 0x0186}, {0x0272, 0x019D},
-	{0x0188, 0x0187}, {0x01BD, 0x01BC}, {0x0259, 0x018F}, {0x0275, 0x019F},
-	{0x018C, 0x018B}, {0x01C6, 0x01C4}, {0x025B, 0x0190}, {0x0283, 0x01A9},
-	{0x0192, 0x0191}, {0x01C9, 0x01C7}, {0x0260, 0x0193}, {0x0288, 0x01AE},
-	{0x0199, 0x0198}, {0x01CC, 0x01CA}, {0x0263, 0x0194}, {0x0292, 0x01B7},
-	{0x01A8, 0x01A7}, {0x01DD, 0x018E}, {0x0268, 0x0197},
-	{0}
-	};
-
-	int i, r;
-	ntfschar *uc;
-
-	uc = ntfs_malloc_nofs(default_upcase_len * sizeof(ntfschar));
-	if (!uc)
-		return uc;
-	memset(uc, 0, default_upcase_len * sizeof(ntfschar));
-	/* Generate the little endian Unicode upcase table used by ntfs. */
-	for (i = 0; i < default_upcase_len; i++)
-		uc[i] = cpu_to_le16(i);
-	for (r = 0; uc_run_table[r][0]; r++)
-		for (i = uc_run_table[r][0]; i < uc_run_table[r][1]; i++)
-			le16_add_cpu(&uc[i], uc_run_table[r][2]);
-	for (r = 0; uc_dup_table[r][0]; r++)
-		for (i = uc_dup_table[r][0]; i < uc_dup_table[r][1]; i += 2)
-			le16_add_cpu(&uc[i + 1], -1);
-	for (r = 0; uc_word_table[r][0]; r++)
-		uc[uc_word_table[r][0]] = cpu_to_le16(uc_word_table[r][1]);
-	return uc;
-}
diff --git a/fs/ntfs/usnjrnl.c b/fs/ntfs/usnjrnl.c
deleted file mode 100644
index 9097a0b4ef25..000000000000
--- a/fs/ntfs/usnjrnl.c
+++ /dev/null
@@ -1,70 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * usnjrnl.h - NTFS kernel transaction log ($UsnJrnl) handling.  Part of the
- *	       Linux-NTFS project.
- *
- * Copyright (c) 2005 Anton Altaparmakov
- */
-
-#ifdef NTFS_RW
-
-#include <linux/fs.h>
-#include <linux/highmem.h>
-#include <linux/mm.h>
-
-#include "aops.h"
-#include "debug.h"
-#include "endian.h"
-#include "time.h"
-#include "types.h"
-#include "usnjrnl.h"
-#include "volume.h"
-
-/**
- * ntfs_stamp_usnjrnl - stamp the transaction log ($UsnJrnl) on an ntfs volume
- * @vol:	ntfs volume on which to stamp the transaction log
- *
- * Stamp the transaction log ($UsnJrnl) on the ntfs volume @vol and return
- * 'true' on success and 'false' on error.
- *
- * This function assumes that the transaction log has already been loaded and
- * consistency checked by a call to fs/ntfs/super.c::load_and_init_usnjrnl().
- */
-bool ntfs_stamp_usnjrnl(ntfs_volume *vol)
-{
-	ntfs_debug("Entering.");
-	if (likely(!NVolUsnJrnlStamped(vol))) {
-		sle64 stamp;
-		struct page *page;
-		USN_HEADER *uh;
-
-		page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
-		if (IS_ERR(page)) {
-			ntfs_error(vol->sb, "Failed to read from "
-					"$UsnJrnl/$DATA/$Max attribute.");
-			return false;
-		}
-		uh = (USN_HEADER*)page_address(page);
-		stamp = get_current_ntfs_time();
-		ntfs_debug("Stamping transaction log ($UsnJrnl): old "
-				"journal_id 0x%llx, old lowest_valid_usn "
-				"0x%llx, new journal_id 0x%llx, new "
-				"lowest_valid_usn 0x%llx.",
-				(long long)sle64_to_cpu(uh->journal_id),
-				(long long)sle64_to_cpu(uh->lowest_valid_usn),
-				(long long)sle64_to_cpu(stamp),
-				i_size_read(vol->usnjrnl_j_ino));
-		uh->lowest_valid_usn =
-				cpu_to_sle64(i_size_read(vol->usnjrnl_j_ino));
-		uh->journal_id = stamp;
-		flush_dcache_page(page);
-		set_page_dirty(page);
-		ntfs_unmap_page(page);
-		/* Set the flag so we do not have to do it again on remount. */
-		NVolSetUsnJrnlStamped(vol);
-	}
-	ntfs_debug("Done.");
-	return true;
-}
-
-#endif /* NTFS_RW */
diff --git a/fs/ntfs/usnjrnl.h b/fs/ntfs/usnjrnl.h
deleted file mode 100644
index 85f531b59395..000000000000
--- a/fs/ntfs/usnjrnl.h
+++ /dev/null
@@ -1,191 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * usnjrnl.h - Defines for NTFS kernel transaction log ($UsnJrnl) handling.
- *	       Part of the Linux-NTFS project.
- *
- * Copyright (c) 2005 Anton Altaparmakov
- */
-
-#ifndef _LINUX_NTFS_USNJRNL_H
-#define _LINUX_NTFS_USNJRNL_H
-
-#ifdef NTFS_RW
-
-#include "types.h"
-#include "endian.h"
-#include "layout.h"
-#include "volume.h"
-
-/*
- * Transaction log ($UsnJrnl) organization:
- *
- * The transaction log records whenever a file is modified in any way.  So for
- * example it will record that file "blah" was written to at a particular time
- * but not what was written.  If will record that a file was deleted or
- * created, that a file was truncated, etc.  See below for all the reason
- * codes used.
- *
- * The transaction log is in the $Extend directory which is in the root
- * directory of each volume.  If it is not present it means transaction
- * logging is disabled.  If it is present it means transaction logging is
- * either enabled or in the process of being disabled in which case we can
- * ignore it as it will go away as soon as Windows gets its hands on it.
- *
- * To determine whether the transaction logging is enabled or in the process
- * of being disabled, need to check the volume flags in the
- * $VOLUME_INFORMATION attribute in the $Volume system file (which is present
- * in the root directory and has a fixed mft record number, see layout.h).
- * If the flag VOLUME_DELETE_USN_UNDERWAY is set it means the transaction log
- * is in the process of being disabled and if this flag is clear it means the
- * transaction log is enabled.
- *
- * The transaction log consists of two parts; the $DATA/$Max attribute as well
- * as the $DATA/$J attribute.  $Max is a header describing the transaction
- * log whilst $J is the transaction log data itself as a sequence of variable
- * sized USN_RECORDs (see below for all the structures).
- *
- * We do not care about transaction logging at this point in time but we still
- * need to let windows know that the transaction log is out of date.  To do
- * this we need to stamp the transaction log.  This involves setting the
- * lowest_valid_usn field in the $DATA/$Max attribute to the usn to be used
- * for the next added USN_RECORD to the $DATA/$J attribute as well as
- * generating a new journal_id in $DATA/$Max.
- *
- * The journal_id is as of the current version (2.0) of the transaction log
- * simply the 64-bit timestamp of when the journal was either created or last
- * stamped.
- *
- * To determine the next usn there are two ways.  The first is to parse
- * $DATA/$J and to find the last USN_RECORD in it and to add its record_length
- * to its usn (which is the byte offset in the $DATA/$J attribute).  The
- * second is simply to take the data size of the attribute.  Since the usns
- * are simply byte offsets into $DATA/$J, this is exactly the next usn.  For
- * obvious reasons we use the second method as it is much simpler and faster.
- *
- * As an aside, note that to actually disable the transaction log, one would
- * need to set the VOLUME_DELETE_USN_UNDERWAY flag (see above), then go
- * through all the mft records on the volume and set the usn field in their
- * $STANDARD_INFORMATION attribute to zero.  Once that is done, one would need
- * to delete the transaction log file, i.e. \$Extent\$UsnJrnl, and finally,
- * one would need to clear the VOLUME_DELETE_USN_UNDERWAY flag.
- *
- * Note that if a volume is unmounted whilst the transaction log is being
- * disabled, the process will continue the next time the volume is mounted.
- * This is why we can safely mount read-write when we see a transaction log
- * in the process of being deleted.
- */
-
-/* Some $UsnJrnl related constants. */
-#define UsnJrnlMajorVer		2
-#define UsnJrnlMinorVer		0
-
-/*
- * $DATA/$Max attribute.  This is (always?) resident and has a fixed size of
- * 32 bytes.  It contains the header describing the transaction log.
- */
-typedef struct {
-/*Ofs*/
-/*   0*/sle64 maximum_size;	/* The maximum on-disk size of the $DATA/$J
-				   attribute. */
-/*   8*/sle64 allocation_delta;	/* Number of bytes by which to increase the
-				   size of the $DATA/$J attribute. */
-/*0x10*/sle64 journal_id;	/* Current id of the transaction log. */
-/*0x18*/leUSN lowest_valid_usn;	/* Lowest valid usn in $DATA/$J for the
-				   current journal_id. */
-/* sizeof() = 32 (0x20) bytes */
-} __attribute__ ((__packed__)) USN_HEADER;
-
-/*
- * Reason flags (32-bit).  Cumulative flags describing the change(s) to the
- * file since it was last opened.  I think the names speak for themselves but
- * if you disagree check out the descriptions in the Linux NTFS project NTFS
- * documentation: http://www.linux-ntfs.org/
- */
-enum {
-	USN_REASON_DATA_OVERWRITE	= cpu_to_le32(0x00000001),
-	USN_REASON_DATA_EXTEND		= cpu_to_le32(0x00000002),
-	USN_REASON_DATA_TRUNCATION	= cpu_to_le32(0x00000004),
-	USN_REASON_NAMED_DATA_OVERWRITE	= cpu_to_le32(0x00000010),
-	USN_REASON_NAMED_DATA_EXTEND	= cpu_to_le32(0x00000020),
-	USN_REASON_NAMED_DATA_TRUNCATION= cpu_to_le32(0x00000040),
-	USN_REASON_FILE_CREATE		= cpu_to_le32(0x00000100),
-	USN_REASON_FILE_DELETE		= cpu_to_le32(0x00000200),
-	USN_REASON_EA_CHANGE		= cpu_to_le32(0x00000400),
-	USN_REASON_SECURITY_CHANGE	= cpu_to_le32(0x00000800),
-	USN_REASON_RENAME_OLD_NAME	= cpu_to_le32(0x00001000),
-	USN_REASON_RENAME_NEW_NAME	= cpu_to_le32(0x00002000),
-	USN_REASON_INDEXABLE_CHANGE	= cpu_to_le32(0x00004000),
-	USN_REASON_BASIC_INFO_CHANGE	= cpu_to_le32(0x00008000),
-	USN_REASON_HARD_LINK_CHANGE	= cpu_to_le32(0x00010000),
-	USN_REASON_COMPRESSION_CHANGE	= cpu_to_le32(0x00020000),
-	USN_REASON_ENCRYPTION_CHANGE	= cpu_to_le32(0x00040000),
-	USN_REASON_OBJECT_ID_CHANGE	= cpu_to_le32(0x00080000),
-	USN_REASON_REPARSE_POINT_CHANGE	= cpu_to_le32(0x00100000),
-	USN_REASON_STREAM_CHANGE	= cpu_to_le32(0x00200000),
-	USN_REASON_CLOSE		= cpu_to_le32(0x80000000),
-};
-
-typedef le32 USN_REASON_FLAGS;
-
-/*
- * Source info flags (32-bit).  Information about the source of the change(s)
- * to the file.  For detailed descriptions of what these mean, see the Linux
- * NTFS project NTFS documentation:
- *	http://www.linux-ntfs.org/
- */
-enum {
-	USN_SOURCE_DATA_MANAGEMENT	  = cpu_to_le32(0x00000001),
-	USN_SOURCE_AUXILIARY_DATA	  = cpu_to_le32(0x00000002),
-	USN_SOURCE_REPLICATION_MANAGEMENT = cpu_to_le32(0x00000004),
-};
-
-typedef le32 USN_SOURCE_INFO_FLAGS;
-
-/*
- * $DATA/$J attribute.  This is always non-resident, is marked as sparse, and
- * is of variabled size.  It consists of a sequence of variable size
- * USN_RECORDS.  The minimum allocated_size is allocation_delta as
- * specified in $DATA/$Max.  When the maximum_size specified in $DATA/$Max is
- * exceeded by more than allocation_delta bytes, allocation_delta bytes are
- * allocated and appended to the $DATA/$J attribute and an equal number of
- * bytes at the beginning of the attribute are freed and made sparse.  Note the
- * making sparse only happens at volume checkpoints and hence the actual
- * $DATA/$J size can exceed maximum_size + allocation_delta temporarily.
- */
-typedef struct {
-/*Ofs*/
-/*   0*/le32 length;		/* Byte size of this record (8-byte
-				   aligned). */
-/*   4*/le16 major_ver;		/* Major version of the transaction log used
-				   for this record. */
-/*   6*/le16 minor_ver;		/* Minor version of the transaction log used
-				   for this record. */
-/*   8*/leMFT_REF mft_reference;/* The mft reference of the file (or
-				   directory) described by this record. */
-/*0x10*/leMFT_REF parent_directory;/* The mft reference of the parent
-				   directory of the file described by this
-				   record. */
-/*0x18*/leUSN usn;		/* The usn of this record.  Equals the offset
-				   within the $DATA/$J attribute. */
-/*0x20*/sle64 time;		/* Time when this record was created. */
-/*0x28*/USN_REASON_FLAGS reason;/* Reason flags (see above). */
-/*0x2c*/USN_SOURCE_INFO_FLAGS source_info;/* Source info flags (see above). */
-/*0x30*/le32 security_id;	/* File security_id copied from
-				   $STANDARD_INFORMATION. */
-/*0x34*/FILE_ATTR_FLAGS file_attributes;	/* File attributes copied from
-				   $STANDARD_INFORMATION or $FILE_NAME (not
-				   sure which). */
-/*0x38*/le16 file_name_size;	/* Size of the file name in bytes. */
-/*0x3a*/le16 file_name_offset;	/* Offset to the file name in bytes from the
-				   start of this record. */
-/*0x3c*/ntfschar file_name[0];	/* Use when creating only.  When reading use
-				   file_name_offset to determine the location
-				   of the name. */
-/* sizeof() = 60 (0x3c) bytes */
-} __attribute__ ((__packed__)) USN_RECORD;
-
-extern bool ntfs_stamp_usnjrnl(ntfs_volume *vol);
-
-#endif /* NTFS_RW */
-
-#endif /* _LINUX_NTFS_USNJRNL_H */
diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h
deleted file mode 100644
index 930a9ae8a053..000000000000
--- a/fs/ntfs/volume.h
+++ /dev/null
@@ -1,164 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part
- *	      of the Linux-NTFS project.
- *
- * Copyright (c) 2001-2006 Anton Altaparmakov
- * Copyright (c) 2002 Richard Russon
- */
-
-#ifndef _LINUX_NTFS_VOLUME_H
-#define _LINUX_NTFS_VOLUME_H
-
-#include <linux/rwsem.h>
-#include <linux/uidgid.h>
-
-#include "types.h"
-#include "layout.h"
-
-/*
- * The NTFS in memory super block structure.
- */
-typedef struct {
-	/*
-	 * FIXME: Reorder to have commonly used together element within the
-	 * same cache line, aiming at a cache line size of 32 bytes. Aim for
-	 * 64 bytes for less commonly used together elements. Put most commonly
-	 * used elements to front of structure. Obviously do this only when the
-	 * structure has stabilized... (AIA)
-	 */
-	/* Device specifics. */
-	struct super_block *sb;		/* Pointer back to the super_block. */
-	LCN nr_blocks;			/* Number of sb->s_blocksize bytes
-					   sized blocks on the device. */
-	/* Configuration provided by user at mount time. */
-	unsigned long flags;		/* Miscellaneous flags, see below. */
-	kuid_t uid;			/* uid that files will be mounted as. */
-	kgid_t gid;			/* gid that files will be mounted as. */
-	umode_t fmask;			/* The mask for file permissions. */
-	umode_t dmask;			/* The mask for directory
-					   permissions. */
-	u8 mft_zone_multiplier;		/* Initial mft zone multiplier. */
-	u8 on_errors;			/* What to do on filesystem errors. */
-	/* NTFS bootsector provided information. */
-	u16 sector_size;		/* in bytes */
-	u8 sector_size_bits;		/* log2(sector_size) */
-	u32 cluster_size;		/* in bytes */
-	u32 cluster_size_mask;		/* cluster_size - 1 */
-	u8 cluster_size_bits;		/* log2(cluster_size) */
-	u32 mft_record_size;		/* in bytes */
-	u32 mft_record_size_mask;	/* mft_record_size - 1 */
-	u8 mft_record_size_bits;	/* log2(mft_record_size) */
-	u32 index_record_size;		/* in bytes */
-	u32 index_record_size_mask;	/* index_record_size - 1 */
-	u8 index_record_size_bits;	/* log2(index_record_size) */
-	LCN nr_clusters;		/* Volume size in clusters == number of
-					   bits in lcn bitmap. */
-	LCN mft_lcn;			/* Cluster location of mft data. */
-	LCN mftmirr_lcn;		/* Cluster location of copy of mft. */
-	u64 serial_no;			/* The volume serial number. */
-	/* Mount specific NTFS information. */
-	u32 upcase_len;			/* Number of entries in upcase[]. */
-	ntfschar *upcase;		/* The upcase table. */
-
-	s32 attrdef_size;		/* Size of the attribute definition
-					   table in bytes. */
-	ATTR_DEF *attrdef;		/* Table of attribute definitions.
-					   Obtained from FILE_AttrDef. */
-
-#ifdef NTFS_RW
-	/* Variables used by the cluster and mft allocators. */
-	s64 mft_data_pos;		/* Mft record number at which to
-					   allocate the next mft record. */
-	LCN mft_zone_start;		/* First cluster of the mft zone. */
-	LCN mft_zone_end;		/* First cluster beyond the mft zone. */
-	LCN mft_zone_pos;		/* Current position in the mft zone. */
-	LCN data1_zone_pos;		/* Current position in the first data
-					   zone. */
-	LCN data2_zone_pos;		/* Current position in the second data
-					   zone. */
-#endif /* NTFS_RW */
-
-	struct inode *mft_ino;		/* The VFS inode of $MFT. */
-
-	struct inode *mftbmp_ino;	/* Attribute inode for $MFT/$BITMAP. */
-	struct rw_semaphore mftbmp_lock; /* Lock for serializing accesses to the
-					    mft record bitmap ($MFT/$BITMAP). */
-#ifdef NTFS_RW
-	struct inode *mftmirr_ino;	/* The VFS inode of $MFTMirr. */
-	int mftmirr_size;		/* Size of mft mirror in mft records. */
-
-	struct inode *logfile_ino;	/* The VFS inode of $LogFile. */
-#endif /* NTFS_RW */
-
-	struct inode *lcnbmp_ino;	/* The VFS inode of $Bitmap. */
-	struct rw_semaphore lcnbmp_lock; /* Lock for serializing accesses to the
-					    cluster bitmap ($Bitmap/$DATA). */
-
-	struct inode *vol_ino;		/* The VFS inode of $Volume. */
-	VOLUME_FLAGS vol_flags;		/* Volume flags. */
-	u8 major_ver;			/* Ntfs major version of volume. */
-	u8 minor_ver;			/* Ntfs minor version of volume. */
-
-	struct inode *root_ino;		/* The VFS inode of the root
-					   directory. */
-	struct inode *secure_ino;	/* The VFS inode of $Secure (NTFS3.0+
-					   only, otherwise NULL). */
-	struct inode *extend_ino;	/* The VFS inode of $Extend (NTFS3.0+
-					   only, otherwise NULL). */
-#ifdef NTFS_RW
-	/* $Quota stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
-	struct inode *quota_ino;	/* The VFS inode of $Quota. */
-	struct inode *quota_q_ino;	/* Attribute inode for $Quota/$Q. */
-	/* $UsnJrnl stuff is NTFS3.0+ specific.  Unused/NULL otherwise. */
-	struct inode *usnjrnl_ino;	/* The VFS inode of $UsnJrnl. */
-	struct inode *usnjrnl_max_ino;	/* Attribute inode for $UsnJrnl/$Max. */
-	struct inode *usnjrnl_j_ino;	/* Attribute inode for $UsnJrnl/$J. */
-#endif /* NTFS_RW */
-	struct nls_table *nls_map;
-} ntfs_volume;
-
-/*
- * Defined bits for the flags field in the ntfs_volume structure.
- */
-typedef enum {
-	NV_Errors,		/* 1: Volume has errors, prevent remount rw. */
-	NV_ShowSystemFiles,	/* 1: Return system files in ntfs_readdir(). */
-	NV_CaseSensitive,	/* 1: Treat file names as case sensitive and
-				      create filenames in the POSIX namespace.
-				      Otherwise be case insensitive but still
-				      create file names in POSIX namespace. */
-	NV_LogFileEmpty,	/* 1: $LogFile journal is empty. */
-	NV_QuotaOutOfDate,	/* 1: $Quota is out of date. */
-	NV_UsnJrnlStamped,	/* 1: $UsnJrnl has been stamped. */
-	NV_SparseEnabled,	/* 1: May create sparse files. */
-} ntfs_volume_flags;
-
-/*
- * Macro tricks to expand the NVolFoo(), NVolSetFoo(), and NVolClearFoo()
- * functions.
- */
-#define DEFINE_NVOL_BIT_OPS(flag)					\
-static inline int NVol##flag(ntfs_volume *vol)		\
-{							\
-	return test_bit(NV_##flag, &(vol)->flags);	\
-}							\
-static inline void NVolSet##flag(ntfs_volume *vol)	\
-{							\
-	set_bit(NV_##flag, &(vol)->flags);		\
-}							\
-static inline void NVolClear##flag(ntfs_volume *vol)	\
-{							\
-	clear_bit(NV_##flag, &(vol)->flags);		\
-}
-
-/* Emit the ntfs volume bitops functions. */
-DEFINE_NVOL_BIT_OPS(Errors)
-DEFINE_NVOL_BIT_OPS(ShowSystemFiles)
-DEFINE_NVOL_BIT_OPS(CaseSensitive)
-DEFINE_NVOL_BIT_OPS(LogFileEmpty)
-DEFINE_NVOL_BIT_OPS(QuotaOutOfDate)
-DEFINE_NVOL_BIT_OPS(UsnJrnlStamped)
-DEFINE_NVOL_BIT_OPS(SparseEnabled)
-
-#endif /* _LINUX_NTFS_VOLUME_H */
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 63f70259edc0..7aadf5010999 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -886,7 +886,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	struct runs_tree *run = &ni->file.run;
 	struct ntfs_sb_info *sbi;
 	u8 cluster_bits;
-	struct ATTRIB *attr = NULL, *attr_b;
+	struct ATTRIB *attr, *attr_b;
 	struct ATTR_LIST_ENTRY *le, *le_b;
 	struct mft_inode *mi, *mi_b;
 	CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen;
@@ -904,12 +904,8 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 		*len = 0;
 	up_read(&ni->file.run_lock);
 
-	if (*len) {
-		if (*lcn != SPARSE_LCN || !new)
-			return 0; /* Fast normal way without allocation. */
-		else if (clen > *len)
-			clen = *len;
-	}
+	if (*len && (*lcn != SPARSE_LCN || !new))
+		return 0; /* Fast normal way without allocation. */
 
 	/* No cluster in cache or we need to allocate cluster in hole. */
 	sbi = ni->mi.sbi;
@@ -918,6 +914,17 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
 	ni_lock(ni);
 	down_write(&ni->file.run_lock);
 
+	/* Repeat the code above (under write lock). */
+	if (!run_lookup_entry(run, vcn, lcn, len, NULL))
+		*len = 0;
+
+	if (*len) {
+		if (*lcn != SPARSE_LCN || !new)
+			goto out; /* normal way without allocation. */
+		if (clen > *len)
+			clen = *len;
+	}
+
 	le_b = NULL;
 	attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
 	if (!attr_b) {
@@ -1736,8 +1743,10 @@ repack:
 			le_b = NULL;
 			attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
 					      0, NULL, &mi_b);
-			if (!attr_b)
-				return -ENOENT;
+			if (!attr_b) {
+				err = -ENOENT;
+				goto out;
+			}
 
 			attr = attr_b;
 			le = le_b;
@@ -1818,13 +1827,15 @@ ins_ext:
 ok:
 	run_truncate_around(run, vcn);
 out:
-	if (new_valid > data_size)
-		new_valid = data_size;
+	if (attr_b) {
+		if (new_valid > data_size)
+			new_valid = data_size;
 
-	valid_size = le64_to_cpu(attr_b->nres.valid_size);
-	if (new_valid != valid_size) {
-		attr_b->nres.valid_size = cpu_to_le64(valid_size);
-		mi_b->dirty = true;
+		valid_size = le64_to_cpu(attr_b->nres.valid_size);
+		if (new_valid != valid_size) {
+			attr_b->nres.valid_size = cpu_to_le64(valid_size);
+			mi_b->dirty = true;
+		}
 	}
 
 	return err;
@@ -2073,7 +2084,7 @@ next_attr:
 
 	/* Update inode size. */
 	ni->i_valid = valid_size;
-	ni->vfs_inode.i_size = data_size;
+	i_size_write(&ni->vfs_inode, data_size);
 	inode_set_bytes(&ni->vfs_inode, total_size);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
@@ -2488,7 +2499,7 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 	mi_b->dirty = true;
 
 done:
-	ni->vfs_inode.i_size += bytes;
+	i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes);
 	ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
 	mark_inode_dirty(&ni->vfs_inode);
 
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 7c01735d1219..9f4bd8d26090 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -29,7 +29,7 @@ static inline bool al_is_valid_le(const struct ntfs_inode *ni,
 void al_destroy(struct ntfs_inode *ni)
 {
 	run_close(&ni->attr_list.run);
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	ni->attr_list.dirty = false;
@@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 {
 	size_t off;
 	u16 sz;
+	const unsigned le_min_size = le_size(0);
 
 	if (!le) {
 		le = ni->attr_list.le;
 	} else {
 		sz = le16_to_cpu(le->size);
-		if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
+		if (sz < le_min_size) {
 			/* Impossible 'cause we should not return such le. */
 			return NULL;
 		}
@@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 
 	/* Check boundary. */
 	off = PtrOffset(ni->attr_list.le, le);
-	if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
+	if (off + le_min_size > ni->attr_list.size) {
 		/* The regular end of list. */
 		return NULL;
 	}
@@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
 	sz = le16_to_cpu(le->size);
 
 	/* Check le for errors. */
-	if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
-	    off + sz > ni->attr_list.size ||
+	if (sz < le_min_size || off + sz > ni->attr_list.size ||
 	    sz < le->name_off + le->name_len * sizeof(short)) {
 		return NULL;
 	}
@@ -318,7 +318,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
 		memcpy(ptr, al->le, off);
 		memcpy(Add2Ptr(ptr, off + sz), le, old_size - off);
 		le = Add2Ptr(ptr, off);
-		kfree(al->le);
+		kvfree(al->le);
 		al->le = ptr;
 	} else {
 		memmove(Add2Ptr(le, sz), le, old_size - off);
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 63f14a0232f6..845f9b22deef 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -124,7 +124,7 @@ void wnd_close(struct wnd_bitmap *wnd)
 {
 	struct rb_node *node, *next;
 
-	kfree(wnd->free_bits);
+	kvfree(wnd->free_bits);
 	wnd->free_bits = NULL;
 	run_close(&wnd->run);
 
@@ -1360,7 +1360,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
 		memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
 		memset(new_free + wnd->nwnd, 0,
 		       (new_wnd - wnd->nwnd) * sizeof(short));
-		kfree(wnd->free_bits);
+		kvfree(wnd->free_bits);
 		wnd->free_bits = new_free;
 	}
 
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index ec0566b322d5..5cf3d9decf64 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 		return 0;
 	}
 
-	/* NTFS: symlinks are "dir + reparse" or "file + reparse" */
-	if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
-		dt_type = DT_LNK;
-	else
-		dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+	/*
+	 * NTFS: symlinks are "dir + reparse" or "file + reparse"
+	 * Unfortunately reparse attribute is used for many purposes (several dozens).
+	 * It is not possible here to know is this name symlink or not.
+	 * To get exactly the type of name we should to open inode (read mft).
+	 * getattr for opened file (fstat) correctly returns symlink.
+	 */
+	dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+
+	/*
+	 * It is not reliable to detect the type of name using duplicated information
+	 * stored in parent directory.
+	 * The only correct way to get the type of name - read MFT record and find ATTR_STD.
+	 * The code below is not good idea.
+	 * It does additional locks/reads just to get the type of name.
+	 * Should we use additional mount option to enable branch below?
+	 */
+	if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) &&
+	    ino != ni->mi.rno) {
+		struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL);
+		if (!IS_ERR_OR_NULL(inode)) {
+			dt_type = fs_umode_to_dtype(inode->i_mode);
+			iput(inode);
+		}
+	}
 
 	return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
 }
@@ -495,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 	struct INDEX_HDR *hdr;
 	const struct ATTR_FILE_NAME *fname;
 	u32 e_size, off, end;
-	u64 vbo = 0;
 	size_t drs = 0, fles = 0, bit = 0;
-	loff_t i_size = ni->vfs_inode.i_size;
 	struct indx_node *node = NULL;
-	u8 index_bits = ni->dir.index_bits;
+	size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits;
 
 	if (is_empty)
 		*is_empty = true;
@@ -518,8 +536,10 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 			e = Add2Ptr(hdr, off);
 			e_size = le16_to_cpu(e->size);
 			if (e_size < sizeof(struct NTFS_DE) ||
-			    off + e_size > end)
+			    off + e_size > end) {
+				/* Looks like corruption. */
 				break;
+			}
 
 			if (de_is_last(e))
 				break;
@@ -543,7 +563,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 				fles += 1;
 		}
 
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_used_bit(&ni->dir, ni, &bit);
@@ -553,8 +573,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 		if (bit == MINUS_ONE_T)
 			goto out;
 
-		vbo = (u64)bit << index_bits;
-		if (vbo >= i_size)
+		if (bit >= max_indx)
 			goto out;
 
 		err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
@@ -564,7 +583,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
 
 		hdr = &node->index->ihdr;
 		bit += 1;
-		vbo = (u64)bit << ni->dir.idx2vbn_bits;
 	}
 
 out:
@@ -593,5 +611,9 @@ const struct file_operations ntfs_dir_operations = {
 	.iterate_shared	= ntfs_readdir,
 	.fsync		= generic_file_fsync,
 	.open		= ntfs_file_open,
+	.unlocked_ioctl = ntfs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = ntfs_compat_ioctl,
+#endif
 };
 // clang-format on
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index a5a30a24ce5d..5418662c80d8 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -48,7 +48,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
 	return 0;
 }
 
-static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
@@ -61,7 +61,7 @@ static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 }
 
 #ifdef CONFIG_COMPAT
-static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
 
 {
 	return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
@@ -188,6 +188,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 	u32 bh_next, bh_off, to;
 	sector_t iblock;
 	struct folio *folio;
+	bool dirty = false;
 
 	for (; idx < idx_end; idx += 1, from = 0) {
 		page_off = (loff_t)idx << PAGE_SHIFT;
@@ -223,29 +224,27 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
 			/* Ok, it's mapped. Make sure it's up-to-date. */
 			if (folio_test_uptodate(folio))
 				set_buffer_uptodate(bh);
-
-			if (!buffer_uptodate(bh)) {
-				err = bh_read(bh, 0);
-				if (err < 0) {
-					folio_unlock(folio);
-					folio_put(folio);
-					goto out;
-				}
+			else if (bh_read(bh, 0) < 0) {
+				err = -EIO;
+				folio_unlock(folio);
+				folio_put(folio);
+				goto out;
 			}
 
 			mark_buffer_dirty(bh);
-
 		} while (bh_off = bh_next, iblock += 1,
 			 head != (bh = bh->b_this_page));
 
 		folio_zero_segment(folio, from, to);
+		dirty = true;
 
 		folio_unlock(folio);
 		folio_put(folio);
 		cond_resched();
 	}
 out:
-	mark_inode_dirty(inode);
+	if (dirty)
+		mark_inode_dirty(inode);
 	return err;
 }
 
@@ -261,6 +260,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	bool rw = vma->vm_flags & VM_WRITE;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "mmap encrypted not supported");
 		return -EOPNOTSUPP;
@@ -499,10 +501,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_punch_hole(ni, vbo, len, &frame_size);
 		ni_unlock(ni);
+		if (!err)
+			goto ok;
+
 		if (err != E_NTFS_NOTALIGNED)
 			goto out;
 
 		/* Process not aligned punch. */
+		err = 0;
 		mask = frame_size - 1;
 		vbo_a = (vbo + mask) & ~mask;
 		end_a = end & ~mask;
@@ -525,6 +531,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 			ni_lock(ni);
 			err = attr_punch_hole(ni, vbo_a, end_a - vbo_a, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		}
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
 		/*
@@ -564,6 +572,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 		ni_lock(ni);
 		err = attr_insert_range(ni, vbo, len);
 		ni_unlock(ni);
+		if (err)
+			goto out;
 	} else {
 		/* Check new size. */
 		u8 cluster_bits = sbi->cluster_bits;
@@ -633,11 +643,18 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
 					    &ni->file.run, i_size, &ni->i_valid,
 					    true, NULL);
 			ni_unlock(ni);
+			if (err)
+				goto out;
 		} else if (new_size > i_size) {
-			inode->i_size = new_size;
+			i_size_write(inode, new_size);
 		}
 	}
 
+ok:
+	err = file_modified(file);
+	if (err)
+		goto out;
+
 out:
 	if (map_locked)
 		filemap_invalidate_unlock(mapping);
@@ -663,6 +680,9 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	umode_t mode = inode->i_mode;
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		goto out;
@@ -676,7 +696,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 		}
 		inode_dio_wait(inode);
-		oldsize = inode->i_size;
+		oldsize = i_size_read(inode);
 		newsize = attr->ia_size;
 
 		if (newsize <= oldsize)
@@ -688,7 +708,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			goto out;
 
 		ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
-		inode->i_size = newsize;
+		i_size_write(inode, newsize);
 	}
 
 	setattr_copy(idmap, inode, attr);
@@ -718,6 +738,9 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -752,6 +775,9 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
 	struct inode *inode = in->f_mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -821,7 +847,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
 	size_t count = iov_iter_count(from);
 	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct ntfs_inode *ni = ntfs_i(inode);
 	u64 valid = ni->i_valid;
@@ -1028,6 +1054,8 @@ out:
 	iocb->ki_pos += written;
 	if (iocb->ki_pos > ni->i_valid)
 		ni->i_valid = iocb->ki_pos;
+	if (iocb->ki_pos > i_size)
+		i_size_write(inode, iocb->ki_pos);
 
 	return written;
 }
@@ -1041,8 +1069,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	ssize_t ret;
+	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (is_encrypted(ni)) {
 		ntfs_inode_warn(inode, "encrypted i/o not supported");
 		return -EOPNOTSUPP;
@@ -1068,6 +1100,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret <= 0)
 		goto out;
 
+	err = file_modified(iocb->ki_filp);
+	if (err) {
+		ret = err;
+		goto out;
+	}
+
 	if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
 		/* Should never be here, see ntfs_file_open(). */
 		ret = -EOPNOTSUPP;
@@ -1097,6 +1135,9 @@ int ntfs_file_open(struct inode *inode, struct file *file)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	if (unlikely((is_compressed(ni) || is_encrypted(ni)) &&
 		     (file->f_flags & O_DIRECT))) {
 		return -EOPNOTSUPP;
@@ -1138,7 +1179,8 @@ static int ntfs_file_release(struct inode *inode, struct file *file)
 		down_write(&ni->file.run_lock);
 
 		err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
-				    inode->i_size, &ni->i_valid, false, NULL);
+				    i_size_read(inode), &ni->i_valid, false,
+				    NULL);
 
 		up_write(&ni->file.run_lock);
 		ni_unlock(ni);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 3df2d9e34b91..7f27382e0ce2 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -778,7 +778,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	run_deallocate(sbi, &ni->attr_list.run, true);
 	run_close(&ni->attr_list.run);
 	ni->attr_list.size = 0;
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.dirty = false;
 
@@ -927,7 +927,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 	return 0;
 
 out:
-	kfree(ni->attr_list.le);
+	kvfree(ni->attr_list.le);
 	ni->attr_list.le = NULL;
 	ni->attr_list.size = 0;
 	return err;
@@ -2099,7 +2099,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page)
 	gfp_t gfp_mask;
 	struct page *pg;
 
-	if (vbo >= ni->vfs_inode.i_size) {
+	if (vbo >= i_size_read(&ni->vfs_inode)) {
 		SetPageUptodate(page);
 		err = 0;
 		goto out;
@@ -2173,7 +2173,7 @@ int ni_decompress_file(struct ntfs_inode *ni)
 {
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct inode *inode = &ni->vfs_inode;
-	loff_t i_size = inode->i_size;
+	loff_t i_size = i_size_read(inode);
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp_mask = mapping_gfp_mask(mapping);
 	struct page **pages = NULL;
@@ -2508,6 +2508,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 		err = -EOPNOTSUPP;
 		goto out1;
 #else
+		loff_t i_size = i_size_read(&ni->vfs_inode);
 		u32 frame_bits = ni_ext_compress_bits(ni);
 		u64 frame64 = frame_vbo >> frame_bits;
 		u64 frames, vbo_data;
@@ -2548,7 +2549,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			}
 		}
 
-		frames = (ni->vfs_inode.i_size - 1) >> frame_bits;
+		frames = (i_size - 1) >> frame_bits;
 
 		err = attr_wof_frame_info(ni, attr, run, frame64, frames,
 					  frame_bits, &ondisk_size, &vbo_data);
@@ -2556,8 +2557,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
 			goto out2;
 
 		if (frame64 == frames) {
-			unc_size = 1 + ((ni->vfs_inode.i_size - 1) &
-					(frame_size - 1));
+			unc_size = 1 + ((i_size - 1) & (frame_size - 1));
 			ondisk_size = attr_size(attr) - vbo_data;
 		} else {
 			unc_size = frame_size;
@@ -3259,6 +3259,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 	if (is_bad_inode(inode) || sb_rdonly(sb))
 		return 0;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (!ni_trylock(ni)) {
 		/* 'ni' is under modification, skip for now. */
 		mark_inode_dirty_sync(inode);
@@ -3288,7 +3291,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 			modified = true;
 		}
 
-		ts = inode_get_mtime(inode);
+		ts = inode_get_ctime(inode);
 		dup.c_time = kernel2nt(&ts);
 		if (std->c_time != dup.c_time) {
 			std->c_time = dup.c_time;
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 98ccb6650858..855519713bf7 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 {
 	const struct RESTART_AREA *ra;
 	u16 cl, fl, ul;
-	u32 off, l_size, file_dat_bits, file_size_round;
+	u32 off, l_size, seq_bits;
 	u16 ro = le16_to_cpu(rhdr->ra_off);
 	u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
 
@@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
 	/* Make sure the sequence number bits match the log file size. */
 	l_size = le64_to_cpu(ra->l_size);
 
-	file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
-	file_size_round = 1u << (file_dat_bits + 3);
-	if (file_size_round != l_size &&
-	    (file_size_round < l_size || (file_size_round / 2) > l_size)) {
-		return false;
+	seq_bits = sizeof(u64) * 8 + 3;
+	while (l_size) {
+		l_size >>= 1;
+		seq_bits -= 1;
 	}
 
+	if (seq_bits != ra->seq_num_bits)
+		return false;
+
 	/* The log page data offset and record header length must be quad-aligned. */
 	if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) ||
 	    !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8))
@@ -974,6 +976,16 @@ skip_looking:
 	return e;
 }
 
+struct restart_info {
+	u64 last_lsn;
+	struct RESTART_HDR *r_page;
+	u32 vbo;
+	bool chkdsk_was_run;
+	bool valid_page;
+	bool initialized;
+	bool restart;
+};
+
 #define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
 
 #define NTFSLOG_WRAPPED 0x00000001
@@ -987,6 +999,7 @@ struct ntfs_log {
 	struct ntfs_inode *ni;
 
 	u32 l_size;
+	u32 orig_file_size;
 	u32 sys_page_size;
 	u32 sys_page_mask;
 	u32 page_size;
@@ -1040,6 +1053,8 @@ struct ntfs_log {
 
 	struct CLIENT_ID client_id;
 	u32 client_undo_commit;
+
+	struct restart_info rst_info, rst_info2;
 };
 
 static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
@@ -1105,16 +1120,6 @@ static inline bool verify_client_lsn(struct ntfs_log *log,
 	       lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
 }
 
-struct restart_info {
-	u64 last_lsn;
-	struct RESTART_HDR *r_page;
-	u32 vbo;
-	bool chkdsk_was_run;
-	bool valid_page;
-	bool initialized;
-	bool restart;
-};
-
 static int read_log_page(struct ntfs_log *log, u32 vbo,
 			 struct RECORD_PAGE_HDR **buffer, bool *usa_error)
 {
@@ -1176,7 +1181,7 @@ out:
  * restart page header. It will stop the first time we find a
  * valid page header.
  */
-static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+static int log_read_rst(struct ntfs_log *log, bool first,
 			struct restart_info *info)
 {
 	u32 skip, vbo;
@@ -1192,7 +1197,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
 	}
 
 	/* Loop continuously until we succeed. */
-	for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+	for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) {
 		bool usa_error;
 		bool brst, bchk;
 		struct RESTART_AREA *ra;
@@ -1285,22 +1290,17 @@ check_result:
 /*
  * Ilog_init_pg_hdr - Init @log from restart page header.
  */
-static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
-			    u32 page_size, u16 major_ver, u16 minor_ver)
+static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver)
 {
-	log->sys_page_size = sys_page_size;
-	log->sys_page_mask = sys_page_size - 1;
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->sys_page_size = log->page_size;
+	log->sys_page_mask = log->page_mask;
 
 	log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
 	if (!log->clst_per_page)
 		log->clst_per_page = 1;
 
-	log->first_page = major_ver >= 2 ?
-				  0x22 * page_size :
-				  ((sys_page_size << 1) + (page_size << 1));
+	log->first_page = major_ver >= 2 ? 0x22 * log->page_size :
+					   4 * log->page_size;
 	log->major_ver = major_ver;
 	log->minor_ver = minor_ver;
 }
@@ -1308,12 +1308,11 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
 /*
  * log_create - Init @log in cases when we don't have a restart area to use.
  */
-static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+static void log_create(struct ntfs_log *log, const u64 last_lsn,
 		       u32 open_log_count, bool wrapped, bool use_multi_page)
 {
-	log->l_size = l_size;
 	/* All file offsets must be quadword aligned. */
-	log->file_data_bits = blksize_bits(l_size) - 3;
+	log->file_data_bits = blksize_bits(log->l_size) - 3;
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
 	log->seq_num = (last_lsn >> log->file_data_bits) + 2;
@@ -3720,10 +3719,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
 	struct ntfs_log *log;
 
-	struct restart_info rst_info, rst_info2;
-	u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0;
+	u64 rec_lsn, checkpt_lsn = 0, rlsn = 0;
 	struct ATTR_NAME_ENTRY *attr_names = NULL;
-	struct ATTR_NAME_ENTRY *ane;
 	struct RESTART_TABLE *dptbl = NULL;
 	struct RESTART_TABLE *trtbl = NULL;
 	const struct RESTART_TABLE *rt;
@@ -3741,9 +3738,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	struct TRANSACTION_ENTRY *tr;
 	struct DIR_PAGE_ENTRY *dp;
 	u32 i, bytes_per_attr_entry;
-	u32 l_size = ni->vfs_inode.i_size;
-	u32 orig_file_size = l_size;
-	u32 page_size, vbo, tail, off, dlen;
+	u32 vbo, tail, off, dlen;
 	u32 saved_len, rec_len, transact_id;
 	bool use_second_page;
 	struct RESTART_AREA *ra2, *ra = NULL;
@@ -3758,52 +3753,50 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	u16 t16;
 	u32 t32;
 
-	/* Get the size of page. NOTE: To replay we can use default page. */
-#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
-	page_size = norm_file_page(PAGE_SIZE, &l_size, true);
-#else
-	page_size = norm_file_page(PAGE_SIZE, &l_size, false);
-#endif
-	if (!page_size)
-		return -EINVAL;
-
 	log = kzalloc(sizeof(struct ntfs_log), GFP_NOFS);
 	if (!log)
 		return -ENOMEM;
 
 	log->ni = ni;
-	log->l_size = l_size;
-	log->one_page_buf = kmalloc(page_size, GFP_NOFS);
+	log->l_size = log->orig_file_size = ni->vfs_inode.i_size;
 
+	/* Get the size of page. NOTE: To replay we can use default page. */
+#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true);
+#else
+	log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, false);
+#endif
+	if (!log->page_size) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	log->one_page_buf = kmalloc(log->page_size, GFP_NOFS);
 	if (!log->one_page_buf) {
 		err = -ENOMEM;
 		goto out;
 	}
 
-	log->page_size = page_size;
-	log->page_mask = page_size - 1;
-	log->page_bits = blksize_bits(page_size);
+	log->page_mask = log->page_size - 1;
+	log->page_bits = blksize_bits(log->page_size);
 
 	/* Look for a restart area on the disk. */
-	memset(&rst_info, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, true, &rst_info);
+	err = log_read_rst(log, true, &log->rst_info);
 	if (err)
 		goto out;
 
 	/* remember 'initialized' */
-	*initialized = rst_info.initialized;
+	*initialized = log->rst_info.initialized;
 
-	if (!rst_info.restart) {
-		if (rst_info.initialized) {
+	if (!log->rst_info.restart) {
+		if (log->rst_info.initialized) {
 			/* No restart area but the file is not initialized. */
 			err = -EINVAL;
 			goto out;
 		}
 
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
-		log_create(log, l_size, 0, get_random_u32(), false, false);
-
-		log->ra = ra;
+		log_init_pg_hdr(log, 1, 1);
+		log_create(log, 0, get_random_u32(), false, false);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3820,25 +3813,26 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	 * If the restart offset above wasn't zero then we won't
 	 * look for a second restart.
 	 */
-	if (rst_info.vbo)
+	if (log->rst_info.vbo)
 		goto check_restart_area;
 
-	memset(&rst_info2, 0, sizeof(struct restart_info));
-	err = log_read_rst(log, l_size, false, &rst_info2);
+	err = log_read_rst(log, false, &log->rst_info2);
 	if (err)
 		goto out;
 
 	/* Determine which restart area to use. */
-	if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
+	if (!log->rst_info2.restart ||
+	    log->rst_info2.last_lsn <= log->rst_info.last_lsn)
 		goto use_first_page;
 
 	use_second_page = true;
 
-	if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) {
+	if (log->rst_info.chkdsk_was_run &&
+	    log->page_size != log->rst_info.vbo) {
 		struct RECORD_PAGE_HDR *sp = NULL;
 		bool usa_error;
 
-		if (!read_log_page(log, page_size, &sp, &usa_error) &&
+		if (!read_log_page(log, log->page_size, &sp, &usa_error) &&
 		    sp->rhdr.sign == NTFS_CHKD_SIGNATURE) {
 			use_second_page = false;
 		}
@@ -3846,52 +3840,43 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
 	}
 
 	if (use_second_page) {
-		kfree(rst_info.r_page);
-		memcpy(&rst_info, &rst_info2, sizeof(struct restart_info));
-		rst_info2.r_page = NULL;
+		kfree(log->rst_info.r_page);
+		memcpy(&log->rst_info, &log->rst_info2,
+		       sizeof(struct restart_info));
+		log->rst_info2.r_page = NULL;
 	}
 
 use_first_page:
-	kfree(rst_info2.r_page);
+	kfree(log->rst_info2.r_page);
 
 check_restart_area:
 	/*
 	 * If the restart area is at offset 0, we want
 	 * to write the second restart area first.
 	 */
-	log->init_ra = !!rst_info.vbo;
+	log->init_ra = !!log->rst_info.vbo;
 
 	/* If we have a valid page then grab a pointer to the restart area. */
-	ra2 = rst_info.valid_page ?
-		      Add2Ptr(rst_info.r_page,
-			      le16_to_cpu(rst_info.r_page->ra_off)) :
+	ra2 = log->rst_info.valid_page ?
+		      Add2Ptr(log->rst_info.r_page,
+			      le16_to_cpu(log->rst_info.r_page->ra_off)) :
 		      NULL;
 
-	if (rst_info.chkdsk_was_run ||
+	if (log->rst_info.chkdsk_was_run ||
 	    (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) {
 		bool wrapped = false;
 		bool use_multi_page = false;
 		u32 open_log_count;
 
 		/* Do some checks based on whether we have a valid log page. */
-		if (!rst_info.valid_page) {
-			open_log_count = get_random_u32();
-			goto init_log_instance;
-		}
-		open_log_count = le32_to_cpu(ra2->open_log_count);
-
-		/*
-		 * If the restart page size isn't changing then we want to
-		 * check how much work we need to do.
-		 */
-		if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size))
-			goto init_log_instance;
+		open_log_count = log->rst_info.valid_page ?
+					 le32_to_cpu(ra2->open_log_count) :
+					 get_random_u32();
 
-init_log_instance:
-		log_init_pg_hdr(log, page_size, page_size, 1, 1);
+		log_init_pg_hdr(log, 1, 1);
 
-		log_create(log, l_size, rst_info.last_lsn, open_log_count,
-			   wrapped, use_multi_page);
+		log_create(log, log->rst_info.last_lsn, open_log_count, wrapped,
+			   use_multi_page);
 
 		ra = log_create_ra(log);
 		if (!ra) {
@@ -3916,28 +3901,27 @@ init_log_instance:
 	 * use the log file. We must use the system page size instead of the
 	 * default size if there is not a clean shutdown.
 	 */
-	t32 = le32_to_cpu(rst_info.r_page->sys_page_size);
-	if (page_size != t32) {
-		l_size = orig_file_size;
-		page_size =
-			norm_file_page(t32, &l_size, t32 == DefaultLogPageSize);
+	t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size);
+	if (log->page_size != t32) {
+		log->l_size = log->orig_file_size;
+		log->page_size = norm_file_page(t32, &log->l_size,
+						t32 == DefaultLogPageSize);
 	}
 
-	if (page_size != t32 ||
-	    page_size != le32_to_cpu(rst_info.r_page->page_size)) {
+	if (log->page_size != t32 ||
+	    log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
 	/* If the file size has shrunk then we won't mount it. */
-	if (l_size < le64_to_cpu(ra2->l_size)) {
+	if (log->l_size < le64_to_cpu(ra2->l_size)) {
 		err = -EINVAL;
 		goto out;
 	}
 
-	log_init_pg_hdr(log, page_size, page_size,
-			le16_to_cpu(rst_info.r_page->major_ver),
-			le16_to_cpu(rst_info.r_page->minor_ver));
+	log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver),
+			le16_to_cpu(log->rst_info.r_page->minor_ver));
 
 	log->l_size = le64_to_cpu(ra2->l_size);
 	log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits);
@@ -3945,7 +3929,7 @@ init_log_instance:
 	log->seq_num_mask = (8 << log->file_data_bits) - 1;
 	log->last_lsn = le64_to_cpu(ra2->current_lsn);
 	log->seq_num = log->last_lsn >> log->file_data_bits;
-	log->ra_off = le16_to_cpu(rst_info.r_page->ra_off);
+	log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off);
 	log->restart_size = log->sys_page_size - log->ra_off;
 	log->record_header_len = le16_to_cpu(ra2->rec_hdr_len);
 	log->ra_size = le16_to_cpu(ra2->ra_len);
@@ -4045,7 +4029,7 @@ find_oldest:
 	log->current_avail = current_log_avail(log);
 
 	/* Remember which restart area to write first. */
-	log->init_ra = rst_info.vbo;
+	log->init_ra = log->rst_info.vbo;
 
 process_log:
 	/* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */
@@ -4105,7 +4089,7 @@ process_log:
 	log->client_id.seq_num = cr->seq_num;
 	log->client_id.client_idx = client;
 
-	err = read_rst_area(log, &rst, &ra_lsn);
+	err = read_rst_area(log, &rst, &checkpt_lsn);
 	if (err)
 		goto out;
 
@@ -4114,9 +4098,8 @@ process_log:
 
 	bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28;
 
-	checkpt_lsn = le64_to_cpu(rst->check_point_start);
-	if (!checkpt_lsn)
-		checkpt_lsn = ra_lsn;
+	if (rst->check_point_start)
+		checkpt_lsn = le64_to_cpu(rst->check_point_start);
 
 	/* Allocate and Read the Transaction Table. */
 	if (!rst->transact_table_len)
@@ -4330,23 +4313,20 @@ check_attr_table:
 	lcb = NULL;
 
 check_attribute_names2:
-	if (!rst->attr_names_len)
-		goto trace_attribute_table;
-
-	ane = attr_names;
-	if (!oatbl)
-		goto trace_attribute_table;
-	while (ane->off) {
-		/* TODO: Clear table on exit! */
-		oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
-		t16 = le16_to_cpu(ane->name_bytes);
-		oe->name_len = t16 / sizeof(short);
-		oe->ptr = ane->name;
-		oe->is_attr_name = 2;
-		ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16);
-	}
-
-trace_attribute_table:
+	if (rst->attr_names_len && oatbl) {
+		struct ATTR_NAME_ENTRY *ane = attr_names;
+		while (ane->off) {
+			/* TODO: Clear table on exit! */
+			oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
+			t16 = le16_to_cpu(ane->name_bytes);
+			oe->name_len = t16 / sizeof(short);
+			oe->ptr = ane->name;
+			oe->is_attr_name = 2;
+			ane = Add2Ptr(ane,
+				      sizeof(struct ATTR_NAME_ENTRY) + t16);
+		}
+	}
+
 	/*
 	 * If the checkpt_lsn is zero, then this is a freshly
 	 * formatted disk and we have no work to do.
@@ -5189,7 +5169,7 @@ out:
 	kfree(oatbl);
 	kfree(dptbl);
 	kfree(attr_names);
-	kfree(rst_info.r_page);
+	kfree(log->rst_info.r_page);
 
 	kfree(ra);
 	kfree(log->one_page_buf);
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index fbfe21dbb425..ae2ef5c11868 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -853,7 +853,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
 	/*
 	 * sb can be NULL here. In this case sbi->flags should be 0 too.
 	 */
-	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR))
+	if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) ||
+	    unlikely(ntfs3_forced_shutdown(sb)))
 		return;
 
 	blocksize = sb->s_blocksize;
@@ -1006,6 +1007,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes)
 	return cpu_to_le32(hash);
 }
 
+/*
+ * simple wrapper for sb_bread_unmovable.
+ */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block)
+{
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+	struct buffer_head *bh;
+
+	if (unlikely(block >= sbi->volume.blocks)) {
+		/* prevent generic message "attempt to access beyond end of device" */
+		ntfs_err(sb, "try to read out of volume at offset 0x%llx",
+			 (u64)block << sb->s_blocksize_bits);
+		return NULL;
+	}
+
+	bh = sb_bread_unmovable(sb, block);
+	if (bh)
+		return bh;
+
+	ntfs_err(sb, "failed to read volume at offset 0x%llx",
+		 (u64)block << sb->s_blocksize_bits);
+	return NULL;
+}
+
 int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer)
 {
 	struct block_device *bdev = sb->s_bdev;
@@ -2128,8 +2153,8 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi,
 			if (le32_to_cpu(d_security->size) == new_sec_size &&
 			    d_security->key.hash == hash_key.hash &&
 			    !memcmp(d_security + 1, sd, size_sd)) {
-				*security_id = d_security->key.sec_id;
 				/* Such security already exists. */
+				*security_id = d_security->key.sec_id;
 				err = 0;
 				goto out;
 			}
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index cf92b2433f7a..daabaad63aaf 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1462,7 +1462,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 		goto out2;
 
 	if (in->name == I30_NAME) {
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 		inode_set_bytes(&ni->vfs_inode, alloc_size);
 	}
 
@@ -1544,7 +1544,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
 	}
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = data_size;
+		i_size_write(&ni->vfs_inode, data_size);
 
 	*vbn = bit << indx->idx2vbn_bits;
 
@@ -2090,7 +2090,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni,
 		return err;
 
 	if (in->name == I30_NAME)
-		ni->vfs_inode.i_size = new_data;
+		i_size_write(&ni->vfs_inode, new_data);
 
 	bpb = bitmap_size(bit);
 	if (bpb * 8 == nbits)
@@ -2576,7 +2576,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni,
 		err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len,
 				    &indx->alloc_run, 0, NULL, false, NULL);
 		if (in->name == I30_NAME)
-			ni->vfs_inode.i_size = 0;
+			i_size_write(&ni->vfs_inode, 0);
 
 		err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len,
 				     false, NULL);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 5e3d71374918..eb7a8c9fba01 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -345,9 +345,7 @@ next_attr:
 			inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer
 							    .PrintNameLength) /
 					sizeof(u16);
-
 			ni->i_valid = inode->i_size;
-
 			/* Clear directory bit. */
 			if (ni->ni_flags & NI_FLAG_DIR) {
 				indx_clear(&ni->dir);
@@ -412,7 +410,6 @@ end_enum:
 		goto out;
 
 	if (!is_match && name) {
-		/* Reuse rec as buffer for ascii name. */
 		err = -ENOENT;
 		goto out;
 	}
@@ -427,6 +424,7 @@ end_enum:
 
 	if (names != le16_to_cpu(rec->hard_links)) {
 		/* Correct minor error on the fly. Do not mark inode as dirty. */
+		ntfs_inode_warn(inode, "Correct links count -> %u.", names);
 		rec->hard_links = cpu_to_le16(names);
 		ni->mi.dirty = true;
 	}
@@ -653,9 +651,10 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo,
 			off = vbo & (PAGE_SIZE - 1);
 			folio_set_bh(bh, folio, off);
 
-			err = bh_read(bh, 0);
-			if (err < 0)
+			if (bh_read(bh, 0) < 0) {
+				err = -EIO;
 				goto out;
+			}
 			folio_zero_segment(folio, off + voff, off + block_size);
 		}
 	}
@@ -853,9 +852,13 @@ static int ntfs_resident_writepage(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
 	struct address_space *mapping = data;
-	struct ntfs_inode *ni = ntfs_i(mapping->host);
+	struct inode *inode = mapping->host;
+	struct ntfs_inode *ni = ntfs_i(inode);
 	int ret;
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	ni_lock(ni);
 	ret = attr_data_write_resident(ni, &folio->page);
 	ni_unlock(ni);
@@ -869,7 +872,12 @@ static int ntfs_resident_writepage(struct folio *folio,
 static int ntfs_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
-	if (is_resident(ntfs_i(mapping->host)))
+	struct inode *inode = mapping->host;
+
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
+	if (is_resident(ntfs_i(inode)))
 		return write_cache_pages(mapping, wbc, ntfs_resident_writepage,
 					 mapping);
 	return mpage_writepages(mapping, wbc, ntfs_get_block);
@@ -889,6 +897,9 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	*pagep = NULL;
 	if (is_resident(ni)) {
 		struct page *page =
@@ -974,7 +985,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
 		}
 
 		if (pos + err > inode->i_size) {
-			inode->i_size = pos + err;
+			i_size_write(inode, pos + err);
 			dirty = true;
 		}
 
@@ -1306,6 +1317,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
 		goto out1;
 	}
 
+	if (unlikely(ntfs3_forced_shutdown(sb))) {
+		err = -EIO;
+		goto out2;
+	}
+
 	/* Mark rw ntfs as dirty. it will be cleared at umount. */
 	ntfs_set_state(sbi, NTFS_DIRTY_DIRTY);
 
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ee3093be5170..084d19d78397 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -181,6 +181,9 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -199,6 +202,9 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	u32 size = strlen(symname);
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0,
 				  symname, size, NULL);
 
@@ -227,6 +233,9 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ntfs_inode *ni = ntfs_i(dir);
 	int err;
 
+	if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+		return -EIO;
+
 	ni_lock_dir(ni);
 
 	err = ntfs_unlink_inode(dir, dentry);
@@ -264,6 +273,9 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir,
 		      1024);
 	static_assert(PATH_MAX >= 4 * 1024);
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
 
@@ -419,7 +431,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	 * fnd contains tree's path to insert to.
 	 * If fnd is not NULL then dir is locked.
 	 */
-	inode = ntfs_create_inode(mnt_idmap(file->f_path.mnt), dir, dentry, uni,
+	inode = ntfs_create_inode(file_mnt_idmap(file), dir, dentry, uni,
 				  mode, 0, NULL, 0, fnd);
 	err = IS_ERR(inode) ? PTR_ERR(inode) :
 			      finish_open(file, dentry, ntfs_file_open);
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 86aecbb01a92..9c7478150a03 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,12 +523,10 @@ struct ATTR_LIST_ENTRY {
 	__le64 vcn;		// 0x08: Starting VCN of this attribute.
 	struct MFT_REF ref;	// 0x10: MFT record number with attribute.
 	__le16 id;		// 0x18: struct ATTRIB ID.
-	__le16 name[3];		// 0x1A: Just to align. To get real name can use bNameOffset.
+	__le16 name[];		// 0x1A: To get real name use name_off.
 
 }; // sizeof(0x20)
 
-static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20);
-
 static inline u32 le_size(u8 name_len)
 {
 	return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) +
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index f6706143d14b..79356fd29a14 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -61,6 +61,8 @@ enum utf16_endian;
 
 /* sbi->flags */
 #define NTFS_FLAGS_NODISCARD		0x00000001
+/* ntfs in shutdown state. */
+#define NTFS_FLAGS_SHUTDOWN_BIT		0x00000002  /* == 4*/
 /* Set when LogFile is replaying. */
 #define NTFS_FLAGS_LOG_REPLAYING	0x00000008
 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -226,7 +228,7 @@ struct ntfs_sb_info {
 	u64 maxbytes; // Maximum size for normal files.
 	u64 maxbytes_sparse; // Maximum size for sparse file.
 
-	u32 flags; // See NTFS_FLAGS_XXX.
+	unsigned long flags; // See NTFS_FLAGS_
 
 	CLST zone_max; // Maximum MFT zone length in clusters
 	CLST bad_clusters; // The count of marked bad clusters.
@@ -473,7 +475,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
 int al_update(struct ntfs_inode *ni, int sync);
 static inline size_t al_aligned(size_t size)
 {
-	return (size + 1023) & ~(size_t)1023;
+	return size_add(size, 1023) & ~(size_t)1023;
 }
 
 /* Globals from bitfunc.c */
@@ -500,6 +502,8 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 int ntfs_file_open(struct inode *inode, struct file *file);
 int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len);
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg);
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg);
 extern const struct inode_operations ntfs_special_inode_operations;
 extern const struct inode_operations ntfs_file_inode_operations;
 extern const struct file_operations ntfs_file_operations;
@@ -584,6 +588,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes);
 int log_replay(struct ntfs_inode *ni, bool *initialized);
 
 /* Globals from fsntfs.c */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block);
 bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes);
 int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
 		       bool simple);
@@ -872,7 +877,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode,
 
 int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry);
 ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-extern const struct xattr_handler * const ntfs_xattr_handlers[];
+extern const struct xattr_handler *const ntfs_xattr_handlers[];
 
 int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size);
 void ntfs_get_wsl_perm(struct inode *inode);
@@ -999,6 +1004,11 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+static inline int ntfs3_forced_shutdown(struct super_block *sb)
+{
+	return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
+}
+
 /*
  * ntfs_up_cluster - Align up on cluster boundary.
  */
@@ -1025,19 +1035,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
 	return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
 }
 
-static inline struct buffer_head *ntfs_bread(struct super_block *sb,
-					     sector_t block)
-{
-	struct buffer_head *bh = sb_bread(sb, block);
-
-	if (bh)
-		return bh;
-
-	ntfs_err(sb, "failed to read volume at offset 0x%llx",
-		 (u64)block << sb->s_blocksize_bits);
-	return NULL;
-}
-
 static inline struct ntfs_inode *ntfs_i(struct inode *inode)
 {
 	return container_of(inode, struct ntfs_inode, vfs_inode);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 53629b1f65e9..6aa3a9d44df1 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -279,7 +279,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 		if (t16 > asize)
 			return NULL;
 
-		if (t16 + le32_to_cpu(attr->res.data_size) > asize)
+		if (le32_to_cpu(attr->res.data_size) > asize - t16)
 			return NULL;
 
 		t32 = sizeof(short) * attr->name_len;
@@ -535,8 +535,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 		return false;
 
 	if (ni && is_attr_indexed(attr)) {
-		le16_add_cpu(&ni->mi.mrec->hard_links, -1);
-		ni->mi.dirty = true;
+		u16 links = le16_to_cpu(ni->mi.mrec->hard_links);
+		struct ATTR_FILE_NAME *fname =
+			attr->type != ATTR_NAME ?
+				NULL :
+				resident_data_ex(attr,
+						 SIZEOF_ATTRIBUTE_FILENAME);
+		if (fname && fname->type == FILE_NAME_DOS) {
+			/* Do not decrease links count deleting DOS name. */
+		} else if (!links) {
+			/* minor error. Not critical. */
+		} else {
+			ni->mi.mrec->hard_links = cpu_to_le16(links - 1);
+			ni->mi.dirty = true;
+		}
 	}
 
 	used -= asize;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 9153dffde950..cef5467fd928 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -122,13 +122,12 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
 
 	if (name) {
 		struct dentry *de = d_find_alias(inode);
-		const u32 name_len = ARRAY_SIZE(s_name_buf) - 1;
 
 		if (de) {
 			spin_lock(&de->d_lock);
-			snprintf(name, name_len, " \"%s\"", de->d_name.name);
+			snprintf(name, sizeof(s_name_buf), " \"%s\"",
+				 de->d_name.name);
 			spin_unlock(&de->d_lock);
-			name[name_len] = 0; /* To be sure. */
 		} else {
 			name[0] = 0;
 		}
@@ -625,7 +624,7 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 {
 	kfree(sbi->new_rec);
 	kvfree(ntfs_put_shared(sbi->upcase));
-	kfree(sbi->def_table);
+	kvfree(sbi->def_table);
 	kfree(sbi->compress.lznt);
 #ifdef CONFIG_NTFS3_LZX_XPRESS
 	xpress_free_decompressor(sbi->compress.xpress);
@@ -715,6 +714,14 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
 }
 
 /*
+ * ntfs_shutdown - super_operations::shutdown
+ */
+static void ntfs_shutdown(struct super_block *sb)
+{
+	set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
+}
+
+/*
  * ntfs_sync_fs - super_operations::sync_fs
  */
 static int ntfs_sync_fs(struct super_block *sb, int wait)
@@ -724,6 +731,9 @@ static int ntfs_sync_fs(struct super_block *sb, int wait)
 	struct ntfs_inode *ni;
 	struct inode *inode;
 
+	if (unlikely(ntfs3_forced_shutdown(sb)))
+		return -EIO;
+
 	ni = sbi->security.ni;
 	if (ni) {
 		inode = &ni->vfs_inode;
@@ -763,6 +773,7 @@ static const struct super_operations ntfs_sops = {
 	.put_super = ntfs_put_super,
 	.statfs = ntfs_statfs,
 	.show_options = ntfs_show_options,
+	.shutdown = ntfs_shutdown,
 	.sync_fs = ntfs_sync_fs,
 	.write_inode = ntfs3_write_inode,
 };
@@ -866,6 +877,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 	u16 fn, ao;
 	u8 cluster_bits;
 	u32 boot_off = 0;
+	sector_t boot_block = 0;
 	const char *hint = "Primary boot";
 
 	/* Save original dev_size. Used with alternative boot. */
@@ -873,11 +885,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
 
 	sbi->volume.blocks = dev_size >> PAGE_SHIFT;
 
-	bh = ntfs_bread(sb, 0);
+read_boot:
+	bh = ntfs_bread(sb, boot_block);
 	if (!bh)
-		return -EIO;
+		return boot_block ? -EINVAL : -EIO;
 
-check_boot:
 	err = -EINVAL;
 
 	/* Corrupted image; do not read OOB */
@@ -1108,26 +1120,24 @@ check_boot:
 	}
 
 out:
-	if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
+	brelse(bh);
+
+	if (err == -EINVAL && !boot_block && dev_size0 > PAGE_SHIFT) {
 		u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
 		u64 lbo = dev_size0 - sizeof(*boot);
 
-		/*
-	 	 * Try alternative boot (last sector)
-		 */
-		brelse(bh);
-
-		sb_set_blocksize(sb, block_size);
-		bh = ntfs_bread(sb, lbo >> blksize_bits(block_size));
-		if (!bh)
-			return -EINVAL;
-
+		boot_block = lbo >> blksize_bits(block_size);
 		boot_off = lbo & (block_size - 1);
-		hint = "Alternative boot";
-		dev_size = dev_size0; /* restore original size. */
-		goto check_boot;
+		if (boot_block && block_size >= boot_off + sizeof(*boot)) {
+			/*
+			 * Try alternative boot (last sector)
+			 */
+			sb_set_blocksize(sb, block_size);
+			hint = "Alternative boot";
+			dev_size = dev_size0; /* restore original size. */
+			goto read_boot;
+		}
 	}
-	brelse(bh);
 
 	return err;
 }
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 4274b6f31cfa..53e7d1fa036a 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -219,6 +219,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
 		if (!ea->name_len)
 			break;
 
+		if (ea->name_len > ea_size)
+			break;
+
 		if (buffer) {
 			/* Check if we can use field ea->name */
 			if (off + ea_size > size)
@@ -744,6 +747,9 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
 	int err;
 	struct ntfs_inode *ni = ntfs_i(inode);
 
+	if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+		return -EIO;
+
 	/* Dispatch request. */
 	if (!strcmp(name, SYSTEM_DOS_ATTRIB)) {
 		/* system.dos_attrib */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4d7efefa98c5..1bde1281d514 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -213,7 +213,7 @@ struct o2hb_region {
 	unsigned int		hr_num_pages;
 
 	struct page             **hr_slot_data;
-	struct bdev_handle	*hr_bdev_handle;
+	struct file		*hr_bdev_file;
 	struct o2hb_disk_slot	*hr_slots;
 
 	/* live node map of this region */
@@ -263,7 +263,7 @@ struct o2hb_region {
 
 static inline struct block_device *reg_bdev(struct o2hb_region *reg)
 {
-	return reg->hr_bdev_handle ? reg->hr_bdev_handle->bdev : NULL;
+	return reg->hr_bdev_file ? file_bdev(reg->hr_bdev_file) : NULL;
 }
 
 struct o2hb_bio_wait_ctxt {
@@ -1509,8 +1509,8 @@ static void o2hb_region_release(struct config_item *item)
 		kfree(reg->hr_slot_data);
 	}
 
-	if (reg->hr_bdev_handle)
-		bdev_release(reg->hr_bdev_handle);
+	if (reg->hr_bdev_file)
+		fput(reg->hr_bdev_file);
 
 	kfree(reg->hr_slots);
 
@@ -1569,7 +1569,7 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
 	unsigned long block_bytes;
 	unsigned int block_bits;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	status = o2hb_read_block_input(reg, page, &block_bytes,
@@ -1598,7 +1598,7 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item,
 	char *p = (char *)page;
 	ssize_t ret;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	ret = kstrtoull(p, 0, &tmp);
@@ -1623,7 +1623,7 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item,
 	unsigned long tmp;
 	char *p = (char *)page;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		return -EINVAL;
 
 	tmp = simple_strtoul(p, &p, 0);
@@ -1642,7 +1642,7 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
 {
 	unsigned int ret = 0;
 
-	if (to_o2hb_region(item)->hr_bdev_handle)
+	if (to_o2hb_region(item)->hr_bdev_file)
 		ret = sprintf(page, "%pg\n", reg_bdev(to_o2hb_region(item)));
 
 	return ret;
@@ -1753,7 +1753,7 @@ out:
 }
 
 /*
- * this is acting as commit; we set up all of hr_bdev_handle and hr_task or
+ * this is acting as commit; we set up all of hr_bdev_file and hr_task or
  * nothing
  */
 static ssize_t o2hb_region_dev_store(struct config_item *item,
@@ -1769,7 +1769,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	ssize_t ret = -EINVAL;
 	int live_threshold;
 
-	if (reg->hr_bdev_handle)
+	if (reg->hr_bdev_file)
 		goto out;
 
 	/* We can't heartbeat without having had our node number
@@ -1795,11 +1795,11 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	if (!S_ISBLK(f.file->f_mapping->host->i_mode))
 		goto out2;
 
-	reg->hr_bdev_handle = bdev_open_by_dev(f.file->f_mapping->host->i_rdev,
+	reg->hr_bdev_file = bdev_file_open_by_dev(f.file->f_mapping->host->i_rdev,
 			BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(reg->hr_bdev_handle)) {
-		ret = PTR_ERR(reg->hr_bdev_handle);
-		reg->hr_bdev_handle = NULL;
+	if (IS_ERR(reg->hr_bdev_file)) {
+		ret = PTR_ERR(reg->hr_bdev_file);
+		reg->hr_bdev_file = NULL;
 		goto out2;
 	}
 
@@ -1903,8 +1903,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 
 out3:
 	if (ret < 0) {
-		bdev_release(reg->hr_bdev_handle);
-		reg->hr_bdev_handle = NULL;
+		fput(reg->hr_bdev_file);
+		reg->hr_bdev_file = NULL;
 	}
 out2:
 	fdput(f);
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index f37174e79fad..6de944818c56 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -27,7 +27,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 	struct ocfs2_file_private *fp = file->private_data;
 	struct ocfs2_lock_res *lockres = &fp->fp_flock;
 
-	if (fl->fl_type == F_WRLCK)
+	if (lock_is_write(fl))
 		level = 1;
 	if (!IS_SETLKW(cmd))
 		trylock = 1;
@@ -53,8 +53,8 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 */
 
 		locks_init_lock(&request);
-		request.fl_type = F_UNLCK;
-		request.fl_flags = FL_FLOCK;
+		request.c.flc_type = F_UNLCK;
+		request.c.flc_flags = FL_FLOCK;
 		locks_lock_file_wait(file, &request);
 
 		ocfs2_file_unlock(file);
@@ -100,14 +100,14 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!(fl->fl_flags & FL_FLOCK))
+	if (!(fl->c.flc_flags & FL_FLOCK))
 		return -ENOLCK;
 
 	if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) ||
 	    ocfs2_mount_local(osb))
 		return locks_lock_file_wait(file, fl);
 
-	if (fl->fl_type == F_UNLCK)
+	if (lock_is_unlock(fl))
 		return ocfs2_do_funlock(file, cmd, fl);
 	else
 		return ocfs2_do_flock(file, inode, cmd, fl);
@@ -118,7 +118,7 @@ int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 	struct inode *inode = file->f_mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!(fl->fl_flags & FL_POSIX))
+	if (!(fl->c.flc_flags & FL_POSIX))
 		return -ENOLCK;
 
 	return ocfs2_plock(osb->cconn, OCFS2_I(inode)->ip_blkno, file, cmd, fl);
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 9b76ee66aeb2..c11406cd87a8 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -744,7 +744,7 @@ static int user_plock(struct ocfs2_cluster_connection *conn,
 		return dlm_posix_cancel(conn->cc_lockspace, ino, file, fl);
 	else if (IS_GETLK(cmd))
 		return dlm_posix_get(conn->cc_lockspace, ino, file, fl);
-	else if (fl->fl_type == F_UNLCK)
+	else if (lock_is_unlock(fl))
 		return dlm_posix_unlock(conn->cc_lockspace, ino, file, fl);
 	else
 		return dlm_posix_lock(conn->cc_lockspace, ino, file, cmd, fl);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 6b906424902b..a70aff17d455 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2027,8 +2027,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
 	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
 	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);
-	memcpy(&sb->s_uuid, di->id2.i_super.s_uuid,
-	       sizeof(di->id2.i_super.s_uuid));
+	super_set_uuid(sb, di->id2.i_super.s_uuid,
+		       sizeof(di->id2.i_super.s_uuid));
 
 	osb->osb_dx_mask = (1 << (cbits - bbits)) - 1;
 
diff --git a/fs/open.c b/fs/open.c
index a84d21e55c39..a7d4bb2c725f 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -154,49 +154,52 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length
 }
 #endif
 
-long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+long do_ftruncate(struct file *file, loff_t length, int small)
 {
 	struct inode *inode;
 	struct dentry *dentry;
-	struct fd f;
 	int error;
 
-	error = -EINVAL;
-	if (length < 0)
-		goto out;
-	error = -EBADF;
-	f = fdget(fd);
-	if (!f.file)
-		goto out;
-
 	/* explicitly opened as large or we are on 64-bit box */
-	if (f.file->f_flags & O_LARGEFILE)
+	if (file->f_flags & O_LARGEFILE)
 		small = 0;
 
-	dentry = f.file->f_path.dentry;
+	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
-	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
-		goto out_putf;
+	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
+		return -EINVAL;
 
-	error = -EINVAL;
 	/* Cannot ftruncate over 2^31 bytes without large file support */
 	if (small && length > MAX_NON_LFS)
-		goto out_putf;
+		return -EINVAL;
 
-	error = -EPERM;
 	/* Check IS_APPEND on real upper inode */
-	if (IS_APPEND(file_inode(f.file)))
-		goto out_putf;
+	if (IS_APPEND(file_inode(file)))
+		return -EPERM;
 	sb_start_write(inode->i_sb);
-	error = security_file_truncate(f.file);
+	error = security_file_truncate(file);
 	if (!error)
-		error = do_truncate(file_mnt_idmap(f.file), dentry, length,
-				    ATTR_MTIME | ATTR_CTIME, f.file);
+		error = do_truncate(file_mnt_idmap(file), dentry, length,
+				    ATTR_MTIME | ATTR_CTIME, file);
 	sb_end_write(inode->i_sb);
-out_putf:
+
+	return error;
+}
+
+long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+{
+	struct fd f;
+	int error;
+
+	if (length < 0)
+		return -EINVAL;
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = do_ftruncate(f.file, length, small);
+
 	fdput(f);
-out:
 	return error;
 }
 
@@ -1364,7 +1367,7 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 {
 	struct filename *name = getname_kernel(filename);
 	struct file *file = ERR_CAST(name);
-	
+
 	if (!IS_ERR(name)) {
 		file = file_open_name(name, flags, mode);
 		putname(name);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index c4b65a6d41cc..4a0779e3ef79 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -446,7 +446,7 @@ static int __init init_openprom_fs(void)
 					    sizeof(struct op_inode_info),
 					    0,
 					    (SLAB_RECLAIM_ACCOUNT |
-					     SLAB_MEM_SPREAD | SLAB_ACCOUNT),
+					     SLAB_ACCOUNT),
 					    op_inode_init_once);
 	if (!op_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b8e25ca51016..8586e2f5d243 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -265,20 +265,18 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 	if (IS_ERR(old_file))
 		return PTR_ERR(old_file);
 
+	/* Try to use clone_file_range to clone up within the same fs */
+	cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0);
+	if (cloned == len)
+		goto out_fput;
+
+	/* Couldn't clone, so now we try to copy the data */
 	error = rw_verify_area(READ, old_file, &old_pos, len);
 	if (!error)
 		error = rw_verify_area(WRITE, new_file, &new_pos, len);
 	if (error)
 		goto out_fput;
 
-	/* Try to use clone_file_range to clone up within the same fs */
-	ovl_start_write(dentry);
-	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
-	ovl_end_write(dentry);
-	if (cloned == len)
-		goto out_fput;
-	/* Couldn't clone, so now we try to copy the data */
-
 	/* Check if lower fs supports seek operation */
 	if (old_file->f_mode & FMODE_LSEEK)
 		skip_hole = true;
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 112b4b12f825..36dcc530ac28 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -280,12 +280,20 @@ static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path,
 {
 	struct ovl_fs_context *ctx = fc->fs_private;
 
-	if (ovl_dentry_weird(path->dentry))
-		return invalfc(fc, "filesystem on %s not supported", name);
-
 	if (!d_is_dir(path->dentry))
 		return invalfc(fc, "%s is not a directory", name);
 
+	/*
+	 * Root dentries of case-insensitive capable filesystems might
+	 * not have the dentry operations set, but still be incompatible
+	 * with overlayfs.  Check explicitly to prevent post-mount
+	 * failures.
+	 */
+	if (sb_has_encoding(path->mnt->mnt_sb))
+		return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name);
+
+	if (ovl_dentry_weird(path->dentry))
+		return invalfc(fc, "filesystem on %s not supported", name);
 
 	/*
 	 * Check whether upper path is read-only here to report failures
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 2eef6c70b2ae..36d4b8b1f784 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -28,41 +28,38 @@ MODULE_LICENSE("GPL");
 
 struct ovl_dir_cache;
 
-static struct dentry *ovl_d_real(struct dentry *dentry,
-				 const struct inode *inode)
+static struct dentry *ovl_d_real(struct dentry *dentry, enum d_real_type type)
 {
-	struct dentry *real = NULL, *lower;
+	struct dentry *upper, *lower;
 	int err;
 
-	/*
-	 * vfs is only expected to call d_real() with NULL from d_real_inode()
-	 * and with overlay inode from file_dentry() on an overlay file.
-	 *
-	 * TODO: remove @inode argument from d_real() API, remove code in this
-	 * function that deals with non-NULL @inode and remove d_real() call
-	 * from file_dentry().
-	 */
-	if (inode && d_inode(dentry) == inode)
-		return dentry;
-	else if (inode)
+	switch (type) {
+	case D_REAL_DATA:
+	case D_REAL_METADATA:
+		break;
+	default:
 		goto bug;
+	}
 
 	if (!d_is_reg(dentry)) {
 		/* d_real_inode() is only relevant for regular files */
 		return dentry;
 	}
 
-	real = ovl_dentry_upper(dentry);
-	if (real && (inode == d_inode(real)))
-		return real;
+	upper = ovl_dentry_upper(dentry);
+	if (upper && (type == D_REAL_METADATA ||
+		      ovl_has_upperdata(d_inode(dentry))))
+		return upper;
 
-	if (real && !inode && ovl_has_upperdata(d_inode(dentry)))
-		return real;
+	if (type == D_REAL_METADATA) {
+		lower = ovl_dentry_lower(dentry);
+		goto real_lower;
+	}
 
 	/*
-	 * Best effort lazy lookup of lowerdata for !inode case to return
+	 * Best effort lazy lookup of lowerdata for D_REAL_DATA case to return
 	 * the real lowerdata dentry.  The only current caller of d_real() with
-	 * NULL inode is d_real_inode() from trace_uprobe and this caller is
+	 * D_REAL_DATA is d_real_inode() from trace_uprobe and this caller is
 	 * likely going to be followed reading from the file, before placing
 	 * uprobes on offset within the file, so lowerdata should be available
 	 * when setting the uprobe.
@@ -73,18 +70,13 @@ static struct dentry *ovl_d_real(struct dentry *dentry,
 	lower = ovl_dentry_lowerdata(dentry);
 	if (!lower)
 		goto bug;
-	real = lower;
 
-	/* Handle recursion */
-	real = d_real(real, inode);
+real_lower:
+	/* Handle recursion into stacked lower fs */
+	return d_real(lower, type);
 
-	if (!inode || inode == d_inode(real))
-		return real;
 bug:
-	WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n",
-	     __func__, dentry, inode ? inode->i_sb->s_id : "NULL",
-	     inode ? inode->i_ino : 0, real,
-	     real && d_inode(real) ? d_inode(real)->i_ino : 0);
+	WARN(1, "%s(%pd4, %d): real dentry not found\n", __func__, dentry, type);
 	return dentry;
 }
 
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index a8e17f14d7a2..d285d1d7baad 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -774,13 +774,14 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 			 const struct path *upperpath)
 {
 	bool set = false;
+	uuid_t uuid;
 	int res;
 
 	/* Try to load existing persistent uuid */
-	res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, sb->s_uuid.b,
+	res = ovl_path_getxattr(ofs, upperpath, OVL_XATTR_UUID, uuid.b,
 				UUID_SIZE);
 	if (res == UUID_SIZE)
-		return true;
+		goto set_uuid;
 
 	if (res != -ENODATA)
 		goto fail;
@@ -808,17 +809,20 @@ bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
 	}
 
 	/* Generate overlay instance uuid */
-	uuid_gen(&sb->s_uuid);
+	uuid_gen(&uuid);
 
 	/* Try to store persistent uuid */
 	set = true;
-	res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, sb->s_uuid.b,
+	res = ovl_setxattr(ofs, upperpath->dentry, OVL_XATTR_UUID, uuid.b,
 			   UUID_SIZE);
-	if (res == 0)
-		return true;
+	if (res)
+		goto fail;
+
+set_uuid:
+	super_set_uuid(sb, uuid.b, sizeof(uuid));
+	return true;
 
 fail:
-	memset(sb->s_uuid.b, 0, UUID_SIZE);
 	ofs->config.uuid = OVL_UUID_NULL;
 	pr_warn("failed to %s uuid (%pd2, err=%i); falling back to uuid=null.\n",
 		set ? "set" : "get", upperpath->dentry, res);
diff --git a/fs/pidfs.c b/fs/pidfs.c
new file mode 100644
index 000000000000..8fd71a00be9c
--- /dev/null
+++ b/fs/pidfs.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/pid.h>
+#include <linux/pidfs.h>
+#include <linux/pid_namespace.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/proc_ns.h>
+#include <linux/pseudo_fs.h>
+#include <linux/seq_file.h>
+#include <uapi/linux/pidfd.h>
+
+#include "internal.h"
+
+static int pidfd_release(struct inode *inode, struct file *file)
+{
+#ifndef CONFIG_FS_PID
+	struct pid *pid = file->private_data;
+
+	file->private_data = NULL;
+	put_pid(pid);
+#endif
+	return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+/**
+ * pidfd_show_fdinfo - print information about a pidfd
+ * @m: proc fdinfo file
+ * @f: file referencing a pidfd
+ *
+ * Pid:
+ * This function will print the pid that a given pidfd refers to in the
+ * pid namespace of the procfs instance.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its pid. This is
+ * similar to calling getppid() on a process whose parent is outside of
+ * its pid namespace.
+ *
+ * NSpid:
+ * If pid namespaces are supported then this function will also print
+ * the pid of a given pidfd refers to for all descendant pid namespaces
+ * starting from the current pid namespace of the instance, i.e. the
+ * Pid field and the first entry in the NSpid field will be identical.
+ * If the pid namespace of the process is not a descendant of the pid
+ * namespace of the procfs instance 0 will be shown as its first NSpid
+ * entry and no others will be shown.
+ * Note that this differs from the Pid and NSpid fields in
+ * /proc/<pid>/status where Pid and NSpid are always shown relative to
+ * the  pid namespace of the procfs instance. The difference becomes
+ * obvious when sending around a pidfd between pid namespaces from a
+ * different branch of the tree, i.e. where no ancestral relation is
+ * present between the pid namespaces:
+ * - create two new pid namespaces ns1 and ns2 in the initial pid
+ *   namespace (also take care to create new mount namespaces in the
+ *   new pid namespace and mount procfs)
+ * - create a process with a pidfd in ns1
+ * - send pidfd from ns1 to ns2
+ * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
+ *   have exactly one entry, which is 0
+ */
+static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct pid *pid = pidfd_pid(f);
+	struct pid_namespace *ns;
+	pid_t nr = -1;
+
+	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
+		ns = proc_pid_ns(file_inode(m->file)->i_sb);
+		nr = pid_nr_ns(pid, ns);
+	}
+
+	seq_put_decimal_ll(m, "Pid:\t", nr);
+
+#ifdef CONFIG_PID_NS
+	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
+	if (nr > 0) {
+		int i;
+
+		/* If nr is non-zero it means that 'pid' is valid and that
+		 * ns, i.e. the pid namespace associated with the procfs
+		 * instance, is in the pid namespace hierarchy of pid.
+		 * Start at one below the already printed level.
+		 */
+		for (i = ns->level + 1; i <= pid->level; i++)
+			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
+	}
+#endif
+	seq_putc(m, '\n');
+}
+#endif
+
+/*
+ * Poll support for process exit notification.
+ */
+static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct pid *pid = pidfd_pid(file);
+	bool thread = file->f_flags & PIDFD_THREAD;
+	struct task_struct *task;
+	__poll_t poll_flags = 0;
+
+	poll_wait(file, &pid->wait_pidfd, pts);
+	/*
+	 * Depending on PIDFD_THREAD, inform pollers when the thread
+	 * or the whole thread-group exits.
+	 */
+	guard(rcu)();
+	task = pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP;
+	else if (task->exit_state && (thread || thread_group_empty(task)))
+		poll_flags = EPOLLIN | EPOLLRDNORM;
+
+	return poll_flags;
+}
+
+static const struct file_operations pidfs_file_operations = {
+	.release	= pidfd_release,
+	.poll		= pidfd_poll,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= pidfd_show_fdinfo,
+#endif
+};
+
+struct pid *pidfd_pid(const struct file *file)
+{
+	if (file->f_op != &pidfs_file_operations)
+		return ERR_PTR(-EBADF);
+#ifdef CONFIG_FS_PID
+	return file_inode(file)->i_private;
+#else
+	return file->private_data;
+#endif
+}
+
+#ifdef CONFIG_FS_PID
+static struct vfsmount *pidfs_mnt __ro_after_init;
+
+/*
+ * The vfs falls back to simple_setattr() if i_op->setattr() isn't
+ * implemented. Let's reject it completely until we have a clean
+ * permission concept for pidfds.
+ */
+static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			 struct iattr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path,
+			 struct kstat *stat, u32 request_mask,
+			 unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static const struct inode_operations pidfs_inode_operations = {
+	.getattr = pidfs_getattr,
+	.setattr = pidfs_setattr,
+};
+
+static void pidfs_evict_inode(struct inode *inode)
+{
+	struct pid *pid = inode->i_private;
+
+	clear_inode(inode);
+	put_pid(pid);
+}
+
+static const struct super_operations pidfs_sops = {
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= pidfs_evict_inode,
+	.statfs		= simple_statfs,
+};
+
+static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	return dynamic_dname(buffer, buflen, "pidfd:[%lu]",
+			     d_inode(dentry)->i_ino);
+}
+
+static const struct dentry_operations pidfs_dentry_operations = {
+	.d_delete	= always_delete_dentry,
+	.d_dname	= pidfs_dname,
+	.d_prune	= stashed_dentry_prune,
+};
+
+static void pidfs_init_inode(struct inode *inode, void *data)
+{
+	inode->i_private = data;
+	inode->i_flags |= S_PRIVATE;
+	inode->i_mode |= S_IRWXU;
+	inode->i_op = &pidfs_inode_operations;
+	inode->i_fop = &pidfs_file_operations;
+}
+
+static void pidfs_put_data(void *data)
+{
+	struct pid *pid = data;
+	put_pid(pid);
+}
+
+static const struct stashed_operations pidfs_stashed_ops = {
+	.init_inode = pidfs_init_inode,
+	.put_data = pidfs_put_data,
+};
+
+static int pidfs_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx;
+
+	ctx = init_pseudo(fc, PID_FS_MAGIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ops = &pidfs_sops;
+	ctx->dops = &pidfs_dentry_operations;
+	fc->s_fs_info = (void *)&pidfs_stashed_ops;
+	return 0;
+}
+
+static struct file_system_type pidfs_type = {
+	.name			= "pidfs",
+	.init_fs_context	= pidfs_init_fs_context,
+	.kill_sb		= kill_anon_super,
+};
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
+{
+
+	struct file *pidfd_file;
+	struct path path;
+	int ret;
+
+	/*
+	* Inode numbering for pidfs start at RESERVED_PIDS + 1.
+	* This avoids collisions with the root inode which is 1
+	* for pseudo filesystems.
+	 */
+	ret = path_from_stashed(&pid->stashed, pid->ino, pidfs_mnt,
+				get_pid(pid), &path);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	pidfd_file = dentry_open(&path, flags, current_cred());
+	path_put(&path);
+	return pidfd_file;
+}
+
+void __init pidfs_init(void)
+{
+	pidfs_mnt = kern_mount(&pidfs_type);
+	if (IS_ERR(pidfs_mnt))
+		panic("Failed to mount pidfs pseudo filesystem");
+}
+
+bool is_pidfs_sb(const struct super_block *sb)
+{
+	return sb == pidfs_mnt->mnt_sb;
+}
+
+#else /* !CONFIG_FS_PID */
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
+{
+	struct file *pidfd_file;
+
+	pidfd_file = anon_inode_getfile("[pidfd]", &pidfs_file_operations, pid,
+					flags | O_RDWR);
+	if (IS_ERR(pidfd_file))
+		return pidfd_file;
+
+	get_pid(pid);
+	return pidfd_file;
+}
+
+void __init pidfs_init(void) { }
+bool is_pidfs_sb(const struct super_block *sb)
+{
+	return false;
+}
+#endif
diff --git a/fs/pipe.c b/fs/pipe.c
index f1adbfe743d4..50c8a8596b52 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -76,18 +76,20 @@ static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
  * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
  */
 
-static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
+#define cmp_int(l, r)		((l > r) - (l < r))
+
+#ifdef CONFIG_PROVE_LOCKING
+static int pipe_lock_cmp_fn(const struct lockdep_map *a,
+			    const struct lockdep_map *b)
 {
-	if (pipe->files)
-		mutex_lock_nested(&pipe->mutex, subclass);
+	return cmp_int((unsigned long) a, (unsigned long) b);
 }
+#endif
 
 void pipe_lock(struct pipe_inode_info *pipe)
 {
-	/*
-	 * pipe_lock() nests non-pipe inode locks (for writing to a file)
-	 */
-	pipe_lock_nested(pipe, I_MUTEX_PARENT);
+	if (pipe->files)
+		mutex_lock(&pipe->mutex);
 }
 EXPORT_SYMBOL(pipe_lock);
 
@@ -98,28 +100,16 @@ void pipe_unlock(struct pipe_inode_info *pipe)
 }
 EXPORT_SYMBOL(pipe_unlock);
 
-static inline void __pipe_lock(struct pipe_inode_info *pipe)
-{
-	mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT);
-}
-
-static inline void __pipe_unlock(struct pipe_inode_info *pipe)
-{
-	mutex_unlock(&pipe->mutex);
-}
-
 void pipe_double_lock(struct pipe_inode_info *pipe1,
 		      struct pipe_inode_info *pipe2)
 {
 	BUG_ON(pipe1 == pipe2);
 
-	if (pipe1 < pipe2) {
-		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
-		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
-	} else {
-		pipe_lock_nested(pipe2, I_MUTEX_PARENT);
-		pipe_lock_nested(pipe1, I_MUTEX_CHILD);
-	}
+	if (pipe1 > pipe2)
+		swap(pipe1, pipe2);
+
+	pipe_lock(pipe1);
+	pipe_lock(pipe2);
 }
 
 static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
@@ -271,7 +261,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		return 0;
 
 	ret = 0;
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	/*
 	 * We only wake up writers if the pipe was full when we started
@@ -368,7 +358,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 			ret = -EAGAIN;
 			break;
 		}
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 
 		/*
 		 * We only get here if we didn't actually read anything.
@@ -400,13 +390,13 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0)
 			return -ERESTARTSYS;
 
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
 		wake_next_reader = true;
 	}
 	if (pipe_empty(pipe->head, pipe->tail))
 		wake_next_reader = false;
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	if (was_full)
 		wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
@@ -462,7 +452,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 	if (unlikely(total_len == 0))
 		return 0;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	if (!pipe->readers) {
 		send_sig(SIGPIPE, current, 0);
@@ -582,19 +572,19 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		 * after waiting we need to re-check whether the pipe
 		 * become empty while we dropped the lock.
 		 */
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 		if (was_empty)
 			wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		was_empty = pipe_empty(pipe->head, pipe->tail);
 		wake_next_writer = true;
 	}
 out:
 	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
 		wake_next_writer = false;
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	/*
 	 * If we do do a wakeup event, we do a 'sync' wakeup, because we
@@ -629,7 +619,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case FIONREAD:
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		count = 0;
 		head = pipe->head;
 		tail = pipe->tail;
@@ -639,16 +629,16 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			count += pipe->bufs[tail & mask].len;
 			tail++;
 		}
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 
 		return put_user(count, (int __user *)arg);
 
 #ifdef CONFIG_WATCH_QUEUE
 	case IOC_WATCH_QUEUE_SET_SIZE: {
 		int ret;
-		__pipe_lock(pipe);
+		mutex_lock(&pipe->mutex);
 		ret = watch_queue_set_size(pipe, arg);
-		__pipe_unlock(pipe);
+		mutex_unlock(&pipe->mutex);
 		return ret;
 	}
 
@@ -734,7 +724,7 @@ pipe_release(struct inode *inode, struct file *file)
 {
 	struct pipe_inode_info *pipe = file->private_data;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 	if (file->f_mode & FMODE_READ)
 		pipe->readers--;
 	if (file->f_mode & FMODE_WRITE)
@@ -747,7 +737,7 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	put_pipe_info(inode, pipe);
 	return 0;
@@ -759,7 +749,7 @@ pipe_fasync(int fd, struct file *filp, int on)
 	struct pipe_inode_info *pipe = filp->private_data;
 	int retval = 0;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 	if (filp->f_mode & FMODE_READ)
 		retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
 	if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
@@ -768,7 +758,7 @@ pipe_fasync(int fd, struct file *filp, int on)
 			/* this can happen only if on == T */
 			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
 	}
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return retval;
 }
 
@@ -834,6 +824,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 		pipe->nr_accounted = pipe_bufs;
 		pipe->user = user;
 		mutex_init(&pipe->mutex);
+		lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL);
 		return pipe;
 	}
 
@@ -1144,7 +1135,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	filp->private_data = pipe;
 	/* OK, we have a pipe and it's pinned down */
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	/* We can only do regular read/write on fifos */
 	stream_open(inode, filp);
@@ -1214,7 +1205,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	}
 
 	/* Ok! */
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return 0;
 
 err_rd:
@@ -1230,7 +1221,7 @@ err_wr:
 	goto err;
 
 err:
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 
 	put_pipe_info(inode, pipe);
 	return ret;
@@ -1411,7 +1402,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
 	if (!pipe)
 		return -EBADF;
 
-	__pipe_lock(pipe);
+	mutex_lock(&pipe->mutex);
 
 	switch (cmd) {
 	case F_SETPIPE_SZ:
@@ -1425,7 +1416,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
 		break;
 	}
 
-	__pipe_unlock(pipe);
+	mutex_unlock(&pipe->mutex);
 	return ret;
 }
 
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index e1af20893ebe..6bf587d1a9b8 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -786,12 +786,12 @@ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns,
 		return ERR_PTR(count);
 	if (count == 0)
 		return NULL;
-	
+
 	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 	acl_e = acl->a_entries;
-	
+
 	for (end = entry + count; entry != end; acl_e++, entry++) {
 		acl_e->e_tag  = le16_to_cpu(entry->e_tag);
 		acl_e->e_perm = le16_to_cpu(entry->e_perm);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff08a8957552..34a47fb0c57f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	int permitted;
 	struct mm_struct *mm;
 	unsigned long long start_time;
-	unsigned long cmin_flt = 0, cmaj_flt = 0;
-	unsigned long  min_flt = 0,  maj_flt = 0;
-	u64 cutime, cstime, utime, stime;
-	u64 cgtime, gtime;
+	unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+	u64 cutime, cstime, cgtime, utime, stime, gtime;
 	unsigned long rsslim = 0;
 	unsigned long flags;
 	int exit_code = task->exit_code;
+	struct signal_struct *sig = task->signal;
+	unsigned int seq = 1;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	sigemptyset(&sigign);
 	sigemptyset(&sigcatch);
-	cutime = cstime = utime = stime = 0;
-	cgtime = gtime = 0;
 
 	if (lock_task_sighand(task, &flags)) {
-		struct signal_struct *sig = task->signal;
-
 		if (sig->tty) {
 			struct pid *pgrp = tty_get_pgrp(sig->tty);
 			tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,28 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		num_threads = get_nr_threads(task);
 		collect_sigign_sigcatch(task, &sigign, &sigcatch);
 
-		cmin_flt = sig->cmin_flt;
-		cmaj_flt = sig->cmaj_flt;
-		cutime = sig->cutime;
-		cstime = sig->cstime;
-		cgtime = sig->cgtime;
 		rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
 
-		/* add up live thread stats at the group level */
 		if (whole) {
-			struct task_struct *t;
-
-			__for_each_thread(sig, t) {
-				min_flt += t->min_flt;
-				maj_flt += t->maj_flt;
-				gtime += task_gtime(t);
-			}
-
-			min_flt += sig->min_flt;
-			maj_flt += sig->maj_flt;
-			thread_group_cputime_adjusted(task, &utime, &stime);
-			gtime += sig->gtime;
-
 			if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
 				exit_code = sig->group_exit_code;
 		}
@@ -562,10 +539,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 	if (permitted && (!whole || num_threads < 2))
 		wchan = !task_is_running(task);
-	if (!whole) {
+
+	do {
+		seq++; /* 2 on the 1st/lockless path, otherwise odd */
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+		cmin_flt = sig->cmin_flt;
+		cmaj_flt = sig->cmaj_flt;
+		cutime = sig->cutime;
+		cstime = sig->cstime;
+		cgtime = sig->cgtime;
+
+		if (whole) {
+			struct task_struct *t;
+
+			min_flt = sig->min_flt;
+			maj_flt = sig->maj_flt;
+			gtime = sig->gtime;
+
+			rcu_read_lock();
+			__for_each_thread(sig, t) {
+				min_flt += t->min_flt;
+				maj_flt += t->maj_flt;
+				gtime += task_gtime(t);
+			}
+			rcu_read_unlock();
+		}
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
+	if (whole) {
+		thread_group_cputime_adjusted(task, &utime, &stime);
+	} else {
+		task_cputime_adjusted(task, &utime, &stime);
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
-		task_cputime_adjusted(task, &utime, &stime);
 		gtime = task_gtime(task);
 	}
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 98a031ac2648..18550c071d71 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1878,8 +1878,6 @@ void proc_pid_evict_inode(struct proc_inode *ei)
 		hlist_del_init_rcu(&ei->sibling_inodes);
 		spin_unlock(&pid->lock);
 	}
-
-	put_pid(pid);
 }
 
 struct inode *proc_pid_make_inode(struct super_block *sb,
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b33e490e3fd9..dcd513dccf55 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -30,7 +30,6 @@
 
 static void proc_evict_inode(struct inode *inode)
 {
-	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
 	struct proc_inode *ei = PROC_I(inode);
 
@@ -38,17 +37,8 @@ static void proc_evict_inode(struct inode *inode)
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
-	if (ei->pid) {
+	if (ei->pid)
 		proc_pid_evict_inode(ei);
-		ei->pid = NULL;
-	}
-
-	/* Let go of any associated proc directory entry */
-	de = ei->pde;
-	if (de) {
-		pde_put(de);
-		ei->pde = NULL;
-	}
 
 	head = ei->sysctl;
 	if (head) {
@@ -80,6 +70,13 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 
 static void proc_free_inode(struct inode *inode)
 {
+	struct proc_inode *ei = PROC_I(inode);
+
+	if (ei->pid)
+		put_pid(ei->pid);
+	/* Let go of any associated proc directory entry */
+	if (ei->pde)
+		pde_put(ei->pde);
 	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
@@ -95,7 +92,7 @@ void __init proc_init_kmemcache(void)
 	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
 					     sizeof(struct proc_inode),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+						SLAB_ACCOUNT|
 						SLAB_PANIC),
 					     init_once);
 	pde_opener_cache =
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b55dbc70287b..06a297a27ba3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -271,7 +271,7 @@ static void proc_kill_sb(struct super_block *sb)
 
 	kill_anon_super(sb);
 	put_pid_ns(fs_info->pid_ns);
-	kfree(fs_info);
+	kfree_rcu(fs_info, rcu);
 }
 
 static struct file_system_type proc_fs_type = {
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d0d9bfdad30c..56815799ce79 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -307,7 +307,6 @@ int pstore_put_backend_records(struct pstore_info *psi)
 {
 	struct pstore_private *pos, *tmp;
 	struct dentry *root;
-	int rc = 0;
 
 	root = psinfo_lock_root();
 	if (!root)
@@ -317,11 +316,8 @@ int pstore_put_backend_records(struct pstore_info *psi)
 		list_for_each_entry_safe(pos, tmp, &records_list, list) {
 			if (pos->record->psi == psi) {
 				list_del_init(&pos->list);
-				rc = simple_unlink(d_inode(root), pos->dentry);
-				if (WARN_ON(rc))
-					break;
-				d_drop(pos->dentry);
-				dput(pos->dentry);
+				d_invalidate(pos->dentry);
+				simple_unlink(d_inode(root), pos->dentry);
 				pos->dentry = NULL;
 			}
 		}
@@ -329,7 +325,7 @@ int pstore_put_backend_records(struct pstore_info *psi)
 
 	inode_unlock(d_inode(root));
 
-	return rc;
+	return 0;
 }
 
 /*
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 88b34fdbf759..b1a455f42e93 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -893,6 +893,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "ramoops" },
 	{}
 };
+MODULE_DEVICE_TABLE(of, dt_match);
 
 static struct platform_driver ramoops_driver = {
 	.probe		= ramoops_probe,
diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c
index 2770746bb7aa..694db616663f 100644
--- a/fs/pstore/zone.c
+++ b/fs/pstore/zone.c
@@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone,
 		char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n",
 				      kmsg_dump_reason_str(record->reason),
 				      record->count);
+		if (!buf)
+			return -ENOMEM;
 		hlen = strlen(buf);
 		record->buf = krealloc(buf, hlen + size, GFP_KERNEL);
 		if (!record->buf) {
@@ -1215,7 +1217,6 @@ static struct pstore_zone **psz_init_zones(enum pstore_type_id type,
 		pr_err("allocate for zones %s failed\n", name);
 		return ERR_PTR(-ENOMEM);
 	}
-	memset(zones, 0, c * sizeof(*zones));
 
 	for (i = 0; i < c; i++) {
 		zone = psz_init_zone(type, off, record_size);
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 6eb9bb369b57..7b5711f76709 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -21,6 +21,7 @@
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
+#include <linux/fs_context.h>
 #include "qnx4.h"
 
 #define QNX4_VERSION  4
@@ -30,28 +31,33 @@ static const struct super_operations qnx4_sops;
 
 static struct inode *qnx4_alloc_inode(struct super_block *sb);
 static void qnx4_free_inode(struct inode *inode);
-static int qnx4_remount(struct super_block *sb, int *flags, char *data);
 static int qnx4_statfs(struct dentry *, struct kstatfs *);
+static int qnx4_get_tree(struct fs_context *fc);
 
 static const struct super_operations qnx4_sops =
 {
 	.alloc_inode	= qnx4_alloc_inode,
 	.free_inode	= qnx4_free_inode,
 	.statfs		= qnx4_statfs,
-	.remount_fs	= qnx4_remount,
 };
 
-static int qnx4_remount(struct super_block *sb, int *flags, char *data)
+static int qnx4_reconfigure(struct fs_context *fc)
 {
+	struct super_block *sb = fc->root->d_sb;
 	struct qnx4_sb_info *qs;
 
 	sync_filesystem(sb);
 	qs = qnx4_sb(sb);
 	qs->Version = QNX4_VERSION;
-	*flags |= SB_RDONLY;
+	fc->sb_flags |= SB_RDONLY;
 	return 0;
 }
 
+static const struct fs_context_operations qnx4_context_opts = {
+	.get_tree	= qnx4_get_tree,
+	.reconfigure	= qnx4_reconfigure,
+};
+
 static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_head *bh, int create )
 {
 	unsigned long phys;
@@ -183,12 +189,13 @@ static const char *qnx4_checkroot(struct super_block *sb,
 	return "bitmap file not found.";
 }
 
-static int qnx4_fill_super(struct super_block *s, void *data, int silent)
+static int qnx4_fill_super(struct super_block *s, struct fs_context *fc)
 {
 	struct buffer_head *bh;
 	struct inode *root;
 	const char *errmsg;
 	struct qnx4_sb_info *qs;
+	int silent = fc->sb_flags & SB_SILENT;
 
 	qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL);
 	if (!qs)
@@ -216,7 +223,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent)
 	errmsg = qnx4_checkroot(s, (struct qnx4_super_block *) bh->b_data);
 	brelse(bh);
 	if (errmsg != NULL) {
- 		if (!silent)
+		if (!silent)
 			printk(KERN_ERR "qnx4: %s\n", errmsg);
 		return -EINVAL;
 	}
@@ -235,6 +242,18 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent)
 	return 0;
 }
 
+static int qnx4_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, qnx4_fill_super);
+}
+
+static int qnx4_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &qnx4_context_opts;
+
+	return 0;
+}
+
 static void qnx4_kill_sb(struct super_block *sb)
 {
 	struct qnx4_sb_info *qs = qnx4_sb(sb);
@@ -376,18 +395,12 @@ static void destroy_inodecache(void)
 	kmem_cache_destroy(qnx4_inode_cachep);
 }
 
-static struct dentry *qnx4_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, qnx4_fill_super);
-}
-
 static struct file_system_type qnx4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "qnx4",
-	.mount		= qnx4_mount,
-	.kill_sb	= qnx4_kill_sb,
-	.fs_flags	= FS_REQUIRES_DEV,
+	.owner			= THIS_MODULE,
+	.name			= "qnx4",
+	.kill_sb		= qnx4_kill_sb,
+	.fs_flags		= FS_REQUIRES_DEV,
+	.init_fs_context	= qnx4_init_fs_context,
 };
 MODULE_ALIAS_FS("qnx4");
 
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index a286c545717f..405913f4faff 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -615,7 +615,7 @@ static int init_inodecache(void)
 	qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache",
 					     sizeof(struct qnx6_inode_info),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+						SLAB_ACCOUNT),
 					     init_once);
 	if (!qnx6_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 171c912af50f..6474529c4253 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2386,7 +2386,7 @@ static int journal_read(struct super_block *sb)
 
 	cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb);
 	reiserfs_info(sb, "checking transaction log (%pg)\n",
-		      journal->j_bdev_handle->bdev);
+		      file_bdev(journal->j_bdev_file));
 	start = ktime_get_seconds();
 
 	/*
@@ -2447,7 +2447,7 @@ static int journal_read(struct super_block *sb)
 		 * device and journal device to be the same
 		 */
 		d_bh =
-		    reiserfs_breada(journal->j_bdev_handle->bdev, cur_dblock,
+		    reiserfs_breada(file_bdev(journal->j_bdev_file), cur_dblock,
 				    sb->s_blocksize,
 				    SB_ONDISK_JOURNAL_1st_BLOCK(sb) +
 				    SB_ONDISK_JOURNAL_SIZE(sb));
@@ -2588,9 +2588,9 @@ static void journal_list_init(struct super_block *sb)
 
 static void release_journal_dev(struct reiserfs_journal *journal)
 {
-	if (journal->j_bdev_handle) {
-		bdev_release(journal->j_bdev_handle);
-		journal->j_bdev_handle = NULL;
+	if (journal->j_bdev_file) {
+		fput(journal->j_bdev_file);
+		journal->j_bdev_file = NULL;
 	}
 }
 
@@ -2605,7 +2605,7 @@ static int journal_init_dev(struct super_block *super,
 
 	result = 0;
 
-	journal->j_bdev_handle = NULL;
+	journal->j_bdev_file = NULL;
 	jdev = SB_ONDISK_JOURNAL_DEVICE(super) ?
 	    new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev;
 
@@ -2616,37 +2616,37 @@ static int journal_init_dev(struct super_block *super,
 	if ((!jdev_name || !jdev_name[0])) {
 		if (jdev == super->s_dev)
 			holder = NULL;
-		journal->j_bdev_handle = bdev_open_by_dev(jdev, blkdev_mode,
+		journal->j_bdev_file = bdev_file_open_by_dev(jdev, blkdev_mode,
 							  holder, NULL);
-		if (IS_ERR(journal->j_bdev_handle)) {
-			result = PTR_ERR(journal->j_bdev_handle);
-			journal->j_bdev_handle = NULL;
+		if (IS_ERR(journal->j_bdev_file)) {
+			result = PTR_ERR(journal->j_bdev_file);
+			journal->j_bdev_file = NULL;
 			reiserfs_warning(super, "sh-458",
 					 "cannot init journal device unknown-block(%u,%u): %i",
 					 MAJOR(jdev), MINOR(jdev), result);
 			return result;
 		} else if (jdev != super->s_dev)
-			set_blocksize(journal->j_bdev_handle->bdev,
+			set_blocksize(file_bdev(journal->j_bdev_file),
 				      super->s_blocksize);
 
 		return 0;
 	}
 
-	journal->j_bdev_handle = bdev_open_by_path(jdev_name, blkdev_mode,
+	journal->j_bdev_file = bdev_file_open_by_path(jdev_name, blkdev_mode,
 						   holder, NULL);
-	if (IS_ERR(journal->j_bdev_handle)) {
-		result = PTR_ERR(journal->j_bdev_handle);
-		journal->j_bdev_handle = NULL;
+	if (IS_ERR(journal->j_bdev_file)) {
+		result = PTR_ERR(journal->j_bdev_file);
+		journal->j_bdev_file = NULL;
 		reiserfs_warning(super, "sh-457",
 				 "journal_init_dev: Cannot open '%s': %i",
 				 jdev_name, result);
 		return result;
 	}
 
-	set_blocksize(journal->j_bdev_handle->bdev, super->s_blocksize);
+	set_blocksize(file_bdev(journal->j_bdev_file), super->s_blocksize);
 	reiserfs_info(super,
 		      "journal_init_dev: journal device: %pg\n",
-		      journal->j_bdev_handle->bdev);
+		      file_bdev(journal->j_bdev_file));
 	return 0;
 }
 
@@ -2804,7 +2804,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 				 "journal header magic %x (device %pg) does "
 				 "not match to magic found in super block %x",
 				 jh->jh_journal.jp_journal_magic,
-				 journal->j_bdev_handle->bdev,
+				 file_bdev(journal->j_bdev_file),
 				 sb_jp_journal_magic(rs));
 		brelse(bhjh);
 		goto free_and_return;
@@ -2828,7 +2828,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	reiserfs_info(sb, "journal params: device %pg, size %u, "
 		      "journal first block %u, max trans len %u, max batch %u, "
 		      "max commit age %u, max trans age %u\n",
-		      journal->j_bdev_handle->bdev,
+		      file_bdev(journal->j_bdev_file),
 		      SB_ONDISK_JOURNAL_SIZE(sb),
 		      SB_ONDISK_JOURNAL_1st_BLOCK(sb),
 		      journal->j_trans_max,
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 83cb9402e0f9..5c68a4a52d78 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -354,7 +354,7 @@ static int show_journal(struct seq_file *m, void *unused)
 		   "prepare: \t%12lu\n"
 		   "prepare_retry: \t%12lu\n",
 		   DJP(jp_journal_1st_block),
-		   SB_JOURNAL(sb)->j_bdev_handle->bdev,
+		   file_bdev(SB_JOURNAL(sb)->j_bdev_file),
 		   DJP(jp_journal_dev),
 		   DJP(jp_journal_size),
 		   DJP(jp_journal_trans_max),
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 725667880e62..0554903f42a9 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -299,7 +299,7 @@ struct reiserfs_journal {
 	/* oldest journal block.  start here for traverse */
 	struct reiserfs_journal_cnode *j_first;
 
-	struct bdev_handle *j_bdev_handle;
+	struct file *j_bdev_file;
 
 	/* first block on s_dev of reserved area journal */
 	int j_1st_reserved_block;
@@ -2810,10 +2810,10 @@ struct reiserfs_journal_header {
 
 /* We need these to make journal.c code more readable */
 #define journal_find_get_block(s, block) __find_get_block(\
-		SB_JOURNAL(s)->j_bdev_handle->bdev, block, s->s_blocksize)
-#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_bdev_handle->bdev,\
+		file_bdev(SB_JOURNAL(s)->j_bdev_file), block, s->s_blocksize)
+#define journal_getblk(s, block) __getblk(file_bdev(SB_JOURNAL(s)->j_bdev_file),\
 		block, s->s_blocksize)
-#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_bdev_handle->bdev,\
+#define journal_bread(s, block) __bread(file_bdev(SB_JOURNAL(s)->j_bdev_file),\
 		block, s->s_blocksize)
 
 enum reiserfs_bh_state_bits {
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 67b5510beded..2cc469d481a2 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -670,7 +670,6 @@ static int __init init_inodecache(void)
 						  sizeof(struct
 							 reiserfs_inode_info),
 						  0, (SLAB_RECLAIM_ACCOUNT|
-						      SLAB_MEM_SPREAD|
 						      SLAB_ACCOUNT),
 						  init_once);
 	if (reiserfs_inode_cachep == NULL)
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f8c1120b8311..de07f978ce3e 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -373,9 +373,9 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out,
-			   loff_t len, unsigned int remap_flags)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
 {
 	loff_t ret;
 
@@ -391,23 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;
 
-	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, remap_flags);
-	if (ret < 0)
-		return ret;
-
-	fsnotify_access(file_in);
-	fsnotify_modify(file_out);
-	return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out,
-			    loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
 	ret = remap_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
@@ -417,10 +400,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 		return ret;
 
 	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
-				  remap_flags);
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, remap_flags);
 	file_end_write(file_out);
+	if (ret < 0)
+		return ret;
 
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
 	return ret;
 }
 EXPORT_SYMBOL(vfs_clone_file_range);
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 545ad44f96b8..2be227532f39 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb)
 #ifdef CONFIG_ROMFS_ON_BLOCK
 	if (sb->s_bdev) {
 		sync_blockdev(sb->s_bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 #endif
 }
@@ -630,8 +630,8 @@ static int __init init_romfs_fs(void)
 	romfs_inode_cachep =
 		kmem_cache_create("romfs_i",
 				  sizeof(struct romfs_inode_info), 0,
-				  SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
-				  SLAB_ACCOUNT, romfs_i_init_once);
+				  SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+				  romfs_i_init_once);
 
 	if (!romfs_inode_cachep) {
 		pr_err("Failed to initialise inode cache\n");
diff --git a/fs/select.c b/fs/select.c
index 0ee55af1a55c..9515c3fa1a03 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
 		wait->_key |= POLLOUT_SET;
 }
 
-static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 {
 	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
@@ -839,7 +839,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
 
 struct poll_list {
 	struct poll_list *next;
-	int len;
+	unsigned int len;
 	struct pollfd entries[];
 };
 
@@ -975,14 +975,15 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
-	int err = -EFAULT, fdcount, len;
+	int err = -EFAULT, fdcount;
 	/* Allocate small arguments on the stack to save memory and be
 	   faster - use long to make sure the buffer is aligned properly
 	   on 64 bit archs to avoid unaligned access */
 	long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
 	struct poll_list *const head = (struct poll_list *)stack_pps;
  	struct poll_list *walk = head;
- 	unsigned long todo = nfds;
+	unsigned int todo = nfds;
+	unsigned int len;
 
 	if (nfds > rlimit(RLIMIT_NOFILE))
 		return -EINVAL;
@@ -998,9 +999,9 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 					sizeof(struct pollfd) * walk->len))
 			goto out_fds;
 
-		todo -= walk->len;
-		if (!todo)
+		if (walk->len >= todo)
 			break;
+		todo -= walk->len;
 
 		len = min(todo, POLLFD_PER_PAGE);
 		walk = walk->next = kmalloc(struct_size(walk, entries, len),
@@ -1020,7 +1021,7 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 
 	for (walk = head; walk; walk = walk->next) {
 		struct pollfd *fds = walk->entries;
-		int j;
+		unsigned int j;
 
 		for (j = walk->len; j; fds++, ufds++, j--)
 			unsafe_put_user(fds->revents, &ufds->revents, Efault);
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 1daeb5714faa..3de5047a7ff9 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -242,6 +242,7 @@ replay_again:
 		.desired_access =  FILE_READ_DATA | FILE_READ_ATTRIBUTES,
 		.disposition = FILE_OPEN,
 		.fid = pfid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2a4a4e3a8751..fb368b191eef 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1085,7 +1085,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 }
 
 static int
-cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv)
+cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv)
 {
 	/*
 	 * Note that this is called by vfs setlease with i_lock held to
@@ -1094,9 +1094,6 @@ cifs_setlease(struct file *file, int arg, struct file_lock **lease, void **priv)
 	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 
-	if (!(S_ISREG(inode->i_mode)))
-		return -EINVAL;
-
 	/* Check if file is oplocked if this is request for new lease */
 	if (arg == F_UNLCK ||
 	    ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
@@ -1172,6 +1169,9 @@ const char *cifs_get_link(struct dentry *dentry, struct inode *inode,
 {
 	char *target_path;
 
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
 	target_path = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!target_path)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 16befff4cbb4..53c75cfb33ab 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -87,7 +87,7 @@
 #define SMB_INTERFACE_POLL_INTERVAL	600
 
 /* maximum number of PDUs in one compound */
-#define MAX_COMPOUND 5
+#define MAX_COMPOUND 7
 
 /*
  * Default number of credits to keep available for SMB3.
@@ -1032,6 +1032,8 @@ struct cifs_chan {
 	__u8 signkey[SMB3_SIGN_KEY_SIZE];
 };
 
+#define CIFS_SES_FLAG_SCALE_CHANNELS (0x1)
+
 /*
  * Session structure.  One of these for each uid session with a particular host
  */
@@ -1064,6 +1066,7 @@ struct cifs_ses {
 	enum securityEnum sectype; /* what security flavor was specified? */
 	bool sign;		/* is signing required? */
 	bool domainAuto:1;
+	unsigned int flags;
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
@@ -1375,6 +1378,7 @@ struct cifs_open_parms {
 	struct cifs_fid *fid;
 	umode_t mode;
 	bool reconnect:1;
+	bool replay:1; /* indicates that this open is for a replay */
 };
 
 struct cifs_fid {
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 01e89070df5a..5eb83bafc7fd 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -2066,20 +2066,20 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
 		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
-			pLockData->fl_type = F_UNLCK;
+			pLockData->c.flc_type = F_UNLCK;
 		else {
 			if (parm_data->lock_type ==
 					cpu_to_le16(CIFS_RDLCK))
-				pLockData->fl_type = F_RDLCK;
+				pLockData->c.flc_type = F_RDLCK;
 			else if (parm_data->lock_type ==
 					cpu_to_le16(CIFS_WRLCK))
-				pLockData->fl_type = F_WRLCK;
+				pLockData->c.flc_type = F_WRLCK;
 
 			pLockData->fl_start = le64_to_cpu(parm_data->start);
 			pLockData->fl_end = pLockData->fl_start +
 				(le64_to_cpu(parm_data->length) ?
 				 le64_to_cpu(parm_data->length) - 1 : 0);
-			pLockData->fl_pid = -le32_to_cpu(parm_data->pid);
+			pLockData->c.flc_pid = -le32_to_cpu(parm_data->pid);
 		}
 	}
 
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index bfd568f89710..ac9595504f4b 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -233,6 +233,12 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
 	list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
 		/* check if iface is still active */
 		spin_lock(&ses->chan_lock);
+		if (cifs_ses_get_chan_index(ses, server) ==
+		    CIFS_INVAL_CHAN_INDEX) {
+			spin_unlock(&ses->chan_lock);
+			continue;
+		}
+
 		if (!cifs_chan_is_iface_active(ses, server)) {
 			spin_unlock(&ses->chan_lock);
 			cifs_chan_update_iface(ses, server);
@@ -3438,8 +3444,18 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * the user on mount
 	 */
 	if ((cifs_sb->ctx->wsize == 0) ||
-	    (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx)))
-		cifs_sb->ctx->wsize = server->ops->negotiate_wsize(tcon, ctx);
+	    (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) {
+		cifs_sb->ctx->wsize =
+			round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
+		/*
+		 * in the very unlikely event that the server sent a max write size under PAGE_SIZE,
+		 * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096
+		 */
+		if (cifs_sb->ctx->wsize == 0) {
+			cifs_sb->ctx->wsize = PAGE_SIZE;
+			cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n");
+		}
+	}
 	if ((cifs_sb->ctx->rsize == 0) ||
 	    (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
 		cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
@@ -4228,6 +4244,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index a8a1d386da65..449c59830039 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -565,6 +565,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+
+	/* if tcon is marked for needing reconnect, update state */
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_TCON;
+
 	if (tcon->status == TID_GOOD) {
 		spin_unlock(&tcon->tc_lock);
 		return 0;
@@ -625,8 +630,8 @@ out:
 		spin_lock(&tcon->tc_lock);
 		if (tcon->status == TID_IN_TCON)
 			tcon->status = TID_GOOD;
-		spin_unlock(&tcon->tc_lock);
 		tcon->need_reconnect = false;
+		spin_unlock(&tcon->tc_lock);
 	}
 
 	return rc;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index b75282c204da..c3b8e7091a4d 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -175,6 +175,9 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
 
 	/* only send once per connect */
 	spin_lock(&tcon->tc_lock);
+	if (tcon->need_reconnect)
+		tcon->status = TID_NEED_RECON;
+
 	if (tcon->status != TID_NEED_RECON) {
 		spin_unlock(&tcon->tc_lock);
 		return;
@@ -1312,20 +1315,20 @@ cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
 	down_read(&cinode->lock_sem);
 
 	exist = cifs_find_lock_conflict(cfile, offset, length, type,
-					flock->fl_flags, &conf_lock,
+					flock->c.flc_flags, &conf_lock,
 					CIFS_LOCK_OP);
 	if (exist) {
 		flock->fl_start = conf_lock->offset;
 		flock->fl_end = conf_lock->offset + conf_lock->length - 1;
-		flock->fl_pid = conf_lock->pid;
+		flock->c.flc_pid = conf_lock->pid;
 		if (conf_lock->type & server->vals->shared_lock_type)
-			flock->fl_type = F_RDLCK;
+			flock->c.flc_type = F_RDLCK;
 		else
-			flock->fl_type = F_WRLCK;
+			flock->c.flc_type = F_WRLCK;
 	} else if (!cinode->can_cache_brlcks)
 		rc = 1;
 	else
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 
 	up_read(&cinode->lock_sem);
 	return rc;
@@ -1401,16 +1404,16 @@ cifs_posix_lock_test(struct file *file, struct file_lock *flock)
 {
 	int rc = 0;
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
-	unsigned char saved_type = flock->fl_type;
+	unsigned char saved_type = flock->c.flc_type;
 
-	if ((flock->fl_flags & FL_POSIX) == 0)
+	if ((flock->c.flc_flags & FL_POSIX) == 0)
 		return 1;
 
 	down_read(&cinode->lock_sem);
 	posix_test_lock(file, flock);
 
-	if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) {
-		flock->fl_type = saved_type;
+	if (lock_is_unlock(flock) && !cinode->can_cache_brlcks) {
+		flock->c.flc_type = saved_type;
 		rc = 1;
 	}
 
@@ -1431,7 +1434,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 	struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
 	int rc = FILE_LOCK_DEFERRED + 1;
 
-	if ((flock->fl_flags & FL_POSIX) == 0)
+	if ((flock->c.flc_flags & FL_POSIX) == 0)
 		return rc;
 
 	cifs_down_write(&cinode->lock_sem);
@@ -1581,7 +1584,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	el = locks_to_send.next;
 	spin_lock(&flctx->flc_lock);
-	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
+	for_each_file_lock(flock, &flctx->flc_posix) {
+		unsigned char ftype = flock->c.flc_type;
+
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1591,12 +1596,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 			break;
 		}
 		length = cifs_flock_len(flock);
-		if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK)
+		if (ftype == F_RDLCK || ftype == F_SHLCK)
 			type = CIFS_RDLCK;
 		else
 			type = CIFS_WRLCK;
 		lck = list_entry(el, struct lock_to_push, llist);
-		lck->pid = hash_lockowner(flock->fl_owner);
+		lck->pid = hash_lockowner(flock->c.flc_owner);
 		lck->netfid = cfile->fid.netfid;
 		lck->length = length;
 		lck->type = type;
@@ -1663,42 +1668,43 @@ static void
 cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock,
 		bool *wait_flag, struct TCP_Server_Info *server)
 {
-	if (flock->fl_flags & FL_POSIX)
+	if (flock->c.flc_flags & FL_POSIX)
 		cifs_dbg(FYI, "Posix\n");
-	if (flock->fl_flags & FL_FLOCK)
+	if (flock->c.flc_flags & FL_FLOCK)
 		cifs_dbg(FYI, "Flock\n");
-	if (flock->fl_flags & FL_SLEEP) {
+	if (flock->c.flc_flags & FL_SLEEP) {
 		cifs_dbg(FYI, "Blocking lock\n");
 		*wait_flag = true;
 	}
-	if (flock->fl_flags & FL_ACCESS)
+	if (flock->c.flc_flags & FL_ACCESS)
 		cifs_dbg(FYI, "Process suspended by mandatory locking - not implemented yet\n");
-	if (flock->fl_flags & FL_LEASE)
+	if (flock->c.flc_flags & FL_LEASE)
 		cifs_dbg(FYI, "Lease on file - not implemented yet\n");
-	if (flock->fl_flags &
+	if (flock->c.flc_flags &
 	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP |
 	       FL_ACCESS | FL_LEASE | FL_CLOSE | FL_OFDLCK)))
-		cifs_dbg(FYI, "Unknown lock flags 0x%x\n", flock->fl_flags);
+		cifs_dbg(FYI, "Unknown lock flags 0x%x\n",
+		         flock->c.flc_flags);
 
 	*type = server->vals->large_lock_type;
-	if (flock->fl_type == F_WRLCK) {
+	if (lock_is_write(flock)) {
 		cifs_dbg(FYI, "F_WRLCK\n");
 		*type |= server->vals->exclusive_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_UNLCK) {
+	} else if (lock_is_unlock(flock)) {
 		cifs_dbg(FYI, "F_UNLCK\n");
 		*type |= server->vals->unlock_lock_type;
 		*unlock = 1;
 		/* Check if unlock includes more than one lock range */
-	} else if (flock->fl_type == F_RDLCK) {
+	} else if (lock_is_read(flock)) {
 		cifs_dbg(FYI, "F_RDLCK\n");
 		*type |= server->vals->shared_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_EXLCK) {
+	} else if (flock->c.flc_type == F_EXLCK) {
 		cifs_dbg(FYI, "F_EXLCK\n");
 		*type |= server->vals->exclusive_lock_type;
 		*lock = 1;
-	} else if (flock->fl_type == F_SHLCK) {
+	} else if (flock->c.flc_type == F_SHLCK) {
 		cifs_dbg(FYI, "F_SHLCK\n");
 		*type |= server->vals->shared_lock_type;
 		*lock = 1;
@@ -1730,7 +1736,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 		else
 			posix_lock_type = CIFS_WRLCK;
 		rc = CIFSSMBPosixLock(xid, tcon, netfid,
-				      hash_lockowner(flock->fl_owner),
+				      hash_lockowner(flock->c.flc_owner),
 				      flock->fl_start, length, flock,
 				      posix_lock_type, wait_flag);
 		return rc;
@@ -1747,7 +1753,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	if (rc == 0) {
 		rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
 					    type, 0, 1, false);
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 		if (rc != 0)
 			cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
 				 rc);
@@ -1755,7 +1761,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	}
 
 	if (type & server->vals->shared_lock_type) {
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 		return 0;
 	}
 
@@ -1767,12 +1773,12 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
 	if (rc == 0) {
 		rc = server->ops->mand_lock(xid, cfile, flock->fl_start, length,
 			type | server->vals->shared_lock_type, 0, 1, false);
-		flock->fl_type = F_RDLCK;
+		flock->c.flc_type = F_RDLCK;
 		if (rc != 0)
 			cifs_dbg(VFS, "Error unlocking previously locked range %d during test of lock\n",
 				 rc);
 	} else
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 
 	return 0;
 }
@@ -1940,7 +1946,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 			posix_lock_type = CIFS_UNLCK;
 
 		rc = CIFSSMBPosixLock(xid, tcon, cfile->fid.netfid,
-				      hash_lockowner(flock->fl_owner),
+				      hash_lockowner(flock->c.flc_owner),
 				      flock->fl_start, length,
 				      NULL, posix_lock_type, wait_flag);
 		goto out;
@@ -1950,7 +1956,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		struct cifsLockInfo *lock;
 
 		lock = cifs_lock_init(flock->fl_start, length, type,
-				      flock->fl_flags);
+				      flock->c.flc_flags);
 		if (!lock)
 			return -ENOMEM;
 
@@ -1989,7 +1995,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		rc = server->ops->mand_unlock_range(cfile, flock, xid);
 
 out:
-	if ((flock->fl_flags & FL_POSIX) || (flock->fl_flags & FL_FLOCK)) {
+	if ((flock->c.flc_flags & FL_POSIX) || (flock->c.flc_flags & FL_FLOCK)) {
 		/*
 		 * If this is a request to remove all locks because we
 		 * are closing the file, it doesn't matter if the
@@ -1998,7 +2004,7 @@ out:
 		 */
 		if (rc) {
 			cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc);
-			if (!(flock->fl_flags & FL_CLOSE))
+			if (!(flock->c.flc_flags & FL_CLOSE))
 				return rc;
 		}
 		rc = locks_lock_file_wait(file, flock);
@@ -2019,7 +2025,7 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	xid = get_xid();
 
-	if (!(fl->fl_flags & FL_FLOCK)) {
+	if (!(fl->c.flc_flags & FL_FLOCK)) {
 		rc = -ENOLCK;
 		free_xid(xid);
 		return rc;
@@ -2070,7 +2076,8 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 	xid = get_xid();
 
 	cifs_dbg(FYI, "%s: %pD2 cmd=0x%x type=0x%x flags=0x%x r=%lld:%lld\n", __func__, file, cmd,
-		 flock->fl_flags, flock->fl_type, (long long)flock->fl_start,
+		 flock->c.flc_flags, flock->c.flc_type,
+		 (long long)flock->fl_start,
 		 (long long)flock->fl_end);
 
 	cfile = (struct cifsFileInfo *)file->private_data;
@@ -2951,7 +2958,7 @@ skip_write:
 			continue;
 		}
 
-		folio_batch_release(&fbatch);		
+		folio_batch_release(&fbatch);
 		cond_resched();
 	} while (wbc->nr_to_write > 0);
 
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 52cbef2eeb28..4b2f5aa2ea0e 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -211,7 +211,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c
 
 	switch (match_token(value, cifs_secflavor_tokens, args)) {
 	case Opt_sec_krb5p:
-		cifs_errorf(fc, "sec=krb5p is not supported!\n");
+		cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n");
 		return 1;
 	case Opt_sec_krb5i:
 		ctx->sign = true;
@@ -1111,6 +1111,17 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 	case Opt_wsize:
 		ctx->wsize = result.uint_32;
 		ctx->got_wsize = true;
+		if (ctx->wsize % PAGE_SIZE != 0) {
+			ctx->wsize = round_down(ctx->wsize, PAGE_SIZE);
+			if (ctx->wsize == 0) {
+				ctx->wsize = PAGE_SIZE;
+				cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE);
+			} else {
+				cifs_dbg(VFS,
+					 "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n",
+					 ctx->wsize, PAGE_SIZE);
+			}
+		}
 		break;
 	case Opt_acregmax:
 		ctx->acregmax = HZ * result.uint_32;
diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c
index a6968573b775..4a517b280f2b 100644
--- a/fs/smb/client/namespace.c
+++ b/fs/smb/client/namespace.c
@@ -168,6 +168,21 @@ static char *automount_fullpath(struct dentry *dentry, void *page)
 	return s;
 }
 
+static void fs_context_set_ids(struct smb3_fs_context *ctx)
+{
+	kuid_t uid = current_fsuid();
+	kgid_t gid = current_fsgid();
+
+	if (ctx->multiuser) {
+		if (!ctx->uid_specified)
+			ctx->linux_uid = uid;
+		if (!ctx->gid_specified)
+			ctx->linux_gid = gid;
+	}
+	if (!ctx->cruid_specified)
+		ctx->cred_uid = uid;
+}
+
 /*
  * Create a vfsmount that we can automount
  */
@@ -205,6 +220,7 @@ static struct vfsmount *cifs_do_automount(struct path *path)
 	tmp.leaf_fullpath = NULL;
 	tmp.UNC = tmp.prepath = NULL;
 	tmp.dfs_root_ses = NULL;
+	fs_context_set_ids(&tmp);
 
 	rc = smb3_fs_context_dup(ctx, &tmp);
 	if (rc) {
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 3b1b01d10f7d..b520eea7bfce 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -307,14 +307,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
 }
 
 static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr,
-				       SEARCH_ID_FULL_DIR_INFO *info,
+				       const void *info,
 				       struct cifs_sb_info *cifs_sb)
 {
+	const FILE_FULL_DIRECTORY_INFO *di = info;
+
 	__dir_info_to_fattr(fattr, info);
 
-	/* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */
+	/* See MS-FSCC 2.4.14, 2.4.19 */
 	if (fattr->cf_cifsattrs & ATTR_REPARSE)
-		fattr->cf_cifstag = le32_to_cpu(info->EaSize);
+		fattr->cf_cifstag = le32_to_cpu(di->EaSize);
 	cifs_fill_common_info(fattr, cifs_sb);
 }
 
@@ -396,7 +398,7 @@ ffirst_retry:
 	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	} else /* not srvinos - BB fixme add check for backlevel? */ {
-		cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
+		cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
 	}
 
 	search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME;
@@ -987,10 +989,9 @@ static int cifs_filldir(char *find_entry, struct file *file,
 				       (FIND_FILE_STANDARD_INFO *)find_entry,
 				       cifs_sb);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
 	case SMB_FIND_FILE_ID_FULL_DIR_INFO:
-		cifs_fulldir_info_to_fattr(&fattr,
-					   (SEARCH_ID_FULL_DIR_INFO *)find_entry,
-					   cifs_sb);
+		cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb);
 		break;
 	default:
 		cifs_dir_info_to_fattr(&fattr,
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index cde81042bebd..8f37373fd333 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -75,6 +75,10 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 {
 	unsigned int i;
 
+	/* if the channel is waiting for termination */
+	if (server && server->terminate)
+		return CIFS_INVAL_CHAN_INDEX;
+
 	for (i = 0; i < ses->chan_count; i++) {
 		if (ses->chans[i].server == server)
 			return i;
@@ -84,7 +88,6 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
 	if (server)
 		cifs_dbg(VFS, "unable to get chan index for server: 0x%llx",
 			 server->conn_id);
-	WARN_ON(1);
 	return CIFS_INVAL_CHAN_INDEX;
 }
 
@@ -269,6 +272,8 @@ int cifs_try_adding_channels(struct cifs_ses *ses)
 					 &iface->sockaddr,
 					 rc);
 				kref_put(&iface->refcount, release_iface);
+				/* failure to add chan should increase weight */
+				iface->weight_fulfilled++;
 				continue;
 			}
 
diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c
index e0ee96d69d49..c23478ab1cf8 100644
--- a/fs/smb/client/smb2file.c
+++ b/fs/smb/client/smb2file.c
@@ -228,7 +228,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 			 * flock and OFD lock are associated with an open
 			 * file description, not the process.
 			 */
-			if (!(flock->fl_flags & (FL_FLOCK | FL_OFDLCK)))
+			if (!(flock->c.flc_flags & (FL_FLOCK | FL_OFDLCK)))
 				continue;
 		if (cinode->can_cache_brlcks) {
 			/*
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 83c898afc835..4695433fcf39 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -619,7 +619,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 		goto out;
 	}
 
-	while (bytes_left >= sizeof(*p)) {
+	while (bytes_left >= (ssize_t)sizeof(*p)) {
 		memset(&tmp_iface, 0, sizeof(tmp_iface));
 		tmp_iface.speed = le64_to_cpu(p->LinkSpeed);
 		tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0;
@@ -1204,6 +1204,7 @@ replay_again:
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -1569,6 +1570,7 @@ replay_again:
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, create_options),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	if (qi.flags & PASSTHRU_FSCTL) {
@@ -2295,6 +2297,7 @@ replay_again:
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -2681,6 +2684,7 @@ replay_again:
 		.disposition = FILE_OPEN,
 		.create_options = cifs_create_options(cifs_sb, 0),
 		.fid = &fid,
+		.replay = !!(retries),
 	};
 
 	rc = SMB2_open_init(tcon, server,
@@ -5213,7 +5217,7 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 	struct inode *new;
 	struct kvec iov;
 	__le16 *path;
-	char *sym;
+	char *sym, sep = CIFS_DIR_SEP(cifs_sb);
 	u16 len, plen;
 	int rc = 0;
 
@@ -5227,7 +5231,8 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 		.symlink_target = sym,
 	};
 
-	path = cifs_convert_path_to_utf16(symname, cifs_sb);
+	convert_delimiter(sym, sep);
+	path = cifs_convert_path_to_utf16(sym, cifs_sb);
 	if (!path) {
 		rc = -ENOMEM;
 		goto out;
@@ -5250,7 +5255,10 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
 	buf->PrintNameLength = cpu_to_le16(plen);
 	memcpy(buf->PathBuffer, path, plen);
 	buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0);
+	if (*sym != sep)
+		buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE);
 
+	convert_delimiter(sym, '/');
 	iov.iov_base = buf;
 	iov.iov_len = len;
 	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 86f6f35b7f32..608ee05491e2 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -178,6 +178,7 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses,
 		}
 
 		ses->chans[chan_index].server = NULL;
+		server->terminate = true;
 		spin_unlock(&ses->chan_lock);
 
 		/*
@@ -188,7 +189,6 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses,
 		 */
 		cifs_put_tcp_session(server, from_reconnect);
 
-		server->terminate = true;
 		cifs_signal_cifsd_for_reconnect(server, false);
 
 		/* mark primary server as needing reconnect */
@@ -399,6 +399,15 @@ skip_sess_setup:
 		goto out;
 	}
 
+	spin_lock(&ses->ses_lock);
+	if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) {
+		spin_unlock(&ses->ses_lock);
+		mutex_unlock(&ses->session_mutex);
+		goto skip_add_channels;
+	}
+	ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
+
 	if (!rc &&
 	    (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
 		mutex_unlock(&ses->session_mutex);
@@ -410,7 +419,7 @@ skip_sess_setup:
 		rc = SMB3_request_interfaces(xid, tcon, false);
 		free_xid(xid);
 
-		if (rc == -EOPNOTSUPP) {
+		if (rc == -EOPNOTSUPP && ses->chan_count > 1) {
 			/*
 			 * some servers like Azure SMB server do not advertise
 			 * that multichannel has been disabled with server
@@ -428,17 +437,22 @@ skip_sess_setup:
 		if (ses->chan_max > ses->chan_count &&
 		    ses->iface_count &&
 		    !SERVER_IS_CHAN(server)) {
-			if (ses->chan_count == 1)
+			if (ses->chan_count == 1) {
 				cifs_server_dbg(VFS, "supports multichannel now\n");
+				queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+						 (SMB_INTERFACE_POLL_INTERVAL * HZ));
+			}
 
 			cifs_try_adding_channels(ses);
-			queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
-					   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 		}
 	} else {
 		mutex_unlock(&ses->session_mutex);
 	}
+
 skip_add_channels:
+	spin_lock(&ses->ses_lock);
+	ses->flags &= ~CIFS_SES_FLAG_SCALE_CHANNELS;
+	spin_unlock(&ses->ses_lock);
 
 	if (smb2_command != SMB2_INTERNAL_CMD)
 		mod_delayed_work(cifsiod_wq, &server->reconnect, 0);
@@ -2390,8 +2404,13 @@ create_durable_v2_buf(struct cifs_open_parms *oparms)
 	 */
 	buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout);
 	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
-	generate_random_uuid(buf->dcontext.CreateGuid);
-	memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+
+	/* for replay, we should not overwrite the existing create guid */
+	if (!oparms->replay) {
+		generate_random_uuid(buf->dcontext.CreateGuid);
+		memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+	} else
+		memcpy(buf->dcontext.CreateGuid, pfid->create_guid, 16);
 
 	/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
 	buf->Name[0] = 'D';
@@ -3128,6 +3147,7 @@ replay_again:
 	/* reinitialize for possible replay */
 	flags = 0;
 	server = cifs_pick_channel(ses);
+	oparms->replay = !!(retries);
 
 	cifs_dbg(FYI, "create/open\n");
 	if (!ses || !server)
@@ -5192,6 +5212,9 @@ int SMB2_query_directory_init(const unsigned int xid,
 	case SMB_FIND_FILE_POSIX_INFO:
 		req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO;
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION;
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			info_level);
@@ -5261,6 +5284,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon,
 		/* note that posix payload are variable size */
 		info_buf_size = sizeof(struct smb2_posix_info);
 		break;
+	case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+		info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO);
+		break;
 	default:
 		cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
 			 srch_inf->info_level);
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index e00278fcfa4f..994d70193432 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -435,8 +435,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	if (!(flags & CIFS_TRANSFORM_REQ))
 		return __smb_send_rqst(server, num_rqst, rqst);
 
-	if (num_rqst > MAX_COMPOUND - 1)
-		return -ENOMEM;
+	if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1))
+		return -EIO;
 
 	if (!server->ops->init_transform_rq) {
 		cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n");
diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c
index 9e8afaa686e3..1a5faa6f6e7b 100644
--- a/fs/smb/server/misc.c
+++ b/fs/smb/server/misc.c
@@ -261,6 +261,7 @@ out_ascii:
 
 /**
  * ksmbd_extract_sharename() - get share name from tree connect request
+ * @um: pointer to a unicode_map structure for character encoding handling
  * @treename:	buffer containing tree name and share name
  *
  * Return:      share name on success, otherwise error
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index ba7a72a6a4f4..089527a8b4ff 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -6173,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 		err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 					     offsetof(struct smb2_read_rsp, Buffer),
 					     aux_payload_buf, nbytes);
-		if (err)
+		if (err) {
+			kvfree(aux_payload_buf);
 			goto out;
+		}
 		kvfree(rpc_resp);
 	} else {
 		err = ksmbd_iov_pin_rsp(work, (void *)rsp,
@@ -6384,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work)
 	err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
 				     offsetof(struct smb2_read_rsp, Buffer),
 				     aux_payload_buf, nbytes);
-	if (err)
+	if (err) {
+		kvfree(aux_payload_buf);
 		goto out;
+	}
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -6760,10 +6764,10 @@ struct file_lock *smb_flock_init(struct file *f)
 
 	locks_init_lock(fl);
 
-	fl->fl_owner = f;
-	fl->fl_pid = current->tgid;
-	fl->fl_file = f;
-	fl->fl_flags = FL_POSIX;
+	fl->c.flc_owner = f;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = f;
+	fl->c.flc_flags = FL_POSIX;
 	fl->fl_ops = NULL;
 	fl->fl_lmops = NULL;
 
@@ -6780,30 +6784,30 @@ static int smb2_set_flock_flags(struct file_lock *flock, int flags)
 	case SMB2_LOCKFLAG_SHARED:
 		ksmbd_debug(SMB, "received shared request\n");
 		cmd = F_SETLKW;
-		flock->fl_type = F_RDLCK;
-		flock->fl_flags |= FL_SLEEP;
+		flock->c.flc_type = F_RDLCK;
+		flock->c.flc_flags |= FL_SLEEP;
 		break;
 	case SMB2_LOCKFLAG_EXCLUSIVE:
 		ksmbd_debug(SMB, "received exclusive request\n");
 		cmd = F_SETLKW;
-		flock->fl_type = F_WRLCK;
-		flock->fl_flags |= FL_SLEEP;
+		flock->c.flc_type = F_WRLCK;
+		flock->c.flc_flags |= FL_SLEEP;
 		break;
 	case SMB2_LOCKFLAG_SHARED | SMB2_LOCKFLAG_FAIL_IMMEDIATELY:
 		ksmbd_debug(SMB,
 			    "received shared & fail immediately request\n");
 		cmd = F_SETLK;
-		flock->fl_type = F_RDLCK;
+		flock->c.flc_type = F_RDLCK;
 		break;
 	case SMB2_LOCKFLAG_EXCLUSIVE | SMB2_LOCKFLAG_FAIL_IMMEDIATELY:
 		ksmbd_debug(SMB,
 			    "received exclusive & fail immediately request\n");
 		cmd = F_SETLK;
-		flock->fl_type = F_WRLCK;
+		flock->c.flc_type = F_WRLCK;
 		break;
 	case SMB2_LOCKFLAG_UNLOCK:
 		ksmbd_debug(SMB, "received unlock request\n");
-		flock->fl_type = F_UNLCK;
+		flock->c.flc_type = F_UNLCK;
 		cmd = F_SETLK;
 		break;
 	}
@@ -6841,13 +6845,13 @@ static void smb2_remove_blocked_lock(void **argv)
 	struct file_lock *flock = (struct file_lock *)argv[0];
 
 	ksmbd_vfs_posix_lock_unblock(flock);
-	wake_up(&flock->fl_wait);
+	locks_wake_up(flock);
 }
 
 static inline bool lock_defer_pending(struct file_lock *fl)
 {
 	/* check pending lock waiters */
-	return waitqueue_active(&fl->fl_wait);
+	return waitqueue_active(&fl->c.flc_wait);
 }
 
 /**
@@ -6938,8 +6942,8 @@ int smb2_lock(struct ksmbd_work *work)
 		list_for_each_entry(cmp_lock, &lock_list, llist) {
 			if (cmp_lock->fl->fl_start <= flock->fl_start &&
 			    cmp_lock->fl->fl_end >= flock->fl_end) {
-				if (cmp_lock->fl->fl_type != F_UNLCK &&
-				    flock->fl_type != F_UNLCK) {
+				if (cmp_lock->fl->c.flc_type != F_UNLCK &&
+				    flock->c.flc_type != F_UNLCK) {
 					pr_err("conflict two locks in one request\n");
 					err = -EINVAL;
 					locks_free_lock(flock);
@@ -6987,12 +6991,12 @@ int smb2_lock(struct ksmbd_work *work)
 		list_for_each_entry(conn, &conn_list, conns_list) {
 			spin_lock(&conn->llist_lock);
 			list_for_each_entry_safe(cmp_lock, tmp2, &conn->lock_list, clist) {
-				if (file_inode(cmp_lock->fl->fl_file) !=
-				    file_inode(smb_lock->fl->fl_file))
+				if (file_inode(cmp_lock->fl->c.flc_file) !=
+				    file_inode(smb_lock->fl->c.flc_file))
 					continue;
 
-				if (smb_lock->fl->fl_type == F_UNLCK) {
-					if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file &&
+				if (lock_is_unlock(smb_lock->fl)) {
+					if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file &&
 					    cmp_lock->start == smb_lock->start &&
 					    cmp_lock->end == smb_lock->end &&
 					    !lock_defer_pending(cmp_lock->fl)) {
@@ -7009,7 +7013,7 @@ int smb2_lock(struct ksmbd_work *work)
 					continue;
 				}
 
-				if (cmp_lock->fl->fl_file == smb_lock->fl->fl_file) {
+				if (cmp_lock->fl->c.flc_file == smb_lock->fl->c.flc_file) {
 					if (smb_lock->flags & SMB2_LOCKFLAG_SHARED)
 						continue;
 				} else {
@@ -7051,7 +7055,7 @@ int smb2_lock(struct ksmbd_work *work)
 		}
 		up_read(&conn_list_lock);
 out_check_cl:
-		if (smb_lock->fl->fl_type == F_UNLCK && nolock) {
+		if (lock_is_unlock(smb_lock->fl) && nolock) {
 			pr_err("Try to unlock nolocked range\n");
 			rsp->hdr.Status = STATUS_RANGE_NOT_LOCKED;
 			goto out;
@@ -7175,7 +7179,7 @@ out:
 		struct file_lock *rlock = NULL;
 
 		rlock = smb_flock_init(filp);
-		rlock->fl_type = F_UNLCK;
+		rlock->c.flc_type = F_UNLCK;
 		rlock->fl_start = smb_lock->start;
 		rlock->fl_end = smb_lock->end;
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index a6961bfe3e13..c487e834331a 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -337,18 +337,18 @@ static int check_lock_range(struct file *filp, loff_t start, loff_t end,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(flock, &ctx->flc_posix, fl_list) {
+	for_each_file_lock(flock, &ctx->flc_posix) {
 		/* check conflict locks */
 		if (flock->fl_end >= start && end >= flock->fl_start) {
-			if (flock->fl_type == F_RDLCK) {
+			if (lock_is_read(flock)) {
 				if (type == WRITE) {
 					pr_err("not allow write by shared lock\n");
 					error = 1;
 					goto out;
 				}
-			} else if (flock->fl_type == F_WRLCK) {
+			} else if (lock_is_write(flock)) {
 				/* check owner in lock */
-				if (flock->fl_file != filp) {
+				if (flock->c.flc_file != filp) {
 					error = 1;
 					pr_err("not allow rw access by exclusive lock from other opens\n");
 					goto out;
@@ -1837,13 +1837,13 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work,
 
 void ksmbd_vfs_posix_lock_wait(struct file_lock *flock)
 {
-	wait_event(flock->fl_wait, !flock->fl_blocker);
+	wait_event(flock->c.flc_wait, !flock->c.flc_blocker);
 }
 
 int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout)
 {
-	return wait_event_interruptible_timeout(flock->fl_wait,
-						!flock->fl_blocker,
+	return wait_event_interruptible_timeout(flock->c.flc_wait,
+						!flock->c.flc_blocker,
 						timeout);
 }
 
diff --git a/fs/super.c b/fs/super.c
index d35e85295489..ee05ab6b37e7 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -274,9 +274,10 @@ static void destroy_super_work(struct work_struct *work)
 {
 	struct super_block *s = container_of(work, struct super_block,
 							destroy_work);
-	int i;
-
-	for (i = 0; i < SB_FREEZE_LEVELS; i++)
+	security_sb_free(s);
+	put_user_ns(s->s_user_ns);
+	kfree(s->s_subtype);
+	for (int i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
 	kfree(s);
 }
@@ -296,9 +297,6 @@ static void destroy_unused_super(struct super_block *s)
 	super_unlock_excl(s);
 	list_lru_destroy(&s->s_dentry_lru);
 	list_lru_destroy(&s->s_inode_lru);
-	security_sb_free(s);
-	put_user_ns(s->s_user_ns);
-	kfree(s->s_subtype);
 	shrinker_free(s->s_shrink);
 	/* no delays needed */
 	destroy_super_work(&s->destroy_work);
@@ -409,9 +407,6 @@ static void __put_super(struct super_block *s)
 		WARN_ON(s->s_dentry_lru.node);
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(!list_empty(&s->s_mounts));
-		security_sb_free(s);
-		put_user_ns(s->s_user_ns);
-		kfree(s->s_subtype);
 		call_rcu(&s->rcu, destroy_super_rcu);
 	}
 }
@@ -1532,16 +1527,16 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 		struct fs_context *fc)
 {
 	blk_mode_t mode = sb_open_mode(sb_flags);
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct block_device *bdev;
 
-	bdev_handle = bdev_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
-	if (IS_ERR(bdev_handle)) {
+	bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops);
+	if (IS_ERR(bdev_file)) {
 		if (fc)
 			errorf(fc, "%s: Can't open blockdev", fc->source);
-		return PTR_ERR(bdev_handle);
+		return PTR_ERR(bdev_file);
 	}
-	bdev = bdev_handle->bdev;
+	bdev = file_bdev(bdev_file);
 
 	/*
 	 * This really should be in blkdev_get_by_dev, but right now can't due
@@ -1549,7 +1544,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	 * writable from userspace even for a read-only block device.
 	 */
 	if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EACCES;
 	}
 
@@ -1560,11 +1555,11 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
 		if (fc)
 			warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
-		bdev_release(bdev_handle);
+		fput(bdev_file);
 		return -EBUSY;
 	}
 	spin_lock(&sb_lock);
-	sb->s_bdev_handle = bdev_handle;
+	sb->s_bdev_file = bdev_file;
 	sb->s_bdev = bdev;
 	sb->s_bdi = bdi_get(bdev->bd_disk->bdi);
 	if (bdev_stable_writes(bdev))
@@ -1680,7 +1675,7 @@ void kill_block_super(struct super_block *sb)
 	generic_shutdown_super(sb);
 	if (bdev) {
 		sync_blockdev(bdev);
-		bdev_release(sb->s_bdev_handle);
+		fput(sb->s_bdev_file);
 	}
 }
 
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 5a915b2e68f5..76bc2d5e75a9 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -336,7 +336,7 @@ int __init sysv_init_icache(void)
 {
 	sysv_inode_cachep = kmem_cache_create("sysv_inode_cache",
 			sizeof(struct sysv_inode_info), 0,
-			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT,
+			SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT,
 			init_once);
 	if (!sysv_inode_cachep)
 		return -ENOMEM;
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 410ab2a44d2f..19bcb51a2203 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -83,9 +83,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh)
 	return (sysv_zone_t*)((char*)bh->b_data + bh->b_size);
 }
 
-/*
- * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock)
- */
 static Indirect *get_branch(struct inode *inode,
 			    int depth,
 			    int offsets[],
@@ -105,15 +102,18 @@ static Indirect *get_branch(struct inode *inode,
 		bh = sb_bread(sb, block);
 		if (!bh)
 			goto failure;
+		read_lock(&pointers_lock);
 		if (!verify_chain(chain, p))
 			goto changed;
 		add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets);
+		read_unlock(&pointers_lock);
 		if (!p->key)
 			goto no_block;
 	}
 	return NULL;
 
 changed:
+	read_unlock(&pointers_lock);
 	brelse(bh);
 	*err = -EAGAIN;
 	goto no_block;
@@ -219,9 +219,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b
 		goto out;
 
 reread:
-	read_lock(&pointers_lock);
 	partial = get_branch(inode, depth, offsets, chain, &err);
-	read_unlock(&pointers_lock);
 
 	/* Simplest case - block found, no allocation needed */
 	if (!partial) {
@@ -291,9 +289,9 @@ static Indirect *find_shared(struct inode *inode,
 	*top = 0;
 	for (k = depth; k > 1 && !offsets[k-1]; k--)
 		;
+	partial = get_branch(inode, k, offsets, chain, &err);
 
 	write_lock(&pointers_lock);
-	partial = get_branch(inode, k, offsets, chain, &err);
 	if (!partial)
 		partial = chain + k-1;
 	/*
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 6b211522a13e..110e8a272189 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -62,6 +62,46 @@ enum {
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
+/*
+ * eventfs_inode reference count management.
+ *
+ * NOTE! We count only references from dentries, in the
+ * form 'dentry->d_fsdata'. There are also references from
+ * directory inodes ('ti->private'), but the dentry reference
+ * count is always a superset of the inode reference count.
+ */
+static void release_ei(struct kref *ref)
+{
+	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+
+	WARN_ON_ONCE(!ei->is_freed);
+
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	kfree_rcu(ei, rcu);
+}
+
+static inline void put_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_put(&ei->kref, release_ei);
+}
+
+static inline void free_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		ei->is_freed = 1;
+		put_ei(ei);
+	}
+}
+
+static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
+{
+	if (ei)
+		kref_get(&ei->kref);
+	return ei;
+}
+
 static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags);
@@ -156,33 +196,30 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	return ret;
 }
 
-static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry)
+static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
 {
-	struct inode *inode;
+	struct inode *root;
 
 	/* Only update if the "events" was on the top level */
 	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
 		return;
 
 	/* Get the tracefs root inode. */
-	inode = d_inode(dentry->d_sb->s_root);
-	ei->attr.uid = inode->i_uid;
-	ei->attr.gid = inode->i_gid;
+	root = d_inode(sb->s_root);
+	ei->attr.uid = root->i_uid;
+	ei->attr.gid = root->i_gid;
 }
 
 static void set_top_events_ownership(struct inode *inode)
 {
 	struct tracefs_inode *ti = get_tracefs(inode);
 	struct eventfs_inode *ei = ti->private;
-	struct dentry *dentry;
 
 	/* The top events directory doesn't get automatically updated */
 	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
 		return;
 
-	dentry = ei->dentry;
-
-	update_top_events_attr(ei, dentry);
+	update_top_events_attr(ei, inode->i_sb);
 
 	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
 		inode->i_uid = ei->attr.uid;
@@ -233,10 +270,11 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 {
 	struct eventfs_inode *ei;
 
-	mutex_lock(&eventfs_mutex);
 	do {
-		/* The parent always has an ei, except for events itself */
-		ei = dentry->d_parent->d_fsdata;
+		// The parent is stable because we do not do renames
+		dentry = dentry->d_parent;
+		// ... and directories always have d_fsdata
+		ei = dentry->d_fsdata;
 
 		/*
 		 * If the ei is being freed, the ownership of the children
@@ -246,12 +284,10 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 			ei = NULL;
 			break;
 		}
-
-		dentry = ei->dentry;
+		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
-	mutex_unlock(&eventfs_mutex);
 
-	update_top_events_attr(ei, dentry);
+	update_top_events_attr(ei, dentry->d_sb);
 
 	return ei;
 }
@@ -281,50 +317,11 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 		inode->i_gid = attr->gid;
 }
 
-static void update_gid(struct eventfs_inode *ei, kgid_t gid, int level)
-{
-	struct eventfs_inode *ei_child;
-
-	/* at most we have events/system/event */
-	if (WARN_ON_ONCE(level > 3))
-		return;
-
-	ei->attr.gid = gid;
-
-	if (ei->entry_attrs) {
-		for (int i = 0; i < ei->nr_entries; i++) {
-			ei->entry_attrs[i].gid = gid;
-		}
-	}
-
-	/*
-	 * Only eventfs_inode with dentries are updated, make sure
-	 * all eventfs_inodes are updated. If one of the children
-	 * do not have a dentry, this function must traverse it.
-	 */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		if (!ei_child->dentry)
-			update_gid(ei_child, gid, level + 1);
-	}
-}
-
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
-{
-	struct eventfs_inode *ei = dentry->d_fsdata;
-	int idx;
-
-	idx = srcu_read_lock(&eventfs_srcu);
-	update_gid(ei, gid, 0);
-	srcu_read_unlock(&eventfs_srcu, idx);
-}
-
 /**
- * create_file - create a file in the tracefs filesystem
- * @name: the name of the file to create.
+ * lookup_file - look up a file in the tracefs filesystem
+ * @dentry: the dentry to look up
  * @mode: the permission that the file should have.
  * @attr: saved attributes changed by user
- * @parent: parent dentry for this file.
  * @data: something that the caller will want to get to later on.
  * @fop: struct file_operations that should be used for this file.
  *
@@ -332,30 +329,25 @@ void eventfs_update_gid(struct dentry *dentry, kgid_t gid)
  * directory. The inode.i_private pointer will point to @data in the open()
  * call.
  */
-static struct dentry *create_file(const char *name, umode_t mode,
+static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
+				  struct dentry *dentry,
+				  umode_t mode,
 				  struct eventfs_attr *attr,
-				  struct dentry *parent, void *data,
+				  void *data,
 				  const struct file_operations *fop)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
 	if (!(mode & S_IFMT))
 		mode |= S_IFREG;
 
 	if (WARN_ON_ONCE(!S_ISREG(mode)))
-		return NULL;
-
-	WARN_ON_ONCE(!parent);
-	dentry = eventfs_start_creating(name, parent);
-
-	if (IS_ERR(dentry))
-		return dentry;
+		return ERR_PTR(-EIO);
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, attr, mode);
@@ -369,32 +361,31 @@ static struct dentry *create_file(const char *name, umode_t mode,
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
-	d_instantiate(dentry, inode);
-	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+
+	// Files have their parent's ei as their fsdata
+	dentry->d_fsdata = get_ei(parent_ei);
+
+	d_add(dentry, inode);
+	return NULL;
 };
 
 /**
- * create_dir - create a dir in the tracefs filesystem
+ * lookup_dir_entry - look up a dir in the tracefs filesystem
+ * @dentry: the directory to look up
  * @ei: the eventfs_inode that represents the directory to create
- * @parent: parent dentry for this file.
  *
- * This function will create a dentry for a directory represented by
+ * This function will look up a dentry for a directory represented by
  * a eventfs_inode.
  */
-static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent)
+static struct dentry *lookup_dir_entry(struct dentry *dentry,
+	struct eventfs_inode *pei, struct eventfs_inode *ei)
 {
 	struct tracefs_inode *ti;
-	struct dentry *dentry;
 	struct inode *inode;
 
-	dentry = eventfs_start_creating(ei->name, parent);
-	if (IS_ERR(dentry))
-		return dentry;
-
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
-		return eventfs_failed_creating(dentry);
+		return ERR_PTR(-ENOMEM);
 
 	/* If the user updated the directory's attributes, use them */
 	update_inode_attr(dentry, inode, &ei->attr,
@@ -408,64 +399,46 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
 
 	ti = get_tracefs(inode);
 	ti->flags |= TRACEFS_EVENT_INODE;
+	/* Only directories have ti->private set to an ei, not files */
+	ti->private = ei;
 
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return eventfs_end_creating(dentry);
+	dentry->d_fsdata = get_ei(ei);
+
+	d_add(dentry, inode);
+	return NULL;
 }
 
-static void free_ei(struct eventfs_inode *ei)
+static inline struct eventfs_inode *alloc_ei(const char *name)
 {
-	kfree_const(ei->name);
-	kfree(ei->d_children);
-	kfree(ei->entry_attrs);
-	kfree(ei);
+	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+
+	if (!ei)
+		return NULL;
+
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name) {
+		kfree(ei);
+		return NULL;
+	}
+	kref_init(&ei->kref);
+	return ei;
 }
 
 /**
- * eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode
- * @ti: the tracefs_inode of the dentry
+ * eventfs_d_release - dentry is going away
  * @dentry: dentry which has the reference to remove.
  *
  * Remove the association between a dentry from an eventfs_inode.
  */
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
+void eventfs_d_release(struct dentry *dentry)
 {
-	struct eventfs_inode *ei;
-	int i;
-
-	mutex_lock(&eventfs_mutex);
-
-	ei = dentry->d_fsdata;
-	if (!ei)
-		goto out;
-
-	/* This could belong to one of the files of the ei */
-	if (ei->dentry != dentry) {
-		for (i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i] == dentry)
-				break;
-		}
-		if (WARN_ON_ONCE(i == ei->nr_entries))
-			goto out;
-		ei->d_children[i] = NULL;
-	} else if (ei->is_freed) {
-		free_ei(ei);
-	} else {
-		ei->dentry = NULL;
-	}
-
-	dentry->d_fsdata = NULL;
- out:
-	mutex_unlock(&eventfs_mutex);
+	put_ei(dentry->d_fsdata);
 }
 
 /**
- * create_file_dentry - create a dentry for a file of an eventfs_inode
+ * lookup_file_dentry - create a dentry for a file of an eventfs_inode
  * @ei: the eventfs_inode that the file will be created under
- * @idx: the index into the d_children[] of the @ei
+ * @idx: the index into the entry_attrs[] of the @ei
  * @parent: The parent dentry of the created file.
  * @name: The name of the file to create
  * @mode: The mode of the file.
@@ -476,163 +449,17 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
  * address located at @e_dentry.
  */
 static struct dentry *
-create_file_dentry(struct eventfs_inode *ei, int idx,
-		   struct dentry *parent, const char *name, umode_t mode, void *data,
+lookup_file_dentry(struct dentry *dentry,
+		   struct eventfs_inode *ei, int idx,
+		   umode_t mode, void *data,
 		   const struct file_operations *fops)
 {
 	struct eventfs_attr *attr = NULL;
-	struct dentry **e_dentry = &ei->d_children[idx];
-	struct dentry *dentry;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
 
-	mutex_lock(&eventfs_mutex);
-	if (ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	/* If the e_dentry already has a dentry, use it */
-	if (*e_dentry) {
-		dget(*e_dentry);
-		mutex_unlock(&eventfs_mutex);
-		return *e_dentry;
-	}
-
-	/* ei->entry_attrs are protected by SRCU */
 	if (ei->entry_attrs)
 		attr = &ei->entry_attrs[idx];
 
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_file(name, mode, attr, parent, data, fops);
-
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry)) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed, don't return it. If e_dentry is NULL
-		 * it means it was already freed.
-		 */
-		if (ei->is_freed) {
-			dentry = NULL;
-		} else {
-			dentry = *e_dentry;
-			dget(dentry);
-		}
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!*e_dentry && !ei->is_freed) {
-		*e_dentry = dentry;
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	return dentry;
-}
-
-/**
- * eventfs_post_create_dir - post create dir routine
- * @ei: eventfs_inode of recently created dir
- *
- * Map the meta-data of files within an eventfs dir to their parent dentry
- */
-static void eventfs_post_create_dir(struct eventfs_inode *ei)
-{
-	struct eventfs_inode *ei_child;
-	struct tracefs_inode *ti;
-
-	lockdep_assert_held(&eventfs_mutex);
-
-	/* srcu lock already held */
-	/* fill parent-child relation */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
-		ei_child->d_parent = ei->dentry;
-	}
-
-	ti = get_tracefs(ei->dentry->d_inode);
-	ti->private = ei;
-}
-
-/**
- * create_dir_dentry - Create a directory dentry for the eventfs_inode
- * @pei: The eventfs_inode parent of ei.
- * @ei: The eventfs_inode to create the directory for
- * @parent: The dentry of the parent of this directory
- *
- * This creates and attaches a directory dentry to the eventfs_inode @ei.
- */
-static struct dentry *
-create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
-		  struct dentry *parent)
-{
-	struct dentry *dentry = NULL;
-
-	WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
-
-	mutex_lock(&eventfs_mutex);
-	if (pei->is_freed || ei->is_freed) {
-		mutex_unlock(&eventfs_mutex);
-		return NULL;
-	}
-	if (ei->dentry) {
-		/* If the eventfs_inode already has a dentry, use it */
-		dentry = ei->dentry;
-		dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	dentry = create_dir(ei, parent);
-
-	mutex_lock(&eventfs_mutex);
-
-	if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
-		/*
-		 * When the mutex was released, something else could have
-		 * created the dentry for this e_dentry. In which case
-		 * use that one.
-		 *
-		 * If ei->is_freed is set, the e_dentry is currently on its
-		 * way to being freed.
-		 */
-		dentry = ei->dentry;
-		if (dentry)
-			dget(dentry);
-		mutex_unlock(&eventfs_mutex);
-		return dentry;
-	}
-
-	if (!ei->dentry && !ei->is_freed) {
-		ei->dentry = dentry;
-		eventfs_post_create_dir(ei);
-		dentry->d_fsdata = ei;
-	} else {
-		/*
-		 * Should never happen unless we get here due to being freed.
-		 * Otherwise it means two dentries exist with the same name.
-		 */
-		WARN_ON_ONCE(!ei->is_freed);
-		dentry = NULL;
-	}
-	mutex_unlock(&eventfs_mutex);
-
-	return dentry;
+	return lookup_file(ei, dentry, mode, attr, data, fops);
 }
 
 /**
@@ -649,79 +476,50 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 					  struct dentry *dentry,
 					  unsigned int flags)
 {
-	const struct file_operations *fops;
-	const struct eventfs_entry *entry;
 	struct eventfs_inode *ei_child;
 	struct tracefs_inode *ti;
 	struct eventfs_inode *ei;
-	struct dentry *ei_dentry = NULL;
-	struct dentry *ret = NULL;
-	struct dentry *d;
 	const char *name = dentry->d_name.name;
-	umode_t mode;
-	void *data;
-	int idx;
-	int i;
-	int r;
+	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
 	if (!(ti->flags & TRACEFS_EVENT_INODE))
-		return NULL;
-
-	/* Grab srcu to prevent the ei from going away */
-	idx = srcu_read_lock(&eventfs_srcu);
+		return ERR_PTR(-EIO);
 
-	/*
-	 * Grab the eventfs_mutex to consistent value from ti->private.
-	 * This s
-	 */
 	mutex_lock(&eventfs_mutex);
-	ei = READ_ONCE(ti->private);
-	if (ei && !ei->is_freed)
-		ei_dentry = READ_ONCE(ei->dentry);
-	mutex_unlock(&eventfs_mutex);
 
-	if (!ei || !ei_dentry)
+	ei = ti->private;
+	if (!ei || ei->is_freed)
 		goto out;
 
-	data = ei->data;
-
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 srcu_read_lock_held(&eventfs_srcu)) {
+	list_for_each_entry(ei_child, &ei->children, list) {
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		ret = simple_lookup(dir, dentry, flags);
-		if (IS_ERR(ret))
+		if (ei_child->is_freed)
 			goto out;
-		d = create_dir_dentry(ei, ei_child, ei_dentry);
-		dput(d);
+		result = lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
 	}
 
-	for (i = 0; i < ei->nr_entries; i++) {
-		entry = &ei->entries[i];
-		if (strcmp(name, entry->name) == 0) {
-			void *cdata = data;
-			mutex_lock(&eventfs_mutex);
-			/* If ei->is_freed, then the event itself may be too */
-			if (!ei->is_freed)
-				r = entry->callback(name, &mode, &cdata, &fops);
-			else
-				r = -1;
-			mutex_unlock(&eventfs_mutex);
-			if (r <= 0)
-				continue;
-			ret = simple_lookup(dir, dentry, flags);
-			if (IS_ERR(ret))
-				goto out;
-			d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
-			dput(d);
-			break;
-		}
+	for (int i = 0; i < ei->nr_entries; i++) {
+		void *data;
+		umode_t mode;
+		const struct file_operations *fops;
+		const struct eventfs_entry *entry = &ei->entries[i];
+
+		if (strcmp(name, entry->name) != 0)
+			continue;
+
+		data = ei->data;
+		if (entry->callback(name, &mode, &data, &fops) <= 0)
+			goto out;
+
+		result = lookup_file_dentry(dentry, ei, i, mode, data, fops);
+		goto out;
 	}
  out:
-	srcu_read_unlock(&eventfs_srcu, idx);
-	return ret;
+	mutex_unlock(&eventfs_mutex);
+	return result;
 }
 
 /*
@@ -871,25 +669,10 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	if (!parent)
 		return ERR_PTR(-EINVAL);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
 		return ERR_PTR(-ENOMEM);
 
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name) {
-		kfree(ei);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	if (size) {
-		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
-		if (!ei->d_children) {
-			kfree_const(ei->name);
-			kfree(ei);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->data = data;
@@ -897,10 +680,8 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 	INIT_LIST_HEAD(&ei->list);
 
 	mutex_lock(&eventfs_mutex);
-	if (!parent->is_freed) {
+	if (!parent->is_freed)
 		list_add_tail(&ei->list, &parent->children);
-		ei->d_parent = parent->dentry;
-	}
 	mutex_unlock(&eventfs_mutex);
 
 	/* Was the parent freed? */
@@ -940,28 +721,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 
-	ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	ei = alloc_ei(name);
 	if (!ei)
-		goto fail_ei;
+		goto fail;
 
 	inode = tracefs_get_inode(dentry->d_sb);
 	if (unlikely(!inode))
 		goto fail;
 
-	if (size) {
-		ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
-		if (!ei->d_children)
-			goto fail;
-	}
-
-	ei->dentry = dentry;
+	// Note: we have a ref to the dentry from tracefs_start_creating()
+	ei->events_dir = dentry;
 	ei->entries = entries;
 	ei->nr_entries = size;
 	ei->is_events = 1;
 	ei->data = data;
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name)
-		goto fail;
 
 	/* Save the ownership of this directory */
 	uid = d_inode(dentry->d_parent)->i_uid;
@@ -992,11 +765,19 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	inode->i_op = &eventfs_root_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
-	dentry->d_fsdata = ei;
+	dentry->d_fsdata = get_ei(ei);
 
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
+	/*
+	 * Keep all eventfs directories with i_nlink == 1.
+	 * Due to the dynamic nature of the dentry creations and not
+	 * wanting to add a pointer to the parent eventfs_inode in the
+	 * eventfs_inode structure, keeping the i_nlink in sync with the
+	 * number of directories would cause too much complexity for
+	 * something not worth much. Keeping directory links at 1
+	 * tells userspace not to trust the link number.
+	 */
 	d_instantiate(dentry, inode);
+	/* The dentry of the "events" parent does keep track though */
 	inc_nlink(dentry->d_parent->d_inode);
 	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
 	tracefs_end_creating(dentry);
@@ -1004,72 +785,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	return ei;
 
  fail:
-	kfree(ei->d_children);
-	kfree(ei);
- fail_ei:
+	free_ei(ei);
 	tracefs_failed_creating(dentry);
 	return ERR_PTR(-ENOMEM);
 }
 
-static LLIST_HEAD(free_list);
-
-static void eventfs_workfn(struct work_struct *work)
-{
-        struct eventfs_inode *ei, *tmp;
-        struct llist_node *llnode;
-
-	llnode = llist_del_all(&free_list);
-        llist_for_each_entry_safe(ei, tmp, llnode, llist) {
-		/* This dput() matches the dget() from unhook_dentry() */
-		for (int i = 0; i < ei->nr_entries; i++) {
-			if (ei->d_children[i])
-				dput(ei->d_children[i]);
-		}
-		/* This should only get here if it had a dentry */
-		if (!WARN_ON_ONCE(!ei->dentry))
-			dput(ei->dentry);
-        }
-}
-
-static DECLARE_WORK(eventfs_work, eventfs_workfn);
-
-static void free_rcu_ei(struct rcu_head *head)
-{
-	struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu);
-
-	if (ei->dentry) {
-		/* Do not free the ei until all references of dentry are gone */
-		if (llist_add(&ei->llist, &free_list))
-			queue_work(system_unbound_wq, &eventfs_work);
-		return;
-	}
-
-	/* If the ei doesn't have a dentry, neither should its children */
-	for (int i = 0; i < ei->nr_entries; i++) {
-		WARN_ON_ONCE(ei->d_children[i]);
-	}
-
-	free_ei(ei);
-}
-
-static void unhook_dentry(struct dentry *dentry)
-{
-	if (!dentry)
-		return;
-	/*
-	 * Need to add a reference to the dentry that is expected by
-	 * simple_recursive_removal(), which will include a dput().
-	 */
-	dget(dentry);
-
-	/*
-	 * Also add a reference for the dput() in eventfs_workfn().
-	 * That is required as that dput() will free the ei after
-	 * the SRCU grace period is over.
-	 */
-	dget(dentry);
-}
-
 /**
  * eventfs_remove_rec - remove eventfs dir or file from list
  * @ei: eventfs_inode to be removed.
@@ -1082,8 +802,6 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 {
 	struct eventfs_inode *ei_child;
 
-	if (!ei)
-		return;
 	/*
 	 * Check recursion depth. It should never be greater than 3:
 	 * 0 - events/
@@ -1095,28 +813,11 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
 		return;
 
 	/* search for nested folders or files */
-	list_for_each_entry_srcu(ei_child, &ei->children, list,
-				 lockdep_is_held(&eventfs_mutex)) {
-		/* Children only have dentry if parent does */
-		WARN_ON_ONCE(ei_child->dentry && !ei->dentry);
+	list_for_each_entry(ei_child, &ei->children, list)
 		eventfs_remove_rec(ei_child, level + 1);
-	}
-
-
-	ei->is_freed = 1;
 
-	for (int i = 0; i < ei->nr_entries; i++) {
-		if (ei->d_children[i]) {
-			/* Children only have dentry if parent does */
-			WARN_ON_ONCE(!ei->dentry);
-			unhook_dentry(ei->d_children[i]);
-		}
-	}
-
-	unhook_dentry(ei->dentry);
-
-	list_del_rcu(&ei->list);
-	call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_ei);
+	list_del(&ei->list);
+	free_ei(ei);
 }
 
 /**
@@ -1127,22 +828,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
  */
 void eventfs_remove_dir(struct eventfs_inode *ei)
 {
-	struct dentry *dentry;
-
 	if (!ei)
 		return;
 
 	mutex_lock(&eventfs_mutex);
-	dentry = ei->dentry;
 	eventfs_remove_rec(ei, 0);
 	mutex_unlock(&eventfs_mutex);
-
-	/*
-	 * If any of the ei children has a dentry, then the ei itself
-	 * must have a dentry.
-	 */
-	if (dentry)
-		simple_recursive_removal(dentry, NULL);
 }
 
 /**
@@ -1155,7 +846,11 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
 	struct dentry *dentry;
 
-	dentry = ei->dentry;
+	dentry = ei->events_dir;
+	if (!dentry)
+		return;
+
+	ei->events_dir = NULL;
 	eventfs_remove_dir(ei);
 
 	/*
@@ -1165,5 +860,6 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
 	 * sticks around while the other ei->dentry are created
 	 * and destroyed dynamically.
 	 */
+	d_invalidate(dentry);
 	dput(dentry);
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index e1b172c0e091..d65ffad4c327 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
 	if (!ti)
 		return NULL;
 
-	ti->flags = 0;
-
 	return &ti->vfs_inode;
 }
 
@@ -379,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
 	.show_options	= tracefs_show_options,
 };
 
-static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode)
+/*
+ * It would be cleaner if eventfs had its own dentry ops.
+ *
+ * Note that d_revalidate is called potentially under RCU,
+ * so it can't take the eventfs mutex etc. It's fine - if
+ * we open a file just as it's marked dead, things will
+ * still work just fine, and just see the old stale case.
+ */
+static void tracefs_d_release(struct dentry *dentry)
 {
-	struct tracefs_inode *ti;
+	if (dentry->d_fsdata)
+		eventfs_d_release(dentry);
+}
 
-	if (!dentry || !inode)
-		return;
+static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct eventfs_inode *ei = dentry->d_fsdata;
 
-	ti = get_tracefs(inode);
-	if (ti && ti->flags & TRACEFS_EVENT_INODE)
-		eventfs_set_ei_status_free(ti, dentry);
-	iput(inode);
+	return !(ei && ei->is_freed);
 }
 
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_dentry_iput,
+	.d_revalidate = tracefs_d_revalidate,
+	.d_release = tracefs_d_release,
 };
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
@@ -497,75 +504,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
 	return dentry;
 }
 
-/**
- * eventfs_start_creating - start the process of creating a dentry
- * @name: Name of the file created for the dentry
- * @parent: The parent dentry where this dentry will be created
- *
- * This is a simple helper function for the dynamically created eventfs
- * files. When the directory of the eventfs files are accessed, their
- * dentries are created on the fly. This function is used to start that
- * process.
- */
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
-{
-	struct dentry *dentry;
-	int error;
-
-	/* Must always have a parent. */
-	if (WARN_ON_ONCE(!parent))
-		return ERR_PTR(-EINVAL);
-
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
-	if (error)
-		return ERR_PTR(error);
-
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
-
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-	return dentry;
-}
-
-/**
- * eventfs_failed_creating - clean up a failed eventfs dentry creation
- * @dentry: The dentry to clean up
- *
- * If after calling eventfs_start_creating(), a failure is detected, the
- * resources created by eventfs_start_creating() needs to be cleaned up. In
- * that case, this function should be called to perform that clean up.
- */
-struct dentry *eventfs_failed_creating(struct dentry *dentry)
-{
-	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	return NULL;
-}
-
-/**
- * eventfs_end_creating - Finish the process of creating a eventfs dentry
- * @dentry: The dentry that has successfully been created.
- *
- * This function is currently just a place holder to match
- * eventfs_start_creating(). In case any synchronization needs to be added,
- * this function will be used to implement that without having to modify
- * the callers of eventfs_start_creating().
- */
-struct dentry *eventfs_end_creating(struct dentry *dentry)
-{
-	return dentry;
-}
-
 /* Find the inode that this will use for default */
 static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
 {
@@ -779,7 +717,11 @@ static void init_once(void *foo)
 {
 	struct tracefs_inode *ti = (struct tracefs_inode *) foo;
 
+	/* inode_init_once() calls memset() on the vfs_inode portion */
 	inode_init_once(&ti->vfs_inode);
+
+	/* Zero out the rest */
+	memset_after(ti, 0, vfs_inode);
 }
 
 static int __init tracefs_init(void)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 45397df9bb65..beb3dcd0e434 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -11,9 +11,10 @@ enum {
 };
 
 struct tracefs_inode {
+	struct inode            vfs_inode;
+	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
 	unsigned long           flags;
 	void                    *private;
-	struct inode            vfs_inode;
 };
 
 /*
@@ -31,43 +32,37 @@ struct eventfs_attr {
 /*
  * struct eventfs_inode - hold the properties of the eventfs directories.
  * @list:	link list into the parent directory
+ * @rcu:	Union with @list for freeing
+ * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @children:	link list into the child eventfs_inode
- * @dentry:     the dentry of the directory
- * @d_parent:   pointer to the parent's dentry
- * @d_children: The array of dentries to represent the files when created
+ * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
- * @attr:	Saved mode and ownership of eventfs_inode itself
  * @data:	The private data to pass to the callbacks
+ * @attr:	Saved mode and ownership of eventfs_inode itself
  * @is_freed:	Flag set if the eventfs is on its way to be freed
  *                Note if is_freed is set, then dentry is corrupted.
+ * @is_events:	Flag set for only the top level "events" directory
  * @nr_entries: The number of items in @entries
+ * @ino:	The saved inode number
  */
 struct eventfs_inode {
-	struct list_head		list;
+	union {
+		struct list_head	list;
+		struct rcu_head		rcu;
+	};
+	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct list_head		children;
-	struct dentry			*dentry; /* Check is_freed to access */
-	struct dentry			*d_parent;
-	struct dentry			**d_children;
+	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
-	struct eventfs_attr		attr;
 	void				*data;
+	struct eventfs_attr		attr;
+	struct kref			kref;
 	unsigned int			is_freed:1;
 	unsigned int			is_events:1;
 	unsigned int			nr_entries:30;
 	unsigned int			ino;
-	/*
-	 * Union - used for deletion
-	 * @llist:	for calling dput() if needed after RCU
-	 * @rcu:	eventfs_inode to delete in RCU
-	 */
-	union {
-		struct llist_node	llist;
-		struct rcu_head		rcu;
-	};
 };
 
 static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@@ -79,10 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
 struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
-struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
-struct dentry *eventfs_failed_creating(struct dentry *dentry);
-struct dentry *eventfs_end_creating(struct dentry *dentry);
-void eventfs_update_gid(struct dentry *dentry, kgid_t gid);
-void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
+
+void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index e413a9cf8ee3..551148de66cd 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -205,7 +205,6 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 	dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino);
 
 	err = fscrypt_prepare_lookup(dir, dentry, &nm);
-	generic_set_encrypted_ci_d_ops(dentry);
 	if (err == -ENOENT)
 		return d_splice_alias(NULL, dentry);
 	if (err)
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 09e270d6ed02..d2881041b393 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2239,13 +2239,14 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out_umount;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		err = -ENOMEM;
 		goto out_umount;
 	}
 
-	import_uuid(&sb->s_uuid, c->uuid);
+	super_set_uuid(sb, c->uuid, sizeof(c->uuid));
 
 	mutex_unlock(&c->umount_mutex);
 	return 0;
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index a6a6b2749241..b3506f56e180 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -69,7 +69,6 @@ struct fsverity_info {
 	u8 file_digest[FS_VERITY_MAX_DIGEST_SIZE];
 	const struct inode *inode;
 	unsigned long *hash_block_verified;
-	spinlock_t hash_page_init_lock;
 };
 
 #define FS_VERITY_MAX_SIGNATURE_SIZE	(FS_VERITY_MAX_DESCRIPTOR_SIZE - \
diff --git a/fs/verity/open.c b/fs/verity/open.c
index 6c31a871b84b..fdeb95eca3af 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -239,7 +239,6 @@ struct fsverity_info *fsverity_create_info(const struct inode *inode,
 			err = -ENOMEM;
 			goto fail;
 		}
-		spin_lock_init(&vi->hash_page_init_lock);
 	}
 
 	return vi;
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 904ccd7e8e16..4fcad0825a12 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -19,7 +19,6 @@ static struct workqueue_struct *fsverity_read_workqueue;
 static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage,
 				   unsigned long hblock_idx)
 {
-	bool verified;
 	unsigned int blocks_per_page;
 	unsigned int i;
 
@@ -43,12 +42,20 @@ static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage,
 	 * re-instantiated from the backing storage are re-verified.  To do
 	 * this, we use PG_checked again, but now it doesn't really mean
 	 * "checked".  Instead, now it just serves as an indicator for whether
-	 * the hash page is newly instantiated or not.
+	 * the hash page is newly instantiated or not.  If the page is new, as
+	 * indicated by PG_checked=0, we clear the bitmap bits for the page's
+	 * blocks since they are untrustworthy, then set PG_checked=1.
+	 * Otherwise we return the bitmap bit for the requested block.
 	 *
-	 * The first thread that sees PG_checked=0 must clear the corresponding
-	 * bitmap bits, then set PG_checked=1.  This requires a spinlock.  To
-	 * avoid having to take this spinlock in the common case of
-	 * PG_checked=1, we start with an opportunistic lockless read.
+	 * Multiple threads may execute this code concurrently on the same page.
+	 * This is safe because we use memory barriers to ensure that if a
+	 * thread sees PG_checked=1, then it also sees the associated bitmap
+	 * clearing to have occurred.  Also, all writes and their corresponding
+	 * reads are atomic, and all writes are safe to repeat in the event that
+	 * multiple threads get into the PG_checked=0 section.  (Clearing a
+	 * bitmap bit again at worst causes a hash block to be verified
+	 * redundantly.  That event should be very rare, so it's not worth using
+	 * a lock to avoid.  Setting PG_checked again has no effect.)
 	 */
 	if (PageChecked(hpage)) {
 		/*
@@ -58,24 +65,17 @@ static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage,
 		smp_rmb();
 		return test_bit(hblock_idx, vi->hash_block_verified);
 	}
-	spin_lock(&vi->hash_page_init_lock);
-	if (PageChecked(hpage)) {
-		verified = test_bit(hblock_idx, vi->hash_block_verified);
-	} else {
-		blocks_per_page = vi->tree_params.blocks_per_page;
-		hblock_idx = round_down(hblock_idx, blocks_per_page);
-		for (i = 0; i < blocks_per_page; i++)
-			clear_bit(hblock_idx + i, vi->hash_block_verified);
-		/*
-		 * A write memory barrier is needed here to give RELEASE
-		 * semantics to the below SetPageChecked() operation.
-		 */
-		smp_wmb();
-		SetPageChecked(hpage);
-		verified = false;
-	}
-	spin_unlock(&vi->hash_page_init_lock);
-	return verified;
+	blocks_per_page = vi->tree_params.blocks_per_page;
+	hblock_idx = round_down(hblock_idx, blocks_per_page);
+	for (i = 0; i < blocks_per_page; i++)
+		clear_bit(hblock_idx + i, vi->hash_block_verified);
+	/*
+	 * A write memory barrier is needed here to give RELEASE semantics to
+	 * the below SetPageChecked() operation.
+	 */
+	smp_wmb();
+	SetPageChecked(hpage);
+	return false;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 9976a00a73f9..e965a48e7db9 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -421,10 +421,10 @@ xfs_attr_complete_op(
 	bool			do_replace = args->op_flags & XFS_DA_OP_REPLACE;
 
 	args->op_flags &= ~XFS_DA_OP_REPLACE;
-	if (do_replace) {
-		args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+	if (do_replace)
 		return replace_state;
-	}
+
 	return XFS_DAS_DONE;
 }
 
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 31100120b2c5..e31663cb7b43 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1119,20 +1119,6 @@ xfs_rtbitmap_blockcount(
 }
 
 /*
- * Compute the maximum level number of the realtime summary file, as defined by
- * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
- * use of rt volumes with more than 2^32 extents.
- */
-uint8_t
-xfs_compute_rextslog(
-	xfs_rtbxlen_t		rtextents)
-{
-	if (!rtextents)
-		return 0;
-	return xfs_highbit64(rtextents);
-}
-
-/*
  * Compute the number of rtbitmap words needed to populate every block of a
  * bitmap that is large enough to track the given number of rt extents.
  */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h
index 274dc7dae1fa..152a66750af5 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.h
+++ b/fs/xfs/libxfs/xfs_rtbitmap.h
@@ -351,20 +351,6 @@ xfs_rtfree_extent(
 int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno,
 		xfs_filblks_t rtlen);
 
-uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
-
-/* Do we support an rt volume having this number of rtextents? */
-static inline bool
-xfs_validate_rtextents(
-	xfs_rtbxlen_t		rtextents)
-{
-	/* No runt rt volumes */
-	if (rtextents == 0)
-		return false;
-
-	return true;
-}
-
 xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t
 		rtextents);
 unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp,
@@ -383,8 +369,6 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp,
 # define xfs_rtsummary_read_buf(a,b)			(-ENOSYS)
 # define xfs_rtbuf_cache_relse(a)			(0)
 # define xfs_rtalloc_extent_is_free(m,t,s,l,i)		(-ENOSYS)
-# define xfs_compute_rextslog(rtx)			(0)
-# define xfs_validate_rtextents(rtx)			(false)
 static inline xfs_filblks_t
 xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents)
 {
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4a9e8588f4c9..5bb6e2bd6dee 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1377,3 +1377,17 @@ xfs_validate_stripe_geometry(
 	}
 	return true;
 }
+
+/*
+ * Compute the maximum level number of the realtime summary file, as defined by
+ * mkfs.  The historic use of highbit32 on a 64-bit quantity prohibited correct
+ * use of rt volumes with more than 2^32 extents.
+ */
+uint8_t
+xfs_compute_rextslog(
+	xfs_rtbxlen_t		rtextents)
+{
+	if (!rtextents)
+		return 0;
+	return xfs_highbit64(rtextents);
+}
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 19134b23c10b..2e8e8d63d4eb 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -38,4 +38,6 @@ extern int	xfs_sb_get_secondary(struct xfs_mount *mp,
 extern bool	xfs_validate_stripe_geometry(struct xfs_mount *mp,
 		__s64 sunit, __s64 swidth, int sectorsize, bool silent);
 
+uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
+
 #endif	/* __XFS_SB_H__ */
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 20b5375f2d9c..62e02d5380ad 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -251,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off);
 bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off,
 		xfs_fileoff_t len);
 
+/* Do we support an rt volume having this number of rtextents? */
+static inline bool
+xfs_validate_rtextents(
+	xfs_rtbxlen_t		rtextents)
+{
+	/* No runt rt volumes */
+	if (rtextents == 0)
+		return false;
+
+	return true;
+}
+
 #endif	/* __XFS_TYPES_H__ */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 441ca9977652..46583517377f 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -15,6 +15,7 @@
 #include "xfs_inode.h"
 #include "xfs_bmap.h"
 #include "xfs_bit.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index fabd0ed9dfa6..b1ff4f33324a 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -16,6 +16,7 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_bit.h"
 #include "xfs_bmap.h"
+#include "xfs_sb.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 813f85156b0c..1698507d1ac7 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -112,7 +112,7 @@ xfs_end_ioend(
 	 * longer dirty. If we don't remove delalloc blocks here, they become
 	 * stale and can corrupt free space accounting on unmount.
 	 */
-	error = blk_status_to_errno(ioend->io_bio->bi_status);
+	error = blk_status_to_errno(ioend->io_bio.bi_status);
 	if (unlikely(error)) {
 		if (ioend->io_flags & IOMAP_F_SHARED) {
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
@@ -179,7 +179,7 @@ STATIC void
 xfs_end_bio(
 	struct bio		*bio)
 {
-	struct iomap_ioend	*ioend = bio->bi_private;
+	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	unsigned long		flags;
 
@@ -276,7 +276,8 @@ static int
 xfs_map_blocks(
 	struct iomap_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset)
+	loff_t			offset,
+	unsigned int		len)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -444,7 +445,7 @@ xfs_prepare_ioend(
 	/* send ioends that might require a transaction to the completion wq */
 	if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
 	    (ioend->io_flags & IOMAP_F_SHARED))
-		ioend->io_bio->bi_end_io = xfs_end_bio;
+		ioend->io_bio.bi_end_io = xfs_end_bio;
 	return status;
 }
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8e5bd50d29fe..01b41fabbe3c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1951,7 +1951,7 @@ xfs_free_buftarg(
 	fs_put_dax(btp->bt_daxdev, btp->bt_mount);
 	/* the main block device is closed by kill_block_super */
 	if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
-		bdev_release(btp->bt_bdev_handle);
+		fput(btp->bt_bdev_file);
 
 	kmem_free(btp);
 }
@@ -1994,7 +1994,7 @@ xfs_setsize_buftarg_early(
 struct xfs_buftarg *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct bdev_handle	*bdev_handle)
+	struct file		*bdev_file)
 {
 	xfs_buftarg_t		*btp;
 	const struct dax_holder_operations *ops = NULL;
@@ -2005,9 +2005,9 @@ xfs_alloc_buftarg(
 	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
 
 	btp->bt_mount = mp;
-	btp->bt_bdev_handle = bdev_handle;
-	btp->bt_dev = bdev_handle->bdev->bd_dev;
-	btp->bt_bdev = bdev_handle->bdev;
+	btp->bt_bdev_file = bdev_file;
+	btp->bt_bdev = file_bdev(bdev_file);
+	btp->bt_dev = btp->bt_bdev->bd_dev;
 	btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
 					    mp, ops);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b470de08a46c..304e858d04fb 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -98,7 +98,7 @@ typedef unsigned int xfs_buf_flags_t;
  */
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
-	struct bdev_handle	*bt_bdev_handle;
+	struct file		*bt_bdev_file;
 	struct block_device	*bt_bdev;
 	struct dax_device	*bt_daxdev;
 	u64			bt_dax_part_off;
@@ -366,7 +366,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
  *	Handling of buftargs.
  */
 struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
-		struct bdev_handle *bdev_handle);
+		struct file *bdev_file);
 extern void xfs_free_buftarg(struct xfs_buftarg *);
 extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index aabb25dc3efa..57fa21ad7912 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -62,7 +62,7 @@ xfs_uuid_mount(
 	int			hole, i;
 
 	/* Publish UUID in struct super_block */
-	uuid_copy(&mp->m_super->s_uuid, uuid);
+	super_set_uuid(mp->m_super, uuid->b, sizeof(*uuid));
 
 	if (xfs_has_nouuid(mp))
 		return 0;
@@ -706,6 +706,8 @@ xfs_mountfs(
 	/* enable fail_at_unmount as default */
 	mp->m_fail_unmount = true;
 
+	super_set_sysfs_name_id(mp->m_super);
+
 	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
 			       NULL, mp->m_super->s_id);
 	if (error)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 5a2512d20bd0..00fbd5b6e582 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -350,7 +350,6 @@ xfs_setup_dax_always(
 		return -EINVAL;
 	}
 
-	xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
 	return 0;
 
 disable_dax:
@@ -362,16 +361,16 @@ STATIC int
 xfs_blkdev_get(
 	xfs_mount_t		*mp,
 	const char		*name,
-	struct bdev_handle	**handlep)
+	struct file		**bdev_filep)
 {
 	int			error = 0;
 
-	*handlep = bdev_open_by_path(name,
+	*bdev_filep = bdev_file_open_by_path(name,
 		BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
 		mp->m_super, &fs_holder_ops);
-	if (IS_ERR(*handlep)) {
-		error = PTR_ERR(*handlep);
-		*handlep = NULL;
+	if (IS_ERR(*bdev_filep)) {
+		error = PTR_ERR(*bdev_filep);
+		*bdev_filep = NULL;
 		xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
 	}
 
@@ -436,26 +435,26 @@ xfs_open_devices(
 {
 	struct super_block	*sb = mp->m_super;
 	struct block_device	*ddev = sb->s_bdev;
-	struct bdev_handle	*logdev_handle = NULL, *rtdev_handle = NULL;
+	struct file		*logdev_file = NULL, *rtdev_file = NULL;
 	int			error;
 
 	/*
 	 * Open real time and log devices - order is important.
 	 */
 	if (mp->m_logname) {
-		error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle);
+		error = xfs_blkdev_get(mp, mp->m_logname, &logdev_file);
 		if (error)
 			return error;
 	}
 
 	if (mp->m_rtname) {
-		error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_handle);
+		error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_file);
 		if (error)
 			goto out_close_logdev;
 
-		if (rtdev_handle->bdev == ddev ||
-		    (logdev_handle &&
-		     rtdev_handle->bdev == logdev_handle->bdev)) {
+		if (file_bdev(rtdev_file) == ddev ||
+		    (logdev_file &&
+		     file_bdev(rtdev_file) == file_bdev(logdev_file))) {
 			xfs_warn(mp,
 	"Cannot mount filesystem with identical rtdev and ddev/logdev.");
 			error = -EINVAL;
@@ -467,25 +466,25 @@ xfs_open_devices(
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = -ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_handle);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_file);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
-	if (rtdev_handle) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_handle);
+	if (rtdev_file) {
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_file);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
-	if (logdev_handle && logdev_handle->bdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_handle);
+	if (logdev_file && file_bdev(logdev_file) != ddev) {
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_file);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
 		mp->m_logdev_targp = mp->m_ddev_targp;
 		/* Handle won't be used, drop it */
-		if (logdev_handle)
-			bdev_release(logdev_handle);
+		if (logdev_file)
+			fput(logdev_file);
 	}
 
 	return 0;
@@ -496,11 +495,11 @@ xfs_open_devices(
  out_free_ddev_targ:
 	xfs_free_buftarg(mp->m_ddev_targp);
  out_close_rtdev:
-	 if (rtdev_handle)
-		bdev_release(rtdev_handle);
+	 if (rtdev_file)
+		fput(rtdev_file);
  out_close_logdev:
-	if (logdev_handle)
-		bdev_release(logdev_handle);
+	if (logdev_file)
+		fput(logdev_file);
 	return error;
 }
 
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 6ab2318a9c8e..3b103715acc9 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -125,7 +125,8 @@ static void zonefs_readahead(struct readahead_control *rac)
  * which implies that the page range can only be within the fixed inode size.
  */
 static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
-				   struct inode *inode, loff_t offset)
+				   struct inode *inode, loff_t offset,
+				   unsigned int len)
 {
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 
@@ -348,7 +349,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
 	if (error) {
-		zonefs_io_error(inode, true);
+		/*
+		 * For Sync IOs, error recovery is called from
+		 * zonefs_file_dio_write().
+		 */
+		if (!is_sync_kiocb(iocb))
+			zonefs_io_error(inode, true);
 		return error;
 	}
 
@@ -491,6 +497,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 			ret = -EINVAL;
 			goto inode_unlock;
 		}
+		/*
+		 * Advance the zone write pointer offset. This assumes that the
+		 * IO will succeed, which is OK to do because we do not allow
+		 * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO
+		 * fails, the error path will correct the write pointer offset.
+		 */
+		z->z_wpoffset += count;
+		zonefs_inode_account_active(inode);
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
 
@@ -504,20 +518,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	if (ret == -ENOTBLK)
 		ret = -EBUSY;
 
-	if (zonefs_zone_is_seq(z) &&
-	    (ret > 0 || ret == -EIOCBQUEUED)) {
-		if (ret > 0)
-			count = ret;
-
-		/*
-		 * Update the zone write pointer offset assuming the write
-		 * operation succeeded. If it did not, the error recovery path
-		 * will correct it. Also do active seq file accounting.
-		 */
-		mutex_lock(&zi->i_truncate_mutex);
-		z->z_wpoffset += count;
-		zonefs_inode_account_active(inode);
-		mutex_unlock(&zi->i_truncate_mutex);
+	/*
+	 * For a failed IO or partial completion, trigger error recovery
+	 * to update the zone write pointer offset to a correct value.
+	 * For asynchronous IOs, zonefs_file_write_dio_end_io() may already
+	 * have executed error recovery if the IO already completed when we
+	 * reach here. However, we cannot know that and execute error recovery
+	 * again (that will not change anything).
+	 */
+	if (zonefs_zone_is_seq(z)) {
+		if (ret > 0 && ret != count)
+			ret = -EIO;
+		if (ret < 0 && ret != -EIOCBQUEUED)
+			zonefs_io_error(inode, true);
 	}
 
 inode_unlock:
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 93971742613a..236a6d88306f 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -15,12 +15,13 @@
 #include <linux/writeback.h>
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
-#include <linux/parser.h>
 #include <linux/uio.h>
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/crc32.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/fs_parser.h>
+#include <linux/fs_context.h>
 
 #include "zonefs.h"
 
@@ -113,7 +114,7 @@ static int zonefs_zone_mgmt(struct super_block *sb,
 
 	trace_zonefs_zone_mgmt(sb, z, op);
 	ret = blkdev_zone_mgmt(sb->s_bdev, op, z->z_sector,
-			       z->z_size >> SECTOR_SHIFT, GFP_NOFS);
+			       z->z_size >> SECTOR_SHIFT);
 	if (ret) {
 		zonefs_err(sb,
 			   "Zone management operation %s at %llu failed %d\n",
@@ -246,16 +247,18 @@ static void zonefs_inode_update_mode(struct inode *inode)
 	z->z_mode = inode->i_mode;
 }
 
-struct zonefs_ioerr_data {
-	struct inode	*inode;
-	bool		write;
-};
-
 static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 			      void *data)
 {
-	struct zonefs_ioerr_data *err = data;
-	struct inode *inode = err->inode;
+	struct blk_zone *z = data;
+
+	*z = *zone;
+	return 0;
+}
+
+static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone,
+				   bool write)
+{
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
@@ -270,8 +273,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	data_size = zonefs_check_zone_condition(sb, z, zone);
 	isize = i_size_read(inode);
 	if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
-	    !err->write && isize == data_size)
-		return 0;
+	    !write && isize == data_size)
+		return;
 
 	/*
 	 * At this point, we detected either a bad zone or an inconsistency
@@ -292,7 +295,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * In all cases, warn about inode size inconsistency and handle the
 	 * IO error according to the zone condition and to the mount options.
 	 */
-	if (zonefs_zone_is_seq(z) && isize != data_size)
+	if (isize != data_size)
 		zonefs_warn(sb,
 			    "inode %lu: invalid size %lld (should be %lld)\n",
 			    inode->i_ino, isize, data_size);
@@ -352,8 +355,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	zonefs_i_size_write(inode, data_size);
 	z->z_wpoffset = data_size;
 	zonefs_inode_account_active(inode);
-
-	return 0;
 }
 
 /*
@@ -367,23 +368,25 @@ void __zonefs_io_error(struct inode *inode, bool write)
 {
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct super_block *sb = inode->i_sb;
-	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	unsigned int noio_flag;
-	unsigned int nr_zones = 1;
-	struct zonefs_ioerr_data err = {
-		.inode = inode,
-		.write = write,
-	};
+	struct blk_zone zone;
 	int ret;
 
 	/*
-	 * The only files that have more than one zone are conventional zone
-	 * files with aggregated conventional zones, for which the inode zone
-	 * size is always larger than the device zone size.
+	 * Conventional zone have no write pointer and cannot become read-only
+	 * or offline. So simply fake a report for a single or aggregated zone
+	 * and let zonefs_handle_io_error() correct the zone inode information
+	 * according to the mount options.
 	 */
-	if (z->z_size > bdev_zone_sectors(sb->s_bdev))
-		nr_zones = z->z_size >>
-			(sbi->s_zone_sectors_shift + SECTOR_SHIFT);
+	if (!zonefs_zone_is_seq(z)) {
+		zone.start = z->z_sector;
+		zone.len = z->z_size >> SECTOR_SHIFT;
+		zone.wp = zone.start + zone.len;
+		zone.type = BLK_ZONE_TYPE_CONVENTIONAL;
+		zone.cond = BLK_ZONE_COND_NOT_WP;
+		zone.capacity = zone.len;
+		goto handle_io_error;
+	}
 
 	/*
 	 * Memory allocations in blkdev_report_zones() can trigger a memory
@@ -394,12 +397,20 @@ void __zonefs_io_error(struct inode *inode, bool write)
 	 * the GFP_NOIO context avoids both problems.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones,
-				  zonefs_io_error_cb, &err);
-	if (ret != nr_zones)
+	ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1,
+				  zonefs_io_error_cb, &zone);
+	memalloc_noio_restore(noio_flag);
+
+	if (ret != 1) {
 		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
 			   inode->i_ino, ret);
-	memalloc_noio_restore(noio_flag);
+		zonefs_warn(sb, "remounting filesystem read-only\n");
+		sb->s_flags |= SB_RDONLY;
+		return;
+	}
+
+handle_io_error:
+	zonefs_handle_io_error(inode, &zone, write);
 }
 
 static struct kmem_cache *zonefs_inode_cachep;
@@ -460,58 +471,47 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 }
 
 enum {
-	Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
-	Opt_explicit_open, Opt_err,
+	Opt_errors, Opt_explicit_open,
 };
 
-static const match_table_t tokens = {
-	{ Opt_errors_ro,	"errors=remount-ro"},
-	{ Opt_errors_zro,	"errors=zone-ro"},
-	{ Opt_errors_zol,	"errors=zone-offline"},
-	{ Opt_errors_repair,	"errors=repair"},
-	{ Opt_explicit_open,	"explicit-open" },
-	{ Opt_err,		NULL}
+struct zonefs_context {
+	unsigned long s_mount_opts;
 };
 
-static int zonefs_parse_options(struct super_block *sb, char *options)
-{
-	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
-	substring_t args[MAX_OPT_ARGS];
-	char *p;
-
-	if (!options)
-		return 0;
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
+static const struct constant_table zonefs_param_errors[] = {
+	{"remount-ro",		ZONEFS_MNTOPT_ERRORS_RO},
+	{"zone-ro",		ZONEFS_MNTOPT_ERRORS_ZRO},
+	{"zone-offline",	ZONEFS_MNTOPT_ERRORS_ZOL},
+	{"repair", 		ZONEFS_MNTOPT_ERRORS_REPAIR},
+	{}
+};
 
-		if (!*p)
-			continue;
+static const struct fs_parameter_spec zonefs_param_spec[] = {
+	fsparam_enum	("errors",		Opt_errors, zonefs_param_errors),
+	fsparam_flag	("explicit-open",	Opt_explicit_open),
+	{}
+};
 
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_errors_ro:
-			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
-			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_RO;
-			break;
-		case Opt_errors_zro:
-			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
-			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZRO;
-			break;
-		case Opt_errors_zol:
-			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
-			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZOL;
-			break;
-		case Opt_errors_repair:
-			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
-			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
-			break;
-		case Opt_explicit_open:
-			sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
-			break;
-		default:
-			return -EINVAL;
-		}
+static int zonefs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct zonefs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, zonefs_param_spec, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_errors:
+		ctx->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
+		ctx->s_mount_opts |= result.uint_32;
+		break;
+	case Opt_explicit_open:
+		ctx->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	return 0;
@@ -533,13 +533,6 @@ static int zonefs_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
-static int zonefs_remount(struct super_block *sb, int *flags, char *data)
-{
-	sync_filesystem(sb);
-
-	return zonefs_parse_options(sb, data);
-}
-
 static int zonefs_inode_setattr(struct mnt_idmap *idmap,
 				struct dentry *dentry, struct iattr *iattr)
 {
@@ -1195,7 +1188,6 @@ static const struct super_operations zonefs_sops = {
 	.alloc_inode	= zonefs_alloc_inode,
 	.free_inode	= zonefs_free_inode,
 	.statfs		= zonefs_statfs,
-	.remount_fs	= zonefs_remount,
 	.show_options	= zonefs_show_options,
 };
 
@@ -1240,9 +1232,10 @@ static void zonefs_release_zgroup_inodes(struct super_block *sb)
  * sub-directories and files according to the device zone configuration and
  * format options.
  */
-static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
+static int zonefs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct zonefs_sb_info *sbi;
+	struct zonefs_context *ctx = fc->fs_private;
 	struct inode *inode;
 	enum zonefs_ztype ztype;
 	int ret;
@@ -1279,7 +1272,7 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_uid = GLOBAL_ROOT_UID;
 	sbi->s_gid = GLOBAL_ROOT_GID;
 	sbi->s_perm = 0640;
-	sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
+	sbi->s_mount_opts = ctx->s_mount_opts;
 
 	atomic_set(&sbi->s_wro_seq_files, 0);
 	sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev);
@@ -1290,10 +1283,6 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	if (ret)
 		return ret;
 
-	ret = zonefs_parse_options(sb, data);
-	if (ret)
-		return ret;
-
 	zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
 
 	if (!sbi->s_max_wro_seq_files &&
@@ -1354,12 +1343,6 @@ cleanup:
 	return ret;
 }
 
-static struct dentry *zonefs_mount(struct file_system_type *fs_type,
-				   int flags, const char *dev_name, void *data)
-{
-	return mount_bdev(fs_type, flags, dev_name, data, zonefs_fill_super);
-}
-
 static void zonefs_kill_super(struct super_block *sb)
 {
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
@@ -1374,15 +1357,65 @@ static void zonefs_kill_super(struct super_block *sb)
 	kfree(sbi);
 }
 
+static void zonefs_free_fc(struct fs_context *fc)
+{
+	struct zonefs_context *ctx = fc->fs_private;
+
+	kfree(ctx);
+}
+
+static int zonefs_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, zonefs_fill_super);
+}
+
+static int zonefs_reconfigure(struct fs_context *fc)
+{
+	struct zonefs_context *ctx = fc->fs_private;
+	struct super_block *sb = fc->root->d_sb;
+	struct zonefs_sb_info *sbi = sb->s_fs_info;
+
+	sync_filesystem(fc->root->d_sb);
+	/* Copy new options from ctx into sbi. */
+	sbi->s_mount_opts = ctx->s_mount_opts;
+
+	return 0;
+}
+
+static const struct fs_context_operations zonefs_context_ops = {
+	.parse_param    = zonefs_parse_param,
+	.get_tree       = zonefs_get_tree,
+	.reconfigure	= zonefs_reconfigure,
+	.free           = zonefs_free_fc,
+};
+
+/*
+ * Set up the filesystem mount context.
+ */
+static int zonefs_init_fs_context(struct fs_context *fc)
+{
+	struct zonefs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct zonefs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	ctx->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
+	fc->ops = &zonefs_context_ops;
+	fc->fs_private = ctx;
+
+	return 0;
+}
+
 /*
  * File system definition and registration.
  */
 static struct file_system_type zonefs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "zonefs",
-	.mount		= zonefs_mount,
-	.kill_sb	= zonefs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV,
+	.owner			= THIS_MODULE,
+	.name			= "zonefs",
+	.kill_sb		= zonefs_kill_super,
+	.fs_flags		= FS_REQUIRES_DEV,
+	.init_fs_context	= zonefs_init_fs_context,
+	.parameters		= zonefs_param_spec,
 };
 
 static int __init zonefs_init_inodecache(void)
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 961f4d88f9ef..0c0695763bea 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -193,7 +193,6 @@ do {									\
 #ifndef smp_store_release
 #define smp_store_release(p, v)						\
 do {									\
-	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	WRITE_ONCE(*p, v);						\
 } while (0)
@@ -203,7 +202,6 @@ do {									\
 #define smp_load_acquire(p)						\
 ({									\
 	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
-	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	(typeof(*p))___p1;						\
 })
diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h
index c4c423e97f06..4453906105ca 100644
--- a/include/drm/bridge/aux-bridge.h
+++ b/include/drm/bridge/aux-bridge.h
@@ -9,6 +9,8 @@
 
 #include <drm/drm_connector.h>
 
+struct auxiliary_device;
+
 #if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE)
 int drm_aux_bridge_register(struct device *parent);
 #else
@@ -19,10 +21,23 @@ static inline int drm_aux_bridge_register(struct device *parent)
 #endif
 
 #if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np);
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev);
 struct device *drm_dp_hpd_bridge_register(struct device *parent,
 					  struct device_node *np);
 void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status);
 #else
+static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent,
+								    struct device_node *np)
+{
+	return NULL;
+}
+
+static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev)
+{
+	return 0;
+}
+
 static inline struct device *drm_dp_hpd_bridge_register(struct device *parent,
 							struct device_node *np)
 {
diff --git a/include/dt-bindings/arm/qcom,ids.h b/include/dt-bindings/arm/qcom,ids.h
index 51e0f6059410..19ac7b36f608 100644
--- a/include/dt-bindings/arm/qcom,ids.h
+++ b/include/dt-bindings/arm/qcom,ids.h
@@ -252,8 +252,11 @@
 #define QCOM_ID_IPQ9510			521
 #define QCOM_ID_QRB4210			523
 #define QCOM_ID_QRB2210			524
+#define QCOM_ID_SM8475			530
+#define QCOM_ID_SM8475P			531
 #define QCOM_ID_SA8775P			534
 #define QCOM_ID_QRU1000			539
+#define QCOM_ID_SM8475_2		540
 #define QCOM_ID_QDU1000			545
 #define QCOM_ID_SM8650			557
 #define QCOM_ID_SM4450			568
@@ -265,6 +268,8 @@
 #define QCOM_ID_IPQ5322			593
 #define QCOM_ID_IPQ5312			594
 #define QCOM_ID_IPQ5302			595
+#define QCOM_ID_QCS8550			603
+#define QCOM_ID_QCM8550			604
 #define QCOM_ID_IPQ5300			624
 
 /*
diff --git a/include/dt-bindings/clock/exynos850.h b/include/dt-bindings/clock/exynos850.h
index 3090e09c9a55..bc15108aa3c2 100644
--- a/include/dt-bindings/clock/exynos850.h
+++ b/include/dt-bindings/clock/exynos850.h
@@ -320,6 +320,8 @@
 #define CLK_GOUT_SSS_PCLK		12
 #define CLK_GOUT_GPIO_CORE_PCLK		13
 #define CLK_GOUT_SYSREG_CORE_PCLK	14
+#define CLK_GOUT_PDMA_CORE_ACLK		15
+#define CLK_GOUT_SPDMA_CORE_ACLK	16
 
 /* CMU_DPU */
 #define CLK_MOUT_DPU_USER		1
diff --git a/include/dt-bindings/clock/google,gs101.h b/include/dt-bindings/clock/google,gs101.h
index 21adec22387c..3dac3577788a 100644
--- a/include/dt-bindings/clock/google,gs101.h
+++ b/include/dt-bindings/clock/google,gs101.h
@@ -389,4 +389,133 @@
 #define CLK_GOUT_MISC_WDT_CLUSTER1_PCLK			73
 #define CLK_GOUT_MISC_XIU_D_MISC_ACLK			74
 
+/* CMU_PERIC0 */
+#define CLK_MOUT_PERIC0_BUS_USER			1
+#define CLK_MOUT_PERIC0_I3C_USER			2
+#define CLK_MOUT_PERIC0_USI0_UART_USER			3
+#define CLK_MOUT_PERIC0_USI14_USI_USER			4
+#define CLK_MOUT_PERIC0_USI1_USI_USER			5
+#define CLK_MOUT_PERIC0_USI2_USI_USER			6
+#define CLK_MOUT_PERIC0_USI3_USI_USER			7
+#define CLK_MOUT_PERIC0_USI4_USI_USER			8
+#define CLK_MOUT_PERIC0_USI5_USI_USER			9
+#define CLK_MOUT_PERIC0_USI6_USI_USER			10
+#define CLK_MOUT_PERIC0_USI7_USI_USER			11
+#define CLK_MOUT_PERIC0_USI8_USI_USER			12
+#define CLK_DOUT_PERIC0_I3C				13
+#define CLK_DOUT_PERIC0_USI0_UART			14
+#define CLK_DOUT_PERIC0_USI14_USI			15
+#define CLK_DOUT_PERIC0_USI1_USI			16
+#define CLK_DOUT_PERIC0_USI2_USI			17
+#define CLK_DOUT_PERIC0_USI3_USI			18
+#define CLK_DOUT_PERIC0_USI4_USI			19
+#define CLK_DOUT_PERIC0_USI5_USI			20
+#define CLK_DOUT_PERIC0_USI6_USI			21
+#define CLK_DOUT_PERIC0_USI7_USI			22
+#define CLK_DOUT_PERIC0_USI8_USI			23
+#define CLK_GOUT_PERIC0_IP				24
+#define CLK_GOUT_PERIC0_PERIC0_CMU_PERIC0_PCLK		25
+#define CLK_GOUT_PERIC0_CLK_PERIC0_OSCCLK_CLK		26
+#define CLK_GOUT_PERIC0_D_TZPC_PERIC0_PCLK		27
+#define CLK_GOUT_PERIC0_GPC_PERIC0_PCLK			28
+#define CLK_GOUT_PERIC0_GPIO_PERIC0_PCLK		29
+#define CLK_GOUT_PERIC0_LHM_AXI_P_PERIC0_I_CLK		30
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_0		31
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_1		32
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_10		33
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_11		34
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_12		35
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_13		36
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_14		37
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_15		38
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_2		39
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_3		40
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_4		41
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_5		42
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_6		43
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_7		44
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_8		45
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_IPCLK_9		46
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_0		47
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_1		48
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_10		49
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_11		50
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_12		51
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_13		52
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_14		53
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_15		54
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_2		55
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_3		56
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_4		57
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_5		58
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_6		59
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_7		60
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_8		61
+#define CLK_GOUT_PERIC0_PERIC0_TOP0_PCLK_9		62
+#define CLK_GOUT_PERIC0_PERIC0_TOP1_IPCLK_0		63
+#define CLK_GOUT_PERIC0_PERIC0_TOP1_IPCLK_2		64
+#define CLK_GOUT_PERIC0_PERIC0_TOP1_PCLK_0		65
+#define CLK_GOUT_PERIC0_PERIC0_TOP1_PCLK_2		66
+#define CLK_GOUT_PERIC0_CLK_PERIC0_BUSP_CLK		67
+#define CLK_GOUT_PERIC0_CLK_PERIC0_I3C_CLK		68
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI0_UART_CLK	69
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI14_USI_CLK	70
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI1_USI_CLK		71
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI2_USI_CLK		72
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI3_USI_CLK		73
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI4_USI_CLK		74
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI5_USI_CLK		75
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI6_USI_CLK		76
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI7_USI_CLK		77
+#define CLK_GOUT_PERIC0_CLK_PERIC0_USI8_USI_CLK		78
+#define CLK_GOUT_PERIC0_SYSREG_PERIC0_PCLK		79
+
+/* CMU_PERIC1 */
+#define CLK_MOUT_PERIC1_BUS_USER			1
+#define CLK_MOUT_PERIC1_I3C_USER			2
+#define CLK_MOUT_PERIC1_USI0_USI_USER			3
+#define CLK_MOUT_PERIC1_USI10_USI_USER			4
+#define CLK_MOUT_PERIC1_USI11_USI_USER			5
+#define CLK_MOUT_PERIC1_USI12_USI_USER			6
+#define CLK_MOUT_PERIC1_USI13_USI_USER			7
+#define CLK_MOUT_PERIC1_USI9_USI_USER			8
+#define CLK_DOUT_PERIC1_I3C				9
+#define CLK_DOUT_PERIC1_USI0_USI			10
+#define CLK_DOUT_PERIC1_USI10_USI			11
+#define CLK_DOUT_PERIC1_USI11_USI			12
+#define CLK_DOUT_PERIC1_USI12_USI			13
+#define CLK_DOUT_PERIC1_USI13_USI			14
+#define CLK_DOUT_PERIC1_USI9_USI			15
+#define CLK_GOUT_PERIC1_IP				16
+#define CLK_GOUT_PERIC1_PCLK				17
+#define CLK_GOUT_PERIC1_CLK_PERIC1_I3C_CLK		18
+#define CLK_GOUT_PERIC1_CLK_PERIC1_OSCCLK_CLK		19
+#define CLK_GOUT_PERIC1_D_TZPC_PERIC1_PCLK		20
+#define CLK_GOUT_PERIC1_GPC_PERIC1_PCLK			21
+#define CLK_GOUT_PERIC1_GPIO_PERIC1_PCLK		22
+#define CLK_GOUT_PERIC1_LHM_AXI_P_PERIC1_I_CLK		23
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_1		24
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_2		25
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_3		26
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_4		27
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_5		28
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_6		29
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_IPCLK_8		30
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_1		31
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_15		32
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_2		33
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_3		34
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_4		35
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_5		36
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_6		37
+#define CLK_GOUT_PERIC1_PERIC1_TOP0_PCLK_8		38
+#define CLK_GOUT_PERIC1_CLK_PERIC1_BUSP_CLK		39
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI0_USI_CLK		40
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI10_USI_CLK	41
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI11_USI_CLK	42
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI12_USI_CLK	43
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI13_USI_CLK	44
+#define CLK_GOUT_PERIC1_CLK_PERIC1_USI9_USI_CLK		45
+#define CLK_GOUT_PERIC1_SYSREG_PERIC1_PCLK		46
+
 #endif /* _DT_BINDINGS_CLOCK_GOOGLE_GS101_H */
diff --git a/include/dt-bindings/clock/qcom,gcc-msm8953.h b/include/dt-bindings/clock/qcom,gcc-msm8953.h
index 783162da6148..13b4a62877e5 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8953.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8953.h
@@ -218,6 +218,10 @@
 #define GCC_USB3PHY_PHY_BCR			3
 #define GCC_USB3_PHY_BCR			4
 #define GCC_USB_30_BCR				5
+#define GCC_MDSS_BCR				6
+#define GCC_CRYPTO_BCR				7
+#define GCC_SDCC1_BCR				8
+#define GCC_SDCC2_BCR				9
 
 /* GDSCs */
 #define CPP_GDSC				0
diff --git a/include/dt-bindings/clock/qcom,gcc-sc8180x.h b/include/dt-bindings/clock/qcom,gcc-sc8180x.h
index e893415ae13d..90c6e021a035 100644
--- a/include/dt-bindings/clock/qcom,gcc-sc8180x.h
+++ b/include/dt-bindings/clock/qcom,gcc-sc8180x.h
@@ -246,6 +246,8 @@
 #define GCC_PCIE_3_CLKREF_CLK					236
 #define GCC_USB3_PRIM_CLKREF_CLK				237
 #define GCC_USB3_SEC_CLKREF_CLK					238
+#define GCC_UFS_MEM_CLKREF_EN					239
+#define GCC_UFS_CARD_CLKREF_EN					240
 
 #define GCC_EMAC_BCR						0
 #define GCC_GPU_BCR						1
diff --git a/include/dt-bindings/clock/qcom,x1e80100-camcc.h b/include/dt-bindings/clock/qcom,x1e80100-camcc.h
new file mode 100644
index 000000000000..d72fdfb06a7c
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-camcc.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_CAM_CC_X1E80100_H
+#define _DT_BINDINGS_CLK_QCOM_CAM_CC_X1E80100_H
+
+/* CAM_CC clocks */
+#define CAM_CC_BPS_AHB_CLK					0
+#define CAM_CC_BPS_CLK						1
+#define CAM_CC_BPS_CLK_SRC					2
+#define CAM_CC_BPS_FAST_AHB_CLK					3
+#define CAM_CC_CAMNOC_AXI_NRT_CLK				4
+#define CAM_CC_CAMNOC_AXI_RT_CLK				5
+#define CAM_CC_CAMNOC_AXI_RT_CLK_SRC				6
+#define CAM_CC_CAMNOC_DCD_XO_CLK				7
+#define CAM_CC_CAMNOC_XO_CLK					8
+#define CAM_CC_CCI_0_CLK					9
+#define CAM_CC_CCI_0_CLK_SRC					10
+#define CAM_CC_CCI_1_CLK					11
+#define CAM_CC_CCI_1_CLK_SRC					12
+#define CAM_CC_CORE_AHB_CLK					13
+#define CAM_CC_CPAS_AHB_CLK					14
+#define CAM_CC_CPAS_BPS_CLK					15
+#define CAM_CC_CPAS_FAST_AHB_CLK				16
+#define CAM_CC_CPAS_IFE_0_CLK					17
+#define CAM_CC_CPAS_IFE_1_CLK					18
+#define CAM_CC_CPAS_IFE_LITE_CLK				19
+#define CAM_CC_CPAS_IPE_NPS_CLK					20
+#define CAM_CC_CPAS_SFE_0_CLK					21
+#define CAM_CC_CPHY_RX_CLK_SRC					22
+#define CAM_CC_CSI0PHYTIMER_CLK					23
+#define CAM_CC_CSI0PHYTIMER_CLK_SRC				24
+#define CAM_CC_CSI1PHYTIMER_CLK					25
+#define CAM_CC_CSI1PHYTIMER_CLK_SRC				26
+#define CAM_CC_CSI2PHYTIMER_CLK					27
+#define CAM_CC_CSI2PHYTIMER_CLK_SRC				28
+#define CAM_CC_CSI3PHYTIMER_CLK					29
+#define CAM_CC_CSI3PHYTIMER_CLK_SRC				30
+#define CAM_CC_CSI4PHYTIMER_CLK					31
+#define CAM_CC_CSI4PHYTIMER_CLK_SRC				32
+#define CAM_CC_CSI5PHYTIMER_CLK					33
+#define CAM_CC_CSI5PHYTIMER_CLK_SRC				34
+#define CAM_CC_CSID_CLK						35
+#define CAM_CC_CSID_CLK_SRC					36
+#define CAM_CC_CSID_CSIPHY_RX_CLK				37
+#define CAM_CC_CSIPHY0_CLK					38
+#define CAM_CC_CSIPHY1_CLK					39
+#define CAM_CC_CSIPHY2_CLK					40
+#define CAM_CC_CSIPHY3_CLK					41
+#define CAM_CC_CSIPHY4_CLK					42
+#define CAM_CC_CSIPHY5_CLK					43
+#define CAM_CC_FAST_AHB_CLK_SRC					44
+#define CAM_CC_GDSC_CLK						45
+#define CAM_CC_ICP_AHB_CLK					46
+#define CAM_CC_ICP_CLK						47
+#define CAM_CC_ICP_CLK_SRC					48
+#define CAM_CC_IFE_0_CLK					49
+#define CAM_CC_IFE_0_CLK_SRC					50
+#define CAM_CC_IFE_0_DSP_CLK					51
+#define CAM_CC_IFE_0_FAST_AHB_CLK				52
+#define CAM_CC_IFE_1_CLK					53
+#define CAM_CC_IFE_1_CLK_SRC					54
+#define CAM_CC_IFE_1_DSP_CLK					55
+#define CAM_CC_IFE_1_FAST_AHB_CLK				56
+#define CAM_CC_IFE_LITE_AHB_CLK					57
+#define CAM_CC_IFE_LITE_CLK					58
+#define CAM_CC_IFE_LITE_CLK_SRC					59
+#define CAM_CC_IFE_LITE_CPHY_RX_CLK				60
+#define CAM_CC_IFE_LITE_CSID_CLK				61
+#define CAM_CC_IFE_LITE_CSID_CLK_SRC				62
+#define CAM_CC_IPE_NPS_AHB_CLK					63
+#define CAM_CC_IPE_NPS_CLK					64
+#define CAM_CC_IPE_NPS_CLK_SRC					65
+#define CAM_CC_IPE_NPS_FAST_AHB_CLK				66
+#define CAM_CC_IPE_PPS_CLK					67
+#define CAM_CC_IPE_PPS_FAST_AHB_CLK				68
+#define CAM_CC_JPEG_CLK						69
+#define CAM_CC_JPEG_CLK_SRC					70
+#define CAM_CC_MCLK0_CLK					71
+#define CAM_CC_MCLK0_CLK_SRC					72
+#define CAM_CC_MCLK1_CLK					73
+#define CAM_CC_MCLK1_CLK_SRC					74
+#define CAM_CC_MCLK2_CLK					75
+#define CAM_CC_MCLK2_CLK_SRC					76
+#define CAM_CC_MCLK3_CLK					77
+#define CAM_CC_MCLK3_CLK_SRC					78
+#define CAM_CC_MCLK4_CLK					79
+#define CAM_CC_MCLK4_CLK_SRC					80
+#define CAM_CC_MCLK5_CLK					81
+#define CAM_CC_MCLK5_CLK_SRC					82
+#define CAM_CC_MCLK6_CLK					83
+#define CAM_CC_MCLK6_CLK_SRC					84
+#define CAM_CC_MCLK7_CLK					85
+#define CAM_CC_MCLK7_CLK_SRC					86
+#define CAM_CC_PLL0						87
+#define CAM_CC_PLL0_OUT_EVEN					88
+#define CAM_CC_PLL0_OUT_ODD					89
+#define CAM_CC_PLL1						90
+#define CAM_CC_PLL1_OUT_EVEN					91
+#define CAM_CC_PLL2						92
+#define CAM_CC_PLL3						93
+#define CAM_CC_PLL3_OUT_EVEN					94
+#define CAM_CC_PLL4						95
+#define CAM_CC_PLL4_OUT_EVEN					96
+#define CAM_CC_PLL6						97
+#define CAM_CC_PLL6_OUT_EVEN					98
+#define CAM_CC_PLL8						99
+#define CAM_CC_PLL8_OUT_EVEN					100
+#define CAM_CC_SFE_0_CLK					101
+#define CAM_CC_SFE_0_CLK_SRC					102
+#define CAM_CC_SFE_0_FAST_AHB_CLK				103
+#define CAM_CC_SLEEP_CLK					104
+#define CAM_CC_SLEEP_CLK_SRC					105
+#define CAM_CC_SLOW_AHB_CLK_SRC					106
+#define CAM_CC_XO_CLK_SRC					107
+
+/* CAM_CC power domains */
+#define CAM_CC_BPS_GDSC						0
+#define CAM_CC_IFE_0_GDSC					1
+#define CAM_CC_IFE_1_GDSC					2
+#define CAM_CC_IPE_0_GDSC					3
+#define CAM_CC_SFE_0_GDSC					4
+#define CAM_CC_TITAN_TOP_GDSC					5
+
+/* CAM_CC resets */
+#define CAM_CC_BPS_BCR						0
+#define CAM_CC_ICP_BCR						1
+#define CAM_CC_IFE_0_BCR					2
+#define CAM_CC_IFE_1_BCR					3
+#define CAM_CC_IPE_0_BCR					4
+#define CAM_CC_SFE_0_BCR					5
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,x1e80100-dispcc.h b/include/dt-bindings/clock/qcom,x1e80100-dispcc.h
new file mode 100644
index 000000000000..d4a83e4fd0d1
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-dispcc.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_X1E80100_DISP_CC_H
+#define _DT_BINDINGS_CLK_QCOM_X1E80100_DISP_CC_H
+
+/* DISP_CC clocks */
+#define DISP_CC_MDSS_ACCU_CLK					0
+#define DISP_CC_MDSS_AHB1_CLK					1
+#define DISP_CC_MDSS_AHB_CLK					2
+#define DISP_CC_MDSS_AHB_CLK_SRC				3
+#define DISP_CC_MDSS_BYTE0_CLK					4
+#define DISP_CC_MDSS_BYTE0_CLK_SRC				5
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC				6
+#define DISP_CC_MDSS_BYTE0_INTF_CLK				7
+#define DISP_CC_MDSS_BYTE1_CLK					8
+#define DISP_CC_MDSS_BYTE1_CLK_SRC				9
+#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC				10
+#define DISP_CC_MDSS_BYTE1_INTF_CLK				11
+#define DISP_CC_MDSS_DPTX0_AUX_CLK				12
+#define DISP_CC_MDSS_DPTX0_AUX_CLK_SRC				13
+#define DISP_CC_MDSS_DPTX0_LINK_CLK				14
+#define DISP_CC_MDSS_DPTX0_LINK_CLK_SRC				15
+#define DISP_CC_MDSS_DPTX0_LINK_DIV_CLK_SRC			16
+#define DISP_CC_MDSS_DPTX0_LINK_INTF_CLK			17
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK				18
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC			19
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK				20
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC			21
+#define DISP_CC_MDSS_DPTX0_USB_ROUTER_LINK_INTF_CLK		22
+#define DISP_CC_MDSS_DPTX1_AUX_CLK				23
+#define DISP_CC_MDSS_DPTX1_AUX_CLK_SRC				24
+#define DISP_CC_MDSS_DPTX1_LINK_CLK				25
+#define DISP_CC_MDSS_DPTX1_LINK_CLK_SRC				26
+#define DISP_CC_MDSS_DPTX1_LINK_DIV_CLK_SRC			27
+#define DISP_CC_MDSS_DPTX1_LINK_INTF_CLK			28
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK				29
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC			30
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK				31
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK_SRC			32
+#define DISP_CC_MDSS_DPTX1_USB_ROUTER_LINK_INTF_CLK		33
+#define DISP_CC_MDSS_DPTX2_AUX_CLK				34
+#define DISP_CC_MDSS_DPTX2_AUX_CLK_SRC				35
+#define DISP_CC_MDSS_DPTX2_LINK_CLK				36
+#define DISP_CC_MDSS_DPTX2_LINK_CLK_SRC				37
+#define DISP_CC_MDSS_DPTX2_LINK_DIV_CLK_SRC			38
+#define DISP_CC_MDSS_DPTX2_LINK_INTF_CLK			39
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK				40
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC			41
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK				42
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK_SRC			43
+#define DISP_CC_MDSS_DPTX2_USB_ROUTER_LINK_INTF_CLK		44
+#define DISP_CC_MDSS_DPTX3_AUX_CLK				45
+#define DISP_CC_MDSS_DPTX3_AUX_CLK_SRC				46
+#define DISP_CC_MDSS_DPTX3_LINK_CLK				47
+#define DISP_CC_MDSS_DPTX3_LINK_CLK_SRC				48
+#define DISP_CC_MDSS_DPTX3_LINK_DIV_CLK_SRC			49
+#define DISP_CC_MDSS_DPTX3_LINK_INTF_CLK			50
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK				51
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC			52
+#define DISP_CC_MDSS_ESC0_CLK					53
+#define DISP_CC_MDSS_ESC0_CLK_SRC				54
+#define DISP_CC_MDSS_ESC1_CLK					55
+#define DISP_CC_MDSS_ESC1_CLK_SRC				56
+#define DISP_CC_MDSS_MDP1_CLK					57
+#define DISP_CC_MDSS_MDP_CLK					58
+#define DISP_CC_MDSS_MDP_CLK_SRC				59
+#define DISP_CC_MDSS_MDP_LUT1_CLK				60
+#define DISP_CC_MDSS_MDP_LUT_CLK				61
+#define DISP_CC_MDSS_NON_GDSC_AHB_CLK				62
+#define DISP_CC_MDSS_PCLK0_CLK					63
+#define DISP_CC_MDSS_PCLK0_CLK_SRC				64
+#define DISP_CC_MDSS_PCLK1_CLK					65
+#define DISP_CC_MDSS_PCLK1_CLK_SRC				66
+#define DISP_CC_MDSS_RSCC_AHB_CLK				67
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK				68
+#define DISP_CC_MDSS_VSYNC1_CLK					69
+#define DISP_CC_MDSS_VSYNC_CLK					70
+#define DISP_CC_MDSS_VSYNC_CLK_SRC				71
+#define DISP_CC_PLL0						72
+#define DISP_CC_PLL1						73
+#define DISP_CC_SLEEP_CLK					74
+#define DISP_CC_SLEEP_CLK_SRC					75
+#define DISP_CC_XO_CLK						76
+#define DISP_CC_XO_CLK_SRC					77
+
+/* DISP_CC resets */
+#define DISP_CC_MDSS_CORE_BCR					0
+#define DISP_CC_MDSS_CORE_INT2_BCR				1
+#define DISP_CC_MDSS_RSCC_BCR					2
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC						0
+#define MDSS_INT2_GDSC						1
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,x1e80100-gpucc.h b/include/dt-bindings/clock/qcom,x1e80100-gpucc.h
new file mode 100644
index 000000000000..61a3a8f3ac43
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-gpucc.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_X1E80100_GPU_CC_H
+#define _DT_BINDINGS_CLK_QCOM_X1E80100_GPU_CC_H
+
+/* GPU_CC clocks */
+#define GPU_CC_AHB_CLK						0
+#define GPU_CC_CB_CLK						1
+#define GPU_CC_CRC_AHB_CLK					2
+#define GPU_CC_CX_FF_CLK					3
+#define GPU_CC_CX_GMU_CLK					4
+#define GPU_CC_CXO_AON_CLK					5
+#define GPU_CC_CXO_CLK						6
+#define GPU_CC_DEMET_CLK					7
+#define GPU_CC_DEMET_DIV_CLK_SRC				8
+#define GPU_CC_FF_CLK_SRC					9
+#define GPU_CC_FREQ_MEASURE_CLK					10
+#define GPU_CC_GMU_CLK_SRC					11
+#define GPU_CC_GX_GMU_CLK					12
+#define GPU_CC_GX_VSENSE_CLK					13
+#define GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK				14
+#define GPU_CC_HUB_AON_CLK					15
+#define GPU_CC_HUB_CLK_SRC					16
+#define GPU_CC_HUB_CX_INT_CLK					17
+#define GPU_CC_MEMNOC_GFX_CLK					18
+#define GPU_CC_MND1X_0_GFX3D_CLK				19
+#define GPU_CC_MND1X_1_GFX3D_CLK				20
+#define GPU_CC_PLL0						21
+#define GPU_CC_PLL1						22
+#define GPU_CC_SLEEP_CLK					23
+#define GPU_CC_XO_CLK_SRC					24
+#define GPU_CC_XO_DIV_CLK_SRC					25
+
+/* GDSCs */
+#define GPU_CX_GDSC						0
+#define GPU_GX_GDSC						1
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,x1e80100-tcsr.h b/include/dt-bindings/clock/qcom,x1e80100-tcsr.h
new file mode 100644
index 000000000000..bae2c4654ee2
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-tcsr.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_X1E80100_TCSR_CC_H
+#define _DT_BINDINGS_CLK_QCOM_X1E80100_TCSR_CC_H
+
+/* TCSR CC clocks */
+#define TCSR_PCIE_2L_4_CLKREF_EN				0
+#define TCSR_PCIE_2L_5_CLKREF_EN				1
+#define TCSR_PCIE_8L_CLKREF_EN					2
+#define TCSR_USB3_MP0_CLKREF_EN					3
+#define TCSR_USB3_MP1_CLKREF_EN					4
+#define TCSR_USB2_1_CLKREF_EN					5
+#define TCSR_UFS_PHY_CLKREF_EN					6
+#define TCSR_USB4_1_CLKREF_EN					7
+#define TCSR_USB4_2_CLKREF_EN					8
+#define TCSR_USB2_2_CLKREF_EN					9
+#define TCSR_PCIE_4L_CLKREF_EN					10
+#define TCSR_EDP_CLKREF_EN					11
+
+#endif
diff --git a/include/dt-bindings/clock/renesas,r8a779h0-cpg-mssr.h b/include/dt-bindings/clock/renesas,r8a779h0-cpg-mssr.h
new file mode 100644
index 000000000000..7ab6cfbaf901
--- /dev/null
+++ b/include/dt-bindings/clock/renesas,r8a779h0-cpg-mssr.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+#ifndef __DT_BINDINGS_CLOCK_RENESAS_R8A779H0_CPG_MSSR_H__
+#define __DT_BINDINGS_CLOCK_RENESAS_R8A779H0_CPG_MSSR_H__
+
+#include <dt-bindings/clock/renesas-cpg-mssr.h>
+
+/* r8a779h0 CPG Core Clocks */
+
+#define R8A779H0_CLK_ZX			0
+#define R8A779H0_CLK_ZD			1
+#define R8A779H0_CLK_ZS			2
+#define R8A779H0_CLK_ZT			3
+#define R8A779H0_CLK_ZTR		4
+#define R8A779H0_CLK_S0D2		5
+#define R8A779H0_CLK_S0D3		6
+#define R8A779H0_CLK_S0D4		7
+#define R8A779H0_CLK_S0D1_VIO		8
+#define R8A779H0_CLK_S0D2_VIO		9
+#define R8A779H0_CLK_S0D4_VIO		10
+#define R8A779H0_CLK_S0D8_VIO		11
+#define R8A779H0_CLK_VIOBUSD1		12
+#define R8A779H0_CLK_VIOBUSD2		13
+#define R8A779H0_CLK_S0D1_VC		14
+#define R8A779H0_CLK_S0D2_VC		15
+#define R8A779H0_CLK_S0D4_VC		16
+#define R8A779H0_CLK_VCBUSD1		17
+#define R8A779H0_CLK_VCBUSD2		18
+#define R8A779H0_CLK_S0D2_MM		19
+#define R8A779H0_CLK_S0D4_MM		20
+#define R8A779H0_CLK_S0D2_U3DG		21
+#define R8A779H0_CLK_S0D4_U3DG		22
+#define R8A779H0_CLK_S0D2_RT		23
+#define R8A779H0_CLK_S0D3_RT		24
+#define R8A779H0_CLK_S0D4_RT		25
+#define R8A779H0_CLK_S0D6_RT		26
+#define R8A779H0_CLK_S0D2_PER		27
+#define R8A779H0_CLK_S0D3_PER		28
+#define R8A779H0_CLK_S0D4_PER		29
+#define R8A779H0_CLK_S0D6_PER		30
+#define R8A779H0_CLK_S0D12_PER		31
+#define R8A779H0_CLK_S0D24_PER		32
+#define R8A779H0_CLK_S0D1_HSC		33
+#define R8A779H0_CLK_S0D2_HSC		34
+#define R8A779H0_CLK_S0D4_HSC		35
+#define R8A779H0_CLK_S0D8_HSC		36
+#define R8A779H0_CLK_SVD1_IR		37
+#define R8A779H0_CLK_SVD2_IR		38
+#define R8A779H0_CLK_IMPAD1		39
+#define R8A779H0_CLK_IMPAD4		40
+#define R8A779H0_CLK_IMPB		41
+#define R8A779H0_CLK_SVD1_VIP		42
+#define R8A779H0_CLK_SVD2_VIP		43
+#define R8A779H0_CLK_CL			44
+#define R8A779H0_CLK_CL16M		45
+#define R8A779H0_CLK_CL16M_MM		46
+#define R8A779H0_CLK_CL16M_RT		47
+#define R8A779H0_CLK_CL16M_PER		48
+#define R8A779H0_CLK_CL16M_HSC		49
+#define R8A779H0_CLK_ZC0		50
+#define R8A779H0_CLK_ZC1		51
+#define R8A779H0_CLK_ZC2		52
+#define R8A779H0_CLK_ZC3		53
+#define R8A779H0_CLK_ZB3		54
+#define R8A779H0_CLK_ZB3D2		55
+#define R8A779H0_CLK_ZB3D4		56
+#define R8A779H0_CLK_ZG			57
+#define R8A779H0_CLK_SD0H		58
+#define R8A779H0_CLK_SD0		59
+#define R8A779H0_CLK_RPC		60
+#define R8A779H0_CLK_RPCD2		61
+#define R8A779H0_CLK_MSO		62
+#define R8A779H0_CLK_CANFD		63
+#define R8A779H0_CLK_CSI		64
+#define R8A779H0_CLK_FRAY		65
+#define R8A779H0_CLK_IPC		66
+#define R8A779H0_CLK_SASYNCRT		67
+#define R8A779H0_CLK_SASYNCPERD1	68
+#define R8A779H0_CLK_SASYNCPERD2	69
+#define R8A779H0_CLK_SASYNCPERD4	70
+#define R8A779H0_CLK_DSIEXT		71
+#define R8A779H0_CLK_DSIREF		72
+#define R8A779H0_CLK_ADGH		73
+#define R8A779H0_CLK_OSC		74
+#define R8A779H0_CLK_ZR0		75
+#define R8A779H0_CLK_ZR1		76
+#define R8A779H0_CLK_ZR2		77
+#define R8A779H0_CLK_RGMII		78
+#define R8A779H0_CLK_CPEX		79
+#define R8A779H0_CLK_CP			80
+#define R8A779H0_CLK_CBFUSA		81
+#define R8A779H0_CLK_R			82
+
+#endif /* __DT_BINDINGS_CLOCK_RENESAS_R8A779H0_CPG_MSSR_H__ */
diff --git a/include/dt-bindings/clock/rockchip,rk3588-cru.h b/include/dt-bindings/clock/rockchip,rk3588-cru.h
index 5790b1391201..0c7d3ca2d5bc 100644
--- a/include/dt-bindings/clock/rockchip,rk3588-cru.h
+++ b/include/dt-bindings/clock/rockchip,rk3588-cru.h
@@ -733,8 +733,7 @@
 #define ACLK_AV1_PRE			718
 #define PCLK_AV1_PRE			719
 #define HCLK_SDIO_PRE			720
-
-#define CLK_NR_CLKS			(HCLK_SDIO_PRE + 1)
+#define PCLK_VO1GRF			721
 
 /* scmi-clocks indices */
 
diff --git a/include/dt-bindings/mfd/stm32f7-rcc.h b/include/dt-bindings/mfd/stm32f7-rcc.h
index 8d73a9c51e2b..a4e4f9271395 100644
--- a/include/dt-bindings/mfd/stm32f7-rcc.h
+++ b/include/dt-bindings/mfd/stm32f7-rcc.h
@@ -108,6 +108,7 @@
 #define STM32F7_RCC_APB2_SAI1		22
 #define STM32F7_RCC_APB2_SAI2		23
 #define STM32F7_RCC_APB2_LTDC		26
+#define STM32F7_RCC_APB2_DSI		27
 
 #define STM32F7_APB2_RESET(bit)	(STM32F7_RCC_APB2_##bit + (0x24 * 8))
 #define STM32F7_APB2_CLOCK(bit)	(STM32F7_RCC_APB2_##bit + 0xA0)
diff --git a/include/dt-bindings/power/renesas,r8a779h0-sysc.h b/include/dt-bindings/power/renesas,r8a779h0-sysc.h
new file mode 100644
index 000000000000..f27976f523e8
--- /dev/null
+++ b/include/dt-bindings/power/renesas,r8a779h0-sysc.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+#ifndef __DT_BINDINGS_POWER_RENESAS_R8A779H0_SYSC_H__
+#define __DT_BINDINGS_POWER_RENESAS_R8A779H0_SYSC_H__
+
+/*
+ * These power domain indices match the Power Domain Register Numbers (PDR)
+ */
+
+#define R8A779H0_PD_A1E0D0C0		0
+#define R8A779H0_PD_A1E0D0C1		1
+#define R8A779H0_PD_A1E0D0C2		2
+#define R8A779H0_PD_A1E0D0C3		3
+#define R8A779H0_PD_A2E0D0		16
+#define R8A779H0_PD_A3CR0		21
+#define R8A779H0_PD_A3CR1		22
+#define R8A779H0_PD_A3CR2		23
+#define R8A779H0_PD_A33DGA		24
+#define R8A779H0_PD_A23DGB		25
+#define R8A779H0_PD_C4			31
+#define R8A779H0_PD_A1DSP0		33
+#define R8A779H0_PD_A2IMP01		34
+#define R8A779H0_PD_A2PSC		35
+#define R8A779H0_PD_A2CV0		36
+#define R8A779H0_PD_A2CV1		37
+#define R8A779H0_PD_A3IMR0		38
+#define R8A779H0_PD_A3IMR1		39
+#define R8A779H0_PD_A3VC		40
+#define R8A779H0_PD_A2CN0		42
+#define R8A779H0_PD_A1CN0		44
+#define R8A779H0_PD_A1DSP1		45
+#define R8A779H0_PD_A2DMA		47
+#define R8A779H0_PD_A2CV2		48
+#define R8A779H0_PD_A2CV3		49
+#define R8A779H0_PD_A3IMR2		50
+#define R8A779H0_PD_A3IMR3		51
+#define R8A779H0_PD_A3PCI		52
+#define R8A779H0_PD_A2PCIPHY		53
+#define R8A779H0_PD_A3VIP0		56
+#define R8A779H0_PD_A3VIP2		58
+#define R8A779H0_PD_A3ISP0		60
+#define R8A779H0_PD_A3DUL		62
+
+/* Always-on power area */
+#define R8A779H0_PD_ALWAYS_ON		64
+
+#endif /* __DT_BINDINGS_POWER_RENESAS_R8A779H0_SYSC_H__ */
diff --git a/include/dt-bindings/reset/qcom,x1e80100-gpucc.h b/include/dt-bindings/reset/qcom,x1e80100-gpucc.h
new file mode 100644
index 000000000000..32b43e71a16f
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,x1e80100-gpucc.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_RESET_QCOM_X1E80100_GPU_CC_H
+#define _DT_BINDINGS_RESET_QCOM_X1E80100_GPU_CC_H
+
+#define GPUCC_GPU_CC_ACD_BCR					0
+#define GPUCC_GPU_CC_CB_BCR					1
+#define GPUCC_GPU_CC_CX_BCR					2
+#define GPUCC_GPU_CC_FAST_HUB_BCR				3
+#define GPUCC_GPU_CC_FF_BCR					4
+#define GPUCC_GPU_CC_GFX3D_AON_BCR				5
+#define GPUCC_GPU_CC_GMU_BCR					6
+#define GPUCC_GPU_CC_GX_BCR					7
+#define GPUCC_GPU_CC_XO_BCR					8
+
+#endif
diff --git a/include/kunit/test.h b/include/kunit/test.h
index fcb4a4940ace..61637ef32302 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -579,12 +579,12 @@ void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt,
 
 void __noreturn __kunit_abort(struct kunit *test);
 
-void __kunit_do_failed_assertion(struct kunit *test,
-			       const struct kunit_loc *loc,
-			       enum kunit_assert_type type,
-			       const struct kunit_assert *assert,
-			       assert_format_t assert_format,
-			       const char *fmt, ...);
+void __printf(6, 7) __kunit_do_failed_assertion(struct kunit *test,
+						const struct kunit_loc *loc,
+						enum kunit_assert_type type,
+						const struct kunit_assert *assert,
+						assert_format_t assert_format,
+						const char *fmt, ...);
 
 #define _KUNIT_FAILED(test, assert_type, assert_class, assert_format, INITIALIZER, fmt, ...) do { \
 	static const struct kunit_loc __loc = KUNIT_CURRENT_LOC;	       \
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index dc7ed2f46886..2b90c48a6a87 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -85,8 +85,10 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn,
 		u64 *value);
 struct amd_iommu *get_amd_iommu(unsigned int idx);
 
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-int amd_iommu_snp_enable(void);
+#ifdef CONFIG_KVM_AMD_SEV
+int amd_iommu_snp_disable(void);
+#else
+static inline int amd_iommu_snp_disable(void) { return 0; }
 #endif
 
 #endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 3d0fde57ba90..c906f666ff5d 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,7 +209,7 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
-extern struct bus_type ffa_bus_type;
+extern const struct bus_type ffa_bus_type;
 
 /* FFA transport related */
 struct ffa_partition_info {
diff --git a/include/linux/async.h b/include/linux/async.h
index 33c9ff4afb49..19b778d08600 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -120,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie);
 extern void async_synchronize_cookie_domain(async_cookie_t cookie,
 					    struct async_domain *domain);
 extern bool current_is_async(void);
+extern void async_init(void);
 #endif
diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h
index 5e95faa959c4..956bcba5dbf2 100644
--- a/include/linux/atomic/atomic-arch-fallback.h
+++ b/include/linux/atomic/atomic-arch-fallback.h
@@ -2005,6 +2005,7 @@ raw_atomic_xchg_relaxed(atomic_t *v, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere.
  *
@@ -2033,6 +2034,7 @@ raw_atomic_cmpxchg(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere.
  *
@@ -2061,6 +2063,7 @@ raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere.
  *
@@ -2088,6 +2091,7 @@ raw_atomic_cmpxchg_release(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere.
  *
@@ -2112,7 +2116,8 @@ raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere.
  *
@@ -2145,7 +2150,8 @@ raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere.
  *
@@ -2178,7 +2184,8 @@ raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere.
  *
@@ -2210,7 +2217,8 @@ raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere.
  *
@@ -2403,6 +2411,7 @@ raw_atomic_add_negative_relaxed(int i, atomic_t *v)
  * @u: int value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere.
  *
@@ -2432,6 +2441,7 @@ raw_atomic_fetch_add_unless(atomic_t *v, int a, int u)
  * @u: int value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere.
  *
@@ -2452,6 +2462,7 @@ raw_atomic_add_unless(atomic_t *v, int a, int u)
  * @v: pointer to atomic_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere.
  *
@@ -2472,6 +2483,7 @@ raw_atomic_inc_not_zero(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere.
  *
@@ -2499,6 +2511,7 @@ raw_atomic_inc_unless_negative(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere.
  *
@@ -2526,6 +2539,7 @@ raw_atomic_dec_unless_positive(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere.
  *
@@ -4117,6 +4131,7 @@ raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere.
  *
@@ -4145,6 +4160,7 @@ raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere.
  *
@@ -4173,6 +4189,7 @@ raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere.
  *
@@ -4200,6 +4217,7 @@ raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere.
  *
@@ -4224,7 +4242,8 @@ raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere.
  *
@@ -4257,7 +4276,8 @@ raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere.
  *
@@ -4290,7 +4310,8 @@ raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere.
  *
@@ -4322,7 +4343,8 @@ raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere.
  *
@@ -4515,6 +4537,7 @@ raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
  * @u: s64 value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere.
  *
@@ -4544,6 +4567,7 @@ raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
  * @u: s64 value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere.
  *
@@ -4564,6 +4588,7 @@ raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
  * @v: pointer to atomic64_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere.
  *
@@ -4584,6 +4609,7 @@ raw_atomic64_inc_not_zero(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere.
  *
@@ -4611,6 +4637,7 @@ raw_atomic64_inc_unless_negative(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere.
  *
@@ -4638,6 +4665,7 @@ raw_atomic64_dec_unless_positive(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere.
  *
@@ -4662,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v)
 }
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// eec048affea735b8464f58e6d96992101f8f85f1
+// 14850c0b0db20c62fdc78ccd1d42b98b88d76331
diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index 54d7bbe0aeaa..debd487fe971 100644
--- a/include/linux/atomic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -1182,6 +1182,7 @@ atomic_xchg_relaxed(atomic_t *v, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there.
  *
@@ -1202,6 +1203,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there.
  *
@@ -1221,6 +1223,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there.
  *
@@ -1241,6 +1244,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there.
  *
@@ -1260,7 +1264,8 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there.
  *
@@ -1282,7 +1287,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there.
  *
@@ -1303,7 +1309,8 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there.
  *
@@ -1325,7 +1332,8 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
  * @new: int value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there.
  *
@@ -1475,6 +1483,7 @@ atomic_add_negative_relaxed(int i, atomic_t *v)
  * @u: int value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there.
  *
@@ -1495,6 +1504,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u)
  * @u: int value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_add_unless() there.
  *
@@ -1513,6 +1523,7 @@ atomic_add_unless(atomic_t *v, int a, int u)
  * @v: pointer to atomic_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there.
  *
@@ -1531,6 +1542,7 @@ atomic_inc_not_zero(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there.
  *
@@ -1549,6 +1561,7 @@ atomic_inc_unless_negative(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there.
  *
@@ -1567,6 +1580,7 @@ atomic_dec_unless_positive(atomic_t *v)
  * @v: pointer to atomic_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there.
  *
@@ -2746,6 +2760,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there.
  *
@@ -2766,6 +2781,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there.
  *
@@ -2785,6 +2801,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there.
  *
@@ -2805,6 +2822,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there.
  *
@@ -2824,7 +2842,8 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there.
  *
@@ -2846,7 +2865,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there.
  *
@@ -2867,7 +2887,8 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there.
  *
@@ -2889,7 +2910,8 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
  * @new: s64 value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there.
  *
@@ -3039,6 +3061,7 @@ atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
  * @u: s64 value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there.
  *
@@ -3059,6 +3082,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
  * @u: s64 value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there.
  *
@@ -3077,6 +3101,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
  * @v: pointer to atomic64_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there.
  *
@@ -3095,6 +3120,7 @@ atomic64_inc_not_zero(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there.
  *
@@ -3113,6 +3139,7 @@ atomic64_inc_unless_negative(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there.
  *
@@ -3131,6 +3158,7 @@ atomic64_dec_unless_positive(atomic64_t *v)
  * @v: pointer to atomic64_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there.
  *
@@ -4310,6 +4338,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there.
  *
@@ -4330,6 +4359,7 @@ atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there.
  *
@@ -4349,6 +4379,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there.
  *
@@ -4369,6 +4400,7 @@ atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there.
  *
@@ -4388,7 +4420,8 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there.
  *
@@ -4410,7 +4443,8 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there.
  *
@@ -4431,7 +4465,8 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there.
  *
@@ -4453,7 +4488,8 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there.
  *
@@ -4603,6 +4639,7 @@ atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
  * @u: long value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there.
  *
@@ -4623,6 +4660,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
  * @u: long value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there.
  *
@@ -4641,6 +4679,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u)
  * @v: pointer to atomic_long_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there.
  *
@@ -4659,6 +4698,7 @@ atomic_long_inc_not_zero(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there.
  *
@@ -4677,6 +4717,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there.
  *
@@ -4695,6 +4736,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there.
  *
@@ -5008,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 2cc4bc990fef44d3836ec108f11b610f3f438184
+// ce5b65e0f1f8a276268b667194581d24bed219d4
diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h
index c82947170ddc..3ef844b3ab8a 100644
--- a/include/linux/atomic/atomic-long.h
+++ b/include/linux/atomic/atomic-long.h
@@ -1352,6 +1352,7 @@ raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere.
  *
@@ -1374,6 +1375,7 @@ raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere.
  *
@@ -1396,6 +1398,7 @@ raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere.
  *
@@ -1418,6 +1421,7 @@ raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere.
  *
@@ -1440,7 +1444,8 @@ raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with full ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere.
  *
@@ -1463,7 +1468,8 @@ raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with acquire ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere.
  *
@@ -1486,7 +1492,8 @@ raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with release ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere.
  *
@@ -1509,7 +1516,8 @@ raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
  * @new: long value to assign
  *
  * If (@v == @old), atomically updates @v to @new with relaxed ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere.
  *
@@ -1677,6 +1685,7 @@ raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
  * @u: long value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere.
  *
@@ -1699,6 +1708,7 @@ raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
  * @u: long value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere.
  *
@@ -1719,6 +1729,7 @@ raw_atomic_long_add_unless(atomic_long_t *v, long a, long u)
  * @v: pointer to atomic_long_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere.
  *
@@ -1739,6 +1750,7 @@ raw_atomic_long_inc_not_zero(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere.
  *
@@ -1759,6 +1771,7 @@ raw_atomic_long_inc_unless_negative(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere.
  *
@@ -1779,6 +1792,7 @@ raw_atomic_long_dec_unless_positive(atomic_long_t *v)
  * @v: pointer to atomic_long_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere.
  *
@@ -1795,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v)
 }
 
 #endif /* _LINUX_ATOMIC_LONG_H */
-// 4ef23f98c73cff96d239896175fd26b10b88899e
+// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492..2ad261082bba 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -141,8 +141,6 @@ struct bdi_writeback {
 	struct delayed_work dwork;	/* work item used for writeback */
 	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
-	unsigned long dirty_sleep;	/* last wait */
-
 	struct list_head bdi_node;	/* anchored at bdi->wb_list */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
 	 * any dirty wbs, which is depended upon by bdi_has_dirty().
 	 */
 	atomic_long_t tot_write_bandwidth;
+	/*
+	 * Jiffies when last process was dirty throttled on this bdi. Used by
+	 * blk-wbt.
+	 */
+	unsigned long last_bdp_sleep;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1a97277f99b1..8e7af9a03b41 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id);
 
 void wb_start_background_writeback(struct bdi_writeback *wb);
 void wb_workfn(struct work_struct *work);
-void wb_wakeup_delayed(struct bdi_writeback *wb);
 
 void wb_wait_for_completion(struct wb_completion *done);
 
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 99451431e4d6..df24c8fb1009 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -6,6 +6,7 @@
 
 #include <linux/align.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/errno.h>
 #include <linux/find.h>
 #include <linux/limits.h>
@@ -127,6 +128,8 @@ unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node);
 unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node);
 void bitmap_free(const unsigned long *bitmap);
 
+DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T))
+
 /* Managed variants of the above. */
 unsigned long *devm_bitmap_alloc(struct device *dev,
 				 unsigned int nbits, gfp_t flags);
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 378b2459efe2..e253e7bd0d17 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -20,6 +20,7 @@ struct blk_integrity_iter {
 	unsigned int		data_size;
 	unsigned short		interval;
 	unsigned char		tuple_size;
+	unsigned char		pi_offset;
 	const char		*disk_name;
 };
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 7a8150a5f051..d3d8fd8e229b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -8,6 +8,7 @@
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
 #include <linux/srcu.h>
+#include <linux/rw_hint.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -135,6 +136,7 @@ struct request {
 	struct blk_crypto_keyslot *crypt_keyslot;
 #endif
 
+	enum rw_hint write_hint;
 	unsigned short ioprio;
 
 	enum mq_rq_state state;
@@ -682,17 +684,19 @@ enum {
 
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass);
-#define blk_mq_alloc_disk(set, queuedata)				\
+#define blk_mq_alloc_disk(set, lim, queuedata)				\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_mq_alloc_disk(set, queuedata, &__key);			\
+	__blk_mq_alloc_disk(set, lim, queuedata, &__key);		\
 })
 struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
 		struct lock_class_key *lkclass);
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
 void blk_mq_destroy_queue(struct request_queue *);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f288c94374b3..cb1526ec44b5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -10,6 +10,7 @@
 #include <linux/bvec.h>
 #include <linux/device.h>
 #include <linux/ktime.h>
+#include <linux/rw_hint.h>
 
 struct bio_set;
 struct bio;
@@ -206,52 +207,10 @@ static inline bool blk_path_error(blk_status_t error)
 	return true;
 }
 
-/*
- * From most significant bit:
- * 1 bit: reserved for other usage, see below
- * 12 bits: original size of bio
- * 51 bits: issue time of bio
- */
-#define BIO_ISSUE_RES_BITS      1
-#define BIO_ISSUE_SIZE_BITS     12
-#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
-#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
-#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
-#define BIO_ISSUE_SIZE_MASK     \
-	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
-#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
-
-/* Reserved bit for blk-throtl */
-#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
-
 struct bio_issue {
 	u64 value;
 };
 
-static inline u64 __bio_issue_time(u64 time)
-{
-	return time & BIO_ISSUE_TIME_MASK;
-}
-
-static inline u64 bio_issue_time(struct bio_issue *issue)
-{
-	return __bio_issue_time(issue->value);
-}
-
-static inline sector_t bio_issue_size(struct bio_issue *issue)
-{
-	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
-}
-
-static inline void bio_issue_init(struct bio_issue *issue,
-				       sector_t size)
-{
-	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
-	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
-			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
-			((u64)size << BIO_ISSUE_SIZE_SHIFT));
-}
-
 typedef __u32 __bitwise blk_opf_t;
 
 typedef unsigned int blk_qc_t;
@@ -269,6 +228,7 @@ struct bio {
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
 	unsigned short		bi_ioprio;
+	enum rw_hint		bi_write_hint;
 	blk_status_t		bi_status;
 	atomic_t		__bi_remaining;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99e4f5e72213..f9b87c39cab0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/sbitmap.h>
 #include <linux/uuid.h>
 #include <linux/xarray.h>
+#include <linux/file.h>
 
 struct module;
 struct request_queue;
@@ -42,7 +43,7 @@ struct blk_crypto_profile;
 
 extern const struct device_type disk_type;
 extern const struct device_type part_type;
-extern struct class block_class;
+extern const struct class block_class;
 
 /*
  * Maximum number of blkcg policies allowed to be registered concurrently.
@@ -108,6 +109,7 @@ struct blk_integrity {
 	const struct blk_integrity_profile	*profile;
 	unsigned char				flags;
 	unsigned char				tuple_size;
+	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
 };
@@ -189,8 +191,6 @@ struct gendisk {
 	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 #endif /* CONFIG_BLK_DEV_ZONED */
@@ -292,6 +292,7 @@ struct queue_limits {
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
+	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
 	unsigned int		max_zone_append_sectors;
@@ -307,6 +308,8 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
 	bool			zoned;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -325,7 +328,7 @@ void disk_set_zoned(struct gendisk *disk);
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
+		sector_t sectors, sector_t nr_sectors);
 int blk_revalidate_disk_zones(struct gendisk *disk,
 		void (*update_driver_data)(struct gendisk *disk));
 
@@ -473,6 +476,7 @@ struct request_queue {
 
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
+	struct mutex		limits_lock;
 
 	/*
 	 * for reusing dead hctx instance in case of updating
@@ -639,23 +643,23 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
-	disk->max_open_zones = max_open_zones;
+	disk->queue->limits.max_open_zones = max_open_zones;
 }
 
 static inline void disk_set_max_active_zones(struct gendisk *disk,
 		unsigned int max_active_zones)
 {
-	disk->max_active_zones = max_active_zones;
+	disk->queue->limits.max_active_zones = max_active_zones;
 }
 
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_open_zones;
+	return bdev->bd_disk->queue->limits.max_open_zones;
 }
 
 static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_active_zones;
+	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
@@ -763,22 +767,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
 void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass);
 
 /**
  * blk_alloc_disk - allocate a gendisk structure
+ * @lim: queue limits to be used for this disk.
  * @node_id: numa node to allocate on
  *
  * Allocate and pre-initialize a gendisk structure for use with BIO based
  * drivers.
  *
+ * Returns an ERR_PTR on error, else the allocated disk.
+ *
  * Context: can sleep
  */
-#define blk_alloc_disk(node_id)						\
+#define blk_alloc_disk(lim, node_id)					\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_alloc_disk(node_id, &__key);				\
+	__blk_alloc_disk(lim, node_id, &__key);				\
 })
 
 int __register_blkdev(unsigned int major, const char *name,
@@ -861,6 +869,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset,
 	return chunk_sectors - (offset & (chunk_sectors - 1));
 }
 
+/**
+ * queue_limits_start_update - start an atomic update of queue limits
+ * @q:		queue to update
+ *
+ * This functions starts an atomic update of the queue limits.  It takes a lock
+ * to prevent other updates and returns a snapshot of the current limits that
+ * the caller can modify.  The caller must call queue_limits_commit_update()
+ * to finish the update.
+ *
+ * Context: process context.  The caller must have frozen the queue or ensured
+ * that there is outstanding I/O by other means.
+ */
+static inline struct queue_limits
+queue_limits_start_update(struct request_queue *q)
+	__acquires(q->limits_lock)
+{
+	mutex_lock(&q->limits_lock);
+	return q->limits;
+}
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim);
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+
 /*
  * Access functions for manipulating queue properties
  */
@@ -894,8 +925,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-			      sector_t offset);
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
@@ -942,6 +973,7 @@ struct blk_plug {
 
 	/* if ios_left is > 1, we can batch tag/rq allocations */
 	struct request *cached_rq;
+	u64 cur_ktime;
 	unsigned short nr_ios;
 
 	unsigned short rq_count;
@@ -972,6 +1004,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 		__blk_flush_plug(plug, async);
 }
 
+/*
+ * tsk == current here
+ */
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (plug)
+		plug->cur_ktime = 0;
+	current->flags &= ~PF_BLOCK_TS;
+}
+
 int blkdev_issue_flush(struct block_device *bdev);
 long nr_blockdev_pages(void);
 #else /* CONFIG_BLOCK */
@@ -995,6 +1039,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+}
+
 static inline int blkdev_issue_flush(struct block_device *bdev)
 {
 	return 0;
@@ -1474,26 +1522,20 @@ extern const struct blk_holder_ops fs_holder_ops;
 	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
 	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
-struct bdev_handle {
-	struct block_device *bdev;
-	void *holder;
-	blk_mode_t mode;
-};
-
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
-struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops);
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-void bdev_release(struct bdev_handle *handle);
 
 /* just for blk-cgroup, don't use elsewhere */
 struct block_device *blkdev_get_no_open(dev_t dev);
 void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
+struct block_device *file_bdev(struct file *bdev_file);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 555aae5448ae..bd1e361b351c 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -83,7 +83,7 @@ struct bvec_iter {
 
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
-} __packed;
+} __packed __aligned(4);
 
 struct bvec_iter_all {
 	struct bio_vec	bv;
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 2eaaabbe98cb..1717cc57cdac 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -283,7 +283,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
-	bool sparse_read;
+	u64 sparse_read_total;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fa018d5864e7..f66f6aac74f6 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -45,6 +45,7 @@ enum ceph_sparse_read_state {
 	CEPH_SPARSE_READ_HDR	= 0,
 	CEPH_SPARSE_READ_EXTENTS,
 	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA_PRE,
 	CEPH_SPARSE_READ_DATA,
 };
 
@@ -64,7 +65,7 @@ struct ceph_sparse_read {
 	u64				sr_req_len;  /* orig request length */
 	u64				sr_pos;      /* current pos in buffer */
 	int				sr_index;    /* current extent index */
-	__le32				sr_datalen;  /* length of actual data */
+	u32				sr_datalen;  /* length of actual data */
 	u32				sr_count;    /* extent count in reply */
 	int				sr_ext_len;  /* length of extent array */
 	struct ceph_sparse_extent	*sr_extent;  /* extent array */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 1d42d4b17327..0ad8b550bb4b 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -291,7 +291,19 @@ static inline void timer_probe(void) {}
 #define TIMER_ACPI_DECLARE(name, table_id, fn)		\
 	ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn)
 
-extern ulong max_cswd_read_retries;
+static inline unsigned int clocksource_get_max_watchdog_retry(void)
+{
+	/*
+	 * When system is in the boot phase or under heavy workload, there
+	 * can be random big latencies during the clocksource/watchdog
+	 * read, so allow retries to filter the noise latency. As the
+	 * latency's frequency and maximum value goes up with the number of
+	 * CPUs, scale the number of retries with the number of online
+	 * CPUs.
+	 */
+	return (ilog2(num_online_cpus()) / 2) + 1;
+}
+
 void clocksource_verify_percpu(struct clocksource *cs);
 
 #endif /* _LINUX_CLOCKSOURCE_H */
diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h
index 16775d7d8f8d..a4fa3436940c 100644
--- a/include/linux/clocksource_ids.h
+++ b/include/linux/clocksource_ids.h
@@ -6,6 +6,9 @@
 enum clocksource_ids {
 	CSID_GENERIC		= 0,
 	CSID_ARM_ARCH_COUNTER,
+	CSID_X86_TSC_EARLY,
+	CSID_X86_TSC,
+	CSID_X86_KVM_CLK,
 	CSID_MAX,
 };
 
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index aebb65bf95a7..aff92b1d284f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -35,7 +35,7 @@
 	(typeof(ptr)) (__ptr + (off));					\
 })
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 #define __noretpoline __attribute__((__indirect_branch__("keep")))
 #endif
 
@@ -64,6 +64,26 @@
 		__builtin_unreachable();	\
 	} while (0)
 
+/*
+ * GCC 'asm goto' with outputs miscompiles certain code sequences:
+ *
+ *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
+ *
+ * Work around it via the same compiler barrier quirk that we used
+ * to use for the old 'asm goto' workaround.
+ *
+ * Also, always mark such 'asm goto' statements as volatile: all
+ * asm goto statements are supposed to be volatile as per the
+ * documentation, but some versions of gcc didn't actually do
+ * that for asms with outputs:
+ *
+ *    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
+ */
+#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND
+#define asm_goto_output(x...) \
+	do { asm volatile goto(x); asm (""); } while (0)
+#endif
+
 #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
 #define __HAVE_BUILTIN_BSWAP32__
 #define __HAVE_BUILTIN_BSWAP64__
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index bb1339c7057b..cdcdaa48b4d2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -209,7 +209,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define ___ADDRESSABLE(sym, __attrs) \
 	static void * __used __attrs \
-		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
+	__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym;
 #define __ADDRESSABLE(sym) \
 	___ADDRESSABLE(sym, __section(".discard.addressable"))
 
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 28566624f008..8bdf6e0918c1 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -95,11 +95,11 @@
 #endif
 
 /*
- * Optional: only supported since gcc >= 14
+ * Optional: only supported since gcc >= 15
  * Optional: only supported since clang >= 18
  *
  *   gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
- * clang: https://reviews.llvm.org/D148381
+ * clang: https://github.com/llvm/llvm-project/pull/76348
  */
 #if __has_attribute(__counted_by__)
 # define __counted_by(member)		__attribute__((__counted_by__(member)))
@@ -334,6 +334,18 @@
 #define __section(section)              __attribute__((__section__(section)))
 
 /*
+ * Optional: only supported since gcc >= 12
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-uninitialized-variable-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#uninitialized
+ */
+#if __has_attribute(__uninitialized__)
+# define __uninitialized		__attribute__((__uninitialized__))
+#else
+# define __uninitialized
+#endif
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6f1ca49306d2..0caf354cb94b 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -362,8 +362,15 @@ struct ftrace_likely_data {
 #define __member_size(p)	__builtin_object_size(p, 1)
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+/*
+ * Some versions of gcc do not mark 'asm goto' volatile:
+ *
+ *  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979
+ *
+ * We do it here by hand, because it doesn't hurt.
+ */
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm volatile goto(x)
 #endif
 
 #ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c1a7dc325121..265b0f8fc0b3 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -90,6 +90,29 @@ enum {
 	GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E,	\
 		  0x72, 0x2D, 0xEB, 0x41)
 
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
 /*
  * Flags bits definitions for flags in struct cper_record_header
  * If set, the error has been recovered
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index dcb89c987164..ae5a20cf2f9c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -75,6 +75,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev,
 					     struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_gds(struct device *dev,
 			    struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev,
+					       struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
@@ -112,7 +114,7 @@ void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 int bringup_hibernate_cpu(unsigned int sleep_cpu);
-void bringup_nonboot_cpus(unsigned int setup_max_cpus);
+void bringup_nonboot_cpus(unsigned int max_cpus);
 
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
@@ -196,6 +198,8 @@ void arch_cpu_idle(void);
 void arch_cpu_idle_prepare(void);
 void arch_cpu_idle_enter(void);
 void arch_cpu_idle_exit(void);
+void arch_tick_broadcast_enter(void);
+void arch_tick_broadcast_exit(void);
 void __noreturn arch_cpu_idle_dead(void);
 
 #ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 172d0a743e5d..35e78ddb2b37 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -184,6 +184,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_HRTIMERS_DYING,
+	CPUHP_AP_TICK_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
@@ -231,6 +232,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
 	CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
 	CPUHP_AP_PERF_CSKY_ONLINE,
+	CPUHP_AP_TMIGR_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RANDOM_ONLINE,
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 875d12598bd2..0ce6ff0d9c9a 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -121,11 +121,6 @@ static inline int cpuset_do_page_mem_spread(void)
 	return task_spread_page(current);
 }
 
-static inline int cpuset_do_slab_mem_spread(void)
-{
-	return task_spread_slab(current);
-}
-
 extern bool current_cpuset_is_being_rebound(void);
 
 extern void rebuild_sched_domains(void);
@@ -264,11 +259,6 @@ static inline int cpuset_do_page_mem_spread(void)
 	return 0;
 }
 
-static inline int cpuset_do_slab_mem_spread(void)
-{
-	return 0;
-}
-
 static inline bool current_cpuset_is_being_rebound(void)
 {
 	return false;
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 91125eca4c8a..03fa6d50d46f 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -140,22 +140,4 @@ struct cxl_cper_event_rec {
 	union cxl_event event;
 } __packed;
 
-typedef void (*cxl_cper_callback)(enum cxl_event_type type,
-				  struct cxl_cper_event_rec *rec);
-
-#ifdef CONFIG_ACPI_APEI_GHES
-int cxl_cper_register_callback(cxl_cper_callback callback);
-int cxl_cper_unregister_callback(cxl_cper_callback callback);
-#else
-static inline int cxl_cper_register_callback(cxl_cper_callback callback)
-{
-	return 0;
-}
-
-static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
-{
-	return 0;
-}
-#endif
-
 #endif /* _LINUX_CXL_EVENT_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1666c387861f..bf53e3894aae 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -125,6 +125,11 @@ enum dentry_d_lock_class
 	DENTRY_D_LOCK_NESTED
 };
 
+enum d_real_type {
+	D_REAL_DATA,
+	D_REAL_METADATA,
+};
+
 struct dentry_operations {
 	int (*d_revalidate)(struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
@@ -139,7 +144,7 @@ struct dentry_operations {
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *);
+	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 } ____cacheline_aligned;
 
 /*
@@ -173,6 +178,7 @@ struct dentry_operations {
 #define DCACHE_DONTCACHE		BIT(7) /* Purge from memory on final dput() */
 
 #define DCACHE_CANT_MOUNT		BIT(8)
+#define DCACHE_GENOCIDE			BIT(9)
 #define DCACHE_SHRINK_LIST		BIT(10)
 
 #define DCACHE_OP_WEAK_REVALIDATE	BIT(11)
@@ -546,24 +552,23 @@ static inline struct inode *d_backing_inode(const struct dentry *upper)
 /**
  * d_real - Return the real dentry
  * @dentry: the dentry to query
- * @inode: inode to select the dentry from multiple layers (can be NULL)
+ * @type: the type of real dentry (data or metadata)
  *
  * If dentry is on a union/overlay, then return the underlying, real dentry.
  * Otherwise return the dentry itself.
  *
  * See also: Documentation/filesystems/vfs.rst
  */
-static inline struct dentry *d_real(struct dentry *dentry,
-				    const struct inode *inode)
+static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type)
 {
 	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-		return dentry->d_op->d_real(dentry, inode);
+		return dentry->d_op->d_real(dentry, type);
 	else
 		return dentry;
 }
 
 /**
- * d_real_inode - Return the real inode
+ * d_real_inode - Return the real inode hosting the data
  * @dentry: The dentry to query
  *
  * If dentry is on a union/overlay, then return the underlying, real inode.
@@ -572,7 +577,7 @@ static inline struct dentry *d_real(struct dentry *dentry,
 static inline struct inode *d_real_inode(const struct dentry *dentry)
 {
 	/* This usage of d_real() results in const dentry */
-	return d_backing_inode(d_real((struct dentry *) dentry, NULL));
+	return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA));
 }
 
 struct name_snapshot {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 772ab4d74d94..82b2195efaca 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -165,7 +165,7 @@ void dm_error(const char *message);
 
 struct dm_dev {
 	struct block_device *bdev;
-	struct bdev_handle *bdev_handle;
+	struct file *bdev_file;
 	struct dax_device *dax_dev;
 	blk_mode_t mode;
 	char name[16];
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 3df70d6131c8..752dbde4cec1 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -953,7 +953,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 
 static inline bool is_slave_direction(enum dma_transfer_direction direction)
 {
-	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM);
+	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) ||
+	       (direction == DMA_DEV_TO_DEV);
 }
 
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 9cf896ea1d41..e37344f6a231 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -10,6 +10,8 @@
 #include <uapi/linux/dpll.h>
 #include <linux/device.h>
 #include <linux/netlink.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
 
 struct dpll_device;
 struct dpll_pin;
@@ -120,15 +122,24 @@ struct dpll_pin_properties {
 };
 
 #if IS_ENABLED(CONFIG_DPLL)
-size_t dpll_msg_pin_handle_size(struct dpll_pin *pin);
-int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin);
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
+void dpll_netdev_pin_clear(struct net_device *dev);
+
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev);
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+			       const struct net_device *dev);
 #else
-static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
+static inline void
+dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { }
+static inline void dpll_netdev_pin_clear(struct net_device *dev) { }
+
+static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
 {
 	return 0;
 }
 
-static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+static inline int
+dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev)
 {
 	return 0;
 }
diff --git a/include/linux/file.h b/include/linux/file.h
index 6834a29338c4..169692cb1906 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -24,6 +24,8 @@ struct inode;
 struct path;
 extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
 	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
 extern struct file *alloc_file_clone(struct file *, int flags,
 	const struct file_operations *);
 
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index 95e868e09e29..daee999d05f3 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -27,6 +27,7 @@
 #define FILE_LOCK_DEFERRED 1
 
 struct file_lock;
+struct file_lease;
 
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -39,14 +40,17 @@ struct lock_manager_operations {
 	void (*lm_put_owner)(fl_owner_t);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
-	bool (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock *, int, struct list_head *);
-	void (*lm_setup)(struct file_lock *, void **);
-	bool (*lm_breaker_owns_lease)(struct file_lock *);
 	bool (*lm_lock_expirable)(struct file_lock *cfl);
 	void (*lm_expire_lock)(void);
 };
 
+struct lease_manager_operations {
+	bool (*lm_break)(struct file_lease *);
+	int (*lm_change)(struct file_lease *, int, struct list_head *);
+	void (*lm_setup)(struct file_lease *, void **);
+	bool (*lm_breaker_owns_lease)(struct file_lease *);
+};
+
 struct lock_manager {
 	struct list_head list;
 	/*
@@ -85,31 +89,31 @@ bool opens_in_grace(struct net *);
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
-struct file_lock {
-	struct file_lock *fl_blocker;	/* The lock, that is blocking us */
-	struct list_head fl_list;	/* link into file_lock_context */
-	struct hlist_node fl_link;	/* node in global lists */
-	struct list_head fl_blocked_requests;	/* list of requests with
+
+struct file_lock_core {
+	struct file_lock_core *flc_blocker;	/* The lock that is blocking us */
+	struct list_head flc_list;	/* link into file_lock_context */
+	struct hlist_node flc_link;	/* node in global lists */
+	struct list_head flc_blocked_requests;	/* list of requests with
 						 * ->fl_blocker pointing here
 						 */
-	struct list_head fl_blocked_member;	/* node in
+	struct list_head flc_blocked_member;	/* node in
 						 * ->fl_blocker->fl_blocked_requests
 						 */
-	fl_owner_t fl_owner;
-	unsigned int fl_flags;
-	unsigned char fl_type;
-	unsigned int fl_pid;
-	int fl_link_cpu;		/* what cpu's list is this on? */
-	wait_queue_head_t fl_wait;
-	struct file *fl_file;
+	fl_owner_t flc_owner;
+	unsigned int flc_flags;
+	unsigned char flc_type;
+	pid_t flc_pid;
+	int flc_link_cpu;		/* what cpu's list is this on? */
+	wait_queue_head_t flc_wait;
+	struct file *flc_file;
+};
+
+struct file_lock {
+	struct file_lock_core c;
 	loff_t fl_start;
 	loff_t fl_end;
 
-	struct fasync_struct *	fl_fasync; /* for lease break notifications */
-	/* for lease breaks: */
-	unsigned long fl_break_time;
-	unsigned long fl_downgrade_time;
-
 	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
 	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
 	union {
@@ -126,6 +130,15 @@ struct file_lock {
 	} fl_u;
 } __randomize_layout;
 
+struct file_lease {
+	struct file_lock_core c;
+	struct fasync_struct *	fl_fasync; /* for lease break notifications */
+	/* for lease breaks: */
+	unsigned long fl_break_time;
+	unsigned long fl_downgrade_time;
+	const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */
+} __randomize_layout;
+
 struct file_lock_context {
 	spinlock_t		flc_lock;
 	struct list_head	flc_flock;
@@ -147,11 +160,31 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 int fcntl_setlease(unsigned int fd, struct file *filp, int arg);
 int fcntl_getlease(struct file *filp);
 
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_UNLCK;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_RDLCK;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_WRLCK;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+	wake_up(&fl->c.flc_wait);
+}
+
 /* fs/locks.c */
 void locks_free_lock_context(struct inode *inode);
 void locks_free_lock(struct file_lock *fl);
 void locks_init_lock(struct file_lock *);
-struct file_lock * locks_alloc_lock(void);
+struct file_lock *locks_alloc_lock(void);
 void locks_copy_lock(struct file_lock *, struct file_lock *);
 void locks_copy_conflock(struct file_lock *, struct file_lock *);
 void locks_remove_posix(struct file *, fl_owner_t);
@@ -165,11 +198,16 @@ int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_l
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 bool vfs_inode_has_locks(struct inode *inode);
 int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
+
+void locks_init_lease(struct file_lease *);
+void locks_free_lease(struct file_lease *fl);
+struct file_lease *locks_alloc_lease(void);
 int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 void lease_get_mtime(struct inode *, struct timespec64 *time);
-int generic_setlease(struct file *, int, struct file_lock **, void **priv);
-int vfs_setlease(struct file *, int, struct file_lock **, void **);
-int lease_modify(struct file_lock *, int, struct list_head *);
+int generic_setlease(struct file *, int, struct file_lease **, void **priv);
+int kernel_setlease(struct file *, int, struct file_lease **, void **);
+int vfs_setlease(struct file *, int, struct file_lease **, void **);
+int lease_modify(struct file_lease *, int, struct list_head *);
 
 struct notifier_block;
 int lease_register_notifier(struct notifier_block *);
@@ -223,6 +261,25 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+}
+
 static inline void
 locks_free_lock_context(struct inode *inode)
 {
@@ -233,6 +290,11 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
+static inline void locks_init_lease(struct file_lease *fl)
+{
+	return;
+}
+
 static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
@@ -307,18 +369,24 @@ static inline void lease_get_mtime(struct inode *inode,
 }
 
 static inline int generic_setlease(struct file *filp, int arg,
-				    struct file_lock **flp, void **priv)
+				    struct file_lease **flp, void **priv)
+{
+	return -EINVAL;
+}
+
+static inline int kernel_setlease(struct file *filp, int arg,
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, int arg,
-			       struct file_lock **lease, void **priv)
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock *fl, int arg,
+static inline int lease_modify(struct file_lease *fl, int arg,
 			       struct list_head *dispose)
 {
 	return -EINVAL;
@@ -341,6 +409,9 @@ locks_inode_context(const struct inode *inode)
 
 #endif /* !CONFIG_FILE_LOCKING */
 
+/* for walking lists of file_locks linked by fl_list */
+#define for_each_file_lock(_fl, _head)	list_for_each_entry(_fl, _head, c.flc_list)
+
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 {
 	return locks_lock_inode_wait(file_inode(filp), fl);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a70495..0a22b7245982 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -43,6 +43,8 @@
 #include <linux/cred.h>
 #include <linux/mnt_idmapping.h>
 #include <linux/slab.h>
+#include <linux/maple_tree.h>
+#include <linux/rw_hint.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -309,19 +311,6 @@ struct address_space;
 struct writeback_control;
 struct readahead_control;
 
-/*
- * Write life time hint values.
- * Stored in struct inode as u8.
- */
-enum rw_hint {
-	WRITE_LIFE_NOT_SET	= 0,
-	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
-	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
-	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
-	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
-	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
-};
-
 /* Match RWF_* bits to IOCB bits */
 #define IOCB_HIPRI		(__force int) RWF_HIPRI
 #define IOCB_DSYNC		(__force int) RWF_DSYNC
@@ -352,6 +341,8 @@ enum rw_hint {
  * unrelated IO (like cache flushing, new IO generation, etc).
  */
 #define IOCB_DIO_CALLER_COMP	(1 << 22)
+/* kiocb is a read or write operation submitted by fs/aio.c. */
+#define IOCB_AIO_RW		(1 << 23)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
@@ -482,10 +473,10 @@ struct address_space {
 	pgoff_t			writeback_index;
 	const struct address_space_operations *a_ops;
 	unsigned long		flags;
-	struct rw_semaphore	i_mmap_rwsem;
 	errseq_t		wb_err;
 	spinlock_t		i_private_lock;
 	struct list_head	i_private_list;
+	struct rw_semaphore	i_mmap_rwsem;
 	void *			i_private_data;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
@@ -677,7 +668,7 @@ struct inode {
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	u8			i_blkbits;
-	u8			i_write_hint;
+	enum rw_hint		i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -907,7 +898,8 @@ static inline loff_t i_size_read(const struct inode *inode)
 	preempt_enable();
 	return i_size;
 #else
-	return inode->i_size;
+	/* Pairs with smp_store_release() in i_size_write() */
+	return smp_load_acquire(&inode->i_size);
 #endif
 }
 
@@ -929,7 +921,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 	inode->i_size = i_size;
 	preempt_enable();
 #else
-	inode->i_size = i_size;
+	/*
+	 * Pairs with smp_load_acquire() in i_size_read() to ensure
+	 * changes related to inode size (such as page contents) are
+	 * visible before we see the changed inode size.
+	 */
+	smp_store_release(&inode->i_size, i_size);
 #endif
 }
 
@@ -1064,6 +1061,7 @@ struct file *get_file_active(struct file **f);
 typedef void *fl_owner_t;
 
 struct file_lock;
+struct file_lease;
 
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
@@ -1078,9 +1076,20 @@ static inline struct inode *file_inode(const struct file *f)
 	return f->f_inode;
 }
 
+/*
+ * file_dentry() is a relic from the days that overlayfs was using files with a
+ * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs.
+ * In those days, file_dentry() was needed to get the underlying fs dentry that
+ * matches f_inode.
+ * Files with "fake" path should not exist nowadays, so use an assertion to make
+ * sure that file_dentry() was not papering over filesystem bugs.
+ */
 static inline struct dentry *file_dentry(const struct file *file)
 {
-	return d_real(file->f_path.dentry, file_inode(file));
+	struct dentry *dentry = file->f_path.dentry;
+
+	WARN_ON_ONCE(d_inode(dentry) != file_inode(file));
+	return dentry;
 }
 
 struct fasync_struct {
@@ -1228,8 +1237,8 @@ struct super_block {
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
-	struct block_device	*s_bdev;
-	struct bdev_handle	*s_bdev_handle;
+	struct block_device	*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
+	struct file		*s_bdev_file;
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
@@ -1255,8 +1264,22 @@ struct super_block {
 	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
 #endif
 
+	/*
+	 * q: why are s_id and s_sysfs_name not the same? both are human
+	 * readable strings that identify the filesystem
+	 * a: s_id is allowed to change at runtime; it's used in log messages,
+	 * and we want to when a device starts out as single device (s_id is dev
+	 * name) but then a device is hot added and we have to switch to
+	 * identifying it by UUID
+	 * but s_sysfs_name is a handle for programmatic access, and can't
+	 * change at runtime
+	 */
 	char			s_id[32];	/* Informational name */
 	uuid_t			s_uuid;		/* UUID */
+	u8			s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
+
+	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+	char			s_sysfs_name[UUID_STRING_LEN + 1];
 
 	unsigned int		s_max_links;
 
@@ -2005,7 +2028,7 @@ struct file_operations {
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
 	void (*splice_eof)(struct file *file);
-	int (*setlease)(struct file *, int, struct file_lock **, void **);
+	int (*setlease)(struct file *, int, struct file_lease **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -2101,9 +2124,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
 				  loff_t *count, unsigned int remap_flags);
-extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t len, unsigned int remap_flags);
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
@@ -2532,6 +2552,44 @@ extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
 
+static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len)
+{
+	if (WARN_ON(len > sizeof(sb->s_uuid)))
+		len = sizeof(sb->s_uuid);
+	sb->s_uuid_len = len;
+	memcpy(&sb->s_uuid, uuid, len);
+}
+
+/* set sb sysfs name based on sb->s_bdev */
+static inline void super_set_sysfs_name_bdev(struct super_block *sb)
+{
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
+}
+
+/* set sb sysfs name based on sb->s_uuid */
+static inline void super_set_sysfs_name_uuid(struct super_block *sb)
+{
+	WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
+}
+
+/* set sb sysfs name based on sb->s_id */
+static inline void super_set_sysfs_name_id(struct super_block *sb)
+{
+	strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
+}
+
+/* try to use something standard before you use this */
+__printf(2, 3)
+static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
+	va_end(args);
+}
+
 extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
@@ -2928,6 +2986,17 @@ extern bool path_is_under(const struct path *, const struct path *);
 
 extern char *file_path(struct file *, char *, int);
 
+/**
+ * is_dot_dotdot - returns true only if @name is "." or ".."
+ * @name: file name to check
+ * @len: length of file name, in bytes
+ */
+static inline bool is_dot_dotdot(const char *name, size_t len)
+{
+	return len && unlikely(name[0] == '.') &&
+		(len == 1 || (len == 2 && name[1] == '.'));
+}
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
@@ -3238,7 +3307,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
-extern int simple_nosetlease(struct file *, int, struct file_lock **, void **);
+extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
@@ -3260,13 +3329,14 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 		const void __user *from, size_t count);
 
 struct offset_ctx {
-	struct xarray		xa;
-	u32			next_offset;
+	struct maple_tree	mt;
+	unsigned long		next_offset;
 };
 
 void simple_offset_init(struct offset_ctx *octx);
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
+int simple_offset_empty(struct dentry *dentry);
 int simple_offset_rename_exchange(struct inode *old_dir,
 				  struct dentry *old_dentry,
 				  struct inode *new_dir,
@@ -3280,7 +3350,16 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
-extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
+extern void generic_set_sb_d_ops(struct super_block *sb);
+
+static inline bool sb_has_encoding(const struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_UNICODE)
+	return !!sb->s_encoding;
+#else
+	return false;
+#endif
+}
 
 int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid);
@@ -3335,6 +3414,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
+	if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
+		return -EINVAL;
 
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
@@ -3345,6 +3426,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
 
+	if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
+		if (IS_APPEND(file_inode(ki->ki_filp)))
+			return -EPERM;
+		ki->ki_flags &= ~IOCB_APPEND;
+	}
+
 	ki->ki_flags |= kiocb_flags;
 	return 0;
 }
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 12f9e455d569..772f822dc6b8 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -192,6 +192,8 @@ struct fscrypt_operations {
 					     unsigned int *num_devs);
 };
 
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
+
 static inline struct fscrypt_inode_info *
 fscrypt_get_inode_info(const struct inode *inode)
 {
@@ -221,15 +223,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 }
 
 /*
- * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
- * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
- * cleared.  Note that we don't have to support arbitrary moves of this flag
- * because fscrypt doesn't allow no-key names to be the source or target of a
- * rename().
+ * When d_splice_alias() moves a directory's no-key alias to its
+ * plaintext alias as a result of the encryption key being added,
+ * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity
+ * to disable d_revalidate.  Note that we don't have to support the
+ * inverse operation because fscrypt doesn't allow no-key names to be
+ * the source or target of a rename().
  */
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
-	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+	/*
+	 * VFS calls fscrypt_handle_d_move even for non-fscrypt
+	 * filesystems.
+	 */
+	if (dentry->d_flags & DCACHE_NOKEY_NAME) {
+		dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+
+		/*
+		 * Other filesystem features might be handling dentry
+		 * revalidation, in which case it cannot be disabled.
+		 */
+		if (dentry->d_op->d_revalidate == fscrypt_d_revalidate)
+			dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+	}
 }
 
 /**
@@ -261,6 +277,35 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_NOKEY_NAME;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+	/*
+	 * This code tries to only take ->d_lock when necessary to write
+	 * to ->d_flags.  We shouldn't be peeking on d_flags for
+	 * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case
+	 * there is a race, the worst it can happen is that we fail to
+	 * unset DCACHE_OP_REVALIDATE and pay the cost of an extra
+	 * d_revalidate.
+	 */
+	if (is_nokey_name) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags |= DCACHE_NOKEY_NAME;
+		spin_unlock(&dentry->d_lock);
+	} else if (dentry->d_flags & DCACHE_OP_REVALIDATE &&
+		   dentry->d_op->d_revalidate == fscrypt_d_revalidate) {
+		/*
+		 * Unencrypted dentries and encrypted dentries where the
+		 * key is available are always valid from fscrypt
+		 * perspective. Avoid the cost of calling
+		 * fscrypt_d_revalidate unnecessarily.
+		 */
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+		spin_unlock(&dentry->d_lock);
+	}
+}
+
 /* crypto.c */
 void fscrypt_enqueue_decrypt_work(struct work_struct *);
 
@@ -368,7 +413,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 bool fscrypt_match_name(const struct fscrypt_name *fname,
 			const u8 *de_name, u32 de_name_len);
 u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
 bool fscrypt_decrypt_bio(struct bio *bio);
@@ -425,6 +469,11 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return false;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+}
+
 /* crypto.c */
 static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 {
@@ -982,6 +1031,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
 	fname->usr_fname = &dentry->d_name;
 	fname->disk_name.name = (unsigned char *)dentry->d_name.name;
 	fname->disk_name.len = dentry->d_name.len;
+
+	fscrypt_prepare_dentry(dentry, false);
+
 	return 0;
 }
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index de292a007138..e2a916cf29c4 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -353,6 +353,15 @@ static inline bool gfp_has_io_fs(gfp_t gfp)
 	return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
 }
 
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+	return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
 extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_CONTIG_ALLOC
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 9a5c6c76e653..7f75c9a51874 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -819,6 +819,24 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc)
+{
+	WARN_ON(1);
+	return ERR_PTR(-ENODEV);
+}
+
+static inline int gpio_device_get_base(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return -ENODEV;
+}
+
+static inline const char *gpio_device_get_label(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return NULL;
+}
+
 static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
 				       unsigned int offset)
 {
diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index 840cd254172d..7118ac28d468 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -77,17 +77,6 @@ enum hid_bpf_attach_flags {
 int hid_bpf_device_event(struct hid_bpf_ctx *ctx);
 int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx);
 
-/* Following functions are kfunc that we export to BPF programs */
-/* available everywhere in HID-BPF */
-__u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t __sz);
-
-/* only available in syscall */
-int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags);
-int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
-		       enum hid_report_type rtype, enum hid_class_request reqtype);
-struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id);
-void hid_bpf_release_context(struct hid_bpf_ctx *ctx);
-
 /*
  * Below is HID internal
  */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 87e3bedf8eb0..aa1e65ccb615 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -18,12 +18,8 @@
 #include <linux/list.h>
 #include <linux/percpu-defs.h>
 #include <linux/rbtree.h>
-#include <linux/seqlock.h>
 #include <linux/timer.h>
 
-struct hrtimer_clock_base;
-struct hrtimer_cpu_base;
-
 /*
  * Mode arguments of xxx_hrtimer functions:
  *
@@ -98,105 +94,6 @@ struct hrtimer_sleeper {
 	struct task_struct *task;
 };
 
-#ifdef CONFIG_64BIT
-# define __hrtimer_clock_base_align	____cacheline_aligned
-#else
-# define __hrtimer_clock_base_align
-#endif
-
-/**
- * struct hrtimer_clock_base - the timer base for a specific clock
- * @cpu_base:		per cpu clock base
- * @index:		clock type index for per_cpu support when moving a
- *			timer to a base on another cpu.
- * @clockid:		clock id for per_cpu support
- * @seq:		seqcount around __run_hrtimer
- * @running:		pointer to the currently running hrtimer
- * @active:		red black tree root node for the active timers
- * @get_time:		function to retrieve the current time of the clock
- * @offset:		offset of this clock to the monotonic base
- */
-struct hrtimer_clock_base {
-	struct hrtimer_cpu_base	*cpu_base;
-	unsigned int		index;
-	clockid_t		clockid;
-	seqcount_raw_spinlock_t	seq;
-	struct hrtimer		*running;
-	struct timerqueue_head	active;
-	ktime_t			(*get_time)(void);
-	ktime_t			offset;
-} __hrtimer_clock_base_align;
-
-enum  hrtimer_base_type {
-	HRTIMER_BASE_MONOTONIC,
-	HRTIMER_BASE_REALTIME,
-	HRTIMER_BASE_BOOTTIME,
-	HRTIMER_BASE_TAI,
-	HRTIMER_BASE_MONOTONIC_SOFT,
-	HRTIMER_BASE_REALTIME_SOFT,
-	HRTIMER_BASE_BOOTTIME_SOFT,
-	HRTIMER_BASE_TAI_SOFT,
-	HRTIMER_MAX_CLOCK_BASES,
-};
-
-/**
- * struct hrtimer_cpu_base - the per cpu clock bases
- * @lock:		lock protecting the base and associated clock bases
- *			and timers
- * @cpu:		cpu number
- * @active_bases:	Bitfield to mark bases with active timers
- * @clock_was_set_seq:	Sequence counter of clock was set events
- * @hres_active:	State of high resolution mode
- * @in_hrtirq:		hrtimer_interrupt() is currently executing
- * @hang_detected:	The last hrtimer interrupt detected a hang
- * @softirq_activated:	displays, if the softirq is raised - update of softirq
- *			related settings is not required then.
- * @nr_events:		Total number of hrtimer interrupt events
- * @nr_retries:		Total number of hrtimer interrupt retries
- * @nr_hangs:		Total number of hrtimer interrupt hangs
- * @max_hang_time:	Maximum time spent in hrtimer_interrupt
- * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
- *			 expired
- * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
- *			callback to finish.
- * @expires_next:	absolute time of the next event, is required for remote
- *			hrtimer enqueue; it is the total first expiry time (hard
- *			and soft hrtimer are taken into account)
- * @next_timer:		Pointer to the first expiring timer
- * @softirq_expires_next: Time to check, if soft queues needs also to be expired
- * @softirq_next_timer: Pointer to the first expiring softirq based timer
- * @clock_base:		array of clock bases for this cpu
- *
- * Note: next_timer is just an optimization for __remove_hrtimer().
- *	 Do not dereference the pointer because it is not reliable on
- *	 cross cpu removals.
- */
-struct hrtimer_cpu_base {
-	raw_spinlock_t			lock;
-	unsigned int			cpu;
-	unsigned int			active_bases;
-	unsigned int			clock_was_set_seq;
-	unsigned int			hres_active		: 1,
-					in_hrtirq		: 1,
-					hang_detected		: 1,
-					softirq_activated       : 1;
-#ifdef CONFIG_HIGH_RES_TIMERS
-	unsigned int			nr_events;
-	unsigned short			nr_retries;
-	unsigned short			nr_hangs;
-	unsigned int			max_hang_time;
-#endif
-#ifdef CONFIG_PREEMPT_RT
-	spinlock_t			softirq_expiry_lock;
-	atomic_t			timer_waiters;
-#endif
-	ktime_t				expires_next;
-	struct hrtimer			*next_timer;
-	ktime_t				softirq_expires_next;
-	struct hrtimer			*softirq_next_timer;
-	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
-} ____cacheline_aligned;
-
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
 	timer->node.expires = time;
@@ -445,20 +342,12 @@ extern u64
 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
 
 /**
- * hrtimer_forward_now - forward the timer expiry so it expires after now
+ * hrtimer_forward_now() - forward the timer expiry so it expires after now
  * @timer:	hrtimer to forward
  * @interval:	the interval to forward
  *
- * Forward the timer expiry so it will expire after the current time
- * of the hrtimer clock base. Returns the number of overruns.
- *
- * Can be safely called from the callback function of @timer. If
- * called from other contexts @timer must neither be enqueued nor
- * running the callback and the caller needs to take care of
- * serialization.
- *
- * Note: This only updates the timer expiry value and does not requeue
- * the timer.
+ * It is a variant of hrtimer_forward(). The timer will expire after the current
+ * time of the hrtimer clock base. See hrtimer_forward() for details.
  */
 static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 				      ktime_t interval)
diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h
index 2d3e3c5fb946..c3b4b7ed7c16 100644
--- a/include/linux/hrtimer_defs.h
+++ b/include/linux/hrtimer_defs.h
@@ -3,6 +3,8 @@
 #define _LINUX_HRTIMER_DEFS_H
 
 #include <linux/ktime.h>
+#include <linux/timerqueue.h>
+#include <linux/seqlock.h>
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -24,4 +26,106 @@
 
 #endif
 
+#ifdef CONFIG_64BIT
+# define __hrtimer_clock_base_align	____cacheline_aligned
+#else
+# define __hrtimer_clock_base_align
+#endif
+
+/**
+ * struct hrtimer_clock_base - the timer base for a specific clock
+ * @cpu_base:		per cpu clock base
+ * @index:		clock type index for per_cpu support when moving a
+ *			timer to a base on another cpu.
+ * @clockid:		clock id for per_cpu support
+ * @seq:		seqcount around __run_hrtimer
+ * @running:		pointer to the currently running hrtimer
+ * @active:		red black tree root node for the active timers
+ * @get_time:		function to retrieve the current time of the clock
+ * @offset:		offset of this clock to the monotonic base
+ */
+struct hrtimer_clock_base {
+	struct hrtimer_cpu_base	*cpu_base;
+	unsigned int		index;
+	clockid_t		clockid;
+	seqcount_raw_spinlock_t	seq;
+	struct hrtimer		*running;
+	struct timerqueue_head	active;
+	ktime_t			(*get_time)(void);
+	ktime_t			offset;
+} __hrtimer_clock_base_align;
+
+enum  hrtimer_base_type {
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_BOOTTIME,
+	HRTIMER_BASE_TAI,
+	HRTIMER_BASE_MONOTONIC_SOFT,
+	HRTIMER_BASE_REALTIME_SOFT,
+	HRTIMER_BASE_BOOTTIME_SOFT,
+	HRTIMER_BASE_TAI_SOFT,
+	HRTIMER_MAX_CLOCK_BASES,
+};
+
+/**
+ * struct hrtimer_cpu_base - the per cpu clock bases
+ * @lock:		lock protecting the base and associated clock bases
+ *			and timers
+ * @cpu:		cpu number
+ * @active_bases:	Bitfield to mark bases with active timers
+ * @clock_was_set_seq:	Sequence counter of clock was set events
+ * @hres_active:	State of high resolution mode
+ * @in_hrtirq:		hrtimer_interrupt() is currently executing
+ * @hang_detected:	The last hrtimer interrupt detected a hang
+ * @softirq_activated:	displays, if the softirq is raised - update of softirq
+ *			related settings is not required then.
+ * @nr_events:		Total number of hrtimer interrupt events
+ * @nr_retries:		Total number of hrtimer interrupt retries
+ * @nr_hangs:		Total number of hrtimer interrupt hangs
+ * @max_hang_time:	Maximum time spent in hrtimer_interrupt
+ * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
+ *			 expired
+ * @online:		CPU is online from an hrtimers point of view
+ * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
+ *			callback to finish.
+ * @expires_next:	absolute time of the next event, is required for remote
+ *			hrtimer enqueue; it is the total first expiry time (hard
+ *			and soft hrtimer are taken into account)
+ * @next_timer:		Pointer to the first expiring timer
+ * @softirq_expires_next: Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer: Pointer to the first expiring softirq based timer
+ * @clock_base:		array of clock bases for this cpu
+ *
+ * Note: next_timer is just an optimization for __remove_hrtimer().
+ *	 Do not dereference the pointer because it is not reliable on
+ *	 cross cpu removals.
+ */
+struct hrtimer_cpu_base {
+	raw_spinlock_t			lock;
+	unsigned int			cpu;
+	unsigned int			active_bases;
+	unsigned int			clock_was_set_seq;
+	unsigned int			hres_active		: 1,
+					in_hrtirq		: 1,
+					hang_detected		: 1,
+					softirq_activated       : 1,
+					online			: 1;
+#ifdef CONFIG_HIGH_RES_TIMERS
+	unsigned int			nr_events;
+	unsigned short			nr_retries;
+	unsigned short			nr_hangs;
+	unsigned int			max_hang_time;
+#endif
+#ifdef CONFIG_PREEMPT_RT
+	spinlock_t			softirq_expiry_lock;
+	atomic_t			timer_waiters;
+#endif
+	ktime_t				expires_next;
+	struct hrtimer			*next_timer;
+	ktime_t				softirq_expires_next;
+	struct hrtimer			*softirq_next_timer;
+	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
+} ____cacheline_aligned;
+
+
 #endif
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2b00faf98017..6ef0557b4bff 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -164,8 +164,28 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+
+/*
+ * If the requested ring buffer size is at least 8 times the size of the
+ * header, steal space from the ring buffer for the header. Otherwise, add
+ * space for the header so that is doesn't take too much of the ring buffer
+ * space.
+ *
+ * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a
+ * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring
+ * buffer size (such as 128 Kbytes) and so end up making a nearly twice as
+ * large allocation that will be almost half wasted. As a contrasting example,
+ * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the
+ * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring.
+ * In this latter case, we must add 64 Kbytes for the header and not worry
+ * about what's wasted.
+ */
+#define VMBUS_HEADER_ADJ(payload_sz) \
+	((payload_sz) >=  8 * sizeof(struct hv_ring_buffer) ? \
+	0 : sizeof(struct hv_ring_buffer))
+
 /* Calculate the proper size of a ringbuffer, it must be page-aligned */
-#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \
 					       (payload_sz))
 
 struct hv_ring_buffer_info {
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 7852f6c9a714..719cf9cc6e1a 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -8,6 +8,8 @@
 #ifndef __AD_SIGMA_DELTA_H__
 #define __AD_SIGMA_DELTA_H__
 
+#include <linux/iio/iio.h>
+
 enum ad_sigma_delta_mode {
 	AD_SD_MODE_CONTINUOUS = 0,
 	AD_SD_MODE_SINGLE = 1,
@@ -99,7 +101,7 @@ struct ad_sigma_delta {
 	 * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
 	 * rounded to 16 bytes to take into account padding.
 	 */
-	uint8_t				tx_buf[4] ____cacheline_aligned;
+	uint8_t				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
 	uint8_t				rx_buf[16] __aligned(8);
 };
 
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 607c3a89a647..f9ae5cdd884f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -258,9 +258,9 @@ struct st_sensor_data {
 	bool hw_irq_trigger;
 	s64 hw_timestamp;
 
-	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
-
 	struct mutex odr_lock;
+
+	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
 
 #ifdef CONFIG_IIO_BUFFER
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index dc9ea299e088..8898966bc0f0 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -11,6 +11,7 @@
 
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
+#include <linux/iio/iio.h>
 #include <linux/iio/types.h>
 
 #define ADIS_WRITE_REG(reg) ((0x80 | (reg)))
@@ -131,7 +132,7 @@ struct adis {
 	unsigned long		irq_flag;
 	void			*buffer;
 
-	u8			tx[10] ____cacheline_aligned;
+	u8			tx[10] __aligned(IIO_DMA_MINALIGN);
 	u8			rx[4];
 };
 
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index adb83a42a6b9..35227d47cfc9 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_INDIRECT_CALL_WRAPPER_H
 #define _LINUX_INDIRECT_CALL_WRAPPER_H
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 
 /*
  * INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 854ad67a5f70..e24893625085 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -2,6 +2,7 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
 #include <linux/llist.h>
@@ -240,12 +241,14 @@ struct io_ring_ctx {
 		unsigned int		poll_activated: 1;
 		unsigned int		drain_disabled: 1;
 		unsigned int		compat: 1;
+		unsigned int		iowq_limits_set : 1;
 
 		struct task_struct	*submitter_task;
 		struct io_rings		*rings;
 		struct percpu_ref	refs;
 
 		enum task_work_notify_mode	notify_method;
+		unsigned			sq_thread_idle;
 	} ____cacheline_aligned_in_smp;
 
 	/* submission data */
@@ -274,10 +277,20 @@ struct io_ring_ctx {
 		 */
 		struct io_rsrc_node	*rsrc_node;
 		atomic_t		cancel_seq;
+
+		/*
+		 * ->iopoll_list is protected by the ctx->uring_lock for
+		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
+		 * For SQPOLL, only the single threaded io_sq_thread() will
+		 * manipulate the list, hence no extra locking is needed there.
+		 */
+		bool			poll_multi_queue;
+		struct io_wq_work_list	iopoll_list;
+
 		struct io_file_table	file_table;
+		struct io_mapped_ubuf	**user_bufs;
 		unsigned		nr_user_files;
 		unsigned		nr_user_bufs;
-		struct io_mapped_ubuf	**user_bufs;
 
 		struct io_submit_state	submit_state;
 
@@ -289,15 +302,6 @@ struct io_ring_ctx {
 		struct io_alloc_cache	netmsg_cache;
 
 		/*
-		 * ->iopoll_list is protected by the ctx->uring_lock for
-		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
-		 * For SQPOLL, only the single threaded io_sq_thread() will
-		 * manipulate the list, hence no extra locking is needed there.
-		 */
-		struct io_wq_work_list	iopoll_list;
-		bool			poll_multi_queue;
-
-		/*
 		 * Any cancelable uring_cmd is added to this list in
 		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()
 		 */
@@ -343,8 +347,8 @@ struct io_ring_ctx {
 	spinlock_t		completion_lock;
 
 	/* IRQ completion list, under ->completion_lock */
-	struct io_wq_work_list	locked_free_list;
 	unsigned int		locked_free_nr;
+	struct io_wq_work_list	locked_free_list;
 
 	struct list_head	io_buffers_comp;
 	struct list_head	cq_overflow_list;
@@ -366,9 +370,6 @@ struct io_ring_ctx {
 	unsigned int		file_alloc_start;
 	unsigned int		file_alloc_end;
 
-	struct xarray		personalities;
-	u32			pers_next;
-
 	struct list_head	io_buffers_cache;
 
 	/* deferred free list, protected by ->uring_lock */
@@ -389,6 +390,9 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
+	u32			pers_next;
+	struct xarray		personalities;
+
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
@@ -405,11 +409,22 @@ struct io_ring_ctx {
 
 	/* io-wq management, e.g. thread count */
 	u32				iowq_limits[2];
-	bool				iowq_limits_set;
 
 	struct callback_head		poll_wq_task_work;
 	struct list_head		defer_list;
-	unsigned			sq_thread_idle;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct list_head	napi_list;	/* track busy poll napi_id */
+	spinlock_t		napi_lock;	/* napi_list lock */
+
+	/* napi busy poll default timeout */
+	unsigned int		napi_busy_poll_to;
+	bool			napi_prefer_busy_poll;
+	bool			napi_enabled;
+
+	DECLARE_HASHTABLE(napi_ht, 4);
+#endif
+
 	/* protected by ->completion_lock */
 	unsigned			evfd_last_cq_tail;
 
@@ -455,7 +470,6 @@ enum {
 	REQ_F_SKIP_LINK_CQES_BIT,
 	REQ_F_SINGLE_POLL_BIT,
 	REQ_F_DOUBLE_POLL_BIT,
-	REQ_F_PARTIAL_IO_BIT,
 	REQ_F_APOLL_MULTISHOT_BIT,
 	REQ_F_CLEAR_POLLIN_BIT,
 	REQ_F_HASH_LOCKED_BIT,
@@ -463,75 +477,88 @@ enum {
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
 	REQ_F_POLL_NO_LAZY_BIT,
+	REQ_F_CANCEL_SEQ_BIT,
+	REQ_F_CAN_POLL_BIT,
+	REQ_F_BL_EMPTY_BIT,
+	REQ_F_BL_NO_RECYCLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
 };
 
+typedef u64 __bitwise io_req_flags_t;
+#define IO_REQ_FLAG(bitno)	((__force io_req_flags_t) BIT_ULL((bitno)))
+
 enum {
 	/* ctx owns file */
-	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	REQ_F_FIXED_FILE	= IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT),
 	/* drain existing IO first */
-	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	REQ_F_IO_DRAIN		= IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT),
 	/* linked sqes */
-	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	REQ_F_LINK		= IO_REQ_FLAG(REQ_F_LINK_BIT),
 	/* doesn't sever on completion < 0 */
-	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	REQ_F_HARDLINK		= IO_REQ_FLAG(REQ_F_HARDLINK_BIT),
 	/* IOSQE_ASYNC */
-	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+	REQ_F_FORCE_ASYNC	= IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT),
 	/* IOSQE_BUFFER_SELECT */
-	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
+	REQ_F_BUFFER_SELECT	= IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT),
 	/* IOSQE_CQE_SKIP_SUCCESS */
-	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),
+	REQ_F_CQE_SKIP		= IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT),
 
 	/* fail rest of links */
-	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
+	REQ_F_FAIL		= IO_REQ_FLAG(REQ_F_FAIL_BIT),
 	/* on inflight list, should be cancelled and waited on exit reliably */
-	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	REQ_F_INFLIGHT		= IO_REQ_FLAG(REQ_F_INFLIGHT_BIT),
 	/* read/write uses file position */
-	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	REQ_F_CUR_POS		= IO_REQ_FLAG(REQ_F_CUR_POS_BIT),
 	/* must not punt to workers */
-	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	REQ_F_NOWAIT		= IO_REQ_FLAG(REQ_F_NOWAIT_BIT),
 	/* has or had linked timeout */
-	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	REQ_F_LINK_TIMEOUT	= IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT),
 	/* needs cleanup */
-	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
+	REQ_F_NEED_CLEANUP	= IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT),
 	/* already went through poll handler */
-	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
+	REQ_F_POLLED		= IO_REQ_FLAG(REQ_F_POLLED_BIT),
 	/* buffer already selected */
-	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	REQ_F_BUFFER_SELECTED	= IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT),
 	/* buffer selected from ring, needs commit */
-	REQ_F_BUFFER_RING	= BIT(REQ_F_BUFFER_RING_BIT),
+	REQ_F_BUFFER_RING	= IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT),
 	/* caller should reissue async */
-	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
+	REQ_F_REISSUE		= IO_REQ_FLAG(REQ_F_REISSUE_BIT),
 	/* supports async reads/writes */
-	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
+	REQ_F_SUPPORT_NOWAIT	= IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT),
 	/* regular file */
-	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	REQ_F_ISREG		= IO_REQ_FLAG(REQ_F_ISREG_BIT),
 	/* has creds assigned */
-	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
+	REQ_F_CREDS		= IO_REQ_FLAG(REQ_F_CREDS_BIT),
 	/* skip refcounting if not set */
-	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
+	REQ_F_REFCOUNT		= IO_REQ_FLAG(REQ_F_REFCOUNT_BIT),
 	/* there is a linked timeout that has to be armed */
-	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
+	REQ_F_ARM_LTIMEOUT	= IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT),
 	/* ->async_data allocated */
-	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
+	REQ_F_ASYNC_DATA	= IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT),
 	/* don't post CQEs while failing linked requests */
-	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
+	REQ_F_SKIP_LINK_CQES	= IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT),
 	/* single poll may be active */
-	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
+	REQ_F_SINGLE_POLL	= IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT),
 	/* double poll may active */
-	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
-	/* request has already done partial IO */
-	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
+	REQ_F_DOUBLE_POLL	= IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT),
 	/* fast poll multishot mode */
-	REQ_F_APOLL_MULTISHOT	= BIT(REQ_F_APOLL_MULTISHOT_BIT),
+	REQ_F_APOLL_MULTISHOT	= IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT),
 	/* recvmsg special flag, clear EPOLLIN */
-	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
+	REQ_F_CLEAR_POLLIN	= IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
-	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	REQ_F_HASH_LOCKED	= IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
 	/* don't use lazy poll wake for this request */
-	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
+	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
+	/* cancel sequence is set and valid */
+	REQ_F_CANCEL_SEQ	= IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
+	/* file is pollable */
+	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
+	/* buffer list was empty after selection of buffer */
+	REQ_F_BL_EMPTY		= IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
+	/* don't recycle provided buffers for this request */
+	REQ_F_BL_NO_RECYCLE	= IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -592,15 +619,17 @@ struct io_kiocb {
 	 * and after selection it points to the buffer ID itself.
 	 */
 	u16				buf_index;
-	unsigned int			flags;
+
+	unsigned			nr_tw;
+
+	/* REQ_F_* flags */
+	io_req_flags_t			flags;
 
 	struct io_cqe			cqe;
 
 	struct io_ring_ctx		*ctx;
 	struct task_struct		*task;
 
-	struct io_rsrc_node		*rsrc_node;
-
 	union {
 		/* store used ubuf, so we can prevent reloading */
 		struct io_mapped_ubuf	*imu;
@@ -621,10 +650,12 @@ struct io_kiocb {
 		/* cache ->apoll->events */
 		__poll_t apoll_events;
 	};
+
+	struct io_rsrc_node		*rsrc_node;
+
 	atomic_t			refs;
 	atomic_t			poll_refs;
 	struct io_task_work		io_task_work;
-	unsigned			nr_tw;
 	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
 	struct hlist_node		hash_node;
 	/* internal polling, see IORING_FEAT_FAST_POLL */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 96dd0acbba44..6fc1c858013d 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -293,22 +293,32 @@ struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
 	u16			io_type;
 	u16			io_flags;	/* IOMAP_F_* */
-	u32			io_folios;	/* folios added to ioend */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
-	struct bio		*io_bio;	/* bio being built */
-	struct bio		io_inline_bio;	/* MUST BE LAST! */
+	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
+static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
+{
+	return container_of(bio, struct iomap_ioend, io_bio);
+}
+
 struct iomap_writeback_ops {
 	/*
 	 * Required, maps the blocks so that writeback can be performed on
 	 * the range starting at offset.
+	 *
+	 * Can return arbitrarily large regions, but we need to call into it at
+	 * least once per folio to allow the file systems to synchronize with
+	 * the write path that could be invalidating mappings.
+	 *
+	 * An existing mapping from a previous call to this method can be reused
+	 * by the file system if it is still valid.
 	 */
 	int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
-				loff_t offset);
+			  loff_t offset, unsigned len);
 
 	/*
 	 * Optional, allows the file systems to perform actions just before
@@ -329,6 +339,7 @@ struct iomap_writepage_ctx {
 	struct iomap		iomap;
 	struct iomap_ioend	*ioend;
 	const struct iomap_writeback_ops *ops;
+	u32			nr_folios;	/* folios added to the ioend */
 };
 
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 1ea2a820e1eb..5e27cb3a3be9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -892,11 +892,14 @@ struct iommu_fwspec {
 struct iommu_sva {
 	struct device			*dev;
 	struct iommu_domain		*domain;
+	struct list_head		handle_item;
+	refcount_t			users;
 };
 
 struct iommu_mm_data {
 	u32			pasid;
 	struct list_head	sva_domains;
+	struct list_head	sva_handles;
 };
 
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 90081afa10ce..97baa937ab5b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -179,7 +179,7 @@ struct irq_common_data {
 struct irq_data {
 	u32			mask;
 	unsigned int		irq;
-	unsigned long		hwirq;
+	irq_hw_number_t		hwirq;
 	struct irq_common_data	*common;
 	struct irq_chip		*chip;
 	struct irq_domain	*domain;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index ee0a82c60508..21ecf582a0fe 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -619,6 +619,23 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain)
 
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
+#ifdef CONFIG_GENERIC_MSI_IRQ
+int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+				  unsigned int type);
+void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq);
+#else
+static inline int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+						unsigned int type)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
 #else /* CONFIG_IRQ_DOMAIN */
 static inline void irq_dispose_mapping(unsigned int virq) { }
 static inline struct irq_domain *irq_find_matching_fwnode(
diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h
index c29921fd8cd1..5c1fe6f1fcde 100644
--- a/include/linux/irqdomain_defs.h
+++ b/include/linux/irqdomain_defs.h
@@ -26,6 +26,8 @@ enum irq_domain_bus_token {
 	DOMAIN_BUS_DMAR,
 	DOMAIN_BUS_AMDVI,
 	DOMAIN_BUS_PCI_DEVICE_IMS,
+	DOMAIN_BUS_DEVICE_MSI,
+	DOMAIN_BUS_WIRED_TO_MSI,
 };
 
 #endif /* _LINUX_IRQDOMAIN_DEFS_H */
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
index c30f454a9518..72dd1eb3a0e7 100644
--- a/include/linux/irqhandler.h
+++ b/include/linux/irqhandler.h
@@ -8,7 +8,7 @@
  */
 
 struct irq_desc;
-struct irq_data;
+
 typedef	void (*irq_flow_handler_t)(struct irq_desc *desc);
 
 #endif
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index e0ae2a43e0eb..d9f1435a5a13 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -102,12 +102,15 @@ static inline u64 get_jiffies_64(void)
 }
 #endif
 
-/*
- *	These inlines deal with timer wrapping correctly. You are
- *	strongly encouraged to use them:
- *	1. Because people otherwise forget
- *	2. Because if the timer wrap changes in future you won't have to
- *	   alter your driver code.
+/**
+ * DOC: General information about time_* inlines
+ *
+ * These inlines deal with timer wrapping correctly. You are strongly encouraged
+ * to use them:
+ *
+ * #. Because people otherwise forget
+ * #. Because if the timer wrap changes in future you won't have to alter your
+ *    driver code.
  */
 
 /**
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7e7fd25b09b3..179df96b20f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2031,6 +2031,32 @@ static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 		return 1;
 	return 0;
 }
+
+/*
+ * This lockless version of the range-based retry check *must* be paired with a
+ * call to the locked version after acquiring mmu_lock, i.e. this is safe to
+ * use only as a pre-check to avoid contending mmu_lock.  This version *will*
+ * get false negatives and false positives.
+ */
+static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
+						   unsigned long mmu_seq,
+						   gfn_t gfn)
+{
+	/*
+	 * Use READ_ONCE() to ensure the in-progress flag and sequence counter
+	 * are always read from memory, e.g. so that checking for retry in a
+	 * loop won't result in an infinite retry loop.  Don't force loads for
+	 * start+end, as the key to avoiding infinite retry loops is observing
+	 * the 1=>0 transition of in-progress, i.e. getting false negatives
+	 * due to stale start+end values is acceptable.
+	 */
+	if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
+	    gfn >= kvm->mmu_invalidate_range_start &&
+	    gfn < kvm->mmu_invalidate_range_end)
+		return true;
+
+	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 9f565416d186..1b95fe31051f 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -375,12 +375,12 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
 static inline int nlm_compare_locks(const struct file_lock *fl1,
 				    const struct file_lock *fl2)
 {
-	return file_inode(fl1->fl_file) == file_inode(fl2->fl_file)
-	     && fl1->fl_pid   == fl2->fl_pid
-	     && fl1->fl_owner == fl2->fl_owner
+	return file_inode(fl1->c.flc_file) == file_inode(fl2->c.flc_file)
+	     && fl1->c.flc_pid   == fl2->c.flc_pid
+	     && fl1->c.flc_owner == fl2->c.flc_owner
 	     && fl1->fl_start == fl2->fl_start
 	     && fl1->fl_end   == fl2->fl_end
-	     &&(fl1->fl_type  == fl2->fl_type || fl2->fl_type == F_UNLCK);
+	     &&(fl1->c.flc_type  == fl2->c.flc_type || fl2->c.flc_type == F_UNLCK);
 }
 
 extern const struct lock_manager_operations nlmsvc_lock_operations;
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index b60fbcd8cdfa..80cca9426761 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -52,7 +52,7 @@ struct nlm_lock {
  *	FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to
  *	32 bytes.
  */
- 
+
 struct nlm_cookie
 {
 	unsigned char data[NLM_MAXCOOKIELEN];
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 185924c56378..76458b6d53da 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -315,9 +315,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how)
 LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb)
-LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock,
 	 sockptr_t optval, sockptr_t optlen, unsigned int len)
-LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock,
 	 struct sk_buff *skb, u32 *secid)
 LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority)
 LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk)
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index b3d63123b945..a53ad4dabd7e 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -171,6 +171,7 @@ enum maple_type {
 #define MT_FLAGS_LOCK_IRQ	0x100
 #define MT_FLAGS_LOCK_BH	0x200
 #define MT_FLAGS_LOCK_EXTERN	0x300
+#define MT_FLAGS_ALLOC_WRAPPED	0x0800
 
 #define MAPLE_HEIGHT_MAX	31
 
@@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first,
 int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
@@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
 void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 
 bool mas_nomem(struct ma_state *mas, gfp_t gfp);
 void mas_pause(struct ma_state *mas);
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b695f9e946da..e2082240586d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -121,6 +121,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
 #endif
 void memblock_trim_memory(phys_addr_t align);
+unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				     phys_addr_t base2, phys_addr_t size2);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
 bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c726f90ab752..486b7492050c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         sw_r_roce_src_udp_port[0x1];
 	u8         fl_rc_qp_when_roce_disabled[0x1];
 	u8         fl_rc_qp_when_roce_enabled[0x1];
-	u8         reserved_at_7[0x1];
+	u8         roce_cc_general[0x1];
 	u8	   qp_ooo_transmit_default[0x1];
 	u8         reserved_at_9[0x15];
 	u8	   qp_ts_format[0x2];
@@ -10261,7 +10261,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 
 	u8         regs_63_to_46[0x12];
 	u8         mrtc[0x1];
-	u8         regs_44_to_32[0xd];
+	u8         regs_44_to_41[0x4];
+	u8         mfrl[0x1];
+	u8         regs_39_to_32[0x8];
 
 	u8         regs_31_to_10[0x16];
 	u8         mtmp[0x1];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index bd53cf4be7bd..f0e55bf3ec8b 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg {
 	union {
 		struct {
 			__be16 sz;
-			u8     start[2];
+			union {
+				u8     start[2];
+				DECLARE_FLEX_ARRAY(u8, data);
+			};
 		} inline_hdr;
 		struct {
 			__be16 type;
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 40d94411d492..dc7048824be8 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -156,6 +156,7 @@ calc_vm_flag_bits(unsigned long flags)
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
+	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
 	       arch_calc_vm_flag_bits(flags);
 }
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4ed33b127821..a497f189d988 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2013,9 +2013,9 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	rcu_read_lock();
+	rcu_read_lock_sched();
 	if (!valid_section(ms)) {
-		rcu_read_unlock();
+		rcu_read_unlock_sched();
 		return 0;
 	}
 	/*
@@ -2023,7 +2023,7 @@ static inline int pfn_valid(unsigned long pfn)
 	 * the entire section-sized span.
 	 */
 	ret = early_section(ms) || pfn_section_valid(ms, pfn);
-	rcu_read_unlock();
+	rcu_read_unlock_sched();
 
 	return ret;
 }
diff --git a/include/linux/module.h b/include/linux/module.h
index 96bc462872c0..1153b0d99a80 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -885,7 +885,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr,
 static inline void module_bug_cleanup(struct module *mod) {}
 #endif	/* CONFIG_GENERIC_BUG */
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 extern bool retpoline_module_ok(bool has_retpoline);
 #else
 static inline bool retpoline_module_ok(bool has_retpoline)
diff --git a/include/linux/msi.h b/include/linux/msi.h
index ddace8c34dcf..26d07e23052e 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -412,6 +412,7 @@ bool arch_restore_msi_irqs(struct pci_dev *dev);
 struct irq_domain;
 struct irq_domain_ops;
 struct irq_chip;
+struct irq_fwspec;
 struct device_node;
 struct fwnode_handle;
 struct msi_domain_info;
@@ -431,6 +432,8 @@ struct msi_domain_info;
  *			function.
  * @msi_post_free:	Optional function which is invoked after freeing
  *			all interrupts.
+ * @msi_translate:	Optional translate callback to support the odd wire to
+ *			MSI bridges, e.g. MBIGEN
  *
  * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying
  * irqdomain.
@@ -468,6 +471,8 @@ struct msi_domain_ops {
 					    struct device *dev);
 	void		(*msi_post_free)(struct irq_domain *domain,
 					 struct device *dev);
+	int		(*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec,
+					 irq_hw_number_t *hwirq, unsigned int *type);
 };
 
 /**
@@ -547,6 +552,10 @@ enum {
 	MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS	= (1 << 5),
 	/* Free MSI descriptors */
 	MSI_FLAG_FREE_MSI_DESCS		= (1 << 6),
+	/* Use dev->fwnode for MSI device domain creation */
+	MSI_FLAG_USE_DEV_FWNODE		= (1 << 7),
+	/* Set parent->dev into domain->pm_dev on device domain creation */
+	MSI_FLAG_PARENT_PM_DEV		= (1 << 8),
 
 	/* Mask for the generic functionality */
 	MSI_GENERIC_FLAGS_MASK		= GENMASK(15, 0),
@@ -572,6 +581,11 @@ enum {
  * struct msi_parent_ops - MSI parent domain callbacks and configuration info
  *
  * @supported_flags:	Required: The supported MSI flags of the parent domain
+ * @required_flags:	Optional: The required MSI flags of the parent MSI domain
+ * @bus_select_token:	Optional: The bus token of the real parent domain for
+ *			irq_domain::select()
+ * @bus_select_mask:	Optional: A mask of supported BUS_DOMAINs for
+ *			irq_domain::select()
  * @prefix:		Optional: Prefix for the domain and chip name
  * @init_dev_msi_info:	Required: Callback for MSI parent domains to setup parent
  *			domain specific domain flags, domain ops and interrupt chip
@@ -579,6 +593,9 @@ enum {
  */
 struct msi_parent_ops {
 	u32		supported_flags;
+	u32		required_flags;
+	u32		bus_select_token;
+	u32		bus_select_mask;
 	const char	*prefix;
 	bool		(*init_dev_msi_info)(struct device *dev, struct irq_domain *domain,
 					     struct irq_domain *msi_parent_domain,
@@ -627,9 +644,6 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
 						  struct msi_domain_info *info,
 						  struct irq_domain *parent);
-int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
-				   irq_write_msi_msg_t write_msi_msg);
-void platform_msi_domain_free_irqs(struct device *dev);
 
 /* When an MSI domain is used as an intermediate domain */
 int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
@@ -656,6 +670,10 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir
 void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq,
 				     unsigned int nvec);
 void *platform_msi_get_host_data(struct irq_domain *domain);
+/* Per device platform MSI */
+int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec,
+					    irq_write_msi_msg_t write_msi_msg);
+void platform_device_msi_free_irqs_all(struct device *dev);
 
 bool msi_device_has_isolated_msi(struct device *dev);
 #else /* CONFIG_GENERIC_MSI_IRQ */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 7e208d46ba5b..67edc4ca2bee 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -32,11 +32,9 @@
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)
 #endif
 
-#ifndef CONFIG_PREEMPT_RT
-
 #ifdef CONFIG_DEBUG_MUTEXES
 
-#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
+# define __DEBUG_MUTEX_INITIALIZER(lockname)				\
 	, .magic = &lockname
 
 extern void mutex_destroy(struct mutex *lock);
@@ -49,6 +47,7 @@ static inline void mutex_destroy(struct mutex *lock) {}
 
 #endif
 
+#ifndef CONFIG_PREEMPT_RT
 /**
  * mutex_init - initialize the mutex
  * @mutex: the mutex to be initialized
@@ -101,9 +100,6 @@ extern bool mutex_is_locked(struct mutex *lock);
 
 extern void __mutex_rt_init(struct mutex *lock, const char *name,
 			    struct lock_class_key *key);
-extern int mutex_trylock(struct mutex *lock);
-
-static inline void mutex_destroy(struct mutex *lock) { }
 
 #define mutex_is_locked(l)	rt_mutex_base_is_locked(&(l)->rtmutex)
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 118c40258d07..78a09af89e39 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -79,8 +79,6 @@ struct xdp_buff;
 struct xdp_frame;
 struct xdp_metadata_ops;
 struct xdp_md;
-/* DPLL specific */
-struct dpll_pin;
 
 typedef u32 xdp_features_t;
 
@@ -2141,6 +2139,11 @@ struct net_device {
 
 	/* TXRX read-mostly hotpath */
 	__cacheline_group_begin(net_device_read_txrx);
+	union {
+		struct pcpu_lstats __percpu		*lstats;
+		struct pcpu_sw_netstats __percpu	*tstats;
+		struct pcpu_dstats __percpu		*dstats;
+	};
 	unsigned int		flags;
 	unsigned short		hard_header_len;
 	netdev_features_t	features;
@@ -2395,11 +2398,6 @@ struct net_device {
 	enum netdev_ml_priv_type	ml_priv_type;
 
 	enum netdev_stat_type		pcpu_stat_type:8;
-	union {
-		struct pcpu_lstats __percpu		*lstats;
-		struct pcpu_sw_netstats __percpu	*tstats;
-		struct pcpu_dstats __percpu		*dstats;
-	};
 
 #if IS_ENABLED(CONFIG_GARP)
 	struct garp_port __rcu	*garp_port;
@@ -2469,7 +2467,7 @@ struct net_device {
 	struct devlink_port	*devlink_port;
 
 #if IS_ENABLED(CONFIG_DPLL)
-	struct dpll_pin		*dpll_pin;
+	struct dpll_pin	__rcu	*dpll_pin;
 #endif
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 	/** @page_pools: page pools created for this netdevice */
@@ -3499,6 +3497,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue
 #endif
 }
 
+static inline int netdev_queue_dql_avail(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+	/* Non-BQL migrated drivers will return 0, too. */
+	return dql_avail(&txq->dql);
+#else
+	return 0;
+#endif
+}
+
 /**
  *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
  *	@dev_queue: pointer to transmit queue
@@ -4032,17 +4040,6 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
-void netdev_dpll_pin_clear(struct net_device *dev);
-
-static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_DPLL)
-	return dev->dpll_pin;
-#else
-	return NULL;
-#endif
-}
 
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 80900d910992..ce660d51549b 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -474,6 +474,7 @@ struct nf_ct_hook {
 			      const struct sk_buff *);
 	void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
 	void (*set_closing)(struct nf_conntrack *nfct);
+	int (*confirm)(struct sk_buff *skb);
 };
 extern const struct nf_ct_hook __rcu *nf_ct_hook;
 
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index e8c350a3ade1..e9f4f845d760 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -186,6 +186,8 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Cancel ongoing garbage collectors before destroying the set*/
+	void (*cancel_gc)(struct ip_set *set);
 	/* Region-locking is used */
 	bool region_lock;
 };
@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type);
 
 /* A generic IP set */
 struct ip_set {
+	/* For call_cru in destroy */
+	struct rcu_head rcu;
 	/* The name of the set */
 	char name[IPSET_MAXNAMELEN];
 	/* Lock protecting the set data */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index cd797e00fe35..92de074e63b9 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -124,6 +124,7 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	struct net		*cl_net;
 	struct list_head	pending_cb_stateids;
+	struct rcu_head		rcu;
 };
 
 /*
@@ -265,6 +266,7 @@ struct nfs_server {
 	const struct cred	*cred;
 	bool			has_sec_mnt_opts;
 	struct kobject		kobj;
+	struct rcu_head		rcu;
 };
 
 /* Server capabilities */
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 0f1d024bd958..7d22ea50b098 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -7,7 +7,7 @@
 struct proc_ns_operations;
 
 struct ns_common {
-	atomic_long_t stashed;
+	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
 	refcount_t count;
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6fe92fb..eb2f04d636c8 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,7 +6,11 @@
 #ifndef _LINUX_NVME_RDMA_H
 #define _LINUX_NVME_RDMA_H
 
-#define NVME_RDMA_MAX_QUEUE_SIZE	128
+#define NVME_RDMA_IP_PORT		4420
+
+#define NVME_RDMA_MAX_QUEUE_SIZE 256
+#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128
+#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128
 
 enum nvme_rdma_cm_fmt {
 	NVME_RDMA_CM_FMT_1_0 = 0x0,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 462c21e0e417..425573202295 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -23,8 +23,6 @@
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-#define NVME_RDMA_IP_PORT	4420
-
 #define NVME_NSID_ALL		0xffffffff
 
 enum nvme_subsys_type {
@@ -646,6 +644,7 @@ enum {
 	NVME_CMD_EFFECTS_NCC		= 1 << 2,
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
+	NVME_CMD_EFFECTS_CSER_MASK	= GENMASK(15, 14),
 	NVME_CMD_EFFECTS_CSE_MASK	= GENMASK(18, 16),
 	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
 	NVME_CMD_EFFECTS_SCOPE_MASK	= GENMASK(31, 20),
@@ -816,12 +815,6 @@ struct nvme_reservation_status_ext {
 	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
-enum nvme_async_event_type {
-	NVME_AER_TYPE_ERROR	= 0,
-	NVME_AER_TYPE_SMART	= 1,
-	NVME_AER_TYPE_NOTICE	= 2,
-};
-
 /* I/O commands */
 
 enum nvme_opcode {
@@ -1818,7 +1811,7 @@ struct nvme_command {
 	};
 };
 
-static inline bool nvme_is_fabrics(struct nvme_command *cmd)
+static inline bool nvme_is_fabrics(const struct nvme_command *cmd)
 {
 	return cmd->common.opcode == nvme_fabrics_command;
 }
@@ -1837,7 +1830,7 @@ struct nvme_error_slot {
 	__u8		resv2[24];
 };
 
-static inline bool nvme_is_write(struct nvme_command *cmd)
+static inline bool nvme_is_write(const struct nvme_command *cmd)
 {
 	/*
 	 * What a mess...
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 33212e93f4a6..b3b8d3dab52d 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -131,7 +131,7 @@
  */
 .macro VALIDATE_UNRET_BEGIN
 #if defined(CONFIG_NOINSTR_VALIDATION) && \
-	(defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO))
+	(defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO))
 .Lhere_\@:
 	.pushsection .discard.validate_unret
 	.long	.Lhere_\@ - .
diff --git a/include/linux/pci.h b/include/linux/pci.h
index add9368e6314..7ab0d13672da 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1422,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
 int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state);
 int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
+int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state);
 pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
 void pci_pme_active(struct pci_dev *dev, bool enable);
@@ -1625,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
 
 void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
 		  void *userdata);
+void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
+			 void *userdata);
 int pci_cfg_space_size(struct pci_dev *dev);
 unsigned char pci_bus_max_busnr(struct pci_bus *bus);
 void pci_setup_bridge(struct pci_bus *bus);
@@ -2025,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; }
 static inline void pci_restore_state(struct pci_dev *dev) { }
 static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 { return 0; }
+static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state)
+{ return 0; }
 static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable)
 { return 0; }
 static inline pci_power_t pci_choose_state(struct pci_dev *dev,
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 395cacce1179..c79a0efd0258 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -55,6 +55,10 @@ struct pid
 	refcount_t count;
 	unsigned int level;
 	spinlock_t lock;
+#ifdef CONFIG_FS_PID
+	struct dentry *stashed;
+	unsigned long ino;
+#endif
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
 	struct hlist_head inodes;
@@ -66,15 +70,13 @@ struct pid
 
 extern struct pid init_struct_pid;
 
-extern const struct file_operations pidfd_fops;
-
 struct file;
 
-extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_pid(const struct file *file);
 struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
 struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags);
-int pidfd_create(struct pid *pid, unsigned int flags);
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret);
+void do_notify_pidfd(struct task_struct *task);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
new file mode 100644
index 000000000000..40dd325a32a6
--- /dev/null
+++ b/include/linux/pidfs.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PID_FS_H
+#define _LINUX_PID_FS_H
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
+void __init pidfs_init(void);
+bool is_pidfs_sb(const struct super_block *sb);
+
+#endif /* _LINUX_PID_FS_H */
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 79594aeb160d..2f1b952d596a 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -154,9 +154,9 @@ struct packet_stacked_data
 
 struct pktcdvd_device
 {
-	struct bdev_handle	*bdev_handle;	/* dev attached */
+	struct file		*bdev_file;	/* dev attached */
 	/* handle acquired for bdev during pkt_open_dev() */
-	struct bdev_handle	*open_bdev_handle;
+	struct file		*f_open_bdev;
 	dev_t			pkt_dev;	/* our dev */
 	struct packet_settings	settings;
 	struct packet_stats	stats;
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 27a7dad17eef..1f0ee2459f2a 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -92,4 +92,7 @@
 /********** VFS **********/
 #define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA))
 
+/********** lib/stackdepot.c **********/
+#define STACK_DEPOT_POISON ((void *)(0xD390 + POISON_POINTER_DELTA))
+
 #endif
diff --git a/include/linux/poll.h b/include/linux/poll.h
index a9e0e1c2d1f2..d1ea4f3714a8 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -14,11 +14,7 @@
 
 /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
    additional memory. */
-#ifdef __clang__
-#define MAX_STACK_ALLOC 768
-#else
 #define MAX_STACK_ALLOC 832
-#endif
 #define FRONTEND_STACK_ALLOC	256
 #define SELECT_STACK_ALLOC	FRONTEND_STACK_ALLOC
 #define POLL_STACK_ALLOC	FRONTEND_STACK_ALLOC
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index de407e7c3b55..0b2a89854440 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -65,6 +65,7 @@ struct proc_fs_info {
 	kgid_t pid_gid;
 	enum proc_hidepid hide_pid;
 	enum proc_pidonly pidonly;
+	struct rcu_head rcu;
 };
 
 static inline struct proc_fs_info *proc_sb_info(struct super_block *sb)
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 49539bc416ce..5ea470eb4d76 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -66,7 +66,7 @@ static inline void proc_free_inum(unsigned int inum) {}
 
 static inline int ns_alloc_inum(struct ns_common *ns)
 {
-	atomic_long_set(&ns->stashed, 0);
+	WRITE_ONCE(ns->stashed, NULL);
 	return proc_alloc_inum(&ns->inum);
 }
 
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 7fd17e82bab4..3705c2044fc0 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -78,6 +78,36 @@ enum sev_cmd {
 	SEV_CMD_DBG_DECRYPT		= 0x060,
 	SEV_CMD_DBG_ENCRYPT		= 0x061,
 
+	/* SNP specific commands */
+	SEV_CMD_SNP_INIT		= 0x081,
+	SEV_CMD_SNP_SHUTDOWN		= 0x082,
+	SEV_CMD_SNP_PLATFORM_STATUS	= 0x083,
+	SEV_CMD_SNP_DF_FLUSH		= 0x084,
+	SEV_CMD_SNP_INIT_EX		= 0x085,
+	SEV_CMD_SNP_SHUTDOWN_EX		= 0x086,
+	SEV_CMD_SNP_DECOMMISSION	= 0x090,
+	SEV_CMD_SNP_ACTIVATE		= 0x091,
+	SEV_CMD_SNP_GUEST_STATUS	= 0x092,
+	SEV_CMD_SNP_GCTX_CREATE		= 0x093,
+	SEV_CMD_SNP_GUEST_REQUEST	= 0x094,
+	SEV_CMD_SNP_ACTIVATE_EX		= 0x095,
+	SEV_CMD_SNP_LAUNCH_START	= 0x0A0,
+	SEV_CMD_SNP_LAUNCH_UPDATE	= 0x0A1,
+	SEV_CMD_SNP_LAUNCH_FINISH	= 0x0A2,
+	SEV_CMD_SNP_DBG_DECRYPT		= 0x0B0,
+	SEV_CMD_SNP_DBG_ENCRYPT		= 0x0B1,
+	SEV_CMD_SNP_PAGE_SWAP_OUT	= 0x0C0,
+	SEV_CMD_SNP_PAGE_SWAP_IN	= 0x0C1,
+	SEV_CMD_SNP_PAGE_MOVE		= 0x0C2,
+	SEV_CMD_SNP_PAGE_MD_INIT	= 0x0C3,
+	SEV_CMD_SNP_PAGE_SET_STATE	= 0x0C6,
+	SEV_CMD_SNP_PAGE_RECLAIM	= 0x0C7,
+	SEV_CMD_SNP_PAGE_UNSMASH	= 0x0C8,
+	SEV_CMD_SNP_CONFIG		= 0x0C9,
+	SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX = 0x0CA,
+	SEV_CMD_SNP_COMMIT		= 0x0CB,
+	SEV_CMD_SNP_VLEK_LOAD		= 0x0CD,
+
 	SEV_CMD_MAX,
 };
 
@@ -523,12 +553,269 @@ struct sev_data_attestation_report {
 	u32 len;				/* In/Out */
 } __packed;
 
+/**
+ * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params
+ *
+ * @address: physical address of firmware image
+ * @len: length of the firmware image
+ */
+struct sev_data_snp_download_firmware {
+	u64 address;				/* In */
+	u32 len;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_activate - SNP_ACTIVATE command params
+ *
+ * @gctx_paddr: system physical address guest context page
+ * @asid: ASID to bind to the guest
+ */
+struct sev_data_snp_activate {
+	u64 gctx_paddr;				/* In */
+	u32 asid;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_addr - generic SNP command params
+ *
+ * @address: physical address of generic data param
+ */
+struct sev_data_snp_addr {
+	u64 address;				/* In/Out */
+} __packed;
+
+/**
+ * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @policy: guest policy
+ * @ma_gctx_paddr: system physical address of migration agent
+ * @ma_en: the guest is associated with a migration agent
+ * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the
+ *          purpose of guest-assisted migration.
+ * @rsvd: reserved
+ * @gosvw: guest OS-visible workarounds, as defined by hypervisor
+ */
+struct sev_data_snp_launch_start {
+	u64 gctx_paddr;				/* In */
+	u64 policy;				/* In */
+	u64 ma_gctx_paddr;			/* In */
+	u32 ma_en:1;				/* In */
+	u32 imi_en:1;				/* In */
+	u32 rsvd:30;
+	u8 gosvw[16];				/* In */
+} __packed;
+
+/* SNP support page type */
+enum {
+	SNP_PAGE_TYPE_NORMAL		= 0x1,
+	SNP_PAGE_TYPE_VMSA		= 0x2,
+	SNP_PAGE_TYPE_ZERO		= 0x3,
+	SNP_PAGE_TYPE_UNMEASURED	= 0x4,
+	SNP_PAGE_TYPE_SECRET		= 0x5,
+	SNP_PAGE_TYPE_CPUID		= 0x6,
+
+	SNP_PAGE_TYPE_MAX
+};
+
+/**
+ * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @page_size: page size 0 indicates 4K and 1 indicates 2MB page
+ * @page_type: encoded page type
+ * @imi_page: indicates that this page is part of the IMI (Incoming Migration
+ *            Image) of the guest
+ * @rsvd: reserved
+ * @rsvd2: reserved
+ * @address: system physical address of destination page to encrypt
+ * @rsvd3: reserved
+ * @vmpl1_perms: VMPL permission mask for VMPL1
+ * @vmpl2_perms: VMPL permission mask for VMPL2
+ * @vmpl3_perms: VMPL permission mask for VMPL3
+ * @rsvd4: reserved
+ */
+struct sev_data_snp_launch_update {
+	u64 gctx_paddr;				/* In */
+	u32 page_size:1;			/* In */
+	u32 page_type:3;			/* In */
+	u32 imi_page:1;				/* In */
+	u32 rsvd:27;
+	u32 rsvd2;
+	u64 address;				/* In */
+	u32 rsvd3:8;
+	u32 vmpl1_perms:8;			/* In */
+	u32 vmpl2_perms:8;			/* In */
+	u32 vmpl3_perms:8;			/* In */
+	u32 rsvd4;
+} __packed;
+
+/**
+ * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @id_block_paddr: system physical address of ID block
+ * @id_auth_paddr: system physical address of ID block authentication structure
+ * @id_block_en: indicates whether ID block is present
+ * @auth_key_en: indicates whether author key is present in authentication structure
+ * @rsvd: reserved
+ * @host_data: host-supplied data for guest, not interpreted by firmware
+ */
+struct sev_data_snp_launch_finish {
+	u64 gctx_paddr;
+	u64 id_block_paddr;
+	u64 id_auth_paddr;
+	u8 id_block_en:1;
+	u8 auth_key_en:1;
+	u64 rsvd:62;
+	u8 host_data[32];
+} __packed;
+
+/**
+ * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @address: system physical address of guest status page
+ */
+struct sev_data_snp_guest_status {
+	u64 gctx_paddr;
+	u64 address;
+} __packed;
+
+/**
+ * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params
+ *
+ * @paddr: system physical address of page to be claimed. The 0th bit in the
+ *         address indicates the page size. 0h indicates 4KB and 1h indicates
+ *         2MB page.
+ */
+struct sev_data_snp_page_reclaim {
+	u64 paddr;
+} __packed;
+
+/**
+ * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params
+ *
+ * @paddr: system physical address of page to be unsmashed. The 0th bit in the
+ *         address indicates the page size. 0h indicates 4 KB and 1h indicates
+ *         2 MB page.
+ */
+struct sev_data_snp_page_unsmash {
+	u64 paddr;
+} __packed;
+
+/**
+ * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @src_addr: source address of data to operate on
+ * @dst_addr: destination address of data to operate on
+ */
+struct sev_data_snp_dbg {
+	u64 gctx_paddr;				/* In */
+	u64 src_addr;				/* In */
+	u64 dst_addr;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @req_paddr: system physical address of request page
+ * @res_paddr: system physical address of response page
+ */
+struct sev_data_snp_guest_request {
+	u64 gctx_paddr;				/* In */
+	u64 req_paddr;				/* In */
+	u64 res_paddr;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_init_ex - SNP_INIT_EX structure
+ *
+ * @init_rmp: indicate that the RMP should be initialized.
+ * @list_paddr_en: indicate that list_paddr is valid
+ * @rsvd: reserved
+ * @rsvd1: reserved
+ * @list_paddr: system physical address of range list
+ * @rsvd2: reserved
+ */
+struct sev_data_snp_init_ex {
+	u32 init_rmp:1;
+	u32 list_paddr_en:1;
+	u32 rsvd:30;
+	u32 rsvd1;
+	u64 list_paddr;
+	u8  rsvd2[48];
+} __packed;
+
+/**
+ * struct sev_data_range - RANGE structure
+ *
+ * @base: system physical address of first byte of range
+ * @page_count: number of 4KB pages in this range
+ * @rsvd: reserved
+ */
+struct sev_data_range {
+	u64 base;
+	u32 page_count;
+	u32 rsvd;
+} __packed;
+
+/**
+ * struct sev_data_range_list - RANGE_LIST structure
+ *
+ * @num_elements: number of elements in RANGE_ARRAY
+ * @rsvd: reserved
+ * @ranges: array of num_elements of type RANGE
+ */
+struct sev_data_range_list {
+	u32 num_elements;
+	u32 rsvd;
+	struct sev_data_range ranges[];
+} __packed;
+
+/**
+ * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure
+ *
+ * @len: length of the command buffer read by the PSP
+ * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU
+ * @rsvd1: reserved
+ */
+struct sev_data_snp_shutdown_ex {
+	u32 len;
+	u32 iommu_snp_shutdown:1;
+	u32 rsvd1:31;
+} __packed;
+
+/**
+ * struct sev_platform_init_args
+ *
+ * @error: SEV firmware error code
+ * @probe: True if this is being called as part of CCP module probe, which
+ *  will defer SEV_INIT/SEV_INIT_EX firmware initialization until needed
+ *  unless psp_init_on_probe module param is set
+ */
+struct sev_platform_init_args {
+	int error;
+	bool probe;
+};
+
+/**
+ * struct sev_data_snp_commit - SNP_COMMIT structure
+ *
+ * @len: length of the command buffer read by the PSP
+ */
+struct sev_data_snp_commit {
+	u32 len;
+} __packed;
+
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
 
 /**
  * sev_platform_init - perform SEV INIT command
  *
- * @error: SEV command return code
+ * @args: struct sev_platform_init_args to pass in arguments
  *
  * Returns:
  * 0 if the SEV successfully processed the command
@@ -537,7 +824,7 @@ struct sev_data_attestation_report {
  * -%ETIMEDOUT if the SEV command timed out
  * -%EIO       if the SEV returned a non-zero return code
  */
-int sev_platform_init(int *error);
+int sev_platform_init(struct sev_platform_init_args *args);
 
 /**
  * sev_platform_status - perform SEV PLATFORM_STATUS command
@@ -637,14 +924,32 @@ int sev_guest_df_flush(int *error);
  */
 int sev_guest_decommission(struct sev_data_decommission *data, int *error);
 
+/**
+ * sev_do_cmd - issue an SEV or an SEV-SNP command
+ *
+ * @cmd: SEV or SEV-SNP firmware command to issue
+ * @data: arguments for firmware command
+ * @psp_ret: SEV command return code
+ *
+ * Returns:
+ * 0 if the SEV device successfully processed the command
+ * -%ENODEV    if the PSP device is not available
+ * -%ENOTSUPP  if PSP device does not support SEV
+ * -%ETIMEDOUT if the SEV command timed out
+ * -%EIO       if PSP device returned a non-zero return code
+ */
+int sev_do_cmd(int cmd, void *data, int *psp_ret);
+
 void *psp_copy_user_blob(u64 uaddr, u32 len);
+void *snp_alloc_firmware_page(gfp_t mask);
+void snp_free_firmware_page(void *addr);
 
 #else	/* !CONFIG_CRYPTO_DEV_SP_PSP */
 
 static inline int
 sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; }
 
-static inline int sev_platform_init(int *error) { return -ENODEV; }
+static inline int sev_platform_init(struct sev_platform_init_args *args) { return -ENODEV; }
 
 static inline int
 sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; }
@@ -653,6 +958,9 @@ static inline int
 sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; }
 
 static inline int
+sev_do_cmd(int cmd, void *data, int *psp_ret) { return -ENODEV; }
+
+static inline int
 sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; }
 
 static inline int sev_guest_df_flush(int *error) { return -ENODEV; }
@@ -662,6 +970,13 @@ sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int
 
 static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); }
 
+static inline void *snp_alloc_firmware_page(gfp_t mask)
+{
+	return NULL;
+}
+
+static inline void snp_free_firmware_page(void *addr) { }
+
 #endif	/* CONFIG_CRYPTO_DEV_SP_PSP */
 
 #endif	/* __PSP_SEV_H__ */
diff --git a/include/linux/pti.h b/include/linux/pti.h
index 1a941efcaa62..1fbf9d6c20ef 100644
--- a/include/linux/pti.h
+++ b/include/linux/pti.h
@@ -2,7 +2,7 @@
 #ifndef _INCLUDE_PTI_H
 #define _INCLUDE_PTI_H
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 #include <asm/pti.h>
 #else
 static inline void pti_init(void) { }
diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h
index 746fd67c3480..e8c74fa3f455 100644
--- a/include/linux/ptp_kvm.h
+++ b/include/linux/ptp_kvm.h
@@ -8,15 +8,15 @@
 #ifndef _PTP_KVM_H_
 #define _PTP_KVM_H_
 
+#include <linux/clocksource_ids.h>
 #include <linux/types.h>
 
 struct timespec64;
-struct clocksource;
 
 int kvm_arch_ptp_init(void);
 void kvm_arch_ptp_exit(void);
 int kvm_arch_ptp_get_clock(struct timespec64 *ts);
 int kvm_arch_ptp_get_crosststamp(u64 *cycle,
-		struct timespec64 *tspec, struct clocksource **cs);
+		struct timespec64 *tspec, enum clocksource_ids *cs_id);
 
 #endif /* _PTP_KVM_H_ */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eaaef3ffec22..90507d4afcd6 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs)
 #define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
 #endif
 
+#ifndef exception_ip
+#define exception_ip(x) instruction_pointer(x)
+#endif
+
 extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
 
 extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
diff --git a/include/linux/ras.h b/include/linux/ras.h
index 1f4048bf2674..a64182bc72ad 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -25,6 +25,7 @@ void log_non_standard_event(const guid_t *sec_type,
 			    const guid_t *fru_id, const char *fru_text,
 			    const u8 sev, const u8 *err, const u32 len);
 void log_arm_hw_error(struct cper_sec_proc_arm *err);
+
 #else
 static inline void
 log_non_standard_event(const guid_t *sec_type,
@@ -35,4 +36,21 @@ static inline void
 log_arm_hw_error(struct cper_sec_proc_arm *err) { return; }
 #endif
 
+struct atl_err {
+	u64 addr;
+	u64 ipid;
+	u32 cpu;
+};
+
+#if IS_ENABLED(CONFIG_AMD_ATL)
+void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *));
+void amd_atl_unregister_decoder(void);
+void amd_retire_dram_row(struct atl_err *err);
+unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err);
+#else
+static inline void amd_retire_dram_row(struct atl_err *err) { }
+static inline unsigned long
+amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; }
+#endif /* CONFIG_AMD_ATL */
+
 #endif /* __RAS_H__ */
diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h
index 0027d4c8087c..3860dbb9107a 100644
--- a/include/linux/rcu_sync.h
+++ b/include/linux/rcu_sync.h
@@ -37,7 +37,6 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp)
 }
 
 extern void rcu_sync_init(struct rcu_sync *);
-extern void rcu_sync_enter_start(struct rcu_sync *);
 extern void rcu_sync_enter(struct rcu_sync *);
 extern void rcu_sync_exit(struct rcu_sync *);
 extern void rcu_sync_dtor(struct rcu_sync *);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 0746b1b0b663..16f519914415 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t);
 	do {									\
 		int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting);	\
 										\
-		if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) &&	\
+		if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) &&	\
 		    likely(!___rttq_nesting)) {					\
-			rcu_trc_cmpxchg_need_qs((t), 0,	TRC_NEED_QS_CHECKED);	\
+			rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED);	\
 		} else if (___rttq_nesting && ___rttq_nesting != INT_MIN &&	\
 			   !READ_ONCE((t)->trc_reader_special.b.blocked)) {	\
 			rcu_tasks_trace_qs_blkd(t);				\
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 66942d7fba7f..a365f67131ec 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -6,6 +6,12 @@
 #include <linux/list.h>
 #include <linux/pid.h>
 
+/* CLOSID, RMID value used by the default control group */
+#define RESCTRL_RESERVED_CLOSID		0
+#define RESCTRL_RESERVED_RMID		0
+
+#define RESCTRL_PICK_ANY_CPU		-1
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 int proc_resctrl_show(struct seq_file *m,
@@ -153,7 +159,7 @@ struct resctrl_schema;
  * @cache_level:	Which cache level defines scope of this resource
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
- * @domains:		All domains for this resource
+ * @domains:		RCU list of all domains for this resource
  * @name:		Name to use in "schemata" file.
  * @data_width:		Character width of data when displaying
  * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
@@ -219,36 +225,70 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
+void resctrl_online_cpu(unsigned int cpu);
+void resctrl_offline_cpu(unsigned int cpu);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
  *			      for this resource and domain.
  * @r:			resource that the counter should be read from.
  * @d:			domain that the counter should be read from.
+ * @closid:		closid that matches the rmid. Depending on the architecture, the
+ *			counter may match traffic of both @closid and @rmid, or @rmid
+ *			only.
  * @rmid:		rmid of the counter to read.
  * @eventid:		eventid to read, e.g. L3 occupancy.
  * @val:		result of the counter read in bytes.
+ * @arch_mon_ctx:	An architecture specific value from
+ *			resctrl_arch_mon_ctx_alloc(), for MPAM this identifies
+ *			the hardware monitor allocated for this read request.
  *
- * Call from process context on a CPU that belongs to domain @d.
+ * Some architectures need to sleep when first programming some of the counters.
+ * (specifically: arm64's MPAM cache occupancy counters can return 'not ready'
+ *  for a short period of time). Call from a non-migrateable process context on
+ * a CPU that belongs to domain @d. e.g. use smp_call_on_cpu() or
+ * schedule_work_on(). This function can be called with interrupts masked,
+ * e.g. using smp_call_function_any(), but may consistently return an error.
  *
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 rmid, enum resctrl_event_id eventid, u64 *val);
+			   u32 closid, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val, void *arch_mon_ctx);
+
+/**
+ * resctrl_arch_rmid_read_context_check()  - warn about invalid contexts
+ *
+ * When built with CONFIG_DEBUG_ATOMIC_SLEEP generate a warning when
+ * resctrl_arch_rmid_read() is called with preemption disabled.
+ *
+ * The contract with resctrl_arch_rmid_read() is that if interrupts
+ * are unmasked, it can sleep. This allows NOHZ_FULL systems to use an
+ * IPI, (and fail if the call needed to sleep), while most of the time
+ * the work is scheduled, allowing the call to sleep.
+ */
+static inline void resctrl_arch_rmid_read_context_check(void)
+{
+	if (!irqs_disabled())
+		might_sleep();
+}
 
 /**
  * resctrl_arch_reset_rmid() - Reset any private state associated with rmid
  *			       and eventid.
  * @r:		The domain's resource.
  * @d:		The rmid's domain.
+ * @closid:	closid that matches the rmid. Depending on the architecture, the
+ *		counter may match traffic of both @closid and @rmid, or @rmid only.
  * @rmid:	The rmid whose counter values should be reset.
  * @eventid:	The eventid whose counter values should be reset.
  *
  * This can be called from any CPU.
  */
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
-			     u32 rmid, enum resctrl_event_id eventid);
+			     u32 closid, u32 rmid,
+			     enum resctrl_event_id eventid);
 
 /**
  * resctrl_arch_reset_rmid_all() - Reset all private state associated with
diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h
new file mode 100644
index 000000000000..309ca72f2dfb
--- /dev/null
+++ b/include/linux/rw_hint.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RW_HINT_H
+#define _LINUX_RW_HINT_H
+
+#include <linux/build_bug.h>
+#include <linux/compiler_attributes.h>
+#include <uapi/linux/fcntl.h>
+
+/* Block storage write lifetime hint values. */
+enum rw_hint {
+	WRITE_LIFE_NOT_SET	= RWH_WRITE_LIFE_NOT_SET,
+	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
+	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
+	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
+	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
+	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
+} __packed;
+
+/* Sparse ignores __packed annotations on enums, hence the #ifndef below. */
+#ifndef __CHECKER__
+static_assert(sizeof(enum rw_hint) == 1);
+#endif
+
+#endif /* _LINUX_RW_HINT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffe8f618ab86..17cb0761ff65 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -858,6 +858,8 @@ struct task_struct {
 	u8				rcu_tasks_idx;
 	int				rcu_tasks_idle_cpu;
 	struct list_head		rcu_tasks_holdout_list;
+	int				rcu_tasks_exit_cpu;
+	struct list_head		rcu_tasks_exit_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 #ifdef CONFIG_TASKS_TRACE_RCU
@@ -1642,7 +1644,7 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
-#define PF__HOLE__20000000	0x20000000
+#define PF_BLOCK_TS		0x20000000	/* plug has ts that needs updating */
 #define PF__HOLE__40000000	0x40000000
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index a8b28647aafc..b04a5d04dee9 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -117,13 +117,13 @@ SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS)
 
 /*
- * Domain members share CPU package resources (i.e. caches)
+ * Domain members share CPU Last Level Caches
  *
  * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
  *               the same cache(s).
  * NEEDS_GROUPS: Caches are shared between groups.
  */
-SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+SD_FLAG(SD_SHARE_LLC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
 
 /*
  * Only a single load balancing instance
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 4b7664c56208..0a0e23c45406 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -735,8 +735,6 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
-extern bool thread_group_exited(struct pid *pid);
-
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
 							unsigned long *flags);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index a6e04b4a21d7..18572c9ea724 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -38,21 +38,21 @@ extern const struct sd_flag_debug sd_flag_debug[];
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {
-	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC;
 }
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
 static inline int cpu_cluster_flags(void)
 {
-	return SD_CLUSTER | SD_SHARE_PKG_RESOURCES;
+	return SD_CLUSTER | SD_SHARE_LLC;
 }
 #endif
 
 #ifdef CONFIG_SCHED_MC
 static inline int cpu_core_flags(void)
 {
-	return SD_SHARE_PKG_RESOURCES;
+	return SD_SHARE_LLC;
 }
 #endif
 
@@ -176,6 +176,7 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
+bool cpus_equal_capacity(int this_cpu, int that_cpu);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 bool cpus_share_resources(int this_cpu, int that_cpu);
 
@@ -226,6 +227,11 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 {
 }
 
+static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return true;
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index f2f05fb42d28..2ee94ff0320c 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -47,6 +47,10 @@ struct scmi_clock_info {
 	bool rate_discrete;
 	bool rate_changed_notifications;
 	bool rate_change_requested_notifications;
+	bool state_ctrl_forbidden;
+	bool rate_ctrl_forbidden;
+	bool parent_ctrl_forbidden;
+	bool extended_config;
 	union {
 		struct {
 			int num_rates;
@@ -72,6 +76,13 @@ struct scmi_handle;
 struct scmi_device;
 struct scmi_protocol_handle;
 
+enum scmi_clock_oem_config {
+	SCMI_CLOCK_CFG_DUTY_CYCLE = 0x1,
+	SCMI_CLOCK_CFG_PHASE,
+	SCMI_CLOCK_CFG_OEM_START = 0x80,
+	SCMI_CLOCK_CFG_OEM_END = 0xFF,
+};
+
 /**
  * struct scmi_clk_proto_ops - represents the various operations provided
  *	by SCMI Clock Protocol
@@ -104,10 +115,11 @@ struct scmi_clk_proto_ops {
 	int (*state_get)(const struct scmi_protocol_handle *ph, u32 clk_id,
 			 bool *enabled, bool atomic);
 	int (*config_oem_get)(const struct scmi_protocol_handle *ph, u32 clk_id,
-			      u8 oem_type, u32 *oem_val, u32 *attributes,
-			      bool atomic);
+			      enum scmi_clock_oem_config oem_type,
+			      u32 *oem_val, u32 *attributes, bool atomic);
 	int (*config_oem_set)(const struct scmi_protocol_handle *ph, u32 clk_id,
-			      u8 oem_type, u32 oem_val, bool atomic);
+			      enum scmi_clock_oem_config oem_type,
+			      u32 oem_val, bool atomic);
 	int (*parent_get)(const struct scmi_protocol_handle *ph, u32 clk_id, u32 *parent_id);
 	int (*parent_set)(const struct scmi_protocol_handle *ph, u32 clk_id, u32 parent_id);
 };
@@ -953,6 +965,8 @@ struct scmi_perf_limits_report {
 	unsigned int	domain_id;
 	unsigned int	range_max;
 	unsigned int	range_min;
+	unsigned long	range_max_freq;
+	unsigned long	range_min_freq;
 };
 
 struct scmi_perf_level_report {
@@ -960,6 +974,7 @@ struct scmi_perf_level_report {
 	unsigned int	agent_id;
 	unsigned int	domain_id;
 	unsigned int	performance_level;
+	unsigned long	performance_level_freq;
 };
 
 struct scmi_sensor_trip_point_report {
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index c44f4b47b945..fe41da005970 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -2,7 +2,10 @@
 #ifndef _LINUX_SEQ_BUF_H
 #define _LINUX_SEQ_BUF_H
 
-#include <linux/fs.h>
+#include <linux/bug.h>
+#include <linux/minmax.h>
+#include <linux/seq_file.h>
+#include <linux/types.h>
 
 /*
  * Trace sequences are used to allow a function to call several other functions
@@ -10,7 +13,7 @@
  */
 
 /**
- * seq_buf - seq buffer structure
+ * struct seq_buf - seq buffer structure
  * @buffer:	pointer to the buffer
  * @size:	size of the buffer
  * @len:	the amount of data inside the buffer
@@ -77,10 +80,10 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
 }
 
 /**
- * seq_buf_str - get %NUL-terminated C string from seq_buf
+ * seq_buf_str - get NUL-terminated C string from seq_buf
  * @s: the seq_buf handle
  *
- * This makes sure that the buffer in @s is nul terminated and
+ * This makes sure that the buffer in @s is NUL-terminated and
  * safe to read as a string.
  *
  * Note, if this is called when the buffer has overflowed, then
@@ -90,7 +93,7 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
  * After this function is called, s->buffer is safe to use
  * in string operations.
  *
- * Returns @s->buf after making sure it is terminated.
+ * Returns: @s->buf after making sure it is terminated.
  */
 static inline const char *seq_buf_str(struct seq_buf *s)
 {
@@ -110,7 +113,7 @@ static inline const char *seq_buf_str(struct seq_buf *s)
  * @s: the seq_buf handle
  * @bufp: the beginning of the buffer is stored here
  *
- * Return the number of bytes available in the buffer, or zero if
+ * Returns: the number of bytes available in the buffer, or zero if
  * there's no space.
  */
 static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
@@ -132,7 +135,7 @@ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
  * @num: the number of bytes to commit
  *
  * Commit @num bytes of data written to a buffer previously acquired
- * by seq_buf_get.  To signal an error condition, or that the data
+ * by seq_buf_get_buf(). To signal an error condition, or that the data
  * didn't fit in the available space, pass a negative @num value.
  */
 static inline void seq_buf_commit(struct seq_buf *s, int num)
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 536b2581d3e2..55b1f3ba48ac 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -748,8 +748,17 @@ struct uart_driver {
 
 void uart_write_wakeup(struct uart_port *port);
 
-#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test,      \
-		for_post)						      \
+/**
+ * enum UART_TX_FLAGS -- flags for uart_port_tx_flags()
+ *
+ * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer
+ */
+enum UART_TX_FLAGS {
+	UART_TX_NOSTOP = BIT(0),
+};
+
+#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done,	      \
+		       for_test, for_post)				      \
 ({									      \
 	struct uart_port *__port = (uport);				      \
 	struct circ_buf *xmit = &__port->state->xmit;			      \
@@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port);
 	if (pending < WAKEUP_CHARS) {					      \
 		uart_write_wakeup(__port);				      \
 									      \
-		if (pending == 0)					      \
+		if (!((flags) & UART_TX_NOSTOP) && pending == 0)	      \
 			__port->ops->stop_tx(__port);			      \
 	}								      \
 									      \
@@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port);
  */
 #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \
 	unsigned int __count = (count);					      \
-	__uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count,	      \
+	__uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count,     \
 			__count--);					      \
 })
 
@@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port);
  * See uart_port_tx_limited() for more details.
  */
 #define uart_port_tx(port, ch, tx_ready, put_char)			\
-	__uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({}))
+	__uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({}))
+
 
+/**
+ * uart_port_tx_flags -- transmit helper for uart_port with flags
+ * @port: uart port
+ * @ch: variable to store a character to be written to the HW
+ * @flags: %UART_TX_NOSTOP or similar
+ * @tx_ready: can HW accept more data function
+ * @put_char: function to write a character
+ *
+ * See uart_port_tx_limited() for more details.
+ */
+#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char)		\
+	__uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({}))
 /*
  * Baud rate helpers.
  */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index e87520dc2959..fcd61dfe2af3 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -105,6 +105,12 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func,
 	on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
 }
 
+/*
+ * Architecture specific boot CPU setup.  Defined as empty weak function in
+ * init/main.c. Architectures can override it.
+ */
+void smp_prepare_boot_cpu(void);
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -171,12 +177,6 @@ void generic_smp_call_function_single_interrupt(void);
 #define generic_smp_call_function_interrupt \
 	generic_smp_call_function_single_interrupt
 
-/*
- * Mark the boot cpu "online" so that it can call console drivers in
- * printk() and can access its per-cpu storage.
- */
-void smp_prepare_boot_cpu(void);
-
 extern unsigned int setup_max_cpus;
 extern void __init setup_nr_cpu_ids(void);
 extern void __init smp_init(void);
@@ -203,7 +203,6 @@ static inline void up_smp_call_function(smp_call_func_t func, void *info)
 			(up_smp_call_function(func, info))
 
 static inline void smp_send_reschedule(int cpu) { }
-#define smp_prepare_boot_cpu()			do {} while (0)
 #define smp_call_function_many(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
 static inline void call_function_init(void) { }
@@ -218,6 +217,8 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 static inline void kick_all_cpus_sync(void) {  }
 static inline void wake_up_all_idle_cpus(void) {  }
 
+#define setup_max_cpus 0
+
 #ifdef CONFIG_UP_LATE_INIT
 extern void __init up_late_init(void);
 static inline void smp_init(void) { up_late_init(); }
@@ -261,7 +262,7 @@ static inline int get_boot_cpu_id(void)
  * regular asm read for the stable.
  */
 #ifndef __smp_processor_id
-#define __smp_processor_id(x) raw_smp_processor_id(x)
+#define __smp_processor_id() raw_smp_processor_id()
 #endif
 
 #ifdef CONFIG_DEBUG_PREEMPT
diff --git a/include/linux/soc/andes/irq.h b/include/linux/soc/andes/irq.h
new file mode 100644
index 000000000000..edc3182d6e66
--- /dev/null
+++ b/include/linux/soc/andes/irq.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Andes Technology Corporation
+ */
+#ifndef __ANDES_IRQ_H
+#define __ANDES_IRQ_H
+
+/* Andes PMU irq number */
+#define ANDES_RV_IRQ_PMOVI		18
+#define ANDES_RV_IRQ_LAST		ANDES_RV_IRQ_PMOVI
+#define ANDES_SLI_CAUSE_BASE		256
+
+/* Andes PMU related registers */
+#define ANDES_CSR_SLIE			0x9c4
+#define ANDES_CSR_SLIP			0x9c5
+#define ANDES_CSR_SCOUNTEROF		0x9d4
+
+#endif /* __ANDES_IRQ_H */
diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h
index be98aebcb3e1..7161a3183eda 100644
--- a/include/linux/soc/qcom/apr.h
+++ b/include/linux/soc/qcom/apr.h
@@ -9,7 +9,7 @@
 #include <dt-bindings/soc/qcom,apr.h>
 #include <dt-bindings/soc/qcom,gpr.h>
 
-extern struct bus_type aprbus;
+extern const struct bus_type aprbus;
 
 #define APR_HDR_LEN(hdr_len) ((hdr_len)/4)
 
diff --git a/include/linux/soc/qcom/qcom-pbs.h b/include/linux/soc/qcom/qcom-pbs.h
new file mode 100644
index 000000000000..8a46209ccf13
--- /dev/null
+++ b/include/linux/soc/qcom/qcom-pbs.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _QCOM_PBS_H
+#define _QCOM_PBS_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device_node;
+struct pbs_dev;
+
+#if IS_ENABLED(CONFIG_QCOM_PBS)
+int qcom_pbs_trigger_event(struct pbs_dev *pbs, u8 bitmap);
+struct pbs_dev *get_pbs_client_device(struct device *client_dev);
+#else
+static inline int qcom_pbs_trigger_event(struct pbs_dev *pbs, u8 bitmap)
+{
+	return -ENODEV;
+}
+
+static inline struct pbs_dev *get_pbs_client_device(struct device *client_dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
+#endif
diff --git a/include/linux/soc/samsung/exynos-pmu.h b/include/linux/soc/samsung/exynos-pmu.h
index a4f5516cc956..2bd9d12d9a52 100644
--- a/include/linux/soc/samsung/exynos-pmu.h
+++ b/include/linux/soc/samsung/exynos-pmu.h
@@ -10,6 +10,7 @@
 #define __LINUX_SOC_EXYNOS_PMU_H
 
 struct regmap;
+struct device_node;
 
 enum sys_powerdown {
 	SYS_AFTR,
@@ -20,12 +21,20 @@ enum sys_powerdown {
 
 extern void exynos_sys_powerdown_conf(enum sys_powerdown mode);
 #ifdef CONFIG_EXYNOS_PMU
-extern struct regmap *exynos_get_pmu_regmap(void);
+struct regmap *exynos_get_pmu_regmap(void);
+struct regmap *exynos_get_pmu_regmap_by_phandle(struct device_node *np,
+						const char *propname);
 #else
 static inline struct regmap *exynos_get_pmu_regmap(void)
 {
 	return ERR_PTR(-ENODEV);
 }
+
+static inline struct regmap *exynos_get_pmu_regmap_by_phandle(struct device_node *np,
+							      const char *propname)
+{
+	return ERR_PTR(-ENODEV);
+}
 #endif
 
 #endif /* __LINUX_SOC_EXYNOS_PMU_H */
diff --git a/include/linux/string.h b/include/linux/string.h
index ab148d8dbfc1..4795ee5c50c6 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -217,6 +217,7 @@ extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2);
 extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2);
 extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp);
+extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
 extern void argv_free(char **argv);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 67cf1c9efd80..23617da0e565 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -339,7 +339,6 @@ struct svc_program {
 	const struct svc_version **pg_vers;	/* version array */
 	char *			pg_name;	/* service name */
 	char *			pg_class;	/* class name: services sharing authentication */
-	struct svc_stat *	pg_stats;	/* rpc statistics */
 	enum svc_auth_status	(*pg_authenticate)(struct svc_rqst *rqstp);
 	__be32			(*pg_init_request)(struct svc_rqst *,
 						   const struct svc_program *,
@@ -411,7 +410,9 @@ bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,
 void		   svc_rqst_release_pages(struct svc_rqst *rqstp);
 void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
-struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
+struct svc_serv *  svc_create_pooled(struct svc_program *prog,
+				     struct svc_stat *stats,
+				     unsigned int bufsize,
 				     int (*threadfn)(void *data));
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_info *si, struct file *file);
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index e7595ae62fe2..24cd199dd6f3 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -203,6 +203,30 @@ struct svc_rdma_recv_ctxt {
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
+/*
+ * State for sending a Write chunk.
+ *  - Tracks progress of writing one chunk over all its segments
+ *  - Stores arguments for the SGL constructor functions
+ */
+struct svc_rdma_write_info {
+	struct svcxprt_rdma	*wi_rdma;
+	struct list_head	wi_list;
+
+	const struct svc_rdma_chunk	*wi_chunk;
+
+	/* write state of this chunk */
+	unsigned int		wi_seg_off;
+	unsigned int		wi_seg_no;
+
+	/* SGL constructor arguments */
+	const struct xdr_buf	*wi_xdr;
+	unsigned char		*wi_base;
+	unsigned int		wi_next_off;
+
+	struct svc_rdma_chunk_ctxt	wi_cc;
+	struct work_struct	wi_work;
+};
+
 struct svc_rdma_send_ctxt {
 	struct llist_node	sc_node;
 	struct rpc_rdma_cid	sc_cid;
@@ -210,9 +234,15 @@ struct svc_rdma_send_ctxt {
 
 	struct svcxprt_rdma	*sc_rdma;
 	struct ib_send_wr	sc_send_wr;
+	struct ib_send_wr	*sc_wr_chain;
+	int			sc_sqecount;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
 	struct xdr_stream	sc_stream;
+
+	struct list_head	sc_write_info_list;
+	struct svc_rdma_write_info sc_reply_info;
+
 	void			*sc_xprt_buf;
 	int			sc_page_count;
 	int			sc_cur_sge_no;
@@ -236,18 +266,27 @@ extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt);
 extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
+extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+			     struct svc_rdma_chunk_ctxt *cc);
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
 extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
 			     struct svc_rdma_chunk_ctxt *cc);
 extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
 				struct svc_rdma_chunk_ctxt *cc,
 				enum dma_data_direction dir);
-extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     const struct svc_rdma_chunk *chunk,
-				     const struct xdr_buf *xdr);
-extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
-				     const struct svc_rdma_recv_ctxt *rctxt,
-				     const struct xdr_buf *xdr);
+extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
+					 struct svc_rdma_send_ctxt *ctxt);
+extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma,
+					 struct svc_rdma_send_ctxt *ctxt);
+extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
+				       const struct svc_rdma_pcl *write_pcl,
+				       struct svc_rdma_send_ctxt *sctxt,
+				       const struct xdr_buf *xdr);
+extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma,
+					const struct svc_rdma_pcl *write_pcl,
+					const struct svc_rdma_pcl *reply_pcl,
+					struct svc_rdma_send_ctxt *sctxt,
+					const struct xdr_buf *xdr);
 extern int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 				      struct svc_rqst *rqstp,
 				      struct svc_rdma_recv_ctxt *head);
@@ -258,8 +297,8 @@ extern struct svc_rdma_send_ctxt *
 		svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma);
 extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_send_ctxt *ctxt);
-extern int svc_rdma_send(struct svcxprt_rdma *rdma,
-			 struct svc_rdma_send_ctxt *ctxt);
+extern int svc_rdma_post_send(struct svcxprt_rdma *rdma,
+			      struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_pcl *write_pcl,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4db00ddad261..378ab1cd23bd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,7 +298,7 @@ struct swap_info_struct {
 	unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
 	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
 	struct rb_root swap_extent_root;/* root of the swap extent rbtree */
-	struct bdev_handle *bdev_handle;/* open handle of the bdev */
+	struct file *bdev_file;		/* open handle of the bdev */
 	struct block_device *bdev;	/* swap device or bdev of swap file */
 	struct file *swap_file;		/* seldom referenced */
 	unsigned int old_block_size;	/* seldom referenced */
@@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp)
 	return 0;
 }
 
+static inline int swapcache_prepare(swp_entry_t swp)
+{
+	return 0;
+}
+
 static inline void swap_free(swp_entry_t swp)
 {
 }
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 89b290d8c8dc..a1c47a6d69b0 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -221,8 +221,10 @@ struct tcp_sock {
 	u32	lost_out;	/* Lost packets			*/
 	u32	sacked_out;	/* SACK'd packets			*/
 	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	u8	chrono_type : 2,	/* current chronograph type */
 		repair      : 1,
+		tcp_usec_ts : 1, /* TSval values in usec */
 		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
 		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	__cacheline_group_end(tcp_sock_read_txrx);
@@ -352,7 +354,6 @@ struct tcp_sock {
 	u32	compressed_ack_rcv_nxt;
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
 
-	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
 		u64 mstamp; /* (Re)sent time of the skb */
@@ -368,8 +369,7 @@ struct tcp_sock {
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
-		tcp_usec_ts:1, /* TSval values in usec */
-		unused:4;
+		unused:5;
 	u8	thin_lto    : 1,/* Use linear timeouts for thin streams */
 		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index 911ddf92dcee..71632e3c5f18 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -482,7 +482,7 @@ static inline bool tee_param_is_memref(struct tee_param *param)
 	}
 }
 
-extern struct bus_type tee_bus_type;
+extern const struct bus_type tee_bus_type;
 
 /**
  * struct tee_client_device - tee based device
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 716d17f31c45..4924a33700b7 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/sched.h>
 #include <linux/rcupdate.h>
+#include <linux/static_key.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void __init tick_init(void);
@@ -19,16 +20,22 @@ extern void __init tick_init(void);
 extern void tick_suspend_local(void);
 /* Should be core only, but XEN resume magic and ARM BL switcher require it */
 extern void tick_resume_local(void);
-extern void tick_handover_do_timer(void);
 extern void tick_cleanup_dead_cpu(int cpu);
 #else /* CONFIG_GENERIC_CLOCKEVENTS */
 static inline void tick_init(void) { }
 static inline void tick_suspend_local(void) { }
 static inline void tick_resume_local(void) { }
-static inline void tick_handover_do_timer(void) { }
 static inline void tick_cleanup_dead_cpu(int cpu) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU)
+extern int tick_cpu_dying(unsigned int cpu);
+extern void tick_assert_timekeeping_handover(void);
+#else
+#define tick_cpu_dying	NULL
+static inline void tick_assert_timekeeping_handover(void) { }
+#endif
+
 #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND)
 extern void tick_freeze(void);
 extern void tick_unfreeze(void);
@@ -63,18 +70,14 @@ enum tick_broadcast_state {
 	TICK_BROADCAST_ENTER,
 };
 
+extern struct static_key_false arch_needs_tick_broadcast;
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern void tick_broadcast_control(enum tick_broadcast_mode mode);
 #else
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
-#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
-extern void tick_offline_cpu(unsigned int cpu);
-#else
-static inline void tick_offline_cpu(unsigned int cpu) { }
-#endif
-
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else
@@ -164,9 +167,16 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
+/*
+ * Mask of CPUs that are nohz_full.
+ *
+ * Users should be guarded by CONFIG_NO_HZ_FULL or a tick_nohz_full_cpu()
+ * check.
+ */
+extern cpumask_var_t tick_nohz_full_mask;
+
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
-extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 7c43e98cf211..7e50cbd97f86 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -268,15 +268,17 @@ struct system_device_crosststamp {
 };
 
 /**
- * struct system_counterval_t - system counter value with the pointer to the
+ * struct system_counterval_t - system counter value with the ID of the
  *				corresponding clocksource
  * @cycles:	System counter value
- * @cs:		Clocksource corresponding to system counter value. Used by
- *		timekeeping code to verify comparibility of two cycle values
+ * @cs_id:	Clocksource ID corresponding to system counter value. Used by
+ *		timekeeping code to verify comparability of two cycle values.
+ *		The default ID, CSID_GENERIC, does not identify a specific
+ *		clocksource.
  */
 struct system_counterval_t {
 	u64			cycles;
-	struct clocksource	*cs;
+	enum clocksource_ids	cs_id;
 };
 
 /*
diff --git a/include/linux/timer.h b/include/linux/timer.h
index f18a2f1eb79e..14a633ba61d6 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -36,16 +36,10 @@
  * workqueue locking issues. It's not meant for executing random crap
  * with interrupts disabled. Abuse is monitored!
  *
- * @TIMER_PINNED: A pinned timer will not be affected by any timer
- * placement heuristics (like, NOHZ) and will always expire on the CPU
- * on which the timer was enqueued.
- *
- * Note: Because enqueuing of timers can migrate the timer from one
- * CPU to another, pinned timers are not guaranteed to stay on the
- * initialy selected CPU.  They move to the CPU on which the enqueue
- * function is invoked via mod_timer() or add_timer().  If the timer
- * should be placed on a particular CPU, then add_timer_on() has to be
- * used.
+ * @TIMER_PINNED: A pinned timer will always expire on the CPU on which the
+ * timer was enqueued. When a particular CPU is required, add_timer_on()
+ * has to be used. Enqueue via mod_timer() and add_timer() is always done
+ * on the local CPU.
  */
 #define TIMER_CPUMASK		0x0003FFFF
 #define TIMER_MIGRATING		0x00040000
@@ -165,6 +159,8 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires);
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
 extern void add_timer(struct timer_list *timer);
+extern void add_timer_local(struct timer_list *timer);
+extern void add_timer_global(struct timer_list *timer);
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
 extern int timer_delete_sync(struct timer_list *timer);
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 9ec229dfddaa..1ef95c0287f0 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -9,9 +9,15 @@
 /*
  * Trace sequences are used to allow a function to call several other functions
  * to create a string of data to use.
+ *
+ * Have the trace seq to be 8K which is typically PAGE_SIZE * 2 on
+ * most architectures. The TRACE_SEQ_BUFFER_SIZE (which is
+ * TRACE_SEQ_SIZE minus the other fields of trace_seq), is the
+ * max size the output of a trace event may be.
  */
 
-#define TRACE_SEQ_BUFFER_SIZE	(PAGE_SIZE * 2 - \
+#define TRACE_SEQ_SIZE		8192
+#define TRACE_SEQ_BUFFER_SIZE	(TRACE_SEQ_SIZE - \
 	(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
 
 struct trace_seq {
diff --git a/include/linux/uio.h b/include/linux/uio.h
index bea9c89922d9..00cebe2b70de 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -40,7 +40,6 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
-	bool copy_mc;
 	bool nofault;
 	bool data_source;
 	size_t iov_offset;
@@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 
 #ifdef CONFIG_ARCH_HAS_COPY_MC
 size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
-static inline void iov_iter_set_copy_mc(struct iov_iter *i)
-{
-	i->copy_mc = true;
-}
-
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return i->copy_mc;
-}
 #else
 #define _copy_mc_to_iter _copy_to_iter
-static inline void iov_iter_set_copy_mc(struct iov_iter *i) { }
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return false;
-}
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_UBUF,
-		.copy_mc = false,
 		.data_source = direction,
 		.ubuf = buf,
 		.count = count,
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index a771ccc038ac..6532beb587b1 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -236,7 +236,6 @@ struct usb_ep {
 	unsigned		max_streams:16;
 	unsigned		mult:2;
 	unsigned		maxburst:5;
-	unsigned		fifo_mode:1;
 	u8			address;
 	const struct usb_endpoint_descriptor	*desc;
 	const struct usb_ss_ep_comp_descriptor	*comp_desc;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index cd77fc6095a1..ac95e7c89df5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -55,7 +55,7 @@ struct giveback_urb_bh {
 	bool high_prio;
 	spinlock_t lock;
 	struct list_head  head;
-	struct tasklet_struct bh;
+	struct work_struct bh;
 	struct usb_host_endpoint *completing_ep;
 };
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 2cc0a9606175..158784dd189a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -22,20 +22,54 @@
  */
 #define work_data_bits(work) ((unsigned long *)(&(work)->data))
 
-enum {
+enum work_bits {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
-	WORK_STRUCT_INACTIVE_BIT= 1,	/* work item is inactive */
-	WORK_STRUCT_PWQ_BIT	= 2,	/* data points to pwq */
-	WORK_STRUCT_LINKED_BIT	= 3,	/* next work is linked to this one */
+	WORK_STRUCT_INACTIVE_BIT,	/* work item is inactive */
+	WORK_STRUCT_PWQ_BIT,		/* data points to pwq */
+	WORK_STRUCT_LINKED_BIT,		/* next work is linked to this one */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
-	WORK_STRUCT_STATIC_BIT	= 4,	/* static initializer (debugobjects) */
-	WORK_STRUCT_COLOR_SHIFT	= 5,	/* color for workqueue flushing */
-#else
-	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
+	WORK_STRUCT_STATIC_BIT,		/* static initializer (debugobjects) */
 #endif
+	WORK_STRUCT_FLAG_BITS,
 
+	/* color for workqueue flushing */
+	WORK_STRUCT_COLOR_SHIFT	= WORK_STRUCT_FLAG_BITS,
 	WORK_STRUCT_COLOR_BITS	= 4,
 
+	/*
+	 * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/
+	 * debugobjects turned off. This makes pwqs aligned to 256 bytes (512
+	 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors.
+	 *
+	 * MSB
+	 * [ pwq pointer ] [ flush color ] [ STRUCT flags ]
+	 *                     4 bits        4 or 5 bits
+	 */
+	WORK_STRUCT_PWQ_SHIFT	= WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS,
+
+	/*
+	 * data contains off-queue information when !WORK_STRUCT_PWQ.
+	 *
+	 * MSB
+	 * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ]
+	 *                 1 bit        4 or 5 bits
+	 */
+	WORK_OFFQ_FLAG_SHIFT	= WORK_STRUCT_FLAG_BITS,
+	WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT,
+	WORK_OFFQ_FLAG_END,
+	WORK_OFFQ_FLAG_BITS	= WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT,
+
+	/*
+	 * When a work item is off queue, the high bits encode off-queue flags
+	 * and the last pool it was on. Cap pool ID to 31 bits and use the
+	 * highest number to indicate that no pool is associated.
+	 */
+	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS,
+	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
+	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
+};
+
+enum work_flags {
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_INACTIVE	= 1 << WORK_STRUCT_INACTIVE_BIT,
 	WORK_STRUCT_PWQ		= 1 << WORK_STRUCT_PWQ_BIT,
@@ -45,35 +79,14 @@ enum {
 #else
 	WORK_STRUCT_STATIC	= 0,
 #endif
+};
 
+enum wq_misc_consts {
 	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS),
 
 	/* not bound to any CPU, prefer the local CPU */
 	WORK_CPU_UNBOUND	= NR_CPUS,
 
-	/*
-	 * Reserve 8 bits off of pwq pointer w/ debugobjects turned off.
-	 * This makes pwqs aligned to 256 bytes and allows 16 workqueue
-	 * flush colors.
-	 */
-	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
-				  WORK_STRUCT_COLOR_BITS,
-
-	/* data contains off-queue information when !WORK_STRUCT_PWQ */
-	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_COLOR_SHIFT,
-
-	__WORK_OFFQ_CANCELING	= WORK_OFFQ_FLAG_BASE,
-
-	/*
-	 * When a work item is off queue, its high bits point to the last
-	 * pool it was on.  Cap at 31 bits and use the highest number to
-	 * indicate that no pool is associated.
-	 */
-	WORK_OFFQ_FLAG_BITS	= 1,
-	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
-	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
-	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
-
 	/* bit mask for work_busy() return values */
 	WORK_BUSY_PENDING	= 1 << 0,
 	WORK_BUSY_RUNNING	= 1 << 1,
@@ -83,12 +96,10 @@ enum {
 };
 
 /* Convenience constants - of type 'unsigned long', not 'enum'! */
-#define WORK_OFFQ_CANCELING	(1ul << __WORK_OFFQ_CANCELING)
+#define WORK_OFFQ_CANCELING	(1ul << WORK_OFFQ_CANCELING_BIT)
 #define WORK_OFFQ_POOL_NONE	((1ul << WORK_OFFQ_POOL_BITS) - 1)
 #define WORK_STRUCT_NO_POOL	(WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT)
-
-#define WORK_STRUCT_FLAG_MASK    ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
+#define WORK_STRUCT_PWQ_MASK	(~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1))
 
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
@@ -347,7 +358,8 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
  * Workqueue flags and constants.  For details, please refer to
  * Documentation/core-api/workqueue.rst.
  */
-enum {
+enum wq_flags {
+	WQ_BH			= 1 << 0, /* execute in bottom half (softirq) context */
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
 	WQ_FREEZABLE		= 1 << 2, /* freeze during suspend */
 	WQ_MEM_RECLAIM		= 1 << 3, /* may be used for memory reclaim */
@@ -386,11 +398,22 @@ enum {
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
-	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
 
+	/* BH wq only allows the following flags */
+	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI,
+};
+
+enum wq_consts {
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_UNBOUND_MAX_ACTIVE	= WQ_MAX_ACTIVE,
 	WQ_DFL_ACTIVE		= WQ_MAX_ACTIVE / 2,
+
+	/*
+	 * Per-node default cap on min_active. Unless explicitly set, min_active
+	 * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see
+	 * workqueue_struct->min_active definition.
+	 */
+	WQ_DFL_MIN_ACTIVE	= 8,
 };
 
 /*
@@ -420,6 +443,9 @@ enum {
  * they are same as their non-power-efficient counterparts - e.g.
  * system_power_efficient_wq is identical to system_wq if
  * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
+ *
+ * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
+ * are executed in the queueing CPU's BH context in the queueing order.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_highpri_wq;
@@ -428,16 +454,43 @@ extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
 extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;
+extern struct workqueue_struct *system_bh_wq;
+extern struct workqueue_struct *system_bh_highpri_wq;
+
+void workqueue_softirq_action(bool highpri);
+void workqueue_softirq_dead(unsigned int cpu);
 
 /**
  * alloc_workqueue - allocate a workqueue
  * @fmt: printf format for the name of the workqueue
  * @flags: WQ_* flags
- * @max_active: max in-flight work items per CPU, 0 for default
+ * @max_active: max in-flight work items, 0 for default
  * remaining args: args for @fmt
  *
- * Allocate a workqueue with the specified parameters.  For detailed
- * information on WQ_* flags, please refer to
+ * For a per-cpu workqueue, @max_active limits the number of in-flight work
+ * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be
+ * executing at most one work item for the workqueue.
+ *
+ * For unbound workqueues, @max_active limits the number of in-flight work items
+ * for the whole system. e.g. @max_active of 16 indicates that that there can be
+ * at most 16 work items executing for the workqueue in the whole system.
+ *
+ * As sharing the same active counter for an unbound workqueue across multiple
+ * NUMA nodes can be expensive, @max_active is distributed to each NUMA node
+ * according to the proportion of the number of online CPUs and enforced
+ * independently.
+ *
+ * Depending on online CPU distribution, a node may end up with per-node
+ * max_active which is significantly lower than @max_active, which can lead to
+ * deadlocks if the per-node concurrency limit is lower than the maximum number
+ * of interdependent work items for the workqueue.
+ *
+ * To guarantee forward progress regardless of online CPU distribution, the
+ * concurrency limit on every node is guaranteed to be equal to or greater than
+ * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means
+ * that the sum of per-node max_active's may be larger than @max_active.
+ *
+ * For detailed information on %WQ_* flags, please refer to
  * Documentation/core-api/workqueue.rst.
  *
  * RETURNS:
@@ -460,8 +513,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
-			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
@@ -471,6 +523,9 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
 #define create_singlethread_workqueue(name)				\
 	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
+#define from_work(var, callback_work, work_fieldname)	\
+	container_of(callback_work, typeof(*var), work_fieldname)
+
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
 struct workqueue_attrs *alloc_workqueue_attrs(void);
@@ -508,6 +563,8 @@ extern bool flush_rcu_work(struct rcu_work *rwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
+extern void workqueue_set_min_active(struct workqueue_struct *wq,
+				     int min_active);
 extern struct work_struct *current_work(void);
 extern bool current_is_workqueue_rescuer(void);
 extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 49c4640027d8..afd40dce40f3 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -46,12 +46,6 @@ struct scm_stat {
 
 #define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
 
-#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
-#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-#define unix_state_lock_nested(s) \
-				spin_lock_nested(&unix_sk(s)->lock, \
-				SINGLE_DEPTH_NESTING)
-
 /* The AF_UNIX socket */
 struct unix_sock {
 	/* WARNING: sk has to be the first member */
@@ -77,6 +71,20 @@ struct unix_sock {
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
 #define unix_peer(sk) (unix_sk(sk)->peer)
 
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+enum unix_socket_lock_class {
+	U_LOCK_NORMAL,
+	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
+	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+};
+
+static inline void unix_state_lock_nested(struct sock *sk,
+				   enum unix_socket_lock_class subclass)
+{
+	spin_lock_nested(&unix_sk(sk)->lock, subclass);
+}
+
 #define peer_wait peer_wq.wait
 
 long unix_inq_len(struct sock *sk);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 4dabeb6c76d3..9b09acac538e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -48,6 +48,10 @@ void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
 		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
 {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cf79656ce09c..2b54fdd8ca15 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2910,6 +2910,8 @@ struct cfg80211_bss_ies {
  *	own the beacon_ies, but they're just pointers to the ones from the
  *	@hidden_beacon_bss struct)
  * @proberesp_ies: the information elements from the last Probe Response frame
+ * @proberesp_ecsa_stuck: ECSA element is stuck in the Probe Response frame,
+ *	cannot rely on it having valid data
  * @hidden_beacon_bss: in case this BSS struct represents a probe response from
  *	a BSS that hides the SSID in its beacon, this points to the BSS struct
  *	that holds the beacon data. @beacon_ies is still valid, of course, and
@@ -2950,6 +2952,8 @@ struct cfg80211_bss {
 	u8 chains;
 	s8 chain_signal[IEEE80211_MAX_CHAINS];
 
+	u8 proberesp_ecsa_stuck:1;
+
 	u8 bssid_index;
 	u8 max_bssid_indicator;
 
diff --git a/include/net/ip.h b/include/net/ip.h
index de0c69c57e3c..25cb688bdc62 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -767,7 +767,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
diff --git a/include/net/mctp.h b/include/net/mctp.h
index da86e106c91d..2bff5f47ce82 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -249,6 +249,7 @@ struct mctp_route {
 struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
 				     mctp_eid_t daddr);
 
+/* always takes ownership of skb */
 int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);
 
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 956c752ceb31..a763dd327c6e 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
-			     const struct nf_flow_route *route);
+			     struct nf_flow_route *route);
 
 int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
 void flow_offload_refresh(struct nf_flowtable *flow_table,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4e1ea18eb5f0..510244cc0f8f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -808,10 +808,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 	return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS);
 }
 
-static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
+					  u64 tstamp)
 {
 	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
+	       time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+	return __nft_set_elem_expired(ext, get_jiffies_64());
 }
 
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -1351,6 +1357,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
  *	@type: stateful object numeric type
  *	@owner: module owner
  *	@maxattr: maximum netlink attribute
+ *	@family: address family for AF-specific object types
  *	@policy: netlink attribute policy
  */
 struct nft_object_type {
@@ -1360,6 +1367,7 @@ struct nft_object_type {
 	struct list_head		list;
 	u32				type;
 	unsigned int                    maxattr;
+	u8				family;
 	struct module			*owner;
 	const struct nla_policy		*policy;
 };
@@ -1777,6 +1785,7 @@ struct nftables_pernet {
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
 	u64			table_handle;
+	u64			tstamp;
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
@@ -1789,6 +1798,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net)
 	return net_generic(net, nf_tables_net_id);
 }
 
+static inline u64 nft_net_tstamp(const struct net *net)
+{
+	return nft_pernet(net)->tstamp;
+}
+
 #define __NFT_REDUCE_READONLY	1UL
 #define NFT_REDUCE_READONLY	(void *)__NFT_REDUCE_READONLY
 
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 780a5f6ad4a6..ff27cb2e1662 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -93,7 +93,7 @@ extern const struct nft_set_type nft_set_bitmap_type;
 extern const struct nft_set_type nft_set_pipapo_type;
 extern const struct nft_set_type nft_set_pipapo_avx2_type;
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
 		      const u32 *key, const struct nft_set_ext **ext);
 bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 934fdb977551..cefe0c4bdae3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
 
 static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
 {
-#ifdef CONFIG_BQL
-	/* Non-BQL migrated drivers will return 0, too. */
-	return dql_avail(&txq->dql);
-#else
-	return 0;
-#endif
+	return netdev_queue_dql_avail(txq);
 }
 
 struct Qdisc_class_ops {
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index a43062d4c734..8346b0d29542 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -308,6 +308,9 @@ void switchdev_deferred_process(void);
 int switchdev_port_attr_set(struct net_device *dev,
 			    const struct switchdev_attr *attr,
 			    struct netlink_ext_ack *extack);
+bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
+					enum switchdev_notifier_type nt,
+					const struct switchdev_obj *obj);
 int switchdev_port_obj_add(struct net_device *dev,
 			   const struct switchdev_obj *obj,
 			   struct netlink_ext_ack *extack);
diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h
index a608546bcefc..ffe58a02537c 100644
--- a/include/net/tc_wrapper.h
+++ b/include/net/tc_wrapper.h
@@ -4,7 +4,7 @@
 
 #include <net/pkt_cls.h>
 
-#if IS_ENABLED(CONFIG_RETPOLINE)
+#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)
 
 #include <linux/cpufeature.h>
 #include <linux/static_key.h>
diff --git a/include/net/tcp.h b/include/net/tcp.h
index dd78a1181031..f6eba9652d01 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2506,7 +2506,7 @@ struct tcp_ulp_ops {
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 	/* diagnostic */
-	int (*get_info)(const struct sock *sk, struct sk_buff *skb);
+	int (*get_info)(struct sock *sk, struct sk_buff *skb);
 	size_t (*get_info_size)(const struct sock *sk);
 	/* clone ulp */
 	void (*clone)(const struct request_sock *req, struct sock *newsk,
diff --git a/include/net/tls.h b/include/net/tls.h
index 962f0c501111..340ad43971e4 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -97,9 +97,6 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
-	/* protect crypto_wait with encrypt_pending */
-	spinlock_t encrypt_compl_lock;
-	int async_notify;
 	u8 async_capable:1;
 
 #define BIT_TX_SCHEDULED	0
@@ -136,8 +133,6 @@ struct tls_sw_context_rx {
 	struct tls_strparser strp;
 
 	atomic_t decrypt_pending;
-	/* protect crypto_wait with decrypt_pending*/
-	spinlock_t decrypt_compl_lock;
 	struct sk_buff_head async_hold;
 	struct wait_queue_head wq;
 };
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 5ec1e71a09de..c38f4fe5e64c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -100,10 +100,6 @@ struct scsi_vpd {
 	unsigned char	data[];
 };
 
-enum scsi_vpd_parameters {
-	SCSI_VPD_HEADER_SIZE = 4,
-};
-
 struct scsi_device {
 	struct Scsi_Host *host;
 	struct request_queue *request_queue;
@@ -208,6 +204,7 @@ struct scsi_device {
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
 	unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */
+	unsigned read_before_ms:1;	/* perform a READ before MODE SENSE */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned no_write_same:1;	/* no WRITE SAME command */
 	unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
diff --git a/include/soc/qcom/qcom-spmi-pmic.h b/include/soc/qcom/qcom-spmi-pmic.h
index 17a0a8c3d656..a62d500a6fda 100644
--- a/include/soc/qcom/qcom-spmi-pmic.h
+++ b/include/soc/qcom/qcom-spmi-pmic.h
@@ -49,7 +49,7 @@
 #define PMK8350_SUBTYPE		0x2f
 #define PMR735B_SUBTYPE		0x34
 #define PM6350_SUBTYPE		0x36
-#define PM2250_SUBTYPE		0x37
+#define PM4125_SUBTYPE		0x37
 
 #define PMI8998_FAB_ID_SMIC	0x11
 #define PMI8998_FAB_ID_GF	0x30
diff --git a/include/soc/qcom/spm.h b/include/soc/qcom/spm.h
index 4951f9d8b0bd..5b263c685812 100644
--- a/include/soc/qcom/spm.h
+++ b/include/soc/qcom/spm.h
@@ -7,11 +7,6 @@
 #ifndef __SPM_H__
 #define __SPM_H__
 
-#include <linux/cpuidle.h>
-
-#define MAX_PMIC_DATA		2
-#define MAX_SEQ_DATA		64
-
 enum pm_sleep_mode {
 	PM_SLEEP_MODE_STBY,
 	PM_SLEEP_MODE_RET,
@@ -20,23 +15,7 @@ enum pm_sleep_mode {
 	PM_SLEEP_MODE_NR,
 };
 
-struct spm_reg_data {
-	const u16 *reg_offset;
-	u32 spm_cfg;
-	u32 spm_dly;
-	u32 pmic_dly;
-	u32 pmic_data[MAX_PMIC_DATA];
-	u32 avs_ctl;
-	u32 avs_limit;
-	u8 seq[MAX_SEQ_DATA];
-	u8 start_index[PM_SLEEP_MODE_NR];
-};
-
-struct spm_driver_data {
-	void __iomem *reg_base;
-	const struct spm_reg_data *reg_data;
-};
-
+struct spm_driver_data;
 void spm_set_low_power_mode(struct spm_driver_data *drv,
 			    enum pm_sleep_mode mode);
 
diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h
index 3a513be50243..8f421b9f7585 100644
--- a/include/soc/tegra/fuse.h
+++ b/include/soc/tegra/fuse.h
@@ -17,6 +17,7 @@
 #define TEGRA186	0x18
 #define TEGRA194	0x19
 #define TEGRA234	0x23
+#define TEGRA241	0x24
 #define TEGRA264	0x26
 
 #define TEGRA_FUSE_SKU_CALIB_0	0xf0
diff --git a/include/soc/tegra/pmc.h b/include/soc/tegra/pmc.h
index aadb845d281d..c545875d0ff1 100644
--- a/include/soc/tegra/pmc.h
+++ b/include/soc/tegra/pmc.h
@@ -148,10 +148,6 @@ enum tegra_io_pad {
 	TEGRA_IO_PAD_AO_HV,
 };
 
-/* deprecated, use TEGRA_IO_PAD_{HDMI,LVDS} instead */
-#define TEGRA_IO_RAIL_HDMI	TEGRA_IO_PAD_HDMI
-#define TEGRA_IO_RAIL_LVDS	TEGRA_IO_PAD_LVDS
-
 #ifdef CONFIG_SOC_TEGRA_PMC
 int tegra_powergate_power_on(unsigned int id);
 int tegra_powergate_power_off(unsigned int id);
@@ -164,10 +160,6 @@ int tegra_powergate_sequence_power_up(unsigned int id, struct clk *clk,
 int tegra_io_pad_power_enable(enum tegra_io_pad id);
 int tegra_io_pad_power_disable(enum tegra_io_pad id);
 
-/* deprecated, use tegra_io_pad_power_{enable,disable}() instead */
-int tegra_io_rail_power_on(unsigned int id);
-int tegra_io_rail_power_off(unsigned int id);
-
 void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode);
 void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode);
 
@@ -211,16 +203,6 @@ static inline int tegra_io_pad_get_voltage(enum tegra_io_pad id)
 	return -ENOSYS;
 }
 
-static inline int tegra_io_rail_power_on(unsigned int id)
-{
-	return -ENOSYS;
-}
-
-static inline int tegra_io_rail_power_off(unsigned int id)
-{
-	return -ENOSYS;
-}
-
 static inline void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode)
 {
 }
diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 8c18e8b6d27d..b24716ab2750 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -75,6 +75,7 @@
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_0		0x25E2040
 #define CS35L56_DSP1_AHBM_WINDOW_DEBUG_1		0x25E2044
 #define CS35L56_DSP1_XMEM_UNPACKED24_0			0x2800000
+#define CS35L56_DSP1_FW_VER				0x2800010
 #define CS35L56_DSP1_HALO_STATE_A1			0x2801E58
 #define CS35L56_DSP1_HALO_STATE				0x28021E0
 #define CS35L56_DSP1_PM_CUR_STATE_A1			0x2804000
@@ -241,7 +242,7 @@
 
 #define CS35L56_CONTROL_PORT_READY_US			2200
 #define CS35L56_HALO_STATE_POLL_US			1000
-#define CS35L56_HALO_STATE_TIMEOUT_US			50000
+#define CS35L56_HALO_STATE_TIMEOUT_US			250000
 #define CS35L56_RESET_PULSE_MIN_US			1100
 #define CS35L56_WAKE_HOLD_TIME_US			1000
 
@@ -272,6 +273,7 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
 extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
 
 int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base);
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
 int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
 int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base);
@@ -284,7 +286,10 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_suspend_common(struct cs35l56_base *cs35l56_base);
 int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_soundwire);
 void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp);
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version);
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base);
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base);
 int cs35l56_get_bclk_freq_id(unsigned int freq);
 void cs35l56_fill_supply_names(struct regulator_bulk_data *data);
 
diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h
index ecc02e955279..1f4c39922d82 100644
--- a/include/sound/soc-card.h
+++ b/include/sound/soc-card.h
@@ -30,6 +30,8 @@ static inline void snd_soc_card_mutex_unlock(struct snd_soc_card *card)
 
 struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
 					       const char *name);
+struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card,
+						      const char *name);
 int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type,
 			  struct snd_soc_jack *jack);
 int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id,
diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index b00d65417c31..9aff384941de 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -142,6 +142,7 @@ struct tasdevice_priv {
 
 void tas2781_reset(struct tasdevice_priv *tas_dev);
 int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+	struct module *module,
 	void (*cont)(const struct firmware *fw, void *context));
 struct tasdevice_priv *tasdevice_kzalloc(struct i2c_client *i2c);
 int tasdevice_init(struct tasdevice_priv *tas_priv);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 08f2c93d6b16..450c44c83a5d 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1189,8 +1189,8 @@ TRACE_EVENT(afs_flock_op,
 		    __entry->from = fl->fl_start;
 		    __entry->len = fl->fl_end - fl->fl_start + 1;
 		    __entry->op = op;
-		    __entry->type = fl->fl_type;
-		    __entry->flags = fl->fl_flags;
+		    __entry->type = fl->c.flc_type;
+		    __entry->flags = fl->c.flc_flags;
 		    __entry->debug_id = fl->fl_u.afs.debug_id;
 			   ),
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 65029dfb92fb..a697f4b77162 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -772,15 +772,14 @@ TRACE_EVENT(ext4_mb_release_group_pa,
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
-	TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
+	TP_PROTO(struct inode *inode, unsigned int len),
 
-	TP_ARGS(inode, len, needed),
+	TP_ARGS(inode, len),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,		dev		)
 		__field(	ino_t,		ino		)
 		__field(	unsigned int,	len		)
-		__field(	unsigned int,	needed		)
 
 	),
 
@@ -788,13 +787,11 @@ TRACE_EVENT(ext4_discard_preallocations,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->len	= len;
-		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %d,%d ino %lu len: %u needed %u",
+	TP_printk("dev %d,%d ino %lu len: %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino, __entry->len,
-		  __entry->needed)
+		  (unsigned long) __entry->ino, __entry->len)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 1646dadd7f37..b8d1e00a7982 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -68,11 +68,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__field(struct file_lock *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_blocker)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_pid)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
+		__field(struct file_lock_core *, blocker)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, pid)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
 		__field(loff_t, fl_start)
 		__field(loff_t, fl_end)
 		__field(int, ret)
@@ -82,11 +82,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
-		__entry->fl_owner = fl ? fl->fl_owner : NULL;
-		__entry->fl_pid = fl ? fl->fl_pid : 0;
-		__entry->fl_flags = fl ? fl->fl_flags : 0;
-		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->blocker = fl ? fl->c.flc_blocker : NULL;
+		__entry->owner = fl ? fl->c.flc_owner : NULL;
+		__entry->pid = fl ? fl->c.flc_pid : 0;
+		__entry->flags = fl ? fl->c.flc_flags : 0;
+		__entry->type = fl ? fl->c.flc_type : 0;
 		__entry->fl_start = fl ? fl->fl_start : 0;
 		__entry->fl_end = fl ? fl->fl_end : 0;
 		__entry->ret = ret;
@@ -94,9 +94,9 @@ DECLARE_EVENT_CLASS(filelock_lock,
 
 	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
-		__entry->fl_pid, show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type),
+		__entry->i_ino, __entry->blocker, __entry->owner,
+		__entry->pid, show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type),
 		__entry->fl_start, __entry->fl_end, __entry->ret)
 );
 
@@ -117,59 +117,59 @@ DEFINE_EVENT(filelock_lock, flock_lock_inode,
 		TP_ARGS(inode, fl, ret));
 
 DECLARE_EVENT_CLASS(filelock_lease,
-	TP_PROTO(struct inode *inode, struct file_lock *fl),
+	TP_PROTO(struct inode *inode, struct file_lease *fl),
 
 	TP_ARGS(inode, fl),
 
 	TP_STRUCT__entry(
-		__field(struct file_lock *, fl)
+		__field(struct file_lease *, fl)
 		__field(unsigned long, i_ino)
 		__field(dev_t, s_dev)
-		__field(struct file_lock *, fl_blocker)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
-		__field(unsigned long, fl_break_time)
-		__field(unsigned long, fl_downgrade_time)
+		__field(struct file_lock_core *, blocker)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
+		__field(unsigned long, break_time)
+		__field(unsigned long, downgrade_time)
 	),
 
 	TP_fast_assign(
 		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_blocker = fl ? fl->fl_blocker : NULL;
-		__entry->fl_owner = fl ? fl->fl_owner : NULL;
-		__entry->fl_flags = fl ? fl->fl_flags : 0;
-		__entry->fl_type = fl ? fl->fl_type : 0;
-		__entry->fl_break_time = fl ? fl->fl_break_time : 0;
-		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
+		__entry->blocker = fl ? fl->c.flc_blocker : NULL;
+		__entry->owner = fl ? fl->c.flc_owner : NULL;
+		__entry->flags = fl ? fl->c.flc_flags : 0;
+		__entry->type = fl ? fl->c.flc_type : 0;
+		__entry->break_time = fl ? fl->fl_break_time : 0;
+		__entry->downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
 	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
-		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
-		show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type),
-		__entry->fl_break_time, __entry->fl_downgrade_time)
+		__entry->i_ino, __entry->blocker, __entry->owner,
+		show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type),
+		__entry->break_time, __entry->downgrade_time)
 );
 
-DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
-DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lease *fl),
 		TP_ARGS(inode, fl));
 
 TRACE_EVENT(generic_add_lease,
-	TP_PROTO(struct inode *inode, struct file_lock *fl),
+	TP_PROTO(struct inode *inode, struct file_lease *fl),
 
 	TP_ARGS(inode, fl),
 
@@ -179,9 +179,9 @@ TRACE_EVENT(generic_add_lease,
 		__field(int, rcount)
 		__field(int, icount)
 		__field(dev_t, s_dev)
-		__field(fl_owner_t, fl_owner)
-		__field(unsigned int, fl_flags)
-		__field(unsigned char, fl_type)
+		__field(fl_owner_t, owner)
+		__field(unsigned int, flags)
+		__field(unsigned char, type)
 	),
 
 	TP_fast_assign(
@@ -190,21 +190,21 @@ TRACE_EVENT(generic_add_lease,
 		__entry->wcount = atomic_read(&inode->i_writecount);
 		__entry->rcount = atomic_read(&inode->i_readcount);
 		__entry->icount = atomic_read(&inode->i_count);
-		__entry->fl_owner = fl->fl_owner;
-		__entry->fl_flags = fl->fl_flags;
-		__entry->fl_type = fl->fl_type;
+		__entry->owner = fl->c.flc_owner;
+		__entry->flags = fl->c.flc_flags;
+		__entry->type = fl->c.flc_type;
 	),
 
 	TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s",
 		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino, __entry->wcount, __entry->rcount,
-		__entry->icount, __entry->fl_owner,
-		show_fl_flags(__entry->fl_flags),
-		show_fl_type(__entry->fl_type))
+		__entry->icount, __entry->owner,
+		show_fl_flags(__entry->flags),
+		show_fl_type(__entry->type))
 );
 
 TRACE_EVENT(leases_conflict,
-	TP_PROTO(bool conflict, struct file_lock *lease, struct file_lock *breaker),
+	TP_PROTO(bool conflict, struct file_lease *lease, struct file_lease *breaker),
 
 	TP_ARGS(conflict, lease, breaker),
 
@@ -220,11 +220,11 @@ TRACE_EVENT(leases_conflict,
 
 	TP_fast_assign(
 		__entry->lease = lease;
-		__entry->l_fl_flags = lease->fl_flags;
-		__entry->l_fl_type = lease->fl_type;
+		__entry->l_fl_flags = lease->c.flc_flags;
+		__entry->l_fl_type = lease->c.flc_type;
 		__entry->breaker = breaker;
-		__entry->b_fl_flags = breaker->fl_flags;
-		__entry->b_fl_type = breaker->fl_type;
+		__entry->b_fl_flags = breaker->c.flc_flags;
+		__entry->b_fl_type = breaker->c.flc_type;
 		__entry->conflict = conflict;
 	),
 
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 69454f1f98b0..e948df7ce625 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -148,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__field(  void *,			req		)
 		__field(  u64,				user_data	)
 		__field(  u8,				opcode		)
-		__field(  unsigned int,			flags		)
+		__field(  unsigned long long,		flags		)
 		__field(  struct io_wq_work *,		work		)
 		__field(  int,				rw		)
 
@@ -159,7 +159,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__entry->ctx		= req->ctx;
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->opcode		= req->opcode;
 		__entry->work		= &req->work;
 		__entry->rw		= rw;
@@ -167,10 +167,10 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%llx, %s queue, work %p",
 		__entry->ctx, __entry->req, __entry->user_data,
-		__get_str(op_str),
-		__entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
+		__get_str(op_str), __entry->flags,
+		__entry->rw ? "hashed" : "normal", __entry->work)
 );
 
 /**
@@ -378,7 +378,7 @@ TRACE_EVENT(io_uring_submit_req,
 		__field(  void *,		req		)
 		__field(  unsigned long long,	user_data	)
 		__field(  u8,			opcode		)
-		__field(  u32,			flags		)
+		__field(  unsigned long long,	flags		)
 		__field(  bool,			sq_thread	)
 
 		__string( op_str, io_uring_get_opcode(req->opcode) )
@@ -389,16 +389,16 @@ TRACE_EVENT(io_uring_submit_req,
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
 		__entry->opcode		= req->opcode;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->sq_thread	= req->ctx->flags & IORING_SETUP_SQPOLL;
 
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%llx, "
 		  "sq_thread %d", __entry->ctx, __entry->req,
-		  __entry->user_data, __get_str(op_str),
-		  __entry->flags, __entry->sq_thread)
+		  __entry->user_data, __get_str(op_str), __entry->flags,
+		  __entry->sq_thread)
 );
 
 /*
@@ -602,29 +602,25 @@ TRACE_EVENT(io_uring_cqe_overflow,
  *
  * @tctx:		pointer to a io_uring_task
  * @count:		how many functions it ran
- * @loops:		how many loops it ran
  *
  */
 TRACE_EVENT(io_uring_task_work_run,
 
-	TP_PROTO(void *tctx, unsigned int count, unsigned int loops),
+	TP_PROTO(void *tctx, unsigned int count),
 
-	TP_ARGS(tctx, count, loops),
+	TP_ARGS(tctx, count),
 
 	TP_STRUCT__entry (
 		__field(  void *,		tctx		)
 		__field(  unsigned int,		count		)
-		__field(  unsigned int,		loops		)
 	),
 
 	TP_fast_assign(
 		__entry->tctx		= tctx;
 		__entry->count		= count;
-		__entry->loops		= loops;
 	),
 
-	TP_printk("tctx %p, count %u, loops %u",
-		 __entry->tctx, __entry->count, __entry->loops)
+	TP_printk("tctx %p, count %u", __entry->tctx, __entry->count)
 );
 
 TRACE_EVENT(io_uring_short_write,
diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index a3995925cb05..1f4258308b96 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset,
 	TP_ARGS(q),
 
 	TP_STRUCT__entry(
-		__string(	dev,		qdisc_dev(q)	)
-		__string(	kind,		q->ops->id	)
-		__field(	u32,		parent		)
-		__field(	u32,		handle		)
+		__string(	dev,		qdisc_dev(q)->name	)
+		__string(	kind,		q->ops->id		)
+		__field(	u32,		parent			)
+		__field(	u32,		handle			)
 	),
 
 	TP_fast_assign(
-		__assign_str(dev, qdisc_dev(q));
+		__assign_str(dev, qdisc_dev(q)->name);
 		__assign_str(kind, q->ops->id);
 		__entry->parent = q->parent;
 		__entry->handle = q->handle;
@@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy,
 	TP_ARGS(q),
 
 	TP_STRUCT__entry(
-		__string(	dev,		qdisc_dev(q)	)
-		__string(	kind,		q->ops->id	)
-		__field(	u32,		parent		)
-		__field(	u32,		handle		)
+		__string(	dev,		qdisc_dev(q)->name	)
+		__string(	kind,		q->ops->id		)
+		__field(	u32,		parent			)
+		__field(	u32,		handle			)
 	),
 
 	TP_fast_assign(
-		__assign_str(dev, qdisc_dev(q));
+		__assign_str(dev, qdisc_dev(q)->name);
 		__assign_str(kind, q->ops->id);
 		__entry->parent = q->parent;
 		__entry->handle = q->handle;
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 110c1475c527..027ac3ab457d 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2118,6 +2118,10 @@ DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_write);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_err);
 
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_reply);
+DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_reply_flush);
+DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_reply_err);
+
 TRACE_EVENT(svcrdma_qp_error,
 	TP_PROTO(
 		const struct ib_event *event,
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c1ef7b3705c..87b8de9b6c1c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -128,6 +128,7 @@
 	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
+	EM(rxrpc_skb_get_last_nack,		"GET last-nack") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
 	EM(rxrpc_skb_get_to_recvmsg,		"GET to-recv  ") \
@@ -141,6 +142,7 @@
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
+	EM(rxrpc_skb_put_last_nack,		"PUT last-nack") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
@@ -1552,7 +1554,7 @@ TRACE_EVENT(rxrpc_congest,
 		    memcpy(&__entry->sum, summary, sizeof(__entry->sum));
 			   ),
 
-	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s",
 		      __entry->call,
 		      __entry->ack_serial,
 		      __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1560,9 +1562,9 @@ TRACE_EVENT(rxrpc_congest,
 		      __print_symbolic(__entry->sum.mode, rxrpc_congest_modes),
 		      __entry->sum.cwnd,
 		      __entry->sum.ssthresh,
-		      __entry->sum.nr_acks, __entry->sum.saw_nacks,
+		      __entry->sum.nr_acks, __entry->sum.nr_retained_nacks,
 		      __entry->sum.nr_new_acks,
-		      __entry->sum.nr_rot_new_acks,
+		      __entry->sum.nr_new_nacks,
 		      __entry->top - __entry->hard_ack,
 		      __entry->sum.cumulative_acks,
 		      __entry->sum.dup_acks,
diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h
new file mode 100644
index 000000000000..79f19e76a80b
--- /dev/null
+++ b/include/trace/events/timer_migration.h
@@ -0,0 +1,298 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM timer_migration
+
+#if !defined(_TRACE_TIMER_MIGRATION_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TIMER_MIGRATION_H
+
+#include <linux/tracepoint.h>
+
+/* Group events */
+TRACE_EVENT(tmigr_group_set,
+
+	TP_PROTO(struct tmigr_group *group),
+
+	TP_ARGS(group),
+
+	TP_STRUCT__entry(
+		__field( void *,	group		)
+		__field( unsigned int,	lvl		)
+		__field( unsigned int,	numa_node	)
+	),
+
+	TP_fast_assign(
+		__entry->group		= group;
+		__entry->lvl		= group->level;
+		__entry->numa_node	= group->numa_node;
+	),
+
+	TP_printk("group=%p lvl=%d numa=%d",
+		  __entry->group, __entry->lvl, __entry->numa_node)
+);
+
+TRACE_EVENT(tmigr_connect_child_parent,
+
+	TP_PROTO(struct tmigr_group *child),
+
+	TP_ARGS(child),
+
+	TP_STRUCT__entry(
+		__field( void *,	child		)
+		__field( void *,	parent		)
+		__field( unsigned int,	lvl		)
+		__field( unsigned int,	numa_node	)
+		__field( unsigned int,	num_children	)
+		__field( u32,		childmask	)
+	),
+
+	TP_fast_assign(
+		__entry->child		= child;
+		__entry->parent		= child->parent;
+		__entry->lvl		= child->parent->level;
+		__entry->numa_node	= child->parent->numa_node;
+		__entry->num_children	= child->parent->num_children;
+		__entry->childmask	= child->childmask;
+	),
+
+	TP_printk("group=%p childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->child,  __entry->childmask, __entry->parent,
+		  __entry->lvl, __entry->numa_node, __entry->num_children)
+);
+
+TRACE_EVENT(tmigr_connect_cpu_parent,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc),
+
+	TP_STRUCT__entry(
+		__field( void *,	parent		)
+		__field( unsigned int,	cpu		)
+		__field( unsigned int,	lvl		)
+		__field( unsigned int,	numa_node	)
+		__field( unsigned int,	num_children	)
+		__field( u32,		childmask	)
+	),
+
+	TP_fast_assign(
+		__entry->parent		= tmc->tmgroup;
+		__entry->cpu		= tmc->cpuevt.cpu;
+		__entry->lvl		= tmc->tmgroup->level;
+		__entry->numa_node	= tmc->tmgroup->numa_node;
+		__entry->num_children	= tmc->tmgroup->num_children;
+		__entry->childmask	= tmc->childmask;
+	),
+
+	TP_printk("cpu=%d childmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
+		  __entry->cpu,	 __entry->childmask, __entry->parent,
+		  __entry->lvl, __entry->numa_node, __entry->num_children)
+);
+
+DECLARE_EVENT_CLASS(tmigr_group_and_cpu,
+
+	TP_PROTO(struct tmigr_group *group, union tmigr_state state, u32 childmask),
+
+	TP_ARGS(group, state, childmask),
+
+	TP_STRUCT__entry(
+		__field( void *,	group		)
+		__field( void *,	parent		)
+		__field( unsigned int,	lvl		)
+		__field( unsigned int,	numa_node	)
+		__field( u32,		childmask	)
+		__field( u8,		active		)
+		__field( u8,		migrator	)
+	),
+
+	TP_fast_assign(
+		__entry->group		= group;
+		__entry->parent		= group->parent;
+		__entry->lvl		= group->level;
+		__entry->numa_node	= group->numa_node;
+		__entry->childmask	= childmask;
+		__entry->active		= state.active;
+		__entry->migrator	= state.migrator;
+	),
+
+	TP_printk("group=%p lvl=%d numa=%d active=%0x migrator=%0x "
+		  "parent=%p childmask=%0x",
+		  __entry->group, __entry->lvl, __entry->numa_node,
+		  __entry->active, __entry->migrator,
+		  __entry->parent, __entry->childmask)
+);
+
+DEFINE_EVENT(tmigr_group_and_cpu, tmigr_group_set_cpu_inactive,
+
+	TP_PROTO(struct tmigr_group *group, union tmigr_state state, u32 childmask),
+
+	TP_ARGS(group, state, childmask)
+);
+
+DEFINE_EVENT(tmigr_group_and_cpu, tmigr_group_set_cpu_active,
+
+	TP_PROTO(struct tmigr_group *group, union tmigr_state state, u32 childmask),
+
+	TP_ARGS(group, state, childmask)
+);
+
+/* CPU events*/
+DECLARE_EVENT_CLASS(tmigr_cpugroup,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc),
+
+	TP_STRUCT__entry(
+		__field( u64,		wakeup	)
+		__field( void *,	parent	)
+		__field( unsigned int,	cpu	)
+
+	),
+
+	TP_fast_assign(
+		__entry->wakeup		= tmc->wakeup;
+		__entry->parent		= tmc->tmgroup;
+		__entry->cpu		= tmc->cpuevt.cpu;
+	),
+
+	TP_printk("cpu=%d parent=%p wakeup=%llu", __entry->cpu, __entry->parent, __entry->wakeup)
+);
+
+DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_new_timer,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc)
+);
+
+DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_active,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc)
+);
+
+DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_online,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc)
+);
+
+DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_offline,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc)
+);
+
+DEFINE_EVENT(tmigr_cpugroup, tmigr_handle_remote_cpu,
+
+	TP_PROTO(struct tmigr_cpu *tmc),
+
+	TP_ARGS(tmc)
+);
+
+DECLARE_EVENT_CLASS(tmigr_idle,
+
+	TP_PROTO(struct tmigr_cpu *tmc, u64 nextevt),
+
+	TP_ARGS(tmc, nextevt),
+
+	TP_STRUCT__entry(
+		__field( u64,		nextevt)
+		__field( u64,		wakeup)
+		__field( void *,	parent)
+		__field( unsigned int,	cpu)
+	),
+
+	TP_fast_assign(
+		__entry->nextevt	= nextevt;
+		__entry->wakeup		= tmc->wakeup;
+		__entry->parent		= tmc->tmgroup;
+		__entry->cpu		= tmc->cpuevt.cpu;
+	),
+
+	TP_printk("cpu=%d parent=%p nextevt=%llu wakeup=%llu",
+		  __entry->cpu, __entry->parent, __entry->nextevt, __entry->wakeup)
+);
+
+DEFINE_EVENT(tmigr_idle, tmigr_cpu_idle,
+
+	TP_PROTO(struct tmigr_cpu *tmc, u64 nextevt),
+
+	TP_ARGS(tmc, nextevt)
+);
+
+DEFINE_EVENT(tmigr_idle, tmigr_cpu_new_timer_idle,
+
+	TP_PROTO(struct tmigr_cpu *tmc, u64 nextevt),
+
+	TP_ARGS(tmc, nextevt)
+);
+
+TRACE_EVENT(tmigr_update_events,
+
+	TP_PROTO(struct tmigr_group *child, struct tmigr_group *group,
+		 union tmigr_state childstate,	union tmigr_state groupstate,
+		 u64 nextevt),
+
+	TP_ARGS(child, group, childstate, groupstate, nextevt),
+
+	TP_STRUCT__entry(
+		__field( void *,	child			)
+		__field( void *,	group			)
+		__field( u64,		nextevt			)
+		__field( u64,		group_next_expiry	)
+		__field( u64,		child_evt_expiry	)
+		__field( unsigned int,	group_lvl		)
+		__field( unsigned int,	child_evtcpu		)
+		__field( u8,		child_active		)
+		__field( u8,		group_active		)
+	),
+
+	TP_fast_assign(
+		__entry->child			= child;
+		__entry->group			= group;
+		__entry->nextevt		= nextevt;
+		__entry->group_next_expiry	= group->next_expiry;
+		__entry->child_evt_expiry	= child ? child->groupevt.nextevt.expires : 0;
+		__entry->group_lvl		= group->level;
+		__entry->child_evtcpu		= child ? child->groupevt.cpu : 0;
+		__entry->child_active		= childstate.active;
+		__entry->group_active		= groupstate.active;
+	),
+
+	TP_printk("child=%p group=%p group_lvl=%d child_active=%0x group_active=%0x "
+		  "nextevt=%llu next_expiry=%llu child_evt_expiry=%llu child_evtcpu=%d",
+		  __entry->child, __entry->group, __entry->group_lvl, __entry->child_active,
+		  __entry->group_active,
+		  __entry->nextevt, __entry->group_next_expiry, __entry->child_evt_expiry,
+		  __entry->child_evtcpu)
+);
+
+TRACE_EVENT(tmigr_handle_remote,
+
+	TP_PROTO(struct tmigr_group *group),
+
+	TP_ARGS(group),
+
+	TP_STRUCT__entry(
+		__field( void * ,	group	)
+		__field( unsigned int ,	lvl	)
+	),
+
+	TP_fast_assign(
+		__entry->group		= group;
+		__entry->lvl		= group->level;
+	),
+
+	TP_printk("group=%p lvl=%d",
+		   __entry->group, __entry->lvl)
+);
+
+#endif /*  _TRACE_TIMER_MIGRATION_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h
index 0d9d48dca38a..64ab5dac59ce 100644
--- a/include/trace/misc/nfs.h
+++ b/include/trace/misc/nfs.h
@@ -385,3 +385,37 @@ TRACE_DEFINE_ENUM(IOMODE_ANY);
 		{ SEQ4_STATUS_RESTART_RECLAIM_NEEDED,	"RESTART_RECLAIM_NEEDED" }, \
 		{ SEQ4_STATUS_CB_PATH_DOWN_SESSION,	"CB_PATH_DOWN_SESSION" }, \
 		{ SEQ4_STATUS_BACKCHANNEL_FAULT,	"BACKCHANNEL_FAULT" })
+
+TRACE_DEFINE_ENUM(OP_CB_GETATTR);
+TRACE_DEFINE_ENUM(OP_CB_RECALL);
+TRACE_DEFINE_ENUM(OP_CB_LAYOUTRECALL);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY);
+TRACE_DEFINE_ENUM(OP_CB_PUSH_DELEG);
+TRACE_DEFINE_ENUM(OP_CB_RECALL_ANY);
+TRACE_DEFINE_ENUM(OP_CB_RECALLABLE_OBJ_AVAIL);
+TRACE_DEFINE_ENUM(OP_CB_RECALL_SLOT);
+TRACE_DEFINE_ENUM(OP_CB_SEQUENCE);
+TRACE_DEFINE_ENUM(OP_CB_WANTS_CANCELLED);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY_LOCK);
+TRACE_DEFINE_ENUM(OP_CB_NOTIFY_DEVICEID);
+TRACE_DEFINE_ENUM(OP_CB_OFFLOAD);
+TRACE_DEFINE_ENUM(OP_CB_ILLEGAL);
+
+#define show_nfs4_cb_op(x) \
+	__print_symbolic(x, \
+		{ 0,				"CB_NULL" }, \
+		{ 1,				"CB_COMPOUND" }, \
+		{ OP_CB_GETATTR,		"CB_GETATTR" }, \
+		{ OP_CB_RECALL,			"CB_RECALL" }, \
+		{ OP_CB_LAYOUTRECALL,		"CB_LAYOUTRECALL" }, \
+		{ OP_CB_NOTIFY,			"CB_NOTIFY" }, \
+		{ OP_CB_PUSH_DELEG,		"CB_PUSH_DELEG" }, \
+		{ OP_CB_RECALL_ANY,		"CB_RECALL_ANY" }, \
+		{ OP_CB_RECALLABLE_OBJ_AVAIL,	"CB_RECALLABLE_OBJ_AVAIL" }, \
+		{ OP_CB_RECALL_SLOT,		"CB_RECALL_SLOT" }, \
+		{ OP_CB_SEQUENCE,		"CB_SEQUENCE" }, \
+		{ OP_CB_WANTS_CANCELLED,	"CB_WANTS_CANCELLED" }, \
+		{ OP_CB_NOTIFY_LOCK,		"CB_NOTIFY_LOCK" }, \
+		{ OP_CB_NOTIFY_DEVICEID,	"CB_NOTIFY_DEVICEID" }, \
+		{ OP_CB_OFFLOAD,		"CB_OFFLOAD" }, \
+		{ OP_CB_ILLEGAL,		"CB_ILLEGAL" })
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index 63c49318a863..19a13468eca5 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -305,6 +305,7 @@ struct drm_ivpu_submit {
 
 /* drm_ivpu_bo_wait job status codes */
 #define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
 
 /**
  * struct drm_ivpu_bo_wait - Wait for BO to become inactive
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index 0bade1592f34..77d7ff0d5b11 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -54,6 +54,20 @@ extern "C" {
  */
 #define NOUVEAU_GETPARAM_EXEC_PUSH_MAX   17
 
+/*
+ * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size
+ *
+ * Query the VRAM BAR size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18
+
+/*
+ * NOUVEAU_GETPARAM_VRAM_USED
+ *
+ * Get remaining VRAM size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_USED 19
+
 struct drm_nouveau_getparam {
 	__u64 param;
 	__u64 value;
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 9fa3ae324731..bb0c8a994116 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -831,11 +831,6 @@ struct drm_xe_vm_destroy {
  *  - %DRM_XE_VM_BIND_OP_PREFETCH
  *
  * and the @flags can be:
- *  - %DRM_XE_VM_BIND_FLAG_READONLY
- *  - %DRM_XE_VM_BIND_FLAG_ASYNC
- *  - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the
- *    MAP operation immediately rather than deferring the MAP to the page
- *    fault handler.
  *  - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page
  *    tables are setup with a special bit which indicates writes are
  *    dropped and all reads return zero. In the future, the NULL flags
@@ -928,9 +923,8 @@ struct drm_xe_vm_bind_op {
 	/** @op: Bind operation to perform */
 	__u32 op;
 
-#define DRM_XE_VM_BIND_FLAG_READONLY	(1 << 0)
-#define DRM_XE_VM_BIND_FLAG_IMMEDIATE	(1 << 1)
 #define DRM_XE_VM_BIND_FLAG_NULL	(1 << 2)
+#define DRM_XE_VM_BIND_FLAG_DUMPABLE	(1 << 3)
 	/** @flags: Bind flags */
 	__u32 flags;
 
@@ -1045,20 +1039,6 @@ struct drm_xe_exec_queue_create {
 #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY		0
 #define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE		1
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT	2
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE		3
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT		4
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER		5
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY		6
-#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY	7
-/* Monitor 128KB contiguous region with 4K sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_128K				0
-/* Monitor 2MB contiguous region with 64KB sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_2M				1
-/* Monitor 16MB contiguous region with 512KB sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_16M				2
-/* Monitor 64MB contiguous region with 2M sub-granularity */
-#define     DRM_XE_ACC_GRANULARITY_64M				3
 
 	/** @extensions: Pointer to the first extension struct, if any */
 	__u64 extensions;
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index f8bc34a6bcfa..cdf6ad872149 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -92,6 +92,7 @@ struct btrfs_qgroup_limit {
  * struct btrfs_qgroup_inherit.flags
  */
 #define BTRFS_QGROUP_INHERIT_SET_LIMITS	(1ULL << 0)
+#define BTRFS_QGROUP_INHERIT_FLAGS_SUPP (BTRFS_QGROUP_INHERIT_SET_LIMITS)
 
 struct btrfs_qgroup_inherit {
 	__u64	flags;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48ad69f7722e..45e4e64fd664 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -64,6 +64,24 @@ struct fstrim_range {
 	__u64 minlen;
 };
 
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+	__u8	len;
+	__u8	uuid[16];
+};
+
+struct fs_sysfs_path {
+	__u8			len;
+	__u8			name[128];
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -215,6 +233,13 @@ struct fsxattr {
 #define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
 #define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID		_IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
@@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO O_APPEND */
 #define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
 
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND	((__force __kernel_rwf_t)0x00000020)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND)
+			 RWF_APPEND | RWF_NOAPPEND)
 
 /* Pagemap ioctl */
 #define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index 5060963707b1..f2e0b2d50e6b 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -91,8 +91,6 @@ enum iio_modifier {
 	IIO_MOD_CO2,
 	IIO_MOD_VOC,
 	IIO_MOD_LIGHT_UV,
-	IIO_MOD_LIGHT_UVA,
-	IIO_MOD_LIGHT_UVB,
 	IIO_MOD_LIGHT_DUV,
 	IIO_MOD_PM1,
 	IIO_MOD_PM2P5,
@@ -107,6 +105,8 @@ enum iio_modifier {
 	IIO_MOD_PITCH,
 	IIO_MOD_YAW,
 	IIO_MOD_ROLL,
+	IIO_MOD_LIGHT_UVA,
+	IIO_MOD_LIGHT_UVB,
 };
 
 enum iio_event_type {
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index c4c53a9ab959..ff8d21f9e95b 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -145,7 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
-#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
+#define IPV6_TLV_IOAM		49	/* RFC 9486 */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 7a673b52827b..7bd10201a02b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -255,6 +255,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
 	IORING_OP_FIXED_FD_INSTALL,
+	IORING_OP_FTRUNCATE,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -570,6 +571,10 @@ enum {
 	/* return status information for a buffer group */
 	IORING_REGISTER_PBUF_STATUS		= 26,
 
+	/* set/clear busy poll settings */
+	IORING_REGISTER_NAPI			= 27,
+	IORING_UNREGISTER_NAPI			= 28,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -703,6 +708,14 @@ struct io_uring_buf_status {
 	__u32	resv[8];
 };
 
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+	__u32	busy_poll_to;
+	__u8	prefer_busy_poll;
+	__u8	pad[3];
+	__u64	resv;
+};
+
 /*
  * io_uring_restriction->opcode values
  */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 6325d1d0e90f..1b40a968ba91 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -101,5 +101,6 @@
 #define DMA_BUF_MAGIC		0x444d4142	/* "DMAB" */
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
+#define PID_FS_MAGIC		0x50494446	/* "PIDF" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ca30232b7bc8..117c6a9b845b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -285,9 +285,11 @@ enum nft_rule_attributes {
 /**
  * enum nft_rule_compat_flags - nf_tables rule compat flags
  *
+ * @NFT_RULE_COMPAT_F_UNUSED: unused
  * @NFT_RULE_COMPAT_F_INV: invert the check result
  */
 enum nft_rule_compat_flags {
+	NFT_RULE_COMPAT_F_UNUSED = (1 << 0),
 	NFT_RULE_COMPAT_F_INV	= (1 << 1),
 	NFT_RULE_COMPAT_F_MASK	= NFT_RULE_COMPAT_F_INV,
 };
diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
index 5406fbc13074..72ec000a97cd 100644
--- a/include/uapi/linux/pidfd.h
+++ b/include/uapi/linux/pidfd.h
@@ -7,6 +7,12 @@
 #include <linux/fcntl.h>
 
 /* Flags for pidfd_open().  */
-#define PIDFD_NONBLOCK O_NONBLOCK
+#define PIDFD_NONBLOCK	O_NONBLOCK
+#define PIDFD_THREAD	O_EXCL
+
+/* Flags for pidfd_send_signal(). */
+#define PIDFD_SIGNAL_THREAD		(1UL << 0)
+#define PIDFD_SIGNAL_THREAD_GROUP	(1UL << 1)
+#define PIDFD_SIGNAL_PROCESS_GROUP	(1UL << 2)
 
 #endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index b44ba7dcdefc..b7a2c2ee35b7 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -28,6 +28,9 @@ enum {
 	SEV_PEK_CERT_IMPORT,
 	SEV_GET_ID,	/* This command is deprecated, use SEV_GET_ID2 */
 	SEV_GET_ID2,
+	SNP_PLATFORM_STATUS,
+	SNP_COMMIT,
+	SNP_SET_CONFIG,
 
 	SEV_MAX,
 };
@@ -69,6 +72,12 @@ typedef enum {
 	SEV_RET_RESOURCE_LIMIT,
 	SEV_RET_SECURE_DATA_INVALID,
 	SEV_RET_INVALID_KEY = 0x27,
+	SEV_RET_INVALID_PAGE_SIZE,
+	SEV_RET_INVALID_PAGE_STATE,
+	SEV_RET_INVALID_MDATA_ENTRY,
+	SEV_RET_INVALID_PAGE_OWNER,
+	SEV_RET_INVALID_PAGE_AEAD_OFLOW,
+	SEV_RET_RMP_INIT_REQUIRED,
 	SEV_RET_MAX,
 } sev_ret_code;
 
@@ -156,6 +165,56 @@ struct sev_user_data_get_id2 {
 } __packed;
 
 /**
+ * struct sev_user_data_snp_status - SNP status
+ *
+ * @api_major: API major version
+ * @api_minor: API minor version
+ * @state: current platform state
+ * @is_rmp_initialized: whether RMP is initialized or not
+ * @rsvd: reserved
+ * @build_id: firmware build id for the API version
+ * @mask_chip_id: whether chip id is present in attestation reports or not
+ * @mask_chip_key: whether attestation reports are signed or not
+ * @vlek_en: VLEK (Version Loaded Endorsement Key) hashstick is loaded
+ * @rsvd1: reserved
+ * @guest_count: the number of guest currently managed by the firmware
+ * @current_tcb_version: current TCB version
+ * @reported_tcb_version: reported TCB version
+ */
+struct sev_user_data_snp_status {
+	__u8 api_major;			/* Out */
+	__u8 api_minor;			/* Out */
+	__u8 state;			/* Out */
+	__u8 is_rmp_initialized:1;	/* Out */
+	__u8 rsvd:7;
+	__u32 build_id;			/* Out */
+	__u32 mask_chip_id:1;		/* Out */
+	__u32 mask_chip_key:1;		/* Out */
+	__u32 vlek_en:1;		/* Out */
+	__u32 rsvd1:29;
+	__u32 guest_count;		/* Out */
+	__u64 current_tcb_version;	/* Out */
+	__u64 reported_tcb_version;	/* Out */
+} __packed;
+
+/**
+ * struct sev_user_data_snp_config - system wide configuration value for SNP.
+ *
+ * @reported_tcb: the TCB version to report in the guest attestation report.
+ * @mask_chip_id: whether chip id is present in attestation reports or not
+ * @mask_chip_key: whether attestation reports are signed or not
+ * @rsvd: reserved
+ * @rsvd1: reserved
+ */
+struct sev_user_data_snp_config {
+	__u64 reported_tcb  ;   /* In */
+	__u32 mask_chip_id:1;   /* In */
+	__u32 mask_chip_key:1;  /* In */
+	__u32 rsvd:30;          /* In */
+	__u8 rsvd1[52];
+} __packed;
+
+/**
  * struct sev_issue_cmd - SEV ioctl parameters
  *
  * @cmd: SEV commands to execute
diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 9086367db043..de9b4733607e 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -145,12 +145,13 @@ struct serial_rs485 {
 #define SER_RS485_ENABLED		_BITUL(0)
 #define SER_RS485_RTS_ON_SEND		_BITUL(1)
 #define SER_RS485_RTS_AFTER_SEND	_BITUL(2)
-#define SER_RS485_RX_DURING_TX		_BITUL(3)
-#define SER_RS485_TERMINATE_BUS		_BITUL(4)
-#define SER_RS485_ADDRB			_BITUL(5)
-#define SER_RS485_ADDR_RECV		_BITUL(6)
-#define SER_RS485_ADDR_DEST		_BITUL(7)
-#define SER_RS485_MODE_RS422		_BITUL(8)
+/* Placeholder for bit 3: SER_RS485_RTS_BEFORE_SEND, which isn't used anymore */
+#define SER_RS485_RX_DURING_TX		_BITUL(4)
+#define SER_RS485_TERMINATE_BUS		_BITUL(5)
+#define SER_RS485_ADDRB			_BITUL(6)
+#define SER_RS485_ADDR_RECV		_BITUL(7)
+#define SER_RS485_ADDR_DEST		_BITUL(8)
+#define SER_RS485_MODE_RS422		_BITUL(9)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index b9cfc5c96268..c8dc5f8ea699 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -49,6 +49,8 @@
 	_IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_GET_FEATURES	\
 	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_DEL_DEV_ASYNC	\
+	_IOR('u', 0x14, struct ublksrv_ctrl_cmd)
 
 /*
  * 64bits are enough now, and it should be easy to extend in case of
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index d5b9cfbd9cea..628d46a0da92 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 16)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 17)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -416,7 +416,7 @@ struct snd_pcm_hw_params {
 	unsigned int rmask;		/* W: requested masks */
 	unsigned int cmask;		/* R: changed masks */
 	unsigned int info;		/* R: Info flags for returned setup */
-	unsigned int msbits;		/* R: used most significant bits */
+	unsigned int msbits;		/* R: used most significant bits (in sample bit-width) */
 	unsigned int rate_num;		/* R: rate numerator */
 	unsigned int rate_den;		/* R: rate denominator */
 	snd_pcm_uframes_t fifo_size;	/* R: chip FIFO size in frames */
diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h
index 48d2790ef928..3109282672f3 100644
--- a/include/uapi/xen/gntalloc.h
+++ b/include/uapi/xen/gntalloc.h
@@ -31,7 +31,10 @@ struct ioctl_gntalloc_alloc_gref {
 	__u64 index;
 	/* The grant references of the newly created grant, one per page */
 	/* Variable size, depending on count */
-	__u32 gref_ids[1];
+	union {
+		__u32 gref_ids[1];
+		__DECLARE_FLEX_ARRAY(__u32, gref_ids_flex);
+	};
 };
 
 #define GNTALLOC_FLAG_WRITABLE 1
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 73eb622e7663..5d5c0b8efff2 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -19,6 +19,12 @@
 #include <vdso/time32.h>
 #include <vdso/time64.h>
 
+#ifdef CONFIG_ARM64
+#include <asm/page-def.h>
+#else
+#include <asm/page.h>
+#endif
+
 #ifdef CONFIG_ARCH_HAS_VDSO_DATA
 #include <asm/vdso/data.h>
 #else
@@ -121,6 +127,14 @@ struct vdso_data {
 extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
 extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
 
+/**
+ * union vdso_data_store - Generic vDSO data page
+ */
+union vdso_data_store {
+	struct vdso_data	data[CS_BASES];
+	u8			page[PAGE_SIZE];
+};
+
 /*
  * The generic vDSO implementation requires that gettimeofday.h
  * provides:
diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h
index 9a2af9fca45e..73501149439d 100644
--- a/include/vdso/helpers.h
+++ b/include/vdso/helpers.h
@@ -30,9 +30,9 @@ static __always_inline u32 vdso_read_retry(const struct vdso_data *vd,
 static __always_inline void vdso_write_begin(struct vdso_data *vd)
 {
 	/*
-	 * WRITE_ONCE it is required otherwise the compiler can validly tear
+	 * WRITE_ONCE() is required otherwise the compiler can validly tear
 	 * updates to vd[x].seq and it is possible that the value seen by the
-	 * reader it is inconsistent.
+	 * reader is inconsistent.
 	 */
 	WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1);
 	WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1);
@@ -43,9 +43,9 @@ static __always_inline void vdso_write_end(struct vdso_data *vd)
 {
 	smp_wmb();
 	/*
-	 * WRITE_ONCE it is required otherwise the compiler can validly tear
+	 * WRITE_ONCE() is required otherwise the compiler can validly tear
 	 * updates to vd[x].seq and it is possible that the value seen by the
-	 * reader it is inconsistent.
+	 * reader is inconsistent.
 	 */
 	WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1);
 	WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1);
diff --git a/init/Kconfig b/init/Kconfig
index 8d4e836e1b6b..7c5df7b0b576 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT
 	# Detect buggy gcc and clang, fixed in gcc-11 clang-14.
 	def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null)
 
+config GCC_ASM_GOTO_OUTPUT_WORKAROUND
+	bool
+	depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT
+	# Fixed in GCC 14, 13.3, 12.4 and 11.5
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
+	default y if GCC_VERSION < 110500
+	default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400
+	default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300
+
 config TOOLS_SUPPORT_RELR
 	def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh)
 
@@ -106,7 +115,7 @@ config CONSTRUCTORS
 	bool
 
 config IRQ_WORK
-	bool
+	def_bool y if SMP
 
 config BUILDTIME_TABLE_SORT
 	bool
@@ -867,22 +876,22 @@ config CC_IMPLICIT_FALLTHROUGH
 	default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
 	default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
 
-# Currently, disable gcc-11+ array-bounds globally.
+# Currently, disable gcc-10+ array-bounds globally.
 # It's still broken in gcc-13, so no upper bound yet.
-config GCC11_NO_ARRAY_BOUNDS
+config GCC10_NO_ARRAY_BOUNDS
 	def_bool y
 
 config CC_NO_ARRAY_BOUNDS
 	bool
-	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC11_NO_ARRAY_BOUNDS
+	default y if CC_IS_GCC && GCC_VERSION >= 100000 && GCC10_NO_ARRAY_BOUNDS
 
-# Currently, disable -Wstringop-overflow for GCC 11, globally.
-config GCC11_NO_STRINGOP_OVERFLOW
+# Currently, disable -Wstringop-overflow for GCC globally.
+config GCC_NO_STRINGOP_OVERFLOW
 	def_bool y
 
 config CC_NO_STRINGOP_OVERFLOW
 	bool
-	default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_STRINGOP_OVERFLOW
+	default y if CC_IS_GCC && GCC_NO_STRINGOP_OVERFLOW
 
 config CC_STRINGOP_OVERFLOW
 	bool
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 279ad28bf4fb..3c5fd993bc7e 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -208,6 +208,9 @@ retry:
 				goto out;
 			case -EACCES:
 			case -EINVAL:
+#ifdef CONFIG_BLOCK
+				init_flush_fput();
+#endif
 				continue;
 		}
 	        /*
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 15e372b00ce7..6069ea3eb80d 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -9,6 +9,8 @@
 #include <linux/major.h>
 #include <linux/root_dev.h>
 #include <linux/init_syscalls.h>
+#include <linux/task_work.h>
+#include <linux/file.h>
 
 void  mount_root_generic(char *name, char *pretty_name, int flags);
 void  mount_root(char *root_device_name);
@@ -41,3 +43,10 @@ static inline bool initrd_load(char *root_device_name)
 	}
 
 #endif
+
+/* Ensure that async file closing finished to prevent spurious errors. */
+static inline void init_flush_fput(void)
+{
+	flush_delayed_fput();
+	task_work_run();
+}
diff --git a/init/init_task.c b/init/init_task.c
index 7ecb458eb3da..4daee6d761c8 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -147,6 +147,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	.rcu_tasks_holdout = false,
 	.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
 	.rcu_tasks_idle_cpu = -1,
+	.rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
 #endif
 #ifdef CONFIG_TASKS_TRACE_RCU
 	.trc_reader_nesting = 0,
diff --git a/init/initramfs.c b/init/initramfs.c
index 76deb48c38cb..01dbd0e81501 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -16,9 +16,10 @@
 #include <linux/mm.h>
 #include <linux/namei.h>
 #include <linux/init_syscalls.h>
-#include <linux/task_work.h>
 #include <linux/umh.h>
 
+#include "do_mounts.h"
+
 static __initdata bool csum_present;
 static __initdata u32 io_csum;
 
@@ -679,8 +680,6 @@ static void __init populate_initrd_image(char *err)
 	struct file *file;
 	loff_t pos = 0;
 
-	unpack_to_rootfs(__initramfs_start, __initramfs_size);
-
 	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
 			err);
 	file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
@@ -736,8 +735,7 @@ done:
 	initrd_start = 0;
 	initrd_end = 0;
 
-	flush_delayed_fput();
-	task_work_run();
+	init_flush_fput();
 }
 
 static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain);
diff --git a/init/main.c b/init/main.c
index e24b0780fdff..7dce08198b13 100644
--- a/init/main.c
+++ b/init/main.c
@@ -99,6 +99,7 @@
 #include <linux/init_syscalls.h>
 #include <linux/stackdepot.h>
 #include <linux/randomize_kstack.h>
+#include <linux/pidfs.h>
 #include <net/net_namespace.h>
 
 #include <asm/io.h>
@@ -603,7 +604,6 @@ static int __init rdinit_setup(char *str)
 __setup("rdinit=", rdinit_setup);
 
 #ifndef CONFIG_SMP
-static const unsigned int setup_max_cpus = NR_CPUS;
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 #endif
@@ -776,6 +776,10 @@ void __init __weak smp_setup_processor_id(void)
 {
 }
 
+void __init __weak smp_prepare_boot_cpu(void)
+{
+}
+
 # if THREAD_SIZE >= PAGE_SIZE
 void __init __weak thread_stack_cache_init(void)
 {
@@ -1059,6 +1063,7 @@ void start_kernel(void)
 	seq_file_init();
 	proc_root_init();
 	nsfs_init();
+	pidfs_init();
 	cpuset_init();
 	cgroup_init();
 	taskstats_init_early();
@@ -1545,6 +1550,7 @@ static noinline void __init kernel_init_freeable(void)
 	sched_init_smp();
 
 	workqueue_init_topology();
+	async_init();
 	padata_init();
 	page_alloc_init_late();
 
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 2cdc51825405..2e1d4e03799c 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o \
-					notif.o waitid.o register.o
+					notif.o waitid.o register.o truncate.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
+obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index 8a8b07dfc444..acfcdd7f059a 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -58,9 +58,8 @@ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd)
 		return false;
 	if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
 check_seq:
-		if (cd->seq == req->work.cancel_seq)
+		if (io_cancel_match_sequence(req, cd->seq))
 			return false;
-		req->work.cancel_seq = cd->seq;
 	}
 
 	return true;
diff --git a/io_uring/cancel.h b/io_uring/cancel.h
index c0a8e7c520b6..76b32e65c03c 100644
--- a/io_uring/cancel.h
+++ b/io_uring/cancel.h
@@ -25,4 +25,14 @@ void init_hash_table(struct io_hash_table *table, unsigned size);
 int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg);
 bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd);
 
+static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence)
+{
+	if ((req->flags & REQ_F_CANCEL_SEQ) && sequence == req->work.cancel_seq)
+		return true;
+
+	req->flags |= REQ_F_CANCEL_SEQ;
+	req->work.cancel_seq = sequence;
+	return false;
+}
+
 #endif
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 976e9500f651..8d444dd1b0a7 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -55,6 +55,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	struct io_ring_ctx *ctx = f->private_data;
 	struct io_overflow_cqe *ocqe;
 	struct io_rings *r = ctx->rings;
+	struct rusage sq_usage;
 	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
 	unsigned int sq_head = READ_ONCE(r->sq.head);
 	unsigned int sq_tail = READ_ONCE(r->sq.tail);
@@ -64,6 +65,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	unsigned int sq_shift = 0;
 	unsigned int sq_entries, cq_entries;
 	int sq_pid = -1, sq_cpu = -1;
+	u64 sq_total_time = 0, sq_work_time = 0;
 	bool has_lock;
 	unsigned int i;
 
@@ -145,12 +147,24 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
 		struct io_sq_data *sq = ctx->sq_data;
 
-		sq_pid = sq->task_pid;
-		sq_cpu = sq->sq_cpu;
+		/*
+		 * sq->thread might be NULL if we raced with the sqpoll
+		 * thread termination.
+		 */
+		if (sq->thread) {
+			sq_pid = sq->task_pid;
+			sq_cpu = sq->sq_cpu;
+			getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
+			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
+					 + sq_usage.ru_stime.tv_usec);
+			sq_work_time = sq->work_time;
+		}
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
 	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
+	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
 	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
 	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
 		struct file *f = io_file_from_index(&ctx->file_table, i);
diff --git a/io_uring/filetable.h b/io_uring/filetable.h
index b47adf170c31..b2435c4dca1f 100644
--- a/io_uring/filetable.h
+++ b/io_uring/filetable.h
@@ -17,7 +17,7 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
 int io_register_file_alloc_range(struct io_ring_ctx *ctx,
 				 struct io_uring_file_index_range __user *arg);
 
-unsigned int io_file_get_flags(struct file *file);
+io_req_flags_t io_file_get_flags(struct file *file);
 
 static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
 {
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index cd9a137ad6ce..cf348c33f485 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -59,7 +59,6 @@
 #include <linux/bvec.h>
 #include <linux/net.h>
 #include <net/sock.h>
-#include <net/af_unix.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -95,6 +94,7 @@
 #include "notif.h"
 #include "waitid.h"
 #include "futex.h"
+#include "napi.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -122,11 +122,6 @@
 #define IO_COMPL_BATCH			32
 #define IO_REQ_ALLOC_BATCH		8
 
-enum {
-	IO_CHECK_CQ_OVERFLOW_BIT,
-	IO_CHECK_CQ_DROPPED_BIT,
-};
-
 struct io_defer_entry {
 	struct list_head	list;
 	struct io_kiocb		*req;
@@ -349,6 +344,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
 	INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd);
+	io_napi_init(ctx);
+
 	return ctx;
 err:
 	kfree(ctx->cancel_table.hbs);
@@ -463,7 +460,6 @@ static void io_prep_async_work(struct io_kiocb *req)
 
 	req->work.list.next = NULL;
 	req->work.flags = 0;
-	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
 	if (req->flags & REQ_F_FORCE_ASYNC)
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
 
@@ -670,7 +666,6 @@ static void io_cq_unlock_post(struct io_ring_ctx *ctx)
 	io_commit_cqring_flush(ctx);
 }
 
-/* Returns true if there are no backlogged entries after the flush */
 static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
 {
 	struct io_overflow_cqe *ocqe;
@@ -949,6 +944,8 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags)
 	u64 user_data = req->cqe.user_data;
 	struct io_uring_cqe *cqe;
 
+	lockdep_assert(!io_wq_current_is_worker());
+
 	if (!defer)
 		return __io_post_aux_cqe(ctx, user_data, res, cflags, false);
 
@@ -1025,15 +1022,15 @@ static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 
 void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 {
-	if (req->ctx->task_complete && req->ctx->submitter_task != current) {
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (ctx->task_complete && ctx->submitter_task != current) {
 		req->io_task_work.func = io_req_task_complete;
 		io_req_task_work_add(req);
 	} else if (!(issue_flags & IO_URING_F_UNLOCKED) ||
-		   !(req->ctx->flags & IORING_SETUP_IOPOLL)) {
+		   !(ctx->flags & IORING_SETUP_IOPOLL)) {
 		__io_req_complete_post(req, issue_flags);
 	} else {
-		struct io_ring_ctx *ctx = req->ctx;
-
 		mutex_lock(&ctx->uring_lock);
 		__io_req_complete_post(req, issue_flags & ~IO_URING_F_UNLOCKED);
 		mutex_unlock(&ctx->uring_lock);
@@ -1174,40 +1171,44 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
 	percpu_ref_put(&ctx->refs);
 }
 
-static unsigned int handle_tw_list(struct llist_node *node,
-				   struct io_ring_ctx **ctx,
-				   struct io_tw_state *ts,
-				   struct llist_node *last)
+/*
+ * Run queued task_work, returning the number of entries processed in *count.
+ * If more entries than max_entries are available, stop processing once this
+ * is reached and return the rest of the list.
+ */
+struct llist_node *io_handle_tw_list(struct llist_node *node,
+				     unsigned int *count,
+				     unsigned int max_entries)
 {
-	unsigned int count = 0;
+	struct io_ring_ctx *ctx = NULL;
+	struct io_tw_state ts = { };
 
-	while (node && node != last) {
+	do {
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
 
-		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-
-		if (req->ctx != *ctx) {
-			ctx_flush_and_put(*ctx, ts);
-			*ctx = req->ctx;
+		if (req->ctx != ctx) {
+			ctx_flush_and_put(ctx, &ts);
+			ctx = req->ctx;
 			/* if not contended, grab and improve batching */
-			ts->locked = mutex_trylock(&(*ctx)->uring_lock);
-			percpu_ref_get(&(*ctx)->refs);
+			ts.locked = mutex_trylock(&ctx->uring_lock);
+			percpu_ref_get(&ctx->refs);
 		}
 		INDIRECT_CALL_2(req->io_task_work.func,
 				io_poll_task_func, io_req_rw_complete,
-				req, ts);
+				req, &ts);
 		node = next;
-		count++;
+		(*count)++;
 		if (unlikely(need_resched())) {
-			ctx_flush_and_put(*ctx, ts);
-			*ctx = NULL;
+			ctx_flush_and_put(ctx, &ts);
+			ctx = NULL;
 			cond_resched();
 		}
-	}
+	} while (node && *count < max_entries);
 
-	return count;
+	ctx_flush_and_put(ctx, &ts);
+	return node;
 }
 
 /**
@@ -1224,22 +1225,6 @@ static inline struct llist_node *io_llist_xchg(struct llist_head *head,
 	return xchg(&head->first, new);
 }
 
-/**
- * io_llist_cmpxchg - possibly swap all entries in a lock-less list
- * @head:	the head of lock-less list to delete all entries
- * @old:	expected old value of the first entry of the list
- * @new:	new entry as the head of the list
- *
- * perform a cmpxchg on the first entry of the list.
- */
-
-static inline struct llist_node *io_llist_cmpxchg(struct llist_head *head,
-						  struct llist_node *old,
-						  struct llist_node *new)
-{
-	return cmpxchg(&head->first, old, new);
-}
-
 static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 {
 	struct llist_node *node = llist_del_all(&tctx->task_list);
@@ -1268,45 +1253,41 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
 	}
 }
 
-void tctx_task_work(struct callback_head *cb)
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx,
+				      unsigned int max_entries,
+				      unsigned int *count)
 {
-	struct io_tw_state ts = {};
-	struct io_ring_ctx *ctx = NULL;
-	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
-						  task_work);
-	struct llist_node fake = {};
 	struct llist_node *node;
-	unsigned int loops = 0;
-	unsigned int count = 0;
 
 	if (unlikely(current->flags & PF_EXITING)) {
 		io_fallback_tw(tctx, true);
-		return;
+		return NULL;
 	}
 
-	do {
-		loops++;
-		node = io_llist_xchg(&tctx->task_list, &fake);
-		count += handle_tw_list(node, &ctx, &ts, &fake);
-
-		/* skip expensive cmpxchg if there are items in the list */
-		if (READ_ONCE(tctx->task_list.first) != &fake)
-			continue;
-		if (ts.locked && !wq_list_empty(&ctx->submit_state.compl_reqs)) {
-			io_submit_flush_completions(ctx);
-			if (READ_ONCE(tctx->task_list.first) != &fake)
-				continue;
-		}
-		node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL);
-	} while (node != &fake);
-
-	ctx_flush_and_put(ctx, &ts);
+	node = llist_del_all(&tctx->task_list);
+	if (node) {
+		node = llist_reverse_order(node);
+		node = io_handle_tw_list(node, count, max_entries);
+	}
 
 	/* relaxed read is enough as only the task itself sets ->in_cancel */
 	if (unlikely(atomic_read(&tctx->in_cancel)))
 		io_uring_drop_tctx_refs(current);
 
-	trace_io_uring_task_work_run(tctx, count, loops);
+	trace_io_uring_task_work_run(tctx, *count);
+	return node;
+}
+
+void tctx_task_work(struct callback_head *cb)
+{
+	struct io_uring_task *tctx;
+	struct llist_node *ret;
+	unsigned int count = 0;
+
+	tctx = container_of(cb, struct io_uring_task, task_work);
+	ret = tctx_task_work_run(tctx, UINT_MAX, &count);
+	/* can't happen */
+	WARN_ON_ONCE(ret);
 }
 
 static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
@@ -1389,6 +1370,15 @@ static void io_req_normal_work_add(struct io_kiocb *req)
 	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 
+	/* SQPOLL doesn't need the task_work added, it'll run it itself */
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		struct io_sq_data *sqd = ctx->sq_data;
+
+		if (wq_has_sleeper(&sqd->wait))
+			wake_up(&sqd->wait);
+		return;
+	}
+
 	if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
 		return;
 
@@ -1420,7 +1410,20 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 	}
 }
 
-static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts)
+static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events,
+				       int min_events)
+{
+	if (llist_empty(&ctx->work_llist))
+		return false;
+	if (events < min_events)
+		return true;
+	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+	return false;
+}
+
+static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
+			       int min_events)
 {
 	struct llist_node *node;
 	unsigned int loops = 0;
@@ -1440,7 +1443,6 @@ again:
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
-		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
 		INDIRECT_CALL_2(req->io_task_work.func,
 				io_poll_task_func, io_req_rw_complete,
 				req, ts);
@@ -1449,18 +1451,20 @@ again:
 	}
 	loops++;
 
-	if (!llist_empty(&ctx->work_llist))
+	if (io_run_local_work_continue(ctx, ret, min_events))
 		goto again;
 	if (ts->locked) {
 		io_submit_flush_completions(ctx);
-		if (!llist_empty(&ctx->work_llist))
+		if (io_run_local_work_continue(ctx, ret, min_events))
 			goto again;
 	}
+
 	trace_io_uring_local_work_run(ctx, ret, loops);
 	return ret;
 }
 
-static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
+static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
+					   int min_events)
 {
 	struct io_tw_state ts = { .locked = true, };
 	int ret;
@@ -1468,20 +1472,20 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
 	if (llist_empty(&ctx->work_llist))
 		return 0;
 
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	/* shouldn't happen! */
 	if (WARN_ON_ONCE(!ts.locked))
 		mutex_lock(&ctx->uring_lock);
 	return ret;
 }
 
-static int io_run_local_work(struct io_ring_ctx *ctx)
+static int io_run_local_work(struct io_ring_ctx *ctx, int min_events)
 {
 	struct io_tw_state ts = {};
 	int ret;
 
 	ts.locked = mutex_trylock(&ctx->uring_lock);
-	ret = __io_run_local_work(ctx, &ts);
+	ret = __io_run_local_work(ctx, &ts, min_events);
 	if (ts.locked)
 		mutex_unlock(&ctx->uring_lock);
 
@@ -1677,7 +1681,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
 		    io_task_work_pending(ctx)) {
 			u32 tail = ctx->cached_cq_tail;
 
-			(void) io_run_local_work_locked(ctx);
+			(void) io_run_local_work_locked(ctx, min);
 
 			if (task_work_pending(current) ||
 			    wq_list_empty(&ctx->iopoll_list)) {
@@ -1768,9 +1772,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
 	}
 }
 
-unsigned int io_file_get_flags(struct file *file)
+io_req_flags_t io_file_get_flags(struct file *file)
 {
-	unsigned int res = 0;
+	io_req_flags_t res = 0;
 
 	if (S_ISREG(file_inode(file)->i_mode))
 		res |= REQ_F_ISREG;
@@ -1966,10 +1970,28 @@ fail:
 		goto fail;
 	}
 
+	/*
+	 * If DEFER_TASKRUN is set, it's only allowed to post CQEs from the
+	 * submitter task context. Final request completions are handed to the
+	 * right context, however this is not the case of auxiliary CQEs,
+	 * which is the main mean of operation for multishot requests.
+	 * Don't allow any multishot execution from io-wq. It's more restrictive
+	 * than necessary and also cleaner.
+	 */
+	if (req->flags & REQ_F_APOLL_MULTISHOT) {
+		err = -EBADFD;
+		if (!io_file_can_poll(req))
+			goto fail;
+		err = -ECANCELED;
+		if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
+			goto fail;
+		return;
+	}
+
 	if (req->flags & REQ_F_FORCE_ASYNC) {
 		bool opcode_poll = def->pollin || def->pollout;
 
-		if (opcode_poll && file_can_poll(req->file)) {
+		if (opcode_poll && io_file_can_poll(req)) {
 			needs_poll = true;
 			issue_flags |= IO_URING_F_NONBLOCK;
 		}
@@ -2171,7 +2193,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	/* req is partially pre-initialised, see io_preinit_req() */
 	req->opcode = opcode = READ_ONCE(sqe->opcode);
 	/* same numerical values with corresponding REQ_F_*, safe to copy */
-	req->flags = sqe_flags = READ_ONCE(sqe->flags);
+	sqe_flags = READ_ONCE(sqe->flags);
+	req->flags = (io_req_flags_t) sqe_flags;
 	req->cqe.user_data = READ_ONCE(sqe->user_data);
 	req->file = NULL;
 	req->rsrc_node = NULL;
@@ -2475,33 +2498,6 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	return ret;
 }
 
-struct io_wait_queue {
-	struct wait_queue_entry wq;
-	struct io_ring_ctx *ctx;
-	unsigned cq_tail;
-	unsigned nr_timeouts;
-	ktime_t timeout;
-};
-
-static inline bool io_has_work(struct io_ring_ctx *ctx)
-{
-	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
-	       !llist_empty(&ctx->work_llist);
-}
-
-static inline bool io_should_wake(struct io_wait_queue *iowq)
-{
-	struct io_ring_ctx *ctx = iowq->ctx;
-	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
-
-	/*
-	 * Wake up if we have enough events, or if a timeout occurred since we
-	 * started waiting. For timeouts, we always want to return to userspace,
-	 * regardless of event count.
-	 */
-	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
-}
-
 static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
 			    int wake_flags, void *key)
 {
@@ -2520,7 +2516,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
 {
 	if (!llist_empty(&ctx->work_llist)) {
 		__set_current_state(TASK_RUNNING);
-		if (io_run_local_work(ctx) > 0)
+		if (io_run_local_work(ctx, INT_MAX) > 0)
 			return 0;
 	}
 	if (io_run_task_work() > 0)
@@ -2588,7 +2584,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	if (!io_allowed_run_tw(ctx))
 		return -EEXIST;
 	if (!llist_empty(&ctx->work_llist))
-		io_run_local_work(ctx);
+		io_run_local_work(ctx, min_events);
 	io_run_task_work();
 	io_cqring_overflow_flush(ctx);
 	/* if user messes with these they will just get an early return */
@@ -2621,16 +2617,19 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
+
 		iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
+		io_napi_adjust_timeout(ctx, &iowq, &ts);
 	}
 
+	io_napi_busy_loop(ctx, &iowq);
+
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
+		int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
 		unsigned long check_cq;
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
-			int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
-
 			atomic_set(&ctx->cq_wait_nr, nr_wait);
 			set_current_state(TASK_INTERRUPTIBLE);
 		} else {
@@ -2649,7 +2648,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		 */
 		io_run_task_work();
 		if (!llist_empty(&ctx->work_llist))
-			io_run_local_work(ctx);
+			io_run_local_work(ctx, nr_wait);
 
 		/*
 		 * Non-local task_work will be run on exit to userspace, but
@@ -2917,6 +2916,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_req_caches_free(ctx);
 	if (ctx->hash_map)
 		io_wq_put_hash(ctx->hash_map);
+	io_napi_free(ctx);
 	kfree(ctx->cancel_table.hbs);
 	kfree(ctx->cancel_table_locked.hbs);
 	kfree(ctx->io_bl);
@@ -3304,7 +3304,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 
 	if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) &&
 	    io_allowed_defer_tw_run(ctx))
-		ret |= io_run_local_work(ctx) > 0;
+		ret |= io_run_local_work(ctx, INT_MAX) > 0;
 	ret |= io_cancel_defer_files(ctx, task, cancel_all);
 	mutex_lock(&ctx->uring_lock);
 	ret |= io_poll_remove_all(ctx, task, cancel_all);
@@ -3666,7 +3666,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			 * it should handle ownership problems if any.
 			 */
 			if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
-				(void)io_run_local_work_locked(ctx);
+				(void)io_run_local_work_locked(ctx, min_complete);
 		}
 		mutex_unlock(&ctx->uring_lock);
 	}
@@ -4153,7 +4153,7 @@ static int __init io_uring_init(void)
 	BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
 	BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);
 
-	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
+	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof_field(struct io_kiocb, flags));
 
 	BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
 
@@ -4175,9 +4175,8 @@ static int __init io_uring_init(void)
 				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU,
 				offsetof(struct io_kiocb, cmd.data),
 				sizeof_field(struct io_kiocb, cmd.data), NULL);
-	io_buf_cachep = kmem_cache_create("io_buffer", sizeof(struct io_buffer), 0,
-					  SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
-					  NULL);
+	io_buf_cachep = KMEM_CACHE(io_buffer,
+					  SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 
 #ifdef CONFIG_SYSCTL
 	register_sysctl_init("kernel", kernel_io_uring_disabled_table);
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 04e33f25919c..6426ee382276 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -5,6 +5,7 @@
 #include <linux/lockdep.h>
 #include <linux/resume_user_mode.h>
 #include <linux/kasan.h>
+#include <linux/poll.h>
 #include <linux/io_uring_types.h>
 #include <uapi/linux/eventpoll.h>
 #include "io-wq.h"
@@ -15,12 +16,18 @@
 #include <trace/events/io_uring.h>
 #endif
 
-
 enum {
 	IOU_OK			= 0,
 	IOU_ISSUE_SKIP_COMPLETE	= -EIOCBQUEUED,
 
 	/*
+	 * Requeue the task_work to restart operations on this request. The
+	 * actual value isn't important, should just be not an otherwise
+	 * valid error code, yet less than -MAX_ERRNO and valid internally.
+	 */
+	IOU_REQUEUE		= -3072,
+
+	/*
 	 * Intended only when both IO_URING_F_MULTISHOT is passed
 	 * to indicate to the poll runner that multishot should be
 	 * removed and the result is set on req->cqe.res.
@@ -28,6 +35,32 @@ enum {
 	IOU_STOP_MULTISHOT	= -ECANCELED,
 };
 
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	unsigned cq_tail;
+	unsigned nr_timeouts;
+	ktime_t timeout;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_busy_poll_to;
+	bool napi_prefer_busy_poll;
+#endif
+};
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+	struct io_ring_ctx *ctx = iowq->ctx;
+	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
+
+	/*
+	 * Wake up if we have enough events, or if a timeout occurred since we
+	 * started waiting. For timeouts, we always want to return to userspace,
+	 * regardless of event count.
+	 */
+	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
 bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
 void io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
@@ -50,6 +83,8 @@ void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
 void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
 void io_req_task_queue_fail(struct io_kiocb *req, int ret);
 void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
+struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
 void tctx_task_work(struct callback_head *cb);
 __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
 int io_uring_alloc_task_context(struct task_struct *task,
@@ -201,7 +236,7 @@ static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx,
 					 unsigned issue_flags)
 {
 	lockdep_assert_held(&ctx->uring_lock);
-	if (issue_flags & IO_URING_F_UNLOCKED)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_unlock(&ctx->uring_lock);
 }
 
@@ -214,7 +249,7 @@ static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
 	 * The only exception is when we've detached the request and issue it
 	 * from an async worker thread, grab the lock for that case.
 	 */
-	if (issue_flags & IO_URING_F_UNLOCKED)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_lock(&ctx->uring_lock);
 	lockdep_assert_held(&ctx->uring_lock);
 }
@@ -268,6 +303,8 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 
 static inline int io_run_task_work(void)
 {
+	bool ret = false;
+
 	/*
 	 * Always check-and-clear the task_work notification signal. With how
 	 * signaling works for task_work, we can find it set with nothing to
@@ -279,18 +316,26 @@ static inline int io_run_task_work(void)
 	 * PF_IO_WORKER never returns to userspace, so check here if we have
 	 * notify work that needs processing.
 	 */
-	if (current->flags & PF_IO_WORKER &&
-	    test_thread_flag(TIF_NOTIFY_RESUME)) {
-		__set_current_state(TASK_RUNNING);
-		resume_user_mode_work(NULL);
+	if (current->flags & PF_IO_WORKER) {
+		if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+			__set_current_state(TASK_RUNNING);
+			resume_user_mode_work(NULL);
+		}
+		if (current->io_uring) {
+			unsigned int count = 0;
+
+			tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+			if (count)
+				ret = true;
+		}
 	}
 	if (task_work_pending(current)) {
 		__set_current_state(TASK_RUNNING);
 		task_work_run();
-		return 1;
+		ret = true;
 	}
 
-	return 0;
+	return ret;
 }
 
 static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
@@ -392,4 +437,26 @@ static inline size_t uring_sqe_size(struct io_ring_ctx *ctx)
 		return 2 * sizeof(struct io_uring_sqe);
 	return sizeof(struct io_uring_sqe);
 }
+
+static inline bool io_file_can_poll(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_CAN_POLL)
+		return true;
+	if (file_can_poll(req->file)) {
+		req->flags |= REQ_F_CAN_POLL;
+		return true;
+	}
+	return false;
+}
+
+enum {
+	IO_CHECK_CQ_OVERFLOW_BIT,
+	IO_CHECK_CQ_DROPPED_BIT,
+};
+
+static inline bool io_has_work(struct io_ring_ctx *ctx)
+{
+	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
+	       !llist_empty(&ctx->work_llist);
+}
 #endif
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 18df5a9d2f5e..9be42bff936b 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -81,15 +81,6 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	struct io_buffer_list *bl;
 	struct io_buffer *buf;
 
-	/*
-	 * For legacy provided buffer mode, don't recycle if we already did
-	 * IO to this buffer. For ring-mapped provided buffer mode, we should
-	 * increment ring->head to explicitly monopolize the buffer to avoid
-	 * multiple use.
-	 */
-	if (req->flags & REQ_F_PARTIAL_IO)
-		return false;
-
 	io_ring_submit_lock(ctx, issue_flags);
 
 	buf = req->kbuf;
@@ -102,10 +93,8 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	return true;
 }
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 {
-	unsigned int cflags;
-
 	/*
 	 * We can add this buffer back to two lists:
 	 *
@@ -118,21 +107,17 @@ unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 	 * We migrate buffers from the comp_list to the issue cache list
 	 * when we need one.
 	 */
-	if (req->flags & REQ_F_BUFFER_RING) {
-		/* no buffers to recycle for this case */
-		cflags = __io_put_kbuf_list(req, NULL);
-	} else if (issue_flags & IO_URING_F_UNLOCKED) {
+	if (issue_flags & IO_URING_F_UNLOCKED) {
 		struct io_ring_ctx *ctx = req->ctx;
 
 		spin_lock(&ctx->completion_lock);
-		cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp);
+		__io_put_kbuf_list(req, &ctx->io_buffers_comp);
 		spin_unlock(&ctx->completion_lock);
 	} else {
 		lockdep_assert_held(&req->ctx->uring_lock);
 
-		cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
+		__io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
 	}
-	return cflags;
 }
 
 static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
@@ -145,6 +130,8 @@ static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
 		list_del(&kbuf->list);
 		if (*len == 0 || *len > kbuf->len)
 			*len = kbuf->len;
+		if (list_empty(&bl->buf_list))
+			req->flags |= REQ_F_BL_EMPTY;
 		req->flags |= REQ_F_BUFFER_SELECTED;
 		req->kbuf = kbuf;
 		req->buf_index = kbuf->bid;
@@ -158,12 +145,16 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 					  unsigned int issue_flags)
 {
 	struct io_uring_buf_ring *br = bl->buf_ring;
+	__u16 tail, head = bl->head;
 	struct io_uring_buf *buf;
-	__u16 head = bl->head;
 
-	if (unlikely(smp_load_acquire(&br->tail) == head))
+	tail = smp_load_acquire(&br->tail);
+	if (unlikely(tail == head))
 		return NULL;
 
+	if (head + 1 == tail)
+		req->flags |= REQ_F_BL_EMPTY;
+
 	head &= bl->mask;
 	/* mmaped buffers are always contig */
 	if (bl->is_mmap || head < IO_BUFFER_LIST_BUF_PER_PAGE) {
@@ -180,7 +171,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
 
-	if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
+	if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) {
 		/*
 		 * If we came in unlocked, we have no choice but to consume the
 		 * buffer here, otherwise nothing ensures that the buffer won't
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 53dfaa71a397..5218bfd79e87 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -57,7 +57,7 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
 
 void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
 bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
 
@@ -73,21 +73,9 @@ static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
 	 * to monopolize the buffer.
 	 */
 	if (req->buf_list) {
-		if (req->flags & REQ_F_PARTIAL_IO) {
-			/*
-			 * If we end up here, then the io_uring_lock has
-			 * been kept held since we retrieved the buffer.
-			 * For the io-wq case, we already cleared
-			 * req->buf_list when the buffer was retrieved,
-			 * hence it cannot be set here for that case.
-			 */
-			req->buf_list->head++;
-			req->buf_list = NULL;
-		} else {
-			req->buf_index = req->buf_list->bgid;
-			req->flags &= ~REQ_F_BUFFER_RING;
-			return true;
-		}
+		req->buf_index = req->buf_list->bgid;
+		req->flags &= ~REQ_F_BUFFER_RING;
+		return true;
 	}
 	return false;
 }
@@ -101,6 +89,8 @@ static inline bool io_do_buffer_select(struct io_kiocb *req)
 
 static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 {
+	if (req->flags & REQ_F_BL_NO_RECYCLE)
+		return false;
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		return io_kbuf_recycle_legacy(req, issue_flags);
 	if (req->flags & REQ_F_BUFFER_RING)
@@ -108,41 +98,54 @@ static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	return false;
 }
 
-static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req,
-					      struct list_head *list)
+static inline void __io_put_kbuf_ring(struct io_kiocb *req)
 {
-	unsigned int ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->buf_list) {
+		req->buf_index = req->buf_list->bgid;
+		req->buf_list->head++;
+	}
+	req->flags &= ~REQ_F_BUFFER_RING;
+}
 
+static inline void __io_put_kbuf_list(struct io_kiocb *req,
+				      struct list_head *list)
+{
 	if (req->flags & REQ_F_BUFFER_RING) {
-		if (req->buf_list) {
-			req->buf_index = req->buf_list->bgid;
-			req->buf_list->head++;
-		}
-		req->flags &= ~REQ_F_BUFFER_RING;
+		__io_put_kbuf_ring(req);
 	} else {
 		req->buf_index = req->kbuf->bgid;
 		list_add(&req->kbuf->list, list);
 		req->flags &= ~REQ_F_BUFFER_SELECTED;
 	}
-
-	return ret;
 }
 
 static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
 {
+	unsigned int ret;
+
 	lockdep_assert_held(&req->ctx->completion_lock);
 
 	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
 		return 0;
-	return __io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	__io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+	return ret;
 }
 
 static inline unsigned int io_put_kbuf(struct io_kiocb *req,
 				       unsigned issue_flags)
 {
+	unsigned int ret;
 
-	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
+	if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
 		return 0;
-	return __io_put_kbuf(req, issue_flags);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->flags & REQ_F_BUFFER_RING)
+		__io_put_kbuf_ring(req);
+	else
+		__io_put_kbuf(req, issue_flags);
+	return ret;
 }
 #endif
diff --git a/io_uring/napi.c b/io_uring/napi.c
new file mode 100644
index 000000000000..883a1a665907
--- /dev/null
+++ b/io_uring/napi.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "io_uring.h"
+#include "napi.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+/* Timeout for cleanout of stale entries. */
+#define NAPI_TIMEOUT		(60 * SEC_CONVERSION)
+
+struct io_napi_entry {
+	unsigned int		napi_id;
+	struct list_head	list;
+
+	unsigned long		timeout;
+	struct hlist_node	node;
+
+	struct rcu_head		rcu;
+};
+
+static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
+					       unsigned int napi_id)
+{
+	struct io_napi_entry *e;
+
+	hlist_for_each_entry_rcu(e, hash_list, node) {
+		if (e->napi_id != napi_id)
+			continue;
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		return e;
+	}
+
+	return NULL;
+}
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+{
+	struct hlist_head *hash_list;
+	unsigned int napi_id;
+	struct sock *sk;
+	struct io_napi_entry *e;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+
+	rcu_read_lock();
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (e) {
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	e = kmalloc(sizeof(*e), GFP_NOWAIT);
+	if (!e)
+		return;
+
+	e->napi_id = napi_id;
+	e->timeout = jiffies + NAPI_TIMEOUT;
+
+	spin_lock(&ctx->napi_lock);
+	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
+		spin_unlock(&ctx->napi_lock);
+		kfree(e);
+		return;
+	}
+
+	hlist_add_tail_rcu(&e->node, hash_list);
+	list_add_tail(&e->list, &ctx->napi_list);
+	spin_unlock(&ctx->napi_lock);
+}
+
+static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		if (time_after(jiffies, e->timeout)) {
+			list_del(&e->list);
+			hash_del_rcu(&e->node);
+			kfree_rcu(e, rcu);
+		}
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
+{
+	if (is_stale)
+		__io_napi_remove_stale(ctx);
+}
+
+static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
+					     unsigned long bp_usec)
+{
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+
+	return true;
+}
+
+static bool io_napi_busy_loop_should_end(void *data,
+					 unsigned long start_time)
+{
+	struct io_wait_queue *iowq = data;
+
+	if (signal_pending(current))
+		return true;
+	if (io_should_wake(iowq) || io_has_work(iowq->ctx))
+		return true;
+	if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to))
+		return true;
+
+	return false;
+}
+
+static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
+				   void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool (*loop_end)(void *, unsigned long) = NULL;
+	bool is_stale = false;
+
+	if (loop_end_arg)
+		loop_end = io_napi_busy_loop_should_end;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list) {
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+
+		if (time_after(jiffies, e->timeout))
+			is_stale = true;
+	}
+
+	return is_stale;
+}
+
+static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
+				       struct io_wait_queue *iowq)
+{
+	unsigned long start_time = busy_loop_current_time();
+	void *loop_end_arg = NULL;
+	bool is_stale = false;
+
+	/* Singular lists use a different napi loop end check function and are
+	 * only executed once.
+	 */
+	if (list_is_singular(&ctx->napi_list))
+		loop_end_arg = iowq;
+
+	rcu_read_lock();
+	do {
+		is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg);
+	} while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+}
+
+/*
+ * io_napi_init() - Init napi settings
+ * @ctx: pointer to io-uring context structure
+ *
+ * Init napi settings in the io-uring context.
+ */
+void io_napi_init(struct io_ring_ctx *ctx)
+{
+	INIT_LIST_HEAD(&ctx->napi_list);
+	spin_lock_init(&ctx->napi_lock);
+	ctx->napi_prefer_busy_poll = false;
+	ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
+}
+
+/*
+ * io_napi_free() - Deallocate napi
+ * @ctx: pointer to io-uring context structure
+ *
+ * Free the napi list and the hash table in the io-uring context.
+ */
+void io_napi_free(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	LIST_HEAD(napi_list);
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		hash_del_rcu(&e->node);
+		kfree_rcu(e, rcu);
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+/*
+ * io_napi_register() - Register napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Register napi in the io-uring context.
+ */
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+	struct io_uring_napi napi;
+
+	if (copy_from_user(&napi, arg, sizeof(napi)))
+		return -EFAULT;
+	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+		return -EINVAL;
+
+	if (copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
+	WRITE_ONCE(ctx->napi_enabled, true);
+	return 0;
+}
+
+/*
+ * io_napi_unregister() - Unregister napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Unregister napi. If arg has been specified copy the busy poll timeout and
+ * prefer busy poll setting to the passed in structure.
+ */
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+
+	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+	WRITE_ONCE(ctx->napi_enabled, false);
+	return 0;
+}
+
+/*
+ * __io_napi_adjust_timeout() - Add napi id to the busy poll list
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @ts: pointer to timespec or NULL
+ *
+ * Adjust the busy loop timeout according to timespec and busy poll timeout.
+ */
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			      struct timespec64 *ts)
+{
+	unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
+
+	if (ts) {
+		struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
+
+		if (timespec64_compare(ts, &poll_to_ts) > 0) {
+			*ts = timespec64_sub(*ts, poll_to_ts);
+		} else {
+			u64 to = timespec64_to_ns(ts);
+
+			do_div(to, 1000);
+			ts->tv_sec = 0;
+			ts->tv_nsec = 0;
+		}
+	}
+
+	iowq->napi_busy_poll_to = poll_to;
+}
+
+/*
+ * __io_napi_busy_loop() - execute busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ *
+ * Execute the busy poll loop and merge the spliced off list.
+ */
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
+{
+	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled)
+		io_napi_blocking_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	LIST_HEAD(napi_list);
+	bool is_stale = false;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return 0;
+	if (list_empty_careful(&ctx->napi_list))
+		return 0;
+
+	rcu_read_lock();
+	is_stale = __io_napi_do_busy_loop(ctx, NULL);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+	return 1;
+}
+
+#endif
diff --git a/io_uring/napi.h b/io_uring/napi.h
new file mode 100644
index 000000000000..6fc0393d0dbe
--- /dev/null
+++ b/io_uring/napi.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef IOU_NAPI_H
+#define IOU_NAPI_H
+
+#include <linux/kernel.h>
+#include <linux/io_uring.h>
+#include <net/busy_poll.h>
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+void io_napi_init(struct io_ring_ctx *ctx);
+void io_napi_free(struct io_ring_ctx *ctx);
+
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg);
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg);
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
+
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+		struct io_wait_queue *iowq, struct timespec64 *ts);
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq);
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx);
+
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return !list_empty(&ctx->napi_list);
+}
+
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_adjust_timeout(ctx, iowq, ts);
+}
+
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_add() - Add napi id to the busy poll list
+ * @req: pointer to io_kiocb request
+ *
+ * Add the napi id of the socket to the napi busy poll list and hash table.
+ */
+static inline void io_napi_add(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct socket *sock;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return;
+
+	sock = sock_from_file(req->file);
+	if (sock)
+		__io_napi_add(ctx, sock);
+}
+
+#else
+
+static inline void io_napi_init(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_napi_free(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return false;
+}
+static inline void io_napi_add(struct io_kiocb *req)
+{
+}
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+}
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+}
+static inline int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	return 0;
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+#endif
diff --git a/io_uring/net.c b/io_uring/net.c
index 75d494dad7e2..19451f0dbf81 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -60,6 +60,7 @@ struct io_sr_msg {
 	unsigned			len;
 	unsigned			done_io;
 	unsigned			msg_flags;
+	unsigned			nr_multishot_loops;
 	u16				flags;
 	/* initialised and used only by !msg send variants */
 	u16				addr_len;
@@ -70,18 +71,12 @@ struct io_sr_msg {
 	struct io_kiocb 		*notif;
 };
 
-static inline bool io_check_multishot(struct io_kiocb *req,
-				      unsigned int issue_flags)
-{
-	/*
-	 * When ->locked_cq is set we only allow to post CQEs from the original
-	 * task context. Usual request completions will be handled in other
-	 * generic paths but multipoll may decide to post extra cqes.
-	 */
-	return !(issue_flags & IO_URING_F_IOWQ) ||
-		!(issue_flags & IO_URING_F_MULTISHOT) ||
-		!req->ctx->task_complete;
-}
+/*
+ * Number of times we'll try and do receives if there's more data. If we
+ * exceed this limit, then add us to the back of the queue and retry from
+ * there. This helps fairness between flooding clients.
+ */
+#define MULTISHOT_MAX_RETRY	32
 
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
@@ -196,16 +191,130 @@ static int io_setup_async_msg(struct io_kiocb *req,
 	return -EAGAIN;
 }
 
+#ifdef CONFIG_COMPAT
+static int io_compat_msg_copy_hdr(struct io_kiocb *req,
+				  struct io_async_msghdr *iomsg,
+				  struct compat_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct compat_iovec __user *uiov;
+	int ret;
+
+	if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg)))
+		return -EFAULT;
+
+	uiov = compat_ptr(msg->msg_iov);
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		compat_ssize_t clen;
+
+		iomsg->free_iov = NULL;
+		if (msg->msg_iovlen == 0) {
+			sr->len = 0;
+		} else if (msg->msg_iovlen > 1) {
+			return -EINVAL;
+		} else {
+			if (!access_ok(uiov, sizeof(*uiov)))
+				return -EFAULT;
+			if (__get_user(clen, &uiov->iov_len))
+				return -EFAULT;
+			if (clen < 0)
+				return -EINVAL;
+			sr->len = clen;
+		}
+
+		return 0;
+	}
+
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen,
+				UIO_FASTIOV, &iomsg->free_iov,
+				&iomsg->msg.msg_iter, true);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+#endif
+
+static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
+			   struct user_msghdr *msg, int ddir)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	int ret;
+
+	if (!user_access_begin(sr->umsg, sizeof(*sr->umsg)))
+		return -EFAULT;
+
+	ret = -EFAULT;
+	unsafe_get_user(msg->msg_name, &sr->umsg->msg_name, ua_end);
+	unsafe_get_user(msg->msg_namelen, &sr->umsg->msg_namelen, ua_end);
+	unsafe_get_user(msg->msg_iov, &sr->umsg->msg_iov, ua_end);
+	unsafe_get_user(msg->msg_iovlen, &sr->umsg->msg_iovlen, ua_end);
+	unsafe_get_user(msg->msg_control, &sr->umsg->msg_control, ua_end);
+	unsafe_get_user(msg->msg_controllen, &sr->umsg->msg_controllen, ua_end);
+	msg->msg_flags = 0;
+
+	if (req->flags & REQ_F_BUFFER_SELECT) {
+		if (msg->msg_iovlen == 0) {
+			sr->len = iomsg->fast_iov[0].iov_len = 0;
+			iomsg->fast_iov[0].iov_base = NULL;
+			iomsg->free_iov = NULL;
+		} else if (msg->msg_iovlen > 1) {
+			ret = -EINVAL;
+			goto ua_end;
+		} else {
+			/* we only need the length for provided buffers */
+			if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t)))
+				goto ua_end;
+			unsafe_get_user(iomsg->fast_iov[0].iov_len,
+					&msg->msg_iov[0].iov_len, ua_end);
+			sr->len = iomsg->fast_iov[0].iov_len;
+			iomsg->free_iov = NULL;
+		}
+		ret = 0;
+ua_end:
+		user_access_end();
+		return ret;
+	}
+
+	user_access_end();
+	iomsg->free_iov = iomsg->fast_iov;
+	ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, UIO_FASTIOV,
+				&iomsg->free_iov, &iomsg->msg.msg_iter, false);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return 0;
+}
+
 static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 			       struct io_async_msghdr *iomsg)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+	struct user_msghdr msg;
 	int ret;
 
 	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->free_iov = iomsg->fast_iov;
-	ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags,
-					&iomsg->free_iov);
+	iomsg->msg.msg_iter.nr_segs = 0;
+
+#ifdef CONFIG_COMPAT
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
+
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE);
+		if (unlikely(ret))
+			return ret;
+
+		return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+	}
+#endif
+
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE);
+	if (unlikely(ret))
+		return ret;
+
+	ret = __copy_msghdr(&iomsg->msg, &msg, NULL);
+
 	/* save msg_control as sys_sendmsg() overwrites it */
 	sr->msg_control = iomsg->msg.msg_control_user;
 	return ret;
@@ -265,6 +374,8 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	sr->done_io = 0;
+
 	if (req->opcode == IORING_OP_SEND) {
 		if (READ_ONCE(sqe->__pad3[0]))
 			return -EINVAL;
@@ -287,10 +398,20 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->ctx->compat)
 		sr->msg_flags |= MSG_CMSG_COMPAT;
 #endif
-	sr->done_io = 0;
 	return 0;
 }
 
+static void io_req_msg_cleanup(struct io_kiocb *req,
+			       struct io_async_msghdr *kmsg,
+			       unsigned int issue_flags)
+{
+	req->flags &= ~REQ_F_NEED_CLEANUP;
+	/* fast path, check for non-NULL to avoid function call */
+	if (kmsg->free_iov)
+		kfree(kmsg->free_iov);
+	io_netmsg_recycle(req, issue_flags);
+}
+
 int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
@@ -333,18 +454,14 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 			kmsg->msg.msg_controllen = 0;
 			kmsg->msg.msg_control = NULL;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
 			ret = -EINTR;
 		req_set_fail(req);
 	}
-	/* fast path, check for non-NULL to avoid function call */
-	if (kmsg->free_iov)
-		kfree(kmsg->free_iov);
-	req->flags &= ~REQ_F_NEED_CLEANUP;
-	io_netmsg_recycle(req, issue_flags);
+	io_req_msg_cleanup(req, kmsg, issue_flags);
 	if (ret >= 0)
 		ret += sr->done_io;
 	else if (sr->done_io)
@@ -412,7 +529,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_addr(req, &__address, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -427,142 +544,77 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
-static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg)
+static int io_recvmsg_mshot_prep(struct io_kiocb *req,
+				 struct io_async_msghdr *iomsg,
+				 int namelen, size_t controllen)
 {
-	int hdr;
-
-	if (iomsg->namelen < 0)
-		return true;
-	if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out),
-			       iomsg->namelen, &hdr))
-		return true;
-	if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr))
-		return true;
+	if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) ==
+			  (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) {
+		int hdr;
+
+		if (unlikely(namelen < 0))
+			return -EOVERFLOW;
+		if (check_add_overflow(sizeof(struct io_uring_recvmsg_out),
+					namelen, &hdr))
+			return -EOVERFLOW;
+		if (check_add_overflow(hdr, controllen, &hdr))
+			return -EOVERFLOW;
+
+		iomsg->namelen = namelen;
+		iomsg->controllen = controllen;
+		return 0;
+	}
 
-	return false;
+	return 0;
 }
 
-static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
-				 struct io_async_msghdr *iomsg)
+static int io_recvmsg_copy_hdr(struct io_kiocb *req,
+			       struct io_async_msghdr *iomsg)
 {
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	struct user_msghdr msg;
 	int ret;
 
-	if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg)))
-		return -EFAULT;
-
-	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		if (msg.msg_iovlen == 0) {
-			sr->len = iomsg->fast_iov[0].iov_len = 0;
-			iomsg->fast_iov[0].iov_base = NULL;
-			iomsg->free_iov = NULL;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov)))
-				return -EFAULT;
-			sr->len = iomsg->fast_iov[0].iov_len;
-			iomsg->free_iov = NULL;
-		}
-
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV,
-				     &iomsg->free_iov, &iomsg->msg.msg_iter,
-				     false);
-		if (ret > 0)
-			ret = 0;
-	}
-
-	return ret;
-}
+	iomsg->msg.msg_name = &iomsg->addr;
+	iomsg->msg.msg_iter.nr_segs = 0;
 
 #ifdef CONFIG_COMPAT
-static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
-					struct io_async_msghdr *iomsg)
-{
-	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
-	struct compat_msghdr msg;
-	struct compat_iovec __user *uiov;
-	int ret;
+	if (unlikely(req->ctx->compat)) {
+		struct compat_msghdr cmsg;
 
-	if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg)))
-		return -EFAULT;
-
-	ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
-	if (ret)
-		return ret;
-
-	uiov = compat_ptr(msg.msg_iov);
-	if (req->flags & REQ_F_BUFFER_SELECT) {
-		compat_ssize_t clen;
-
-		iomsg->free_iov = NULL;
-		if (msg.msg_iovlen == 0) {
-			sr->len = 0;
-		} else if (msg.msg_iovlen > 1) {
-			return -EINVAL;
-		} else {
-			if (!access_ok(uiov, sizeof(*uiov)))
-				return -EFAULT;
-			if (__get_user(clen, &uiov->iov_len))
-				return -EFAULT;
-			if (clen < 0)
-				return -EINVAL;
-			sr->len = clen;
-		}
+		ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST);
+		if (unlikely(ret))
+			return ret;
 
-		if (req->flags & REQ_F_APOLL_MULTISHOT) {
-			iomsg->namelen = msg.msg_namelen;
-			iomsg->controllen = msg.msg_controllen;
-			if (io_recvmsg_multishot_overflow(iomsg))
-				return -EOVERFLOW;
-		}
-	} else {
-		iomsg->free_iov = iomsg->fast_iov;
-		ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen,
-				   UIO_FASTIOV, &iomsg->free_iov,
-				   &iomsg->msg.msg_iter, true);
-		if (ret < 0)
+		ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr);
+		if (unlikely(ret))
 			return ret;
-	}
 
-	return 0;
-}
+		return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen,
+						cmsg.msg_controllen);
+	}
 #endif
 
-static int io_recvmsg_copy_hdr(struct io_kiocb *req,
-			       struct io_async_msghdr *iomsg)
-{
-	iomsg->msg.msg_name = &iomsg->addr;
-	iomsg->msg.msg_iter.nr_segs = 0;
+	ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST);
+	if (unlikely(ret))
+		return ret;
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return __io_compat_recvmsg_copy_hdr(req, iomsg);
-#endif
+	ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
+	if (unlikely(ret))
+		return ret;
 
-	return __io_recvmsg_copy_hdr(req, iomsg);
+	return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen,
+					msg.msg_controllen);
 }
 
 int io_recvmsg_prep_async(struct io_kiocb *req)
 {
+	struct io_async_msghdr *iomsg;
 	int ret;
 
 	if (!io_msg_alloc_async_prep(req))
 		return -ENOMEM;
-	ret = io_recvmsg_copy_hdr(req, req->async_data);
+	iomsg = req->async_data;
+	ret = io_recvmsg_copy_hdr(req, iomsg);
 	if (!ret)
 		req->flags |= REQ_F_NEED_CLEANUP;
 	return ret;
@@ -574,6 +626,8 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	sr->done_io = 0;
+
 	if (unlikely(sqe->file_index || sqe->addr2))
 		return -EINVAL;
 
@@ -610,7 +664,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (req->ctx->compat)
 		sr->msg_flags |= MSG_CMSG_COMPAT;
 #endif
-	sr->done_io = 0;
+	sr->nr_multishot_loops = 0;
 	return 0;
 }
 
@@ -618,6 +672,7 @@ static inline void io_recv_prep_retry(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
+	req->flags &= ~REQ_F_BL_EMPTY;
 	sr->done_io = 0;
 	sr->len = 0; /* get from the provided buffer */
 	req->buf_index = sr->buf_group;
@@ -636,32 +691,36 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 	unsigned int cflags;
 
 	cflags = io_put_kbuf(req, issue_flags);
-	if (msg->msg_inq && msg->msg_inq != -1)
+	if (msg->msg_inq > 0)
 		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
 
-	if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
-		io_req_set_res(req, *ret, cflags);
-		*ret = IOU_OK;
-		return true;
-	}
-
-	if (!mshot_finished) {
-		if (io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
-					*ret, cflags | IORING_CQE_F_MORE)) {
-			io_recv_prep_retry(req);
-			/* Known not-empty or unknown state, retry */
-			if (cflags & IORING_CQE_F_SOCK_NONEMPTY ||
-			    msg->msg_inq == -1)
+	/*
+	 * Fill CQE for this receive and see if we should keep trying to
+	 * receive from this socket.
+	 */
+	if ((req->flags & REQ_F_APOLL_MULTISHOT) && !mshot_finished &&
+	    io_fill_cqe_req_aux(req, issue_flags & IO_URING_F_COMPLETE_DEFER,
+				*ret, cflags | IORING_CQE_F_MORE)) {
+		struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+		int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE;
+
+		io_recv_prep_retry(req);
+		/* Known not-empty or unknown state, retry */
+		if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq < 0) {
+			if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
 				return false;
-			if (issue_flags & IO_URING_F_MULTISHOT)
-				*ret = IOU_ISSUE_SKIP_COMPLETE;
-			else
-				*ret = -EAGAIN;
-			return true;
+			/* mshot retries exceeded, force a requeue */
+			sr->nr_multishot_loops = 0;
+			mshot_retry_ret = IOU_REQUEUE;
 		}
-		/* Otherwise stop multishot but use the current result. */
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			*ret = mshot_retry_ret;
+		else
+			*ret = -EAGAIN;
+		return true;
 	}
 
+	/* Finish the request / stop multishot. */
 	io_req_set_res(req, *ret, cflags);
 
 	if (issue_flags & IO_URING_F_MULTISHOT)
@@ -782,8 +841,9 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return io_setup_async_msg(req, kmsg, issue_flags);
 
-	if (!io_check_multishot(req, issue_flags))
-		return io_setup_async_msg(req, kmsg, issue_flags);
+	flags = sr->msg_flags;
+	if (force_nonblock)
+		flags |= MSG_DONTWAIT;
 
 retry_multishot:
 	if (io_do_buffer_select(req)) {
@@ -805,10 +865,6 @@ retry_multishot:
 		iov_iter_ubuf(&kmsg->msg.msg_iter, ITER_DEST, buf, len);
 	}
 
-	flags = sr->msg_flags;
-	if (force_nonblock)
-		flags |= MSG_DONTWAIT;
-
 	kmsg->msg.msg_get_inq = 1;
 	kmsg->msg.msg_inq = -1;
 	if (req->flags & REQ_F_APOLL_MULTISHOT) {
@@ -834,7 +890,7 @@ retry_multishot:
 		}
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -854,13 +910,10 @@ retry_multishot:
 	if (!io_recv_finish(req, &ret, &kmsg->msg, mshot_finished, issue_flags))
 		goto retry_multishot;
 
-	if (mshot_finished) {
-		/* fast path, check for non-NULL to avoid function call */
-		if (kmsg->free_iov)
-			kfree(kmsg->free_iov);
-		io_netmsg_recycle(req, issue_flags);
-		req->flags &= ~REQ_F_NEED_CLEANUP;
-	}
+	if (mshot_finished)
+		io_req_msg_cleanup(req, kmsg, issue_flags);
+	else if (ret == -EAGAIN)
+		return io_setup_async_msg(req, kmsg, issue_flags);
 
 	return ret;
 }
@@ -879,9 +932,6 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return -EAGAIN;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
-
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
 		return -ENOTSOCK;
@@ -894,6 +944,10 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	msg.msg_iocb = NULL;
 	msg.msg_ubuf = NULL;
 
+	flags = sr->msg_flags;
+	if (force_nonblock)
+		flags |= MSG_DONTWAIT;
+
 retry_multishot:
 	if (io_do_buffer_select(req)) {
 		void __user *buf;
@@ -902,6 +956,7 @@ retry_multishot:
 		if (!buf)
 			return -ENOBUFS;
 		sr->buf = buf;
+		sr->len = len;
 	}
 
 	ret = import_ubuf(ITER_DEST, sr->buf, len, &msg.msg_iter);
@@ -911,9 +966,6 @@ retry_multishot:
 	msg.msg_inq = -1;
 	msg.msg_flags = 0;
 
-	flags = sr->msg_flags;
-	if (force_nonblock)
-		flags |= MSG_DONTWAIT;
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&msg.msg_iter);
 
@@ -931,7 +983,7 @@ retry_multishot:
 			sr->len -= ret;
 			sr->buf += ret;
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return -EAGAIN;
 		}
 		if (ret == -ERESTARTSYS)
@@ -981,6 +1033,8 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_kiocb *notif;
 
+	zc->done_io = 0;
+
 	if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
 		return -EINVAL;
 	/* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */
@@ -1033,8 +1087,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (zc->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
 
-	zc->done_io = 0;
-
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		zc->msg_flags |= MSG_CMSG_COMPAT;
@@ -1174,7 +1226,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
 			zc->len -= ret;
 			zc->buf += ret;
 			zc->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_addr(req, &__address, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -1244,7 +1296,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
 
 		if (ret > 0 && io_net_retry(sock, flags)) {
 			sr->done_io += ret;
-			req->flags |= REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_BL_NO_RECYCLE;
 			return io_setup_async_msg(req, kmsg, issue_flags);
 		}
 		if (ret == -ERESTARTSYS)
@@ -1279,7 +1331,7 @@ void io_sendrecv_fail(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
-	if (req->flags & REQ_F_PARTIAL_IO)
+	if (sr->done_io)
 		req->cqe.res = sr->done_io;
 
 	if ((req->flags & REQ_F_NEED_CLEANUP) &&
@@ -1329,8 +1381,6 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *file;
 	int ret, fd;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
 retry:
 	if (!fixed) {
 		fd = __get_unused_fd_flags(accept->flags, accept->nofile);
@@ -1350,7 +1400,7 @@ retry:
 			 * has already been done
 			 */
 			if (issue_flags & IO_URING_F_MULTISHOT)
-				ret = IOU_ISSUE_SKIP_COMPLETE;
+				return IOU_ISSUE_SKIP_COMPLETE;
 			return ret;
 		}
 		if (ret == -ERESTARTSYS)
@@ -1375,7 +1425,8 @@ retry:
 				ret, IORING_CQE_F_MORE))
 		goto retry;
 
-	return -ECANCELED;
+	io_req_set_res(req, ret, 0);
+	return IOU_STOP_MULTISHOT;
 }
 
 int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index b1ee3a9c3807..9c080aadc5a6 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -35,6 +35,7 @@
 #include "rw.h"
 #include "waitid.h"
 #include "futex.h"
+#include "truncate.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -474,6 +475,12 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_install_fixed_fd_prep,
 		.issue			= io_install_fixed_fd,
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.prep			= io_ftruncate_prep,
+		.issue			= io_ftruncate,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -712,6 +719,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FIXED_FD_INSTALL] = {
 		.name			= "FIXED_FD_INSTALL",
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.name			= "FTRUNCATE",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d59b74a99d4e..5f779139cae1 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -15,6 +15,7 @@
 
 #include "io_uring.h"
 #include "refs.h"
+#include "napi.h"
 #include "opdef.h"
 #include "kbuf.h"
 #include "poll.h"
@@ -226,8 +227,29 @@ enum {
 	IOU_POLL_NO_ACTION = 1,
 	IOU_POLL_REMOVE_POLL_USE_RES = 2,
 	IOU_POLL_REISSUE = 3,
+	IOU_POLL_REQUEUE = 4,
 };
 
+static void __io_poll_execute(struct io_kiocb *req, int mask)
+{
+	unsigned flags = 0;
+
+	io_req_set_res(req, mask, 0);
+	req->io_task_work.func = io_poll_task_func;
+
+	trace_io_uring_task_add(req, mask);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
+}
+
+static inline void io_poll_execute(struct io_kiocb *req, int res)
+{
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, res);
+}
+
 /*
  * All poll tw should go through this. Checks for poll events, manages
  * references, does rewait, etc.
@@ -309,6 +331,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 			int ret = io_poll_issue(req, ts);
 			if (ret == IOU_STOP_MULTISHOT)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
+			else if (ret == IOU_REQUEUE)
+				return IOU_POLL_REQUEUE;
 			if (ret < 0)
 				return ret;
 		}
@@ -320,8 +344,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 		 * Release all references, retry if someone tried to restart
 		 * task_work while we were executing it.
 		 */
-	} while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) &
-					IO_POLL_REF_MASK);
+		v &= IO_POLL_REF_MASK;
+	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
 
 	return IOU_POLL_NO_ACTION;
 }
@@ -331,8 +355,12 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	int ret;
 
 	ret = io_poll_check_events(req, ts);
-	if (ret == IOU_POLL_NO_ACTION)
+	if (ret == IOU_POLL_NO_ACTION) {
 		return;
+	} else if (ret == IOU_POLL_REQUEUE) {
+		__io_poll_execute(req, 0);
+		return;
+	}
 	io_poll_remove_entries(req);
 	io_poll_tw_hash_eject(req, ts);
 
@@ -364,26 +392,6 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 	}
 }
 
-static void __io_poll_execute(struct io_kiocb *req, int mask)
-{
-	unsigned flags = 0;
-
-	io_req_set_res(req, mask, 0);
-	req->io_task_work.func = io_poll_task_func;
-
-	trace_io_uring_task_add(req, mask);
-
-	if (!(req->flags & REQ_F_POLL_NO_LAZY))
-		flags = IOU_F_TWQ_LAZY_WAKE;
-	__io_req_task_work_add(req, flags);
-}
-
-static inline void io_poll_execute(struct io_kiocb *req, int res)
-{
-	if (io_poll_get_ownership(req))
-		__io_poll_execute(req, res);
-}
-
 static void io_poll_cancel_req(struct io_kiocb *req)
 {
 	io_poll_mark_cancelled(req);
@@ -532,14 +540,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->wait.private = (void *) wqe_private;
 
 	if (poll->events & EPOLLEXCLUSIVE) {
-		/*
-		 * Exclusive waits may only wake a limited amount of entries
-		 * rather than all of them, this may interfere with lazy
-		 * wake if someone does wait(events > 1). Ensure we don't do
-		 * lazy wake for those, as we need to process each one as they
-		 * come in.
-		 */
-		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
 	} else {
 		add_wait_queue(head, &poll->wait);
@@ -581,10 +581,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 				 struct io_poll_table *ipt, __poll_t mask,
 				 unsigned issue_flags)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-
 	INIT_HLIST_NODE(&req->hash_node);
-	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
 	io_init_poll_iocb(poll, mask);
 	poll->file = req->file;
 	req->apoll_events = poll->events;
@@ -611,6 +608,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		req->flags &= ~REQ_F_HASH_LOCKED;
 
+
+	/*
+	 * Exclusive waits may only wake a limited amount of entries
+	 * rather than all of them, this may interfere with lazy
+	 * wake if someone does wait(events > 1). Ensure we don't do
+	 * lazy wake for those, as we need to process each one as they
+	 * come in.
+	 */
+	if (poll->events & EPOLLEXCLUSIVE)
+		req->flags |= REQ_F_POLL_NO_LAZY;
+
 	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
 
 	if (unlikely(ipt->error || !ipt->nr_entries)) {
@@ -645,6 +653,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask);
 		return 0;
 	}
+	io_napi_add(req);
 
 	if (ipt->owning) {
 		/*
@@ -720,7 +729,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 
 	if (!def->pollin && !def->pollout)
 		return IO_APOLL_ABORTED;
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return IO_APOLL_ABORTED;
 	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
 		mask |= EPOLLONESHOT;
@@ -811,9 +820,8 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
 		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
 			continue;
 		if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
-			if (cd->seq == req->work.cancel_seq)
+			if (io_cancel_match_sequence(req, cd->seq))
 				continue;
-			req->work.cancel_seq = cd->seq;
 		}
 		*out_bucket = hb;
 		return req;
diff --git a/io_uring/poll.h b/io_uring/poll.h
index ff4d5d753387..1dacae9e816c 100644
--- a/io_uring/poll.h
+++ b/io_uring/poll.h
@@ -24,6 +24,15 @@ struct async_poll {
 	struct io_poll		*double_poll;
 };
 
+/*
+ * Must only be called inside issue_flags & IO_URING_F_MULTISHOT, or
+ * potentially other cases where we already "own" this poll request.
+ */
+static inline void io_poll_multishot_retry(struct io_kiocb *req)
+{
+	atomic_inc(&req->poll_refs);
+}
+
 int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_poll_add(struct io_kiocb *req, unsigned int issue_flags);
 
diff --git a/io_uring/register.c b/io_uring/register.c
index 5e62c1208996..99c37775f974 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -26,6 +26,7 @@
 #include "register.h"
 #include "cancel.h"
 #include "kbuf.h"
+#include "napi.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -550,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_pbuf_status(ctx, arg);
 		break;
+	case IORING_REGISTER_NAPI:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_napi(ctx, arg);
+		break;
+	case IORING_UNREGISTER_NAPI:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_unregister_napi(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index c6f199bbee28..e21000238954 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -2,8 +2,6 @@
 #ifndef IOU_RSRC_H
 #define IOU_RSRC_H
 
-#include <net/af_unix.h>
-
 #include "alloc_cache.h"
 
 #define IO_NODE_ALLOC_CACHE_MAX 32
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 118cc9f1cf16..47e097ab5d7e 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -11,6 +11,7 @@
 #include <linux/nospec.h>
 #include <linux/compat.h>
 #include <linux/io_uring/cmd.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -18,6 +19,7 @@
 #include "opdef.h"
 #include "kbuf.h"
 #include "rsrc.h"
+#include "poll.h"
 #include "rw.h"
 
 struct io_rw {
@@ -273,7 +275,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 			 * current cycle.
 			 */
 			io_req_io_end(req);
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return true;
 		}
 		req_set_fail(req);
@@ -340,7 +342,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 		io_req_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
 		if (res == -EAGAIN && io_rw_should_reissue(req)) {
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return;
 		}
 		req->cqe.res = res;
@@ -681,7 +683,7 @@ static bool io_rw_should_retry(struct io_kiocb *req)
 	 * just use poll if we can, and don't attempt if the fs doesn't
 	 * support callback based unlocks
 	 */
-	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+	if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC))
 		return false;
 
 	wait->wait.func = io_async_buf_func;
@@ -720,7 +722,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	struct file *file = req->file;
 	int ret;
 
-	if (unlikely(!file || !(file->f_mode & mode)))
+	if (unlikely(!(file->f_mode & mode)))
 		return -EBADF;
 
 	if (!(req->flags & REQ_F_FIXED_FILE))
@@ -830,7 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 		 * If we can poll, just do that. For a vectored read, we'll
 		 * need to copy state first.
 		 */
-		if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored)
+		if (io_file_can_poll(req) && !io_issue_defs[req->opcode].vectored)
 			return -EAGAIN;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
@@ -929,7 +931,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	/*
 	 * Multishot MUST be used on a pollable file
 	 */
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return -EBADFD;
 
 	ret = __io_read(req, issue_flags);
@@ -962,8 +964,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 		if (io_fill_cqe_req_aux(req,
 					issue_flags & IO_URING_F_COMPLETE_DEFER,
 					ret, cflags | IORING_CQE_F_MORE)) {
-			if (issue_flags & IO_URING_F_MULTISHOT)
+			if (issue_flags & IO_URING_F_MULTISHOT) {
+				/*
+				 * Force retry, as we might have more data to
+				 * be read and otherwise it won't get retried
+				 * until (if ever) another poll is triggered.
+				 */
+				io_poll_multishot_retry(req);
 				return IOU_ISSUE_SKIP_COMPLETE;
+			}
 			return -EAGAIN;
 		}
 	}
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 65b5dbe3c850..363052b4ea76 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -15,9 +15,11 @@
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "napi.h"
 #include "sqpoll.h"
 
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE	8
 
 enum {
 	IO_SQ_THREAD_SHOULD_STOP = 0,
@@ -193,6 +195,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
+		if (io_napi(ctx))
+			ret += io_napi_sqpoll_busy_poll(ctx);
+
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)
@@ -219,10 +224,52 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
 	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 }
 
+/*
+ * Run task_work, processing the retry_list first. The retry_list holds
+ * entries that we passed on in the previous run, if we had more task_work
+ * than we were asked to process. Newly queued task_work isn't run until the
+ * retry list has been fully processed.
+ */
+static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	unsigned int count = 0;
+
+	if (*retry_list) {
+		*retry_list = io_handle_tw_list(*retry_list, &count, max_entries);
+		if (count >= max_entries)
+			return count;
+		max_entries -= count;
+	}
+
+	*retry_list = tctx_task_work_run(tctx, max_entries, &count);
+	return count;
+}
+
+static bool io_sq_tw_pending(struct llist_node *retry_list)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	return retry_list || !llist_empty(&tctx->task_list);
+}
+
+static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start)
+{
+	struct rusage end;
+
+	getrusage(current, RUSAGE_SELF, &end);
+	end.ru_stime.tv_sec -= start->ru_stime.tv_sec;
+	end.ru_stime.tv_usec -= start->ru_stime.tv_usec;
+
+	sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000;
+}
+
 static int io_sq_thread(void *data)
 {
+	struct llist_node *retry_list = NULL;
 	struct io_sq_data *sqd = data;
 	struct io_ring_ctx *ctx;
+	struct rusage start;
 	unsigned long timeout = 0;
 	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
@@ -251,18 +298,21 @@ static int io_sq_thread(void *data)
 		}
 
 		cap_entries = !list_is_singular(&sqd->ctx_list);
+		getrusage(current, RUSAGE_SELF, &start);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
 			int ret = __io_sq_thread(ctx, cap_entries);
 
 			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
 				sqt_spin = true;
 		}
-		if (io_run_task_work())
+		if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
 			sqt_spin = true;
 
 		if (sqt_spin || !time_after(jiffies, timeout)) {
-			if (sqt_spin)
+			if (sqt_spin) {
+				io_sq_update_worktime(sqd, &start);
 				timeout = jiffies + sqd->sq_thread_idle;
+			}
 			if (unlikely(need_resched())) {
 				mutex_unlock(&sqd->lock);
 				cond_resched();
@@ -273,7 +323,7 @@ static int io_sq_thread(void *data)
 		}
 
 		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
-		if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
+		if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending(retry_list)) {
 			bool needs_sched = true;
 
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -312,6 +362,9 @@ static int io_sq_thread(void *data)
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
 
+	if (retry_list)
+		io_sq_tw(&retry_list, UINT_MAX);
+
 	io_uring_cancel_generic(true, sqd);
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index 8df37e8c9149..4171666b1cf4 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -16,6 +16,7 @@ struct io_sq_data {
 	pid_t			task_pid;
 	pid_t			task_tgid;
 
+	u64			work_time;
 	unsigned long		state;
 	struct completion	exited;
 };
diff --git a/io_uring/truncate.c b/io_uring/truncate.c
new file mode 100644
index 000000000000..62ee73d34d72
--- /dev/null
+++ b/io_uring/truncate.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../fs/internal.h"
+
+#include "io_uring.h"
+#include "truncate.h"
+
+struct io_ftrunc {
+	struct file			*file;
+	loff_t				len;
+};
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+
+	if (sqe->rw_flags || sqe->addr || sqe->len || sqe->buf_index ||
+	    sqe->splice_fd_in || sqe->addr3)
+		return -EINVAL;
+
+	ft->len = READ_ONCE(sqe->off);
+
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_ftruncate(req->file, ft->len, 1);
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
diff --git a/io_uring/truncate.h b/io_uring/truncate.h
new file mode 100644
index 000000000000..ec088293a478
--- /dev/null
+++ b/io_uring/truncate.h
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index c33fca585dde..42f63adfa54a 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -5,6 +5,7 @@
 #include <linux/io_uring/cmd.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
+#include <net/sock.h>
 
 #include <uapi/linux/io_uring.h>
 #include <asm/ioctls.h>
diff --git a/io_uring/xattr.c b/io_uring/xattr.c
index e1c810e0b85a..44905b82eea8 100644
--- a/io_uring/xattr.c
+++ b/io_uring/xattr.c
@@ -112,7 +112,7 @@ int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_getxattr(mnt_idmap(req->file->f_path.mnt),
+	ret = do_getxattr(file_mnt_idmap(req->file),
 			req->file->f_path.dentry,
 			&ix->ctx);
 
diff --git a/kernel/async.c b/kernel/async.c
index 97f224a5257b..4c3e6a44595f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -64,6 +64,7 @@ static async_cookie_t next_cookie = 1;
 static LIST_HEAD(async_global_pending);	/* pending from all registered doms */
 static ASYNC_DOMAIN(async_dfl_domain);
 static DEFINE_SPINLOCK(async_lock);
+static struct workqueue_struct *async_wq;
 
 struct async_entry {
 	struct list_head	domain_list;
@@ -174,7 +175,7 @@ static async_cookie_t __async_schedule_node_domain(async_func_t func,
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
+	queue_work_node(node, async_wq, &entry->work);
 
 	return newcookie;
 }
@@ -345,3 +346,17 @@ bool current_is_async(void)
 	return worker && worker->current_func == async_run_entry_fn;
 }
 EXPORT_SYMBOL_GPL(current_is_async);
+
+void __init async_init(void)
+{
+	/*
+	 * Async can schedule a number of interdependent work items. However,
+	 * unbound workqueues can handle only upto min_active interdependent
+	 * work items. The default min_active of 8 isn't sufficient for async
+	 * and can lead to stalls. Let's use a dedicated workqueue with raised
+	 * min_active.
+	 */
+	async_wq = alloc_workqueue("async", WQ_UNBOUND, 0);
+	BUG_ON(!async_wq);
+	workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE);
+}
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index 370217dd7e39..a4181234232b 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -21,24 +21,20 @@ static void backtrace_test_normal(void)
 	dump_stack();
 }
 
-static DECLARE_COMPLETION(backtrace_work);
-
-static void backtrace_test_irq_callback(unsigned long data)
+static void backtrace_test_bh_workfn(struct work_struct *work)
 {
 	dump_stack();
-	complete(&backtrace_work);
 }
 
-static DECLARE_TASKLET_OLD(backtrace_tasklet, &backtrace_test_irq_callback);
+static DECLARE_WORK(backtrace_bh_work, &backtrace_test_bh_workfn);
 
-static void backtrace_test_irq(void)
+static void backtrace_test_bh(void)
 {
-	pr_info("Testing a backtrace from irq context.\n");
+	pr_info("Testing a backtrace from BH context.\n");
 	pr_info("The following trace is a kernel self test and not a bug!\n");
 
-	init_completion(&backtrace_work);
-	tasklet_schedule(&backtrace_tasklet);
-	wait_for_completion(&backtrace_work);
+	queue_work(system_bh_wq, &backtrace_bh_work);
+	flush_work(&backtrace_bh_work);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -65,7 +61,7 @@ static int backtrace_regression_test(void)
 	pr_info("====[ backtrace testing ]===========\n");
 
 	backtrace_test_normal();
-	backtrace_test_irq();
+	backtrace_test_bh();
 	backtrace_test_saved();
 
 	pr_info("====[ end of backtrace testing ]====\n");
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8a0bb80fe48a..ef82ffc90cbe 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -178,7 +178,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)
 {
-	struct xdp_rxq_info rxq;
+	struct xdp_rxq_info rxq = {};
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index be72824f32b2..d19cd863d294 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1101,6 +1101,7 @@ struct bpf_hrtimer {
 	struct bpf_prog *prog;
 	void __rcu *callback_fn;
 	void *value;
+	struct rcu_head rcu;
 };
 
 /* the actual struct hidden inside uapi struct bpf_timer */
@@ -1332,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer)
 
 	if (in_nmi())
 		return -EOPNOTSUPP;
+	rcu_read_lock();
 	__bpf_spin_lock_irqsave(&timer->lock);
 	t = timer->timer;
 	if (!t) {
@@ -1353,6 +1355,7 @@ out:
 	 * if it was running.
 	 */
 	ret = ret ?: hrtimer_cancel(&t->timer);
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -1407,7 +1410,7 @@ out:
 	 */
 	if (this_cpu_read(hrtimer_running) != t)
 		hrtimer_cancel(&t->timer);
-	kfree(t);
+	kfree_rcu(t, rcu);
 }
 
 BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index e5c3500443c6..ec4e97c61eef 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -978,6 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
 					__alignof__(struct bpf_iter_task));
 
+	kit->pos = NULL;
+
 	switch (flags) {
 	case BPF_TASK_ITER_ALL_THREADS:
 	case BPF_TASK_ITER_ALL_PROCS:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 65f598694d55..ddea9567f755 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5227,7 +5227,9 @@ BTF_ID(struct, prog_test_ref_kfunc)
 #ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
 #endif
+#ifdef CONFIG_BPF_JIT
 BTF_ID(struct, bpf_cpumask)
+#endif
 BTF_ID(struct, task_struct)
 BTF_SET_END(rcu_protected_types)
 
@@ -16600,6 +16602,9 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
 {
 	int i;
 
+	if (old->callback_depth > cur->callback_depth)
+		return false;
+
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (!regsafe(env, &old->regs[i], &cur->regs[i],
 			     &env->idmap_scratch, exact))
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ba36c073304a..4237c8748715 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2562,7 +2562,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		update_partition_sd_lb(cs, old_prs);
 out_free:
 	free_cpumasks(NULL, &tmp);
-	return 0;
+	return retval;
 }
 
 /**
@@ -2598,9 +2598,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
 		return 0;
 
-	if (alloc_cpumasks(NULL, &tmp))
-		return -ENOMEM;
-
 	if (*buf)
 		compute_effective_exclusive_cpumask(trialcs, NULL);
 
@@ -2615,6 +2612,9 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval)
 		return retval;
 
+	if (alloc_cpumasks(NULL, &tmp))
+		return -ENOMEM;
+
 	if (old_prs) {
 		if (cpumask_empty(trialcs->effective_xcpus)) {
 			invalidate = true;
@@ -3897,6 +3897,7 @@ static struct cftype legacy_files[] = {
 	},
 
 	{
+		/* obsolete, may be removed in the future */
 		.name = "memory_spread_slab",
 		.read_u64 = cpuset_read_u64,
 		.write_u64 = cpuset_write_u64,
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 6ef0b35fc28c..70ae70d03823 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -458,6 +458,8 @@ static __always_inline void context_tracking_recursion_exit(void)
  * __ct_user_enter - Inform the context tracking that the CPU is going
  *		     to enter user or guest space mode.
  *
+ * @state: userspace context-tracking state to enter.
+ *
  * This function must be called right before we switch from the kernel
  * to user or guest space, when it's guaranteed the remaining kernel
  * instructions to execute won't use any RCU read side critical section
@@ -595,6 +597,8 @@ NOKPROBE_SYMBOL(user_enter_callable);
  * __ct_user_exit - Inform the context tracking that the CPU is
  *		    exiting user or guest mode and entering the kernel.
  *
+ * @state: userspace context-tracking state being exited from.
+ *
  * This function must be called after we entered the kernel from user or
  * guest space before any use of RCU read side critical section. This
  * potentially include any high level kernel code like syscalls, exceptions,
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e6ec3ba4950b..8f6affd051f7 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -54,7 +54,6 @@
  * @rollback:	Perform a rollback
  * @single:	Single callback invocation
  * @bringup:	Single callback bringup or teardown selector
- * @cpu:	CPU number
  * @node:	Remote CPU node; for multi-instance, do a
  *		single entry callback for install/remove
  * @last:	For multi-instance rollback, remember how far we got
@@ -1324,10 +1323,6 @@ static int take_cpu_down(void *_param)
 	 */
 	cpuhp_invoke_callback_range_nofail(false, cpu, st, target);
 
-	/* Give up timekeeping duties */
-	tick_handover_do_timer();
-	/* Remove CPU from timer broadcasting */
-	tick_offline_cpu(cpu);
 	/* Park the stopper thread */
 	stop_machine_park(cpu);
 	return 0;
@@ -1403,6 +1398,7 @@ void cpuhp_report_idle_dead(void)
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
 
 	BUG_ON(st->state != CPUHP_AP_OFFLINE);
+	tick_assert_timekeeping_handover();
 	rcutree_report_cpu_dead();
 	st->state = CPUHP_AP_IDLE_DEAD;
 	/*
@@ -1909,14 +1905,14 @@ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus)
 static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; }
 #endif /* CONFIG_HOTPLUG_PARALLEL */
 
-void __init bringup_nonboot_cpus(unsigned int setup_max_cpus)
+void __init bringup_nonboot_cpus(unsigned int max_cpus)
 {
 	/* Try parallel bringup optimization if enabled */
-	if (cpuhp_bringup_cpus_parallel(setup_max_cpus))
+	if (cpuhp_bringup_cpus_parallel(max_cpus))
 		return;
 
 	/* Full per CPU serialized bringup */
-	cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE);
+	cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE);
 }
 
 #ifdef CONFIG_PM_SLEEP_SMP
@@ -2205,7 +2201,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= NULL,
 		.teardown.single	= hrtimers_cpu_dying,
 	},
-
+	[CPUHP_AP_TICK_DYING] = {
+		.name			= "tick:dying",
+		.startup.single		= NULL,
+		.teardown.single	= tick_cpu_dying,
+	},
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
 	[CPUHP_AP_ONLINE] = {
@@ -3005,7 +3005,7 @@ static ssize_t control_show(struct device *dev,
 		return sysfs_emit(buf, "%d\n", cpu_smt_num_threads);
 #endif
 
-	return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+	return sysfs_emit(buf, "%s\n", state);
 }
 
 static ssize_t control_store(struct device *dev, struct device_attribute *attr,
@@ -3018,7 +3018,7 @@ static DEVICE_ATTR_RW(control);
 static ssize_t active_show(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
+	return sysfs_emit(buf, "%d\n", sched_smt_active());
 }
 static DEVICE_ATTR_RO(active);
 
@@ -3107,10 +3107,10 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
 EXPORT_SYMBOL(cpu_all_bits);
 
 #ifdef CONFIG_INIT_ALL_POSSIBLE
-struct cpumask __cpu_possible_mask __read_mostly
+struct cpumask __cpu_possible_mask __ro_after_init
 	= {CPU_BITS_ALL};
 #else
-struct cpumask __cpu_possible_mask __read_mostly;
+struct cpumask __cpu_possible_mask __ro_after_init;
 #endif
 EXPORT_SYMBOL(__cpu_possible_mask);
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 485bb0389b48..929e98c62965 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -537,7 +537,7 @@ retry:
 		}
 	}
 
-	ret = __replace_page(vma, vaddr, old_page, new_page);
+	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
 	if (new_page)
 		put_page(new_page);
 put_old:
diff --git a/kernel/exit.c b/kernel/exit.c
index 3988a02efaef..41a12630cbbc 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
 	tsk->exit_state = EXIT_ZOMBIE;
+	/*
+	 * sub-thread or delay_group_leader(), wake up the
+	 * PIDFD_THREAD waiters.
+	 */
+	if (!thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
+
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
@@ -1127,17 +1134,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * and nobody can change them.
 		 *
 		 * psig->stats_lock also protects us from our sub-threads
-		 * which can reap other children at the same time. Until
-		 * we change k_getrusage()-like users to rely on this lock
-		 * we have to take ->siglock as well.
+		 * which can reap other children at the same time.
 		 *
 		 * We use thread_group_cputime_adjusted() to get times for
 		 * the thread group, which consolidates times for all threads
 		 * in the group including the group leader.
 		 */
 		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		spin_lock_irq(&current->sighand->siglock);
-		write_seqlock(&psig->stats_lock);
+		write_seqlock_irq(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1160,8 +1164,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
-		write_sequnlock(&psig->stats_lock);
-		spin_unlock_irq(&current->sighand->siglock);
+		write_sequnlock_irq(&psig->stats_lock);
 	}
 
 	if (wo->wo_rusage)
@@ -1893,30 +1896,6 @@ Efault:
 }
 #endif
 
-/**
- * thread_group_exited - check that a thread group has exited
- * @pid: tgid of thread group to be checked.
- *
- * Test if the thread group represented by tgid has exited (all
- * threads are zombies, dead or completely gone).
- *
- * Return: true if the thread group has exited. false otherwise.
- */
-bool thread_group_exited(struct pid *pid)
-{
-	struct task_struct *task;
-	bool exited;
-
-	rcu_read_lock();
-	task = pid_task(pid, PIDTYPE_PID);
-	exited = !task ||
-		(READ_ONCE(task->exit_state) && thread_group_empty(task));
-	rcu_read_unlock();
-
-	return exited;
-}
-EXPORT_SYMBOL(thread_group_exited);
-
 /*
  * This needs to be __function_aligned as GCC implicitly makes any
  * implementation of abort() cold and drops alignment specified by
diff --git a/kernel/fork.c b/kernel/fork.c
index 0d944e92a43f..39a5046c2f0b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -101,6 +101,8 @@
 #include <linux/user_events.h>
 #include <linux/iommu.h>
 #include <linux/rseq.h>
+#include <uapi/linux/pidfd.h>
+#include <linux/pidfs.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -1976,6 +1978,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 	p->rcu_tasks_holdout = false;
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
+	INIT_LIST_HEAD(&p->rcu_tasks_exit_list);
 #endif /* #ifdef CONFIG_TASKS_RCU */
 #ifdef CONFIG_TASKS_TRACE_RCU
 	p->trc_reader_nesting = 0;
@@ -1985,119 +1988,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
-struct pid *pidfd_pid(const struct file *file)
-{
-	if (file->f_op == &pidfd_fops)
-		return file->private_data;
-
-	return ERR_PTR(-EBADF);
-}
-
-static int pidfd_release(struct inode *inode, struct file *file)
-{
-	struct pid *pid = file->private_data;
-
-	file->private_data = NULL;
-	put_pid(pid);
-	return 0;
-}
-
-#ifdef CONFIG_PROC_FS
-/**
- * pidfd_show_fdinfo - print information about a pidfd
- * @m: proc fdinfo file
- * @f: file referencing a pidfd
- *
- * Pid:
- * This function will print the pid that a given pidfd refers to in the
- * pid namespace of the procfs instance.
- * If the pid namespace of the process is not a descendant of the pid
- * namespace of the procfs instance 0 will be shown as its pid. This is
- * similar to calling getppid() on a process whose parent is outside of
- * its pid namespace.
- *
- * NSpid:
- * If pid namespaces are supported then this function will also print
- * the pid of a given pidfd refers to for all descendant pid namespaces
- * starting from the current pid namespace of the instance, i.e. the
- * Pid field and the first entry in the NSpid field will be identical.
- * If the pid namespace of the process is not a descendant of the pid
- * namespace of the procfs instance 0 will be shown as its first NSpid
- * entry and no others will be shown.
- * Note that this differs from the Pid and NSpid fields in
- * /proc/<pid>/status where Pid and NSpid are always shown relative to
- * the  pid namespace of the procfs instance. The difference becomes
- * obvious when sending around a pidfd between pid namespaces from a
- * different branch of the tree, i.e. where no ancestral relation is
- * present between the pid namespaces:
- * - create two new pid namespaces ns1 and ns2 in the initial pid
- *   namespace (also take care to create new mount namespaces in the
- *   new pid namespace and mount procfs)
- * - create a process with a pidfd in ns1
- * - send pidfd from ns1 to ns2
- * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
- *   have exactly one entry, which is 0
- */
-static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
-{
-	struct pid *pid = f->private_data;
-	struct pid_namespace *ns;
-	pid_t nr = -1;
-
-	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
-		ns = proc_pid_ns(file_inode(m->file)->i_sb);
-		nr = pid_nr_ns(pid, ns);
-	}
-
-	seq_put_decimal_ll(m, "Pid:\t", nr);
-
-#ifdef CONFIG_PID_NS
-	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
-	if (nr > 0) {
-		int i;
-
-		/* If nr is non-zero it means that 'pid' is valid and that
-		 * ns, i.e. the pid namespace associated with the procfs
-		 * instance, is in the pid namespace hierarchy of pid.
-		 * Start at one below the already printed level.
-		 */
-		for (i = ns->level + 1; i <= pid->level; i++)
-			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
-	}
-#endif
-	seq_putc(m, '\n');
-}
-#endif
-
-/*
- * Poll support for process exit notification.
- */
-static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
-{
-	struct pid *pid = file->private_data;
-	__poll_t poll_flags = 0;
-
-	poll_wait(file, &pid->wait_pidfd, pts);
-
-	/*
-	 * Inform pollers only when the whole thread group exits.
-	 * If the thread group leader exits before all other threads in the
-	 * group, then poll(2) should block, similar to the wait(2) family.
-	 */
-	if (thread_group_exited(pid))
-		poll_flags = EPOLLIN | EPOLLRDNORM;
-
-	return poll_flags;
-}
-
-const struct file_operations pidfd_fops = {
-	.release = pidfd_release,
-	.poll = pidfd_poll,
-#ifdef CONFIG_PROC_FS
-	.show_fdinfo = pidfd_show_fdinfo,
-#endif
-};
-
 /**
  * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
  * @pid:   the struct pid for which to create a pidfd
@@ -2131,20 +2021,20 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
 	int pidfd;
 	struct file *pidfd_file;
 
-	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
-		return -EINVAL;
-
-	pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	pidfd = get_unused_fd_flags(O_CLOEXEC);
 	if (pidfd < 0)
 		return pidfd;
 
-	pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
-					flags | O_RDWR | O_CLOEXEC);
+	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
 	if (IS_ERR(pidfd_file)) {
 		put_unused_fd(pidfd);
 		return PTR_ERR(pidfd_file);
 	}
-	get_pid(pid); /* held by pidfd_file now */
+	/*
+	 * anon_inode_getfile() ignores everything outside of the
+	 * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually.
+	 */
+	pidfd_file->f_flags |= (flags & PIDFD_THREAD);
 	*ret = pidfd_file;
 	return pidfd;
 }
@@ -2158,7 +2048,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  * Allocate a new file that stashes @pid and reserve a new pidfd number in the
  * caller's file descriptor table. The pidfd is reserved but not installed yet.
  *
- * The helper verifies that @pid is used as a thread group leader.
+ * The helper verifies that @pid is still in use, without PIDFD_THREAD the
+ * task identified by @pid must be a thread-group leader.
  *
  * If this function returns successfully the caller is responsible to either
  * call fd_install() passing the returned pidfd and pidfd file as arguments in
@@ -2177,7 +2068,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  */
 int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 {
-	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
+	bool thread = flags & PIDFD_THREAD;
+
+	if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID))
 		return -EINVAL;
 
 	return __pidfd_prepare(pid, flags, ret);
@@ -2299,9 +2192,8 @@ __latent_entropy struct task_struct *copy_process(
 		/*
 		 * - CLONE_DETACHED is blocked so that we can potentially
 		 *   reuse it later for CLONE_PIDFD.
-		 * - CLONE_THREAD is blocked until someone really needs it.
 		 */
-		if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
+		if (clone_flags & CLONE_DETACHED)
 			return ERR_PTR(-EINVAL);
 	}
 
@@ -2524,8 +2416,10 @@ __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
+		int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0;
+
 		/* Note that no task has been attached to @pid yet. */
-		retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile);
+		retval = __pidfd_prepare(pid, flags, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;
@@ -2876,8 +2770,8 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 	 * here has the advantage that we don't need to have a separate helper
 	 * to check for legacy clone().
 	 */
-	if ((args->flags & CLONE_PIDFD) &&
-	    (args->flags & CLONE_PARENT_SETTID) &&
+	if ((clone_flags & CLONE_PIDFD) &&
+	    (clone_flags & CLONE_PARENT_SETTID) &&
 	    (args->pidfd == args->parent_tid))
 		return -EINVAL;
 
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index dd76323ea3fd..38d6ae651ac7 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -4,10 +4,11 @@
  * Copyright (C) 2020 Bartosz Golaszewski <bgolaszewski@baylibre.com>
  */
 
+#include <linux/cleanup.h>
+#include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irq_sim.h>
 #include <linux/irq_work.h>
-#include <linux/interrupt.h>
 #include <linux/slab.h>
 
 struct irq_sim_work_ctx {
@@ -19,7 +20,6 @@ struct irq_sim_work_ctx {
 };
 
 struct irq_sim_irq_ctx {
-	int			irqnum;
 	bool			enabled;
 	struct irq_sim_work_ctx	*work_ctx;
 };
@@ -164,33 +164,27 @@ static const struct irq_domain_ops irq_sim_domain_ops = {
 struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode,
 					 unsigned int num_irqs)
 {
-	struct irq_sim_work_ctx *work_ctx;
+	struct irq_sim_work_ctx *work_ctx __free(kfree) =
+				kmalloc(sizeof(*work_ctx), GFP_KERNEL);
 
-	work_ctx = kmalloc(sizeof(*work_ctx), GFP_KERNEL);
 	if (!work_ctx)
-		goto err_out;
+		return ERR_PTR(-ENOMEM);
 
-	work_ctx->pending = bitmap_zalloc(num_irqs, GFP_KERNEL);
-	if (!work_ctx->pending)
-		goto err_free_work_ctx;
+	unsigned long *pending __free(bitmap) = bitmap_zalloc(num_irqs, GFP_KERNEL);
+	if (!pending)
+		return ERR_PTR(-ENOMEM);
 
 	work_ctx->domain = irq_domain_create_linear(fwnode, num_irqs,
 						    &irq_sim_domain_ops,
 						    work_ctx);
 	if (!work_ctx->domain)
-		goto err_free_bitmap;
+		return ERR_PTR(-ENOMEM);
 
 	work_ctx->irq_count = num_irqs;
 	work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq);
+	work_ctx->pending = no_free_ptr(pending);
 
-	return work_ctx->domain;
-
-err_free_bitmap:
-	bitmap_free(work_ctx->pending);
-err_free_work_ctx:
-	kfree(work_ctx);
-err_out:
-	return ERR_PTR(-ENOMEM);
+	return no_free_ptr(work_ctx)->domain;
 }
 EXPORT_SYMBOL_GPL(irq_domain_create_sim);
 
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 371eb1711d34..4c6b32318ce3 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -92,11 +92,23 @@ static void desc_smp_init(struct irq_desc *desc, int node,
 #endif
 }
 
+static void free_masks(struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	free_cpumask_var(desc->pending_mask);
+#endif
+	free_cpumask_var(desc->irq_common_data.affinity);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	free_cpumask_var(desc->irq_common_data.effective_affinity);
+#endif
+}
+
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, int node) { return 0; }
 static inline void
 desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
+static inline void free_masks(struct irq_desc *desc) { }
 #endif
 
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
@@ -166,6 +178,39 @@ static void delete_irq_desc(unsigned int irq)
 }
 
 #ifdef CONFIG_SPARSE_IRQ
+static const struct kobj_type irq_kobj_type;
+#endif
+
+static int init_desc(struct irq_desc *desc, int irq, int node,
+		     unsigned int flags,
+		     const struct cpumask *affinity,
+		     struct module *owner)
+{
+	desc->kstat_irqs = alloc_percpu(unsigned int);
+	if (!desc->kstat_irqs)
+		return -ENOMEM;
+
+	if (alloc_masks(desc, node)) {
+		free_percpu(desc->kstat_irqs);
+		return -ENOMEM;
+	}
+
+	raw_spin_lock_init(&desc->lock);
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	mutex_init(&desc->request_mutex);
+	init_waitqueue_head(&desc->wait_for_threads);
+	desc_set_defaults(irq, desc, node, affinity, owner);
+	irqd_set(&desc->irq_data, flags);
+	irq_resend_init(desc);
+#ifdef CONFIG_SPARSE_IRQ
+	kobject_init(&desc->kobj, &irq_kobj_type);
+	init_rcu_head(&desc->rcu);
+#endif
+
+	return 0;
+}
+
+#ifdef CONFIG_SPARSE_IRQ
 
 static void irq_kobj_release(struct kobject *kobj);
 
@@ -384,21 +429,6 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 EXPORT_SYMBOL_GPL(irq_to_desc);
 #endif
 
-#ifdef CONFIG_SMP
-static void free_masks(struct irq_desc *desc)
-{
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	free_cpumask_var(desc->pending_mask);
-#endif
-	free_cpumask_var(desc->irq_common_data.affinity);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
-	free_cpumask_var(desc->irq_common_data.effective_affinity);
-#endif
-}
-#else
-static inline void free_masks(struct irq_desc *desc) { }
-#endif
-
 void irq_lock_sparse(void)
 {
 	mutex_lock(&sparse_irq_lock);
@@ -414,36 +444,19 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
 				   struct module *owner)
 {
 	struct irq_desc *desc;
+	int ret;
 
 	desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node);
 	if (!desc)
 		return NULL;
-	/* allocate based on nr_cpu_ids */
-	desc->kstat_irqs = alloc_percpu(unsigned int);
-	if (!desc->kstat_irqs)
-		goto err_desc;
-
-	if (alloc_masks(desc, node))
-		goto err_kstat;
 
-	raw_spin_lock_init(&desc->lock);
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	mutex_init(&desc->request_mutex);
-	init_rcu_head(&desc->rcu);
-	init_waitqueue_head(&desc->wait_for_threads);
-
-	desc_set_defaults(irq, desc, node, affinity, owner);
-	irqd_set(&desc->irq_data, flags);
-	kobject_init(&desc->kobj, &irq_kobj_type);
-	irq_resend_init(desc);
+	ret = init_desc(desc, irq, node, flags, affinity, owner);
+	if (unlikely(ret)) {
+		kfree(desc);
+		return NULL;
+	}
 
 	return desc;
-
-err_kstat:
-	free_percpu(desc->kstat_irqs);
-err_desc:
-	kfree(desc);
-	return NULL;
 }
 
 static void irq_kobj_release(struct kobject *kobj)
@@ -583,26 +596,29 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 int __init early_irq_init(void)
 {
 	int count, i, node = first_online_node;
-	struct irq_desc *desc;
+	int ret;
 
 	init_irq_default_affinity();
 
 	printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS);
 
-	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
 	for (i = 0; i < count; i++) {
-		desc[i].kstat_irqs = alloc_percpu(unsigned int);
-		alloc_masks(&desc[i], node);
-		raw_spin_lock_init(&desc[i].lock);
-		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		mutex_init(&desc[i].request_mutex);
-		init_waitqueue_head(&desc[i].wait_for_threads);
-		desc_set_defaults(i, &desc[i], node, NULL, NULL);
-		irq_resend_init(&desc[i]);
+		ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL);
+		if (unlikely(ret))
+			goto __free_desc_res;
 	}
+
 	return arch_early_irq_init();
+
+__free_desc_res:
+	while (--i >= 0) {
+		free_masks(irq_desc + i);
+		free_percpu(irq_desc[i].kstat_irqs);
+	}
+
+	return ret;
 }
 
 struct irq_desc *irq_to_desc(unsigned int irq)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 0bdef4fe925b..3dd1c871e091 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -29,6 +29,7 @@ static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
 					unsigned int nr_irqs, int node, void *arg,
 					bool realloc, const struct irq_affinity_desc *affinity);
 static void irq_domain_check_hierarchy(struct irq_domain *domain);
+static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq);
 
 struct irqchip_fwid {
 	struct fwnode_handle	fwnode;
@@ -448,7 +449,7 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 	 */
 	mutex_lock(&irq_domain_mutex);
 	list_for_each_entry(h, &irq_domain_list, link) {
-		if (h->ops->select && fwspec->param_count)
+		if (h->ops->select && bus_token != DOMAIN_BUS_ANY)
 			rc = h->ops->select(h, fwspec, bus_token);
 		else if (h->ops->match)
 			rc = h->ops->match(h, to_of_node(fwnode), bus_token);
@@ -858,8 +859,13 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 	}
 
 	if (irq_domain_is_hierarchy(domain)) {
-		virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE,
-						    fwspec, false, NULL);
+		if (irq_domain_is_msi_device(domain)) {
+			mutex_unlock(&domain->root->mutex);
+			virq = msi_device_domain_alloc_wired(domain, hwirq, type);
+			mutex_lock(&domain->root->mutex);
+		} else
+			virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE,
+							    fwspec, false, NULL);
 		if (virq <= 0) {
 			virq = 0;
 			goto out;
@@ -914,7 +920,7 @@ void irq_dispose_mapping(unsigned int virq)
 		return;
 
 	if (irq_domain_is_hierarchy(domain)) {
-		irq_domain_free_irqs(virq, 1);
+		irq_domain_free_one_irq(domain, virq);
 	} else {
 		irq_domain_disassociate(domain, virq);
 		irq_free_desc(virq);
@@ -1755,6 +1761,14 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
 	irq_free_descs(virq, nr_irqs);
 }
 
+static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq)
+{
+	if (irq_domain_is_msi_device(domain))
+		msi_device_domain_free_wired(domain, virq);
+	else
+		irq_domain_free_irqs(virq, 1);
+}
+
 /**
  * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain
  * @domain:	Domain below which interrupts must be allocated
@@ -1907,9 +1921,9 @@ static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
 	return -EINVAL;
 }
 
-static void irq_domain_check_hierarchy(struct irq_domain *domain)
-{
-}
+static void irq_domain_check_hierarchy(struct irq_domain *domain) { }
+static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq) { }
+
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1782f90cd8c6..ad3eaf2ab959 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -192,10 +192,14 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 	struct irqaction *action;
 
 	for_each_action_of_desc(desc, action) {
-		if (action->thread)
+		if (action->thread) {
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
-		if (action->secondary && action->secondary->thread)
+			wake_up_process(action->thread);
+		}
+		if (action->secondary && action->secondary->thread) {
 			set_bit(IRQTF_AFFINITY, &action->secondary->thread_flags);
+			wake_up_process(action->secondary->thread);
+		}
 	}
 }
 
@@ -1049,10 +1053,57 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static int irq_wait_for_interrupt(struct irqaction *action)
+#ifdef CONFIG_SMP
+/*
+ * Check whether we need to change the affinity of the interrupt thread.
+ */
+static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
+{
+	cpumask_var_t mask;
+	bool valid = false;
+
+	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
+		return;
+
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * In case we are out of memory we set IRQTF_AFFINITY again and
+	 * try again next time
+	 */
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
+		set_bit(IRQTF_AFFINITY, &action->thread_flags);
+		return;
+	}
+
+	raw_spin_lock_irq(&desc->lock);
+	/*
+	 * This code is triggered unconditionally. Check the affinity
+	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
+	 */
+	if (cpumask_available(desc->irq_common_data.affinity)) {
+		const struct cpumask *m;
+
+		m = irq_data_get_effective_affinity_mask(&desc->irq_data);
+		cpumask_copy(mask, m);
+		valid = true;
+	}
+	raw_spin_unlock_irq(&desc->lock);
+
+	if (valid)
+		set_cpus_allowed_ptr(current, mask);
+	free_cpumask_var(mask);
+}
+#else
+static inline void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
+#endif
+
+static int irq_wait_for_interrupt(struct irq_desc *desc,
+				  struct irqaction *action)
 {
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		irq_thread_check_affinity(desc, action);
 
 		if (kthread_should_stop()) {
 			/* may need to run one last time */
@@ -1129,52 +1180,6 @@ out_unlock:
 	chip_bus_sync_unlock(desc);
 }
 
-#ifdef CONFIG_SMP
-/*
- * Check whether we need to change the affinity of the interrupt thread.
- */
-static void
-irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
-{
-	cpumask_var_t mask;
-	bool valid = true;
-
-	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
-		return;
-
-	/*
-	 * In case we are out of memory we set IRQTF_AFFINITY again and
-	 * try again next time
-	 */
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
-		set_bit(IRQTF_AFFINITY, &action->thread_flags);
-		return;
-	}
-
-	raw_spin_lock_irq(&desc->lock);
-	/*
-	 * This code is triggered unconditionally. Check the affinity
-	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
-	 */
-	if (cpumask_available(desc->irq_common_data.affinity)) {
-		const struct cpumask *m;
-
-		m = irq_data_get_effective_affinity_mask(&desc->irq_data);
-		cpumask_copy(mask, m);
-	} else {
-		valid = false;
-	}
-	raw_spin_unlock_irq(&desc->lock);
-
-	if (valid)
-		set_cpus_allowed_ptr(current, mask);
-	free_cpumask_var(mask);
-}
-#else
-static inline void
-irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
-#endif
-
 /*
  * Interrupts which are not explicitly requested as threaded
  * interrupts rely on the implicit bh/preempt disable of the hard irq
@@ -1312,13 +1317,9 @@ static int irq_thread(void *data)
 	init_task_work(&on_exit_work, irq_thread_dtor);
 	task_work_add(current, &on_exit_work, TWA_NONE);
 
-	irq_thread_check_affinity(desc, action);
-
-	while (!irq_wait_for_interrupt(action)) {
+	while (!irq_wait_for_interrupt(desc, action)) {
 		irqreturn_t action_ret;
 
-		irq_thread_check_affinity(desc, action);
-
 		action_ret = handler_fn(desc, action);
 		if (action_ret == IRQ_WAKE_THREAD)
 			irq_wake_secondary(desc, action);
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 75d0ae490e29..8f222d1cccec 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -8,8 +8,6 @@
 #include <linux/cpu.h>
 #include <linux/irq.h>
 
-#define IRQ_MATRIX_SIZE	(BITS_TO_LONGS(IRQ_MATRIX_BITS))
-
 struct cpumap {
 	unsigned int		available;
 	unsigned int		allocated;
@@ -17,8 +15,8 @@ struct cpumap {
 	unsigned int		managed_allocated;
 	bool			initialized;
 	bool			online;
-	unsigned long		alloc_map[IRQ_MATRIX_SIZE];
-	unsigned long		managed_map[IRQ_MATRIX_SIZE];
+	unsigned long		*managed_map;
+	unsigned long		alloc_map[];
 };
 
 struct irq_matrix {
@@ -32,8 +30,8 @@ struct irq_matrix {
 	unsigned int		total_allocated;
 	unsigned int		online_maps;
 	struct cpumap __percpu	*maps;
-	unsigned long		scratch_map[IRQ_MATRIX_SIZE];
-	unsigned long		system_map[IRQ_MATRIX_SIZE];
+	unsigned long		*system_map;
+	unsigned long		scratch_map[];
 };
 
 #define CREATE_TRACE_POINTS
@@ -50,24 +48,32 @@ __init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits,
 					   unsigned int alloc_start,
 					   unsigned int alloc_end)
 {
+	unsigned int cpu, matrix_size = BITS_TO_LONGS(matrix_bits);
 	struct irq_matrix *m;
 
-	if (matrix_bits > IRQ_MATRIX_BITS)
-		return NULL;
-
-	m = kzalloc(sizeof(*m), GFP_KERNEL);
+	m = kzalloc(struct_size(m, scratch_map, matrix_size * 2), GFP_KERNEL);
 	if (!m)
 		return NULL;
 
+	m->system_map = &m->scratch_map[matrix_size];
+
 	m->matrix_bits = matrix_bits;
 	m->alloc_start = alloc_start;
 	m->alloc_end = alloc_end;
 	m->alloc_size = alloc_end - alloc_start;
-	m->maps = alloc_percpu(*m->maps);
+	m->maps = __alloc_percpu(struct_size(m->maps, alloc_map, matrix_size * 2),
+				 __alignof__(*m->maps));
 	if (!m->maps) {
 		kfree(m);
 		return NULL;
 	}
+
+	for_each_possible_cpu(cpu) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+
+		cm->managed_map = &cm->alloc_map[matrix_size];
+	}
+
 	return m;
 }
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 79b4a58ba9c3..f90952ebc494 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -726,11 +726,26 @@ static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
+static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fwspec,
+				irq_hw_number_t *hwirq, unsigned int *type)
+{
+	struct msi_domain_info *info = domain->host_data;
+
+	/*
+	 * This will catch allocations through the regular irqdomain path except
+	 * for MSI domains which really support this, e.g. MBIGEN.
+	 */
+	if (!info->ops->msi_translate)
+		return -ENOTSUPP;
+	return info->ops->msi_translate(domain, fwspec, hwirq, type);
+}
+
 static const struct irq_domain_ops msi_domain_ops = {
 	.alloc		= msi_domain_alloc,
 	.free		= msi_domain_free,
 	.activate	= msi_domain_activate,
 	.deactivate	= msi_domain_deactivate,
+	.translate	= msi_domain_translate,
 };
 
 static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
@@ -830,8 +845,11 @@ static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode,
 	domain = irq_domain_create_hierarchy(parent, flags | IRQ_DOMAIN_FLAG_MSI, 0,
 					     fwnode, &msi_domain_ops, info);
 
-	if (domain)
+	if (domain) {
 		irq_domain_update_bus_token(domain, info->bus_token);
+		if (info->flags & MSI_FLAG_PARENT_PM_DEV)
+			domain->pm_dev = parent->pm_dev;
+	}
 
 	return domain;
 }
@@ -945,9 +963,9 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 				  void *chip_data)
 {
 	struct irq_domain *domain, *parent = dev->msi.domain;
-	const struct msi_parent_ops *pops;
+	struct fwnode_handle *fwnode, *fwnalloced = NULL;
 	struct msi_domain_template *bundle;
-	struct fwnode_handle *fwnode;
+	const struct msi_parent_ops *pops;
 
 	if (!irq_domain_is_msi_parent(parent))
 		return false;
@@ -970,7 +988,19 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 		 pops->prefix ? : "", bundle->chip.name, dev_name(dev));
 	bundle->chip.name = bundle->name;
 
-	fwnode = irq_domain_alloc_named_fwnode(bundle->name);
+	/*
+	 * Using the device firmware node is required for wire to MSI
+	 * device domains so that the existing firmware results in a domain
+	 * match.
+	 * All other device domains like PCI/MSI use the named firmware
+	 * node as they are not guaranteed to have a fwnode. They are never
+	 * looked up and always handled in the context of the device.
+	 */
+	if (bundle->info.flags & MSI_FLAG_USE_DEV_FWNODE)
+		fwnode = dev->fwnode;
+	else
+		fwnode = fwnalloced = irq_domain_alloc_named_fwnode(bundle->name);
+
 	if (!fwnode)
 		goto free_bundle;
 
@@ -997,7 +1027,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 fail:
 	msi_unlock_descs(dev);
 free_fwnode:
-	irq_domain_free_fwnode(fwnode);
+	irq_domain_free_fwnode(fwnalloced);
 free_bundle:
 	kfree(bundle);
 	return false;
@@ -1431,34 +1461,10 @@ int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int
 	return msi_domain_alloc_locked(dev, &ctrl);
 }
 
-/**
- * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at
- *			     a given index - or at the next free index
- *
- * @dev:	Pointer to device struct of the device for which the interrupts
- *		are allocated
- * @domid:	Id of the interrupt domain to operate on
- * @index:	Index for allocation. If @index == %MSI_ANY_INDEX the allocation
- *		uses the next free index.
- * @affdesc:	Optional pointer to an interrupt affinity descriptor structure
- * @icookie:	Optional pointer to a domain specific per instance cookie. If
- *		non-NULL the content of the cookie is stored in msi_desc::data.
- *		Must be NULL for MSI-X allocations
- *
- * This requires a MSI interrupt domain which lets the core code manage the
- * MSI descriptors.
- *
- * Return: struct msi_map
- *
- *	On success msi_map::index contains the allocated index number and
- *	msi_map::virq the corresponding Linux interrupt number
- *
- *	On failure msi_map::index contains the error code and msi_map::virq
- *	is %0.
- */
-struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index,
-				       const struct irq_affinity_desc *affdesc,
-				       union msi_instance_cookie *icookie)
+static struct msi_map __msi_domain_alloc_irq_at(struct device *dev, unsigned int domid,
+						unsigned int index,
+						const struct irq_affinity_desc *affdesc,
+						union msi_instance_cookie *icookie)
 {
 	struct msi_ctrl ctrl = { .domid	= domid, .nirqs = 1, };
 	struct irq_domain *domain;
@@ -1466,17 +1472,16 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u
 	struct msi_desc *desc;
 	int ret;
 
-	msi_lock_descs(dev);
 	domain = msi_get_device_domain(dev, domid);
 	if (!domain) {
 		map.index = -ENODEV;
-		goto unlock;
+		return map;
 	}
 
 	desc = msi_alloc_desc(dev, 1, affdesc);
 	if (!desc) {
 		map.index = -ENOMEM;
-		goto unlock;
+		return map;
 	}
 
 	if (icookie)
@@ -1485,7 +1490,7 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u
 	ret = msi_insert_desc(dev, desc, domid, index);
 	if (ret) {
 		map.index = ret;
-		goto unlock;
+		return map;
 	}
 
 	ctrl.first = ctrl.last = desc->msi_index;
@@ -1498,11 +1503,90 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u
 		map.index = desc->msi_index;
 		map.virq = desc->irq;
 	}
-unlock:
+	return map;
+}
+
+/**
+ * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at
+ *			     a given index - or at the next free index
+ *
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are allocated
+ * @domid:	Id of the interrupt domain to operate on
+ * @index:	Index for allocation. If @index == %MSI_ANY_INDEX the allocation
+ *		uses the next free index.
+ * @affdesc:	Optional pointer to an interrupt affinity descriptor structure
+ * @icookie:	Optional pointer to a domain specific per instance cookie. If
+ *		non-NULL the content of the cookie is stored in msi_desc::data.
+ *		Must be NULL for MSI-X allocations
+ *
+ * This requires a MSI interrupt domain which lets the core code manage the
+ * MSI descriptors.
+ *
+ * Return: struct msi_map
+ *
+ *	On success msi_map::index contains the allocated index number and
+ *	msi_map::virq the corresponding Linux interrupt number
+ *
+ *	On failure msi_map::index contains the error code and msi_map::virq
+ *	is %0.
+ */
+struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index,
+				       const struct irq_affinity_desc *affdesc,
+				       union msi_instance_cookie *icookie)
+{
+	struct msi_map map;
+
+	msi_lock_descs(dev);
+	map = __msi_domain_alloc_irq_at(dev, domid, index, affdesc, icookie);
 	msi_unlock_descs(dev);
 	return map;
 }
 
+/**
+ * msi_device_domain_alloc_wired - Allocate a "wired" interrupt on @domain
+ * @domain:	The domain to allocate on
+ * @hwirq:	The hardware interrupt number to allocate for
+ * @type:	The interrupt type
+ *
+ * This weirdness supports wire to MSI controllers like MBIGEN.
+ *
+ * @hwirq is the hardware interrupt number which is handed in from
+ * irq_create_fwspec_mapping(). As the wire to MSI domain is sparse, but
+ * sized in firmware, the hardware interrupt number cannot be used as MSI
+ * index. For the underlying irq chip the MSI index is irrelevant and
+ * all it needs is the hardware interrupt number.
+ *
+ * To handle this the MSI index is allocated with MSI_ANY_INDEX and the
+ * hardware interrupt number is stored along with the type information in
+ * msi_desc::cookie so the underlying interrupt chip and domain code can
+ * retrieve it.
+ *
+ * Return: The Linux interrupt number (> 0) or an error code
+ */
+int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+				  unsigned int type)
+{
+	unsigned int domid = MSI_DEFAULT_DOMAIN;
+	union msi_instance_cookie icookie = { };
+	struct device *dev = domain->dev;
+	struct msi_map map = { };
+
+	if (WARN_ON_ONCE(!dev || domain->bus_token != DOMAIN_BUS_WIRED_TO_MSI))
+		return -EINVAL;
+
+	icookie.value = ((u64)type << 32) | hwirq;
+
+	msi_lock_descs(dev);
+	if (WARN_ON_ONCE(msi_get_device_domain(dev, domid) != domain))
+		map.index = -EINVAL;
+	else
+		map = __msi_domain_alloc_irq_at(dev, domid, MSI_ANY_INDEX, NULL, &icookie);
+	msi_unlock_descs(dev);
+
+	return map.index >= 0 ? map.virq : map.index;
+}
+
 static void __msi_domain_free_irqs(struct device *dev, struct irq_domain *domain,
 				   struct msi_ctrl *ctrl)
 {
@@ -1629,6 +1713,30 @@ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid)
 }
 
 /**
+ * msi_device_domain_free_wired - Free a wired interrupt in @domain
+ * @domain:	The domain to free the interrupt on
+ * @virq:	The Linux interrupt number to free
+ *
+ * This is the counterpart of msi_device_domain_alloc_wired() for the
+ * weird wired to MSI converting domains.
+ */
+void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq)
+{
+	struct msi_desc *desc = irq_get_msi_desc(virq);
+	struct device *dev = domain->dev;
+
+	if (WARN_ON_ONCE(!dev || !desc || domain->bus_token != DOMAIN_BUS_WIRED_TO_MSI))
+		return;
+
+	msi_lock_descs(dev);
+	if (!WARN_ON_ONCE(msi_get_device_domain(dev, MSI_DEFAULT_DOMAIN) != domain)) {
+		msi_domain_free_irqs_range_locked(dev, MSI_DEFAULT_DOMAIN, desc->msi_index,
+						  desc->msi_index);
+	}
+	msi_unlock_descs(dev);
+}
+
+/**
  * msi_get_domain_info - Get the MSI interrupt domain info for @domain
  * @domain:	The interrupt domain to retrieve data from
  *
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d5a0ee40bf66..9d9095e81792 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1993,7 +1993,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr);
 unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
 				      struct llist_node **cur)
 {
-	struct kretprobe_instance *ri = NULL;
+	struct kretprobe_instance *ri;
 	kprobe_opcode_t *ret;
 
 	if (WARN_ON_ONCE(!cur))
@@ -2802,7 +2802,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v)
 {
 	struct hlist_head *head;
 	struct kprobe *p, *kp;
-	const char *sym = NULL;
+	const char *sym;
 	unsigned int i = *(loff_t *) v;
 	unsigned long offset = 0;
 	char *modname, namebuf[KSYM_NAME_LEN];
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 185bd1c906b0..6083883c4fe0 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -223,9 +223,10 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
 
 void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 {
+	bool contended = false;
+
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
-	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
 
 	/* Notify readers to take the slow path. */
 	rcu_sync_enter(&sem->rss);
@@ -234,8 +235,11 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 	 * Try set sem->block; this provides writer-writer exclusion.
 	 * Having sem->block set makes new readers block.
 	 */
-	if (!__percpu_down_write_trylock(sem))
+	if (!__percpu_down_write_trylock(sem)) {
+		trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
 		percpu_rwsem_wait(sem, /* .reader = */ false);
+		contended = true;
+	}
 
 	/* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */
 
@@ -247,7 +251,8 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 
 	/* Wait for all active readers to complete. */
 	rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE);
-	trace_contention_end(sem, 0);
+	if (contended)
+		trace_contention_end(sem, 0);
 }
 EXPORT_SYMBOL_GPL(percpu_down_write);
 
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 6a0184e9c234..ae2b12f68b90 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -294,8 +294,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 {
 	struct pv_node *pn = (struct pv_node *)node;
 	struct pv_node *pp = (struct pv_node *)prev;
+	bool __maybe_unused wait_early;
 	int loop;
-	bool wait_early;
 
 	for (;;) {
 		for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) {
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4a10e8c16fd2..88d08eeb8bc0 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -237,12 +237,13 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock,
  */
 static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock)
 {
-	unsigned long owner, *p = (unsigned long *) &lock->owner;
+	unsigned long *p = (unsigned long *) &lock->owner;
+	unsigned long owner, new;
 
+	owner = READ_ONCE(*p);
 	do {
-		owner = *p;
-	} while (cmpxchg_relaxed(p, owner,
-				 owner | RT_MUTEX_HAS_WAITERS) != owner);
+		new = owner | RT_MUTEX_HAS_WAITERS;
+	} while (!try_cmpxchg_relaxed(p, &owner, new));
 
 	/*
 	 * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 2340b6d90ec6..c6d17aee4209 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -35,7 +35,7 @@
 /*
  * The least significant 2 bits of the owner value has the following
  * meanings when set.
- *  - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers
+ *  - Bit 0: RWSEM_READER_OWNED - rwsem may be owned by readers (just a hint)
  *  - Bit 1: RWSEM_NONSPINNABLE - Cannot spin on a reader-owned lock
  *
  * When the rwsem is reader-owned and a spinning writer has timed out,
@@ -1002,8 +1002,8 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 
 	/*
 	 * To prevent a constant stream of readers from starving a sleeping
-	 * waiter, don't attempt optimistic lock stealing if the lock is
-	 * currently owned by readers.
+	 * writer, don't attempt optimistic lock stealing if the lock is
+	 * very likely owned by readers.
 	 */
 	if ((atomic_long_read(&sem->owner) & RWSEM_READER_OWNED) &&
 	    (rcnt > 1) && !(count & RWSEM_WRITER_LOCKED))
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 15781acaac1c..6ec3deec68c2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
 	if (proc_ns_file(f.file))
 		err = validate_ns(&nsset, ns);
 	else
-		err = validate_nsset(&nsset, f.file->private_data);
+		err = validate_nsset(&nsset, pidfd_pid(f.file));
 	if (!err) {
 		commit_nsset(&nsset);
 		perf_event_namespaces(current);
diff --git a/kernel/pid.c b/kernel/pid.c
index b52b10865454..99a0c5eb24b8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
+#include <linux/pidfs.h>
 #include <net/sock.h>
 #include <uapi/linux/pidfd.h>
 
@@ -65,6 +66,13 @@ int pid_max = PID_MAX_DEFAULT;
 
 int pid_max_min = RESERVED_PIDS + 1;
 int pid_max_max = PID_MAX_LIMIT;
+#ifdef CONFIG_FS_PID
+/*
+ * Pseudo filesystems start inode numbering after one. We use Reserved
+ * PIDs as a natural offset.
+ */
+static u64 pidfs_ino = RESERVED_PIDS;
+#endif
 
 /*
  * PID-map pages start out as NULL, they get allocated upon
@@ -272,6 +280,10 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
 	spin_lock_irq(&pidmap_lock);
 	if (!(ns->pid_allocated & PIDNS_ADDING))
 		goto out_unlock;
+#ifdef CONFIG_FS_PID
+	pid->stashed = NULL;
+	pid->ino = ++pidfs_ino;
+#endif
 	for ( ; upid >= pid->numbers; --upid) {
 		/* Make the PID visible to find_pid_ns. */
 		idr_replace(&upid->ns->idr, pid, upid->nr);
@@ -349,6 +361,11 @@ static void __change_pid(struct task_struct *task, enum pid_type type,
 	hlist_del_rcu(&task->pid_links[type]);
 	*pid_ptr = new;
 
+	if (type == PIDTYPE_PID) {
+		WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID));
+		wake_up_all(&pid->wait_pidfd);
+	}
+
 	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
 		if (pid_has_task(pid, tmp))
 			return;
@@ -391,8 +408,7 @@ void exchange_tids(struct task_struct *left, struct task_struct *right)
 void transfer_pid(struct task_struct *old, struct task_struct *new,
 			   enum pid_type type)
 {
-	if (type == PIDTYPE_PID)
-		new->thread_pid = old->thread_pid;
+	WARN_ON_ONCE(type == PIDTYPE_PID);
 	hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]);
 }
 
@@ -552,11 +568,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
  * Return the task associated with @pidfd. The function takes a reference on
  * the returned task. The caller is responsible for releasing that reference.
  *
- * Currently, the process identified by @pidfd is always a thread-group leader.
- * This restriction currently exists for all aspects of pidfds including pidfd
- * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling
- * (only supports thread group leaders).
- *
  * Return: On success, the task_struct associated with the pidfd.
  *	   On error, a negative errno number will be returned.
  */
@@ -595,7 +606,7 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags)
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
  */
-int pidfd_create(struct pid *pid, unsigned int flags)
+static int pidfd_create(struct pid *pid, unsigned int flags)
 {
 	int pidfd;
 	struct file *pidfd_file;
@@ -615,11 +626,8 @@ int pidfd_create(struct pid *pid, unsigned int flags)
  * @flags: flags to pass
  *
  * This creates a new pid file descriptor with the O_CLOEXEC flag set for
- * the process identified by @pid. Currently, the process identified by
- * @pid must be a thread-group leader. This restriction currently exists
- * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
- * be used with CLONE_THREAD) and pidfd polling (only supports thread group
- * leaders).
+ * the task identified by @pid. Without PIDFD_THREAD flag the target task
+ * must be a thread-group leader.
  *
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
@@ -629,7 +637,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags & ~PIDFD_NONBLOCK)
+	if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD))
 		return -EINVAL;
 
 	if (pid <= 0)
@@ -682,7 +690,26 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 
 	up_read(&task->signal->exec_update_lock);
 
-	return file ?: ERR_PTR(-EBADF);
+	if (!file) {
+		/*
+		 * It is possible that the target thread is exiting; it can be
+		 * either:
+		 * 1. before exit_signals(), which gives a real fd
+		 * 2. before exit_files() takes the task_lock() gives a real fd
+		 * 3. after exit_files() releases task_lock(), ->files is NULL;
+		 *    this has PF_EXITING, since it was set in exit_signals(),
+		 *    __pidfd_fget() returns EBADF.
+		 * In case 3 we get EBADF, but that really means ESRCH, since
+		 * the task is currently exiting and has freed its files
+		 * struct, so we fix it up.
+		 */
+		if (task->flags & PF_EXITING)
+			file = ERR_PTR(-ESRCH);
+		else
+			file = ERR_PTR(-EBADF);
+	}
+
+	return file;
 }
 
 static int pidfd_getfd(struct pid *pid, int fd)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 6053ddddaf65..692f12fe60c1 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -222,7 +222,7 @@ int swsusp_swap_in_use(void)
  */
 
 static unsigned short root_swap = 0xffff;
-static struct bdev_handle *hib_resume_bdev_handle;
+static struct file *hib_resume_bdev_file;
 
 struct hib_bio_batch {
 	atomic_t		count;
@@ -276,7 +276,7 @@ static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
 	struct bio *bio;
 	int error = 0;
 
-	bio = bio_alloc(hib_resume_bdev_handle->bdev, 1, opf,
+	bio = bio_alloc(file_bdev(hib_resume_bdev_file), 1, opf,
 			GFP_NOIO | __GFP_HIGH);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 
@@ -357,14 +357,14 @@ static int swsusp_swap_check(void)
 		return res;
 	root_swap = res;
 
-	hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
+	hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
 			BLK_OPEN_WRITE, NULL, NULL);
-	if (IS_ERR(hib_resume_bdev_handle))
-		return PTR_ERR(hib_resume_bdev_handle);
+	if (IS_ERR(hib_resume_bdev_file))
+		return PTR_ERR(hib_resume_bdev_file);
 
-	res = set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
+	res = set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE);
 	if (res < 0)
-		bdev_release(hib_resume_bdev_handle);
+		fput(hib_resume_bdev_file);
 
 	return res;
 }
@@ -1523,10 +1523,10 @@ int swsusp_check(bool exclusive)
 	void *holder = exclusive ? &swsusp_holder : NULL;
 	int error;
 
-	hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device,
+	hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device,
 				BLK_OPEN_READ, holder, NULL);
-	if (!IS_ERR(hib_resume_bdev_handle)) {
-		set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE);
+	if (!IS_ERR(hib_resume_bdev_file)) {
+		set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE);
 		clear_page(swsusp_header);
 		error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
 					swsusp_header, NULL);
@@ -1551,11 +1551,11 @@ int swsusp_check(bool exclusive)
 
 put:
 		if (error)
-			bdev_release(hib_resume_bdev_handle);
+			fput(hib_resume_bdev_file);
 		else
 			pr_debug("Image signature found, resuming\n");
 	} else {
-		error = PTR_ERR(hib_resume_bdev_handle);
+		error = PTR_ERR(hib_resume_bdev_file);
 	}
 
 	if (error)
@@ -1570,12 +1570,12 @@ put:
 
 void swsusp_close(void)
 {
-	if (IS_ERR(hib_resume_bdev_handle)) {
+	if (IS_ERR(hib_resume_bdev_file)) {
 		pr_debug("Image device not initialised\n");
 		return;
 	}
 
-	bdev_release(hib_resume_bdev_handle);
+	fput(hib_resume_bdev_file);
 }
 
 /**
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index bdd7eadb33d8..e7d2dd267593 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -314,6 +314,19 @@ config RCU_LAZY
 	  To save power, batch RCU callbacks and flush after delay, memory
 	  pressure, or callback list growing too big.
 
+	  Requires rcu_nocbs=all to be set.
+
+	  Use rcutree.enable_rcu_lazy=0 to turn it off at boot time.
+
+config RCU_LAZY_DEFAULT_OFF
+	bool "Turn RCU lazy invocation off by default"
+	depends on RCU_LAZY
+	default n
+	help
+	  Allows building the kernel with CONFIG_RCU_LAZY=y yet keep it default
+	  off. Boot time param rcutree.enable_rcu_lazy=1 can be used to switch
+	  it back on.
+
 config RCU_DOUBLE_CHECK_CB_TIME
 	bool "RCU callback-batch backup time check"
 	depends on RCU_EXPERT
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index f94f65877f2b..86fce206560e 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -528,6 +528,12 @@ struct task_struct *get_rcu_tasks_gp_kthread(void);
 struct task_struct *get_rcu_tasks_rude_gp_kthread(void);
 #endif // # ifdef CONFIG_TASKS_RUDE_RCU
 
+#ifdef CONFIG_TASKS_RCU_GENERIC
+void tasks_cblist_init_generic(void);
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+static inline void tasks_cblist_init_generic(void) { }
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
+
 #define RCU_SCHEDULER_INACTIVE	0
 #define RCU_SCHEDULER_INIT	1
 #define RCU_SCHEDULER_RUNNING	2
@@ -543,11 +549,11 @@ enum rcutorture_type {
 };
 
 #if defined(CONFIG_RCU_LAZY)
-unsigned long rcu_lazy_get_jiffies_till_flush(void);
-void rcu_lazy_set_jiffies_till_flush(unsigned long j);
+unsigned long rcu_get_jiffies_lazy_flush(void);
+void rcu_set_jiffies_lazy_flush(unsigned long j);
 #else
-static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; }
-static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { }
+static inline unsigned long rcu_get_jiffies_lazy_flush(void) { return 0; }
+static inline void rcu_set_jiffies_lazy_flush(unsigned long j) { }
 #endif
 
 #if defined(CONFIG_TREE_RCU)
@@ -623,12 +629,7 @@ int rcu_get_gp_kthreads_prio(void);
 void rcu_fwd_progress_check(unsigned long j);
 void rcu_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
-#ifdef CONFIG_RCU_EXP_KTHREAD
 extern struct kthread_worker *rcu_exp_gp_kworker;
-extern struct kthread_worker *rcu_exp_par_gp_kworker;
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-extern struct workqueue_struct *rcu_par_gp_wq;
-#endif /* CONFIG_RCU_EXP_KTHREAD */
 void rcu_gp_slow_register(atomic_t *rgssp);
 void rcu_gp_slow_unregister(atomic_t *rgssp);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index ffdb30495e3c..8db4fedaaa1e 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -764,9 +764,9 @@ kfree_scale_init(void)
 
 	if (kfree_by_call_rcu) {
 		/* do a test to check the timeout. */
-		orig_jif = rcu_lazy_get_jiffies_till_flush();
+		orig_jif = rcu_get_jiffies_lazy_flush();
 
-		rcu_lazy_set_jiffies_till_flush(2 * HZ);
+		rcu_set_jiffies_lazy_flush(2 * HZ);
 		rcu_barrier();
 
 		jif_start = jiffies;
@@ -775,7 +775,7 @@ kfree_scale_init(void)
 
 		smp_cond_load_relaxed(&rcu_lazy_test1_cb_called, VAL == 1);
 
-		rcu_lazy_set_jiffies_till_flush(orig_jif);
+		rcu_set_jiffies_lazy_flush(orig_jif);
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n");
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7567ca8e743c..45d6b4c3d199 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1368,9 +1368,13 @@ rcu_torture_writer(void *arg)
 	struct rcu_torture *rp;
 	struct rcu_torture *old_rp;
 	static DEFINE_TORTURE_RANDOM(rand);
+	unsigned long stallsdone = jiffies;
 	bool stutter_waited;
 	unsigned long ulo[NUM_ACTIVE_RCU_POLL_OLDSTATE];
 
+	// If a new stall test is added, this must be adjusted.
+	if (stall_cpu_holdoff + stall_gp_kthread + stall_cpu)
+		stallsdone += (stall_cpu_holdoff + stall_gp_kthread + stall_cpu + 60) * HZ;
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
 	if (!can_expedite)
 		pr_alert("%s" TORTURE_FLAG
@@ -1576,11 +1580,11 @@ rcu_torture_writer(void *arg)
 		    !atomic_read(&rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
 		    !torture_must_stop() &&
-		    boot_ended)
+		    boot_ended &&
+		    time_after(jiffies, stallsdone))
 			for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
 				if (list_empty(&rcu_tortures[i].rtort_free) &&
-				    rcu_access_pointer(rcu_torture_current) !=
-				    &rcu_tortures[i]) {
+				    rcu_access_pointer(rcu_torture_current) != &rcu_tortures[i]) {
 					tracing_off();
 					show_rcu_gp_kthreads();
 					WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
@@ -2441,7 +2445,8 @@ static struct notifier_block rcu_torture_stall_block = {
 
 /*
  * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
- * induces a CPU stall for the time specified by stall_cpu.
+ * induces a CPU stall for the time specified by stall_cpu.  If a new
+ * stall test is added, stallsdone in rcu_torture_writer() must be adjusted.
  */
 static int rcu_torture_stall(void *args)
 {
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 0351a4e83529..e4d673fc30f4 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1234,11 +1234,20 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	/*
-	 * The snapshot for acceleration must be taken _before_ the read of the
-	 * current gp sequence used for advancing, otherwise advancing may fail
-	 * and acceleration may then fail too.
+	 * It's crucial to capture the snapshot 's' for acceleration before
+	 * reading the current gp_seq that is used for advancing. This is
+	 * essential because if the acceleration snapshot is taken after a
+	 * failed advancement attempt, there's a risk that a grace period may
+	 * conclude and a new one may start in the interim. If the snapshot is
+	 * captured after this sequence of events, the acceleration snapshot 's'
+	 * could be excessively advanced, leading to acceleration failure.
+	 * In such a scenario, an 'acceleration leak' can occur, where new
+	 * callbacks become indefinitely stuck in the RCU_NEXT_TAIL segment.
+	 * Also note that encountering advancing failures is a normal
+	 * occurrence when the grace period for RCU_WAIT_TAIL is in progress.
 	 *
-	 * This could happen if:
+	 * To see this, consider the following events which occur if
+	 * rcu_seq_snap() were to be called after advance:
 	 *
 	 *  1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
 	 *     RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
@@ -1264,6 +1273,13 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	if (rhp) {
 		rcu_segcblist_advance(&sdp->srcu_cblist,
 				      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
+		/*
+		 * Acceleration can never fail because the base current gp_seq
+		 * used for acceleration is <= the value of gp_seq used for
+		 * advancing. This means that RCU_NEXT_TAIL segment will
+		 * always be able to be emptied by the acceleration into the
+		 * RCU_NEXT_READY_TAIL or RCU_WAIT_TAIL segments.
+		 */
 		WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s));
 	}
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index e550f97779b8..86df878a2fee 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -24,22 +24,6 @@ void rcu_sync_init(struct rcu_sync *rsp)
 	init_waitqueue_head(&rsp->gp_wait);
 }
 
-/**
- * rcu_sync_enter_start - Force readers onto slow path for multiple updates
- * @rsp: Pointer to rcu_sync structure to use for synchronization
- *
- * Must be called after rcu_sync_init() and before first use.
- *
- * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
- * pairs turn into NO-OPs.
- */
-void rcu_sync_enter_start(struct rcu_sync *rsp)
-{
-	rsp->gp_count++;
-	rsp->gp_state = GP_PASSED;
-}
-
-
 static void rcu_sync_func(struct rcu_head *rhp);
 
 static void rcu_sync_call(struct rcu_sync *rsp)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 732ad5b39946..147b5945d67a 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -32,6 +32,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @rtp_irq_work: IRQ work queue for deferred wakeups.
  * @barrier_q_head: RCU callback for barrier operation.
  * @rtp_blkd_tasks: List of tasks blocked as readers.
+ * @rtp_exit_list: List of tasks in the latter portion of do_exit().
  * @cpu: CPU number corresponding to this entry.
  * @rtpp: Pointer to the rcu_tasks structure.
  */
@@ -46,6 +47,7 @@ struct rcu_tasks_percpu {
 	struct irq_work rtp_irq_work;
 	struct rcu_head barrier_q_head;
 	struct list_head rtp_blkd_tasks;
+	struct list_head rtp_exit_list;
 	int cpu;
 	struct rcu_tasks *rtpp;
 };
@@ -144,8 +146,6 @@ static struct rcu_tasks rt_name =							\
 }
 
 #ifdef CONFIG_TASKS_RCU
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 
 /* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */
 static void tasks_rcu_exit_srcu_stall(struct timer_list *unused);
@@ -240,7 +240,6 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 static void cblist_init_generic(struct rcu_tasks *rtp)
 {
 	int cpu;
-	unsigned long flags;
 	int lim;
 	int shift;
 
@@ -266,15 +265,15 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
 		WARN_ON_ONCE(!rtpcp);
 		if (cpu)
 			raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
-		local_irq_save(flags);  // serialize initialization
 		if (rcu_segcblist_empty(&rtpcp->cblist))
 			rcu_segcblist_init(&rtpcp->cblist);
-		local_irq_restore(flags);
 		INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
 		rtpcp->cpu = cpu;
 		rtpcp->rtpp = rtp;
 		if (!rtpcp->rtp_blkd_tasks.next)
 			INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks);
+		if (!rtpcp->rtp_exit_list.next)
+			INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
 	}
 
 	pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name,
@@ -851,10 +850,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	number of voluntary context switches, and add that task to the
 //	holdout list.
 // rcu_tasks_postscan():
-//	Invoke synchronize_srcu() to ensure that all tasks that were
-//	in the process of exiting (and which thus might not know to
-//	synchronize with this RCU Tasks grace period) have completed
-//	exiting.
+//	Gather per-CPU lists of tasks in do_exit() to ensure that all
+//	tasks that were in the process of exiting (and which thus might
+//	not know to synchronize with this RCU Tasks grace period) have
+//	completed exiting.  The synchronize_rcu() in rcu_tasks_postgp()
+//	will take care of any tasks stuck in the non-preemptible region
+//	of do_exit() following its call to exit_tasks_rcu_stop().
 // check_all_holdout_tasks(), repeatedly until holdout list is empty:
 //	Scans the holdout list, attempting to identify a quiescent state
 //	for each task on the list.  If there is a quiescent state, the
@@ -867,8 +868,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	with interrupts disabled.
 //
 // For each exiting task, the exit_tasks_rcu_start() and
-// exit_tasks_rcu_finish() functions begin and end, respectively, the SRCU
-// read-side critical sections waited for by rcu_tasks_postscan().
+// exit_tasks_rcu_finish() functions add and remove, respectively, the
+// current task to a per-CPU list of tasks that rcu_tasks_postscan() must
+// wait on.  This is necessary because rcu_tasks_postscan() must wait on
+// tasks that have already been removed from the global list of tasks.
 //
 // Pre-grace-period update-side code is ordered before the grace
 // via the raw_spin_lock.*rcu_node().  Pre-grace-period read-side code
@@ -932,9 +935,13 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
 	}
 }
 
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
+
 /* Processing between scanning taskslist and draining the holdout list. */
 static void rcu_tasks_postscan(struct list_head *hop)
 {
+	int cpu;
 	int rtsi = READ_ONCE(rcu_task_stall_info);
 
 	if (!IS_ENABLED(CONFIG_TINY_RCU)) {
@@ -948,9 +955,9 @@ static void rcu_tasks_postscan(struct list_head *hop)
 	 * this, divide the fragile exit path part in two intersecting
 	 * read side critical sections:
 	 *
-	 * 1) An _SRCU_ read side starting before calling exit_notify(),
-	 *    which may remove the task from the tasklist, and ending after
-	 *    the final preempt_disable() call in do_exit().
+	 * 1) A task_struct list addition before calling exit_notify(),
+	 *    which may remove the task from the tasklist, with the
+	 *    removal after the final preempt_disable() call in do_exit().
 	 *
 	 * 2) An _RCU_ read side starting with the final preempt_disable()
 	 *    call in do_exit() and ending with the final call to schedule()
@@ -959,7 +966,37 @@ static void rcu_tasks_postscan(struct list_head *hop)
 	 * This handles the part 1). And postgp will handle part 2) with a
 	 * call to synchronize_rcu().
 	 */
-	synchronize_srcu(&tasks_rcu_exit_srcu);
+
+	for_each_possible_cpu(cpu) {
+		unsigned long j = jiffies + 1;
+		struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, cpu);
+		struct task_struct *t;
+		struct task_struct *t1;
+		struct list_head tmp;
+
+		raw_spin_lock_irq_rcu_node(rtpcp);
+		list_for_each_entry_safe(t, t1, &rtpcp->rtp_exit_list, rcu_tasks_exit_list) {
+			if (list_empty(&t->rcu_tasks_holdout_list))
+				rcu_tasks_pertask(t, hop);
+
+			// RT kernels need frequent pauses, otherwise
+			// pause at least once per pair of jiffies.
+			if (!IS_ENABLED(CONFIG_PREEMPT_RT) && time_before(jiffies, j))
+				continue;
+
+			// Keep our place in the list while pausing.
+			// Nothing else traverses this list, so adding a
+			// bare list_head is OK.
+			list_add(&tmp, &t->rcu_tasks_exit_list);
+			raw_spin_unlock_irq_rcu_node(rtpcp);
+			cond_resched(); // For CONFIG_PREEMPT=n kernels
+			raw_spin_lock_irq_rcu_node(rtpcp);
+			t1 = list_entry(tmp.next, struct task_struct, rcu_tasks_exit_list);
+			list_del(&tmp);
+			j = jiffies + 1;
+		}
+		raw_spin_unlock_irq_rcu_node(rtpcp);
+	}
 
 	if (!IS_ENABLED(CONFIG_TINY_RCU))
 		del_timer_sync(&tasks_rcu_exit_srcu_stall_timer);
@@ -1027,7 +1064,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp)
 	 *
 	 * In addition, this synchronize_rcu() waits for exiting tasks
 	 * to complete their final preempt_disable() region of execution,
-	 * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu),
 	 * enforcing the whole region before tasklist removal until
 	 * the final schedule() with TASK_DEAD state to be an RCU TASKS
 	 * read side critical section.
@@ -1035,9 +1071,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp)
 	synchronize_rcu();
 }
 
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
-DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
-
 static void tasks_rcu_exit_srcu_stall(struct timer_list *unused)
 {
 #ifndef CONFIG_TINY_RCU
@@ -1118,7 +1151,6 @@ module_param(rcu_tasks_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks);
 	rcu_tasks.gp_sleep = HZ / 10;
 	rcu_tasks.init_fract = HZ / 10;
 	if (rcu_tasks_lazy_ms >= 0)
@@ -1147,25 +1179,48 @@ struct task_struct *get_rcu_tasks_gp_kthread(void)
 EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
 
 /*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
+ * Protect against tasklist scan blind spot while the task is exiting and
+ * may be removed from the tasklist.  Do this by adding the task to yet
+ * another list.
+ *
+ * Note that the task will remove itself from this list, so there is no
+ * need for get_task_struct(), except in the case where rcu_tasks_pertask()
+ * adds it to the holdout list, in which case rcu_tasks_pertask() supplies
+ * the needed get_task_struct().
  */
-void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
+void exit_tasks_rcu_start(void)
 {
-	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+	unsigned long flags;
+	struct rcu_tasks_percpu *rtpcp;
+	struct task_struct *t = current;
+
+	WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list));
+	preempt_disable();
+	rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu);
+	t->rcu_tasks_exit_cpu = smp_processor_id();
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	if (!rtpcp->rtp_exit_list.next)
+		INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
+	list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	preempt_enable();
 }
 
 /*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
+ * Remove the task from the "yet another list" because do_exit() is now
+ * non-preemptible, allowing synchronize_rcu() to wait beyond this point.
  */
-void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu)
+void exit_tasks_rcu_stop(void)
 {
+	unsigned long flags;
+	struct rcu_tasks_percpu *rtpcp;
 	struct task_struct *t = current;
 
-	__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
+	WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list));
+	rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu);
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	list_del_init(&t->rcu_tasks_exit_list);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 }
 
 /*
@@ -1282,7 +1337,6 @@ module_param(rcu_tasks_rude_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_rude_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks_rude);
 	rcu_tasks_rude.gp_sleep = HZ / 10;
 	if (rcu_tasks_rude_lazy_ms >= 0)
 		rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms);
@@ -1914,7 +1968,6 @@ module_param(rcu_tasks_trace_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
-	cblist_init_generic(&rcu_tasks_trace);
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
 		rcu_tasks_trace.gp_sleep = HZ / 10;
 		rcu_tasks_trace.init_fract = HZ / 10;
@@ -2086,6 +2139,24 @@ late_initcall(rcu_tasks_verify_schedule_work);
 static void rcu_tasks_initiate_self_tests(void) { }
 #endif /* #else #ifdef CONFIG_PROVE_RCU */
 
+void __init tasks_cblist_init_generic(void)
+{
+	lockdep_assert_irqs_disabled();
+	WARN_ON(num_online_cpus() > 1);
+
+#ifdef CONFIG_TASKS_RCU
+	cblist_init_generic(&rcu_tasks);
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	cblist_init_generic(&rcu_tasks_rude);
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	cblist_init_generic(&rcu_tasks_trace);
+#endif
+}
+
 void __init rcu_init_tasks_generic(void)
 {
 #ifdef CONFIG_TASKS_RCU
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index fec804b79080..705c0d16850a 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -261,4 +261,5 @@ void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 	rcu_early_boot_tests();
+	tasks_cblist_init_generic();
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b2bccfd37c38..d9642dd06c25 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -145,7 +145,7 @@ static int rcu_scheduler_fully_active __read_mostly;
 
 static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp,
 			      unsigned long gps, unsigned long flags);
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp);
 static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
@@ -2145,6 +2145,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
+	 *
+	 * Callbacks execution is fully ordered against preceding grace period
+	 * completion (materialized by rnp->gp_seq update) thanks to the
+	 * smp_mb__after_unlock_lock() upon node locking required for callbacks
+	 * advancing. In NOCB mode this ordering is then further relayed through
+	 * the nocb locking that protects both callbacks advancing and extraction.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -2591,12 +2597,26 @@ static int __init rcu_spawn_core_kthreads(void)
 	return 0;
 }
 
+static void rcutree_enqueue(struct rcu_data *rdp, struct rcu_head *head, rcu_callback_t func)
+{
+	rcu_segcblist_enqueue(&rdp->cblist, head);
+	if (__is_kvfree_rcu_offset((unsigned long)func))
+		trace_rcu_kvfree_callback(rcu_state.name, head,
+					 (unsigned long)func,
+					 rcu_segcblist_n_cbs(&rdp->cblist));
+	else
+		trace_rcu_callback(rcu_state.name, head,
+				   rcu_segcblist_n_cbs(&rdp->cblist));
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
+}
+
 /*
  * Handle any core-RCU processing required by a call_rcu() invocation.
  */
-static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
-			    unsigned long flags)
+static void call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags)
 {
+	rcutree_enqueue(rdp, head, func);
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2692,7 +2712,6 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	unsigned long flags;
 	bool lazy;
 	struct rcu_data *rdp;
-	bool was_alldone;
 
 	/* Misaligned rcu_head! */
 	WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
@@ -2729,30 +2748,18 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	}
 
 	check_cb_ovld(rdp);
-	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy))
-		return; // Enqueued onto ->nocb_bypass, so just leave.
-	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
-	rcu_segcblist_enqueue(&rdp->cblist, head);
-	if (__is_kvfree_rcu_offset((unsigned long)func))
-		trace_rcu_kvfree_callback(rcu_state.name, head,
-					 (unsigned long)func,
-					 rcu_segcblist_n_cbs(&rdp->cblist));
-	else
-		trace_rcu_callback(rcu_state.name, head,
-				   rcu_segcblist_n_cbs(&rdp->cblist));
 
-	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
-
-	/* Go handle any RCU core processing required. */
-	if (unlikely(rcu_rdp_is_offloaded(rdp))) {
-		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
-	} else {
-		__call_rcu_core(rdp, head, flags);
-		local_irq_restore(flags);
-	}
+	if (unlikely(rcu_rdp_is_offloaded(rdp)))
+		call_rcu_nocb(rdp, head, func, flags, lazy);
+	else
+		call_rcu_core(rdp, head, func, flags);
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_RCU_LAZY
+static bool enable_rcu_lazy __read_mostly = !IS_ENABLED(CONFIG_RCU_LAZY_DEFAULT_OFF);
+module_param(enable_rcu_lazy, bool, 0444);
+
 /**
  * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and
  * flush all lazy callbacks (including the new one) to the main ->cblist while
@@ -2778,6 +2785,8 @@ void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
 	__call_rcu_common(head, func, false);
 }
 EXPORT_SYMBOL_GPL(call_rcu_hurry);
+#else
+#define enable_rcu_lazy		false
 #endif
 
 /**
@@ -2826,7 +2835,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	__call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+	__call_rcu_common(head, func, enable_rcu_lazy);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -4394,6 +4403,66 @@ rcu_boot_init_percpu_data(int cpu)
 	rcu_boot_init_nocb_percpu_data(rdp);
 }
 
+struct kthread_worker *rcu_exp_gp_kworker;
+
+static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
+{
+	struct kthread_worker *kworker;
+	const char *name = "rcu_exp_par_gp_kthread_worker/%d";
+	struct sched_param param = { .sched_priority = kthread_prio };
+	int rnp_index = rnp - rcu_get_root();
+
+	if (rnp->exp_kworker)
+		return;
+
+	kworker = kthread_create_worker(0, name, rnp_index);
+	if (IS_ERR_OR_NULL(kworker)) {
+		pr_err("Failed to create par gp kworker on %d/%d\n",
+		       rnp->grplo, rnp->grphi);
+		return;
+	}
+	WRITE_ONCE(rnp->exp_kworker, kworker);
+
+	if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
+		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
+}
+
+static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp)
+{
+	struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker);
+
+	if (!kworker)
+		return NULL;
+
+	return kworker->task;
+}
+
+static void __init rcu_start_exp_gp_kworker(void)
+{
+	const char *name = "rcu_exp_gp_kthread_worker";
+	struct sched_param param = { .sched_priority = kthread_prio };
+
+	rcu_exp_gp_kworker = kthread_create_worker(0, name);
+	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
+		pr_err("Failed to create %s!\n", name);
+		rcu_exp_gp_kworker = NULL;
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD))
+		sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
+}
+
+static void rcu_spawn_rnp_kthreads(struct rcu_node *rnp)
+{
+	if (rcu_scheduler_fully_active) {
+		mutex_lock(&rnp->kthread_mutex);
+		rcu_spawn_one_boost_kthread(rnp);
+		rcu_spawn_exp_par_gp_kworker(rnp);
+		mutex_unlock(&rnp->kthread_mutex);
+	}
+}
+
 /*
  * Invoked early in the CPU-online process, when pretty much all services
  * are available.  The incoming CPU is not present.
@@ -4442,7 +4511,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	rcu_spawn_one_boost_kthread(rnp);
+	rcu_spawn_rnp_kthreads(rnp);
 	rcu_spawn_cpu_nocb_kthread(cpu);
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
 
@@ -4450,13 +4519,64 @@ int rcutree_prepare_cpu(unsigned int cpu)
 }
 
 /*
- * Update RCU priority boot kthread affinity for CPU-hotplug changes.
+ * Update kthreads affinity during CPU-hotplug changes.
+ *
+ * Set the per-rcu_node kthread's affinity to cover all CPUs that are
+ * served by the rcu_node in question.  The CPU hotplug lock is still
+ * held, so the value of rnp->qsmaskinit will be stable.
+ *
+ * We don't include outgoingcpu in the affinity set, use -1 if there is
+ * no outgoing CPU.  If there are no CPUs left in the affinity set,
+ * this function allows the kthread to execute on any CPU.
+ *
+ * Any future concurrent calls are serialized via ->kthread_mutex.
  */
-static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
+static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu)
 {
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	cpumask_var_t cm;
+	unsigned long mask;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct task_struct *task_boost, *task_exp;
+
+	rdp = per_cpu_ptr(&rcu_data, cpu);
+	rnp = rdp->mynode;
+
+	task_boost = rcu_boost_task(rnp);
+	task_exp = rcu_exp_par_gp_task(rnp);
+
+	/*
+	 * If CPU is the boot one, those tasks are created later from early
+	 * initcall since kthreadd must be created first.
+	 */
+	if (!task_boost && !task_exp)
+		return;
+
+	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
+		return;
+
+	mutex_lock(&rnp->kthread_mutex);
+	mask = rcu_rnp_online_cpus(rnp);
+	for_each_leaf_node_possible_cpu(rnp, cpu)
+		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
+		    cpu != outgoingcpu)
+			cpumask_set_cpu(cpu, cm);
+	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
+	if (cpumask_empty(cm)) {
+		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
+		if (outgoingcpu >= 0)
+			cpumask_clear_cpu(outgoingcpu, cm);
+	}
+
+	if (task_exp)
+		set_cpus_allowed_ptr(task_exp, cm);
+
+	if (task_boost)
+		set_cpus_allowed_ptr(task_boost, cm);
 
-	rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
+	mutex_unlock(&rnp->kthread_mutex);
+
+	free_cpumask_var(cm);
 }
 
 /*
@@ -4640,8 +4760,9 @@ void rcutree_migrate_callbacks(int cpu)
 		__call_rcu_nocb_wake(my_rdp, true, flags);
 	} else {
 		rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */
-		raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags);
+		raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
 	}
+	local_irq_restore(flags);
 	if (needwake)
 		rcu_gp_kthread_wake();
 	lockdep_assert_irqs_enabled();
@@ -4730,51 +4851,6 @@ static int rcu_pm_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-#ifdef CONFIG_RCU_EXP_KTHREAD
-struct kthread_worker *rcu_exp_gp_kworker;
-struct kthread_worker *rcu_exp_par_gp_kworker;
-
-static void __init rcu_start_exp_gp_kworkers(void)
-{
-	const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker";
-	const char *gp_kworker_name = "rcu_exp_gp_kthread_worker";
-	struct sched_param param = { .sched_priority = kthread_prio };
-
-	rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
-		pr_err("Failed to create %s!\n", gp_kworker_name);
-		return;
-	}
-
-	rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) {
-		pr_err("Failed to create %s!\n", par_gp_kworker_name);
-		kthread_destroy_worker(rcu_exp_gp_kworker);
-		return;
-	}
-
-	sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
-	sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO,
-				   &param);
-}
-
-static inline void rcu_alloc_par_gp_wq(void)
-{
-}
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-struct workqueue_struct *rcu_par_gp_wq;
-
-static void __init rcu_start_exp_gp_kworkers(void)
-{
-}
-
-static inline void rcu_alloc_par_gp_wq(void)
-{
-	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
-	WARN_ON(!rcu_par_gp_wq);
-}
-#endif /* CONFIG_RCU_EXP_KTHREAD */
-
 /*
  * Spawn the kthreads that handle RCU's grace periods.
  */
@@ -4809,10 +4885,10 @@ static int __init rcu_spawn_gp_kthread(void)
 	 * due to rcu_scheduler_fully_active.
 	 */
 	rcu_spawn_cpu_nocb_kthread(smp_processor_id());
-	rcu_spawn_one_boost_kthread(rdp->mynode);
+	rcu_spawn_rnp_kthreads(rdp->mynode);
 	rcu_spawn_core_kthreads();
 	/* Create kthread worker for expedited GPs */
-	rcu_start_exp_gp_kworkers();
+	rcu_start_exp_gp_kworker();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);
@@ -4915,7 +4991,7 @@ static void __init rcu_init_one(void)
 			init_waitqueue_head(&rnp->exp_wq[2]);
 			init_waitqueue_head(&rnp->exp_wq[3]);
 			spin_lock_init(&rnp->exp_lock);
-			mutex_init(&rnp->boost_kthread_mutex);
+			mutex_init(&rnp->kthread_mutex);
 			raw_spin_lock_init(&rnp->exp_poll_lock);
 			rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED;
 			INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp);
@@ -5152,7 +5228,6 @@ void __init rcu_init(void)
 	/* Create workqueue for Tree SRCU and for expedited GPs. */
 	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_gp_wq);
-	rcu_alloc_par_gp_wq();
 
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */
@@ -5165,6 +5240,8 @@ void __init rcu_init(void)
 	(void)start_poll_synchronize_rcu_expedited();
 
 	rcu_test_sync_prims();
+
+	tasks_cblist_init_generic();
 }
 
 #include "tree_stall.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index e9821a8422db..df48160b3136 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -21,14 +21,10 @@
 
 #include "rcu_segcblist.h"
 
-/* Communicate arguments to a workqueue handler. */
+/* Communicate arguments to a kthread worker handler. */
 struct rcu_exp_work {
 	unsigned long rew_s;
-#ifdef CONFIG_RCU_EXP_KTHREAD
 	struct kthread_work rew_work;
-#else
-	struct work_struct rew_work;
-#endif /* CONFIG_RCU_EXP_KTHREAD */
 };
 
 /* RCU's kthread states for tracing. */
@@ -72,6 +68,9 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	struct kthread_worker *exp_kworker;
+				/* Workers performing per node expedited GP */
+				/* initialization. */
 	unsigned long cbovldmask;
 				/* CPUs experiencing callback overload. */
 	unsigned long ffmask;	/* Fully functional CPUs. */
@@ -113,7 +112,7 @@ struct rcu_node {
 				/*  side effect, not as a lock. */
 	unsigned long boost_time;
 				/* When to start boosting (jiffies). */
-	struct mutex boost_kthread_mutex;
+	struct mutex kthread_mutex;
 				/* Exclusion for thread spawning and affinity */
 				/*  manipulation. */
 	struct task_struct *boost_kthread_task;
@@ -467,11 +466,10 @@ static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j, bool lazy);
-static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				bool *was_alldone, unsigned long flags,
-				bool lazy);
-static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
-				 unsigned long flags);
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy);
+static void __maybe_unused __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
+						unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);
 static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 2ac440bc7e10..6b83537480b1 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -198,10 +198,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			if (wake) {
-				smp_mb(); /* EGP done before wake_up(). */
+			if (wake)
 				swake_up_one_online(&rcu_state.expedited_wq);
-			}
+
 			break;
 		}
 		mask = rnp->grpmask;
@@ -419,7 +418,6 @@ retry_ipi:
 
 static void rcu_exp_sel_wait_wake(unsigned long s);
 
-#ifdef CONFIG_RCU_EXP_KTHREAD
 static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 {
 	struct rcu_exp_work *rewp =
@@ -428,9 +426,14 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_exp_gp_kworker);
+}
+
+static inline bool rcu_exp_par_worker_started(struct rcu_node *rnp)
 {
-	return !!READ_ONCE(rcu_exp_par_gp_kworker);
+	return !!READ_ONCE(rnp->exp_kworker);
 }
 
 static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
@@ -441,7 +444,7 @@ static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
 	 * another work item on the same kthread worker can result in
 	 * deadlock.
 	 */
-	kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work);
+	kthread_queue_work(READ_ONCE(rnp->exp_kworker), &rnp->rew.rew_work);
 }
 
 static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
@@ -466,64 +469,6 @@ static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew
 	kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work);
 }
 
-static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
-{
-}
-#else /* !CONFIG_RCU_EXP_KTHREAD */
-static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
-{
-	struct rcu_exp_work *rewp =
-		container_of(wp, struct rcu_exp_work, rew_work);
-
-	__sync_rcu_exp_select_node_cpus(rewp);
-}
-
-static inline bool rcu_gp_par_worker_started(void)
-{
-	return !!READ_ONCE(rcu_par_gp_wq);
-}
-
-static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
-{
-	int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
-
-	INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-	/* If all offline, queue the work on an unbound CPU. */
-	if (unlikely(cpu > rnp->grphi - rnp->grplo))
-		cpu = WORK_CPU_UNBOUND;
-	else
-		cpu += rnp->grplo;
-	queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
-}
-
-static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
-{
-	flush_work(&rnp->rew.rew_work);
-}
-
-/*
- * Work-queue handler to drive an expedited grace period forward.
- */
-static void wait_rcu_exp_gp(struct work_struct *wp)
-{
-	struct rcu_exp_work *rewp;
-
-	rewp = container_of(wp, struct rcu_exp_work, rew_work);
-	rcu_exp_sel_wait_wake(rewp->rew_s);
-}
-
-static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
-{
-	INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp);
-	queue_work(rcu_gp_wq, &rew->rew_work);
-}
-
-static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
-{
-	destroy_work_on_stack(&rew->rew_work);
-}
-#endif /* CONFIG_RCU_EXP_KTHREAD */
-
 /*
  * Select the nodes that the upcoming expedited grace period needs
  * to wait for.
@@ -541,7 +486,7 @@ static void sync_rcu_exp_select_cpus(void)
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
-		if (!rcu_gp_par_worker_started() ||
+		if (!rcu_exp_par_worker_started(rnp) ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
 			/* No worker started yet or last leaf, do direct call. */
@@ -956,7 +901,6 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
 	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
@@ -996,7 +940,7 @@ void synchronize_rcu_expedited(void)
 		return;  /* Someone else did our work for us. */
 
 	/* Ensure that load happens before action based on it. */
-	if (unlikely(boottime)) {
+	if (unlikely((rcu_scheduler_active == RCU_SCHEDULER_INIT) || !rcu_exp_worker_started())) {
 		/* Direct call during scheduler init and early_initcalls(). */
 		rcu_exp_sel_wait_wake(s);
 	} else {
@@ -1013,9 +957,6 @@ void synchronize_rcu_expedited(void)
 
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rcu_state.exp_mutex);
-
-	if (likely(!boottime))
-		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 4efbf7333d4e..3f85577bddd4 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -256,6 +256,7 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
 	return __wake_nocb_gp(rdp_gp, rdp, force, flags);
 }
 
+#ifdef CONFIG_RCU_LAZY
 /*
  * LAZY_FLUSH_JIFFIES decides the maximum amount of time that
  * can elapse before lazy callbacks are flushed. Lazy callbacks
@@ -264,21 +265,20 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
  * left unsubmitted to RCU after those many jiffies.
  */
 #define LAZY_FLUSH_JIFFIES (10 * HZ)
-static unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES;
+static unsigned long jiffies_lazy_flush = LAZY_FLUSH_JIFFIES;
 
-#ifdef CONFIG_RCU_LAZY
 // To be called only from test code.
-void rcu_lazy_set_jiffies_till_flush(unsigned long jif)
+void rcu_set_jiffies_lazy_flush(unsigned long jif)
 {
-	jiffies_till_flush = jif;
+	jiffies_lazy_flush = jif;
 }
-EXPORT_SYMBOL(rcu_lazy_set_jiffies_till_flush);
+EXPORT_SYMBOL(rcu_set_jiffies_lazy_flush);
 
-unsigned long rcu_lazy_get_jiffies_till_flush(void)
+unsigned long rcu_get_jiffies_lazy_flush(void)
 {
-	return jiffies_till_flush;
+	return jiffies_lazy_flush;
 }
-EXPORT_SYMBOL(rcu_lazy_get_jiffies_till_flush);
+EXPORT_SYMBOL(rcu_get_jiffies_lazy_flush);
 #endif
 
 /*
@@ -299,7 +299,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 	 */
 	if (waketype == RCU_NOCB_WAKE_LAZY &&
 	    rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) {
-		mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush);
+		mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush());
 		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
 	} else if (waketype == RCU_NOCB_WAKE_BYPASS) {
 		mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
@@ -482,7 +482,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	// flush ->nocb_bypass to ->cblist.
 	if ((ncbs && !bypass_is_lazy && j != READ_ONCE(rdp->nocb_bypass_first)) ||
 	    (ncbs &&  bypass_is_lazy &&
-	     (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush))) ||
+	     (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()))) ||
 	    ncbs >= qhimark) {
 		rcu_nocb_lock(rdp);
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
@@ -532,9 +532,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	// 2. Both of these conditions are met:
 	//    a. The bypass list previously had only lazy CBs, and:
 	//    b. The new CB is non-lazy.
-	if (ncbs && (!bypass_is_lazy || lazy)) {
-		local_irq_restore(flags);
-	} else {
+	if (!ncbs || (bypass_is_lazy && !lazy)) {
 		// No-CBs GP kthread might be indefinitely asleep, if so, wake.
 		rcu_nocb_lock(rdp); // Rare during call_rcu() flood.
 		if (!rcu_segcblist_pend_cbs(&rdp->cblist)) {
@@ -544,7 +542,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 		} else {
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("FirstBQnoWake"));
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 		}
 	}
 	return true; // Callback already enqueued.
@@ -566,11 +564,12 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	long lazy_len;
 	long len;
 	struct task_struct *t;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 
 	// If we are being polled or there is no kthread, just leave.
 	t = READ_ONCE(rdp->nocb_gp_kthread);
 	if (rcu_nocb_poll || !t) {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		rcu_nocb_unlock(rdp);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("WakeNotPoll"));
 		return;
@@ -583,17 +582,17 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		rdp->qlen_last_fqs_check = len;
 		// Only lazy CBs in bypass list
 		if (lazy_len && bypass_len == lazy_len) {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY,
 					   TPS("WakeLazy"));
 		} else if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp(rdp, false);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE,
 					   TPS("WakeEmptyIsDeferred"));
 		}
@@ -610,20 +609,32 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 		smp_mb(); /* Enqueue before timer_pending(). */
 		if ((rdp->nocb_cb_sleep ||
 		     !rcu_segcblist_ready_cbs(&rdp->cblist)) &&
-		    !timer_pending(&rdp->nocb_timer)) {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+		    !timer_pending(&rdp_gp->nocb_timer)) {
+			rcu_nocb_unlock(rdp);
 			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE,
 					   TPS("WakeOvfIsDeferred"));
 		} else {
-			rcu_nocb_unlock_irqrestore(rdp, flags);
+			rcu_nocb_unlock(rdp);
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 		}
 	} else {
-		rcu_nocb_unlock_irqrestore(rdp, flags);
+		rcu_nocb_unlock(rdp);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 	}
 }
 
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy)
+{
+	bool was_alldone;
+
+	if (!rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy)) {
+		/* Not enqueued on bypass but locked, do regular enqueue */
+		rcutree_enqueue(rdp, head, func);
+		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
+	}
+}
+
 static int nocb_gp_toggle_rdp(struct rcu_data *rdp,
 			       bool *wake_state)
 {
@@ -723,7 +734,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		lazy_ncbs = READ_ONCE(rdp->lazy_len);
 
 		if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) &&
-		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) ||
+		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()) ||
 		     bypass_ncbs > 2 * qhimark)) {
 			flush_bypass = true;
 		} else if (bypass_ncbs && (lazy_ncbs != bypass_ncbs) &&
@@ -779,7 +790,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 		if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			needwake = rdp->nocb_cb_sleep;
 			WRITE_ONCE(rdp->nocb_cb_sleep, false);
-			smp_mb(); /* CB invocation -after- GP end. */
 		} else {
 			needwake = false;
 		}
@@ -933,8 +943,7 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 		swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
 						    nocb_cb_wait_cond(rdp));
 
-		// VVV Ensure CB invocation follows _sleep test.
-		if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^
+		if (READ_ONCE(rdp->nocb_cb_sleep)) {
 			WARN_ON(signal_pending(current));
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));
 		}
@@ -1383,7 +1392,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 			rcu_nocb_unlock_irqrestore(rdp, flags);
 			continue;
 		}
-		WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
+		rcu_nocb_try_flush_bypass(rdp, jiffies);
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		wake_nocb_gp(rdp, false);
 		sc->nr_to_scan -= _count;
@@ -1768,10 +1777,10 @@ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	return true;
 }
 
-static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				bool *was_alldone, unsigned long flags, bool lazy)
+static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
+			  rcu_callback_t func, unsigned long flags, bool lazy)
 {
-	return false;
+	WARN_ON_ONCE(1);  /* Should be dead code! */
 }
 
 static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 41021080ad25..36a8b5dbf5b5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1195,14 +1195,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	struct sched_param sp;
 	struct task_struct *t;
 
-	mutex_lock(&rnp->boost_kthread_mutex);
-	if (rnp->boost_kthread_task || !rcu_scheduler_fully_active)
-		goto out;
+	if (rnp->boost_kthread_task)
+		return;
 
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
 			   "rcub/%d", rnp_index);
 	if (WARN_ON_ONCE(IS_ERR(t)))
-		goto out;
+		return;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
@@ -1210,48 +1209,11 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
-
- out:
-	mutex_unlock(&rnp->boost_kthread_mutex);
 }
 
-/*
- * Set the per-rcu_node kthread's affinity to cover all CPUs that are
- * served by the rcu_node in question.  The CPU hotplug lock is still
- * held, so the value of rnp->qsmaskinit will be stable.
- *
- * We don't include outgoingcpu in the affinity set, use -1 if there is
- * no outgoing CPU.  If there are no CPUs left in the affinity set,
- * this function allows the kthread to execute on any CPU.
- *
- * Any future concurrent calls are serialized via ->boost_kthread_mutex.
- */
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
 {
-	struct task_struct *t = rnp->boost_kthread_task;
-	unsigned long mask;
-	cpumask_var_t cm;
-	int cpu;
-
-	if (!t)
-		return;
-	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
-		return;
-	mutex_lock(&rnp->boost_kthread_mutex);
-	mask = rcu_rnp_online_cpus(rnp);
-	for_each_leaf_node_possible_cpu(rnp, cpu)
-		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
-		    cpu != outgoingcpu)
-			cpumask_set_cpu(cpu, cm);
-	cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU));
-	if (cpumask_empty(cm)) {
-		cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU));
-		if (outgoingcpu >= 0)
-			cpumask_clear_cpu(outgoingcpu, cm);
-	}
-	set_cpus_allowed_ptr(t, cm);
-	mutex_unlock(&rnp->boost_kthread_mutex);
-	free_cpumask_var(cm);
+	return READ_ONCE(rnp->boost_kthread_task);
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
@@ -1270,10 +1232,10 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 {
 }
 
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static struct task_struct *rcu_boost_task(struct rcu_node *rnp)
 {
+	return NULL;
 }
-
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9116bcc90346..d44efa0d0611 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1792,7 +1792,6 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css);
 #endif
 
 #ifdef CONFIG_SYSCTL
-#ifdef CONFIG_UCLAMP_TASK
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 static void uclamp_update_root_tg(void)
 {
@@ -1898,7 +1897,6 @@ undo:
 	return result;
 }
 #endif
-#endif
 
 static int uclamp_validate(struct task_struct *p,
 			   const struct sched_attr *attr)
@@ -2065,7 +2063,7 @@ static void __init init_uclamp(void)
 	}
 }
 
-#else /* CONFIG_UCLAMP_TASK */
+#else /* !CONFIG_UCLAMP_TASK */
 static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { }
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { }
 static inline int uclamp_validate(struct task_struct *p,
@@ -3955,6 +3953,17 @@ void wake_up_if_idle(int cpu)
 	}
 }
 
+bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+	if (!sched_asym_cpucap_active())
+		return true;
+
+	if (this_cpu == that_cpu)
+		return true;
+
+	return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
+}
+
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	if (this_cpu == that_cpu)
@@ -6787,10 +6796,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 static void sched_update_worker(struct task_struct *tsk)
 {
-	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
+		if (tsk->flags & PF_BLOCK_TS)
+			blk_plug_invalidate_ts(tsk);
 		if (tsk->flags & PF_WQ_WORKER)
 			wq_worker_running(tsk);
-		else
+		else if (tsk->flags & PF_IO_WORKER)
 			io_wq_worker_running(tsk);
 	}
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 533547e3c90a..6a16129f9a5c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7289,7 +7289,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 		if (!available_idle_cpu(cpu)) {
 			idle = false;
 			if (*idle_cpu == -1) {
-				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) {
+				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) {
 					*idle_cpu = cpu;
 					break;
 				}
@@ -7297,7 +7297,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 			}
 			break;
 		}
-		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus))
 			*idle_cpu = cpu;
 	}
 
@@ -7311,13 +7311,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu;
 
 	for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) {
 		if (cpu == target)
 			continue;
+		/*
+		 * Check if the CPU is in the LLC scheduling domain of @target.
+		 * Due to isolcpus, there is no guarantee that all the siblings are in the domain.
+		 */
+		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+			continue;
 		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
 	}
@@ -7341,7 +7347,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma
 	return __select_idle_cpu(core, p);
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -7591,7 +7597,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		has_idle_core = test_idle_cores(target);
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
-			i = select_idle_smt(p, prev);
+			i = select_idle_smt(p, sd, prev);
 			if ((unsigned int)i < nr_cpumask_bits)
 				return i;
 		}
@@ -9237,19 +9243,17 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 
 static inline bool others_have_blocked(struct rq *rq)
 {
-	if (READ_ONCE(rq->avg_rt.util_avg))
+	if (cpu_util_rt(rq))
 		return true;
 
-	if (READ_ONCE(rq->avg_dl.util_avg))
+	if (cpu_util_dl(rq))
 		return true;
 
 	if (thermal_load_avg(rq))
 		return true;
 
-#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-	if (READ_ONCE(rq->avg_irq.util_avg))
+	if (cpu_util_irq(rq))
 		return true;
-#endif
 
 	return false;
 }
@@ -9506,8 +9510,8 @@ static unsigned long scale_rt_capacity(int cpu)
 	 * avg_thermal.load_avg tracks thermal pressure and the weighted
 	 * average uses the actual delta max capacity(load).
 	 */
-	used = READ_ONCE(rq->avg_rt.util_avg);
-	used += READ_ONCE(rq->avg_dl.util_avg);
+	used = cpu_util_rt(rq);
+	used += cpu_util_dl(rq);
 	used += thermal_load_avg(rq);
 
 	if (unlikely(used >= max))
@@ -9740,51 +9744,49 @@ group_type group_classify(unsigned int imbalance_pct,
  */
 static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
 {
+	if (!(sd->flags & SD_ASYM_PACKING))
+		return false;
+
 	if (!sched_smt_active())
 		return true;
 
 	return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu);
 }
 
+static inline bool sched_asym(struct sched_domain *sd, int dst_cpu, int src_cpu)
+{
+	/*
+	 * First check if @dst_cpu can do asym_packing load balance. Only do it
+	 * if it has higher priority than @src_cpu.
+	 */
+	return sched_use_asym_prio(sd, dst_cpu) &&
+		sched_asym_prefer(dst_cpu, src_cpu);
+}
+
 /**
- * sched_asym - Check if the destination CPU can do asym_packing load balance
+ * sched_group_asym - Check if the destination CPU can do asym_packing balance
  * @env:	The load balancing environment
- * @sds:	Load-balancing data with statistics of the local group
  * @sgs:	Load-balancing statistics of the candidate busiest group
  * @group:	The candidate busiest group
  *
  * @env::dst_cpu can do asym_packing if it has higher priority than the
  * preferred CPU of @group.
  *
- * SMT is a special case. If we are balancing load between cores, @env::dst_cpu
- * can do asym_packing balance only if all its SMT siblings are idle. Also, it
- * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
- * imbalances in the number of CPUS are dealt with in find_busiest_group().
- *
- * If we are balancing load within an SMT core, or at PKG domain level, always
- * proceed.
- *
  * Return: true if @env::dst_cpu can do with asym_packing load balance. False
  * otherwise.
  */
 static inline bool
-sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
-	   struct sched_group *group)
+sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group)
 {
-	/* Ensure that the whole local core is idle, if applicable. */
-	if (!sched_use_asym_prio(env->sd, env->dst_cpu))
-		return false;
-
 	/*
-	 * CPU priorities does not make sense for SMT cores with more than one
+	 * CPU priorities do not make sense for SMT cores with more than one
 	 * busy sibling.
 	 */
-	if (group->flags & SD_SHARE_CPUCAPACITY) {
-		if (sgs->group_weight - sgs->idle_cpus != 1)
-			return false;
-	}
+	if ((group->flags & SD_SHARE_CPUCAPACITY) &&
+	    (sgs->group_weight - sgs->idle_cpus != 1))
+		return false;
 
-	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
+	return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu);
 }
 
 /* One group has more than one SMT CPU while the other group does not */
@@ -9938,11 +9940,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_weight = group->group_weight;
 
 	/* Check if dst CPU is idle and preferred to this group */
-	if (!local_group && env->sd->flags & SD_ASYM_PACKING &&
-	    env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
-	    sched_asym(env, sds, sgs, group)) {
+	if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running &&
+	    sched_group_asym(env, sgs, group))
 		sgs->group_asym_packing = 1;
-	}
 
 	/* Check for loaded SMT group to be balanced to dst CPU */
 	if (!local_group && smt_balance(env, sgs, group))
@@ -10006,9 +10006,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	switch (sgs->group_type) {
 	case group_overloaded:
 		/* Select the overloaded group with highest avg_load. */
-		if (sgs->avg_load <= busiest->avg_load)
-			return false;
-		break;
+		return sgs->avg_load > busiest->avg_load;
 
 	case group_imbalanced:
 		/*
@@ -10019,18 +10017,14 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 	case group_asym_packing:
 		/* Prefer to move from lowest priority CPU's work */
-		if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu))
-			return false;
-		break;
+		return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu);
 
 	case group_misfit_task:
 		/*
 		 * If we have more than one misfit sg go with the biggest
 		 * misfit.
 		 */
-		if (sgs->group_misfit_task_load < busiest->group_misfit_task_load)
-			return false;
-		break;
+		return sgs->group_misfit_task_load > busiest->group_misfit_task_load;
 
 	case group_smt_balance:
 		/*
@@ -10182,10 +10176,8 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
 	 * be computed and tested before calling idle_cpu_without().
 	 */
 
-#ifdef CONFIG_SMP
 	if (rq->ttwu_pending)
 		return 0;
-#endif
 
 	return 1;
 }
@@ -10578,16 +10570,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 		update_sg_lb_stats(env, sds, sg, sgs, &sg_status);
 
-		if (local_group)
-			goto next_group;
-
-
-		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
+		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
 			sds->busiest_stat = *sgs;
 		}
 
-next_group:
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
@@ -10691,7 +10678,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 */
 	if (local->group_type == group_has_spare) {
 		if ((busiest->group_type > group_fully_busy) &&
-		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
+		    !(env->sd->flags & SD_SHARE_LLC)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
@@ -11038,10 +11025,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 * If balancing between cores, let lower priority CPUs help
 		 * SMT cores with more than one busy sibling.
 		 */
-		if ((env->sd->flags & SD_ASYM_PACKING) &&
-		    sched_use_asym_prio(env->sd, i) &&
-		    sched_asym_prefer(i, env->dst_cpu) &&
-		    nr_running == 1)
+		if (sched_asym(env->sd, i, env->dst_cpu) && nr_running == 1)
 			continue;
 
 		switch (env->migration_type) {
@@ -11137,8 +11121,7 @@ asym_active_balance(struct lb_env *env)
 	 * the lower priority @env::dst_cpu help it. Do not follow
 	 * CPU priority.
 	 */
-	return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) &&
-	       sched_use_asym_prio(env->sd, env->dst_cpu) &&
+	return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) &&
 	       (sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
 		!sched_use_asym_prio(env->sd, env->src_cpu));
 }
@@ -11910,8 +11893,7 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * preferred CPU must be idle.
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
-			if (sched_use_asym_prio(sd, i) &&
-			    sched_asym_prefer(i, cpu)) {
+			if (sched_asym(sd, i, cpu)) {
 				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 				goto unlock;
 			}
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 31231925f1ec..6135fbe83d68 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -81,6 +81,25 @@ void __weak arch_cpu_idle(void)
 	cpu_idle_force_poll = 1;
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE
+DEFINE_STATIC_KEY_FALSE(arch_needs_tick_broadcast);
+
+static inline void cond_tick_broadcast_enter(void)
+{
+	if (static_branch_unlikely(&arch_needs_tick_broadcast))
+		tick_broadcast_enter();
+}
+
+static inline void cond_tick_broadcast_exit(void)
+{
+	if (static_branch_unlikely(&arch_needs_tick_broadcast))
+		tick_broadcast_exit();
+}
+#else
+static inline void cond_tick_broadcast_enter(void) { }
+static inline void cond_tick_broadcast_exit(void) { }
+#endif
+
 /**
  * default_idle_call - Default CPU idle routine.
  *
@@ -90,6 +109,7 @@ void __cpuidle default_idle_call(void)
 {
 	instrumentation_begin();
 	if (!current_clr_polling_and_test()) {
+		cond_tick_broadcast_enter();
 		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
 
@@ -99,6 +119,7 @@ void __cpuidle default_idle_call(void)
 
 		start_critical_timings();
 		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+		cond_tick_broadcast_exit();
 	}
 	local_irq_enable();
 	instrumentation_end();
@@ -291,7 +312,6 @@ static void do_idle(void)
 		local_irq_disable();
 
 		if (cpu_is_offline(cpu)) {
-			tick_nohz_idle_stop_tick();
 			cpuhp_report_idle_dead();
 			arch_cpu_idle_dead();
 		}
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 2ad881d07752..4e715b9b278e 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -162,6 +162,9 @@
 	| MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK			\
 	| MEMBARRIER_CMD_GET_REGISTRATIONS)
 
+static DEFINE_MUTEX(membarrier_ipi_mutex);
+#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex)
+
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
@@ -259,6 +262,7 @@ static int membarrier_global_expedited(void)
 	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
@@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id)
 	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
+	SERIALIZE_IPI();
 	cpus_read_lock();
 
 	if (cpu_id >= 0) {
@@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
 	 * between threads which are users of @mm has its membarrier state
 	 * updated.
 	 */
+	SERIALIZE_IPI();
 	cpus_read_lock();
 	rcu_read_lock();
 	for_each_online_cpu(cpu) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 001fe047bd5d..d2242679239e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3136,7 +3136,7 @@ static inline bool uclamp_rq_is_idle(struct rq *rq)
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
-	return rq->avg_irq.util_avg;
+	return READ_ONCE(rq->avg_irq.util_avg);
 }
 
 static inline
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 10d1391e7416..99ea5986038c 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -657,13 +657,13 @@ static void destroy_sched_domains(struct sched_domain *sd)
 }
 
 /*
- * Keep a special pointer to the highest sched_domain that has
- * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
- * allows us to avoid some pointer chasing select_idle_sibling().
+ * Keep a special pointer to the highest sched_domain that has SD_SHARE_LLC set
+ * (Last Level Cache Domain) for this allows us to avoid some pointer chasing
+ * select_idle_sibling().
  *
- * Also keep a unique ID per domain (we use the first CPU number in
- * the cpumask of the domain), this allows us to quickly tell if
- * two CPUs are in the same cache domain, see cpus_share_cache().
+ * Also keep a unique ID per domain (we use the first CPU number in the cpumask
+ * of the domain), this allows us to quickly tell if two CPUs are in the same
+ * cache domain, see cpus_share_cache().
  */
 DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
@@ -684,7 +684,7 @@ static void update_top_cache_domain(int cpu)
 	int id = cpu;
 	int size = 1;
 
-	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
+	sd = highest_flag_domain(cpu, SD_SHARE_LLC);
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
@@ -1551,11 +1551,12 @@ static struct cpumask		***sched_domains_numa_masks;
  *
  * These flags are purely descriptive of the topology and do not prescribe
  * behaviour. Behaviour is artificial and mapped in the below sd_init()
- * function:
+ * function. For details, see include/linux/sched/sd_flags.h.
  *
- *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
- *   SD_SHARE_PKG_RESOURCES - describes shared caches
- *   SD_NUMA                - describes NUMA topologies
+ *   SD_SHARE_CPUCAPACITY
+ *   SD_SHARE_LLC
+ *   SD_CLUSTER
+ *   SD_NUMA
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1565,7 +1566,7 @@ static struct cpumask		***sched_domains_numa_masks;
 #define TOPOLOGY_SD_FLAGS		\
 	(SD_SHARE_CPUCAPACITY	|	\
 	 SD_CLUSTER		|	\
-	 SD_SHARE_PKG_RESOURCES |	\
+	 SD_SHARE_LLC		|	\
 	 SD_NUMA		|	\
 	 SD_ASYM_PACKING)
 
@@ -1608,7 +1609,7 @@ sd_init(struct sched_domain_topology_level *tl,
 					| 0*SD_BALANCE_WAKE
 					| 1*SD_WAKE_AFFINE
 					| 0*SD_SHARE_CPUCAPACITY
-					| 0*SD_SHARE_PKG_RESOURCES
+					| 0*SD_SHARE_LLC
 					| 0*SD_SERIALIZE
 					| 1*SD_PREFER_SIBLING
 					| 0*SD_NUMA
@@ -1645,7 +1646,7 @@ sd_init(struct sched_domain_topology_level *tl,
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->imbalance_pct = 110;
 
-	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+	} else if (sd->flags & SD_SHARE_LLC) {
 		sd->imbalance_pct = 117;
 		sd->cache_nice_tries = 1;
 
@@ -1670,7 +1671,7 @@ sd_init(struct sched_domain_topology_level *tl,
 	 * For all levels sharing cache; connect a sched_domain_shared
 	 * instance.
 	 */
-	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+	if (sd->flags & SD_SHARE_LLC) {
 		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
 		atomic_inc(&sd->shared->ref);
 		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
@@ -2445,8 +2446,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			struct sched_domain *child = sd->child;
 
-			if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child &&
-			    (child->flags & SD_SHARE_PKG_RESOURCES)) {
+			if (!(sd->flags & SD_SHARE_LLC) && child &&
+			    (child->flags & SD_SHARE_LLC)) {
 				struct sched_domain __rcu *top_p;
 				unsigned int nr_llcs;
 
diff --git a/kernel/signal.c b/kernel/signal.c
index c9c57d053ce4..bdca529f0f7b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -47,6 +47,7 @@
 #include <linux/cgroup.h>
 #include <linux/audit.h>
 #include <linux/sysctl.h>
+#include <uapi/linux/pidfd.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/signal.h>
@@ -1436,7 +1437,8 @@ void lockdep_assert_task_sighand_held(struct task_struct *task)
 #endif
 
 /*
- * send signal info to all the members of a group
+ * send signal info to all the members of a thread group or to the
+ * individual thread if type == PIDTYPE_PID.
  */
 int group_send_sig_info(int sig, struct kernel_siginfo *info,
 			struct task_struct *p, enum pid_type type)
@@ -1478,7 +1480,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
 	return ret;
 }
 
-int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+static int kill_pid_info_type(int sig, struct kernel_siginfo *info,
+				struct pid *pid, enum pid_type type)
 {
 	int error = -ESRCH;
 	struct task_struct *p;
@@ -1487,11 +1490,10 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
 		rcu_read_lock();
 		p = pid_task(pid, PIDTYPE_PID);
 		if (p)
-			error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
+			error = group_send_sig_info(sig, info, p, type);
 		rcu_read_unlock();
 		if (likely(!p || error != -ESRCH))
 			return error;
-
 		/*
 		 * The task was unhashed in between, try again.  If it
 		 * is dead, pid_task() will return NULL, if we race with
@@ -1500,6 +1502,11 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
 	}
 }
 
+int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+{
+	return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID);
+}
+
 static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
 {
 	int error;
@@ -1898,16 +1905,19 @@ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno,
 	return send_sig_info(info.si_signo, &info, t);
 }
 
-int kill_pgrp(struct pid *pid, int sig, int priv)
+static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
 {
 	int ret;
-
 	read_lock(&tasklist_lock);
-	ret = __kill_pgrp_info(sig, __si_special(priv), pid);
+	ret = __kill_pgrp_info(sig, info, pgrp);
 	read_unlock(&tasklist_lock);
-
 	return ret;
 }
+
+int kill_pgrp(struct pid *pid, int sig, int priv)
+{
+	return kill_pgrp_info(sig, __si_special(priv), pid);
+}
 EXPORT_SYMBOL(kill_pgrp);
 
 int kill_pid(struct pid *pid, int sig, int priv)
@@ -2019,13 +2029,14 @@ ret:
 	return ret;
 }
 
-static void do_notify_pidfd(struct task_struct *task)
+void do_notify_pidfd(struct task_struct *task)
 {
-	struct pid *pid;
+	struct pid *pid = task_pid(task);
 
 	WARN_ON(task->exit_state == 0);
-	pid = task_pid(task);
-	wake_up_all(&pid->wait_pidfd);
+
+	__wake_up(&pid->wait_pidfd, TASK_NORMAL, 0,
+			poll_to_key(EPOLLIN | EPOLLRDNORM));
 }
 
 /*
@@ -2050,9 +2061,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 
 	WARN_ON_ONCE(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
-
-	/* Wake up all pidfd waiters */
-	do_notify_pidfd(tsk);
+	/*
+	 * tsk is a group leader and has no threads, wake up the
+	 * non-PIDFD_THREAD waiters.
+	 */
+	if (thread_group_empty(tsk))
+		do_notify_pidfd(tsk);
 
 	if (sig != SIGCHLD) {
 		/*
@@ -3789,12 +3803,13 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese,
 #endif
 #endif
 
-static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info)
+static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info,
+				 enum pid_type type)
 {
 	clear_siginfo(info);
 	info->si_signo = sig;
 	info->si_errno = 0;
-	info->si_code = SI_USER;
+	info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER;
 	info->si_pid = task_tgid_vnr(current);
 	info->si_uid = from_kuid_munged(current_user_ns(), current_uid());
 }
@@ -3808,7 +3823,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 {
 	struct kernel_siginfo info;
 
-	prepare_kill_siginfo(sig, &info);
+	prepare_kill_siginfo(sig, &info, PIDTYPE_TGID);
 
 	return kill_something_info(sig, &info, pid);
 }
@@ -3861,6 +3876,10 @@ static struct pid *pidfd_to_pid(const struct file *file)
 	return tgid_pidfd_to_pid(file);
 }
 
+#define PIDFD_SEND_SIGNAL_FLAGS                            \
+	(PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \
+	 PIDFD_SIGNAL_PROCESS_GROUP)
+
 /**
  * sys_pidfd_send_signal - Signal a process through a pidfd
  * @pidfd:  file descriptor of the process
@@ -3868,14 +3887,10 @@ static struct pid *pidfd_to_pid(const struct file *file)
  * @info:   signal info
  * @flags:  future flags
  *
- * The syscall currently only signals via PIDTYPE_PID which covers
- * kill(<positive-pid>, <signal>. It does not signal threads or process
- * groups.
- * In order to extend the syscall to threads and process groups the @flags
- * argument should be used. In essence, the @flags argument will determine
- * what is signaled and not the file descriptor itself. Put in other words,
- * grouping is a property of the flags argument not a property of the file
- * descriptor.
+ * Send the signal to the thread group or to the individual thread depending
+ * on PIDFD_THREAD.
+ * In the future extension to @flags may be used to override the default scope
+ * of @pidfd.
  *
  * Return: 0 on success, negative errno on failure
  */
@@ -3886,9 +3901,14 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	struct fd f;
 	struct pid *pid;
 	kernel_siginfo_t kinfo;
+	enum pid_type type;
 
 	/* Enforce flags be set to 0 until we add an extension. */
-	if (flags)
+	if (flags & ~PIDFD_SEND_SIGNAL_FLAGS)
+		return -EINVAL;
+
+	/* Ensure that only a single signal scope determining flag is set. */
+	if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1)
 		return -EINVAL;
 
 	f = fdget(pidfd);
@@ -3906,6 +3926,25 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	if (!access_pidfd_pidns(pid))
 		goto err;
 
+	switch (flags) {
+	case 0:
+		/* Infer scope from the type of pidfd. */
+		if (f.file->f_flags & PIDFD_THREAD)
+			type = PIDTYPE_PID;
+		else
+			type = PIDTYPE_TGID;
+		break;
+	case PIDFD_SIGNAL_THREAD:
+		type = PIDTYPE_PID;
+		break;
+	case PIDFD_SIGNAL_THREAD_GROUP:
+		type = PIDTYPE_TGID;
+		break;
+	case PIDFD_SIGNAL_PROCESS_GROUP:
+		type = PIDTYPE_PGID;
+		break;
+	}
+
 	if (info) {
 		ret = copy_siginfo_from_user_any(&kinfo, info);
 		if (unlikely(ret))
@@ -3917,15 +3956,17 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 
 		/* Only allow sending arbitrary signals to yourself. */
 		ret = -EPERM;
-		if ((task_pid(current) != pid) &&
+		if ((task_pid(current) != pid || type > PIDTYPE_TGID) &&
 		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
 			goto err;
 	} else {
-		prepare_kill_siginfo(sig, &kinfo);
+		prepare_kill_siginfo(sig, &kinfo, type);
 	}
 
-	ret = kill_pid_info(sig, &kinfo, pid);
-
+	if (type == PIDTYPE_PGID)
+		ret = kill_pgrp_info(sig, &kinfo, pid);
+	else
+		ret = kill_pid_info_type(sig, &kinfo, pid, type);
 err:
 	fdput(f);
 	return ret;
@@ -3965,12 +4006,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
 {
 	struct kernel_siginfo info;
 
-	clear_siginfo(&info);
-	info.si_signo = sig;
-	info.si_errno = 0;
-	info.si_code = SI_TKILL;
-	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
+	prepare_kill_siginfo(sig, &info, PIDTYPE_PID);
 
 	return do_send_specific(tgid, pid, sig, &info);
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 210cf5f8d92c..b315b21fb28c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -27,6 +27,7 @@
 #include <linux/tick.h>
 #include <linux/irq.h>
 #include <linux/wait_bit.h>
+#include <linux/workqueue.h>
 
 #include <asm/softirq_stack.h>
 
@@ -802,11 +803,13 @@ static void tasklet_action_common(struct softirq_action *a,
 
 static __latent_entropy void tasklet_action(struct softirq_action *a)
 {
+	workqueue_softirq_action(false);
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
 }
 
 static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
 {
+	workqueue_softirq_action(true);
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
 }
 
@@ -929,6 +932,8 @@ static void run_ksoftirqd(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 static int takeover_tasklets(unsigned int cpu)
 {
+	workqueue_softirq_dead(cpu);
+
 	/* CPU is dead, so no lock needed. */
 	local_irq_disable();
 
diff --git a/kernel/sys.c b/kernel/sys.c
index e219fcfa112d..f8e543f1e38a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1785,21 +1785,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	u64 tgutime, tgstime, utime, stime;
-	unsigned long maxrss = 0;
+	unsigned long maxrss;
+	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
+	unsigned int seq = 0;
 
-	memset((char *)r, 0, sizeof (*r));
+retry:
+	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
+	maxrss = 0;
 
 	if (who == RUSAGE_THREAD) {
 		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = sig->maxrss;
-		goto out;
+		goto out_thread;
 	}
 
-	if (!lock_task_sighand(p, &flags))
-		return;
+	flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
 
 	switch (who) {
 	case RUSAGE_BOTH:
@@ -1819,9 +1822,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		fallthrough;
 
 	case RUSAGE_SELF:
-		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		utime += tgutime;
-		stime += tgstime;
 		r->ru_nvcsw += sig->nvcsw;
 		r->ru_nivcsw += sig->nivcsw;
 		r->ru_minflt += sig->min_flt;
@@ -1830,28 +1830,42 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		r->ru_oublock += sig->oublock;
 		if (maxrss < sig->maxrss)
 			maxrss = sig->maxrss;
+
+		rcu_read_lock();
 		__for_each_thread(sig, t)
 			accumulate_thread_rusage(t, r);
+		rcu_read_unlock();
+
 		break;
 
 	default:
 		BUG();
 	}
-	unlock_task_sighand(p, &flags);
 
-out:
-	r->ru_utime = ns_to_kernel_old_timeval(utime);
-	r->ru_stime = ns_to_kernel_old_timeval(stime);
+	if (need_seqretry(&sig->stats_lock, seq)) {
+		seq = 1;
+		goto retry;
+	}
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
 
-	if (who != RUSAGE_CHILDREN) {
-		struct mm_struct *mm = get_task_mm(p);
+	if (who == RUSAGE_CHILDREN)
+		goto out_children;
 
-		if (mm) {
-			setmax_mm_hiwater_rss(&maxrss, mm);
-			mmput(mm);
-		}
+	thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+	utime += tgutime;
+	stime += tgstime;
+
+out_thread:
+	mm = get_task_mm(p);
+	if (mm) {
+		setmax_mm_hiwater_rss(&maxrss, mm);
+		mmput(mm);
 	}
+
+out_children:
 	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 }
 
 SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index bae8f11070be..fc3b1a06c981 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -39,6 +39,11 @@ config GENERIC_CLOCKEVENTS_BROADCAST
 	bool
 	depends on GENERIC_CLOCKEVENTS
 
+# Handle broadcast in default_idle_call()
+config GENERIC_CLOCKEVENTS_BROADCAST_IDLE
+	bool
+	depends on GENERIC_CLOCKEVENTS_BROADCAST
+
 # Automatically adjust the min. reprogramming time for
 # clock event device
 config GENERIC_CLOCKEVENTS_MIN_ADJUST
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 7e875e63ff3b..4af2a264a160 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -17,6 +17,9 @@ endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
 obj-$(CONFIG_LEGACY_TIMER_TICK)			+= tick-legacy.o
+ifeq ($(CONFIG_SMP),y)
+ obj-$(CONFIG_NO_HZ_COMMON)			+= timer_migration.o
+endif
 obj-$(CONFIG_HAVE_GENERIC_VDSO)			+= vsyscall.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 960143b183cd..a7ca458cdd9c 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -659,7 +659,7 @@ void tick_cleanup_dead_cpu(int cpu)
 #endif
 
 #ifdef CONFIG_SYSFS
-static struct bus_type clockevents_subsys = {
+static const struct bus_type clockevents_subsys = {
 	.name		= "clockevents",
 	.dev_name       = "clockevent",
 };
diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c
index df922f49d171..d06185e054ea 100644
--- a/kernel/time/clocksource-wdtest.c
+++ b/kernel/time/clocksource-wdtest.c
@@ -104,8 +104,8 @@ static void wdtest_ktime_clocksource_reset(void)
 static int wdtest_func(void *arg)
 {
 	unsigned long j1, j2;
+	int i, max_retries;
 	char *s;
-	int i;
 
 	schedule_timeout_uninterruptible(holdoff * HZ);
 
@@ -139,18 +139,19 @@ static int wdtest_func(void *arg)
 	WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC));
 
 	/* Verify tsc-like stability with various numbers of errors injected. */
-	for (i = 0; i <= max_cswd_read_retries + 1; i++) {
-		if (i <= 1 && i < max_cswd_read_retries)
+	max_retries = clocksource_get_max_watchdog_retry();
+	for (i = 0; i <= max_retries + 1; i++) {
+		if (i <= 1 && i < max_retries)
 			s = "";
-		else if (i <= max_cswd_read_retries)
+		else if (i <= max_retries)
 			s = ", expect message";
 		else
 			s = ", expect clock skew";
-		pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s);
+		pr_info("--- Watchdog with %dx error injection, %d retries%s.\n", i, max_retries, s);
 		WRITE_ONCE(wdtest_ktime_read_ndelays, i);
 		schedule_timeout_uninterruptible(2 * HZ);
 		WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays));
-		WARN_ON_ONCE((i <= max_cswd_read_retries) !=
+		WARN_ON_ONCE((i <= max_retries) !=
 			     !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE));
 		wdtest_ktime_clocksource_reset();
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 3052b1f1168e..e5b260aa0e02 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -210,9 +210,6 @@ void clocksource_mark_unstable(struct clocksource *cs)
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
-ulong max_cswd_read_retries = 2;
-module_param(max_cswd_read_retries, ulong, 0644);
-EXPORT_SYMBOL_GPL(max_cswd_read_retries);
 static int verify_n_cpus = 8;
 module_param(verify_n_cpus, int, 0644);
 
@@ -224,11 +221,12 @@ enum wd_read_status {
 
 static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
 {
-	unsigned int nretries;
+	unsigned int nretries, max_retries;
 	u64 wd_end, wd_end2, wd_delta;
 	int64_t wd_delay, wd_seq_delay;
 
-	for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) {
+	max_retries = clocksource_get_max_watchdog_retry();
+	for (nretries = 0; nretries <= max_retries; nretries++) {
 		local_irq_disable();
 		*wdnow = watchdog->read(watchdog);
 		*csnow = cs->read(cs);
@@ -240,7 +238,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 		wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult,
 					      watchdog->shift);
 		if (wd_delay <= WATCHDOG_MAX_SKEW) {
-			if (nretries > 1 || nretries >= max_cswd_read_retries) {
+			if (nretries > 1 || nretries >= max_retries) {
 				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
 					smp_processor_id(), watchdog->name, nretries);
 			}
@@ -1468,7 +1466,7 @@ static struct attribute *clocksource_attrs[] = {
 };
 ATTRIBUTE_GROUPS(clocksource);
 
-static struct bus_type clocksource_subsys = {
+static const struct bus_type clocksource_subsys = {
 	.name = "clocksource",
 	.dev_name = "clocksource",
 };
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 760793998cdd..70625dff62ce 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -38,6 +38,7 @@
 #include <linux/sched/deadline.h>
 #include <linux/sched/nohz.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/isolation.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 #include <linux/compat.h>
@@ -746,7 +747,7 @@ static void hrtimer_switch_to_hres(void)
 	base->hres_active = 1;
 	hrtimer_resolution = HIGH_RES_NSEC;
 
-	tick_setup_sched_timer();
+	tick_setup_sched_timer(true);
 	/* "Retrigger" the interrupt to get things going */
 	retrigger_next_event(NULL);
 }
@@ -1021,21 +1022,23 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 }
 
 /**
- * hrtimer_forward - forward the timer expiry
+ * hrtimer_forward() - forward the timer expiry
  * @timer:	hrtimer to forward
  * @now:	forward past this time
  * @interval:	the interval to forward
  *
  * Forward the timer expiry so it will expire in the future.
- * Returns the number of overruns.
  *
- * Can be safely called from the callback function of @timer. If
- * called from other contexts @timer must neither be enqueued nor
- * running the callback and the caller needs to take care of
- * serialization.
+ * .. note::
+ *  This only updates the timer expiry value and does not requeue the timer.
  *
- * Note: This only updates the timer expiry value and does not requeue
- * the timer.
+ * There is also a variant of the function hrtimer_forward_now().
+ *
+ * Context: Can be safely called from the callback function of @timer. If called
+ *          from other contexts @timer must neither be enqueued nor running the
+ *          callback and the caller needs to take care of serialization.
+ *
+ * Return: The number of overruns are returned.
  */
 u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
 {
@@ -1085,6 +1088,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 			   enum hrtimer_mode mode)
 {
 	debug_activate(timer, mode);
+	WARN_ON_ONCE(!base->cpu_base->online);
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
@@ -2183,6 +2187,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
 	cpu_base->softirq_next_timer = NULL;
 	cpu_base->expires_next = KTIME_MAX;
 	cpu_base->softirq_expires_next = KTIME_MAX;
+	cpu_base->online = 1;
 	hrtimer_cpu_base_init_expiry_lock(cpu_base);
 	return 0;
 }
@@ -2221,10 +2226,8 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 
 int hrtimers_cpu_dying(unsigned int dying_cpu)
 {
+	int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER));
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i, ncpu = cpumask_first(cpu_active_mask);
-
-	tick_cancel_sched_timer(dying_cpu);
 
 	old_base = this_cpu_ptr(&hrtimer_bases);
 	new_base = &per_cpu(hrtimer_bases, ncpu);
@@ -2250,6 +2253,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 
 	raw_spin_unlock(&new_base->lock);
+	old_base->online = 0;
 	raw_spin_unlock(&old_base->lock);
 
 	return 0;
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index e9138cd7a0f5..fb0fdec8719a 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -111,15 +111,13 @@ void tick_handle_periodic(struct clock_event_device *dev)
 
 	tick_periodic(cpu);
 
-#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON)
 	/*
 	 * The cpu might have transitioned to HIGHRES or NOHZ mode via
 	 * update_process_times() -> run_local_timers() ->
 	 * hrtimer_run_queues().
 	 */
-	if (dev->event_handler != tick_handle_periodic)
+	if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic)
 		return;
-#endif
 
 	if (!clockevent_state_oneshot(dev))
 		return;
@@ -398,16 +396,31 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
 #ifdef CONFIG_HOTPLUG_CPU
+void tick_assert_timekeeping_handover(void)
+{
+	WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id());
+}
 /*
- * Transfer the do_timer job away from a dying cpu.
- *
- * Called with interrupts disabled. No locking required. If
- * tick_do_timer_cpu is owned by this cpu, nothing can change it.
+ * Stop the tick and transfer the timekeeping job away from a dying cpu.
  */
-void tick_handover_do_timer(void)
+int tick_cpu_dying(unsigned int dying_cpu)
 {
-	if (tick_do_timer_cpu == smp_processor_id())
+	/*
+	 * If the current CPU is the timekeeper, it's the only one that
+	 * can safely hand over its duty. Also all online CPUs are in
+	 * stop machine, guaranteed not to be idle, therefore it's safe
+	 * to pick any online successor.
+	 */
+	if (tick_do_timer_cpu == dying_cpu)
 		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
+
+	/* Make sure the CPU won't try to retake the timekeeping duty */
+	tick_sched_timer_dying(dying_cpu);
+
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(dying_cpu);
+
+	return 0;
 }
 
 /*
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 481b7ab65e2c..5f2105e637bd 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -8,6 +8,11 @@
 #include "timekeeping.h"
 #include "tick-sched.h"
 
+struct timer_events {
+	u64	local;
+	u64	global;
+};
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 # define TICK_DO_TIMER_NONE	-1
@@ -137,8 +142,10 @@ static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_
 #endif /* !(BROADCAST && ONESHOT) */
 
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_offline_cpu(unsigned int cpu);
 extern void tick_broadcast_offline(unsigned int cpu);
 #else
+static inline void tick_offline_cpu(unsigned int cpu) { }
 static inline void tick_broadcast_offline(unsigned int cpu) { }
 #endif
 
@@ -152,8 +159,16 @@ static inline void tick_nohz_init(void) { }
 #ifdef CONFIG_NO_HZ_COMMON
 extern unsigned long tick_nohz_active;
 extern void timers_update_nohz(void);
+extern u64 get_jiffies_update(unsigned long *basej);
 # ifdef CONFIG_SMP
 extern struct static_key_false timers_migration_enabled;
+extern void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem,
+					      struct timer_events *tevt,
+					      unsigned int cpu);
+extern void timer_lock_remote_bases(unsigned int cpu);
+extern void timer_unlock_remote_bases(unsigned int cpu);
+extern bool timer_base_is_idle(void);
+extern void timer_expire_remote(unsigned int cpu);
 # endif
 #else /* CONFIG_NO_HZ_COMMON */
 static inline void timers_update_nohz(void) { }
@@ -163,6 +178,7 @@ static inline void timers_update_nohz(void) { }
 DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
 
 extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem);
+u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle);
 void timer_clear_idle(void);
 
 #define CLOCK_SET_WALL							\
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 01fb50c1b17e..269e21590df5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -43,7 +43,6 @@ struct tick_sched *tick_get_tick_sched(int cpu)
 	return &per_cpu(tick_cpu_sched, cpu);
 }
 
-#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
 /*
  * The time when the last jiffy update happened. Write access must hold
  * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a
@@ -181,13 +180,32 @@ static ktime_t tick_init_jiffy_update(void)
 	return period;
 }
 
+static inline int tick_sched_flag_test(struct tick_sched *ts,
+				       unsigned long flag)
+{
+	return !!(ts->flags & flag);
+}
+
+static inline void tick_sched_flag_set(struct tick_sched *ts,
+				       unsigned long flag)
+{
+	lockdep_assert_irqs_disabled();
+	ts->flags |= flag;
+}
+
+static inline void tick_sched_flag_clear(struct tick_sched *ts,
+					 unsigned long flag)
+{
+	lockdep_assert_irqs_disabled();
+	ts->flags &= ~flag;
+}
+
 #define MAX_STALLED_JIFFIES 5
 
 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 {
 	int cpu = smp_processor_id();
 
-#ifdef CONFIG_NO_HZ_COMMON
 	/*
 	 * Check if the do_timer duty was dropped. We don't care about
 	 * concurrency: This happens only when the CPU in charge went
@@ -198,13 +216,13 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * If nohz_full is enabled, this should not happen because the
 	 * 'tick_do_timer_cpu' CPU never relinquishes.
 	 */
-	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
+	    unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
 #ifdef CONFIG_NO_HZ_FULL
 		WARN_ON_ONCE(tick_nohz_full_running);
 #endif
 		tick_do_timer_cpu = cpu;
 	}
-#endif
 
 	/* Check if jiffies need an update */
 	if (tick_do_timer_cpu == cpu)
@@ -225,13 +243,12 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 		}
 	}
 
-	if (ts->inidle)
+	if (tick_sched_flag_test(ts, TS_FLAG_INIDLE))
 		ts->got_idle_tick = 1;
 }
 
 static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 {
-#ifdef CONFIG_NO_HZ_COMMON
 	/*
 	 * When we are idle and the tick is stopped, we have to touch
 	 * the watchdog as we might not schedule for a really long
@@ -240,7 +257,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 	 * idle" jiffy stamp so the idle accounting adjustment we do
 	 * when we go busy again does not account too many ticks.
 	 */
-	if (ts->tick_stopped) {
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
+	    tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		touch_softlockup_watchdog_sched();
 		if (is_idle_task(current))
 			ts->idle_jiffies++;
@@ -251,11 +269,52 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 		 */
 		ts->next_tick = 0;
 	}
-#endif
+
 	update_process_times(user_mode(regs));
 	profile_tick(CPU_PROFILING);
 }
-#endif
+
+/*
+ * We rearm the timer until we get disabled by the idle code.
+ * Called with interrupts disabled.
+ */
+static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer)
+{
+	struct tick_sched *ts =	container_of(timer, struct tick_sched, sched_timer);
+	struct pt_regs *regs = get_irq_regs();
+	ktime_t now = ktime_get();
+
+	tick_sched_do_timer(ts, now);
+
+	/*
+	 * Do not call when we are not in IRQ context and have
+	 * no valid 'regs' pointer
+	 */
+	if (regs)
+		tick_sched_handle(ts, regs);
+	else
+		ts->next_tick = 0;
+
+	/*
+	 * In dynticks mode, tick reprogram is deferred:
+	 * - to the idle task if in dynticks-idle
+	 * - to IRQ exit if in full-dynticks.
+	 */
+	if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED)))
+		return HRTIMER_NORESTART;
+
+	hrtimer_forward(timer, now, TICK_NSEC);
+
+	return HRTIMER_RESTART;
+}
+
+static void tick_sched_timer_cancel(struct tick_sched *ts)
+{
+	if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES))
+		hrtimer_cancel(&ts->sched_timer);
+	else if (tick_sched_flag_test(ts, TS_FLAG_NOHZ))
+		tick_program_event(KTIME_MAX, 1);
+}
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
@@ -529,7 +588,7 @@ void __tick_nohz_task_switch(void)
 
 	ts = this_cpu_ptr(&tick_cpu_sched);
 
-	if (ts->tick_stopped) {
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		if (atomic_read(&current->tick_dep_mask) ||
 		    atomic_read(&current->signal->tick_dep_mask))
 			tick_nohz_full_kick();
@@ -601,7 +660,7 @@ void __init tick_nohz_init(void)
 	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
 		cpumask_pr_args(tick_nohz_full_mask));
 }
-#endif
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
 
 /*
  * NOHZ - aka dynamic tick functionality
@@ -626,14 +685,14 @@ bool tick_nohz_tick_stopped(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
-	return ts->tick_stopped;
+	return tick_sched_flag_test(ts, TS_FLAG_STOPPED);
 }
 
 bool tick_nohz_tick_stopped_cpu(int cpu)
 {
 	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
 
-	return ts->tick_stopped;
+	return tick_sched_flag_test(ts, TS_FLAG_STOPPED);
 }
 
 /**
@@ -663,7 +722,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
 	ktime_t delta;
 
-	if (WARN_ON_ONCE(!ts->idle_active))
+	if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)))
 		return;
 
 	delta = ktime_sub(now, ts->idle_entrytime);
@@ -675,7 +734,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
 
 	ts->idle_entrytime = now;
-	ts->idle_active = 0;
+	tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE);
 	write_seqcount_end(&ts->idle_sleeptime_seq);
 
 	sched_clock_idle_wakeup_event();
@@ -685,7 +744,7 @@ static void tick_nohz_start_idle(struct tick_sched *ts)
 {
 	write_seqcount_begin(&ts->idle_sleeptime_seq);
 	ts->idle_entrytime = ktime_get();
-	ts->idle_active = 1;
+	tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE);
 	write_seqcount_end(&ts->idle_sleeptime_seq);
 
 	sched_clock_idle_sleep_event();
@@ -707,7 +766,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
 	do {
 		seq = read_seqcount_begin(&ts->idle_sleeptime_seq);
 
-		if (ts->idle_active && compute_delta) {
+		if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) {
 			ktime_t delta = ktime_sub(now, ts->idle_entrytime);
 
 			idle = ktime_add(*sleeptime, delta);
@@ -780,7 +839,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	/* Forward the time to expire in the future */
 	hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
 
-	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+	if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) {
 		hrtimer_start_expires(&ts->sched_timer,
 				      HRTIMER_MODE_ABS_PINNED_HARD);
 	} else {
@@ -799,18 +858,40 @@ static inline bool local_timer_softirq_pending(void)
 	return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
 }
 
-static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
+/*
+ * Read jiffies and the time when jiffies were updated last
+ */
+u64 get_jiffies_update(unsigned long *basej)
 {
-	u64 basemono, next_tick, delta, expires;
 	unsigned long basejiff;
 	unsigned int seq;
+	u64 basemono;
 
-	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqcount_begin(&jiffies_seq);
 		basemono = last_jiffies_update;
 		basejiff = jiffies;
 	} while (read_seqcount_retry(&jiffies_seq, seq));
+	*basej = basejiff;
+	return basemono;
+}
+
+/**
+ * tick_nohz_next_event() - return the clock monotonic based next event
+ * @ts:		pointer to tick_sched struct
+ * @cpu:	CPU number
+ *
+ * Return:
+ * *%0		- When the next event is a maximum of TICK_NSEC in the future
+ *		  and the tick is not stopped yet
+ * *%next_event	- Next event based on clock monotonic
+ */
+static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
+{
+	u64 basemono, next_tick, delta, expires;
+	unsigned long basejiff;
+
+	basemono = get_jiffies_update(&basejiff);
 	ts->last_jiffies = basejiff;
 	ts->timer_expires_base = basemono;
 
@@ -850,15 +931,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	delta = next_tick - basemono;
 	if (delta <= (u64)TICK_NSEC) {
 		/*
-		 * Tell the timer code that the base is not idle, i.e. undo
-		 * the effect of get_next_timer_interrupt():
-		 */
-		timer_clear_idle();
-		/*
 		 * We've not stopped the tick yet, and there's a timer in the
 		 * next period, so no point in stopping it either, bail.
 		 */
-		if (!ts->tick_stopped) {
+		if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 			ts->timer_expires = 0;
 			goto out;
 		}
@@ -871,7 +947,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 */
 	delta = timekeeping_max_deferment();
 	if (cpu != tick_do_timer_cpu &&
-	    (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last))
+	    (tick_do_timer_cpu != TICK_DO_TIMER_NONE ||
+	     !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
 		delta = KTIME_MAX;
 
 	/* Calculate the next expiry time */
@@ -889,13 +966,39 @@ out:
 static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
+	unsigned long basejiff = ts->last_jiffies;
 	u64 basemono = ts->timer_expires_base;
-	u64 expires = ts->timer_expires;
+	bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
+	u64 expires;
 
 	/* Make sure we won't be trying to stop it twice in a row. */
 	ts->timer_expires_base = 0;
 
 	/*
+	 * Now the tick should be stopped definitely - so the timer base needs
+	 * to be marked idle as well to not miss a newly queued timer.
+	 */
+	expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle);
+	if (expires > ts->timer_expires) {
+		/*
+		 * This path could only happen when the first timer was removed
+		 * between calculating the possible sleep length and now (when
+		 * high resolution mode is not active, timer could also be a
+		 * hrtimer).
+		 *
+		 * We have to stick to the original calculated expiry value to
+		 * not stop the tick for too long with a shallow C-state (which
+		 * was programmed by cpuidle because of an early next expiration
+		 * value).
+		 */
+		expires = ts->timer_expires;
+	}
+
+	/* If the timer base is not idle, retain the not yet stopped tick. */
+	if (!timer_idle)
+		return;
+
+	/*
 	 * If this CPU is the one which updates jiffies, then give up
 	 * the assignment and let it be taken by the CPU which runs
 	 * the tick timer next, which might be this CPU as well. If we
@@ -905,13 +1008,13 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 */
 	if (cpu == tick_do_timer_cpu) {
 		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-		ts->do_timer_last = 1;
+		tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST);
 	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
-		ts->do_timer_last = 0;
+		tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST);
 	}
 
 	/* Skip reprogram of event if it's not changed */
-	if (ts->tick_stopped && (expires == ts->next_tick)) {
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) {
 		/* Sanity check: make sure clockevent is actually programmed */
 		if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
 			return;
@@ -929,12 +1032,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 * call we save the current tick time, so we can restart the
 	 * scheduler tick in tick_nohz_restart_sched_tick().
 	 */
-	if (!ts->tick_stopped) {
+	if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		calc_load_nohz_start();
 		quiet_vmstat();
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
-		ts->tick_stopped = 1;
+		tick_sched_flag_set(ts, TS_FLAG_STOPPED);
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
@@ -945,14 +1048,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 * the tick timer.
 	 */
 	if (unlikely(expires == KTIME_MAX)) {
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
-			hrtimer_cancel(&ts->sched_timer);
-		else
-			tick_program_event(KTIME_MAX, 1);
+		tick_sched_timer_cancel(ts);
 		return;
 	}
 
-	if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+	if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) {
 		hrtimer_start(&ts->sched_timer, expires,
 			      HRTIMER_MODE_ABS_PINNED_HARD);
 	} else {
@@ -967,7 +1067,7 @@ static void tick_nohz_retain_tick(struct tick_sched *ts)
 }
 
 #ifdef CONFIG_NO_HZ_FULL
-static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu)
+static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu)
 {
 	if (tick_nohz_next_event(ts, cpu))
 		tick_nohz_stop_tick(ts, cpu);
@@ -991,7 +1091,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	touch_softlockup_watchdog_sched();
 
 	/* Cancel the scheduled timer and restore the tick: */
-	ts->tick_stopped  = 0;
+	tick_sched_flag_clear(ts, TS_FLAG_STOPPED);
 	tick_nohz_restart(ts, now);
 }
 
@@ -1002,8 +1102,8 @@ static void __tick_nohz_full_update_tick(struct tick_sched *ts,
 	int cpu = smp_processor_id();
 
 	if (can_stop_full_tick(cpu, ts))
-		tick_nohz_stop_sched_tick(ts, cpu);
-	else if (ts->tick_stopped)
+		tick_nohz_full_stop_tick(ts, cpu);
+	else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
 		tick_nohz_restart_sched_tick(ts, now);
 #endif
 }
@@ -1013,7 +1113,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	if (!tick_nohz_full_cpu(smp_processor_id()))
 		return;
 
-	if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+	if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ))
 		return;
 
 	__tick_nohz_full_update_tick(ts, ktime_get());
@@ -1060,25 +1160,9 @@ static bool report_idle_softirq(void)
 
 static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 {
-	/*
-	 * If this CPU is offline and it is the one which updates
-	 * jiffies, then give up the assignment and let it be taken by
-	 * the CPU which runs the tick timer next. If we don't drop
-	 * this here, the jiffies might be stale and do_timer() never
-	 * gets invoked.
-	 */
-	if (unlikely(!cpu_online(cpu))) {
-		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-		/*
-		 * Make sure the CPU doesn't get fooled by obsolete tick
-		 * deadline if it comes back online later.
-		 */
-		ts->next_tick = 0;
-		return false;
-	}
+	WARN_ON_ONCE(cpu_is_offline(cpu));
 
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+	if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ)))
 		return false;
 
 	if (need_resched())
@@ -1128,14 +1212,14 @@ void tick_nohz_idle_stop_tick(void)
 	ts->idle_calls++;
 
 	if (expires > 0LL) {
-		int was_stopped = ts->tick_stopped;
+		int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
 
 		tick_nohz_stop_tick(ts, cpu);
 
 		ts->idle_sleeps++;
 		ts->idle_expires = expires;
 
-		if (!was_stopped && ts->tick_stopped) {
+		if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 			ts->idle_jiffies = ts->last_jiffies;
 			nohz_balance_enter_idle(cpu);
 		}
@@ -1147,11 +1231,6 @@ void tick_nohz_idle_stop_tick(void)
 void tick_nohz_idle_retain_tick(void)
 {
 	tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
-	/*
-	 * Undo the effect of get_next_timer_interrupt() called from
-	 * tick_nohz_next_event().
-	 */
-	timer_clear_idle();
 }
 
 /**
@@ -1171,7 +1250,7 @@ void tick_nohz_idle_enter(void)
 
 	WARN_ON_ONCE(ts->timer_expires_base);
 
-	ts->inidle = 1;
+	tick_sched_flag_set(ts, TS_FLAG_INIDLE);
 	tick_nohz_start_idle(ts);
 
 	local_irq_enable();
@@ -1200,7 +1279,7 @@ void tick_nohz_irq_exit(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
-	if (ts->inidle)
+	if (tick_sched_flag_test(ts, TS_FLAG_INIDLE))
 		tick_nohz_start_idle(ts);
 	else
 		tick_nohz_full_update_tick(ts);
@@ -1254,7 +1333,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 	ktime_t now = ts->idle_entrytime;
 	ktime_t next_event;
 
-	WARN_ON_ONCE(!ts->inidle);
+	WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE));
 
 	*delta_next = ktime_sub(dev->next_event, now);
 
@@ -1326,7 +1405,7 @@ void tick_nohz_idle_restart_tick(void)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
-	if (ts->tick_stopped) {
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) {
 		ktime_t now = ktime_get();
 		tick_nohz_restart_sched_tick(ts, now);
 		tick_nohz_account_idle_time(ts, now);
@@ -1367,12 +1446,12 @@ void tick_nohz_idle_exit(void)
 
 	local_irq_disable();
 
-	WARN_ON_ONCE(!ts->inidle);
+	WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE));
 	WARN_ON_ONCE(ts->timer_expires_base);
 
-	ts->inidle = 0;
-	idle_active = ts->idle_active;
-	tick_stopped = ts->tick_stopped;
+	tick_sched_flag_clear(ts, TS_FLAG_INIDLE);
+	idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE);
+	tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
 
 	if (idle_active || tick_stopped)
 		now = ktime_get();
@@ -1391,38 +1470,22 @@ void tick_nohz_idle_exit(void)
  * at the clockevent level. hrtimer can't be used instead, because its
  * infrastructure actually relies on the tick itself as a backend in
  * low-resolution mode (see hrtimer_run_queues()).
- *
- * This low-resolution handler still makes use of some hrtimer APIs meanwhile
- * for convenience with expiration calculation and forwarding.
  */
 static void tick_nohz_lowres_handler(struct clock_event_device *dev)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
-	struct pt_regs *regs = get_irq_regs();
-	ktime_t now = ktime_get();
 
 	dev->next_event = KTIME_MAX;
 
-	tick_sched_do_timer(ts, now);
-	tick_sched_handle(ts, regs);
-
-	/*
-	 * In dynticks mode, tick reprogram is deferred:
-	 * - to the idle task if in dynticks-idle
-	 * - to IRQ exit if in full-dynticks.
-	 */
-	if (likely(!ts->tick_stopped)) {
-		hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
+	if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART))
 		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
-	}
-
 }
 
-static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
+static inline void tick_nohz_activate(struct tick_sched *ts)
 {
 	if (!tick_nohz_enabled)
 		return;
-	ts->nohz_mode = mode;
+	tick_sched_flag_set(ts, TS_FLAG_NOHZ);
 	/* One update is enough */
 	if (!test_and_set_bit(0, &tick_nohz_active))
 		timers_update_nohz();
@@ -1433,9 +1496,6 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
  */
 static void tick_nohz_switch_to_nohz(void)
 {
-	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
-	ktime_t next;
-
 	if (!tick_nohz_enabled)
 		return;
 
@@ -1444,16 +1504,9 @@ static void tick_nohz_switch_to_nohz(void)
 
 	/*
 	 * Recycle the hrtimer in 'ts', so we can share the
-	 * hrtimer_forward_now() function with the highres code.
+	 * highres code.
 	 */
-	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	/* Get the next period */
-	next = tick_init_jiffy_update();
-
-	hrtimer_set_expires(&ts->sched_timer, next);
-	hrtimer_forward_now(&ts->sched_timer, TICK_NSEC);
-	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
-	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
+	tick_setup_sched_timer(false);
 }
 
 static inline void tick_nohz_irq_enter(void)
@@ -1461,10 +1514,10 @@ static inline void tick_nohz_irq_enter(void)
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
-	if (!ts->idle_active && !ts->tick_stopped)
+	if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE))
 		return;
 	now = ktime_get();
-	if (ts->idle_active)
+	if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))
 		tick_nohz_stop_idle(ts, now);
 	/*
 	 * If all CPUs are idle we may need to update a stale jiffies value.
@@ -1473,7 +1526,7 @@ static inline void tick_nohz_irq_enter(void)
 	 * rare case (typically stop machine). So we must make sure we have a
 	 * last resort.
 	 */
-	if (ts->tick_stopped)
+	if (tick_sched_flag_test(ts, TS_FLAG_STOPPED))
 		tick_nohz_update_jiffies(now);
 }
 
@@ -1481,7 +1534,7 @@ static inline void tick_nohz_irq_enter(void)
 
 static inline void tick_nohz_switch_to_nohz(void) { }
 static inline void tick_nohz_irq_enter(void) { }
-static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
+static inline void tick_nohz_activate(struct tick_sched *ts) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
@@ -1494,45 +1547,6 @@ void tick_irq_enter(void)
 	tick_nohz_irq_enter();
 }
 
-/*
- * High resolution timer specific code
- */
-#ifdef CONFIG_HIGH_RES_TIMERS
-/*
- * We rearm the timer until we get disabled by the idle code.
- * Called with interrupts disabled.
- */
-static enum hrtimer_restart tick_nohz_highres_handler(struct hrtimer *timer)
-{
-	struct tick_sched *ts =
-		container_of(timer, struct tick_sched, sched_timer);
-	struct pt_regs *regs = get_irq_regs();
-	ktime_t now = ktime_get();
-
-	tick_sched_do_timer(ts, now);
-
-	/*
-	 * Do not call when we are not in IRQ context and have
-	 * no valid 'regs' pointer
-	 */
-	if (regs)
-		tick_sched_handle(ts, regs);
-	else
-		ts->next_tick = 0;
-
-	/*
-	 * In dynticks mode, tick reprogram is deferred:
-	 * - to the idle task if in dynticks-idle
-	 * - to IRQ exit if in full-dynticks.
-	 */
-	if (unlikely(ts->tick_stopped))
-		return HRTIMER_NORESTART;
-
-	hrtimer_forward(timer, now, TICK_NSEC);
-
-	return HRTIMER_RESTART;
-}
-
 static int sched_skew_tick;
 
 static int __init skew_tick(char *str)
@@ -1545,15 +1559,19 @@ early_param("skew_tick", skew_tick);
 
 /**
  * tick_setup_sched_timer - setup the tick emulation timer
+ * @mode: tick_nohz_mode to setup for
  */
-void tick_setup_sched_timer(void)
+void tick_setup_sched_timer(bool hrtimer)
 {
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
-	ktime_t now = ktime_get();
 
 	/* Emulate tick processing via per-CPU hrtimers: */
 	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
-	ts->sched_timer.function = tick_nohz_highres_handler;
+
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) {
+		tick_sched_flag_set(ts, TS_FLAG_HIGHRES);
+		ts->sched_timer.function = tick_nohz_handler;
+	}
 
 	/* Get the next period (per-CPU) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
@@ -1566,23 +1584,35 @@ void tick_setup_sched_timer(void)
 		hrtimer_add_expires_ns(&ts->sched_timer, offset);
 	}
 
-	hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
-	hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD);
-	tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
+	hrtimer_forward_now(&ts->sched_timer, TICK_NSEC);
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer)
+		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD);
+	else
+		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+	tick_nohz_activate(ts);
 }
-#endif /* HIGH_RES_TIMERS */
 
-#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
-void tick_cancel_sched_timer(int cpu)
+/*
+ * Shut down the tick and make sure the CPU won't try to retake the timekeeping
+ * duty before disabling IRQs in idle for the last time.
+ */
+void tick_sched_timer_dying(int cpu)
 {
+	struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct clock_event_device *dev = td->evtdev;
 	ktime_t idle_sleeptime, iowait_sleeptime;
 	unsigned long idle_calls, idle_sleeps;
 
-# ifdef CONFIG_HIGH_RES_TIMERS
-	if (ts->sched_timer.base)
-		hrtimer_cancel(&ts->sched_timer);
-# endif
+	/* This must happen before hrtimers are migrated! */
+	tick_sched_timer_cancel(ts);
+
+	/*
+	 * If the clockevents doesn't support CLOCK_EVT_STATE_ONESHOT_STOPPED,
+	 * make sure not to call low-res tick handler.
+	 */
+	if (tick_sched_flag_test(ts, TS_FLAG_NOHZ))
+		dev->event_handler = clockevents_handle_noop;
 
 	idle_sleeptime = ts->idle_sleeptime;
 	iowait_sleeptime = ts->iowait_sleeptime;
@@ -1594,7 +1624,6 @@ void tick_cancel_sched_timer(int cpu)
 	ts->idle_calls = idle_calls;
 	ts->idle_sleeps = idle_sleeps;
 }
-#endif
 
 /*
  * Async notification about clocksource changes
@@ -1632,7 +1661,7 @@ int tick_check_oneshot_change(int allow_nohz)
 	if (!test_and_clear_bit(0, &ts->check_clocks))
 		return 0;
 
-	if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
+	if (tick_sched_flag_test(ts, TS_FLAG_NOHZ))
 		return 0;
 
 	if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available())
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 5ed5a9d41d5a..e11c4dc65bcb 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -14,20 +14,26 @@ struct tick_device {
 	enum tick_device_mode mode;
 };
 
-enum tick_nohz_mode {
-	NOHZ_MODE_INACTIVE,
-	NOHZ_MODE_LOWRES,
-	NOHZ_MODE_HIGHRES,
-};
+/* The CPU is in the tick idle mode */
+#define TS_FLAG_INIDLE		BIT(0)
+/* The idle tick has been stopped */
+#define TS_FLAG_STOPPED		BIT(1)
+/*
+ * Indicator that the CPU is actively in the tick idle mode;
+ * it is reset during irq handling phases.
+ */
+#define TS_FLAG_IDLE_ACTIVE	BIT(2)
+/* CPU was the last one doing do_timer before going idle */
+#define TS_FLAG_DO_TIMER_LAST	BIT(3)
+/* NO_HZ is enabled */
+#define TS_FLAG_NOHZ		BIT(4)
+/* High resolution tick mode */
+#define TS_FLAG_HIGHRES		BIT(5)
 
 /**
  * struct tick_sched - sched tick emulation and no idle tick control/stats
  *
- * @inidle:		Indicator that the CPU is in the tick idle mode
- * @tick_stopped:	Indicator that the idle tick has been stopped
- * @idle_active:	Indicator that the CPU is actively in the tick idle mode;
- *			it is reset during irq handling phases.
- * @do_timer_last:	CPU was the last one doing do_timer before going idle
+ * @flags:		State flags gathering the TS_FLAG_* features
  * @got_idle_tick:	Tick timer function has run with @inidle set
  * @stalled_jiffies:	Number of stalled jiffies detected across ticks
  * @last_tick_jiffies:	Value of jiffies seen on last tick
@@ -57,11 +63,7 @@ enum tick_nohz_mode {
  */
 struct tick_sched {
 	/* Common flags */
-	unsigned int			inidle		: 1;
-	unsigned int			tick_stopped	: 1;
-	unsigned int			idle_active	: 1;
-	unsigned int			do_timer_last	: 1;
-	unsigned int			got_idle_tick	: 1;
+	unsigned long			flags;
 
 	/* Tick handling: jiffies stall check */
 	unsigned int			stalled_jiffies;
@@ -73,13 +75,13 @@ struct tick_sched {
 	ktime_t				next_tick;
 	unsigned long			idle_jiffies;
 	ktime_t				idle_waketime;
+	unsigned int			got_idle_tick;
 
 	/* Idle entry */
 	seqcount_t			idle_sleeptime_seq;
 	ktime_t				idle_entrytime;
 
 	/* Tick stop */
-	enum tick_nohz_mode		nohz_mode;
 	unsigned long			last_jiffies;
 	u64				timer_expires_base;
 	u64				timer_expires;
@@ -102,11 +104,11 @@ struct tick_sched {
 
 extern struct tick_sched *tick_get_tick_sched(int cpu);
 
-extern void tick_setup_sched_timer(void);
-#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
-extern void tick_cancel_sched_timer(int cpu);
+extern void tick_setup_sched_timer(bool hrtimer);
+#if defined CONFIG_TICK_ONESHOT
+extern void tick_sched_timer_dying(int cpu);
 #else
-static inline void tick_cancel_sched_timer(int cpu) { }
+static inline void tick_sched_timer_dying(int cpu) { }
 #endif
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c
index ca058c8af6ba..3e5d422dd15c 100644
--- a/kernel/time/time_test.c
+++ b/kernel/time/time_test.c
@@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test)
 
 		days = div_s64(secs, 86400);
 
-		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \
+		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \
 			year, month, mdday, yday, days
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 266d02809dbb..b58dffc58a8f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1180,13 +1180,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 }
 
 /*
- * cycle_between - true if test occurs chronologically between before and after
+ * timestamp_in_interval - true if ts is chronologically in [start, end]
+ *
+ * True if ts occurs chronologically at or after start, and before or at end.
  */
-static bool cycle_between(u64 before, u64 test, u64 after)
+static bool timestamp_in_interval(u64 start, u64 end, u64 ts)
 {
-	if (test > before && test < after)
+	if (ts >= start && ts <= end)
 		return true;
-	if (test < before && before > after)
+	if (start > end && (ts >= start || ts <= end))
 		return true;
 	return false;
 }
@@ -1232,11 +1234,12 @@ int get_device_system_crosststamp(int (*get_time_fn)
 			return ret;
 
 		/*
-		 * Verify that the clocksource associated with the captured
-		 * system counter value is the same as the currently installed
-		 * timekeeper clocksource
+		 * Verify that the clocksource ID associated with the captured
+		 * system counter value is the same as for the currently
+		 * installed timekeeper clocksource
 		 */
-		if (tk->tkr_mono.clock != system_counterval.cs)
+		if (system_counterval.cs_id == CSID_GENERIC ||
+		    tk->tkr_mono.clock->id != system_counterval.cs_id)
 			return -ENODEV;
 		cycles = system_counterval.cycles;
 
@@ -1246,7 +1249,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		 */
 		now = tk_clock_read(&tk->tkr_mono);
 		interval_start = tk->tkr_mono.cycle_last;
-		if (!cycle_between(interval_start, cycles, now)) {
+		if (!timestamp_in_interval(interval_start, now, cycles)) {
 			clock_was_set_seq = tk->clock_was_set_seq;
 			cs_was_changed_seq = tk->cs_was_changed_seq;
 			cycles = interval_start;
@@ -1259,10 +1262,8 @@ int get_device_system_crosststamp(int (*get_time_fn)
 				      tk_core.timekeeper.offs_real);
 		base_raw = tk->tkr_raw.base;
 
-		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono,
-						     system_counterval.cycles);
-		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw,
-						    system_counterval.cycles);
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
 	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
@@ -1277,13 +1278,13 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		bool discontinuity;
 
 		/*
-		 * Check that the counter value occurs after the provided
+		 * Check that the counter value is not before the provided
 		 * history reference and that the history doesn't cross a
 		 * clocksource change
 		 */
 		if (!history_begin ||
-		    !cycle_between(history_begin->cycles,
-				   system_counterval.cycles, cycles) ||
+		    !timestamp_in_interval(history_begin->cycles,
+					   cycles, system_counterval.cycles) ||
 		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
 			return -EINVAL;
 		partial_history_cycles = cycles - system_counterval.cycles;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 352b161113cd..e69e75d3858c 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -53,6 +53,7 @@
 #include <asm/io.h>
 
 #include "tick-internal.h"
+#include "timer_migration.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
@@ -187,15 +188,66 @@ EXPORT_SYMBOL(jiffies_64);
 #define WHEEL_SIZE	(LVL_SIZE * LVL_DEPTH)
 
 #ifdef CONFIG_NO_HZ_COMMON
-# define NR_BASES	2
-# define BASE_STD	0
-# define BASE_DEF	1
+/*
+ * If multiple bases need to be locked, use the base ordering for lock
+ * nesting, i.e. lowest number first.
+ */
+# define NR_BASES	3
+# define BASE_LOCAL	0
+# define BASE_GLOBAL	1
+# define BASE_DEF	2
 #else
 # define NR_BASES	1
-# define BASE_STD	0
+# define BASE_LOCAL	0
+# define BASE_GLOBAL	0
 # define BASE_DEF	0
 #endif
 
+/**
+ * struct timer_base - Per CPU timer base (number of base depends on config)
+ * @lock:		Lock protecting the timer_base
+ * @running_timer:	When expiring timers, the lock is dropped. To make
+ *			sure not to race agains deleting/modifying a
+ *			currently running timer, the pointer is set to the
+ *			timer, which expires at the moment. If no timer is
+ *			running, the pointer is NULL.
+ * @expiry_lock:	PREEMPT_RT only: Lock is taken in softirq around
+ *			timer expiry callback execution and when trying to
+ *			delete a running timer and it wasn't successful in
+ *			the first glance. It prevents priority inversion
+ *			when callback was preempted on a remote CPU and a
+ *			caller tries to delete the running timer. It also
+ *			prevents a life lock, when the task which tries to
+ *			delete a timer preempted the softirq thread which
+ *			is running the timer callback function.
+ * @timer_waiters:	PREEMPT_RT only: Tells, if there is a waiter
+ *			waiting for the end of the timer callback function
+ *			execution.
+ * @clk:		clock of the timer base; is updated before enqueue
+ *			of a timer; during expiry, it is 1 offset ahead of
+ *			jiffies to avoid endless requeuing to current
+ *			jiffies
+ * @next_expiry:	expiry value of the first timer; it is updated when
+ *			finding the next timer and during enqueue; the
+ *			value is not valid, when next_expiry_recalc is set
+ * @cpu:		Number of CPU the timer base belongs to
+ * @next_expiry_recalc: States, whether a recalculation of next_expiry is
+ *			required. Value is set true, when a timer was
+ *			deleted.
+ * @is_idle:		Is set, when timer_base is idle. It is triggered by NOHZ
+ *			code. This state is only used in standard
+ *			base. Deferrable timers, which are enqueued remotely
+ *			never wake up an idle CPU. So no matter of supporting it
+ *			for this base.
+ * @timers_pending:	Is set, when a timer is pending in the base. It is only
+ *			reliable when next_expiry_recalc is not set.
+ * @pending_map:	bitmap of the timer wheel; each bit reflects a
+ *			bucket of the wheel. When a bit is set, at least a
+ *			single timer is enqueued in the related bucket.
+ * @vectors:		Array of lists; Each array member reflects a bucket
+ *			of the timer wheel. The list contains all timers
+ *			which are enqueued into a specific bucket.
+ */
 struct timer_base {
 	raw_spinlock_t		lock;
 	struct timer_list	*running_timer;
@@ -583,11 +635,16 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 
 	/*
 	 * We might have to IPI the remote CPU if the base is idle and the
-	 * timer is not deferrable. If the other CPU is on the way to idle
-	 * then it can't set base->is_idle as we hold the base lock:
+	 * timer is pinned. If it is a non pinned timer, it is only queued
+	 * on the remote CPU, when timer was running during queueing. Then
+	 * everything is handled by remote CPU anyway. If the other CPU is
+	 * on the way to idle then it can't set base->is_idle as we hold
+	 * the base lock:
 	 */
-	if (base->is_idle)
+	if (base->is_idle) {
+		WARN_ON_ONCE(!(timer->flags & TIMER_PINNED));
 		wake_up_nohz_cpu(base->cpu);
+	}
 }
 
 /*
@@ -899,7 +956,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base,
 
 static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 {
-	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);
+	int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
+	struct timer_base *base;
+
+	base = per_cpu_ptr(&timer_bases[index], cpu);
 
 	/*
 	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
@@ -912,7 +972,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
 
 static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL;
+	struct timer_base *base;
+
+	base = this_cpu_ptr(&timer_bases[index]);
 
 	/*
 	 * If the timer is deferrable and NO_HZ_COMMON is set then we need
@@ -928,17 +991,6 @@ static inline struct timer_base *get_timer_base(u32 tflags)
 	return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);
 }
 
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-	if (static_branch_likely(&timers_migration_enabled) &&
-	    !(tflags & TIMER_PINNED))
-		return get_timer_cpu_base(tflags, get_nohz_timer_target());
-#endif
-	return get_timer_this_cpu_base(tflags);
-}
-
 static inline void __forward_timer_base(struct timer_base *base,
 					unsigned long basej)
 {
@@ -1093,7 +1145,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 	if (!ret && (options & MOD_TIMER_PENDING_ONLY))
 		goto out_unlock;
 
-	new_base = get_target_base(base, timer->flags);
+	new_base = get_timer_this_cpu_base(timer->flags);
 
 	if (base != new_base) {
 		/*
@@ -1246,11 +1298,48 @@ void add_timer(struct timer_list *timer)
 EXPORT_SYMBOL(add_timer);
 
 /**
+ * add_timer_local() - Start a timer on the local CPU
+ * @timer:	The timer to be started
+ *
+ * Same as add_timer() except that the timer flag TIMER_PINNED is set.
+ *
+ * See add_timer() for further details.
+ */
+void add_timer_local(struct timer_list *timer)
+{
+	if (WARN_ON_ONCE(timer_pending(timer)))
+		return;
+	timer->flags |= TIMER_PINNED;
+	__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
+}
+EXPORT_SYMBOL(add_timer_local);
+
+/**
+ * add_timer_global() - Start a timer without TIMER_PINNED flag set
+ * @timer:	The timer to be started
+ *
+ * Same as add_timer() except that the timer flag TIMER_PINNED is unset.
+ *
+ * See add_timer() for further details.
+ */
+void add_timer_global(struct timer_list *timer)
+{
+	if (WARN_ON_ONCE(timer_pending(timer)))
+		return;
+	timer->flags &= ~TIMER_PINNED;
+	__mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING);
+}
+EXPORT_SYMBOL(add_timer_global);
+
+/**
  * add_timer_on - Start a timer on a particular CPU
  * @timer:	The timer to be started
  * @cpu:	The CPU to start it on
  *
- * Same as add_timer() except that it starts the timer on the given CPU.
+ * Same as add_timer() except that it starts the timer on the given CPU and
+ * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in
+ * the next round, add_timer_global() should be used instead as it unsets
+ * the TIMER_PINNED flag.
  *
  * See add_timer() for further details.
  */
@@ -1264,6 +1353,9 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	if (WARN_ON_ONCE(timer_pending(timer)))
 		return;
 
+	/* Make sure timer flags have TIMER_PINNED flag set */
+	timer->flags |= TIMER_PINNED;
+
 	new_base = get_timer_cpu_base(timer->flags, cpu);
 
 	/*
@@ -1911,71 +2003,350 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires)
 	return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC;
 }
 
+static unsigned long next_timer_interrupt(struct timer_base *base,
+					  unsigned long basej)
+{
+	if (base->next_expiry_recalc)
+		next_expiry_recalc(base);
+
+	/*
+	 * Move next_expiry for the empty base into the future to prevent an
+	 * unnecessary raise of the timer softirq when the next_expiry value
+	 * will be reached even if there is no timer pending.
+	 *
+	 * This update is also required to make timer_base::next_expiry values
+	 * easy comparable to find out which base holds the first pending timer.
+	 */
+	if (!base->timers_pending)
+		base->next_expiry = basej + NEXT_TIMER_MAX_DELTA;
+
+	return base->next_expiry;
+}
+
+static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem,
+						struct timer_base *base_local,
+						struct timer_base *base_global,
+						struct timer_events *tevt)
+{
+	unsigned long nextevt, nextevt_local, nextevt_global;
+	bool local_first;
+
+	nextevt_local = next_timer_interrupt(base_local, basej);
+	nextevt_global = next_timer_interrupt(base_global, basej);
+
+	local_first = time_before_eq(nextevt_local, nextevt_global);
+
+	nextevt = local_first ? nextevt_local : nextevt_global;
+
+	/*
+	 * If the @nextevt is at max. one tick away, use @nextevt and store
+	 * it in the local expiry value. The next global event is irrelevant in
+	 * this case and can be left as KTIME_MAX.
+	 */
+	if (time_before_eq(nextevt, basej + 1)) {
+		/* If we missed a tick already, force 0 delta */
+		if (time_before(nextevt, basej))
+			nextevt = basej;
+		tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC;
+
+		/*
+		 * This is required for the remote check only but it doesn't
+		 * hurt, when it is done for both call sites:
+		 *
+		 * * The remote callers will only take care of the global timers
+		 *   as local timers will be handled by CPU itself. When not
+		 *   updating tevt->global with the already missed first global
+		 *   timer, it is possible that it will be missed completely.
+		 *
+		 * * The local callers will ignore the tevt->global anyway, when
+		 *   nextevt is max. one tick away.
+		 */
+		if (!local_first)
+			tevt->global = tevt->local;
+		return nextevt;
+	}
+
+	/*
+	 * Update tevt.* values:
+	 *
+	 * If the local queue expires first, then the global event can be
+	 * ignored. If the global queue is empty, nothing to do either.
+	 */
+	if (!local_first && base_global->timers_pending)
+		tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC;
+
+	if (base_local->timers_pending)
+		tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC;
+
+	return nextevt;
+}
+
+# ifdef CONFIG_SMP
 /**
- * get_next_timer_interrupt - return the time (clock mono) of the next timer
+ * fetch_next_timer_interrupt_remote() - Store next timers into @tevt
  * @basej:	base time jiffies
  * @basem:	base time clock monotonic
+ * @tevt:	Pointer to the storage for the expiry values
+ * @cpu:	Remote CPU
+ *
+ * Stores the next pending local and global timer expiry values in the
+ * struct pointed to by @tevt. If a queue is empty the corresponding
+ * field is set to KTIME_MAX. If local event expires before global
+ * event, global event is set to KTIME_MAX as well.
  *
- * Returns the tick aligned clock monotonic time of the next pending
- * timer or KTIME_MAX if no timer is pending.
+ * Caller needs to make sure timer base locks are held (use
+ * timer_lock_remote_bases() for this purpose).
  */
-u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
+void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem,
+				       struct timer_events *tevt,
+				       unsigned int cpu)
+{
+	struct timer_base *base_local, *base_global;
+
+	/* Preset local / global events */
+	tevt->local = tevt->global = KTIME_MAX;
+
+	base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
+	base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
+
+	lockdep_assert_held(&base_local->lock);
+	lockdep_assert_held(&base_global->lock);
+
+	fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt);
+}
+
+/**
+ * timer_unlock_remote_bases - unlock timer bases of cpu
+ * @cpu:	Remote CPU
+ *
+ * Unlocks the remote timer bases.
+ */
+void timer_unlock_remote_bases(unsigned int cpu)
+	__releases(timer_bases[BASE_LOCAL]->lock)
+	__releases(timer_bases[BASE_GLOBAL]->lock)
+{
+	struct timer_base *base_local, *base_global;
+
+	base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
+	base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
+
+	raw_spin_unlock(&base_global->lock);
+	raw_spin_unlock(&base_local->lock);
+}
+
+/**
+ * timer_lock_remote_bases - lock timer bases of cpu
+ * @cpu:	Remote CPU
+ *
+ * Locks the remote timer bases.
+ */
+void timer_lock_remote_bases(unsigned int cpu)
+	__acquires(timer_bases[BASE_LOCAL]->lock)
+	__acquires(timer_bases[BASE_GLOBAL]->lock)
+{
+	struct timer_base *base_local, *base_global;
+
+	base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu);
+	base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
+
+	lockdep_assert_irqs_disabled();
+
+	raw_spin_lock(&base_local->lock);
+	raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
+}
+
+/**
+ * timer_base_is_idle() - Return whether timer base is set idle
+ *
+ * Returns value of local timer base is_idle value.
+ */
+bool timer_base_is_idle(void)
+{
+	return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle);
+}
+
+static void __run_timer_base(struct timer_base *base);
+
+/**
+ * timer_expire_remote() - expire global timers of cpu
+ * @cpu:	Remote CPU
+ *
+ * Expire timers of global base of remote CPU.
+ */
+void timer_expire_remote(unsigned int cpu)
+{
+	struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu);
+
+	__run_timer_base(base);
+}
+
+static void timer_use_tmigr(unsigned long basej, u64 basem,
+			    unsigned long *nextevt, bool *tick_stop_path,
+			    bool timer_base_idle, struct timer_events *tevt)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
-	unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA;
-	u64 expires = KTIME_MAX;
-	bool was_idle;
+	u64 next_tmigr;
+
+	if (timer_base_idle)
+		next_tmigr = tmigr_cpu_new_timer(tevt->global);
+	else if (tick_stop_path)
+		next_tmigr = tmigr_cpu_deactivate(tevt->global);
+	else
+		next_tmigr = tmigr_quick_check(tevt->global);
 
 	/*
-	 * Pretend that there is no timer pending if the cpu is offline.
-	 * Possible pending timers will be migrated later to an active cpu.
+	 * If the CPU is the last going idle in timer migration hierarchy, make
+	 * sure the CPU will wake up in time to handle remote timers.
+	 * next_tmigr == KTIME_MAX if other CPUs are still active.
 	 */
-	if (cpu_is_offline(smp_processor_id()))
-		return expires;
+	if (next_tmigr < tevt->local) {
+		u64 tmp;
 
-	raw_spin_lock(&base->lock);
-	if (base->next_expiry_recalc)
-		next_expiry_recalc(base);
+		/* If we missed a tick already, force 0 delta */
+		if (next_tmigr < basem)
+			next_tmigr = basem;
+
+		tmp = div_u64(next_tmigr - basem, TICK_NSEC);
+
+		*nextevt = basej + (unsigned long)tmp;
+		tevt->local = next_tmigr;
+	}
+}
+# else
+static void timer_use_tmigr(unsigned long basej, u64 basem,
+			    unsigned long *nextevt, bool *tick_stop_path,
+			    bool timer_base_idle, struct timer_events *tevt)
+{
+	/*
+	 * Make sure first event is written into tevt->local to not miss a
+	 * timer on !SMP systems.
+	 */
+	tevt->local = min_t(u64, tevt->local, tevt->global);
+}
+# endif /* CONFIG_SMP */
+
+static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
+					     bool *idle)
+{
+	struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX };
+	struct timer_base *base_local, *base_global;
+	unsigned long nextevt;
+	bool idle_is_possible;
+
+	/*
+	 * When the CPU is offline, the tick is cancelled and nothing is supposed
+	 * to try to stop it.
+	 */
+	if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) {
+		if (idle)
+			*idle = true;
+		return tevt.local;
+	}
+
+	base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
+	base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]);
+
+	raw_spin_lock(&base_local->lock);
+	raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING);
+
+	nextevt = fetch_next_timer_interrupt(basej, basem, base_local,
+					     base_global, &tevt);
+
+	/*
+	 * If the next event is only one jiffie ahead there is no need to call
+	 * timer migration hierarchy related functions. The value for the next
+	 * global timer in @tevt struct equals then KTIME_MAX. This is also
+	 * true, when the timer base is idle.
+	 *
+	 * The proper timer migration hierarchy function depends on the callsite
+	 * and whether timer base is idle or not. @nextevt will be updated when
+	 * this CPU needs to handle the first timer migration hierarchy
+	 * event. See timer_use_tmigr() for detailed information.
+	 */
+	idle_is_possible = time_after(nextevt, basej + 1);
+	if (idle_is_possible)
+		timer_use_tmigr(basej, basem, &nextevt, idle,
+				base_local->is_idle, &tevt);
 
 	/*
 	 * We have a fresh next event. Check whether we can forward the
 	 * base.
 	 */
-	__forward_timer_base(base, basej);
+	__forward_timer_base(base_local, basej);
+	__forward_timer_base(base_global, basej);
 
-	if (base->timers_pending) {
-		nextevt = base->next_expiry;
+	/*
+	 * Set base->is_idle only when caller is timer_base_try_to_set_idle()
+	 */
+	if (idle) {
+		/*
+		 * Bases are idle if the next event is more than a tick
+		 * away. Caution: @nextevt could have changed by enqueueing a
+		 * global timer into timer migration hierarchy. Therefore a new
+		 * check is required here.
+		 *
+		 * If the base is marked idle then any timer add operation must
+		 * forward the base clk itself to keep granularity small. This
+		 * idle logic is only maintained for the BASE_LOCAL and
+		 * BASE_GLOBAL base, deferrable timers may still see large
+		 * granularity skew (by design).
+		 */
+		if (!base_local->is_idle && time_after(nextevt, basej + 1)) {
+			base_local->is_idle = true;
+			trace_timer_base_idle(true, base_local->cpu);
+		}
+		*idle = base_local->is_idle;
 
-		/* If we missed a tick already, force 0 delta */
-		if (time_before(nextevt, basej))
-			nextevt = basej;
-		expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
-	} else {
 		/*
-		 * Move next_expiry for the empty base into the future to
-		 * prevent a unnecessary raise of the timer softirq when the
-		 * next_expiry value will be reached even if there is no timer
-		 * pending.
+		 * When timer base is not set idle, undo the effect of
+		 * tmigr_cpu_deactivate() to prevent inconsitent states - active
+		 * timer base but inactive timer migration hierarchy.
+		 *
+		 * When timer base was already marked idle, nothing will be
+		 * changed here.
 		 */
-		base->next_expiry = nextevt;
+		if (!base_local->is_idle && idle_is_possible)
+			tmigr_cpu_activate();
 	}
 
-	/*
-	 * Base is idle if the next event is more than a tick away.
-	 *
-	 * If the base is marked idle then any timer add operation must forward
-	 * the base clk itself to keep granularity small. This idle logic is
-	 * only maintained for the BASE_STD base, deferrable timers may still
-	 * see large granularity skew (by design).
-	 */
-	was_idle = base->is_idle;
-	base->is_idle = time_after(nextevt, basej + 1);
-	if (was_idle != base->is_idle)
-		trace_timer_base_idle(base->is_idle, base->cpu);
+	raw_spin_unlock(&base_global->lock);
+	raw_spin_unlock(&base_local->lock);
 
-	raw_spin_unlock(&base->lock);
+	return cmp_next_hrtimer_event(basem, tevt.local);
+}
 
-	return cmp_next_hrtimer_event(basem, expires);
+/**
+ * get_next_timer_interrupt() - return the time (clock mono) of the next timer
+ * @basej:	base time jiffies
+ * @basem:	base time clock monotonic
+ *
+ * Returns the tick aligned clock monotonic time of the next pending timer or
+ * KTIME_MAX if no timer is pending. If timer of global base was queued into
+ * timer migration hierarchy, first global timer is not taken into account. If
+ * it was the last CPU of timer migration hierarchy going idle, first global
+ * event is taken into account.
+ */
+u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
+{
+	return __get_next_timer_interrupt(basej, basem, NULL);
+}
+
+/**
+ * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases
+ * @basej:	base time jiffies
+ * @basem:	base time clock monotonic
+ * @idle:	pointer to store the value of timer_base->is_idle on return;
+ *		*idle contains the information whether tick was already stopped
+ *
+ * Returns the tick aligned clock monotonic time of the next pending timer or
+ * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is
+ * returned as well.
+ */
+u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle)
+{
+	if (*idle)
+		return KTIME_MAX;
+
+	return __get_next_timer_interrupt(basej, basem, idle);
 }
 
 /**
@@ -1985,18 +2356,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
  */
 void timer_clear_idle(void)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
-
 	/*
-	 * We do this unlocked. The worst outcome is a remote enqueue sending
-	 * a pointless IPI, but taking the lock would just make the window for
-	 * sending the IPI a few instructions smaller for the cost of taking
-	 * the lock in the exit from idle path.
+	 * We do this unlocked. The worst outcome is a remote pinned timer
+	 * enqueue sending a pointless IPI, but taking the lock would just
+	 * make the window for sending the IPI a few instructions smaller
+	 * for the cost of taking the lock in the exit from idle
+	 * path. Required for BASE_LOCAL only.
 	 */
-	if (base->is_idle) {
-		base->is_idle = false;
-		trace_timer_base_idle(false, smp_processor_id());
-	}
+	__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);
+	trace_timer_base_idle(false, smp_processor_id());
+
+	/* Activate without holding the timer_base->lock */
+	tmigr_cpu_activate();
 }
 #endif
 
@@ -2009,11 +2380,10 @@ static inline void __run_timers(struct timer_base *base)
 	struct hlist_head heads[LVL_DEPTH];
 	int levels;
 
-	if (time_before(jiffies, base->next_expiry))
-		return;
+	lockdep_assert_held(&base->lock);
 
-	timer_base_lock_expiry(base);
-	raw_spin_lock_irq(&base->lock);
+	if (base->running_timer)
+		return;
 
 	while (time_after_eq(jiffies, base->clk) &&
 	       time_after_eq(jiffies, base->next_expiry)) {
@@ -2037,20 +2407,40 @@ static inline void __run_timers(struct timer_base *base)
 		while (levels--)
 			expire_timers(base, heads + levels);
 	}
+}
+
+static void __run_timer_base(struct timer_base *base)
+{
+	if (time_before(jiffies, base->next_expiry))
+		return;
+
+	timer_base_lock_expiry(base);
+	raw_spin_lock_irq(&base->lock);
+	__run_timers(base);
 	raw_spin_unlock_irq(&base->lock);
 	timer_base_unlock_expiry(base);
 }
 
+static void run_timer_base(int index)
+{
+	struct timer_base *base = this_cpu_ptr(&timer_bases[index]);
+
+	__run_timer_base(base);
+}
+
 /*
  * This function runs timers and the timer-tq in bottom half context.
  */
 static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	run_timer_base(BASE_LOCAL);
+	if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) {
+		run_timer_base(BASE_GLOBAL);
+		run_timer_base(BASE_DEF);
 
-	__run_timers(base);
-	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
-		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
+		if (is_timers_nohz_active())
+			tmigr_handle_remote();
+	}
 }
 
 /*
@@ -2058,19 +2448,18 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
  */
 static void run_local_timers(void)
 {
-	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
+	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]);
 
 	hrtimer_run_queues();
-	/* Raise the softirq only if required. */
-	if (time_before(jiffies, base->next_expiry)) {
-		if (!IS_ENABLED(CONFIG_NO_HZ_COMMON))
-			return;
-		/* CPU is awake, so check the deferrable base. */
-		base++;
-		if (time_before(jiffies, base->next_expiry))
+
+	for (int i = 0; i < NR_BASES; i++, base++) {
+		/* Raise the softirq only if required. */
+		if (time_after_eq(jiffies, base->next_expiry) ||
+		    (i == BASE_DEF && tmigr_requires_handle_remote())) {
+			raise_softirq(TIMER_SOFTIRQ);
 			return;
+		}
 	}
-	raise_softirq(TIMER_SOFTIRQ);
 }
 
 /*
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ed7d6ad694fb..1c311c46da50 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -147,11 +147,15 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 # define P_ns(x) \
 	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
 		   (unsigned long long)(ktime_to_ns(ts->x)))
+# define P_flag(x, f)			    \
+	SEQ_printf(m, "  .%-15s: %d\n", #x, !!(ts->flags & (f)))
+
 	{
 		struct tick_sched *ts = tick_get_tick_sched(cpu);
-		P(nohz_mode);
+		P_flag(nohz, TS_FLAG_NOHZ);
+		P_flag(highres, TS_FLAG_HIGHRES);
 		P_ns(last_tick);
-		P(tick_stopped);
+		P_flag(tick_stopped, TS_FLAG_STOPPED);
 		P(idle_jiffies);
 		P(idle_calls);
 		P(idle_sleeps);
@@ -256,7 +260,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)
 
 static inline void timer_list_header(struct seq_file *m, u64 now)
 {
-	SEQ_printf(m, "Timer List Version: v0.9\n");
+	SEQ_printf(m, "Timer List Version: v0.10\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 	SEQ_printf(m, "\n");
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
new file mode 100644
index 000000000000..8f49b6b96dfd
--- /dev/null
+++ b/kernel/time/timer_migration.c
@@ -0,0 +1,1793 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Infrastructure for migratable timers
+ *
+ * Copyright(C) 2022 linutronix GmbH
+ */
+#include <linux/cpuhotplug.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/timerqueue.h>
+#include <trace/events/ipi.h>
+
+#include "timer_migration.h"
+#include "tick-internal.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/timer_migration.h>
+
+/*
+ * The timer migration mechanism is built on a hierarchy of groups. The
+ * lowest level group contains CPUs, the next level groups of CPU groups
+ * and so forth. The CPU groups are kept per node so for the normal case
+ * lock contention won't happen across nodes. Depending on the number of
+ * CPUs per node even the next level might be kept as groups of CPU groups
+ * per node and only the levels above cross the node topology.
+ *
+ * Example topology for a two node system with 24 CPUs each.
+ *
+ * LVL 2                           [GRP2:0]
+ *                              GRP1:0 = GRP1:M
+ *
+ * LVL 1            [GRP1:0]                      [GRP1:1]
+ *               GRP0:0 - GRP0:2               GRP0:3 - GRP0:5
+ *
+ * LVL 0  [GRP0:0]  [GRP0:1]  [GRP0:2]  [GRP0:3]  [GRP0:4]  [GRP0:5]
+ * CPUS     0-7       8-15      16-23     24-31     32-39     40-47
+ *
+ * The groups hold a timer queue of events sorted by expiry time. These
+ * queues are updated when CPUs go in idle. When they come out of idle
+ * ignore flag of events is set.
+ *
+ * Each group has a designated migrator CPU/group as long as a CPU/group is
+ * active in the group. This designated role is necessary to avoid that all
+ * active CPUs in a group try to migrate expired timers from other CPUs,
+ * which would result in massive lock bouncing.
+ *
+ * When a CPU is awake, it checks in it's own timer tick the group
+ * hierarchy up to the point where it is assigned the migrator role or if
+ * no CPU is active, it also checks the groups where no migrator is set
+ * (TMIGR_NONE).
+ *
+ * If it finds expired timers in one of the group queues it pulls them over
+ * from the idle CPU and runs the timer function. After that it updates the
+ * group and the parent groups if required.
+ *
+ * CPUs which go idle arm their CPU local timer hardware for the next local
+ * (pinned) timer event. If the next migratable timer expires after the
+ * next local timer or the CPU has no migratable timer pending then the
+ * CPU does not queue an event in the LVL0 group. If the next migratable
+ * timer expires before the next local timer then the CPU queues that timer
+ * in the LVL0 group. In both cases the CPU marks itself idle in the LVL0
+ * group.
+ *
+ * When CPU comes out of idle and when a group has at least a single active
+ * child, the ignore flag of the tmigr_event is set. This indicates, that
+ * the event is ignored even if it is still enqueued in the parent groups
+ * timer queue. It will be removed when touching the timer queue the next
+ * time. This spares locking in active path as the lock protects (after
+ * setup) only event information. For more information about locking,
+ * please read the section "Locking rules".
+ *
+ * If the CPU is the migrator of the group then it delegates that role to
+ * the next active CPU in the group or sets migrator to TMIGR_NONE when
+ * there is no active CPU in the group. This delegation needs to be
+ * propagated up the hierarchy so hand over from other leaves can happen at
+ * all hierarchy levels w/o doing a search.
+ *
+ * When the last CPU in the system goes idle, then it drops all migrator
+ * duties up to the top level of the hierarchy (LVL2 in the example). It
+ * then has to make sure, that it arms it's own local hardware timer for
+ * the earliest event in the system.
+ *
+ *
+ * Lifetime rules:
+ * ---------------
+ *
+ * The groups are built up at init time or when CPUs come online. They are
+ * not destroyed when a group becomes empty due to offlining. The group
+ * just won't participate in the hierarchy management anymore. Destroying
+ * groups would result in interesting race conditions which would just make
+ * the whole mechanism slow and complex.
+ *
+ *
+ * Locking rules:
+ * --------------
+ *
+ * For setting up new groups and handling events it's required to lock both
+ * child and parent group. The lock ordering is always bottom up. This also
+ * includes the per CPU locks in struct tmigr_cpu. For updating the migrator and
+ * active CPU/group information atomic_try_cmpxchg() is used instead and only
+ * the per CPU tmigr_cpu->lock is held.
+ *
+ * During the setup of groups tmigr_level_list is required. It is protected by
+ * @tmigr_mutex.
+ *
+ * When @timer_base->lock as well as tmigr related locks are required, the lock
+ * ordering is: first @timer_base->lock, afterwards tmigr related locks.
+ *
+ *
+ * Protection of the tmigr group state information:
+ * ------------------------------------------------
+ *
+ * The state information with the list of active children and migrator needs to
+ * be protected by a sequence counter. It prevents a race when updates in child
+ * groups are propagated in changed order. The state update is performed
+ * lockless and group wise. The following scenario describes what happens
+ * without updating the sequence counter:
+ *
+ * Therefore, let's take three groups and four CPUs (CPU2 and CPU3 as well
+ * as GRP0:1 will not change during the scenario):
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:0, GRP0:1
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = CPU0           migrator = CPU2
+ *           active   = CPU0           active   = CPU2
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             active      idle           active      idle
+ *
+ *
+ * 1. CPU0 goes idle. As the update is performed group wise, in the first step
+ *    only GRP0:0 is updated. The update of GRP1:0 is pending as CPU0 has to
+ *    walk the hierarchy.
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:0, GRP0:1
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *       --> migrator = TMIGR_NONE     migrator = CPU2
+ *       --> active   =                active   = CPU2
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *         --> idle        idle           active      idle
+ *
+ * 2. While CPU0 goes idle and continues to update the state, CPU1 comes out of
+ *    idle. CPU1 updates GRP0:0. The update for GRP1:0 is pending as CPU1 also
+ *    has to walk the hierarchy. Both CPUs (CPU0 and CPU1) now walk the
+ *    hierarchy to perform the needed update from their point of view. The
+ *    currently visible state looks the following:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:0, GRP0:1
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *       --> migrator = CPU1           migrator = CPU2
+ *       --> active   = CPU1           active   = CPU2
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle    --> active         active      idle
+ *
+ * 3. Here is the race condition: CPU1 managed to propagate its changes (from
+ *    step 2) through the hierarchy to GRP1:0 before CPU0 (step 1) did. The
+ *    active members of GRP1:0 remain unchanged after the update since it is
+ *    still valid from CPU1 current point of view:
+ *
+ *    LVL 1            [GRP1:0]
+ *                 --> migrator = GRP0:1
+ *                 --> active   = GRP0:0, GRP0:1
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = CPU1           migrator = CPU2
+ *           active   = CPU1           active   = CPU2
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        active         active      idle
+ *
+ * 4. Now CPU0 finally propagates its changes (from step 1) to GRP1:0.
+ *
+ *    LVL 1            [GRP1:0]
+ *                 --> migrator = GRP0:1
+ *                 --> active   = GRP0:1
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = CPU1           migrator = CPU2
+ *           active   = CPU1           active   = CPU2
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        active         active      idle
+ *
+ *
+ * The race of CPU0 vs. CPU1 led to an inconsistent state in GRP1:0. CPU1 is
+ * active and is correctly listed as active in GRP0:0. However GRP1:0 does not
+ * have GRP0:0 listed as active, which is wrong. The sequence counter has been
+ * added to avoid inconsistent states during updates. The state is updated
+ * atomically only if all members, including the sequence counter, match the
+ * expected value (compare-and-exchange).
+ *
+ * Looking back at the previous example with the addition of the sequence
+ * counter: The update as performed by CPU0 in step 4 will fail. CPU1 changed
+ * the sequence number during the update in step 3 so the expected old value (as
+ * seen by CPU0 before starting the walk) does not match.
+ *
+ * Prevent race between new event and last CPU going inactive
+ * ----------------------------------------------------------
+ *
+ * When the last CPU is going idle and there is a concurrent update of a new
+ * first global timer of an idle CPU, the group and child states have to be read
+ * while holding the lock in tmigr_update_events(). The following scenario shows
+ * what happens, when this is not done.
+ *
+ * 1. Only CPU2 is active:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:1
+ *                     next_expiry = KTIME_MAX
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = CPU2
+ *           active   =                active   = CPU2
+ *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           active      idle
+ *
+ * 2. Now CPU 2 goes idle (and has no global timer, that has to be handled) and
+ *    propagates that to GRP0:1:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:1
+ *                     next_expiry = KTIME_MAX
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE --> migrator = TMIGR_NONE
+ *           active   =            --> active   =
+ *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle       --> idle        idle
+ *
+ * 3. Now the idle state is propagated up to GRP1:0. As this is now the last
+ *    child going idle in top level group, the expiry of the next group event
+ *    has to be handed back to make sure no event is lost. As there is no event
+ *    enqueued, KTIME_MAX is handed back to CPU2.
+ *
+ *    LVL 1            [GRP1:0]
+ *                 --> migrator = TMIGR_NONE
+ *                 --> active   =
+ *                     next_expiry = KTIME_MAX
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
+ *           active   =                active   =
+ *           next_expiry = KTIME_MAX   next_expiry = KTIME_MAX
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle       --> idle        idle
+ *
+ * 4. CPU 0 has a new timer queued from idle and it expires at TIMER0. CPU0
+ *    propagates that to GRP0:0:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = TMIGR_NONE
+ *                     active   =
+ *                     next_expiry = KTIME_MAX
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
+ *           active   =                active   =
+ *       --> next_expiry = TIMER0      next_expiry  = KTIME_MAX
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           idle        idle
+ *
+ * 5. GRP0:0 is not active, so the new timer has to be propagated to
+ *    GRP1:0. Therefore the GRP1:0 state has to be read. When the stalled value
+ *    (from step 2) is read, the timer is enqueued into GRP1:0, but nothing is
+ *    handed back to CPU0, as it seems that there is still an active child in
+ *    top level group.
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = TMIGR_NONE
+ *                     active   =
+ *                 --> next_expiry = TIMER0
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = TMIGR_NONE
+ *           active   =                active   =
+ *           next_expiry = TIMER0      next_expiry  = KTIME_MAX
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           idle        idle
+ *
+ * This is prevented by reading the state when holding the lock (when a new
+ * timer has to be propagated from idle path)::
+ *
+ *   CPU2 (tmigr_inactive_up())          CPU0 (tmigr_new_timer_up())
+ *   --------------------------          ---------------------------
+ *   // step 3:
+ *   cmpxchg(&GRP1:0->state);
+ *   tmigr_update_events() {
+ *       spin_lock(&GRP1:0->lock);
+ *       // ... update events ...
+ *       // hand back first expiry when GRP1:0 is idle
+ *       spin_unlock(&GRP1:0->lock);
+ *       // ^^^ release state modification
+ *   }
+ *                                       tmigr_update_events() {
+ *                                           spin_lock(&GRP1:0->lock)
+ *                                           // ^^^ acquire state modification
+ *                                           group_state = atomic_read(&GRP1:0->state)
+ *                                           // .... update events ...
+ *                                           // hand back first expiry when GRP1:0 is idle
+ *                                           spin_unlock(&GRP1:0->lock) <3>
+ *                                           // ^^^ makes state visible for other
+ *                                           // callers of tmigr_new_timer_up()
+ *                                       }
+ *
+ * When CPU0 grabs the lock directly after cmpxchg, the first timer is reported
+ * back to CPU0 and also later on to CPU2. So no timer is missed. A concurrent
+ * update of the group state from active path is no problem, as the upcoming CPU
+ * will take care of the group events.
+ *
+ * Required event and timerqueue update after a remote expiry:
+ * -----------------------------------------------------------
+ *
+ * After expiring timers of a remote CPU, a walk through the hierarchy and
+ * update of events and timerqueues is required. It is obviously needed if there
+ * is a 'new' global timer but also if there is no new global timer but the
+ * remote CPU is still idle.
+ *
+ * 1. CPU0 and CPU1 are idle and have both a global timer expiring at the same
+ *    time. So both have an event enqueued in the timerqueue of GRP0:0. CPU3 is
+ *    also idle and has no global timer pending. CPU2 is the only active CPU and
+ *    thus also the migrator:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:1
+ *                 --> timerqueue = evt-GRP0:0
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = CPU2
+ *           active   =                active   = CPU2
+ *           groupevt.ignore = false   groupevt.ignore = true
+ *           groupevt.cpu = CPU0       groupevt.cpu =
+ *           timerqueue = evt-CPU0,    timerqueue =
+ *                        evt-CPU1
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           active      idle
+ *
+ * 2. CPU2 starts to expire remote timers. It starts with LVL0 group
+ *    GRP0:1. There is no event queued in the timerqueue, so CPU2 continues with
+ *    the parent of GRP0:1: GRP1:0. In GRP1:0 it dequeues the first event. It
+ *    looks at tmigr_event::cpu struct member and expires the pending timer(s)
+ *    of CPU0.
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:1
+ *                 --> timerqueue =
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = CPU2
+ *           active   =                active   = CPU2
+ *           groupevt.ignore = false   groupevt.ignore = true
+ *       --> groupevt.cpu = CPU0       groupevt.cpu =
+ *           timerqueue = evt-CPU0,    timerqueue =
+ *                        evt-CPU1
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           active      idle
+ *
+ * 3. Some work has to be done after expiring the timers of CPU0. If we stop
+ *    here, then CPU1's pending global timer(s) will not expire in time and the
+ *    timerqueue of GRP0:0 has still an event for CPU0 enqueued which has just
+ *    been processed. So it is required to walk the hierarchy from CPU0's point
+ *    of view and update it accordingly. CPU0's event will be removed from the
+ *    timerqueue because it has no pending timer. If CPU0 would have a timer
+ *    pending then it has to expire after CPU1's first timer because all timers
+ *    from this period were just expired. Either way CPU1's event will be first
+ *    in GRP0:0's timerqueue and therefore set in the CPU field of the group
+ *    event which is then enqueued in GRP1:0's timerqueue as GRP0:0 is still not
+ *    active:
+ *
+ *    LVL 1            [GRP1:0]
+ *                     migrator = GRP0:1
+ *                     active   = GRP0:1
+ *                 --> timerqueue = evt-GRP0:0
+ *                   /                \
+ *    LVL 0  [GRP0:0]                  [GRP0:1]
+ *           migrator = TMIGR_NONE     migrator = CPU2
+ *           active   =                active   = CPU2
+ *           groupevt.ignore = false   groupevt.ignore = true
+ *       --> groupevt.cpu = CPU1       groupevt.cpu =
+ *       --> timerqueue = evt-CPU1     timerqueue =
+ *              /         \                /         \
+ *    CPUs     0           1              2           3
+ *             idle        idle           active      idle
+ *
+ * Now CPU2 (migrator) will continue step 2 at GRP1:0 and will expire the
+ * timer(s) of CPU1.
+ *
+ * The hierarchy walk in step 3 can be skipped if the migrator notices that a
+ * CPU of GRP0:0 is active again. The CPU will mark GRP0:0 active and take care
+ * of the group as migrator and any needed updates within the hierarchy.
+ */
+
+static DEFINE_MUTEX(tmigr_mutex);
+static struct list_head *tmigr_level_list __read_mostly;
+
+static unsigned int tmigr_hierarchy_levels __read_mostly;
+static unsigned int tmigr_crossnode_level __read_mostly;
+
+static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu);
+
+#define TMIGR_NONE	0xFF
+#define BIT_CNT		8
+
+static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc)
+{
+	return !(tmc->tmgroup && tmc->online);
+}
+
+/*
+ * Returns true, when @childmask corresponds to the group migrator or when the
+ * group is not active - so no migrator is set.
+ */
+static bool tmigr_check_migrator(struct tmigr_group *group, u8 childmask)
+{
+	union tmigr_state s;
+
+	s.state = atomic_read(&group->migr_state);
+
+	if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE))
+		return true;
+
+	return false;
+}
+
+static bool tmigr_check_migrator_and_lonely(struct tmigr_group *group, u8 childmask)
+{
+	bool lonely, migrator = false;
+	unsigned long active;
+	union tmigr_state s;
+
+	s.state = atomic_read(&group->migr_state);
+
+	if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE))
+		migrator = true;
+
+	active = s.active;
+	lonely = bitmap_weight(&active, BIT_CNT) <= 1;
+
+	return (migrator && lonely);
+}
+
+static bool tmigr_check_lonely(struct tmigr_group *group)
+{
+	unsigned long active;
+	union tmigr_state s;
+
+	s.state = atomic_read(&group->migr_state);
+
+	active = s.active;
+
+	return bitmap_weight(&active, BIT_CNT) <= 1;
+}
+
+typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *);
+
+static void __walk_groups(up_f up, void *data,
+			  struct tmigr_cpu *tmc)
+{
+	struct tmigr_group *child = NULL, *group = tmc->tmgroup;
+
+	do {
+		WARN_ON_ONCE(group->level >= tmigr_hierarchy_levels);
+
+		if (up(group, child, data))
+			break;
+
+		child = group;
+		group = group->parent;
+	} while (group);
+}
+
+static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc)
+{
+	lockdep_assert_held(&tmc->lock);
+
+	__walk_groups(up, data, tmc);
+}
+
+/**
+ * struct tmigr_walk - data required for walking the hierarchy
+ * @nextexp:		Next CPU event expiry information which is handed into
+ *			the timer migration code by the timer code
+ *			(get_next_timer_interrupt())
+ * @firstexp:		Contains the first event expiry information when last
+ *			active CPU of hierarchy is on the way to idle to make
+ *			sure CPU will be back in time.
+ * @evt:		Pointer to tmigr_event which needs to be queued (of idle
+ *			child group)
+ * @childmask:		childmask of child group
+ * @remote:		Is set, when the new timer path is executed in
+ *			tmigr_handle_remote_cpu()
+ */
+struct tmigr_walk {
+	u64			nextexp;
+	u64			firstexp;
+	struct tmigr_event	*evt;
+	u8			childmask;
+	bool			remote;
+};
+
+/**
+ * struct tmigr_remote_data - data required for remote expiry hierarchy walk
+ * @basej:		timer base in jiffies
+ * @now:		timer base monotonic
+ * @firstexp:		returns expiry of the first timer in the idle timer
+ *			migration hierarchy to make sure the timer is handled in
+ *			time; it is stored in the per CPU tmigr_cpu struct of
+ *			CPU which expires remote timers
+ * @childmask:		childmask of child group
+ * @check:		is set if there is the need to handle remote timers;
+ *			required in tmigr_requires_handle_remote() only
+ * @tmc_active:		this flag indicates, whether the CPU which triggers
+ *			the hierarchy walk is !idle in the timer migration
+ *			hierarchy. When the CPU is idle and the whole hierarchy is
+ *			idle, only the first event of the top level has to be
+ *			considered.
+ */
+struct tmigr_remote_data {
+	unsigned long	basej;
+	u64		now;
+	u64		firstexp;
+	u8		childmask;
+	bool		check;
+	bool		tmc_active;
+};
+
+/*
+ * Returns the next event of the timerqueue @group->events
+ *
+ * Removes timers with ignore flag and update next_expiry of the group. Values
+ * of the group event are updated in tmigr_update_events() only.
+ */
+static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group)
+{
+	struct timerqueue_node *node = NULL;
+	struct tmigr_event *evt = NULL;
+
+	lockdep_assert_held(&group->lock);
+
+	WRITE_ONCE(group->next_expiry, KTIME_MAX);
+
+	while ((node = timerqueue_getnext(&group->events))) {
+		evt = container_of(node, struct tmigr_event, nextevt);
+
+		if (!evt->ignore) {
+			WRITE_ONCE(group->next_expiry, evt->nextevt.expires);
+			return evt;
+		}
+
+		/*
+		 * Remove next timers with ignore flag, because the group lock
+		 * is held anyway
+		 */
+		if (!timerqueue_del(&group->events, node))
+			break;
+	}
+
+	return NULL;
+}
+
+/*
+ * Return the next event (with the expiry equal or before @now)
+ *
+ * Event, which is returned, is also removed from the queue.
+ */
+static struct tmigr_event *tmigr_next_expired_groupevt(struct tmigr_group *group,
+						       u64 now)
+{
+	struct tmigr_event *evt = tmigr_next_groupevt(group);
+
+	if (!evt || now < evt->nextevt.expires)
+		return NULL;
+
+	/*
+	 * The event is ready to expire. Remove it and update next group event.
+	 */
+	timerqueue_del(&group->events, &evt->nextevt);
+	tmigr_next_groupevt(group);
+
+	return evt;
+}
+
+static u64 tmigr_next_groupevt_expires(struct tmigr_group *group)
+{
+	struct tmigr_event *evt;
+
+	evt = tmigr_next_groupevt(group);
+
+	if (!evt)
+		return KTIME_MAX;
+	else
+		return evt->nextevt.expires;
+}
+
+static bool tmigr_active_up(struct tmigr_group *group,
+			    struct tmigr_group *child,
+			    void *ptr)
+{
+	union tmigr_state curstate, newstate;
+	struct tmigr_walk *data = ptr;
+	bool walk_done;
+	u8 childmask;
+
+	childmask = data->childmask;
+	/*
+	 * No memory barrier is required here in contrast to
+	 * tmigr_inactive_up(), as the group state change does not depend on the
+	 * child state.
+	 */
+	curstate.state = atomic_read(&group->migr_state);
+
+	do {
+		newstate = curstate;
+		walk_done = true;
+
+		if (newstate.migrator == TMIGR_NONE) {
+			newstate.migrator = childmask;
+
+			/* Changes need to be propagated */
+			walk_done = false;
+		}
+
+		newstate.active |= childmask;
+		newstate.seq++;
+
+	} while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state));
+
+	if ((walk_done == false) && group->parent)
+		data->childmask = group->childmask;
+
+	/*
+	 * The group is active (again). The group event might be still queued
+	 * into the parent group's timerqueue but can now be handled by the
+	 * migrator of this group. Therefore the ignore flag for the group event
+	 * is updated to reflect this.
+	 *
+	 * The update of the ignore flag in the active path is done lockless. In
+	 * worst case the migrator of the parent group observes the change too
+	 * late and expires remotely all events belonging to this group. The
+	 * lock is held while updating the ignore flag in idle path. So this
+	 * state change will not be lost.
+	 */
+	group->groupevt.ignore = true;
+
+	trace_tmigr_group_set_cpu_active(group, newstate, childmask);
+
+	return walk_done;
+}
+
+static void __tmigr_cpu_activate(struct tmigr_cpu *tmc)
+{
+	struct tmigr_walk data;
+
+	data.childmask = tmc->childmask;
+
+	trace_tmigr_cpu_active(tmc);
+
+	tmc->cpuevt.ignore = true;
+	WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+
+	walk_groups(&tmigr_active_up, &data, tmc);
+}
+
+/**
+ * tmigr_cpu_activate() - set this CPU active in timer migration hierarchy
+ *
+ * Call site timer_clear_idle() is called with interrupts disabled.
+ */
+void tmigr_cpu_activate(void)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+	if (tmigr_is_not_available(tmc))
+		return;
+
+	if (WARN_ON_ONCE(!tmc->idle))
+		return;
+
+	raw_spin_lock(&tmc->lock);
+	tmc->idle = false;
+	__tmigr_cpu_activate(tmc);
+	raw_spin_unlock(&tmc->lock);
+}
+
+/*
+ * Returns true, if there is nothing to be propagated to the next level
+ *
+ * @data->firstexp is set to expiry of first gobal event of the (top level of
+ * the) hierarchy, but only when hierarchy is completely idle.
+ *
+ * The child and group states need to be read under the lock, to prevent a race
+ * against a concurrent tmigr_inactive_up() run when the last CPU goes idle. See
+ * also section "Prevent race between new event and last CPU going inactive" in
+ * the documentation at the top.
+ *
+ * This is the only place where the group event expiry value is set.
+ */
+static
+bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
+			 struct tmigr_walk *data)
+{
+	struct tmigr_event *evt, *first_childevt;
+	union tmigr_state childstate, groupstate;
+	bool remote = data->remote;
+	bool walk_done = false;
+	u64 nextexp;
+
+	if (child) {
+		raw_spin_lock(&child->lock);
+		raw_spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING);
+
+		childstate.state = atomic_read(&child->migr_state);
+		groupstate.state = atomic_read(&group->migr_state);
+
+		if (childstate.active) {
+			walk_done = true;
+			goto unlock;
+		}
+
+		first_childevt = tmigr_next_groupevt(child);
+		nextexp = child->next_expiry;
+		evt = &child->groupevt;
+
+		evt->ignore = (nextexp == KTIME_MAX) ? true : false;
+	} else {
+		nextexp = data->nextexp;
+
+		first_childevt = evt = data->evt;
+
+		/*
+		 * Walking the hierarchy is required in any case when a
+		 * remote expiry was done before. This ensures to not lose
+		 * already queued events in non active groups (see section
+		 * "Required event and timerqueue update after a remote
+		 * expiry" in the documentation at the top).
+		 *
+		 * The two call sites which are executed without a remote expiry
+		 * before, are not prevented from propagating changes through
+		 * the hierarchy by the return:
+		 *  - When entering this path by tmigr_new_timer(), @evt->ignore
+		 *    is never set.
+		 *  - tmigr_inactive_up() takes care of the propagation by
+		 *    itself and ignores the return value. But an immediate
+		 *    return is required because nothing has to be done in this
+		 *    level as the event could be ignored.
+		 */
+		if (evt->ignore && !remote)
+			return true;
+
+		raw_spin_lock(&group->lock);
+
+		childstate.state = 0;
+		groupstate.state = atomic_read(&group->migr_state);
+	}
+
+	/*
+	 * If the child event is already queued in the group, remove it from the
+	 * queue when the expiry time changed only or when it could be ignored.
+	 */
+	if (timerqueue_node_queued(&evt->nextevt)) {
+		if ((evt->nextevt.expires == nextexp) && !evt->ignore)
+			goto check_toplvl;
+
+		if (!timerqueue_del(&group->events, &evt->nextevt))
+			WRITE_ONCE(group->next_expiry, KTIME_MAX);
+	}
+
+	if (evt->ignore) {
+		/*
+		 * When the next child event could be ignored (nextexp is
+		 * KTIME_MAX) and there was no remote timer handling before or
+		 * the group is already active, there is no need to walk the
+		 * hierarchy even if there is a parent group.
+		 *
+		 * The other way round: even if the event could be ignored, but
+		 * if a remote timer handling was executed before and the group
+		 * is not active, walking the hierarchy is required to not miss
+		 * an enqueued timer in the non active group. The enqueued timer
+		 * of the group needs to be propagated to a higher level to
+		 * ensure it is handled.
+		 */
+		if (!remote || groupstate.active)
+			walk_done = true;
+	} else {
+		evt->nextevt.expires = nextexp;
+		evt->cpu = first_childevt->cpu;
+
+		if (timerqueue_add(&group->events, &evt->nextevt))
+			WRITE_ONCE(group->next_expiry, nextexp);
+	}
+
+check_toplvl:
+	if (!group->parent && (groupstate.migrator == TMIGR_NONE)) {
+		walk_done = true;
+
+		/*
+		 * Nothing to do when update was done during remote timer
+		 * handling. First timer in top level group which needs to be
+		 * handled when top level group is not active, is calculated
+		 * directly in tmigr_handle_remote_up().
+		 */
+		if (remote)
+			goto unlock;
+
+		/*
+		 * The top level group is idle and it has to be ensured the
+		 * global timers are handled in time. (This could be optimized
+		 * by keeping track of the last global scheduled event and only
+		 * arming it on the CPU if the new event is earlier. Not sure if
+		 * its worth the complexity.)
+		 */
+		data->firstexp = tmigr_next_groupevt_expires(group);
+	}
+
+	trace_tmigr_update_events(child, group, childstate, groupstate,
+				  nextexp);
+
+unlock:
+	raw_spin_unlock(&group->lock);
+
+	if (child)
+		raw_spin_unlock(&child->lock);
+
+	return walk_done;
+}
+
+static bool tmigr_new_timer_up(struct tmigr_group *group,
+			       struct tmigr_group *child,
+			       void *ptr)
+{
+	struct tmigr_walk *data = ptr;
+
+	return tmigr_update_events(group, child, data);
+}
+
+/*
+ * Returns the expiry of the next timer that needs to be handled. KTIME_MAX is
+ * returned, if an active CPU will handle all the timer migration hierarchy
+ * timers.
+ */
+static u64 tmigr_new_timer(struct tmigr_cpu *tmc, u64 nextexp)
+{
+	struct tmigr_walk data = { .nextexp = nextexp,
+				   .firstexp = KTIME_MAX,
+				   .evt = &tmc->cpuevt };
+
+	lockdep_assert_held(&tmc->lock);
+
+	if (tmc->remote)
+		return KTIME_MAX;
+
+	trace_tmigr_cpu_new_timer(tmc);
+
+	tmc->cpuevt.ignore = false;
+	data.remote = false;
+
+	walk_groups(&tmigr_new_timer_up, &data, tmc);
+
+	/* If there is a new first global event, make sure it is handled */
+	return data.firstexp;
+}
+
+static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now,
+				    unsigned long jif)
+{
+	struct timer_events tevt;
+	struct tmigr_walk data;
+	struct tmigr_cpu *tmc;
+
+	tmc = per_cpu_ptr(&tmigr_cpu, cpu);
+
+	raw_spin_lock_irq(&tmc->lock);
+
+	/*
+	 * If the remote CPU is offline then the timers have been migrated to
+	 * another CPU.
+	 *
+	 * If tmigr_cpu::remote is set, at the moment another CPU already
+	 * expires the timers of the remote CPU.
+	 *
+	 * If tmigr_event::ignore is set, then the CPU returns from idle and
+	 * takes care of its timers.
+	 *
+	 * If the next event expires in the future, then the event has been
+	 * updated and there are no timers to expire right now. The CPU which
+	 * updated the event takes care when hierarchy is completely
+	 * idle. Otherwise the migrator does it as the event is enqueued.
+	 */
+	if (!tmc->online || tmc->remote || tmc->cpuevt.ignore ||
+	    now < tmc->cpuevt.nextevt.expires) {
+		raw_spin_unlock_irq(&tmc->lock);
+		return;
+	}
+
+	trace_tmigr_handle_remote_cpu(tmc);
+
+	tmc->remote = true;
+	WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+
+	/* Drop the lock to allow the remote CPU to exit idle */
+	raw_spin_unlock_irq(&tmc->lock);
+
+	if (cpu != smp_processor_id())
+		timer_expire_remote(cpu);
+
+	/*
+	 * Lock ordering needs to be preserved - timer_base locks before tmigr
+	 * related locks (see section "Locking rules" in the documentation at
+	 * the top). During fetching the next timer interrupt, also tmc->lock
+	 * needs to be held. Otherwise there is a possible race window against
+	 * the CPU itself when it comes out of idle, updates the first timer in
+	 * the hierarchy and goes back to idle.
+	 *
+	 * timer base locks are dropped as fast as possible: After checking
+	 * whether the remote CPU went offline in the meantime and after
+	 * fetching the next remote timer interrupt. Dropping the locks as fast
+	 * as possible keeps the locking region small and prevents holding
+	 * several (unnecessary) locks during walking the hierarchy for updating
+	 * the timerqueue and group events.
+	 */
+	local_irq_disable();
+	timer_lock_remote_bases(cpu);
+	raw_spin_lock(&tmc->lock);
+
+	/*
+	 * When the CPU went offline in the meantime, no hierarchy walk has to
+	 * be done for updating the queued events, because the walk was
+	 * already done during marking the CPU offline in the hierarchy.
+	 *
+	 * When the CPU is no longer idle, the CPU takes care of the timers and
+	 * also of the timers in the hierarchy.
+	 *
+	 * (See also section "Required event and timerqueue update after a
+	 * remote expiry" in the documentation at the top)
+	 */
+	if (!tmc->online || !tmc->idle) {
+		timer_unlock_remote_bases(cpu);
+		goto unlock;
+	}
+
+	/* next	event of CPU */
+	fetch_next_timer_interrupt_remote(jif, now, &tevt, cpu);
+	timer_unlock_remote_bases(cpu);
+
+	data.nextexp = tevt.global;
+	data.firstexp = KTIME_MAX;
+	data.evt = &tmc->cpuevt;
+	data.remote = true;
+
+	/*
+	 * The update is done even when there is no 'new' global timer pending
+	 * on the remote CPU (see section "Required event and timerqueue update
+	 * after a remote expiry" in the documentation at the top)
+	 */
+	walk_groups(&tmigr_new_timer_up, &data, tmc);
+
+unlock:
+	tmc->remote = false;
+	raw_spin_unlock_irq(&tmc->lock);
+}
+
+static bool tmigr_handle_remote_up(struct tmigr_group *group,
+				   struct tmigr_group *child,
+				   void *ptr)
+{
+	struct tmigr_remote_data *data = ptr;
+	struct tmigr_event *evt;
+	unsigned long jif;
+	u8 childmask;
+	u64 now;
+
+	jif = data->basej;
+	now = data->now;
+
+	childmask = data->childmask;
+
+	trace_tmigr_handle_remote(group);
+again:
+	/*
+	 * Handle the group only if @childmask is the migrator or if the
+	 * group has no migrator. Otherwise the group is active and is
+	 * handled by its own migrator.
+	 */
+	if (!tmigr_check_migrator(group, childmask))
+		return true;
+
+	raw_spin_lock_irq(&group->lock);
+
+	evt = tmigr_next_expired_groupevt(group, now);
+
+	if (evt) {
+		unsigned int remote_cpu = evt->cpu;
+
+		raw_spin_unlock_irq(&group->lock);
+
+		tmigr_handle_remote_cpu(remote_cpu, now, jif);
+
+		/* check if there is another event, that needs to be handled */
+		goto again;
+	}
+
+	/*
+	 * Update of childmask for the next level and keep track of the expiry
+	 * of the first event that needs to be handled (group->next_expiry was
+	 * updated by tmigr_next_expired_groupevt(), next was set by
+	 * tmigr_handle_remote_cpu()).
+	 */
+	data->childmask = group->childmask;
+	data->firstexp = group->next_expiry;
+
+	raw_spin_unlock_irq(&group->lock);
+
+	return false;
+}
+
+/**
+ * tmigr_handle_remote() - Handle global timers of remote idle CPUs
+ *
+ * Called from the timer soft interrupt with interrupts enabled.
+ */
+void tmigr_handle_remote(void)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	struct tmigr_remote_data data;
+
+	if (tmigr_is_not_available(tmc))
+		return;
+
+	data.childmask = tmc->childmask;
+	data.firstexp = KTIME_MAX;
+
+	/*
+	 * NOTE: This is a doubled check because the migrator test will be done
+	 * in tmigr_handle_remote_up() anyway. Keep this check to speed up the
+	 * return when nothing has to be done.
+	 */
+	if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask))
+		return;
+
+	data.now = get_jiffies_update(&data.basej);
+
+	/*
+	 * Update @tmc->wakeup only at the end and do not reset @tmc->wakeup to
+	 * KTIME_MAX. Even if tmc->lock is not held during the whole remote
+	 * handling, tmc->wakeup is fine to be stale as it is called in
+	 * interrupt context and tick_nohz_next_event() is executed in interrupt
+	 * exit path only after processing the last pending interrupt.
+	 */
+
+	__walk_groups(&tmigr_handle_remote_up, &data, tmc);
+
+	raw_spin_lock_irq(&tmc->lock);
+	WRITE_ONCE(tmc->wakeup, data.firstexp);
+	raw_spin_unlock_irq(&tmc->lock);
+}
+
+static bool tmigr_requires_handle_remote_up(struct tmigr_group *group,
+					    struct tmigr_group *child,
+					    void *ptr)
+{
+	struct tmigr_remote_data *data = ptr;
+	u8 childmask;
+
+	childmask = data->childmask;
+
+	/*
+	 * Handle the group only if the child is the migrator or if the group
+	 * has no migrator. Otherwise the group is active and is handled by its
+	 * own migrator.
+	 */
+	if (!tmigr_check_migrator(group, childmask))
+		return true;
+
+	/*
+	 * When there is a parent group and the CPU which triggered the
+	 * hierarchy walk is not active, proceed the walk to reach the top level
+	 * group before reading the next_expiry value.
+	 */
+	if (group->parent && !data->tmc_active)
+		goto out;
+
+	/*
+	 * The lock is required on 32bit architectures to read the variable
+	 * consistently with a concurrent writer. On 64bit the lock is not
+	 * required because the read operation is not split and so it is always
+	 * consistent.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT)) {
+		data->firstexp = READ_ONCE(group->next_expiry);
+		if (data->now >= data->firstexp) {
+			data->check = true;
+			return true;
+		}
+	} else {
+		raw_spin_lock(&group->lock);
+		data->firstexp = group->next_expiry;
+		if (data->now >= group->next_expiry) {
+			data->check = true;
+			raw_spin_unlock(&group->lock);
+			return true;
+		}
+		raw_spin_unlock(&group->lock);
+	}
+
+out:
+	/* Update of childmask for the next level */
+	data->childmask = group->childmask;
+	return false;
+}
+
+/**
+ * tmigr_requires_handle_remote() - Check the need of remote timer handling
+ *
+ * Must be called with interrupts disabled.
+ */
+bool tmigr_requires_handle_remote(void)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	struct tmigr_remote_data data;
+	unsigned long jif;
+	bool ret = false;
+
+	if (tmigr_is_not_available(tmc))
+		return ret;
+
+	data.now = get_jiffies_update(&jif);
+	data.childmask = tmc->childmask;
+	data.firstexp = KTIME_MAX;
+	data.tmc_active = !tmc->idle;
+	data.check = false;
+
+	/*
+	 * If the CPU is active, walk the hierarchy to check whether a remote
+	 * expiry is required.
+	 *
+	 * Check is done lockless as interrupts are disabled and @tmc->idle is
+	 * set only by the local CPU.
+	 */
+	if (!tmc->idle) {
+		__walk_groups(&tmigr_requires_handle_remote_up, &data, tmc);
+
+		return data.check;
+	}
+
+	/*
+	 * When the CPU is idle, compare @tmc->wakeup with @data.now. The lock
+	 * is required on 32bit architectures to read the variable consistently
+	 * with a concurrent writer. On 64bit the lock is not required because
+	 * the read operation is not split and so it is always consistent.
+	 */
+	if (IS_ENABLED(CONFIG_64BIT)) {
+		if (data.now >= READ_ONCE(tmc->wakeup))
+			return true;
+	} else {
+		raw_spin_lock(&tmc->lock);
+		if (data.now >= tmc->wakeup)
+			ret = true;
+		raw_spin_unlock(&tmc->lock);
+	}
+
+	return ret;
+}
+
+/**
+ * tmigr_cpu_new_timer() - enqueue next global timer into hierarchy (idle tmc)
+ * @nextexp:	Next expiry of global timer (or KTIME_MAX if not)
+ *
+ * The CPU is already deactivated in the timer migration
+ * hierarchy. tick_nohz_get_sleep_length() calls tick_nohz_next_event()
+ * and thereby the timer idle path is executed once more. @tmc->wakeup
+ * holds the first timer, when the timer migration hierarchy is
+ * completely idle.
+ *
+ * Returns the first timer that needs to be handled by this CPU or KTIME_MAX if
+ * nothing needs to be done.
+ */
+u64 tmigr_cpu_new_timer(u64 nextexp)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	u64 ret;
+
+	if (tmigr_is_not_available(tmc))
+		return nextexp;
+
+	raw_spin_lock(&tmc->lock);
+
+	ret = READ_ONCE(tmc->wakeup);
+	if (nextexp != KTIME_MAX) {
+		if (nextexp != tmc->cpuevt.nextevt.expires ||
+		    tmc->cpuevt.ignore) {
+			ret = tmigr_new_timer(tmc, nextexp);
+		}
+	}
+	/*
+	 * Make sure the reevaluation of timers in idle path will not miss an
+	 * event.
+	 */
+	WRITE_ONCE(tmc->wakeup, ret);
+
+	trace_tmigr_cpu_new_timer_idle(tmc, nextexp);
+	raw_spin_unlock(&tmc->lock);
+	return ret;
+}
+
+static bool tmigr_inactive_up(struct tmigr_group *group,
+			      struct tmigr_group *child,
+			      void *ptr)
+{
+	union tmigr_state curstate, newstate, childstate;
+	struct tmigr_walk *data = ptr;
+	bool walk_done;
+	u8 childmask;
+
+	childmask = data->childmask;
+	childstate.state = 0;
+
+	/*
+	 * The memory barrier is paired with the cmpxchg() in tmigr_active_up()
+	 * to make sure the updates of child and group states are ordered. The
+	 * ordering is mandatory, as the group state change depends on the child
+	 * state.
+	 */
+	curstate.state = atomic_read_acquire(&group->migr_state);
+
+	for (;;) {
+		if (child)
+			childstate.state = atomic_read(&child->migr_state);
+
+		newstate = curstate;
+		walk_done = true;
+
+		/* Reset active bit when the child is no longer active */
+		if (!childstate.active)
+			newstate.active &= ~childmask;
+
+		if (newstate.migrator == childmask) {
+			/*
+			 * Find a new migrator for the group, because the child
+			 * group is idle!
+			 */
+			if (!childstate.active) {
+				unsigned long new_migr_bit, active = newstate.active;
+
+				new_migr_bit = find_first_bit(&active, BIT_CNT);
+
+				if (new_migr_bit != BIT_CNT) {
+					newstate.migrator = BIT(new_migr_bit);
+				} else {
+					newstate.migrator = TMIGR_NONE;
+
+					/* Changes need to be propagated */
+					walk_done = false;
+				}
+			}
+		}
+
+		newstate.seq++;
+
+		WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active));
+
+		if (atomic_try_cmpxchg(&group->migr_state, &curstate.state,
+				       newstate.state))
+			break;
+
+		/*
+		 * The memory barrier is paired with the cmpxchg() in
+		 * tmigr_active_up() to make sure the updates of child and group
+		 * states are ordered. It is required only when the above
+		 * try_cmpxchg() fails.
+		 */
+		smp_mb__after_atomic();
+	}
+
+	data->remote = false;
+
+	/* Event Handling */
+	tmigr_update_events(group, child, data);
+
+	if (group->parent && (walk_done == false))
+		data->childmask = group->childmask;
+
+	/*
+	 * data->firstexp was set by tmigr_update_events() and contains the
+	 * expiry of the first global event which needs to be handled. It
+	 * differs from KTIME_MAX if:
+	 * - group is the top level group and
+	 * - group is idle (which means CPU was the last active CPU in the
+	 *   hierarchy) and
+	 * - there is a pending event in the hierarchy
+	 */
+	WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent);
+
+	trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
+
+	return walk_done;
+}
+
+static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp)
+{
+	struct tmigr_walk data = { .nextexp = nextexp,
+				   .firstexp = KTIME_MAX,
+				   .evt = &tmc->cpuevt,
+				   .childmask = tmc->childmask };
+
+	/*
+	 * If nextexp is KTIME_MAX, the CPU event will be ignored because the
+	 * local timer expires before the global timer, no global timer is set
+	 * or CPU goes offline.
+	 */
+	if (nextexp != KTIME_MAX)
+		tmc->cpuevt.ignore = false;
+
+	walk_groups(&tmigr_inactive_up, &data, tmc);
+	return data.firstexp;
+}
+
+/**
+ * tmigr_cpu_deactivate() - Put current CPU into inactive state
+ * @nextexp:	The next global timer expiry of the current CPU
+ *
+ * Must be called with interrupts disabled.
+ *
+ * Return: the next event expiry of the current CPU or the next event expiry
+ * from the hierarchy if this CPU is the top level migrator or the hierarchy is
+ * completely idle.
+ */
+u64 tmigr_cpu_deactivate(u64 nextexp)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	u64 ret;
+
+	if (tmigr_is_not_available(tmc))
+		return nextexp;
+
+	raw_spin_lock(&tmc->lock);
+
+	ret = __tmigr_cpu_deactivate(tmc, nextexp);
+
+	tmc->idle = true;
+
+	/*
+	 * Make sure the reevaluation of timers in idle path will not miss an
+	 * event.
+	 */
+	WRITE_ONCE(tmc->wakeup, ret);
+
+	trace_tmigr_cpu_idle(tmc, nextexp);
+	raw_spin_unlock(&tmc->lock);
+	return ret;
+}
+
+/**
+ * tmigr_quick_check() - Quick forecast of next tmigr event when CPU wants to
+ *			 go idle
+ * @nextevt:	The next global timer expiry of the current CPU
+ *
+ * Return:
+ * * KTIME_MAX		- when it is probable that nothing has to be done (not
+ *			  the only one in the level 0 group; and if it is the
+ *			  only one in level 0 group, but there are more than a
+ *			  single group active on the way to top level)
+ * * nextevt		- when CPU is offline and has to handle timer on his own
+ *			  or when on the way to top in every group only a single
+ *			  child is active but @nextevt is before the lowest
+ *			  next_expiry encountered while walking up to top level.
+ * * next_expiry	- value of lowest expiry encountered while walking groups
+ *			  if only a single child is active on each and @nextevt
+ *			  is after this lowest expiry.
+ */
+u64 tmigr_quick_check(u64 nextevt)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	struct tmigr_group *group = tmc->tmgroup;
+
+	if (tmigr_is_not_available(tmc))
+		return nextevt;
+
+	if (WARN_ON_ONCE(tmc->idle))
+		return nextevt;
+
+	if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask))
+		return KTIME_MAX;
+
+	do {
+		if (!tmigr_check_lonely(group)) {
+			return KTIME_MAX;
+		} else {
+			/*
+			 * Since current CPU is active, events may not be sorted
+			 * from bottom to the top because the CPU's event is ignored
+			 * up to the top and its sibling's events not propagated upwards.
+			 * Thus keep track of the lowest observed expiry.
+			 */
+			nextevt = min_t(u64, nextevt, READ_ONCE(group->next_expiry));
+			if (!group->parent)
+				return nextevt;
+		}
+		group = group->parent;
+	} while (group);
+
+	return KTIME_MAX;
+}
+
+static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl,
+			     int node)
+{
+	union tmigr_state s;
+
+	raw_spin_lock_init(&group->lock);
+
+	group->level = lvl;
+	group->numa_node = lvl < tmigr_crossnode_level ? node : NUMA_NO_NODE;
+
+	group->num_children = 0;
+
+	s.migrator = TMIGR_NONE;
+	s.active = 0;
+	s.seq = 0;
+	atomic_set(&group->migr_state, s.state);
+
+	timerqueue_init_head(&group->events);
+	timerqueue_init(&group->groupevt.nextevt);
+	group->groupevt.nextevt.expires = KTIME_MAX;
+	WRITE_ONCE(group->next_expiry, KTIME_MAX);
+	group->groupevt.ignore = true;
+}
+
+static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node,
+					   unsigned int lvl)
+{
+	struct tmigr_group *tmp, *group = NULL;
+
+	lockdep_assert_held(&tmigr_mutex);
+
+	/* Try to attach to an existing group first */
+	list_for_each_entry(tmp, &tmigr_level_list[lvl], list) {
+		/*
+		 * If @lvl is below the cross NUMA node level, check whether
+		 * this group belongs to the same NUMA node.
+		 */
+		if (lvl < tmigr_crossnode_level && tmp->numa_node != node)
+			continue;
+
+		/* Capacity left? */
+		if (tmp->num_children >= TMIGR_CHILDREN_PER_GROUP)
+			continue;
+
+		/*
+		 * TODO: A possible further improvement: Make sure that all CPU
+		 * siblings end up in the same group of the lowest level of the
+		 * hierarchy. Rely on the topology sibling mask would be a
+		 * reasonable solution.
+		 */
+
+		group = tmp;
+		break;
+	}
+
+	if (group)
+		return group;
+
+	/* Allocate and	set up a new group */
+	group = kzalloc_node(sizeof(*group), GFP_KERNEL, node);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	tmigr_init_group(group, lvl, node);
+
+	/* Setup successful. Add it to the hierarchy */
+	list_add(&group->list, &tmigr_level_list[lvl]);
+	trace_tmigr_group_set(group);
+	return group;
+}
+
+static void tmigr_connect_child_parent(struct tmigr_group *child,
+				       struct tmigr_group *parent)
+{
+	union tmigr_state childstate;
+
+	raw_spin_lock_irq(&child->lock);
+	raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);
+
+	child->parent = parent;
+	child->childmask = BIT(parent->num_children++);
+
+	raw_spin_unlock(&parent->lock);
+	raw_spin_unlock_irq(&child->lock);
+
+	trace_tmigr_connect_child_parent(child);
+
+	/*
+	 * To prevent inconsistent states, active children need to be active in
+	 * the new parent as well. Inactive children are already marked inactive
+	 * in the parent group:
+	 *
+	 * * When new groups were created by tmigr_setup_groups() starting from
+	 *   the lowest level (and not higher then one level below the current
+	 *   top level), then they are not active. They will be set active when
+	 *   the new online CPU comes active.
+	 *
+	 * * But if a new group above the current top level is required, it is
+	 *   mandatory to propagate the active state of the already existing
+	 *   child to the new parent. So tmigr_connect_child_parent() is
+	 *   executed with the formerly top level group (child) and the newly
+	 *   created group (parent).
+	 */
+	childstate.state = atomic_read(&child->migr_state);
+	if (childstate.migrator != TMIGR_NONE) {
+		struct tmigr_walk data;
+
+		data.childmask = child->childmask;
+
+		/*
+		 * There is only one new level per time. When connecting the
+		 * child and the parent and set the child active when the parent
+		 * is inactive, the parent needs to be the uppermost
+		 * level. Otherwise there went something wrong!
+		 */
+		WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
+	}
+}
+
+static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
+{
+	struct tmigr_group *group, *child, **stack;
+	int top = 0, err = 0, i = 0;
+	struct list_head *lvllist;
+
+	stack = kcalloc(tmigr_hierarchy_levels, sizeof(*stack), GFP_KERNEL);
+	if (!stack)
+		return -ENOMEM;
+
+	do {
+		group = tmigr_get_group(cpu, node, i);
+		if (IS_ERR(group)) {
+			err = PTR_ERR(group);
+			break;
+		}
+
+		top = i;
+		stack[i++] = group;
+
+		/*
+		 * When booting only less CPUs of a system than CPUs are
+		 * available, not all calculated hierarchy levels are required.
+		 *
+		 * The loop is aborted as soon as the highest level, which might
+		 * be different from tmigr_hierarchy_levels, contains only a
+		 * single group.
+		 */
+		if (group->parent || i == tmigr_hierarchy_levels ||
+		    (list_empty(&tmigr_level_list[i]) &&
+		     list_is_singular(&tmigr_level_list[i - 1])))
+			break;
+
+	} while (i < tmigr_hierarchy_levels);
+
+	do {
+		group = stack[--i];
+
+		if (err < 0) {
+			list_del(&group->list);
+			kfree(group);
+			continue;
+		}
+
+		WARN_ON_ONCE(i != group->level);
+
+		/*
+		 * Update tmc -> group / child -> group connection
+		 */
+		if (i == 0) {
+			struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+			raw_spin_lock_irq(&group->lock);
+
+			tmc->tmgroup = group;
+			tmc->childmask = BIT(group->num_children++);
+
+			raw_spin_unlock_irq(&group->lock);
+
+			trace_tmigr_connect_cpu_parent(tmc);
+
+			/* There are no children that need to be connected */
+			continue;
+		} else {
+			child = stack[i - 1];
+			tmigr_connect_child_parent(child, group);
+		}
+
+		/* check if uppermost level was newly created */
+		if (top != i)
+			continue;
+
+		WARN_ON_ONCE(top == 0);
+
+		lvllist = &tmigr_level_list[top];
+		if (group->num_children == 1 && list_is_singular(lvllist)) {
+			lvllist = &tmigr_level_list[top - 1];
+			list_for_each_entry(child, lvllist, list) {
+				if (child->parent)
+					continue;
+
+				tmigr_connect_child_parent(child, group);
+			}
+		}
+	} while (i > 0);
+
+	kfree(stack);
+
+	return err;
+}
+
+static int tmigr_add_cpu(unsigned int cpu)
+{
+	int node = cpu_to_node(cpu);
+	int ret;
+
+	mutex_lock(&tmigr_mutex);
+	ret = tmigr_setup_groups(cpu, node);
+	mutex_unlock(&tmigr_mutex);
+
+	return ret;
+}
+
+static int tmigr_cpu_online(unsigned int cpu)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	int ret;
+
+	/* First online attempt? Initialize CPU data */
+	if (!tmc->tmgroup) {
+		raw_spin_lock_init(&tmc->lock);
+
+		ret = tmigr_add_cpu(cpu);
+		if (ret < 0)
+			return ret;
+
+		if (tmc->childmask == 0)
+			return -EINVAL;
+
+		timerqueue_init(&tmc->cpuevt.nextevt);
+		tmc->cpuevt.nextevt.expires = KTIME_MAX;
+		tmc->cpuevt.ignore = true;
+		tmc->cpuevt.cpu = cpu;
+
+		tmc->remote = false;
+		WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+	}
+	raw_spin_lock_irq(&tmc->lock);
+	trace_tmigr_cpu_online(tmc);
+	tmc->idle = timer_base_is_idle();
+	if (!tmc->idle)
+		__tmigr_cpu_activate(tmc);
+	tmc->online = true;
+	raw_spin_unlock_irq(&tmc->lock);
+	return 0;
+}
+
+/*
+ * tmigr_trigger_active() - trigger a CPU to become active again
+ *
+ * This function is executed on a CPU which is part of cpu_online_mask, when the
+ * last active CPU in the hierarchy is offlining. With this, it is ensured that
+ * the other CPU is active and takes over the migrator duty.
+ */
+static long tmigr_trigger_active(void *unused)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+
+	WARN_ON_ONCE(!tmc->online || tmc->idle);
+
+	return 0;
+}
+
+static int tmigr_cpu_offline(unsigned int cpu)
+{
+	struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu);
+	int migrator;
+	u64 firstexp;
+
+	raw_spin_lock_irq(&tmc->lock);
+	tmc->online = false;
+	WRITE_ONCE(tmc->wakeup, KTIME_MAX);
+
+	/*
+	 * CPU has to handle the local events on his own, when on the way to
+	 * offline; Therefore nextevt value is set to KTIME_MAX
+	 */
+	firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX);
+	trace_tmigr_cpu_offline(tmc);
+	raw_spin_unlock_irq(&tmc->lock);
+
+	if (firstexp != KTIME_MAX) {
+		migrator = cpumask_any_but(cpu_online_mask, cpu);
+		work_on_cpu(migrator, tmigr_trigger_active, NULL);
+	}
+
+	return 0;
+}
+
+static int __init tmigr_init(void)
+{
+	unsigned int cpulvl, nodelvl, cpus_per_node, i;
+	unsigned int nnodes = num_possible_nodes();
+	unsigned int ncpus = num_possible_cpus();
+	int ret = -ENOMEM;
+
+	BUILD_BUG_ON_NOT_POWER_OF_2(TMIGR_CHILDREN_PER_GROUP);
+
+	/* Nothing to do if running on UP */
+	if (ncpus == 1)
+		return 0;
+
+	/*
+	 * Calculate the required hierarchy levels. Unfortunately there is no
+	 * reliable information available, unless all possible CPUs have been
+	 * brought up and all NUMA nodes are populated.
+	 *
+	 * Estimate the number of levels with the number of possible nodes and
+	 * the number of possible CPUs. Assume CPUs are spread evenly across
+	 * nodes. We cannot rely on cpumask_of_node() because it only works for
+	 * online CPUs.
+	 */
+	cpus_per_node = DIV_ROUND_UP(ncpus, nnodes);
+
+	/* Calc the hierarchy levels required to hold the CPUs of a node */
+	cpulvl = DIV_ROUND_UP(order_base_2(cpus_per_node),
+			      ilog2(TMIGR_CHILDREN_PER_GROUP));
+
+	/* Calculate the extra levels to connect all nodes */
+	nodelvl = DIV_ROUND_UP(order_base_2(nnodes),
+			       ilog2(TMIGR_CHILDREN_PER_GROUP));
+
+	tmigr_hierarchy_levels = cpulvl + nodelvl;
+
+	/*
+	 * If a NUMA node spawns more than one CPU level group then the next
+	 * level(s) of the hierarchy contains groups which handle all CPU groups
+	 * of the same NUMA node. The level above goes across NUMA nodes. Store
+	 * this information for the setup code to decide in which level node
+	 * matching is no longer required.
+	 */
+	tmigr_crossnode_level = cpulvl;
+
+	tmigr_level_list = kcalloc(tmigr_hierarchy_levels, sizeof(struct list_head), GFP_KERNEL);
+	if (!tmigr_level_list)
+		goto err;
+
+	for (i = 0; i < tmigr_hierarchy_levels; i++)
+		INIT_LIST_HEAD(&tmigr_level_list[i]);
+
+	pr_info("Timer migration: %d hierarchy levels; %d children per group;"
+		" %d crossnode level\n",
+		tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP,
+		tmigr_crossnode_level);
+
+	ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online",
+				tmigr_cpu_online, tmigr_cpu_offline);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	pr_err("Timer migration setup failed\n");
+	return ret;
+}
+late_initcall(tmigr_init);
diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
new file mode 100644
index 000000000000..6c37d94a37d9
--- /dev/null
+++ b/kernel/time/timer_migration.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _KERNEL_TIME_MIGRATION_H
+#define _KERNEL_TIME_MIGRATION_H
+
+/* Per group capacity. Must be a power of 2! */
+#define TMIGR_CHILDREN_PER_GROUP 8
+
+/**
+ * struct tmigr_event - a timer event associated to a CPU
+ * @nextevt:	The node to enqueue an event in the parent group queue
+ * @cpu:	The CPU to which this event belongs
+ * @ignore:	Hint whether the event could be ignored; it is set when
+ *		CPU or group is active;
+ */
+struct tmigr_event {
+	struct timerqueue_node	nextevt;
+	unsigned int		cpu;
+	bool			ignore;
+};
+
+/**
+ * struct tmigr_group - timer migration hierarchy group
+ * @lock:		Lock protecting the event information and group hierarchy
+ *			information during setup
+ * @parent:		Pointer to the parent group
+ * @groupevt:		Next event of the group which is only used when the
+ *			group is !active. The group event is then queued into
+ *			the parent timer queue.
+ *			Ignore bit of @groupevt is set when the group is active.
+ * @next_expiry:	Base monotonic expiry time of the next event of the
+ *			group; It is used for the racy lockless check whether a
+ *			remote expiry is required; it is always reliable
+ * @events:		Timer queue for child events queued in the group
+ * @migr_state:		State of the group (see union tmigr_state)
+ * @level:		Hierarchy level of the group; Required during setup
+ * @numa_node:		Required for setup only to make sure CPU and low level
+ *			group information is NUMA local. It is set to NUMA node
+ *			as long as the group level is per NUMA node (level <
+ *			tmigr_crossnode_level); otherwise it is set to
+ *			NUMA_NO_NODE
+ * @num_children:	Counter of group children to make sure the group is only
+ *			filled with TMIGR_CHILDREN_PER_GROUP; Required for setup
+ *			only
+ * @childmask:		childmask of the group in the parent group; is set
+ *			during setup and will never change; can be read
+ *			lockless
+ * @list:		List head that is added to the per level
+ *			tmigr_level_list; is required during setup when a
+ *			new group needs to be connected to the existing
+ *			hierarchy groups
+ */
+struct tmigr_group {
+	raw_spinlock_t		lock;
+	struct tmigr_group	*parent;
+	struct tmigr_event	groupevt;
+	u64			next_expiry;
+	struct timerqueue_head	events;
+	atomic_t		migr_state;
+	unsigned int		level;
+	int			numa_node;
+	unsigned int		num_children;
+	u8			childmask;
+	struct list_head	list;
+};
+
+/**
+ * struct tmigr_cpu - timer migration per CPU group
+ * @lock:		Lock protecting the tmigr_cpu group information
+ * @online:		Indicates whether the CPU is online; In deactivate path
+ *			it is required to know whether the migrator in the top
+ *			level group is to be set offline, while a timer is
+ *			pending. Then another online CPU needs to be notified to
+ *			take over the migrator role. Furthermore the information
+ *			is required in CPU hotplug path as the CPU is able to go
+ *			idle before the timer migration hierarchy hotplug AP is
+ *			reached. During this phase, the CPU has to handle the
+ *			global timers on its own and must not act as a migrator.
+ * @idle:		Indicates whether the CPU is idle in the timer migration
+ *			hierarchy
+ * @remote:		Is set when timers of the CPU are expired remotely
+ * @tmgroup:		Pointer to the parent group
+ * @childmask:		childmask of tmigr_cpu in the parent group
+ * @wakeup:		Stores the first timer when the timer migration
+ *			hierarchy is completely idle and remote expiry was done;
+ *			is returned to timer code in the idle path and is only
+ *			used in idle path.
+ * @cpuevt:		CPU event which could be enqueued into the parent group
+ */
+struct tmigr_cpu {
+	raw_spinlock_t		lock;
+	bool			online;
+	bool			idle;
+	bool			remote;
+	struct tmigr_group	*tmgroup;
+	u8			childmask;
+	u64			wakeup;
+	struct tmigr_event	cpuevt;
+};
+
+/**
+ * union tmigr_state - state of tmigr_group
+ * @state:	Combined version of the state - only used for atomic
+ *		read/cmpxchg function
+ * @struct:	Split version of the state - only use the struct members to
+ *		update information to stay independent of endianness
+ */
+union tmigr_state {
+	u32 state;
+	/**
+	 * struct - split state of tmigr_group
+	 * @active:	Contains each childmask bit of the active children
+	 * @migrator:	Contains childmask of the child which is migrator
+	 * @seq:	Sequence counter needs to be increased when an update
+	 *		to the tmigr_state is done. It prevents a race when
+	 *		updates in the child groups are propagated in changed
+	 *		order. Detailed information about the scenario is
+	 *		given in the documentation at the begin of
+	 *		timer_migration.c.
+	 */
+	struct {
+		u8	active;
+		u8	migrator;
+		u16	seq;
+	} __packed;
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void tmigr_handle_remote(void);
+extern bool tmigr_requires_handle_remote(void);
+extern void tmigr_cpu_activate(void);
+extern u64 tmigr_cpu_deactivate(u64 nextevt);
+extern u64 tmigr_cpu_new_timer(u64 nextevt);
+extern u64 tmigr_quick_check(u64 nextevt);
+#else
+static inline void tmigr_handle_remote(void) { }
+static inline bool tmigr_requires_handle_remote(void) { return false; }
+static inline void tmigr_cpu_activate(void) { }
+#endif
+
+#endif
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 6cd2a4e3afb8..9ff018245840 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -189,9 +189,6 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 {
 	int size;
 
-	if (num <= 0)
-		return -EINVAL;
-
 	if (!fp->exit_handler) {
 		fp->rethook = NULL;
 		return 0;
@@ -199,15 +196,16 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
 
 	/* Initialize rethook if needed */
 	if (fp->nr_maxactive)
-		size = fp->nr_maxactive;
+		num = fp->nr_maxactive;
 	else
-		size = num * num_possible_cpus() * 2;
-	if (size <= 0)
+		num *= num_possible_cpus() * 2;
+	if (num <= 0)
 		return -EINVAL;
 
+	size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size;
+
 	/* Initialize rethook */
-	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler,
-				sizeof(struct fprobe_rethook_node), size);
+	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num);
 	if (IS_ERR(fp->rethook))
 		return PTR_ERR(fp->rethook);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b01ae7d36021..83ba342aef31 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs);
 
 static int register_ftrace_function_nolock(struct ftrace_ops *ops);
 
+/*
+ * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct
+ * call will be jumped from ftrace_regs_caller. Only if the architecture does
+ * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
+ * jumps from ftrace_caller for multiple ftrace_ops.
+ */
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS
 #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
+#else
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#endif
 
 static int check_direct_multi(struct ftrace_ops *ops)
 {
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 13aaf5e85b81..3103a484182e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -384,7 +384,6 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
-	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -756,8 +755,19 @@ static void rb_wake_up_waiters(struct irq_work *work)
 
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		struct ring_buffer_per_cpu *cpu_buffer =
+			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
+
+		/* Called from interrupt context */
+		raw_spin_lock(&cpu_buffer->reader_lock);
 		rbwork->wakeup_full = false;
 		rbwork->full_waiters_pending = false;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -798,14 +808,40 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 		rbwork = &cpu_buffer->irq_work;
 	}
 
-	rbwork->wait_index++;
-	/* make sure the waiters see the new index */
-	smp_wmb();
-
 	/* This can be called in any context */
 	irq_work_queue(&rbwork->work);
 }
 
+static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	bool ret = false;
+
+	/* Reads of all CPUs always waits for any data */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		return !ring_buffer_empty(buffer);
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!ring_buffer_empty_cpu(buffer, cpu)) {
+		unsigned long flags;
+		bool pagebusy;
+
+		if (!full)
+			return true;
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+		ret = !pagebusy && full_hit(buffer, cpu, full);
+
+		if (!cpu_buffer->shortest_full ||
+		    cpu_buffer->shortest_full > full)
+			cpu_buffer->shortest_full = full;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+	return ret;
+}
+
 /**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
@@ -821,7 +857,6 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
-	long wait_index;
 	int ret = 0;
 
 	/*
@@ -840,81 +875,54 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		work = &cpu_buffer->irq_work;
 	}
 
-	wait_index = READ_ONCE(work->wait_index);
-
-	while (true) {
-		if (full)
-			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-		else
-			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
-
-		/*
-		 * The events can happen in critical sections where
-		 * checking a work queue can cause deadlocks.
-		 * After adding a task to the queue, this flag is set
-		 * only to notify events to try to wake up the queue
-		 * using irq_work.
-		 *
-		 * We don't clear it even if the buffer is no longer
-		 * empty. The flag only causes the next event to run
-		 * irq_work to do the work queue wake up. The worse
-		 * that can happen if we race with !trace_empty() is that
-		 * an event will cause an irq_work to try to wake up
-		 * an empty queue.
-		 *
-		 * There's no reason to protect this flag either, as
-		 * the work queue and irq_work logic will do the necessary
-		 * synchronization for the wake ups. The only thing
-		 * that is necessary is that the wake up happens after
-		 * a task has been queued. It's OK for spurious wake ups.
-		 */
-		if (full)
-			work->full_waiters_pending = true;
-		else
-			work->waiters_pending = true;
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
-			break;
-
-		if (cpu != RING_BUFFER_ALL_CPUS &&
-		    !ring_buffer_empty_cpu(buffer, cpu)) {
-			unsigned long flags;
-			bool pagebusy;
-			bool done;
-
-			if (!full)
-				break;
-
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			done = !pagebusy && full_hit(buffer, cpu, full);
+	if (full)
+		prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
+	else
+		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
 
-			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full > full)
-				cpu_buffer->shortest_full = full;
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (done)
-				break;
-		}
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	if (full)
+		work->full_waiters_pending = true;
+	else
+		work->waiters_pending = true;
 
-		schedule();
+	if (rb_watermark_hit(buffer, cpu, full))
+		goto out;
 
-		/* Make sure to see the new wait index */
-		smp_rmb();
-		if (wait_index != work->wait_index)
-			break;
+	if (signal_pending(current)) {
+		ret = -EINTR;
+		goto out;
 	}
 
+	schedule();
+ out:
 	if (full)
 		finish_wait(&work->full_waiters, &wait);
 	else
 		finish_wait(&work->waiters, &wait);
 
+	if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current))
+		ret = -EINTR;
+
 	return ret;
 }
 
@@ -937,28 +945,33 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
+		unsigned long flags;
+
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		rbwork->full_waiters_pending = true;
 		if (!cpu_buffer->shortest_full ||
 		    cpu_buffer->shortest_full > full)
 			cpu_buffer->shortest_full = full;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	} else {
-		poll_wait(filp, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		poll_wait(filp, &rbwork->waiters, poll_table);
+		rbwork->waiters_pending = true;
 	}
 
 	/*
@@ -1009,7 +1022,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer)
 	u64 ts;
 
 	/* Skip retpolines :-( */
-	if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local))
+	if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local))
 		ts = trace_clock_local();
 	else
 		ts = buffer->clock();
@@ -5877,6 +5890,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 	if (psize <= BUF_PAGE_HDR_SIZE)
 		return -EINVAL;
 
+	/* Size of a subbuf cannot be greater than the write counter */
+	if (psize > RB_WRITE_MASK + 1)
+		return -EINVAL;
+
 	old_order = buffer->subbuf_order;
 	old_size = buffer->subbuf_size;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a7c6fd934e9..c9c898307348 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -39,6 +39,7 @@
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/panic_notifier.h>
+#include <linux/kmemleak.h>
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
@@ -1532,7 +1533,7 @@ void disable_trace_on_warning(void)
 bool tracer_tracing_is_on(struct trace_array *tr)
 {
 	if (tr->array_buffer.buffer)
-		return ring_buffer_record_is_on(tr->array_buffer.buffer);
+		return ring_buffer_record_is_set_on(tr->array_buffer.buffer);
 	return !tr->buffer_disabled;
 }
 
@@ -2320,7 +2321,7 @@ struct saved_cmdlines_buffer {
 	unsigned *map_cmdline_to_pid;
 	unsigned cmdline_num;
 	int cmdline_idx;
-	char *saved_cmdlines;
+	char saved_cmdlines[];
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
@@ -2334,47 +2335,60 @@ static inline void set_cmdline(int idx, const char *cmdline)
 	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
 }
 
-static int allocate_cmdlines_buffer(unsigned int val,
-				    struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+	kfree(s->map_cmdline_to_pid);
+	kmemleak_free(s);
+	free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
 {
+	struct saved_cmdlines_buffer *s;
+	struct page *page;
+	int orig_size, size;
+	int order;
+
+	/* Figure out how much is needed to hold the given number of cmdlines */
+	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+	order = get_order(orig_size);
+	size = 1 << (order + PAGE_SHIFT);
+	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		return NULL;
+
+	s = page_address(page);
+	kmemleak_alloc(s, size, 1, GFP_KERNEL);
+	memset(s, 0, sizeof(*s));
+
+	/* Round up to actual allocation */
+	val = (size - sizeof(*s)) / TASK_COMM_LEN;
+	s->cmdline_num = val;
+
 	s->map_cmdline_to_pid = kmalloc_array(val,
 					      sizeof(*s->map_cmdline_to_pid),
 					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid)
-		return -ENOMEM;
-
-	s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
-	if (!s->saved_cmdlines) {
-		kfree(s->map_cmdline_to_pid);
-		return -ENOMEM;
+	if (!s->map_cmdline_to_pid) {
+		free_saved_cmdlines_buffer(s);
+		return NULL;
 	}
 
 	s->cmdline_idx = 0;
-	s->cmdline_num = val;
 	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
 	       sizeof(s->map_pid_to_cmdline));
 	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
 	       val * sizeof(*s->map_cmdline_to_pid));
 
-	return 0;
+	return s;
 }
 
 static int trace_create_savedcmd(void)
 {
-	int ret;
-
-	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
-	if (!savedcmd)
-		return -ENOMEM;
+	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
 
-	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
-	if (ret < 0) {
-		kfree(savedcmd);
-		savedcmd = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
+	return savedcmd ? 0 : -ENOMEM;
 }
 
 int is_tracing_stopped(void)
@@ -6056,26 +6070,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
-	kfree(s->saved_cmdlines);
-	kfree(s->map_cmdline_to_pid);
-	kfree(s);
-}
-
 static int tracing_resize_saved_cmdlines(unsigned int val)
 {
 	struct saved_cmdlines_buffer *s, *savedcmd_temp;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = allocate_cmdlines_buffer(val);
 	if (!s)
 		return -ENOMEM;
 
-	if (allocate_cmdlines_buffer(val, s) < 0) {
-		kfree(s);
-		return -ENOMEM;
-	}
-
 	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
@@ -7291,6 +7293,8 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+#define TRACE_MARKER_MAX_SIZE		4096
+
 static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
@@ -7318,6 +7322,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if ((ssize_t)cnt < 0)
 		return -EINVAL;
 
+	if (cnt > TRACE_MARKER_MAX_SIZE)
+		cnt = TRACE_MARKER_MAX_SIZE;
+
 	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
  again:
 	size = cnt + meta_size;
@@ -7326,11 +7333,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt < FAULTED_SIZE)
 		size += FAULTED_SIZE - cnt;
 
-	if (size > TRACE_SEQ_BUFFER_SIZE) {
-		cnt -= size - TRACE_SEQ_BUFFER_SIZE;
-		goto again;
-	}
-
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
@@ -8391,6 +8393,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	return size;
 }
 
+static int tracing_buffers_flush(struct file *file, fl_owner_t id)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	return 0;
+}
+
 static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_buffer_info *info = file->private_data;
@@ -8402,12 +8418,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	__trace_array_put(iter->tr);
 
-	iter->wait_index++;
-	/* Make sure the waiters see the new wait_index */
-	smp_wmb();
-
-	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
-
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
@@ -8623,6 +8633,7 @@ static const struct file_operations tracing_buffers_fops = {
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
+	.flush		= tracing_buffers_flush,
 	.splice_read	= tracing_buffers_splice_read,
 	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
index ca224d53bfdc..5bbdbcbbde3c 100644
--- a/kernel/trace/trace_btf.c
+++ b/kernel/trace/trace_btf.c
@@ -91,8 +91,8 @@ retry:
 	for_each_member(i, type, member) {
 		if (!member->name_off) {
 			/* Anonymous union/struct: push it for later use */
-			type = btf_type_skip_modifiers(btf, member->type, &tid);
-			if (type && top < BTF_ANON_STACK_MAX) {
+			if (btf_type_skip_modifiers(btf, member->type, &tid) &&
+			    top < BTF_ANON_STACK_MAX) {
 				anon_stack[top].tid = tid;
 				anon_stack[top++].offset =
 					cur_offset + member->offset;
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index e7af286af4f1..c82b401a294d 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry,
 	if (is_dynamic) {
 		union trace_synth_field *data = &entry->fields[*n_u64];
 
+		len = fetch_store_strlen((unsigned long)str_val);
 		data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
-		data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
+		data->as_dynamic.len = len;
 
 		ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 46439e3bcec4..b33c3861fbbb 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	if (tracing_alloc_snapshot_instance(file->tr) != 0)
-		return 0;
+	int ret = tracing_alloc_snapshot_instance(file->tr);
+
+	if (ret < 0)
+		return ret;
 
 	return register_trigger(glob, data, file);
 }
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index bd0d01d00fb9..a8e28f9b9271 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	tlat = this_cpu_tmr_var();
 	tlat->count = 0;
 
+	hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
+	tlat->timer.function = timerlat_irq;
+
 	migrate_enable();
 	return 0;
 };
@@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 		tlat->tracing_thread = false;
 		tlat->kthread = current;
 
-		hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
-		tlat->timer.function = timerlat_irq;
-
 		/* Annotate now to drift new period */
 		tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 3e7fa44dc2b2..d8b302d01083 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1587,12 +1587,11 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
 {
 	struct print_entry *field;
 	struct trace_seq *s = &iter->seq;
-	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
 	seq_print_ip_sym(s, field->ip, flags);
-	trace_seq_printf(s, ": %.*s", max, field->buf);
+	trace_seq_printf(s, ": %s", field->buf);
 
 	return trace_handle_return(s);
 }
@@ -1601,11 +1600,10 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
 					 struct trace_event *event)
 {
 	struct print_entry *field;
-	int max = iter->ent_size - offsetof(struct print_entry, buf);
 
 	trace_assign_type(field, iter->ent);
 
-	trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
+	trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
 
 	return trace_handle_return(&iter->seq);
 }
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 4dc74d73fc1d..34289f9c6707 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 	if (!(ctx->flags & TPARG_FL_TEVENT) &&
 	    (strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
 	     strncmp(arg, "\\\"", 2) == 0)) {
-		/* The type of $comm must be "string", and not an array. */
-		if (parg->count || (t && strcmp(t, "string")))
+		/* The type of $comm must be "string", and not an array type. */
+		if (parg->count || (t && strcmp(t, "string"))) {
+			trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
+					NEED_STRING_TYPE);
 			goto out;
+		}
 		parg->type = find_fetch_type("string", ctx->flags);
 	} else
 		parg->type = find_fetch_type(t, ctx->flags);
@@ -1169,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 		trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
 		goto out;
 	}
-	parg->offset = *size;
-	*size += parg->type->size * (parg->count ?: 1);
-
-	ret = -ENOMEM;
-	if (parg->count) {
-		len = strlen(parg->type->fmttype) + 6;
-		parg->fmt = kmalloc(len, GFP_KERNEL);
-		if (!parg->fmt)
-			goto out;
-		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
-			 parg->count);
-	}
 
 	code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
 	if (!code)
@@ -1204,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
 				goto fail;
 		}
 	}
+	parg->offset = *size;
+	*size += parg->type->size * (parg->count ?: 1);
+
+	if (parg->count) {
+		len = strlen(parg->type->fmttype) + 6;
+		parg->fmt = kmalloc(len, GFP_KERNEL);
+		if (!parg->fmt) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+			 parg->count);
+	}
 
 	ret = -EINVAL;
 	/* Store operation */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 850d9ecb6765..c1877d018269 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(BAD_HYPHEN,		"Failed to parse single hyphen. Forgot '>'?"),	\
 	C(NO_BTF_FIELD,		"This field is not found."),	\
 	C(BAD_BTF_TID,		"Failed to get BTF type info."),\
-	C(BAD_TYPE4STR,		"This type does not fit for string."),
+	C(BAD_TYPE4STR,		"This type does not fit for string."),\
+	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 76e60faed892..bf2bdac46843 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -29,6 +29,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/signal.h>
 #include <linux/completion.h>
 #include <linux/workqueue.h>
@@ -53,10 +54,11 @@
 #include <linux/nmi.h>
 #include <linux/kvm_para.h>
 #include <linux/delay.h>
+#include <linux/irq_work.h>
 
 #include "workqueue_internal.h"
 
-enum {
+enum worker_pool_flags {
 	/*
 	 * worker_pool flags
 	 *
@@ -72,10 +74,17 @@ enum {
 	 * Note that DISASSOCIATED should be flipped only while holding
 	 * wq_pool_attach_mutex to avoid changing binding state while
 	 * worker_attach_to_pool() is in progress.
+	 *
+	 * As there can only be one concurrent BH execution context per CPU, a
+	 * BH pool is per-CPU and always DISASSOCIATED.
 	 */
-	POOL_MANAGER_ACTIVE	= 1 << 0,	/* being managed */
+	POOL_BH			= 1 << 0,	/* is a BH pool */
+	POOL_MANAGER_ACTIVE	= 1 << 1,	/* being managed */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
+	POOL_BH_DRAINING	= 1 << 3,	/* draining after CPU offline */
+};
 
+enum worker_flags {
 	/* worker flags */
 	WORKER_DIE		= 1 << 1,	/* die die die */
 	WORKER_IDLE		= 1 << 2,	/* is idle */
@@ -86,7 +95,13 @@ enum {
 
 	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_CPU_INTENSIVE |
 				  WORKER_UNBOUND | WORKER_REBOUND,
+};
 
+enum work_cancel_flags {
+	WORK_CANCEL_DELAYED	= 1 << 0,	/* canceling a delayed_work */
+};
+
+enum wq_internal_consts {
 	NR_STD_WORKER_POOLS	= 2,		/* # standard pools per cpu */
 
 	UNBOUND_POOL_HASH_ORDER	= 6,		/* hashed by pool->attrs */
@@ -108,10 +123,18 @@ enum {
 	RESCUER_NICE_LEVEL	= MIN_NICE,
 	HIGHPRI_NICE_LEVEL	= MIN_NICE,
 
-	WQ_NAME_LEN		= 24,
+	WQ_NAME_LEN		= 32,
 };
 
 /*
+ * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and
+ * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because
+ * msecs_to_jiffies() can't be an initializer.
+ */
+#define BH_WORKER_JIFFIES	msecs_to_jiffies(2)
+#define BH_WORKER_RESTARTS	10
+
+/*
  * Structure fields follow one of the following exclusion rules.
  *
  * I: Modifiable by initialization/destruction paths and read-only for
@@ -122,6 +145,9 @@ enum {
  *
  * L: pool->lock protected.  Access with pool->lock held.
  *
+ * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for
+ *     reads.
+ *
  * K: Only modified by worker while holding pool->lock. Can be safely read by
  *    self, while holding pool->lock or from IRQ context if %current is the
  *    kworker.
@@ -143,6 +169,9 @@ enum {
  *
  * WR: wq->mutex protected for writes.  RCU protected for reads.
  *
+ * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read
+ *     with READ_ONCE() without locking.
+ *
  * MD: wq_mayday_lock protected.
  *
  * WD: Used internally by the watchdog.
@@ -219,7 +248,7 @@ enum pool_workqueue_stats {
 };
 
 /*
- * The per-pool workqueue.  While queued, the lower WORK_STRUCT_FLAG_BITS
+ * The per-pool workqueue.  While queued, bits below WORK_PWQ_SHIFT
  * of work_struct->data are used for flags and the remaining high bits
  * point to the pwq; thus, pwqs need to be aligned at two's power of the
  * number of flag bits.
@@ -232,6 +261,7 @@ struct pool_workqueue {
 	int			refcnt;		/* L: reference count */
 	int			nr_in_flight[WORK_NR_COLORS];
 						/* L: nr of in_flight works */
+	bool			plugged;	/* L: execution suspended */
 
 	/*
 	 * nr_active management and WORK_STRUCT_INACTIVE:
@@ -240,18 +270,18 @@ struct pool_workqueue {
 	 * pwq->inactive_works instead of pool->worklist and marked with
 	 * WORK_STRUCT_INACTIVE.
 	 *
-	 * All work items marked with WORK_STRUCT_INACTIVE do not participate
-	 * in pwq->nr_active and all work items in pwq->inactive_works are
-	 * marked with WORK_STRUCT_INACTIVE.  But not all WORK_STRUCT_INACTIVE
-	 * work items are in pwq->inactive_works.  Some of them are ready to
-	 * run in pool->worklist or worker->scheduled.  Those work itmes are
-	 * only struct wq_barrier which is used for flush_work() and should
-	 * not participate in pwq->nr_active.  For non-barrier work item, it
-	 * is marked with WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works.
+	 * All work items marked with WORK_STRUCT_INACTIVE do not participate in
+	 * nr_active and all work items in pwq->inactive_works are marked with
+	 * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are
+	 * in pwq->inactive_works. Some of them are ready to run in
+	 * pool->worklist or worker->scheduled. Those work itmes are only struct
+	 * wq_barrier which is used for flush_work() and should not participate
+	 * in nr_active. For non-barrier work item, it is marked with
+	 * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works.
 	 */
 	int			nr_active;	/* L: nr of active works */
-	int			max_active;	/* L: max active works */
 	struct list_head	inactive_works;	/* L: inactive works */
+	struct list_head	pending_node;	/* LN: node on wq_node_nr_active->pending_pwqs */
 	struct list_head	pwqs_node;	/* WR: node on wq->pwqs */
 	struct list_head	mayday_node;	/* MD: node on wq->maydays */
 
@@ -265,7 +295,7 @@ struct pool_workqueue {
 	 */
 	struct kthread_work	release_work;
 	struct rcu_head		rcu;
-} __aligned(1 << WORK_STRUCT_FLAG_BITS);
+} __aligned(1 << WORK_STRUCT_PWQ_SHIFT);
 
 /*
  * Structure used to wait for workqueue flush.
@@ -279,6 +309,26 @@ struct wq_flusher {
 struct wq_device;
 
 /*
+ * Unlike in a per-cpu workqueue where max_active limits its concurrency level
+ * on each CPU, in an unbound workqueue, max_active applies to the whole system.
+ * As sharing a single nr_active across multiple sockets can be very expensive,
+ * the counting and enforcement is per NUMA node.
+ *
+ * The following struct is used to enforce per-node max_active. When a pwq wants
+ * to start executing a work item, it should increment ->nr using
+ * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over
+ * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish
+ * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in
+ * round-robin order.
+ */
+struct wq_node_nr_active {
+	int			max;		/* per-node max_active */
+	atomic_t		nr;		/* per-node nr_active */
+	raw_spinlock_t		lock;		/* nests inside pool locks */
+	struct list_head	pending_pwqs;	/* LN: pwqs with inactive works */
+};
+
+/*
  * The externally visible workqueue.  It relays the issued work items to
  * the appropriate worker_pool through its pool_workqueues.
  */
@@ -298,10 +348,15 @@ struct workqueue_struct {
 	struct worker		*rescuer;	/* MD: rescue worker */
 
 	int			nr_drainers;	/* WQ: drain in progress */
-	int			saved_max_active; /* WQ: saved pwq max_active */
+
+	/* See alloc_workqueue() function comment for info on min/max_active */
+	int			max_active;	/* WO: max active works */
+	int			min_active;	/* WO: min active works */
+	int			saved_max_active; /* WQ: saved max_active */
+	int			saved_min_active; /* WQ: saved min_active */
 
 	struct workqueue_attrs	*unbound_attrs;	/* PW: only for unbound wqs */
-	struct pool_workqueue	*dfl_pwq;	/* PW: only for unbound wqs */
+	struct pool_workqueue __rcu *dfl_pwq;   /* PW: only for unbound wqs */
 
 #ifdef CONFIG_SYSFS
 	struct wq_device	*wq_dev;	/* I: for sysfs interface */
@@ -323,10 +378,9 @@ struct workqueue_struct {
 	/* hot fields used during command issue, aligned to cacheline */
 	unsigned int		flags ____cacheline_aligned; /* WQ: WQ_* flags */
 	struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */
+	struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */
 };
 
-static struct kmem_cache *pwq_cache;
-
 /*
  * Each pod type describes how CPUs should be grouped for unbound workqueues.
  * See the comment above workqueue_attrs->affn_scope.
@@ -338,16 +392,13 @@ struct wq_pod_type {
 	int			*cpu_pod;	/* cpu -> pod */
 };
 
-static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
-static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
-
 static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
-	[WQ_AFFN_DFL]			= "default",
-	[WQ_AFFN_CPU]			= "cpu",
-	[WQ_AFFN_SMT]			= "smt",
-	[WQ_AFFN_CACHE]			= "cache",
-	[WQ_AFFN_NUMA]			= "numa",
-	[WQ_AFFN_SYSTEM]		= "system",
+	[WQ_AFFN_DFL]		= "default",
+	[WQ_AFFN_CPU]		= "cpu",
+	[WQ_AFFN_SMT]		= "smt",
+	[WQ_AFFN_CACHE]		= "cache",
+	[WQ_AFFN_NUMA]		= "numa",
+	[WQ_AFFN_SYSTEM]	= "system",
 };
 
 /*
@@ -359,12 +410,22 @@ static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = {
  */
 static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
 module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
+#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT
+static unsigned int wq_cpu_intensive_warning_thresh = 4;
+module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644);
+#endif
 
 /* see the comment above the definition of WQ_POWER_EFFICIENT */
 static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
 module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
 static bool wq_online;			/* can kworkers be created yet? */
+static bool wq_topo_initialized __read_mostly = false;
+
+static struct kmem_cache *pwq_cache;
+
+static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES];
+static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE;
 
 /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */
 static struct workqueue_attrs *wq_update_pod_attrs_buf;
@@ -405,8 +466,17 @@ static bool wq_debug_force_rr_cpu = false;
 #endif
 module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
+/* to raise softirq for the BH worker pools on other CPUs */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS],
+				     bh_pool_irq_works);
+
+/* the BH worker pools */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
+				     bh_worker_pools);
+
 /* the per-cpu worker pools */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
+				     cpu_worker_pools);
 
 static DEFINE_IDR(worker_pool_idr);	/* PR: idr of all pools */
 
@@ -420,6 +490,12 @@ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
 
 /*
+ * Used to synchronize multiple cancel_sync attempts on the same work item. See
+ * work_grab_pending() and __cancel_work_sync().
+ */
+static DECLARE_WAIT_QUEUE_HEAD(wq_cancel_waitq);
+
+/*
  * I: kthread_worker to release pwq's. pwq release needs to be bounced to a
  * process context while holding a pool lock. Bounce to a dedicated kthread
  * worker to avoid A-A deadlocks.
@@ -440,6 +516,10 @@ struct workqueue_struct *system_power_efficient_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_power_efficient_wq);
 struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
+struct workqueue_struct *system_bh_wq;
+EXPORT_SYMBOL_GPL(system_bh_wq);
+struct workqueue_struct *system_bh_highpri_wq;
+EXPORT_SYMBOL_GPL(system_bh_highpri_wq);
 
 static int worker_thread(void *__worker);
 static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
@@ -450,16 +530,21 @@ static void show_one_worker_pool(struct worker_pool *pool);
 #include <trace/events/workqueue.h>
 
 #define assert_rcu_or_pool_mutex()					\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() &&			\
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU or wq_pool_mutex should be held")
 
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() &&			\
 			 !lockdep_is_held(&wq->mutex) &&		\
 			 !lockdep_is_held(&wq_pool_mutex),		\
 			 "RCU, wq->mutex or wq_pool_mutex should be held")
 
+#define for_each_bh_worker_pool(pool, cpu)				\
+	for ((pool) = &per_cpu(bh_worker_pools, cpu)[0];		\
+	     (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
+	     (pool)++)
+
 #define for_each_cpu_worker_pool(pool, cpu)				\
 	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\
 	     (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
@@ -632,6 +717,36 @@ static int worker_pool_assign_id(struct worker_pool *pool)
 	return ret;
 }
 
+static struct pool_workqueue __rcu **
+unbound_pwq_slot(struct workqueue_struct *wq, int cpu)
+{
+       if (cpu >= 0)
+               return per_cpu_ptr(wq->cpu_pwq, cpu);
+       else
+               return &wq->dfl_pwq;
+}
+
+/* @cpu < 0 for dfl_pwq */
+static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu)
+{
+	return rcu_dereference_check(*unbound_pwq_slot(wq, cpu),
+				     lockdep_is_held(&wq_pool_mutex) ||
+				     lockdep_is_held(&wq->mutex));
+}
+
+/**
+ * unbound_effective_cpumask - effective cpumask of an unbound workqueue
+ * @wq: workqueue of interest
+ *
+ * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which
+ * is masked with wq_unbound_cpumask to determine the effective cpumask. The
+ * default pwq is always mapped to the pool with the current effective cpumask.
+ */
+static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq)
+{
+	return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask;
+}
+
 static unsigned int work_color_to_flags(int color)
 {
 	return color << WORK_STRUCT_COLOR_SHIFT;
@@ -653,10 +768,9 @@ static int work_next_color(int color)
  * contain the pointer to the queued pwq.  Once execution starts, the flag
  * is cleared and the high bits contain OFFQ flags and pool ID.
  *
- * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling()
- * and clear_work_data() can be used to set the pwq, pool or clear
- * work->data.  These functions should only be called while the work is
- * owned - ie. while the PENDING bit is set.
+ * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling()
+ * can be used to set the pwq, pool or clear work->data. These functions should
+ * only be called while the work is owned - ie. while the PENDING bit is set.
  *
  * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq
  * corresponding to a work.  Pool is available once the work has been
@@ -668,29 +782,28 @@ static int work_next_color(int color)
  * but stay off timer and worklist for arbitrarily long and nobody should
  * try to steal the PENDING bit.
  */
-static inline void set_work_data(struct work_struct *work, unsigned long data,
-				 unsigned long flags)
+static inline void set_work_data(struct work_struct *work, unsigned long data)
 {
 	WARN_ON_ONCE(!work_pending(work));
-	atomic_long_set(&work->data, data | flags | work_static(work));
+	atomic_long_set(&work->data, data | work_static(work));
 }
 
 static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
-			 unsigned long extra_flags)
+			 unsigned long flags)
 {
-	set_work_data(work, (unsigned long)pwq,
-		      WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
+	set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING |
+		      WORK_STRUCT_PWQ | flags);
 }
 
 static void set_work_pool_and_keep_pending(struct work_struct *work,
-					   int pool_id)
+					   int pool_id, unsigned long flags)
 {
-	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT,
-		      WORK_STRUCT_PENDING);
+	set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
+		      WORK_STRUCT_PENDING | flags);
 }
 
 static void set_work_pool_and_clear_pending(struct work_struct *work,
-					    int pool_id)
+					    int pool_id, unsigned long flags)
 {
 	/*
 	 * The following wmb is paired with the implied mb in
@@ -699,7 +812,8 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	 * owner.
 	 */
 	smp_wmb();
-	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+	set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) |
+		      flags);
 	/*
 	 * The following mb guarantees that previous clear of a PENDING bit
 	 * will not be reordered with any speculative LOADS or STORES from
@@ -731,15 +845,9 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	smp_mb();
 }
 
-static void clear_work_data(struct work_struct *work)
-{
-	smp_wmb();	/* see set_work_pool_and_clear_pending() */
-	set_work_data(work, WORK_STRUCT_NO_POOL, 0);
-}
-
 static inline struct pool_workqueue *work_struct_pwq(unsigned long data)
 {
-	return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK);
+	return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK);
 }
 
 static struct pool_workqueue *get_work_pwq(struct work_struct *work)
@@ -806,7 +914,7 @@ static void mark_work_canceling(struct work_struct *work)
 	unsigned long pool_id = get_work_pool_id(work);
 
 	pool_id <<= WORK_OFFQ_POOL_SHIFT;
-	set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING);
+	set_work_data(work, pool_id | WORK_STRUCT_PENDING | WORK_OFFQ_CANCELING);
 }
 
 static bool work_is_canceling(struct work_struct *work)
@@ -1101,6 +1209,29 @@ static bool assign_work(struct work_struct *work, struct worker *worker,
 	return true;
 }
 
+static struct irq_work *bh_pool_irq_work(struct worker_pool *pool)
+{
+	int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0;
+
+	return &per_cpu(bh_pool_irq_works, pool->cpu)[high];
+}
+
+static void kick_bh_pool(struct worker_pool *pool)
+{
+#ifdef CONFIG_SMP
+	/* see drain_dead_softirq_workfn() for BH_DRAINING */
+	if (unlikely(pool->cpu != smp_processor_id() &&
+		     !(pool->flags & POOL_BH_DRAINING))) {
+		irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu);
+		return;
+	}
+#endif
+	if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+		raise_softirq_irqoff(HI_SOFTIRQ);
+	else
+		raise_softirq_irqoff(TASKLET_SOFTIRQ);
+}
+
 /**
  * kick_pool - wake up an idle worker if necessary
  * @pool: pool to kick
@@ -1118,6 +1249,11 @@ static bool kick_pool(struct worker_pool *pool)
 	if (!need_more_worker(pool) || !worker)
 		return false;
 
+	if (pool->flags & POOL_BH) {
+		kick_bh_pool(pool);
+		return true;
+	}
+
 	p = worker->task;
 
 #ifdef CONFIG_SMP
@@ -1198,11 +1334,13 @@ restart:
 		u64 cnt;
 
 		/*
-		 * Start reporting from the fourth time and back off
+		 * Start reporting from the warning_thresh and back off
 		 * exponentially.
 		 */
 		cnt = atomic64_inc_return_relaxed(&ent->cnt);
-		if (cnt >= 4 && is_power_of_2(cnt))
+		if (wq_cpu_intensive_warning_thresh &&
+		    cnt >= wq_cpu_intensive_warning_thresh &&
+		    is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh))
 			printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n",
 					ent->func, wq_cpu_intensive_thresh_us,
 					atomic64_read(&ent->cnt));
@@ -1231,10 +1369,12 @@ restart:
 
 	ent = &wci_ents[wci_nr_ents++];
 	ent->func = func;
-	atomic64_set(&ent->cnt, 1);
+	atomic64_set(&ent->cnt, 0);
 	hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func);
 
 	raw_spin_unlock(&wci_lock);
+
+	goto restart;
 }
 
 #else	/* CONFIG_WQ_CPU_INTENSIVE_REPORT */
@@ -1402,6 +1542,74 @@ work_func_t wq_worker_last_func(struct task_struct *task)
 }
 
 /**
+ * wq_node_nr_active - Determine wq_node_nr_active to use
+ * @wq: workqueue of interest
+ * @node: NUMA node, can be %NUMA_NO_NODE
+ *
+ * Determine wq_node_nr_active to use for @wq on @node. Returns:
+ *
+ * - %NULL for per-cpu workqueues as they don't need to use shared nr_active.
+ *
+ * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE.
+ *
+ * - Otherwise, node_nr_active[@node].
+ */
+static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq,
+						   int node)
+{
+	if (!(wq->flags & WQ_UNBOUND))
+		return NULL;
+
+	if (node == NUMA_NO_NODE)
+		node = nr_node_ids;
+
+	return wq->node_nr_active[node];
+}
+
+/**
+ * wq_update_node_max_active - Update per-node max_actives to use
+ * @wq: workqueue to update
+ * @off_cpu: CPU that's going down, -1 if a CPU is not going down
+ *
+ * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is
+ * distributed among nodes according to the proportions of numbers of online
+ * cpus. The result is always between @wq->min_active and max_active.
+ */
+static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu)
+{
+	struct cpumask *effective = unbound_effective_cpumask(wq);
+	int min_active = READ_ONCE(wq->min_active);
+	int max_active = READ_ONCE(wq->max_active);
+	int total_cpus, node;
+
+	lockdep_assert_held(&wq->mutex);
+
+	if (!wq_topo_initialized)
+		return;
+
+	if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective))
+		off_cpu = -1;
+
+	total_cpus = cpumask_weight_and(effective, cpu_online_mask);
+	if (off_cpu >= 0)
+		total_cpus--;
+
+	for_each_node(node) {
+		int node_cpus;
+
+		node_cpus = cpumask_weight_and(effective, cpumask_of_node(node));
+		if (off_cpu >= 0 && cpu_to_node(off_cpu) == node)
+			node_cpus--;
+
+		wq_node_nr_active(wq, node)->max =
+			clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus),
+			      min_active, max_active);
+	}
+
+	wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active;
+}
+
+/**
  * get_pwq - get an extra reference on the specified pool_workqueue
  * @pwq: pool_workqueue to get
  *
@@ -1453,24 +1661,336 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq)
 	}
 }
 
-static void pwq_activate_inactive_work(struct work_struct *work)
+static bool pwq_is_empty(struct pool_workqueue *pwq)
 {
-	struct pool_workqueue *pwq = get_work_pwq(work);
+	return !pwq->nr_active && list_empty(&pwq->inactive_works);
+}
 
+static void __pwq_activate_work(struct pool_workqueue *pwq,
+				struct work_struct *work)
+{
+	unsigned long *wdb = work_data_bits(work);
+
+	WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE));
 	trace_workqueue_activate_work(work);
 	if (list_empty(&pwq->pool->worklist))
 		pwq->pool->watchdog_ts = jiffies;
 	move_linked_works(work, &pwq->pool->worklist, NULL);
-	__clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work));
+	__clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb);
+}
+
+/**
+ * pwq_activate_work - Activate a work item if inactive
+ * @pwq: pool_workqueue @work belongs to
+ * @work: work item to activate
+ *
+ * Returns %true if activated. %false if already active.
+ */
+static bool pwq_activate_work(struct pool_workqueue *pwq,
+			      struct work_struct *work)
+{
+	struct worker_pool *pool = pwq->pool;
+	struct wq_node_nr_active *nna;
+
+	lockdep_assert_held(&pool->lock);
+
+	if (!(*work_data_bits(work) & WORK_STRUCT_INACTIVE))
+		return false;
+
+	nna = wq_node_nr_active(pwq->wq, pool->node);
+	if (nna)
+		atomic_inc(&nna->nr);
+
 	pwq->nr_active++;
+	__pwq_activate_work(pwq, work);
+	return true;
+}
+
+static bool tryinc_node_nr_active(struct wq_node_nr_active *nna)
+{
+	int max = READ_ONCE(nna->max);
+
+	while (true) {
+		int old, tmp;
+
+		old = atomic_read(&nna->nr);
+		if (old >= max)
+			return false;
+		tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1);
+		if (tmp == old)
+			return true;
+	}
+}
+
+/**
+ * pwq_tryinc_nr_active - Try to increment nr_active for a pwq
+ * @pwq: pool_workqueue of interest
+ * @fill: max_active may have increased, try to increase concurrency level
+ *
+ * Try to increment nr_active for @pwq. Returns %true if an nr_active count is
+ * successfully obtained. %false otherwise.
+ */
+static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill)
+{
+	struct workqueue_struct *wq = pwq->wq;
+	struct worker_pool *pool = pwq->pool;
+	struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node);
+	bool obtained = false;
+
+	lockdep_assert_held(&pool->lock);
+
+	if (!nna) {
+		/* BH or per-cpu workqueue, pwq->nr_active is sufficient */
+		obtained = pwq->nr_active < READ_ONCE(wq->max_active);
+		goto out;
+	}
+
+	if (unlikely(pwq->plugged))
+		return false;
+
+	/*
+	 * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is
+	 * already waiting on $nna, pwq_dec_nr_active() will maintain the
+	 * concurrency level. Don't jump the line.
+	 *
+	 * We need to ignore the pending test after max_active has increased as
+	 * pwq_dec_nr_active() can only maintain the concurrency level but not
+	 * increase it. This is indicated by @fill.
+	 */
+	if (!list_empty(&pwq->pending_node) && likely(!fill))
+		goto out;
+
+	obtained = tryinc_node_nr_active(nna);
+	if (obtained)
+		goto out;
+
+	/*
+	 * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs
+	 * and try again. The smp_mb() is paired with the implied memory barrier
+	 * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either
+	 * we see the decremented $nna->nr or they see non-empty
+	 * $nna->pending_pwqs.
+	 */
+	raw_spin_lock(&nna->lock);
+
+	if (list_empty(&pwq->pending_node))
+		list_add_tail(&pwq->pending_node, &nna->pending_pwqs);
+	else if (likely(!fill))
+		goto out_unlock;
+
+	smp_mb();
+
+	obtained = tryinc_node_nr_active(nna);
+
+	/*
+	 * If @fill, @pwq might have already been pending. Being spuriously
+	 * pending in cold paths doesn't affect anything. Let's leave it be.
+	 */
+	if (obtained && likely(!fill))
+		list_del_init(&pwq->pending_node);
+
+out_unlock:
+	raw_spin_unlock(&nna->lock);
+out:
+	if (obtained)
+		pwq->nr_active++;
+	return obtained;
+}
+
+/**
+ * pwq_activate_first_inactive - Activate the first inactive work item on a pwq
+ * @pwq: pool_workqueue of interest
+ * @fill: max_active may have increased, try to increase concurrency level
+ *
+ * Activate the first inactive work item of @pwq if available and allowed by
+ * max_active limit.
+ *
+ * Returns %true if an inactive work item has been activated. %false if no
+ * inactive work item is found or max_active limit is reached.
+ */
+static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill)
+{
+	struct work_struct *work =
+		list_first_entry_or_null(&pwq->inactive_works,
+					 struct work_struct, entry);
+
+	if (work && pwq_tryinc_nr_active(pwq, fill)) {
+		__pwq_activate_work(pwq, work);
+		return true;
+	} else {
+		return false;
+	}
 }
 
-static void pwq_activate_first_inactive(struct pool_workqueue *pwq)
+/**
+ * unplug_oldest_pwq - unplug the oldest pool_workqueue
+ * @wq: workqueue_struct where its oldest pwq is to be unplugged
+ *
+ * This function should only be called for ordered workqueues where only the
+ * oldest pwq is unplugged, the others are plugged to suspend execution to
+ * ensure proper work item ordering::
+ *
+ *    dfl_pwq --------------+     [P] - plugged
+ *                          |
+ *                          v
+ *    pwqs -> A -> B [P] -> C [P] (newest)
+ *            |    |        |
+ *            1    3        5
+ *            |    |        |
+ *            2    4        6
+ *
+ * When the oldest pwq is drained and removed, this function should be called
+ * to unplug the next oldest one to start its work item execution. Note that
+ * pwq's are linked into wq->pwqs with the oldest first, so the first one in
+ * the list is the oldest.
+ */
+static void unplug_oldest_pwq(struct workqueue_struct *wq)
 {
-	struct work_struct *work = list_first_entry(&pwq->inactive_works,
-						    struct work_struct, entry);
+	struct pool_workqueue *pwq;
 
-	pwq_activate_inactive_work(work);
+	lockdep_assert_held(&wq->mutex);
+
+	/* Caller should make sure that pwqs isn't empty before calling */
+	pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue,
+				       pwqs_node);
+	raw_spin_lock_irq(&pwq->pool->lock);
+	if (pwq->plugged) {
+		pwq->plugged = false;
+		if (pwq_activate_first_inactive(pwq, true))
+			kick_pool(pwq->pool);
+	}
+	raw_spin_unlock_irq(&pwq->pool->lock);
+}
+
+/**
+ * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active
+ * @nna: wq_node_nr_active to activate a pending pwq for
+ * @caller_pool: worker_pool the caller is locking
+ *
+ * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked.
+ * @caller_pool may be unlocked and relocked to lock other worker_pools.
+ */
+static void node_activate_pending_pwq(struct wq_node_nr_active *nna,
+				      struct worker_pool *caller_pool)
+{
+	struct worker_pool *locked_pool = caller_pool;
+	struct pool_workqueue *pwq;
+	struct work_struct *work;
+
+	lockdep_assert_held(&caller_pool->lock);
+
+	raw_spin_lock(&nna->lock);
+retry:
+	pwq = list_first_entry_or_null(&nna->pending_pwqs,
+				       struct pool_workqueue, pending_node);
+	if (!pwq)
+		goto out_unlock;
+
+	/*
+	 * If @pwq is for a different pool than @locked_pool, we need to lock
+	 * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock
+	 * / lock dance. For that, we also need to release @nna->lock as it's
+	 * nested inside pool locks.
+	 */
+	if (pwq->pool != locked_pool) {
+		raw_spin_unlock(&locked_pool->lock);
+		locked_pool = pwq->pool;
+		if (!raw_spin_trylock(&locked_pool->lock)) {
+			raw_spin_unlock(&nna->lock);
+			raw_spin_lock(&locked_pool->lock);
+			raw_spin_lock(&nna->lock);
+			goto retry;
+		}
+	}
+
+	/*
+	 * $pwq may not have any inactive work items due to e.g. cancellations.
+	 * Drop it from pending_pwqs and see if there's another one.
+	 */
+	work = list_first_entry_or_null(&pwq->inactive_works,
+					struct work_struct, entry);
+	if (!work) {
+		list_del_init(&pwq->pending_node);
+		goto retry;
+	}
+
+	/*
+	 * Acquire an nr_active count and activate the inactive work item. If
+	 * $pwq still has inactive work items, rotate it to the end of the
+	 * pending_pwqs so that we round-robin through them. This means that
+	 * inactive work items are not activated in queueing order which is fine
+	 * given that there has never been any ordering across different pwqs.
+	 */
+	if (likely(tryinc_node_nr_active(nna))) {
+		pwq->nr_active++;
+		__pwq_activate_work(pwq, work);
+
+		if (list_empty(&pwq->inactive_works))
+			list_del_init(&pwq->pending_node);
+		else
+			list_move_tail(&pwq->pending_node, &nna->pending_pwqs);
+
+		/* if activating a foreign pool, make sure it's running */
+		if (pwq->pool != caller_pool)
+			kick_pool(pwq->pool);
+	}
+
+out_unlock:
+	raw_spin_unlock(&nna->lock);
+	if (locked_pool != caller_pool) {
+		raw_spin_unlock(&locked_pool->lock);
+		raw_spin_lock(&caller_pool->lock);
+	}
+}
+
+/**
+ * pwq_dec_nr_active - Retire an active count
+ * @pwq: pool_workqueue of interest
+ *
+ * Decrement @pwq's nr_active and try to activate the first inactive work item.
+ * For unbound workqueues, this function may temporarily drop @pwq->pool->lock.
+ */
+static void pwq_dec_nr_active(struct pool_workqueue *pwq)
+{
+	struct worker_pool *pool = pwq->pool;
+	struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node);
+
+	lockdep_assert_held(&pool->lock);
+
+	/*
+	 * @pwq->nr_active should be decremented for both percpu and unbound
+	 * workqueues.
+	 */
+	pwq->nr_active--;
+
+	/*
+	 * For a percpu workqueue, it's simple. Just need to kick the first
+	 * inactive work item on @pwq itself.
+	 */
+	if (!nna) {
+		pwq_activate_first_inactive(pwq, false);
+		return;
+	}
+
+	/*
+	 * If @pwq is for an unbound workqueue, it's more complicated because
+	 * multiple pwqs and pools may be sharing the nr_active count. When a
+	 * pwq needs to wait for an nr_active count, it puts itself on
+	 * $nna->pending_pwqs. The following atomic_dec_return()'s implied
+	 * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to
+	 * guarantee that either we see non-empty pending_pwqs or they see
+	 * decremented $nna->nr.
+	 *
+	 * $nna->max may change as CPUs come online/offline and @pwq->wq's
+	 * max_active gets updated. However, it is guaranteed to be equal to or
+	 * larger than @pwq->wq->min_active which is above zero unless freezing.
+	 * This maintains the forward progress guarantee.
+	 */
+	if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max))
+		return;
+
+	if (!list_empty(&nna->pending_pwqs))
+		node_activate_pending_pwq(nna, pool);
 }
 
 /**
@@ -1481,6 +2001,11 @@ static void pwq_activate_first_inactive(struct pool_workqueue *pwq)
  * A work either has completed or is removed from pending queue,
  * decrement nr_in_flight of its pwq and handle workqueue flushing.
  *
+ * NOTE:
+ * For unbound workqueues, this function may temporarily drop @pwq->pool->lock
+ * and thus should be called after all other state updates for the in-flight
+ * work item is complete.
+ *
  * CONTEXT:
  * raw_spin_lock_irq(pool->lock).
  */
@@ -1488,14 +2013,8 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_
 {
 	int color = get_work_color(work_data);
 
-	if (!(work_data & WORK_STRUCT_INACTIVE)) {
-		pwq->nr_active--;
-		if (!list_empty(&pwq->inactive_works)) {
-			/* one down, submit an inactive one */
-			if (pwq->nr_active < pwq->max_active)
-				pwq_activate_first_inactive(pwq);
-		}
-	}
+	if (!(work_data & WORK_STRUCT_INACTIVE))
+		pwq_dec_nr_active(pwq);
 
 	pwq->nr_in_flight[color]--;
 
@@ -1523,8 +2042,8 @@ out_put:
 /**
  * try_to_grab_pending - steal work item from worklist and disable irq
  * @work: work item to steal
- * @is_dwork: @work is a delayed_work
- * @flags: place to store irq state
+ * @cflags: %WORK_CANCEL_ flags
+ * @irq_flags: place to store irq state
  *
  * Try to grab PENDING bit of @work.  This function can handle @work in any
  * stable state - idle, on timer or on worklist.
@@ -1546,20 +2065,20 @@ out_put:
  * irqsafe, ensures that we return -EAGAIN for finite short period of time.
  *
  * On successful return, >= 0, irq is disabled and the caller is
- * responsible for releasing it using local_irq_restore(*@flags).
+ * responsible for releasing it using local_irq_restore(*@irq_flags).
  *
  * This function is safe to call from any context including IRQ handler.
  */
-static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
-			       unsigned long *flags)
+static int try_to_grab_pending(struct work_struct *work, u32 cflags,
+			       unsigned long *irq_flags)
 {
 	struct worker_pool *pool;
 	struct pool_workqueue *pwq;
 
-	local_irq_save(*flags);
+	local_irq_save(*irq_flags);
 
 	/* try to steal the timer if it exists */
-	if (is_dwork) {
+	if (cflags & WORK_CANCEL_DELAYED) {
 		struct delayed_work *dwork = to_delayed_work(work);
 
 		/*
@@ -1595,6 +2114,8 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 	 */
 	pwq = get_work_pwq(work);
 	if (pwq && pwq->pool == pool) {
+		unsigned long work_data;
+
 		debug_work_deactivate(work);
 
 		/*
@@ -1608,14 +2129,19 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 		 * management later on and cause stall.  Make sure the work
 		 * item is activated before grabbing.
 		 */
-		if (*work_data_bits(work) & WORK_STRUCT_INACTIVE)
-			pwq_activate_inactive_work(work);
+		pwq_activate_work(pwq, work);
 
 		list_del_init(&work->entry);
-		pwq_dec_nr_in_flight(pwq, *work_data_bits(work));
 
-		/* work->data points to pwq iff queued, point to pool */
-		set_work_pool_and_keep_pending(work, pool->id);
+		/*
+		 * work->data points to pwq iff queued. Let's point to pool. As
+		 * this destroys work->data needed by the next step, stash it.
+		 */
+		work_data = *work_data_bits(work);
+		set_work_pool_and_keep_pending(work, pool->id, 0);
+
+		/* must be the last step, see the function comment */
+		pwq_dec_nr_in_flight(pwq, work_data);
 
 		raw_spin_unlock(&pool->lock);
 		rcu_read_unlock();
@@ -1624,13 +2150,82 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 	raw_spin_unlock(&pool->lock);
 fail:
 	rcu_read_unlock();
-	local_irq_restore(*flags);
+	local_irq_restore(*irq_flags);
 	if (work_is_canceling(work))
 		return -ENOENT;
 	cpu_relax();
 	return -EAGAIN;
 }
 
+struct cwt_wait {
+	wait_queue_entry_t	wait;
+	struct work_struct	*work;
+};
+
+static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
+{
+	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+	if (cwait->work != key)
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+/**
+ * work_grab_pending - steal work item from worklist and disable irq
+ * @work: work item to steal
+ * @cflags: %WORK_CANCEL_ flags
+ * @irq_flags: place to store IRQ state
+ *
+ * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer
+ * or on worklist.
+ *
+ * Must be called in process context. IRQ is disabled on return with IRQ state
+ * stored in *@irq_flags. The caller is responsible for re-enabling it using
+ * local_irq_restore().
+ *
+ * Returns %true if @work was pending. %false if idle.
+ */
+static bool work_grab_pending(struct work_struct *work, u32 cflags,
+			      unsigned long *irq_flags)
+{
+	struct cwt_wait cwait;
+	int ret;
+
+	might_sleep();
+repeat:
+	ret = try_to_grab_pending(work, cflags, irq_flags);
+	if (likely(ret >= 0))
+		return ret;
+	if (ret != -ENOENT)
+		goto repeat;
+
+	/*
+	 * Someone is already canceling. Wait for it to finish. flush_work()
+	 * doesn't work for PREEMPT_NONE because we may get woken up between
+	 * @work's completion and the other canceling task resuming and clearing
+	 * CANCELING - flush_work() will return false immediately as @work is no
+	 * longer busy, try_to_grab_pending() will return -ENOENT as @work is
+	 * still being canceled and the other canceling task won't be able to
+	 * clear CANCELING as we're hogging the CPU.
+	 *
+	 * Let's wait for completion using a waitqueue. As this may lead to the
+	 * thundering herd problem, use a custom wake function which matches
+	 * @work along with exclusive wait and wakeup.
+	 */
+	init_wait(&cwait.wait);
+	cwait.wait.func = cwt_wakefn;
+	cwait.work = work;
+
+	prepare_to_wait_exclusive(&wq_cancel_waitq, &cwait.wait,
+				  TASK_UNINTERRUPTIBLE);
+	if (work_is_canceling(work))
+		schedule();
+	finish_wait(&wq_cancel_waitq, &cwait.wait);
+
+	goto repeat;
+}
+
 /**
  * insert_work - insert a work into a pool
  * @pwq: pwq @work belongs to
@@ -1718,7 +2313,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 */
 	lockdep_assert_irqs_disabled();
 
-
 	/*
 	 * For a draining wq, only works from the same workqueue are
 	 * allowed. The __WQ_DESTROYING helps to spot the issue that
@@ -1793,12 +2387,16 @@ retry:
 	pwq->nr_in_flight[pwq->work_color]++;
 	work_flags = work_color_to_flags(pwq->work_color);
 
-	if (likely(pwq->nr_active < pwq->max_active)) {
+	/*
+	 * Limit the number of concurrently active work items to max_active.
+	 * @work must also queue behind existing inactive work items to maintain
+	 * ordering when max_active changes. See wq_adjust_max_active().
+	 */
+	if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) {
 		if (list_empty(&pool->worklist))
 			pool->watchdog_ts = jiffies;
 
 		trace_workqueue_activate_work(work);
-		pwq->nr_active++;
 		insert_work(pwq, work, &pool->worklist, work_flags);
 		kick_pool(pool);
 	} else {
@@ -1829,16 +2427,16 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq,
 		   struct work_struct *work)
 {
 	bool ret = false;
-	unsigned long flags;
+	unsigned long irq_flags;
 
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		__queue_work(cpu, wq, work);
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL(queue_work_on);
@@ -1895,7 +2493,7 @@ static int select_numa_node_cpu(int node)
 bool queue_work_node(int node, struct workqueue_struct *wq,
 		     struct work_struct *work)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	bool ret = false;
 
 	/*
@@ -1909,7 +2507,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq,
 	 */
 	WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND));
 
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		int cpu = select_numa_node_cpu(node);
@@ -1918,7 +2516,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq,
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(queue_work_node);
@@ -1958,10 +2556,18 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	if (unlikely(cpu != WORK_CPU_UNBOUND))
+	if (housekeeping_enabled(HK_TYPE_TIMER)) {
+		/* If the current cpu is a housekeeping cpu, use it. */
+		cpu = smp_processor_id();
+		if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER))
+			cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
 		add_timer_on(timer, cpu);
-	else
-		add_timer(timer);
+	} else {
+		if (likely(cpu == WORK_CPU_UNBOUND))
+			add_timer_global(timer);
+		else
+			add_timer_on(timer, cpu);
+	}
 }
 
 /**
@@ -1980,17 +2586,17 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 {
 	struct work_struct *work = &dwork->work;
 	bool ret = false;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/* read the comment in __queue_work() */
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		__queue_delayed_work(cpu, wq, dwork, delay);
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
 	return ret;
 }
 EXPORT_SYMBOL(queue_delayed_work_on);
@@ -2016,16 +2622,17 @@ EXPORT_SYMBOL(queue_delayed_work_on);
 bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
 			 struct delayed_work *dwork, unsigned long delay)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	int ret;
 
 	do {
-		ret = try_to_grab_pending(&dwork->work, true, &flags);
+		ret = try_to_grab_pending(&dwork->work, WORK_CANCEL_DELAYED,
+					  &irq_flags);
 	} while (unlikely(ret == -EAGAIN));
 
 	if (likely(ret >= 0)) {
 		__queue_delayed_work(cpu, wq, dwork, delay);
-		local_irq_restore(flags);
+		local_irq_restore(irq_flags);
 	}
 
 	/* -ENOENT from try_to_grab_pending() becomes %true */
@@ -2100,19 +2707,21 @@ static cpumask_t *pool_allowed_cpus(struct worker_pool *pool)
  * cpu-[un]hotplugs.
  */
 static void worker_attach_to_pool(struct worker *worker,
-				   struct worker_pool *pool)
+				  struct worker_pool *pool)
 {
 	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
-	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
-	 * stable across this function.  See the comments above the flag
-	 * definition for details.
+	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable
+	 * across this function. See the comments above the flag definition for
+	 * details. BH workers are, while per-CPU, always DISASSOCIATED.
 	 */
-	if (pool->flags & POOL_DISASSOCIATED)
+	if (pool->flags & POOL_DISASSOCIATED) {
 		worker->flags |= WORKER_UNBOUND;
-	else
+	} else {
+		WARN_ON_ONCE(pool->flags & POOL_BH);
 		kthread_set_per_cpu(worker->task, pool->cpu);
+	}
 
 	if (worker->rescue_wq)
 		set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool));
@@ -2136,6 +2745,9 @@ static void worker_detach_from_pool(struct worker *worker)
 	struct worker_pool *pool = worker->pool;
 	struct completion *detach_completion = NULL;
 
+	/* there is one permanent BH worker per CPU which should never detach */
+	WARN_ON_ONCE(pool->flags & POOL_BH);
+
 	mutex_lock(&wq_pool_attach_mutex);
 
 	kthread_set_per_cpu(worker->task, -1);
@@ -2187,27 +2799,29 @@ static struct worker *create_worker(struct worker_pool *pool)
 
 	worker->id = id;
 
-	if (pool->cpu >= 0)
-		snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id,
-			 pool->attrs->nice < 0  ? "H" : "");
-	else
-		snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id);
-
-	worker->task = kthread_create_on_node(worker_thread, worker, pool->node,
-					      "kworker/%s", id_buf);
-	if (IS_ERR(worker->task)) {
-		if (PTR_ERR(worker->task) == -EINTR) {
-			pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n",
-			       id_buf);
-		} else {
-			pr_err_once("workqueue: Failed to create a worker thread: %pe",
-				    worker->task);
+	if (!(pool->flags & POOL_BH)) {
+		if (pool->cpu >= 0)
+			snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id,
+				 pool->attrs->nice < 0  ? "H" : "");
+		else
+			snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id);
+
+		worker->task = kthread_create_on_node(worker_thread, worker,
+					pool->node, "kworker/%s", id_buf);
+		if (IS_ERR(worker->task)) {
+			if (PTR_ERR(worker->task) == -EINTR) {
+				pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n",
+				       id_buf);
+			} else {
+				pr_err_once("workqueue: Failed to create a worker thread: %pe",
+					    worker->task);
+			}
+			goto fail;
 		}
-		goto fail;
-	}
 
-	set_user_nice(worker->task, pool->attrs->nice);
-	kthread_bind_mask(worker->task, pool_allowed_cpus(pool));
+		set_user_nice(worker->task, pool->attrs->nice);
+		kthread_bind_mask(worker->task, pool_allowed_cpus(pool));
+	}
 
 	/* successful, attach the worker to the pool */
 	worker_attach_to_pool(worker, pool);
@@ -2217,14 +2831,14 @@ static struct worker *create_worker(struct worker_pool *pool)
 
 	worker->pool->nr_workers++;
 	worker_enter_idle(worker);
-	kick_pool(pool);
 
 	/*
 	 * @worker is waiting on a completion in kthread() and will trigger hung
-	 * check if not woken up soon. As kick_pool() might not have waken it
-	 * up, wake it up explicitly once more.
+	 * check if not woken up soon. As kick_pool() is noop if @pool is empty,
+	 * wake it up explicitly.
 	 */
-	wake_up_process(worker->task);
+	if (worker->task)
+		wake_up_process(worker->task);
 
 	raw_spin_unlock_irq(&pool->lock);
 
@@ -2543,6 +3157,8 @@ __acquires(&pool->lock)
 	struct pool_workqueue *pwq = get_work_pwq(work);
 	struct worker_pool *pool = worker->pool;
 	unsigned long work_data;
+	int lockdep_start_depth, rcu_start_depth;
+	bool bh_draining = pool->flags & POOL_BH_DRAINING;
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * It is permissible to free the struct work_struct from
@@ -2565,7 +3181,8 @@ __acquires(&pool->lock)
 	worker->current_work = work;
 	worker->current_func = work->func;
 	worker->current_pwq = pwq;
-	worker->current_at = worker->task->se.sum_exec_runtime;
+	if (worker->task)
+		worker->current_at = worker->task->se.sum_exec_runtime;
 	work_data = *work_data_bits(work);
 	worker->current_color = get_work_color(work_data);
 
@@ -2600,12 +3217,16 @@ __acquires(&pool->lock)
 	 * PENDING and queued state changes happen together while IRQ is
 	 * disabled.
 	 */
-	set_work_pool_and_clear_pending(work, pool->id);
+	set_work_pool_and_clear_pending(work, pool->id, 0);
 
 	pwq->stats[PWQ_STAT_STARTED]++;
 	raw_spin_unlock_irq(&pool->lock);
 
-	lock_map_acquire(&pwq->wq->lockdep_map);
+	rcu_start_depth = rcu_preempt_depth();
+	lockdep_start_depth = lockdep_depth(current);
+	/* see drain_dead_softirq_workfn() */
+	if (!bh_draining)
+		lock_map_acquire(&pwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
 	/*
 	 * Strictly speaking we should mark the invariant state without holding
@@ -2638,12 +3259,17 @@ __acquires(&pool->lock)
 	trace_workqueue_execute_end(work, worker->current_func);
 	pwq->stats[PWQ_STAT_COMPLETED]++;
 	lock_map_release(&lockdep_map);
-	lock_map_release(&pwq->wq->lockdep_map);
+	if (!bh_draining)
+		lock_map_release(&pwq->wq->lockdep_map);
 
-	if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
-		pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
-		       "     last function: %ps\n",
-		       current->comm, preempt_count(), task_pid_nr(current),
+	if (unlikely((worker->task && in_atomic()) ||
+		     lockdep_depth(current) != lockdep_start_depth ||
+		     rcu_preempt_depth() != rcu_start_depth)) {
+		pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n"
+		       "     preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n",
+		       current->comm, task_pid_nr(current), preempt_count(),
+		       lockdep_start_depth, lockdep_depth(current),
+		       rcu_start_depth, rcu_preempt_depth(),
 		       worker->current_func);
 		debug_show_held_locks(current);
 		dump_stack();
@@ -2657,7 +3283,8 @@ __acquires(&pool->lock)
 	 * stop_machine. At the same time, report a quiescent RCU state so
 	 * the same condition doesn't freeze RCU.
 	 */
-	cond_resched();
+	if (worker->task)
+		cond_resched();
 
 	raw_spin_lock_irq(&pool->lock);
 
@@ -2677,6 +3304,8 @@ __acquires(&pool->lock)
 	worker->current_func = NULL;
 	worker->current_pwq = NULL;
 	worker->current_color = INT_MAX;
+
+	/* must be the last step, see the function comment */
 	pwq_dec_nr_in_flight(pwq, work_data);
 }
 
@@ -2938,6 +3567,139 @@ repeat:
 	goto repeat;
 }
 
+static void bh_worker(struct worker *worker)
+{
+	struct worker_pool *pool = worker->pool;
+	int nr_restarts = BH_WORKER_RESTARTS;
+	unsigned long end = jiffies + BH_WORKER_JIFFIES;
+
+	raw_spin_lock_irq(&pool->lock);
+	worker_leave_idle(worker);
+
+	/*
+	 * This function follows the structure of worker_thread(). See there for
+	 * explanations on each step.
+	 */
+	if (!need_more_worker(pool))
+		goto done;
+
+	WARN_ON_ONCE(!list_empty(&worker->scheduled));
+	worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND);
+
+	do {
+		struct work_struct *work =
+			list_first_entry(&pool->worklist,
+					 struct work_struct, entry);
+
+		if (assign_work(work, worker, NULL))
+			process_scheduled_works(worker);
+	} while (keep_working(pool) &&
+		 --nr_restarts && time_before(jiffies, end));
+
+	worker_set_flags(worker, WORKER_PREP);
+done:
+	worker_enter_idle(worker);
+	kick_pool(pool);
+	raw_spin_unlock_irq(&pool->lock);
+}
+
+/*
+ * TODO: Convert all tasklet users to workqueue and use softirq directly.
+ *
+ * This is currently called from tasklet[_hi]action() and thus is also called
+ * whenever there are tasklets to run. Let's do an early exit if there's nothing
+ * queued. Once conversion from tasklet is complete, the need_more_worker() test
+ * can be dropped.
+ *
+ * After full conversion, we'll add worker->softirq_action, directly use the
+ * softirq action and obtain the worker pointer from the softirq_action pointer.
+ */
+void workqueue_softirq_action(bool highpri)
+{
+	struct worker_pool *pool =
+		&per_cpu(bh_worker_pools, smp_processor_id())[highpri];
+	if (need_more_worker(pool))
+		bh_worker(list_first_entry(&pool->workers, struct worker, node));
+}
+
+struct wq_drain_dead_softirq_work {
+	struct work_struct	work;
+	struct worker_pool	*pool;
+	struct completion	done;
+};
+
+static void drain_dead_softirq_workfn(struct work_struct *work)
+{
+	struct wq_drain_dead_softirq_work *dead_work =
+		container_of(work, struct wq_drain_dead_softirq_work, work);
+	struct worker_pool *pool = dead_work->pool;
+	bool repeat;
+
+	/*
+	 * @pool's CPU is dead and we want to execute its still pending work
+	 * items from this BH work item which is running on a different CPU. As
+	 * its CPU is dead, @pool can't be kicked and, as work execution path
+	 * will be nested, a lockdep annotation needs to be suppressed. Mark
+	 * @pool with %POOL_BH_DRAINING for the special treatments.
+	 */
+	raw_spin_lock_irq(&pool->lock);
+	pool->flags |= POOL_BH_DRAINING;
+	raw_spin_unlock_irq(&pool->lock);
+
+	bh_worker(list_first_entry(&pool->workers, struct worker, node));
+
+	raw_spin_lock_irq(&pool->lock);
+	pool->flags &= ~POOL_BH_DRAINING;
+	repeat = need_more_worker(pool);
+	raw_spin_unlock_irq(&pool->lock);
+
+	/*
+	 * bh_worker() might hit consecutive execution limit and bail. If there
+	 * still are pending work items, reschedule self and return so that we
+	 * don't hog this CPU's BH.
+	 */
+	if (repeat) {
+		if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+			queue_work(system_bh_highpri_wq, work);
+		else
+			queue_work(system_bh_wq, work);
+	} else {
+		complete(&dead_work->done);
+	}
+}
+
+/*
+ * @cpu is dead. Drain the remaining BH work items on the current CPU. It's
+ * possible to allocate dead_work per CPU and avoid flushing. However, then we
+ * have to worry about draining overlapping with CPU coming back online or
+ * nesting (one CPU's dead_work queued on another CPU which is also dead and so
+ * on). Let's keep it simple and drain them synchronously. These are BH work
+ * items which shouldn't be requeued on the same pool. Shouldn't take long.
+ */
+void workqueue_softirq_dead(unsigned int cpu)
+{
+	int i;
+
+	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
+		struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i];
+		struct wq_drain_dead_softirq_work dead_work;
+
+		if (!need_more_worker(pool))
+			continue;
+
+		INIT_WORK(&dead_work.work, drain_dead_softirq_workfn);
+		dead_work.pool = pool;
+		init_completion(&dead_work.done);
+
+		if (pool->attrs->nice == HIGHPRI_NICE_LEVEL)
+			queue_work(system_bh_highpri_wq, &dead_work.work);
+		else
+			queue_work(system_bh_wq, &dead_work.work);
+
+		wait_for_completion(&dead_work.done);
+	}
+}
+
 /**
  * check_flush_dependency - check for flush dependency sanity
  * @target_wq: workqueue being flushed
@@ -3010,6 +3772,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
 			      struct wq_barrier *barr,
 			      struct work_struct *target, struct worker *worker)
 {
+	static __maybe_unused struct lock_class_key bh_key, thr_key;
 	unsigned int work_flags = 0;
 	unsigned int work_color;
 	struct list_head *head;
@@ -3019,15 +3782,20 @@ static void insert_wq_barrier(struct pool_workqueue *pwq,
 	 * as we know for sure that this will not trigger any of the
 	 * checks and call back into the fixup functions where we
 	 * might deadlock.
+	 *
+	 * BH and threaded workqueues need separate lockdep keys to avoid
+	 * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W}
+	 * usage".
 	 */
-	INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
+	INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func,
+			      (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key);
 	__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
 
 	init_completion_map(&barr->done, &target->lockdep_map);
 
 	barr->task = current;
 
-	/* The barrier work item does not participate in pwq->nr_active. */
+	/* The barrier work item does not participate in nr_active. */
 	work_flags |= WORK_STRUCT_INACTIVE;
 
 	/*
@@ -3124,6 +3892,35 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
 	return wait;
 }
 
+static void touch_wq_lockdep_map(struct workqueue_struct *wq)
+{
+#ifdef CONFIG_LOCKDEP
+	if (wq->flags & WQ_BH)
+		local_bh_disable();
+
+	lock_map_acquire(&wq->lockdep_map);
+	lock_map_release(&wq->lockdep_map);
+
+	if (wq->flags & WQ_BH)
+		local_bh_enable();
+#endif
+}
+
+static void touch_work_lockdep_map(struct work_struct *work,
+				   struct workqueue_struct *wq)
+{
+#ifdef CONFIG_LOCKDEP
+	if (wq->flags & WQ_BH)
+		local_bh_disable();
+
+	lock_map_acquire(&work->lockdep_map);
+	lock_map_release(&work->lockdep_map);
+
+	if (wq->flags & WQ_BH)
+		local_bh_enable();
+#endif
+}
+
 /**
  * __flush_workqueue - ensure that any scheduled work has run to completion.
  * @wq: workqueue to flush
@@ -3143,8 +3940,7 @@ void __flush_workqueue(struct workqueue_struct *wq)
 	if (WARN_ON(!wq_online))
 		return;
 
-	lock_map_acquire(&wq->lockdep_map);
-	lock_map_release(&wq->lockdep_map);
+	touch_wq_lockdep_map(wq);
 
 	mutex_lock(&wq->mutex);
 
@@ -3316,7 +4112,7 @@ reflush:
 		bool drained;
 
 		raw_spin_lock_irq(&pwq->pool->lock);
-		drained = !pwq->nr_active && list_empty(&pwq->inactive_works);
+		drained = pwq_is_empty(pwq);
 		raw_spin_unlock_irq(&pwq->pool->lock);
 
 		if (drained)
@@ -3343,6 +4139,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	struct worker *worker = NULL;
 	struct worker_pool *pool;
 	struct pool_workqueue *pwq;
+	struct workqueue_struct *wq;
 
 	might_sleep();
 
@@ -3366,11 +4163,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 		pwq = worker->current_pwq;
 	}
 
-	check_flush_dependency(pwq->wq, work);
+	wq = pwq->wq;
+	check_flush_dependency(wq, work);
 
 	insert_wq_barrier(pwq, barr, work, worker);
 	raw_spin_unlock_irq(&pool->lock);
 
+	touch_work_lockdep_map(work, wq);
+
 	/*
 	 * Force a lock recursion deadlock when using flush_work() inside a
 	 * single-threaded or rescuer equipped workqueue.
@@ -3380,11 +4180,9 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
 	 * workqueues the deadlock happens when the rescuer stalls, blocking
 	 * forward progress.
 	 */
-	if (!from_cancel &&
-	    (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) {
-		lock_map_acquire(&pwq->wq->lockdep_map);
-		lock_map_release(&pwq->wq->lockdep_map);
-	}
+	if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer))
+		touch_wq_lockdep_map(wq);
+
 	rcu_read_unlock();
 	return true;
 already_gone:
@@ -3403,9 +4201,6 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 	if (WARN_ON(!work->func))
 		return false;
 
-	lock_map_acquire(&work->lockdep_map);
-	lock_map_release(&work->lockdep_map);
-
 	if (start_flush_work(work, &barr, from_cancel)) {
 		wait_for_completion(&barr.done);
 		destroy_work_on_stack(&barr.work);
@@ -3432,108 +4227,6 @@ bool flush_work(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
-struct cwt_wait {
-	wait_queue_entry_t		wait;
-	struct work_struct	*work;
-};
-
-static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
-{
-	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
-
-	if (cwait->work != key)
-		return 0;
-	return autoremove_wake_function(wait, mode, sync, key);
-}
-
-static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
-{
-	static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
-	unsigned long flags;
-	int ret;
-
-	do {
-		ret = try_to_grab_pending(work, is_dwork, &flags);
-		/*
-		 * If someone else is already canceling, wait for it to
-		 * finish.  flush_work() doesn't work for PREEMPT_NONE
-		 * because we may get scheduled between @work's completion
-		 * and the other canceling task resuming and clearing
-		 * CANCELING - flush_work() will return false immediately
-		 * as @work is no longer busy, try_to_grab_pending() will
-		 * return -ENOENT as @work is still being canceled and the
-		 * other canceling task won't be able to clear CANCELING as
-		 * we're hogging the CPU.
-		 *
-		 * Let's wait for completion using a waitqueue.  As this
-		 * may lead to the thundering herd problem, use a custom
-		 * wake function which matches @work along with exclusive
-		 * wait and wakeup.
-		 */
-		if (unlikely(ret == -ENOENT)) {
-			struct cwt_wait cwait;
-
-			init_wait(&cwait.wait);
-			cwait.wait.func = cwt_wakefn;
-			cwait.work = work;
-
-			prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
-						  TASK_UNINTERRUPTIBLE);
-			if (work_is_canceling(work))
-				schedule();
-			finish_wait(&cancel_waitq, &cwait.wait);
-		}
-	} while (unlikely(ret < 0));
-
-	/* tell other tasks trying to grab @work to back off */
-	mark_work_canceling(work);
-	local_irq_restore(flags);
-
-	/*
-	 * This allows canceling during early boot.  We know that @work
-	 * isn't executing.
-	 */
-	if (wq_online)
-		__flush_work(work, true);
-
-	clear_work_data(work);
-
-	/*
-	 * Paired with prepare_to_wait() above so that either
-	 * waitqueue_active() is visible here or !work_is_canceling() is
-	 * visible there.
-	 */
-	smp_mb();
-	if (waitqueue_active(&cancel_waitq))
-		__wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
-
-	return ret;
-}
-
-/**
- * cancel_work_sync - cancel a work and wait for it to finish
- * @work: the work to cancel
- *
- * Cancel @work and wait for its execution to finish.  This function
- * can be used even if the work re-queues itself or migrates to
- * another workqueue.  On return from this function, @work is
- * guaranteed to be not pending or executing on any CPU.
- *
- * cancel_work_sync(&delayed_work->work) must not be used for
- * delayed_work's.  Use cancel_delayed_work_sync() instead.
- *
- * The caller must ensure that the workqueue on which @work was last
- * queued can't be destroyed before this function returns.
- *
- * Return:
- * %true if @work was pending, %false otherwise.
- */
-bool cancel_work_sync(struct work_struct *work)
-{
-	return __cancel_work_timer(work, false);
-}
-EXPORT_SYMBOL_GPL(cancel_work_sync);
-
 /**
  * flush_delayed_work - wait for a dwork to finish executing the last queueing
  * @dwork: the delayed work to flush
@@ -3576,20 +4269,50 @@ bool flush_rcu_work(struct rcu_work *rwork)
 }
 EXPORT_SYMBOL(flush_rcu_work);
 
-static bool __cancel_work(struct work_struct *work, bool is_dwork)
+static bool __cancel_work(struct work_struct *work, u32 cflags)
 {
-	unsigned long flags;
+	unsigned long irq_flags;
 	int ret;
 
 	do {
-		ret = try_to_grab_pending(work, is_dwork, &flags);
+		ret = try_to_grab_pending(work, cflags, &irq_flags);
 	} while (unlikely(ret == -EAGAIN));
 
 	if (unlikely(ret < 0))
 		return false;
 
-	set_work_pool_and_clear_pending(work, get_work_pool_id(work));
-	local_irq_restore(flags);
+	set_work_pool_and_clear_pending(work, get_work_pool_id(work), 0);
+	local_irq_restore(irq_flags);
+	return ret;
+}
+
+static bool __cancel_work_sync(struct work_struct *work, u32 cflags)
+{
+	unsigned long irq_flags;
+	bool ret;
+
+	/* claim @work and tell other tasks trying to grab @work to back off */
+	ret = work_grab_pending(work, cflags, &irq_flags);
+	mark_work_canceling(work);
+	local_irq_restore(irq_flags);
+
+	/*
+	 * Skip __flush_work() during early boot when we know that @work isn't
+	 * executing. This allows canceling during early boot.
+	 */
+	if (wq_online)
+		__flush_work(work, true);
+
+	/*
+	 * smp_mb() at the end of set_work_pool_and_clear_pending() is paired
+	 * with prepare_to_wait() above so that either waitqueue_active() is
+	 * visible here or !work_is_canceling() is visible there.
+	 */
+	set_work_pool_and_clear_pending(work, WORK_OFFQ_POOL_NONE, 0);
+
+	if (waitqueue_active(&wq_cancel_waitq))
+		__wake_up(&wq_cancel_waitq, TASK_NORMAL, 1, work);
+
 	return ret;
 }
 
@@ -3598,11 +4321,35 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork)
  */
 bool cancel_work(struct work_struct *work)
 {
-	return __cancel_work(work, false);
+	return __cancel_work(work, 0);
 }
 EXPORT_SYMBOL(cancel_work);
 
 /**
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
+ *
+ * Cancel @work and wait for its execution to finish.  This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue.  On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
+ *
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's.  Use cancel_delayed_work_sync() instead.
+ *
+ * The caller must ensure that the workqueue on which @work was last
+ * queued can't be destroyed before this function returns.
+ *
+ * Return:
+ * %true if @work was pending, %false otherwise.
+ */
+bool cancel_work_sync(struct work_struct *work)
+{
+	return __cancel_work_sync(work, 0);
+}
+EXPORT_SYMBOL_GPL(cancel_work_sync);
+
+/**
  * cancel_delayed_work - cancel a delayed work
  * @dwork: delayed_work to cancel
  *
@@ -3620,7 +4367,7 @@ EXPORT_SYMBOL(cancel_work);
  */
 bool cancel_delayed_work(struct delayed_work *dwork)
 {
-	return __cancel_work(&dwork->work, true);
+	return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED);
 }
 EXPORT_SYMBOL(cancel_delayed_work);
 
@@ -3635,7 +4382,7 @@ EXPORT_SYMBOL(cancel_delayed_work);
  */
 bool cancel_delayed_work_sync(struct delayed_work *dwork)
 {
-	return __cancel_work_timer(&dwork->work, true);
+	return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED);
 }
 EXPORT_SYMBOL(cancel_delayed_work_sync);
 
@@ -3927,11 +4674,66 @@ static void wq_free_lockdep(struct workqueue_struct *wq)
 }
 #endif
 
+static void free_node_nr_active(struct wq_node_nr_active **nna_ar)
+{
+	int node;
+
+	for_each_node(node) {
+		kfree(nna_ar[node]);
+		nna_ar[node] = NULL;
+	}
+
+	kfree(nna_ar[nr_node_ids]);
+	nna_ar[nr_node_ids] = NULL;
+}
+
+static void init_node_nr_active(struct wq_node_nr_active *nna)
+{
+	nna->max = WQ_DFL_MIN_ACTIVE;
+	atomic_set(&nna->nr, 0);
+	raw_spin_lock_init(&nna->lock);
+	INIT_LIST_HEAD(&nna->pending_pwqs);
+}
+
+/*
+ * Each node's nr_active counter will be accessed mostly from its own node and
+ * should be allocated in the node.
+ */
+static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar)
+{
+	struct wq_node_nr_active *nna;
+	int node;
+
+	for_each_node(node) {
+		nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node);
+		if (!nna)
+			goto err_free;
+		init_node_nr_active(nna);
+		nna_ar[node] = nna;
+	}
+
+	/* [nr_node_ids] is used as the fallback */
+	nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE);
+	if (!nna)
+		goto err_free;
+	init_node_nr_active(nna);
+	nna_ar[nr_node_ids] = nna;
+
+	return 0;
+
+err_free:
+	free_node_nr_active(nna_ar);
+	return -ENOMEM;
+}
+
 static void rcu_free_wq(struct rcu_head *rcu)
 {
 	struct workqueue_struct *wq =
 		container_of(rcu, struct workqueue_struct, rcu);
 
+	if (wq->flags & WQ_UNBOUND)
+		free_node_nr_active(wq->node_nr_active);
+
 	wq_free_lockdep(wq);
 	free_percpu(wq->cpu_pwq);
 	free_workqueue_attrs(wq->unbound_attrs);
@@ -4121,6 +4923,13 @@ static void pwq_release_workfn(struct kthread_work *work)
 		mutex_lock(&wq->mutex);
 		list_del_rcu(&pwq->pwqs_node);
 		is_last = list_empty(&wq->pwqs);
+
+		/*
+		 * For ordered workqueue with a plugged dfl_pwq, restart it now.
+		 */
+		if (!is_last && (wq->flags & __WQ_ORDERED))
+			unplug_oldest_pwq(wq);
+
 		mutex_unlock(&wq->mutex);
 	}
 
@@ -4130,6 +4939,15 @@ static void pwq_release_workfn(struct kthread_work *work)
 		mutex_unlock(&wq_pool_mutex);
 	}
 
+	if (!list_empty(&pwq->pending_node)) {
+		struct wq_node_nr_active *nna =
+			wq_node_nr_active(pwq->wq, pwq->pool->node);
+
+		raw_spin_lock_irq(&nna->lock);
+		list_del_init(&pwq->pending_node);
+		raw_spin_unlock_irq(&nna->lock);
+	}
+
 	call_rcu(&pwq->rcu, rcu_free_pwq);
 
 	/*
@@ -4142,55 +4960,11 @@ static void pwq_release_workfn(struct kthread_work *work)
 	}
 }
 
-/**
- * pwq_adjust_max_active - update a pwq's max_active to the current setting
- * @pwq: target pool_workqueue
- *
- * If @pwq isn't freezing, set @pwq->max_active to the associated
- * workqueue's saved_max_active and activate inactive work items
- * accordingly.  If @pwq is freezing, clear @pwq->max_active to zero.
- */
-static void pwq_adjust_max_active(struct pool_workqueue *pwq)
-{
-	struct workqueue_struct *wq = pwq->wq;
-	bool freezable = wq->flags & WQ_FREEZABLE;
-	unsigned long flags;
-
-	/* for @wq->saved_max_active */
-	lockdep_assert_held(&wq->mutex);
-
-	/* fast exit for non-freezable wqs */
-	if (!freezable && pwq->max_active == wq->saved_max_active)
-		return;
-
-	/* this function can be called during early boot w/ irq disabled */
-	raw_spin_lock_irqsave(&pwq->pool->lock, flags);
-
-	/*
-	 * During [un]freezing, the caller is responsible for ensuring that
-	 * this function is called at least once after @workqueue_freezing
-	 * is updated and visible.
-	 */
-	if (!freezable || !workqueue_freezing) {
-		pwq->max_active = wq->saved_max_active;
-
-		while (!list_empty(&pwq->inactive_works) &&
-		       pwq->nr_active < pwq->max_active)
-			pwq_activate_first_inactive(pwq);
-
-		kick_pool(pwq->pool);
-	} else {
-		pwq->max_active = 0;
-	}
-
-	raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
-}
-
 /* initialize newly allocated @pwq which is associated with @wq and @pool */
 static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
 		     struct worker_pool *pool)
 {
-	BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
+	BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK);
 
 	memset(pwq, 0, sizeof(*pwq));
 
@@ -4199,6 +4973,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq,
 	pwq->flush_color = -1;
 	pwq->refcnt = 1;
 	INIT_LIST_HEAD(&pwq->inactive_works);
+	INIT_LIST_HEAD(&pwq->pending_node);
 	INIT_LIST_HEAD(&pwq->pwqs_node);
 	INIT_LIST_HEAD(&pwq->mayday_node);
 	kthread_init_work(&pwq->release_work, pwq_release_workfn);
@@ -4218,11 +4993,8 @@ static void link_pwq(struct pool_workqueue *pwq)
 	/* set the matching work_color */
 	pwq->work_color = wq->work_color;
 
-	/* sync max_active to the current setting */
-	pwq_adjust_max_active(pwq);
-
 	/* link in @pwq */
-	list_add_rcu(&pwq->pwqs_node, &wq->pwqs);
+	list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs);
 }
 
 /* obtain a pool matching @attr and create a pwq associating the pool and @wq */
@@ -4289,10 +5061,11 @@ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu,
 				"possible intersect\n");
 }
 
-/* install @pwq into @wq's cpu_pwq and return the old pwq */
+/* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */
 static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq,
 					int cpu, struct pool_workqueue *pwq)
 {
+	struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu);
 	struct pool_workqueue *old_pwq;
 
 	lockdep_assert_held(&wq_pool_mutex);
@@ -4301,8 +5074,8 @@ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq,
 	/* link_pwq() can handle duplicate calls */
 	link_pwq(pwq);
 
-	old_pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu));
-	rcu_assign_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu), pwq);
+	old_pwq = rcu_access_pointer(*slot);
+	rcu_assign_pointer(*slot, pwq);
 	return old_pwq;
 }
 
@@ -4383,6 +5156,15 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
 	cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask);
 	ctx->attrs = new_attrs;
 
+	/*
+	 * For initialized ordered workqueues, there should only be one pwq
+	 * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution
+	 * of newly queued work items until execution of older work items in
+	 * the old pwq's have completed.
+	 */
+	if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))
+		ctx->dfl_pwq->plugged = true;
+
 	ctx->wq = wq;
 	return ctx;
 
@@ -4402,14 +5184,19 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx)
 
 	copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs);
 
-	/* save the previous pwq and install the new one */
+	/* save the previous pwqs and install the new ones */
 	for_each_possible_cpu(cpu)
 		ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu,
 							ctx->pwq_tbl[cpu]);
+	ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq);
+
+	/* update node_nr_active->max */
+	wq_update_node_max_active(ctx->wq, -1);
 
-	/* @dfl_pwq might not have been used, ensure it's linked */
-	link_pwq(ctx->dfl_pwq);
-	swap(ctx->wq->dfl_pwq, ctx->dfl_pwq);
+	/* rescuer needs to respect wq cpumask changes */
+	if (ctx->wq->rescuer)
+		set_cpus_allowed_ptr(ctx->wq->rescuer->task,
+				     unbound_effective_cpumask(ctx->wq));
 
 	mutex_unlock(&ctx->wq->mutex);
 }
@@ -4423,14 +5210,6 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 	if (WARN_ON(!(wq->flags & WQ_UNBOUND)))
 		return -EINVAL;
 
-	/* creating multiple pwqs breaks ordering guarantee */
-	if (!list_empty(&wq->pwqs)) {
-		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
-			return -EINVAL;
-
-		wq->flags &= ~__WQ_ORDERED;
-	}
-
 	ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
@@ -4519,9 +5298,7 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu,
 
 	/* nothing to do if the target cpumask matches the current pwq */
 	wq_calc_pod_cpumask(target_attrs, cpu, off_cpu);
-	pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu),
-					lockdep_is_held(&wq_pool_mutex));
-	if (wqattrs_equal(target_attrs, pwq->pool->attrs))
+	if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs))
 		return;
 
 	/* create a new pwq */
@@ -4539,10 +5316,11 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu,
 
 use_dfl_pwq:
 	mutex_lock(&wq->mutex);
-	raw_spin_lock_irq(&wq->dfl_pwq->pool->lock);
-	get_pwq(wq->dfl_pwq);
-	raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock);
-	old_pwq = install_unbound_pwq(wq, cpu, wq->dfl_pwq);
+	pwq = unbound_pwq(wq, -1);
+	raw_spin_lock_irq(&pwq->pool->lock);
+	get_pwq(pwq);
+	raw_spin_unlock_irq(&pwq->pool->lock);
+	old_pwq = install_unbound_pwq(wq, cpu, pwq);
 out_unlock:
 	mutex_unlock(&wq->mutex);
 	put_pwq_unlocked(old_pwq);
@@ -4559,10 +5337,17 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 
 	if (!(wq->flags & WQ_UNBOUND)) {
 		for_each_possible_cpu(cpu) {
-			struct pool_workqueue **pwq_p =
-				per_cpu_ptr(wq->cpu_pwq, cpu);
-			struct worker_pool *pool =
-				&(per_cpu_ptr(cpu_worker_pools, cpu)[highpri]);
+			struct pool_workqueue **pwq_p;
+			struct worker_pool __percpu *pools;
+			struct worker_pool *pool;
+
+			if (wq->flags & WQ_BH)
+				pools = bh_worker_pools;
+			else
+				pools = cpu_worker_pools;
+
+			pool = &(per_cpu_ptr(pools, cpu)[highpri]);
+			pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu);
 
 			*pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL,
 						       pool->node);
@@ -4580,10 +5365,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 
 	cpus_read_lock();
 	if (wq->flags & __WQ_ORDERED) {
+		struct pool_workqueue *dfl_pwq;
+
 		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
 		/* there should only be single pwq for ordering guarantee */
-		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
-			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+		dfl_pwq = rcu_access_pointer(wq->dfl_pwq);
+		WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node ||
+			      wq->pwqs.prev != &dfl_pwq->pwqs_node),
 		     "ordering guarantee broken for workqueue %s\n", wq->name);
 	} else {
 		ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
@@ -4652,12 +5440,78 @@ static int init_rescuer(struct workqueue_struct *wq)
 	}
 
 	wq->rescuer = rescuer;
-	kthread_bind_mask(rescuer->task, cpu_possible_mask);
+	if (wq->flags & WQ_UNBOUND)
+		kthread_bind_mask(rescuer->task, wq_unbound_cpumask);
+	else
+		kthread_bind_mask(rescuer->task, cpu_possible_mask);
 	wake_up_process(rescuer->task);
 
 	return 0;
 }
 
+/**
+ * wq_adjust_max_active - update a wq's max_active to the current setting
+ * @wq: target workqueue
+ *
+ * If @wq isn't freezing, set @wq->max_active to the saved_max_active and
+ * activate inactive work items accordingly. If @wq is freezing, clear
+ * @wq->max_active to zero.
+ */
+static void wq_adjust_max_active(struct workqueue_struct *wq)
+{
+	bool activated;
+	int new_max, new_min;
+
+	lockdep_assert_held(&wq->mutex);
+
+	if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) {
+		new_max = 0;
+		new_min = 0;
+	} else {
+		new_max = wq->saved_max_active;
+		new_min = wq->saved_min_active;
+	}
+
+	if (wq->max_active == new_max && wq->min_active == new_min)
+		return;
+
+	/*
+	 * Update @wq->max/min_active and then kick inactive work items if more
+	 * active work items are allowed. This doesn't break work item ordering
+	 * because new work items are always queued behind existing inactive
+	 * work items if there are any.
+	 */
+	WRITE_ONCE(wq->max_active, new_max);
+	WRITE_ONCE(wq->min_active, new_min);
+
+	if (wq->flags & WQ_UNBOUND)
+		wq_update_node_max_active(wq, -1);
+
+	if (new_max == 0)
+		return;
+
+	/*
+	 * Round-robin through pwq's activating the first inactive work item
+	 * until max_active is filled.
+	 */
+	do {
+		struct pool_workqueue *pwq;
+
+		activated = false;
+		for_each_pwq(pwq, wq) {
+			unsigned long irq_flags;
+
+			/* can be called during early boot w/ irq disabled */
+			raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags);
+			if (pwq_activate_first_inactive(pwq, true)) {
+				activated = true;
+				kick_pool(pwq->pool);
+			}
+			raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags);
+		}
+	} while (activated);
+}
+
 __printf(1, 4)
 struct workqueue_struct *alloc_workqueue(const char *fmt,
 					 unsigned int flags,
@@ -4665,23 +5519,27 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 {
 	va_list args;
 	struct workqueue_struct *wq;
-	struct pool_workqueue *pwq;
+	size_t wq_size;
+	int name_len;
 
-	/*
-	 * Unbound && max_active == 1 used to imply ordered, which is no longer
-	 * the case on many machines due to per-pod pools. While
-	 * alloc_ordered_workqueue() is the right way to create an ordered
-	 * workqueue, keep the previous behavior to avoid subtle breakages.
-	 */
-	if ((flags & WQ_UNBOUND) && max_active == 1)
-		flags |= __WQ_ORDERED;
+	if (flags & WQ_BH) {
+		if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS))
+			return NULL;
+		if (WARN_ON_ONCE(max_active))
+			return NULL;
+	}
 
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
 
 	/* allocate wq and format name */
-	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
+	if (flags & WQ_UNBOUND)
+		wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1);
+	else
+		wq_size = sizeof(*wq);
+
+	wq = kzalloc(wq_size, GFP_KERNEL);
 	if (!wq)
 		return NULL;
 
@@ -4692,15 +5550,30 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 	}
 
 	va_start(args, max_active);
-	vsnprintf(wq->name, sizeof(wq->name), fmt, args);
+	name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args);
 	va_end(args);
 
-	max_active = max_active ?: WQ_DFL_ACTIVE;
-	max_active = wq_clamp_max_active(max_active, flags, wq->name);
+	if (name_len >= WQ_NAME_LEN)
+		pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n",
+			     wq->name);
+
+	if (flags & WQ_BH) {
+		/*
+		 * BH workqueues always share a single execution context per CPU
+		 * and don't impose any max_active limit.
+		 */
+		max_active = INT_MAX;
+	} else {
+		max_active = max_active ?: WQ_DFL_ACTIVE;
+		max_active = wq_clamp_max_active(max_active, flags, wq->name);
+	}
 
 	/* init wq */
 	wq->flags = flags;
-	wq->saved_max_active = max_active;
+	wq->max_active = max_active;
+	wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE);
+	wq->saved_max_active = wq->max_active;
+	wq->saved_min_active = wq->min_active;
 	mutex_init(&wq->mutex);
 	atomic_set(&wq->nr_pwqs_to_flush, 0);
 	INIT_LIST_HEAD(&wq->pwqs);
@@ -4711,8 +5584,13 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 	wq_init_lockdep(wq);
 	INIT_LIST_HEAD(&wq->list);
 
+	if (flags & WQ_UNBOUND) {
+		if (alloc_node_nr_active(wq->node_nr_active) < 0)
+			goto err_unreg_lockdep;
+	}
+
 	if (alloc_and_link_pwqs(wq) < 0)
-		goto err_unreg_lockdep;
+		goto err_free_node_nr_active;
 
 	if (wq_online && init_rescuer(wq) < 0)
 		goto err_destroy;
@@ -4728,8 +5606,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 	mutex_lock(&wq_pool_mutex);
 
 	mutex_lock(&wq->mutex);
-	for_each_pwq(pwq, wq)
-		pwq_adjust_max_active(pwq);
+	wq_adjust_max_active(wq);
 	mutex_unlock(&wq->mutex);
 
 	list_add_tail_rcu(&wq->list, &workqueues);
@@ -4738,6 +5615,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 
 	return wq;
 
+err_free_node_nr_active:
+	if (wq->flags & WQ_UNBOUND)
+		free_node_nr_active(wq->node_nr_active);
 err_unreg_lockdep:
 	wq_unregister_lockdep(wq);
 	wq_free_lockdep(wq);
@@ -4759,9 +5639,9 @@ static bool pwq_busy(struct pool_workqueue *pwq)
 		if (pwq->nr_in_flight[i])
 			return true;
 
-	if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1))
+	if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1))
 		return true;
-	if (pwq->nr_active || !list_empty(&pwq->inactive_works))
+	if (!pwq_is_empty(pwq))
 		return true;
 
 	return false;
@@ -4843,13 +5723,12 @@ void destroy_workqueue(struct workqueue_struct *wq)
 	rcu_read_lock();
 
 	for_each_possible_cpu(cpu) {
-		pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu));
-		RCU_INIT_POINTER(*per_cpu_ptr(wq->cpu_pwq, cpu), NULL);
-		put_pwq_unlocked(pwq);
+		put_pwq_unlocked(unbound_pwq(wq, cpu));
+		RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL);
 	}
 
-	put_pwq_unlocked(wq->dfl_pwq);
-	wq->dfl_pwq = NULL;
+	put_pwq_unlocked(unbound_pwq(wq, -1));
+	RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL);
 
 	rcu_read_unlock();
 }
@@ -4860,34 +5739,63 @@ EXPORT_SYMBOL_GPL(destroy_workqueue);
  * @wq: target workqueue
  * @max_active: new max_active value.
  *
- * Set max_active of @wq to @max_active.
+ * Set max_active of @wq to @max_active. See the alloc_workqueue() function
+ * comment.
  *
  * CONTEXT:
  * Don't call from IRQ context.
  */
 void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 {
-	struct pool_workqueue *pwq;
-
+	/* max_active doesn't mean anything for BH workqueues */
+	if (WARN_ON(wq->flags & WQ_BH))
+		return;
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
-	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
+	if (wq->flags & WQ_UNBOUND)
+		wq->saved_min_active = min(wq->saved_min_active, max_active);
 
-	for_each_pwq(pwq, wq)
-		pwq_adjust_max_active(pwq);
+	wq_adjust_max_active(wq);
 
 	mutex_unlock(&wq->mutex);
 }
 EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
 /**
+ * workqueue_set_min_active - adjust min_active of an unbound workqueue
+ * @wq: target unbound workqueue
+ * @min_active: new min_active value
+ *
+ * Set min_active of an unbound workqueue. Unlike other types of workqueues, an
+ * unbound workqueue is not guaranteed to be able to process max_active
+ * interdependent work items. Instead, an unbound workqueue is guaranteed to be
+ * able to process min_active number of interdependent work items which is
+ * %WQ_DFL_MIN_ACTIVE by default.
+ *
+ * Use this function to adjust the min_active value between 0 and the current
+ * max_active.
+ */
+void workqueue_set_min_active(struct workqueue_struct *wq, int min_active)
+{
+	/* min_active is only meaningful for non-ordered unbound workqueues */
+	if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) !=
+		    WQ_UNBOUND))
+		return;
+
+	mutex_lock(&wq->mutex);
+	wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active);
+	wq_adjust_max_active(wq);
+	mutex_unlock(&wq->mutex);
+}
+
+/**
  * current_work - retrieve %current task's work struct
  *
  * Determine if %current task is a workqueue worker and what it's working on.
@@ -4972,7 +5880,7 @@ EXPORT_SYMBOL_GPL(workqueue_congested);
 unsigned int work_busy(struct work_struct *work)
 {
 	struct worker_pool *pool;
-	unsigned long flags;
+	unsigned long irq_flags;
 	unsigned int ret = 0;
 
 	if (work_pending(work))
@@ -4981,10 +5889,10 @@ unsigned int work_busy(struct work_struct *work)
 	rcu_read_lock();
 	pool = get_work_pool(work);
 	if (pool) {
-		raw_spin_lock_irqsave(&pool->lock, flags);
+		raw_spin_lock_irqsave(&pool->lock, irq_flags);
 		if (find_worker_executing_work(pool, work))
 			ret |= WORK_BUSY_RUNNING;
-		raw_spin_unlock_irqrestore(&pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 	}
 	rcu_read_unlock();
 
@@ -5069,7 +5977,24 @@ static void pr_cont_pool_info(struct worker_pool *pool)
 	pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask);
 	if (pool->node != NUMA_NO_NODE)
 		pr_cont(" node=%d", pool->node);
-	pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice);
+	pr_cont(" flags=0x%x", pool->flags);
+	if (pool->flags & POOL_BH)
+		pr_cont(" bh%s",
+			pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
+	else
+		pr_cont(" nice=%d", pool->attrs->nice);
+}
+
+static void pr_cont_worker_id(struct worker *worker)
+{
+	struct worker_pool *pool = worker->pool;
+
+	if (pool->flags & WQ_BH)
+		pr_cont("bh%s",
+			pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
+	else
+		pr_cont("%d%s", task_pid_nr(worker->task),
+			worker->rescue_wq ? "(RESCUER)" : "");
 }
 
 struct pr_cont_work_struct {
@@ -5128,8 +6053,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 	pr_info("  pwq %d:", pool->id);
 	pr_cont_pool_info(pool);
 
-	pr_cont(" active=%d/%d refcnt=%d%s\n",
-		pwq->nr_active, pwq->max_active, pwq->refcnt,
+	pr_cont(" active=%d refcnt=%d%s\n",
+		pwq->nr_active, pwq->refcnt,
 		!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
@@ -5146,10 +6071,9 @@ static void show_pwq(struct pool_workqueue *pwq)
 			if (worker->current_pwq != pwq)
 				continue;
 
-			pr_cont("%s %d%s:%ps", comma ? "," : "",
-				task_pid_nr(worker->task),
-				worker->rescue_wq ? "(RESCUER)" : "",
-				worker->current_func);
+			pr_cont(" %s", comma ? "," : "");
+			pr_cont_worker_id(worker);
+			pr_cont(":%ps", worker->current_func);
 			list_for_each_entry(work, &worker->scheduled, entry)
 				pr_cont_work(false, work, &pcws);
 			pr_cont_work_flush(comma, (work_func_t)-1L, &pcws);
@@ -5200,10 +6124,10 @@ void show_one_workqueue(struct workqueue_struct *wq)
 {
 	struct pool_workqueue *pwq;
 	bool idle = true;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	for_each_pwq(pwq, wq) {
-		if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
+		if (!pwq_is_empty(pwq)) {
 			idle = false;
 			break;
 		}
@@ -5214,8 +6138,8 @@ void show_one_workqueue(struct workqueue_struct *wq)
 	pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags);
 
 	for_each_pwq(pwq, wq) {
-		raw_spin_lock_irqsave(&pwq->pool->lock, flags);
-		if (pwq->nr_active || !list_empty(&pwq->inactive_works)) {
+		raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags);
+		if (!pwq_is_empty(pwq)) {
 			/*
 			 * Defer printing to avoid deadlocks in console
 			 * drivers that queue work while holding locks
@@ -5225,7 +6149,7 @@ void show_one_workqueue(struct workqueue_struct *wq)
 			show_pwq(pwq);
 			printk_deferred_exit();
 		}
-		raw_spin_unlock_irqrestore(&pwq->pool->lock, flags);
+		raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags);
 		/*
 		 * We could be printing a lot from atomic context, e.g.
 		 * sysrq-t -> show_all_workqueues(). Avoid triggering
@@ -5244,10 +6168,10 @@ static void show_one_worker_pool(struct worker_pool *pool)
 {
 	struct worker *worker;
 	bool first = true;
-	unsigned long flags;
+	unsigned long irq_flags;
 	unsigned long hung = 0;
 
-	raw_spin_lock_irqsave(&pool->lock, flags);
+	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 	if (pool->nr_workers == pool->nr_idle)
 		goto next_pool;
 
@@ -5268,14 +6192,14 @@ static void show_one_worker_pool(struct worker_pool *pool)
 		pr_cont(" manager: %d",
 			task_pid_nr(pool->manager->task));
 	list_for_each_entry(worker, &pool->idle_list, entry) {
-		pr_cont(" %s%d", first ? "idle: " : "",
-			task_pid_nr(worker->task));
+		pr_cont(" %s", first ? "idle: " : "");
+		pr_cont_worker_id(worker);
 		first = false;
 	}
 	pr_cont("\n");
 	printk_deferred_exit();
 next_pool:
-	raw_spin_unlock_irqrestore(&pool->lock, flags);
+	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 	/*
 	 * We could be printing a lot from atomic context, e.g.
 	 * sysrq-t -> show_all_workqueues(). Avoid triggering
@@ -5542,13 +6466,15 @@ int workqueue_online_cpu(unsigned int cpu)
 	mutex_lock(&wq_pool_mutex);
 
 	for_each_pool(pool, pi) {
-		mutex_lock(&wq_pool_attach_mutex);
+		/* BH pools aren't affected by hotplug */
+		if (pool->flags & POOL_BH)
+			continue;
 
+		mutex_lock(&wq_pool_attach_mutex);
 		if (pool->cpu == cpu)
 			rebind_workers(pool);
 		else if (pool->cpu < 0)
 			restore_unbound_workers_cpumask(pool, cpu);
-
 		mutex_unlock(&wq_pool_attach_mutex);
 	}
 
@@ -5562,6 +6488,10 @@ int workqueue_online_cpu(unsigned int cpu)
 
 			for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]])
 				wq_update_pod(wq, tcpu, cpu, true);
+
+			mutex_lock(&wq->mutex);
+			wq_update_node_max_active(wq, -1);
+			mutex_unlock(&wq->mutex);
 		}
 	}
 
@@ -5590,6 +6520,10 @@ int workqueue_offline_cpu(unsigned int cpu)
 
 			for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]])
 				wq_update_pod(wq, tcpu, cpu, false);
+
+			mutex_lock(&wq->mutex);
+			wq_update_node_max_active(wq, cpu);
+			mutex_unlock(&wq->mutex);
 		}
 	}
 	mutex_unlock(&wq_pool_mutex);
@@ -5677,7 +6611,6 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe_key);
 void freeze_workqueues_begin(void)
 {
 	struct workqueue_struct *wq;
-	struct pool_workqueue *pwq;
 
 	mutex_lock(&wq_pool_mutex);
 
@@ -5686,8 +6619,7 @@ void freeze_workqueues_begin(void)
 
 	list_for_each_entry(wq, &workqueues, list) {
 		mutex_lock(&wq->mutex);
-		for_each_pwq(pwq, wq)
-			pwq_adjust_max_active(pwq);
+		wq_adjust_max_active(wq);
 		mutex_unlock(&wq->mutex);
 	}
 
@@ -5752,7 +6684,6 @@ out_unlock:
 void thaw_workqueues(void)
 {
 	struct workqueue_struct *wq;
-	struct pool_workqueue *pwq;
 
 	mutex_lock(&wq_pool_mutex);
 
@@ -5764,8 +6695,7 @@ void thaw_workqueues(void)
 	/* restore max_active and repopulate worklist */
 	list_for_each_entry(wq, &workqueues, list) {
 		mutex_lock(&wq->mutex);
-		for_each_pwq(pwq, wq)
-			pwq_adjust_max_active(pwq);
+		wq_adjust_max_active(wq);
 		mutex_unlock(&wq->mutex);
 	}
 
@@ -5784,16 +6714,9 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 	lockdep_assert_held(&wq_pool_mutex);
 
 	list_for_each_entry(wq, &workqueues, list) {
-		if (!(wq->flags & WQ_UNBOUND))
+		if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING))
 			continue;
 
-		/* creating multiple pwqs breaks ordering guarantee */
-		if (!list_empty(&wq->pwqs)) {
-			if (wq->flags & __WQ_ORDERED_EXPLICIT)
-				continue;
-			wq->flags &= ~__WQ_ORDERED;
-		}
-
 		ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask);
 		if (IS_ERR(ctx)) {
 			ret = PTR_ERR(ctx);
@@ -6307,11 +7230,10 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	int ret;
 
 	/*
-	 * Adjusting max_active or creating new pwqs by applying
-	 * attributes breaks ordering guarantee.  Disallow exposing ordered
-	 * workqueues.
+	 * Adjusting max_active breaks ordering guarantee.  Disallow exposing
+	 * ordered workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+	if (WARN_ON(wq->flags & __WQ_ORDERED))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
@@ -6408,10 +7330,10 @@ static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;
 static void show_cpu_pool_hog(struct worker_pool *pool)
 {
 	struct worker *worker;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int bkt;
 
-	raw_spin_lock_irqsave(&pool->lock, flags);
+	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
 		if (task_is_running(worker->task)) {
@@ -6429,7 +7351,7 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 		}
 	}
 
-	raw_spin_unlock_irqrestore(&pool->lock, flags);
+	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 }
 
 static void show_cpu_pools_hogs(void)
@@ -6501,7 +7423,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		/* did we stall? */
 		if (time_after(now, ts + thresh)) {
 			lockup_detected = true;
-			if (pool->cpu >= 0) {
+			if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) {
 				pool->cpu_stall = true;
 				cpu_pool_stall = true;
 			}
@@ -6584,6 +7506,16 @@ static inline void wq_watchdog_init(void) { }
 
 #endif	/* CONFIG_WQ_WATCHDOG */
 
+static void bh_pool_kick_normal(struct irq_work *irq_work)
+{
+	raise_softirq_irqoff(TASKLET_SOFTIRQ);
+}
+
+static void bh_pool_kick_highpri(struct irq_work *irq_work)
+{
+	raise_softirq_irqoff(HI_SOFTIRQ);
+}
+
 static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask)
 {
 	if (!cpumask_intersects(wq_unbound_cpumask, mask)) {
@@ -6595,6 +7527,22 @@ static void __init restrict_unbound_cpumask(const char *name, const struct cpuma
 	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask);
 }
 
+static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice)
+{
+	BUG_ON(init_worker_pool(pool));
+	pool->cpu = cpu;
+	cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
+	cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu));
+	pool->attrs->nice = nice;
+	pool->attrs->affn_strict = true;
+	pool->node = cpu_to_node(cpu);
+
+	/* alloc pool ID */
+	mutex_lock(&wq_pool_mutex);
+	BUG_ON(worker_pool_assign_id(pool));
+	mutex_unlock(&wq_pool_mutex);
+}
+
 /**
  * workqueue_init_early - early init for workqueue subsystem
  *
@@ -6609,6 +7557,8 @@ void __init workqueue_init_early(void)
 {
 	struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM];
 	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
+	void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal,
+						       bh_pool_kick_highpri };
 	int i, cpu;
 
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
@@ -6630,6 +7580,13 @@ void __init workqueue_init_early(void)
 	wq_update_pod_attrs_buf = alloc_workqueue_attrs();
 	BUG_ON(!wq_update_pod_attrs_buf);
 
+	/*
+	 * If nohz_full is enabled, set power efficient workqueue as unbound.
+	 * This allows workqueue items to be moved to HK CPUs.
+	 */
+	if (housekeeping_enabled(HK_TYPE_TICK))
+		wq_power_efficient = true;
+
 	/* initialize WQ_AFFN_SYSTEM pods */
 	pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL);
 	pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL);
@@ -6643,25 +7600,21 @@ void __init workqueue_init_early(void)
 	pt->pod_node[0] = NUMA_NO_NODE;
 	pt->cpu_pod[0] = 0;
 
-	/* initialize CPU pools */
+	/* initialize BH and CPU pools */
 	for_each_possible_cpu(cpu) {
 		struct worker_pool *pool;
 
 		i = 0;
-		for_each_cpu_worker_pool(pool, cpu) {
-			BUG_ON(init_worker_pool(pool));
-			pool->cpu = cpu;
-			cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu));
-			cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu));
-			pool->attrs->nice = std_nice[i++];
-			pool->attrs->affn_strict = true;
-			pool->node = cpu_to_node(cpu);
-
-			/* alloc pool ID */
-			mutex_lock(&wq_pool_mutex);
-			BUG_ON(worker_pool_assign_id(pool));
-			mutex_unlock(&wq_pool_mutex);
+		for_each_bh_worker_pool(pool, cpu) {
+			init_cpu_worker_pool(pool, cpu, std_nice[i]);
+			pool->flags |= POOL_BH;
+			init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]);
+			i++;
 		}
+
+		i = 0;
+		for_each_cpu_worker_pool(pool, cpu)
+			init_cpu_worker_pool(pool, cpu, std_nice[i++]);
 	}
 
 	/* create default unbound and ordered wq attrs */
@@ -6691,13 +7644,17 @@ void __init workqueue_init_early(void)
 					      WQ_FREEZABLE, 0);
 	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
 					      WQ_POWER_EFFICIENT, 0);
-	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
+	system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient",
 					      WQ_FREEZABLE | WQ_POWER_EFFICIENT,
 					      0);
+	system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
+	system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
+					       WQ_BH | WQ_HIGHPRI, 0);
 	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
 	       !system_unbound_wq || !system_freezable_wq ||
 	       !system_power_efficient_wq ||
-	       !system_freezable_power_efficient_wq);
+	       !system_freezable_power_efficient_wq ||
+	       !system_bh_wq || !system_bh_highpri_wq);
 }
 
 static void __init wq_cpu_intensive_thresh_init(void)
@@ -6763,9 +7720,10 @@ void __init workqueue_init(void)
 	 * up. Also, create a rescuer for workqueues that requested it.
 	 */
 	for_each_possible_cpu(cpu) {
-		for_each_cpu_worker_pool(pool, cpu) {
+		for_each_bh_worker_pool(pool, cpu)
+			pool->node = cpu_to_node(cpu);
+		for_each_cpu_worker_pool(pool, cpu)
 			pool->node = cpu_to_node(cpu);
-		}
 	}
 
 	list_for_each_entry(wq, &workqueues, list) {
@@ -6776,7 +7734,16 @@ void __init workqueue_init(void)
 
 	mutex_unlock(&wq_pool_mutex);
 
-	/* create the initial workers */
+	/*
+	 * Create the initial workers. A BH pool has one pseudo worker that
+	 * represents the shared BH execution context and thus doesn't get
+	 * affected by hotplug events. Create the BH pseudo workers for all
+	 * possible CPUs here.
+	 */
+	for_each_possible_cpu(cpu)
+		for_each_bh_worker_pool(pool, cpu)
+			BUG_ON(!create_worker(pool));
+
 	for_each_online_cpu(cpu) {
 		for_each_cpu_worker_pool(pool, cpu) {
 			pool->flags &= ~POOL_DISASSOCIATED;
@@ -6856,7 +7823,7 @@ static bool __init cpus_share_numa(int cpu0, int cpu1)
 /**
  * workqueue_init_topology - initialize CPU pods for unbound workqueues
  *
- * This is the third step of there-staged workqueue subsystem initialization and
+ * This is the third step of three-staged workqueue subsystem initialization and
  * invoked after SMP and topology information are fully initialized. It
  * initializes the unbound CPU pods accordingly.
  */
@@ -6870,6 +7837,8 @@ void __init workqueue_init_topology(void)
 	init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache);
 	init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa);
 
+	wq_topo_initialized = true;
+
 	mutex_lock(&wq_pool_mutex);
 
 	/*
@@ -6878,8 +7847,12 @@ void __init workqueue_init_topology(void)
 	 * combinations to apply per-pod sharing.
 	 */
 	list_for_each_entry(wq, &workqueues, list) {
-		for_each_online_cpu(cpu) {
+		for_each_online_cpu(cpu)
 			wq_update_pod(wq, cpu, cpu, true);
+		if (wq->flags & WQ_UNBOUND) {
+			mutex_lock(&wq->mutex);
+			wq_update_node_max_active(wq, -1);
+			mutex_unlock(&wq->mutex);
 		}
 	}
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 975a07f9f1cc..6c596e65de8a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1303,7 +1303,7 @@ config PROVE_LOCKING
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES if !PREEMPT_RT
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
-	select DEBUG_RWSEMS
+	select DEBUG_RWSEMS if !PREEMPT_RT
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
 	select PREEMPT_COUNT if !ARCH_NO_PREEMPT
@@ -1426,7 +1426,7 @@ config DEBUG_WW_MUTEX_SLOWPATH
 
 config DEBUG_RWSEMS
 	bool "RW Semaphore debugging: basic checks"
-	depends on DEBUG_KERNEL
+	depends on DEBUG_KERNEL && !PREEMPT_RT
 	help
 	  This debugging feature allows mismatched rw semaphore locks
 	  and unlocks to be detected and reported.
@@ -2235,6 +2235,7 @@ config TEST_DIV64
 config TEST_IOV_ITER
 	tristate "Test iov_iter operation" if !KUNIT_ALL_TESTS
 	depends on KUNIT
+	depends on MMU
 	default KUNIT_ALL_TESTS
 	help
 	  Enable this to turn on testing of the operation of the I/O iterator
@@ -2857,28 +2858,6 @@ config TEST_MEMCAT_P
 
 	  If unsure, say N.
 
-config TEST_LIVEPATCH
-	tristate "Test livepatching"
-	default n
-	depends on DYNAMIC_DEBUG
-	depends on LIVEPATCH
-	depends on m
-	help
-	  Test kernel livepatching features for correctness.  The tests will
-	  load test modules that will be livepatched in various scenarios.
-
-	  To run all the livepatching tests:
-
-	  make -C tools/testing/selftests TARGETS=livepatch run_tests
-
-	  Alternatively, individual tests may be invoked:
-
-	  tools/testing/selftests/livepatch/test-callbacks.sh
-	  tools/testing/selftests/livepatch/test-livepatch.sh
-	  tools/testing/selftests/livepatch/test-shadow-vars.sh
-
-	  If unsure, say N.
-
 config TEST_OBJAGG
 	tristate "Perform selftest on object aggreration manager"
 	default n
diff --git a/lib/Makefile b/lib/Makefile
index 6b09731d8e61..95ed57f377fd 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -134,8 +134,6 @@ endif
 obj-$(CONFIG_TEST_FPU) += test_fpu.o
 CFLAGS_test_fpu.o += $(FPU_CFLAGS)
 
-obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
-
 # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module,
 # so we can't just use obj-$(CONFIG_KUNIT).
 ifdef CONFIG_KUNIT
diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index 225bb7701460..bf70850035c7 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -215,7 +215,7 @@ static const u32 init_sums_no_overflow[] = {
 	0xffff0000, 0xfffffffb,
 };
 
-static const __sum16 expected_csum_ipv6_magic[] = {
+static const u16 expected_csum_ipv6_magic[] = {
 	0x18d4, 0x3085, 0x2e4b, 0xd9f4, 0xbdc8, 0x78f,	0x1034, 0x8422, 0x6fc0,
 	0xd2f6, 0xbeb5, 0x9d3,	0x7e2a, 0x312e, 0x778e, 0xc1bb, 0x7cf2, 0x9d1e,
 	0xca21, 0xf3ff, 0x7569, 0xb02e, 0xca86, 0x7e76, 0x4539, 0x45e3, 0xf28d,
@@ -241,7 +241,7 @@ static const __sum16 expected_csum_ipv6_magic[] = {
 	0x3845, 0x1014
 };
 
-static const __sum16 expected_fast_csum[] = {
+static const u16 expected_fast_csum[] = {
 	0xda83, 0x45da, 0x4f46, 0x4e4f, 0x34e,	0xe902, 0xa5e9, 0x87a5, 0x7187,
 	0x5671, 0xf556, 0x6df5, 0x816d, 0x8f81, 0xbb8f, 0xfbba, 0x5afb, 0xbe5a,
 	0xedbe, 0xabee, 0x6aac, 0xe6b,	0xea0d, 0x67ea, 0x7e68, 0x8a7e, 0x6f8a,
@@ -577,7 +577,8 @@ static void test_csum_no_carry_inputs(struct kunit *test)
 
 static void test_ip_fast_csum(struct kunit *test)
 {
-	__sum16 csum_result, expected;
+	__sum16 csum_result;
+	u16 expected;
 
 	for (int len = IPv4_MIN_WORDS; len < IPv4_MAX_WORDS; len++) {
 		for (int index = 0; index < NUM_IP_FAST_CSUM_TESTS; index++) {
@@ -586,7 +587,7 @@ static void test_ip_fast_csum(struct kunit *test)
 				expected_fast_csum[(len - IPv4_MIN_WORDS) *
 						   NUM_IP_FAST_CSUM_TESTS +
 						   index];
-			CHECK_EQ(expected, csum_result);
+			CHECK_EQ(to_sum16(expected), csum_result);
 		}
 	}
 }
@@ -598,7 +599,7 @@ static void test_csum_ipv6_magic(struct kunit *test)
 	const struct in6_addr *daddr;
 	unsigned int len;
 	unsigned char proto;
-	unsigned int csum;
+	__wsum csum;
 
 	const int daddr_offset = sizeof(struct in6_addr);
 	const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr);
@@ -611,10 +612,10 @@ static void test_csum_ipv6_magic(struct kunit *test)
 		saddr = (const struct in6_addr *)(random_buf + i);
 		daddr = (const struct in6_addr *)(random_buf + i +
 						  daddr_offset);
-		len = *(unsigned int *)(random_buf + i + len_offset);
+		len = le32_to_cpu(*(__le32 *)(random_buf + i + len_offset));
 		proto = *(random_buf + i + proto_offset);
-		csum = *(unsigned int *)(random_buf + i + csum_offset);
-		CHECK_EQ(expected_csum_ipv6_magic[i],
+		csum = *(__wsum *)(random_buf + i + csum_offset);
+		CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]),
 			 csum_ipv6_magic(saddr, daddr, len, proto, csum));
 	}
 #endif /* !CONFIG_NET */
diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c
index d4572dbc9145..705b82736be0 100644
--- a/lib/cmdline_kunit.c
+++ b/lib/cmdline_kunit.c
@@ -124,7 +124,7 @@ static void cmdline_do_one_range_test(struct kunit *test, const char *in,
 			    n, e[0], r[0]);
 
 	p = memchr_inv(&r[1], 0, sizeof(r) - sizeof(r[0]));
-	KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %u out of bound", n, p - r);
+	KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %td out of bound", n, p - r);
 }
 
 static void cmdline_test_range(struct kunit *test)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e0aa6b440ca5..4a6a9f419bd7 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -166,7 +166,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
-		.copy_mc = false,
 		.nofault = false,
 		.data_source = direction,
 		.__iov = iov,
@@ -245,26 +244,8 @@ EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
 #endif /* CONFIG_ARCH_HAS_COPY_MC */
 
 static __always_inline
-size_t memcpy_from_iter_mc(void *iter_from, size_t progress,
-			   size_t len, void *to, void *priv2)
-{
-	return copy_mc_to_kernel(to + progress, iter_from, len);
-}
-
-static size_t __copy_from_iter_mc(void *addr, size_t bytes, struct iov_iter *i)
-{
-	if (unlikely(i->count < bytes))
-		bytes = i->count;
-	if (unlikely(!bytes))
-		return 0;
-	return iterate_bvec(i, bytes, addr, NULL, memcpy_from_iter_mc);
-}
-
-static __always_inline
 size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(iov_iter_is_copy_mc(i)))
-		return __copy_from_iter_mc(addr, bytes, i);
 	return iterate_and_advance(i, bytes, addr,
 				   copy_from_user_iter, memcpy_from_iter);
 }
@@ -633,7 +614,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_KVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.kvec = kvec,
 		.nr_segs = nr_segs,
@@ -650,7 +630,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_BVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.bvec = bvec,
 		.nr_segs = nr_segs,
@@ -679,7 +658,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
 	BUG_ON(direction & ~1);
 	*i = (struct iov_iter) {
 		.iter_type = ITER_XARRAY,
-		.copy_mc = false,
 		.data_source = direction,
 		.xarray = xarray,
 		.xarray_start = start,
@@ -703,7 +681,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
 	BUG_ON(direction != READ);
 	*i = (struct iov_iter){
 		.iter_type = ITER_DISCARD,
-		.copy_mc = false,
 		.data_source = false,
 		.count = count,
 		.iov_offset = 0
@@ -714,12 +691,11 @@ EXPORT_SYMBOL(iov_iter_discard);
 static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
 				   unsigned len_mask)
 {
+	const struct iovec *iov = iter_iov(i);
 	size_t size = i->count;
 	size_t skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		const struct iovec *iov = iter_iov(i) + k;
+	do {
 		size_t len = iov->iov_len - skip;
 
 		if (len > size)
@@ -729,34 +705,36 @@ static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
 		if ((unsigned long)(iov->iov_base + skip) & addr_mask)
 			return false;
 
+		iov++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return true;
 }
 
 static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
 				  unsigned len_mask)
 {
-	size_t size = i->count;
+	const struct bio_vec *bvec = i->bvec;
 	unsigned skip = i->iov_offset;
-	unsigned k;
+	size_t size = i->count;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		size_t len = i->bvec[k].bv_len - skip;
+	do {
+		size_t len = bvec->bv_len;
 
 		if (len > size)
 			len = size;
 		if (len & len_mask)
 			return false;
-		if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask)
+		if ((unsigned long)(bvec->bv_offset + skip) & addr_mask)
 			return false;
 
+		bvec++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return true;
 }
 
@@ -800,13 +778,12 @@ EXPORT_SYMBOL_GPL(iov_iter_is_aligned);
 
 static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
 {
+	const struct iovec *iov = iter_iov(i);
 	unsigned long res = 0;
 	size_t size = i->count;
 	size_t skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		const struct iovec *iov = iter_iov(i) + k;
+	do {
 		size_t len = iov->iov_len - skip;
 		if (len) {
 			res |= (unsigned long)iov->iov_base + skip;
@@ -814,30 +791,31 @@ static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
 				len = size;
 			res |= len;
 			size -= len;
-			if (!size)
-				break;
 		}
-	}
+		iov++;
+		skip = 0;
+	} while (size);
 	return res;
 }
 
 static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i)
 {
+	const struct bio_vec *bvec = i->bvec;
 	unsigned res = 0;
 	size_t size = i->count;
 	unsigned skip = i->iov_offset;
-	unsigned k;
 
-	for (k = 0; k < i->nr_segs; k++, skip = 0) {
-		size_t len = i->bvec[k].bv_len - skip;
-		res |= (unsigned long)i->bvec[k].bv_offset + skip;
+	do {
+		size_t len = bvec->bv_len - skip;
+		res |= (unsigned long)bvec->bv_offset + skip;
 		if (len > size)
 			len = size;
 		res |= len;
+		bvec++;
 		size -= len;
-		if (!size)
-			break;
-	}
+		skip = 0;
+	} while (size);
+
 	return res;
 }
 
@@ -1166,11 +1144,12 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 EXPORT_SYMBOL(dup_iter);
 
 static __noclone int copy_compat_iovec_from_user(struct iovec *iov,
-		const struct iovec __user *uvec, unsigned long nr_segs)
+		const struct iovec __user *uvec, u32 nr_segs)
 {
 	const struct compat_iovec __user *uiov =
 		(const struct compat_iovec __user *)uvec;
-	int ret = -EFAULT, i;
+	int ret = -EFAULT;
+	u32 i;
 
 	if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
 		return -EFAULT;
diff --git a/lib/kobject.c b/lib/kobject.c
index 59dbcbdb1c91..72fa20f405f1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -74,10 +74,12 @@ static int create_dir(struct kobject *kobj)
 	if (error)
 		return error;
 
-	error = sysfs_create_groups(kobj, ktype->default_groups);
-	if (error) {
-		sysfs_remove_dir(kobj);
-		return error;
+	if (ktype) {
+		error = sysfs_create_groups(kobj, ktype->default_groups);
+		if (error) {
+			sysfs_remove_dir(kobj);
+			return error;
+		}
 	}
 
 	/*
@@ -589,7 +591,8 @@ static void __kobject_del(struct kobject *kobj)
 	sd = kobj->sd;
 	ktype = get_ktype(kobj);
 
-	sysfs_remove_groups(kobj, ktype->default_groups);
+	if (ktype)
+		sysfs_remove_groups(kobj, ktype->default_groups);
 
 	/* send "remove" if the caller did not do it but sent "add" */
 	if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
@@ -666,6 +669,10 @@ static void kobject_cleanup(struct kobject *kobj)
 	pr_debug("'%s' (%p): %s, parent %p\n",
 		 kobject_name(kobj), kobj, __func__, kobj->parent);
 
+	if (t && !t->release)
+		pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
+			 kobject_name(kobj), kobj);
+
 	/* remove from sysfs if the caller did not do it */
 	if (kobj->state_in_sysfs) {
 		pr_debug("'%s' (%p): auto cleanup kobject_del\n",
@@ -676,13 +683,10 @@ static void kobject_cleanup(struct kobject *kobj)
 		parent = NULL;
 	}
 
-	if (t->release) {
+	if (t && t->release) {
 		pr_debug("'%s' (%p): calling ktype release\n",
 			 kobject_name(kobj), kobj);
 		t->release(kobj);
-	} else {
-		pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
-			 kobject_name(kobj), kobj);
 	}
 
 	/* free name if we allocated it */
@@ -1056,7 +1060,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa
 {
 	const struct kobj_ns_type_operations *ops = NULL;
 
-	if (parent && parent->ktype->child_ns_type)
+	if (parent && parent->ktype && parent->ktype->child_ns_type)
 		ops = parent->ktype->child_ns_type(parent);
 
 	return ops;
diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
index 54bd55836405..5fcd48ff0f36 100644
--- a/lib/kunit/device-impl.h
+++ b/lib/kunit/device-impl.h
@@ -13,5 +13,7 @@
 
 // For internal use only -- registers the kunit_bus.
 int kunit_bus_init(void);
+// For internal use only -- unregisters the kunit_bus.
+void kunit_bus_shutdown(void);
 
 #endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
index f5371287b375..abc603730b8e 100644
--- a/lib/kunit/device.c
+++ b/lib/kunit/device.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 
 #include <kunit/test.h>
 #include <kunit/device.h>
@@ -35,7 +36,7 @@ struct kunit_device {
 
 #define to_kunit_device(d) container_of_const(d, struct kunit_device, dev)
 
-static struct bus_type kunit_bus_type = {
+static const struct bus_type kunit_bus_type = {
 	.name		= "kunit",
 };
 
@@ -45,8 +46,8 @@ int kunit_bus_init(void)
 	int error;
 
 	kunit_bus_device = root_device_register("kunit");
-	if (!kunit_bus_device)
-		return -ENOMEM;
+	if (IS_ERR(kunit_bus_device))
+		return PTR_ERR(kunit_bus_device);
 
 	error = bus_register(&kunit_bus_type);
 	if (error)
@@ -54,6 +55,20 @@ int kunit_bus_init(void)
 	return error;
 }
 
+/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */
+void kunit_bus_shutdown(void)
+{
+	/* Make sure the bus exists before we unregister it. */
+	if (IS_ERR_OR_NULL(kunit_bus_device))
+		return;
+
+	bus_unregister(&kunit_bus_type);
+
+	root_device_unregister(kunit_bus_device);
+
+	kunit_bus_device = NULL;
+}
+
 /* Release a 'fake' KUnit device. */
 static void kunit_device_release(struct device *d)
 {
@@ -119,6 +134,9 @@ static struct kunit_device *kunit_device_register_internal(struct kunit *test,
 		return ERR_PTR(err);
 	}
 
+	kunit_dev->dev.dma_mask = &kunit_dev->dev.coherent_dma_mask;
+	kunit_dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+
 	kunit_add_action(test, device_unregister_wrapper, &kunit_dev->dev);
 
 	return kunit_dev;
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 717b9599036b..70b9a43cd257 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -33,13 +33,13 @@ static char *filter_glob_param;
 static char *filter_param;
 static char *filter_action_param;
 
-module_param_named(filter_glob, filter_glob_param, charp, 0400);
+module_param_named(filter_glob, filter_glob_param, charp, 0600);
 MODULE_PARM_DESC(filter_glob,
 		"Filter which KUnit test suites/tests run at boot-time, e.g. list* or list*.*del_test");
-module_param_named(filter, filter_param, charp, 0400);
+module_param_named(filter, filter_param, charp, 0600);
 MODULE_PARM_DESC(filter,
 		"Filter which KUnit test suites/tests run at boot-time using attributes, e.g. speed>slow");
-module_param_named(filter_action, filter_action_param, charp, 0400);
+module_param_named(filter_action, filter_action_param, charp, 0600);
 MODULE_PARM_DESC(filter_action,
 		"Changes behavior of filtered tests using attributes, valid values are:\n"
 		"<none>: do not run filtered tests as normal\n"
@@ -146,6 +146,10 @@ void kunit_free_suite_set(struct kunit_suite_set suite_set)
 	kfree(suite_set.start);
 }
 
+/*
+ * Filter and reallocate test suites. Must return the filtered test suites set
+ * allocated at a valid virtual address or NULL in case of error.
+ */
 struct kunit_suite_set
 kunit_filter_suites(const struct kunit_suite_set *suite_set,
 		    const char *filter_glob,
diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c
index 22d4ee86dbed..3f7f967e3688 100644
--- a/lib/kunit/executor_test.c
+++ b/lib/kunit/executor_test.c
@@ -129,7 +129,7 @@ static void parse_filter_attr_test(struct kunit *test)
 			GFP_KERNEL);
 	for (j = 0; j < filter_count; j++) {
 		parsed_filters[j] = kunit_next_attr_filter(&filter, &err);
-		KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter '%s'", filters[j]);
+		KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter from '%s'", filters);
 	}
 
 	KUNIT_EXPECT_STREQ(test, kunit_attr_filter_name(parsed_filters[0]), "speed");
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index c4259d910356..f7980ef236a3 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -720,7 +720,7 @@ static void kunit_device_cleanup_test(struct kunit *test)
 	long action_was_run = 0;
 
 	test_device = kunit_device_register(test, "my_device");
-	KUNIT_ASSERT_NOT_NULL(test, test_device);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
 
 	/* Add an action to verify cleanup. */
 	devm_add_action(test_device, test_dev_action, &action_was_run);
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index f95d2093a0aa..1d1475578515 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -17,6 +17,7 @@
 #include <linux/panic.h>
 #include <linux/sched/debug.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
 
 #include "debugfs.h"
 #include "device-impl.h"
@@ -801,12 +802,19 @@ static void kunit_module_exit(struct module *mod)
 	};
 	const char *action = kunit_action();
 
+	/*
+	 * Check if the start address is a valid virtual address to detect
+	 * if the module load sequence has failed and the suite set has not
+	 * been initialized and filtered.
+	 */
+	if (!suite_set.start || !virt_addr_valid(suite_set.start))
+		return;
+
 	if (!action)
 		__kunit_test_suites_exit(mod->kunit_suites,
 					 mod->num_kunit_suites);
 
-	if (suite_set.start)
-		kunit_free_suite_set(suite_set);
+	kunit_free_suite_set(suite_set);
 }
 
 static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
@@ -816,12 +824,12 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val,
 
 	switch (val) {
 	case MODULE_STATE_LIVE:
+		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_GOING:
 		kunit_module_exit(mod);
 		break;
 	case MODULE_STATE_COMING:
-		kunit_module_init(mod);
 		break;
 	case MODULE_STATE_UNFORMED:
 		break;
@@ -920,6 +928,9 @@ static void __exit kunit_exit(void)
 #ifdef CONFIG_MODULES
 	unregister_module_notifier(&kunit_mod_nb);
 #endif
+
+	kunit_bus_shutdown();
+
 	kunit_debugfs_cleanup();
 }
 module_exit(kunit_exit);
diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile
deleted file mode 100644
index dcc912b3478f..000000000000
--- a/lib/livepatch/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for livepatch test code.
-
-obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \
-				test_klp_callbacks_demo.o \
-				test_klp_callbacks_demo2.o \
-				test_klp_callbacks_busy.o \
-				test_klp_callbacks_mod.o \
-				test_klp_livepatch.o \
-				test_klp_shadow_vars.o \
-				test_klp_state.o \
-				test_klp_state2.o \
-				test_klp_state3.o
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 6f241bb38799..af0970288727 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -4290,6 +4290,56 @@ exists:
 
 }
 
+/**
+ * mas_alloc_cyclic() - Internal call to find somewhere to store an entry
+ * @mas: The maple state.
+ * @startp: Pointer to ID.
+ * @range_lo: Lower bound of range to search.
+ * @range_hi: Upper bound of range to search.
+ * @entry: The entry to store.
+ * @next: Pointer to next ID to allocate.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * Return: 0 if the allocation succeeded without wrapping, 1 if the
+ * allocation succeeded after wrapping, or -EBUSY if there are no
+ * free entries.
+ */
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp)
+{
+	unsigned long min = range_lo;
+	int ret = 0;
+
+	range_lo = max(min, *next);
+	ret = mas_empty_area(mas, range_lo, range_hi, 1);
+	if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) {
+		mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED;
+		ret = 1;
+	}
+	if (ret < 0 && range_lo > min) {
+		ret = mas_empty_area(mas, min, range_hi, 1);
+		if (ret == 0)
+			ret = 1;
+	}
+	if (ret < 0)
+		return ret;
+
+	do {
+		mas_insert(mas, entry);
+	} while (mas_nomem(mas, gfp));
+	if (mas_is_err(mas))
+		return xa_err(mas->node);
+
+	*startp = mas->index;
+	*next = *startp + 1;
+	if (*next == 0)
+		mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED;
+
+	return ret;
+}
+EXPORT_SYMBOL(mas_alloc_cyclic);
+
 static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index)
 {
 retry:
@@ -6443,6 +6493,49 @@ unlock:
 }
 EXPORT_SYMBOL(mtree_alloc_range);
 
+/**
+ * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree.
+ * @mt: The maple tree.
+ * @startp: Pointer to ID.
+ * @range_lo: Lower bound of range to search.
+ * @range_hi: Upper bound of range to search.
+ * @entry: The entry to store.
+ * @next: Pointer to next ID to allocate.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * Finds an empty entry in @mt after @next, stores the new index into
+ * the @id pointer, stores the entry at that index, then updates @next.
+ *
+ * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag.
+ *
+ * Context: Any context.  Takes and releases the mt.lock.  May sleep if
+ * the @gfp flags permit.
+ *
+ * Return: 0 if the allocation succeeded without wrapping, 1 if the
+ * allocation succeeded after wrapping, -ENOMEM if memory could not be
+ * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no
+ * free entries.
+ */
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp)
+{
+	int ret;
+
+	MA_STATE(mas, mt, 0, 0);
+
+	if (!mt_is_alloc(mt))
+		return -EINVAL;
+	if (WARN_ON_ONCE(mt_is_reserved(entry)))
+		return -EINVAL;
+	mtree_lock(mt);
+	ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi,
+			       next, gfp);
+	mtree_unlock(mt);
+	return ret;
+}
+EXPORT_SYMBOL(mtree_alloc_cyclic);
+
 int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp)
diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c
index 440aee705ccc..30e00ef0bf2e 100644
--- a/lib/memcpy_kunit.c
+++ b/lib/memcpy_kunit.c
@@ -32,7 +32,7 @@ struct some_bytes {
 	BUILD_BUG_ON(sizeof(instance.data) != 32);	\
 	for (size_t i = 0; i < sizeof(instance.data); i++) {	\
 		KUNIT_ASSERT_EQ_MSG(test, instance.data[i], v, \
-			"line %d: '%s' not initialized to 0x%02x @ %d (saw 0x%02x)\n", \
+			"line %d: '%s' not initialized to 0x%02x @ %zu (saw 0x%02x)\n", \
 			__LINE__, #instance, v, i, instance.data[i]);	\
 	}	\
 } while (0)
@@ -41,7 +41,7 @@ struct some_bytes {
 	BUILD_BUG_ON(sizeof(one) != sizeof(two)); \
 	for (size_t i = 0; i < sizeof(one); i++) {	\
 		KUNIT_EXPECT_EQ_MSG(test, one.data[i], two.data[i], \
-			"line %d: %s.data[%d] (0x%02x) != %s.data[%d] (0x%02x)\n", \
+			"line %d: %s.data[%zu] (0x%02x) != %s.data[%zu] (0x%02x)\n", \
 			__LINE__, #one, i, one.data[i], #two, i, two.data[i]); \
 	}	\
 	kunit_info(test, "ok: " TEST_OP "() " name "\n");	\
diff --git a/lib/nlattr.c b/lib/nlattr.c
index ed2ab43e1b22..be9c576b6e2d 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -30,6 +30,8 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
@@ -43,6 +45,8 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 /*
diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index cd0b9e95f499..863e2d320938 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -12,15 +12,14 @@
  */
 
 #include <linux/raid/pq.h>
-#include <asm/fpu/api.h>
-#include <asm/vx-insn.h>
+#include <asm/fpu.h>
 
 #define NSIZE 16
 
-static inline void LOAD_CONST(void)
+static __always_inline void LOAD_CONST(void)
 {
-	asm volatile("VREPIB %v24,7");
-	asm volatile("VREPIB %v25,0x1d");
+	fpu_vrepib(24, 0x07);
+	fpu_vrepib(25, 0x1d);
 }
 
 /*
@@ -28,10 +27,7 @@ static inline void LOAD_CONST(void)
  * vector register y left by 1 bit and stores the result in
  * vector register x.
  */
-static inline void SHLBYTE(int x, int y)
-{
-	asm volatile ("VAB %0,%1,%1" : : "i" (x), "i" (y));
-}
+#define SHLBYTE(x, y)		fpu_vab(x, y, y)
 
 /*
  * For each of the 16 bytes in the vector register y the MASK()
@@ -39,49 +35,17 @@ static inline void SHLBYTE(int x, int y)
  * or 0x00 if the high bit is 0. The result is stored in vector
  * register x.
  */
-static inline void MASK(int x, int y)
-{
-	asm volatile ("VESRAVB	%0,%1,24" : : "i" (x), "i" (y));
-}
-
-static inline void AND(int x, int y, int z)
-{
-	asm volatile ("VN %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
-}
-
-static inline void XOR(int x, int y, int z)
-{
-	asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
-}
+#define MASK(x, y)		fpu_vesravb(x, y, 24)
 
-static inline void LOAD_DATA(int x, u8 *ptr)
-{
-	typedef struct { u8 _[16 * $#]; } addrtype;
-	register addrtype *__ptr asm("1") = (addrtype *) ptr;
-
-	asm volatile ("VLM %2,%3,0,%1"
-		      : : "m" (*__ptr), "a" (__ptr), "i" (x),
-			  "i" (x + $# - 1));
-}
-
-static inline void STORE_DATA(int x, u8 *ptr)
-{
-	typedef struct { u8 _[16 * $#]; } addrtype;
-	register addrtype *__ptr asm("1") = (addrtype *) ptr;
-
-	asm volatile ("VSTM %2,%3,0,1"
-		      : "=m" (*__ptr) : "a" (__ptr), "i" (x),
-			"i" (x + $# - 1));
-}
-
-static inline void COPY_VEC(int x, int y)
-{
-	asm volatile ("VLR %0,%1" : : "i" (x), "i" (y));
-}
+#define AND(x, y, z)		fpu_vn(x, y, z)
+#define XOR(x, y, z)		fpu_vx(x, y, z)
+#define LOAD_DATA(x, ptr)	fpu_vlm(x, x + $# - 1, ptr)
+#define STORE_DATA(x, ptr)	fpu_vstm(x, x + $# - 1, ptr)
+#define COPY_VEC(x, y)		fpu_vlr(x, y)
 
 static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 {
-	struct kernel_fpu vxstate;
+	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
 	u8 **dptr, *p, *q;
 	int d, z, z0;
 
@@ -114,7 +78,7 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 					size_t bytes, void **ptrs)
 {
-	struct kernel_fpu vxstate;
+	DECLARE_KERNEL_FPU_ONSTACK32(vxstate);
 	u8 **dptr, *p, *q;
 	int d, z, z0;
 
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 010c730ca7fc..f3f3436d60a9 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -13,16 +13,26 @@
  * seq_buf_init() more than once to reset the seq_buf to start
  * from scratch.
  */
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hex.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
 #include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
 
 /**
  * seq_buf_can_fit - can the new data fit in the current buffer?
  * @s: the seq_buf descriptor
  * @len: The length to see if it can fit in the current buffer
  *
- * Returns true if there's enough unused space in the seq_buf buffer
+ * Returns: true if there's enough unused space in the seq_buf buffer
  * to fit the amount of new data according to @len.
  */
 static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
@@ -35,7 +45,7 @@ static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
  * @m: the seq_file descriptor that is the destination
  * @s: the seq_buf descriptor that is the source.
  *
- * Returns zero on success, non zero otherwise
+ * Returns: zero on success, non-zero otherwise.
  */
 int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
 {
@@ -50,9 +60,9 @@ int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
  * @fmt: printf format string
  * @args: va_list of arguments from a printf() type function
  *
- * Writes a vnprintf() format into the sequencce buffer.
+ * Writes a vnprintf() format into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
 {
@@ -78,7 +88,7 @@ int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
  *
  * Writes a printf() format into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 {
@@ -94,12 +104,12 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 EXPORT_SYMBOL_GPL(seq_buf_printf);
 
 /**
- * seq_buf_do_printk - printk seq_buf line by line
+ * seq_buf_do_printk - printk() seq_buf line by line
  * @s: seq_buf descriptor
  * @lvl: printk level
  *
  * printk()-s a multi-line sequential buffer line by line. The function
- * makes sure that the buffer in @s is nul terminated and safe to read
+ * makes sure that the buffer in @s is NUL-terminated and safe to read
  * as a string.
  */
 void seq_buf_do_printk(struct seq_buf *s, const char *lvl)
@@ -139,7 +149,7 @@ EXPORT_SYMBOL_GPL(seq_buf_do_printk);
  * This function will take the format and the binary array and finish
  * the conversion into the ASCII string within the buffer.
  *
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
 {
@@ -167,7 +177,7 @@ int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
  *
  * Copy a simple string into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_puts(struct seq_buf *s, const char *str)
 {
@@ -196,7 +206,7 @@ EXPORT_SYMBOL_GPL(seq_buf_puts);
  *
  * Copy a single character into the sequence buffer.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putc(struct seq_buf *s, unsigned char c)
 {
@@ -212,7 +222,7 @@ int seq_buf_putc(struct seq_buf *s, unsigned char c)
 EXPORT_SYMBOL_GPL(seq_buf_putc);
 
 /**
- * seq_buf_putmem - write raw data into the sequenc buffer
+ * seq_buf_putmem - write raw data into the sequence buffer
  * @s: seq_buf descriptor
  * @mem: The raw memory to copy into the buffer
  * @len: The length of the raw memory to copy (in bytes)
@@ -221,7 +231,7 @@ EXPORT_SYMBOL_GPL(seq_buf_putc);
  * buffer and a strcpy() would not work. Using this function allows
  * for such cases.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
 {
@@ -249,7 +259,7 @@ int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
  * raw memory into the buffer it writes its ASCII representation of it
  * in hex characters.
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
 		       unsigned int len)
@@ -297,7 +307,7 @@ int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
  *
  * Write a path name into the sequence buffer.
  *
- * Returns the number of written bytes on success, -1 on overflow
+ * Returns: the number of written bytes on success, -1 on overflow.
  */
 int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
 {
@@ -332,6 +342,7 @@ int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
  * or until it reaches the end of the content in the buffer (@s->len),
  * whichever comes first.
  *
+ * Returns:
  * On success, it returns a positive number of the number of bytes
  * it copied.
  *
@@ -382,11 +393,11 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, size_t start, int cnt)
  * linebuf size is maximal length for one line.
  * 32 * 3 - maximum bytes per line, each printed into 2 chars + 1 for
  *	separating space
- * 2 - spaces separating hex dump and ascii representation
- * 32 - ascii representation
+ * 2 - spaces separating hex dump and ASCII representation
+ * 32 - ASCII representation
  * 1 - terminating '\0'
  *
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
  */
 int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, int prefix_type,
 		     int rowsize, int groupsize,
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index a0be5d05c7f0..4a7055a63d9f 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -14,6 +14,7 @@
 
 #define pr_fmt(fmt) "stackdepot: " fmt
 
+#include <linux/debugfs.h>
 #include <linux/gfp.h>
 #include <linux/jhash.h>
 #include <linux/kernel.h>
@@ -21,8 +22,10 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
-#include <linux/percpu.h>
+#include <linux/poison.h>
 #include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -41,17 +44,7 @@
 #define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN)
 #define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \
 			       STACK_DEPOT_EXTRA_BITS)
-#if IS_ENABLED(CONFIG_KMSAN) && CONFIG_STACKDEPOT_MAX_FRAMES >= 32
-/*
- * KMSAN is frequently used in fuzzing scenarios and thus saves a lot of stack
- * traces. As KMSAN does not support evicting stack traces from the stack
- * depot, the stack depot capacity might be reached quickly with large stack
- * records. Adjust the maximum number of stack depot pools for this case.
- */
-#define DEPOT_POOLS_CAP (8192 * (CONFIG_STACKDEPOT_MAX_FRAMES / 16))
-#else
 #define DEPOT_POOLS_CAP 8192
-#endif
 #define DEPOT_MAX_POOLS \
 	(((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \
 	 (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP)
@@ -67,17 +60,30 @@ union handle_parts {
 };
 
 struct stack_record {
-	struct list_head list;		/* Links in hash table or freelist */
+	struct list_head hash_list;	/* Links in the hash table */
 	u32 hash;			/* Hash in hash table */
 	u32 size;			/* Number of stored frames */
-	union handle_parts handle;
+	union handle_parts handle;	/* Constant after initialization */
 	refcount_t count;
-	unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+	union {
+		unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
+		struct {
+			/*
+			 * An important invariant of the implementation is to
+			 * only place a stack record onto the freelist iff its
+			 * refcount is zero. Because stack records with a zero
+			 * refcount are never considered as valid, it is safe to
+			 * union @entries and freelist management state below.
+			 * Conversely, as soon as an entry is off the freelist
+			 * and its refcount becomes non-zero, the below must not
+			 * be accessed until being placed back on the freelist.
+			 */
+			struct list_head free_list;	/* Links in the freelist */
+			unsigned long rcu_state;	/* RCU cookie */
+		};
+	};
 };
 
-#define DEPOT_STACK_RECORD_SIZE \
-	ALIGN(sizeof(struct stack_record), 1 << DEPOT_STACK_ALIGN)
-
 static bool stack_depot_disabled;
 static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT);
 static bool __stack_depot_early_init_passed __initdata;
@@ -103,17 +109,33 @@ static void *stack_pools[DEPOT_MAX_POOLS];
 static void *new_pool;
 /* Number of pools in stack_pools. */
 static int pools_num;
+/* Offset to the unused space in the currently used pool. */
+static size_t pool_offset = DEPOT_POOL_SIZE;
 /* Freelist of stack records within stack_pools. */
 static LIST_HEAD(free_stacks);
-/*
- * Stack depot tries to keep an extra pool allocated even before it runs out
- * of space in the currently used pool. This flag marks whether this extra pool
- * needs to be allocated. It has the value 0 when either an extra pool is not
- * yet allocated or if the limit on the number of pools is reached.
- */
-static bool new_pool_required = true;
-/* Lock that protects the variables above. */
-static DEFINE_RWLOCK(pool_rwlock);
+/* The lock must be held when performing pool or freelist modifications. */
+static DEFINE_RAW_SPINLOCK(pool_lock);
+
+/* Statistics counters for debugfs. */
+enum depot_counter_id {
+	DEPOT_COUNTER_REFD_ALLOCS,
+	DEPOT_COUNTER_REFD_FREES,
+	DEPOT_COUNTER_REFD_INUSE,
+	DEPOT_COUNTER_FREELIST_SIZE,
+	DEPOT_COUNTER_PERSIST_COUNT,
+	DEPOT_COUNTER_PERSIST_BYTES,
+	DEPOT_COUNTER_COUNT,
+};
+static long counters[DEPOT_COUNTER_COUNT];
+static const char *const counter_names[] = {
+	[DEPOT_COUNTER_REFD_ALLOCS]	= "refcounted_allocations",
+	[DEPOT_COUNTER_REFD_FREES]	= "refcounted_frees",
+	[DEPOT_COUNTER_REFD_INUSE]	= "refcounted_in_use",
+	[DEPOT_COUNTER_FREELIST_SIZE]	= "freelist_size",
+	[DEPOT_COUNTER_PERSIST_COUNT]	= "persistent_count",
+	[DEPOT_COUNTER_PERSIST_BYTES]	= "persistent_bytes",
+};
+static_assert(ARRAY_SIZE(counter_names) == DEPOT_COUNTER_COUNT);
 
 static int __init disable_stack_depot(char *str)
 {
@@ -258,174 +280,273 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(stack_depot_init);
 
-/* Initializes a stack depol pool. */
-static void depot_init_pool(void *pool)
+/*
+ * Initializes new stack pool, and updates the list of pools.
+ */
+static bool depot_init_pool(void **prealloc)
 {
-	int offset;
+	lockdep_assert_held(&pool_lock);
 
-	lockdep_assert_held_write(&pool_rwlock);
+	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
+		/* Bail out if we reached the pool limit. */
+		WARN_ON_ONCE(pools_num > DEPOT_MAX_POOLS); /* should never happen */
+		WARN_ON_ONCE(!new_pool); /* to avoid unnecessary pre-allocation */
+		WARN_ONCE(1, "Stack depot reached limit capacity");
+		return false;
+	}
 
-	WARN_ON(!list_empty(&free_stacks));
+	if (!new_pool && *prealloc) {
+		/* We have preallocated memory, use it. */
+		WRITE_ONCE(new_pool, *prealloc);
+		*prealloc = NULL;
+	}
 
-	/* Initialize handles and link stack records into the freelist. */
-	for (offset = 0; offset <= DEPOT_POOL_SIZE - DEPOT_STACK_RECORD_SIZE;
-	     offset += DEPOT_STACK_RECORD_SIZE) {
-		struct stack_record *stack = pool + offset;
+	if (!new_pool)
+		return false; /* new_pool and *prealloc are NULL */
 
-		stack->handle.pool_index = pools_num;
-		stack->handle.offset = offset >> DEPOT_STACK_ALIGN;
-		stack->handle.extra = 0;
+	/* Save reference to the pool to be used by depot_fetch_stack(). */
+	stack_pools[pools_num] = new_pool;
 
-		list_add(&stack->list, &free_stacks);
-	}
+	/*
+	 * Stack depot tries to keep an extra pool allocated even before it runs
+	 * out of space in the currently used pool.
+	 *
+	 * To indicate that a new preallocation is needed new_pool is reset to
+	 * NULL; do not reset to NULL if we have reached the maximum number of
+	 * pools.
+	 */
+	if (pools_num < DEPOT_MAX_POOLS)
+		WRITE_ONCE(new_pool, NULL);
+	else
+		WRITE_ONCE(new_pool, STACK_DEPOT_POISON);
 
-	/* Save reference to the pool to be used by depot_fetch_stack(). */
-	stack_pools[pools_num] = pool;
-	pools_num++;
+	/* Pairs with concurrent READ_ONCE() in depot_fetch_stack(). */
+	WRITE_ONCE(pools_num, pools_num + 1);
+	ASSERT_EXCLUSIVE_WRITER(pools_num);
+
+	pool_offset = 0;
+
+	return true;
 }
 
 /* Keeps the preallocated memory to be used for a new stack depot pool. */
 static void depot_keep_new_pool(void **prealloc)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
 	/*
 	 * If a new pool is already saved or the maximum number of
 	 * pools is reached, do not use the preallocated memory.
 	 */
-	if (!new_pool_required)
+	if (new_pool)
 		return;
 
-	/*
-	 * Use the preallocated memory for the new pool
-	 * as long as we do not exceed the maximum number of pools.
-	 */
-	if (pools_num < DEPOT_MAX_POOLS) {
-		new_pool = *prealloc;
-		*prealloc = NULL;
+	WRITE_ONCE(new_pool, *prealloc);
+	*prealloc = NULL;
+}
+
+/*
+ * Try to initialize a new stack record from the current pool, a cached pool, or
+ * the current pre-allocation.
+ */
+static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
+{
+	struct stack_record *stack;
+	void *current_pool;
+	u32 pool_index;
+
+	lockdep_assert_held(&pool_lock);
+
+	if (pool_offset + size > DEPOT_POOL_SIZE) {
+		if (!depot_init_pool(prealloc))
+			return NULL;
 	}
 
-	/*
-	 * At this point, either a new pool is kept or the maximum
-	 * number of pools is reached. In either case, take note that
-	 * keeping another pool is not required.
-	 */
-	new_pool_required = false;
+	if (WARN_ON_ONCE(pools_num < 1))
+		return NULL;
+	pool_index = pools_num - 1;
+	current_pool = stack_pools[pool_index];
+	if (WARN_ON_ONCE(!current_pool))
+		return NULL;
+
+	stack = current_pool + pool_offset;
+
+	/* Pre-initialize handle once. */
+	stack->handle.pool_index = pool_index;
+	stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
+	stack->handle.extra = 0;
+	INIT_LIST_HEAD(&stack->hash_list);
+
+	pool_offset += size;
+
+	return stack;
 }
 
-/* Updates references to the current and the next stack depot pools. */
-static bool depot_update_pools(void **prealloc)
+/* Try to find next free usable entry from the freelist. */
+static struct stack_record *depot_pop_free(void)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	struct stack_record *stack;
 
-	/* Check if we still have objects in the freelist. */
-	if (!list_empty(&free_stacks))
-		goto out_keep_prealloc;
+	lockdep_assert_held(&pool_lock);
 
-	/* Check if we have a new pool saved and use it. */
-	if (new_pool) {
-		depot_init_pool(new_pool);
-		new_pool = NULL;
+	if (list_empty(&free_stacks))
+		return NULL;
 
-		/* Take note that we might need a new new_pool. */
-		if (pools_num < DEPOT_MAX_POOLS)
-			new_pool_required = true;
+	/*
+	 * We maintain the invariant that the elements in front are least
+	 * recently used, and are therefore more likely to be associated with an
+	 * RCU grace period in the past. Consequently it is sufficient to only
+	 * check the first entry.
+	 */
+	stack = list_first_entry(&free_stacks, struct stack_record, free_list);
+	if (!poll_state_synchronize_rcu(stack->rcu_state))
+		return NULL;
 
-		/* Try keeping the preallocated memory for new_pool. */
-		goto out_keep_prealloc;
-	}
+	list_del(&stack->free_list);
+	counters[DEPOT_COUNTER_FREELIST_SIZE]--;
 
-	/* Bail out if we reached the pool limit. */
-	if (unlikely(pools_num >= DEPOT_MAX_POOLS)) {
-		WARN_ONCE(1, "Stack depot reached limit capacity");
-		return false;
-	}
+	return stack;
+}
 
-	/* Check if we have preallocated memory and use it. */
-	if (*prealloc) {
-		depot_init_pool(*prealloc);
-		*prealloc = NULL;
-		return true;
-	}
+static inline size_t depot_stack_record_size(struct stack_record *s, unsigned int nr_entries)
+{
+	const size_t used = flex_array_size(s, entries, nr_entries);
+	const size_t unused = sizeof(s->entries) - used;
 
-	return false;
+	WARN_ON_ONCE(sizeof(s->entries) < used);
 
-out_keep_prealloc:
-	/* Keep the preallocated memory for a new pool if required. */
-	if (*prealloc)
-		depot_keep_new_pool(prealloc);
-	return true;
+	return ALIGN(sizeof(struct stack_record) - unused, 1 << DEPOT_STACK_ALIGN);
 }
 
 /* Allocates a new stack in a stack depot pool. */
 static struct stack_record *
-depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
+depot_alloc_stack(unsigned long *entries, unsigned int nr_entries, u32 hash, depot_flags_t flags, void **prealloc)
 {
-	struct stack_record *stack;
+	struct stack_record *stack = NULL;
+	size_t record_size;
 
-	lockdep_assert_held_write(&pool_rwlock);
+	lockdep_assert_held(&pool_lock);
 
-	/* Update current and new pools if required and possible. */
-	if (!depot_update_pools(prealloc))
+	/* This should already be checked by public API entry points. */
+	if (WARN_ON_ONCE(!nr_entries))
 		return NULL;
 
-	/* Check if we have a stack record to save the stack trace. */
-	if (list_empty(&free_stacks))
-		return NULL;
+	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
+	if (nr_entries > CONFIG_STACKDEPOT_MAX_FRAMES)
+		nr_entries = CONFIG_STACKDEPOT_MAX_FRAMES;
 
-	/* Get and unlink the first entry from the freelist. */
-	stack = list_first_entry(&free_stacks, struct stack_record, list);
-	list_del(&stack->list);
+	if (flags & STACK_DEPOT_FLAG_GET) {
+		/*
+		 * Evictable entries have to allocate the max. size so they may
+		 * safely be re-used by differently sized allocations.
+		 */
+		record_size = depot_stack_record_size(stack, CONFIG_STACKDEPOT_MAX_FRAMES);
+		stack = depot_pop_free();
+	} else {
+		record_size = depot_stack_record_size(stack, nr_entries);
+	}
 
-	/* Limit number of saved frames to CONFIG_STACKDEPOT_MAX_FRAMES. */
-	if (size > CONFIG_STACKDEPOT_MAX_FRAMES)
-		size = CONFIG_STACKDEPOT_MAX_FRAMES;
+	if (!stack) {
+		stack = depot_pop_free_pool(prealloc, record_size);
+		if (!stack)
+			return NULL;
+	}
 
 	/* Save the stack trace. */
 	stack->hash = hash;
-	stack->size = size;
-	/* stack->handle is already filled in by depot_init_pool(). */
-	refcount_set(&stack->count, 1);
-	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
+	stack->size = nr_entries;
+	/* stack->handle is already filled in by depot_pop_free_pool(). */
+	memcpy(stack->entries, entries, flex_array_size(stack, entries, nr_entries));
+
+	if (flags & STACK_DEPOT_FLAG_GET) {
+		refcount_set(&stack->count, 1);
+		counters[DEPOT_COUNTER_REFD_ALLOCS]++;
+		counters[DEPOT_COUNTER_REFD_INUSE]++;
+	} else {
+		/* Warn on attempts to switch to refcounting this entry. */
+		refcount_set(&stack->count, REFCOUNT_SATURATED);
+		counters[DEPOT_COUNTER_PERSIST_COUNT]++;
+		counters[DEPOT_COUNTER_PERSIST_BYTES] += record_size;
+	}
 
 	/*
 	 * Let KMSAN know the stored stack record is initialized. This shall
 	 * prevent false positive reports if instrumented code accesses it.
 	 */
-	kmsan_unpoison_memory(stack, DEPOT_STACK_RECORD_SIZE);
+	kmsan_unpoison_memory(stack, record_size);
 
 	return stack;
 }
 
 static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 {
+	const int pools_num_cached = READ_ONCE(pools_num);
 	union handle_parts parts = { .handle = handle };
 	void *pool;
 	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
 
-	lockdep_assert_held(&pool_rwlock);
+	lockdep_assert_not_held(&pool_lock);
 
-	if (parts.pool_index > pools_num) {
+	if (parts.pool_index > pools_num_cached) {
 		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
-		     parts.pool_index, pools_num, handle);
+		     parts.pool_index, pools_num_cached, handle);
 		return NULL;
 	}
 
 	pool = stack_pools[parts.pool_index];
-	if (!pool)
+	if (WARN_ON(!pool))
 		return NULL;
 
 	stack = pool + offset;
+	if (WARN_ON(!refcount_read(&stack->count)))
+		return NULL;
+
 	return stack;
 }
 
 /* Links stack into the freelist. */
 static void depot_free_stack(struct stack_record *stack)
 {
-	lockdep_assert_held_write(&pool_rwlock);
+	unsigned long flags;
+
+	lockdep_assert_not_held(&pool_lock);
+
+	raw_spin_lock_irqsave(&pool_lock, flags);
+	printk_deferred_enter();
 
-	list_add(&stack->list, &free_stacks);
+	/*
+	 * Remove the entry from the hash list. Concurrent list traversal may
+	 * still observe the entry, but since the refcount is zero, this entry
+	 * will no longer be considered as valid.
+	 */
+	list_del_rcu(&stack->hash_list);
+
+	/*
+	 * Due to being used from constrained contexts such as the allocators,
+	 * NMI, or even RCU itself, stack depot cannot rely on primitives that
+	 * would sleep (such as synchronize_rcu()) or recursively call into
+	 * stack depot again (such as call_rcu()).
+	 *
+	 * Instead, get an RCU cookie, so that we can ensure this entry isn't
+	 * moved onto another list until the next grace period, and concurrent
+	 * RCU list traversal remains safe.
+	 */
+	stack->rcu_state = get_state_synchronize_rcu();
+
+	/*
+	 * Add the entry to the freelist tail, so that older entries are
+	 * considered first - their RCU cookie is more likely to no longer be
+	 * associated with the current grace period.
+	 */
+	list_add_tail(&stack->free_list, &free_stacks);
+
+	counters[DEPOT_COUNTER_FREELIST_SIZE]++;
+	counters[DEPOT_COUNTER_REFD_FREES]++;
+	counters[DEPOT_COUNTER_REFD_INUSE]--;
+
+	printk_deferred_exit();
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 }
 
 /* Calculates the hash for a stack. */
@@ -453,22 +574,52 @@ int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2,
 
 /* Finds a stack in a bucket of the hash table. */
 static inline struct stack_record *find_stack(struct list_head *bucket,
-					     unsigned long *entries, int size,
-					     u32 hash)
+					      unsigned long *entries, int size,
+					      u32 hash, depot_flags_t flags)
 {
-	struct list_head *pos;
-	struct stack_record *found;
+	struct stack_record *stack, *ret = NULL;
 
-	lockdep_assert_held(&pool_rwlock);
+	/*
+	 * Stack depot may be used from instrumentation that instruments RCU or
+	 * tracing itself; use variant that does not call into RCU and cannot be
+	 * traced.
+	 *
+	 * Note: Such use cases must take care when using refcounting to evict
+	 * unused entries, because the stack record free-then-reuse code paths
+	 * do call into RCU.
+	 */
+	rcu_read_lock_sched_notrace();
+
+	list_for_each_entry_rcu(stack, bucket, hash_list) {
+		if (stack->hash != hash || stack->size != size)
+			continue;
+
+		/*
+		 * This may race with depot_free_stack() accessing the freelist
+		 * management state unioned with @entries. The refcount is zero
+		 * in that case and the below refcount_inc_not_zero() will fail.
+		 */
+		if (data_race(stackdepot_memcmp(entries, stack->entries, size)))
+			continue;
+
+		/*
+		 * Try to increment refcount. If this succeeds, the stack record
+		 * is valid and has not yet been freed.
+		 *
+		 * If STACK_DEPOT_FLAG_GET is not used, it is undefined behavior
+		 * to then call stack_depot_put() later, and we can assume that
+		 * a stack record is never placed back on the freelist.
+		 */
+		if ((flags & STACK_DEPOT_FLAG_GET) && !refcount_inc_not_zero(&stack->count))
+			continue;
 
-	list_for_each(pos, bucket) {
-		found = list_entry(pos, struct stack_record, list);
-		if (found->hash == hash &&
-		    found->size == size &&
-		    !stackdepot_memcmp(entries, found->entries, size))
-			return found;
+		ret = stack;
+		break;
 	}
-	return NULL;
+
+	rcu_read_unlock_sched_notrace();
+
+	return ret;
 }
 
 depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
@@ -482,7 +633,6 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	struct page *page = NULL;
 	void *prealloc = NULL;
 	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
-	bool need_alloc = false;
 	unsigned long flags;
 	u32 hash;
 
@@ -505,31 +655,16 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & stack_hash_mask];
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
-	/* Fast path: look the stack trace up without full locking. */
-	found = find_stack(bucket, entries, nr_entries, hash);
-	if (found) {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
-		printk_deferred_exit();
-		read_unlock_irqrestore(&pool_rwlock, flags);
+	/* Fast path: look the stack trace up without locking. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
+	if (found)
 		goto exit;
-	}
-
-	/* Take note if another stack pool needs to be allocated. */
-	if (new_pool_required)
-		need_alloc = true;
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
 
 	/*
 	 * Allocate memory for a new pool if required now:
 	 * we won't be able to do that under the lock.
 	 */
-	if (unlikely(can_alloc && need_alloc)) {
+	if (unlikely(can_alloc && !READ_ONCE(new_pool))) {
 		/*
 		 * Zero out zone modifiers, as we don't have specific zone
 		 * requirements. Keep the flags related to allocation in atomic
@@ -543,31 +678,36 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	write_lock_irqsave(&pool_rwlock, flags);
+	raw_spin_lock_irqsave(&pool_lock, flags);
 	printk_deferred_enter();
 
-	found = find_stack(bucket, entries, nr_entries, hash);
+	/* Try to find again, to avoid concurrently inserting duplicates. */
+	found = find_stack(bucket, entries, nr_entries, hash, depot_flags);
 	if (!found) {
 		struct stack_record *new =
-			depot_alloc_stack(entries, nr_entries, hash, &prealloc);
+			depot_alloc_stack(entries, nr_entries, hash, depot_flags, &prealloc);
 
 		if (new) {
-			list_add(&new->list, bucket);
+			/*
+			 * This releases the stack record into the bucket and
+			 * makes it visible to readers in find_stack().
+			 */
+			list_add_rcu(&new->hash_list, bucket);
 			found = new;
 		}
-	} else {
-		if (depot_flags & STACK_DEPOT_FLAG_GET)
-			refcount_inc(&found->count);
+	}
+
+	if (prealloc) {
 		/*
-		 * Stack depot already contains this stack trace, but let's
-		 * keep the preallocated memory for future.
+		 * Either stack depot already contains this stack trace, or
+		 * depot_alloc_stack() did not consume the preallocated memory.
+		 * Try to keep the preallocated memory for future.
 		 */
-		if (prealloc)
-			depot_keep_new_pool(&prealloc);
+		depot_keep_new_pool(&prealloc);
 	}
 
 	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
+	raw_spin_unlock_irqrestore(&pool_lock, flags);
 exit:
 	if (prealloc) {
 		/* Stack depot didn't use this memory, free it. */
@@ -592,7 +732,6 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 			       unsigned long **entries)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	*entries = NULL;
 	/*
@@ -604,13 +743,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 	if (!handle || stack_depot_disabled)
 		return 0;
 
-	read_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-
-	printk_deferred_exit();
-	read_unlock_irqrestore(&pool_rwlock, flags);
+	/*
+	 * Should never be NULL, otherwise this is a use-after-put (or just a
+	 * corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or use after stack_depot_put()"))
+		return 0;
 
 	*entries = stack->entries;
 	return stack->size;
@@ -620,29 +759,20 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch);
 void stack_depot_put(depot_stack_handle_t handle)
 {
 	struct stack_record *stack;
-	unsigned long flags;
 
 	if (!handle || stack_depot_disabled)
 		return;
 
-	write_lock_irqsave(&pool_rwlock, flags);
-	printk_deferred_enter();
-
 	stack = depot_fetch_stack(handle);
-	if (WARN_ON(!stack))
-		goto out;
-
-	if (refcount_dec_and_test(&stack->count)) {
-		/* Unlink stack from the hash table. */
-		list_del(&stack->list);
+	/*
+	 * Should always be able to find the stack record, otherwise this is an
+	 * unbalanced put attempt (or corrupt handle).
+	 */
+	if (WARN(!stack, "corrupt handle or unbalanced stack_depot_put()"))
+		return;
 
-		/* Free stack. */
+	if (refcount_dec_and_test(&stack->count))
 		depot_free_stack(stack);
-	}
-
-out:
-	printk_deferred_exit();
-	write_unlock_irqrestore(&pool_rwlock, flags);
 }
 EXPORT_SYMBOL_GPL(stack_depot_put);
 
@@ -690,3 +820,30 @@ unsigned int stack_depot_get_extra_bits(depot_stack_handle_t handle)
 	return parts.extra;
 }
 EXPORT_SYMBOL(stack_depot_get_extra_bits);
+
+static int stats_show(struct seq_file *seq, void *v)
+{
+	/*
+	 * data race ok: These are just statistics counters, and approximate
+	 * statistics are ok for debugging.
+	 */
+	seq_printf(seq, "pools: %d\n", data_race(pools_num));
+	for (int i = 0; i < DEPOT_COUNTER_COUNT; i++)
+		seq_printf(seq, "%s: %ld\n", counter_names[i], data_race(counters[i]));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(stats);
+
+static int depot_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	if (stack_depot_disabled)
+		return 0;
+
+	dir = debugfs_create_dir("stackdepot", NULL);
+	debugfs_create_file("stats", 0444, dir, NULL, &stats_fops);
+	return 0;
+}
+late_initcall(depot_debugfs_init);
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 29185ac5c727..399380db449c 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -3599,6 +3599,45 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	mas_unlock(&mas);
 }
 
+static noinline void __init alloc_cyclic_testing(struct maple_tree *mt)
+{
+	unsigned long location;
+	unsigned long next;
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+
+	next = 0;
+	mtree_lock(mt);
+	for (int i = 0; i < 100; i++) {
+		mas_alloc_cyclic(&mas, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+		MAS_BUG_ON(&mas, i != location - 2);
+		MAS_BUG_ON(&mas, mas.index != location);
+		MAS_BUG_ON(&mas, mas.last != location);
+		MAS_BUG_ON(&mas, i != next - 3);
+	}
+
+	mtree_unlock(mt);
+	mtree_destroy(mt);
+	next = 0;
+	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+	for (int i = 0; i < 100; i++) {
+		mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+		MT_BUG_ON(mt, i != location - 2);
+		MT_BUG_ON(mt, i != next - 3);
+		MT_BUG_ON(mt, mtree_load(mt, location) != mt);
+	}
+
+	mtree_destroy(mt);
+	/* Overflow test */
+	next = ULONG_MAX - 1;
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 0);
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 0);
+	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, ret != 1);
+}
+
 static DEFINE_MTREE(tree);
 static int __init maple_tree_seed(void)
 {
@@ -3880,6 +3919,11 @@ static int __init maple_tree_seed(void)
 	check_state_handling(&tree);
 	mtree_destroy(&tree);
 
+	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+	alloc_cyclic_testing(&tree);
+	mtree_destroy(&tree);
+
+
 #if defined(BENCH)
 skip:
 #endif
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1e3447bccdb1..5f2be8c8df11 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -372,31 +372,6 @@ static int __init default_bdi_init(void)
 }
 subsys_initcall(default_bdi_init);
 
-/*
- * This function is used when the first inode for this wb is marked dirty. It
- * wakes-up the corresponding bdi thread which should then take care of the
- * periodic background write-out of dirty inodes. Since the write-out would
- * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
- * set up a timer which wakes the bdi thread up later.
- *
- * Note, we wouldn't bother setting up the timer, but this function is on the
- * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
- * by delaying the wake-up.
- *
- * We have to be careful not to postpone flush work if it is scheduled for
- * earlier. Thus we use queue_delayed_work().
- */
-void wb_wakeup_delayed(struct bdi_writeback *wb)
-{
-	unsigned long timeout;
-
-	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_irq(&wb->work_lock);
-	if (test_bit(WB_registered, &wb->state))
-		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_irq(&wb->work_lock);
-}
-
 static void wb_update_bandwidth_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(to_delayed_work(work),
@@ -436,7 +411,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
-	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
@@ -921,6 +895,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
+	bdi->last_bdp_sleep = jiffies;
 
 	return cgwb_bdi_init(bdi);
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 4add68d40e8d..b961db601df4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2723,16 +2723,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, struct page **capture)
 {
-	int may_perform_io = (__force int)(gfp_mask & __GFP_IO);
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
 
-	/*
-	 * Check if the GFP flags allow compaction - GFP_NOIO is really
-	 * tricky context because the migration might require IO
-	 */
-	if (!may_perform_io)
+	if (!gfp_compaction_allowed(gfp_mask))
 		return COMPACT_SKIPPED;
 
 	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 36f6f1d21ff0..5b325749fc12 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1026,6 +1026,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
 
+		if (c->passed_sample_intervals != s->next_apply_sis)
+			continue;
+
 		if (!s->wmarks.activated)
 			continue;
 
@@ -1176,10 +1179,6 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 		if (c->passed_sample_intervals != s->next_apply_sis)
 			continue;
 
-		s->next_apply_sis +=
-			(s->apply_interval_us ? s->apply_interval_us :
-			 c->attrs.aggr_interval) / sample_interval;
-
 		if (!s->wmarks.activated)
 			continue;
 
@@ -1195,6 +1194,14 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 		damon_for_each_region_safe(r, next_r, t)
 			damon_do_apply_schemes(c, t, r);
 	}
+
+	damon_for_each_scheme(s, c) {
+		if (c->passed_sample_intervals != s->next_apply_sis)
+			continue;
+		s->next_apply_sis +=
+			(s->apply_interval_us ? s->apply_interval_us :
+			 c->attrs.aggr_interval) / sample_interval;
+	}
 }
 
 /*
diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index f2e5f9431892..3de2916a65c3 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -185,9 +185,21 @@ static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres)
 	return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO);
 }
 
+static void damon_lru_sort_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_lru_sort_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *hot_scheme, *cold_scheme;
+	struct damos *old_hot_scheme = NULL, *old_cold_scheme = NULL;
 	unsigned int hot_thres, cold_thres;
 	int err = 0;
 
@@ -195,18 +207,35 @@ static int damon_lru_sort_apply_parameters(void)
 	if (err)
 		return err;
 
+	damon_for_each_scheme(scheme, ctx) {
+		if (!old_hot_scheme) {
+			old_hot_scheme = scheme;
+			continue;
+		}
+		old_cold_scheme = scheme;
+	}
+
 	hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) *
 		hot_thres_access_freq / 1000;
-	scheme = damon_lru_sort_new_hot_scheme(hot_thres);
-	if (!scheme)
+	hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres);
+	if (!hot_scheme)
 		return -ENOMEM;
-	damon_set_schemes(ctx, &scheme, 1);
+	if (old_hot_scheme)
+		damon_lru_sort_copy_quota_status(&hot_scheme->quota,
+				&old_hot_scheme->quota);
 
 	cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval;
-	scheme = damon_lru_sort_new_cold_scheme(cold_thres);
-	if (!scheme)
+	cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres);
+	if (!cold_scheme) {
+		damon_destroy_scheme(hot_scheme);
 		return -ENOMEM;
-	damon_add_scheme(ctx, scheme);
+	}
+	if (old_cold_scheme)
+		damon_lru_sort_copy_quota_status(&cold_scheme->quota,
+				&old_cold_scheme->quota);
+
+	damon_set_schemes(ctx, &hot_scheme, 1);
+	damon_add_scheme(ctx, cold_scheme);
 
 	return damon_set_region_biggest_system_ram_default(target,
 					&monitor_region_start,
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index ab974e477d2f..66e190f0374a 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -150,9 +150,20 @@ static struct damos *damon_reclaim_new_scheme(void)
 			&damon_reclaim_wmarks);
 }
 
+static void damon_reclaim_copy_quota_status(struct damos_quota *dst,
+		struct damos_quota *src)
+{
+	dst->total_charged_sz = src->total_charged_sz;
+	dst->total_charged_ns = src->total_charged_ns;
+	dst->charged_sz = src->charged_sz;
+	dst->charged_from = src->charged_from;
+	dst->charge_target_from = src->charge_target_from;
+	dst->charge_addr_from = src->charge_addr_from;
+}
+
 static int damon_reclaim_apply_parameters(void)
 {
-	struct damos *scheme;
+	struct damos *scheme, *old_scheme;
 	struct damos_filter *filter;
 	int err = 0;
 
@@ -164,6 +175,11 @@ static int damon_reclaim_apply_parameters(void)
 	scheme = damon_reclaim_new_scheme();
 	if (!scheme)
 		return -ENOMEM;
+	if (!list_empty(&ctx->schemes)) {
+		damon_for_each_scheme(old_scheme, ctx)
+			damon_reclaim_copy_quota_status(&scheme->quota,
+					&old_scheme->quota);
+	}
 	if (skip_anon) {
 		filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true);
 		if (!filter) {
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 8dbaac6e5c2d..ae0f0b314f3a 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -1905,6 +1905,10 @@ void damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
 	damon_for_each_scheme(scheme, ctx) {
 		struct damon_sysfs_scheme *sysfs_scheme;
 
+		/* user could have removed the scheme sysfs dir */
+		if (i >= sysfs_schemes->nr)
+			break;
+
 		sysfs_scheme = sysfs_schemes->schemes_arr[i];
 		damos_sysfs_set_quota_score(sysfs_scheme->quotas->goals,
 				&scheme->quota);
@@ -2194,7 +2198,7 @@ static void damos_tried_regions_init_upd_status(
 		sysfs_regions->upd_timeout_jiffies = jiffies +
 			2 * usecs_to_jiffies(scheme->apply_interval_us ?
 					scheme->apply_interval_us :
-					ctx->attrs.sample_interval);
+					ctx->attrs.aggr_interval);
 	}
 }
 
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 5662e29fe253..65c19025da3d 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -362,6 +362,12 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	vaddr &= HPAGE_PUD_MASK;
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	/*
+	 * Some architectures have debug checks to make sure
+	 * huge pud mapping are only found with devmap entries
+	 * For now test with only devmap entries.
+	 */
+	pud = pud_mkdevmap(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
 	pudp_set_wrprotect(args->mm, vaddr, args->pudp);
@@ -374,6 +380,7 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	WARN_ON(!pud_none(pud));
 #endif /* __PAGETABLE_PMD_FOLDED */
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	pud = pud_mkdevmap(pud);
 	pud = pud_wrprotect(pud);
 	pud = pud_mkclean(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
@@ -391,6 +398,7 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
+	pud = pud_mkdevmap(pud);
 	pud = pud_mkyoung(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
diff --git a/mm/filemap.c b/mm/filemap.c
index 750e779c23db..8df4797c5287 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2609,15 +2609,6 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
 		/*
-		 * Pairs with a barrier in
-		 * block_write_end()->mark_buffer_dirty() or other page
-		 * dirtying routines like iomap_write_end() to ensure
-		 * changes to page contents are visible before we see
-		 * increased inode size.
-		 */
-		smp_rmb();
-
-		/*
 		 * Once we start copying data, we don't want to be touching any
 		 * cachelines that might be contended:
 		 */
@@ -4111,28 +4102,40 @@ static void filemap_cachestat(struct address_space *mapping,
 
 	rcu_read_lock();
 	xas_for_each(&xas, folio, last_index) {
+		int order;
 		unsigned long nr_pages;
 		pgoff_t folio_first_index, folio_last_index;
 
+		/*
+		 * Don't deref the folio. It is not pinned, and might
+		 * get freed (and reused) underneath us.
+		 *
+		 * We *could* pin it, but that would be expensive for
+		 * what should be a fast and lightweight syscall.
+		 *
+		 * Instead, derive all information of interest from
+		 * the rcu-protected xarray.
+		 */
+
 		if (xas_retry(&xas, folio))
 			continue;
 
+		order = xa_get_order(xas.xa, xas.xa_index);
+		nr_pages = 1 << order;
+		folio_first_index = round_down(xas.xa_index, 1 << order);
+		folio_last_index = folio_first_index + nr_pages - 1;
+
+		/* Folios might straddle the range boundaries, only count covered pages */
+		if (folio_first_index < first_index)
+			nr_pages -= first_index - folio_first_index;
+
+		if (folio_last_index > last_index)
+			nr_pages -= folio_last_index - last_index;
+
 		if (xa_is_value(folio)) {
 			/* page is evicted */
 			void *shadow = (void *)folio;
 			bool workingset; /* not used */
-			int order = xa_get_order(xas.xa, xas.xa_index);
-
-			nr_pages = 1 << order;
-			folio_first_index = round_down(xas.xa_index, 1 << order);
-			folio_last_index = folio_first_index + nr_pages - 1;
-
-			/* Folios might straddle the range boundaries, only count covered pages */
-			if (folio_first_index < first_index)
-				nr_pages -= first_index - folio_first_index;
-
-			if (folio_last_index > last_index)
-				nr_pages -= folio_last_index - last_index;
 
 			cs->nr_evicted += nr_pages;
 
@@ -4150,24 +4153,13 @@ static void filemap_cachestat(struct address_space *mapping,
 			goto resched;
 		}
 
-		nr_pages = folio_nr_pages(folio);
-		folio_first_index = folio_pgoff(folio);
-		folio_last_index = folio_first_index + nr_pages - 1;
-
-		/* Folios might straddle the range boundaries, only count covered pages */
-		if (folio_first_index < first_index)
-			nr_pages -= first_index - folio_first_index;
-
-		if (folio_last_index > last_index)
-			nr_pages -= folio_last_index - last_index;
-
 		/* page is in cache */
 		cs->nr_cache += nr_pages;
 
-		if (folio_test_dirty(folio))
+		if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY))
 			cs->nr_dirty += nr_pages;
 
-		if (folio_test_writeback(folio))
+		if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK))
 			cs->nr_writeback += nr_pages;
 
 resched:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 94ef5c02b459..94c958f7ebb5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -809,7 +810,10 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 {
 	loff_t off_end = off + len;
 	loff_t off_align = round_up(off, size);
-	unsigned long len_pad, ret;
+	unsigned long len_pad, ret, off_sub;
+
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
@@ -835,7 +839,13 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	if (ret == addr)
 		return addr;
 
-	ret += (off - ret) & (size - 1);
+	off_sub = (off - ret) & (size - 1);
+
+	if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown &&
+	    !off_sub)
+		return ret + size;
+
+	ret += off_sub;
 	return ret;
 }
 
@@ -2437,7 +2447,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			page = pmd_page(old_pmd);
 			folio = page_folio(page);
 			if (!folio_test_dirty(folio) && pmd_dirty(old_pmd))
-				folio_set_dirty(folio);
+				folio_mark_dirty(folio);
 			if (!folio_test_referenced(folio) && pmd_young(old_pmd))
 				folio_set_referenced(folio);
 			folio_remove_rmap_pmd(folio, page, vma);
@@ -3563,7 +3573,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	}
 
 	if (pmd_dirty(pmdval))
-		folio_set_dirty(folio);
+		folio_mark_dirty(folio);
 	if (pmd_write(pmdval))
 		entry = make_writable_migration_entry(page_to_pfn(page));
 	else if (anon_exclusive)
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 610efae91220..6ca63e8dda74 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -65,8 +65,7 @@ void kasan_save_track(struct kasan_track *track, gfp_t flags)
 {
 	depot_stack_handle_t stack;
 
-	stack = kasan_save_stack(flags,
-			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
+	stack = kasan_save_stack(flags, STACK_DEPOT_FLAG_CAN_ALLOC);
 	kasan_set_track(track, stack);
 }
 
@@ -266,10 +265,9 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 		return true;
 
 	/*
-	 * If the object is not put into quarantine, it will likely be quickly
-	 * reallocated. Thus, release its metadata now.
+	 * Note: Keep per-object metadata to allow KASAN print stack traces for
+	 * use-after-free-before-realloc bugs.
 	 */
-	kasan_release_object_meta(cache, object);
 
 	/* Let slab put the object onto the freelist. */
 	return false;
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index df6627f62402..1900f8576034 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -485,16 +485,6 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 	if (alloc_meta) {
 		/* Zero out alloc meta to mark it as invalid. */
 		__memset(alloc_meta, 0, sizeof(*alloc_meta));
-
-		/*
-		 * Prepare the lock for saving auxiliary stack traces.
-		 * Temporarily disable KASAN bug reporting to allow instrumented
-		 * raw_spin_lock_init to access aux_lock, which resides inside
-		 * of a redzone.
-		 */
-		kasan_disable_current();
-		raw_spin_lock_init(&alloc_meta->aux_lock);
-		kasan_enable_current();
 	}
 
 	/*
@@ -506,47 +496,23 @@ void kasan_init_object_meta(struct kmem_cache *cache, const void *object)
 
 static void release_alloc_meta(struct kasan_alloc_meta *meta)
 {
-	/* Evict the stack traces from stack depot. */
-	stack_depot_put(meta->alloc_track.stack);
-	stack_depot_put(meta->aux_stack[0]);
-	stack_depot_put(meta->aux_stack[1]);
-
-	/*
-	 * Zero out alloc meta to mark it as invalid but keep aux_lock
-	 * initialized to avoid having to reinitialize it when another object
-	 * is allocated in the same slot.
-	 */
-	__memset(&meta->alloc_track, 0, sizeof(meta->alloc_track));
-	__memset(meta->aux_stack, 0, sizeof(meta->aux_stack));
+	/* Zero out alloc meta to mark it as invalid. */
+	__memset(meta, 0, sizeof(*meta));
 }
 
 static void release_free_meta(const void *object, struct kasan_free_meta *meta)
 {
+	if (!kasan_arch_is_ready())
+		return;
+
 	/* Check if free meta is valid. */
 	if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_SLAB_FREE_META)
 		return;
 
-	/* Evict the stack trace from the stack depot. */
-	stack_depot_put(meta->free_track.stack);
-
 	/* Mark free meta as invalid. */
 	*(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE;
 }
 
-void kasan_release_object_meta(struct kmem_cache *cache, const void *object)
-{
-	struct kasan_alloc_meta *alloc_meta;
-	struct kasan_free_meta *free_meta;
-
-	alloc_meta = kasan_get_alloc_meta(cache, object);
-	if (alloc_meta)
-		release_alloc_meta(alloc_meta);
-
-	free_meta = kasan_get_free_meta(cache, object);
-	if (free_meta)
-		release_free_meta(object, free_meta);
-}
-
 size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
 {
 	struct kasan_cache *info = &cache->kasan_info;
@@ -571,8 +537,6 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 	struct kmem_cache *cache;
 	struct kasan_alloc_meta *alloc_meta;
 	void *object;
-	depot_stack_handle_t new_handle, old_handle;
-	unsigned long flags;
 
 	if (is_kfence_address(addr) || !slab)
 		return;
@@ -583,33 +547,18 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 	if (!alloc_meta)
 		return;
 
-	new_handle = kasan_save_stack(0, depot_flags);
-
-	/*
-	 * Temporarily disable KASAN bug reporting to allow instrumented
-	 * spinlock functions to access aux_lock, which resides inside of a
-	 * redzone.
-	 */
-	kasan_disable_current();
-	raw_spin_lock_irqsave(&alloc_meta->aux_lock, flags);
-	old_handle = alloc_meta->aux_stack[1];
 	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
-	alloc_meta->aux_stack[0] = new_handle;
-	raw_spin_unlock_irqrestore(&alloc_meta->aux_lock, flags);
-	kasan_enable_current();
-
-	stack_depot_put(old_handle);
+	alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags);
 }
 
 void kasan_record_aux_stack(void *addr)
 {
-	return __kasan_record_aux_stack(addr,
-			STACK_DEPOT_FLAG_CAN_ALLOC | STACK_DEPOT_FLAG_GET);
+	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 
 void kasan_record_aux_stack_noalloc(void *addr)
 {
-	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_GET);
+	return __kasan_record_aux_stack(addr, 0);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
@@ -620,7 +569,7 @@ void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
 	if (!alloc_meta)
 		return;
 
-	/* Evict previous stack traces (might exist for krealloc or mempool). */
+	/* Invalidate previous stack traces (might exist for krealloc or mempool). */
 	release_alloc_meta(alloc_meta);
 
 	kasan_save_track(&alloc_meta->alloc_track, flags);
@@ -634,7 +583,7 @@ void kasan_save_free_info(struct kmem_cache *cache, void *object)
 	if (!free_meta)
 		return;
 
-	/* Evict previous stack trace (might exist for mempool). */
+	/* Invalidate previous stack trace (might exist for mempool). */
 	release_free_meta(object, free_meta);
 
 	kasan_save_track(&free_meta->free_track, 0);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index d0f172f2b978..fb2b9ac0659a 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -6,7 +6,6 @@
 #include <linux/kasan.h>
 #include <linux/kasan-tags.h>
 #include <linux/kfence.h>
-#include <linux/spinlock.h>
 #include <linux/stackdepot.h>
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
@@ -265,13 +264,6 @@ struct kasan_global {
 struct kasan_alloc_meta {
 	struct kasan_track alloc_track;
 	/* Free track is stored in kasan_free_meta. */
-	/*
-	 * aux_lock protects aux_stack from accesses from concurrent
-	 * kasan_record_aux_stack calls. It is a raw spinlock to avoid sleeping
-	 * on RT kernels, as kasan_record_aux_stack_noalloc can be called from
-	 * non-sleepable contexts.
-	 */
-	raw_spinlock_t aux_lock;
 	depot_stack_handle_t aux_stack[2];
 };
 
@@ -398,10 +390,8 @@ struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
 struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
 						const void *object);
 void kasan_init_object_meta(struct kmem_cache *cache, const void *object);
-void kasan_release_object_meta(struct kmem_cache *cache, const void *object);
 #else
 static inline void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { }
-static inline void kasan_release_object_meta(struct kmem_cache *cache, const void *object) { }
 #endif
 
 depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 3ba02efb952a..6958aa713c67 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -145,7 +145,10 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 	void *object = qlink_to_object(qlink, cache);
 	struct kasan_free_meta *free_meta = kasan_get_free_meta(cache, object);
 
-	kasan_release_object_meta(cache, object);
+	/*
+	 * Note: Keep per-object metadata to allow KASAN print stack traces for
+	 * use-after-free-before-realloc bugs.
+	 */
 
 	/*
 	 * If init_on_free is enabled and KASAN's free metadata is stored in
diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed5..cfa5e7288261 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -429,6 +429,7 @@ restart:
 		if (++batch_count == SWAP_CLUSTER_MAX) {
 			batch_count = 0;
 			if (need_resched()) {
+				arch_leave_lazy_mmu_mode();
 				pte_unmap_unlock(start_pte, ptl);
 				cond_resched();
 				goto restart;
diff --git a/mm/memblock.c b/mm/memblock.c
index 4dcb2ee35eca..d09136e040d3 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -180,8 +180,9 @@ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
 /*
  * Address comparison utilities
  */
-static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
-				       phys_addr_t base2, phys_addr_t size2)
+unsigned long __init_memblock
+memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2,
+		       phys_addr_t size2)
 {
 	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
 }
@@ -2249,6 +2250,7 @@ static const char * const flagname[] = {
 	[ilog2(MEMBLOCK_MIRROR)] = "MIRROR",
 	[ilog2(MEMBLOCK_NOMAP)] = "NOMAP",
 	[ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG",
+	[ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT",
 };
 
 static int memblock_debug_show(struct seq_file *m, void *private)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e4c8735e7c85..61932c9215e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx)
 }
 
 struct memcg_vmstats_percpu {
+	/* Stats updates since the last flush */
+	unsigned int			stats_updates;
+
+	/* Cached pointers for fast iteration in memcg_rstat_updated() */
+	struct memcg_vmstats_percpu	*parent;
+	struct memcg_vmstats		*vmstats;
+
+	/* The above should fit a single cacheline for memcg_rstat_updated() */
+
 	/* Local (CPU and cgroup) page state & events */
 	long			state[MEMCG_NR_STAT];
 	unsigned long		events[NR_MEMCG_EVENTS];
@@ -632,10 +641,7 @@ struct memcg_vmstats_percpu {
 	/* Cgroup1: threshold notifications & softlimit tree updates */
 	unsigned long		nr_page_events;
 	unsigned long		targets[MEM_CGROUP_NTARGETS];
-
-	/* Stats updates since the last flush */
-	unsigned int		stats_updates;
-};
+} ____cacheline_aligned;
 
 struct memcg_vmstats {
 	/* Aggregated (CPU and subtree) page state & events */
@@ -698,36 +704,35 @@ static void memcg_stats_unlock(void)
 }
 
 
-static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 {
-	return atomic64_read(&memcg->vmstats->stats_updates) >
+	return atomic64_read(&vmstats->stats_updates) >
 		MEMCG_CHARGE_BATCH * num_online_cpus();
 }
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	struct memcg_vmstats_percpu *statc;
 	int cpu = smp_processor_id();
-	unsigned int x;
 
 	if (!val)
 		return;
 
 	cgroup_rstat_updated(memcg->css.cgroup, cpu);
-
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
-					  abs(val));
-
-		if (x < MEMCG_CHARGE_BATCH)
+	statc = this_cpu_ptr(memcg->vmstats_percpu);
+	for (; statc; statc = statc->parent) {
+		statc->stats_updates += abs(val);
+		if (statc->stats_updates < MEMCG_CHARGE_BATCH)
 			continue;
 
 		/*
 		 * If @memcg is already flush-able, increasing stats_updates is
 		 * redundant. Avoid the overhead of the atomic update.
 		 */
-		if (!memcg_should_flush_stats(memcg))
-			atomic64_add(x, &memcg->vmstats->stats_updates);
-		__this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+		if (!memcg_vmstats_needs_flush(statc->vmstats))
+			atomic64_add(statc->stats_updates,
+				     &statc->vmstats->stats_updates);
+		statc->stats_updates = 0;
 	}
 }
 
@@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	if (memcg_should_flush_stats(memcg))
+	if (memcg_vmstats_needs_flush(memcg->vmstats))
 		do_flush_stats(memcg);
 }
 
@@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
 	/*
-	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
+	 * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
 	do_flush_stats(root_mem_cgroup);
@@ -2623,8 +2628,9 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
 }
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * Reclaims memory over the high limit. Called directly from
+ * try_charge() (context permitting), as well as from the userland
+ * return path where reclaim is always able to block.
  */
 void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
@@ -2644,6 +2650,17 @@ void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 
 retry_reclaim:
 	/*
+	 * Bail if the task is already exiting. Unlike memory.max,
+	 * memory.high enforcement isn't as strict, and there is no
+	 * OOM killer involved, which means the excess could already
+	 * be much bigger (and still growing) than it could for
+	 * memory.max; the dying task could get stuck in fruitless
+	 * reclaim for a long time, which isn't desirable.
+	 */
+	if (task_is_dying())
+		goto out;
+
+	/*
 	 * The allocating task should reclaim at least the batch size, but for
 	 * subsequent retries we only want to do what's necessary to prevent oom
 	 * or breaching resource isolation.
@@ -2693,6 +2710,9 @@ retry_reclaim:
 	}
 
 	/*
+	 * Reclaim didn't manage to push usage below the limit, slow
+	 * this allocating task down.
+	 *
 	 * If we exit early, we're guaranteed to die (since
 	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
 	 * need to account for any ill-begotten jiffies to pay them off later.
@@ -2887,11 +2907,17 @@ done_restock:
 		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
+	/*
+	 * Reclaim is set up above to be called from the userland
+	 * return path. But also attempt synchronous reclaim to avoid
+	 * excessive overrun while the task is still inside the
+	 * kernel. If this is successful, the return path will see it
+	 * when it rechecks the overage and simply bail out.
+	 */
 	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
 	    !(current->flags & PF_MEMALLOC) &&
-	    gfpflags_allow_blocking(gfp_mask)) {
+	    gfpflags_allow_blocking(gfp_mask))
 		mem_cgroup_handle_over_high(gfp_mask);
-	}
 	return 0;
 }
 
@@ -5456,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	__mem_cgroup_free(memcg);
 }
 
-static struct mem_cgroup *mem_cgroup_alloc(void)
+static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 {
+	struct memcg_vmstats_percpu *statc, *pstatc;
 	struct mem_cgroup *memcg;
-	int node;
+	int node, cpu;
 	int __maybe_unused i;
 	long error = -ENOMEM;
 
@@ -5483,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg->vmstats_percpu)
 		goto fail;
 
+	for_each_possible_cpu(cpu) {
+		if (parent)
+			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+		statc->parent = parent ? pstatc : NULL;
+		statc->vmstats = memcg->vmstats;
+	}
+
 	for_each_node(node)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
@@ -5528,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	struct mem_cgroup *memcg, *old_memcg;
 
 	old_memcg = set_active_memcg(parent);
-	memcg = mem_cgroup_alloc();
+	memcg = mem_cgroup_alloc(parent);
 	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
@@ -7936,9 +7971,13 @@ bool mem_cgroup_swap_full(struct folio *folio)
 
 static int __init setup_swap_account(char *s)
 {
-	pr_warn_once("The swapaccount= commandline option is deprecated. "
-		     "Please report your usecase to linux-mm@kvack.org if you "
-		     "depend on this functionality.\n");
+	bool res;
+
+	if (!kstrtobool(s, &res) && !res)
+		pr_warn_once("The swapaccount=0 commandline option is deprecated "
+			     "in favor of configuring swap control via cgroupfs. "
+			     "Please report your usecase to linux-mm@kvack.org if you "
+			     "depend on this functionality.\n");
 	return 1;
 }
 __setup("swapaccount=", setup_swap_account);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f9b61f4a668..9349948f1abf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -982,7 +982,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p,
 	int count = page_count(p) - 1;
 
 	if (extra_pins)
-		count -= 1;
+		count -= folio_nr_pages(page_folio(p));
 
 	if (count > 0) {
 		pr_err("%#lx: %s still referenced by %d users\n",
@@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  */
 static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
+	if (PageSlab(page))
+		return false;
+
 	/* Soft offline could migrate non-LRU movable pages */
 	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
 		return true;
diff --git a/mm/memory.c b/mm/memory.c
index 7e1f4849463a..0bfc8b007c01 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1464,7 +1464,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			delay_rmap = 0;
 			if (!folio_test_anon(folio)) {
 				if (pte_dirty(ptent)) {
-					folio_set_dirty(folio);
+					folio_mark_dirty(folio);
 					if (tlb_delay_rmap(tlb)) {
 						delay_rmap = 1;
 						force_flush = 1;
@@ -3799,6 +3799,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	struct page *page;
 	struct swap_info_struct *si = NULL;
 	rmap_t rmap_flags = RMAP_NONE;
+	bool need_clear_cache = false;
 	bool exclusive = false;
 	swp_entry_t entry;
 	pte_t pte;
@@ -3867,6 +3868,20 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
 		    __swap_count(entry) == 1) {
+			/*
+			 * Prevent parallel swapin from proceeding with
+			 * the cache flag. Otherwise, another thread may
+			 * finish swapin first, free the entry, and swapout
+			 * reusing the same entry. It's undetectable as
+			 * pte_same() returns true due to entry reuse.
+			 */
+			if (swapcache_prepare(entry)) {
+				/* Relax a bit to prevent rapid repeated page faults */
+				schedule_timeout_uninterruptible(1);
+				goto out;
+			}
+			need_clear_cache = true;
+
 			/* skip swapcache */
 			folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
 						vma, vmf->address, false);
@@ -4117,6 +4132,9 @@ unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
+	/* Clear the swap cache pin for direct swapin after PTL unlock */
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -4131,6 +4149,8 @@ out_release:
 		folio_unlock(swapcache);
 		folio_put(swapcache);
 	}
+	if (need_clear_cache)
+		swapcache_clear(si, entry);
 	if (si)
 		put_swap_device(si);
 	return ret;
@@ -5478,7 +5498,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs
 		return true;
 
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
@@ -5503,7 +5523,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
 {
 	mmap_read_unlock(mm);
 	if (regs && !user_mode(regs)) {
-		unsigned long ip = instruction_pointer(regs);
+		unsigned long ip = exception_ip(regs);
 		if (!search_exception_tables(ip))
 			return false;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index cc9f2bcd73b4..c27b1f8097d4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2519,6 +2519,14 @@ static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
 			if (managed_zone(pgdat->node_zones + z))
 				break;
 		}
+
+		/*
+		 * If there are no managed zones, it should not proceed
+		 * further.
+		 */
+		if (z < 0)
+			return 0;
+
 		wakeup_kswapd(pgdat->node_zones + z, 0,
 			      folio_order(folio), ZONE_MOVABLE);
 		return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index b78e83d351d2..3281287771c9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -954,13 +954,21 @@ static struct vm_area_struct
 	} else if (merge_prev) {			/* case 2 */
 		if (curr) {
 			vma_start_write(curr);
-			err = dup_anon_vma(prev, curr, &anon_dup);
 			if (end == curr->vm_end) {	/* case 7 */
+				/*
+				 * can_vma_merge_after() assumed we would not be
+				 * removing prev vma, so it skipped the check
+				 * for vm_ops->close, but we are removing curr
+				 */
+				if (curr->vm_ops && curr->vm_ops->close)
+					err = -EINVAL;
 				remove = curr;
 			} else {			/* case 5 */
 				adjust = curr;
 				adj_start = (end - curr->vm_start);
 			}
+			if (!err)
+				err = dup_anon_vma(prev, curr, &anon_dup);
 		}
 	} else { /* merge_next */
 		vma_start_write(next);
@@ -1825,15 +1833,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		/*
 		 * mmap_region() will call shmem_zero_setup() to create a file,
 		 * so use shmem's get_unmapped_area in case it can be huge.
-		 * do_mmap() will clear pgoff, so match alignment.
 		 */
-		pgoff = 0;
 		get_area = shmem_get_unmapped_area;
 	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 		/* Ensures that larger anonymous mappings are THP aligned. */
 		get_area = thp_get_unmapped_area;
 	}
 
+	/* Always treat pgoff as zero for anonymous memory. */
+	if (!file)
+		pgoff = 0;
+
 	addr = get_area(file, addr, len, pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40..3f255534986a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 */
 	dtc->wb_thresh = __wb_calc_thresh(dtc);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
@@ -1921,7 +1921,7 @@ pause:
 			break;
 		}
 		__set_current_state(TASK_KILLABLE);
-		wb->dirty_sleep = now;
+		bdi->last_bdp_sleep = jiffies;
 		io_schedule_timeout(pause);
 
 		current->dirty_paused_when = now + pause;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 150d4f23b010..a663202045dc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4041,6 +4041,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+	bool can_compact = gfp_compaction_allowed(gfp_mask);
 	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
 	unsigned int alloc_flags;
@@ -4111,7 +4112,7 @@ restart:
 	 * Don't try this for allocations that are allowed to ignore
 	 * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
 	 */
-	if (can_direct_reclaim &&
+	if (can_direct_reclaim && can_compact &&
 			(costly_order ||
 			   (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
 			&& !gfp_pfmemalloc_allowed(gfp_mask)) {
@@ -4209,9 +4210,10 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_RETRY_MAYFAIL
+	 * __GFP_RETRY_MAYFAIL and we can compact
 	 */
-	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
+	if (costly_order && (!can_compact ||
+			     !(gfp_mask & __GFP_RETRY_MAYFAIL)))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
@@ -4224,7 +4226,7 @@ retry:
 	 * implementation of the compaction depends on the sufficient amount
 	 * of free memory (see __compaction_suitable)
 	 */
-	if (did_some_progress > 0 &&
+	if (did_some_progress > 0 && can_compact &&
 			should_compact_retry(ac, order, alloc_flags,
 				compact_result, &compact_priority,
 				&compaction_retries))
diff --git a/mm/readahead.c b/mm/readahead.c
index 23620c57c122..2648ec4f0494 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -469,7 +469,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 
 	if (!folio)
 		return -ENOMEM;
-	mark = round_up(mark, 1UL << order);
+	mark = round_down(mark, 1UL << order);
 	if (index == mark)
 		folio_set_readahead(folio);
 	err = filemap_add_folio(ractl->mapping, folio, index, gfp);
@@ -575,7 +575,7 @@ static void ondemand_readahead(struct readahead_control *ractl,
 	 * It's the expected callback index, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	expected = round_up(ra->start + ra->size - ra->async_size,
+	expected = round_down(ra->start + ra->size - ra->async_size,
 			1UL << order);
 	if (index == expected || index == (ra->start + ra->size)) {
 		ra->start += ra->size;
diff --git a/mm/shmem.c b/mm/shmem.c
index d7c84ff62186..29d5a024df48 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3374,7 +3374,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry)
 
 static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
 {
-	if (!simple_empty(dentry))
+	if (!simple_offset_empty(dentry))
 		return -ENOTEMPTY;
 
 	drop_nlink(d_inode(dentry));
@@ -3431,7 +3431,7 @@ static int shmem_rename2(struct mnt_idmap *idmap,
 		return simple_offset_rename_exchange(old_dir, old_dentry,
 						     new_dir, new_dentry);
 
-	if (!simple_empty(new_dentry))
+	if (!simple_offset_empty(new_dentry))
 		return -ENOTEMPTY;
 
 	if (flags & RENAME_WHITEOUT) {
@@ -4355,7 +4355,9 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 #ifdef CONFIG_TMPFS_POSIX_ACL
 	sb->s_flags |= SB_POSIXACL;
 #endif
-	uuid_gen(&sb->s_uuid);
+	uuid_t uuid;
+	uuid_gen(&uuid);
+	super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 #ifdef CONFIG_TMPFS_QUOTA
 	if (ctx->seen & SHMEM_SEEN_QUOTA) {
diff --git a/mm/swap.h b/mm/swap.h
index 758c46ca671e..fc2f6ade7f80 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -41,6 +41,7 @@ void __delete_from_swap_cache(struct folio *folio,
 void delete_from_swap_cache(struct folio *folio);
 void clear_shadow_from_swap_cache(int type, unsigned long begin,
 				  unsigned long end);
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry);
 struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr);
 struct folio *filemap_get_incore_folio(struct address_space *mapping,
@@ -97,6 +98,10 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 	return 0;
 }
 
+static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+}
+
 static inline struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e671266ad772..7255c01a1e4e 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -680,9 +680,10 @@ skip:
 	/* The page was likely read above, so no need for plugging here */
 	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 					&page_allocated, false);
-	if (unlikely(page_allocated))
+	if (unlikely(page_allocated)) {
+		zswap_folio_swapin(folio);
 		swap_read_folio(folio, false, NULL);
-	zswap_folio_swapin(folio);
+	}
 	return folio;
 }
 
@@ -855,9 +856,10 @@ skip:
 	/* The folio was likely read above, so no need for plugging here */
 	folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
 					&page_allocated, false);
-	if (unlikely(page_allocated))
+	if (unlikely(page_allocated)) {
+		zswap_folio_swapin(folio);
 		swap_read_folio(folio, false, NULL);
-	zswap_folio_swapin(folio);
+	}
 	return folio;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 556ff7347d5f..573843d9cc91 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2532,10 +2532,10 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	exit_swap_address_space(p->type);
 
 	inode = mapping->host;
-	if (p->bdev_handle) {
+	if (p->bdev_file) {
 		set_blocksize(p->bdev, old_block_size);
-		bdev_release(p->bdev_handle);
-		p->bdev_handle = NULL;
+		fput(p->bdev_file);
+		p->bdev_file = NULL;
 	}
 
 	inode_lock(inode);
@@ -2765,14 +2765,14 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	int error;
 
 	if (S_ISBLK(inode->i_mode)) {
-		p->bdev_handle = bdev_open_by_dev(inode->i_rdev,
+		p->bdev_file = bdev_file_open_by_dev(inode->i_rdev,
 				BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL);
-		if (IS_ERR(p->bdev_handle)) {
-			error = PTR_ERR(p->bdev_handle);
-			p->bdev_handle = NULL;
+		if (IS_ERR(p->bdev_file)) {
+			error = PTR_ERR(p->bdev_file);
+			p->bdev_file = NULL;
 			return error;
 		}
-		p->bdev = p->bdev_handle->bdev;
+		p->bdev = file_bdev(p->bdev_file);
 		p->old_block_size = block_size(p->bdev);
 		error = set_blocksize(p->bdev, PAGE_SIZE);
 		if (error < 0)
@@ -3208,10 +3208,10 @@ bad_swap:
 	p->percpu_cluster = NULL;
 	free_percpu(p->cluster_next_cpu);
 	p->cluster_next_cpu = NULL;
-	if (p->bdev_handle) {
+	if (p->bdev_file) {
 		set_blocksize(p->bdev, p->old_block_size);
-		bdev_release(p->bdev_handle);
-		p->bdev_handle = NULL;
+		fput(p->bdev_file);
+		p->bdev_file = NULL;
 	}
 	inode = NULL;
 	destroy_swap_extents(p);
@@ -3365,6 +3365,19 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
+void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+{
+	struct swap_cluster_info *ci;
+	unsigned long offset = swp_offset(entry);
+	unsigned char usage;
+
+	ci = lock_cluster_or_swap_info(si, offset);
+	usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE);
+	unlock_cluster_or_swap_info(si, ci);
+	if (!usage)
+		free_swap_slot(entry);
+}
+
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 {
 	return swap_type_to_swap_info(swp_type(entry));
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 20e3b0d9cf7e..313f1c42768a 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -357,6 +357,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
 					      unsigned long dst_start,
 					      unsigned long src_start,
 					      unsigned long len,
+					      atomic_t *mmap_changing,
 					      uffd_flags_t flags)
 {
 	struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -472,6 +473,15 @@ retry:
 				goto out;
 			}
 			mmap_read_lock(dst_mm);
+			/*
+			 * If memory mappings are changing because of non-cooperative
+			 * operation (e.g. mremap) running in parallel, bail out and
+			 * request the user to retry later
+			 */
+			if (mmap_changing && atomic_read(mmap_changing)) {
+				err = -EAGAIN;
+				break;
+			}
 
 			dst_vma = NULL;
 			goto retry;
@@ -506,6 +516,7 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma,
 				    unsigned long dst_start,
 				    unsigned long src_start,
 				    unsigned long len,
+				    atomic_t *mmap_changing,
 				    uffd_flags_t flags);
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -622,8 +633,8 @@ retry:
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
 	if (is_vm_hugetlb_page(dst_vma))
-		return  mfill_atomic_hugetlb(dst_vma, dst_start,
-					     src_start, len, flags);
+		return  mfill_atomic_hugetlb(dst_vma, dst_start, src_start,
+					     len, mmap_changing, flags);
 
 	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
 		goto out_unlock;
@@ -891,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		err = -EAGAIN;
 		goto out;
 	}
@@ -903,9 +914,6 @@ static int move_present_pte(struct mm_struct *mm,
 		goto out;
 	}
 
-	folio_move_anon_rmap(src_folio, dst_vma);
-	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
-
 	orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte);
 	/* Folio got pinned from under us. Put it back and fail the move. */
 	if (folio_maybe_dma_pinned(src_folio)) {
@@ -914,6 +922,9 @@ static int move_present_pte(struct mm_struct *mm,
 		goto out;
 	}
 
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
 	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
 	/* Follow mremap() behavior and treat the entry dirty after the move */
 	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
@@ -935,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(*src_pte, orig_src_pte) ||
-	    !pte_same(*dst_pte, orig_dst_pte)) {
+	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1005,7 +1016,7 @@ retry:
 	}
 
 	spin_lock(dst_ptl);
-	orig_dst_pte = *dst_pte;
+	orig_dst_pte = ptep_get(dst_pte);
 	spin_unlock(dst_ptl);
 	if (!pte_none(orig_dst_pte)) {
 		err = -EEXIST;
@@ -1013,7 +1024,7 @@ retry:
 	}
 
 	spin_lock(src_ptl);
-	orig_src_pte = *src_pte;
+	orig_src_pte = ptep_get(src_pte);
 	spin_unlock(src_ptl);
 	if (pte_none(orig_src_pte)) {
 		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
@@ -1043,7 +1054,7 @@ retry:
 			 * page isn't freed under us
 			 */
 			spin_lock(src_ptl);
-			if (!pte_same(orig_src_pte, *src_pte)) {
+			if (!pte_same(orig_src_pte, ptep_get(src_pte))) {
 				spin_unlock(src_ptl);
 				err = -EAGAIN;
 				goto out;
diff --git a/mm/util.c b/mm/util.c
index 5a6a9802583b..5faf3adc6f43 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -136,6 +136,23 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
 EXPORT_SYMBOL(kmemdup);
 
 /**
+ * kmemdup_array - duplicate a given array.
+ *
+ * @src: array to duplicate.
+ * @element_size: size of each element of array.
+ * @count: number of elements to duplicate from array.
+ * @gfp: GFP mask to use.
+ *
+ * Return: duplicated array of @src or %NULL in case of error,
+ * result is physically contiguous. Use kfree() to free.
+ */
+void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp)
+{
+	return kmemdup(src, size_mul(element_size, count), gfp);
+}
+EXPORT_SYMBOL(kmemdup_array);
+
+/**
  * kvmemdup - duplicate region of memory
  *
  * @src: memory region to duplicate
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4f9c854ce6cc..4255619a1a31 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5753,7 +5753,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+	if (gfp_compaction_allowed(sc->gfp_mask) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -5998,6 +5998,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long watermark;
 
+	if (!gfp_compaction_allowed(sc->gfp_mask))
+		return false;
+
 	/* Allocation can already succeed, nothing to do */
 	if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone),
 			      sc->reclaim_idx, 0))
diff --git a/mm/zswap.c b/mm/zswap.c
index ca25b676048e..db4625af65fb 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -377,10 +377,9 @@ void zswap_folio_swapin(struct folio *folio)
 {
 	struct lruvec *lruvec;
 
-	if (folio) {
-		lruvec = folio_lruvec(folio);
-		atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
-	}
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+	lruvec = folio_lruvec(folio);
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
 }
 
 /*********************************
@@ -536,10 +535,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
  */
 static void zswap_free_entry(struct zswap_entry *entry)
 {
-	if (entry->objcg) {
-		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
-		obj_cgroup_put(entry->objcg);
-	}
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
@@ -548,6 +543,10 @@ static void zswap_free_entry(struct zswap_entry *entry)
 		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
+	if (entry->objcg) {
+		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+		obj_cgroup_put(entry->objcg);
+	}
 	zswap_entry_cache_free(entry);
 	atomic_dec(&zswap_stored_pages);
 	zswap_update_total_size();
@@ -895,10 +894,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
 		 * shrinker context).
 		 */
-		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
-			ret = LRU_SKIP;
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache)
 			*encountered_page_in_swapcache = true;
-		}
 
 		goto put_unlock;
 	}
@@ -1442,6 +1439,8 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) {
 		spin_unlock(&tree->lock);
 		delete_from_swap_cache(folio);
+		folio_unlock(folio);
+		folio_put(folio);
 		return -ENOMEM;
 	}
 	spin_unlock(&tree->lock);
@@ -1519,7 +1518,7 @@ bool zswap_store(struct folio *folio)
 	if (folio_test_large(folio))
 		return false;
 
-	if (!zswap_enabled || !tree)
+	if (!tree)
 		return false;
 
 	/*
@@ -1534,6 +1533,10 @@ bool zswap_store(struct folio *folio)
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	spin_unlock(&tree->lock);
+
+	if (!zswap_enabled)
+		return false;
+
 	objcg = get_obj_cgroup_from_folio(folio);
 	if (objcg && !obj_cgroup_may_zswap(objcg)) {
 		memcg = get_mem_cgroup_from_objcg(objcg);
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7b3341cef926..850d4a185f55 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void)
 module_init(lowpan_module_init);
 module_exit(lowpan_module_exit);
 
+MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module");
 MODULE_LICENSE("GPL");
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 033871e718a3..324e3ab96bb3 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void)
 module_init(atm_mpoa_init);
 module_exit(atm_mpoa_cleanup);
 
+MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver");
 MODULE_LICENSE("GPL");
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d982daea8329..14088c4ff2f6 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2175,6 +2175,7 @@ void batadv_mcast_free(struct batadv_priv *bat_priv)
 	cancel_delayed_work_sync(&bat_priv->mcast.work);
 
 	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST_TRACKER, 1);
 	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
 
 	/* safely calling outside of worker, as worker was canceled above */
@@ -2198,6 +2199,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 				      BATADV_MCAST_WANT_NO_RTR4);
 	batadv_mcast_want_rtr6_update(bat_priv, orig,
 				      BATADV_MCAST_WANT_NO_RTR6);
+	batadv_mcast_have_mc_ptype_update(bat_priv, orig,
+					  BATADV_MCAST_HAVE_MC_PTYPE_CAPA);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 65601aa52e0d..2821a42cefdc 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);
 
+	hci_dev_hold(hdev);
 	BT_DBG("%s", hdev->name);
 
 	if (hdev->hw_error)
@@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work)
 	else
 		bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);
 
-	if (hci_dev_do_close(hdev))
-		return;
+	if (!hci_dev_do_close(hdev))
+		hci_dev_do_open(hdev);
 
-	hci_dev_do_open(hdev);
+	hci_dev_put(hdev);
 }
 
 void hci_uuids_clear(struct hci_dev *hdev)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ef8c3bed7361..2a5f5a7d2412 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5329,9 +5329,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (!conn || !hci_conn_ssp_enabled(conn))
+	if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
 		goto unlock;
 
+	/* Assume remote supports SSP since it has triggered this event */
+	set_bit(HCI_CONN_SSP_ENABLED, &conn->flags);
+
 	hci_conn_hold(conn);
 
 	if (!hci_dev_test_flag(hdev, HCI_MGMT))
@@ -6794,6 +6797,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_UNKNOWN_CONN_ID);
 
+	if (max > hcon->le_conn_max_interval)
+		return send_conn_param_neg_reply(hdev, handle,
+						 HCI_ERROR_INVALID_LL_PARAMS);
+
 	if (hci_check_conn_params(min, max, latency, timeout))
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_INVALID_LL_PARAMS);
@@ -7420,10 +7427,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
 	 * keep track of the bdaddr of the connection event that woke us up.
 	 */
 	if (event == HCI_EV_CONN_REQUEST) {
-		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_CONN_COMPLETE) {
-		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_LE_META) {
 		struct hci_ev_le_meta *le_ev = (void *)skb->data;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a6fc8a2a5c67..5716345a26df 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2206,8 +2206,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev,
 
 	/* During suspend, only wakeable devices can be in acceptlist */
 	if (hdev->suspended &&
-	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP))
+	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) {
+		hci_le_del_accept_list_sync(hdev, &params->addr,
+					    params->addr_type);
 		return 0;
+	}
 
 	/* Select filter policy to accept all advertising */
 	if (*num_entries >= hdev->le_accept_list_size)
@@ -5559,7 +5562,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length)
 
 	bt_dev_dbg(hdev, "");
 
-	if (hci_dev_test_flag(hdev, HCI_INQUIRY))
+	if (test_bit(HCI_INQUIRY, &hdev->flags))
 		return 0;
 
 	hci_dev_lock(hdev);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 60298975d5c4..656f49b299d2 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5613,7 +5613,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 
 	memset(&rsp, 0, sizeof(rsp));
 
-	err = hci_check_conn_params(min, max, latency, to_multiplier);
+	if (max > hcon->le_conn_max_interval) {
+		BT_DBG("requested connection interval exceeds current bounds.");
+		err = -EINVAL;
+	} else {
+		err = hci_check_conn_params(min, max, latency, to_multiplier);
+	}
+
 	if (err)
 		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
 	else
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index bb72ff6eb22f..ee3b4aad8bd8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1045,6 +1045,8 @@ static void rpa_expired(struct work_struct *work)
 	hci_cmd_sync_queue(hdev, rpa_expired_sync, NULL, NULL);
 }
 
+static int set_discoverable_sync(struct hci_dev *hdev, void *data);
+
 static void discov_off(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev,
@@ -1063,7 +1065,7 @@ static void discov_off(struct work_struct *work)
 	hci_dev_clear_flag(hdev, HCI_DISCOVERABLE);
 	hdev->discov_timeout = 0;
 
-	hci_update_discoverable(hdev);
+	hci_cmd_sync_queue(hdev, set_discoverable_sync, NULL, NULL);
 
 	mgmt_new_settings(hdev);
 
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 053ef8f25fae..1d34d8497033 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1941,7 +1941,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
 	/* Get data directly from socket receive queue without copying it. */
 	while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
 		skb_orphan(skb);
-		if (!skb_linearize(skb)) {
+		if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) {
 			s = rfcomm_recv_frame(s, skb);
 			if (!s)
 				break;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d7d021af1029..2d7b73242958 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1762,6 +1762,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_query_delay_expired(struct timer_list *t)
+{
+}
+
 static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx,
 					    struct br_ip *ip,
 					    struct sk_buff *skb)
@@ -3198,7 +3202,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx,
 				unsigned long max_delay)
 {
 	if (!timer_pending(&query->timer))
-		query->delay_time = jiffies + max_delay;
+		mod_timer(&query->delay_timer, jiffies + max_delay);
 
 	mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval);
 }
@@ -4041,13 +4045,11 @@ void br_multicast_ctx_init(struct net_bridge *br,
 	brmctx->multicast_querier_interval = 255 * HZ;
 	brmctx->multicast_membership_interval = 260 * HZ;
 
-	brmctx->ip4_other_query.delay_time = 0;
 	brmctx->ip4_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock);
 	brmctx->multicast_igmp_version = 2;
 #if IS_ENABLED(CONFIG_IPV6)
 	brmctx->multicast_mld_version = 1;
-	brmctx->ip6_other_query.delay_time = 0;
 	brmctx->ip6_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
 #endif
@@ -4056,6 +4058,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip4_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip4_other_query.timer,
 		    br_ip4_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip4_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip4_own_query.timer,
 		    br_ip4_multicast_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -4063,6 +4067,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip6_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip6_other_query.timer,
 		    br_ip6_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip6_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip6_own_query.timer,
 		    br_ip6_multicast_query_expired, 0);
 #endif
@@ -4197,10 +4203,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx)
 {
 	del_timer_sync(&brmctx->ip4_mc_router_timer);
 	del_timer_sync(&brmctx->ip4_other_query.timer);
+	del_timer_sync(&brmctx->ip4_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
 	del_timer_sync(&brmctx->ip6_mc_router_timer);
 	del_timer_sync(&brmctx->ip6_other_query.timer);
+	del_timer_sync(&brmctx->ip6_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip6_own_query.timer);
 #endif
 }
@@ -4643,13 +4651,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val)
 	max_delay = brmctx->multicast_query_response_interval;
 
 	if (!timer_pending(&brmctx->ip4_other_query.timer))
-		brmctx->ip4_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip4_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (!timer_pending(&brmctx->ip6_other_query.timer))
-		brmctx->ip6_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip6_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip6_own_query);
 #endif
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index ed1720890757..35e10c5a766d 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -43,6 +43,10 @@
 #include <linux/sysctl.h>
 #endif
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#endif
+
 static unsigned int brnf_net_id __read_mostly;
 
 struct brnf_net {
@@ -553,6 +557,90 @@ static unsigned int br_nf_pre_routing(void *priv,
 	return NF_STOLEN;
 }
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+/* conntracks' nf_confirm logic cannot handle cloned skbs referencing
+ * the same nf_conn entry, which will happen for multicast (broadcast)
+ * Frames on bridges.
+ *
+ * Example:
+ *      macvlan0
+ *      br0
+ *  ethX  ethY
+ *
+ * ethX (or Y) receives multicast or broadcast packet containing
+ * an IP packet, not yet in conntrack table.
+ *
+ * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting.
+ *    -> skb->_nfct now references a unconfirmed entry
+ * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge
+ *    interface.
+ * 3. skb gets passed up the stack.
+ * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb
+ *    and schedules a work queue to send them out on the lower devices.
+ *
+ *    The clone skb->_nfct is not a copy, it is the same entry as the
+ *    original skb.  The macvlan rx handler then returns RX_HANDLER_PASS.
+ * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb.
+ *
+ * The Macvlan broadcast worker and normal confirm path will race.
+ *
+ * This race will not happen if step 2 already confirmed a clone. In that
+ * case later steps perform skb_clone() with skb->_nfct already confirmed (in
+ * hash table).  This works fine.
+ *
+ * But such confirmation won't happen when eb/ip/nftables rules dropped the
+ * packets before they reached the nf_confirm step in postrouting.
+ *
+ * Work around this problem by explicit confirmation of the entry at
+ * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed
+ * entry.
+ *
+ */
+static unsigned int br_nf_local_in(void *priv,
+				   struct sk_buff *skb,
+				   const struct nf_hook_state *state)
+{
+	struct nf_conntrack *nfct = skb_nfct(skb);
+	const struct nf_ct_hook *ct_hook;
+	struct nf_conn *ct;
+	int ret;
+
+	if (!nfct || skb->pkt_type == PACKET_HOST)
+		return NF_ACCEPT;
+
+	ct = container_of(nfct, struct nf_conn, ct_general);
+	if (likely(nf_ct_is_confirmed(ct)))
+		return NF_ACCEPT;
+
+	WARN_ON_ONCE(skb_shared(skb));
+	WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
+
+	/* We can't call nf_confirm here, it would create a dependency
+	 * on nf_conntrack module.
+	 */
+	ct_hook = rcu_dereference(nf_ct_hook);
+	if (!ct_hook) {
+		skb->_nfct = 0ul;
+		nf_conntrack_put(nfct);
+		return NF_ACCEPT;
+	}
+
+	nf_bridge_pull_encap_header(skb);
+	ret = ct_hook->confirm(skb);
+	switch (ret & NF_VERDICT_MASK) {
+	case NF_STOLEN:
+		return NF_STOLEN;
+	default:
+		nf_bridge_push_encap_header(skb);
+		break;
+	}
+
+	ct = container_of(nfct, struct nf_conn, ct_general);
+	WARN_ON_ONCE(!nf_ct_is_confirmed(ct));
+
+	return ret;
+}
+#endif
 
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -964,6 +1052,14 @@ static const struct nf_hook_ops br_nf_ops[] = {
 		.hooknum = NF_BR_PRE_ROUTING,
 		.priority = NF_BR_PRI_BRNF,
 	},
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	{
+		.hook = br_nf_local_in,
+		.pf = NFPROTO_BRIDGE,
+		.hooknum = NF_BR_LOCAL_IN,
+		.priority = NF_BR_PRI_LAST,
+	},
+#endif
 	{
 		.hook = br_nf_forward,
 		.pf = NFPROTO_BRIDGE,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b0a92c344722..86ea5e6689b5 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -78,7 +78,7 @@ struct bridge_mcast_own_query {
 /* other querier */
 struct bridge_mcast_other_query {
 	struct timer_list		timer;
-	unsigned long			delay_time;
+	struct timer_list		delay_timer;
 };
 
 /* selected querier */
@@ -1159,7 +1159,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx,
 		own_querier_enabled = false;
 	}
 
-	return time_is_before_jiffies(querier->delay_time) &&
+	return !timer_pending(&querier->delay_timer) &&
 	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index ee84e783e1df..7b41ee8740cb 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -595,21 +595,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev,
 }
 
 static int br_switchdev_mdb_queue_one(struct list_head *mdb_list,
+				      struct net_device *dev,
+				      unsigned long action,
 				      enum switchdev_obj_id id,
 				      const struct net_bridge_mdb_entry *mp,
 				      struct net_device *orig_dev)
 {
-	struct switchdev_obj_port_mdb *mdb;
+	struct switchdev_obj_port_mdb mdb = {
+		.obj = {
+			.id = id,
+			.orig_dev = orig_dev,
+		},
+	};
+	struct switchdev_obj_port_mdb *pmdb;
 
-	mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC);
-	if (!mdb)
-		return -ENOMEM;
+	br_switchdev_mdb_populate(&mdb, mp);
+
+	if (action == SWITCHDEV_PORT_OBJ_ADD &&
+	    switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) {
+		/* This event is already in the deferred queue of
+		 * events, so this replay must be elided, lest the
+		 * driver receives duplicate events for it. This can
+		 * only happen when replaying additions, since
+		 * modifications are always immediately visible in
+		 * br->mdb_list, whereas actual event delivery may be
+		 * delayed.
+		 */
+		return 0;
+	}
 
-	mdb->obj.id = id;
-	mdb->obj.orig_dev = orig_dev;
-	br_switchdev_mdb_populate(mdb, mp);
-	list_add_tail(&mdb->obj.list, mdb_list);
+	pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC);
+	if (!pmdb)
+		return -ENOMEM;
 
+	list_add_tail(&pmdb->obj.list, mdb_list);
 	return 0;
 }
 
@@ -677,51 +696,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev,
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return 0;
 
-	/* We cannot walk over br->mdb_list protected just by the rtnl_mutex,
-	 * because the write-side protection is br->multicast_lock. But we
-	 * need to emulate the [ blocking ] calling context of a regular
-	 * switchdev event, so since both br->multicast_lock and RCU read side
-	 * critical sections are atomic, we have no choice but to pick the RCU
-	 * read side lock, queue up all our events, leave the critical section
-	 * and notify switchdev from blocking context.
+	if (adding)
+		action = SWITCHDEV_PORT_OBJ_ADD;
+	else
+		action = SWITCHDEV_PORT_OBJ_DEL;
+
+	/* br_switchdev_mdb_queue_one() will take care to not queue a
+	 * replay of an event that is already pending in the switchdev
+	 * deferred queue. In order to safely determine that, there
+	 * must be no new deferred MDB notifications enqueued for the
+	 * duration of the MDB scan. Therefore, grab the write-side
+	 * lock to avoid racing with any concurrent IGMP/MLD snooping.
 	 */
-	rcu_read_lock();
+	spin_lock_bh(&br->multicast_lock);
 
-	hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) {
+	hlist_for_each_entry(mp, &br->mdb_list, mdb_node) {
 		struct net_bridge_port_group __rcu * const *pp;
 		const struct net_bridge_port_group *p;
 
 		if (mp->host_joined) {
-			err = br_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_HOST_MDB,
 							 mp, br_dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 
-		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
+		for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 		     pp = &p->next) {
 			if (p->key.port->dev != dev)
 				continue;
 
-			err = br_switchdev_mdb_queue_one(&mdb_list,
+			err = br_switchdev_mdb_queue_one(&mdb_list, dev, action,
 							 SWITCHDEV_OBJ_ID_PORT_MDB,
 							 mp, dev);
 			if (err) {
-				rcu_read_unlock();
+				spin_unlock_bh(&br->multicast_lock);
 				goto out_free_mdb;
 			}
 		}
 	}
 
-	rcu_read_unlock();
-
-	if (adding)
-		action = SWITCHDEV_PORT_OBJ_ADD;
-	else
-		action = SWITCHDEV_PORT_OBJ_DEL;
+	spin_unlock_bh(&br->multicast_lock);
 
 	list_for_each_entry(obj, &mdb_list, list) {
 		err = br_switchdev_mdb_replay_one(nb, dev,
@@ -786,6 +804,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p,
 	br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL);
 
 	br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL);
+
+	/* Make sure that the device leaving this bridge has seen all
+	 * relevant events before it is disassociated. In the normal
+	 * case, when the device is directly attached to the bridge,
+	 * this is covered by del_nbp(). If the association was indirect
+	 * however, e.g. via a team or bond, and the device is leaving
+	 * that intermediate device, then the bridge port remains in
+	 * place.
+	 */
+	switchdev_deferred_process();
 }
 
 /* Let the bridge know that this port is offloaded, so that it can assign a
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index abb090f94ed2..6f877e31709b 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -291,6 +291,30 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
 	return nf_conntrack_in(skb, &bridge_state);
 }
 
+static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
+				    const struct nf_hook_state *state)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (skb->pkt_type == PACKET_HOST)
+		return NF_ACCEPT;
+
+	/* nf_conntrack_confirm() cannot handle concurrent clones,
+	 * this happens for broad/multicast frames with e.g. macvlan on top
+	 * of the bridge device.
+	 */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+		return NF_ACCEPT;
+
+	/* let inet prerouting call conntrack again */
+	skb->_nfct = 0;
+	nf_ct_put(ct);
+
+	return NF_ACCEPT;
+}
+
 static void nf_ct_bridge_frag_save(struct sk_buff *skb,
 				   struct nf_bridge_frag_data *data)
 {
@@ -386,6 +410,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = {
 		.priority	= NF_IP_PRI_CONNTRACK,
 	},
 	{
+		.hook		= nf_ct_bridge_in,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
+	},
+	{
 		.hook		= nf_ct_bridge_post,
 		.pf		= NFPROTO_BRIDGE,
 		.hooknum	= NF_BR_POST_ROUTING,
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 16af1a7f80f6..31a93cae5111 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -86,7 +86,7 @@ struct j1939_priv {
 	unsigned int tp_max_packet_size;
 
 	/* lock for j1939_socks list */
-	spinlock_t j1939_socks_lock;
+	rwlock_t j1939_socks_lock;
 	struct list_head j1939_socks;
 
 	struct kref rx_kref;
@@ -301,6 +301,7 @@ struct j1939_sock {
 
 	int ifindex;
 	struct j1939_addr addr;
+	spinlock_t filters_lock;
 	struct j1939_filter *filters;
 	int nfilters;
 	pgn_t pgn_rx_filter;
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index ecff1c947d68..a6fb89fa6278 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
 		return ERR_PTR(-ENOMEM);
 
 	j1939_tp_init(priv);
-	spin_lock_init(&priv->j1939_socks_lock);
+	rwlock_init(&priv->j1939_socks_lock);
 	INIT_LIST_HEAD(&priv->j1939_socks);
 
 	mutex_lock(&j1939_netdev_lock);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 14c431663233..305dd72c844c 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
 	jsk->state |= J1939_SOCK_BOUND;
 	j1939_priv_get(priv);
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	write_lock_bh(&priv->j1939_socks_lock);
 	list_add_tail(&jsk->list, &priv->j1939_socks);
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	write_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
 {
-	spin_lock_bh(&priv->j1939_socks_lock);
+	write_lock_bh(&priv->j1939_socks_lock);
 	list_del_init(&jsk->list);
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	write_unlock_bh(&priv->j1939_socks_lock);
 
 	j1939_priv_put(priv);
 	jsk->state &= ~J1939_SOCK_BOUND;
@@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk,
 static bool j1939_sk_match_filter(struct j1939_sock *jsk,
 				  const struct j1939_sk_buff_cb *skcb)
 {
-	const struct j1939_filter *f = jsk->filters;
-	int nfilter = jsk->nfilters;
+	const struct j1939_filter *f;
+	int nfilter;
+
+	spin_lock_bh(&jsk->filters_lock);
+
+	f = jsk->filters;
+	nfilter = jsk->nfilters;
 
 	if (!nfilter)
 		/* receive all when no filters are assigned */
-		return true;
+		goto filter_match_found;
 
 	for (; nfilter; ++f, --nfilter) {
 		if ((skcb->addr.pgn & f->pgn_mask) != f->pgn)
@@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk,
 			continue;
 		if ((skcb->addr.src_name & f->name_mask) != f->name)
 			continue;
-		return true;
+		goto filter_match_found;
 	}
+
+	spin_unlock_bh(&jsk->filters_lock);
 	return false;
+
+filter_match_found:
+	spin_unlock_bh(&jsk->filters_lock);
+	return true;
 }
 
 static bool j1939_sk_recv_match_one(struct j1939_sock *jsk,
@@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb)
 	struct j1939_sock *jsk;
 	bool match = false;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		match = j1939_sk_recv_match_one(jsk, skcb);
 		if (match)
 			break;
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 
 	return match;
 }
@@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
 {
 	struct j1939_sock *jsk;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		j1939_sk_recv_one(jsk, skb);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static void j1939_sk_sock_destruct(struct sock *sk)
@@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk)
 	atomic_set(&jsk->skb_pending, 0);
 	spin_lock_init(&jsk->sk_session_queue_lock);
 	INIT_LIST_HEAD(&jsk->sk_session_queue);
+	spin_lock_init(&jsk->filters_lock);
 
 	/* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */
 	sock_set_flag(sk, SOCK_RCU_FREE);
@@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
 		}
 
 		lock_sock(&jsk->sk);
+		spin_lock_bh(&jsk->filters_lock);
 		ofilters = jsk->filters;
 		jsk->filters = filters;
 		jsk->nfilters = count;
+		spin_unlock_bh(&jsk->filters_lock);
 		release_sock(&jsk->sk);
 		kfree(ofilters);
 		return 0;
@@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session,
 	}
 
 	/* spread RX notifications to all sockets subscribed to this session */
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		if (j1939_sk_recv_match_one(jsk, &session->skcb))
 			__j1939_sk_errqueue(session, &jsk->sk, type);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 };
 
 void j1939_sk_send_loop_abort(struct sock *sk, int err)
@@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 	struct j1939_sock *jsk;
 	int error_code = ENETDOWN;
 
-	spin_lock_bh(&priv->j1939_socks_lock);
+	read_lock_bh(&priv->j1939_socks_lock);
 	list_for_each_entry(jsk, &priv->j1939_socks, list) {
 		jsk->sk.sk_err = error_code;
 		if (!sock_flag(&jsk->sk, SOCK_DEAD))
@@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 
 		j1939_sk_queue_drop_all(priv, jsk, error_code);
 	}
-	spin_unlock_bh(&priv->j1939_socks_lock);
+	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
 static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index f9a50d7f0d20..0cb61c76b9b8 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	/* Initialize data cursor if it's not a sparse read */
-	if (!msg->sparse_read)
-		ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+	u64 len = msg->sparse_read_total ? : data_len;
+
+	ceph_msg_data_cursor_init(&msg->cursor, msg, len);
 }
 
 /*
@@ -991,7 +992,7 @@ static inline int read_partial_message_section(struct ceph_connection *con,
 	return read_partial_message_chunk(con, section, sec_len, crc);
 }
 
-static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
@@ -1026,7 +1027,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
 	return 1;
 }
 
-static int read_sparse_msg_data(struct ceph_connection *con)
+static int read_partial_sparse_msg_data(struct ceph_connection *con)
 {
 	struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
@@ -1036,31 +1037,31 @@ static int read_sparse_msg_data(struct ceph_connection *con)
 	if (do_datacrc)
 		crc = con->in_data_crc;
 
-	do {
+	while (cursor->total_resid) {
 		if (con->v1.in_sr_kvec.iov_base)
 			ret = read_partial_message_chunk(con,
 							 &con->v1.in_sr_kvec,
 							 con->v1.in_sr_len,
 							 &crc);
 		else if (cursor->sr_resid > 0)
-			ret = read_sparse_msg_extent(con, &crc);
-
-		if (ret <= 0) {
-			if (do_datacrc)
-				con->in_data_crc = crc;
-			return ret;
-		}
+			ret = read_partial_sparse_msg_extent(con, &crc);
+		if (ret <= 0)
+			break;
 
 		memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
 		ret = con->ops->sparse_read(con, cursor,
 				(char **)&con->v1.in_sr_kvec.iov_base);
+		if (ret <= 0) {
+			ret = ret ? ret : 1;  /* must return > 0 to indicate success */
+			break;
+		}
 		con->v1.in_sr_len = ret;
-	} while (ret > 0);
+	}
 
 	if (do_datacrc)
 		con->in_data_crc = crc;
 
-	return ret < 0 ? ret : 1;  /* must return > 0 to indicate success */
+	return ret;
 }
 
 static int read_partial_msg_data(struct ceph_connection *con)
@@ -1253,8 +1254,8 @@ static int read_partial_message(struct ceph_connection *con)
 		if (!m->num_data_items)
 			return -EIO;
 
-		if (m->sparse_read)
-			ret = read_sparse_msg_data(con);
+		if (m->sparse_read_total)
+			ret = read_partial_sparse_msg_data(con);
 		else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
 			ret = read_partial_msg_data_bounce(con);
 		else
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index f8ec60e1aba3..bd608ffa0627 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con)
 	struct sg_table enc_sgt = {};
 	struct sg_table sgt = {};
 	struct page **pages = NULL;
-	bool sparse = con->in_msg->sparse_read;
+	bool sparse = !!con->in_msg->sparse_read_total;
 	int dpos = 0;
 	int tail_len;
 	int ret;
@@ -2034,6 +2034,9 @@ static int prepare_sparse_read_data(struct ceph_connection *con)
 	if (!con_secure(con))
 		con->in_data_crc = -1;
 
+	ceph_msg_data_cursor_init(&con->v2.in_cursor, msg,
+				  msg->sparse_read_total);
+
 	reset_in_kvecs(con);
 	con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT;
 	con->v2.data_len_remain = data_len(msg);
@@ -2060,7 +2063,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
 	}
 
 	if (data_len(msg)) {
-		if (msg->sparse_read)
+		if (msg->sparse_read_total)
 			con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
 		else
 			con->v2.in_state = IN_S_PREPARE_READ_DATA;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 625622016f57..9d078b37fe0b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	}
 
 	m = ceph_msg_get(req->r_reply);
-	m->sparse_read = (bool)srlen;
+	m->sparse_read_total = srlen;
 
 	dout("get_reply tid %lld %p\n", tid, m);
 
@@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con,
 	}
 
 	if (o->o_sparse_op_idx < 0) {
-		u64 srlen = sparse_data_requested(req);
-
-		dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
-		     __func__, o->o_osd, srlen);
-		ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+		dout("%s: [%d] starting new sparse read req\n",
+		     __func__, o->o_osd);
 	} else {
 		u64 end;
 
@@ -5857,8 +5854,8 @@ static int osd_sparse_read(struct ceph_connection *con,
 	struct ceph_osd *o = con->private;
 	struct ceph_sparse_read *sr = &o->o_sparse_read;
 	u32 count = sr->sr_count;
-	u64 eoff, elen;
-	int ret;
+	u64 eoff, elen, len = 0;
+	int i, ret;
 
 	switch (sr->sr_state) {
 	case CEPH_SPARSE_READ_HDR:
@@ -5903,8 +5900,20 @@ next_op:
 		convert_extent_map(sr);
 		ret = sizeof(sr->sr_datalen);
 		*pbuf = (char *)&sr->sr_datalen;
-		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		sr->sr_state = CEPH_SPARSE_READ_DATA_PRE;
 		break;
+	case CEPH_SPARSE_READ_DATA_PRE:
+		/* Convert sr_datalen to host-endian */
+		sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen);
+		for (i = 0; i < count; i++)
+			len += sr->sr_extent[i].len;
+		if (sr->sr_datalen != len) {
+			pr_warn_ratelimited("data len %u != extent len %llu\n",
+					    sr->sr_datalen, len);
+			return -EREMOTEIO;
+		}
+		sr->sr_state = CEPH_SPARSE_READ_DATA;
+		fallthrough;
 	case CEPH_SPARSE_READ_DATA:
 		if (sr->sr_index >= count) {
 			sr->sr_state = CEPH_SPARSE_READ_HDR;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 103d46fa0eeb..a8b625abe242 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
 			   size_t len, void *from, void *priv2)
 {
 	__wsum *csum = priv2;
-	__wsum next = csum_partial_copy_nocheck(from, iter_to, len);
+	__wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
 
 	*csum = csum_block_add(*csum, next, progress);
 	return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index cb2dab0feee0..a892f7265189 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
 		return -ENOMEM;
 	netdev_name_node_add(net, name_node);
 	/* The node that holds dev->name acts as a head of per-device list. */
-	list_add_tail(&name_node->list, &dev->name_node->list);
+	list_add_tail_rcu(&name_node->list, &dev->name_node->list);
 
 	return 0;
 }
@@ -6177,8 +6177,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
-			   u16 budget)
+enum {
+	NAPI_F_PREFER_BUSY_POLL	= 1,
+	NAPI_F_END_ON_RESCHED	= 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+			   unsigned flags, u16 budget)
 {
 	bool skip_schedule = false;
 	unsigned long timeout;
@@ -6198,7 +6203,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 
 	local_bh_disable();
 
-	if (prefer_busy_poll) {
+	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
 		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
 		if (napi->defer_hard_irqs_count && timeout) {
@@ -6222,23 +6227,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 	local_bh_enable();
 }
 
-void napi_busy_loop(unsigned int napi_id,
-		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+		      bool (*loop_end)(void *, unsigned long),
+		      void *loop_end_arg, unsigned flags, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 restart:
 	napi_poll = NULL;
 
-	rcu_read_lock();
-
 	napi = napi_by_id(napi_id);
 	if (!napi)
-		goto out;
+		return;
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_disable();
@@ -6254,14 +6259,14 @@ restart:
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
 				   NAPIF_STATE_IN_BUSY_POLL)) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
 					  NAPIF_STATE_SCHED) != val) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
@@ -6281,12 +6286,15 @@ count:
 			break;
 
 		if (unlikely(need_resched())) {
+			if (flags & NAPI_F_END_ON_RESCHED)
+				break;
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+				busy_poll_stop(napi, have_poll_lock, flags, budget);
 			if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 				preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
+			rcu_read_lock();
 			if (loop_end(loop_end_arg, start_time))
 				return;
 			goto restart;
@@ -6294,10 +6302,31 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+		busy_poll_stop(napi, have_poll_lock, flags, budget);
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = NAPI_F_END_ON_RESCHED;
+
+	if (prefer_busy_poll)
+		flags |= NAPI_F_PREFER_BUSY_POLL;
+
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+	rcu_read_lock();
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(napi_busy_loop);
@@ -9074,28 +9103,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
 }
 EXPORT_SYMBOL(netdev_port_same_parent_id);
 
-static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
-#if IS_ENABLED(CONFIG_DPLL)
-	rtnl_lock();
-	dev->dpll_pin = dpll_pin;
-	rtnl_unlock();
-#endif
-}
-
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
-	WARN_ON(!dpll_pin);
-	netdev_dpll_pin_assign(dev, dpll_pin);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_set);
-
-void netdev_dpll_pin_clear(struct net_device *dev)
-{
-	netdev_dpll_pin_assign(dev, NULL);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_clear);
-
 /**
  *	dev_change_proto_down - set carrier according to proto_down.
  *
@@ -11652,11 +11659,12 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
 
 	/* TXRX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
 
 	/* RX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index 4c2e77bd12f4..358c44680d91 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -225,7 +225,7 @@ static void gso_test_func(struct kunit *test)
 
 	segs = skb_segment(skb, features);
 	if (IS_ERR(segs)) {
-		KUNIT_FAIL(test, "segs error %lld", PTR_ERR(segs));
+		KUNIT_FAIL(test, "segs error %pe", segs);
 		goto free_gso_skb;
 	} else if (!segs) {
 		KUNIT_FAIL(test, "no segments");
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index ffe5244e5597..278294aca66a 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -94,11 +94,12 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			state->pp_id = pool->user.id;
 			err = fill(skb, pool, info);
 			if (err)
-				break;
+				goto out;
 		}
 
 		state->pp_id = 0;
 	}
+out:
 	mutex_unlock(&page_pools_lock);
 	rtnl_unlock();
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f6f29eb03ec2..bd50e9fe3234 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void)
 static size_t rtnl_prop_list_size(const struct net_device *dev)
 {
 	struct netdev_name_node *name_node;
-	size_t size;
+	unsigned int cnt = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(name_node, &dev->name_node->list, list)
+		cnt++;
+	rcu_read_unlock();
 
-	if (list_empty(&dev->name_node->list))
+	if (!cnt)
 		return 0;
-	size = nla_total_size(0);
-	list_for_each_entry(name_node, &dev->name_node->list, list)
-		size += nla_total_size(ALTIFNAMSIZ);
-	return size;
+
+	return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ);
 }
 
 static size_t rtnl_proto_down_size(const struct net_device *dev)
@@ -1054,7 +1057,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev)
 {
 	size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */
 
-	size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev));
+	size += dpll_netdev_pin_handle_size(dev);
 
 	return size;
 }
@@ -1789,7 +1792,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb,
 	if (!dpll_pin_nest)
 		return -EMSGSIZE;
 
-	ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev));
+	ret = dpll_netdev_add_pin_handle(skb, dev);
 	if (ret < 0)
 		goto nest_cancel;
 
@@ -5166,10 +5169,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
 	struct net_device *dev;
-	struct nlattr *br_spec, *attr = NULL;
+	struct nlattr *br_spec, *attr, *br_flags_attr = NULL;
 	int rem, err = -EOPNOTSUPP;
 	u16 flags = 0;
-	bool have_flags = false;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
 		return -EINVAL;
@@ -5187,11 +5189,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
-			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) {
 				if (nla_len(attr) < sizeof(flags))
 					return -EINVAL;
 
-				have_flags = true;
+				br_flags_attr = attr;
 				flags = nla_get_u16(attr);
 			}
 
@@ -5235,8 +5237,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	if (have_flags)
-		memcpy(nla_data(attr), &flags, sizeof(flags));
+	if (br_flags_attr)
+		memcpy(nla_data(br_flags_attr), &flags, sizeof(flags));
 out:
 	return err;
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 93ecfceac1bc..4d75ef9d24bf 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
 
 		rcu_read_lock();
 		psock = sk_psock(sk);
-		if (psock)
-			psock->saved_data_ready(sk);
+		if (psock) {
+			read_lock_bh(&sk->sk_callback_lock);
+			sk_psock_data_ready(sk, psock);
+			read_unlock_bh(&sk->sk_callback_lock);
+		}
 		rcu_read_unlock();
 	}
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 0a7f46c37f0c..5e78798456fd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1188,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		 */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		return 0;
+	case SO_PEEK_OFF:
+		{
+		int (*set_peek_off)(struct sock *sk, int val);
+
+		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+		if (set_peek_off)
+			ret = set_peek_off(sk, val);
+		else
+			ret = -EOPNOTSUPP;
+		return ret;
+		}
 	}
 
 	sockopt_lock_sock(sk);
@@ -1430,18 +1441,6 @@ set_sndbuf:
 		sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
 		break;
 
-	case SO_PEEK_OFF:
-		{
-		int (*set_peek_off)(struct sock *sk, int val);
-
-		set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
-		if (set_peek_off)
-			ret = set_peek_off(sk, val);
-		else
-			ret = -EOPNOTSUPP;
-		break;
-		}
-
 	case SO_NOFCS:
 		sock_valbool_flag(sk, SOCK_NOFCS, valbool);
 		break;
diff --git a/net/devlink/core.c b/net/devlink/core.c
index 4275a2bc6d8e..7f0b093208d7 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -46,7 +46,7 @@ struct devlink_rel {
 		u32 obj_index;
 		devlink_rel_notify_cb_t *notify_cb;
 		devlink_rel_cleanup_cb_t *cleanup_cb;
-		struct work_struct notify_work;
+		struct delayed_work notify_work;
 	} nested_in;
 };
 
@@ -70,7 +70,7 @@ static void __devlink_rel_put(struct devlink_rel *rel)
 static void devlink_rel_nested_in_notify_work(struct work_struct *work)
 {
 	struct devlink_rel *rel = container_of(work, struct devlink_rel,
-					       nested_in.notify_work);
+					       nested_in.notify_work.work);
 	struct devlink *devlink;
 
 	devlink = devlinks_xa_get(rel->nested_in.devlink_index);
@@ -96,13 +96,13 @@ rel_put:
 	return;
 
 reschedule_work:
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 1);
 }
 
 static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel)
 {
 	__devlink_rel_get(rel);
-	schedule_work(&rel->nested_in.notify_work);
+	schedule_delayed_work(&rel->nested_in.notify_work, 0);
 }
 
 static struct devlink_rel *devlink_rel_alloc(void)
@@ -123,8 +123,8 @@ static struct devlink_rel *devlink_rel_alloc(void)
 	}
 
 	refcount_set(&rel->refcount, 1);
-	INIT_WORK(&rel->nested_in.notify_work,
-		  &devlink_rel_nested_in_notify_work);
+	INIT_DELAYED_WORK(&rel->nested_in.notify_work,
+			  &devlink_rel_nested_in_notify_work);
 	return rel;
 }
 
@@ -529,14 +529,20 @@ static int __init devlink_init(void)
 {
 	int err;
 
-	err = genl_register_family(&devlink_nl_family);
-	if (err)
-		goto out;
 	err = register_pernet_subsys(&devlink_pernet_ops);
 	if (err)
 		goto out;
+	err = genl_register_family(&devlink_nl_family);
+	if (err)
+		goto out_unreg_pernet_subsys;
 	err = register_netdevice_notifier(&devlink_port_netdevice_nb);
+	if (!err)
+		return 0;
+
+	genl_unregister_family(&devlink_nl_family);
 
+out_unreg_pernet_subsys:
+	unregister_pernet_subsys(&devlink_pernet_ops);
 out:
 	WARN_ON(err);
 	return err;
diff --git a/net/devlink/port.c b/net/devlink/port.c
index 62e54e152ecf..4b2d46ccfe48 100644
--- a/net/devlink/port.c
+++ b/net/devlink/port.c
@@ -583,7 +583,7 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink,
 
 	xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) {
 		err = devlink_nl_port_fill(msg, devlink_port,
-					   DEVLINK_CMD_NEW,
+					   DEVLINK_CMD_PORT_NEW,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, flags,
 					   cb->extack);
@@ -674,7 +674,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 		return -EOPNOTSUPP;
 	}
 	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE],
 				    "Function does not support state setting");
 		return -EOPNOTSUPP;
 	}
diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c
index 16ed7bfd29e4..34fd1d9b2db8 100644
--- a/net/handshake/handshake-test.c
+++ b/net/handshake/handshake-test.c
@@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test)
 	handshake_req_cancel(sock->sk);
 
 	/* Act */
-	fput(filp);
+	/* Ensure the close/release/put process has run to
+	 * completion before checking the result.
+	 */
+	__fput_sync(filp);
 
 	/* Assert */
 	KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 7ceb9ac6e730..9d71b66183da 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "HSR: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n");
 		return;
 	}
 
@@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "PRP: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n");
 		return;
 	}
 
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 80cdc6f6b34c..5d68cb181695 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb)
 		return false;
 
 	/* Get next tlv */
-	total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length;
+	total_length += hsr_sup_tag->tlv.HSR_TLV_length;
 	if (!pskb_may_pull(skb, total_length))
 		return false;
 	skb_pull(skb, total_length);
@@ -435,7 +435,7 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
 			continue;
 
 		/* Don't send frame over port where it has been sent before.
-		 * Also fro SAN, this shouldn't be done.
+		 * Also for SAN, this shouldn't be done.
 		 */
 		if (!frame->is_from_san &&
 		    hsr_register_frame_out(port, frame->node_src,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4e635dd3d3c8..a5a820ee2026 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1628,10 +1628,12 @@ EXPORT_SYMBOL(inet_current_timestamp);
 
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
-	if (sk->sk_family == AF_INET)
+	unsigned int family = READ_ONCE(sk->sk_family);
+
+	if (family == AF_INET)
 		return ip_recv_error(sk, msg, len, addr_len);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6)
+	if (family == AF_INET6)
 		return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len);
 #endif
 	return -EINVAL;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2e6e1fdf82b..64aec3dff8ec 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -597,5 +597,6 @@ static void __exit ah4_fini(void)
 
 module_init(ah4_init);
 module_exit(ah4_fini);
+MODULE_DESCRIPTION("IPv4 AH transformation library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9456f5bb35e5..0d0d725b46ad 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	if (neigh) {
 		if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) {
 			read_lock_bh(&neigh->lock);
-			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			memcpy(r->arp_ha.sa_data, neigh->ha,
+			       min(dev->addr_len, sizeof(r->arp_ha.sa_data_min)));
 			r->arp_flags = arp_state_to_flags(neigh);
 			read_unlock_bh(&neigh->lock);
 			r->arp_ha.sa_family = dev->type;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ca0ff15dc8fa..bc74f131fe4d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1825,6 +1825,21 @@ done:
 	return err;
 }
 
+/* Combine dev_addr_genid and dev_base_seq to detect changes.
+ */
+static u32 inet_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->ipv4.dev_addr_genid) +
+		  net->dev_base_seq;
+
+	/* Must not return 0 (see nl_dump_check_consistent()).
+	 * Chose a value far away from 0.
+	 */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
 static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = cb->nlh;
@@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 		idx = 0;
 		head = &tgt_net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^
-			  tgt_net->dev_base_seq;
+		cb->seq = inet_base_seq(tgt_net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
-			  net->dev_base_seq;
+		cb->seq = inet_base_seq(net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f13a..4dd9e5040672 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void)
 
 module_init(esp4_init);
 module_exit(esp4_fini);
+MODULE_DESCRIPTION("IPv4 ESP transformation library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 93e9193df544..308ff34002ea 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1130,10 +1130,33 @@ ok:
 	return 0;
 
 error:
+	if (sk_hashed(sk)) {
+		spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash);
+
+		sock_prot_inuse_add(net, sk->sk_prot, -1);
+
+		spin_lock(lock);
+		sk_nulls_del_node_init_rcu(sk);
+		spin_unlock(lock);
+
+		sk->sk_hash = 0;
+		inet_sk(sk)->inet_sport = 0;
+		inet_sk(sk)->inet_num = 0;
+
+		if (tw)
+			inet_twsk_bind_unhash(tw, hinfo);
+	}
+
 	spin_unlock(&head2->lock);
 	if (tb_created)
 		inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
-	spin_unlock_bh(&head->lock);
+	spin_unlock(&head->lock);
+
+	if (tw)
+		inet_twsk_deschedule_put(tw);
+
+	local_bh_enable();
+
 	return -ENOMEM;
 }
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5169c3c72cff..6b9cf5a24c19 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1793,6 +1793,7 @@ static void __exit ipgre_fini(void)
 
 module_init(ipgre_init);
 module_exit(ipgre_fini);
+MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("gre");
 MODULE_ALIAS_RTNL_LINK("gretap");
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b06f678b03a1..67d846622365 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk,
 	unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
 	int csummode = CHECKSUM_NONE;
 	struct rtable *rt = (struct rtable *)cork->dst;
+	bool paged, hold_tskey, extra_uref = false;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged, extra_uref = false;
 	u32 tskey = 0;
 
 	skb = skb_peek_tail(queue);
@@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
 	paged = !!cork->gso_size;
 
-	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
@@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk,
 
 	cork->length += length;
 
+	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+	if (hold_tskey)
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
 	/* So, what's going on in the loop below?
 	 *
 	 * We use calculated fragment length to generate chained skb,
@@ -1274,6 +1275,8 @@ error:
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	if (hold_tskey)
+		atomic_dec(&sk->sk_tskey);
 	return err;
 }
 
@@ -1287,6 +1290,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	if (unlikely(!rt))
 		return -EFAULT;
 
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
+
 	/*
 	 * setup for corking.
 	 */
@@ -1303,12 +1312,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
-
-	if (!inetdev_valid_mtu(cork->fragsize))
-		return -ENETUNREACH;
-
 	cork->gso_size = ipc->gso_size;
 
 	cork->dst = &rt->dst;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7aa9dc0e6760..21d2ffa919e9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1363,12 +1363,13 @@ e_inval:
  * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
+ * @drop_dst: if true, drops skb dst
  *
  * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
  * destination in skb->cb[] before dst drop.
  * This way, receiver doesn't make cache line misses to read rtable.
  */
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
 	bool prepare = inet_test_bit(PKTINFO, sk) ||
@@ -1397,7 +1398,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	if (drop_dst)
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index beeae624c412..1b6981de3f29 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -554,6 +554,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
+static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	static const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
@@ -632,13 +646,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, headroom)) {
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
+
+	ip_tunnel_adj_headroom(dev, headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
@@ -818,16 +832,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
 
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, max_headroom)) {
 		ip_rt_put(rt);
 		DEV_STATS_INC(dev, tx_dropped);
 		kfree_skb(skb);
 		return;
 	}
 
+	ip_tunnel_adj_headroom(dev, max_headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
@@ -1298,4 +1312,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id)
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_setup);
 
+MODULE_DESCRIPTION("IPv4 tunnel implementation library");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 586b1b3e35b8..80ccd6661aa3 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	};
 	skb_reset_network_header(skb);
 
-	csum = csum_partial(icmp6h, len, 0);
+	csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
 	icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
 					      IPPROTO_ICMPV6, csum);
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9ab9b3ebe0cd..d1d6bb28ed6e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -721,6 +721,7 @@ static void __exit vti_fini(void)
 
 module_init(vti_init);
 module_exit(vti_fini);
+MODULE_DESCRIPTION("Virtual (secure) IP tunneling library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("vti");
 MODULE_ALIAS_NETDEV("ip_vti0");
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 27b8f83c6ea2..03afa3871efc 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -658,6 +658,7 @@ static void __exit ipip_fini(void)
 
 module_init(ipip_init);
 module_exit(ipip_fini);
+MODULE_DESCRIPTION("IP/IP protocol decoder library");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d6f59531b3a..362229836510 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
 		msg->im_vif_hi = vifi >> 8;
-		ipv4_pktinfo_prepare(mroute_sk, pkt);
+		ipv4_pktinfo_prepare(mroute_sk, pkt, false);
 		memcpy(skb->cb, pkt->cb, sizeof(skb->cb));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 27da9d7294c0..aea89326c697 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Charge it to the socket. */
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
 		kfree_skb_reason(skb, reason);
 		return NET_RX_DROP;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a1c6de385cce..c82dc42f57c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1786,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 
 static bool can_map_frag(const skb_frag_t *frag)
 {
-	return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+	struct page *page;
+
+	if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag))
+		return false;
+
+	page = skb_frag_page(frag);
+
+	if (PageCompound(page) || page->mapping)
+		return false;
+
+	return true;
 }
 
 static int find_next_mappable_frag(const skb_frag_t *frag,
@@ -4605,7 +4615,8 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32);
 
 	/* RX read-mostly hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 5048c47c79b2..4c1f836aae38 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void)
 
 module_init(tunnel4_init);
 module_exit(tunnel4_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel library");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 148ffb007969..e474b201900f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk)
 
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 {
-	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
-		bool slow = lock_sock_fast(sk);
-
-		sk_peek_offset_bwd(sk, len);
-		unlock_sock_fast(sk, slow);
-	}
+	sk_peek_offset_bwd(sk, len);
 
 	if (!skb_unref(skb))
 		return;
@@ -2169,7 +2164,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 
 	udp_csum_pull_header(skb);
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index a87defb2b167..860aff5f8599 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup);
 
+MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 8489fa106583..8cb266af1393 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -114,5 +114,6 @@ static void __exit ipip_fini(void)
 
 module_init(ipip_init);
 module_exit(ipip_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 733ace18806c..055230b669cf 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -708,6 +708,22 @@ errout:
 	return err;
 }
 
+/* Combine dev_addr_genid and dev_base_seq to detect changes.
+ */
+static u32 inet6_base_seq(const struct net *net)
+{
+	u32 res = atomic_read(&net->ipv6.dev_addr_genid) +
+		  net->dev_base_seq;
+
+	/* Must not return 0 (see nl_dump_check_consistent()).
+	 * Chose a value far away from 0.
+	 */
+	if (!res)
+		res = 0x80000000;
+	return res;
+}
+
+
 static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 				      struct netlink_callback *cb)
 {
@@ -741,8 +757,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 		idx = 0;
 		head = &net->dev_index_head[h];
 		rcu_read_lock();
-		cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^
-			  net->dev_base_seq;
+		cb->seq = inet6_base_seq(net);
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
@@ -5362,7 +5377,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 	}
 
 	rcu_read_lock();
-	cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq;
+	cb->seq = inet6_base_seq(tgt_net);
 	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
 		idx = 0;
 		head = &tgt_net->dev_index_head[h];
@@ -5494,9 +5509,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (!addr)
-		return -EINVAL;
-
+	if (!addr) {
+		err = -EINVAL;
+		goto errout;
+	}
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_index)
 		dev = dev_get_by_index(tgt_net, ifm->ifa_index);
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 507a8353a6bd..c008d21925d7 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
 /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
+const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LOOPBACK_INIT;
 EXPORT_SYMBOL(in6addr_loopback);
-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
+const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_ANY_INIT;
 EXPORT_SYMBOL(in6addr_any);
-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allnodes);
-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allrouters);
-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allnodes);
-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allrouters);
-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_sitelocal_allrouters);
 
 static void snmp6_free_dev(struct inet6_dev *idev)
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2016e90e6e1d..eb474f0987ae 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -800,5 +800,6 @@ static void __exit ah6_fini(void)
 module_init(ah6_init);
 module_exit(ah6_fini);
 
+MODULE_DESCRIPTION("IPv6 AH transformation helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 2cc1a45742d8..6e6efe026cdc 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void)
 module_init(esp6_init);
 module_exit(esp6_fini);
 
+MODULE_DESCRIPTION("IPv6 ESP transformation helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 4952ae792450..02e9ffb63af1 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -177,6 +177,8 @@ static bool ip6_parse_tlv(bool hopbyhop,
 				case IPV6_TLV_IOAM:
 					if (!ipv6_hop_ioam(skb, off))
 						return false;
+
+					nh = skb_network_header(skb);
 					break;
 				case IPV6_TLV_JUMBO:
 					if (!ipv6_hop_jumbo(skb, off))
@@ -943,6 +945,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff)
 		if (!skb_valid_dst(skb))
 			ip6_route_input(skb);
 
+		/* About to mangle packet header */
+		if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len))
+			goto drop;
+
+		/* Trace pointer may have changed */
+		trace = (struct ioam6_trace_hdr *)(skb_network_header(skb)
+						   + optoff + sizeof(*hdr));
+
 		ioam6_fill_trace_data(skb, ns, trace, true);
 		break;
 	default:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a722a43dd668..31b86fe661aa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk,
 	bool zc = false;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
+	bool paged, hold_tskey, extra_uref = false;
 	struct ipv6_txoptions *opt = v6_cork->opt;
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
 	unsigned int wmem_alloc_delta = 0;
-	bool paged, extra_uref = false;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
-	if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
-	    READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
-		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
@@ -1538,6 +1534,11 @@ emsgsize:
 			flags &= ~MSG_SPLICE_PAGES;
 	}
 
+	hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+		     READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+	if (hold_tskey)
+		tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1794,6 +1795,8 @@ error:
 	cork->length -= length;
 	IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
 	refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+	if (hold_tskey)
+		atomic_dec(&sk->sk_tskey);
 	return err;
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 46c19bd48990..9bbabf750a21 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 						struct sk_buff *skb),
 			 bool log_ecn_err)
 {
-	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-	int err;
+	const struct ipv6hdr *ipv6h;
+	int nh, err;
 
 	if ((!(tpi->flags & TUNNEL_CSUM) &&
 	     (tunnel->parms.i_flags & TUNNEL_CSUM)) ||
@@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 			goto drop;
 		}
 
-		ipv6h = ipv6_hdr(skb);
 		skb->protocol = eth_type_trans(skb, tunnel->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 	} else {
@@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 	}
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
+
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(tunnel->dev, rx_length_errors);
+		DEV_STATS_INC(tunnel->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	ipv6h = (struct ipv6hdr *)(skb->head + nh);
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 
 	__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7bf0327b380..c99053189ea8 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup);
 
+MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 83d2a8be263f..6a16a5bd0d91 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -405,6 +405,7 @@ static void __exit mip6_fini(void)
 module_init(mip6_init);
 module_exit(mip6_fini);
 
+MODULE_DESCRIPTION("IPv6 Mobility driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS);
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ea1dec8448fc..ef815ba583a8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5332,19 +5332,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	err_nh = NULL;
 	list_for_each_entry(nh, &rt6_nh_list, next) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
-		fib6_info_release(nh->fib6_info);
-
-		if (!err) {
-			/* save reference to last route successfully inserted */
-			rt_last = nh->fib6_info;
-
-			/* save reference to first route for notification */
-			if (!rt_notif)
-				rt_notif = nh->fib6_info;
-		}
 
-		/* nh->fib6_info is used or freed at this point, reset to NULL*/
-		nh->fib6_info = NULL;
 		if (err) {
 			if (replace && nhn)
 				NL_SET_ERR_MSG_MOD(extack,
@@ -5352,6 +5340,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			err_nh = nh;
 			goto add_errout;
 		}
+		/* save reference to last route successfully inserted */
+		rt_last = nh->fib6_info;
+
+		/* save reference to first route for notification */
+		if (!rt_notif)
+			rt_notif = nh->fib6_info;
 
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
@@ -5412,8 +5406,7 @@ add_errout:
 
 cleanup:
 	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
-		if (nh->fib6_info)
-			fib6_info_release(nh->fib6_info);
+		fib6_info_release(nh->fib6_info);
 		list_del(&nh->next);
 		kfree(nh);
 	}
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 29346a6eec9f..35508abd76f4 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -512,22 +512,24 @@ int __init seg6_init(void)
 {
 	int err;
 
-	err = genl_register_family(&seg6_genl_family);
+	err = register_pernet_subsys(&ip6_segments_ops);
 	if (err)
 		goto out;
 
-	err = register_pernet_subsys(&ip6_segments_ops);
+	err = genl_register_family(&seg6_genl_family);
 	if (err)
-		goto out_unregister_genl;
+		goto out_unregister_pernet;
 
 #ifdef CONFIG_IPV6_SEG6_LWTUNNEL
 	err = seg6_iptunnel_init();
 	if (err)
-		goto out_unregister_pernet;
+		goto out_unregister_genl;
 
 	err = seg6_local_init();
-	if (err)
-		goto out_unregister_pernet;
+	if (err) {
+		seg6_iptunnel_exit();
+		goto out_unregister_genl;
+	}
 #endif
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
@@ -548,11 +550,11 @@ out_unregister_iptun:
 #endif
 #endif
 #ifdef CONFIG_IPV6_SEG6_LWTUNNEL
-out_unregister_pernet:
-	unregister_pernet_subsys(&ip6_segments_ops);
-#endif
 out_unregister_genl:
 	genl_unregister_family(&seg6_genl_family);
+#endif
+out_unregister_pernet:
+	unregister_pernet_subsys(&ip6_segments_ops);
 	goto out;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cc24cefdb85c..5e9f625b76e3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1956,6 +1956,7 @@ xfrm_tunnel_failed:
 
 module_init(sit_init);
 module_exit(sit_cleanup);
+MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 00e8d8b1c9a7..dc4ea9b11794 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void)
 
 module_init(tunnel6_init);
 module_exit(tunnel6_fini);
+MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver");
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1323f2f6928e..f6cb94f82cc3 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void)
 
 module_init(xfrm6_tunnel_init);
 module_exit(xfrm6_tunnel_fini);
+MODULE_DESCRIPTION("IPv6 XFRM tunnel driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6);
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 6334f64f04d5..b0b3e9c5af44 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID";
 static LIST_HEAD(iucv_handler_list);
 
 /*
- * iucv_path_table: an array of iucv_path structures.
+ * iucv_path_table: array of pointers to iucv_path structures.
  */
 static struct iucv_path **iucv_path_table;
 static unsigned long iucv_max_pathid;
@@ -544,7 +544,7 @@ static int iucv_enable(void)
 
 	cpus_read_lock();
 	rc = -ENOMEM;
-	alloc_size = iucv_max_pathid * sizeof(struct iucv_path);
+	alloc_size = iucv_max_pathid * sizeof(*iucv_path_table);
 	iucv_path_table = kzalloc(alloc_size, GFP_KERNEL);
 	if (!iucv_path_table)
 		goto out;
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d68d01804dc7..f79fb99271ed 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3924,5 +3924,6 @@ out_unregister_key_proto:
 
 module_init(ipsec_pfkey_init);
 module_exit(ipsec_pfkey_exit);
+MODULE_DESCRIPTION("PF_KEY socket helpers");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_KEY);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index dd3153966173..7bf14cf9ffaa 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -627,7 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 back_from_confirm:
 	lock_sock(sk);
-	ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0;
+	ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0);
 	err = ip6_append_data(sk, ip_generic_getfrag, msg,
 			      ulen, transhdrlen, &ipc6,
 			      &fl6, (struct rt6_info *)dst,
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 20551cfb7da6..fde1140d899e 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock)
 	}
 	netdev_put(llc->dev, &llc->dev_tracker);
 	sock_put(sk);
+	sock_orphan(sk);
+	sock->sk = NULL;
 	llc_sk_free(sk);
 out:
 	return 0;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 489dd97f5172..327682995c92 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -987,7 +987,8 @@ static int
 ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 				     struct cfg80211_unsol_bcast_probe_resp *params,
 				     struct ieee80211_link_data *link,
-				     struct ieee80211_bss_conf *link_conf)
+				     struct ieee80211_bss_conf *link_conf,
+				     u64 *changed)
 {
 	struct unsol_bcast_probe_resp_data *new, *old = NULL;
 
@@ -1011,7 +1012,8 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
 		RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL);
 	}
 
-	return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	*changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	return 0;
 }
 
 static int ieee80211_set_ftm_responder_params(
@@ -1450,10 +1452,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		goto error;
-	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata, link_conf);
 	if (err) {
@@ -1525,10 +1526,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 
 	err = ieee80211_set_unsol_bcast_probe_resp(sdata,
 						   &params->unsol_bcast_probe_resp,
-						   link, link_conf);
+						   link, link_conf, &changed);
 	if (err < 0)
 		return err;
-	changed |= err;
 
 	if (beacon->he_bss_color_valid &&
 	    beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) {
@@ -1869,6 +1869,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 					      sband->band);
 	}
 
+	ieee80211_sta_set_rx_nss(link_sta);
+
 	return ret;
 }
 
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index dce5606ed66d..68596ef78b15 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -997,8 +997,8 @@ static void add_link_files(struct ieee80211_link_data *link,
 	}
 }
 
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif)
+static void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
+					 bool mld_vif)
 {
 	char buf[10+IFNAMSIZ];
 
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index b226b1aae88a..a02ec0a413f6 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -11,8 +11,6 @@
 #include "ieee80211_i.h"
 
 #ifdef CONFIG_MAC80211_DEBUGFS
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
-				  bool mld_vif);
 void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
@@ -24,9 +22,6 @@ void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link);
 void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link);
 #else
-static inline void ieee80211_debugfs_add_netdev(
-	struct ieee80211_sub_if_data *sdata, bool mld_vif)
-{}
 static inline void ieee80211_debugfs_remove_netdev(
 	struct ieee80211_sub_if_data *sdata)
 {}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e4e7c0b38cb6..11c4caa4748e 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1783,7 +1783,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	/* need to do this after the switch so vif.type is correct */
 	ieee80211_link_setup(&sdata->deflink);
 
-	ieee80211_debugfs_add_netdev(sdata, false);
+	ieee80211_debugfs_recreate_netdev(sdata, false);
 }
 
 static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 073105deb424..2022a26eb881 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2023 Intel Corporation
+ * Copyright (C) 2018 - 2024 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -2918,6 +2918,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	/* other links will be destroyed */
 	sdata->deflink.u.mgd.bss = NULL;
+	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
 
 	netif_carrier_off(sdata->dev);
 
@@ -5045,9 +5046,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!link)
 		return 0;
 
-	/* will change later if needed */
-	link->smps_mode = IEEE80211_SMPS_OFF;
-
 	/*
 	 * If this fails (possibly due to channel context sharing
 	 * on incompatible channels, e.g. 80+80 and 160 sharing the
@@ -7096,6 +7094,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
 	link->u.mgd.p2p_noa_index = -1;
 	link->u.mgd.conn_flags = 0;
 	link->conf->bssid = link->u.mgd.bssid;
+	link->smps_mode = IEEE80211_SMPS_OFF;
 
 	wiphy_work_init(&link->u.mgd.request_smps_work,
 			ieee80211_request_smps_mgd_work);
@@ -7309,6 +7308,75 @@ out_err:
 	return err;
 }
 
+static bool ieee80211_mgd_csa_present(struct ieee80211_sub_if_data *sdata,
+				      const struct cfg80211_bss_ies *ies,
+				      u8 cur_channel, bool ignore_ecsa)
+{
+	const struct element *csa_elem, *ecsa_elem;
+	struct ieee80211_channel_sw_ie *csa = NULL;
+	struct ieee80211_ext_chansw_ie *ecsa = NULL;
+
+	if (!ies)
+		return false;
+
+	csa_elem = cfg80211_find_elem(WLAN_EID_CHANNEL_SWITCH,
+				      ies->data, ies->len);
+	if (csa_elem && csa_elem->datalen == sizeof(*csa))
+		csa = (void *)csa_elem->data;
+
+	ecsa_elem = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				       ies->data, ies->len);
+	if (ecsa_elem && ecsa_elem->datalen == sizeof(*ecsa))
+		ecsa = (void *)ecsa_elem->data;
+
+	if (csa && csa->count == 0)
+		csa = NULL;
+	if (csa && !csa->mode && csa->new_ch_num == cur_channel)
+		csa = NULL;
+
+	if (ecsa && ecsa->count == 0)
+		ecsa = NULL;
+	if (ecsa && !ecsa->mode && ecsa->new_ch_num == cur_channel)
+		ecsa = NULL;
+
+	if (ignore_ecsa && ecsa) {
+		sdata_info(sdata,
+			   "Ignoring ECSA in probe response - was considered stuck!\n");
+		return csa;
+	}
+
+	return csa || ecsa;
+}
+
+static bool ieee80211_mgd_csa_in_process(struct ieee80211_sub_if_data *sdata,
+					 struct cfg80211_bss *bss)
+{
+	u8 cur_channel;
+	bool ret;
+
+	cur_channel = ieee80211_frequency_to_channel(bss->channel->center_freq);
+
+	rcu_read_lock();
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->beacon_ies),
+				      cur_channel, false)) {
+		ret = true;
+		goto out;
+	}
+
+	if (ieee80211_mgd_csa_present(sdata,
+				      rcu_dereference(bss->proberesp_ies),
+				      cur_channel, bss->proberesp_ecsa_stuck)) {
+		ret = true;
+		goto out;
+	}
+
+	ret = false;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /* config hooks */
 int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 		       struct cfg80211_auth_request *req)
@@ -7317,7 +7385,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_auth_data *auth_data;
 	struct ieee80211_link_data *link;
-	const struct element *csa_elem, *ecsa_elem;
 	u16 auth_alg;
 	int err;
 	bool cont_auth;
@@ -7360,21 +7427,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->assoc_data)
 		return -EBUSY;
 
-	rcu_read_lock();
-	csa_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(req->bss,
-					   WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, req->bss)) {
 		sdata_info(sdata, "AP is in CSA process, reject auth\n");
 		return -EINVAL;
 	}
-	rcu_read_unlock();
 
 	auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len +
 			    req->ie_len, GFP_KERNEL);
@@ -7684,7 +7740,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_mgd_assoc_data *assoc_data;
-	const struct element *ssid_elem, *csa_elem, *ecsa_elem;
+	const struct element *ssid_elem;
 	struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
 	ieee80211_conn_flags_t conn_flags = 0;
 	struct ieee80211_link_data *link;
@@ -7707,23 +7763,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	cbss = req->link_id < 0 ? req->bss : req->links[req->link_id].bss;
 
-	rcu_read_lock();
-	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
-	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
-		rcu_read_unlock();
+	if (ieee80211_mgd_csa_in_process(sdata, cbss)) {
+		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
 		kfree(assoc_data);
 		return -EINVAL;
 	}
 
-	csa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_CHANNEL_SWITCH);
-	ecsa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_EXT_CHANSWITCH_ANN);
-	if ((csa_elem &&
-	     csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
-	     ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
-	    (ecsa_elem &&
-	     ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
-	     ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
-		sdata_info(sdata, "AP is in CSA process, reject assoc\n");
+	rcu_read_lock();
+	ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
+	if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
 		rcu_read_unlock();
 		kfree(assoc_data);
 		return -EINVAL;
@@ -7998,8 +8046,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 		rcu_read_lock();
 		beacon_ies = rcu_dereference(req->bss->beacon_ies);
-
-		if (beacon_ies) {
+		if (!beacon_ies) {
 			/*
 			 * Wait up to one beacon interval ...
 			 * should this be more if we miss one?
@@ -8080,6 +8127,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
 					    req->reason_code, false);
+		drv_mgd_complete_tx(sdata->local, sdata, &info);
 		return 0;
 	}
 
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index d5ea5f5bcf3a..9d33fd2377c8 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -119,7 +119,8 @@ void rate_control_rate_update(struct ieee80211_local *local,
 		rcu_read_unlock();
 	}
 
-	drv_sta_rc_update(local, sta->sdata, &sta->sta, changed);
+	if (sta->uploaded)
+		drv_sta_rc_update(local, sta->sdata, &sta->sta, changed);
 }
 
 int ieee80211_rate_control_register(const struct rate_control_ops *ops)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 645355e5f1bc..f9d5842601fa 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -237,14 +237,18 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 }
 
 static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_channel *channel,
 					u32 scan_flags, const u8 *da)
 {
 	if (!sdata)
 		return false;
-	/* accept broadcast for OCE */
-	if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP &&
-	    is_broadcast_ether_addr(da))
+
+	/* accept broadcast on 6 GHz and for OCE */
+	if (is_broadcast_ether_addr(da) &&
+	    (channel->band == NL80211_BAND_6GHZ ||
+	     scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP))
 		return true;
+
 	if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
 		return true;
 	return ether_addr_equal(da, sdata->vif.addr);
@@ -293,6 +297,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0);
 	}
 
+	channel = ieee80211_get_channel_khz(local->hw.wiphy,
+					    ieee80211_rx_status_to_khz(rx_status));
+
+	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+		return;
+
 	if (ieee80211_is_probe_resp(mgmt->frame_control)) {
 		struct cfg80211_scan_request *scan_req;
 		struct cfg80211_sched_scan_request *sched_scan_req;
@@ -310,19 +320,15 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 		/* ignore ProbeResp to foreign address or non-bcast (OCE)
 		 * unless scanning with randomised address
 		 */
-		if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags,
+		if (!ieee80211_scan_accept_presp(sdata1, channel,
+						 scan_req_flags,
 						 mgmt->da) &&
-		    !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags,
+		    !ieee80211_scan_accept_presp(sdata2, channel,
+						 sched_scan_req_flags,
 						 mgmt->da))
 			return;
 	}
 
-	channel = ieee80211_get_channel_khz(local->hw.wiphy,
-					ieee80211_rx_status_to_khz(rx_status));
-
-	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
-		return;
-
 	bss = ieee80211_bss_info_update(local, rx_status,
 					mgmt, skb->len,
 					channel);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 68a48abc7287..6fbb15b65902 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  *
  * Transmit and frame generation functions.
  */
@@ -3100,10 +3100,11 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 			/* DA SA BSSID */
 			build.da_offs = offsetof(struct ieee80211_hdr, addr1);
 			build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
+			rcu_read_lock();
 			link = rcu_dereference(sdata->link[tdls_link_id]);
-			if (WARN_ON_ONCE(!link))
-				break;
-			memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			if (!WARN_ON_ONCE(!link))
+				memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+			rcu_read_unlock();
 			build.hdr_len = 24;
 			break;
 		}
@@ -3926,6 +3927,7 @@ begin:
 			goto begin;
 
 		skb = __skb_dequeue(&tx.skbs);
+		info = IEEE80211_SKB_CB(skb);
 
 		if (!skb_queue_empty(&tx.skbs)) {
 			spin_lock_bh(&fq->lock);
@@ -3970,7 +3972,7 @@ begin:
 	}
 
 encap_out:
-	IEEE80211_SKB_CB(skb)->control.vif = vif;
+	info->control.vif = vif;
 
 	if (tx.sta &&
 	    wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
index a05c5b971789..3a8612309137 100644
--- a/net/mac80211/wbrf.c
+++ b/net/mac80211/wbrf.c
@@ -23,8 +23,6 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local)
 		return;
 
 	local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev);
-	dev_dbg(dev, "WBRF is %s supported\n",
-		local->wbrf_supported ? "" : "not");
 }
 
 static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end)
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 7a47a58aa54b..ceee44ea09d9 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk,
 	spin_unlock_irqrestore(&mns->keys_lock, flags);
 
 	if (!tagbits) {
-		kfree(key);
+		mctp_key_unref(key);
 		return ERR_PTR(-EBUSY);
 	}
 
@@ -888,7 +888,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex);
 		if (!dev) {
 			rcu_read_unlock();
-			return rc;
+			goto out_free;
 		}
 		rt->dev = __mctp_dev_get(dev);
 		rcu_read_unlock();
@@ -903,7 +903,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rt->mtu = 0;
 
 	} else {
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out_free;
 	}
 
 	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
@@ -966,12 +967,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rc = mctp_do_fragment_route(rt, skb, mtu, tag);
 	}
 
+	/* route output functions consume the skb, even on error */
+	skb = NULL;
+
 out_release:
 	if (!ext_rt)
 		mctp_route_release(rt);
 
 	mctp_dev_put(tmp_rt.dev);
 
+out_free:
+	kfree_skb(skb);
 	return rc;
 }
 
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index a536586742f2..7017dd60659d 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -13,17 +13,22 @@
 #include <uapi/linux/mptcp.h>
 #include "protocol.h"
 
-static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
+static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *sf;
 	struct nlattr *start;
 	u32 flags = 0;
+	bool slow;
 	int err;
 
+	if (inet_sk_state_load(sk) == TCP_LISTEN)
+		return 0;
+
 	start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP);
 	if (!start)
 		return -EMSGSIZE;
 
+	slow = lock_sock_fast(sk);
 	rcu_read_lock();
 	sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data);
 	if (!sf) {
@@ -63,17 +68,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb)
 			sf->map_data_len) ||
 	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
 	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
-	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) {
+	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
 		err = -EMSGSIZE;
 		goto nla_failure;
 	}
 
 	rcu_read_unlock();
+	unlock_sock_fast(sk, slow);
 	nla_nest_end(skb, start);
 	return 0;
 
 nla_failure:
 	rcu_read_unlock();
+	unlock_sock_fast(sk, slow);
 	nla_nest_cancel(skb, start);
 	return err;
 }
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 74698582a285..ad28da655f8b 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	mptcp_data_unlock(sk);
 }
 
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				   const struct mptcp_options_received *mp_opt)
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				     const struct mptcp_options_received *mp_opt)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *skb;
 
-	mptcp_data_lock(sk);
 	skb = skb_peek_tail(&sk->sk_receive_queue);
 	if (skb) {
 		WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
@@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_
 	}
 
 	pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
-	mptcp_data_unlock(sk);
 }
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index d2527d189a79..63fc0758c22d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		/* subflows are fully established as soon as we get any
 		 * additional ack, including ADD_ADDR.
 		 */
-		subflow->fully_established = 1;
-		WRITE_ONCE(msk->fully_established, true);
-		goto check_notify;
+		goto set_fully_established;
 	}
 
 	/* If the first established packet does not contain MP_CAPABLE + data
@@ -983,10 +981,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	if (mp_opt->deny_join_id0)
 		WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 
-set_fully_established:
 	if (unlikely(!READ_ONCE(msk->pm.server_side)))
 		pr_warn_once("bogus mpc option on established client sk");
-	mptcp_subflow_fully_established(subflow, mp_opt);
+
+set_fully_established:
+	mptcp_data_lock((struct sock *)msk);
+	__mptcp_subflow_fully_established(msk, subflow, mp_opt);
+	mptcp_data_unlock((struct sock *)msk);
 
 check_notify:
 	/* if the subflow is not already linked into the conn_list, we can't
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 287a60381eae..58d17d9604e7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	}
 }
 
-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
-				  const struct mptcp_addr_info *addr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		if (addrs[i].id == addr->id)
-			return true;
-	}
-
-	return false;
-}
-
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
@@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
+		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+		/* Forbid creation of new subflows matching existing
+		 * ones, possibly already created by incoming ADD_ADDR
+		 */
+		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+		mptcp_for_each_subflow(msk, subflow)
+			if (READ_ONCE(subflow->local_id) == local->id)
+				__set_bit(subflow->remote_id, unavail_id);
+
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
-			addrs[i].id = subflow->remote_id;
+			addrs[i].id = READ_ONCE(subflow->remote_id);
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
+			if (test_bit(addrs[i].id, unavail_id))
+				continue;
+
 			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
 				continue;
 
-			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
-			    msk->pm.subflows < subflows_max) {
+			if (msk->pm.subflows < subflows_max) {
+				/* forbid creating multiple address towards
+				 * this id
+				 */
+				__set_bit(addrs[i].id, unavail_id);
 				msk->pm.subflows++;
 				i++;
 			}
@@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 
 		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+			u8 remote_id = READ_ONCE(subflow->remote_id);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-			u8 id = subflow->local_id;
+			u8 id = subflow_get_local_id(subflow);
 
-			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
 				continue;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
 			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, subflow->local_id, subflow->remote_id,
-				 msk->mpc_endpoint_id);
+				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
 
@@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 }
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
-					     struct mptcp_pm_addr_entry *entry)
+					     struct mptcp_pm_addr_entry *entry,
+					     bool needs_id)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 		}
 	}
 
-	if (!entry->addr.id) {
+	if (!entry->addr.id && needs_id) {
 find_next:
 		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
 						    MPTCP_PM_MAX_ADDR_ID + 1,
@@ -960,7 +964,7 @@ find_next:
 		}
 	}
 
-	if (!entry->addr.id)
+	if (!entry->addr.id && needs_id)
 		goto out;
 
 	__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1285,6 +1289,18 @@ next:
 	return 0;
 }
 
+static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
+				      struct genl_info *info)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
+					 mptcp_pm_address_nl_policy, info->extack) &&
+	    tb[MPTCP_PM_ADDR_ATTR_ID])
+		return true;
+	return false;
+}
+
 int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
@@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 			goto out_free;
 		}
 	}
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
+						!mptcp_pm_has_addr_attr_id(attr, info));
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;
@@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 	if (WARN_ON_ONCE(!sf))
 		return -EINVAL;
 
-	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
+	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf)))
 		return -EMSGSIZE;
 
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index efecbe3cf415..bc97cc30f013 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk)
 }
 
 static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
-						    struct mptcp_pm_addr_entry *entry)
+						    struct mptcp_pm_addr_entry *entry,
+						    bool needs_id)
 {
 	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	struct mptcp_pm_addr_entry *match = NULL;
@@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 	list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
 		addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true);
-		if (addr_match && entry->addr.id == 0)
+		if (addr_match && entry->addr.id == 0 && needs_id)
 			entry->addr.id = e->addr.id;
 		id_match = (e->addr.id == entry->addr.id);
 		if (addr_match && id_match) {
@@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		}
 
 		*e = *entry;
-		if (!e->addr.id)
+		if (!e->addr.id && needs_id)
 			e->addr.id = find_next_zero_bit(id_bitmap,
 							MPTCP_PM_MAX_ADDR_ID + 1,
 							1);
@@ -130,10 +131,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 				    struct mptcp_addr_info *skc)
 {
-	struct mptcp_pm_addr_entry new_entry;
+	struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry;
 	__be16 msk_sport =  ((struct inet_sock *)
 			     inet_sk((struct sock *)msk))->inet_sport;
 
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&e->addr, skc, false)) {
+			entry = e;
+			break;
+		}
+	}
+	spin_unlock_bh(&msk->pm.lock);
+	if (entry)
+		return entry->addr.id;
+
 	memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
 	new_entry.addr = *skc;
 	new_entry.addr.id = 0;
@@ -142,7 +154,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 	if (new_entry.addr.port == msk_sport)
 		new_entry.addr.port = 0;
 
-	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry);
+	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
 }
 
 int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
@@ -187,7 +199,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 		goto announce_err;
 	}
 
-	err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val);
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "did not match address and id");
 		goto announce_err;
@@ -222,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,
 
 	lock_sock(sk);
 	mptcp_for_each_subflow(msk, subflow) {
-		if (subflow->local_id == 0) {
+		if (READ_ONCE(subflow->local_id) == 0) {
 			has_id_0 = true;
 			break;
 		}
@@ -367,7 +379,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	local.addr = addr_l;
-	err = mptcp_userspace_pm_append_new_local_addr(msk, &local);
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "did not match address and id");
 		goto create_err;
@@ -483,6 +495,16 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 		goto destroy_err;
 	}
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) {
+		ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6);
+		addr_l.family = AF_INET6;
+	}
+	if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) {
+		ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6);
+		addr_r.family = AF_INET6;
+	}
+#endif
 	if (addr_l.family != addr_r.family) {
 		GENL_SET_ERR_MSG(info, "address families do not match");
 		err = -EINVAL;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3ed4709a7509..7833a49f6214 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	subflow->subflow_id = msk->subflow_id++;
 
 	/* This is the first subflow, always with id 0 */
-	subflow->local_id_valid = 1;
+	WRITE_ONCE(subflow->local_id, 0);
 	mptcp_sock_graft(msk->first, sk->sk_socket);
 	iput(SOCK_INODE(ssock));
 
@@ -1260,6 +1260,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		mpext = mptcp_get_ext(skb);
 		if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
 			TCP_SKB_CB(skb)->eor = 1;
+			tcp_mark_push(tcp_sk(ssk), skb);
 			goto alloc_skb;
 		}
 
@@ -1505,8 +1506,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
 
 void mptcp_check_and_set_pending(struct sock *sk)
 {
-	if (mptcp_send_head(sk))
-		mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+	if (mptcp_send_head(sk)) {
+		mptcp_data_lock(sk);
+		mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+		mptcp_data_unlock(sk);
+	}
 }
 
 static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -1960,6 +1964,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (copied <= 0)
 		return;
 
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, msk->first);
+
 	msk->rcvq_space.copied += copied;
 
 	mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -2314,9 +2321,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	if (__mptcp_check_fallback(msk))
 		return false;
 
-	if (tcp_rtx_and_write_queues_empty(sk))
-		return false;
-
 	/* the closing socket has some data untransmitted and/or unacked:
 	 * some data in the mptcp rtx queue has not really xmitted yet.
 	 * keep it simple and re-inject the whole mptcp level rtx queue
@@ -3145,7 +3149,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
 	WRITE_ONCE(msk->flags, 0);
 	msk->cb_flags = 0;
-	msk->push_pending = 0;
 	msk->recovery = false;
 	msk->can_ack = false;
 	msk->fully_established = false;
@@ -3161,6 +3164,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 	msk->bytes_received = 0;
 	msk->bytes_sent = 0;
 	msk->bytes_retrans = 0;
+	msk->rcvspace_init = 0;
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
@@ -3174,8 +3178,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 
 	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
 }
+
+static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
+{
+	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
+	struct ipv6_pinfo *newnp;
+
+	newnp = inet6_sk(newsk);
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		if (!opt)
+			net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__);
+	}
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+}
 #endif
 
+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
+{
+	struct ip_options_rcu *inet_opt, *newopt = NULL;
+	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_sock *newinet;
+
+	newinet = inet_sk(newsk);
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt) {
+		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+				      inet_opt->opt.optlen, GFP_ATOMIC);
+		if (newopt)
+			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
+			       inet_opt->opt.optlen);
+		else
+			net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
+	}
+	RCU_INIT_POINTER(newinet->inet_opt, newopt);
+	rcu_read_unlock();
+}
+
 struct sock *mptcp_sk_clone_init(const struct sock *sk,
 				 const struct mptcp_options_received *mp_opt,
 				 struct sock *ssk,
@@ -3183,6 +3229,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk;
 
 	if (!nsk)
@@ -3195,6 +3242,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 
 	__mptcp_init_sock(nsk);
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (nsk->sk_family == AF_INET6)
+		mptcp_copy_ip6_options(nsk, sk);
+	else
+#endif
+		mptcp_copy_ip_options(nsk, sk);
+
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
@@ -3206,7 +3260,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	msk->write_seq = subflow_req->idsn + 1;
 	msk->snd_nxt = msk->write_seq;
 	msk->snd_una = msk->write_seq;
-	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+	msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
@@ -3223,7 +3277,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 
 	/* The msk maintain a ref to each subflow in the connections list */
 	WRITE_ONCE(msk->first, ssk);
-	list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+	subflow = mptcp_subflow_ctx(ssk);
+	list_add(&subflow->node, &msk->conn_list);
 	sock_hold(ssk);
 
 	/* new mpc subflow takes ownership of the newly
@@ -3238,6 +3293,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	__mptcp_propagate_sndbuf(nsk, ssk);
 
 	mptcp_rcv_space_init(msk, ssk);
+
+	if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+		__mptcp_subflow_fully_established(msk, subflow, mp_opt);
 	bh_unlock_sock(nsk);
 
 	/* note: the newly allocated socket refcount is 2 now */
@@ -3248,6 +3306,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 {
 	const struct tcp_sock *tp = tcp_sk(ssk);
 
+	msk->rcvspace_init = 1;
 	msk->rcvq_space.copied = 0;
 	msk->rcvq_space.rtt_us = 0;
 
@@ -3258,8 +3317,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
-	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3333,8 +3390,7 @@ static void mptcp_release_cb(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	for (;;) {
-		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
-				      msk->push_pending;
+		unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
 		struct list_head join_list;
 
 		if (!flags)
@@ -3350,7 +3406,6 @@ static void mptcp_release_cb(struct sock *sk)
 		 *    datapath acquires the msk socket spinlock while helding
 		 *    the subflow socket lock
 		 */
-		msk->push_pending = 0;
 		msk->cb_flags &= ~flags;
 		spin_unlock_bh(&sk->sk_lock.slock);
 
@@ -3478,13 +3533,8 @@ void mptcp_finish_connect(struct sock *ssk)
 	 * accessing the field below
 	 */
 	WRITE_ONCE(msk->local_key, subflow->local_key);
-	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
-	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
-	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
-
-	mptcp_rcv_space_init(msk, ssk);
 }
 
 void mptcp_sock_graft(struct sock *sk, struct socket *parent)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3517f2d24a22..07f6242afc1a 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -286,7 +286,6 @@ struct mptcp_sock {
 	int		rmem_released;
 	unsigned long	flags;
 	unsigned long	cb_flags;
-	unsigned long	push_pending;
 	bool		recovery;		/* closing subflow write queue reinjected */
 	bool		can_ack;
 	bool		fully_established;
@@ -305,7 +304,8 @@ struct mptcp_sock {
 			nodelay:1,
 			fastopening:1,
 			in_accept_queue:1,
-			free_first:1;
+			free_first:1,
+			rcvspace_init:1;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -491,10 +491,9 @@ struct mptcp_subflow_context {
 		remote_key_valid : 1,        /* received the peer key from */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1, /* local_id is correctly initialized */
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
-		__unused : 9;
+		__unused : 10;
 	bool	data_avail;
 	bool	scheduled;
 	u32	remote_nonce;
@@ -505,7 +504,7 @@ struct mptcp_subflow_context {
 		u8	hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */
 		u64	iasn;	    /* initial ack sequence number, MPC subflows only */
 	};
-	u8	local_id;
+	s16	local_id;	    /* if negative not initialized yet */
 	u8	remote_id;
 	u8	reset_seen:1;
 	u8	reset_transient:1;
@@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow)
 {
 	memset(&subflow->reset, 0, sizeof(subflow->reset));
 	subflow->request_mptcp = 1;
+	WRITE_ONCE(subflow->local_id, -1);
 }
 
 static inline u64
@@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt);
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+				       struct mptcp_subflow_context *subflow,
+				       const struct mptcp_options_received *mp_opt);
 bool __mptcp_retransmit_pending_data(struct sock *sk);
 void mptcp_check_and_set_pending(struct sock *sk);
 void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -789,6 +790,16 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
 	       READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
 }
 
+static inline void mptcp_write_space(struct sock *sk)
+{
+	if (sk_stream_is_writeable(sk)) {
+		/* pairs with memory barrier in mptcp_poll */
+		smp_mb();
+		if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
+			sk_stream_write_space(sk);
+	}
+}
+
 static inline void __mptcp_sync_sndbuf(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -807,6 +818,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk)
 
 	/* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */
 	WRITE_ONCE(sk->sk_sndbuf, new_sndbuf);
+	mptcp_write_space(sk);
 }
 
 /* The called held both the msk socket and the subflow socket locks,
@@ -837,16 +849,6 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
 	local_bh_enable();
 }
 
-static inline void mptcp_write_space(struct sock *sk)
-{
-	if (sk_stream_is_writeable(sk)) {
-		/* pairs with memory barrier in mptcp_poll */
-		smp_mb();
-		if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
-			sk_stream_write_space(sk);
-	}
-}
-
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags);
 
 #define MPTCP_TOKEN_MAX_RETRIES	4
@@ -952,8 +954,8 @@ void mptcp_event_pm_listener(const struct sock *ssk,
 			     enum mptcp_event_type event);
 bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				   const struct mptcp_options_received *mp_opt);
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+				     const struct mptcp_options_received *mp_opt);
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
 					      struct request_sock *req);
 
@@ -1021,6 +1023,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 
+static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
+{
+	int local_id = READ_ONCE(subflow->local_id);
+
+	if (local_id < 0)
+		return 0;
+	return local_id;
+}
+
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_work(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
@@ -1128,7 +1139,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 
-	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
+	return (1 << sk->sk_state) &
+	       (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) &&
 	       is_active_ssk(subflow) &&
 	       !subflow->conn_finished;
 }
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0dcb721c89d1..71ba86246ff8 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -421,29 +421,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 
 void __mptcp_sync_state(struct sock *sk, int state)
 {
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *ssk = msk->first;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	__mptcp_propagate_sndbuf(sk, ssk);
+	if (!msk->rcvspace_init)
+		mptcp_rcv_space_init(msk, ssk);
 
-	__mptcp_propagate_sndbuf(sk, msk->first);
 	if (sk->sk_state == TCP_SYN_SENT) {
+		/* subflow->idsn is always available is TCP_SYN_SENT state,
+		 * even for the FASTOPEN scenarios
+		 */
+		WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+		WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 		mptcp_set_state(sk, state);
 		sk->sk_state_change(sk);
 	}
 }
 
-static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk)) {
-		__mptcp_sync_state(sk, ssk->sk_state);
-	} else {
-		msk->pending_state = ssk->sk_state;
-		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
-	}
-	mptcp_data_unlock(sk);
-}
-
 static void subflow_set_remote_key(struct mptcp_sock *msk,
 				   struct mptcp_subflow_context *subflow,
 				   const struct mptcp_options_received *mp_opt)
@@ -465,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
 	atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
 }
 
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk,
+				  struct mptcp_subflow_context *subflow,
+				  const struct mptcp_options_received *mp_opt)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	mptcp_data_lock(sk);
+	if (mp_opt) {
+		/* Options are available only in the non fallback cases
+		 * avoid updating rx path fields otherwise
+		 */
+		WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+		WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
+		subflow_set_remote_key(msk, subflow, mp_opt);
+	}
+
+	if (!sock_owned_by_user(sk)) {
+		__mptcp_sync_state(sk, ssk->sk_state);
+	} else {
+		msk->pending_state = ssk->sk_state;
+		__set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+	}
+	mptcp_data_unlock(sk);
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -499,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		if (mp_opt.deny_join_id0)
 			WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 		subflow->mp_capable = 1;
-		subflow_set_remote_key(msk, subflow, &mp_opt);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, &mp_opt);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
@@ -514,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->backup = mp_opt.backup;
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
-		subflow->remote_id = mp_opt.join_id;
+		WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
 			 subflow, subflow->thmac, subflow->remote_nonce,
 			 subflow->backup);
@@ -545,8 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		}
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
-		mptcp_rcv_space_init(msk, sk);
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
 	return;
 
@@ -557,8 +577,8 @@ do_reset:
 
 static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
 {
-	subflow->local_id = local_id;
-	subflow->local_id_valid = 1;
+	WARN_ON_ONCE(local_id < 0 || local_id > 255);
+	WRITE_ONCE(subflow->local_id, local_id);
 }
 
 static int subflow_chk_local_id(struct sock *sk)
@@ -567,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	int err;
 
-	if (likely(subflow->local_id_valid))
+	if (likely(subflow->local_id >= 0))
 		return 0;
 
 	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
@@ -731,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
 	kfree_rcu(ctx, rcu);
 }
 
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt)
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+				       struct mptcp_subflow_context *subflow,
+				       const struct mptcp_options_received *mp_opt)
 {
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	subflow->fully_established = 1;
 	WRITE_ONCE(msk->fully_established, true);
 
 	if (subflow->is_mptfo)
-		mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
+		__mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -834,7 +853,6 @@ create_child:
 			 * mpc option
 			 */
 			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
-				mptcp_subflow_fully_established(ctx, &mp_opt);
 				mptcp_pm_fully_established(owner, child);
 				ctx->pm_notified = 1;
 			}
@@ -1549,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
-	subflow->remote_id = remote_id;
+	WRITE_ONCE(subflow->remote_id, remote_id);
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	subflow->subflow_id = msk->subflow_id++;
@@ -1713,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
 	pr_debug("subflow=%p", ctx);
 
 	ctx->tcp_sock = sk;
+	WRITE_ONCE(ctx->local_id, -1);
 
 	return ctx;
 }
@@ -1744,10 +1763,9 @@ static void subflow_state_change(struct sock *sk)
 	msk = mptcp_sk(parent);
 	if (subflow_simultaneous_connect(sk)) {
 		mptcp_do_fallback(sk);
-		mptcp_rcv_space_init(msk, sk);
 		pr_fallback(msk);
 		subflow->conn_finished = 1;
-		mptcp_propagate_state(parent, sk);
+		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
 
 	/* as recvmsg() does not acquire the subflow socket for ssk selection
@@ -1949,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->idsn = subflow_req->idsn;
 
 		/* this is the first subflow, id is always 0 */
-		new_ctx->local_id_valid = 1;
+		subflow_set_local_id(new_ctx, 0);
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
 		new_ctx->fully_established = 1;
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
-		new_ctx->remote_id = subflow_req->remote_id;
+		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
 
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index d4958e7e7631..614815a3ed73 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -101,7 +101,7 @@ endif
 endif
 
 ifdef CONFIG_NFT_CT
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
 nf_tables-objs += nft_ct_fast.o
 endif
 endif
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 21f7860e8fa1..cb48a2b9cb9f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -30,6 +30,7 @@
 #define mtype_del		IPSET_TOKEN(MTYPE, _del)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype			MTYPE
 
 #define get_ext(set, map, id)	((map)->extensions + ((set)->dsize * (id)))
@@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set)
 {
 	struct mtype *map = set->data;
 
-	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&map->gc);
-
 	if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
 	ip_set_free(map->members);
@@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t)
 	add_timer(&map->gc);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct mtype *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		del_timer_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant mtype = {
 	.kadt	= mtype_kadt,
 	.uadt	= mtype_uadt,
@@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = {
 	.head	= mtype_head,
 	.list	= mtype_list,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 };
 
 #endif /* __IP_SET_BITMAP_IP_GEN_H */
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 4c133e06be1d..3184cc6be4c9 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info,
 	return ret;
 
 cleanup:
+	set->variant->cancel_gc(set);
 	set->variant->destroy(set);
 put_out:
 	module_put(set->type->me);
@@ -1182,6 +1183,14 @@ ip_set_destroy_set(struct ip_set *set)
 	kfree(set);
 }
 
+static void
+ip_set_destroy_set_rcu(struct rcu_head *head)
+{
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
+
+	ip_set_destroy_set(set);
+}
+
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			  const struct nlattr * const attr[])
 {
@@ -1193,8 +1202,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* Must wait for flush to be really finished in list:set */
-	rcu_barrier();
 
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
@@ -1206,8 +1213,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * counter, so if it's already zero, we can proceed
 	 * without holding the lock.
 	 */
-	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
+		/* Must wait for flush to be really finished in list:set */
+		rcu_barrier();
+		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
 			if (s && (s->ref || s->ref_netlink)) {
@@ -1221,6 +1230,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			s = ip_set(inst, i);
 			if (s) {
 				ip_set(inst, i) = NULL;
+				/* Must cancel garbage collectors */
+				s->variant->cancel_gc(s);
 				ip_set_destroy_set(s);
 			}
 		}
@@ -1228,6 +1239,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		inst->is_destroyed = false;
 	} else {
 		u32 flags = flag_exist(info->nlh);
+		u16 features = 0;
+
+		read_lock_bh(&ip_set_ref_lock);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
@@ -1238,10 +1252,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			ret = -IPSET_ERR_BUSY;
 			goto out;
 		}
+		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
-
-		ip_set_destroy_set(s);
+		if (features & IPSET_TYPE_NAME) {
+			/* Must wait for flush to be really finished  */
+			rcu_barrier();
+		}
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
+		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
 out:
@@ -1394,9 +1414,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
-	/* Make sure all readers of the old set pointers are completed. */
-	synchronize_rcu();
-
 	return 0;
 }
 
@@ -2362,6 +2379,7 @@ ip_set_net_exit(struct net *net)
 		set = ip_set(inst, i);
 		if (set) {
 			ip_set(inst, i) = NULL;
+			set->variant->cancel_gc(set);
 			ip_set_destroy_set(set);
 		}
 	}
@@ -2409,8 +2427,11 @@ ip_set_fini(void)
 {
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-
 	unregister_pernet_subsys(&ip_set_net_ops);
+
+	/* Wait for call_rcu() in destroy */
+	rcu_barrier();
+
 	pr_debug("these are the famous last words\n");
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cbf80da9a01c..cf3ce72c3de6 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {};
 #undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
+#undef mtype_cancel_gc
 #undef mtype_variant
 #undef mtype_data_match
 
@@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {};
 #define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
 #define mtype_data_match	IPSET_TOKEN(MTYPE, _data_match)
 
@@ -430,7 +432,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
 	u32 i;
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = __ipset_dereference(hbucket(t, i));
+		n = (__force struct hbucket *)hbucket(t, i);
 		if (!n)
 			continue;
 		if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -450,10 +452,7 @@ mtype_destroy(struct ip_set *set)
 	struct htype *h = set->data;
 	struct list_head *l, *lt;
 
-	if (SET_WITH_TIMEOUT(set))
-		cancel_delayed_work_sync(&h->gc.dwork);
-
-	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+	mtype_ahash_destroy(set, (__force struct htable *)h->table, true);
 	list_for_each_safe(l, lt, &h->ad) {
 		list_del(l);
 		kfree(l);
@@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc)
 	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct htype *h = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		cancel_delayed_work_sync(&h->gc.dwork);
+}
+
 static int
 mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	  struct ip_set_ext *mext, u32 flags);
@@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = {
 	.uref	= mtype_uref,
 	.resize	= mtype_resize,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 	.region_lock = true,
 };
 
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e162636525cf..6c3f28bc59b3 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set)
 	struct list_set *map = set->data;
 	struct set_elem *e, *n;
 
-	if (SET_WITH_TIMEOUT(set))
-		timer_shutdown_sync(&map->gc);
-
 	list_for_each_entry_safe(e, n, &map->members, list) {
 		list_del(&e->list);
 		ip_set_put_byindex(map->net, e->id);
@@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
+static void
+list_set_cancel_gc(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		timer_shutdown_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant set_variant = {
 	.kadt	= list_set_kadt,
 	.uadt	= list_set_uadt,
@@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = {
 	.head	= list_set_head,
 	.list	= list_set_list,
 	.same_set = list_set_same_set,
+	.cancel_gc = list_set_cancel_gc,
 };
 
 static void
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 2e5f3864d353..5b876fa7f9af 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2756,6 +2756,7 @@ static const struct nf_ct_hook nf_conntrack_hook = {
 	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 	.attach		= nf_conntrack_attach,
 	.set_closing	= nf_conntrack_set_closing,
+	.confirm	= __nf_conntrack_confirm,
 };
 
 void nf_conntrack_init_end(void)
diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index e697a824b001..540d97715bd2 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f,
 	/* Get fields bitmap */
 	if (nf_h323_error_boundary(bs, 0, f->sz))
 		return H323_ERROR_BOUND;
+	if (f->sz > 32)
+		return H323_ERROR_RANGE;
 	bmp = get_bitmap(bs, f->sz);
 	if (base)
 		*(unsigned int *)base = bmp;
@@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f,
 	bmp2_len = get_bits(bs, 7) + 1;
 	if (nf_h323_error_boundary(bs, 0, bmp2_len))
 		return H323_ERROR_BOUND;
+	if (bmp2_len > 32)
+		return H323_ERROR_RANGE;
 	bmp2 = get_bitmap(bs, bmp2_len);
 	bmp |= bmp2 >> f->sz;
 	if (base)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0c22a02c2035..3b846cbdc050 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -876,6 +876,7 @@ struct ctnetlink_filter_u32 {
 
 struct ctnetlink_filter {
 	u8 family;
+	bool zone_filter;
 
 	u_int32_t orig_flags;
 	u_int32_t reply_flags;
@@ -992,9 +993,12 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 	if (err)
 		goto err_filter;
 
-	err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
-	if (err < 0)
-		goto err_filter;
+	if (cda[CTA_ZONE]) {
+		err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
+		if (err < 0)
+			goto err_filter;
+		filter->zone_filter = true;
+	}
 
 	if (!cda[CTA_FILTER])
 		return filter;
@@ -1148,7 +1152,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	if (filter->family && nf_ct_l3num(ct) != filter->family)
 		goto ignore_entry;
 
-	if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID &&
+	if (filter->zone_filter &&
 	    !nf_ct_zone_equal_any(ct, &filter->zone))
 		goto ignore_entry;
 
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c6bd533983c1..4cc97f971264 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -283,7 +283,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			pr_debug("Setting vtag %x for secondary conntrack\n",
 				 sh->vtag);
 			ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
-		} else {
+		} else if (sch->type == SCTP_CID_SHUTDOWN_ACK) {
 		/* If it is a shutdown ack OOTB packet, we expect a return
 		   shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */
 			pr_debug("Setting vtag %x for new conn OOTB\n",
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e573be5afde7..ae493599a3ef 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 			    const struct sk_buff *skb,
 			    unsigned int dataoff,
 			    const struct tcphdr *tcph,
-			    u32 end, u32 win)
+			    u32 end, u32 win,
+			    enum ip_conntrack_dir dir)
 {
 	/* SYN-ACK in reply to a SYN
 	 * or SYN from reply direction in simultaneous open.
@@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 	 * Both sides must send the Window Scale option
 	 * to enable window scaling in either direction.
 	 */
-	if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
+	if (dir == IP_CT_DIR_REPLY &&
+	    !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
 	      receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) {
 		sender->td_scale = 0;
 		receiver->td_scale = 0;
@@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		if (tcph->syn) {
 			tcp_init_sender(sender, receiver,
 					skb, dataoff, tcph,
-					end, win);
+					end, win, dir);
 			if (!tcph->ack)
 				/* Simultaneous open */
 				return NFCT_TCP_ACCEPT;
@@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		 */
 		tcp_init_sender(sender, receiver,
 				skb, dataoff, tcph,
-				end, win);
+				end, win, dir);
 
 		if (dir == IP_CT_DIR_REPLY && !tcph->ack)
 			return NFCT_TCP_ACCEPT;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 920a5a29ae1d..a0571339239c 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple)
 	return 0;
 }
 
+static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route,
+					     enum flow_offload_tuple_dir dir)
+{
+	struct dst_entry *dst = route->tuple[dir].dst;
+
+	route->tuple[dir].dst = NULL;
+
+	return dst;
+}
+
 static int flow_offload_fill_route(struct flow_offload *flow,
-				   const struct nf_flow_route *route,
+				   struct nf_flow_route *route,
 				   enum flow_offload_tuple_dir dir)
 {
 	struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple;
-	struct dst_entry *dst = route->tuple[dir].dst;
+	struct dst_entry *dst = nft_route_dst_fetch(route, dir);
 	int i, j = 0;
 
 	switch (flow_tuple->l3proto) {
@@ -122,6 +132,7 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 		       ETH_ALEN);
 		flow_tuple->out.ifidx = route->tuple[dir].out.ifindex;
 		flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex;
+		dst_release(dst);
 		break;
 	case FLOW_OFFLOAD_XMIT_XFRM:
 	case FLOW_OFFLOAD_XMIT_NEIGH:
@@ -146,7 +157,7 @@ static void nft_flow_dst_release(struct flow_offload *flow,
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
-			    const struct nf_flow_route *route)
+			     struct nf_flow_route *route)
 {
 	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
 	flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 8cc52d2bd31b..e16f158388bb 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type)
 		return;
 	}
 
-	BUG_ON(loggers[pf][type] == NULL);
-
 	rcu_read_lock();
 	logger = rcu_dereference(loggers[pf][type]);
-	module_put(logger->me);
+	if (!logger)
+		WARN_ON_ONCE(1);
+	else
+		module_put(logger->me);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_logger_put);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index c3d7ecbc777c..016c816d91cb 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 find_free_id:
 	if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
 		off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
-	else
+	else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) ||
+		 maniptype != NF_NAT_MANIP_DST)
 		off = get_random_u16();
+	else
+		off = 0;
 
 	attempts = range_size;
 	if (attempts > NF_NAT_MAX_ATTEMPTS)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c537104411e7..1683dc196b59 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -684,15 +684,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
 	return err;
 }
 
-static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
-				   struct nft_flowtable *flowtable)
+static struct nft_trans *
+nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
+		        struct nft_flowtable *flowtable)
 {
 	struct nft_trans *trans;
 
 	trans = nft_trans_alloc(ctx, msg_type,
 				sizeof(struct nft_trans_flowtable));
 	if (trans == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	if (msg_type == NFT_MSG_NEWFLOWTABLE)
 		nft_activate_next(ctx->net, flowtable);
@@ -701,22 +702,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
 	nft_trans_flowtable(trans) = flowtable;
 	nft_trans_commit_list_add_tail(ctx->net, trans);
 
-	return 0;
+	return trans;
 }
 
 static int nft_delflowtable(struct nft_ctx *ctx,
 			    struct nft_flowtable *flowtable)
 {
-	int err;
+	struct nft_trans *trans;
 
-	err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable);
-	if (err < 0)
-		return err;
+	trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
 	nft_deactivate_next(ctx->net, flowtable);
 	nft_use_dec(&ctx->table->use);
 
-	return err;
+	return 0;
 }
 
 static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg)
@@ -1251,6 +1252,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 	return 0;
 
 err_register_hooks:
+	ctx->table->flags |= NFT_TABLE_F_DORMANT;
 	nft_trans_destroy(trans);
 	return ret;
 }
@@ -2080,7 +2082,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 	struct nft_hook *hook;
 	int err;
 
-	hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT);
+	hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT);
 	if (!hook) {
 		err = -ENOMEM;
 		goto err_hook_alloc;
@@ -2503,19 +2505,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	RCU_INIT_POINTER(chain->blob_gen_0, blob);
 	RCU_INIT_POINTER(chain->blob_gen_1, blob);
 
-	err = nf_tables_register_hook(net, table, chain);
-	if (err < 0)
-		goto err_destroy_chain;
-
 	if (!nft_use_inc(&table->use)) {
 		err = -EMFILE;
-		goto err_use;
+		goto err_destroy_chain;
 	}
 
 	trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-		goto err_unregister_hook;
+		goto err_trans;
 	}
 
 	nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET;
@@ -2523,17 +2521,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		nft_trans_chain_policy(trans) = policy;
 
 	err = nft_chain_add(table, chain);
-	if (err < 0) {
-		nft_trans_destroy(trans);
-		goto err_unregister_hook;
-	}
+	if (err < 0)
+		goto err_chain_add;
+
+	/* This must be LAST to ensure no packets are walking over this chain. */
+	err = nf_tables_register_hook(net, table, chain);
+	if (err < 0)
+		goto err_register_hook;
 
 	return 0;
 
-err_unregister_hook:
+err_register_hook:
+	nft_chain_del(chain);
+err_chain_add:
+	nft_trans_destroy(trans);
+err_trans:
 	nft_use_dec_restore(&table->use);
-err_use:
-	nf_tables_unregister_hook(net, table, chain);
 err_destroy_chain:
 	nf_tables_chain_destroy(ctx);
 
@@ -4998,6 +5001,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) ==
 			     (NFT_SET_EVAL | NFT_SET_OBJECT))
 			return -EOPNOTSUPP;
+		if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) ==
+			     (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT))
+			return -EOPNOTSUPP;
+		if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) ==
+			     (NFT_SET_CONSTANT | NFT_SET_TIMEOUT))
+			return -EOPNOTSUPP;
 	}
 
 	desc.dtype = 0;
@@ -5421,6 +5430,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 
 	if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
 		list_del_rcu(&set->list);
+		set->dead = 1;
 		if (event)
 			nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
 					     GFP_KERNEL);
@@ -7551,11 +7561,15 @@ nla_put_failure:
 	return -1;
 }
 
-static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
+static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
 	list_for_each_entry(type, &nf_tables_objects, list) {
+		if (type->family != NFPROTO_UNSPEC &&
+		    type->family != family)
+			continue;
+
 		if (objtype == type->type)
 			return type;
 	}
@@ -7563,11 +7577,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
 }
 
 static const struct nft_object_type *
-nft_obj_type_get(struct net *net, u32 objtype)
+nft_obj_type_get(struct net *net, u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
-	type = __nft_obj_type_get(objtype);
+	type = __nft_obj_type_get(objtype, family);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
@@ -7660,7 +7674,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		type = __nft_obj_type_get(objtype);
+		type = __nft_obj_type_get(objtype, family);
 		if (WARN_ON_ONCE(!type))
 			return -ENOENT;
 
@@ -7674,7 +7688,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 	if (!nft_use_inc(&table->use))
 		return -EMFILE;
 
-	type = nft_obj_type_get(net, objtype);
+	type = nft_obj_type_get(net, objtype, family);
 	if (IS_ERR(type)) {
 		err = PTR_ERR(type);
 		goto err_type;
@@ -8451,9 +8465,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 	u8 family = info->nfmsg->nfgen_family;
 	const struct nf_flowtable_type *type;
 	struct nft_flowtable *flowtable;
-	struct nft_hook *hook, *next;
 	struct net *net = info->net;
 	struct nft_table *table;
+	struct nft_trans *trans;
 	struct nft_ctx ctx;
 	int err;
 
@@ -8533,34 +8547,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 	err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable,
 				       extack, true);
 	if (err < 0)
-		goto err4;
+		goto err_flowtable_parse_hooks;
 
 	list_splice(&flowtable_hook.list, &flowtable->hook_list);
 	flowtable->data.priority = flowtable_hook.priority;
 	flowtable->hooknum = flowtable_hook.num;
 
+	trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto err_flowtable_trans;
+	}
+
+	/* This must be LAST to ensure no packets are walking over this flowtable. */
 	err = nft_register_flowtable_net_hooks(ctx.net, table,
 					       &flowtable->hook_list,
 					       flowtable);
-	if (err < 0) {
-		nft_hooks_destroy(&flowtable->hook_list);
-		goto err4;
-	}
-
-	err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
 	if (err < 0)
-		goto err5;
+		goto err_flowtable_hooks;
 
 	list_add_tail_rcu(&flowtable->list, &table->flowtables);
 
 	return 0;
-err5:
-	list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
-		nft_unregister_flowtable_hook(net, flowtable, hook);
-		list_del_rcu(&hook->list);
-		kfree_rcu(hook, rcu);
-	}
-err4:
+
+err_flowtable_hooks:
+	nft_trans_destroy(trans);
+err_flowtable_trans:
+	nft_hooks_destroy(&flowtable->hook_list);
+err_flowtable_parse_hooks:
 	flowtable->data.type->free(&flowtable->data);
 err3:
 	module_put(type->owner);
@@ -9823,6 +9837,7 @@ dead_elem:
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
 	struct nft_set_elem_catchall *catchall, *next;
+	u64 tstamp = nft_net_tstamp(gc->net);
 	const struct nft_set *set = gc->set;
 	struct nft_elem_priv *elem_priv;
 	struct nft_set_ext *ext;
@@ -9832,7 +9847,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
 
-		if (!nft_set_elem_expired(ext))
+		if (!__nft_set_elem_expired(ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -10618,6 +10633,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
 	bool genid_ok;
 
 	mutex_lock(&nft_net->commit_mutex);
+	nft_net->tstamp = get_jiffies_64();
 
 	genid_ok = genid == 0 || nft_net->base_seq == genid;
 	if (!genid_ok)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index c3e635364701..a48d5f0e2f3e 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -21,7 +21,7 @@
 #include <net/netfilter/nf_log.h>
 #include <net/netfilter/nft_meta.h>
 
-#if defined(CONFIG_RETPOLINE) && defined(CONFIG_X86)
+#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_X86)
 
 static struct static_key_false nf_tables_skip_direct_calls;
 
@@ -207,7 +207,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr,
 			       struct nft_regs *regs,
 			       struct nft_pktinfo *pkt)
 {
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	unsigned long e;
 
 	if (nf_skip_indirect_calls())
@@ -236,7 +236,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr,
 	X(e, nft_objref_map_eval);
 #undef  X
 indirect_call:
-#endif /* CONFIG_RETPOLINE */
+#endif /* CONFIG_MITIGATION_RETPOLINE */
 	expr->ops->eval(expr, regs, pkt);
 }
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 171d1f52d3dd..5cf38fc0a366 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -232,18 +232,25 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict)
 	if (verdict == NF_ACCEPT ||
 	    verdict == NF_REPEAT ||
 	    verdict == NF_STOP) {
+		unsigned int ct_verdict = verdict;
+
 		rcu_read_lock();
 		ct_hook = rcu_dereference(nf_ct_hook);
 		if (ct_hook)
-			verdict = ct_hook->update(entry->state.net, entry->skb);
+			ct_verdict = ct_hook->update(entry->state.net, entry->skb);
 		rcu_read_unlock();
 
-		switch (verdict & NF_VERDICT_MASK) {
+		switch (ct_verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+			/* follow userspace verdict, could be REPEAT */
+			break;
 		case NF_STOLEN:
 			nf_queue_entry_free(entry);
 			return;
+		default:
+			verdict = ct_verdict & NF_VERDICT_MASK;
+			break;
 		}
-
 	}
 	nf_reinject(entry, verdict);
 }
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index f0eeda97bfcd..d3d11dede545 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr,
 
 static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
 	[NFTA_TARGET_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_TARGET_REV]	= { .type = NLA_U32 },
+	[NFTA_TARGET_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_TARGET_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1]
 static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 {
 	struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
+	u32 l4proto;
 	u32 flags;
 	int err;
 
@@ -212,12 +213,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 		return -EINVAL;
 
 	flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS]));
-	if (flags & ~NFT_RULE_COMPAT_F_MASK)
+	if (flags & NFT_RULE_COMPAT_F_UNUSED ||
+	    flags & ~NFT_RULE_COMPAT_F_MASK)
 		return -EINVAL;
 	if (flags & NFT_RULE_COMPAT_F_INV)
 		*inv = true;
 
-	*proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+	if (l4proto > U16_MAX)
+		return -EINVAL;
+
+	*proto = l4proto;
+
 	return 0;
 }
 
@@ -352,10 +359,20 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
 	    ctx->family != NFPROTO_BRIDGE &&
 	    ctx->family != NFPROTO_ARP)
 		return -EOPNOTSUPP;
 
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -419,7 +436,7 @@ static void nft_match_eval(const struct nft_expr *expr,
 
 static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
 	[NFTA_MATCH_NAME]	= { .type = NLA_NUL_STRING },
-	[NFTA_MATCH_REV]	= { .type = NLA_U32 },
+	[NFTA_MATCH_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_MATCH_INFO]	= { .type = NLA_BINARY },
 };
 
@@ -603,10 +620,20 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
 	    ctx->family != NFPROTO_BRIDGE &&
 	    ctx->family != NFPROTO_ARP)
 		return -EOPNOTSUPP;
 
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -724,7 +751,7 @@ out_put:
 static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = {
 	[NFTA_COMPAT_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = NFT_COMPAT_NAME_MAX-1 },
-	[NFTA_COMPAT_REV]	= { .type = NLA_U32 },
+	[NFTA_COMPAT_REV]	= NLA_POLICY_MAX(NLA_BE32, 255),
 	[NFTA_COMPAT_TYPE]	= { .type = NLA_U32 },
 };
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 86bb9d7797d9..452ed94c3a4d 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -476,6 +476,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 		break;
 #endif
 	case NFT_CT_ID:
+		if (tb[NFTA_CT_DIRECTION])
+			return -EINVAL;
+
 		len = sizeof(u32);
 		break;
 	default:
@@ -751,7 +754,7 @@ static bool nft_ct_set_reduce(struct nft_regs_track *track,
 	return false;
 }
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 static const struct nft_expr_ops nft_ct_get_fast_ops = {
 	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
@@ -796,7 +799,7 @@ nft_ct_select_ops(const struct nft_ctx *ctx,
 		return ERR_PTR(-EINVAL);
 
 	if (tb[NFTA_CT_DREG]) {
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 		u32 k = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 
 		switch (k) {
@@ -1250,7 +1253,30 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_CT_EXPECT_L3PROTO])
 		priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO]));
 
+	switch (priv->l3num) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+		if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET)
+			break;
+
+		return -EINVAL;
+	case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */
+	default:
+		return -EAFNOSUPPORT;
+	}
+
 	priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]);
+	switch (priv->l4proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+	case IPPROTO_DCCP:
+	case IPPROTO_SCTP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
 	priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 397351fa4d5f..ab9576098701 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 		ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
 	}
 
+	__set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
 	ret = flow_offload_add(flowtable, flow);
 	if (ret < 0)
 		goto err_flow_add;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 870e5b113d13..a0055f510e31 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -24,7 +24,7 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 bool nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key, const struct nft_set_ext **ext)
 {
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6c2061bfdae6..6968a3b34236 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg {
 	const struct nft_set		*set;
 	const u32			*key;
 	u8				genmask;
+	u64				tstamp;
 };
 
 static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
@@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
 		return 1;
 	if (nft_set_elem_is_dead(&he->ext))
 		return 1;
-	if (nft_set_elem_expired(&he->ext))
+	if (__nft_set_elem_expired(&he->ext, x->tstamp))
 		return 1;
 	if (!nft_set_elem_active(&he->ext, x->genmask))
 		return 1;
@@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_cur(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 		.genmask = NFT_GENMASK_ANY,
 		.set	 = set,
 		.key	 = key,
+		.tstamp  = get_jiffies_64(),
 	};
 
 	he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 	struct nft_rhash_elem *prev;
 
@@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set,
 		.genmask = nft_genmask_next(net),
 		.set	 = set,
 		.key	 = elem->key.val.data,
+		.tstamp	 = nft_net_tstamp(net),
 	};
 
 	rcu_read_lock();
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index efd523496be4..aa1d9e93a9a0 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -342,9 +342,6 @@
 #include "nft_set_pipapo_avx2.h"
 #include "nft_set_pipapo.h"
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
-
 /**
  * pipapo_refill() - For each set bit, set bits from selected mapping table item
  * @map:	Bitmap to be scanned for set bits
@@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		       const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
+	struct nft_pipapo_scratch *scratch;
 	unsigned long *res_map, *fill_map;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
@@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 
 	local_bh_disable();
 
-	map_index = raw_cpu_read(nft_pipapo_scratch_index);
-
 	m = rcu_dereference(priv->match);
 
 	if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
 		goto out;
 
-	res_map  = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0);
-	fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max);
+	scratch = *raw_cpu_ptr(m->scratch);
+
+	map_index = scratch->map_index;
+
+	res_map  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
 
@@ -460,7 +460,7 @@ next_match:
 		b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
 				  last);
 		if (b < 0) {
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return false;
@@ -477,7 +477,7 @@ next_match:
 			 * current inactive bitmap is clean and can be reused as
 			 * *next* bitmap (not initial) for the next packet.
 			 */
-			raw_cpu_write(nft_pipapo_scratch_index, map_index);
+			scratch->map_index = map_index;
 			local_bh_enable();
 
 			return true;
@@ -504,6 +504,7 @@ out:
  * @set:	nftables API set representation
  * @data:	Key data to be matched against existing elements
  * @genmask:	If set, check that element is active in given genmask
+ * @tstamp:	timestamp to check for expired elements
  *
  * This is essentially the same as the lookup function, except that it matches
  * key data against the uncommitted copy and doesn't use preallocated maps for
@@ -513,7 +514,8 @@ out:
  */
 static struct nft_pipapo_elem *pipapo_get(const struct net *net,
 					  const struct nft_set *set,
-					  const u8 *data, u8 genmask)
+					  const u8 *data, u8 genmask,
+					  u64 tstamp)
 {
 	struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
 	struct nft_pipapo *priv = nft_set_priv(set);
@@ -566,7 +568,7 @@ next_match:
 			goto out;
 
 		if (last) {
-			if (nft_set_elem_expired(&f->mt[b].e->ext))
+			if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
 				goto next_match;
 			if ((genmask &&
 			     !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
@@ -603,10 +605,10 @@ static struct nft_elem_priv *
 nft_pipapo_get(const struct net *net, const struct nft_set *set,
 	       const struct nft_set_elem *elem, unsigned int flags)
 {
-	static struct nft_pipapo_elem *e;
+	struct nft_pipapo_elem *e;
 
 	e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
-		       nft_genmask_cur(net));
+		       nft_genmask_cur(net), get_jiffies_64());
 	if (IS_ERR(e))
 		return ERR_CAST(e);
 
@@ -1109,6 +1111,25 @@ static void pipapo_map(struct nft_pipapo_match *m,
 }
 
 /**
+ * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address
+ * @m:		Matching data
+ * @cpu:	CPU number
+ */
+static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu)
+{
+	struct nft_pipapo_scratch *s;
+	void *mem;
+
+	s = *per_cpu_ptr(m->scratch, cpu);
+	if (!s)
+		return;
+
+	mem = s;
+	mem -= s->align_off;
+	kfree(mem);
+}
+
+/**
  * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results
  * @clone:	Copy of matching data with pending insertions and deletions
  * @bsize_max:	Maximum bucket size, scratch maps cover two buckets
@@ -1121,12 +1142,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 	int i;
 
 	for_each_possible_cpu(i) {
-		unsigned long *scratch;
+		struct nft_pipapo_scratch *scratch;
 #ifdef NFT_PIPAPO_ALIGN
-		unsigned long *scratch_aligned;
+		void *scratch_aligned;
+		u32 align_off;
 #endif
-
-		scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 +
+		scratch = kzalloc_node(struct_size(scratch, map,
+						   bsize_max * 2) +
 				       NFT_PIPAPO_ALIGN_HEADROOM,
 				       GFP_KERNEL, cpu_to_node(i));
 		if (!scratch) {
@@ -1140,14 +1162,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 			return -ENOMEM;
 		}
 
-		kfree(*per_cpu_ptr(clone->scratch, i));
-
-		*per_cpu_ptr(clone->scratch, i) = scratch;
+		pipapo_free_scratch(clone, i);
 
 #ifdef NFT_PIPAPO_ALIGN
-		scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch);
-		*per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
+		/* Align &scratch->map (not the struct itself): the extra
+		 * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
+		 * above guarantee we can waste up to those bytes in order
+		 * to align the map field regardless of its offset within
+		 * the struct.
+		 */
+		BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM);
+
+		scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
+		scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
+		align_off = scratch_aligned - (void *)scratch;
+
+		scratch = scratch_aligned;
+		scratch->align_off = align_off;
 #endif
+		*per_cpu_ptr(clone->scratch, i) = scratch;
 	}
 
 	return 0;
@@ -1173,6 +1206,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo_match *m = priv->clone;
 	u8 genmask = nft_genmask_next(net);
 	struct nft_pipapo_elem *e, *dup;
+	u64 tstamp = nft_net_tstamp(net);
 	struct nft_pipapo_field *f;
 	const u8 *start_p, *end_p;
 	int i, bsize_max, err = 0;
@@ -1182,7 +1216,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 	else
 		end = start;
 
-	dup = pipapo_get(net, set, start, genmask);
+	dup = pipapo_get(net, set, start, genmask, tstamp);
 	if (!IS_ERR(dup)) {
 		/* Check if we already have the same exact entry */
 		const struct nft_data *dup_key, *dup_end;
@@ -1204,7 +1238,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
 	if (PTR_ERR(dup) == -ENOENT) {
 		/* Look for partially overlapping entries */
-		dup = pipapo_get(net, set, end, nft_genmask_next(net));
+		dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp);
 	}
 
 	if (PTR_ERR(dup) != -ENOENT) {
@@ -1301,11 +1335,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	if (!new->scratch)
 		goto out_scratch;
 
-#ifdef NFT_PIPAPO_ALIGN
-	new->scratch_aligned = alloc_percpu(*new->scratch_aligned);
-	if (!new->scratch_aligned)
-		goto out_scratch;
-#endif
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(new->scratch, i) = NULL;
 
@@ -1357,10 +1386,7 @@ out_lt:
 	}
 out_scratch_realloc:
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(new->scratch, i));
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(new->scratch_aligned);
-#endif
+		pipapo_free_scratch(new, i);
 out_scratch:
 	free_percpu(new->scratch);
 	kfree(new);
@@ -1560,6 +1586,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	int rules_f0, first_rule = 0;
 	struct nft_pipapo_elem *e;
 	struct nft_trans_gc *gc;
@@ -1594,7 +1621,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		/* synchronous gc never fails, there is no need to set on
 		 * NFT_SET_ELEM_DEAD_BIT.
 		 */
-		if (nft_set_elem_expired(&e->ext)) {
+		if (__nft_set_elem_expired(&e->ext, tstamp)) {
 			priv->dirty = true;
 
 			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -1640,13 +1667,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
 	int i;
 
 	for_each_possible_cpu(i)
-		kfree(*per_cpu_ptr(m->scratch, i));
+		pipapo_free_scratch(m, i);
 
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
-
 	pipapo_free_fields(m);
 
 	kfree(m);
@@ -1769,7 +1792,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
 {
 	struct nft_pipapo_elem *e;
 
-	e = pipapo_get(net, set, data, nft_genmask_next(net));
+	e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net));
 	if (IS_ERR(e))
 		return NULL;
 
@@ -2132,7 +2155,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 	m->field_count = field_count;
 	m->bsize_max = 0;
 
-	m->scratch = alloc_percpu(unsigned long *);
+	m->scratch = alloc_percpu(struct nft_pipapo_scratch *);
 	if (!m->scratch) {
 		err = -ENOMEM;
 		goto out_scratch;
@@ -2140,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	for_each_possible_cpu(i)
 		*per_cpu_ptr(m->scratch, i) = NULL;
 
-#ifdef NFT_PIPAPO_ALIGN
-	m->scratch_aligned = alloc_percpu(unsigned long *);
-	if (!m->scratch_aligned) {
-		err = -ENOMEM;
-		goto out_free;
-	}
-	for_each_possible_cpu(i)
-		*per_cpu_ptr(m->scratch_aligned, i) = NULL;
-#endif
-
 	rcu_head_init(&m->rcu);
 
 	nft_pipapo_for_each_field(f, i, m) {
@@ -2180,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set,
 	return 0;
 
 out_free:
-#ifdef NFT_PIPAPO_ALIGN
-	free_percpu(m->scratch_aligned);
-#endif
 	free_percpu(m->scratch);
 out_scratch:
 	kfree(m);
@@ -2236,11 +2246,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 
 		nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(m->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(m->scratch, cpu));
+			pipapo_free_scratch(m, cpu);
 		free_percpu(m->scratch);
 		pipapo_free_fields(m);
 		kfree(m);
@@ -2253,11 +2260,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 		if (priv->dirty)
 			nft_set_pipapo_match_destroy(ctx, set, m);
 
-#ifdef NFT_PIPAPO_ALIGN
-		free_percpu(priv->clone->scratch_aligned);
-#endif
 		for_each_possible_cpu(cpu)
-			kfree(*per_cpu_ptr(priv->clone->scratch, cpu));
+			pipapo_free_scratch(priv->clone, cpu);
 		free_percpu(priv->clone->scratch);
 
 		pipapo_free_fields(priv->clone);
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 1040223da5fa..3842c7341a9f 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -131,20 +131,28 @@ struct nft_pipapo_field {
 };
 
 /**
+ * struct nft_pipapo_scratch - percpu data used for lookup and matching
+ * @map_index:	Current working bitmap index, toggled between field matches
+ * @align_off:	Offset to get the originally allocated address
+ * @map:	store partial matching results during lookup
+ */
+struct nft_pipapo_scratch {
+	u8 map_index;
+	u32 align_off;
+	unsigned long map[];
+};
+
+/**
  * struct nft_pipapo_match - Data used for lookup and matching
- * @field_count		Amount of fields in set
+ * @field_count:	Amount of fields in set
  * @scratch:		Preallocated per-CPU maps for partial matching results
- * @scratch_aligned:	Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
  * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
- * @rcu			Matching data is swapped on commits
+ * @rcu:		Matching data is swapped on commits
  * @f:			Fields, with lookup and mapping tables
  */
 struct nft_pipapo_match {
 	int field_count;
-#ifdef NFT_PIPAPO_ALIGN
-	unsigned long * __percpu *scratch_aligned;
-#endif
-	unsigned long * __percpu *scratch;
+	struct nft_pipapo_scratch * __percpu *scratch;
 	size_t bsize_max;
 	struct rcu_head rcu;
 	struct nft_pipapo_field f[] __counted_by(field_count);
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 52e0d026d30a..a3a8ddca9918 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -57,7 +57,7 @@
 
 /* Jump to label if @reg is zero */
 #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label)			\
-	asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
+	asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";"	\
 			  "je %l[" #label "]" : : : : label)
 
 /* Store 256 bits from YMM register into memory. Contrary to bucket load
@@ -71,9 +71,6 @@
 #define NFT_PIPAPO_AVX2_ZERO(reg)					\
 	asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg)
 
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index);
-
 /**
  * nft_pipapo_avx2_prepare() - Prepare before main algorithm body
  *
@@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 			    const u32 *key, const struct nft_set_ext **ext)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	unsigned long *res, *fill, *scratch;
+	struct nft_pipapo_scratch *scratch;
 	u8 genmask = nft_genmask_cur(net);
 	const u8 *rp = (const u8 *)key;
 	struct nft_pipapo_match *m;
 	struct nft_pipapo_field *f;
+	unsigned long *res, *fill;
 	bool map_index;
 	int i, ret = 0;
 
@@ -1141,15 +1139,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	 */
 	kernel_fpu_begin_mask(0);
 
-	scratch = *raw_cpu_ptr(m->scratch_aligned);
+	scratch = *raw_cpu_ptr(m->scratch);
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
 		return false;
 	}
-	map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index);
 
-	res  = scratch + (map_index ? m->bsize_max : 0);
-	fill = scratch + (map_index ? 0 : m->bsize_max);
+	map_index = scratch->map_index;
+
+	res  = scratch->map + (map_index ? m->bsize_max : 0);
+	fill = scratch->map + (map_index ? 0 : m->bsize_max);
 
 	/* Starting map doesn't need to be set for this implementation */
 
@@ -1221,7 +1220,7 @@ next_match:
 
 out:
 	if (i % 2)
-		raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index);
+		scratch->map_index = !map_index;
 	kernel_fpu_end();
 
 	return ret >= 0;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65..9944fe479e53 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -234,7 +234,7 @@ static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set,
 
 static const struct nft_rbtree_elem *
 nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
-		   struct nft_rbtree_elem *rbe, u8 genmask)
+		   struct nft_rbtree_elem *rbe)
 {
 	struct nft_set *set = (struct nft_set *)__set;
 	struct rb_node *prev = rb_prev(&rbe->node);
@@ -253,7 +253,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
 	while (prev) {
 		rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
 		if (nft_rbtree_interval_end(rbe_prev) &&
-		    nft_set_elem_active(&rbe_prev->ext, genmask))
+		    nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY))
 			break;
 
 		prev = rb_prev(prev);
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	/* Descend the tree to search for an existing element greater than the
@@ -360,11 +361,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		/* perform garbage collection to avoid bogus overlap reports
 		 * but skip new elements in this transaction.
 		 */
-		if (nft_set_elem_expired(&rbe->ext) &&
+		if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
 		    nft_set_elem_active(&rbe->ext, cur_genmask)) {
 			const struct nft_rbtree_elem *removed_end;
 
-			removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask);
+			removed_end = nft_rbtree_gc_elem(set, priv, rbe);
 			if (IS_ERR(removed_end))
 				return PTR_ERR(removed_end);
 
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	u8 genmask = nft_genmask_next(net);
+	u64 tstamp = nft_net_tstamp(net);
 	int d;
 
 	while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
-			} else if (nft_set_elem_expired(&rbe->ext)) {
+			} else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
 				break;
 			} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
 				parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+	struct net *net = read_pnet(&set->net);
+	u64 tstamp = nft_net_tstamp(net);
 	struct rb_node *node, *next;
 	struct nft_trans_gc *gc;
-	struct net *net;
 
 	set  = nft_set_container_of(priv);
 	net  = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
 			rbe_end = rbe;
 			continue;
 		}
-		if (!nft_set_elem_expired(&rbe->ext))
+		if (!__nft_set_elem_expired(&rbe->ext, tstamp))
 			continue;
 
 		gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 9f21953c7433..f735d79d8be5 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = {
 
 static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
 	.type		= NFT_OBJECT_TUNNEL,
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_obj_ops,
 	.maxattr	= NFTA_TUNNEL_KEY_MAX,
 	.policy		= nft_tunnel_key_policy,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9c962347cf85..ff315351269f 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group)
 static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
 					   gfp_t gfp_mask)
 {
-	unsigned int len = skb_end_offset(skb);
+	unsigned int len = skb->len;
 	struct sk_buff *new;
 
 	new = alloc_skb(len, gfp_mask);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 0eed00184adf..104a80b75477 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol,
 	nr_init_timers(sk);
 
 	nr->t1     =
-		msecs_to_jiffies(sysctl_netrom_transport_timeout);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout));
 	nr->t2     =
-		msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay));
 	nr->n2     =
-		msecs_to_jiffies(sysctl_netrom_transport_maximum_tries);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries));
 	nr->t4     =
-		msecs_to_jiffies(sysctl_netrom_transport_busy_delay);
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay));
 	nr->idle   =
-		msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout);
-	nr->window = sysctl_netrom_transport_requested_window_size;
+		msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout));
+	nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size);
 
 	nr->bpqext = 1;
 	nr->state  = NR_STATE_0;
@@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 		 * G8PZT's Xrouter which is sending packets with command type 7
 		 * as an extension of the protocol.
 		 */
-		if (sysctl_netrom_reset_circuit &&
+		if (READ_ONCE(sysctl_netrom_reset_circuit) &&
 		    (frametype != NR_RESET || flags != 0))
 			nr_transmit_reset(skb, 1);
 
diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c
index 3aaac4a22b38..2c34389c3ce6 100644
--- a/net/netrom/nr_dev.c
+++ b/net/netrom/nr_dev.c
@@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev,
 	buff[6] |= AX25_SSSID_SPARE;
 	buff    += AX25_ADDR_LEN;
 
-	*buff++ = sysctl_netrom_network_ttl_initialiser;
+	*buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	*buff++ = NR_PROTO_IP;
 	*buff++ = NR_PROTO_IP;
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 2f084b6f69d7..97944db6b5ac 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit)
+		if (READ_ONCE(sysctl_netrom_reset_circuit))
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c
index 44929657f5b7..5e531394a724 100644
--- a/net/netrom/nr_out.c
+++ b/net/netrom/nr_out.c
@@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb)
 	dptr[6] |= AX25_SSSID_SPARE;
 	dptr += AX25_ADDR_LEN;
 
-	*dptr++ = sysctl_netrom_network_ttl_initialiser;
+	*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	if (!nr_route_frame(skb, NULL)) {
 		kfree_skb(skb);
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index baea3cbd76ca..70480869ad1c 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		nr_neigh->digipeat = NULL;
 		nr_neigh->ax25     = NULL;
 		nr_neigh->dev      = dev;
-		nr_neigh->quality  = sysctl_netrom_default_path_quality;
+		nr_neigh->quality  = READ_ONCE(sysctl_netrom_default_path_quality);
 		nr_neigh->locked   = 0;
 		nr_neigh->count    = 0;
 		nr_neigh->number   = nr_neigh_no++;
@@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason)
 	nr_neigh->ax25 = NULL;
 	ax25_cb_put(ax25);
 
-	if (++nr_neigh->failed < sysctl_netrom_link_fails_count) {
+	if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) {
 		nr_neigh_put(nr_neigh);
 		return;
 	}
@@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	if (ax25 != NULL) {
 		ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat,
 				  ax25->ax25_dev->dev, 0,
-				  sysctl_netrom_obsolescence_count_initialiser);
+				  READ_ONCE(sysctl_netrom_obsolescence_count_initialiser));
 		if (ret)
 			return ret;
 	}
@@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 		return ret;
 	}
 
-	if (!sysctl_netrom_routing_control && ax25 != NULL)
+	if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL)
 		return 0;
 
 	/* Its Time-To-Live has expired */
diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c
index e2d2af924cff..c3bbd5880850 100644
--- a/net/netrom/nr_subr.c
+++ b/net/netrom/nr_subr.c
@@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype)
 		*dptr++ = nr->my_id;
 		*dptr++ = frametype;
 		*dptr++ = nr->window;
-		if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser;
+		if (nr->bpqext)
+			*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 		break;
 
 	case NR_DISCREQ:
@@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags)
 	dptr[6] |= AX25_SSSID_SPARE;
 	dptr += AX25_ADDR_LEN;
 
-	*dptr++ = sysctl_netrom_network_ttl_initialiser;
+	*dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser);
 
 	if (mine) {
 		*dptr++ = 0;
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 97348cedb16b..cdad47b140fa 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
 	nci_hci_deallocate(ndev);
+
+	/* drop partial rx data packet if present */
+	if (ndev->rx_data_reassembly)
+		kfree_skb(ndev->rx_data_reassembly);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 88965e2068ac..ebc5728aab4e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -48,6 +48,7 @@ struct ovs_len_tbl {
 
 #define OVS_ATTR_NESTED -1
 #define OVS_ATTR_VARIABLE -2
+#define OVS_COPY_ACTIONS_MAX_DEPTH 16
 
 static bool actions_may_change_flow(const struct nlattr *actions)
 {
@@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci,
-				  u32 mpls_label_count, bool log);
+				  u32 mpls_label_count, bool log,
+				  u32 depth);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 				    const struct sw_flow_key *key,
 				    struct sw_flow_actions **sfa,
 				    __be16 eth_type, __be16 vlan_tci,
-				    u32 mpls_label_count, bool log, bool last)
+				    u32 mpls_label_count, bool log, bool last,
+				    u32 depth)
 {
 	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
 	const struct nlattr *probability, *actions;
@@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
 				     const struct sw_flow_key *key,
 				     struct sw_flow_actions **sfa,
 				     __be16 eth_type, __be16 vlan_tci,
-				     u32 mpls_label_count, bool log)
+				     u32 mpls_label_count, bool log,
+				     u32 depth)
 {
 	const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
 	int start, action_start, err, rem;
@@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
 		return action_start;
 
 	err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
-				     vlan_tci, mpls_label_count, log);
+				     vlan_tci, mpls_label_count, log,
+				     depth + 1);
 	if (err)
 		return err;
 
@@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net,
 				   const struct sw_flow_key *key,
 				   struct sw_flow_actions **sfa,
 				   __be16 eth_type, __be16 vlan_tci,
-				   u32 mpls_label_count, bool log, bool last)
+				   u32 mpls_label_count, bool log, bool last,
+				   u32 depth)
 {
 	int start, err;
 	u32 exec;
@@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net,
 		return err;
 
 	err = __ovs_nla_copy_actions(net, attr, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 	if (err)
 		return err;
 
@@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 					   struct sw_flow_actions **sfa,
 					   __be16 eth_type, __be16 vlan_tci,
 					   u32 mpls_label_count,
-					   bool log, bool last)
+					   bool log, bool last, u32 depth)
 {
 	const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
 	struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
@@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 		return nested_acts_start;
 
 	err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
-				     eth_type, vlan_tci, mpls_label_count, log);
+				     eth_type, vlan_tci, mpls_label_count, log,
+				     depth + 1);
 
 	if (err)
 		return err;
@@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				  const struct sw_flow_key *key,
 				  struct sw_flow_actions **sfa,
 				  __be16 eth_type, __be16 vlan_tci,
-				  u32 mpls_label_count, bool log)
+				  u32 mpls_label_count, bool log,
+				  u32 depth)
 {
 	u8 mac_proto = ovs_key_mac_proto(key);
 	const struct nlattr *a;
 	int rem, err;
 
+	if (depth > OVS_COPY_ACTIONS_MAX_DEPTH)
+		return -EOVERFLOW;
+
 	nla_for_each_nested(a, attr, rem) {
 		/* Expected argument lengths, (u32)-1 for variable length. */
 		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			err = validate_and_copy_sample(net, a, key, sfa,
 						       eth_type, vlan_tci,
 						       mpls_label_count,
-						       log, last);
+						       log, last, depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			err = validate_and_copy_clone(net, a, key, sfa,
 						      eth_type, vlan_tci,
 						      mpls_label_count,
-						      log, last);
+						      log, last, depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 							      eth_type,
 							      vlan_tci,
 							      mpls_label_count,
-							      log, last);
+							      log, last,
+							      depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 		case OVS_ACTION_ATTR_DEC_TTL:
 			err = validate_and_copy_dec_ttl(net, a, key, sfa,
 							eth_type, vlan_tci,
-							mpls_label_count, log);
+							mpls_label_count, log,
+							depth);
 			if (err)
 				return err;
 			skip_copy = true;
@@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 	(*sfa)->orig_len = nla_len(attr);
 	err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
-				     key->eth.vlan.tci, mpls_label_count, log);
+				     key->eth.vlan.tci, mpls_label_count, log,
+				     0);
 	if (err)
 		ovs_nla_free_flow_actions(*sfa);
 
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 3aa50dc7535b..976fe250b509 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -34,10 +34,10 @@ static int pn_ioctl(struct sock *sk, int cmd, int *karg)
 
 	switch (cmd) {
 	case SIOCINQ:
-		lock_sock(sk);
+		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		*karg = skb ? skb->len : 0;
-		release_sock(sk);
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return 0;
 
 	case SIOCPNADDRESOURCE:
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index faba31f2eff2..3dd5f52bc1b5 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len)
 	return 0;
 }
 
+static unsigned int pep_first_packet_length(struct sock *sk)
+{
+	struct pep_sock *pn = pep_sk(sk);
+	struct sk_buff_head *q;
+	struct sk_buff *skb;
+	unsigned int len = 0;
+	bool found = false;
+
+	if (sock_flag(sk, SOCK_URGINLINE)) {
+		q = &pn->ctrlreq_queue;
+		spin_lock_bh(&q->lock);
+		skb = skb_peek(q);
+		if (skb) {
+			len = skb->len;
+			found = true;
+		}
+		spin_unlock_bh(&q->lock);
+	}
+
+	if (likely(!found)) {
+		q = &sk->sk_receive_queue;
+		spin_lock_bh(&q->lock);
+		skb = skb_peek(q);
+		if (skb)
+			len = skb->len;
+		spin_unlock_bh(&q->lock);
+	}
+
+	return len;
+}
+
 static int pep_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	struct pep_sock *pn = pep_sk(sk);
@@ -929,15 +960,7 @@ static int pep_ioctl(struct sock *sk, int cmd, int *karg)
 			break;
 		}
 
-		lock_sock(sk);
-		if (sock_flag(sk, SOCK_URGINLINE) &&
-		    !skb_queue_empty(&pn->ctrlreq_queue))
-			*karg = skb_peek(&pn->ctrlreq_queue)->len;
-		else if (!skb_queue_empty(&sk->sk_receive_queue))
-			*karg = skb_peek(&sk->sk_receive_queue)->len;
-		else
-			*karg = 0;
-		release_sock(sk);
+		*karg = pep_first_packet_length(sk);
 		ret = 0;
 		break;
 
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index fba82d36593a..a4e3c5de998b 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 			kfree(sg);
 		}
 		ret = PTR_ERR(trans_private);
+		/* Trigger connection so that its ready for the next retry */
+		if (ret == -ENODEV)
+			rds_conn_connect_if_down(cp->cp_conn);
 		goto out;
 	}
 
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c71b923764fd..5627f80013f8 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 	struct sock *sk = rds_rs_to_sk(rs);
 	int ret = 0;
 	unsigned long flags;
+	struct rds_incoming *to_drop = NULL;
 
 	write_lock_irqsave(&rs->rs_recv_lock, flags);
 	if (!list_empty(&inc->i_item)) {
@@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
 					      -be32_to_cpu(inc->i_hdr.h_len),
 					      inc->i_hdr.h_dport);
 			list_del_init(&inc->i_item);
-			rds_inc_put(inc);
+			to_drop = inc;
 		}
 	}
 	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
 
+	if (to_drop)
+		rds_inc_put(to_drop);
+
 	rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop);
 	return ret;
 }
@@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs)
 	struct sock *sk = rds_rs_to_sk(rs);
 	struct rds_incoming *inc, *tmp;
 	unsigned long flags;
+	LIST_HEAD(to_drop);
 
 	write_lock_irqsave(&rs->rs_recv_lock, flags);
 	list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) {
 		rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong,
 				      -be32_to_cpu(inc->i_hdr.h_len),
 				      inc->i_hdr.h_dport);
+		list_move(&inc->i_item, &to_drop);
+	}
+	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+
+	list_for_each_entry_safe(inc, tmp, &to_drop, i_item) {
 		list_del_init(&inc->i_item);
 		rds_inc_put(inc);
 	}
-	write_unlock_irqrestore(&rs->rs_recv_lock, flags);
 }
 
 /*
diff --git a/net/rds/send.c b/net/rds/send.c
index 5e57a1581dc6..2899def23865 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1313,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* Parse any control messages the user may have included. */
 	ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct);
-	if (ret) {
-		/* Trigger connection so that its ready for the next retry */
-		if (ret ==  -EAGAIN)
-			rds_conn_connect_if_down(conn);
+	if (ret)
 		goto out;
-	}
 
 	if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) {
 		printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n",
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index dbeb75c29857..7818aae1be8e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -199,11 +199,19 @@ struct rxrpc_host_header {
  */
 struct rxrpc_skb_priv {
 	struct rxrpc_connection *conn;	/* Connection referred to (poke packet) */
-	u16		offset;		/* Offset of data */
-	u16		len;		/* Length of data */
-	u8		flags;
+	union {
+		struct {
+			u16		offset;		/* Offset of data */
+			u16		len;		/* Length of data */
+			u8		flags;
 #define RXRPC_RX_VERIFIED	0x01
-
+		};
+		struct {
+			rxrpc_seq_t	first_ack;	/* First packet in acks table */
+			u8		nr_acks;	/* Number of acks+nacks */
+			u8		nr_nacks;	/* Number of nacks */
+		};
+	};
 	struct rxrpc_host_header hdr;	/* RxRPC packet header from this packet */
 };
 
@@ -510,7 +518,7 @@ struct rxrpc_connection {
 	enum rxrpc_call_completion completion;	/* Completion condition */
 	s32			abort_code;	/* Abort code of connection abort */
 	int			debug_id;	/* debug ID for printks */
-	atomic_t		serial;		/* packet serial number counter */
+	rxrpc_serial_t		tx_serial;	/* Outgoing packet serial number counter */
 	unsigned int		hi_serial;	/* highest serial number received */
 	u32			service_id;	/* Service ID, possibly upgraded */
 	u32			security_level;	/* Security level selected */
@@ -692,11 +700,11 @@ struct rxrpc_call {
 	u8			cong_dup_acks;	/* Count of ACKs showing missing packets */
 	u8			cong_cumul_acks; /* Cumulative ACK count */
 	ktime_t			cong_tstamp;	/* Last time cwnd was changed */
+	struct sk_buff		*cong_last_nack; /* Last ACK with nacks received */
 
 	/* Receive-phase ACK management (ACKs we send). */
 	u8			ackr_reason;	/* reason to ACK */
 	u16			ackr_sack_base;	/* Starting slot in SACK table ring */
-	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
 	rxrpc_seq_t		ackr_window;	/* Base of SACK window */
 	rxrpc_seq_t		ackr_wtop;	/* Base of SACK window */
 	unsigned int		ackr_nr_unacked; /* Number of unacked packets */
@@ -730,7 +738,8 @@ struct rxrpc_call {
 struct rxrpc_ack_summary {
 	u16			nr_acks;		/* Number of ACKs in packet */
 	u16			nr_new_acks;		/* Number of new ACKs in packet */
-	u16			nr_rot_new_acks;	/* Number of rotated new ACKs */
+	u16			nr_new_nacks;		/* Number of new nacks in packet */
+	u16			nr_retained_nacks;	/* Number of nacks retained between ACKs */
 	u8			ack_reason;
 	bool			saw_nacks;		/* Saw NACKs in packet */
 	bool			new_low_nack;		/* T if new low NACK found */
@@ -823,6 +832,20 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb)
 #include <trace/events/rxrpc.h>
 
 /*
+ * Allocate the next serial number on a connection.  0 must be skipped.
+ */
+static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn)
+{
+	rxrpc_serial_t serial;
+
+	serial = conn->tx_serial;
+	if (serial == 0)
+		serial = 1;
+	conn->tx_serial = serial + 1;
+	return serial;
+}
+
+/*
  * af_rxrpc.c
  */
 extern atomic_t rxrpc_n_rx_skbs;
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index e363f21a2014..0f78544d043b 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial,
 	unsigned long expiry = rxrpc_soft_ack_delay;
 	unsigned long now = jiffies, ack_at;
 
-	call->ackr_serial = serial;
-
 	if (rxrpc_soft_ack_delay < expiry)
 		expiry = rxrpc_soft_ack_delay;
 	if (call->peer->srtt_us != 0)
@@ -114,6 +112,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 {
 	struct rxrpc_ackpacket *ack = NULL;
+	struct rxrpc_skb_priv *sp;
 	struct rxrpc_txbuf *txb;
 	unsigned long resend_at;
 	rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
@@ -141,14 +140,15 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
 	 * explicitly NAK'd packets.
 	 */
 	if (ack_skb) {
+		sp = rxrpc_skb(ack_skb);
 		ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
 
-		for (i = 0; i < ack->nAcks; i++) {
+		for (i = 0; i < sp->nr_acks; i++) {
 			rxrpc_seq_t seq;
 
 			if (ack->acks[i] & 1)
 				continue;
-			seq = ntohl(ack->firstPacket) + i;
+			seq = sp->first_ack + i;
 			if (after(txb->seq, transmitted))
 				break;
 			if (after(txb->seq, seq))
@@ -373,7 +373,6 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
 bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	unsigned long now, next, t;
-	rxrpc_serial_t ackr_serial;
 	bool resend = false, expired = false;
 	s32 abort_code;
 
@@ -423,8 +422,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
 	if (time_after_eq(now, t)) {
 		trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
 		cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
-		ackr_serial = xchg(&call->ackr_serial, 0);
-		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial,
+		rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0,
 			       rxrpc_propose_ack_ping_for_lost_ack);
 	}
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0943e54370ba..9fc9a6c3f685 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -686,6 +686,7 @@ static void rxrpc_destroy_call(struct work_struct *work)
 
 	del_timer_sync(&call->timer);
 
+	rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
 	rxrpc_cleanup_ring(call);
 	while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
 					       struct rxrpc_txbuf, call_link))) {
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 95f4bc206b3d..1f251d758cb9 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -95,6 +95,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 
 	_enter("%d", conn->debug_id);
 
+	if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) {
+		if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+				  &pkt.ack, sizeof(pkt.ack)) < 0)
+			return;
+		if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE)
+			return;
+	}
+
 	chan = &conn->channels[channel];
 
 	/* If the last call got moved on whilst we were waiting to run, just
@@ -117,7 +125,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	iov[2].iov_base	= &ack_info;
 	iov[2].iov_len	= sizeof(ack_info);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 
 	pkt.whdr.epoch		= htonl(conn->proto.epoch);
 	pkt.whdr.cid		= htonl(conn->proto.cid | channel);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 92495e73b869..9691de00ade7 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 	}
 
 	cumulative_acks += summary->nr_new_acks;
-	cumulative_acks += summary->nr_rot_new_acks;
 	if (cumulative_acks > 255)
 		cumulative_acks = 255;
 
-	summary->mode = call->cong_mode;
 	summary->cwnd = call->cong_cwnd;
 	summary->ssthresh = call->cong_ssthresh;
 	summary->cumulative_acks = cumulative_acks;
@@ -151,6 +149,7 @@ out_no_clear_ca:
 		cwnd = RXRPC_TX_MAX_WINDOW;
 	call->cong_cwnd = cwnd;
 	call->cong_cumul_acks = cumulative_acks;
+	summary->mode = call->cong_mode;
 	trace_rxrpc_congest(call, summary, acked_serial, change);
 	if (resend)
 		rxrpc_resend(call, skb);
@@ -213,7 +212,6 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
 	list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) {
 		if (before_eq(txb->seq, call->acks_hard_ack))
 			continue;
-		summary->nr_rot_new_acks++;
 		if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) {
 			set_bit(RXRPC_CALL_TX_LAST, &call->flags);
 			rot_last = true;
@@ -254,6 +252,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
 {
 	ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
 
+	if (unlikely(call->cong_last_nack)) {
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	}
+
 	switch (__rxrpc_call_state(call)) {
 	case RXRPC_CALL_CLIENT_SEND_REQUEST:
 	case RXRPC_CALL_CLIENT_AWAIT_REPLY:
@@ -703,6 +706,43 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
 }
 
 /*
+ * Determine how many nacks from the previous ACK have now been satisfied.
+ */
+static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call,
+					      struct rxrpc_ack_summary *summary,
+					      rxrpc_seq_t seq)
+{
+	struct sk_buff *skb = call->cong_last_nack;
+	struct rxrpc_ackpacket ack;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, new_acks = 0, retained_nacks = 0;
+	rxrpc_seq_t old_seq = sp->first_ack;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack);
+
+	if (after_eq(seq, old_seq + sp->nr_acks)) {
+		summary->nr_new_acks += sp->nr_nacks;
+		summary->nr_new_acks += seq - (old_seq + sp->nr_acks);
+		summary->nr_retained_nacks = 0;
+	} else if (seq == old_seq) {
+		summary->nr_retained_nacks = sp->nr_nacks;
+	} else {
+		for (i = 0; i < sp->nr_acks; i++) {
+			if (acks[i] == RXRPC_ACK_TYPE_NACK) {
+				if (before(old_seq + i, seq))
+					new_acks++;
+				else
+					retained_nacks++;
+			}
+		}
+
+		summary->nr_new_acks += new_acks;
+		summary->nr_retained_nacks = retained_nacks;
+	}
+
+	return old_seq + sp->nr_acks;
+}
+
+/*
  * Process individual soft ACKs.
  *
  * Each ACK in the array corresponds to one packet and can be either an ACK or
@@ -711,25 +751,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
  * the timer on the basis that the peer might just not have processed them at
  * the time the ACK was sent.
  */
-static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
-				  rxrpc_seq_t seq, int nr_acks,
-				  struct rxrpc_ack_summary *summary)
+static void rxrpc_input_soft_acks(struct rxrpc_call *call,
+				  struct rxrpc_ack_summary *summary,
+				  struct sk_buff *skb,
+				  rxrpc_seq_t seq,
+				  rxrpc_seq_t since)
 {
-	unsigned int i;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	unsigned int i, old_nacks = 0;
+	rxrpc_seq_t lowest_nak = seq + sp->nr_acks;
+	u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
 
-	for (i = 0; i < nr_acks; i++) {
+	for (i = 0; i < sp->nr_acks; i++) {
 		if (acks[i] == RXRPC_ACK_TYPE_ACK) {
 			summary->nr_acks++;
-			summary->nr_new_acks++;
+			if (after_eq(seq, since))
+				summary->nr_new_acks++;
 		} else {
-			if (!summary->saw_nacks &&
-			    call->acks_lowest_nak != seq + i) {
-				call->acks_lowest_nak = seq + i;
-				summary->new_low_nack = true;
-			}
 			summary->saw_nacks = true;
+			if (before(seq, since)) {
+				/* Overlap with previous ACK */
+				old_nacks++;
+			} else {
+				summary->nr_new_nacks++;
+				sp->nr_nacks++;
+			}
+
+			if (before(seq, lowest_nak))
+				lowest_nak = seq;
 		}
+		seq++;
+	}
+
+	if (lowest_nak != call->acks_lowest_nak) {
+		call->acks_lowest_nak = lowest_nak;
+		summary->new_low_nack = true;
 	}
+
+	/* We *can* have more nacks than we did - the peer is permitted to drop
+	 * packets it has soft-acked and re-request them.  Further, it is
+	 * possible for the nack distribution to change whilst the number of
+	 * nacks stays the same or goes down.
+	 */
+	if (old_nacks < summary->nr_retained_nacks)
+		summary->nr_new_acks += summary->nr_retained_nacks - old_nacks;
+	summary->nr_retained_nacks = old_nacks;
 }
 
 /*
@@ -773,7 +839,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_ackinfo info;
 	rxrpc_serial_t ack_serial, acked_serial;
-	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
+	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
 	int nr_acks, offset, ioffset;
 
 	_enter("");
@@ -789,6 +855,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	prev_pkt = ntohl(ack.previousPacket);
 	hard_ack = first_soft_ack - 1;
 	nr_acks = ack.nAcks;
+	sp->first_ack = first_soft_ack;
+	sp->nr_acks = nr_acks;
 	summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ?
 			      ack.reason : RXRPC_ACK__INVALID);
 
@@ -858,6 +926,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0)
 		skb_condense(skb);
 
+	if (call->cong_last_nack) {
+		since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack);
+		rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+		call->cong_last_nack = NULL;
+	} else {
+		summary.nr_new_acks = first_soft_ack - call->acks_first_seq;
+		call->acks_lowest_nak = first_soft_ack + nr_acks;
+		since = first_soft_ack;
+	}
+
 	call->acks_latest_ts = skb->tstamp;
 	call->acks_first_seq = first_soft_ack;
 	call->acks_prev_seq = prev_pkt;
@@ -866,7 +944,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_ACK_PING:
 		break;
 	default:
-		if (after(acked_serial, call->acks_highest_serial))
+		if (acked_serial && after(acked_serial, call->acks_highest_serial))
 			call->acks_highest_serial = acked_serial;
 		break;
 	}
@@ -905,8 +983,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	if (nr_acks > 0) {
 		if (offset > (int)skb->len - nr_acks)
 			return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
-		rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
-				      nr_acks, &summary);
+		rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since);
+		rxrpc_get_skb(skb, rxrpc_skb_get_last_nack);
+		call->cong_last_nack = skb;
 	}
 
 	if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) &&
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index a0906145e829..4a292f860ae3 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -216,7 +216,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	iov[0].iov_len	= sizeof(txb->wire) + sizeof(txb->ack) + n;
 	len = iov[0].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 	trace_rxrpc_tx_ack(call->debug_id, serial,
 			   ntohl(txb->ack.firstPacket),
@@ -302,7 +302,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	iov[0].iov_base	= &pkt;
 	iov[0].iov_len	= sizeof(pkt);
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	pkt.whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt));
@@ -334,7 +334,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	_enter("%x,{%d}", txb->seq, txb->len);
 
 	/* Each transmission of a Tx packet needs a new serial number */
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	txb->wire.serial = htonl(serial);
 
 	if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) &&
@@ -558,7 +558,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 6c86cbb98d1d..26dc2f26d92d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -181,7 +181,7 @@ print:
 		   atomic_read(&conn->active),
 		   state,
 		   key_serial(conn->key),
-		   atomic_read(&conn->serial),
+		   conn->tx_serial,
 		   conn->hi_serial,
 		   conn->channels[0].call_id,
 		   conn->channels[1].call_id,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index b52dedcebce0..6b32d61d4cdc 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 
 	len = iov[0].iov_len + iov[1].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
@@ -721,7 +721,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 
 	len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len;
 
-	serial = atomic_inc_return(&conn->serial);
+	serial = rxrpc_get_next_serial(conn);
 	whdr.serial = htonl(serial);
 
 	rxrpc_local_dont_fragment(conn->local, false);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 12386f590b0f..6faa7d00da09 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -232,18 +232,14 @@ release_idr:
 	return err;
 }
 
-static bool is_mirred_nested(void)
-{
-	return unlikely(__this_cpu_read(mirred_nest_level) > 1);
-}
-
-static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
+static int
+tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb)
 {
 	int err;
 
 	if (!want_ingress)
 		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
-	else if (is_mirred_nested())
+	else if (!at_ingress)
 		err = netif_rx(skb);
 	else
 		err = netif_receive_skb(skb);
@@ -270,8 +266,7 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 	if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) {
 		net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
 				       dev->name);
-		err = -ENODEV;
-		goto out;
+		goto err_cant_do;
 	}
 
 	/* we could easily avoid the clone only if called by ingress and clsact;
@@ -283,10 +278,8 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 		tcf_mirred_can_reinsert(retval);
 	if (!dont_clone) {
 		skb_to_send = skb_clone(skb, GFP_ATOMIC);
-		if (!skb_to_send) {
-			err =  -ENOMEM;
-			goto out;
-		}
+		if (!skb_to_send)
+			goto err_cant_do;
 	}
 
 	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
@@ -319,19 +312,20 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m,
 
 		skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress);
 
-		err = tcf_mirred_forward(want_ingress, skb_to_send);
+		err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send);
 	} else {
-		err = tcf_mirred_forward(want_ingress, skb_to_send);
+		err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send);
 	}
-
-	if (err) {
-out:
+	if (err)
 		tcf_action_inc_overlimit_qstats(&m->common);
-		if (is_redirect)
-			retval = TC_ACT_SHOT;
-	}
 
 	return retval;
+
+err_cant_do:
+	if (is_redirect)
+		retval = TC_ACT_SHOT;
+	tcf_action_inc_overlimit_qstats(&m->common);
+	return retval;
 }
 
 static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m,
@@ -533,8 +527,6 @@ static int mirred_device_event(struct notifier_block *unused,
 				 * net_device are already rcu protected.
 				 */
 				RCU_INIT_POINTER(m->tcfm_dev, NULL);
-			} else if (m->tcfm_blockid) {
-				m->tcfm_blockid = 0;
 			}
 			spin_unlock_bh(&m->tcf_lock);
 		}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index efb9d2811b73..6ee7064c82fc 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2460,8 +2460,11 @@ unbind_filter:
 	}
 
 errout_idr:
-	if (!fold)
+	if (!fold) {
+		spin_lock(&tp->lock);
 		idr_remove(&head->handle_idr, fnew->handle);
+		spin_unlock(&tp->lock);
+	}
 	__fl_put(fnew);
 errout_tb:
 	kfree(tb);
diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index 5ea84decec19..5337bc462755 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -222,6 +222,7 @@ static void __exit exit_em_canid(void)
 	tcf_em_unregister(&em_canid_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_canid);
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index f17b049ea530..c90ad7ea26b4 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void)
 	tcf_em_unregister(&em_cmp_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_cmp);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 09d8afd04a2a..8996c73c9779 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void)
 	tcf_em_unregister(&em_meta_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_meta);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index a83b237cbeb0..4f9f21a05d5e 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void)
 	tcf_em_unregister(&em_nbyte_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_nbyte);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index f176afb70559..420c66203b17 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -147,6 +147,7 @@ static void __exit exit_em_text(void)
 	tcf_em_unregister(&em_text_ops);
 }
 
+MODULE_DESCRIPTION("ematch classifier for embedded text in skbs");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_text);
diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c
index 71b070da0437..fdec4db5ec89 100644
--- a/net/sched/em_u32.c
+++ b/net/sched/em_u32.c
@@ -52,6 +52,7 @@ static void __exit exit_em_u32(void)
 	tcf_em_unregister(&em_u32_ops);
 }
 
+MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data");
 MODULE_LICENSE("GPL");
 
 module_init(init_em_u32);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 36b025cc4fd2..87f6e3c6daa8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2410,7 +2410,7 @@ static struct pernet_operations psched_net_ops = {
 	.exit = psched_net_exit,
 };
 
-#if IS_ENABLED(CONFIG_RETPOLINE)
+#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)
 DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper);
 #endif
 
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 7182c5a450fb..5c1652181805 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue)
 	INIT_WORK(&queue->immediate, NULL);
 }
 
+/* Properly release the chunk which is being worked on. */
+static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk)
+{
+	if (chunk->head_skb)
+		chunk->skb = chunk->head_skb;
+	sctp_chunk_free(chunk);
+}
+
 /* Release the memory associated with an SCTP inqueue.  */
 void sctp_inq_free(struct sctp_inq *queue)
 {
@@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue)
 	 * free it as well.
 	 */
 	if (queue->in_progress) {
-		sctp_chunk_free(queue->in_progress);
+		sctp_inq_chunk_free(queue->in_progress);
 		queue->in_progress = NULL;
 	}
 }
@@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 				goto new_skb;
 			}
 
-			if (chunk->head_skb)
-				chunk->skb = chunk->head_skb;
-			sctp_chunk_free(chunk);
+			sctp_inq_chunk_free(chunk);
 			chunk = queue->in_progress = NULL;
 		} else {
 			/* Nothing to do. Next chunk in the packet, please. */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a2cb30af46cb..0f53a5c6fd9d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->file->private_data = smc->clcsock;
 		smc->clcsock->wq.fasync_list =
 			smc->sk.sk_socket->wq.fasync_list;
+		smc->sk.sk_socket->wq.fasync_list = NULL;
 
 		/* There might be some wait entries remaining
 		 * in smc sk->sk_wq and they should be woken up
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 95cc95458e2d..e4c858411207 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1877,9 +1877,15 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
 			   struct smcd_dev *smcismdev,
 			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
-		smc_ism_is_virtual(smcismdev) ?
-		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
+	if (lgr->peer_gid.gid != peer_gid->gid ||
+	    lgr->smcd != smcismdev)
+		return false;
+
+	if (smc_ism_is_virtual(smcismdev) &&
+	    lgr->peer_gid.gid_ext != peer_gid->gid_ext)
+		return false;
+
+	return true;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index d2b02710ab07..b2c1b683a88e 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -921,6 +921,8 @@ out_err:
  * Caller provides the truncation length of the output token (h) in
  * cksumout.len.
  *
+ * Note that for RPCSEC, the "initial cipher state" is always all zeroes.
+ *
  * Return values:
  *   %GSS_S_COMPLETE: Digest computed, @cksumout filled in
  *   %GSS_S_FAILURE: Call failed
@@ -931,22 +933,19 @@ u32 krb5_etm_checksum(struct crypto_sync_skcipher *cipher,
 		      int body_offset, struct xdr_netobj *cksumout)
 {
 	unsigned int ivsize = crypto_sync_skcipher_ivsize(cipher);
+	static const u8 iv[GSS_KRB5_MAX_BLOCKSIZE];
 	struct ahash_request *req;
 	struct scatterlist sg[1];
-	u8 *iv, *checksumdata;
 	int err = -ENOMEM;
+	u8 *checksumdata;
 
 	checksumdata = kmalloc(crypto_ahash_digestsize(tfm), GFP_KERNEL);
 	if (!checksumdata)
 		return GSS_S_FAILURE;
-	/* For RPCSEC, the "initial cipher state" is always all zeroes. */
-	iv = kzalloc(ivsize, GFP_KERNEL);
-	if (!iv)
-		goto out_free_mem;
 
 	req = ahash_request_alloc(tfm, GFP_KERNEL);
 	if (!req)
-		goto out_free_mem;
+		goto out_free_cksumdata;
 	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 	err = crypto_ahash_init(req);
 	if (err)
@@ -970,8 +969,7 @@ u32 krb5_etm_checksum(struct crypto_sync_skcipher *cipher,
 
 out_free_ahash:
 	ahash_request_free(req);
-out_free_mem:
-	kfree(iv);
+out_free_cksumdata:
 	kfree_sensitive(checksumdata);
 	return err ? GSS_S_FAILURE : GSS_S_COMPLETE;
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 64cff717c3d9..3366505bc669 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -398,6 +398,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	u64 seq_send64;
 	int keylen;
 	u32 time32;
+	int ret;
 
 	p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags));
 	if (IS_ERR(p))
@@ -450,8 +451,16 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	}
 	ctx->mech_used.len = gss_kerberos_mech.gm_oid.len;
 
-	return gss_krb5_import_ctx_v2(ctx, gfp_mask);
+	ret = gss_krb5_import_ctx_v2(ctx, gfp_mask);
+	if (ret) {
+		p = ERR_PTR(ret);
+		goto out_free;
+	}
 
+	return 0;
+
+out_free:
+	kfree(ctx->mech_used.data);
 out_err:
 	return PTR_ERR(p);
 }
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index d79f12c2550a..cb32ab9a8395 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -250,8 +250,8 @@ static int gssx_dec_option_array(struct xdr_stream *xdr,
 
 	creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL);
 	if (!creds) {
-		kfree(oa->data);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto free_oa;
 	}
 
 	oa->data[0].option.data = CREDS_VALUE;
@@ -265,29 +265,40 @@ static int gssx_dec_option_array(struct xdr_stream *xdr,
 
 		/* option buffer */
 		p = xdr_inline_decode(xdr, 4);
-		if (unlikely(p == NULL))
-			return -ENOSPC;
+		if (unlikely(p == NULL)) {
+			err = -ENOSPC;
+			goto free_creds;
+		}
 
 		length = be32_to_cpup(p);
 		p = xdr_inline_decode(xdr, length);
-		if (unlikely(p == NULL))
-			return -ENOSPC;
+		if (unlikely(p == NULL)) {
+			err = -ENOSPC;
+			goto free_creds;
+		}
 
 		if (length == sizeof(CREDS_VALUE) &&
 		    memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) {
 			/* We have creds here. parse them */
 			err = gssx_dec_linux_creds(xdr, creds);
 			if (err)
-				return err;
+				goto free_creds;
 			oa->data[0].value.len = 1; /* presence */
 		} else {
 			/* consume uninteresting buffer */
 			err = gssx_dec_buffer(xdr, &dummy);
 			if (err)
-				return err;
+				goto free_creds;
 		}
 	}
 	return 0;
+
+free_creds:
+	kfree(creds);
+free_oa:
+	kfree(oa->data);
+	oa->data = NULL;
+	return err;
 }
 
 static int gssx_dec_status(struct xdr_stream *xdr,
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 65fc1297c6df..383860cb1d5b 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -314,7 +314,7 @@ EXPORT_SYMBOL_GPL(rpc_proc_unregister);
 struct proc_dir_entry *
 svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops)
 {
-	return do_register(net, statp->program->pg_name, statp, proc_ops);
+	return do_register(net, statp->program->pg_name, net, proc_ops);
 }
 EXPORT_SYMBOL_GPL(svc_proc_register);
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index f60c93e5a25d..b33e429336fb 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -451,8 +451,8 @@ __svc_init_bc(struct svc_serv *serv)
  * Create an RPC service
  */
 static struct svc_serv *
-__svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
-	     int (*threadfn)(void *data))
+__svc_create(struct svc_program *prog, struct svc_stat *stats,
+	     unsigned int bufsize, int npools, int (*threadfn)(void *data))
 {
 	struct svc_serv	*serv;
 	unsigned int vers;
@@ -463,7 +463,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		return NULL;
 	serv->sv_name      = prog->pg_name;
 	serv->sv_program   = prog;
-	serv->sv_stats     = prog->pg_stats;
+	serv->sv_stats     = stats;
 	if (bufsize > RPCSVC_MAXPAYLOAD)
 		bufsize = RPCSVC_MAXPAYLOAD;
 	serv->sv_max_payload = bufsize? bufsize : 4096;
@@ -529,26 +529,28 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize,
 			    int (*threadfn)(void *data))
 {
-	return __svc_create(prog, bufsize, 1, threadfn);
+	return __svc_create(prog, NULL, bufsize, 1, threadfn);
 }
 EXPORT_SYMBOL_GPL(svc_create);
 
 /**
  * svc_create_pooled - Create an RPC service with pooled threads
  * @prog: the RPC program the new service will handle
+ * @stats: the stats struct if desired
  * @bufsize: maximum message size for @prog
  * @threadfn: a function to service RPC requests for @prog
  *
  * Returns an instantiated struct svc_serv object or NULL.
  */
 struct svc_serv *svc_create_pooled(struct svc_program *prog,
+				   struct svc_stat *stats,
 				   unsigned int bufsize,
 				   int (*threadfn)(void *data))
 {
 	struct svc_serv *serv;
 	unsigned int npools = svc_pool_map_get();
 
-	serv = __svc_create(prog, bufsize, npools, threadfn);
+	serv = __svc_create(prog, stats, bufsize, npools, threadfn);
 	if (!serv)
 		goto out_err;
 	return serv;
@@ -1375,7 +1377,8 @@ svc_process_common(struct svc_rqst *rqstp)
 		goto err_bad_proc;
 
 	/* Syntactic check complete */
-	serv->sv_stats->rpccnt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpccnt++;
 	trace_svc_process(rqstp, progp->pg_name);
 
 	aoffset = xdr_stream_pos(xdr);
@@ -1427,7 +1430,8 @@ err_short_len:
 	goto close_xprt;
 
 err_bad_rpc:
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	xdr_stream_encode_u32(xdr, RPC_MSG_DENIED);
 	xdr_stream_encode_u32(xdr, RPC_MISMATCH);
 	/* Only RPCv2 supported */
@@ -1438,7 +1442,8 @@ err_bad_rpc:
 err_bad_auth:
 	dprintk("svc: authentication failed (%d)\n",
 		be32_to_cpu(rqstp->rq_auth_stat));
-	serv->sv_stats->rpcbadauth++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadauth++;
 	/* Restore write pointer to location of reply status: */
 	xdr_truncate_encode(xdr, XDR_UNIT * 2);
 	xdr_stream_encode_u32(xdr, RPC_MSG_DENIED);
@@ -1448,7 +1453,8 @@ err_bad_auth:
 
 err_bad_prog:
 	dprintk("svc: unknown program %d\n", rqstp->rq_prog);
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_prog_unavail;
 	goto sendit;
 
@@ -1456,7 +1462,8 @@ err_bad_vers:
 	svc_printk(rqstp, "unknown version (%d for prog %d, %s)\n",
 		       rqstp->rq_vers, rqstp->rq_prog, progp->pg_name);
 
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_prog_mismatch;
 
 	/*
@@ -1470,19 +1477,22 @@ err_bad_vers:
 err_bad_proc:
 	svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc);
 
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_proc_unavail;
 	goto sendit;
 
 err_garbage_args:
 	svc_printk(rqstp, "failed to decode RPC header\n");
 
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_garbage_args;
 	goto sendit;
 
 err_system_err:
-	serv->sv_stats->rpcbadfmt++;
+	if (serv->sv_stats)
+		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_system_err;
 	goto sendit;
 }
@@ -1534,7 +1544,8 @@ void svc_process(struct svc_rqst *rqstp)
 out_baddir:
 	svc_printk(rqstp, "bad direction 0x%08x, dropping request\n",
 		   be32_to_cpu(*p));
-	rqstp->rq_server->sv_stats->rpcbadfmt++;
+	if (rqstp->rq_server->sv_stats)
+		rqstp->rq_server->sv_stats->rpcbadfmt++;
 out_drop:
 	svc_drop(rqstp);
 }
@@ -1598,10 +1609,10 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 	/* Finally, send the reply synchronously */
 	if (rqstp->bc_to_initval > 0) {
 		timeout.to_initval = rqstp->bc_to_initval;
-		timeout.to_retries = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_retries;
 	} else {
 		timeout.to_initval = req->rq_xprt->timeout->to_initval;
-		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+		timeout.to_retries = req->rq_xprt->timeout->to_retries;
 	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
 	task = rpc_run_bc_task(req, &timeout);
@@ -1612,7 +1623,6 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 	WARN_ON_ONCE(atomic_read(&task->tk_count) != 1);
 	rpc_put_task(task);
 }
-EXPORT_SYMBOL_GPL(svc_process_bc);
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 
 /**
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index c9be6778643b..e5a78b761012 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -90,7 +90,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	 */
 	get_page(virt_to_page(rqst->rq_buffer));
 	sctxt->sc_send_wr.opcode = IB_WR_SEND;
-	return svc_rdma_send(rdma, sctxt);
+	return svc_rdma_post_send(rdma, sctxt);
 }
 
 /* Server-side transport endpoint wants a whole page for its send
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index c00fcce61d1e..f2a100c4c81f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -197,28 +197,6 @@ void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
 		llist_add_batch(first, last, &rdma->sc_rw_ctxts);
 }
 
-/* State for sending a Write or Reply chunk.
- *  - Tracks progress of writing one chunk over all its segments
- *  - Stores arguments for the SGL constructor functions
- */
-struct svc_rdma_write_info {
-	struct svcxprt_rdma	*wi_rdma;
-
-	const struct svc_rdma_chunk	*wi_chunk;
-
-	/* write state of this chunk */
-	unsigned int		wi_seg_off;
-	unsigned int		wi_seg_no;
-
-	/* SGL constructor arguments */
-	const struct xdr_buf	*wi_xdr;
-	unsigned char		*wi_base;
-	unsigned int		wi_next_off;
-
-	struct svc_rdma_chunk_ctxt	wi_cc;
-	struct work_struct	wi_work;
-};
-
 static struct svc_rdma_write_info *
 svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
 			  const struct svc_rdma_chunk *chunk)
@@ -253,6 +231,71 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
 }
 
 /**
+ * svc_rdma_write_chunk_release - Release Write chunk I/O resources
+ * @rdma: controlling transport
+ * @ctxt: Send context that is being released
+ */
+void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
+				  struct svc_rdma_send_ctxt *ctxt)
+{
+	struct svc_rdma_write_info *info;
+	struct svc_rdma_chunk_ctxt *cc;
+
+	while (!list_empty(&ctxt->sc_write_info_list)) {
+		info = list_first_entry(&ctxt->sc_write_info_list,
+					struct svc_rdma_write_info, wi_list);
+		list_del(&info->wi_list);
+
+		cc = &info->wi_cc;
+		svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
+		svc_rdma_write_info_free(info);
+	}
+}
+
+/**
+ * svc_rdma_reply_chunk_release - Release Reply chunk I/O resources
+ * @rdma: controlling transport
+ * @ctxt: Send context that is being released
+ */
+void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma,
+				  struct svc_rdma_send_ctxt *ctxt)
+{
+	struct svc_rdma_chunk_ctxt *cc = &ctxt->sc_reply_info.wi_cc;
+
+	if (!cc->cc_sqecount)
+		return;
+	svc_rdma_cc_release(rdma, cc, DMA_TO_DEVICE);
+}
+
+/**
+ * svc_rdma_reply_done - Reply chunk Write completion handler
+ * @cq: controlling Completion Queue
+ * @wc: Work Completion report
+ *
+ * Pages under I/O are released by a subsequent Send completion.
+ */
+static void svc_rdma_reply_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+	struct ib_cqe *cqe = wc->wr_cqe;
+	struct svc_rdma_chunk_ctxt *cc =
+			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
+	struct svcxprt_rdma *rdma = cq->cq_context;
+
+	switch (wc->status) {
+	case IB_WC_SUCCESS:
+		trace_svcrdma_wc_reply(&cc->cc_cid);
+		return;
+	case IB_WC_WR_FLUSH_ERR:
+		trace_svcrdma_wc_reply_flush(wc, &cc->cc_cid);
+		break;
+	default:
+		trace_svcrdma_wc_reply_err(wc, &cc->cc_cid);
+	}
+
+	svc_xprt_deferred_close(&rdma->sc_xprt);
+}
+
+/**
  * svc_rdma_write_done - Write chunk completion
  * @cq: controlling Completion Queue
  * @wc: Work Completion
@@ -265,13 +308,11 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_chunk_ctxt *cc =
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
-	struct svc_rdma_write_info *info =
-			container_of(cc, struct svc_rdma_write_info, wi_cc);
 
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
 		trace_svcrdma_wc_write(&cc->cc_cid);
-		break;
+		return;
 	case IB_WC_WR_FLUSH_ERR:
 		trace_svcrdma_wc_write_flush(wc, &cc->cc_cid);
 		break;
@@ -279,12 +320,11 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 		trace_svcrdma_wc_write_err(wc, &cc->cc_cid);
 	}
 
-	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
-
-	if (unlikely(wc->status != IB_WC_SUCCESS))
-		svc_xprt_deferred_close(&rdma->sc_xprt);
-
-	svc_rdma_write_info_free(info);
+	/* The RDMA Write has flushed, so the client won't get
+	 * some of the outgoing RPC message. Signal the loss
+	 * to the client by closing the connection.
+	 */
+	svc_xprt_deferred_close(&rdma->sc_xprt);
 }
 
 /**
@@ -580,41 +620,54 @@ static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data)
 	return xdr->len;
 }
 
-/**
- * svc_rdma_send_write_chunk - Write all segments in a Write chunk
- * @rdma: controlling RDMA transport
- * @chunk: Write chunk provided by the client
- * @xdr: xdr_buf containing the data payload
- *
- * Returns a non-negative number of bytes the chunk consumed, or
- *	%-E2BIG if the payload was larger than the Write chunk,
- *	%-EINVAL if client provided too many segments,
- *	%-ENOMEM if rdma_rw context pool was exhausted,
- *	%-ENOTCONN if posting failed (connection is lost),
- *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
+/* Link Write WRs for @chunk onto @sctxt's WR chain.
  */
-int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-			      const struct svc_rdma_chunk *chunk,
-			      const struct xdr_buf *xdr)
+static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma,
+					struct svc_rdma_send_ctxt *sctxt,
+					const struct svc_rdma_chunk *chunk,
+					const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
 	struct svc_rdma_chunk_ctxt *cc;
+	struct ib_send_wr *first_wr;
+	struct xdr_buf payload;
+	struct list_head *pos;
+	struct ib_cqe *cqe;
 	int ret;
 
+	if (xdr_buf_subsegment(xdr, &payload, chunk->ch_position,
+			       chunk->ch_payload_length))
+		return -EMSGSIZE;
+
 	info = svc_rdma_write_info_alloc(rdma, chunk);
 	if (!info)
 		return -ENOMEM;
 	cc = &info->wi_cc;
 
-	ret = svc_rdma_xb_write(xdr, info);
-	if (ret != xdr->len)
+	ret = svc_rdma_xb_write(&payload, info);
+	if (ret != payload.len)
 		goto out_err;
 
-	trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
-	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
-	if (ret < 0)
+	ret = -EINVAL;
+	if (unlikely(cc->cc_sqecount > rdma->sc_sq_depth))
 		goto out_err;
-	return xdr->len;
+
+	first_wr = sctxt->sc_wr_chain;
+	cqe = &cc->cc_cqe;
+	list_for_each(pos, &cc->cc_rwctxts) {
+		struct svc_rdma_rw_ctxt *rwc;
+
+		rwc = list_entry(pos, struct svc_rdma_rw_ctxt, rw_list);
+		first_wr = rdma_rw_ctx_wrs(&rwc->rw_ctx, rdma->sc_qp,
+					   rdma->sc_port_num, cqe, first_wr);
+		cqe = NULL;
+	}
+	sctxt->sc_wr_chain = first_wr;
+	sctxt->sc_sqecount += cc->cc_sqecount;
+	list_add(&info->wi_list, &sctxt->sc_write_info_list);
+
+	trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
+	return 0;
 
 out_err:
 	svc_rdma_write_info_free(info);
@@ -622,9 +675,39 @@ out_err:
 }
 
 /**
- * svc_rdma_send_reply_chunk - Write all segments in the Reply chunk
+ * svc_rdma_prepare_write_list - Construct WR chain for sending Write list
  * @rdma: controlling RDMA transport
- * @rctxt: Write and Reply chunks from client
+ * @write_pcl: Write list provisioned by the client
+ * @sctxt: Send WR resources
+ * @xdr: xdr_buf containing an RPC Reply message
+ *
+ * Returns zero on success, or a negative errno if one or more
+ * Write chunks could not be sent.
+ */
+int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
+				const struct svc_rdma_pcl *write_pcl,
+				struct svc_rdma_send_ctxt *sctxt,
+				const struct xdr_buf *xdr)
+{
+	struct svc_rdma_chunk *chunk;
+	int ret;
+
+	pcl_for_each_chunk(chunk, write_pcl) {
+		if (!chunk->ch_payload_length)
+			break;
+		ret = svc_rdma_prepare_write_chunk(rdma, sctxt, chunk, xdr);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+/**
+ * svc_rdma_prepare_reply_chunk - Construct WR chain for writing the Reply chunk
+ * @rdma: controlling RDMA transport
+ * @write_pcl: Write chunk list provided by client
+ * @reply_pcl: Reply chunk provided by client
+ * @sctxt: Send WR resources
  * @xdr: xdr_buf containing an RPC Reply
  *
  * Returns a non-negative number of bytes the chunk consumed, or
@@ -634,39 +717,45 @@ out_err:
  *	%-ENOTCONN if posting failed (connection is lost),
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
-int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
-			      const struct svc_rdma_recv_ctxt *rctxt,
-			      const struct xdr_buf *xdr)
+int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma,
+				 const struct svc_rdma_pcl *write_pcl,
+				 const struct svc_rdma_pcl *reply_pcl,
+				 struct svc_rdma_send_ctxt *sctxt,
+				 const struct xdr_buf *xdr)
 {
-	struct svc_rdma_write_info *info;
-	struct svc_rdma_chunk_ctxt *cc;
-	struct svc_rdma_chunk *chunk;
+	struct svc_rdma_write_info *info = &sctxt->sc_reply_info;
+	struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
+	struct ib_send_wr *first_wr;
+	struct list_head *pos;
+	struct ib_cqe *cqe;
 	int ret;
 
-	if (pcl_is_empty(&rctxt->rc_reply_pcl))
-		return 0;
-
-	chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
-	info = svc_rdma_write_info_alloc(rdma, chunk);
-	if (!info)
-		return -ENOMEM;
-	cc = &info->wi_cc;
+	info->wi_rdma = rdma;
+	info->wi_chunk = pcl_first_chunk(reply_pcl);
+	info->wi_seg_off = 0;
+	info->wi_seg_no = 0;
+	info->wi_cc.cc_cqe.done = svc_rdma_reply_done;
 
-	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	ret = pcl_process_nonpayloads(write_pcl, xdr,
 				      svc_rdma_xb_write, info);
 	if (ret < 0)
-		goto out_err;
+		return ret;
 
-	trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount);
-	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
-	if (ret < 0)
-		goto out_err;
+	first_wr = sctxt->sc_wr_chain;
+	cqe = &cc->cc_cqe;
+	list_for_each(pos, &cc->cc_rwctxts) {
+		struct svc_rdma_rw_ctxt *rwc;
 
-	return xdr->len;
+		rwc = list_entry(pos, struct svc_rdma_rw_ctxt, rw_list);
+		first_wr = rdma_rw_ctx_wrs(&rwc->rw_ctx, rdma->sc_qp,
+					   rdma->sc_port_num, cqe, first_wr);
+		cqe = NULL;
+	}
+	sctxt->sc_wr_chain = first_wr;
+	sctxt->sc_sqecount += cc->cc_sqecount;
 
-out_err:
-	svc_rdma_write_info_free(info);
-	return ret;
+	trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount);
+	return xdr->len;
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 1a49b7f02041..dfca39abd16c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -142,6 +142,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 	ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
 	ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED;
 	ctxt->sc_cqe.done = svc_rdma_wc_send;
+	INIT_LIST_HEAD(&ctxt->sc_write_info_list);
 	ctxt->sc_xprt_buf = buffer;
 	xdr_buf_init(&ctxt->sc_hdrbuf, ctxt->sc_xprt_buf,
 		     rdma->sc_max_req_size);
@@ -205,9 +206,13 @@ out:
 	xdr_init_encode(&ctxt->sc_stream, &ctxt->sc_hdrbuf,
 			ctxt->sc_xprt_buf, NULL);
 
+	svc_rdma_cc_init(rdma, &ctxt->sc_reply_info.wi_cc);
 	ctxt->sc_send_wr.num_sge = 0;
 	ctxt->sc_cur_sge_no = 0;
 	ctxt->sc_page_count = 0;
+	ctxt->sc_wr_chain = &ctxt->sc_send_wr;
+	ctxt->sc_sqecount = 1;
+
 	return ctxt;
 
 out_empty:
@@ -223,6 +228,9 @@ static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma,
 	struct ib_device *device = rdma->sc_cm_id->device;
 	unsigned int i;
 
+	svc_rdma_write_chunk_release(rdma, ctxt);
+	svc_rdma_reply_chunk_release(rdma, ctxt);
+
 	if (ctxt->sc_page_count)
 		release_pages(ctxt->sc_pages, ctxt->sc_page_count);
 
@@ -293,7 +301,7 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 	struct svc_rdma_send_ctxt *ctxt =
 		container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe);
 
-	svc_rdma_wake_send_waiters(rdma, 1);
+	svc_rdma_wake_send_waiters(rdma, ctxt->sc_sqecount);
 
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		goto flushed;
@@ -312,51 +320,76 @@ flushed:
 }
 
 /**
- * svc_rdma_send - Post a single Send WR
- * @rdma: transport on which to post the WR
- * @ctxt: send ctxt with a Send WR ready to post
+ * svc_rdma_post_send - Post a WR chain to the Send Queue
+ * @rdma: transport context
+ * @ctxt: WR chain to post
+ *
+ * Copy fields in @ctxt to stack variables in order to guarantee
+ * that these values remain available after the ib_post_send() call.
+ * In some error flow cases, svc_rdma_wc_send() releases @ctxt.
+ *
+ * Note there is potential for starvation when the Send Queue is
+ * full because there is no order to when waiting threads are
+ * awoken. The transport is typically provisioned with a deep
+ * enough Send Queue that SQ exhaustion should be a rare event.
  *
- * Returns zero if the Send WR was posted successfully. Otherwise, a
- * negative errno is returned.
+ * Return values:
+ *   %0: @ctxt's WR chain was posted successfully
+ *   %-ENOTCONN: The connection was lost
  */
-int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
+int svc_rdma_post_send(struct svcxprt_rdma *rdma,
+		       struct svc_rdma_send_ctxt *ctxt)
 {
-	struct ib_send_wr *wr = &ctxt->sc_send_wr;
-	int ret;
+	struct ib_send_wr *first_wr = ctxt->sc_wr_chain;
+	struct ib_send_wr *send_wr = &ctxt->sc_send_wr;
+	const struct ib_send_wr *bad_wr = first_wr;
+	struct rpc_rdma_cid cid = ctxt->sc_cid;
+	int ret, sqecount = ctxt->sc_sqecount;
 
 	might_sleep();
 
 	/* Sync the transport header buffer */
 	ib_dma_sync_single_for_device(rdma->sc_pd->device,
-				      wr->sg_list[0].addr,
-				      wr->sg_list[0].length,
+				      send_wr->sg_list[0].addr,
+				      send_wr->sg_list[0].length,
 				      DMA_TO_DEVICE);
 
 	/* If the SQ is full, wait until an SQ entry is available */
-	while (1) {
-		if ((atomic_dec_return(&rdma->sc_sq_avail) < 0)) {
+	while (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags)) {
+		if (atomic_sub_return(sqecount, &rdma->sc_sq_avail) < 0) {
+			svc_rdma_wake_send_waiters(rdma, sqecount);
+
+			/* When the transport is torn down, assume
+			 * ib_drain_sq() will trigger enough Send
+			 * completions to wake us. The XPT_CLOSE test
+			 * above should then cause the while loop to
+			 * exit.
+			 */
 			percpu_counter_inc(&svcrdma_stat_sq_starve);
-			trace_svcrdma_sq_full(rdma, &ctxt->sc_cid);
-			atomic_inc(&rdma->sc_sq_avail);
+			trace_svcrdma_sq_full(rdma, &cid);
 			wait_event(rdma->sc_send_wait,
-				   atomic_read(&rdma->sc_sq_avail) > 1);
-			if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
-				return -ENOTCONN;
-			trace_svcrdma_sq_retry(rdma, &ctxt->sc_cid);
+				   atomic_read(&rdma->sc_sq_avail) > 0);
+			trace_svcrdma_sq_retry(rdma, &cid);
 			continue;
 		}
 
 		trace_svcrdma_post_send(ctxt);
-		ret = ib_post_send(rdma->sc_qp, wr, NULL);
-		if (ret)
-			break;
+		ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
+		if (ret) {
+			trace_svcrdma_sq_post_err(rdma, &cid, ret);
+			svc_xprt_deferred_close(&rdma->sc_xprt);
+
+			/* If even one WR was posted, there will be a
+			 * Send completion that bumps sc_sq_avail.
+			 */
+			if (bad_wr == first_wr) {
+				svc_rdma_wake_send_waiters(rdma, sqecount);
+				break;
+			}
+		}
 		return 0;
 	}
-
-	trace_svcrdma_sq_post_err(rdma, &ctxt->sc_cid, ret);
-	svc_xprt_deferred_close(&rdma->sc_xprt);
-	wake_up(&rdma->sc_send_wait);
-	return ret;
+	return -ENOTCONN;
 }
 
 /**
@@ -839,16 +872,10 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
  * in sc_sges[0], and the RPC xdr_buf is prepared in following sges.
  *
  * Depending on whether a Write list or Reply chunk is present,
- * the server may send all, a portion of, or none of the xdr_buf.
+ * the server may Send all, a portion of, or none of the xdr_buf.
  * In the latter case, only the transport header (sc_sges[0]) is
  * transmitted.
  *
- * RDMA Send is the last step of transmitting an RPC reply. Pages
- * involved in the earlier RDMA Writes are here transferred out
- * of the rqstp and into the sctxt's page array. These pages are
- * DMA unmapped by each Write completion, but the subsequent Send
- * completion finally releases these pages.
- *
  * Assumptions:
  * - The Reply's transport header will never be larger than a page.
  */
@@ -857,6 +884,7 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 				   const struct svc_rdma_recv_ctxt *rctxt,
 				   struct svc_rqst *rqstp)
 {
+	struct ib_send_wr *send_wr = &sctxt->sc_send_wr;
 	int ret;
 
 	ret = svc_rdma_map_reply_msg(rdma, sctxt, &rctxt->rc_write_pcl,
@@ -864,16 +892,19 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 	if (ret < 0)
 		return ret;
 
+	/* Transfer pages involved in RDMA Writes to the sctxt's
+	 * page array. Completion handling releases these pages.
+	 */
 	svc_rdma_save_io_pages(rqstp, sctxt);
 
 	if (rctxt->rc_inv_rkey) {
-		sctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV;
-		sctxt->sc_send_wr.ex.invalidate_rkey = rctxt->rc_inv_rkey;
+		send_wr->opcode = IB_WR_SEND_WITH_INV;
+		send_wr->ex.invalidate_rkey = rctxt->rc_inv_rkey;
 	} else {
-		sctxt->sc_send_wr.opcode = IB_WR_SEND;
+		send_wr->opcode = IB_WR_SEND;
 	}
 
-	return svc_rdma_send(rdma, sctxt);
+	return svc_rdma_post_send(rdma, sctxt);
 }
 
 /**
@@ -937,7 +968,7 @@ void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 	sctxt->sc_send_wr.num_sge = 1;
 	sctxt->sc_send_wr.opcode = IB_WR_SEND;
 	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
-	if (svc_rdma_send(rdma, sctxt))
+	if (svc_rdma_post_send(rdma, sctxt))
 		goto put_ctxt;
 	return;
 
@@ -984,10 +1015,20 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	if (!p)
 		goto put_ctxt;
 
-	ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
+	ret = svc_rdma_prepare_write_list(rdma, &rctxt->rc_write_pcl, sctxt,
+					  &rqstp->rq_res);
 	if (ret < 0)
-		goto reply_chunk;
-	rc_size = ret;
+		goto put_ctxt;
+
+	rc_size = 0;
+	if (!pcl_is_empty(&rctxt->rc_reply_pcl)) {
+		ret = svc_rdma_prepare_reply_chunk(rdma, &rctxt->rc_write_pcl,
+						   &rctxt->rc_reply_pcl, sctxt,
+						   &rqstp->rq_res);
+		if (ret < 0)
+			goto reply_chunk;
+		rc_size = ret;
+	}
 
 	*p++ = *rdma_argp;
 	*p++ = *(rdma_argp + 1);
@@ -1030,45 +1071,33 @@ drop_connection:
 
 /**
  * svc_rdma_result_payload - special processing for a result payload
- * @rqstp: svc_rqst to operate on
- * @offset: payload's byte offset in @xdr
+ * @rqstp: RPC transaction context
+ * @offset: payload's byte offset in @rqstp->rq_res
  * @length: size of payload, in bytes
  *
+ * Assign the passed-in result payload to the current Write chunk,
+ * and advance to cur_result_payload to the next Write chunk, if
+ * there is one.
+ *
  * Return values:
  *   %0 if successful or nothing needed to be done
- *   %-EMSGSIZE on XDR buffer overflow
  *   %-E2BIG if the payload was larger than the Write chunk
- *   %-EINVAL if client provided too many segments
- *   %-ENOMEM if rdma_rw context pool was exhausted
- *   %-ENOTCONN if posting failed (connection is lost)
- *   %-EIO if rdma_rw initialization failed (DMA mapping, etc)
  */
 int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
 			    unsigned int length)
 {
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
 	struct svc_rdma_chunk *chunk;
-	struct svcxprt_rdma *rdma;
-	struct xdr_buf subbuf;
-	int ret;
 
 	chunk = rctxt->rc_cur_result_payload;
 	if (!length || !chunk)
 		return 0;
 	rctxt->rc_cur_result_payload =
 		pcl_next_chunk(&rctxt->rc_write_pcl, chunk);
+
 	if (length > chunk->ch_length)
 		return -E2BIG;
-
 	chunk->ch_position = offset;
 	chunk->ch_payload_length = length;
-
-	if (xdr_buf_subsegment(&rqstp->rq_res, &subbuf, offset, length))
-		return -EMSGSIZE;
-
-	rdma = container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
-	ret = svc_rdma_send_write_chunk(rdma, chunk, &subbuf);
-	if (ret < 0)
-		return ret;
 	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4f27325ace4a..2b1c16b9547d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -415,15 +415,20 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge)
 		newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
 	rq_depth = newxprt->sc_max_requests + newxprt->sc_max_bc_requests +
-		   newxprt->sc_recv_batch;
+		   newxprt->sc_recv_batch + 1 /* drain */;
 	if (rq_depth > dev->attrs.max_qp_wr) {
 		rq_depth = dev->attrs.max_qp_wr;
 		newxprt->sc_recv_batch = 1;
 		newxprt->sc_max_requests = rq_depth - 2;
 		newxprt->sc_max_bc_requests = 2;
 	}
-	ctxts = rdma_rw_mr_factor(dev, newxprt->sc_port_num, RPCSVC_MAXPAGES);
-	ctxts *= newxprt->sc_max_requests;
+
+	/* Arbitrarily estimate the number of rw_ctxs needed for
+	 * this transport. This is enough rw_ctxs to make forward
+	 * progress even if the client is using one rkey per page
+	 * in each Read chunk.
+	 */
+	ctxts = 3 * RPCSVC_MAXPAGES;
 	newxprt->sc_sq_depth = rq_depth + ctxts;
 	if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr)
 		newxprt->sc_sq_depth = dev->attrs.max_qp_wr;
@@ -460,12 +465,14 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr);
 	dprintk("    cap.max_send_sge = %d, cap.max_recv_sge = %d\n",
 		qp_attr.cap.max_send_sge, qp_attr.cap.max_recv_sge);
-
+	dprintk("    send CQ depth = %u, recv CQ depth = %u\n",
+		newxprt->sc_sq_depth, rq_depth);
 	ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd, &qp_attr);
 	if (ret) {
 		trace_svcrdma_qp_err(newxprt, ret);
 		goto errout;
 	}
+	newxprt->sc_max_send_sges = qp_attr.cap.max_send_sge;
 	newxprt->sc_qp = newxprt->sc_cm_id->qp;
 
 	if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS))
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 58f3dc8d0d71..d92c13e78a56 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2987,20 +2987,11 @@ static int bc_send_request(struct rpc_rqst *req)
 	return len;
 }
 
-/*
- * The close routine. Since this is client initiated, we do nothing
- */
-
 static void bc_close(struct rpc_xprt *xprt)
 {
 	xprt_disconnect_done(xprt);
 }
 
-/*
- * The xprt destroy routine. Again, because this connection is client
- * initiated, we do nothing
- */
-
 static void bc_destroy(struct rpc_xprt *xprt)
 {
 	dprintk("RPC:       bc_destroy xprt %p\n", xprt);
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 5b045284849e..c9189a970eec 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -19,6 +19,35 @@
 #include <linux/rtnetlink.h>
 #include <net/switchdev.h>
 
+static bool switchdev_obj_eq(const struct switchdev_obj *a,
+			     const struct switchdev_obj *b)
+{
+	const struct switchdev_obj_port_vlan *va, *vb;
+	const struct switchdev_obj_port_mdb *ma, *mb;
+
+	if (a->id != b->id || a->orig_dev != b->orig_dev)
+		return false;
+
+	switch (a->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		va = SWITCHDEV_OBJ_PORT_VLAN(a);
+		vb = SWITCHDEV_OBJ_PORT_VLAN(b);
+		return va->flags == vb->flags &&
+			va->vid == vb->vid &&
+			va->changed == vb->changed;
+	case SWITCHDEV_OBJ_ID_PORT_MDB:
+	case SWITCHDEV_OBJ_ID_HOST_MDB:
+		ma = SWITCHDEV_OBJ_PORT_MDB(a);
+		mb = SWITCHDEV_OBJ_PORT_MDB(b);
+		return ma->vid == mb->vid &&
+			ether_addr_equal(ma->addr, mb->addr);
+	default:
+		break;
+	}
+
+	BUG();
+}
+
 static LIST_HEAD(deferred);
 static DEFINE_SPINLOCK(deferred_lock);
 
@@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
 
+/**
+ *	switchdev_port_obj_act_is_deferred - Is object action pending?
+ *
+ *	@dev: port device
+ *	@nt: type of action; add or delete
+ *	@obj: object to test
+ *
+ *	Returns true if a deferred item is pending, which is
+ *	equivalent to the action @nt on an object @obj.
+ *
+ *	rtnl_lock must be held.
+ */
+bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
+					enum switchdev_notifier_type nt,
+					const struct switchdev_obj *obj)
+{
+	struct switchdev_deferred_item *dfitem;
+	bool found = false;
+
+	ASSERT_RTNL();
+
+	spin_lock_bh(&deferred_lock);
+
+	list_for_each_entry(dfitem, &deferred, list) {
+		if (dfitem->dev != dev)
+			continue;
+
+		if ((dfitem->func == switchdev_port_obj_add_deferred &&
+		     nt == SWITCHDEV_PORT_OBJ_ADD) ||
+		    (dfitem->func == switchdev_port_obj_del_deferred &&
+		     nt == SWITCHDEV_PORT_OBJ_DEL)) {
+			if (switchdev_obj_eq((const void *)dfitem->data, obj)) {
+				found = true;
+				break;
+			}
+		}
+	}
+
+	spin_unlock_bh(&deferred_lock);
+
+	return found;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred);
+
 static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
 static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain);
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2cde375477e3..878415c43527 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1086,6 +1086,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
 
 #ifdef CONFIG_TIPC_MEDIA_UDP
 	if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) {
+		if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) {
+			rtnl_unlock();
+			NL_SET_ERR_MSG(info->extack, "UDP option is unsupported");
+			return -EINVAL;
+		}
+
 		err = tipc_udp_nl_bearer_add(b,
 					     attrs[TIPC_NLA_BEARER_UDP_OPTS]);
 		if (err) {
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 1c2c6800949d..b4674f03d71a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx)
 	return 0;
 }
 
-static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
+static int tls_get_info(struct sock *sk, struct sk_buff *skb)
 {
 	u16 version, cipher_type;
 	struct tls_context *ctx;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 31e8a94dfc11..211f57164cb6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -52,6 +52,7 @@ struct tls_decrypt_arg {
 	struct_group(inargs,
 	bool zc;
 	bool async;
+	bool async_done;
 	u8 tail;
 	);
 
@@ -63,6 +64,7 @@ struct tls_decrypt_ctx {
 	u8 iv[TLS_MAX_IV_SIZE];
 	u8 aad[TLS_MAX_AAD_SIZE];
 	u8 tail;
+	bool free_sgout;
 	struct scatterlist sg[];
 };
 
@@ -187,7 +189,6 @@ static void tls_decrypt_done(void *data, int err)
 	struct aead_request *aead_req = data;
 	struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
 	struct scatterlist *sgout = aead_req->dst;
-	struct scatterlist *sgin = aead_req->src;
 	struct tls_sw_context_rx *ctx;
 	struct tls_decrypt_ctx *dctx;
 	struct tls_context *tls_ctx;
@@ -196,6 +197,17 @@ static void tls_decrypt_done(void *data, int err)
 	struct sock *sk;
 	int aead_size;
 
+	/* If requests get too backlogged crypto API returns -EBUSY and calls
+	 * ->complete(-EINPROGRESS) immediately followed by ->complete(0)
+	 * to make waiting for backlog to flush with crypto_wait_req() easier.
+	 * First wait converts -EBUSY -> -EINPROGRESS, and the second one
+	 * -EINPROGRESS -> 0.
+	 * We have a single struct crypto_async_request per direction, this
+	 * scheme doesn't help us, so just ignore the first ->complete().
+	 */
+	if (err == -EINPROGRESS)
+		return;
+
 	aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead);
 	aead_size = ALIGN(aead_size, __alignof__(*dctx));
 	dctx = (void *)((u8 *)aead_req + aead_size);
@@ -213,7 +225,7 @@ static void tls_decrypt_done(void *data, int err)
 	}
 
 	/* Free the destination pages if skb was not decrypted inplace */
-	if (sgout != sgin) {
+	if (dctx->free_sgout) {
 		/* Skip the first S/G entry as it points to AAD */
 		for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
 			if (!sg)
@@ -224,10 +236,17 @@ static void tls_decrypt_done(void *data, int err)
 
 	kfree(aead_req);
 
-	spin_lock_bh(&ctx->decrypt_compl_lock);
-	if (!atomic_dec_return(&ctx->decrypt_pending))
+	if (atomic_dec_and_test(&ctx->decrypt_pending))
 		complete(&ctx->async_wait.completion);
-	spin_unlock_bh(&ctx->decrypt_compl_lock);
+}
+
+static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
+{
+	if (!atomic_dec_and_test(&ctx->decrypt_pending))
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	atomic_inc(&ctx->decrypt_pending);
+
+	return ctx->async_wait.err;
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -253,20 +272,33 @@ static int tls_do_decryption(struct sock *sk,
 		aead_request_set_callback(aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
 					  tls_decrypt_done, aead_req);
+		DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1);
 		atomic_inc(&ctx->decrypt_pending);
 	} else {
+		DECLARE_CRYPTO_WAIT(wait);
+
 		aead_request_set_callback(aead_req,
 					  CRYPTO_TFM_REQ_MAY_BACKLOG,
-					  crypto_req_done, &ctx->async_wait);
+					  crypto_req_done, &wait);
+		ret = crypto_aead_decrypt(aead_req);
+		if (ret == -EINPROGRESS || ret == -EBUSY)
+			ret = crypto_wait_req(ret, &wait);
+		return ret;
 	}
 
 	ret = crypto_aead_decrypt(aead_req);
-	if (ret == -EINPROGRESS) {
-		if (darg->async)
-			return 0;
+	if (ret == -EINPROGRESS)
+		return 0;
 
-		ret = crypto_wait_req(ret, &ctx->async_wait);
+	if (ret == -EBUSY) {
+		ret = tls_decrypt_async_wait(ctx);
+		darg->async_done = true;
+		/* all completions have run, we're not doing async anymore */
+		darg->async = false;
+		return ret;
 	}
+
+	atomic_dec(&ctx->decrypt_pending);
 	darg->async = false;
 
 	return ret;
@@ -439,9 +471,10 @@ static void tls_encrypt_done(void *data, int err)
 	struct tls_rec *rec = data;
 	struct scatterlist *sge;
 	struct sk_msg *msg_en;
-	bool ready = false;
 	struct sock *sk;
-	int pending;
+
+	if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */
+		return;
 
 	msg_en = &rec->msg_encrypted;
 
@@ -476,23 +509,25 @@ static void tls_encrypt_done(void *data, int err)
 		/* If received record is at head of tx_list, schedule tx */
 		first_rec = list_first_entry(&ctx->tx_list,
 					     struct tls_rec, list);
-		if (rec == first_rec)
-			ready = true;
+		if (rec == first_rec) {
+			/* Schedule the transmission */
+			if (!test_and_set_bit(BIT_TX_SCHEDULED,
+					      &ctx->tx_bitmask))
+				schedule_delayed_work(&ctx->tx_work.work, 1);
+		}
 	}
 
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	pending = atomic_dec_return(&ctx->encrypt_pending);
-
-	if (!pending && ctx->async_notify)
+	if (atomic_dec_and_test(&ctx->encrypt_pending))
 		complete(&ctx->async_wait.completion);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
+}
 
-	if (!ready)
-		return;
+static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
+{
+	if (!atomic_dec_and_test(&ctx->encrypt_pending))
+		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	atomic_inc(&ctx->encrypt_pending);
 
-	/* Schedule the transmission */
-	if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
-		schedule_delayed_work(&ctx->tx_work.work, 1);
+	return ctx->async_wait.err;
 }
 
 static int tls_do_encryption(struct sock *sk,
@@ -541,9 +576,14 @@ static int tls_do_encryption(struct sock *sk,
 
 	/* Add the record in tx_list */
 	list_add_tail((struct list_head *)&rec->list, &ctx->tx_list);
+	DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1);
 	atomic_inc(&ctx->encrypt_pending);
 
 	rc = crypto_aead_encrypt(aead_req);
+	if (rc == -EBUSY) {
+		rc = tls_encrypt_async_wait(ctx);
+		rc = rc ?: -EINPROGRESS;
+	}
 	if (!rc || rc != -EINPROGRESS) {
 		atomic_dec(&ctx->encrypt_pending);
 		sge->offset -= prot->prepend_size;
@@ -984,7 +1024,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
-	int pending;
 
 	if (!eor && (msg->msg_flags & MSG_EOR))
 		return -EINVAL;
@@ -1163,24 +1202,12 @@ trim_sgl:
 	if (!num_async) {
 		goto send_end;
 	} else if (num_zc) {
-		/* Wait for pending encryptions to get completed */
-		spin_lock_bh(&ctx->encrypt_compl_lock);
-		ctx->async_notify = true;
-
-		pending = atomic_read(&ctx->encrypt_pending);
-		spin_unlock_bh(&ctx->encrypt_compl_lock);
-		if (pending)
-			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
-		else
-			reinit_completion(&ctx->async_wait.completion);
-
-		/* There can be no concurrent accesses, since we have no
-		 * pending encrypt operations
-		 */
-		WRITE_ONCE(ctx->async_notify, false);
+		int err;
 
-		if (ctx->async_wait.err) {
-			ret = ctx->async_wait.err;
+		/* Wait for pending encryptions to get completed */
+		err = tls_encrypt_async_wait(ctx);
+		if (err) {
+			ret = err;
 			copied = 0;
 		}
 	}
@@ -1229,7 +1256,6 @@ void tls_sw_splice_eof(struct socket *sock)
 	ssize_t copied = 0;
 	bool retrying = false;
 	int ret = 0;
-	int pending;
 
 	if (!ctx->open_rec)
 		return;
@@ -1264,22 +1290,7 @@ retry:
 	}
 
 	/* Wait for pending encryptions to get completed */
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	ctx->async_notify = true;
-
-	pending = atomic_read(&ctx->encrypt_pending);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
-	if (pending)
-		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
-	else
-		reinit_completion(&ctx->async_wait.completion);
-
-	/* There can be no concurrent accesses, since we have no pending
-	 * encrypt operations
-	 */
-	WRITE_ONCE(ctx->async_notify, false);
-
-	if (ctx->async_wait.err)
+	if (tls_encrypt_async_wait(ctx))
 		goto unlock;
 
 	/* Transmit if any encryptions have completed */
@@ -1581,12 +1592,16 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 	} else if (out_sg) {
 		memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
 	}
+	dctx->free_sgout = !!pages;
 
 	/* Prepare and submit AEAD request */
 	err = tls_do_decryption(sk, sgin, sgout, dctx->iv,
 				data_len + prot->tail_size, aead_req, darg);
-	if (err)
+	if (err) {
+		if (darg->async_done)
+			goto exit_free_skb;
 		goto exit_free_pages;
+	}
 
 	darg->skb = clear_skb ?: tls_strp_msg(ctx);
 	clear_skb = NULL;
@@ -1598,6 +1613,9 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
 		return err;
 	}
 
+	if (unlikely(darg->async_done))
+		return 0;
+
 	if (prot->tail_size)
 		darg->tail = dctx->tail;
 
@@ -1769,7 +1787,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 			   u8 *control,
 			   size_t skip,
 			   size_t len,
-			   bool is_peek)
+			   bool is_peek,
+			   bool *more)
 {
 	struct sk_buff *skb = skb_peek(&ctx->rx_list);
 	struct tls_msg *tlm;
@@ -1782,7 +1801,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 		err = tls_record_content_type(msg, tlm, control);
 		if (err <= 0)
-			goto out;
+			goto more;
 
 		if (skip < rxm->full_len)
 			break;
@@ -1800,12 +1819,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 		err = tls_record_content_type(msg, tlm, control);
 		if (err <= 0)
-			goto out;
+			goto more;
 
 		err = skb_copy_datagram_msg(skb, rxm->offset + skip,
 					    msg, chunk);
 		if (err < 0)
-			goto out;
+			goto more;
 
 		len = len - chunk;
 		copied = copied + chunk;
@@ -1841,6 +1860,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx,
 
 out:
 	return copied ? : err;
+more:
+	if (more)
+		*more = true;
+	goto out;
 }
 
 static bool
@@ -1940,10 +1963,12 @@ int tls_sw_recvmsg(struct sock *sk,
 	struct strp_msg *rxm;
 	struct tls_msg *tlm;
 	ssize_t copied = 0;
+	ssize_t peeked = 0;
 	bool async = false;
 	int target, err;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
+	bool rx_more = false;
 	bool released = true;
 	bool bpf_strp_enabled;
 	bool zc_capable;
@@ -1963,12 +1988,12 @@ int tls_sw_recvmsg(struct sock *sk,
 		goto end;
 
 	/* Process pending decrypted records. It must be non-zero-copy */
-	err = process_rx_list(ctx, msg, &control, 0, len, is_peek);
+	err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more);
 	if (err < 0)
 		goto end;
 
 	copied = err;
-	if (len <= copied)
+	if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more)
 		goto end;
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
@@ -2061,6 +2086,8 @@ put_on_rx_list:
 				decrypted += chunk;
 				len -= chunk;
 				__skb_queue_tail(&ctx->rx_list, skb);
+				if (unlikely(control != TLS_RECORD_TYPE_DATA))
+					break;
 				continue;
 			}
 
@@ -2084,8 +2111,10 @@ put_on_rx_list:
 			if (err < 0)
 				goto put_on_rx_list_err;
 
-			if (is_peek)
+			if (is_peek) {
+				peeked += chunk;
 				goto put_on_rx_list;
+			}
 
 			if (partially_consumed) {
 				rxm->offset += chunk;
@@ -2109,16 +2138,10 @@ put_on_rx_list:
 
 recv_end:
 	if (async) {
-		int ret, pending;
+		int ret;
 
 		/* Wait for all previously submitted records to be decrypted */
-		spin_lock_bh(&ctx->decrypt_compl_lock);
-		reinit_completion(&ctx->async_wait.completion);
-		pending = atomic_read(&ctx->decrypt_pending);
-		spin_unlock_bh(&ctx->decrypt_compl_lock);
-		ret = 0;
-		if (pending)
-			ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+		ret = tls_decrypt_async_wait(ctx);
 		__skb_queue_purge(&ctx->async_hold);
 
 		if (ret) {
@@ -2130,12 +2153,11 @@ recv_end:
 
 		/* Drain records from the rx_list & copy if required */
 		if (is_peek || is_kvec)
-			err = process_rx_list(ctx, msg, &control, copied,
-					      decrypted, is_peek);
+			err = process_rx_list(ctx, msg, &control, copied + peeked,
+					      decrypted - peeked, is_peek, NULL);
 		else
 			err = process_rx_list(ctx, msg, &control, 0,
-					      async_copy_bytes, is_peek);
-		decrypted += max(err, 0);
+					      async_copy_bytes, is_peek, NULL);
 	}
 
 	copied += decrypted;
@@ -2435,16 +2457,9 @@ void tls_sw_release_resources_tx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
 	struct tls_rec *rec, *tmp;
-	int pending;
 
 	/* Wait for any pending async encryptions to complete */
-	spin_lock_bh(&ctx->encrypt_compl_lock);
-	ctx->async_notify = true;
-	pending = atomic_read(&ctx->encrypt_pending);
-	spin_unlock_bh(&ctx->encrypt_compl_lock);
-
-	if (pending)
-		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+	tls_encrypt_async_wait(ctx);
 
 	tls_tx_records(sk, -1);
 
@@ -2607,7 +2622,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc
 	}
 
 	crypto_init_wait(&sw_ctx_tx->async_wait);
-	spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
+	atomic_set(&sw_ctx_tx->encrypt_pending, 1);
 	INIT_LIST_HEAD(&sw_ctx_tx->tx_list);
 	INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler);
 	sw_ctx_tx->tx_work.sk = sk;
@@ -2628,7 +2643,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx)
 	}
 
 	crypto_init_wait(&sw_ctx_rx->async_wait);
-	spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
+	atomic_set(&sw_ctx_rx->decrypt_pending, 1);
 	init_waitqueue_head(&sw_ctx_rx->wq);
 	skb_queue_head_init(&sw_ctx_rx->rx_list);
 	skb_queue_head_init(&sw_ctx_rx->async_hold);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ac1f2bc18fc9..0748e7ea5210 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t);
 static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t,
 				  int);
 
-static int unix_set_peek_off(struct sock *sk, int val)
-{
-	struct unix_sock *u = unix_sk(sk);
-
-	if (mutex_lock_interruptible(&u->iolock))
-		return -EINTR;
-
-	WRITE_ONCE(sk->sk_peek_off, val);
-	mutex_unlock(&u->iolock);
-
-	return 0;
-}
-
 #ifdef CONFIG_PROC_FS
 static int unix_count_nr_fds(struct sock *sk)
 {
@@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = {
 	.read_skb =	unix_stream_read_skb,
 	.mmap =		sock_no_mmap,
 	.splice_read =	unix_stream_splice_read,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = {
 	.read_skb =	unix_read_skb,
 	.recvmsg =	unix_dgram_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = {
 	.sendmsg =	unix_seqpacket_sendmsg,
 	.recvmsg =	unix_seqpacket_recvmsg,
 	.mmap =		sock_no_mmap,
-	.set_peek_off =	unix_set_peek_off,
+	.set_peek_off =	sk_set_peek_off,
 	.show_fdinfo =	unix_show_fdinfo,
 };
 
@@ -1344,13 +1331,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
-		unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
+	unix_state_lock(sk1);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1591,7 +1576,7 @@ restart:
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);
diff --git a/net/unix/diag.c b/net/unix/diag.c
index bec09a3a1d44..be19827eca36 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 			 * queue lock. With the other's queue locked it's
 			 * OK to lock the state.
 			 */
-			unix_state_lock_nested(req);
+			unix_state_lock_nested(req, U_LOCK_DIAG);
 			peer = unix_sk(req)->peer;
 			buf[i++] = (peer ? sock_i_ino(peer) : 0);
 			unix_state_unlock(req);
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 2405f0f9af31..2a81880dac7b 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -284,9 +284,17 @@ void unix_gc(void)
 	 * which are creating the cycle(s).
 	 */
 	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
+	list_for_each_entry(u, &gc_candidates, link) {
 		scan_children(&u->sk, inc_inflight, &hitlist);
 
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+		if (u->oob_skb) {
+			kfree_skb(u->oob_skb);
+			u->oob_skb = NULL;
+		}
+#endif
+	}
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 409d74c57ca0..3fb1b637352a 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1661,6 +1661,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy,
 			      unsigned long delay)
 {
 	if (!delay) {
+		del_timer(&dwork->timer);
 		wiphy_work_queue(wiphy, &dwork->work);
 		return;
 	}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b09700400d09..bd54a928bab4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4197,6 +4197,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)
 
 		if (ntype != NL80211_IFTYPE_MESH_POINT)
 			return -EINVAL;
+		if (otype != NL80211_IFTYPE_MESH_POINT)
+			return -EINVAL;
 		if (netif_running(dev))
 			return -EBUSY;
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2249b1a89d1c..389a52c29bfc 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1731,6 +1731,61 @@ static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known,
 	}
 }
 
+static void cfg80211_check_stuck_ecsa(struct cfg80211_registered_device *rdev,
+				      struct cfg80211_internal_bss *known,
+				      const struct cfg80211_bss_ies *old)
+{
+	const struct ieee80211_ext_chansw_ie *ecsa;
+	const struct element *elem_new, *elem_old;
+	const struct cfg80211_bss_ies *new, *bcn;
+
+	if (known->pub.proberesp_ecsa_stuck)
+		return;
+
+	new = rcu_dereference_protected(known->pub.proberesp_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (WARN_ON(!new))
+		return;
+
+	if (new->tsf - old->tsf < USEC_PER_SEC)
+		return;
+
+	elem_old = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      old->data, old->len);
+	if (!elem_old)
+		return;
+
+	elem_new = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+				      new->data, new->len);
+	if (!elem_new)
+		return;
+
+	bcn = rcu_dereference_protected(known->pub.beacon_ies,
+					lockdep_is_held(&rdev->bss_lock));
+	if (bcn &&
+	    cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+			       bcn->data, bcn->len))
+		return;
+
+	if (elem_new->datalen != elem_old->datalen)
+		return;
+	if (elem_new->datalen < sizeof(struct ieee80211_ext_chansw_ie))
+		return;
+	if (memcmp(elem_new->data, elem_old->data, elem_new->datalen))
+		return;
+
+	ecsa = (void *)elem_new->data;
+
+	if (!ecsa->mode)
+		return;
+
+	if (ecsa->new_ch_num !=
+	    ieee80211_frequency_to_channel(known->pub.channel->center_freq))
+		return;
+
+	known->pub.proberesp_ecsa_stuck = 1;
+}
+
 static bool
 cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *known,
@@ -1750,8 +1805,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 		/* Override possible earlier Beacon frame IEs */
 		rcu_assign_pointer(known->pub.ies,
 				   new->pub.proberesp_ies);
-		if (old)
+		if (old) {
+			cfg80211_check_stuck_ecsa(rdev, known, old);
 			kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+		}
 	}
 
 	if (rcu_access_pointer(new->pub.beacon_ies)) {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 1eadfac03cc4..b78c0e095e22 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -722,7 +722,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			memcpy(vaddr, buffer, len);
 			kunmap_local(vaddr);
 
-			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
+			skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
+			refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
 		}
 
 		if (first_frag && desc->options & XDP_TX_METADATA) {
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 41533c631431..e6da7e8495c9 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void)
 }
 EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
 
+MODULE_DESCRIPTION("XFRM Algorithm interface");
 MODULE_LICENSE("GPL");
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 3784534c9185..653e51ae3964 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -407,7 +407,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct net_device *dev = x->xso.dev;
 
-	if (!x->type_offload || x->encap)
+	if (!x->type_offload)
 		return false;
 
 	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET ||
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 662c83beb345..e5722c95b8bb 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -704,9 +704,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	int family;
 	int err;
 
-	switch (x->outer_mode.family) {
+	family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family
+		: skb_dst(skb)->ops->family;
+
+	switch (family) {
 	case AF_INET:
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 		IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 1b7e75159727..da6ecc6b3e15 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2694,7 +2694,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 			if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m)
 				mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
 
-			family = xfrm[i]->props.family;
+			if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				family = xfrm[i]->props.family;
+
 			oif = fl->flowi_oif ? : fl->flowi_l3mdev;
 			dst = xfrm_dst_lookup(xfrm[i], tos, oif,
 					      &saddr, &daddr, family, mark);
@@ -3416,7 +3418,7 @@ decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reve
 	}
 
 	fl4->flowi4_proto = flkeys->basic.ip_proto;
-	fl4->flowi4_tos = flkeys->ip.tos;
+	fl4->flowi4_tos = flkeys->ip.tos & ~INET_ECN_MASK;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ad01997c3aa9..912c1189ba41 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb)
 	if (xp->xfrm_nr == 0)
 		return 0;
 
+	if (xp->xfrm_nr > XFRM_MAX_DEPTH)
+		return -ENOBUFS;
+
 	for (i = 0; i < xp->xfrm_nr; i++) {
 		struct xfrm_user_tmpl *up = &vec[i];
 		struct xfrm_tmpl *kp = &xp->xfrm_vec[i];
@@ -3888,5 +3891,6 @@ static void __exit xfrm_user_exit(void)
 
 module_init(xfrm_user_init);
 module_exit(xfrm_user_exit);
+MODULE_DESCRIPTION("XFRM User interface");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);
diff --git a/rust/Makefile b/rust/Makefile
index 9d2a16cc91cb..a78fcf4004b0 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -40,7 +40,7 @@ obj-$(CONFIG_RUST_KERNEL_DOCTESTS) += doctests_kernel_generated_kunit.o
 ifdef CONFIG_RUST
 
 # `$(rust_flags)` is passed in case the user added `--sysroot`.
-rustc_sysroot := $(shell $(RUSTC) $(rust_flags) --print sysroot)
+rustc_sysroot := $(shell MAKEFLAGS= $(RUSTC) $(rust_flags) --print sysroot)
 rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2)
 RUST_LIB_SRC ?= $(rustc_sysroot)/lib/rustlib/src/rust/library
 
@@ -108,14 +108,14 @@ rustdoc-macros: private rustdoc_host = yes
 rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \
     --extern proc_macro
 rustdoc-macros: $(src)/macros/lib.rs FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-core: private rustc_target_flags = $(core-cfgs)
 rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 # We need to allow `rustdoc::broken_intra_doc_links` because some
 # `no_global_oom_handling` functions refer to non-`no_global_oom_handling`
@@ -124,7 +124,7 @@ rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE
 rustdoc-alloc: private rustc_target_flags = $(alloc-cfgs) \
     -Arustdoc::broken_intra_doc_links
 rustdoc-alloc: $(src)/alloc/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 rustdoc-kernel: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \
@@ -132,7 +132,7 @@ rustdoc-kernel: private rustc_target_flags = --extern alloc \
 rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \
     rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \
     $(obj)/bindings.o FORCE
-	$(call if_changed,rustdoc)
+	+$(call if_changed,rustdoc)
 
 quiet_cmd_rustc_test_library = RUSTC TL $<
       cmd_rustc_test_library = \
@@ -146,18 +146,18 @@ quiet_cmd_rustc_test_library = RUSTC TL $<
 		--crate-name $(subst rusttest-,,$(subst rusttestlib-,,$@)) $<
 
 rusttestlib-build_error: $(src)/build_error.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-macros: private rustc_target_flags = --extern proc_macro
 rusttestlib-macros: private rustc_test_library_proc = yes
 rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 rusttestlib-uapi: $(src)/uapi/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test_library)
 
 quiet_cmd_rustdoc_test = RUSTDOC T $<
       cmd_rustdoc_test = \
@@ -189,7 +189,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
     $(src)/kernel/lib.rs $(obj)/kernel.o \
     $(objtree)/scripts/rustdoc_test_builder \
     $(objtree)/scripts/rustdoc_test_gen FORCE
-	$(call if_changed,rustdoc_test_kernel)
+	+$(call if_changed,rustdoc_test_kernel)
 
 # We cannot use `-Zpanic-abort-tests` because some tests are dynamic,
 # so for the moment we skip `-Cpanic=abort`.
@@ -254,21 +254,21 @@ quiet_cmd_rustsysroot = RUSTSYSROOT
 		$(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib
 
 rusttest-prepare: FORCE
-	$(call if_changed,rustsysroot)
+	+$(call if_changed,rustsysroot)
 
 rusttest-macros: private rustc_target_flags = --extern proc_macro
 rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro
 rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE
-	$(call if_changed,rustc_test)
-	$(call if_changed,rustdoc_test)
+	+$(call if_changed,rustc_test)
+	+$(call if_changed,rustdoc_test)
 
 rusttest-kernel: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros --extern bindings --extern uapi
 rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \
     rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \
     rusttestlib-uapi FORCE
-	$(call if_changed,rustc_test)
-	$(call if_changed,rustc_test_library)
+	+$(call if_changed,rustc_test)
+	+$(call if_changed,rustc_test_library)
 
 ifdef CONFIG_CC_IS_CLANG
 bindgen_c_flags = $(c_flags)
@@ -396,7 +396,7 @@ quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@
 # Therefore, to get `libmacros.so` automatically recompiled when the compiler
 # version changes, we add `core.o` as a dependency (even if it is not needed).
 $(obj)/libmacros.so: $(src)/macros/lib.rs $(obj)/core.o FORCE
-	$(call if_changed_dep,rustc_procmacro)
+	+$(call if_changed_dep,rustc_procmacro)
 
 quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@
       cmd_rustc_library = \
@@ -435,36 +435,36 @@ $(obj)/core.o: private skip_flags = -Dunreachable_pub
 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym))
 $(obj)/core.o: private rustc_target_flags = $(core-cfgs)
 $(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs scripts/target.json FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
 $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/alloc.o: private skip_clippy = 1
 $(obj)/alloc.o: private skip_flags = -Dunreachable_pub
 $(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs)
 $(obj)/alloc.o: $(src)/alloc/lib.rs $(obj)/compiler_builtins.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/bindings.o: $(src)/bindings/lib.rs \
     $(obj)/compiler_builtins.o \
     $(obj)/bindings/bindings_generated.rs \
     $(obj)/bindings/bindings_helpers_generated.rs FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/uapi.o: $(src)/uapi/lib.rs \
     $(obj)/compiler_builtins.o \
     $(obj)/uapi/uapi_generated.rs FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 $(obj)/kernel.o: private rustc_target_flags = --extern alloc \
     --extern build_error --extern macros --extern bindings --extern uapi
 $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \
     $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE
-	$(call if_changed_dep,rustc_library)
+	+$(call if_changed_dep,rustc_library)
 
 endif # CONFIG_RUST
diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs
index 150e13750ff7..abb791cc2371 100644
--- a/rust/alloc/alloc.rs
+++ b/rust/alloc/alloc.rs
@@ -379,13 +379,20 @@ pub const fn handle_alloc_error(layout: Layout) -> ! {
         panic!("allocation failed");
     }
 
+    #[inline]
     fn rt_error(layout: Layout) -> ! {
         unsafe {
             __rust_alloc_error_handler(layout.size(), layout.align());
         }
     }
 
-    unsafe { core::intrinsics::const_eval_select((layout,), ct_error, rt_error) }
+    #[cfg(not(feature = "panic_immediate_abort"))]
+    unsafe {
+        core::intrinsics::const_eval_select((layout,), ct_error, rt_error)
+    }
+
+    #[cfg(feature = "panic_immediate_abort")]
+    ct_error(layout)
 }
 
 // For alloc test `std::alloc::handle_alloc_error` can be used directly.
@@ -418,12 +425,14 @@ pub mod __alloc_error_handler {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 /// Specialize clones into pre-allocated, uninitialized memory.
 /// Used by `Box::clone` and `Rc`/`Arc::make_mut`.
 pub(crate) trait WriteCloneIntoRaw: Sized {
     unsafe fn write_clone_into_raw(&self, target: *mut Self);
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Clone> WriteCloneIntoRaw for T {
     #[inline]
     default unsafe fn write_clone_into_raw(&self, target: *mut Self) {
@@ -433,6 +442,7 @@ impl<T: Clone> WriteCloneIntoRaw for T {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Copy> WriteCloneIntoRaw for T {
     #[inline]
     unsafe fn write_clone_into_raw(&self, target: *mut Self) {
diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs
index 9620eba17268..c93a22a5c97f 100644
--- a/rust/alloc/boxed.rs
+++ b/rust/alloc/boxed.rs
@@ -161,7 +161,7 @@ use core::marker::Tuple;
 use core::marker::Unsize;
 use core::mem::{self, SizedTypeProperties};
 use core::ops::{
-    CoerceUnsized, Deref, DerefMut, DispatchFromDyn, Generator, GeneratorState, Receiver,
+    CoerceUnsized, Coroutine, CoroutineState, Deref, DerefMut, DispatchFromDyn, Receiver,
 };
 use core::pin::Pin;
 use core::ptr::{self, NonNull, Unique};
@@ -211,7 +211,7 @@ impl<T> Box<T> {
     /// ```
     /// let five = Box::new(5);
     /// ```
-    #[cfg(all(not(no_global_oom_handling)))]
+    #[cfg(not(no_global_oom_handling))]
     #[inline(always)]
     #[stable(feature = "rust1", since = "1.0.0")]
     #[must_use]
@@ -1042,10 +1042,18 @@ impl<T: ?Sized, A: Allocator> Box<T, A> {
     /// use std::ptr;
     ///
     /// let x = Box::new(String::from("Hello"));
-    /// let p = Box::into_raw(x);
+    /// let ptr = Box::into_raw(x);
     /// unsafe {
-    ///     ptr::drop_in_place(p);
-    ///     dealloc(p as *mut u8, Layout::new::<String>());
+    ///     ptr::drop_in_place(ptr);
+    ///     dealloc(ptr as *mut u8, Layout::new::<String>());
+    /// }
+    /// ```
+    /// Note: This is equivalent to the following:
+    /// ```
+    /// let x = Box::new(String::from("Hello"));
+    /// let ptr = Box::into_raw(x);
+    /// unsafe {
+    ///     drop(Box::from_raw(ptr));
     /// }
     /// ```
     ///
@@ -2110,28 +2118,28 @@ impl<T: ?Sized, A: Allocator> AsMut<T> for Box<T, A> {
 #[stable(feature = "pin", since = "1.33.0")]
 impl<T: ?Sized, A: Allocator> Unpin for Box<T, A> where A: 'static {}
 
-#[unstable(feature = "generator_trait", issue = "43122")]
-impl<G: ?Sized + Generator<R> + Unpin, R, A: Allocator> Generator<R> for Box<G, A>
+#[unstable(feature = "coroutine_trait", issue = "43122")]
+impl<G: ?Sized + Coroutine<R> + Unpin, R, A: Allocator> Coroutine<R> for Box<G, A>
 where
     A: 'static,
 {
     type Yield = G::Yield;
     type Return = G::Return;
 
-    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState<Self::Yield, Self::Return> {
         G::resume(Pin::new(&mut *self), arg)
     }
 }
 
-#[unstable(feature = "generator_trait", issue = "43122")]
-impl<G: ?Sized + Generator<R>, R, A: Allocator> Generator<R> for Pin<Box<G, A>>
+#[unstable(feature = "coroutine_trait", issue = "43122")]
+impl<G: ?Sized + Coroutine<R>, R, A: Allocator> Coroutine<R> for Pin<Box<G, A>>
 where
     A: 'static,
 {
     type Yield = G::Yield;
     type Return = G::Return;
 
-    fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> {
+    fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState<Self::Yield, Self::Return> {
         G::resume((*self).as_mut(), arg)
     }
 }
@@ -2448,4 +2456,8 @@ impl<T: core::error::Error> core::error::Error for Box<T> {
     fn source(&self) -> Option<&(dyn core::error::Error + 'static)> {
         core::error::Error::source(&**self)
     }
+
+    fn provide<'b>(&'b self, request: &mut core::error::Request<'b>) {
+        core::error::Error::provide(&**self, request);
+    }
 }
diff --git a/rust/alloc/collections/mod.rs b/rust/alloc/collections/mod.rs
index 2506065d158a..00ffb3b97365 100644
--- a/rust/alloc/collections/mod.rs
+++ b/rust/alloc/collections/mod.rs
@@ -150,6 +150,7 @@ impl Display for TryReserveError {
 
 /// An intermediate trait for specialization of `Extend`.
 #[doc(hidden)]
+#[cfg(not(no_global_oom_handling))]
 trait SpecExtend<I: IntoIterator> {
     /// Extends `self` with the contents of the given iterator.
     fn spec_extend(&mut self, iter: I);
diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs
index 9c7ea73da108..36f79c075593 100644
--- a/rust/alloc/lib.rs
+++ b/rust/alloc/lib.rs
@@ -80,6 +80,8 @@
     not(no_sync),
     target_has_atomic = "ptr"
 ))]
+#![doc(rust_logo)]
+#![feature(rustdoc_internals)]
 #![no_std]
 #![needs_allocator]
 // Lints:
@@ -115,7 +117,6 @@
 #![feature(const_eval_select)]
 #![feature(const_maybe_uninit_as_mut_ptr)]
 #![feature(const_maybe_uninit_write)]
-#![feature(const_maybe_uninit_zeroed)]
 #![feature(const_pin)]
 #![feature(const_refs_to_cell)]
 #![feature(const_size_of_val)]
@@ -141,7 +142,6 @@
 #![feature(maybe_uninit_uninit_array)]
 #![feature(maybe_uninit_uninit_array_transpose)]
 #![feature(pattern)]
-#![feature(pointer_byte_offsets)]
 #![feature(ptr_internals)]
 #![feature(ptr_metadata)]
 #![feature(ptr_sub_ptr)]
@@ -156,6 +156,7 @@
 #![feature(std_internals)]
 #![feature(str_internals)]
 #![feature(strict_provenance)]
+#![feature(trusted_fused)]
 #![feature(trusted_len)]
 #![feature(trusted_random_access)]
 #![feature(try_trait_v2)]
@@ -168,7 +169,7 @@
 //
 // Language features:
 // tidy-alphabetical-start
-#![cfg_attr(not(test), feature(generator_trait))]
+#![cfg_attr(not(test), feature(coroutine_trait))]
 #![cfg_attr(test, feature(panic_update_hook))]
 #![cfg_attr(test, feature(test))]
 #![feature(allocator_internals)]
@@ -276,7 +277,7 @@ pub(crate) mod test_helpers {
     /// seed not being the same for every RNG invocation too.
     pub(crate) fn test_rng() -> rand_xorshift::XorShiftRng {
         use std::hash::{BuildHasher, Hash, Hasher};
-        let mut hasher = std::collections::hash_map::RandomState::new().build_hasher();
+        let mut hasher = std::hash::RandomState::new().build_hasher();
         std::panic::Location::caller().hash(&mut hasher);
         let hc64 = hasher.finish();
         let seed_vec =
diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs
index a7425582a323..98b6abf30af6 100644
--- a/rust/alloc/raw_vec.rs
+++ b/rust/alloc/raw_vec.rs
@@ -27,6 +27,16 @@ enum AllocInit {
     Zeroed,
 }
 
+#[repr(transparent)]
+#[cfg_attr(target_pointer_width = "16", rustc_layout_scalar_valid_range_end(0x7fff))]
+#[cfg_attr(target_pointer_width = "32", rustc_layout_scalar_valid_range_end(0x7fff_ffff))]
+#[cfg_attr(target_pointer_width = "64", rustc_layout_scalar_valid_range_end(0x7fff_ffff_ffff_ffff))]
+struct Cap(usize);
+
+impl Cap {
+    const ZERO: Cap = unsafe { Cap(0) };
+}
+
 /// A low-level utility for more ergonomically allocating, reallocating, and deallocating
 /// a buffer of memory on the heap without having to worry about all the corner cases
 /// involved. This type is excellent for building your own data structures like Vec and VecDeque.
@@ -52,7 +62,12 @@ enum AllocInit {
 #[allow(missing_debug_implementations)]
 pub(crate) struct RawVec<T, A: Allocator = Global> {
     ptr: Unique<T>,
-    cap: usize,
+    /// Never used for ZSTs; it's `capacity()`'s responsibility to return usize::MAX in that case.
+    ///
+    /// # Safety
+    ///
+    /// `cap` must be in the `0..=isize::MAX` range.
+    cap: Cap,
     alloc: A,
 }
 
@@ -121,7 +136,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// the returned `RawVec`.
     pub const fn new_in(alloc: A) -> Self {
         // `cap: 0` means "unallocated". zero-sized types are ignored.
-        Self { ptr: Unique::dangling(), cap: 0, alloc }
+        Self { ptr: Unique::dangling(), cap: Cap::ZERO, alloc }
     }
 
     /// Like `with_capacity`, but parameterized over the choice of
@@ -203,7 +218,7 @@ impl<T, A: Allocator> RawVec<T, A> {
             // here should change to `ptr.len() / mem::size_of::<T>()`.
             Self {
                 ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) },
-                cap: capacity,
+                cap: unsafe { Cap(capacity) },
                 alloc,
             }
         }
@@ -228,7 +243,7 @@ impl<T, A: Allocator> RawVec<T, A> {
         // here should change to `ptr.len() / mem::size_of::<T>()`.
         Ok(Self {
             ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) },
-            cap: capacity,
+            cap: unsafe { Cap(capacity) },
             alloc,
         })
     }
@@ -240,12 +255,13 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// The `ptr` must be allocated (via the given allocator `alloc`), and with the given
     /// `capacity`.
     /// The `capacity` cannot exceed `isize::MAX` for sized types. (only a concern on 32-bit
-    /// systems). ZST vectors may have a capacity up to `usize::MAX`.
+    /// systems). For ZSTs capacity is ignored.
     /// If the `ptr` and `capacity` come from a `RawVec` created via `alloc`, then this is
     /// guaranteed.
     #[inline]
     pub unsafe fn from_raw_parts_in(ptr: *mut T, capacity: usize, alloc: A) -> Self {
-        Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap: capacity, alloc }
+        let cap = if T::IS_ZST { Cap::ZERO } else { unsafe { Cap(capacity) } };
+        Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap, alloc }
     }
 
     /// Gets a raw pointer to the start of the allocation. Note that this is
@@ -261,7 +277,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// This will always be `usize::MAX` if `T` is zero-sized.
     #[inline(always)]
     pub fn capacity(&self) -> usize {
-        if T::IS_ZST { usize::MAX } else { self.cap }
+        if T::IS_ZST { usize::MAX } else { self.cap.0 }
     }
 
     /// Returns a shared reference to the allocator backing this `RawVec`.
@@ -270,7 +286,7 @@ impl<T, A: Allocator> RawVec<T, A> {
     }
 
     fn current_memory(&self) -> Option<(NonNull<u8>, Layout)> {
-        if T::IS_ZST || self.cap == 0 {
+        if T::IS_ZST || self.cap.0 == 0 {
             None
         } else {
             // We could use Layout::array here which ensures the absence of isize and usize overflows
@@ -280,7 +296,7 @@ impl<T, A: Allocator> RawVec<T, A> {
             let _: () = const { assert!(mem::size_of::<T>() % mem::align_of::<T>() == 0) };
             unsafe {
                 let align = mem::align_of::<T>();
-                let size = mem::size_of::<T>().unchecked_mul(self.cap);
+                let size = mem::size_of::<T>().unchecked_mul(self.cap.0);
                 let layout = Layout::from_size_align_unchecked(size, align);
                 Some((self.ptr.cast().into(), layout))
             }
@@ -338,10 +354,13 @@ impl<T, A: Allocator> RawVec<T, A> {
     /// The same as `reserve`, but returns on errors instead of panicking or aborting.
     pub fn try_reserve(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> {
         if self.needs_to_grow(len, additional) {
-            self.grow_amortized(len, additional)
-        } else {
-            Ok(())
+            self.grow_amortized(len, additional)?;
         }
+        unsafe {
+            // Inform the optimizer that the reservation has succeeded or wasn't needed
+            core::intrinsics::assume(!self.needs_to_grow(len, additional));
+        }
+        Ok(())
     }
 
     /// The same as `reserve_for_push`, but returns on errors instead of panicking or aborting.
@@ -378,7 +397,14 @@ impl<T, A: Allocator> RawVec<T, A> {
         len: usize,
         additional: usize,
     ) -> Result<(), TryReserveError> {
-        if self.needs_to_grow(len, additional) { self.grow_exact(len, additional) } else { Ok(()) }
+        if self.needs_to_grow(len, additional) {
+            self.grow_exact(len, additional)?;
+        }
+        unsafe {
+            // Inform the optimizer that the reservation has succeeded or wasn't needed
+            core::intrinsics::assume(!self.needs_to_grow(len, additional));
+        }
+        Ok(())
     }
 
     /// Shrinks the buffer down to the specified capacity. If the given amount
@@ -404,12 +430,15 @@ impl<T, A: Allocator> RawVec<T, A> {
         additional > self.capacity().wrapping_sub(len)
     }
 
-    fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) {
+    /// # Safety:
+    ///
+    /// `cap` must not exceed `isize::MAX`.
+    unsafe fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) {
         // Allocators currently return a `NonNull<[u8]>` whose length matches
         // the size requested. If that ever changes, the capacity here should
         // change to `ptr.len() / mem::size_of::<T>()`.
         self.ptr = unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) };
-        self.cap = cap;
+        self.cap = unsafe { Cap(cap) };
     }
 
     // This method is usually instantiated many times. So we want it to be as
@@ -434,14 +463,15 @@ impl<T, A: Allocator> RawVec<T, A> {
 
         // This guarantees exponential growth. The doubling cannot overflow
         // because `cap <= isize::MAX` and the type of `cap` is `usize`.
-        let cap = cmp::max(self.cap * 2, required_cap);
+        let cap = cmp::max(self.cap.0 * 2, required_cap);
         let cap = cmp::max(Self::MIN_NON_ZERO_CAP, cap);
 
         let new_layout = Layout::array::<T>(cap);
 
         // `finish_grow` is non-generic over `T`.
         let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
-        self.set_ptr_and_cap(ptr, cap);
+        // SAFETY: finish_grow would have resulted in a capacity overflow if we tried to allocate more than isize::MAX items
+        unsafe { self.set_ptr_and_cap(ptr, cap) };
         Ok(())
     }
 
@@ -460,7 +490,10 @@ impl<T, A: Allocator> RawVec<T, A> {
 
         // `finish_grow` is non-generic over `T`.
         let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?;
-        self.set_ptr_and_cap(ptr, cap);
+        // SAFETY: finish_grow would have resulted in a capacity overflow if we tried to allocate more than isize::MAX items
+        unsafe {
+            self.set_ptr_and_cap(ptr, cap);
+        }
         Ok(())
     }
 
@@ -478,7 +511,7 @@ impl<T, A: Allocator> RawVec<T, A> {
         if cap == 0 {
             unsafe { self.alloc.deallocate(ptr, layout) };
             self.ptr = Unique::dangling();
-            self.cap = 0;
+            self.cap = Cap::ZERO;
         } else {
             let ptr = unsafe {
                 // `Layout::array` cannot overflow here because it would have
@@ -489,7 +522,10 @@ impl<T, A: Allocator> RawVec<T, A> {
                     .shrink(ptr, layout, new_layout)
                     .map_err(|_| AllocError { layout: new_layout, non_exhaustive: () })?
             };
-            self.set_ptr_and_cap(ptr, cap);
+            // SAFETY: if the allocation is valid, then the capacity is too
+            unsafe {
+                self.set_ptr_and_cap(ptr, cap);
+            }
         }
         Ok(())
     }
@@ -569,6 +605,7 @@ fn alloc_guard(alloc_size: usize) -> Result<(), TryReserveError> {
 // ensure that the code generation related to these panics is minimal as there's
 // only one location which panics rather than a bunch throughout the module.
 #[cfg(not(no_global_oom_handling))]
+#[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
 fn capacity_overflow() -> ! {
     panic!("capacity overflow");
 }
diff --git a/rust/alloc/vec/into_iter.rs b/rust/alloc/vec/into_iter.rs
index aac0ec16aef1..136bfe94af6c 100644
--- a/rust/alloc/vec/into_iter.rs
+++ b/rust/alloc/vec/into_iter.rs
@@ -9,7 +9,8 @@ use crate::raw_vec::RawVec;
 use core::array;
 use core::fmt;
 use core::iter::{
-    FusedIterator, InPlaceIterable, SourceIter, TrustedLen, TrustedRandomAccessNoCoerce,
+    FusedIterator, InPlaceIterable, SourceIter, TrustedFused, TrustedLen,
+    TrustedRandomAccessNoCoerce,
 };
 use core::marker::PhantomData;
 use core::mem::{self, ManuallyDrop, MaybeUninit, SizedTypeProperties};
@@ -287,9 +288,7 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> {
         // Also note the implementation of `Self: TrustedRandomAccess` requires
         // that `T: Copy` so reading elements from the buffer doesn't invalidate
         // them for `Drop`.
-        unsafe {
-            if T::IS_ZST { mem::zeroed() } else { ptr::read(self.ptr.add(i)) }
-        }
+        unsafe { if T::IS_ZST { mem::zeroed() } else { ptr::read(self.ptr.add(i)) } }
     }
 }
 
@@ -341,6 +340,10 @@ impl<T, A: Allocator> ExactSizeIterator for IntoIter<T, A> {
 #[stable(feature = "fused", since = "1.26.0")]
 impl<T, A: Allocator> FusedIterator for IntoIter<T, A> {}
 
+#[doc(hidden)]
+#[unstable(issue = "none", feature = "trusted_fused")]
+unsafe impl<T, A: Allocator> TrustedFused for IntoIter<T, A> {}
+
 #[unstable(feature = "trusted_len", issue = "37572")]
 unsafe impl<T, A: Allocator> TrustedLen for IntoIter<T, A> {}
 
@@ -425,7 +428,10 @@ unsafe impl<#[may_dangle] T, A: Allocator> Drop for IntoIter<T, A> {
 // also refer to the vec::in_place_collect module documentation to get an overview
 #[unstable(issue = "none", feature = "inplace_iteration")]
 #[doc(hidden)]
-unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {}
+unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {
+    const EXPAND_BY: Option<NonZeroUsize> = NonZeroUsize::new(1);
+    const MERGE_BY: Option<NonZeroUsize> = NonZeroUsize::new(1);
+}
 
 #[unstable(issue = "none", feature = "inplace_iteration")]
 #[doc(hidden)]
diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs
index 41ca71805ef0..220fb9d6f45b 100644
--- a/rust/alloc/vec/mod.rs
+++ b/rust/alloc/vec/mod.rs
@@ -105,6 +105,7 @@ mod into_iter;
 #[cfg(not(no_global_oom_handling))]
 use self::is_zero::IsZero;
 
+#[cfg(not(no_global_oom_handling))]
 mod is_zero;
 
 #[cfg(not(no_global_oom_handling))]
@@ -123,7 +124,7 @@ use self::set_len_on_drop::SetLenOnDrop;
 mod set_len_on_drop;
 
 #[cfg(not(no_global_oom_handling))]
-use self::in_place_drop::{InPlaceDrop, InPlaceDstBufDrop};
+use self::in_place_drop::{InPlaceDrop, InPlaceDstDataSrcBufDrop};
 
 #[cfg(not(no_global_oom_handling))]
 mod in_place_drop;
@@ -1376,7 +1377,7 @@ impl<T, A: Allocator> Vec<T, A> {
     /// [`as_mut_ptr`]: Vec::as_mut_ptr
     /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
-    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
+    #[rustc_never_returns_null_ptr]
     #[inline]
     pub fn as_ptr(&self) -> *const T {
         // We shadow the slice method of the same name to avoid going through
@@ -1436,7 +1437,7 @@ impl<T, A: Allocator> Vec<T, A> {
     /// [`as_mut_ptr`]: Vec::as_mut_ptr
     /// [`as_ptr`]: Vec::as_ptr
     #[stable(feature = "vec_as_ptr", since = "1.37.0")]
-    #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)]
+    #[rustc_never_returns_null_ptr]
     #[inline]
     pub fn as_mut_ptr(&mut self) -> *mut T {
         // We shadow the slice method of the same name to avoid going through
@@ -1565,7 +1566,8 @@ impl<T, A: Allocator> Vec<T, A> {
     #[stable(feature = "rust1", since = "1.0.0")]
     pub fn swap_remove(&mut self, index: usize) -> T {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("swap_remove index (is {index}) should be < len (is {len})");
         }
@@ -1606,7 +1608,8 @@ impl<T, A: Allocator> Vec<T, A> {
     #[stable(feature = "rust1", since = "1.0.0")]
     pub fn insert(&mut self, index: usize, element: T) {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("insertion index (is {index}) should be <= len (is {len})");
         }
@@ -1667,7 +1670,7 @@ impl<T, A: Allocator> Vec<T, A> {
     #[track_caller]
     pub fn remove(&mut self, index: usize) -> T {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
         #[track_caller]
         fn assert_failed(index: usize, len: usize) -> ! {
             panic!("removal index (is {index}) should be < len (is {len})");
@@ -1891,7 +1894,32 @@ impl<T, A: Allocator> Vec<T, A> {
             return;
         }
 
-        /* INVARIANT: vec.len() > read >= write > write-1 >= 0 */
+        // Check if we ever want to remove anything.
+        // This allows to use copy_non_overlapping in next cycle.
+        // And avoids any memory writes if we don't need to remove anything.
+        let mut first_duplicate_idx: usize = 1;
+        let start = self.as_mut_ptr();
+        while first_duplicate_idx != len {
+            let found_duplicate = unsafe {
+                // SAFETY: first_duplicate always in range [1..len)
+                // Note that we start iteration from 1 so we never overflow.
+                let prev = start.add(first_duplicate_idx.wrapping_sub(1));
+                let current = start.add(first_duplicate_idx);
+                // We explicitly say in docs that references are reversed.
+                same_bucket(&mut *current, &mut *prev)
+            };
+            if found_duplicate {
+                break;
+            }
+            first_duplicate_idx += 1;
+        }
+        // Don't need to remove anything.
+        // We cannot get bigger than len.
+        if first_duplicate_idx == len {
+            return;
+        }
+
+        /* INVARIANT: vec.len() > read > write > write-1 >= 0 */
         struct FillGapOnDrop<'a, T, A: core::alloc::Allocator> {
             /* Offset of the element we want to check if it is duplicate */
             read: usize,
@@ -1937,31 +1965,39 @@ impl<T, A: Allocator> Vec<T, A> {
             }
         }
 
-        let mut gap = FillGapOnDrop { read: 1, write: 1, vec: self };
-        let ptr = gap.vec.as_mut_ptr();
-
         /* Drop items while going through Vec, it should be more efficient than
          * doing slice partition_dedup + truncate */
 
+        // Construct gap first and then drop item to avoid memory corruption if `T::drop` panics.
+        let mut gap =
+            FillGapOnDrop { read: first_duplicate_idx + 1, write: first_duplicate_idx, vec: self };
+        unsafe {
+            // SAFETY: we checked that first_duplicate_idx in bounds before.
+            // If drop panics, `gap` would remove this item without drop.
+            ptr::drop_in_place(start.add(first_duplicate_idx));
+        }
+
         /* SAFETY: Because of the invariant, read_ptr, prev_ptr and write_ptr
          * are always in-bounds and read_ptr never aliases prev_ptr */
         unsafe {
             while gap.read < len {
-                let read_ptr = ptr.add(gap.read);
-                let prev_ptr = ptr.add(gap.write.wrapping_sub(1));
+                let read_ptr = start.add(gap.read);
+                let prev_ptr = start.add(gap.write.wrapping_sub(1));
 
-                if same_bucket(&mut *read_ptr, &mut *prev_ptr) {
+                // We explicitly say in docs that references are reversed.
+                let found_duplicate = same_bucket(&mut *read_ptr, &mut *prev_ptr);
+                if found_duplicate {
                     // Increase `gap.read` now since the drop may panic.
                     gap.read += 1;
                     /* We have found duplicate, drop it in-place */
                     ptr::drop_in_place(read_ptr);
                 } else {
-                    let write_ptr = ptr.add(gap.write);
+                    let write_ptr = start.add(gap.write);
 
-                    /* Because `read_ptr` can be equal to `write_ptr`, we either
-                     * have to use `copy` or conditional `copy_nonoverlapping`.
-                     * Looks like the first option is faster. */
-                    ptr::copy(read_ptr, write_ptr, 1);
+                    /* read_ptr cannot be equal to write_ptr because at this point
+                     * we guaranteed to skip at least one element (before loop starts).
+                     */
+                    ptr::copy_nonoverlapping(read_ptr, write_ptr, 1);
 
                     /* We have filled that place, so go further */
                     gap.write += 1;
@@ -2097,6 +2133,7 @@ impl<T, A: Allocator> Vec<T, A> {
         } else {
             unsafe {
                 self.len -= 1;
+                core::intrinsics::assume(self.len < self.capacity());
                 Some(ptr::read(self.as_ptr().add(self.len())))
             }
         }
@@ -2299,7 +2336,8 @@ impl<T, A: Allocator> Vec<T, A> {
         A: Clone,
     {
         #[cold]
-        #[inline(never)]
+        #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))]
+        #[track_caller]
         fn assert_failed(at: usize, len: usize) -> ! {
             panic!("`at` split index (is {at}) should be <= len (is {len})");
         }
@@ -2840,6 +2878,7 @@ pub fn from_elem_in<T: Clone, A: Allocator>(elem: T, n: usize, alloc: A) -> Vec<
     <T as SpecFromElem>::from_elem(elem, n, alloc)
 }
 
+#[cfg(not(no_global_oom_handling))]
 trait ExtendFromWithinSpec {
     /// # Safety
     ///
@@ -2848,6 +2887,7 @@ trait ExtendFromWithinSpec {
     unsafe fn spec_extend_from_within(&mut self, src: Range<usize>);
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     default unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
         // SAFETY:
@@ -2867,6 +2907,7 @@ impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     }
 }
 
+#[cfg(not(no_global_oom_handling))]
 impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> {
     unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) {
         let count = src.len();
@@ -2947,7 +2988,7 @@ impl<T: Clone, A: Allocator + Clone> Clone for Vec<T, A> {
 /// ```
 /// use std::hash::BuildHasher;
 ///
-/// let b = std::collections::hash_map::RandomState::new();
+/// let b = std::hash::RandomState::new();
 /// let v: Vec<u8> = vec![0xa8, 0x3c, 0x09];
 /// let s: &[u8] = &[0xa8, 0x3c, 0x09];
 /// assert_eq!(b.hash_one(v), b.hash_one(s));
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index c0cb4b05b918..65b98831b975 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -9,12 +9,13 @@
 #include <kunit/test.h>
 #include <linux/errname.h>
 #include <linux/ethtool.h>
+#include <linux/jiffies.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
-#include <linux/slab.h>
 #include <linux/refcount.h>
-#include <linux/wait.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
 #include <linux/workqueue.h>
 
 /* `bindgen` gets confused at certain things. */
diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs
index 4b057e837358..01ad139e19bc 100644
--- a/rust/kernel/allocator.rs
+++ b/rust/kernel/allocator.rs
@@ -35,7 +35,7 @@ unsafe fn krealloc_aligned(ptr: *mut u8, new_layout: Layout, flags: bindings::gf
     // - `ptr` is either null or a pointer returned from a previous `k{re}alloc()` by the
     //   function safety requirement.
     // - `size` is greater than 0 since it's either a `layout.size()` (which cannot be zero
-    //    according to the function safety requirement) or a result from `next_power_of_two()`.
+    //   according to the function safety requirement) or a result from `next_power_of_two()`.
     unsafe { bindings::krealloc(ptr as *const core::ffi::c_void, size, flags) as *mut u8 }
 }
 
diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index 4f0c1edd63b7..4786d3ee1e92 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -264,13 +264,9 @@ pub fn to_result(err: core::ffi::c_int) -> Result {
 ///     pdev: &mut PlatformDevice,
 ///     index: u32,
 /// ) -> Result<*mut core::ffi::c_void> {
-///     // SAFETY: FFI call.
-///     unsafe {
-///         from_err_ptr(bindings::devm_platform_ioremap_resource(
-///             pdev.to_ptr(),
-///             index,
-///         ))
-///     }
+///     // SAFETY: `pdev` points to a valid platform device. There are no safety requirements
+///     // on `index`.
+///     from_err_ptr(unsafe { bindings::devm_platform_ioremap_resource(pdev.to_ptr(), index) })
 /// }
 /// ```
 // TODO: Remove `dead_code` marker once an in-kernel client is available.
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 65be9ae57b80..424257284d16 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -36,7 +36,7 @@
 //!
 //! ```rust
 //! # #![allow(clippy::disallowed_names)]
-//! use kernel::{prelude::*, sync::Mutex, new_mutex};
+//! use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! #[pin_data]
 //! struct Foo {
@@ -56,7 +56,7 @@
 //!
 //! ```rust
 //! # #![allow(clippy::disallowed_names)]
-//! # use kernel::{prelude::*, sync::Mutex, new_mutex};
+//! # use kernel::sync::{new_mutex, Mutex};
 //! # use core::pin::Pin;
 //! # #[pin_data]
 //! # struct Foo {
@@ -79,7 +79,7 @@
 //! above method only works for types where you can access the fields.
 //!
 //! ```rust
-//! # use kernel::{new_mutex, sync::{Arc, Mutex}};
+//! # use kernel::sync::{new_mutex, Arc, Mutex};
 //! let mtx: Result<Arc<Mutex<usize>>> = Arc::pin_init(new_mutex!(42, "example::mtx"));
 //! ```
 //!
@@ -751,10 +751,10 @@ macro_rules! try_init {
 ///
 /// # Safety
 ///
-/// When implementing this type you will need to take great care. Also there are probably very few
+/// When implementing this trait you will need to take great care. Also there are probably very few
 /// cases where a manual implementation is necessary. Use [`pin_init_from_closure`] where possible.
 ///
-/// The [`PinInit::__pinned_init`] function
+/// The [`PinInit::__pinned_init`] function:
 /// - returns `Ok(())` if it initialized every field of `slot`,
 /// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means:
 ///     - `slot` can be deallocated without UB occurring,
@@ -861,10 +861,10 @@ where
 ///
 /// # Safety
 ///
-/// When implementing this type you will need to take great care. Also there are probably very few
+/// When implementing this trait you will need to take great care. Also there are probably very few
 /// cases where a manual implementation is necessary. Use [`init_from_closure`] where possible.
 ///
-/// The [`Init::__init`] function
+/// The [`Init::__init`] function:
 /// - returns `Ok(())` if it initialized every field of `slot`,
 /// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means:
 ///     - `slot` can be deallocated without UB occurring,
@@ -1013,7 +1013,7 @@ pub fn uninit<T, E>() -> impl Init<MaybeUninit<T>, E> {
 ///
 /// ```rust
 /// use kernel::{error::Error, init::init_array_from_fn};
-/// let array: Box<[usize; 1_000]>= Box::init::<Error>(init_array_from_fn(|i| i)).unwrap();
+/// let array: Box<[usize; 1_000]> = Box::init::<Error>(init_array_from_fn(|i| i)).unwrap();
 /// assert_eq!(array.len(), 1_000);
 /// ```
 pub fn init_array_from_fn<I, const N: usize, T, E>(
@@ -1027,7 +1027,7 @@ where
         // Counts the number of initialized elements and when dropped drops that many elements from
         // `slot`.
         let mut init_count = ScopeGuard::new_with_data(0, |i| {
-            // We now free every element that has been initialized before:
+            // We now free every element that has been initialized before.
             // SAFETY: The loop initialized exactly the values from 0..i and since we
             // return `Err` below, the caller will consider the memory at `slot` as
             // uninitialized.
@@ -1056,7 +1056,7 @@ where
 ///
 /// ```rust
 /// use kernel::{sync::{Arc, Mutex}, init::pin_init_array_from_fn, new_mutex};
-/// let array: Arc<[Mutex<usize>; 1_000]>=
+/// let array: Arc<[Mutex<usize>; 1_000]> =
 ///     Arc::pin_init(pin_init_array_from_fn(|i| new_mutex!(i))).unwrap();
 /// assert_eq!(array.len(), 1_000);
 /// ```
@@ -1071,7 +1071,7 @@ where
         // Counts the number of initialized elements and when dropped drops that many elements from
         // `slot`.
         let mut init_count = ScopeGuard::new_with_data(0, |i| {
-            // We now free every element that has been initialized before:
+            // We now free every element that has been initialized before.
             // SAFETY: The loop initialized exactly the values from 0..i and since we
             // return `Err` below, the caller will consider the memory at `slot` as
             // uninitialized.
diff --git a/rust/kernel/ioctl.rs b/rust/kernel/ioctl.rs
index f1d42ab69972..cfa7d080b531 100644
--- a/rust/kernel/ioctl.rs
+++ b/rust/kernel/ioctl.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-//! ioctl() number definitions
+//! `ioctl()` number definitions.
 //!
 //! C header: [`include/asm-generic/ioctl.h`](srctree/include/asm-generic/ioctl.h)
 
@@ -28,13 +28,13 @@ pub const fn _IO(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_NONE, ty, nr, 0)
 }
 
-/// Build an ioctl number for an read-only ioctl.
+/// Build an ioctl number for a read-only ioctl.
 #[inline(always)]
 pub const fn _IOR<T>(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_READ, ty, nr, core::mem::size_of::<T>())
 }
 
-/// Build an ioctl number for an write-only ioctl.
+/// Build an ioctl number for a write-only ioctl.
 #[inline(always)]
 pub const fn _IOW<T>(ty: u32, nr: u32) -> u32 {
     _IOC(uapi::_IOC_WRITE, ty, nr, core::mem::size_of::<T>())
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 7ac39874aeac..be68d5e567b1 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -14,11 +14,9 @@
 #![no_std]
 #![feature(allocator_api)]
 #![feature(coerce_unsized)]
-#![feature(const_maybe_uninit_zeroed)]
 #![feature(dispatch_from_dyn)]
 #![feature(new_uninit)]
 #![feature(offset_of)]
-#![feature(ptr_metadata)]
 #![feature(receiver_trait)]
 #![feature(unsize)]
 
@@ -49,6 +47,7 @@ pub mod std_vendor;
 pub mod str;
 pub mod sync;
 pub mod task;
+pub mod time;
 pub mod types;
 pub mod workqueue;
 
@@ -78,7 +77,7 @@ pub trait Module: Sized + Sync {
 
 /// Equivalent to `THIS_MODULE` in the C API.
 ///
-/// C header: `include/linux/export.h`
+/// C header: [`include/linux/export.h`](srctree/include/linux/export.h)
 pub struct ThisModule(*mut bindings::module);
 
 // SAFETY: `THIS_MODULE` may be used from all threads within a module.
@@ -102,3 +101,35 @@ fn panic(info: &core::panic::PanicInfo<'_>) -> ! {
     // SAFETY: FFI call.
     unsafe { bindings::BUG() };
 }
+
+/// Produces a pointer to an object from a pointer to one of its fields.
+///
+/// # Safety
+///
+/// The pointer passed to this macro, and the pointer returned by this macro, must both be in
+/// bounds of the same allocation.
+///
+/// # Examples
+///
+/// ```
+/// # use kernel::container_of;
+/// struct Test {
+///     a: u64,
+///     b: u32,
+/// }
+///
+/// let test = Test { a: 10, b: 20 };
+/// let b_ptr = &test.b;
+/// // SAFETY: The pointer points at the `b` field of a `Test`, so the resulting pointer will be
+/// // in-bounds of the same allocation as `b_ptr`.
+/// let test_alias = unsafe { container_of!(b_ptr, Test, b) };
+/// assert!(core::ptr::eq(&test, test_alias));
+/// ```
+#[macro_export]
+macro_rules! container_of {
+    ($ptr:expr, $type:ty, $($f:tt)*) => {{
+        let ptr = $ptr as *const _ as *const u8;
+        let offset: usize = ::core::mem::offset_of!($type, $($f)*);
+        ptr.sub(offset) as *const $type
+    }}
+}
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index 7d848b83add4..925ced8fdc61 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -13,9 +13,102 @@ use crate::{
 };
 
 /// Byte string without UTF-8 validity guarantee.
-///
-/// `BStr` is simply an alias to `[u8]`, but has a more evident semantical meaning.
-pub type BStr = [u8];
+#[repr(transparent)]
+pub struct BStr([u8]);
+
+impl BStr {
+    /// Returns the length of this string.
+    #[inline]
+    pub const fn len(&self) -> usize {
+        self.0.len()
+    }
+
+    /// Returns `true` if the string is empty.
+    #[inline]
+    pub const fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// Creates a [`BStr`] from a `[u8]`.
+    #[inline]
+    pub const fn from_bytes(bytes: &[u8]) -> &Self {
+        // SAFETY: `BStr` is transparent to `[u8]`.
+        unsafe { &*(bytes as *const [u8] as *const BStr) }
+    }
+}
+
+impl fmt::Display for BStr {
+    /// Formats printable ASCII characters, escaping the rest.
+    ///
+    /// ```
+    /// # use kernel::{fmt, b_str, str::{BStr, CString}};
+    /// let ascii = b_str!("Hello, BStr!");
+    /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes());
+    ///
+    /// let non_ascii = b_str!("🦀");
+    /// let s = CString::try_from_fmt(fmt!("{}", non_ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes());
+    /// ```
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        for &b in &self.0 {
+            match b {
+                // Common escape codes.
+                b'\t' => f.write_str("\\t")?,
+                b'\n' => f.write_str("\\n")?,
+                b'\r' => f.write_str("\\r")?,
+                // Printable characters.
+                0x20..=0x7e => f.write_char(b as char)?,
+                _ => write!(f, "\\x{:02x}", b)?,
+            }
+        }
+        Ok(())
+    }
+}
+
+impl fmt::Debug for BStr {
+    /// Formats printable ASCII characters with a double quote on either end,
+    /// escaping the rest.
+    ///
+    /// ```
+    /// # use kernel::{fmt, b_str, str::{BStr, CString}};
+    /// // Embedded double quotes are escaped.
+    /// let ascii = b_str!("Hello, \"BStr\"!");
+    /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes());
+    ///
+    /// let non_ascii = b_str!("😺");
+    /// let s = CString::try_from_fmt(fmt!("{:?}", non_ascii)).unwrap();
+    /// assert_eq!(s.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes());
+    /// ```
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.write_char('"')?;
+        for &b in &self.0 {
+            match b {
+                // Common escape codes.
+                b'\t' => f.write_str("\\t")?,
+                b'\n' => f.write_str("\\n")?,
+                b'\r' => f.write_str("\\r")?,
+                // String escape characters.
+                b'\"' => f.write_str("\\\"")?,
+                b'\\' => f.write_str("\\\\")?,
+                // Printable characters.
+                0x20..=0x7e => f.write_char(b as char)?,
+                _ => write!(f, "\\x{:02x}", b)?,
+            }
+        }
+        f.write_char('"')
+    }
+}
+
+impl Deref for BStr {
+    type Target = [u8];
+
+    #[inline]
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
 
 /// Creates a new [`BStr`] from a string literal.
 ///
@@ -33,7 +126,7 @@ pub type BStr = [u8];
 macro_rules! b_str {
     ($str:literal) => {{
         const S: &'static str = $str;
-        const C: &'static $crate::str::BStr = S.as_bytes();
+        const C: &'static $crate::str::BStr = $crate::str::BStr::from_bytes(S.as_bytes());
         C
     }};
 }
@@ -149,13 +242,13 @@ impl CStr {
         self.0.as_ptr() as _
     }
 
-    /// Convert the string to a byte slice without the trailing 0 byte.
+    /// Convert the string to a byte slice without the trailing `NUL` byte.
     #[inline]
     pub fn as_bytes(&self) -> &[u8] {
         &self.0[..self.len()]
     }
 
-    /// Convert the string to a byte slice containing the trailing 0 byte.
+    /// Convert the string to a byte slice containing the trailing `NUL` byte.
     #[inline]
     pub const fn as_bytes_with_nul(&self) -> &[u8] {
         &self.0
@@ -191,9 +284,9 @@ impl CStr {
     /// ```
     /// # use kernel::c_str;
     /// # use kernel::str::CStr;
+    /// let bar = c_str!("ツ");
     /// // SAFETY: String literals are guaranteed to be valid UTF-8
     /// // by the Rust compiler.
-    /// let bar = c_str!("ツ");
     /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ");
     /// ```
     #[inline]
@@ -271,7 +364,7 @@ impl fmt::Debug for CStr {
 impl AsRef<BStr> for CStr {
     #[inline]
     fn as_ref(&self) -> &BStr {
-        self.as_bytes()
+        BStr::from_bytes(self.as_bytes())
     }
 }
 
@@ -280,7 +373,7 @@ impl Deref for CStr {
 
     #[inline]
     fn deref(&self) -> &Self::Target {
-        self.as_bytes()
+        self.as_ref()
     }
 }
 
@@ -327,7 +420,7 @@ where
 
     #[inline]
     fn index(&self, index: Idx) -> &Self::Output {
-        &self.as_bytes()[index]
+        &self.as_ref()[index]
     }
 }
 
@@ -357,6 +450,21 @@ macro_rules! c_str {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use alloc::format;
+
+    const ALL_ASCII_CHARS: &'static str =
+        "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\
+        \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \
+        !\"#$%&'()*+,-./0123456789:;<=>?@\
+        ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\
+        \\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d\\x8e\\x8f\
+        \\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b\\x9c\\x9d\\x9e\\x9f\
+        \\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9\\xaa\\xab\\xac\\xad\\xae\\xaf\
+        \\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\
+        \\xc0\\xc1\\xc2\\xc3\\xc4\\xc5\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\
+        \\xd0\\xd1\\xd2\\xd3\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\
+        \\xe0\\xe1\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef\
+        \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff";
 
     #[test]
     fn test_cstr_to_str() {
@@ -381,6 +489,69 @@ mod tests {
         let unchecked_str = unsafe { checked_cstr.as_str_unchecked() };
         assert_eq!(unchecked_str, "🐧");
     }
+
+    #[test]
+    fn test_cstr_display() {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+        assert_eq!(format!("{}", hello_world), "hello, world!");
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a");
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+    }
+
+    #[test]
+    fn test_cstr_display_all_bytes() {
+        let mut bytes: [u8; 256] = [0; 256];
+        // fill `bytes` with [1..=255] + [0]
+        for i in u8::MIN..=u8::MAX {
+            bytes[i as usize] = i.wrapping_add(1);
+        }
+        let cstr = CStr::from_bytes_with_nul(&bytes).unwrap();
+        assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS);
+    }
+
+    #[test]
+    fn test_cstr_debug() {
+        let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap();
+        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap();
+        assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\"");
+        let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap();
+        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap();
+        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+    }
+
+    #[test]
+    fn test_bstr_display() {
+        let hello_world = BStr::from_bytes(b"hello, world!");
+        assert_eq!(format!("{}", hello_world), "hello, world!");
+        let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
+        assert_eq!(format!("{}", escapes), "_\\t_\\n_\\r_\\_'_\"_");
+        let others = BStr::from_bytes(b"\x01");
+        assert_eq!(format!("{}", others), "\\x01");
+        let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
+        assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu");
+        let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
+        assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80");
+    }
+
+    #[test]
+    fn test_bstr_debug() {
+        let hello_world = BStr::from_bytes(b"hello, world!");
+        assert_eq!(format!("{:?}", hello_world), "\"hello, world!\"");
+        let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_");
+        assert_eq!(format!("{:?}", escapes), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\"");
+        let others = BStr::from_bytes(b"\x01");
+        assert_eq!(format!("{:?}", others), "\"\\x01\"");
+        let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu");
+        assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\"");
+        let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80");
+        assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\"");
+    }
 }
 
 /// Allows formatting of [`fmt::Arguments`] into a raw buffer.
@@ -449,7 +620,7 @@ impl RawFormatter {
         self.pos as _
     }
 
-    /// Return the number of bytes written to the formatter.
+    /// Returns the number of bytes written to the formatter.
     pub(crate) fn bytes_written(&self) -> usize {
         self.pos - self.beg
     }
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index d219ee518eff..c983f63fd56e 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -13,8 +13,9 @@ pub mod lock;
 mod locked_by;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
-pub use condvar::CondVar;
-pub use lock::{mutex::Mutex, spinlock::SpinLock};
+pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
+pub use lock::mutex::{new_mutex, Mutex};
+pub use lock::spinlock::{new_spinlock, SpinLock};
 pub use locked_by::LockedBy;
 
 /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
index 77cdbcf7bd2e..7d4c4bf58388 100644
--- a/rust/kernel/sync/arc.rs
+++ b/rust/kernel/sync/arc.rs
@@ -30,7 +30,7 @@ use core::{
     mem::{ManuallyDrop, MaybeUninit},
     ops::{Deref, DerefMut},
     pin::Pin,
-    ptr::{NonNull, Pointee},
+    ptr::NonNull,
 };
 use macros::pin_data;
 
@@ -56,7 +56,7 @@ mod std_vendor;
 ///     b: u32,
 /// }
 ///
-/// // Create a ref-counted instance of `Example`.
+/// // Create a refcounted instance of `Example`.
 /// let obj = Arc::try_new(Example { a: 10, b: 20 })?;
 ///
 /// // Get a new pointer to `obj` and increment the refcount.
@@ -239,22 +239,20 @@ impl<T: ?Sized> Arc<T> {
         // binary, so its layout is not so large that it can trigger arithmetic overflow.
         let val_offset = unsafe { refcount_layout.extend(val_layout).unwrap_unchecked().1 };
 
-        let metadata: <T as Pointee>::Metadata = core::ptr::metadata(ptr);
-        // SAFETY: The metadata of `T` and `ArcInner<T>` is the same because `ArcInner` is a struct
-        // with `T` as its last field.
+        // Pointer casts leave the metadata unchanged. This is okay because the metadata of `T` and
+        // `ArcInner<T>` is the same since `ArcInner` is a struct with `T` as its last field.
         //
         // This is documented at:
         // <https://doc.rust-lang.org/std/ptr/trait.Pointee.html>.
-        let metadata: <ArcInner<T> as Pointee>::Metadata =
-            unsafe { core::mem::transmute_copy(&metadata) };
+        let ptr = ptr as *const ArcInner<T>;
+
         // SAFETY: The pointer is in-bounds of an allocation both before and after offsetting the
         // pointer, since it originates from a previous call to `Arc::into_raw` and is still valid.
-        let ptr = unsafe { (ptr as *mut u8).sub(val_offset) as *mut () };
-        let ptr = core::ptr::from_raw_parts_mut(ptr, metadata);
+        let ptr = unsafe { ptr.byte_sub(val_offset) };
 
         // SAFETY: By the safety requirements we know that `ptr` came from `Arc::into_raw`, so the
         // reference count held then will be owned by the new `Arc` object.
-        unsafe { Self::from_inner(NonNull::new_unchecked(ptr)) }
+        unsafe { Self::from_inner(NonNull::new_unchecked(ptr.cast_mut())) }
     }
 
     /// Returns an [`ArcBorrow`] from the given [`Arc`].
@@ -365,12 +363,12 @@ impl<T: ?Sized> From<Pin<UniqueArc<T>>> for Arc<T> {
 /// A borrowed reference to an [`Arc`] instance.
 ///
 /// For cases when one doesn't ever need to increment the refcount on the allocation, it is simpler
-/// to use just `&T`, which we can trivially get from an `Arc<T>` instance.
+/// to use just `&T`, which we can trivially get from an [`Arc<T>`] instance.
 ///
 /// However, when one may need to increment the refcount, it is preferable to use an `ArcBorrow<T>`
 /// over `&Arc<T>` because the latter results in a double-indirection: a pointer (shared reference)
-/// to a pointer (`Arc<T>`) to the object (`T`). An [`ArcBorrow`] eliminates this double
-/// indirection while still allowing one to increment the refcount and getting an `Arc<T>` when/if
+/// to a pointer ([`Arc<T>`]) to the object (`T`). An [`ArcBorrow`] eliminates this double
+/// indirection while still allowing one to increment the refcount and getting an [`Arc<T>`] when/if
 /// needed.
 ///
 /// # Invariants
@@ -510,7 +508,7 @@ impl<T: ?Sized> Deref for ArcBorrow<'_, T> {
 /// # test().unwrap();
 /// ```
 ///
-/// In the following example we first allocate memory for a ref-counted `Example` but we don't
+/// In the following example we first allocate memory for a refcounted `Example` but we don't
 /// initialise it on allocation. We do initialise it later with a call to [`UniqueArc::write`],
 /// followed by a conversion to `Arc<Example>`. This is particularly useful when allocation happens
 /// in one context (e.g., sleepable) and initialisation in another (e.g., atomic):
@@ -560,7 +558,7 @@ impl<T> UniqueArc<T> {
     /// Tries to allocate a new [`UniqueArc`] instance.
     pub fn try_new(value: T) -> Result<Self, AllocError> {
         Ok(Self {
-            // INVARIANT: The newly-created object has a ref-count of 1.
+            // INVARIANT: The newly-created object has a refcount of 1.
             inner: Arc::try_new(value)?,
         })
     }
@@ -574,7 +572,7 @@ impl<T> UniqueArc<T> {
             data <- init::uninit::<T, AllocError>(),
         }? AllocError))?;
         Ok(UniqueArc {
-            // INVARIANT: The newly-created object has a ref-count of 1.
+            // INVARIANT: The newly-created object has a refcount of 1.
             // SAFETY: The pointer from the `Box` is valid.
             inner: unsafe { Arc::from_inner(Box::leak(inner).into()) },
         })
diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs
index f65e19d5a37c..0c3671caffeb 100644
--- a/rust/kernel/sync/condvar.rs
+++ b/rust/kernel/sync/condvar.rs
@@ -6,8 +6,18 @@
 //! variable.
 
 use super::{lock::Backend, lock::Guard, LockClassKey};
-use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque};
+use crate::{
+    bindings,
+    init::PinInit,
+    pin_init,
+    str::CStr,
+    task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE},
+    time::Jiffies,
+    types::Opaque,
+};
+use core::ffi::{c_int, c_long};
 use core::marker::PhantomPinned;
+use core::ptr;
 use macros::pin_data;
 
 /// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class.
@@ -17,6 +27,7 @@ macro_rules! new_condvar {
         $crate::sync::CondVar::new($crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_condvar;
 
 /// A conditional variable.
 ///
@@ -34,8 +45,7 @@ macro_rules! new_condvar {
 /// The following is an example of using a condvar with a mutex:
 ///
 /// ```
-/// use kernel::sync::{CondVar, Mutex};
-/// use kernel::{new_condvar, new_mutex};
+/// use kernel::sync::{new_condvar, new_mutex, CondVar, Mutex};
 ///
 /// #[pin_data]
 /// pub struct Example {
@@ -73,10 +83,12 @@ macro_rules! new_condvar {
 #[pin_data]
 pub struct CondVar {
     #[pin]
-    pub(crate) wait_list: Opaque<bindings::wait_queue_head>,
+    pub(crate) wait_queue_head: Opaque<bindings::wait_queue_head>,
 
     /// A condvar needs to be pinned because it contains a [`struct list_head`] that is
     /// self-referential, so it cannot be safely moved once it is initialised.
+    ///
+    /// [`struct list_head`]: srctree/include/linux/types.h
     #[pin]
     _pin: PhantomPinned,
 }
@@ -96,28 +108,35 @@ impl CondVar {
             _pin: PhantomPinned,
             // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have
             // static lifetimes so they live indefinitely.
-            wait_list <- Opaque::ffi_init(|slot| unsafe {
+            wait_queue_head <- Opaque::ffi_init(|slot| unsafe {
                 bindings::__init_waitqueue_head(slot, name.as_char_ptr(), key.as_ptr())
             }),
         })
     }
 
-    fn wait_internal<T: ?Sized, B: Backend>(&self, wait_state: u32, guard: &mut Guard<'_, T, B>) {
+    fn wait_internal<T: ?Sized, B: Backend>(
+        &self,
+        wait_state: c_int,
+        guard: &mut Guard<'_, T, B>,
+        timeout_in_jiffies: c_long,
+    ) -> c_long {
         let wait = Opaque::<bindings::wait_queue_entry>::uninit();
 
         // SAFETY: `wait` points to valid memory.
         unsafe { bindings::init_wait(wait.get()) };
 
-        // SAFETY: Both `wait` and `wait_list` point to valid memory.
+        // SAFETY: Both `wait` and `wait_queue_head` point to valid memory.
         unsafe {
-            bindings::prepare_to_wait_exclusive(self.wait_list.get(), wait.get(), wait_state as _)
+            bindings::prepare_to_wait_exclusive(self.wait_queue_head.get(), wait.get(), wait_state)
         };
 
-        // SAFETY: No arguments, switches to another thread.
-        guard.do_unlocked(|| unsafe { bindings::schedule() });
+        // SAFETY: Switches to another thread. The timeout can be any number.
+        let ret = guard.do_unlocked(|| unsafe { bindings::schedule_timeout(timeout_in_jiffies) });
+
+        // SAFETY: Both `wait` and `wait_queue_head` point to valid memory.
+        unsafe { bindings::finish_wait(self.wait_queue_head.get(), wait.get()) };
 
-        // SAFETY: Both `wait` and `wait_list` point to valid memory.
-        unsafe { bindings::finish_wait(self.wait_list.get(), wait.get()) };
+        ret
     }
 
     /// Releases the lock and waits for a notification in uninterruptible mode.
@@ -127,7 +146,7 @@ impl CondVar {
     /// [`CondVar::notify_one`] or [`CondVar::notify_all`]. Note that it may also wake up
     /// spuriously.
     pub fn wait<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) {
-        self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, guard);
+        self.wait_internal(TASK_UNINTERRUPTIBLE, guard, MAX_SCHEDULE_TIMEOUT);
     }
 
     /// Releases the lock and waits for a notification in interruptible mode.
@@ -138,29 +157,60 @@ impl CondVar {
     /// Returns whether there is a signal pending.
     #[must_use = "wait_interruptible returns if a signal is pending, so the caller must check the return value"]
     pub fn wait_interruptible<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) -> bool {
-        self.wait_internal(bindings::TASK_INTERRUPTIBLE, guard);
+        self.wait_internal(TASK_INTERRUPTIBLE, guard, MAX_SCHEDULE_TIMEOUT);
         crate::current!().signal_pending()
     }
 
-    /// Calls the kernel function to notify the appropriate number of threads with the given flags.
-    fn notify(&self, count: i32, flags: u32) {
-        // SAFETY: `wait_list` points to valid memory.
+    /// Releases the lock and waits for a notification in interruptible mode.
+    ///
+    /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
+    /// thread to sleep. It wakes up when notified by [`CondVar::notify_one`] or
+    /// [`CondVar::notify_all`], or when a timeout occurs, or when the thread receives a signal.
+    #[must_use = "wait_interruptible_timeout returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_interruptible_timeout<T: ?Sized, B: Backend>(
+        &self,
+        guard: &mut Guard<'_, T, B>,
+        jiffies: Jiffies,
+    ) -> CondVarTimeoutResult {
+        let jiffies = jiffies.try_into().unwrap_or(MAX_SCHEDULE_TIMEOUT);
+        let res = self.wait_internal(TASK_INTERRUPTIBLE, guard, jiffies);
+
+        match (res as Jiffies, crate::current!().signal_pending()) {
+            (jiffies, true) => CondVarTimeoutResult::Signal { jiffies },
+            (0, false) => CondVarTimeoutResult::Timeout,
+            (jiffies, false) => CondVarTimeoutResult::Woken { jiffies },
+        }
+    }
+
+    /// Calls the kernel function to notify the appropriate number of threads.
+    fn notify(&self, count: c_int) {
+        // SAFETY: `wait_queue_head` points to valid memory.
         unsafe {
             bindings::__wake_up(
-                self.wait_list.get(),
-                bindings::TASK_NORMAL,
+                self.wait_queue_head.get(),
+                TASK_NORMAL,
                 count,
-                flags as _,
+                ptr::null_mut(),
             )
         };
     }
 
+    /// Calls the kernel function to notify one thread synchronously.
+    ///
+    /// This method behaves like `notify_one`, except that it hints to the scheduler that the
+    /// current thread is about to go to sleep, so it should schedule the target thread on the same
+    /// CPU.
+    pub fn notify_sync(&self) {
+        // SAFETY: `wait_queue_head` points to valid memory.
+        unsafe { bindings::__wake_up_sync(self.wait_queue_head.get(), TASK_NORMAL) };
+    }
+
     /// Wakes a single waiter up, if any.
     ///
     /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
     /// completely (as opposed to automatically waking up the next waiter).
     pub fn notify_one(&self) {
-        self.notify(1, 0);
+        self.notify(1);
     }
 
     /// Wakes all waiters up, if any.
@@ -168,6 +218,22 @@ impl CondVar {
     /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
     /// completely (as opposed to automatically waking up the next waiter).
     pub fn notify_all(&self) {
-        self.notify(0, 0);
+        self.notify(0);
     }
 }
+
+/// The return type of `wait_timeout`.
+pub enum CondVarTimeoutResult {
+    /// The timeout was reached.
+    Timeout,
+    /// Somebody woke us up.
+    Woken {
+        /// Remaining sleep duration.
+        jiffies: Jiffies,
+    },
+    /// A signal occurred.
+    Signal {
+        /// Remaining sleep duration.
+        jiffies: Jiffies,
+    },
+}
diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
index f12a684bc957..5b5c8efe427a 100644
--- a/rust/kernel/sync/lock.rs
+++ b/rust/kernel/sync/lock.rs
@@ -21,14 +21,21 @@ pub mod spinlock;
 /// # Safety
 ///
 /// - Implementers must ensure that only one thread/CPU may access the protected data once the lock
-/// is owned, that is, between calls to `lock` and `unlock`.
-/// - Implementers must also ensure that `relock` uses the same locking method as the original
-/// lock operation.
+///   is owned, that is, between calls to [`lock`] and [`unlock`].
+/// - Implementers must also ensure that [`relock`] uses the same locking method as the original
+///   lock operation.
+///
+/// [`lock`]: Backend::lock
+/// [`unlock`]: Backend::unlock
+/// [`relock`]: Backend::relock
 pub unsafe trait Backend {
     /// The state required by the lock.
     type State;
 
-    /// The state required to be kept between lock and unlock.
+    /// The state required to be kept between [`lock`] and [`unlock`].
+    ///
+    /// [`lock`]: Backend::lock
+    /// [`unlock`]: Backend::unlock
     type GuardState;
 
     /// Initialises the lock.
@@ -139,7 +146,7 @@ pub struct Guard<'a, T: ?Sized, B: Backend> {
 unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
 impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
-    pub(crate) fn do_unlocked(&mut self, cb: impl FnOnce()) {
+    pub(crate) fn do_unlocked<U>(&mut self, cb: impl FnOnce() -> U) -> U {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };
 
@@ -147,7 +154,7 @@ impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
         let _relock =
             ScopeGuard::new(|| unsafe { B::relock(self.lock.state.get(), &mut self.state) });
 
-        cb();
+        cb()
     }
 }
 
diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs
index 8c524a3ec45a..ef4c4634d294 100644
--- a/rust/kernel/sync/lock/mutex.rs
+++ b/rust/kernel/sync/lock/mutex.rs
@@ -17,6 +17,7 @@ macro_rules! new_mutex {
             $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_mutex;
 
 /// A mutual exclusion primitive.
 ///
@@ -35,7 +36,7 @@ macro_rules! new_mutex {
 /// contains an inner struct (`Inner`) that is protected by a mutex.
 ///
 /// ```
-/// use kernel::{init::InPlaceInit, init::PinInit, new_mutex, pin_init, sync::Mutex};
+/// use kernel::sync::{new_mutex, Mutex};
 ///
 /// struct Inner {
 ///     a: u32,
diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs
index 068535ce1b29..0b22c635634f 100644
--- a/rust/kernel/sync/lock/spinlock.rs
+++ b/rust/kernel/sync/lock/spinlock.rs
@@ -17,6 +17,7 @@ macro_rules! new_spinlock {
             $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_spinlock;
 
 /// A spinlock.
 ///
@@ -33,7 +34,7 @@ macro_rules! new_spinlock {
 /// contains an inner struct (`Inner`) that is protected by a spinlock.
 ///
 /// ```
-/// use kernel::{init::InPlaceInit, init::PinInit, new_spinlock, pin_init, sync::SpinLock};
+/// use kernel::sync::{new_spinlock, SpinLock};
 ///
 /// struct Inner {
 ///     a: u32,
@@ -112,7 +113,7 @@ unsafe impl super::Backend for SpinLockBackend {
 
     unsafe fn unlock(ptr: *mut Self::State, _guard_state: &Self::GuardState) {
         // SAFETY: The safety requirements of this function ensure that `ptr` is valid and that the
-        // caller is the owner of the mutex.
+        // caller is the owner of the spinlock.
         unsafe { bindings::spin_unlock(ptr) }
     }
 }
diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs
index b17ee5cd98f3..babc731bd5f6 100644
--- a/rust/kernel/sync/locked_by.rs
+++ b/rust/kernel/sync/locked_by.rs
@@ -9,14 +9,17 @@ use core::{cell::UnsafeCell, mem::size_of, ptr};
 /// Allows access to some data to be serialised by a lock that does not wrap it.
 ///
 /// In most cases, data protected by a lock is wrapped by the appropriate lock type, e.g.,
-/// [`super::Mutex`] or [`super::SpinLock`]. [`LockedBy`] is meant for cases when this is not
-/// possible. For example, if a container has a lock and some data in the contained elements needs
+/// [`Mutex`] or [`SpinLock`]. [`LockedBy`] is meant for cases when this is not possible.
+/// For example, if a container has a lock and some data in the contained elements needs
 /// to be protected by the same lock.
 ///
 /// [`LockedBy`] wraps the data in lieu of another locking primitive, and only allows access to it
 /// when the caller shows evidence that the 'external' lock is locked. It panics if the evidence
 /// refers to the wrong instance of the lock.
 ///
+/// [`Mutex`]: super::Mutex
+/// [`SpinLock`]: super::SpinLock
+///
 /// # Examples
 ///
 /// The following is an example for illustrative purposes: `InnerDirectory::bytes_used` is an
diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 9451932d5d86..ca6e7e31d71c 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -5,7 +5,23 @@
 //! C header: [`include/linux/sched.h`](srctree/include/linux/sched.h).
 
 use crate::{bindings, types::Opaque};
-use core::{marker::PhantomData, ops::Deref, ptr};
+use core::{
+    ffi::{c_int, c_long, c_uint},
+    marker::PhantomData,
+    ops::Deref,
+    ptr,
+};
+
+/// A sentinel value used for infinite timeouts.
+pub const MAX_SCHEDULE_TIMEOUT: c_long = c_long::MAX;
+
+/// Bitmask for tasks that are sleeping in an interruptible state.
+pub const TASK_INTERRUPTIBLE: c_int = bindings::TASK_INTERRUPTIBLE as c_int;
+/// Bitmask for tasks that are sleeping in an uninterruptible state.
+pub const TASK_UNINTERRUPTIBLE: c_int = bindings::TASK_UNINTERRUPTIBLE as c_int;
+/// Convenience constant for waking up tasks regardless of whether they are in interruptible or
+/// uninterruptible sleep.
+pub const TASK_NORMAL: c_uint = bindings::TASK_NORMAL as c_uint;
 
 /// Returns the currently running task.
 #[macro_export]
@@ -23,7 +39,7 @@ macro_rules! current {
 ///
 /// All instances are valid tasks created by the C portion of the kernel.
 ///
-/// Instances of this type are always ref-counted, that is, a call to `get_task_struct` ensures
+/// Instances of this type are always refcounted, that is, a call to `get_task_struct` ensures
 /// that the allocation remains valid at least until the matching call to `put_task_struct`.
 ///
 /// # Examples
@@ -116,7 +132,7 @@ impl Task {
     /// Returns the group leader of the given task.
     pub fn group_leader(&self) -> &Task {
         // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always
-        // have a valid group_leader.
+        // have a valid `group_leader`.
         let ptr = unsafe { *ptr::addr_of!((*self.0.get()).group_leader) };
 
         // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`,
@@ -147,7 +163,7 @@ impl Task {
     }
 }
 
-// SAFETY: The type invariants guarantee that `Task` is always ref-counted.
+// SAFETY: The type invariants guarantee that `Task` is always refcounted.
 unsafe impl crate::types::AlwaysRefCounted for Task {
     fn inc_ref(&self) {
         // SAFETY: The existence of a shared reference means that the refcount is nonzero.
diff --git a/rust/kernel/time.rs b/rust/kernel/time.rs
new file mode 100644
index 000000000000..25a896eed468
--- /dev/null
+++ b/rust/kernel/time.rs
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Time related primitives.
+//!
+//! This module contains the kernel APIs related to time and timers that
+//! have been ported or wrapped for usage by Rust code in the kernel.
+
+/// The time unit of Linux kernel. One jiffy equals (1/HZ) second.
+pub type Jiffies = core::ffi::c_ulong;
+
+/// The millisecond time unit.
+pub type Msecs = core::ffi::c_uint;
+
+/// Converts milliseconds to jiffies.
+#[inline]
+pub fn msecs_to_jiffies(msecs: Msecs) -> Jiffies {
+    // SAFETY: The `__msecs_to_jiffies` function is always safe to call no
+    // matter what the argument is.
+    unsafe { bindings::__msecs_to_jiffies(msecs) }
+}
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index fdb778e65d79..aa77bad9bce4 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -46,6 +46,25 @@ pub trait ForeignOwnable: Sized {
     /// Additionally, all instances (if any) of values returned by [`ForeignOwnable::borrow`] for
     /// this object must have been dropped.
     unsafe fn from_foreign(ptr: *const core::ffi::c_void) -> Self;
+
+    /// Tries to convert a foreign-owned object back to a Rust-owned one.
+    ///
+    /// A convenience wrapper over [`ForeignOwnable::from_foreign`] that returns [`None`] if `ptr`
+    /// is null.
+    ///
+    /// # Safety
+    ///
+    /// `ptr` must either be null or satisfy the safety requirements for
+    /// [`ForeignOwnable::from_foreign`].
+    unsafe fn try_from_foreign(ptr: *const core::ffi::c_void) -> Option<Self> {
+        if ptr.is_null() {
+            None
+        } else {
+            // SAFETY: Since `ptr` is not null here, then `ptr` satisfies the safety requirements
+            // of `from_foreign` given the safety requirements of this function.
+            unsafe { Some(Self::from_foreign(ptr)) }
+        }
+    }
 }
 
 impl<T: 'static> ForeignOwnable for Box<T> {
@@ -90,6 +109,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we have multiple exit paths and we want to log regardless of which one is
 /// taken:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example1(arg: bool) {
@@ -108,6 +128,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we want to log the same message on all early exits but a different one on
 /// the main exit path:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example2(arg: bool) {
@@ -129,6 +150,7 @@ impl ForeignOwnable for () {
 ///
 /// In the example below, we need a mutable object (the vector) to be accessible within the log
 /// function, so we wrap it in the [`ScopeGuard`]:
+///
 /// ```
 /// # use kernel::types::ScopeGuard;
 /// fn example3(arg: bool) -> Result {
diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 498397877376..480cb292e7c2 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -12,19 +12,19 @@
 //!
 //! # The raw API
 //!
-//! The raw API consists of the `RawWorkItem` trait, where the work item needs to provide an
+//! The raw API consists of the [`RawWorkItem`] trait, where the work item needs to provide an
 //! arbitrary function that knows how to enqueue the work item. It should usually not be used
 //! directly, but if you want to, you can use it without using the pieces from the safe API.
 //!
 //! # The safe API
 //!
-//! The safe API is used via the `Work` struct and `WorkItem` traits. Furthermore, it also includes
-//! a trait called `WorkItemPointer`, which is usually not used directly by the user.
+//! The safe API is used via the [`Work`] struct and [`WorkItem`] traits. Furthermore, it also
+//! includes a trait called [`WorkItemPointer`], which is usually not used directly by the user.
 //!
-//!  * The `Work` struct is the Rust wrapper for the C `work_struct` type.
-//!  * The `WorkItem` trait is implemented for structs that can be enqueued to a workqueue.
-//!  * The `WorkItemPointer` trait is implemented for the pointer type that points at a something
-//!    that implements `WorkItem`.
+//!  * The [`Work`] struct is the Rust wrapper for the C `work_struct` type.
+//!  * The [`WorkItem`] trait is implemented for structs that can be enqueued to a workqueue.
+//!  * The [`WorkItemPointer`] trait is implemented for the pointer type that points at a something
+//!    that implements [`WorkItem`].
 //!
 //! ## Example
 //!
@@ -35,8 +35,7 @@
 //! ```
 //! use kernel::prelude::*;
 //! use kernel::sync::Arc;
-//! use kernel::workqueue::{self, Work, WorkItem};
-//! use kernel::{impl_has_work, new_work};
+//! use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
 //!
 //! #[pin_data]
 //! struct MyStruct {
@@ -78,8 +77,7 @@
 //! ```
 //! use kernel::prelude::*;
 //! use kernel::sync::Arc;
-//! use kernel::workqueue::{self, Work, WorkItem};
-//! use kernel::{impl_has_work, new_work};
+//! use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
 //!
 //! #[pin_data]
 //! struct MyStruct {
@@ -147,6 +145,7 @@ macro_rules! new_work {
         $crate::workqueue::Work::new($crate::optional_name!($($name)?), $crate::static_lock_class!())
     };
 }
+pub use new_work;
 
 /// A kernel work queue.
 ///
@@ -168,7 +167,7 @@ impl Queue {
     /// # Safety
     ///
     /// The caller must ensure that the provided raw pointer is not dangling, that it points at a
-    /// valid workqueue, and that it remains valid until the end of 'a.
+    /// valid workqueue, and that it remains valid until the end of `'a`.
     pub unsafe fn from_raw<'a>(ptr: *const bindings::workqueue_struct) -> &'a Queue {
         // SAFETY: The `Queue` type is `#[repr(transparent)]`, so the pointer cast is valid. The
         // caller promises that the pointer is not dangling.
@@ -199,7 +198,11 @@ impl Queue {
         // stay valid until we call the function pointer in the `work_struct`, so the access is ok.
         unsafe {
             w.__enqueue(move |work_ptr| {
-                bindings::queue_work_on(bindings::WORK_CPU_UNBOUND as _, queue_ptr, work_ptr)
+                bindings::queue_work_on(
+                    bindings::wq_misc_consts_WORK_CPU_UNBOUND as _,
+                    queue_ptr,
+                    work_ptr,
+                )
             })
         }
     }
@@ -218,7 +221,9 @@ impl Queue {
     }
 }
 
-/// A helper type used in `try_spawn`.
+/// A helper type used in [`try_spawn`].
+///
+/// [`try_spawn`]: Queue::try_spawn
 #[pin_data]
 struct ClosureWork<T> {
     #[pin]
@@ -253,14 +258,16 @@ impl<T: FnOnce()> WorkItem for ClosureWork<T> {
 /// actual value of the id is not important as long as you use different ids for different fields
 /// of the same struct. (Fields of different structs need not use different ids.)
 ///
-/// Note that the id is used only to select the right method to call during compilation. It wont be
+/// Note that the id is used only to select the right method to call during compilation. It won't be
 /// part of the final executable.
 ///
 /// # Safety
 ///
-/// Implementers must ensure that any pointers passed to a `queue_work_on` closure by `__enqueue`
+/// Implementers must ensure that any pointers passed to a `queue_work_on` closure by [`__enqueue`]
 /// remain valid for the duration specified in the guarantees section of the documentation for
-/// `__enqueue`.
+/// [`__enqueue`].
+///
+/// [`__enqueue`]: RawWorkItem::__enqueue
 pub unsafe trait RawWorkItem<const ID: u64> {
     /// The return type of [`Queue::enqueue`].
     type EnqueueOutput;
@@ -290,10 +297,11 @@ pub unsafe trait RawWorkItem<const ID: u64> {
 
 /// Defines the method that should be called directly when a work item is executed.
 ///
-/// This trait is implemented by `Pin<Box<T>>` and `Arc<T>`, and is mainly intended to be
+/// This trait is implemented by `Pin<Box<T>>` and [`Arc<T>`], and is mainly intended to be
 /// implemented for smart pointer types. For your own structs, you would implement [`WorkItem`]
-/// instead. The `run` method on this trait will usually just perform the appropriate
-/// `container_of` translation and then call into the `run` method from the [`WorkItem`] trait.
+/// instead. The [`run`] method on this trait will usually just perform the appropriate
+/// `container_of` translation and then call into the [`run`][WorkItem::run] method from the
+/// [`WorkItem`] trait.
 ///
 /// This trait is used when the `work_struct` field is defined using the [`Work`] helper.
 ///
@@ -309,8 +317,10 @@ pub unsafe trait WorkItemPointer<const ID: u64>: RawWorkItem<ID> {
     ///
     /// # Safety
     ///
-    /// The provided `work_struct` pointer must originate from a previous call to `__enqueue` where
-    /// the `queue_work_on` closure returned true, and the pointer must still be valid.
+    /// The provided `work_struct` pointer must originate from a previous call to [`__enqueue`]
+    /// where the `queue_work_on` closure returned true, and the pointer must still be valid.
+    ///
+    /// [`__enqueue`]: RawWorkItem::__enqueue
     unsafe extern "C" fn run(ptr: *mut bindings::work_struct);
 }
 
@@ -328,12 +338,14 @@ pub trait WorkItem<const ID: u64 = 0> {
 
 /// Links for a work item.
 ///
-/// This struct contains a function pointer to the `run` function from the [`WorkItemPointer`]
+/// This struct contains a function pointer to the [`run`] function from the [`WorkItemPointer`]
 /// trait, and defines the linked list pointers necessary to enqueue a work item in a workqueue.
 ///
 /// Wraps the kernel's C `struct work_struct`.
 ///
 /// This is a helper type used to associate a `work_struct` with the [`WorkItem`] that uses it.
+///
+/// [`run`]: WorkItemPointer::run
 #[repr(transparent)]
 pub struct Work<T: ?Sized, const ID: u64 = 0> {
     work: Opaque<bindings::work_struct>,
@@ -396,9 +408,8 @@ impl<T: ?Sized, const ID: u64> Work<T, ID> {
 /// like this:
 ///
 /// ```no_run
-/// use kernel::impl_has_work;
 /// use kernel::prelude::*;
-/// use kernel::workqueue::Work;
+/// use kernel::workqueue::{impl_has_work, Work};
 ///
 /// struct MyWorkItem {
 ///     work_field: Work<MyWorkItem, 1>,
@@ -409,28 +420,25 @@ impl<T: ?Sized, const ID: u64> Work<T, ID> {
 /// }
 /// ```
 ///
-/// Note that since the `Work` type is annotated with an id, you can have several `work_struct`
+/// Note that since the [`Work`] type is annotated with an id, you can have several `work_struct`
 /// fields by using a different id for each one.
 ///
 /// # Safety
 ///
-/// The [`OFFSET`] constant must be the offset of a field in Self of type [`Work<T, ID>`]. The methods on
-/// this trait must have exactly the behavior that the definitions given below have.
+/// The [`OFFSET`] constant must be the offset of a field in `Self` of type [`Work<T, ID>`]. The
+/// methods on this trait must have exactly the behavior that the definitions given below have.
 ///
-/// [`Work<T, ID>`]: Work
 /// [`impl_has_work!`]: crate::impl_has_work
 /// [`OFFSET`]: HasWork::OFFSET
 pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// The offset of the [`Work<T, ID>`] field.
-    ///
-    /// [`Work<T, ID>`]: Work
     const OFFSET: usize;
 
     /// Returns the offset of the [`Work<T, ID>`] field.
     ///
-    /// This method exists because the [`OFFSET`] constant cannot be accessed if the type is not Sized.
+    /// This method exists because the [`OFFSET`] constant cannot be accessed if the type is not
+    /// [`Sized`].
     ///
-    /// [`Work<T, ID>`]: Work
     /// [`OFFSET`]: HasWork::OFFSET
     #[inline]
     fn get_work_offset(&self) -> usize {
@@ -442,8 +450,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// # Safety
     ///
     /// The provided pointer must point at a valid struct of type `Self`.
-    ///
-    /// [`Work<T, ID>`]: Work
     #[inline]
     unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<T, ID> {
         // SAFETY: The caller promises that the pointer is valid.
@@ -455,8 +461,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
     /// # Safety
     ///
     /// The pointer must point at a [`Work<T, ID>`] field in a struct of type `Self`.
-    ///
-    /// [`Work<T, ID>`]: Work
     #[inline]
     unsafe fn work_container_of(ptr: *mut Work<T, ID>) -> *mut Self
     where
@@ -473,9 +477,8 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
 /// # Examples
 ///
 /// ```
-/// use kernel::impl_has_work;
 /// use kernel::sync::Arc;
-/// use kernel::workqueue::{self, Work};
+/// use kernel::workqueue::{self, impl_has_work, Work};
 ///
 /// struct MyStruct {
 ///     work_field: Work<MyStruct, 17>,
@@ -485,8 +488,6 @@ pub unsafe trait HasWork<T, const ID: u64 = 0> {
 ///     impl HasWork<MyStruct, 17> for MyStruct { self.work_field }
 /// }
 /// ```
-///
-/// [`HasWork<T, ID>`]: HasWork
 #[macro_export]
 macro_rules! impl_has_work {
     ($(impl$(<$($implarg:ident),*>)?
@@ -509,6 +510,7 @@ macro_rules! impl_has_work {
         }
     )*};
 }
+pub use impl_has_work;
 
 impl_has_work! {
     impl<T> HasWork<Self> for ClosureWork<T> { self.work }
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index d62d8710d77a..27979e582e4b 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -222,10 +222,15 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
             }};
 
             // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
+            /// # Safety
+            ///
+            /// This function must not be called after module initialization, because it may be
+            /// freed after that completes.
             #[cfg(MODULE)]
             #[doc(hidden)]
             #[no_mangle]
-            pub extern \"C\" fn init_module() -> core::ffi::c_int {{
+            #[link_section = \".init.text\"]
+            pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
                 __init()
             }}
 
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7048bb3594d6..634e81d83efd 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -4,14 +4,14 @@
 #define __ASM_GOTO_WORKAROUND_H
 
 /*
- * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * This will bring in asm_goto_output and asm_inline macro definitions
  * if enabled by compiler and config options.
  */
 #include <linux/types.h>
 
-#ifdef asm_volatile_goto
-#undef asm_volatile_goto
-#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
 #endif
 
 /*
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
index 5a84b6443875..3ee8ecfb8c04 100644
--- a/scripts/Kconfig.include
+++ b/scripts/Kconfig.include
@@ -33,7 +33,7 @@ ld-option = $(success,$(LD) -v $(1))
 
 # $(as-instr,<instr>)
 # Return y if the assembler supports <instr>, n otherwise
-as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler-with-cpp -o /dev/null -)
+as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -)
 
 # check if $(CC) and $(LD) exist
 $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found)
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index dae447a1ad30..0fb7a785594c 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -290,7 +290,7 @@ quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_o_rs = $(rust_common_cmd) --emit=obj=$@ $<
 
 $(obj)/%.o: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_o_rs)
+	+$(call if_changed_dep,rustc_o_rs)
 
 quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_rsi_rs = \
@@ -298,19 +298,19 @@ quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
 	command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@
 
 $(obj)/%.rsi: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_rsi_rs)
+	+$(call if_changed_dep,rustc_rsi_rs)
 
 quiet_cmd_rustc_s_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_s_rs = $(rust_common_cmd) --emit=asm=$@ $<
 
 $(obj)/%.s: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_s_rs)
+	+$(call if_changed_dep,rustc_s_rs)
 
 quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@
       cmd_rustc_ll_rs = $(rust_common_cmd) --emit=llvm-ir=$@ $<
 
 $(obj)/%.ll: $(src)/%.rs FORCE
-	$(call if_changed_dep,rustc_ll_rs)
+	+$(call if_changed_dep,rustc_ll_rs)
 
 # Compile assembler sources (.S)
 # ---------------------------------------------------------------------------
diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler
index 8fcb427405a6..92be0c9a13ee 100644
--- a/scripts/Makefile.compiler
+++ b/scripts/Makefile.compiler
@@ -38,7 +38,7 @@ as-option = $(call try-run,\
 # Usage: aflags-y += $(call as-instr,instr,option1,option2)
 
 as-instr = $(call try-run,\
-	printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3))
+	printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3))
 
 # __cc-option
 # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586)
diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf
index ab271b2051a2..226ea3df3b4b 100644
--- a/scripts/Makefile.defconf
+++ b/scripts/Makefile.defconf
@@ -9,8 +9,8 @@
 # Input config fragments without '.config' suffix
 define merge_into_defconfig
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
 
@@ -23,7 +23,7 @@ endef
 # Input config fragments without '.config' suffix
 define merge_into_defconfig_override
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-Q -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+		-Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 08d83d9db31a..3c17e6ba421c 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -156,7 +156,7 @@ quiet_cmd_host-rust	= HOSTRUSTC $@
       cmd_host-rust	= \
 	$(HOSTRUSTC) $(hostrust_flags) --emit=link=$@ $<
 $(host-rust): $(obj)/%: $(src)/%.rs FORCE
-	$(call if_changed_dep,host-rust)
+	+$(call if_changed_dep,host-rust)
 
 targets += $(host-csingle) $(host-cmulti) $(host-cobjs) \
 	   $(host-cxxmulti) $(host-cxxobjs) $(host-rust)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index cd5b181060f1..01a80a216f56 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -254,7 +254,7 @@ objtool := $(objtree)/tools/objtool/objtool
 
 objtool-args-$(CONFIG_HAVE_JUMP_LABEL_HACK)		+= --hacks=jump_label
 objtool-args-$(CONFIG_HAVE_NOINSTR_HACK)		+= --hacks=noinstr
-objtool-args-$(CONFIG_CALL_DEPTH_TRACKING)		+= --hacks=skylake
+objtool-args-$(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)	+= --hacks=skylake
 objtool-args-$(CONFIG_X86_KERNEL_IBT)			+= --ibt
 objtool-args-$(CONFIG_FINEIBT)				+= --cfi
 objtool-args-$(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL)	+= --mcount
@@ -262,9 +262,9 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL
 objtool-args-$(CONFIG_HAVE_OBJTOOL_NOP_MCOUNT)		+= --mnop
 endif
 objtool-args-$(CONFIG_UNWINDER_ORC)			+= --orc
-objtool-args-$(CONFIG_RETPOLINE)			+= --retpoline
-objtool-args-$(CONFIG_RETHUNK)				+= --rethunk
-objtool-args-$(CONFIG_SLS)				+= --sls
+objtool-args-$(CONFIG_MITIGATION_RETPOLINE)		+= --retpoline
+objtool-args-$(CONFIG_MITIGATION_RETHUNK)		+= --rethunk
+objtool-args-$(CONFIG_MITIGATION_SLS)			+= --sls
 objtool-args-$(CONFIG_STACK_VALIDATION)			+= --stackval
 objtool-args-$(CONFIG_HAVE_STATIC_CALL_INLINE)		+= --static-call
 objtool-args-$(CONFIG_HAVE_UACCESS_VALIDATION)		+= --uaccess
@@ -340,7 +340,7 @@ quiet_cmd_gzip = GZIP    $@
 # DTC
 # ---------------------------------------------------------------------------
 DTC ?= $(objtree)/scripts/dtc/dtc
-DTC_FLAGS += -Wno-interrupt_provider \
+DTC_FLAGS += \
 	-Wno-unique_unit_address
 
 # Disable noisy checks by default
@@ -358,7 +358,6 @@ endif
 ifneq ($(findstring 2,$(KBUILD_EXTRA_WARN)),)
 DTC_FLAGS += -Wnode_name_chars_strict \
 	-Wproperty_name_chars_strict \
-	-Winterrupt_provider \
 	-Wunique_unit_address
 endif
 
diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
index 25b3b587d37c..6de297916ce6 100644
--- a/scripts/Makefile.vmlinux_o
+++ b/scripts/Makefile.vmlinux_o
@@ -38,7 +38,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION))
 vmlinux-objtool-args-$(delay-objtool)			+= $(objtool-args-y)
 vmlinux-objtool-args-$(CONFIG_GCOV_KERNEL)		+= --no-unreachable
 vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION)	+= --noinstr \
-							   $(if $(or $(CONFIG_CPU_UNRET_ENTRY),$(CONFIG_CPU_SRSO)), --unret)
+							   $(if $(or $(CONFIG_MITIGATION_UNRET_ENTRY),$(CONFIG_MITIGATION_SRSO)), --unret)
 
 objtool-args = $(vmlinux-objtool-args-y) --link
 
diff --git a/scripts/atomic/kerneldoc/add_unless b/scripts/atomic/kerneldoc/add_unless
index f828e5f6750c..fbc2fadfbdc4 100644
--- a/scripts/atomic/kerneldoc/add_unless
+++ b/scripts/atomic/kerneldoc/add_unless
@@ -10,6 +10,7 @@ cat <<EOF
  * @u: ${int} value to compare with
  *
  * If (@v != @u), atomically updates @v to (@v + @a) with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/cmpxchg b/scripts/atomic/kerneldoc/cmpxchg
index 3bce328f50cf..02b24ee9d8a4 100644
--- a/scripts/atomic/kerneldoc/cmpxchg
+++ b/scripts/atomic/kerneldoc/cmpxchg
@@ -6,6 +6,7 @@ cat <<EOF
  * @new: ${int} value to assign
  *
  * If (@v == @old), atomically updates @v to @new with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/dec_if_positive b/scripts/atomic/kerneldoc/dec_if_positive
index 04f1aed3cf83..9468b4a69603 100644
--- a/scripts/atomic/kerneldoc/dec_if_positive
+++ b/scripts/atomic/kerneldoc/dec_if_positive
@@ -4,6 +4,7 @@ cat <<EOF
  * @v: pointer to ${atomic}_t
  *
  * If (@v > 0), atomically updates @v to (@v - 1) with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/dec_unless_positive b/scripts/atomic/kerneldoc/dec_unless_positive
index ee73612f0354..06a678678f71 100644
--- a/scripts/atomic/kerneldoc/dec_unless_positive
+++ b/scripts/atomic/kerneldoc/dec_unless_positive
@@ -4,6 +4,7 @@ cat <<EOF
  * @v: pointer to ${atomic}_t
  *
  * If (@v <= 0), atomically updates @v to (@v - 1) with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/inc_not_zero b/scripts/atomic/kerneldoc/inc_not_zero
index 618be08e653e..c1a30fc66ee9 100644
--- a/scripts/atomic/kerneldoc/inc_not_zero
+++ b/scripts/atomic/kerneldoc/inc_not_zero
@@ -4,6 +4,7 @@ cat <<EOF
  * @v: pointer to ${atomic}_t
  *
  * If (@v != 0), atomically updates @v to (@v + 1) with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/inc_unless_negative b/scripts/atomic/kerneldoc/inc_unless_negative
index 597f23d4dc8d..ece0d2c7b38f 100644
--- a/scripts/atomic/kerneldoc/inc_unless_negative
+++ b/scripts/atomic/kerneldoc/inc_unless_negative
@@ -4,6 +4,7 @@ cat <<EOF
  * @v: pointer to ${atomic}_t
  *
  * If (@v >= 0), atomically updates @v to (@v + 1) with ${desc_order} ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/atomic/kerneldoc/try_cmpxchg b/scripts/atomic/kerneldoc/try_cmpxchg
index 296553206c06..3ccff29538f5 100644
--- a/scripts/atomic/kerneldoc/try_cmpxchg
+++ b/scripts/atomic/kerneldoc/try_cmpxchg
@@ -6,7 +6,8 @@ cat <<EOF
  * @new: ${int} value to assign
  *
  * If (@v == @old), atomically updates @v to @new with ${desc_order} ordering.
- * Otherwise, updates @old to the current value of @v.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
  *
  * ${desc_noinstr}
  *
diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py
index 61b7dddedc46..0669bac5e900 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -513,7 +513,7 @@ eBPF programs can have an associated license, passed along with the bytecode
 instructions to the kernel when the programs are loaded. The format for that
 string is identical to the one in use for kernel modules (Dual licenses, such
 as "Dual BSD/GPL", may be used). Some helper functions are only accessible to
-programs that are compatible with the GNU Privacy License (GPL).
+programs that are compatible with the GNU General Public License (GNU GPL).
 
 In order to use such helpers, the eBPF program must be loaded with the correct
 license string passed (via **attr**) to the **bpf**\\ () system call, and this
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
index 5dea4479240b..e4fb686dfaa9 100755
--- a/scripts/clang-tools/gen_compile_commands.py
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -170,7 +170,7 @@ def process_line(root_directory, command_prefix, file_path):
     # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the
     # kernel version). The compile_commands.json file is not interepreted
     # by Make, so this code replaces the escaped version with '#'.
-    prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#')
+    prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#')
 
     # Return the canonical path, eliminating any symbolic links encountered in the path.
     abs_path = os.path.realpath(os.path.join(root_directory, file_path))
diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in
index e810e0c27ff1..10fadc238719 100644
--- a/scripts/gdb/linux/constants.py.in
+++ b/scripts/gdb/linux/constants.py.in
@@ -139,7 +139,7 @@ LX_CONFIG(CONFIG_ARM64_64K_PAGES)
 if IS_BUILTIN(CONFIG_ARM64):
     LX_VALUE(CONFIG_ARM64_PA_BITS)
     LX_VALUE(CONFIG_ARM64_VA_BITS)
-    LX_VALUE(CONFIG_ARM64_PAGE_SHIFT)
+    LX_VALUE(CONFIG_PAGE_SHIFT)
     LX_VALUE(CONFIG_ARCH_FORCE_MAX_ORDER)
 LX_CONFIG(CONFIG_SPARSEMEM)
 LX_CONFIG(CONFIG_SPARSEMEM_EXTREME)
diff --git a/scripts/gdb/linux/mm.py b/scripts/gdb/linux/mm.py
index ad5641dcb068..515730fd4c9d 100644
--- a/scripts/gdb/linux/mm.py
+++ b/scripts/gdb/linux/mm.py
@@ -41,7 +41,7 @@ class aarch64_page_ops():
             self.SECTION_SIZE_BITS = 27
         self.MAX_PHYSMEM_BITS = constants.LX_CONFIG_ARM64_VA_BITS
 
-        self.PAGE_SHIFT = constants.LX_CONFIG_ARM64_PAGE_SHIFT
+        self.PAGE_SHIFT = constants.LX_CONFIG_PAGE_SHIFT
         self.PAGE_SIZE = 1 << self.PAGE_SHIFT
         self.PAGE_MASK = (~(self.PAGE_SIZE - 1)) & ((1 << 64) - 1)
 
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index c8047f4441e6..e8316beb17a7 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -82,7 +82,7 @@ lx-symbols command."""
         self.module_files_updated = True
 
     def _get_module_file(self, module_name):
-        module_pattern = ".*/{0}\.ko(?:.debug)?$".format(
+        module_pattern = r".*/{0}\.ko(?:.debug)?$".format(
             module_name.replace("_", r"[_\-]"))
         for name in self.module_files:
             if re.match(module_pattern, name) and os.path.exists(name):
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 0da52b548ba5..19f72bfdbb82 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -155,7 +155,7 @@ fn main() {
             "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128",
         );
         let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string();
-        if cfg.has("RETPOLINE") {
+        if cfg.has("MITIGATION_RETPOLINE") {
             features += ",+retpoline-external-thunk";
         }
         ts.push("features", features);
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 3e808528aaea..e9e9fb8d8674 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -345,6 +345,8 @@ void sym_calc_value(struct symbol *sym)
 
 	oldval = sym->curr;
 
+	newval.tri = no;
+
 	switch (sym->type) {
 	case S_INT:
 		newval.val = "0";
@@ -357,7 +359,7 @@ void sym_calc_value(struct symbol *sym)
 		break;
 	case S_BOOLEAN:
 	case S_TRISTATE:
-		newval = symbol_no.curr;
+		newval.val = "n";
 		break;
 	default:
 		sym->curr.val = sym->name;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index a432b171be82..7862a8101747 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -135,8 +135,13 @@ gen_btf()
 	${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \
 		--strip-all ${1} ${2} 2>/dev/null
 	# Change e_type to ET_REL so that it can be used to link final vmlinux.
-	# Unlike GNU ld, lld does not allow an ET_EXEC input.
-	printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none
+	# GNU ld 2.35+ and lld do not allow an ET_EXEC input.
+	if is_enabled CONFIG_CPU_BIG_ENDIAN; then
+		et_rel='\0\1'
+	else
+		et_rel='\1\0'
+	fi
+	printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none
 }
 
 # Create ${2} .S file with all symbols from the ${1} object file
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 9faa4d3d91e3..e217683b10d6 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -33,7 +33,7 @@ llvm)
 	fi
 	;;
 rustc)
-	echo 1.74.1
+	echo 1.76.0
 	;;
 bindgen)
 	echo 0.65.1
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 9ba1c9da0a40..57ff5656d566 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -48,17 +48,8 @@ ${NM} -n ${1} | sed >${2} -e "
 / __kvm_nvhe_\\$/d
 / __kvm_nvhe_\.L/d
 
-# arm64 lld
-/ __AArch64ADRPThunk_/d
-
-# arm lld
-/ __ARMV5PILongThunk_/d
-/ __ARMV7PILongThunk_/d
-/ __ThumbV7PILongThunk_/d
-
-# mips lld
-/ __LA25Thunk_/d
-/ __microLA25Thunk_/d
+# lld arm/aarch64/mips thunks
+/ __[[:alnum:]]*Thunk_/d
 
 # CFI type identifiers
 / __kcfi_typeid_/d
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 795b21154446..bf7c4b4b5ff4 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -70,9 +70,7 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 		break;
 	case LOG_ERROR:
 		fprintf(stderr, "ERROR: ");
-		break;
-	case LOG_FATAL:
-		fprintf(stderr, "FATAL: ");
+		error_occurred = true;
 		break;
 	default: /* invalid loglevel, ignore */
 		break;
@@ -83,16 +81,8 @@ void modpost_log(enum loglevel loglevel, const char *fmt, ...)
 	va_start(arglist, fmt);
 	vfprintf(stderr, fmt, arglist);
 	va_end(arglist);
-
-	if (loglevel == LOG_FATAL)
-		exit(1);
-	if (loglevel == LOG_ERROR)
-		error_occurred = true;
 }
 
-void __attribute__((alias("modpost_log")))
-modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
-
 static inline bool strends(const char *str, const char *postfix)
 {
 	if (strlen(str) < strlen(postfix))
@@ -806,7 +796,8 @@ static void check_section(const char *modname, struct elf_info *elf,
 
 #define DATA_SECTIONS ".data", ".data.rel"
 #define TEXT_SECTIONS ".text", ".text.*", ".sched.text", \
-		".kprobes.text", ".cpuidle.text", ".noinstr.text"
+		".kprobes.text", ".cpuidle.text", ".noinstr.text", \
+		".ltext", ".ltext.*"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
 		".fixup", ".entry.text", ".exception.text", \
 		".coldtext", ".softirqentry.text"
@@ -1857,7 +1848,7 @@ static void add_header(struct buffer *b, struct module *mod)
 
 	buf_printf(b,
 		   "\n"
-		   "#ifdef CONFIG_RETPOLINE\n"
+		   "#ifdef CONFIG_MITIGATION_RETPOLINE\n"
 		   "MODULE_INFO(retpoline, \"Y\");\n"
 		   "#endif\n");
 
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 835cababf1b0..ee43c7950636 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -194,15 +194,11 @@ void *sym_get_data(const struct elf_info *info, const Elf_Sym *sym);
 enum loglevel {
 	LOG_WARN,
 	LOG_ERROR,
-	LOG_FATAL
 };
 
 void __attribute__((format(printf, 2, 3)))
 modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
-void __attribute__((format(printf, 2, 3), noreturn))
-modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
-
 /*
  * warn - show the given message, then let modpost continue running, still
  *        allowing modpost to exit successfully. This should be used when
@@ -218,4 +214,4 @@ modpost_log_noret(enum loglevel loglevel, const char *fmt, ...);
  */
 #define warn(fmt, args...)	modpost_log(LOG_WARN, fmt, ##args)
 #define error(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
-#define fatal(fmt, args...)	modpost_log_noret(LOG_FATAL, fmt, ##args)
+#define fatal(fmt, args...)	do { error(fmt, ##args); exit(1); } while (1)
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index 31066bfdba04..dc4878502276 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
 
 	/* Sum all files in the same dir or subdirs. */
 	while ((line = get_line(&pos))) {
-		char* p = line;
+		char* p;
+
+		/* trim the leading spaces away */
+		while (isspace(*line))
+			line++;
+		p = line;
 
 		if (strncmp(line, "source_", sizeof("source_")-1) == 0) {
 			p = strrchr(line, ' ');
diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
index 89298983a169..f58726671fb3 100644
--- a/scripts/package/kernel.spec
+++ b/scripts/package/kernel.spec
@@ -55,12 +55,12 @@ patch -p1 < %{SOURCE2}
 %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
 
 %install
-mkdir -p %{buildroot}/boot
-cp $(%{make} %{makeflags} -s image_name) %{buildroot}/boot/vmlinuz-%{KERNELRELEASE}
+mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
 %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} modules_install
 %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
-cp System.map %{buildroot}/boot/System.map-%{KERNELRELEASE}
-cp .config %{buildroot}/boot/config-%{KERNELRELEASE}
+cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
 ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEASE}/build
 %if %{with_devel}
 %{make} %{makeflags} run-command KBUILD_RUN_COMMAND='${srctree}/scripts/package/install-extmod-build %{buildroot}/usr/src/kernels/%{KERNELRELEASE}'
@@ -70,13 +70,14 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA
 rm -rf %{buildroot}
 
 %post
-if [ -x /sbin/installkernel -a -r /boot/vmlinuz-%{KERNELRELEASE} -a -r /boot/System.map-%{KERNELRELEASE} ]; then
-cp /boot/vmlinuz-%{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm
-cp /boot/System.map-%{KERNELRELEASE} /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/vmlinuz-%{KERNELRELEASE} /boot/System.map-%{KERNELRELEASE}
-/sbin/installkernel %{KERNELRELEASE} /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
-rm -f /boot/.vmlinuz-%{KERNELRELEASE}-rpm /boot/.System.map-%{KERNELRELEASE}-rpm
+if [ -x /usr/bin/kernel-install ]; then
+	/usr/bin/kernel-install add %{KERNELRELEASE} /lib/modules/%{KERNELRELEASE}/vmlinuz
 fi
+for file in vmlinuz System.map config; do
+	if ! cmp --silent "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"; then
+		cp "/lib/modules/%{KERNELRELEASE}/${file}" "/boot/${file}-%{KERNELRELEASE}"
+	fi
+done
 
 %preun
 if [ -x /sbin/new-kernel-pkg ]; then
@@ -94,7 +95,6 @@ fi
 %defattr (-, root, root)
 /lib/modules/%{KERNELRELEASE}
 %exclude /lib/modules/%{KERNELRELEASE}/build
-/boot/*
 
 %files headers
 %defattr (-, root, root)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 98e1150bee9d..9a3dcaafb5b1 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -784,7 +784,7 @@ static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
 	int error = -ENOENT;
 	struct aa_task_ctx *ctx = task_ctx(current);
 	struct aa_label *label = NULL;
-	char *value;
+	char *value = NULL;
 
 	switch (attr) {
 	case LSM_ATTR_CURRENT:
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index df387de29bfa..45c3e5dda355 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -179,7 +179,8 @@ static int __init integrity_add_key(const unsigned int id, const void *data,
 				   KEY_ALLOC_NOT_IN_QUOTA);
 	if (IS_ERR(key)) {
 		rc = PTR_ERR(key);
-		pr_err("Problem loading X.509 certificate %d\n", rc);
+		if (id != INTEGRITY_KEYRING_MACHINE)
+			pr_err("Problem loading X.509 certificate %d\n", rc);
 	} else {
 		pr_notice("Loaded X.509 cert '%s'\n",
 			  key_ref_to_ptr(key)->description);
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index fc520a06f9af..0171f7eb6ee1 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -737,8 +737,8 @@ static int current_check_refer_path(struct dentry *const old_dentry,
 	bool allow_parent1, allow_parent2;
 	access_mask_t access_request_parent1, access_request_parent2;
 	struct path mnt_dir;
-	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS],
-		layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS];
+	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {},
+		     layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};
 
 	if (!dom)
 		return 0;
diff --git a/security/security.c b/security/security.c
index 0144a98d3712..7035ee35a393 100644
--- a/security/security.c
+++ b/security/security.c
@@ -29,6 +29,7 @@
 #include <linux/backing-dev.h>
 #include <linux/string.h>
 #include <linux/msg.h>
+#include <linux/overflow.h>
 #include <net/flow.h>
 
 /* How many LSMs were built into the kernel? */
@@ -4015,6 +4016,7 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
 	struct security_hook_list *hp;
 	struct lsm_ctx *lctx;
 	int rc = LSM_RET_DEFAULT(setselfattr);
+	u64 required_len;
 
 	if (flags)
 		return -EINVAL;
@@ -4027,8 +4029,9 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
 	if (IS_ERR(lctx))
 		return PTR_ERR(lctx);
 
-	if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) ||
-	    lctx->len < lctx->ctx_len + sizeof(*lctx)) {
+	if (size < lctx->len ||
+	    check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) ||
+	    lctx->len < required_len) {
 		rc = -EINVAL;
 		goto free_out;
 	}
@@ -4255,7 +4258,19 @@ EXPORT_SYMBOL(security_inode_setsecctx);
  */
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 {
-	return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) {
+		rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen);
+		if (rc != LSM_RET_DEFAULT(inode_getsecctx))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(inode_getsecctx);
 }
 EXPORT_SYMBOL(security_inode_getsecctx);
 
@@ -4612,8 +4627,20 @@ EXPORT_SYMBOL(security_sock_rcv_skb);
 int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 				      sockptr_t optlen, unsigned int len)
 {
-	return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock,
-			     optval, optlen, len);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream,
+			     list) {
+		rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen,
+						       len);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_stream);
 }
 
 /**
@@ -4633,8 +4660,19 @@ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
 int security_socket_getpeersec_dgram(struct socket *sock,
 				     struct sk_buff *skb, u32 *secid)
 {
-	return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock,
-			     skb, secid);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Only one module will provide a security context.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram,
+			     list) {
+		rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid);
+		if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram))
+			return rc;
+	}
+	return LSM_RET_DEFAULT(socket_getpeersec_dgram);
 }
 EXPORT_SYMBOL(security_socket_getpeersec_dgram);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a6bf90ace84c..338b023a8c3e 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6559,7 +6559,7 @@ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
 			       size_t *size, u32 flags)
 {
 	int rc;
-	char *val;
+	char *val = NULL;
 	int val_len;
 
 	val_len = selinux_lsm_getattr(attr, current, &val);
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index 57ee70ae50f2..ea3140d510ec 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -2649,13 +2649,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
 {
 	int error = buffer_len;
 	size_t avail_len = buffer_len;
-	char *cp0 = head->write_buf;
+	char *cp0;
 	int idx;
 
 	if (!head->write)
 		return -EINVAL;
 	if (mutex_lock_interruptible(&head->io_sem))
 		return -EINTR;
+	cp0 = head->write_buf;
 	head->read_user_buf_avail = 0;
 	idx = tomoyo_read_lock();
 	/* Read a line and dispatch it to the policy handler. */
diff --git a/sound/core/Makefile b/sound/core/Makefile
index a6b444ee2832..f6526b337137 100644
--- a/sound/core/Makefile
+++ b/sound/core/Makefile
@@ -32,7 +32,6 @@ snd-ump-objs      := ump.o
 snd-ump-$(CONFIG_SND_UMP_LEGACY_RAWMIDI) += ump_convert.o
 snd-timer-objs    := timer.o
 snd-hrtimer-objs  := hrtimer.o
-snd-rtctimer-objs := rtctimer.o
 snd-hwdep-objs    := hwdep.o
 snd-seq-device-objs := seq_device.o
 
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index a09f0154e6a7..d0788126cbab 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -211,6 +211,10 @@ static const char * const snd_pcm_format_names[] = {
 	FORMAT(DSD_U32_LE),
 	FORMAT(DSD_U16_BE),
 	FORMAT(DSD_U32_BE),
+	FORMAT(S20_LE),
+	FORMAT(S20_BE),
+	FORMAT(U20_LE),
+	FORMAT(U20_BE),
 };
 
 /**
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f5ff00f99788..21baf6bf7e25 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -486,6 +486,11 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream,
 		i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS);
 		if (snd_interval_single(i))
 			params->msbits = snd_interval_value(i);
+		m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
+		if (snd_mask_single(m)) {
+			snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m);
+			params->msbits = snd_pcm_format_width(format);
+		}
 	}
 
 	if (params->msbits) {
diff --git a/sound/core/ump.c b/sound/core/ump.c
index 3bef1944e955..fe7911498cc4 100644
--- a/sound/core/ump.c
+++ b/sound/core/ump.c
@@ -985,7 +985,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream)
 	struct snd_ump_endpoint *ump = substream->rmidi->private_data;
 	int dir = substream->stream;
 	int group = ump->legacy_mapping[substream->number];
-	int err;
+	int err = 0;
 
 	mutex_lock(&ump->open_mutex);
 	if (ump->legacy_substreams[dir][group]) {
@@ -1009,7 +1009,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream)
 	spin_unlock_irq(&ump->legacy_locks[dir]);
  unlock:
 	mutex_unlock(&ump->open_mutex);
-	return 0;
+	return err;
 }
 
 static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream)
diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index a13c0b408aad..7be17bca257f 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -951,7 +951,7 @@ static int generate_tx_packet_descs(struct amdtp_stream *s, struct pkt_desc *des
 				// to the reason.
 				unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle,
 								IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES);
-				lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0);
+				lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0);
 			}
 			if (lost) {
 				dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n",
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index 21a90b3c4cc7..8e0ff70fb610 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -156,7 +156,7 @@ config SND_HDA_SCODEC_CS35L56_I2C
 	depends on I2C
 	depends on ACPI || COMPILE_TEST
 	depends on SND_SOC
-	select CS_DSP
+	select FW_CS_DSP
 	select SND_HDA_GENERIC
 	select SND_SOC_CS35L56_SHARED
 	select SND_HDA_SCODEC_CS35L56
@@ -171,7 +171,7 @@ config SND_HDA_SCODEC_CS35L56_SPI
 	depends on SPI_MASTER
 	depends on ACPI || COMPILE_TEST
 	depends on SND_SOC
-	select CS_DSP
+	select FW_CS_DSP
 	select SND_HDA_GENERIC
 	select SND_SOC_CS35L56_SHARED
 	select SND_HDA_SCODEC_CS35L56
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 35277ce890a4..e436d4dab317 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -76,11 +76,14 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431533", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431573", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431663", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 1000, 4500, 24 },
+	{ "10431683", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "104316A3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104316F3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "104317F3", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431863", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "104318D3", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+	{ "10431A83", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431C9F", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431CAF", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
 	{ "10431CCF", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
@@ -89,10 +92,14 @@ static const struct cs35l41_config cs35l41_config_table[] = {
 	{ "10431D1F", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431DA2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
 	{ "10431E02", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "10431E12", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "10431EE2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
 	{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
 	{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
 	{ "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+	{ "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+	{ "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
+	{ "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
 	{ "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "17AA38B5", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
 	{ "17AA38B6", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
@@ -410,11 +417,14 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431533", generic_dsd_config },
 	{ "CSC3551", "10431573", generic_dsd_config },
 	{ "CSC3551", "10431663", generic_dsd_config },
+	{ "CSC3551", "10431683", generic_dsd_config },
+	{ "CSC3551", "104316A3", generic_dsd_config },
 	{ "CSC3551", "104316D3", generic_dsd_config },
 	{ "CSC3551", "104316F3", generic_dsd_config },
 	{ "CSC3551", "104317F3", generic_dsd_config },
 	{ "CSC3551", "10431863", generic_dsd_config },
 	{ "CSC3551", "104318D3", generic_dsd_config },
+	{ "CSC3551", "10431A83", generic_dsd_config },
 	{ "CSC3551", "10431C9F", generic_dsd_config },
 	{ "CSC3551", "10431CAF", generic_dsd_config },
 	{ "CSC3551", "10431CCF", generic_dsd_config },
@@ -423,10 +433,14 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
 	{ "CSC3551", "10431D1F", generic_dsd_config },
 	{ "CSC3551", "10431DA2", generic_dsd_config },
 	{ "CSC3551", "10431E02", generic_dsd_config },
+	{ "CSC3551", "10431E12", generic_dsd_config },
 	{ "CSC3551", "10431EE2", generic_dsd_config },
 	{ "CSC3551", "10431F12", generic_dsd_config },
 	{ "CSC3551", "10431F1F", generic_dsd_config },
 	{ "CSC3551", "10431F62", generic_dsd_config },
+	{ "CSC3551", "17AA386F", generic_dsd_config },
+	{ "CSC3551", "17AA38A9", generic_dsd_config },
+	{ "CSC3551", "17AA38AB", generic_dsd_config },
 	{ "CSC3551", "17AA38B4", generic_dsd_config },
 	{ "CSC3551", "17AA38B5", generic_dsd_config },
 	{ "CSC3551", "17AA38B6", generic_dsd_config },
diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index b61e1de8c4bf..75a14ba54fcd 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -30,14 +30,23 @@
   *  ASP1_RX_WL = 24 bits per sample
   *  ASP1_TX_WL = 24 bits per sample
   *  ASP1_RXn_EN 1..3 and ASP1_TXn_EN 1..4 disabled
+  *
+  * Override any Windows-specific mixer settings applied by the firmware.
   */
 static const struct reg_sequence cs35l56_hda_dai_config[] = {
 	{ CS35L56_ASP1_CONTROL1,	0x00000021 },
 	{ CS35L56_ASP1_CONTROL2,	0x20200200 },
 	{ CS35L56_ASP1_CONTROL3,	0x00000003 },
+	{ CS35L56_ASP1_FRAME_CONTROL1,	0x03020100 },
+	{ CS35L56_ASP1_FRAME_CONTROL5,	0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL5,	0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL1,	0x00000018 },
 	{ CS35L56_ASP1_ENABLES1,	0x00000000 },
+	{ CS35L56_ASP1TX1_INPUT,	0x00000018 },
+	{ CS35L56_ASP1TX2_INPUT,	0x00000019 },
+	{ CS35L56_ASP1TX3_INPUT,	0x00000020 },
+	{ CS35L56_ASP1TX4_INPUT,	0x00000028 },
+
 };
 
 static void cs35l56_hda_play(struct cs35l56_hda *cs35l56)
@@ -133,6 +142,10 @@ static int cs35l56_hda_runtime_resume(struct device *dev)
 		}
 	}
 
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
+
 	return 0;
 
 err:
@@ -384,7 +397,7 @@ static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
 
 static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 					     const struct firmware **firmware, char **filename,
-					     const char *dir, const char *system_name,
+					     const char *base_name, const char *system_name,
 					     const char *amp_name,
 					     const char *filetype)
 {
@@ -392,17 +405,13 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	int ret = 0;
 
 	if (system_name && amp_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%s-%s-%s.%s", base_name,
 				      system_name, amp_name, filetype);
 	else if (system_name)
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc-%s.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
+		*filename = kasprintf(GFP_KERNEL, "%s-%s.%s", base_name,
 				      system_name, filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%scs35l56%s-%02x-dsp1-misc.%s", dir,
-				      cs35l56->base.secured ? "s" : "", cs35l56->base.rev,
-				      filetype);
+		*filename = kasprintf(GFP_KERNEL, "%s.%s", base_name, filetype);
 
 	if (!*filename)
 		return -ENOMEM;
@@ -435,8 +444,8 @@ static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 	return 0;
 }
 
-static const char cirrus_dir[] = "cirrus/";
 static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
+					       unsigned int preloaded_fw_ver,
 					       const struct firmware **wmfw_firmware,
 					       char **wmfw_filename,
 					       const struct firmware **coeff_firmware,
@@ -444,55 +453,73 @@ static void cs35l56_hda_request_firmware_files(struct cs35l56_hda *cs35l56,
 {
 	const char *system_name = cs35l56->system_name;
 	const char *amp_name = cs35l56->amp_name;
+	char base_name[37];
 	int ret;
 
+	if (preloaded_fw_ver) {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-%06x-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "",
+			 preloaded_fw_ver & 0xffffff);
+	} else {
+		snprintf(base_name, sizeof(base_name),
+			 "cirrus/cs35l56-%02x%s-dsp1-misc",
+			 cs35l56->base.rev,
+			 cs35l56->base.secured ? "-s" : "");
+	}
+
 	if (system_name && amp_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, amp_name, "wmfw")) {
+						       base_name, system_name, amp_name, "wmfw")) {
 			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
+							  base_name, system_name, amp_name, "bin");
 			return;
 		}
 	}
 
 	if (system_name) {
 		if (!cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						       cirrus_dir, system_name, NULL, "wmfw")) {
+						       base_name, system_name, NULL, "wmfw")) {
 			if (amp_name)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  amp_name, "bin");
 			if (!*coeff_firmware)
 				cs35l56_hda_request_firmware_file(cs35l56,
 								  coeff_firmware, coeff_filename,
-								  cirrus_dir, system_name,
+								  base_name, system_name,
 								  NULL, "bin");
 			return;
 		}
+
+		/*
+		 * Check for system-specific bin files without wmfw before
+		 * falling back to generic firmware
+		 */
+		if (amp_name)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  base_name, system_name, amp_name, "bin");
+		if (!*coeff_firmware)
+			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
+							  base_name, system_name, NULL, "bin");
+
+		if (*coeff_firmware)
+			return;
 	}
 
 	ret = cs35l56_hda_request_firmware_file(cs35l56, wmfw_firmware, wmfw_filename,
-						cirrus_dir, NULL, NULL, "wmfw");
+						base_name, NULL, NULL, "wmfw");
 	if (!ret) {
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 		return;
 	}
 
-	/* When a firmware file is not found must still search for the coeff files */
-	if (system_name) {
-		if (amp_name)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, amp_name, "bin");
-		if (!*coeff_firmware)
-			cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-							  cirrus_dir, system_name, NULL, "bin");
-	}
-
 	if (!*coeff_firmware)
 		cs35l56_hda_request_firmware_file(cs35l56, coeff_firmware, coeff_filename,
-						  cirrus_dir, NULL, NULL, "bin");
+						  base_name, NULL, NULL, "bin");
 }
 
 static void cs35l56_hda_release_firmware_files(const struct firmware *wmfw_firmware,
@@ -526,7 +553,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	const struct firmware *wmfw_firmware = NULL;
 	char *coeff_filename = NULL;
 	char *wmfw_filename = NULL;
-	unsigned int firmware_missing;
+	unsigned int preloaded_fw_ver;
+	bool firmware_missing;
 	int ret = 0;
 
 	/* Prepare for a new DSP power-up */
@@ -537,24 +565,21 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
+	/*
+	 * The firmware can only be upgraded if it is currently running
+	 * from the built-in ROM. If not, the wmfw/bin must be for the
+	 * version of firmware that is running on the chip.
+	 */
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &preloaded_fw_ver);
+	if (ret)
 		goto err_pm_put;
-	}
 
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
+	if (firmware_missing)
+		preloaded_fw_ver = 0;
 
-	/*
-	 * Firmware can only be downloaded if the CS35L56 is secured or is
-	 * running from the built-in ROM. If it is secured the BIOS will have
-	 * downloaded firmware, and the wmfw/bin files will only contain
-	 * tunings that are safe to download with the firmware running.
-	 */
-	if (cs35l56->base.secured || firmware_missing) {
-		cs35l56_hda_request_firmware_files(cs35l56, &wmfw_firmware, &wmfw_filename,
-						   &coeff_firmware, &coeff_filename);
-	}
+	cs35l56_hda_request_firmware_files(cs35l56, preloaded_fw_ver,
+					   &wmfw_firmware, &wmfw_filename,
+					   &coeff_firmware, &coeff_filename);
 
 	/*
 	 * If the BIOS didn't patch the firmware a bin file is mandatory to
@@ -569,12 +594,12 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	mutex_lock(&cs35l56->base.irq_lock);
 
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * If the firmware hasn't been patched it must be shutdown before
+	 * doing a full patch and reset afterwards. If it is already
+	 * running a patched version the firmware files only contain
+	 * tunings and we can use the lower cost reinit sequence instead.
 	 */
-	if (!cs35l56->base.secured && (wmfw_firmware || coeff_firmware)) {
+	if (firmware_missing && (wmfw_firmware || coeff_firmware)) {
 		ret = cs35l56_firmware_shutdown(&cs35l56->base);
 		if (ret)
 			goto err;
@@ -593,7 +618,7 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56)
 	if (coeff_filename)
 		dev_dbg(cs35l56->base.dev, "Loaded Coefficients: %s\n", coeff_filename);
 
-	if (cs35l56->base.secured) {
+	if (!firmware_missing) {
 		ret = cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 		if (ret)
 			goto err_powered_up;
@@ -976,6 +1001,9 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id)
 
 	regmap_multi_reg_write(cs35l56->base.regmap, cs35l56_hda_dai_config,
 			       ARRAY_SIZE(cs35l56_hda_dai_config));
+	ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	if (ret)
+		goto err;
 
 	/*
 	 * By default only enable one ASP1TXn, where n=amplifier index,
@@ -1035,16 +1063,6 @@ const struct dev_pm_ops cs35l56_hda_pm_ops = {
 };
 EXPORT_SYMBOL_NS_GPL(cs35l56_hda_pm_ops, SND_HDA_SCODEC_CS35L56);
 
-#if IS_ENABLED(CONFIG_SND_HDA_SCODEC_CS35L56_KUNIT_TEST)
-/* Hooks to export static function to KUnit test */
-
-int cs35l56_hda_test_hook_get_speaker_id(struct device *dev, int amp_index, int num_amps)
-{
-	return cs35l56_hda_get_speaker_id(dev, amp_index, num_amps);
-}
-EXPORT_SYMBOL_NS_GPL(cs35l56_hda_test_hook_get_speaker_id, SND_HDA_SCODEC_CS35L56);
-#endif
-
 MODULE_DESCRIPTION("CS35L56 HDA Driver");
 MODULE_IMPORT_NS(SND_HDA_CIRRUS_SCODEC);
 MODULE_IMPORT_NS(SND_HDA_CS_DSP_CONTROLS);
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 3e7bfeee84fd..efe98f6f19a3 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -1207,6 +1207,9 @@ int azx_probe_codecs(struct azx *chip, unsigned int max_slots)
 				dev_warn(chip->card->dev,
 					 "Codec #%d probe error; disabling it...\n", c);
 				bus->codec_mask &= ~(1 << c);
+				/* no codecs */
+				if (bus->codec_mask == 0)
+					break;
 				/* More badly, accessing to a non-existing
 				 * codec often screws up the controller chip,
 				 * and disturbs the further communications.
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 2276adc84478..1b550c42db09 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1729,9 +1729,11 @@ static int default_bdl_pos_adj(struct azx *chip)
 	/* some exceptions: Atoms seem problematic with value 1 */
 	if (chip->pci->vendor == PCI_VENDOR_ID_INTEL) {
 		switch (chip->pci->device) {
-		case 0x0f04: /* Baytrail */
-		case 0x2284: /* Braswell */
+		case PCI_DEVICE_ID_INTEL_HDA_BYT:
+		case PCI_DEVICE_ID_INTEL_HDA_BSW:
 			return 32;
+		case PCI_DEVICE_ID_INTEL_HDA_APL:
+			return 64;
 		}
 	}
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e8819e8a9876..e8209178d87b 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -344,6 +344,7 @@ enum {
 	CXT_FIXUP_HP_ZBOOK_MUTE_LED,
 	CXT_FIXUP_HEADSET_MIC,
 	CXT_FIXUP_HP_MIC_NO_PRESENCE,
+	CXT_PINCFG_SWS_JS201D,
 };
 
 /* for hda_fixup_thinkpad_acpi() */
@@ -841,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = {
 	{}
 };
 
+/* SuoWoSi/South-holding JS201D with sn6140 */
+static const struct hda_pintbl cxt_pincfg_sws_js201d[] = {
+	{ 0x16, 0x03211040 }, /* hp out */
+	{ 0x17, 0x91170110 }, /* SPK/Class_D */
+	{ 0x18, 0x95a70130 }, /* Internal mic */
+	{ 0x19, 0x03a11020 }, /* Headset Mic */
+	{ 0x1a, 0x40f001f0 }, /* Not used */
+	{ 0x21, 0x40f001f0 }, /* Not used */
+	{}
+};
+
 static const struct hda_fixup cxt_fixups[] = {
 	[CXT_PINCFG_LENOVO_X200] = {
 		.type = HDA_FIXUP_PINS,
@@ -996,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = {
 		.chained = true,
 		.chain_id = CXT_FIXUP_HEADSET_MIC,
 	},
+	[CXT_PINCFG_SWS_JS201D] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = cxt_pincfg_sws_js201d,
+	},
 };
 
 static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -1069,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
+	SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
@@ -1109,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
 	{ .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" },
 	{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
 	{ .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" },
+	{ .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" },
 	{}
 };
 
diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 627899959ffe..e41316e2e983 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -1371,6 +1371,7 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac
 		spec->scodecs[CS8409_CODEC1] = &dolphin_cs42l42_1;
 		spec->scodecs[CS8409_CODEC1]->codec = codec;
 		spec->num_scodecs = 2;
+		spec->gen.suppress_vmaster = 1;
 
 		codec->patch_ops = cs8409_dolphin_patch_ops;
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f6f16622f9cc..a1facdb98d9a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -439,6 +439,10 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 		alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
 		fallthrough;
 	case 0x10ec0215:
+	case 0x10ec0285:
+	case 0x10ec0289:
+		alc_update_coef_idx(codec, 0x36, 1<<13, 0);
+		fallthrough;
 	case 0x10ec0230:
 	case 0x10ec0233:
 	case 0x10ec0235:
@@ -452,9 +456,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0283:
 	case 0x10ec0286:
 	case 0x10ec0288:
-	case 0x10ec0285:
 	case 0x10ec0298:
-	case 0x10ec0289:
 	case 0x10ec0300:
 		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
 		break;
@@ -3682,6 +3684,7 @@ static void alc285_hp_init(struct hda_codec *codec)
 	int i, val;
 	int coef38, coef0d, coef36;
 
+	alc_write_coefex_idx(codec, 0x58, 0x00, 0x1888); /* write default value */
 	alc_update_coef_idx(codec, 0x4a, 1<<15, 1<<15); /* Reset HP JD */
 	coef38 = alc_read_coef_idx(codec, 0x38); /* Amp control */
 	coef0d = alc_read_coef_idx(codec, 0x0d); /* Digital Misc control */
@@ -7442,6 +7445,7 @@ enum {
 	ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
 	ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
 	ALC298_FIXUP_LENOVO_C940_DUET7,
+	ALC287_FIXUP_LENOVO_14IRP8_DUETITL,
 	ALC287_FIXUP_13S_GEN2_SPEAKERS,
 	ALC256_FIXUP_SET_COEF_DEFAULTS,
 	ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
@@ -7493,6 +7497,26 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec,
 	__snd_hda_apply_fixup(codec, id, action, 0);
 }
 
+/* A special fixup for Lenovo Slim/Yoga Pro 9 14IRP8 and Yoga DuetITL 2021;
+ * 14IRP8 PCI SSID will mistakenly be matched with the DuetITL codec SSID,
+ * so we need to apply a different fixup in this case. The only DuetITL codec
+ * SSID reported so far is the 17aa:3802 while the 14IRP8 has the 17aa:38be
+ * and 17aa:38bf. If it weren't for the PCI SSID, the 14IRP8 models would
+ * have matched correctly by their codecs.
+ */
+static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec,
+					      const struct hda_fixup *fix,
+					      int action)
+{
+	int id;
+
+	if (codec->core.subsystem_id == 0x17aa3802)
+		id = ALC287_FIXUP_YOGA7_14ITL_SPEAKERS; /* DuetITL */
+	else
+		id = ALC287_FIXUP_TAS2781_I2C; /* 14IRP8 */
+	__snd_hda_apply_fixup(codec, id, action, 0);
+}
+
 static const struct hda_fixup alc269_fixups[] = {
 	[ALC269_FIXUP_GPIO2] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9377,6 +9401,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc298_fixup_lenovo_c940_duet7,
 	},
+	[ALC287_FIXUP_LENOVO_14IRP8_DUETITL] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc287_fixup_lenovo_14irp8_duetitl,
+	},
 	[ALC287_FIXUP_13S_GEN2_SPEAKERS] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -9577,13 +9605,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = cs35l41_fixup_i2c_two,
 		.chained = true,
-		.chain_id = ALC269_FIXUP_THINKPAD_ACPI,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_TAS2781_I2C] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = tas2781_fixup_i2c,
 		.chained = true,
-		.chain_id = ALC269_FIXUP_THINKPAD_ACPI,
+		.chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_YOGA7_14ARB7_I2C] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9604,6 +9632,8 @@ static const struct hda_fixup alc269_fixups[] = {
 	[ALC287_FIXUP_THINKPAD_I2S_SPK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc287_fixup_bind_dacs,
+		.chained = true,
+		.chain_id = ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
 	},
 	[ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD] = {
 		.type = HDA_FIXUP_FUNC,
@@ -9653,6 +9683,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
@@ -9732,12 +9763,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0c0b, "Dell Oasis 14 RPL-P", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0c0d, "Dell Oasis", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+	SND_PCI_QUIRK(0x1028, 0x0c0e, "Dell Oasis 16", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4),
 	SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2),
@@ -9852,6 +9887,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
@@ -9893,6 +9929,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4),
 	SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
@@ -9918,16 +9955,20 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
+	SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
@@ -9955,8 +9996,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
@@ -9994,6 +10041,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
@@ -10037,14 +10085,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
-	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
-	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
-	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10235,7 +10281,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
 	SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
-	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
+	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8 / DuetITL 2021", ALC287_FIXUP_LENOVO_14IRP8_DUETITL),
 	SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7),
 	SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS),
@@ -10251,6 +10297,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6),
 	SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
@@ -10260,6 +10307,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10322,6 +10371,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
+	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
@@ -10951,6 +11001,8 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
  *   at most one tbl is allowed to define for the same vendor and same codec
  */
 static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1025, "Acer", ALC2XX_FIXUP_HEADSET_MIC,
+		{0x19, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
@@ -11640,8 +11692,7 @@ static void alc897_hp_automute_hook(struct hda_codec *codec,
 
 	snd_hda_gen_hp_automute(codec, jack);
 	vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP;
-	snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL,
-			    vref);
+	snd_hda_set_pin_ctl(codec, 0x1b, vref);
 }
 
 static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
@@ -11650,6 +11701,10 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
 	struct alc_spec *spec = codec->spec;
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.hp_automute_hook = alc897_hp_automute_hook;
+		spec->no_shutup_pins = 1;
+	}
+	if (action == HDA_FIXUP_ACT_PROBE) {
+		snd_hda_set_pin_ctl_cache(codec, 0x1a, PIN_IN | AC_PINCTL_VREF_100);
 	}
 }
 
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 2dd809de62e5..1bfb00102a77 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -710,7 +710,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 
 	strscpy(comps->name, dev_name(dev), sizeof(comps->name));
 
-	ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready);
+	ret = tascodec_init(tas_hda->priv, codec, THIS_MODULE, tasdev_fw_ready);
 	if (!ret)
 		comps->playback_hook = tas2781_hda_playback_hook;
 
diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index c90ec3419247..504d1b8c4cbb 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -505,6 +505,13 @@ static int acp_card_rt5682s_hw_params(struct snd_pcm_substream *substream,
 
 	clk_set_rate(drvdata->wclk, srate);
 	clk_set_rate(drvdata->bclk, srate * ch * format);
+	if (!drvdata->soc_mclk) {
+		ret = acp_clk_enable(drvdata, srate, ch * format);
+		if (ret < 0) {
+			dev_err(rtd->card->dev, "Failed to enable HS clk: %d\n", ret);
+			return ret;
+		}
+	}
 
 	return 0;
 }
@@ -1464,8 +1471,13 @@ int acp_sofdsp_dai_links_create(struct snd_soc_card *card)
 	if (drv_data->amp_cpu_id == I2S_SP) {
 		links[i].name = "acp-amp-codec";
 		links[i].id = AMP_BE_ID;
-		links[i].cpus = sof_sp_virtual;
-		links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		if (drv_data->platform == RENOIR) {
+			links[i].cpus = sof_sp;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp);
+		} else {
+			links[i].cpus = sof_sp_virtual;
+			links[i].num_cpus = ARRAY_SIZE(sof_sp_virtual);
+		}
 		links[i].platforms = sof_component;
 		links[i].num_platforms = ARRAY_SIZE(sof_component);
 		links[i].dpcm_playback = 1;
diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c
index 2a9fd3275e42..20b94814a046 100644
--- a/sound/soc/amd/acp/acp-sof-mach.c
+++ b/sound/soc/amd/acp/acp-sof-mach.c
@@ -48,6 +48,7 @@ static struct acp_card_drvdata sof_rt5682s_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -58,6 +59,7 @@ static struct acp_card_drvdata sof_rt5682s_max_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = RENOIR,
 	.tdm_mode = false,
 };
 
@@ -68,6 +70,7 @@ static struct acp_card_drvdata sof_nau8825_data = {
 	.hs_codec_id = NAU8825,
 	.amp_codec_id = MAX98360A,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
@@ -79,6 +82,7 @@ static struct acp_card_drvdata sof_rt5682s_hs_rt1019_data = {
 	.hs_codec_id = RT5682S,
 	.amp_codec_id = RT1019,
 	.dmic_codec_id = DMIC,
+	.platform = REMBRANDT,
 	.soc_mclk = true,
 	.tdm_mode = false,
 };
diff --git a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
index f85b85ea4be9..2b0aa270a3e9 100644
--- a/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
+++ b/sound/soc/amd/acp/acp3x-es83xx/acp3x-es83xx.c
@@ -358,6 +358,14 @@ static const struct dmi_system_id acp3x_es83xx_dmi_table[] = {
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1010"),
+		},
+		.driver_data = (void *)(ES83XX_ENABLE_DMIC),
+	},
+	{
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "HUAWEI"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HVY-WXX9"),
 			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "M1020"),
 		},
 		.driver_data = (void *)(ES83XX_ENABLE_DMIC),
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index d83cb6e4c62a..90360f8b3e81 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -203,6 +203,20 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 		.driver_data = &acp6x_card,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J2"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21J0"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "21J5"),
 		}
 	},
@@ -238,6 +252,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 		.driver_data = &acp6x_card,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82UU"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82V2"),
 		}
 	},
@@ -251,6 +272,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83AS"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"),
 		}
@@ -300,6 +328,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"),
 		}
@@ -384,6 +419,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8BD6"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "MECHREVO"),
 			DMI_MATCH(DMI_BOARD_NAME, "MRID6"),
 		}
diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c
index 7af6a349b1d4..694b8e313902 100644
--- a/sound/soc/amd/yc/pci-acp6x.c
+++ b/sound/soc/amd/yc/pci-acp6x.c
@@ -162,6 +162,7 @@ static int snd_acp6x_probe(struct pci_dev *pci,
 	/* Yellow Carp device check */
 	switch (pci->revision) {
 	case 0x60:
+	case 0x63:
 	case 0x6f:
 		break;
 	default:
diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c
index 44c221745c3b..2392c6effed8 100644
--- a/sound/soc/codecs/cs35l45.c
+++ b/sound/soc/codecs/cs35l45.c
@@ -184,7 +184,7 @@ static int cs35l45_activate_ctl(struct snd_soc_component *component,
 	else
 		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", ctl_name);
 
-	kcontrol = snd_soc_card_get_kcontrol(component->card, name);
+	kcontrol = snd_soc_card_get_kcontrol_locked(component->card, name);
 	if (!kcontrol) {
 		dev_err(component->dev, "Can't find kcontrol %s\n", name);
 		return -EINVAL;
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 953ba066bab1..cb4e83126b08 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2023 Cirrus Logic, Inc. and
 //                    Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/types.h>
@@ -12,6 +13,15 @@
 #include "cs35l56.h"
 
 static const struct reg_sequence cs35l56_patch[] = {
+	/*
+	 * Firmware can change these to non-defaults to satisfy SDCA.
+	 * Ensure that they are at known defaults.
+	 */
+	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
+	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
+	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
+	{ CS35L56_SWIRE_DP3_CH4_INPUT,		0x00000028 },
+
 	/* These are not reset by a soft-reset, so patch to defaults. */
 	{ CS35L56_MAIN_RENDER_USER_MUTE,	0x00000000 },
 	{ CS35L56_MAIN_RENDER_USER_VOLUME,	0x00000000 },
@@ -34,15 +44,13 @@ static const struct reg_default cs35l56_reg_defaults[] = {
 	{ CS35L56_ASP1_FRAME_CONTROL5,		0x00020100 },
 	{ CS35L56_ASP1_DATA_CONTROL1,		0x00000018 },
 	{ CS35L56_ASP1_DATA_CONTROL5,		0x00000018 },
-	{ CS35L56_ASP1TX1_INPUT,		0x00000018 },
-	{ CS35L56_ASP1TX2_INPUT,		0x00000019 },
-	{ CS35L56_ASP1TX3_INPUT,		0x00000020 },
-	{ CS35L56_ASP1TX4_INPUT,		0x00000028 },
+
+	/* no defaults for ASP1TX mixer */
+
 	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
 	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
 	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
 	{ CS35L56_SWIRE_DP3_CH4_INPUT,		0x00000028 },
-	{ CS35L56_IRQ1_CFG,			0x00000000 },
 	{ CS35L56_IRQ1_MASK_1,			0x83ffffff },
 	{ CS35L56_IRQ1_MASK_2,			0xffff7fff },
 	{ CS35L56_IRQ1_MASK_4,			0xe0ffffff },
@@ -195,6 +203,47 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg)
 	}
 }
 
+/*
+ * The firmware boot sequence can overwrite the ASP1 config registers so that
+ * they don't match regmap's view of their values. Rewrite the values from the
+ * regmap cache into the hardware registers.
+ */
+int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
+{
+	struct reg_sequence asp1_regs[] = {
+		{ .reg = CS35L56_ASP1_ENABLES1 },
+		{ .reg = CS35L56_ASP1_CONTROL1 },
+		{ .reg = CS35L56_ASP1_CONTROL2 },
+		{ .reg = CS35L56_ASP1_CONTROL3 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL1 },
+		{ .reg = CS35L56_ASP1_FRAME_CONTROL5 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL1 },
+		{ .reg = CS35L56_ASP1_DATA_CONTROL5 },
+	};
+	int i, ret;
+
+	/* Read values from regmap cache into a write sequence */
+	for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) {
+		ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def);
+		if (ret)
+			goto err;
+	}
+
+	/* Write the values cache-bypassed so that they will be written to silicon */
+	ret = regmap_multi_reg_write_bypassed(cs35l56_base->regmap, asp1_regs,
+					      ARRAY_SIZE(asp1_regs));
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(cs35l56_base->dev, "Failed to sync ASP1 registers: %d\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_force_sync_asp1_registers_from_cache, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command)
 {
 	unsigned int val;
@@ -286,6 +335,7 @@ void cs35l56_wait_min_reset_pulse(void)
 EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, SND_SOC_CS35L56_SHARED);
 
 static const struct reg_sequence cs35l56_system_reset_seq[] = {
+	REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0),
 	REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET),
 };
 
@@ -400,17 +450,6 @@ int cs35l56_is_fw_reload_needed(struct cs35l56_base *cs35l56_base)
 	unsigned int val;
 	int ret;
 
-	/* Nothing to re-patch if we haven't done any patching yet. */
-	if (!cs35l56_base->fw_patched)
-		return false;
-
-	/*
-	 * If we have control of RESET we will have asserted it so the firmware
-	 * will need re-patching.
-	 */
-	if (cs35l56_base->reset_gpio)
-		return true;
-
 	/*
 	 * In secure mode FIRMWARE_MISSING is cleared by the BIOS loader so
 	 * can't be used here to test for memory retention.
@@ -590,10 +629,35 @@ void cs35l56_init_cs_dsp(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_ds
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_init_cs_dsp, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_read_prot_status(struct cs35l56_base *cs35l56_base,
+			     bool *fw_missing, unsigned int *fw_version)
+{
+	unsigned int prot_status;
+	int ret;
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_PROTECTION_STATUS, &prot_status);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get PROTECTION_STATUS failed: %d\n", ret);
+		return ret;
+	}
+
+	*fw_missing = !!(prot_status & CS35L56_FIRMWARE_MISSING);
+
+	ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP1_FW_VER, fw_version);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "Get FW VER failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, SND_SOC_CS35L56_SHARED);
+
 int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 {
 	int ret;
-	unsigned int devid, revid, otpid, secured;
+	unsigned int devid, revid, otpid, secured, fw_ver;
+	bool fw_missing;
 
 	/*
 	 * When the system is not using a reset_gpio ensure the device is
@@ -652,8 +716,13 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 		return ret;
 	}
 
-	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d\n",
-		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid);
+	ret = cs35l56_read_prot_status(cs35l56_base, &fw_missing, &fw_ver);
+	if (ret)
+		return ret;
+
+	dev_info(cs35l56_base->dev, "Cirrus Logic CS35L56%s Rev %02X OTP%d fw:%d.%d.%d (patched=%u)\n",
+		 cs35l56_base->secured ? "s" : "", cs35l56_base->rev, otpid,
+		 fw_ver >> 16, (fw_ver >> 8) & 0xff, fw_ver & 0xff, !fw_missing);
 
 	/* Wake source and *_BLOCKED interrupts default to unmasked, so mask them */
 	regmap_write(cs35l56_base->regmap, CS35L56_IRQ1_MASK_20, 0xffffffff);
@@ -668,6 +737,41 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_hw_init, SND_SOC_CS35L56_SHARED);
 
+int cs35l56_get_speaker_id(struct cs35l56_base *cs35l56_base)
+{
+	struct gpio_descs *descs;
+	int speaker_id;
+	int i, ret;
+
+	/* Read the speaker type qualifier from the motherboard GPIOs */
+	descs = gpiod_get_array_optional(cs35l56_base->dev, "spk-id", GPIOD_IN);
+	if (!descs) {
+		return -ENOENT;
+	} else if (IS_ERR(descs)) {
+		ret = PTR_ERR(descs);
+		return dev_err_probe(cs35l56_base->dev, ret, "Failed to get spk-id-gpios\n");
+	}
+
+	speaker_id = 0;
+	for (i = 0; i < descs->ndescs; i++) {
+		ret = gpiod_get_value_cansleep(descs->desc[i]);
+		if (ret < 0) {
+			dev_err_probe(cs35l56_base->dev, ret, "Failed to read spk-id[%d]\n", i);
+			goto err;
+		}
+
+		speaker_id |= (ret << i);
+	}
+
+	dev_dbg(cs35l56_base->dev, "Speaker ID = %d\n", speaker_id);
+	ret = speaker_id;
+err:
+	gpiod_put_array(descs);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_get_speaker_id, SND_SOC_CS35L56_SHARED);
+
 static const u32 cs35l56_bclk_valid_for_pll_freq_table[] = {
 	[0x0C] = 128000,
 	[0x0F] = 256000,
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 45b4de3eff94..6dd0319bc843 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2023 Cirrus Logic, Inc. and
 //                    Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/acpi.h>
 #include <linux/completion.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
@@ -15,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
@@ -59,6 +61,131 @@ static int cs35l56_dspwait_put_volsw(struct snd_kcontrol *kcontrol,
 	return snd_soc_put_volsw(kcontrol, ucontrol);
 }
 
+static const unsigned short cs35l56_asp1_mixer_regs[] = {
+	CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX2_INPUT,
+	CS35L56_ASP1TX3_INPUT, CS35L56_ASP1TX4_INPUT,
+};
+
+static const char * const cs35l56_asp1_mux_control_names[] = {
+	"ASP1 TX1 Source", "ASP1 TX2 Source", "ASP1 TX3 Source", "ASP1 TX4 Source"
+};
+
+static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private *cs35l56)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
+	const char *prefix = cs35l56->component->name_prefix;
+	char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+	const char *name;
+	struct snd_kcontrol *kcontrol;
+	struct soc_enum *e;
+	unsigned int val[4];
+	int i, item, ret;
+
+	if (cs35l56->asp1_mixer_widgets_initialized)
+		return 0;
+
+	/*
+	 * Resume so we can read the registers from silicon if the regmap
+	 * cache has not yet been populated.
+	 */
+	ret = pm_runtime_resume_and_get(cs35l56->base.dev);
+	if (ret < 0)
+		return ret;
+
+	/* Wait for firmware download and reboot */
+	cs35l56_wait_dsp_ready(cs35l56);
+
+	ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
+			       val, ARRAY_SIZE(val));
+
+	pm_runtime_mark_last_busy(cs35l56->base.dev);
+	pm_runtime_put_autosuspend(cs35l56->base.dev);
+
+	if (ret) {
+		dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
+		name = cs35l56_asp1_mux_control_names[i];
+
+		if (prefix) {
+			snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
+			name = full_name;
+		}
+
+		kcontrol = snd_soc_card_get_kcontrol_locked(dapm->card, name);
+		if (!kcontrol) {
+			dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
+			continue;
+		}
+
+		e = (struct soc_enum *)kcontrol->private_value;
+		item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+	}
+
+	cs35l56->asp1_mixer_widgets_initialized = true;
+
+	return 0;
+}
+
+static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int index = e->shift_l;
+	unsigned int addr, val;
+	int ret;
+
+	ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+	if (ret)
+		return ret;
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	ret = regmap_read(cs35l56->base.regmap, addr, &val);
+	if (ret)
+		return ret;
+
+	val &= CS35L56_ASP_TXn_SRC_MASK;
+	ucontrol->value.enumerated.item[0] = snd_soc_enum_val_to_item(e, val);
+
+	return 0;
+}
+
+static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
+				      struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+	int item = ucontrol->value.enumerated.item[0];
+	int index = e->shift_l;
+	unsigned int addr, val;
+	bool changed;
+	int ret;
+
+	ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+	if (ret)
+		return ret;
+
+	addr = cs35l56_asp1_mixer_regs[index];
+	val = snd_soc_enum_item_to_val(e, item);
+
+	ret = regmap_update_bits_check(cs35l56->base.regmap, addr,
+				       CS35L56_ASP_TXn_SRC_MASK, val, &changed);
+	if (ret)
+		return ret;
+
+	if (changed)
+		snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+
+	return changed;
+}
+
 static DECLARE_TLV_DB_SCALE(vol_tlv, -10000, 25, 0);
 
 static const struct snd_kcontrol_new cs35l56_controls[] = {
@@ -77,40 +204,44 @@ static const struct snd_kcontrol_new cs35l56_controls[] = {
 };
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx1_enum,
-				  CS35L56_ASP1TX1_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  0, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx1_mux =
-	SOC_DAPM_ENUM("ASP1TX1 SRC", cs35l56_asp1tx1_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX1 SRC", cs35l56_asp1tx1_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx2_enum,
-				  CS35L56_ASP1TX2_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  1, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx2_mux =
-	SOC_DAPM_ENUM("ASP1TX2 SRC", cs35l56_asp1tx2_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX2 SRC", cs35l56_asp1tx2_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx3_enum,
-				  CS35L56_ASP1TX3_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  2, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx3_mux =
-	SOC_DAPM_ENUM("ASP1TX3 SRC", cs35l56_asp1tx3_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX3 SRC", cs35l56_asp1tx3_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx4_enum,
-				  CS35L56_ASP1TX4_INPUT,
-				  0, CS35L56_ASP_TXn_SRC_MASK,
+				  SND_SOC_NOPM,
+				  3, 0,
 				  cs35l56_tx_input_texts,
 				  cs35l56_tx_input_values);
 
 static const struct snd_kcontrol_new asp1_tx4_mux =
-	SOC_DAPM_ENUM("ASP1TX4 SRC", cs35l56_asp1tx4_enum);
+	SOC_DAPM_ENUM_EXT("ASP1TX4 SRC", cs35l56_asp1tx4_enum,
+			  cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
 
 static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx1_enum,
 				CS35L56_SWIRE_DP3_CH1_INPUT,
@@ -148,6 +279,21 @@ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx4_enum,
 static const struct snd_kcontrol_new sdw1_tx4_mux =
 	SOC_DAPM_ENUM("SDW1TX4 SRC", cs35l56_sdw1tx4_enum);
 
+static int cs35l56_asp1_cfg_event(struct snd_soc_dapm_widget *w,
+				  struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		/* Override register values set by firmware boot */
+		return cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+	default:
+		return 0;
+	}
+}
+
 static int cs35l56_play_event(struct snd_soc_dapm_widget *w,
 			      struct snd_kcontrol *kcontrol, int event)
 {
@@ -184,6 +330,9 @@ static const struct snd_soc_dapm_widget cs35l56_dapm_widgets[] = {
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_B", 0, 0),
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_AMP", 0, 0),
 
+	SND_SOC_DAPM_SUPPLY("ASP1 CFG", SND_SOC_NOPM, 0, 0, cs35l56_asp1_cfg_event,
+			    SND_SOC_DAPM_PRE_PMU),
+
 	SND_SOC_DAPM_SUPPLY("PLAY", SND_SOC_NOPM, 0, 0, cs35l56_play_event,
 			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
 
@@ -251,6 +400,9 @@ static const struct snd_soc_dapm_route cs35l56_audio_map[] = {
 	{ "AMP", NULL, "VDD_B" },
 	{ "AMP", NULL, "VDD_AMP" },
 
+	{ "ASP1 Playback", NULL, "ASP1 CFG" },
+	{ "ASP1 Capture", NULL, "ASP1 CFG" },
+
 	{ "ASP1 Playback", NULL, "PLAY" },
 	{ "SDW1 Playback", NULL, "PLAY" },
 
@@ -650,7 +802,7 @@ static struct snd_soc_dai_driver cs35l56_dai[] = {
 	}
 };
 
-static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
@@ -662,19 +814,10 @@ static void cs35l56_secure_patch(struct cs35l56_private *cs35l56)
 		cs35l56_mbox_send(&cs35l56->base, CS35L56_MBOX_CMD_AUDIO_REINIT);
 }
 
-static void cs35l56_patch(struct cs35l56_private *cs35l56)
+static void cs35l56_patch(struct cs35l56_private *cs35l56, bool firmware_missing)
 {
-	unsigned int firmware_missing;
 	int ret;
 
-	ret = regmap_read(cs35l56->base.regmap, CS35L56_PROTECTION_STATUS, &firmware_missing);
-	if (ret) {
-		dev_err(cs35l56->base.dev, "Failed to read PROTECTION_STATUS: %d\n", ret);
-		return;
-	}
-
-	firmware_missing &= CS35L56_FIRMWARE_MISSING;
-
 	/*
 	 * Disable SoundWire interrupts to prevent race with IRQ work.
 	 * Setting sdw_irq_no_unmask prevents the handler re-enabling
@@ -747,23 +890,51 @@ static void cs35l56_dsp_work(struct work_struct *work)
 	struct cs35l56_private *cs35l56 = container_of(work,
 						       struct cs35l56_private,
 						       dsp_work);
+	unsigned int firmware_version;
+	bool firmware_missing;
+	int ret;
 
 	if (!cs35l56->base.init_done)
 		return;
 
 	pm_runtime_get_sync(cs35l56->base.dev);
 
+	ret = cs35l56_read_prot_status(&cs35l56->base, &firmware_missing, &firmware_version);
+	if (ret)
+		goto err;
+
+	/* Populate fw file qualifier with the revision and security state */
+	kfree(cs35l56->dsp.fwf_name);
+	if (firmware_missing) {
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL, "%02x-dsp1", cs35l56->base.rev);
+	} else {
+		/* Firmware files must match the running firmware version */
+		cs35l56->dsp.fwf_name = kasprintf(GFP_KERNEL,
+						  "%02x%s-%06x-dsp1",
+						  cs35l56->base.rev,
+						  cs35l56->base.secured ? "-s" : "",
+						  firmware_version);
+	}
+
+	if (!cs35l56->dsp.fwf_name)
+		goto err;
+
+	dev_dbg(cs35l56->base.dev, "DSP fwf name: '%s' system name: '%s'\n",
+		cs35l56->dsp.fwf_name, cs35l56->dsp.system_name);
+
 	/*
-	 * When the device is running in secure mode the firmware files can
-	 * only contain insecure tunings and therefore we do not need to
-	 * shutdown the firmware to apply them and can use the lower cost
-	 * reinit sequence instead.
+	 * The firmware cannot be patched if it is already running from
+	 * patch RAM. In this case the firmware files are versioned to
+	 * match the running firmware version and will only contain
+	 * tunings. We do not need to shutdown the firmware to apply
+	 * tunings so can use the lower cost reinit sequence instead.
 	 */
-	if (cs35l56->base.secured)
-		cs35l56_secure_patch(cs35l56);
+	if (!firmware_missing)
+		cs35l56_reinit_patch(cs35l56);
 	else
-		cs35l56_patch(cs35l56);
+		cs35l56_patch(cs35l56, firmware_missing);
 
+err:
 	pm_runtime_mark_last_busy(cs35l56->base.dev);
 	pm_runtime_put_autosuspend(cs35l56->base.dev);
 }
@@ -778,10 +949,19 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 
 	if (!cs35l56->dsp.system_name &&
 	    (snd_soc_card_get_pci_ssid(component->card, &vendor, &device) == 0)) {
-		cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
-							  GFP_KERNEL,
-							  "%04x%04x",
-							  vendor, device);
+		/* Append a speaker qualifier if there is a speaker ID */
+		if (cs35l56->speaker_id >= 0) {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x-spkid%d",
+								  vendor, device,
+								  cs35l56->speaker_id);
+		} else {
+			cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev,
+								  GFP_KERNEL,
+								  "%04x%04x",
+								  vendor, device);
+		}
 		if (!cs35l56->dsp.system_name)
 			return -ENOMEM;
 	}
@@ -799,6 +979,13 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 	debugfs_create_bool("can_hibernate", 0444, debugfs_root, &cs35l56->base.can_hibernate);
 	debugfs_create_bool("fw_patched", 0444, debugfs_root, &cs35l56->base.fw_patched);
 
+	/*
+	 * The widgets for the ASP1TX mixer can't be initialized
+	 * until the firmware has been downloaded and rebooted.
+	 */
+	regcache_drop_region(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX4_INPUT);
+	cs35l56->asp1_mixer_widgets_initialized = false;
+
 	queue_work(cs35l56->dsp_wq, &cs35l56->dsp_work);
 
 	return 0;
@@ -809,6 +996,16 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
 
 	cancel_work_sync(&cs35l56->dsp_work);
+
+	if (cs35l56->dsp.cs_dsp.booted)
+		wm_adsp_power_down(&cs35l56->dsp);
+
+	wm_adsp2_component_remove(&cs35l56->dsp, component);
+
+	kfree(cs35l56->dsp.fwf_name);
+	cs35l56->dsp.fwf_name = NULL;
+
+	cs35l56->component = NULL;
 }
 
 static int cs35l56_set_bias_level(struct snd_soc_component *component,
@@ -1050,7 +1247,13 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return 0;
 
-	cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+	/* Append a speaker qualifier if there is a speaker ID */
+	if (cs35l56->speaker_id >= 0)
+		cs35l56->dsp.system_name = devm_kasprintf(dev, GFP_KERNEL, "%s-spkid%d",
+							  prop, cs35l56->speaker_id);
+	else
+		cs35l56->dsp.system_name = devm_kstrdup(dev, prop, GFP_KERNEL);
+
 	if (cs35l56->dsp.system_name == NULL)
 		return -ENOMEM;
 
@@ -1059,12 +1262,101 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
 	return 0;
 }
 
+/*
+ * Some SoundWire laptops have a spk-id-gpios property but it points to
+ * the wrong ACPI Device node so can't be used to get the GPIO. Try to
+ * find the SDCA node containing the GpioIo resource and add a GPIO
+ * mapping to it.
+ */
+static const struct acpi_gpio_params cs35l56_af01_first_gpio = { 0, 0, false };
+static const struct acpi_gpio_mapping cs35l56_af01_spkid_gpios_mapping[] = {
+	{ "spk-id-gpios", &cs35l56_af01_first_gpio, 1 },
+	{ }
+};
+
+static void cs35l56_acpi_dev_release_driver_gpios(void *adev)
+{
+	acpi_dev_remove_driver_gpios(adev);
+}
+
+static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l56)
+{
+	struct fwnode_handle *af01_fwnode;
+	const union acpi_object *obj;
+	struct gpio_desc *desc;
+	int ret;
+
+	/* Find the SDCA node containing the GpioIo */
+	af01_fwnode = device_get_named_child_node(cs35l56->base.dev, "AF01");
+	if (!af01_fwnode) {
+		dev_dbg(cs35l56->base.dev, "No AF01 node\n");
+		return -ENOENT;
+	}
+
+	ret = acpi_dev_get_property(ACPI_COMPANION(cs35l56->base.dev),
+				    "spk-id-gpios", ACPI_TYPE_PACKAGE, &obj);
+	if (ret) {
+		dev_dbg(cs35l56->base.dev, "Could not get spk-id-gpios package: %d\n", ret);
+		return -ENOENT;
+	}
+
+	/* The broken properties we can handle are a 4-element package (one GPIO) */
+	if (obj->package.count != 4) {
+		dev_warn(cs35l56->base.dev, "Unexpected spk-id element count %d\n",
+			 obj->package.count);
+		return -ENOENT;
+	}
+
+	/* Add a GPIO mapping if it doesn't already have one */
+	if (!fwnode_property_present(af01_fwnode, "spk-id-gpios")) {
+		struct acpi_device *adev = to_acpi_device_node(af01_fwnode);
+
+		/*
+		 * Can't use devm_acpi_dev_add_driver_gpios() because the
+		 * mapping isn't being added to the node pointed to by
+		 * ACPI_COMPANION().
+		 */
+		ret = acpi_dev_add_driver_gpios(adev, cs35l56_af01_spkid_gpios_mapping);
+		if (ret) {
+			return dev_err_probe(cs35l56->base.dev, ret,
+					     "Failed to add gpio mapping to AF01\n");
+		}
+
+		ret = devm_add_action_or_reset(cs35l56->base.dev,
+					       cs35l56_acpi_dev_release_driver_gpios,
+					       adev);
+		if (ret)
+			return ret;
+
+		dev_dbg(cs35l56->base.dev, "Added spk-id-gpios mapping to AF01\n");
+	}
+
+	desc = fwnode_gpiod_get_index(af01_fwnode, "spk-id", 0, GPIOD_IN, NULL);
+	if (IS_ERR(desc)) {
+		ret = PTR_ERR(desc);
+		return dev_err_probe(cs35l56->base.dev, ret, "Get GPIO from AF01 failed\n");
+	}
+
+	ret = gpiod_get_value_cansleep(desc);
+	gpiod_put(desc);
+
+	if (ret < 0) {
+		dev_err_probe(cs35l56->base.dev, ret, "Error reading spk-id GPIO\n");
+		return ret;
+		}
+
+	dev_info(cs35l56->base.dev, "Got spk-id from AF01\n");
+
+	return ret;
+}
+
 int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
 	init_completion(&cs35l56->init_completion);
 	mutex_init(&cs35l56->base.irq_lock);
+	cs35l56->speaker_id = -ENOENT;
 
 	dev_set_drvdata(cs35l56->base.dev, cs35l56);
 
@@ -1101,6 +1393,15 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
 		gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 1);
 	}
 
+	ret = cs35l56_get_speaker_id(&cs35l56->base);
+	if (ACPI_COMPANION(cs35l56->base.dev) && cs35l56->sdw_peripheral && (ret == -ENOENT))
+		ret = cs35l56_try_get_broken_sdca_spkid_gpio(cs35l56);
+
+	if ((ret < 0) && (ret != -ENOENT))
+		goto err;
+
+	cs35l56->speaker_id = ret;
+
 	ret = cs35l56_get_firmware_uid(cs35l56);
 	if (ret != 0)
 		goto err;
@@ -1152,11 +1453,9 @@ int cs35l56_init(struct cs35l56_private *cs35l56)
 	if (ret < 0)
 		return ret;
 
-	/* Populate the DSP information with the revision and security state */
-	cs35l56->dsp.part = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL, "cs35l56%s-%02x",
-					   cs35l56->base.secured ? "s" : "", cs35l56->base.rev);
-	if (!cs35l56->dsp.part)
-		return -ENOMEM;
+	ret = cs35l56_set_patch(&cs35l56->base);
+	if (ret)
+		return ret;
 
 	if (!cs35l56->base.reset_gpio) {
 		dev_dbg(cs35l56->base.dev, "No reset gpio: using soft reset\n");
@@ -1190,10 +1489,6 @@ post_soft_reset:
 	if (ret)
 		return ret;
 
-	ret = cs35l56_set_patch(&cs35l56->base);
-	if (ret)
-		return ret;
-
 	/* Registers could be dirty after soft reset or SoundWire enumeration */
 	regcache_sync(cs35l56->base.regmap);
 
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 8159c3e217d9..b000e7365e40 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -44,12 +44,14 @@ struct cs35l56_private {
 	bool sdw_attached;
 	struct completion init_completion;
 
+	int speaker_id;
 	u32 rx_mask;
 	u32 tx_mask;
 	u8 asp_slot_width;
 	u8 asp_slot_count;
 	bool tdm_mode;
 	bool sysclk_set;
+	bool asp1_mixer_widgets_initialized;
 	u8 old_sdw_clock_scale;
 };
 
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 6a64681767de..a97ccb512deb 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2257,7 +2257,10 @@ static int cs42l43_codec_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(priv->dev);
 	pm_runtime_set_active(priv->dev);
 	pm_runtime_get_noresume(priv->dev);
-	devm_pm_runtime_enable(priv->dev);
+
+	ret = devm_pm_runtime_enable(priv->dev);
+	if (ret)
+		goto err_pm;
 
 	for (i = 0; i < ARRAY_SIZE(cs42l43_irqs); i++) {
 		ret = cs42l43_request_irq(priv, dom, cs42l43_irqs[i].name,
@@ -2333,8 +2336,47 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static DEFINE_RUNTIME_DEV_PM_OPS(cs42l43_codec_pm_ops, NULL,
-				 cs42l43_codec_runtime_resume, NULL);
+static int cs42l43_codec_suspend(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	disable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_suspend_noirq(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	enable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_resume(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	enable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static int cs42l43_codec_resume_noirq(struct device *dev)
+{
+	struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+	disable_irq(cs42l43->irq);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cs42l43_codec_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend, cs42l43_codec_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend_noirq, cs42l43_codec_resume_noirq)
+	RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL)
+};
 
 static const struct platform_device_id cs42l43_codec_id_table[] = {
 	{ "cs42l43-codec", },
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index fa890f6205e2..cbcd02ec6ba4 100755..100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -45,6 +45,82 @@ struct es8326_priv {
 	int jack_remove_retry;
 };
 
+static int es8326_crosstalk1_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x20;
+	crosstalk_l &= 0xf0;
+	crosstalk = crosstalk_h >> 1 | crosstalk_l >> 4;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk1_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = (crosstalk & 0x10) << 1;
+	crosstalk_l &= 0x0f;
+	crosstalk_l |= (crosstalk & 0x0f) << 4;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x20, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
+static int es8326_crosstalk2_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	regmap_read(es8326->regmap, ES8326_DAC_RAMPRATE, &crosstalk_h);
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h &= 0x10;
+	crosstalk_l &= 0x0f;
+	crosstalk = crosstalk_h  | crosstalk_l;
+	ucontrol->value.integer.value[0] = crosstalk;
+
+	return 0;
+}
+
+static int es8326_crosstalk2_set(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
+	unsigned int crosstalk_h, crosstalk_l;
+	unsigned int crosstalk;
+
+	crosstalk = ucontrol->value.integer.value[0];
+	regmap_read(es8326->regmap, ES8326_DAC_CROSSTALK, &crosstalk_l);
+	crosstalk_h = crosstalk & 0x10;
+	crosstalk_l &= 0xf0;
+	crosstalk_l |= crosstalk & 0x0f;
+	regmap_update_bits(es8326->regmap, ES8326_DAC_RAMPRATE,
+			0x10, crosstalk_h);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, crosstalk_l);
+
+	return 0;
+}
+
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(dac_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_vol_tlv, -9550, 50, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(adc_analog_pga_tlv, 0, 300, 0);
@@ -102,6 +178,10 @@ static const struct snd_kcontrol_new es8326_snd_controls[] = {
 	SOC_SINGLE_TLV("ALC Capture Target Level", ES8326_ALC_LEVEL,
 			0, 0x0f, 0, drc_target_tlv),
 
+	SOC_SINGLE_EXT("CROSSTALK1", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk1_get, es8326_crosstalk1_set),
+	SOC_SINGLE_EXT("CROSSTALK2", SND_SOC_NOPM, 0, 31, 0,
+			es8326_crosstalk2_get, es8326_crosstalk2_set),
 };
 
 static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
@@ -117,12 +197,6 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("I2S OUT", "I2S1 Capture", 0, SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_AIF_IN("I2S IN", "I2S1 Playback", 0, SND_SOC_NOPM, 0, 0),
 
-	/* ADC Digital Mute */
-	SND_SOC_DAPM_PGA("ADC L1", ES8326_ADC_MUTE, 0, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R1", ES8326_ADC_MUTE, 1, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC L2", ES8326_ADC_MUTE, 2, 1, NULL, 0),
-	SND_SOC_DAPM_PGA("ADC R2", ES8326_ADC_MUTE, 3, 1, NULL, 0),
-
 	/* Analog Power Supply*/
 	SND_SOC_DAPM_DAC("Right DAC", NULL, ES8326_ANA_PDN, 0, 1),
 	SND_SOC_DAPM_DAC("Left DAC", NULL, ES8326_ANA_PDN, 1, 1),
@@ -142,15 +216,10 @@ static const struct snd_soc_dapm_widget es8326_dapm_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route es8326_dapm_routes[] = {
-	{"ADC L1", NULL, "MIC1"},
-	{"ADC R1", NULL, "MIC2"},
-	{"ADC L2", NULL, "MIC3"},
-	{"ADC R2", NULL, "MIC4"},
-
-	{"ADC L", NULL, "ADC L1"},
-	{"ADC R", NULL, "ADC R1"},
-	{"ADC L", NULL, "ADC L2"},
-	{"ADC R", NULL, "ADC R2"},
+	{"ADC L", NULL, "MIC1"},
+	{"ADC R", NULL, "MIC2"},
+	{"ADC L", NULL, "MIC3"},
+	{"ADC R", NULL, "MIC4"},
 
 	{"I2S OUT", NULL, "ADC L"},
 	{"I2S OUT", NULL, "ADC R"},
@@ -440,10 +509,16 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 	unsigned int offset_l, offset_r;
 
 	if (mute) {
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ES8326_MUTE);
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xf0);
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_OFF);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ES8326_MUTE);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF,
+					0x30, 0x00);
+		} else {
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x0F);
+		}
 	} else {
 		if (!es8326->calibrated) {
 			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_FORCE_CAL);
@@ -456,11 +531,22 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction)
 			regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r);
 			es8326->calibrated = true;
 		}
-		regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
-		regmap_write(es8326->regmap, ES8326_HP_VOL, 0x91);
-		regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
-		regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
-				ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+			usleep_range(1000, 5000);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x20);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x30, 0x30);
+			regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
+			regmap_write(es8326->regmap, ES8326_HP_CAL, ES8326_HP_ON);
+			regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE,
+					ES8326_MUTE_MASK, ~(ES8326_MUTE));
+		} else {
+			msleep(300);
+			regmap_update_bits(es8326->regmap,  ES8326_ADC_MUTE,
+					0x0F, 0x00);
+		}
 	}
 	return 0;
 }
@@ -477,23 +563,20 @@ static int es8326_set_bias_level(struct snd_soc_component *codec,
 		if (ret)
 			return ret;
 
-		regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x00);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x02);
+		usleep_range(5000, 10000);
 		regmap_write(es8326->regmap, ES8326_INTOUT_IO, es8326->interrupt_clk);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
 			    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
 		regmap_write(es8326->regmap, ES8326_PGA_PDN, 0x40);
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 		regmap_update_bits(es8326->regmap,  ES8326_CLK_CTL, 0x20, 0x20);
-
-		regmap_update_bits(es8326->regmap, ES8326_RESET,
-				ES8326_CSM_ON, ES8326_CSM_ON);
+		regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x00);
 		break;
 	case SND_SOC_BIAS_PREPARE:
 		break;
 	case SND_SOC_BIAS_STANDBY:
 		regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
-		regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x00);
 		regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x00);
 		regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT);
 		break;
@@ -513,7 +596,7 @@ static const struct snd_soc_dai_ops es8326_ops = {
 	.set_fmt = es8326_set_dai_fmt,
 	.set_sysclk = es8326_set_dai_sysclk,
 	.mute_stream = es8326_mute,
-	.no_capture_mute = 1,
+	.no_capture_mute = 0,
 };
 
 static struct snd_soc_dai_driver es8326_dai = {
@@ -672,6 +755,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			es8326->hp = 0;
 		}
 		regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+		regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a);
+		regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03);
 		/*
 		 * Inverted HPJACK_POL bit to trigger one IRQ to double check HP Removal event
 		 */
@@ -695,8 +780,11 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			 * Don't report jack status.
 			 */
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
+			es8326_enable_micbias(es8326->component);
 			usleep_range(50000, 70000);
 			regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
+			regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08);
 			queue_delayed_work(system_wq, &es8326->jack_detect_work,
 					msecs_to_jiffies(400));
 			es8326->hp = 1;
@@ -736,13 +824,10 @@ exit:
 static irqreturn_t es8326_irq(int irq, void *dev_id)
 {
 	struct es8326_priv *es8326 = dev_id;
-	struct snd_soc_component *comp = es8326->component;
 
 	if (!es8326->jack)
 		goto out;
 
-	es8326_enable_micbias(comp);
-
 	if (es8326->jack->status & SND_JACK_HEADSET)
 		queue_delayed_work(system_wq, &es8326->jack_detect_work,
 				   msecs_to_jiffies(10));
@@ -766,14 +851,14 @@ static int es8326_calibrate(struct snd_soc_component *component)
 	if ((es8326->version == ES8326_VERSION_B) && (es8326->calibrated == false)) {
 		dev_dbg(component->dev, "ES8326_VERSION_B, calibrating\n");
 		regmap_write(es8326->regmap, ES8326_CLK_INV, 0xc0);
-		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x01);
+		regmap_write(es8326->regmap, ES8326_CLK_DIV1, 0x03);
 		regmap_write(es8326->regmap, ES8326_CLK_DLL, 0x30);
 		regmap_write(es8326->regmap, ES8326_CLK_MUX, 0xed);
 		regmap_write(es8326->regmap, ES8326_CLK_DAC_SEL, 0x08);
 		regmap_write(es8326->regmap, ES8326_CLK_TRI, 0xc1);
 		regmap_write(es8326->regmap, ES8326_DAC_MUTE, 0x03);
 		regmap_write(es8326->regmap, ES8326_ANA_VSEL, 0x7f);
-		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x03);
+		regmap_write(es8326->regmap, ES8326_VMIDLOW, 0x23);
 		regmap_write(es8326->regmap, ES8326_DAC2HPMIX, 0x88);
 		usleep_range(15000, 20000);
 		regmap_write(es8326->regmap, ES8326_HP_OFFSET_CAL, 0x8c);
@@ -814,13 +899,13 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* reset internal clock state */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x1f);
 	regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
+	regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0);
 	usleep_range(10000, 15000);
 	regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xe9);
-	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0x4b);
+	regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb);
 	/* set headphone default type and detect pin */
 	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83);
 	regmap_write(es8326->regmap, ES8326_CLK_RESAMPLE, 0x05);
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
 
 	/* set internal oscillator as clock source of headpone cp */
 	regmap_write(es8326->regmap, ES8326_CLK_DIV_CPC, 0x89);
@@ -828,14 +913,15 @@ static int es8326_resume(struct snd_soc_component *component)
 	/* clock manager reset release */
 	regmap_write(es8326->regmap, ES8326_RESET, 0x17);
 	/* set headphone detection as half scan mode */
-	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x30);
+	regmap_write(es8326->regmap, ES8326_HP_MISC, 0x3d);
 	regmap_write(es8326->regmap, ES8326_PULLUP_CTL, 0x00);
 
 	/* enable headphone driver */
+	regmap_write(es8326->regmap, ES8326_HP_VOL, 0xc4);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa7);
 	usleep_range(2000, 5000);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xa3);
-	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0xb3);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x23);
+	regmap_write(es8326->regmap, ES8326_HP_DRIVER_REF, 0x33);
 	regmap_write(es8326->regmap, ES8326_HP_DRIVER, 0xa1);
 
 	regmap_write(es8326->regmap, ES8326_CLK_INV, 0x00);
@@ -844,6 +930,8 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_CLK_CAL_TIME, 0x00);
 	/* calibrate for B version */
 	es8326_calibrate(component);
+	regmap_write(es8326->regmap, ES8326_DAC_CROSSTALK, 0xaa);
+	regmap_write(es8326->regmap, ES8326_DAC_RAMPRATE, 0x00);
 	/* turn off headphone out */
 	regmap_write(es8326->regmap, ES8326_HP_CAL, 0x00);
 	/* set ADC and DAC in low power mode */
@@ -856,6 +944,14 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_write(es8326->regmap, ES8326_DAC_DSM, 0x08);
 	regmap_write(es8326->regmap, ES8326_DAC_VPPSCALE, 0x15);
 
+	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
+			((es8326->version == ES8326_VERSION_B) ?
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
+			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
+	usleep_range(5000, 10000);
+	es8326_enable_micbias(es8326->component);
+	usleep_range(50000, 70000);
+	regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
 	regmap_write(es8326->regmap, ES8326_INT_SOURCE,
 		    (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
 	regmap_write(es8326->regmap, ES8326_INTOUT_IO,
@@ -864,7 +960,7 @@ static int es8326_resume(struct snd_soc_component *component)
 		    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
 	regmap_write(es8326->regmap, ES8326_SDINOUT23_IO, ES8326_IO_INPUT);
 
-	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
+	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
 	regmap_write(es8326->regmap, ES8326_RESET, ES8326_CSM_ON);
 	regmap_update_bits(es8326->regmap, ES8326_PGAGAIN, ES8326_MIC_SEL_MASK,
 			   ES8326_MIC1_SEL);
@@ -872,11 +968,7 @@ static int es8326_resume(struct snd_soc_component *component)
 	regmap_update_bits(es8326->regmap, ES8326_DAC_MUTE, ES8326_MUTE_MASK,
 			   ES8326_MUTE);
 
-	regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x80 |
-			((es8326->version == ES8326_VERSION_B) ?
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol) :
-			(ES8326_HP_DET_SRC_PIN9 | es8326->jack_pol | 0x04)));
-	regmap_write(es8326->regmap, ES8326_HP_VOL, 0x11);
+	regmap_write(es8326->regmap, ES8326_ADC_MUTE, 0x0f);
 
 	es8326->jack_remove_retry = 0;
 	es8326->hp = 0;
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
index 90a08351d6ac..4234bbb900c4 100644
--- a/sound/soc/codecs/es8326.h
+++ b/sound/soc/codecs/es8326.h
@@ -72,6 +72,7 @@
 #define ES8326_DAC_VOL		0x50
 #define ES8326_DRC_RECOVERY	0x53
 #define ES8326_DRC_WINSIZE	0x54
+#define ES8326_DAC_CROSSTALK	0x55
 #define ES8326_HPJACK_TIMER	0x56
 #define ES8326_HPDET_TYPE	0x57
 #define ES8326_INT_SOURCE	0x58
@@ -100,7 +101,7 @@
 #define ES8326_MUTE (3 << 0)
 
 /* ES8326_CLK_CTL */
-#define ES8326_CLK_ON (0x7f << 0)
+#define ES8326_CLK_ON (0x7e << 0)
 #define ES8326_CLK_OFF (0 << 0)
 
 /* ES8326_CLK_INV */
diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c
index 7e21cec3c2fb..6ce309980cd1 100644
--- a/sound/soc/codecs/lpass-wsa-macro.c
+++ b/sound/soc/codecs/lpass-wsa-macro.c
@@ -1584,7 +1584,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 	struct wsa_macro *wsa = snd_soc_component_get_drvdata(component);
 
 	if (w->shift == WSA_MACRO_COMP1) {
@@ -1623,10 +1622,8 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_ENABLE);
-			offset_val = -2;
 		}
 		val = snd_soc_component_read(component, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(component, gain_reg, val);
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
@@ -1654,10 +1651,6 @@ static int wsa_macro_enable_interpolator(struct snd_soc_dapm_widget *w,
 					CDC_WSA_RX1_RX_PATH_MIX_SEC0,
 					CDC_WSA_RX_PGA_HALF_DB_MASK,
 					CDC_WSA_RX_PGA_HALF_DB_DISABLE);
-			offset_val = 2;
-			val = snd_soc_component_read(component, gain_reg);
-			val += offset_val;
-			snd_soc_component_write(component, gain_reg, val);
 		}
 		wsa_macro_config_ear_spkr_gain(component, wsa,
 						event, gain_reg);
diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c
index b9f19fbd2911..b24d6472ad5f 100644
--- a/sound/soc/codecs/madera.c
+++ b/sound/soc/codecs/madera.c
@@ -3884,7 +3884,7 @@ static inline int madera_set_fll_clks(struct madera_fll *fll, int base, bool ena
 	return madera_set_fll_clks_reg(fll, ena,
 				       base + MADERA_FLL_CONTROL_6_OFFS,
 				       MADERA_FLL1_REFCLK_SRC_MASK,
-				       MADERA_FLL1_REFCLK_DIV_SHIFT);
+				       MADERA_FLL1_REFCLK_SRC_SHIFT);
 }
 
 static inline int madera_set_fllao_clks(struct madera_fll *fll, int base, bool ena)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 5150d6ee3748..20191a4473c2 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3317,6 +3317,7 @@ static void rt5645_jack_detect_work(struct work_struct *work)
 				    report, SND_JACK_HEADPHONE);
 		snd_soc_jack_report(rt5645->mic_jack,
 				    report, SND_JACK_MICROPHONE);
+		mutex_unlock(&rt5645->jd_mutex);
 		return;
 	case 4:
 		val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020;
@@ -3692,6 +3693,11 @@ static const struct rt5645_platform_data jd_mode3_monospk_platform_data = {
 	.mono_speaker = true,
 };
 
+static const struct rt5645_platform_data jd_mode3_inv_data = {
+	.jd_mode = 3,
+	.inv_jd1_1 = true,
+};
+
 static const struct rt5645_platform_data jd_mode3_platform_data = {
 	.jd_mode = 3,
 };
@@ -3837,6 +3843,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		  DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		  DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"),
 		  DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"),
+		  /*
+		   * Above strings are too generic, LattePanda BIOS versions for
+		   * all 4 hw revisions are:
+		   * DF-BI-7-S70CR100-*
+		   * DF-BI-7-S70CR110-*
+		   * DF-BI-7-S70CR200-*
+		   * LP-BS-7-S70CR700-*
+		   * Do a partial match for S70CR to avoid false positive matches.
+		   */
+		  DMI_MATCH(DMI_BIOS_VERSION, "S70CR"),
 		},
 		.driver_data = (void *)&lattepanda_board_platform_data,
 	},
@@ -3871,6 +3887,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
 		},
 		.driver_data = (void *)&intel_braswell_platform_data,
 	},
+	{
+		.ident = "Meegopad T08",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+			DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"),
+			DMI_MATCH(DMI_BOARD_VERSION, "V1.1"),
+		},
+		.driver_data = (void *)&jd_mode3_inv_data,
+	},
 	{ }
 };
 
diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
index b7e56ceb1acf..5d0e5348b361 100644
--- a/sound/soc/codecs/tas2781-comlib.c
+++ b/sound/soc/codecs/tas2781-comlib.c
@@ -267,6 +267,7 @@ void tas2781_reset(struct tasdevice_priv *tas_dev)
 EXPORT_SYMBOL_GPL(tas2781_reset);
 
 int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+	struct module *module,
 	void (*cont)(const struct firmware *fw, void *context))
 {
 	int ret = 0;
@@ -280,7 +281,7 @@ int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
 		tas_priv->dev_name, tas_priv->ndev);
 	crc8_populate_msb(tas_priv->crc8_lkp_tbl, TASDEVICE_CRC8_POLYNOMIAL);
 	tas_priv->codec = codec;
-	ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT,
+	ret = request_firmware_nowait(module, FW_ACTION_UEVENT,
 		tas_priv->rca_binaryname, tas_priv->dev, GFP_KERNEL, tas_priv,
 		cont);
 	if (ret)
diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 32913bd1a623..b5abff230e43 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -566,7 +566,7 @@ static int tasdevice_codec_probe(struct snd_soc_component *codec)
 {
 	struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(codec);
 
-	return tascodec_init(tas_priv, codec, tasdevice_fw_ready);
+	return tascodec_init(tas_priv, codec, THIS_MODULE, tasdevice_fw_ready);
 }
 
 static void tasdevice_deinit(void *context)
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index 43c648efd0d9..deb15b95992d 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -3033,7 +3033,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
 	u16 gain_reg;
-	int offset_val = 0;
 	int val = 0;
 
 	switch (w->reg) {
@@ -3073,7 +3072,6 @@ static int wcd9335_codec_enable_mix_path(struct snd_soc_dapm_widget *w,
 	switch (event) {
 	case SND_SOC_DAPM_POST_PMU:
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
@@ -3294,7 +3292,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	u16 gain_reg;
 	u16 reg;
 	int val;
-	int offset_val = 0;
 
 	if (!(snd_soc_dapm_widget_name_cmp(w, "RX INT0 INTERP"))) {
 		reg = WCD9335_CDC_RX0_RX_PATH_CTL;
@@ -3337,7 +3334,6 @@ static int wcd9335_codec_enable_interpolator(struct snd_soc_dapm_widget *w,
 	case SND_SOC_DAPM_POST_PMU:
 		wcd9335_config_compander(comp, w->shift, event);
 		val = snd_soc_component_read(comp, gain_reg);
-		val += offset_val;
 		snd_soc_component_write(comp, gain_reg, val);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 1b6e376f3833..6813268e6a19 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -13,7 +13,6 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/slimbus.h>
 #include <sound/pcm_params.h>
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index faf8d3f9b3c5..6021aa5a5689 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -210,7 +210,7 @@ struct wcd938x_priv {
 };
 
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(ear_pa_gain, 600, -1800);
-static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, -3000);
+static const DECLARE_TLV_DB_SCALE(line_gain, -3000, 150, 0);
 static const SNDRV_CTL_TLVD_DECLARE_DB_MINMAX(analog_gain, 0, 3000);
 
 struct wcd938x_mbhc_zdet_param {
@@ -3587,10 +3587,8 @@ static int wcd938x_probe(struct platform_device *pdev)
 	mutex_init(&wcd938x->micb_lock);
 
 	ret = wcd938x_populate_dt_data(wcd938x, dev);
-	if (ret) {
-		dev_err(dev, "%s: Fail to obtain platform data\n", __func__);
-		return -EINVAL;
-	}
+	if (ret)
+		return ret;
 
 	ret = wcd938x_add_slave_components(wcd938x, dev, &match);
 	if (ret)
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index fb90ae6a8a34..7c6ed2983128 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2229,6 +2229,9 @@ SND_SOC_DAPM_PGA_E("HPOUT", SND_SOC_NOPM, 0, 0, NULL, 0, hp_event,
 
 SND_SOC_DAPM_OUTPUT("HPOUTL"),
 SND_SOC_DAPM_OUTPUT("HPOUTR"),
+
+SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0),
+SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
 };
 
 static const struct snd_soc_dapm_widget wm8962_dapm_spk_mono_widgets[] = {
@@ -2236,7 +2239,6 @@ SND_SOC_DAPM_MIXER("Speaker Mixer", WM8962_MIXER_ENABLES, 1, 0,
 		   spkmixl, ARRAY_SIZE(spkmixl)),
 SND_SOC_DAPM_MUX_E("Speaker PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux,
 		   out_pga_event, SND_SOC_DAPM_POST_PMU),
-SND_SOC_DAPM_PGA("Speaker Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
 SND_SOC_DAPM_OUTPUT("SPKOUT"),
 };
 
@@ -2251,9 +2253,6 @@ SND_SOC_DAPM_MUX_E("SPKOUTL PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux,
 SND_SOC_DAPM_MUX_E("SPKOUTR PGA", WM8962_PWR_MGMT_2, 3, 0, &spkoutr_mux,
 		   out_pga_event, SND_SOC_DAPM_POST_PMU),
 
-SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0),
-SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0),
-
 SND_SOC_DAPM_OUTPUT("SPKOUTL"),
 SND_SOC_DAPM_OUTPUT("SPKOUTR"),
 };
@@ -2366,12 +2365,18 @@ static const struct snd_soc_dapm_route wm8962_spk_mono_intercon[] = {
 	{ "Speaker PGA", "Mixer", "Speaker Mixer" },
 	{ "Speaker PGA", "DAC", "DACL" },
 
-	{ "Speaker Output", NULL, "Speaker PGA" },
-	{ "Speaker Output", NULL, "SYSCLK" },
-	{ "Speaker Output", NULL, "TOCLK" },
-	{ "Speaker Output", NULL, "TEMP_SPK" },
+	{ "SPKOUTL Output", NULL, "Speaker PGA" },
+	{ "SPKOUTL Output", NULL, "SYSCLK" },
+	{ "SPKOUTL Output", NULL, "TOCLK" },
+	{ "SPKOUTL Output", NULL, "TEMP_SPK" },
 
-	{ "SPKOUT", NULL, "Speaker Output" },
+	{ "SPKOUTR Output", NULL, "Speaker PGA" },
+	{ "SPKOUTR Output", NULL, "SYSCLK" },
+	{ "SPKOUTR Output", NULL, "TOCLK" },
+	{ "SPKOUTR Output", NULL, "TEMP_SPK" },
+
+	{ "SPKOUT", NULL, "SPKOUTL Output" },
+	{ "SPKOUT", NULL, "SPKOUTR Output" },
 };
 
 static const struct snd_soc_dapm_route wm8962_spk_stereo_intercon[] = {
@@ -2914,8 +2919,12 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s
 	switch (fll_id) {
 	case WM8962_FLL_MCLK:
 	case WM8962_FLL_BCLK:
+		fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT;
+		break;
 	case WM8962_FLL_OSC:
 		fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT;
+		snd_soc_component_update_bits(component, WM8962_PLL2,
+					      WM8962_OSC_ENA, WM8962_OSC_ENA);
 		break;
 	case WM8962_FLL_INT:
 		snd_soc_component_update_bits(component, WM8962_FLL_CONTROL_1,
@@ -2924,7 +2933,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s
 				    WM8962_FLL_FRC_NCO, WM8962_FLL_FRC_NCO);
 		break;
 	default:
-		dev_err(component->dev, "Unknown FLL source %d\n", ret);
+		dev_err(component->dev, "Unknown FLL source %d\n", source);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index c01e31175015..36ea0dcdc7ab 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -739,19 +739,25 @@ static int wm_adsp_request_firmware_file(struct wm_adsp *dsp,
 					 const char *filetype)
 {
 	struct cs_dsp *cs_dsp = &dsp->cs_dsp;
+	const char *fwf;
 	char *s, c;
 	int ret = 0;
 
+	if (dsp->fwf_name)
+		fwf = dsp->fwf_name;
+	else
+		fwf = dsp->cs_dsp.name;
+
 	if (system_name && asoc_component_prefix)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      asoc_component_prefix, filetype);
 	else if (system_name)
 		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s-%s.%s", dir, dsp->part,
-				      dsp->fwf_name, wm_adsp_fw[dsp->fw].file, system_name,
+				      fwf, wm_adsp_fw[dsp->fw].file, system_name,
 				      filetype);
 	else
-		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, dsp->fwf_name,
+		*filename = kasprintf(GFP_KERNEL, "%s%s-%s-%s.%s", dir, dsp->part, fwf,
 				      wm_adsp_fw[dsp->fw].file, filetype);
 
 	if (*filename == NULL)
@@ -823,6 +829,23 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		}
 	}
 
+	/* Check system-specific bin without wmfw before falling back to generic */
+	if (dsp->wmfw_optional && system_name) {
+		if (asoc_component_prefix)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      asoc_component_prefix, "bin");
+
+		if (!*coeff_firmware)
+			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
+						      cirrus_dir, system_name,
+						      NULL, "bin");
+
+		if (*coeff_firmware)
+			return 0;
+	}
+
+	/* Check legacy location */
 	if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					   "", NULL, NULL, "wmfw")) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -830,62 +853,28 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		return 0;
 	}
 
+	/* Fall back to generic wmfw and optional matching bin */
 	ret = wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 					    cirrus_dir, NULL, NULL, "wmfw");
-	if (!ret) {
+	if (!ret || dsp->wmfw_optional) {
 		wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 					      cirrus_dir, NULL, NULL, "bin");
 		return 0;
 	}
 
-	if (dsp->wmfw_optional) {
-		if (system_name) {
-			if (asoc_component_prefix)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      asoc_component_prefix, "bin");
-
-			if (!*coeff_firmware)
-				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-							      cirrus_dir, system_name,
-							      NULL, "bin");
-		}
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      "", NULL, NULL, "bin");
-
-		if (!*coeff_firmware)
-			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
-						      cirrus_dir, NULL, NULL, "bin");
-
-		return 0;
-	}
-
 	adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
-		 cirrus_dir, dsp->part, dsp->fwf_name, wm_adsp_fw[dsp->fw].file,
-		 system_name, asoc_component_prefix);
+		 cirrus_dir, dsp->part,
+		 dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name,
+		 wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix);
 
 	return -ENOENT;
 }
 
 static int wm_adsp_common_init(struct wm_adsp *dsp)
 {
-	char *p;
-
 	INIT_LIST_HEAD(&dsp->compr_list);
 	INIT_LIST_HEAD(&dsp->buffer_list);
 
-	if (!dsp->fwf_name) {
-		p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL);
-		if (!p)
-			return -ENOMEM;
-
-		dsp->fwf_name = p;
-		for (; *p != 0; ++p)
-			*p = tolower(*p);
-	}
-
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c
index cb83c569e18d..a2e86ef7d18f 100644
--- a/sound/soc/codecs/wsa883x.c
+++ b/sound/soc/codecs/wsa883x.c
@@ -1098,7 +1098,11 @@ static int wsa_dev_mode_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const DECLARE_TLV_DB_SCALE(pa_gain, -300, 150, -300);
+static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(pa_gain,
+	0, 14, TLV_DB_SCALE_ITEM(-300, 0, 0),
+	15, 29, TLV_DB_SCALE_ITEM(-300, 150, 0),
+	30, 31, TLV_DB_SCALE_ITEM(1800, 0, 0),
+);
 
 static int wsa883x_get_swr_port(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c
index f0fb33d719c2..c46f64557a7f 100644
--- a/sound/soc/fsl/fsl_xcvr.c
+++ b/sound/soc/fsl/fsl_xcvr.c
@@ -174,7 +174,9 @@ static int fsl_xcvr_activate_ctl(struct snd_soc_dai *dai, const char *name,
 	struct snd_kcontrol *kctl;
 	bool enabled;
 
-	kctl = snd_soc_card_get_kcontrol(card, name);
+	lockdep_assert_held(&card->snd_card->controls_rwsem);
+
+	kctl = snd_soc_card_get_kcontrol_locked(card, name);
 	if (kctl == NULL)
 		return -ENOENT;
 
@@ -576,10 +578,14 @@ static int fsl_xcvr_startup(struct snd_pcm_substream *substream,
 	xcvr->streams |= BIT(substream->stream);
 
 	if (!xcvr->soc_data->spdif_only) {
+		struct snd_soc_card *card = dai->component->card;
+
 		/* Disable XCVR controls if there is stream started */
+		down_read(&card->snd_card->controls_rwsem);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, false);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, false);
 		fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, false);
+		up_read(&card->snd_card->controls_rwsem);
 	}
 
 	return 0;
@@ -598,11 +604,15 @@ static void fsl_xcvr_shutdown(struct snd_pcm_substream *substream,
 	/* Enable XCVR controls if there is no stream started */
 	if (!xcvr->streams) {
 		if (!xcvr->soc_data->spdif_only) {
+			struct snd_soc_card *card = dai->component->card;
+
+			down_read(&card->snd_card->controls_rwsem);
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, true);
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name,
 						(xcvr->mode == FSL_XCVR_MODE_ARC));
 			fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name,
 						(xcvr->mode == FSL_XCVR_MODE_EARC));
+			up_read(&card->snd_card->controls_rwsem);
 		}
 		ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_IER0,
 					 FSL_XCVR_IRQ_EARC_ALL, 0);
diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c
index 59c3793f65df..db78eb2f0108 100644
--- a/sound/soc/intel/avs/core.c
+++ b/sound/soc/intel/avs/core.c
@@ -477,6 +477,9 @@ static int avs_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	return 0;
 
 err_i915_init:
+	pci_free_irq(pci, 0, adev);
+	pci_free_irq(pci, 0, bus);
+	pci_free_irq_vectors(pci);
 	pci_clear_master(pci);
 	pci_set_drvdata(pci, NULL);
 err_acquire_irq:
diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c
index 778236d3fd28..48b3c67c9103 100644
--- a/sound/soc/intel/avs/topology.c
+++ b/sound/soc/intel/avs/topology.c
@@ -857,7 +857,7 @@ assign_copier_gtw_instance(struct snd_soc_component *comp, struct avs_tplg_modcf
 	}
 
 	/* If topology sets value don't overwrite it */
-	if (cfg->copier.vindex.i2s.instance)
+	if (cfg->copier.vindex.val)
 		return;
 
 	mach = dev_get_platdata(comp->card->dev);
diff --git a/sound/soc/intel/boards/bytcht_cx2072x.c b/sound/soc/intel/boards/bytcht_cx2072x.c
index 10a84a2c1036..c014d85a08b2 100644
--- a/sound/soc/intel/boards/bytcht_cx2072x.c
+++ b/sound/soc/intel/boards/bytcht_cx2072x.c
@@ -241,7 +241,8 @@ static int snd_byt_cht_cx2072x_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_cht_cx2072x_dais); i++) {
-		if (!strcmp(byt_cht_cx2072x_dais[i].codecs->name,
+		if (byt_cht_cx2072x_dais[i].codecs->name &&
+		    !strcmp(byt_cht_cx2072x_dais[i].codecs->name,
 			    "i2c-14F10720:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
index 7e5eea690023..f4ac3ddd148b 100644
--- a/sound/soc/intel/boards/bytcht_da7213.c
+++ b/sound/soc/intel/boards/bytcht_da7213.c
@@ -245,7 +245,8 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(dailink); i++) {
-		if (!strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
+		if (dailink[i].codecs->name &&
+		    !strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
 			dai_index = i;
 			break;
 		}
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 1564a88a885e..2fcec2e02bb5 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -546,7 +546,8 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_cht_es8316_dais); i++) {
-		if (!strcmp(byt_cht_es8316_dais[i].codecs->name,
+		if (byt_cht_es8316_dais[i].codecs->name &&
+		    !strcmp(byt_cht_es8316_dais[i].codecs->name,
 			    "i2c-ESSX8316:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 42466b4b1ca4..05f38d1f7d82 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -685,6 +685,18 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Chuwi Vi8 dual-boot (CWI506) */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "i86"),
+			/* The above are too generic, also match BIOS info */
+			DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		/* Chuwi Vi10 (CWI505) */
 		.matches = {
@@ -1652,7 +1664,8 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_rt5640_dais); i++) {
-		if (!strcmp(byt_rt5640_dais[i].codecs->name,
+		if (byt_rt5640_dais[i].codecs->name &&
+		    !strcmp(byt_rt5640_dais[i].codecs->name,
 			    "i2c-10EC5640:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index f9fe8414f454..80c841b000a3 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -910,7 +910,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 
 	/* fix index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_rt5651_dais); i++) {
-		if (!strcmp(byt_rt5651_dais[i].codecs->name,
+		if (byt_rt5651_dais[i].codecs->name &&
+		    !strcmp(byt_rt5651_dais[i].codecs->name,
 			    "i2c-10EC5651:00")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c
index 6978ebde6693..cccb5e90c0fe 100644
--- a/sound/soc/intel/boards/bytcr_wm5102.c
+++ b/sound/soc/intel/boards/bytcr_wm5102.c
@@ -605,7 +605,8 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev)
 
 	/* find index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(byt_wm5102_dais); i++) {
-		if (!strcmp(byt_wm5102_dais[i].codecs->name,
+		if (byt_wm5102_dais[i].codecs->name &&
+		    !strcmp(byt_wm5102_dais[i].codecs->name,
 			    "wm5102-codec")) {
 			dai_index = i;
 			break;
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index c952a96cde7e..eb41b7115d01 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -40,7 +40,6 @@ struct cht_acpi_card {
 struct cht_mc_private {
 	struct snd_soc_jack jack;
 	struct cht_acpi_card *acpi_card;
-	char codec_name[SND_ACPI_I2C_ID_LEN];
 	struct clk *mclk;
 };
 
@@ -567,14 +566,14 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	}
 
 	card->dev = &pdev->dev;
-	sprintf(drv->codec_name, "i2c-%s:00", drv->acpi_card->codec_id);
 
 	/* set correct codec name */
 	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
-		if (!strcmp(card->dai_link[i].codecs->name,
+		if (cht_dailink[i].codecs->name &&
+		    !strcmp(cht_dailink[i].codecs->name,
 			    "i2c-10EC5645:00")) {
-			card->dai_link[i].codecs->name = drv->codec_name;
 			dai_index = i;
+			break;
 		}
 
 	/* fixup codec name based on HID */
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index 8cf0b33cc02e..be2d1a8dbca8 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -466,7 +466,8 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 
 	/* find index of codec dai */
 	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
-		if (!strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
+		if (cht_dailink[i].codecs->name &&
+		    !strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
 			dai_index = i;
 			break;
 		}
diff --git a/sound/soc/qcom/lpass-cdc-dma.c b/sound/soc/qcom/lpass-cdc-dma.c
index 48b03e60e3a3..8106c586f68a 100644
--- a/sound/soc/qcom/lpass-cdc-dma.c
+++ b/sound/soc/qcom/lpass-cdc-dma.c
@@ -259,7 +259,7 @@ static int lpass_cdc_dma_daiops_trigger(struct snd_pcm_substream *substream,
 				    int cmd, struct snd_soc_dai *dai)
 {
 	struct snd_soc_pcm_runtime *soc_runtime = snd_soc_substream_to_rtd(substream);
-	struct lpaif_dmactl *dmactl;
+	struct lpaif_dmactl *dmactl = NULL;
 	int ret = 0, id;
 
 	switch (cmd) {
diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c
index 052e40cb38fe..00bbd291be5c 100644
--- a/sound/soc/qcom/qdsp6/q6apm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6apm-dai.c
@@ -123,7 +123,7 @@ static struct snd_pcm_hardware q6apm_dai_hardware_playback = {
 	.fifo_size =            0,
 };
 
-static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, void *priv)
+static void event_handler(uint32_t opcode, uint32_t token, void *payload, void *priv)
 {
 	struct q6apm_dai_rtd *prtd = priv;
 	struct snd_pcm_substream *substream = prtd->substream;
@@ -157,7 +157,7 @@ static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, vo
 }
 
 static void event_handler_compr(uint32_t opcode, uint32_t token,
-				uint32_t *payload, void *priv)
+				void *payload, void *priv)
 {
 	struct q6apm_dai_rtd *prtd = priv;
 	struct snd_compr_stream *substream = prtd->cstream;
@@ -352,7 +352,7 @@ static int q6apm_dai_open(struct snd_soc_component *component,
 
 	spin_lock_init(&prtd->lock);
 	prtd->substream = substream;
-	prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler, prtd, graph_id);
+	prtd->graph = q6apm_graph_open(dev, event_handler, prtd, graph_id);
 	if (IS_ERR(prtd->graph)) {
 		dev_err(dev, "%s: Could not allocate memory\n", __func__);
 		ret = PTR_ERR(prtd->graph);
@@ -496,7 +496,7 @@ static int q6apm_dai_compr_open(struct snd_soc_component *component,
 		return -ENOMEM;
 
 	prtd->cstream = stream;
-	prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler_compr, prtd, graph_id);
+	prtd->graph = q6apm_graph_open(dev, event_handler_compr, prtd, graph_id);
 	if (IS_ERR(prtd->graph)) {
 		ret = PTR_ERR(prtd->graph);
 		kfree(prtd);
diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index ed4bb551bfbb..b7fd503a1666 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -32,12 +32,14 @@ static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd)
 	case WSA_CODEC_DMA_RX_0:
 	case WSA_CODEC_DMA_RX_1:
 		/*
-		 * set limit of 0dB on Digital Volume for Speakers,
-		 * this can prevent damage of speakers to some extent without
-		 * active speaker protection
+		 * Set limit of -3 dB on Digital Volume and 0 dB on PA Volume
+		 * to reduce the risk of speaker damage until we have active
+		 * speaker protection in place.
 		 */
-		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84);
-		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84);
+		snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 81);
+		snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 81);
+		snd_soc_limit_volume(card, "SpkrLeft PA Volume", 17);
+		snd_soc_limit_volume(card, "SpkrRight PA Volume", 17);
 		break;
 	default:
 		break;
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 230c48648af3..afd69c6eb654 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -111,6 +111,13 @@ static u32 rsnd_adg_ssi_ws_timing_gen2(struct rsnd_dai_stream *io)
 			ws = 7;
 			break;
 		}
+	} else {
+		/*
+		 * SSI8 is not connected to ADG.
+		 * Thus SSI9 is using ws = 8
+		 */
+		if (id == 9)
+			ws = 8;
 	}
 
 	return (0x6 + ws) << 8;
diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c
index 285ab4c9c716..8a2f163da6bc 100644
--- a/sound/soc/soc-card.c
+++ b/sound/soc/soc-card.c
@@ -5,6 +5,9 @@
 // Copyright (C) 2019 Renesas Electronics Corp.
 // Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 //
+
+#include <linux/lockdep.h>
+#include <linux/rwsem.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
 
@@ -26,12 +29,15 @@ static inline int _soc_card_ret(struct snd_soc_card *card,
 	return ret;
 }
 
-struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
-					       const char *name)
+struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card,
+						      const char *name)
 {
 	struct snd_card *card = soc_card->snd_card;
 	struct snd_kcontrol *kctl;
 
+	/* must be held read or write */
+	lockdep_assert_held(&card->controls_rwsem);
+
 	if (unlikely(!name))
 		return NULL;
 
@@ -40,6 +46,20 @@ struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
 			return kctl;
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol_locked);
+
+struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
+					       const char *name)
+{
+	struct snd_card *card = soc_card->snd_card;
+	struct snd_kcontrol *kctl;
+
+	down_read(&card->controls_rwsem);
+	kctl = snd_soc_card_get_kcontrol_locked(soc_card, name);
+	up_read(&card->controls_rwsem);
+
+	return kctl;
+}
 EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol);
 
 static int jack_new(struct snd_soc_card *card, const char *id, int type,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index f8524b5bfb33..516350533e73 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1037,7 +1037,7 @@ component_dai_empty:
 	return -EINVAL;
 }
 
-#define MAX_DEFAULT_CH_MAP_SIZE 7
+#define MAX_DEFAULT_CH_MAP_SIZE 8
 static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
 	{ .cpu = 1, .codec = 1 },
@@ -1046,6 +1046,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 4, .codec = 4 },
 	{ .cpu = 5, .codec = 5 },
 	{ .cpu = 6, .codec = 6 },
+	{ .cpu = 7, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1055,6 +1056,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZ
 	{ .cpu = 0, .codec = 4 },
 	{ .cpu = 0, .codec = 5 },
 	{ .cpu = 0, .codec = 6 },
+	{ .cpu = 0, .codec = 7 },
 };
 static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_SIZE] = {
 	{ .cpu = 0, .codec = 0 },
@@ -1064,6 +1066,7 @@ static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_S
 	{ .cpu = 4, .codec = 0 },
 	{ .cpu = 5, .codec = 0 },
 	{ .cpu = 6, .codec = 0 },
+	{ .cpu = 7, .codec = 0 },
 };
 static int snd_soc_compensate_channel_connection_map(struct snd_soc_card *card,
 						     struct snd_soc_dai_link *dai_link)
diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c
index 2743f07a5e08..b44b1b1adb6e 100644
--- a/sound/soc/sof/amd/acp-ipc.c
+++ b/sound/soc/sof/amd/acp-ipc.c
@@ -188,11 +188,13 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context)
 
 	dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write);
 	if (dsp_ack) {
+		spin_lock_irq(&sdev->ipc_lock);
 		/* handle immediate reply from DSP core */
 		acp_dsp_ipc_get_reply(sdev);
 		snd_sof_ipc_reply(sdev, 0);
 		/* set the done bit */
 		acp_dsp_ipc_dsp_done(sdev);
+		spin_unlock_irq(&sdev->ipc_lock);
 		ipc_irq = true;
 	}
 
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index 32a741fcb84f..07632ae6ccf5 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -355,21 +355,20 @@ static irqreturn_t acp_irq_thread(int irq, void *context)
 	unsigned int count = ACP_HW_SEM_RETRY_COUNT;
 
 	spin_lock_irq(&sdev->ipc_lock);
-	while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset)) {
-		/* Wait until acquired HW Semaphore lock or timeout */
-		count--;
-		if (!count) {
-			dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
-			spin_unlock_irq(&sdev->ipc_lock);
-			return IRQ_NONE;
-		}
+	/* Wait until acquired HW Semaphore lock or timeout */
+	while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset) && --count)
+		;
+	spin_unlock_irq(&sdev->ipc_lock);
+
+	if (!count) {
+		dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
+		return IRQ_NONE;
 	}
 
 	sof_ops(sdev)->irq_thread(irq, sdev);
 	/* Unlock or Release HW Semaphore */
 	snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset, 0x0);
 
-	spin_unlock_irq(&sdev->ipc_lock);
 	return IRQ_HANDLED;
 };
 
diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c
index 78a57eb9cbc3..b26ffe767fab 100644
--- a/sound/soc/sof/intel/pci-lnl.c
+++ b/sound/soc/sof/intel/pci-lnl.c
@@ -36,7 +36,7 @@ static const struct sof_dev_desc lnl_desc = {
 		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl",
 	},
 	.default_tplg_path = {
-		[SOF_IPC_TYPE_4] = "intel/sof-ace-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_4] = "sof-lnl.ri",
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index 0660d4b2ac96..a361ee9d1107 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -33,18 +33,18 @@ static const struct sof_dev_desc tgl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/tgl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/tgl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-tgl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-tgl.ri",
 	},
 	.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -66,18 +66,18 @@ static const struct sof_dev_desc tglh_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/tgl-h",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl-h",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/tgl-h",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl-h",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-tgl-h.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-tgl-h.ri",
 	},
 	.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -98,18 +98,18 @@ static const struct sof_dev_desc ehl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/ehl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/ehl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/ehl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/ehl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-ehl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-ehl.ri",
 	},
 	.nocodec_tplg_filename = "sof-ehl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -131,18 +131,18 @@ static const struct sof_dev_desc adls_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-s",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-s",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl-s.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl-s.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -164,18 +164,18 @@ static const struct sof_dev_desc adl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -197,18 +197,18 @@ static const struct sof_dev_desc adl_n_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/adl-n",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-n",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/adl-n",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-n",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-adl-n.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-adl-n.ri",
 	},
 	.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -230,18 +230,18 @@ static const struct sof_dev_desc rpls_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/rpl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl-s",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/rpl-s",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl-s",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-rpl-s.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-rpl-s.ri",
 	},
 	.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
@@ -263,18 +263,18 @@ static const struct sof_dev_desc rpl_desc = {
 	.dspless_mode_supported	= true,		/* Only supported for HDaudio */
 	.default_fw_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof",
-		[SOF_IPC_TYPE_4] = "intel/avs/rpl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl",
 	},
 	.default_lib_path = {
-		[SOF_IPC_TYPE_4] = "intel/avs-lib/rpl",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl",
 	},
 	.default_tplg_path = {
 		[SOF_IPC_TYPE_3] = "intel/sof-tplg",
-		[SOF_IPC_TYPE_4] = "intel/avs-tplg",
+		[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
 	},
 	.default_fw_filename = {
 		[SOF_IPC_TYPE_3] = "sof-rpl.ri",
-		[SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+		[SOF_IPC_TYPE_4] = "sof-rpl.ri",
 	},
 	.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
 	.ops = &sof_tgl_ops,
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index a8832a1c1a24..d47698f4be2d 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -2360,27 +2360,16 @@ static int sof_tear_down_left_over_pipelines(struct snd_sof_dev *sdev)
 	return 0;
 }
 
-/*
- * For older firmware, this function doesn't free widgets for static pipelines during suspend.
- * It only resets use_count for all widgets.
- */
-static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify)
+static int sof_ipc3_free_widgets_in_list(struct snd_sof_dev *sdev, bool include_scheduler,
+					 bool *dyn_widgets, bool verify)
 {
 	struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
 	struct snd_sof_widget *swidget;
-	struct snd_sof_route *sroute;
-	bool dyn_widgets = false;
 	int ret;
 
-	/*
-	 * This function is called during suspend and for one-time topology verification during
-	 * first boot. In both cases, there is no need to protect swidget->use_count and
-	 * sroute->setup because during suspend all running streams are suspended and during
-	 * topology loading the sound card unavailable to open PCMs.
-	 */
 	list_for_each_entry(swidget, &sdev->widget_list, list) {
 		if (swidget->dynamic_pipeline_widget) {
-			dyn_widgets = true;
+			*dyn_widgets = true;
 			continue;
 		}
 
@@ -2395,11 +2384,49 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
 			continue;
 		}
 
+		if (include_scheduler && swidget->id != snd_soc_dapm_scheduler)
+			continue;
+
+		if (!include_scheduler && swidget->id == snd_soc_dapm_scheduler)
+			continue;
+
 		ret = sof_widget_free(sdev, swidget);
 		if (ret < 0)
 			return ret;
 	}
 
+	return 0;
+}
+
+/*
+ * For older firmware, this function doesn't free widgets for static pipelines during suspend.
+ * It only resets use_count for all widgets.
+ */
+static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verify)
+{
+	struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
+	struct snd_sof_widget *swidget;
+	struct snd_sof_route *sroute;
+	bool dyn_widgets = false;
+	int ret;
+
+	/*
+	 * This function is called during suspend and for one-time topology verification during
+	 * first boot. In both cases, there is no need to protect swidget->use_count and
+	 * sroute->setup because during suspend all running streams are suspended and during
+	 * topology loading the sound card unavailable to open PCMs. Do not free the scheduler
+	 * widgets yet so that the secondary cores do not get powered down before all the widgets
+	 * associated with the scheduler are freed.
+	 */
+	ret = sof_ipc3_free_widgets_in_list(sdev, false, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
+	/* free all the scheduler widgets now */
+	ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
+	if (ret < 0)
+		return ret;
+
 	/*
 	 * Tear down all pipelines associated with PCMs that did not get suspended
 	 * and unset the prepare flag so that they can be set up again during resume.
diff --git a/sound/soc/sof/ipc3.c b/sound/soc/sof/ipc3.c
index fb40378ad084..c03dd513fbff 100644
--- a/sound/soc/sof/ipc3.c
+++ b/sound/soc/sof/ipc3.c
@@ -1067,7 +1067,7 @@ static void sof_ipc3_rx_msg(struct snd_sof_dev *sdev)
 		return;
 	}
 
-	if (hdr.size < sizeof(hdr)) {
+	if (hdr.size < sizeof(hdr) || hdr.size > SOF_IPC_MSG_MAX_SIZE) {
 		dev_err(sdev->dev, "The received message size is invalid\n");
 		return;
 	}
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 85d3f390e4b2..07eb5c6d4adf 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -413,7 +413,18 @@ skip_pause_transition:
 	ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list);
 	if (ret < 0) {
 		dev_err(sdev->dev, "failed to set final state %d for all pipelines\n", state);
-		goto free;
+		/*
+		 * workaround: if the firmware is crashed while setting the
+		 * pipelines to reset state we must ignore the error code and
+		 * reset it to 0.
+		 * Since the firmware is crashed we will not send IPC messages
+		 * and we are going to see errors printed, but the state of the
+		 * widgets will be correct for the next boot.
+		 */
+		if (sdev->fw_state != SOF_FW_CRASHED || state != SOF_IPC4_PIPE_RESET)
+			goto free;
+
+		ret = 0;
 	}
 
 	/* update RUNNING/RESET state for all pipelines that were just triggered */
diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c
index 702386823d17..f41c30955857 100644
--- a/sound/soc/sunxi/sun4i-spdif.c
+++ b/sound/soc/sunxi/sun4i-spdif.c
@@ -577,6 +577,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = {
 		.compatible = "allwinner,sun50i-h6-spdif",
 		.data = &sun50i_h6_spdif_quirks,
 	},
+	{
+		.compatible = "allwinner,sun50i-h616-spdif",
+		/* Essentially the same as the H6, but without RX */
+		.data = &sun50i_h6_spdif_quirks,
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match);
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 33db334e6556..60fcb872a80b 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -261,6 +261,8 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 	int ret, i, cur, err, pins, clock_id;
 	const u8 *sources;
 	int proto = fmt->protocol;
+	bool readable, writeable;
+	u32 bmControls;
 
 	entity_id &= 0xff;
 
@@ -292,11 +294,27 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 		sources = GET_VAL(selector, proto, baCSourceID);
 		cur = 0;
 
+		if (proto == UAC_VERSION_3)
+			bmControls = le32_to_cpu(*(__le32 *)(&selector->v3.baCSourceID[0] + pins));
+		else
+			bmControls = *(__u8 *)(&selector->v2.baCSourceID[0] + pins);
+
+		readable = uac_v2v3_control_is_readable(bmControls,
+							UAC2_CX_CLOCK_SELECTOR);
+		writeable = uac_v2v3_control_is_writeable(bmControls,
+							  UAC2_CX_CLOCK_SELECTOR);
+
 		if (pins == 1) {
 			ret = 1;
 			goto find_source;
 		}
 
+		/* for now just warn about buggy device */
+		if (!readable)
+			usb_audio_warn(chip,
+				"%s(): clock selector control is not readable, id %d\n",
+				__func__, clock_id);
+
 		/* the entity ID we are looking at is a selector.
 		 * find out what it currently selects */
 		ret = uac_clock_selector_get_val(chip, clock_id);
@@ -325,17 +343,29 @@ static int __uac_clock_find_source(struct snd_usb_audio *chip,
 					      visited, validate);
 		if (ret > 0) {
 			/* Skip setting clock selector again for some devices */
-			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR)
+			if (chip->quirk_flags & QUIRK_FLAG_SKIP_CLOCK_SELECTOR ||
+			    !writeable)
 				return ret;
 			err = uac_clock_selector_set_val(chip, entity_id, cur);
-			if (err < 0)
+			if (err < 0) {
+				if (pins == 1) {
+					usb_audio_dbg(chip,
+						      "%s(): selector returned an error, "
+						      "assuming a firmware bug, id %d, ret %d\n",
+						      __func__, clock_id, err);
+					return ret;
+				}
 				return err;
+			}
 		}
 
 		if (!validate || ret > 0 || !chip->autoclock)
 			return ret;
 
 	find_others:
+		if (!writeable)
+			return -ENXIO;
+
 		/* The current clock source is invalid, try others. */
 		for (i = 1; i <= pins; i++) {
 			if (i == cur)
diff --git a/sound/usb/format.c b/sound/usb/format.c
index ab5fed9f55b6..3b45d0ee7693 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -470,9 +470,11 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 					   int clock)
 {
 	struct usb_device *dev = chip->dev;
+	struct usb_host_interface *alts;
 	unsigned int *table;
 	unsigned int nr_rates;
 	int i, err;
+	u32 bmControls;
 
 	/* performing the rate verification may lead to unexpected USB bus
 	 * behavior afterwards by some unknown reason.  Do this only for the
@@ -481,6 +483,24 @@ static int validate_sample_rate_table_v2v3(struct snd_usb_audio *chip,
 	if (!(chip->quirk_flags & QUIRK_FLAG_VALIDATE_RATES))
 		return 0; /* don't perform the validation as default */
 
+	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
+	if (!alts)
+		return 0;
+
+	if (fp->protocol == UAC_VERSION_3) {
+		struct uac3_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = le32_to_cpu(as->bmControls);
+	} else {
+		struct uac2_as_header_descriptor *as = snd_usb_find_csint_desc(
+				alts->extra, alts->extralen, NULL, UAC_AS_GENERAL);
+		bmControls = as->bmControls;
+	}
+
+	if (!uac_v2v3_control_is_readable(bmControls,
+				UAC2_AS_VAL_ALT_SETTINGS))
+		return 0;
+
 	table = kcalloc(fp->nr_rates, sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 6b0993258e03..c1f2e5a03de9 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1742,50 +1742,44 @@ static void snd_usbmidi_get_port_info(struct snd_rawmidi *rmidi, int number,
 	}
 }
 
-static struct usb_midi_in_jack_descriptor *find_usb_in_jack_descriptor(
-					struct usb_host_interface *hostif, uint8_t jack_id)
+/* return iJack for the corresponding jackID */
+static int find_usb_ijack(struct usb_host_interface *hostif, uint8_t jack_id)
 {
 	unsigned char *extra = hostif->extra;
 	int extralen = hostif->extralen;
+	struct usb_descriptor_header *h;
+	struct usb_midi_out_jack_descriptor *outjd;
+	struct usb_midi_in_jack_descriptor *injd;
+	size_t sz;
 
 	while (extralen > 4) {
-		struct usb_midi_in_jack_descriptor *injd =
-				(struct usb_midi_in_jack_descriptor *)extra;
+		h = (struct usb_descriptor_header *)extra;
+		if (h->bDescriptorType != USB_DT_CS_INTERFACE)
+			goto next;
 
+		outjd = (struct usb_midi_out_jack_descriptor *)h;
+		if (h->bLength >= sizeof(*outjd) &&
+		    outjd->bDescriptorSubtype == UAC_MIDI_OUT_JACK &&
+		    outjd->bJackID == jack_id) {
+			sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
+			if (outjd->bLength < sz)
+				goto next;
+			return *(extra + sz - 1);
+		}
+
+		injd = (struct usb_midi_in_jack_descriptor *)h;
 		if (injd->bLength >= sizeof(*injd) &&
-		    injd->bDescriptorType == USB_DT_CS_INTERFACE &&
 		    injd->bDescriptorSubtype == UAC_MIDI_IN_JACK &&
-				injd->bJackID == jack_id)
-			return injd;
-		if (!extra[0])
-			break;
-		extralen -= extra[0];
-		extra += extra[0];
-	}
-	return NULL;
-}
-
-static struct usb_midi_out_jack_descriptor *find_usb_out_jack_descriptor(
-					struct usb_host_interface *hostif, uint8_t jack_id)
-{
-	unsigned char *extra = hostif->extra;
-	int extralen = hostif->extralen;
+		    injd->bJackID == jack_id)
+			return injd->iJack;
 
-	while (extralen > 4) {
-		struct usb_midi_out_jack_descriptor *outjd =
-				(struct usb_midi_out_jack_descriptor *)extra;
-
-		if (outjd->bLength >= sizeof(*outjd) &&
-		    outjd->bDescriptorType == USB_DT_CS_INTERFACE &&
-		    outjd->bDescriptorSubtype == UAC_MIDI_OUT_JACK &&
-				outjd->bJackID == jack_id)
-			return outjd;
+next:
 		if (!extra[0])
 			break;
 		extralen -= extra[0];
 		extra += extra[0];
 	}
-	return NULL;
+	return 0;
 }
 
 static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
@@ -1796,13 +1790,10 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
 	const char *name_format;
 	struct usb_interface *intf;
 	struct usb_host_interface *hostif;
-	struct usb_midi_in_jack_descriptor *injd;
-	struct usb_midi_out_jack_descriptor *outjd;
 	uint8_t jack_name_buf[32];
 	uint8_t *default_jack_name = "MIDI";
 	uint8_t *jack_name = default_jack_name;
 	uint8_t iJack;
-	size_t sz;
 	int res;
 
 	struct snd_rawmidi_substream *substream =
@@ -1816,21 +1807,7 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
 	intf = umidi->iface;
 	if (intf && jack_id >= 0) {
 		hostif = intf->cur_altsetting;
-		iJack = 0;
-		if (stream != SNDRV_RAWMIDI_STREAM_OUTPUT) {
-			/* in jacks connect to outs */
-			outjd = find_usb_out_jack_descriptor(hostif, jack_id);
-			if (outjd) {
-				sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
-				if (outjd->bLength >= sz)
-					iJack = *(((uint8_t *) outjd) + sz - sizeof(uint8_t));
-			}
-		} else {
-			/* and out jacks connect to ins */
-			injd = find_usb_in_jack_descriptor(hostif, jack_id);
-			if (injd)
-				iJack = injd->iJack;
-		}
+		iJack = find_usb_ijack(hostif, jack_id);
 		if (iJack != 0) {
 			res = usb_string(umidi->dev, iJack, jack_name_buf,
 			  ARRAY_SIZE(jack_name_buf));
diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c
index 1ec177fe284e..820d3e4b672a 100644
--- a/sound/usb/midi2.c
+++ b/sound/usb/midi2.c
@@ -1085,7 +1085,7 @@ int snd_usb_midi_v2_create(struct snd_usb_audio *chip,
 	}
 	if ((quirk && quirk->type != QUIRK_MIDI_STANDARD_INTERFACE) ||
 	    iface->num_altsetting < 2) {
-		usb_audio_info(chip, "Quirk or no altest; falling back to MIDI 1.0\n");
+		usb_audio_info(chip, "Quirk or no altset; falling back to MIDI 1.0\n");
 		goto fallback_to_midi1;
 	}
 	hostif = &iface->altsetting[1];
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 07cc6a201579..09712e61c606 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2031,10 +2031,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04d8, 0xfeea, /* Benchmark DAC1 Pre */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x04e8, 0xa051, /* Samsung USBC Headset (AKG) */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR | QUIRK_FLAG_CTL_MSG_DELAY_5M),
+	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
+		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
 	DEVICE_FLG(0x054c, 0x0b8c, /* Sony WALKMAN NW-A45 DAC */
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */
@@ -2073,14 +2077,22 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x0763, 0x2031, /* M-Audio Fast Track C600 */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x07fd, 0x000b, /* MOTU M Series 2nd hardware revision */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x08bb, 0x2702, /* LineX FM Transmitter */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x0951, 0x16ad, /* Kingston HyperX */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
+	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
+		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1397, 0x0507, /* Behringer UMC202HD */
@@ -2113,6 +2125,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
+		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */
@@ -2155,6 +2171,12 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
+		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
@@ -2163,22 +2185,6 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */
 		   QUIRK_FLAG_ALIGN_TRANSFER),
-	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
-	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
-		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
-	DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
-		   QUIRK_FLAG_IFACE_SKIP_CLOSE),
-	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
-		   QUIRK_FLAG_FIXED_RATE),
-	DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
-		   QUIRK_FLAG_GET_SAMPLE_RATE),
 
 	/* Vendor matches */
 	VENDOR_FLG(0x045e, /* MS Lifecam */
diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c
index e2847c040f75..b158c3cb8e5f 100644
--- a/sound/virtio/virtio_card.c
+++ b/sound/virtio/virtio_card.c
@@ -91,8 +91,6 @@ static void virtsnd_event_notify_cb(struct virtqueue *vqueue)
 			virtsnd_event_dispatch(snd, event);
 			virtsnd_event_send(vqueue, event, true, GFP_ATOMIC);
 		}
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_ctl_msg.c b/sound/virtio/virtio_ctl_msg.c
index 18dc5aca2e0c..9dabea01277f 100644
--- a/sound/virtio/virtio_ctl_msg.c
+++ b/sound/virtio/virtio_ctl_msg.c
@@ -303,8 +303,6 @@ void virtsnd_ctl_notify_cb(struct virtqueue *vqueue)
 		virtqueue_disable_cb(vqueue);
 		while ((msg = virtqueue_get_buf(vqueue, &length)))
 			virtsnd_ctl_msg_complete(msg);
-		if (unlikely(virtqueue_is_broken(vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/sound/virtio/virtio_pcm_msg.c b/sound/virtio/virtio_pcm_msg.c
index 542446c4c7ba..8c32efaf4c52 100644
--- a/sound/virtio/virtio_pcm_msg.c
+++ b/sound/virtio/virtio_pcm_msg.c
@@ -358,8 +358,6 @@ static inline void virtsnd_pcm_notify_cb(struct virtio_snd_queue *queue)
 		virtqueue_disable_cb(queue->vqueue);
 		while ((msg = virtqueue_get_buf(queue->vqueue, &written_bytes)))
 			virtsnd_pcm_msg_complete(msg, written_bytes);
-		if (unlikely(virtqueue_is_broken(queue->vqueue)))
-			break;
 	} while (!virtqueue_enable_cb(queue->vqueue));
 	spin_unlock_irqrestore(&queue->lock, flags);
 }
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f4542d2718f4..25160d26764b 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,6 +198,7 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_TDX_HOST_PLATFORM	( 7*32+ 7) /* Platform supports being a TDX host */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -308,10 +309,14 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
+#define X86_FEATURE_ZEN2		(11*32+28) /* "" CPU based on Zen2 microarchitecture */
+#define X86_FEATURE_ZEN3		(11*32+29) /* "" CPU based on Zen3 microarchitecture */
+#define X86_FEATURE_ZEN4		(11*32+30) /* "" CPU based on Zen4 microarchitecture */
+#define X86_FEATURE_ZEN1		(11*32+31) /* "" CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -321,7 +326,9 @@
 #define X86_FEATURE_FZRM		(12*32+10) /* "" Fast zero-length REP MOVSB */
 #define X86_FEATURE_FSRS		(12*32+11) /* "" Fast short REP STOSB */
 #define X86_FEATURE_FSRC		(12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
+#define X86_FEATURE_FRED		(12*32+17) /* Flexible Return and Event Delivery */
 #define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
+#define X86_FEATURE_WRMSRNS		(12*32+19) /* "" Non-serializing WRMSR */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* Linear Address Masking */
@@ -437,6 +444,7 @@
 #define X86_FEATURE_SEV			(19*32+ 1) /* AMD Secure Encrypted Virtualization */
 #define X86_FEATURE_VM_PAGE_FLUSH	(19*32+ 2) /* "" VM Page Flush MSR is supported */
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP		(19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
@@ -495,6 +503,7 @@
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 #define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+#define X86_BUG_TDX_PW_MCE		X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 702d93fdd10e..1f23960d2b06 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -44,32 +44,32 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 # define DISABLE_PTI		0
 #else
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 # define DISABLE_RETPOLINE	0
 #else
 # define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
 				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
 #endif
 
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
 # define DISABLE_RETHUNK	0
 #else
 # define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
 #endif
 
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
 # define DISABLE_UNRET		0
 #else
 # define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
 #endif
 
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
 # define DISABLE_CALL_DEPTH_TRACKING	0
 #else
 # define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
@@ -117,6 +117,12 @@
 #define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
 #endif
 
+#ifdef CONFIG_X86_FRED
+# define DISABLE_FRED	0
+#else
+# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -133,7 +139,7 @@
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_LAM)
+#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d51e1850ed0..1f9dc9bd13eb 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -36,8 +36,19 @@
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
-/* Intel MSRs. Some also available on other CPUs */
+/* FRED MSRs */
+#define MSR_IA32_FRED_RSP0	0x1cc			/* Level 0 stack pointer */
+#define MSR_IA32_FRED_RSP1	0x1cd			/* Level 1 stack pointer */
+#define MSR_IA32_FRED_RSP2	0x1ce			/* Level 2 stack pointer */
+#define MSR_IA32_FRED_RSP3	0x1cf			/* Level 3 stack pointer */
+#define MSR_IA32_FRED_STKLVLS	0x1d0			/* Exception stack levels */
+#define MSR_IA32_FRED_SSP0	MSR_IA32_PL0_SSP	/* Level 0 shadow stack pointer */
+#define MSR_IA32_FRED_SSP1	0x1d1			/* Level 1 shadow stack pointer */
+#define MSR_IA32_FRED_SSP2	0x1d2			/* Level 2 shadow stack pointer */
+#define MSR_IA32_FRED_SSP3	0x1d3			/* Level 3 shadow stack pointer */
+#define MSR_IA32_FRED_CONFIG	0x1d4			/* Entrypoint and interrupt stack level */
 
+/* Intel MSRs. Some also available on other CPUs */
 #define MSR_TEST_CTRL				0x00000033
 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT	29
 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT		BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
@@ -237,6 +248,11 @@
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
@@ -536,6 +552,9 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* KeyID partitioning between MKTME and TDX */
+#define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index 11ff975242ca..e2ff22b379a4 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -4,7 +4,7 @@
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm goto (fullop "; j" cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 8fd63a067308..ada4b4a79dd4 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 	insn->kaddr = kaddr;
 	insn->end_kaddr = kaddr + buf_len;
 	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
+	insn->x86_64 = x86_64;
 	insn->opnd_bytes = 4;
 	if (x86_64)
 		insn->addr_bytes = 8;
@@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn)
 	if (opcode->got)
 		return 0;
 
-	if (!insn->prefixes.got) {
-		ret = insn_get_prefixes(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_prefixes(insn);
+	if (ret)
+		return ret;
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
@@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn)
 	if (modrm->got)
 		return 0;
 
-	if (!insn->opcode.got) {
-		ret = insn_get_opcode(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_opcode(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
@@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn)
 	if (!insn->x86_64)
 		return 0;
 
-	if (!modrm->got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return 0;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return 0;
 	/*
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
@@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn)
 	if (insn->sib.got)
 		return 0;
 
-	if (!insn->modrm.got) {
-		ret = insn_get_modrm(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		modrm = insn->modrm.bytes[0];
@@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn)
 	if (insn->displacement.got)
 		return 0;
 
-	if (!insn->sib.got) {
-		ret = insn_get_sib(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_sib(insn);
+	if (ret)
+		return ret;
 
 	if (insn->modrm.nbytes) {
 		/*
@@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn)
 	if (insn->immediate.got)
 		return 0;
 
-	if (!insn->displacement.got) {
-		ret = insn_get_displacement(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_displacement(insn);
+	if (ret)
+		return ret;
 
 	if (inat_has_moffset(insn->attr)) {
 		if (!__get_moffset(insn))
@@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn)
 	if (insn->length)
 		return 0;
 
-	if (!insn->immediate.got) {
-		ret = insn_get_immediate(insn);
-		if (ret)
-			return ret;
-	}
+	ret = insn_get_immediate(insn);
+	if (ret)
+		return ret;
 
 	insn->length = (unsigned char)((unsigned long)insn->next_byte
 				     - (unsigned long)insn->kaddr);
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index d055b82d22cc..59cf6f9065aa 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright 2002 Andi Kleen */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -39,7 +39,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 7c59a704c458..0199d56cb479 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -1,10 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index 5168ee0360b2..12af572201a2 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -1051,8 +1051,8 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B)
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
index 2fd551915c20..cdd2fd078027 100644
--- a/tools/include/asm-generic/unaligned.h
+++ b/tools/include/asm-generic/unaligned.h
@@ -105,9 +105,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -117,9 +117,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -129,12 +129,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 1bdd834bdd57..d09f9dc172a4 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,8 +36,8 @@
 #include <linux/compiler-gcc.h>
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
 #endif
 
 #endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 756b013fb832..75f00965ab15 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,21 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
+#define __NR_lsm_get_self_attr 459
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 460
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 461
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 462
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index de723566c5ae..16122819edfe 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -713,7 +713,8 @@ struct drm_gem_open {
 /**
  * DRM_CAP_ASYNC_PAGE_FLIP
  *
- * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
  */
 #define DRM_CAP_ASYNC_PAGE_FLIP		0x7
 /**
@@ -773,6 +774,13 @@ struct drm_gem_open {
  * :ref:`drm_sync_objects`.
  */
 #define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
 
 /* DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
@@ -842,6 +850,31 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
 
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
 /* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
@@ -893,6 +926,7 @@ struct drm_syncobj_transfer {
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -901,6 +935,14 @@ struct drm_syncobj_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 struct drm_syncobj_timeline_wait {
@@ -913,6 +955,14 @@ struct drm_syncobj_timeline_wait {
 	__u32 flags;
 	__u32 first_signaled; /* only valid when not waiting all */
 	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
 };
 
 /**
@@ -1218,6 +1268,26 @@ extern "C" {
 
 #define DRM_IOCTL_SYNCOBJ_EVENTFD	DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
 
+/**
+ * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer.
+ *
+ * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable
+ * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept
+ * alive. When the plane no longer uses the framebuffer (because the
+ * framebuffer is replaced with another one, or the plane is disabled), the
+ * framebuffer is cleaned up.
+ *
+ * This is useful to implement flicker-free transitions between two processes.
+ *
+ * Depending on the threat model, user-space may want to ensure that the
+ * framebuffer doesn't expose any sensitive user information: closed
+ * framebuffers attached to a plane can be read back by the next DRM master.
+ */
+#define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
+
 /*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 218edb0a96f8..fd4f9574d177 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
- * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
  * EXEC_OBJECT_CAPTURE.
  */
 #define I915_PARAM_HAS_EXEC_CAPTURE	 45
@@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy {
 	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engine classess on which the object is being read, and the
+	 * the engine classes on which the object is being read, and the
 	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
@@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise {
 	__u32 handle;
 
 	/* Advice: either the buffer will be needed again in the near future,
-	 *         or wont be and could be discarded under memory pressure.
+	 *         or won't be and could be discarded under memory pressure.
 	 */
 	__u32 madv;
 
@@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info {
  * 	// enough to hold our array of engines. The kernel will fill out the
  * 	// item.length for us, which is the number of bytes we need.
  * 	//
- * 	// Alternatively a large buffer can be allocated straight away enabling
+ *	// Alternatively a large buffer can be allocated straightaway enabling
  * 	// querying in one pass, in which case item.length should contain the
  * 	// length of the provided buffer.
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
@@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info {
  * 	// Now that we allocated the required number of bytes, we call the ioctl
  * 	// again, this time with the data_ptr pointing to our newly allocated
  * 	// blob, which the kernel can then populate with info on all engines.
- * 	item.data_ptr = (uintptr_t)&info,
+ *	item.data_ptr = (uintptr_t)&info;
  *
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
  * 	if (err) ...
@@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info {
 /**
  * struct drm_i915_engine_info
  *
- * Describes one engine and it's capabilities as known to the driver.
+ * Describes one engine and its capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
 	/** @engine: Engine class and instance. */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6c80f96049bd..282e90aeb163 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
 #define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
 					compare object identity and may not
 					be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC	0x80000000
+#endif
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 211b86de35ac..c3308536482b 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -95,6 +25,19 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -102,6 +45,7 @@ struct kvm_userspace_memory_region {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -265,6 +209,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -518,6 +463,13 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -945,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1201,6 +1150,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1291,6 +1245,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1483,6 +1438,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
@@ -1507,20 +1464,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1537,9 +1482,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1592,8 +1534,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
@@ -2267,4 +2207,24 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index bb242fdcfe6b..ad5478dbad00 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -138,4 +138,74 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index c82a7f41b31c..45e49671ae87 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -466,6 +466,8 @@ ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version)
 
 int ynl_recv_ack(struct ynl_sock *ys, int ret)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
+
 	if (!ret) {
 		yerr(ys, YNL_ERROR_EXPECT_ACK,
 		     "Expecting an ACK but nothing received");
@@ -478,7 +480,7 @@ int ynl_recv_ack(struct ynl_sock *ys, int ret)
 		return ret;
 	}
 	return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid,
-			  ynl_cb_null, ys);
+			  ynl_cb_null, &yarg);
 }
 
 int ynl_cb_null(const struct nlmsghdr *nlh, void *data)
@@ -521,6 +523,7 @@ ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts)
 				ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0;
 			}
 		}
+		i++;
 	}
 
 	return 0;
@@ -586,7 +589,13 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name)
 		return err;
 	}
 
-	return ynl_recv_ack(ys, err);
+	err = ynl_recv_ack(ys, err);
+	if (err < 0) {
+		free(ys->mcast_groups);
+		return err;
+	}
+
+	return 0;
 }
 
 struct ynl_sock *
@@ -741,11 +750,14 @@ err_free:
 
 static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data)
 {
-	return ynl_ntf_parse((struct ynl_sock *)data, nlh);
+	struct ynl_parse_arg *yarg = data;
+
+	return ynl_ntf_parse(yarg->ys, nlh);
 }
 
 int ynl_ntf_check(struct ynl_sock *ys)
 {
+	struct ynl_parse_arg yarg = { .ys = ys, };
 	ssize_t len;
 	int err;
 
@@ -767,7 +779,7 @@ int ynl_ntf_check(struct ynl_sock *ys)
 			return len;
 
 		err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid,
-				  ynl_ntf_trampoline, ys,
+				  ynl_ntf_trampoline, &yarg,
 				  ynl_cb_array, NLMSG_MIN_TYPE);
 		if (err < 0)
 			return err;
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index e327cd827135..3a1d80a7878d 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -509,11 +509,20 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 
 		if (op2 == 0x01) {
 
-			if (modrm == 0xca)
-				insn->type = INSN_CLAC;
-			else if (modrm == 0xcb)
-				insn->type = INSN_STAC;
-
+			switch (insn_last_prefix_id(&ins)) {
+			case INAT_PFX_REPE:
+			case INAT_PFX_REPNE:
+				if (modrm == 0xca)
+					/* eretu/erets */
+					insn->type = INSN_CONTEXT_SWITCH;
+				break;
+			default:
+				if (modrm == 0xca)
+					insn->type = INSN_CLAC;
+				else if (modrm == 0xcb)
+					insn->type = INSN_STAC;
+				break;
+			}
 		} else if (op2 >= 0x80 && op2 <= 0x8f) {
 
 			insn->type = INSN_JUMP_CONDITIONAL;
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 29e949579ede..4134d27c696b 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -83,7 +83,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt,
  *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
  *    ensure the same register is used in the mov and jump instructions.
  *
- *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
+ *    NOTE: MITIGATION_RETPOLINE made it harder still to decode dynamic jumps.
  */
 struct reloc *arch_find_switch_table(struct objtool_file *file,
 				    struct instruction *insn)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 548ec3cd7c00..8440b7bb343c 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3980,11 +3980,11 @@ static int validate_retpoline(struct objtool_file *file)
 
 		if (insn->type == INSN_RETURN) {
 			if (opts.rethunk) {
-				WARN_INSN(insn, "'naked' return found in RETHUNK build");
+				WARN_INSN(insn, "'naked' return found in MITIGATION_RETHUNK build");
 			} else
 				continue;
 		} else {
-			WARN_INSN(insn, "indirect %s found in RETPOLINE build",
+			WARN_INSN(insn, "indirect %s found in MITIGATION_RETPOLINE build",
 				  insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call");
 		}
 
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 1b90575ee3c8..3b12595193c9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -47,6 +47,10 @@ Print PMU events and metrics limited to the specific PMU name.
 --json::
 Output in JSON format.
 
+-o::
+--output=::
+	Output file name. By default output is written to stdout.
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 27e7c478880f..f8774a9b1377 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -236,6 +236,16 @@ else
   SHELLCHECK := $(shell which shellcheck 2> /dev/null)
 endif
 
+# shellcheck is using in tools/perf/tests/Build with option -a/--check-sourced (
+# introduced in v0.4.7) and -S/--severity (introduced in v0.6.0). So make the
+# minimal shellcheck version as v0.6.0.
+ifneq ($(SHELLCHECK),)
+  ifeq ($(shell expr $(shell $(SHELLCHECK) --version | grep version: | \
+        sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 060), 1)
+    SHELLCHECK :=
+  endif
+endif
+
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
 export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 61c2c96cc070..e27a1b1288c2 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -30,6 +30,8 @@
  * functions.
  */
 struct print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/**
 	 * @pmu_glob: Optionally restrict PMU and metric matching to PMU or
 	 * debugfs subsystem name.
@@ -66,13 +68,15 @@ static void default_print_start(void *ps)
 {
 	struct print_state *print_state = ps;
 
-	if (!print_state->name_only && pager_in_use())
-		printf("\nList of pre-defined events (to be used in -e or -M):\n\n");
+	if (!print_state->name_only && pager_in_use()) {
+		fprintf(print_state->fp,
+			"\nList of pre-defined events (to be used in -e or -M):\n\n");
+	}
 }
 
 static void default_print_end(void *print_state __maybe_unused) {}
 
-static void wordwrap(const char *s, int start, int max, int corr)
+static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 {
 	int column = start;
 	int n;
@@ -82,10 +86,10 @@ static void wordwrap(const char *s, int start, int max, int corr)
 		int wlen = strcspn(s, " \t\n");
 
 		if ((column + wlen >= max && column > start) || saw_newline) {
-			printf("\n%*s", start, "");
+			fprintf(fp, "\n%*s", start, "");
 			column = start + corr;
 		}
-		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s);
 		if (n <= 0)
 			break;
 		saw_newline = s[wlen] == '\n';
@@ -104,6 +108,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 {
 	struct print_state *print_state = ps;
 	int pos;
+	FILE *fp = print_state->fp;
 
 	if (deprecated && !print_state->deprecated)
 		return;
@@ -119,30 +124,30 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 
 	if (print_state->name_only) {
 		if (event_alias && strlen(event_alias))
-			printf("%s ", event_alias);
+			fprintf(fp, "%s ", event_alias);
 		else
-			printf("%s ", event_name);
+			fprintf(fp, "%s ", event_name);
 		return;
 	}
 
 	if (strcmp(print_state->last_topic, topic ?: "")) {
 		if (topic)
-			printf("\n%s:\n", topic);
+			fprintf(fp, "\n%s:\n", topic);
 		zfree(&print_state->last_topic);
 		print_state->last_topic = strdup(topic ?: "");
 	}
 
 	if (event_alias && strlen(event_alias))
-		pos = printf("  %s OR %s", event_name, event_alias);
+		pos = fprintf(fp, "  %s OR %s", event_name, event_alias);
 	else
-		pos = printf("  %s", event_name);
+		pos = fprintf(fp, "  %s", event_name);
 
 	if (!topic && event_type_desc) {
 		for (; pos < 53; pos++)
-			putchar(' ');
-		printf("[%s]\n", event_type_desc);
+			fputc(' ', fp);
+		fprintf(fp, "[%s]\n", event_type_desc);
 	} else
-		putchar('\n');
+		fputc('\n', fp);
 
 	if (desc && print_state->desc) {
 		char *desc_with_unit = NULL;
@@ -155,22 +160,22 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi
 					      ? "%s. Unit: %s" : "%s Unit: %s",
 					    desc, pmu_name);
 		}
-		printf("%*s", 8, "[");
-		wordwrap(desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc_len > 0 ? desc_with_unit : desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 		free(desc_with_unit);
 	}
 	long_desc = long_desc ?: desc;
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 
 	if (print_state->detailed && encoding_desc) {
-		printf("%*s", 8, "");
-		wordwrap(encoding_desc, 8, pager_get_columns(), 0);
-		putchar('\n');
+		fprintf(fp, "%*s", 8, "");
+		wordwrap(fp, encoding_desc, 8, pager_get_columns(), 0);
+		fputc('\n', fp);
 	}
 }
 
@@ -184,6 +189,7 @@ static void default_print_metric(void *ps,
 				const char *unit __maybe_unused)
 {
 	struct print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
 	if (print_state->event_glob &&
 	    (!print_state->metrics || !name || !strglobmatch(name, print_state->event_glob)) &&
@@ -192,27 +198,27 @@ static void default_print_metric(void *ps,
 
 	if (!print_state->name_only && !print_state->last_metricgroups) {
 		if (print_state->metricgroups) {
-			printf("\nMetric Groups:\n");
+			fprintf(fp, "\nMetric Groups:\n");
 			if (!print_state->metrics)
-				putchar('\n');
+				fputc('\n', fp);
 		} else {
-			printf("\nMetrics:\n\n");
+			fprintf(fp, "\nMetrics:\n\n");
 		}
 	}
 	if (!print_state->last_metricgroups ||
 	    strcmp(print_state->last_metricgroups, group ?: "")) {
 		if (group && print_state->metricgroups) {
 			if (print_state->name_only)
-				printf("%s ", group);
+				fprintf(fp, "%s ", group);
 			else if (print_state->metrics) {
 				const char *gdesc = describe_metricgroup(group);
 
 				if (gdesc)
-					printf("\n%s: [%s]\n", group, gdesc);
+					fprintf(fp, "\n%s: [%s]\n", group, gdesc);
 				else
-					printf("\n%s:\n", group);
+					fprintf(fp, "\n%s:\n", group);
 			} else
-				printf("%s\n", group);
+				fprintf(fp, "%s\n", group);
 		}
 		zfree(&print_state->last_metricgroups);
 		print_state->last_metricgroups = strdup(group ?: "");
@@ -223,53 +229,59 @@ static void default_print_metric(void *ps,
 	if (print_state->name_only) {
 		if (print_state->metrics &&
 		    !strlist__has_entry(print_state->visited_metrics, name)) {
-			printf("%s ", name);
+			fprintf(fp, "%s ", name);
 			strlist__add(print_state->visited_metrics, name);
 		}
 		return;
 	}
-	printf("  %s\n", name);
+	fprintf(fp, "  %s\n", name);
 
 	if (desc && print_state->desc) {
-		printf("%*s", 8, "[");
-		wordwrap(desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (long_desc && print_state->long_desc) {
-		printf("%*s", 8, "[");
-		wordwrap(long_desc, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, long_desc, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (expr && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(expr, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, expr, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 	if (threshold && print_state->detailed) {
-		printf("%*s", 8, "[");
-		wordwrap(threshold, 8, pager_get_columns(), 0);
-		printf("]\n");
+		fprintf(fp, "%*s", 8, "[");
+		wordwrap(fp, threshold, 8, pager_get_columns(), 0);
+		fprintf(fp, "]\n");
 	}
 }
 
 struct json_print_state {
+	/** @fp: File to write output to. */
+	FILE *fp;
 	/** Should a separator be printed prior to the next item? */
 	bool need_sep;
 };
 
-static void json_print_start(void *print_state __maybe_unused)
+static void json_print_start(void *ps)
 {
-	printf("[\n");
+	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
+
+	fprintf(fp, "[\n");
 }
 
 static void json_print_end(void *ps)
 {
 	struct json_print_state *print_state = ps;
+	FILE *fp = print_state->fp;
 
-	printf("%s]\n", print_state->need_sep ? "\n" : "");
+	fprintf(fp, "%s]\n", print_state->need_sep ? "\n" : "");
 }
 
-static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
+static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ...)
 {
 	va_list args;
 
@@ -318,7 +330,7 @@ static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...)
 		}
 	}
 	va_end(args);
-	fputs(buf->buf, stdout);
+	fputs(buf->buf, fp);
 }
 
 static void json_print_event(void *ps, const char *pmu_name, const char *topic,
@@ -330,60 +342,71 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (pmu_name) {
-		fix_escape_printf(&buf, "\t\"Unit\": \"%S\"", pmu_name);
+		fix_escape_fprintf(fp, &buf, "\t\"Unit\": \"%S\"", pmu_name);
 		need_sep = true;
 	}
 	if (topic) {
-		fix_escape_printf(&buf, "%s\t\"Topic\": \"%S\"", need_sep ? ",\n" : "", topic);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Topic\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   topic);
 		need_sep = true;
 	}
 	if (event_name) {
-		fix_escape_printf(&buf, "%s\t\"EventName\": \"%S\"", need_sep ? ",\n" : "",
-				  event_name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_name);
 		need_sep = true;
 	}
 	if (event_alias && strlen(event_alias)) {
-		fix_escape_printf(&buf, "%s\t\"EventAlias\": \"%S\"", need_sep ? ",\n" : "",
-				  event_alias);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventAlias\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_alias);
 		need_sep = true;
 	}
 	if (scale_unit && strlen(scale_unit)) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "",
-				  scale_unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   scale_unit);
 		need_sep = true;
 	}
 	if (event_type_desc) {
-		fix_escape_printf(&buf, "%s\t\"EventType\": \"%S\"", need_sep ? ",\n" : "",
-				  event_type_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"EventType\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   event_type_desc);
 		need_sep = true;
 	}
 	if (deprecated) {
-		fix_escape_printf(&buf, "%s\t\"Deprecated\": \"%S\"", need_sep ? ",\n" : "",
-				  deprecated ? "1" : "0");
+		fix_escape_fprintf(fp, &buf, "%s\t\"Deprecated\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   deprecated ? "1" : "0");
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
 	if (encoding_desc) {
-		fix_escape_printf(&buf, "%s\t\"Encoding\": \"%S\"", need_sep ? ",\n" : "",
-				  encoding_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"Encoding\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   encoding_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -394,43 +417,53 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
+	FILE *fp = print_state->fp;
 	struct strbuf buf;
 
 	strbuf_init(&buf, 0);
-	printf("%s{\n", print_state->need_sep ? ",\n" : "");
+	fprintf(fp, "%s{\n", print_state->need_sep ? ",\n" : "");
 	print_state->need_sep = true;
 	if (group) {
-		fix_escape_printf(&buf, "\t\"MetricGroup\": \"%S\"", group);
+		fix_escape_fprintf(fp, &buf, "\t\"MetricGroup\": \"%S\"", group);
 		need_sep = true;
 	}
 	if (name) {
-		fix_escape_printf(&buf, "%s\t\"MetricName\": \"%S\"", need_sep ? ",\n" : "", name);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricName\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   name);
 		need_sep = true;
 	}
 	if (expr) {
-		fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricExpr\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   expr);
 		need_sep = true;
 	}
 	if (threshold) {
-		fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "",
-				  threshold);
+		fix_escape_fprintf(fp, &buf, "%s\t\"MetricThreshold\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   threshold);
 		need_sep = true;
 	}
 	if (unit) {
-		fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit);
+		fix_escape_fprintf(fp, &buf, "%s\t\"ScaleUnit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   unit);
 		need_sep = true;
 	}
 	if (desc) {
-		fix_escape_printf(&buf, "%s\t\"BriefDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"BriefDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   desc);
 		need_sep = true;
 	}
 	if (long_desc) {
-		fix_escape_printf(&buf, "%s\t\"PublicDescription\": \"%S\"", need_sep ? ",\n" : "",
-				  long_desc);
+		fix_escape_fprintf(fp, &buf, "%s\t\"PublicDescription\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   long_desc);
 		need_sep = true;
 	}
-	printf("%s}", need_sep ? "\n" : "");
+	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
 
@@ -449,8 +482,12 @@ static bool default_skip_duplicate_pmus(void *ps)
 int cmd_list(int argc, const char **argv)
 {
 	int i, ret = 0;
-	struct print_state default_ps = {};
-	struct print_state json_ps = {};
+	struct print_state default_ps = {
+		.fp = stdout,
+	};
+	struct print_state json_ps = {
+		.fp = stdout,
+	};
 	void *ps = &default_ps;
 	struct print_callbacks print_cb = {
 		.print_start = default_print_start,
@@ -461,6 +498,7 @@ int cmd_list(int argc, const char **argv)
 	};
 	const char *cputype = NULL;
 	const char *unit_name = NULL;
+	const char *output_path = NULL;
 	bool json = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &default_ps.name_only, "Dump raw events"),
@@ -471,6 +509,7 @@ int cmd_list(int argc, const char **argv)
 			    "Print longer event descriptions."),
 		OPT_BOOLEAN(0, "details", &default_ps.detailed,
 			    "Print information on the perf event names and expressions used internally by events."),
+		OPT_STRING('o', "output", &output_path, "file", "output file name"),
 		OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated,
 			    "Print deprecated events."),
 		OPT_STRING(0, "cputype", &cputype, "cpu type",
@@ -497,6 +536,11 @@ int cmd_list(int argc, const char **argv)
 	argc = parse_options(argc, argv, list_options, list_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (output_path) {
+		default_ps.fp = fopen(output_path, "w");
+		json_ps.fp = default_ps.fp;
+	}
+
 	setup_pager();
 
 	if (!default_ps.name_only)
@@ -618,5 +662,8 @@ out:
 	free(default_ps.last_topic);
 	free(default_ps.last_metricgroups);
 	strlist__delete(default_ps.visited_metrics);
+	if (output_path)
+		fclose(default_ps.fp);
+
 	return ret;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 91e6828c38cc..86c910125172 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -4080,8 +4080,8 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	if (rec->switch_output.num_files) {
-		rec->switch_output.filenames = calloc(sizeof(char *),
-						      rec->switch_output.num_files);
+		rec->switch_output.filenames = calloc(rec->switch_output.num_files,
+						      sizeof(char *));
 		if (!rec->switch_output.filenames) {
 			err = -EINVAL;
 			goto out_opts;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index baf1ab083436..5301d1badd43 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -357,7 +357,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
 static void prompt_integer(int *target, const char *msg)
 {
-	char *buf = malloc(0), *p;
+	char *buf = NULL, *p;
 	size_t dummy = 0;
 	int tmp;
 
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 35124a4ddcb2..bbfa3883e533 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -114,7 +114,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to certain allocation restrictions.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_alloc_restriction",
         "MetricThreshold": "tma_alloc_restriction > 0.1",
@@ -124,7 +124,7 @@
     {
         "BriefDescription": "Counts the total number of issue slots  that were not consumed by the backend due to backend stalls",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.1",
@@ -169,7 +169,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_detect",
         "MetricThreshold": "tma_branch_detect > 0.05",
@@ -179,7 +179,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to branch mispredicts.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.05",
@@ -189,7 +189,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteer",
         "MetricThreshold": "tma_branch_resteer > 0.05",
@@ -198,7 +198,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to the microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_cisc",
         "MetricThreshold": "tma_cisc > 0.05",
@@ -217,7 +217,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to decode stalls.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_decode",
         "MetricThreshold": "tma_decode > 0.05",
@@ -235,7 +235,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -245,7 +244,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
         "MetricThreshold": "tma_fast_nuke > 0.05",
@@ -254,7 +253,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.1",
@@ -264,7 +263,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.15",
@@ -283,7 +282,7 @@
     },
     {
         "BriefDescription": "Counts the number of floating point divide operations per uop.",
-        "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.FPDIV@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group",
         "MetricName": "tma_fpdiv_uops",
         "MetricThreshold": "tma_fpdiv_uops > 0.2",
@@ -293,7 +292,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to frontend stalls.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.2",
@@ -303,7 +302,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to instruction cache misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05",
@@ -330,7 +329,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / tma_info_core_clks",
         "MetricName": "tma_info_core_ipc",
         "Unit": "cpu_atom"
     },
@@ -342,7 +341,7 @@
     },
     {
         "BriefDescription": "Uops Per Instruction",
-        "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.ALL@ / INST_RETIRED.ANY",
         "MetricName": "tma_info_core_upi",
         "Unit": "cpu_atom"
     },
@@ -366,13 +365,13 @@
     },
     {
         "BriefDescription": "Ratio of all branches which mispredict",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_branch_mispredict_ratio",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
-        "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY",
+        "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / BACLEARS.ANY",
         "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio",
         "Unit": "cpu_atom"
     },
@@ -390,61 +389,61 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_INST_RETIRED.CALL",
         "MetricName": "tma_info_inst_mix_ipcall",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Far Branch",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)",
         "MetricName": "tma_info_inst_mix_ipfarbranch",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Load",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricName": "tma_info_inst_mix_ipload",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricName": "tma_info_inst_mix_ipmisp_cond_taken",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.INDIRECT",
         "MetricName": "tma_info_inst_mix_ipmisp_indirect",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired return Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RETURN",
         "MetricName": "tma_info_inst_mix_ipmisp_ret",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per retired Branch Misprediction",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricName": "tma_info_inst_mix_ipmispredict",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Instructions per Store",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricName": "tma_info_inst_mix_ipstore",
         "Unit": "cpu_atom"
     },
@@ -480,19 +479,19 @@
     },
     {
         "BriefDescription": "Cycle cost per DRAM hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per L2 hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit",
         "Unit": "cpu_atom"
     },
     {
         "BriefDescription": "Cycle cost per LLC hit",
-        "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit",
         "Unit": "cpu_atom"
     },
@@ -504,7 +503,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_atom"
     },
@@ -524,7 +523,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05",
@@ -533,7 +532,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.",
-        "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
         "MetricThreshold": "tma_l1_bound > 0.1",
@@ -542,7 +541,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -552,7 +550,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -571,7 +568,7 @@
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.05",
@@ -581,7 +578,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
         "MetricThreshold": "tma_mem_scheduler > 0.1",
@@ -590,7 +587,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.",
-        "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
+        "MetricExpr": "min(tma_backend_bound, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2",
@@ -609,7 +606,7 @@
     },
     {
         "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@UOPS_RETIRED.MS@ / tma_info_core_slots",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_ms_uops",
         "MetricThreshold": "tma_ms_uops > 0.05",
@@ -620,7 +617,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.",
-        "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
         "MetricThreshold": "tma_non_mem_scheduler > 0.1",
@@ -629,7 +626,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to a machine clear (slow nuke).",
-        "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
         "MetricThreshold": "tma_nuke > 0.05",
@@ -638,7 +635,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to other common frontend stalls not categorized.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_other_fb",
         "MetricThreshold": "tma_other_fb > 0.05",
@@ -647,7 +644,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.",
-        "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.OTHER_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_other_l1",
         "MetricThreshold": "tma_other_l1 > 0.05",
@@ -683,7 +680,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not delivered by the frontend due to wrong predecodes.",
-        "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_predecode",
         "MetricThreshold": "tma_predecode > 0.05",
@@ -692,7 +689,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
         "MetricThreshold": "tma_register > 0.1",
@@ -701,7 +698,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to the reorder buffer being full (ROB stalls).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
         "MetricThreshold": "tma_reorder_buffer > 0.1",
@@ -722,7 +719,7 @@
     {
         "BriefDescription": "Counts the number of issue slots  that result in retirement slots.",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / tma_info_core_slots",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.75",
@@ -741,7 +738,7 @@
     },
     {
         "BriefDescription": "Counts the number of issue slots  that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).",
-        "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots",
+        "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / tma_info_core_slots",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
         "MetricThreshold": "tma_serialization > 0.1",
@@ -768,7 +765,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.",
-        "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_hit",
         "MetricThreshold": "tma_stlb_hit > 0.05",
@@ -777,7 +774,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.",
-        "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.PGWALK_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_stlb_miss",
         "MetricThreshold": "tma_stlb_miss > 0.05",
@@ -795,8 +792,7 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
+        "MetricExpr": "cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
         "MetricThreshold": "tma_store_fwd_blk > 0.05",
@@ -875,7 +871,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+        "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
         "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -905,7 +901,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -927,7 +922,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -948,7 +942,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
         "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
@@ -958,7 +952,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -979,7 +972,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
         "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1019,7 +1012,7 @@
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.FB_FULL@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
@@ -1154,7 +1147,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
         "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1164,7 +1157,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -1173,7 +1165,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
@@ -1181,7 +1173,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200",
@@ -1197,7 +1189,7 @@
     },
     {
         "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
@@ -1205,7 +1197,7 @@
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
         "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
@@ -1213,7 +1205,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -1222,7 +1213,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -1232,7 +1222,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -1242,7 +1231,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -1261,7 +1249,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -1270,7 +1257,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -1280,7 +1266,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -1290,7 +1275,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -1300,7 +1284,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1317,14 +1300,14 @@
     },
     {
         "BriefDescription": "Fraction of branches that are non-taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_NTAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_nt",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of branches that are taken conditionals",
-        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.COND_TAKEN@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;Branches;CodeGen;PGO",
         "MetricName": "tma_info_branches_cond_tk",
         "Unit": "cpu_core"
@@ -1352,7 +1335,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_core_core_clks",
         "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_core_coreipc",
         "Unit": "cpu_core"
@@ -1374,14 +1357,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@IDQ.DSB_UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
         "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35",
@@ -1390,28 +1373,28 @@
     },
     {
         "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FRONTEND_RETIRED.ANY_DSB_MISS",
         "MetricGroup": "DSBmiss;Fed",
         "MetricName": "tma_info_frontend_ipdsb_miss_ret",
         "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
@@ -1440,14 +1423,14 @@
     },
     {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@",
+        "MetricExpr": "cpu_core@LSD.UOPS@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Fed;LSD",
         "MetricName": "tma_info_frontend_lsd_coverage",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
         "Unit": "cpu_core"
@@ -1462,7 +1445,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
@@ -1471,7 +1454,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
@@ -1480,7 +1463,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
@@ -1489,7 +1472,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
@@ -1498,7 +1481,7 @@
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
@@ -1507,7 +1490,7 @@
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
         "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
@@ -1515,7 +1498,7 @@
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
         "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
@@ -1523,7 +1506,7 @@
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
         "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
@@ -1531,7 +1514,7 @@
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
         "MetricThreshold": "tma_info_inst_mix_ipload < 3",
@@ -1539,7 +1522,7 @@
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
         "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
@@ -1547,7 +1530,7 @@
     },
     {
         "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
         "MetricGroup": "Prefetches",
         "MetricName": "tma_info_inst_mix_ipswpf",
         "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
@@ -1555,7 +1538,7 @@
     },
     {
         "BriefDescription": "Instruction per taken branch",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
         "MetricThreshold": "tma_info_inst_mix_iptb < 13",
@@ -1655,14 +1638,14 @@
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / MEM_LOAD_COMPLETED.L1_MISS_ANY",
         "MetricGroup": "Mem;MemoryBound;MemoryLat",
         "MetricName": "tma_info_memory_load_miss_real_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricExpr": "cpu_core@L1D_PEND_MISS.PENDING@ / L1D_PEND_MISS.PENDING_CYCLES",
         "MetricGroup": "Mem;MemoryBW;MemoryBound",
         "MetricName": "tma_info_memory_mlp",
         "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
@@ -1670,28 +1653,28 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD@ / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_data_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / OFFCORE_REQUESTS.DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_miss_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_oro_load_l2_mlp",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
         "MetricGroup": "Memory_Lat;Offcore",
         "MetricName": "tma_info_memory_oro_load_l3_miss_latency",
         "Unit": "cpu_core"
@@ -1755,14 +1738,14 @@
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instructions per a microcode Assist invocation",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
         "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
@@ -1778,7 +1761,7 @@
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1793,7 +1776,7 @@
     },
     {
         "BriefDescription": "Average CPU Utilization",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.REF_TSC@ / TSC",
         "MetricGroup": "HPC;Summary",
         "MetricName": "tma_info_system_cpu_utilization",
         "Unit": "cpu_core"
@@ -1816,7 +1799,7 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
         "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
@@ -1847,6 +1830,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1855,6 +1839,7 @@
     },
     {
         "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL",
         "MetricGroup": "Mem;SoC",
         "MetricName": "tma_info_system_mem_request_latency",
@@ -1897,7 +1882,7 @@
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
         "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
@@ -1905,7 +1890,7 @@
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / tma_info_thread_clks",
         "MetricGroup": "Ret;Summary",
         "MetricName": "tma_info_thread_ipc",
         "Unit": "cpu_core"
@@ -1972,7 +1957,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
         "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -1992,7 +1977,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -2003,7 +1987,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -2024,7 +2007,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
-        "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
         "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
@@ -2045,7 +2028,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_2_3_10@ / (3 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
@@ -2064,7 +2047,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
         "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2073,7 +2056,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -2136,6 +2118,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -2145,7 +2128,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2155,7 +2137,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
-        "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@UOPS_RETIRED.MS@ / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
         "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
@@ -2225,7 +2207,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -2246,7 +2227,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_0@ / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
@@ -2256,7 +2237,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_1@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
@@ -2266,7 +2247,7 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)",
-        "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@UOPS_DISPATCHED.PORT_6@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
@@ -2296,7 +2277,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
         "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2306,7 +2287,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
         "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2316,7 +2298,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
         "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
@@ -2338,7 +2321,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
-        "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group",
         "MetricName": "tma_serializing_operation",
         "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))",
@@ -2348,7 +2331,7 @@
     },
     {
         "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.",
-        "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+        "MetricExpr": "cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group",
         "MetricName": "tma_shuffles",
         "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
@@ -2357,7 +2340,8 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
-        "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
         "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))",
@@ -2377,8 +2361,7 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
         "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
@@ -2398,7 +2381,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
-        "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
         "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -2408,7 +2391,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
@@ -2448,7 +2430,7 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
-        "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
+        "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
         "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
@@ -2467,7 +2449,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
         "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index c150c14ac6ed..a35edf7d86a9 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -195,7 +195,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -457,7 +456,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -466,7 +464,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -683,7 +680,6 @@
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index e31a4aac9f20..56e54babcc26 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -400,7 +400,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
@@ -421,7 +420,6 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
@@ -449,7 +447,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
@@ -656,7 +653,6 @@
     },
     {
         "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
@@ -699,7 +695,6 @@
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
         "MetricGroup": "Cor;SMT",
         "MetricName": "tma_info_botlnk_l0_core_bound_likely",
@@ -707,7 +702,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
@@ -716,7 +710,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
@@ -725,7 +718,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
         "MetricName": "tma_info_bottleneck_big_code",
@@ -742,7 +734,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
         "MetricGroup": "Fed;FetchBW;Frontend",
         "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
@@ -750,7 +741,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))",
         "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_info_bottleneck_memory_bandwidth",
@@ -759,7 +749,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_info_bottleneck_memory_data_tlbs",
@@ -768,7 +757,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))",
         "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_info_bottleneck_memory_latency",
@@ -777,7 +765,6 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM",
         "MetricName": "tma_info_bottleneck_mispredictions",
@@ -1301,6 +1288,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
@@ -1455,7 +1443,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
@@ -1465,7 +1452,6 @@
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
@@ -1538,7 +1524,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
@@ -1596,6 +1581,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
@@ -1604,7 +1590,6 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1676,7 +1661,6 @@
     },
     {
         "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
-        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_other_light_ops",
@@ -1758,6 +1742,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
@@ -1767,6 +1752,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
@@ -1822,6 +1808,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
@@ -1840,7 +1827,6 @@
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
@@ -1868,7 +1854,6 @@
     },
     {
         "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores",
-        "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 4c598cfc5afa..e5fa8d6f9eb1 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -414,16 +414,30 @@ EOF
 	# start daemon
 	daemon_start ${config} test
 
-	# send 2 signals
-	perf daemon signal --config ${config} --session test
-	perf daemon signal --config ${config}
-
-	# stop daemon
-	daemon_exit ${config}
-
-	# count is 2 perf.data for signals and 1 for perf record finished
-	count=`ls ${base}/session-test/*perf.data* | wc -l`
-	if [ ${count} -ne 3 ]; then
+        # send 2 signals then exit. Do this in a loop watching the number of
+        # files to avoid races. If the loop retries more than 600 times then
+        # give up.
+	local retries=0
+	local signals=0
+	local success=0
+	while [ ${retries} -lt 600 ] && [ ${success} -eq 0 ]; do
+		local files
+		files=`ls ${base}/session-test/*perf.data* 2> /dev/null | wc -l`
+		if [ ${signals} -eq 0 ]; then
+			perf daemon signal --config ${config} --session test
+			signals=1
+		elif [ ${signals} -eq 1 ] && [ $files -ge 1 ]; then
+			perf daemon signal --config ${config}
+			signals=2
+		elif [ ${signals} -eq 2 ] && [ $files -ge 2 ]; then
+			daemon_exit ${config}
+			signals=3
+		elif [ ${signals} -eq 3 ] && [ $files -ge 3 ]; then
+			success=1
+		fi
+		retries=$((${retries} +1))
+	done
+	if [ ${success} -eq 0 ]; then
 		error=1
 		echo "FAILED: perf data no generated"
 	fi
diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh
index 22b004f2b23e..8a868ae64560 100755
--- a/tools/perf/tests/shell/list.sh
+++ b/tools/perf/tests/shell/list.sh
@@ -3,17 +3,32 @@
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
-err=0
 
 shelldir=$(dirname "$0")
 # shellcheck source=lib/setup_python.sh
 . "${shelldir}"/lib/setup_python.sh
 
+list_output=$(mktemp /tmp/__perf_test.list_output.json.XXXXX)
+
+cleanup() {
+  rm -f "${list_output}"
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
 test_list_json() {
   echo "Json output test"
-  perf list -j | $PYTHON -m json.tool
+  perf list -j -o "${list_output}"
+  $PYTHON -m json.tool "${list_output}"
   echo "Json output test [Success]"
 }
 
 test_list_json
-exit $err
+cleanup
+exit 0
diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
index 5ae7bd0031a8..fa4d71e2e72a 100755
--- a/tools/perf/tests/shell/script.sh
+++ b/tools/perf/tests/shell/script.sh
@@ -36,8 +36,7 @@ test_db()
 	echo "DB test"
 
 	# Check if python script is supported
-	libpython=$(perf version --build-options | grep python | grep -cv OFF)
-	if [ "${libpython}" != "1" ] ; then
+        if perf version --build-options | grep python | grep -q OFF ; then
 		echo "SKIP: python scripting is not supported"
 		err=2
 		return
@@ -54,7 +53,14 @@ def sample_table(*args):
 def call_path_table(*args):
     print(f'call_path_table({args}')
 _end_of_file_
-	perf record -g -o "${perfdatafile}" true
+	case $(uname -m)
+	in s390x)
+		cmd_flags="--call-graph dwarf -e cpu-clock";;
+	*)
+		cmd_flags="-g";;
+	esac
+
+	perf record $cmd_flags -o "${perfdatafile}" true
 	perf script -i "${perfdatafile}" -s "${db_test}"
 	echo "DB test [Success]"
 }
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5f5320f7c6e2..dc5943a6352d 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -67,6 +67,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a
 	P_FLAG(BTIME);
 	P_FLAG(MNT_ID);
 	P_FLAG(DIOALIGN);
+	P_FLAG(MNT_ID_UNIQUE);
 
 #undef P_FLAG
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 95f25e9fb994..55a300a0977b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -103,7 +103,14 @@ struct evlist *evlist__new_default(void)
 	err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
 	if (err) {
 		evlist__delete(evlist);
-		evlist = NULL;
+		return NULL;
+	}
+
+	if (evlist->core.nr_entries > 1) {
+		struct evsel *evsel;
+
+		evlist__for_each_entry(evlist, evsel)
+			evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
 	}
 
 	return evlist;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 0888b7163b7c..fa359180ebf8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -491,8 +491,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 
 	if (symbol_conf.res_sample) {
-		he->res_samples = calloc(sizeof(struct res_sample),
-					symbol_conf.res_sample);
+		he->res_samples = calloc(symbol_conf.res_sample,
+					sizeof(struct res_sample));
 		if (!he->res_samples)
 			goto err_srcline;
 	}
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 75e2248416f5..178b00205fe6 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -115,6 +115,10 @@
 	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
 #endif
 
+#ifndef SYM_FUNC_ALIAS_MEMFUNC
+#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
 // In the kernel sources (include/linux/cfi_types.h), this has a different
 // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
 // definition:
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ca3e0404f187..966cca5a3e88 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -286,7 +286,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
 
-	metric_events = calloc(sizeof(void *), ids_size + 1);
+	metric_events = calloc(ids_size + 1, sizeof(void *));
 	if (!metric_events)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index b0fc48be623f..9e47712507cc 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -66,7 +66,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 
 	put_tracing_file(events_path);
 	if (events_fd < 0) {
-		printf("Error: failed to open tracing events directory\n");
+		pr_err("Error: failed to open tracing events directory\n");
 		return;
 	}
 
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 3712186353fb..2a0289c14959 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1055,11 +1055,11 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (thread_nr > n)
 		thread_nr = n;
 
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	synthesize_threads = calloc(thread_nr, sizeof(pthread_t));
 	if (synthesize_threads == NULL)
 		goto free_dirent;
 
-	args = calloc(sizeof(*args), thread_nr);
+	args = calloc(thread_nr, sizeof(*args));
 	if (args == NULL)
 		goto free_threads;
 
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index caff3834671f..030b388800f0 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -13,6 +13,7 @@ ldflags-y += --wrap=cxl_hdm_decode_init
 ldflags-y += --wrap=cxl_dvsec_rr_decode
 ldflags-y += --wrap=devm_cxl_add_rch_dport
 ldflags-y += --wrap=cxl_rcd_component_reg_phys
+ldflags-y += --wrap=cxl_endpoint_parse_cdat
 
 DRIVERS := ../../../drivers
 CXL_SRC := $(DRIVERS)/cxl
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index a3cdbb2be038..908e0d083936 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -15,6 +15,8 @@
 
 static int interleave_arithmetic;
 
+#define FAKE_QTG_ID	42
+
 #define NR_CXL_HOST_BRIDGES 2
 #define NR_CXL_SINGLE_HOST 1
 #define NR_CXL_RCH 1
@@ -209,7 +211,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 0 },
@@ -224,7 +226,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 1,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -239,7 +241,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 2,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 0 },
@@ -254,7 +256,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 3,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -269,7 +271,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 4,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 4UL,
 		},
 		.target = { 2 },
@@ -284,7 +286,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_VOLATILE,
-			.qtg_id = 5,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M,
 		},
 		.target = { 3 },
@@ -301,7 +303,7 @@ static struct {
 			.granularity = 4,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, },
@@ -317,7 +319,7 @@ static struct {
 			.granularity = 0,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 1,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 8UL,
 		},
 		.target = { 0, 1, },
@@ -333,7 +335,7 @@ static struct {
 			.granularity = 0,
 			.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
 					ACPI_CEDT_CFMWS_RESTRICT_PMEM,
-			.qtg_id = 0,
+			.qtg_id = FAKE_QTG_ID,
 			.window_size = SZ_256M * 16UL,
 		},
 		.target = { 0, 1, 0, 1, },
@@ -976,6 +978,48 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port)
 	return 0;
 }
 
+/*
+ * Faking the cxl_dpa_perf for the memdev when appropriate.
+ */
+static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range,
+			   struct cxl_dpa_perf *dpa_perf)
+{
+	dpa_perf->qos_class = FAKE_QTG_ID;
+	dpa_perf->dpa_range = *range;
+	dpa_perf->coord.read_latency = 500;
+	dpa_perf->coord.write_latency = 500;
+	dpa_perf->coord.read_bandwidth = 1000;
+	dpa_perf->coord.write_bandwidth = 1000;
+}
+
+static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	struct cxl_root *cxl_root __free(put_cxl_root) =
+		find_cxl_root(port);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct range pmem_range = {
+		.start = cxlds->pmem_res.start,
+		.end = cxlds->pmem_res.end,
+	};
+	struct range ram_range = {
+		.start = cxlds->ram_res.start,
+		.end = cxlds->ram_res.end,
+	};
+
+	if (!cxl_root)
+		return;
+
+	if (range_len(&ram_range))
+		dpa_perf_setup(port, &ram_range, &mds->ram_perf);
+
+	if (range_len(&pmem_range))
+		dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
+
+	cxl_memdev_update_perf(cxlmd);
+}
+
 static struct cxl_mock_ops cxl_mock_ops = {
 	.is_mock_adev = is_mock_adev,
 	.is_mock_bridge = is_mock_bridge,
@@ -989,6 +1033,7 @@ static struct cxl_mock_ops cxl_mock_ops = {
 	.devm_cxl_setup_hdm = mock_cxl_setup_hdm,
 	.devm_cxl_add_passthrough_decoder = mock_cxl_add_passthrough_decoder,
 	.devm_cxl_enumerate_decoders = mock_cxl_enumerate_decoders,
+	.cxl_endpoint_parse_cdat = mock_cxl_endpoint_parse_cdat,
 	.list = LIST_HEAD_INIT(cxl_mock_ops.list),
 };
 
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index 1a61e68e3095..6f737941dc0e 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -285,6 +285,20 @@ resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev,
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, CXL);
 
+void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port)
+{
+	int index;
+	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+
+	if (ops && ops->is_mock_dev(cxlmd->dev.parent))
+		ops->cxl_endpoint_parse_cdat(port);
+	else
+		cxl_endpoint_parse_cdat(port);
+	put_cxl_mock_ops(index);
+}
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL);
+
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(ACPI);
 MODULE_IMPORT_NS(CXL);
diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h
index a94223750346..d1b0271d2822 100644
--- a/tools/testing/cxl/test/mock.h
+++ b/tools/testing/cxl/test/mock.h
@@ -25,6 +25,7 @@ struct cxl_mock_ops {
 	int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port);
 	int (*devm_cxl_enumerate_decoders)(
 		struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info);
+	void (*cxl_endpoint_parse_cdat)(struct cxl_port *port);
 };
 
 void register_cxl_mock_ops(struct cxl_mock_ops *ops);
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 0b6488efed47..7254c110ff23 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -146,6 +146,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations):
 		"""Runs the Linux UML binary. Must be named 'linux'."""
 		linux_bin = os.path.join(build_dir, 'linux')
 		params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt'])
+		print('Running tests with:\n$', linux_bin, ' '.join(shlex.quote(arg) for arg in params))
 		return subprocess.Popen([linux_bin] + params,
 					   stdin=subprocess.PIPE,
 					   stdout=subprocess.PIPE,
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 15b6a111c3be..cd9ae576bfde 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -67,6 +67,7 @@ TARGETS += nsfs
 TARGETS += perf_events
 TARGETS += pidfd
 TARGETS += pid_namespace
+TARGETS += power_supply
 TARGETS += powerpc
 TARGETS += prctl
 TARGETS += proc
@@ -78,6 +79,7 @@ TARGETS += riscv
 TARGETS += rlimits
 TARGETS += rseq
 TARGETS += rtc
+TARGETS += rust
 TARGETS += seccomp
 TARGETS += sgx
 TARGETS += sigaltstack
@@ -236,6 +238,7 @@ ifdef INSTALL_PATH
 	install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/
+	install -m 744 kselftest/ktap_helpers.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 run_kselftest.sh $(INSTALL_PATH)/
 	rm -f $(TEST_LIST)
 	@ret=1;	\
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
index bf84d4a1d9ae..3c440370c1f0 100644
--- a/tools/testing/selftests/bpf/prog_tests/iters.c
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -193,6 +193,7 @@ static void subtest_task_iters(void)
 	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
 	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
 	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
 	pthread_mutex_unlock(&do_nothing_mutex);
 	for (int i = 0; i < thread_num; i++)
 		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
new file mode 100644
index 000000000000..3405923fe4e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "test_progs.h"
+#include "read_vsyscall.skel.h"
+
+#if defined(__x86_64__)
+/* For VSYSCALL_ADDR */
+#include <asm/vsyscall.h>
+#else
+/* To prevent build failure on non-x86 arch */
+#define VSYSCALL_ADDR 0UL
+#endif
+
+struct read_ret_desc {
+	const char *name;
+	int ret;
+} all_read[] = {
+	{ .name = "probe_read_kernel", .ret = -ERANGE },
+	{ .name = "probe_read_kernel_str", .ret = -ERANGE },
+	{ .name = "probe_read", .ret = -ERANGE },
+	{ .name = "probe_read_str", .ret = -ERANGE },
+	{ .name = "probe_read_user", .ret = -EFAULT },
+	{ .name = "probe_read_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user", .ret = -EFAULT },
+	{ .name = "copy_from_user_task", .ret = -EFAULT },
+};
+
+void test_read_vsyscall(void)
+{
+	struct read_vsyscall *skel;
+	unsigned int i;
+	int err;
+
+#if !defined(__x86_64__)
+	test__skip();
+	return;
+#endif
+	skel = read_vsyscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+	err = read_vsyscall__attach(skel);
+	if (!ASSERT_EQ(err, 0, "read_vsyscall attach"))
+		goto out;
+
+	/* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE,
+	 * but it doesn't affect the returned error codes.
+	 */
+	skel->bss->user_ptr = (void *)VSYSCALL_ADDR;
+	usleep(1);
+
+	for (i = 0; i < ARRAY_SIZE(all_read); i++)
+		ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name);
+out:
+	read_vsyscall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 760ad96b4be0..d66687f1ee6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -4,10 +4,29 @@
 #include "timer.skel.h"
 #include "timer_failure.skel.h"
 
+#define NUM_THR 8
+
+static void *spin_lock_thread(void *arg)
+{
+	int i, err, prog_fd = *(int *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	for (i = 0; i < 10000; i++) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "test_run_opts err") ||
+		    !ASSERT_OK(topts.retval, "test_run_opts retval"))
+			break;
+	}
+
+	pthread_exit(arg);
+}
+
 static int timer(struct timer *timer_skel)
 {
-	int err, prog_fd;
+	int i, err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	pthread_t thread_id[NUM_THR];
+	void *ret;
 
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
@@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel)
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index c3b45745cbcc..6d8b54124cb3 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	if (!ASSERT_EQ(query_opts.feature_flags, 0,
 		       "bond query_opts.feature_flags"))
 		goto out;
 
@@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons)
 	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
 		goto out;
 
-	ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK,
+	ASSERT_EQ(query_opts.feature_flags, 0,
 		  "bond query_opts.feature_flags");
 out:
 	bpf_link__destroy(link);
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
index c9b4055cd410..e4d53e40ff20 100644
--- a/tools/testing/selftests/bpf/progs/iters_task.c
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -10,7 +10,7 @@
 char _license[] SEC("license") = "GPL";
 
 pid_t target_pid;
-int procs_cnt, threads_cnt, proc_threads_cnt;
+int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt;
 
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
@@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx)
 	procs_cnt = threads_cnt = proc_threads_cnt = 0;
 
 	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, ~0U) {
+		/* Below instructions shouldn't be executed for invalid flags */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) {
+		/* Below instructions shouldn't be executed for invalid task__nullable */
+		invalid_cnt++;
+	}
+
 	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
 		if (pos->pid == target_pid)
 			procs_cnt++;
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
new file mode 100644
index 000000000000..986f96687ae1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+int target_pid = 0;
+void *user_ptr = 0;
+int read_ret[8];
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int do_probe_read(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr);
+	read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr);
+	read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr);
+	read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr);
+	read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr);
+	read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int do_copy_from_user(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
+	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
+					      bpf_get_current_task_btf(), 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index 8b946c8188c6..f615da97df26 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -51,7 +51,8 @@ struct {
 	__uint(max_entries, 1);
 	__type(key, int);
 	__type(value, struct elem);
-} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps");
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"),
+	race_array SEC(".maps");
 
 __u64 bss_data;
 __u64 abs_data;
@@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a)
 
 	return 0;
 }
+
+static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer)
+{
+	bpf_timer_start(timer, 1000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int race(void *ctx)
+{
+	struct bpf_timer *timer;
+	int err, race_key = 0;
+	struct elem init;
+
+	__builtin_memset(&init, 0, sizeof(struct elem));
+	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
+
+	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	if (!timer)
+		return 1;
+
+	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (err && err != -EBUSY)
+		return 1;
+
+	bpf_timer_set_callback(timer, race_timer_callback);
+	bpf_timer_start(timer, 0, 0);
+	bpf_timer_cancel(timer);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index 5905e036e0ea..a955a6358206 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -239,4 +239,74 @@ int bpf_loop_iter_limit_nested(void *unused)
 	return 1000 * a + b + c;
 }
 
+struct iter_limit_bug_ctx {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+};
+
+static __naked void iter_limit_bug_cb(void)
+{
+	/* This is the same as C code below, but written
+	 * in assembly to control which branches are fall-through.
+	 *
+	 *   switch (bpf_get_prandom_u32()) {
+	 *   case 1:  ctx->a = 42; break;
+	 *   case 2:  ctx->b = 42; break;
+	 *   default: ctx->c = 42; break;
+	 *   }
+	 */
+	asm volatile (
+	"r9 = r2;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = 42;"
+	"r0 = 0;"
+	"if r1 == 0x1 goto 1f;"
+	"if r1 == 0x2 goto 2f;"
+	"*(u64 *)(r9 + 16) = r2;"
+	"exit;"
+	"1: *(u64 *)(r9 + 0) = r2;"
+	"exit;"
+	"2: *(u64 *)(r9 + 8) = r2;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+SEC("tc")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+int iter_limit_bug(struct __sk_buff *skb)
+{
+	struct iter_limit_bug_ctx ctx = { 7, 7, 7 };
+
+	bpf_loop(2, iter_limit_bug_cb, &ctx, 0);
+
+	/* This is the same as C code below,
+	 * written in assembly to guarantee checks order.
+	 *
+	 *   if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7)
+	 *     asm volatile("r1 /= 0;":::"r1");
+	 */
+	asm volatile (
+	"r1 = *(u64 *)%[ctx_a];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_b];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_c];"
+	"if r1 != 7 goto 1f;"
+	"r1 /= 0;"
+	"1:"
+	:
+	: [ctx_a]"m"(ctx.a),
+	  [ctx_b]"m"(ctx.b),
+	  [ctx_c]"m"(ctx.c)
+	: "r1"
+	);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 534576f06df1..c59e4adb905d 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -12,6 +12,7 @@
 #include <syscall.h>
 #include <unistd.h>
 #include <sys/resource.h>
+#include <linux/close_range.h>
 
 #include "../kselftest_harness.h"
 #include "../clone3/clone3_selftests.h"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index d508486cc0bd..9a3d3c389dad 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -62,6 +62,8 @@ prio_test()
 
 	# create bond
 	bond_reset "${param}"
+	# set active_slave to primary eth1 specifically
+	ip -n ${s_ns} link set bond0 type bond active_slave eth1
 
 	# check bonding member prio value
 	ip -n ${s_ns} link set eth0 type bond_slave prio 0
diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
index 2a268b17b61f..dbdd736a41d3 100644
--- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
+++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
@@ -48,6 +48,17 @@ test_LAG_cleanup()
 	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
 	# Used to test dev->mc handling
 	ip address add "$addr6" dev "$name"
+
+	# Check that addresses were added as expected
+	(grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "macvlan unicast address not found on a slave"
+
+	# mcaddr is added asynchronously by addrconf_dad_work(), use busywait
+	(busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address not found on a slave"
+
 	ip link set dev "$name" down
 	ip link del "$name"
 
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 265b6882cc21..b5e3a3aad4bf 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,3 +1,5 @@
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
+CONFIG_MACVLAN=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
-CONFIG_MACVLAN=y
diff --git a/tools/testing/selftests/dt/Makefile b/tools/testing/selftests/dt/Makefile
index 62dc00ee4978..2d33ee9e9b71 100644
--- a/tools/testing/selftests/dt/Makefile
+++ b/tools/testing/selftests/dt/Makefile
@@ -4,7 +4,7 @@ ifneq ($(PY3),)
 
 TEST_PROGS := test_unprobed_devices.sh
 TEST_GEN_FILES := compatible_list
-TEST_FILES := compatible_ignore_list ktap_helpers.sh
+TEST_FILES := compatible_ignore_list
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh
index b07af2a4c4de..2d7e70c5ad2d 100755
--- a/tools/testing/selftests/dt/test_unprobed_devices.sh
+++ b/tools/testing/selftests/dt/test_unprobed_devices.sh
@@ -15,16 +15,12 @@
 
 DIR="$(dirname $(readlink -f "$0"))"
 
-source "${DIR}"/ktap_helpers.sh
+source "${DIR}"/../kselftest/ktap_helpers.sh
 
 PDT=/proc/device-tree/
 COMPAT_LIST="${DIR}"/compatible_list
 IGNORE_LIST="${DIR}"/compatible_ignore_list
 
-KSFT_PASS=0
-KSFT_FAIL=1
-KSFT_SKIP=4
-
 ktap_print_header
 
 if [[ ! -d "${PDT}" ]]; then
@@ -33,8 +29,8 @@ if [[ ! -d "${PDT}" ]]; then
 fi
 
 nodes_compatible=$(
-	for node_compat in $(find ${PDT} -name compatible); do
-		node=$(dirname "${node_compat}")
+	for node in $(find ${PDT} -type d); do
+		[ ! -f "${node}"/compatible ] && continue
 		# Check if node is available
 		if [[ -e "${node}"/status ]]; then
 			status=$(tr -d '\000' < "${node}"/status)
@@ -46,10 +42,11 @@ nodes_compatible=$(
 
 nodes_dev_bound=$(
 	IFS=$'\n'
-	for uevent in $(find /sys/devices -name uevent); do
-		if [[ -d "$(dirname "${uevent}")"/driver ]]; then
-			grep '^OF_FULLNAME=' "${uevent}" | sed -e 's|OF_FULLNAME=||'
-		fi
+	for dev_dir in $(find /sys/devices -type d); do
+		[ ! -f "${dev_dir}"/uevent ] && continue
+		[ ! -d "${dev_dir}"/driver ] && continue
+
+		grep '^OF_FULLNAME=' "${dev_dir}"/uevent | sed -e 's|OF_FULLNAME=||'
 	done
 	)
 
diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
index e19ab0e85709..759f86e7d263 100644
--- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
+++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c
@@ -10,7 +10,6 @@
 #include <linux/mount.h>
 #include <sys/syscall.h>
 #include <sys/stat.h>
-#include <sys/mount.h>
 #include <sys/mman.h>
 #include <sched.h>
 #include <fcntl.h>
@@ -32,7 +31,11 @@ static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags)
 {
 	return syscall(__NR_fsmount, fd, flags, attr_flags);
 }
-
+static int sys_mount(const char *src, const char *tgt, const char *fst,
+		unsigned long flags, const void *data)
+{
+	return syscall(__NR_mount, src, tgt, fst, flags, data);
+}
 static int sys_move_mount(int from_dfd, const char *from_pathname,
 			  int to_dfd, const char *to_pathname,
 			  unsigned int flags)
@@ -166,8 +169,7 @@ int main(int argc, char **argv)
 		ksft_test_result_skip("unable to create a new mount namespace\n");
 		return 1;
 	}
-
-	if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
+	if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) {
 		pr_perror("mount");
 		return 1;
 	}
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index c778d4dcc17e..25d4e0fca385 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -504,7 +504,7 @@ prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
 if [ "$KTAP" = "1" ]; then
   echo -n "# Totals:"
   echo -n " pass:"`echo $PASSED_CASES | wc -w`
-  echo -n " faii:"`echo $FAILED_CASES | wc -w`
+  echo -n " fail:"`echo $FAILED_CASES | wc -w`
   echo -n " xfail:"`echo $XFAILED_CASES | wc -w`
   echo -n " xpass:0"
   echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w`
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
index add7d5bf585d..c45094d1e1d2 100644
--- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
+++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
@@ -1,6 +1,6 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-# description: Test file and directory owership changes for eventfs
+# description: Test file and directory ownership changes for eventfs
 
 original_group=`stat -c "%g" .`
 original_owner=`stat -c "%u" .`
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc
new file mode 100644
index 000000000000..ccfbfde3d942
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc
@@ -0,0 +1,42 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+# description: ftrace - function trace across cpu hotplug
+# requires: function:tracer
+
+if ! which nproc ; then
+  nproc() {
+    ls -d /sys/devices/system/cpu/cpu[0-9]* | wc -l
+  }
+fi
+
+NP=`nproc`
+
+if [ $NP -eq 1 ] ;then
+  echo "We cannot test cpu hotplug in UP environment"
+  exit_unresolved
+fi
+
+# Find online cpu
+for i in /sys/devices/system/cpu/cpu[1-9]*; do
+	if [ -f $i/online ] && [ "$(cat $i/online)" = "1" ]; then
+		cpu=$i
+		break
+	fi
+done
+
+if [ -z "$cpu" ]; then
+	echo "We cannot test cpu hotplug with a single cpu online"
+	exit_unresolved
+fi
+
+echo 0 > tracing_on
+echo > trace
+
+: "Set $(basename $cpu) offline/online with function tracer enabled"
+echo function > current_tracer
+echo 1 > tracing_on
+(echo 0 > $cpu/online)
+(echo "forked"; sleep 1)
+(echo 1 > $cpu/online)
+echo 0 > tracing_on
+echo nop > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index 4562e13cb26b..717898894ef7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -40,7 +40,7 @@ grep "id: \(unknown_\|sys_\)" events/raw_syscalls/sys_exit/hist > /dev/null || \
 
 reset_trigger
 
-echo "Test histgram with log2 modifier"
+echo "Test histogram with log2 modifier"
 
 echo 'hist:keys=bytes_req.log2' > events/kmem/kmalloc/trigger
 for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
index 1ee5518ee6b7..7f3ca5c78df1 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -17,6 +17,8 @@
  *
  *****************************************************************************/
 
+#define _GNU_SOURCE
+
 #include <errno.h>
 #include <limits.h>
 #include <pthread.h>
@@ -358,6 +360,7 @@ out:
 
 int main(int argc, char *argv[])
 {
+	const char *test_name;
 	int c, ret;
 
 	while ((c = getopt(argc, argv, "bchlot:v:")) != -1) {
@@ -397,6 +400,14 @@ int main(int argc, char *argv[])
 		"\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
 		broadcast, locked, owner, timeout_ns);
 
+	ret = asprintf(&test_name,
+		       "%s broadcast=%d locked=%d owner=%d timeout=%ldns",
+		       TEST_NAME, broadcast, locked, owner, timeout_ns);
+	if (ret < 0) {
+		ksft_print_msg("Failed to generate test name\n");
+		test_name = TEST_NAME;
+	}
+
 	/*
 	 * FIXME: unit_test is obsolete now that we parse options and the
 	 * various style of runs are done by run.sh - simplify the code and move
@@ -404,6 +415,6 @@ int main(int argc, char *argv[])
 	 */
 	ret = unit_test(broadcast, locked, owner, timeout_ns);
 
-	print_result(TEST_NAME, ret);
+	print_result(test_name, ret);
 	return ret;
 }
diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py
index 352fc39f3c6c..b62c7dba6777 100644
--- a/tools/testing/selftests/hid/tests/test_wacom_generic.py
+++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py
@@ -880,8 +880,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest
         does not overlap with other contacts. The value of `t` may be
         incremented over time to move the point along a linear path.
         """
-        x = 50 + 10 * contact_id + t
-        y = 100 + 100 * contact_id + t
+        x = 50 + 10 * contact_id + t * 11
+        y = 100 + 100 * contact_id + t * 11
         return test_multitouch.Touch(contact_id, x, y)
 
     def make_contacts(self, n, t=0):
@@ -902,8 +902,8 @@ class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest
         tracking_id = contact_ids.tracking_id
         slot_num = contact_ids.slot_num
 
-        x = 50 + 10 * contact_id + t
-        y = 100 + 100 * contact_id + t
+        x = 50 + 10 * contact_id + t * 11
+        y = 100 + 100 * contact_id + t * 11
 
         # If the data isn't supposed to be stored in any slots, there is
         # nothing we can check for in the evdev stream.
diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config
index 6c4f901d6fed..110d73917615 100644
--- a/tools/testing/selftests/iommu/config
+++ b/tools/testing/selftests/iommu/config
@@ -1,2 +1,3 @@
-CONFIG_IOMMUFD
-CONFIG_IOMMUFD_TEST
+CONFIG_IOMMUFD=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_IOMMUFD_TEST=y
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 1a881e7a21d1..edf1c99c9936 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -12,6 +12,7 @@
 static unsigned long HUGEPAGE_SIZE;
 
 #define MOCK_PAGE_SIZE (PAGE_SIZE / 2)
+#define MOCK_HUGE_PAGE_SIZE (512 * MOCK_PAGE_SIZE)
 
 static unsigned long get_huge_page_size(void)
 {
@@ -1716,10 +1717,12 @@ FIXTURE(iommufd_dirty_tracking)
 FIXTURE_VARIANT(iommufd_dirty_tracking)
 {
 	unsigned long buffer_size;
+	bool hugepages;
 };
 
 FIXTURE_SETUP(iommufd_dirty_tracking)
 {
+	int mmap_flags;
 	void *vrc;
 	int rc;
 
@@ -1732,25 +1735,41 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 			   variant->buffer_size, rc);
 	}
 
+	mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED;
+	if (variant->hugepages) {
+		/*
+		 * MAP_POPULATE will cause the kernel to fail mmap if THPs are
+		 * not available.
+		 */
+		mmap_flags |= MAP_HUGETLB | MAP_POPULATE;
+	}
 	assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0);
 	vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE,
-		   MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+		   mmap_flags, -1, 0);
 	assert(vrc == self->buffer);
 
 	self->page_size = MOCK_PAGE_SIZE;
 	self->bitmap_size =
 		variant->buffer_size / self->page_size / BITS_PER_BYTE;
 
-	/* Provision with an extra (MOCK_PAGE_SIZE) for the unaligned case */
+	/* Provision with an extra (PAGE_SIZE) for the unaligned case */
 	rc = posix_memalign(&self->bitmap, PAGE_SIZE,
-			    self->bitmap_size + MOCK_PAGE_SIZE);
+			    self->bitmap_size + PAGE_SIZE);
 	assert(!rc);
 	assert(self->bitmap);
 	assert((uintptr_t)self->bitmap % PAGE_SIZE == 0);
 
 	test_ioctl_ioas_alloc(&self->ioas_id);
-	test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id,
-			     &self->idev_id);
+	/* Enable 1M mock IOMMU hugepages */
+	if (variant->hugepages) {
+		test_cmd_mock_domain_flags(self->ioas_id,
+					   MOCK_FLAGS_DEVICE_HUGE_IOVA,
+					   &self->stdev_id, &self->hwpt_id,
+					   &self->idev_id);
+	} else {
+		test_cmd_mock_domain(self->ioas_id, &self->stdev_id,
+				     &self->hwpt_id, &self->idev_id);
+	}
 }
 
 FIXTURE_TEARDOWN(iommufd_dirty_tracking)
@@ -1784,12 +1803,26 @@ FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M)
 	.buffer_size = 128UL * 1024UL * 1024UL,
 };
 
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M_huge)
+{
+	/* 4K bitmap (128M IOVA range) */
+	.buffer_size = 128UL * 1024UL * 1024UL,
+	.hugepages = true,
+};
+
 FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M)
 {
 	/* 8K bitmap (256M IOVA range) */
 	.buffer_size = 256UL * 1024UL * 1024UL,
 };
 
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M_huge)
+{
+	/* 8K bitmap (256M IOVA range) */
+	.buffer_size = 256UL * 1024UL * 1024UL,
+	.hugepages = true,
+};
+
 TEST_F(iommufd_dirty_tracking, enforce_dirty)
 {
 	uint32_t ioas_id, stddev_id, idev_id;
@@ -1849,65 +1882,80 @@ TEST_F(iommufd_dirty_tracking, device_dirty_capability)
 
 TEST_F(iommufd_dirty_tracking, get_dirty_bitmap)
 {
-	uint32_t stddev_id;
+	uint32_t page_size = MOCK_PAGE_SIZE;
 	uint32_t hwpt_id;
 	uint32_t ioas_id;
 
+	if (variant->hugepages)
+		page_size = MOCK_HUGE_PAGE_SIZE;
+
 	test_ioctl_ioas_alloc(&ioas_id);
 	test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer,
 				     variant->buffer_size, MOCK_APERTURE_START);
 
 	test_cmd_hwpt_alloc(self->idev_id, ioas_id,
 			    IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id);
-	test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL);
 
 	test_cmd_set_dirty_tracking(hwpt_id, true);
 
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap, self->bitmap_size, 0, _metadata);
 
 	/* PAGE_SIZE unaligned bitmap */
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap + MOCK_PAGE_SIZE,
 				self->bitmap_size, 0, _metadata);
 
-	test_ioctl_destroy(stddev_id);
+	/* u64 unaligned bitmap */
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
+				self->bitmap + 0xff1, self->bitmap_size, 0,
+				_metadata);
+
 	test_ioctl_destroy(hwpt_id);
 }
 
 TEST_F(iommufd_dirty_tracking, get_dirty_bitmap_no_clear)
 {
-	uint32_t stddev_id;
+	uint32_t page_size = MOCK_PAGE_SIZE;
 	uint32_t hwpt_id;
 	uint32_t ioas_id;
 
+	if (variant->hugepages)
+		page_size = MOCK_HUGE_PAGE_SIZE;
+
 	test_ioctl_ioas_alloc(&ioas_id);
 	test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer,
 				     variant->buffer_size, MOCK_APERTURE_START);
 
 	test_cmd_hwpt_alloc(self->idev_id, ioas_id,
 			    IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id);
-	test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL);
 
 	test_cmd_set_dirty_tracking(hwpt_id, true);
 
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap, self->bitmap_size,
 				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
 				_metadata);
 
 	/* Unaligned bitmap */
 	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
-				MOCK_APERTURE_START, self->page_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
 				self->bitmap + MOCK_PAGE_SIZE,
 				self->bitmap_size,
 				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
 				_metadata);
 
-	test_ioctl_destroy(stddev_id);
+	/* u64 unaligned bitmap */
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size, page_size,
+				self->bitmap + 0xff1, self->bitmap_size,
+				IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR,
+				_metadata);
+
 	test_ioctl_destroy(hwpt_id);
 }
 
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index c646264aa41f..8d2b46b2114d 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -344,16 +344,19 @@ static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length,
 						  page_size, bitmap, nr))
 
 static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
-				    __u64 iova, size_t page_size, __u64 *bitmap,
+				    __u64 iova, size_t page_size,
+				    size_t pte_page_size, __u64 *bitmap,
 				    __u64 bitmap_size, __u32 flags,
 				    struct __test_metadata *_metadata)
 {
-	unsigned long i, nbits = bitmap_size * BITS_PER_BYTE;
-	unsigned long nr = nbits / 2;
+	unsigned long npte = pte_page_size / page_size, pteset = 2 * npte;
+	unsigned long nbits = bitmap_size * BITS_PER_BYTE;
+	unsigned long j, i, nr = nbits / pteset ?: 1;
 	__u64 out_dirty = 0;
 
 	/* Mark all even bits as dirty in the mock domain */
-	for (i = 0; i < nbits; i += 2)
+	memset(bitmap, 0, bitmap_size);
+	for (i = 0; i < nbits; i += pteset)
 		set_bit(i, (unsigned long *)bitmap);
 
 	test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size,
@@ -365,8 +368,12 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap,
 				  flags);
 	/* Beware ASSERT_EQ() is two statements -- braces are not redundant! */
-	for (i = 0; i < nbits; i++) {
-		ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap));
+	for (i = 0; i < nbits; i += pteset) {
+		for (j = 0; j < pteset; j++) {
+			ASSERT_EQ(j < npte,
+				  test_bit(i + j, (unsigned long *)bitmap));
+		}
+		ASSERT_EQ(!(i % pteset), test_bit(i, (unsigned long *)bitmap));
 	}
 
 	memset(bitmap, 0, bitmap_size);
@@ -374,19 +381,23 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
 				  flags);
 
 	/* It as read already -- expect all zeroes */
-	for (i = 0; i < nbits; i++) {
-		ASSERT_EQ(!(i % 2) && (flags &
-				       IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR),
-			  test_bit(i, (unsigned long *)bitmap));
+	for (i = 0; i < nbits; i += pteset) {
+		for (j = 0; j < pteset; j++) {
+			ASSERT_EQ(
+				(j < npte) &&
+					(flags &
+					 IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR),
+				test_bit(i + j, (unsigned long *)bitmap));
+		}
 	}
 
 	return 0;
 }
-#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap,      \
-				bitmap_size, flags, _metadata)                 \
+#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, pte_size,\
+				bitmap, bitmap_size, flags, _metadata)     \
 	ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \
-					      page_size, bitmap, bitmap_size,  \
-					      flags, _metadata))
+					      page_size, pte_size, bitmap,     \
+					      bitmap_size, flags, _metadata))
 
 static int _test_cmd_create_access(int fd, unsigned int ioas_id,
 				   __u32 *access_id, unsigned int flags)
diff --git a/tools/testing/selftests/dt/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh
index 8dfae51bb4e2..f2fbb914e058 100644
--- a/tools/testing/selftests/dt/ktap_helpers.sh
+++ b/tools/testing/selftests/kselftest/ktap_helpers.sh
@@ -9,14 +9,27 @@ KTAP_CNT_PASS=0
 KTAP_CNT_FAIL=0
 KTAP_CNT_SKIP=0
 
+KSFT_PASS=0
+KSFT_FAIL=1
+KSFT_XFAIL=2
+KSFT_XPASS=3
+KSFT_SKIP=4
+
+KSFT_NUM_TESTS=0
+
 ktap_print_header() {
 	echo "TAP version 13"
 }
 
+ktap_print_msg()
+{
+	echo "#" $@
+}
+
 ktap_set_plan() {
-	num_tests="$1"
+	KSFT_NUM_TESTS="$1"
 
-	echo "1..$num_tests"
+	echo "1..$KSFT_NUM_TESTS"
 }
 
 ktap_skip_all() {
@@ -65,6 +78,34 @@ ktap_test_fail() {
 	KTAP_CNT_FAIL=$((KTAP_CNT_FAIL+1))
 }
 
+ktap_test_result() {
+	description="$1"
+	shift
+
+	if $@; then
+		ktap_test_pass "$description"
+	else
+		ktap_test_fail "$description"
+	fi
+}
+
+ktap_exit_fail_msg() {
+	echo "Bail out! " $@
+	ktap_print_totals
+
+	exit "$KSFT_FAIL"
+}
+
+ktap_finished() {
+	ktap_print_totals
+
+	if [ $(("$KTAP_CNT_PASS" + "$KTAP_CNT_SKIP")) -eq "$KSFT_NUM_TESTS" ]; then
+		exit "$KSFT_PASS"
+	else
+		exit "$KSFT_FAIL"
+	fi
+}
+
 ktap_print_totals() {
 	echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0"
 }
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 274b8465b42a..2cb8dd1f8275 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -248,7 +248,7 @@ static void *test_vcpu_run(void *arg)
 		REPORT_GUEST_ASSERT(uc);
 		break;
 	default:
-		TEST_FAIL("Unexpected guest exit\n");
+		TEST_FAIL("Unexpected guest exit");
 	}
 
 	return NULL;
@@ -287,7 +287,7 @@ static int test_migrate_vcpu(unsigned int vcpu_idx)
 
 	/* Allow the error where the vCPU thread is already finished */
 	TEST_ASSERT(ret == 0 || ret == ESRCH,
-		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n",
+		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d",
 		    vcpu_idx, new_pcpu, ret);
 
 	return ret;
@@ -326,12 +326,12 @@ static void test_run(struct kvm_vm *vm)
 
 	pthread_mutex_init(&vcpu_done_map_lock, NULL);
 	vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
-	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap\n");
+	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap");
 
 	for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) {
 		ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run,
 				     (void *)(unsigned long)i);
-		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread\n", i);
+		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i);
 	}
 
 	/* Spawn a thread to control the vCPU migrations */
@@ -340,7 +340,7 @@ static void test_run(struct kvm_vm *vm)
 
 		ret = pthread_create(&pt_vcpu_migration, NULL,
 					test_vcpu_migration, NULL);
-		TEST_ASSERT(!ret, "Failed to create the migration pthread\n");
+		TEST_ASSERT(!ret, "Failed to create the migration pthread");
 	}
 
 
@@ -384,7 +384,7 @@ static struct kvm_vm *test_vm_create(void)
 		if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET))
 			vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset);
 		else
-			TEST_FAIL("no support for global offset\n");
+			TEST_FAIL("no support for global offset");
 	}
 
 	for (i = 0; i < nr_vcpus; i++)
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index 31f66ba97228..27c10e7a7e01 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -175,18 +175,18 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 		/* First 'read' should be an upper limit of the features supported */
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit),
-			"Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n",
+			"Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx",
 			reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val);
 
 		/* Test a 'write' by disabling all the features of the register map */
 		ret = __vcpu_set_reg(vcpu, reg_info->reg, 0);
 		TEST_ASSERT(ret == 0,
-			"Failed to clear all the features of reg: 0x%lx; ret: %d\n",
+			"Failed to clear all the features of reg: 0x%lx; ret: %d",
 			reg_info->reg, errno);
 
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == 0,
-			"Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg);
+			"Expected all the features to be cleared for reg: 0x%lx", reg_info->reg);
 
 		/*
 		 * Test enabling a feature that's not supported.
@@ -195,7 +195,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 		if (reg_info->max_feat_bit < 63) {
 			ret = __vcpu_set_reg(vcpu, reg_info->reg, BIT(reg_info->max_feat_bit + 1));
 			TEST_ASSERT(ret != 0 && errno == EINVAL,
-			"Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n",
+			"Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx",
 			errno, reg_info->reg);
 		}
 	}
@@ -216,7 +216,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
 		 */
 		vcpu_get_reg(vcpu, reg_info->reg, &val);
 		TEST_ASSERT(val == 0,
-			"Expected all the features to be cleared for reg: 0x%lx\n",
+			"Expected all the features to be cleared for reg: 0x%lx",
 			reg_info->reg);
 
 		/*
@@ -226,7 +226,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
 		 */
 		ret = __vcpu_set_reg(vcpu, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit));
 		TEST_ASSERT(ret != 0 && errno == EBUSY,
-		"Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n",
+		"Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx",
 		errno, reg_info->reg);
 	}
 }
@@ -265,7 +265,7 @@ static void test_guest_stage(struct kvm_vm **vm, struct kvm_vcpu **vcpu)
 	case TEST_STAGE_HVC_IFACE_FALSE_INFO:
 		break;
 	default:
-		TEST_FAIL("Unknown test stage: %d\n", prev_stage);
+		TEST_FAIL("Unknown test stage: %d", prev_stage);
 	}
 }
 
@@ -294,7 +294,7 @@ static void test_run(void)
 			REPORT_GUEST_ASSERT(uc);
 			break;
 		default:
-			TEST_FAIL("Unexpected guest exit\n");
+			TEST_FAIL("Unexpected guest exit");
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 08a5ca5bed56..53fddad57cbb 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -414,10 +414,10 @@ static bool punch_hole_in_backing_store(struct kvm_vm *vm,
 	if (fd != -1) {
 		ret = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				0, paging_size);
-		TEST_ASSERT(ret == 0, "fallocate failed\n");
+		TEST_ASSERT(ret == 0, "fallocate failed");
 	} else {
 		ret = madvise(hva, paging_size, MADV_DONTNEED);
-		TEST_ASSERT(ret == 0, "madvise failed\n");
+		TEST_ASSERT(ret == 0, "madvise failed");
 	}
 
 	return true;
@@ -501,7 +501,7 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 
 void fail_vcpu_run_no_handler(int ret)
 {
-	TEST_FAIL("Unexpected vcpu run failure\n");
+	TEST_FAIL("Unexpected vcpu run failure");
 }
 
 void fail_vcpu_run_mmio_no_syndrome_handler(int ret)
diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
index f4ceae9c8925..2d189f3da228 100644
--- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c
+++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
@@ -178,7 +178,7 @@ static void expect_call_denied(struct kvm_vcpu *vcpu)
 	struct ucall uc;
 
 	if (get_ucall(vcpu, &uc) != UCALL_SYNC)
-		TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd);
+		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
 
 	TEST_ASSERT(uc.args[1] == SMCCC_RET_NOT_SUPPORTED,
 		    "Unexpected SMCCC return code: %lu", uc.args[1]);
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index 9d51b5691349..5f9713364693 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -517,11 +517,11 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
 
 	if (expect_fail)
 		TEST_ASSERT(pmcr_orig == pmcr,
-			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx\n",
+			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx",
 			    pmcr, pmcr_n);
 	else
 		TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr),
-			    "Failed to update PMCR.N to %lu (received: %lu)\n",
+			    "Failed to update PMCR.N to %lu (received: %lu)",
 			    pmcr_n, get_pmcr_n(pmcr));
 }
 
@@ -594,12 +594,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 		 */
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
 
 		/*
@@ -611,12 +611,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
 		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
-			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
 	}
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 09c116a82a84..bf3609f71854 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -45,10 +45,10 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 
 	/* Let the guest access its memory */
 	ret = _vcpu_run(vcpu);
-	TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+	TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 	if (get_ucall(vcpu, NULL) != UCALL_SYNC) {
 		TEST_ASSERT(false,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 	}
 
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index d374dbcf9a53..504f6fe980e8 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -88,9 +88,9 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 
 		pr_debug("Got sync event from vCPU %d\n", vcpu_idx);
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 6cbecf499767..eaad5b20854c 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -262,7 +262,7 @@ static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		    "vcpu run failed: errno=%d", err);
 
 	TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-		    "Invalid guest sync status: exit_reason=%s\n",
+		    "Invalid guest sync status: exit_reason=%s",
 		    exit_reason_str(run->exit_reason));
 
 	vcpu_handle_sync_stop();
@@ -376,7 +376,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 
 	cleared = kvm_vm_reset_dirty_ring(vcpu->vm);
 
-	/* Cleared pages should be the same as collected */
+	/*
+	 * Cleared pages should be the same as collected, as KVM is supposed to
+	 * clear only the entries that have been harvested.
+	 */
 	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
 		    "with collected (%u)", cleared, count);
 
@@ -410,17 +413,11 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		pr_info("vcpu continues now.\n");
 	} else {
 		TEST_ASSERT(false, "Invalid guest sync status: "
-			    "exit_reason=%s\n",
+			    "exit_reason=%s",
 			    exit_reason_str(run->exit_reason));
 	}
 }
 
-static void dirty_ring_before_vcpu_join(void)
-{
-	/* Kick another round of vcpu just to make sure it will quit */
-	sem_post(&sem_vcpu_cont);
-}
-
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */
@@ -433,7 +430,6 @@ struct log_mode {
 				     uint32_t *ring_buf_idx);
 	/* Hook to call when after each vcpu run */
 	void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err);
-	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
@@ -452,7 +448,6 @@ struct log_mode {
 		.supported = dirty_ring_supported,
 		.create_vm_done = dirty_ring_create_vm_done,
 		.collect_dirty_pages = dirty_ring_collect_dirty_pages,
-		.before_vcpu_join = dirty_ring_before_vcpu_join,
 		.after_vcpu_run = dirty_ring_after_vcpu_run,
 	},
 };
@@ -513,14 +508,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 		mode->after_vcpu_run(vcpu, ret, err);
 }
 
-static void log_mode_before_vcpu_join(void)
-{
-	struct log_mode *mode = &log_modes[host_log_mode];
-
-	if (mode->before_vcpu_join)
-		mode->before_vcpu_join();
-}
-
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -719,6 +706,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 	uint32_t ring_buf_idx = 0;
+	int sem_val;
 
 	if (!log_mode_supported()) {
 		print_skip("Log mode '%s' not supported",
@@ -788,12 +776,22 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	/* Start the iterations */
 	iteration = 1;
 	sync_global_to_guest(vm, iteration);
-	host_quit = false;
+	WRITE_ONCE(host_quit, false);
 	host_dirty_count = 0;
 	host_clear_count = 0;
 	host_track_next_count = 0;
 	WRITE_ONCE(dirty_ring_vcpu_ring_full, false);
 
+	/*
+	 * Ensure the previous iteration didn't leave a dangling semaphore, i.e.
+	 * that the main task and vCPU worker were synchronized and completed
+	 * verification of all iterations.
+	 */
+	sem_getvalue(&sem_vcpu_stop, &sem_val);
+	TEST_ASSERT_EQ(sem_val, 0);
+	sem_getvalue(&sem_vcpu_cont, &sem_val);
+	TEST_ASSERT_EQ(sem_val, 0);
+
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu);
 
 	while (iteration < p->iterations) {
@@ -819,15 +817,21 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		assert(host_log_mode == LOG_MODE_DIRTY_RING ||
 		       atomic_read(&vcpu_sync_stop_requested) == false);
 		vm_dirty_log_verify(mode, bmap);
-		sem_post(&sem_vcpu_cont);
 
-		iteration++;
+		/*
+		 * Set host_quit before sem_vcpu_cont in the final iteration to
+		 * ensure that the vCPU worker doesn't resume the guest.  As
+		 * above, the dirty ring test may stop and wait even when not
+		 * explicitly request to do so, i.e. would hang waiting for a
+		 * "continue" if it's allowed to resume the guest.
+		 */
+		if (++iteration == p->iterations)
+			WRITE_ONCE(host_quit, true);
+
+		sem_post(&sem_vcpu_cont);
 		sync_global_to_guest(vm, iteration);
 	}
 
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	log_mode_before_vcpu_join();
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 8274ef04301f..91f05f78e824 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -152,7 +152,7 @@ static void check_supported(struct vcpu_reg_list *c)
 			continue;
 
 		__TEST_REQUIRE(kvm_has_cap(s->capability),
-			       "%s: %s not available, skipping tests\n",
+			       "%s: %s not available, skipping tests",
 			       config_name(c), s->name);
 	}
 }
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
index 41230b746190..3502caa3590c 100644
--- a/tools/testing/selftests/kvm/guest_print_test.c
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -98,7 +98,7 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg)
 	int offset = len_str - len_substr;
 
 	TEST_ASSERT(len_substr <= len_str,
-		    "Expected '%s' to be a substring of '%s'\n",
+		    "Expected '%s' to be a substring of '%s'",
 		    assert_msg, expected_assert_msg);
 
 	TEST_ASSERT(strcmp(&assert_msg[offset], expected_assert_msg) == 0,
@@ -116,7 +116,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
 		vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
-			    "Unexpected exit reason: %u (%s),\n",
+			    "Unexpected exit reason: %u (%s),",
 			    run->exit_reason, exit_reason_str(run->exit_reason));
 
 		switch (get_ucall(vcpu, &uc)) {
@@ -161,11 +161,11 @@ static void test_limits(void)
 	vcpu_run(vcpu);
 
 	TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
-		    "Unexpected exit reason: %u (%s),\n",
+		    "Unexpected exit reason: %u (%s),",
 		    run->exit_reason, exit_reason_str(run->exit_reason));
 
 	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_ABORT,
-		    "Unexpected ucall command: %lu,  Expected: %u (UCALL_ABORT)\n",
+		    "Unexpected ucall command: %lu,  Expected: %u (UCALL_ABORT)",
 		    uc.cmd, UCALL_ABORT);
 
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index f5d59b9934f1..decc521fc760 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -41,7 +41,7 @@ static void *run_vcpu(void *arg)
 
 	vcpu_run(vcpu);
 
-	TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+	TEST_ASSERT(false, "%s: exited with reason %d: %s",
 		    __func__, run->exit_reason,
 		    exit_reason_str(run->exit_reason));
 	pthread_exit(NULL);
@@ -55,7 +55,7 @@ static void *sleeping_thread(void *arg)
 		fd = open("/dev/null", O_RDWR);
 		close(fd);
 	}
-	TEST_ASSERT(false, "%s: exited\n", __func__);
+	TEST_ASSERT(false, "%s: exited", __func__);
 	pthread_exit(NULL);
 }
 
@@ -118,7 +118,7 @@ static void run_test(uint32_t run)
 	for (i = 0; i < VCPU_NUM; ++i)
 		check_join(threads[i], &b);
 	/* Should not be reached */
-	TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+	TEST_ASSERT(false, "%s: [%d] child escaped the ninja", __func__, run);
 }
 
 void wait_for_child_setup(pid_t pid)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 71a41fa924b7..50a5e31ba8da 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -195,4 +195,6 @@ __printf(3, 4) int guest_snprintf(char *buf, int n, const char *fmt, ...);
 
 char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
 
+char *sys_get_cur_clocksource(void);
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index a84863503fcb..5bca8c947c82 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1271,4 +1271,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 #define PFERR_GUEST_PAGE_MASK	BIT_ULL(PFERR_GUEST_PAGE_BIT)
 #define PFERR_IMPLICIT_ACCESS	BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
 
+bool sys_clocksource_is_based_on_tsc(void);
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 31b3cb24b9a7..b9e23265e4b3 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -65,7 +65,7 @@ int main(int argc, char *argv[])
 
 			int r = setrlimit(RLIMIT_NOFILE, &rl);
 			__TEST_REQUIRE(r >= 0,
-				       "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+				       "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)",
 				       old_rlim_max, nr_fds_wanted);
 		} else {
 			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index e37dc9c21888..e0ba97ac1c56 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -204,9 +204,9 @@ static void *vcpu_worker(void *data)
 		ret = _vcpu_run(vcpu);
 		ts_diff = timespec_elapsed(start);
 
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 		TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
-			    "Invalid guest sync status: exit_reason=%s\n",
+			    "Invalid guest sync status: exit_reason=%s",
 			    exit_reason_str(vcpu->run->exit_reason));
 
 		pr_debug("Got sync event from vCPU %d\n", vcpu->id);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 41c776b642c0..43b9a7283360 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -398,7 +398,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
-		    "  num: %u\n", num);
+		    "  num: %u", num);
 
 	va_start(ap, num);
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b5f28d21a947..184378d593e9 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -38,7 +38,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 	struct list_head *iter;
 	unsigned int nr_gic_pages, nr_vcpus_created = 0;
 
-	TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty\n");
+	TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty");
 
 	/*
 	 * Make sure that the caller is infact calling this
@@ -47,7 +47,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 	list_for_each(iter, &vm->vcpus)
 		nr_vcpus_created++;
 	TEST_ASSERT(nr_vcpus == nr_vcpus_created,
-			"Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)\n",
+			"Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)",
 			nr_vcpus, nr_vcpus_created);
 
 	/* Distributor setup */
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index 266f3876e10a..f34d926d9735 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -184,7 +184,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 				"Seek to program segment offset failed,\n"
 				"  program header idx: %u errno: %i\n"
 				"  offset_rv: 0x%jx\n"
-				"  expected: 0x%jx\n",
+				"  expected: 0x%jx",
 				n1, errno, (intmax_t) offset_rv,
 				(intmax_t) phdr.p_offset);
 			test_read(fd, addr_gva2hva(vm, phdr.p_vaddr),
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index e066d584c656..1b197426f29f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -27,7 +27,8 @@ int open_path_or_exit(const char *path, int flags)
 	int fd;
 
 	fd = open(path, flags);
-	__TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno);
+	__TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno));
+	TEST_ASSERT(fd >= 0, "Failed to open '%s'", path);
 
 	return fd;
 }
@@ -320,7 +321,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	uint64_t nr_pages;
 
 	TEST_ASSERT(nr_runnable_vcpus,
-		    "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");
+		    "Use vm_create_barebones() for VMs that _never_ have vCPUs");
 
 	TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
 		    "nr_vcpus = %d too large for host, max-vcpus = %d",
@@ -491,7 +492,7 @@ void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
 	CPU_ZERO(&mask);
 	CPU_SET(pcpu, &mask);
 	r = sched_setaffinity(0, sizeof(mask), &mask);
-	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
+	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu);
 }
 
 static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
@@ -499,7 +500,7 @@ static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
 	uint32_t pcpu = atoi_non_negative("CPU number", cpu_str);
 
 	TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask),
-		    "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu);
+		    "Not allowed to run on pCPU '%d', check cgroups?", pcpu);
 	return pcpu;
 }
 
@@ -529,7 +530,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 	int i, r;
 
 	cpu_list = strdup(pcpus_string);
-	TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");
+	TEST_ASSERT(cpu_list, "strdup() allocation failed.");
 
 	r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
 	TEST_ASSERT(!r, "sched_getaffinity() failed");
@@ -538,7 +539,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 
 	/* 1. Get all pcpus for vcpus. */
 	for (i = 0; i < nr_vcpus; i++) {
-		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
+		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'", i);
 		vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
 		cpu = strtok(NULL, delim);
 	}
@@ -1057,7 +1058,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
-		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d\n",
+		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
 		ret, errno, slot, flags,
 		guest_paddr, (uint64_t) region->region.memory_size,
 		region->region.guest_memfd);
@@ -1222,7 +1223,7 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
 		len = min_t(uint64_t, end - gpa, region->region.memory_size - offset);
 
 		ret = fallocate(region->region.guest_memfd, mode, fd_offset, len);
-		TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx\n",
+		TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx",
 			    punch_hole ? "punch hole" : "allocate", gpa, len,
 			    region->region.guest_memfd, mode, fd_offset);
 	}
@@ -1265,7 +1266,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	struct kvm_vcpu *vcpu;
 
 	/* Confirm a vcpu with the specified id doesn't already exist. */
-	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id);
+	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists", vcpu_id);
 
 	/* Allocate and initialize new vcpu structure. */
 	vcpu = calloc(1, sizeof(*vcpu));
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index d05487e5a371..cf2c73971308 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -192,7 +192,7 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
 	TEST_ASSERT(guest_num_pages < region_end_gfn,
 		    "Requested more guest memory than address space allows.\n"
 		    "    guest pages: %" PRIx64 " max gfn: %" PRIx64
-		    " nr_vcpus: %d wss: %" PRIx64 "]\n",
+		    " nr_vcpus: %d wss: %" PRIx64 "]",
 		    guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes);
 
 	args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size;
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 7ca736fb4194..2bb33a8ac03c 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -327,7 +327,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
-		    "  num: %u\n", num);
+		    "  num: %u", num);
 
 	va_start(ap, num);
 
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 15945121daf1..f6d227892cbc 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -198,7 +198,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	int i;
 
 	TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
-		    "  num: %u\n",
+		    "  num: %u",
 		    num);
 
 	va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 5d7f28b02d73..5a8f8becb129 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -392,3 +392,28 @@ char *strdup_printf(const char *fmt, ...)
 
 	return str;
 }
+
+#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
+
+char *sys_get_cur_clocksource(void)
+{
+	char *clk_name;
+	struct stat st;
+	FILE *fp;
+
+	fp = fopen(CLOCKSOURCE_PATH, "r");
+	TEST_ASSERT(fp, "failed to open clocksource file, errno: %d", errno);
+
+	TEST_ASSERT(!fstat(fileno(fp), &st), "failed to stat clocksource file, errno: %d",
+		    errno);
+
+	clk_name = malloc(st.st_size);
+	TEST_ASSERT(clk_name, "failed to allocate buffer to read file");
+
+	TEST_ASSERT(fgets(clk_name, st.st_size, fp), "failed to read clocksource file: %d",
+		    ferror(fp));
+
+	fclose(fp);
+
+	return clk_name;
+}
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index 271f63891581..f4eef6eb2dc2 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -69,7 +69,7 @@ static void *uffd_handler_thread_fn(void *arg)
 		if (pollfd[1].revents & POLLIN) {
 			r = read(pollfd[1].fd, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread\n");
+				    "Error reading pipefd in UFFD thread");
 			break;
 		}
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d8288374078e..f639b3e062e3 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -170,10 +170,10 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 		 * this level.
 		 */
 		TEST_ASSERT(current_level != target_level,
-			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
+			    "Cannot create hugepage at level: %u, vaddr: 0x%lx",
 			    current_level, vaddr);
 		TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
-			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
+			    "Cannot create page table at level: %u, vaddr: 0x%lx",
 			    current_level, vaddr);
 	}
 	return pte;
@@ -220,7 +220,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	/* Fill in page table entry. */
 	pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
-		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
+		    "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
 }
 
@@ -253,7 +253,7 @@ static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
 	if (*pte & PTE_LARGE_MASK) {
 		TEST_ASSERT(*level == PG_LEVEL_NONE ||
 			    *level == current_level,
-			    "Unexpected hugepage at level %d\n", current_level);
+			    "Unexpected hugepage at level %d", current_level);
 		*level = current_level;
 	}
 
@@ -825,7 +825,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	struct kvm_regs regs;
 
 	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
-		    "  num: %u\n",
+		    "  num: %u",
 		    num);
 
 	va_start(ap, num);
@@ -1299,3 +1299,14 @@ void kvm_selftest_arch_init(void)
 	host_cpu_is_intel = this_cpu_is_intel();
 	host_cpu_is_amd = this_cpu_is_amd();
 }
+
+bool sys_clocksource_is_based_on_tsc(void)
+{
+	char *clk_name = sys_get_cur_clocksource();
+	bool ret = !strcmp(clk_name, "tsc\n") ||
+		   !strcmp(clk_name, "hyperv_clocksource_tsc_page\n");
+
+	free(clk_name);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 59d97531c9b1..089b8925b6b2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -54,7 +54,7 @@ int vcpu_enable_evmcs(struct kvm_vcpu *vcpu)
 	/* KVM should return supported EVMCS version range */
 	TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
 		    (evmcs_ver & 0xff) > 0,
-		    "Incorrect EVMCS version range: %x:%x\n",
+		    "Incorrect EVMCS version range: %x:%x",
 		    evmcs_ver & 0xff, evmcs_ver >> 8);
 
 	return evmcs_ver;
@@ -387,10 +387,10 @@ static void nested_create_pte(struct kvm_vm *vm,
 		 * this level.
 		 */
 		TEST_ASSERT(current_level != target_level,
-			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx",
 			    current_level, nested_paddr);
 		TEST_ASSERT(!pte->page_size,
-			    "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+			    "Cannot create page table at level: %u, nested_paddr: 0x%lx",
 			    current_level, nested_paddr);
 	}
 }
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 9855c41ca811..156361966612 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -45,7 +45,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
 	/* Let the guest access its memory until a stop signal is received */
 	while (!READ_ONCE(memstress_args.stop_vcpus)) {
 		ret = _vcpu_run(vcpu);
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
 
 		if (get_ucall(vcpu, NULL) == UCALL_SYNC)
 			continue;
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 8698d1ab60d0..579a64f97333 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -175,11 +175,11 @@ static void wait_for_vcpu(void)
 	struct timespec ts;
 
 	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
-		    "clock_gettime() failed: %d\n", errno);
+		    "clock_gettime() failed: %d", errno);
 
 	ts.tv_sec += 2;
 	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
-		    "sem_timedwait() failed: %d\n", errno);
+		    "sem_timedwait() failed: %d", errno);
 }
 
 static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages)
@@ -336,7 +336,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
 
 		gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, slot);
 		TEST_ASSERT(gpa == guest_addr,
-			    "vm_phy_pages_alloc() failed\n");
+			    "vm_phy_pages_alloc() failed");
 
 		data->hva_slots[slot - 1] = addr_gpa2hva(data->vm, guest_addr);
 		memset(data->hva_slots[slot - 1], 0, npages * guest_page_size);
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6652108816db..6435e7a65642 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -49,15 +49,42 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTNTL:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNE:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKR:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHA:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHB:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSED:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSH:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKT:
 	/*
 	 * Like ISA_EXT registers, SBI_EXT registers are only visible when the
 	 * host supports them and disabling them does not affect the visibility
@@ -150,7 +177,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 
 		/* Double check whether the desired extension was enabled */
 		__TEST_REQUIRE(vcpu_has_ext(vcpu, feature),
-			       "%s not available, skipping tests\n", s->name);
+			       "%s not available, skipping tests", s->name);
 	}
 }
 
@@ -394,15 +421,42 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(SVPBMT),
 		KVM_ISA_EXT_ARR(ZBA),
 		KVM_ISA_EXT_ARR(ZBB),
+		KVM_ISA_EXT_ARR(ZBC),
+		KVM_ISA_EXT_ARR(ZBKB),
+		KVM_ISA_EXT_ARR(ZBKC),
+		KVM_ISA_EXT_ARR(ZBKX),
 		KVM_ISA_EXT_ARR(ZBS),
+		KVM_ISA_EXT_ARR(ZFA),
+		KVM_ISA_EXT_ARR(ZFH),
+		KVM_ISA_EXT_ARR(ZFHMIN),
 		KVM_ISA_EXT_ARR(ZICBOM),
 		KVM_ISA_EXT_ARR(ZICBOZ),
 		KVM_ISA_EXT_ARR(ZICNTR),
 		KVM_ISA_EXT_ARR(ZICOND),
 		KVM_ISA_EXT_ARR(ZICSR),
 		KVM_ISA_EXT_ARR(ZIFENCEI),
+		KVM_ISA_EXT_ARR(ZIHINTNTL),
 		KVM_ISA_EXT_ARR(ZIHINTPAUSE),
 		KVM_ISA_EXT_ARR(ZIHPM),
+		KVM_ISA_EXT_ARR(ZKND),
+		KVM_ISA_EXT_ARR(ZKNE),
+		KVM_ISA_EXT_ARR(ZKNH),
+		KVM_ISA_EXT_ARR(ZKR),
+		KVM_ISA_EXT_ARR(ZKSED),
+		KVM_ISA_EXT_ARR(ZKSH),
+		KVM_ISA_EXT_ARR(ZKT),
+		KVM_ISA_EXT_ARR(ZVBB),
+		KVM_ISA_EXT_ARR(ZVBC),
+		KVM_ISA_EXT_ARR(ZVFH),
+		KVM_ISA_EXT_ARR(ZVFHMIN),
+		KVM_ISA_EXT_ARR(ZVKB),
+		KVM_ISA_EXT_ARR(ZVKG),
+		KVM_ISA_EXT_ARR(ZVKNED),
+		KVM_ISA_EXT_ARR(ZVKNHA),
+		KVM_ISA_EXT_ARR(ZVKNHB),
+		KVM_ISA_EXT_ARR(ZVKSED),
+		KVM_ISA_EXT_ARR(ZVKSH),
+		KVM_ISA_EXT_ARR(ZVKT),
 	};
 
 	if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
@@ -888,15 +942,42 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
 KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
 KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
 KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
 KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintntl, ZIHINTNTL);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
 KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkne, ZKNE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknh, ZKNH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknha, ZVKNHA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknhb, ZVKNHB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksed, ZVKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksh, ZVKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkt, ZVKT);
 
 struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_base,
@@ -914,14 +995,41 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_svpbmt,
 	&config_zba,
 	&config_zbb,
+	&config_zbc,
+	&config_zbkb,
+	&config_zbkc,
+	&config_zbkx,
 	&config_zbs,
+	&config_zfa,
+	&config_zfh,
+	&config_zfhmin,
 	&config_zicbom,
 	&config_zicboz,
 	&config_zicntr,
 	&config_zicond,
 	&config_zicsr,
 	&config_zifencei,
+	&config_zihintntl,
 	&config_zihintpause,
 	&config_zihpm,
+	&config_zknd,
+	&config_zkne,
+	&config_zknh,
+	&config_zkr,
+	&config_zksed,
+	&config_zksh,
+	&config_zkt,
+	&config_zvbb,
+	&config_zvbc,
+	&config_zvfh,
+	&config_zvfhmin,
+	&config_zvkb,
+	&config_zvkg,
+	&config_zvkned,
+	&config_zvknha,
+	&config_zvknhb,
+	&config_zvksed,
+	&config_zvksh,
+	&config_zvkt,
 };
 int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index f74e76d03b7e..28f97fb52044 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -245,7 +245,7 @@ int main(int argc, char *argv[])
 		} while (snapshot != atomic_read(&seq_cnt));
 
 		TEST_ASSERT(rseq_cpu == cpu,
-			    "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+			    "rseq CPU = %d, sched CPU = %d", rseq_cpu, cpu);
 	}
 
 	/*
@@ -256,7 +256,7 @@ int main(int argc, char *argv[])
 	 * migrations given the 1us+ delay in the migration task.
 	 */
 	TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
-		    "Only performed %d KVM_RUNs, task stalled too much?\n", i);
+		    "Only performed %d KVM_RUNs, task stalled too much?", i);
 
 	pthread_join(migration_thread, NULL);
 
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index bb3ca9a5d731..b6da8f71ea19 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -375,6 +375,32 @@ static void test_copy(void)
 	kvm_vm_free(t.kvm_vm);
 }
 
+static void test_copy_access_register(void)
+{
+	struct test_default t = test_default_init(guest_copy);
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+
+	prepare_mem12();
+	t.run->psw_mask &= ~(3UL << (63 - 17));
+	t.run->psw_mask |= 1UL << (63 - 17);  /* Enable AR mode */
+
+	/*
+	 * Primary address space gets used if an access register
+	 * contains zero. The host makes use of AR[1] so is a good
+	 * candidate to ensure the guest AR (of zero) is used.
+	 */
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size,
+		   GADDR_V(mem1), AR(1));
+	HOST_SYNC(t.vcpu, STAGE_COPIED);
+
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, t.size,
+		   GADDR_V(mem2), AR(1));
+	ASSERT_MEM_EQ(mem1, mem2, t.size);
+
+	kvm_vm_free(t.kvm_vm);
+}
+
 static void set_storage_key_range(void *addr, size_t len, uint8_t key)
 {
 	uintptr_t _addr, abs, i;
@@ -1102,6 +1128,11 @@ int main(int argc, char *argv[])
 			.requirements_met = extension_cap > 0,
 		},
 		{
+			.name = "copy with access register mode",
+			.test = test_copy_access_register,
+			.requirements_met = true,
+		},
+		{
 			.name = "error checks with key",
 			.test = test_errors_key,
 			.requirements_met = extension_cap > 0,
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index e41e2cb8ffa9..357943f2bea8 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -78,7 +78,7 @@ static void assert_noirq(struct kvm_vcpu *vcpu)
 	 * (notably, the emergency call interrupt we have injected) should
 	 * be cleared by the resets, so this should be 0.
 	 */
-	TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d\n", errno);
+	TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d", errno);
 	TEST_ASSERT(!irqs, "IRQ pending");
 }
 
@@ -199,7 +199,7 @@ static void inject_irq(struct kvm_vcpu *vcpu)
 	irq->type = KVM_S390_INT_EMERGENCY;
 	irq->u.emerg.code = vcpu->id;
 	irqs = __vcpu_ioctl(vcpu, KVM_S390_SET_IRQ_STATE, &irq_state);
-	TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno);
+	TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d", errno);
 }
 
 static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu)
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index 636a70ddac1e..43fb25ddc3ec 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -39,13 +39,13 @@ static void guest_code(void)
 #define REG_COMPARE(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
+		    " values did not match: 0x%llx, 0x%llx", \
 		    left->reg, right->reg)
 
 #define REG_COMPARE32(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%x, 0x%x\n", \
+		    " values did not match: 0x%x, 0x%x", \
 		    left->reg, right->reg)
 
 
@@ -82,14 +82,14 @@ void test_read_invalid(struct kvm_vcpu *vcpu)
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
 	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 }
@@ -103,14 +103,14 @@ void test_set_invalid(struct kvm_vcpu *vcpu)
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 }
@@ -125,12 +125,12 @@ void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu)
 	/* Request and verify all valid register sets. */
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s390_sieic.icptcode == 4 &&
 		    (run->s390_sieic.ipa >> 8) == 0x83 &&
 		    (run->s390_sieic.ipb >> 16) == 0x501,
-		    "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x\n",
+		    "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x",
 		    run->s390_sieic.icptcode, run->s390_sieic.ipa,
 		    run->s390_sieic.ipb);
 
@@ -161,7 +161,7 @@ void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu)
 	}
 
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1,
 		    "r11 sync regs value incorrect 0x%llx.",
@@ -193,7 +193,7 @@ void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu)
 	run->s.regs.gprs[11] = 0xDEADBEEF;
 	run->s.regs.diag318 = 0x4B1D;
 	rv = _vcpu_run(vcpu);
-	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+	TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
 	TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF,
 		    "r11 sync regs value incorrect 0x%llx.",
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 075b80dbe237..06b43ed23580 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -98,11 +98,11 @@ static void wait_for_vcpu(void)
 	struct timespec ts;
 
 	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
-		    "clock_gettime() failed: %d\n", errno);
+		    "clock_gettime() failed: %d", errno);
 
 	ts.tv_sec += 2;
 	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
-		    "sem_timedwait() failed: %d\n", errno);
+		    "sem_timedwait() failed: %d", errno);
 
 	/* Wait for the vCPU thread to reenter the guest. */
 	usleep(100000);
@@ -302,7 +302,7 @@ static void test_delete_memory_region(void)
 	if (run->exit_reason == KVM_EXIT_INTERNAL_ERROR)
 		TEST_ASSERT(regs.rip >= final_rip_start &&
 			    regs.rip < final_rip_end,
-			    "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx\n",
+			    "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx",
 			    final_rip_start, final_rip_end, regs.rip);
 
 	kvm_vm_free(vm);
@@ -367,11 +367,21 @@ static void test_invalid_memory_region_flags(void)
 	}
 
 	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
+		int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
+
 		r = __vm_set_user_memory_region2(vm, 0,
 						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
-						 0, MEM_REGION_SIZE, NULL, 0, 0);
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
 		TEST_ASSERT(r && errno == EINVAL,
 			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");
+
+		r = __vm_set_user_memory_region2(vm, 0,
+						 KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD,
+						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
+		TEST_ASSERT(r && errno == EINVAL,
+			    "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported");
+
+		close(guest_memfd);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
index 7f5b330b6a1b..513d421a9bff 100644
--- a/tools/testing/selftests/kvm/system_counter_offset_test.c
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -108,7 +108,7 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 			handle_abort(&uc);
 			return;
 		default:
-			TEST_ASSERT(0, "unhandled ucall %ld\n",
+			TEST_ASSERT(0, "unhandled ucall %ld",
 				    get_ucall(vcpu, &uc));
 		}
 	}
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 11329e5ff945..eae521f050e0 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -221,7 +221,7 @@ int main(int argc, char *argv[])
 	vm_vaddr_t amx_cfg, tiledata, xstate;
 	struct ucall uc;
 	u32 amx_offset;
-	int stage, ret;
+	int ret;
 
 	/*
 	 * Note, all off-by-default features must be enabled before anything
@@ -263,7 +263,7 @@ int main(int argc, char *argv[])
 	memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE));
 	vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate);
 
-	for (stage = 1; ; stage++) {
+	for (;;) {
 		vcpu_run(vcpu);
 		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
@@ -296,7 +296,7 @@ int main(int argc, char *argv[])
 				void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
 				/* Only check TMM0 register, 1 tile */
 				ret = memcmp(amx_start, tiles_data, TILE_SIZE);
-				TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
+				TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret);
 				kvm_x86_state_cleanup(state);
 				break;
 			case 9:
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index 3b34d8156d1c..8c579ce714e9 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -84,7 +84,7 @@ static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
 
 		TEST_ASSERT(e1->function == e2->function &&
 			    e1->index == e2->index && e1->flags == e2->flags,
-			    "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x\n",
+			    "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x",
 			    i, e1->function, e1->index, e1->flags,
 			    e2->function, e2->index, e2->flags);
 
@@ -170,7 +170,7 @@ static void test_get_cpuid2(struct kvm_vcpu *vcpu)
 
 	vcpu_ioctl(vcpu, KVM_GET_CPUID2, cpuid);
 	TEST_ASSERT(cpuid->nent == vcpu->cpuid->nent,
-		    "KVM didn't update nent on success, wanted %u, got %u\n",
+		    "KVM didn't update nent on success, wanted %u, got %u",
 		    vcpu->cpuid->nent, cpuid->nent);
 
 	for (i = 0; i < vcpu->cpuid->nent; i++) {
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
index 634c6bfcd572..ee3b384b991c 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
@@ -92,7 +92,6 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	uint64_t host_num_pages;
 	uint64_t pages_per_slot;
 	int i;
-	uint64_t total_4k_pages;
 	struct kvm_page_stats stats_populated;
 	struct kvm_page_stats stats_dirty_logging_enabled;
 	struct kvm_page_stats stats_dirty_pass[ITERATIONS];
@@ -107,6 +106,9 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 	pages_per_slot = host_num_pages / SLOTS;
+	TEST_ASSERT_EQ(host_num_pages, pages_per_slot * SLOTS);
+	TEST_ASSERT(!(host_num_pages % 512),
+		    "Number of pages, '%lu' not a multiple of 2MiB", host_num_pages);
 
 	bitmaps = memstress_alloc_bitmaps(SLOTS, pages_per_slot);
 
@@ -165,10 +167,8 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	memstress_free_bitmaps(bitmaps, SLOTS);
 	memstress_destroy_vm(vm);
 
-	/* Make assertions about the page counts. */
-	total_4k_pages = stats_populated.pages_4k;
-	total_4k_pages += stats_populated.pages_2m * 512;
-	total_4k_pages += stats_populated.pages_1g * 512 * 512;
+	TEST_ASSERT_EQ((stats_populated.pages_2m * 512 +
+			stats_populated.pages_1g * 512 * 512), host_num_pages);
 
 	/*
 	 * Check that all huge pages were split. Since large pages can only
@@ -180,19 +180,22 @@ static void run_test(enum vm_guest_mode mode, void *unused)
 	 */
 	if (dirty_log_manual_caps) {
 		TEST_ASSERT_EQ(stats_clear_pass[0].hugepages, 0);
-		TEST_ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages);
+		TEST_ASSERT(stats_clear_pass[0].pages_4k >= host_num_pages,
+			    "Expected at least '%lu' 4KiB pages, found only '%lu'",
+			    host_num_pages, stats_clear_pass[0].pages_4k);
 		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages);
 	} else {
 		TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0);
-		TEST_ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages);
+		TEST_ASSERT(stats_dirty_logging_enabled.pages_4k >= host_num_pages,
+			    "Expected at least '%lu' 4KiB pages, found only '%lu'",
+			    host_num_pages, stats_dirty_logging_enabled.pages_4k);
 	}
 
 	/*
 	 * Once dirty logging is disabled and the vCPUs have touched all their
-	 * memory again, the page counts should be the same as they were
+	 * memory again, the hugepage counts should be the same as they were
 	 * right after initial population of memory.
 	 */
-	TEST_ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k);
 	TEST_ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m);
 	TEST_ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
index 0a1573d52882..37b1a9f52864 100644
--- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h
+++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
@@ -41,7 +41,7 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu)
 
 	insn_bytes = run->emulation_failure.insn_bytes;
 	TEST_ASSERT(insn_bytes[0] == 0xd9 && insn_bytes[1] == 0,
-		    "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x\n",
+		    "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x",
 		    insn_bytes[0], insn_bytes[1]);
 
 	vcpu_regs_get(vcpu, &regs);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index f5e1e98f04f9..e058bc676cd6 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -212,6 +212,7 @@ int main(void)
 	int stage;
 
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME));
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
 
@@ -220,7 +221,7 @@ int main(void)
 	tsc_page_gva = vm_vaddr_alloc_page(vm);
 	memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize());
 	TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
-		"TSC page has to be page aligned\n");
+		"TSC page has to be page aligned");
 	vcpu_args_set(vcpu, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
 
 	host_check_tsc_msr_rdtsc(vcpu);
@@ -237,7 +238,7 @@ int main(void)
 			break;
 		case UCALL_DONE:
 			/* Keep in sync with guest_main() */
-			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d",
 				    stage);
 			goto out;
 		default:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 4f4193fc74ff..b923a285e96f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -454,7 +454,7 @@ static void guest_test_msrs_access(void)
 		case 44:
 			/* MSR is not available when CPUID feature bit is unset */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = false;
 			msr->fault_expected = true;
@@ -462,7 +462,7 @@ static void guest_test_msrs_access(void)
 		case 45:
 			/* MSR is vailable when CPUID feature bit is set */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT);
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = false;
@@ -471,7 +471,7 @@ static void guest_test_msrs_access(void)
 		case 46:
 			/* Writing bits other than 0 is forbidden */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = true;
 			msr->write_val = 0xdeadbeef;
@@ -480,7 +480,7 @@ static void guest_test_msrs_access(void)
 		case 47:
 			/* Setting bit 0 enables the feature */
 			if (!has_invtsc)
-				continue;
+				goto next_stage;
 			msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
 			msr->write = true;
 			msr->write_val = 1;
@@ -513,6 +513,7 @@ static void guest_test_msrs_access(void)
 			return;
 		}
 
+next_stage:
 		stage++;
 		kvm_vm_free(vm);
 	}
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 65e5f4c05068..f1617762c22f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -289,7 +289,7 @@ int main(int argc, char *argv[])
 		switch (get_ucall(vcpu[0], &uc)) {
 		case UCALL_SYNC:
 			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
+				    "Unexpected stage: %ld (%d expected)",
 				    uc.args[1], stage);
 			break;
 		case UCALL_DONE:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
index c4443f71f8dd..05b56095cf76 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
@@ -658,7 +658,7 @@ int main(int argc, char *argv[])
 		switch (get_ucall(vcpu[0], &uc)) {
 		case UCALL_SYNC:
 			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
+				    "Unexpected stage: %ld (%d expected)",
 				    uc.args[1], stage);
 			break;
 		case UCALL_ABORT:
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
index 1778704360a6..5bc12222d87a 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
@@ -92,7 +92,7 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case)
 				break;
 		} while (errno == EINTR);
 
-		TEST_ASSERT(!r, "clock_gettime() failed: %d\n", r);
+		TEST_ASSERT(!r, "clock_gettime() failed: %d", r);
 
 		data.realtime = ts.tv_sec * NSEC_PER_SEC;
 		data.realtime += ts.tv_nsec;
@@ -127,47 +127,11 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 			handle_abort(&uc);
 			return;
 		default:
-			TEST_ASSERT(0, "unhandled ucall: %ld\n", uc.cmd);
+			TEST_ASSERT(0, "unhandled ucall: %ld", uc.cmd);
 		}
 	}
 }
 
-#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
-
-static void check_clocksource(void)
-{
-	char *clk_name;
-	struct stat st;
-	FILE *fp;
-
-	fp = fopen(CLOCKSOURCE_PATH, "r");
-	if (!fp) {
-		pr_info("failed to open clocksource file: %d; assuming TSC.\n",
-			errno);
-		return;
-	}
-
-	if (fstat(fileno(fp), &st)) {
-		pr_info("failed to stat clocksource file: %d; assuming TSC.\n",
-			errno);
-		goto out;
-	}
-
-	clk_name = malloc(st.st_size);
-	TEST_ASSERT(clk_name, "failed to allocate buffer to read file\n");
-
-	if (!fgets(clk_name, st.st_size, fp)) {
-		pr_info("failed to read clocksource file: %d; assuming TSC.\n",
-			ferror(fp));
-		goto out;
-	}
-
-	TEST_ASSERT(!strncmp(clk_name, "tsc\n", st.st_size),
-		    "clocksource not supported: %s", clk_name);
-out:
-	fclose(fp);
-}
-
 int main(void)
 {
 	struct kvm_vcpu *vcpu;
@@ -179,7 +143,7 @@ int main(void)
 	flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK);
 	TEST_REQUIRE(flags & KVM_CLOCK_REALTIME);
 
-	check_clocksource();
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
 
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 83e25bccc139..17bbb96fc4df 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -257,9 +257,9 @@ int main(int argc, char **argv)
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES));
 
 	__TEST_REQUIRE(token == MAGIC_TOKEN,
-		       "This test must be run with the magic token %d.\n"
-		       "This is done by nx_huge_pages_test.sh, which\n"
-		       "also handles environment setup for the test.", MAGIC_TOKEN);
+		       "This test must be run with the magic token via '-t %d'.\n"
+		       "Running via nx_huge_pages_test.sh, which also handles "
+		       "environment setup, is strongly recommended.", MAGIC_TOKEN);
 
 	run_test(reclaim_period_ms, false, reboot_permissions);
 	run_test(reclaim_period_ms, true, reboot_permissions);
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index c9a07963d68a..87011965dc41 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -44,7 +44,7 @@ static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu)
 
 	get_ucall(vcpu, &uc);
 	TEST_ASSERT(uc.cmd == UCALL_SYNC,
-			"Received ucall other than UCALL_SYNC: %lu\n", uc.cmd);
+			"Received ucall other than UCALL_SYNC: %lu", uc.cmd);
 	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
 		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 283cc55597a4..a3bd54b925ab 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -866,7 +866,7 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
 	 * userspace doesn't set any pmu filter.
 	 */
 	count = run_vcpu_to_sync(vcpu);
-	TEST_ASSERT(count, "Unexpected count value: %ld\n", count);
+	TEST_ASSERT(count, "Unexpected count value: %ld", count);
 
 	for (i = 0; i < BIT(nr_fixed_counters); i++) {
 		bitmap = BIT(i);
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index c7ef97561038..a49828adf294 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -91,7 +91,7 @@ static void sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src)
 	int ret;
 
 	ret = __sev_migrate_from(dst, src);
-	TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno);
+	TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d", ret, errno);
 }
 
 static void test_sev_migrate_from(bool es)
@@ -113,7 +113,7 @@ static void test_sev_migrate_from(bool es)
 	/* Migrate the guest back to the original VM. */
 	ret = __sev_migrate_from(src_vm, dst_vms[NR_MIGRATE_TEST_VMS - 1]);
 	TEST_ASSERT(ret == -1 && errno == EIO,
-		    "VM that was migrated from should be dead. ret %d, errno: %d\n", ret,
+		    "VM that was migrated from should be dead. ret %d, errno: %d", ret,
 		    errno);
 
 	kvm_vm_free(src_vm);
@@ -172,7 +172,7 @@ static void test_sev_migrate_parameters(void)
 	vm_no_sev = aux_vm_create(true);
 	ret = __sev_migrate_from(vm_no_vcpu, vm_no_sev);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
+		    "Migrations require SEV enabled. ret %d, errno: %d", ret,
 		    errno);
 
 	if (!have_sev_es)
@@ -187,25 +187,25 @@ static void test_sev_migrate_parameters(void)
 	ret = __sev_migrate_from(sev_vm, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n",
+		"Should not be able migrate to SEV enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(sev_es_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		"Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n",
+		"SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm_no_vmsa);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n",
+		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d",
 		ret, errno);
 
 	kvm_vm_free(sev_vm);
@@ -227,7 +227,7 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src)
 	int ret;
 
 	ret = __sev_mirror_create(dst, src);
-	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
+	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno);
 }
 
 static void verify_mirror_allowed_cmds(int vm_fd)
@@ -259,7 +259,7 @@ static void verify_mirror_allowed_cmds(int vm_fd)
 		ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
 		TEST_ASSERT(
 			ret == -1 && errno == EINVAL,
-			"Should not be able call command: %d. ret: %d, errno: %d\n",
+			"Should not be able call command: %d. ret: %d, errno: %d",
 			cmd_id, ret, errno);
 	}
 
@@ -301,18 +301,18 @@ static void test_sev_mirror_parameters(void)
 	ret = __sev_mirror_create(sev_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to self. ret: %d, errno: %d\n",
+		"Should not be able copy context to self. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_mirror_create(vm_no_vcpu, vm_with_vcpu);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+		    "Copy context requires SEV enabled. ret %d, errno: %d", ret,
 		    errno);
 
 	ret = __sev_mirror_create(vm_with_vcpu, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d",
 		ret, errno);
 
 	if (!have_sev_es)
@@ -322,13 +322,13 @@ static void test_sev_mirror_parameters(void)
 	ret = __sev_mirror_create(sev_vm, sev_es_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n",
+		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	ret = __sev_mirror_create(sev_es_vm, sev_vm);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
-		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d",
 		ret, errno);
 
 	kvm_vm_free(sev_es_vm);
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
index 06edf00a97d6..1a46dd7bb391 100644
--- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
@@ -74,7 +74,7 @@ int main(int argc, char *argv[])
 				    MEM_REGION_SIZE / PAGE_SIZE, 0);
 	gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
 				 MEM_REGION_GPA, MEM_REGION_SLOT);
-	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc");
 	virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
 	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
 	memset(hva, 0, PAGE_SIZE);
@@ -102,7 +102,7 @@ int main(int argc, char *argv[])
 	case UCALL_DONE:
 		break;
 	default:
-		TEST_FAIL("Unrecognized ucall: %lu\n", uc.cmd);
+		TEST_FAIL("Unrecognized ucall: %lu", uc.cmd);
 	}
 
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 00965ba33f73..a91b5b145fa3 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -46,7 +46,7 @@ static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
 #define REG_COMPARE(reg) \
 	TEST_ASSERT(left->reg == right->reg, \
 		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
+		    " values did not match: 0x%llx, 0x%llx", \
 		    left->reg, right->reg)
 	REG_COMPARE(rax);
 	REG_COMPARE(rbx);
@@ -230,14 +230,14 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
 	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
 
@@ -245,14 +245,14 @@ int main(int argc, char *argv[])
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
 	rv = _vcpu_run(vcpu);
 	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
 
diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
index 0ed32ec903d0..dcbb3c29fb8e 100644
--- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
+++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
@@ -143,7 +143,7 @@ static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu)
 
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected.");
 	printf("vCPU received GP in guest.\n");
 }
@@ -188,7 +188,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA.");
 
 	printf("Injecting first UCNA at %#x.\n", FIRST_UCNA_ADDR);
@@ -198,7 +198,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
-		    "Expect UCALL_SYNC\n");
+		    "Expect UCALL_SYNC");
 	TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA.");
 
 	printf("Injecting second UCNA at %#x.\n", SECOND_UCNA_ADDR);
@@ -208,7 +208,7 @@ static void *run_ucna_injection(void *arg)
 
 	TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
 	if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) {
-		TEST_ASSERT(false, "vCPU assertion failure: %s.\n",
+		TEST_ASSERT(false, "vCPU assertion failure: %s.",
 			    (const char *)uc.args[0]);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 255c50b0dc32..9481cbcf284f 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -71,7 +71,7 @@ int main(int argc, char *argv[])
 			break;
 
 		TEST_ASSERT(run->io.port == 0x80,
-			    "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+			    "Expected I/O at port 0x80, got port 0x%x", run->io.port);
 
 		/*
 		 * Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
index 2bed5fb3a0d6..a81a24761aac 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -99,7 +99,7 @@ int main(int argc, char *argv[])
 			TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
 			TEST_ASSERT(run->internal.suberror ==
 				    KVM_INTERNAL_ERROR_EMULATION,
-				    "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+				    "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u",
 				    run->internal.suberror);
 			break;
 		}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index e4ad5fef52ff..7f6f5f23fb9b 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -128,17 +128,17 @@ int main(int argc, char *argv[])
 			 */
 			kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
 			if (uc.args[1]) {
-				TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n");
-				TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n");
+				TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean");
+				TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest");
 			} else {
-				TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n");
-				TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n");
+				TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty");
+				TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest");
 			}
 
-			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n");
-			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n");
-			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n");
-			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n");
+			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty");
+			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest");
+			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty");
+			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest");
 			break;
 		case UCALL_DONE:
 			done = true;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
index a9b827c69f32..fad3634fd9eb 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -28,7 +28,7 @@ static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu)
 
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
 	TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
-		    "Expected emulation failure, got %d\n",
+		    "Expected emulation failure, got %d",
 		    run->emulation_failure.suberror);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
index e710b6e7fb38..1759fa5cb3f2 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
@@ -116,23 +116,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_DONE();
 }
 
-static bool system_has_stable_tsc(void)
-{
-	bool tsc_is_stable;
-	FILE *fp;
-	char buf[4];
-
-	fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
-	if (fp == NULL)
-		return false;
-
-	tsc_is_stable = fgets(buf, sizeof(buf), fp) &&
-			!strncmp(buf, "tsc", sizeof(buf));
-
-	fclose(fp);
-	return tsc_is_stable;
-}
-
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
@@ -148,7 +131,7 @@ int main(int argc, char *argv[])
 
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
-	TEST_REQUIRE(system_has_stable_tsc());
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
 
 	/*
 	 * We set L1's scale factor to be a random number from 2 to 10.
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
index 67ac2a3292ef..725c206ba0b9 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
@@ -216,7 +216,7 @@ static void *vcpu_thread(void *arg)
 			    "Halting vCPU halted %lu times, woke %lu times, received %lu IPIs.\n"
 			    "Halter TPR=%#x PPR=%#x LVR=%#x\n"
 			    "Migrations attempted: %lu\n"
-			    "Migrations completed: %lu\n",
+			    "Migrations completed: %lu",
 			    vcpu->id, (const char *)uc.args[0],
 			    params->data->ipis_sent, params->data->hlt_count,
 			    params->data->wake_count,
@@ -288,7 +288,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 	}
 
 	TEST_ASSERT(nodes > 1,
-		    "Did not find at least 2 numa nodes. Can't do migration\n");
+		    "Did not find at least 2 numa nodes. Can't do migration");
 
 	fprintf(stderr, "Migrating amongst %d nodes found\n", nodes);
 
@@ -347,7 +347,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 				    wake_count != data->wake_count,
 				    "IPI, HLT and wake count have not increased "
 				    "in the last %lu seconds. "
-				    "HLTer is likely hung.\n", interval_secs);
+				    "HLTer is likely hung.", interval_secs);
 
 			ipis_sent = data->ipis_sent;
 			hlt_count = data->hlt_count;
@@ -381,7 +381,7 @@ void get_cmdline_args(int argc, char *argv[], int *run_secs,
 				    "-m adds calls to migrate_pages while vCPUs are running."
 				    " Default is no migrations.\n"
 				    "-d <delay microseconds> - delay between migrate_pages() calls."
-				    " Default is %d microseconds.\n",
+				    " Default is %d microseconds.",
 				    DEFAULT_RUN_SECS, DEFAULT_DELAY_USECS);
 		}
 	}
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index dc6217440db3..25a0b0db5c3c 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -116,7 +116,7 @@ int main(int argc, char *argv[])
 		vcpu_run(vcpu);
 
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
+			    "Unexpected exit reason: %u (%s),",
 			    run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
index e0ddf47362e7..167c97abff1b 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -29,7 +29,7 @@ int main(int argc, char *argv[])
 
 	xss_val = vcpu_get_msr(vcpu, MSR_IA32_XSS);
 	TEST_ASSERT(xss_val == 0,
-		    "MSR_IA32_XSS should be initialized to zero\n");
+		    "MSR_IA32_XSS should be initialized to zero");
 
 	vcpu_set_msr(vcpu, MSR_IA32_XSS, xss_val);
 
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 5b79758cae62..e64bbdf0e86e 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -9,6 +9,7 @@
 
 #include <errno.h>
 #include <linux/landlock.h>
+#include <linux/securebits.h>
 #include <sys/capability.h>
 #include <sys/socket.h>
 #include <sys/syscall.h>
@@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 		/* clang-format off */
 		CAP_DAC_OVERRIDE,
 		CAP_MKNOD,
+		CAP_NET_ADMIN,
+		CAP_NET_BIND_SERVICE,
 		CAP_SYS_ADMIN,
 		CAP_SYS_CHROOT,
-		CAP_NET_BIND_SERVICE,
 		/* clang-format on */
 	};
+	const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED;
+
+	if ((cap_get_secbits() & noroot) != noroot)
+		EXPECT_EQ(0, cap_set_secbits(noroot));
 
 	cap_p = cap_get_proc();
 	EXPECT_NE(NULL, cap_p)
@@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 			TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 		}
 	}
+
+	/* Automatically resets ambient capabilities. */
 	EXPECT_NE(-1, cap_set_proc(cap_p))
 	{
 		TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
@@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
 	{
 		TH_LOG("Failed to cap_free: %s", strerror(errno));
 	}
+
+	/* Quickly checks that ambient capabilities are cleared. */
+	EXPECT_NE(-1, cap_get_ambient(caps[0]));
 }
 
 /* We cannot put such helpers in a library because of kselftest_harness.h . */
@@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata)
 	_init_caps(_metadata, true);
 }
 
-static void _effective_cap(struct __test_metadata *const _metadata,
-			   const cap_value_t caps, const cap_flag_value_t value)
+static void _change_cap(struct __test_metadata *const _metadata,
+			const cap_flag_t flag, const cap_value_t cap,
+			const cap_flag_value_t value)
 {
 	cap_t cap_p;
 
@@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 	{
 		TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
 	}
-	EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value))
+	EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value))
 	{
 		TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
 	}
@@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata,
 }
 
 static void __maybe_unused set_cap(struct __test_metadata *const _metadata,
-				   const cap_value_t caps)
+				   const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_SET);
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET);
 }
 
 static void __maybe_unused clear_cap(struct __test_metadata *const _metadata,
-				     const cap_value_t caps)
+				     const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR);
+}
+
+static void __maybe_unused
+set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap)
+{
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET);
+
+	EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET))
+	{
+		TH_LOG("Failed to set ambient capability %d: %s", cap,
+		       strerror(errno));
+	}
+}
+
+static void __maybe_unused clear_ambient_cap(
+	struct __test_metadata *const _metadata, const cap_value_t cap)
 {
-	_effective_cap(_metadata, caps, CAP_CLEAR);
+	EXPECT_EQ(1, cap_get_ambient(cap));
+	_change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR);
+	EXPECT_EQ(0, cap_get_ambient(cap));
 }
 
 /* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 50818904397c..2d6d9b43d958 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -241,9 +241,11 @@ struct mnt_opt {
 	const char *const data;
 };
 
-const struct mnt_opt mnt_tmp = {
+#define MNT_TMP_DATA "size=4m,mode=700"
+
+static const struct mnt_opt mnt_tmp = {
 	.type = "tmpfs",
-	.data = "size=4m,mode=700",
+	.data = MNT_TMP_DATA,
 };
 
 static int mount_opt(const struct mnt_opt *const mnt, const char *const target)
@@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs)
 /* clang-format off */
 FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) {
 	/* clang-format on */
-	.mnt = mnt_tmp,
+	.mnt = {
+		.type = "tmpfs",
+		.data = MNT_TMP_DATA,
+	},
 	.file_path = file1_s1d1,
 };
 
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index ea5f727dd257..936cfc879f1d 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 #include <sys/socket.h>
+#include <sys/syscall.h>
 #include <sys/un.h>
 
 #include "common.h"
@@ -54,6 +55,11 @@ struct service_fixture {
 	};
 };
 
+static pid_t sys_gettid(void)
+{
+	return syscall(__NR_gettid);
+}
+
 static int set_service(struct service_fixture *const srv,
 		       const struct protocol_variant prot,
 		       const unsigned short index)
@@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv,
 	case AF_UNIX:
 		srv->unix_addr.sun_family = prot.domain;
 		sprintf(srv->unix_addr.sun_path,
-			"_selftests-landlock-net-tid%d-index%d", gettid(),
+			"_selftests-landlock-net-tid%d-index%d", sys_gettid(),
 			index);
 		srv->unix_addr_len = SUN_LEN(&srv->unix_addr);
 		srv->unix_addr.sun_path[0] = '\0';
@@ -101,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata)
 {
 	set_cap(_metadata, CAP_SYS_ADMIN);
 	ASSERT_EQ(0, unshare(CLONE_NEWNET));
-	ASSERT_EQ(0, system("ip link set dev lo up"));
 	clear_cap(_metadata, CAP_SYS_ADMIN);
+
+	set_ambient_cap(_metadata, CAP_NET_ADMIN);
+	ASSERT_EQ(0, system("ip link set dev lo up"));
+	clear_ambient_cap(_metadata, CAP_NET_ADMIN);
 }
 
 static bool is_restricted(const struct protocol_variant *const prot,
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index aa646e0661f3..286ce0ee102b 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -58,7 +58,8 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
-all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \
+	$(if $(TEST_GEN_MODS_DIR),gen_mods_dir)
 
 define RUN_TESTS
 	BASE_DIR="$(selfdir)";			\
@@ -71,8 +72,8 @@ endef
 
 run_tests: all
 ifdef building_out_of_srctree
-	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
-		rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
+	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)$(TEST_GEN_MODS_DIR)" != "X" ]; then \
+		rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(TEST_GEN_MODS_DIR) $(OUTPUT); \
 	fi
 	@if [ "X$(TEST_PROGS)" != "X" ]; then \
 		$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \
@@ -84,11 +85,22 @@ else
 	@$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
 endif
 
+gen_mods_dir:
+	$(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR)
+
+clean_mods_dir:
+	$(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR) clean
+
 define INSTALL_SINGLE_RULE
 	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
 	$(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/)
 endef
 
+define INSTALL_MODS_RULE
+	$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)/$(INSTALL_LIST))
+	$(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST)/*.ko $(INSTALL_PATH)/$(INSTALL_LIST))
+endef
+
 define INSTALL_RULE
 	$(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
@@ -97,6 +109,7 @@ define INSTALL_RULE
 	$(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE)
 	$(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE)
+	$(eval INSTALL_LIST = $(notdir $(TEST_GEN_MODS_DIR))) $(INSTALL_MODS_RULE)
 	$(eval INSTALL_LIST = $(wildcard config settings)) $(INSTALL_SINGLE_RULE)
 endef
 
@@ -122,7 +135,7 @@ define CLEAN
 	$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
 endef
 
-clean:
+clean: $(if $(TEST_GEN_MODS_DIR),clean_mods_dir)
 	$(CLEAN)
 
 # Enables to extend CFLAGS and LDFLAGS from command line, e.g.
@@ -153,4 +166,4 @@ $(OUTPUT)/%:%.S
 	$(LINK.S) $^ $(LDLIBS) -o $@
 endif
 
-.PHONY: run_tests all clean install emit_tests
+.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir
diff --git a/tools/testing/selftests/livepatch/.gitignore b/tools/testing/selftests/livepatch/.gitignore
new file mode 100644
index 000000000000..f1e9c2a20e99
--- /dev/null
+++ b/tools/testing/selftests/livepatch/.gitignore
@@ -0,0 +1 @@
+test_klp-call_getpid
diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile
index 02fadc9d55e0..35418a4790be 100644
--- a/tools/testing/selftests/livepatch/Makefile
+++ b/tools/testing/selftests/livepatch/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+TEST_GEN_FILES := test_klp-call_getpid
+TEST_GEN_MODS_DIR := test_modules
 TEST_PROGS_EXTENDED := functions.sh
 TEST_PROGS := \
 	test-livepatch.sh \
@@ -7,7 +9,8 @@ TEST_PROGS := \
 	test-shadow-vars.sh \
 	test-state.sh \
 	test-ftrace.sh \
-	test-sysfs.sh
+	test-sysfs.sh \
+	test-syscall.sh
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/livepatch/README b/tools/testing/selftests/livepatch/README
index 0942dd5826f8..d2035dd64a2b 100644
--- a/tools/testing/selftests/livepatch/README
+++ b/tools/testing/selftests/livepatch/README
@@ -13,23 +13,36 @@ the message buffer for only the duration of each individual test.)
 Config
 ------
 
-Set these config options and their prerequisites:
+Set CONFIG_LIVEPATCH=y option and it's prerequisites.
 
-CONFIG_LIVEPATCH=y
-CONFIG_TEST_LIVEPATCH=m
 
+Building the tests
+------------------
+
+To only build the tests without running them, run:
+
+  % make -C tools/testing/selftests/livepatch
+
+The command above will compile all test modules and test programs, making them
+ready to be packaged if so desired.
 
 Running the tests
 -----------------
 
-Test kernel modules are built as part of lib/ (make modules) and need to
-be installed (make modules_install) as the test scripts will modprobe
-them.
+Test kernel modules are built before running the livepatch selftests.  The
+modules are located under test_modules directory, and are built as out-of-tree
+modules.  This is specially useful since the same sources can be built and
+tested on systems with different kABI, ensuring they the tests are backwards
+compatible.  The modules will be loaded by the test scripts using insmod.
 
 To run the livepatch selftests, from the top of the kernel source tree:
 
   % make -C tools/testing/selftests TARGETS=livepatch run_tests
 
+or
+
+  % make kselftest TARGETS=livepatch
+
 
 Adding tests
 ------------
diff --git a/tools/testing/selftests/livepatch/config b/tools/testing/selftests/livepatch/config
index ad23100cb27c..e88bf518a23a 100644
--- a/tools/testing/selftests/livepatch/config
+++ b/tools/testing/selftests/livepatch/config
@@ -1,3 +1,2 @@
 CONFIG_LIVEPATCH=y
 CONFIG_DYNAMIC_DEBUG=y
-CONFIG_TEST_LIVEPATCH=m
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index c8416c54b463..fc4c6a016d38 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -34,6 +34,18 @@ function is_root() {
 	fi
 }
 
+# Check if we can compile the modules before loading them
+function has_kdir() {
+	if [ -z "$KDIR" ]; then
+		KDIR="/lib/modules/$(uname -r)/build"
+	fi
+
+	if [ ! -d "$KDIR" ]; then
+		echo "skip all tests: KDIR ($KDIR) not available to compile modules."
+		exit $ksft_skip
+	fi
+}
+
 # die(msg) - game over, man
 #	msg - dying words
 function die() {
@@ -42,17 +54,6 @@ function die() {
 	exit 1
 }
 
-# save existing dmesg so we can detect new content
-function save_dmesg() {
-	SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX)
-	dmesg > "$SAVED_DMESG"
-}
-
-# cleanup temporary dmesg file from save_dmesg()
-function cleanup_dmesg_file() {
-	rm -f "$SAVED_DMESG"
-}
-
 function push_config() {
 	DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
 			awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
@@ -99,7 +100,6 @@ function set_ftrace_enabled() {
 
 function cleanup() {
 	pop_config
-	cleanup_dmesg_file
 }
 
 # setup_config - save the current config and set a script exit trap that
@@ -108,6 +108,7 @@ function cleanup() {
 #		 the ftrace_enabled sysctl.
 function setup_config() {
 	is_root
+	has_kdir
 	push_config
 	set_dynamic_debug
 	set_ftrace_enabled 1
@@ -127,16 +128,14 @@ function loop_until() {
 	done
 }
 
-function assert_mod() {
-	local mod="$1"
-
-	modprobe --dry-run "$mod" &>/dev/null
-}
-
 function is_livepatch_mod() {
 	local mod="$1"
 
-	if [[ $(modinfo "$mod" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then
+	if [[ ! -f "test_modules/$mod.ko" ]]; then
+		die "Can't find \"test_modules/$mod.ko\", try \"make\""
+	fi
+
+	if [[ $(modinfo "test_modules/$mod.ko" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then
 		return 0
 	fi
 
@@ -146,9 +145,9 @@ function is_livepatch_mod() {
 function __load_mod() {
 	local mod="$1"; shift
 
-	local msg="% modprobe $mod $*"
+	local msg="% insmod test_modules/$mod.ko $*"
 	log "${msg%% }"
-	ret=$(modprobe "$mod" "$@" 2>&1)
+	ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1)
 	if [[ "$ret" != "" ]]; then
 		die "$ret"
 	fi
@@ -161,13 +160,10 @@ function __load_mod() {
 
 # load_mod(modname, params) - load a kernel module
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_mod() {
 	local mod="$1"; shift
 
-	assert_mod "$mod" ||
-		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
-
 	is_livepatch_mod "$mod" &&
 		die "use load_lp() to load the livepatch module $mod"
 
@@ -177,13 +173,10 @@ function load_mod() {
 # load_lp_nowait(modname, params) - load a kernel module with a livepatch
 #			but do not wait on until the transition finishes
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_lp_nowait() {
 	local mod="$1"; shift
 
-	assert_mod "$mod" ||
-		skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
-
 	is_livepatch_mod "$mod" ||
 		die "module $mod is not a livepatch"
 
@@ -196,7 +189,7 @@ function load_lp_nowait() {
 
 # load_lp(modname, params) - load a kernel module with a livepatch
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_lp() {
 	local mod="$1"; shift
 
@@ -209,13 +202,13 @@ function load_lp() {
 
 # load_failing_mod(modname, params) - load a kernel module, expect to fail
 #	modname - module name to load
-#	params  - module parameters to pass to modprobe
+#	params  - module parameters to pass to insmod
 function load_failing_mod() {
 	local mod="$1"; shift
 
-	local msg="% modprobe $mod $*"
+	local msg="% insmod test_modules/$mod.ko $*"
 	log "${msg%% }"
-	ret=$(modprobe "$mod" "$@" 2>&1)
+	ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1)
 	if [[ "$ret" == "" ]]; then
 		die "$mod unexpectedly loaded"
 	fi
@@ -280,7 +273,15 @@ function set_pre_patch_ret {
 function start_test {
 	local test="$1"
 
-	save_dmesg
+	# Dump something unique into the dmesg log, then stash the entry
+	# in LAST_DMESG.  The check_result() function will use it to
+	# find new kernel messages since the test started.
+	local last_dmesg_msg="livepatch kselftest timestamp: $(date --rfc-3339=ns)"
+	log "$last_dmesg_msg"
+	loop_until 'dmesg | grep -q "$last_dmesg_msg"' ||
+		die "buffer busy? can't find canary dmesg message: $last_dmesg_msg"
+	LAST_DMESG=$(dmesg | grep "$last_dmesg_msg")
+
 	echo -n "TEST: $test ... "
 	log "===== TEST: $test ====="
 }
@@ -291,23 +292,24 @@ function check_result {
 	local expect="$*"
 	local result
 
-	# Note: when comparing dmesg output, the kernel log timestamps
-	# help differentiate repeated testing runs.  Remove them with a
-	# post-comparison sed filter.
-
-	result=$(dmesg | comm --nocheck-order -13 "$SAVED_DMESG" - | \
+	# Test results include any new dmesg entry since LAST_DMESG, then:
+	# - include lines matching keywords
+	# - exclude lines matching keywords
+	# - filter out dmesg timestamp prefixes
+	result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \
 		 grep -e 'livepatch:' -e 'test_klp' | \
 		 grep -v '\(tainting\|taints\) kernel' | \
 		 sed 's/^\[[ 0-9.]*\] //')
 
 	if [[ "$expect" == "$result" ]] ; then
 		echo "ok"
+	elif [[ "$result" == "" ]] ; then
+		echo -e "not ok\n\nbuffer overrun? can't find canary dmesg entry: $LAST_DMESG\n"
+		die "livepatch kselftest(s) failed"
 	else
 		echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n"
 		die "livepatch kselftest(s) failed"
 	fi
-
-	cleanup_dmesg_file
 }
 
 # check_sysfs_rights(modname, rel_path, expected_rights) - check sysfs
diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh
index 90b26dbb2626..32b150e25b10 100755
--- a/tools/testing/selftests/livepatch/test-callbacks.sh
+++ b/tools/testing/selftests/livepatch/test-callbacks.sh
@@ -34,9 +34,9 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -81,7 +81,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -89,7 +89,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -129,9 +129,9 @@ unload_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -177,7 +177,7 @@ unload_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -185,7 +185,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -219,7 +219,7 @@ load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -254,9 +254,9 @@ load_mod $MOD_TARGET
 load_failing_mod $MOD_LIVEPATCH pre_patch_ret=-19
 unload_mod $MOD_TARGET
 
-check_result "% modprobe $MOD_TARGET
+check_result "% insmod test_modules/$MOD_TARGET.ko
 $MOD_TARGET: ${MOD_TARGET}_init
-% modprobe $MOD_LIVEPATCH pre_patch_ret=-19
+% insmod test_modules/$MOD_LIVEPATCH.ko pre_patch_ret=-19
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 test_klp_callbacks_demo: pre_patch_callback: vmlinux
@@ -265,7 +265,7 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch
 livepatch: '$MOD_LIVEPATCH': completing unpatching transition
 livepatch: '$MOD_LIVEPATCH': unpatching complete
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': No such device
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: No such device
 % rmmod $MOD_TARGET
 $MOD_TARGET: ${MOD_TARGET}_exit"
 
@@ -295,7 +295,7 @@ load_failing_mod $MOD_TARGET
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -304,12 +304,12 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
 % echo -19 > /sys/module/$MOD_LIVEPATCH/parameters/pre_patch_ret
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 livepatch: pre-patch callback failed for object '$MOD_TARGET'
 livepatch: patch '$MOD_LIVEPATCH' failed for module '$MOD_TARGET', refusing to load module '$MOD_TARGET'
-modprobe: ERROR: could not insert '$MOD_TARGET': No such device
+insmod: ERROR: could not insert module test_modules/$MOD_TARGET.ko: No such device
 % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled
 livepatch: '$MOD_LIVEPATCH': initializing unpatching transition
 $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux
@@ -340,11 +340,11 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY block_transition=N
+check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=N
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
 $MOD_TARGET_BUSY: busymod_work_func enter
 $MOD_TARGET_BUSY: busymod_work_func exit
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -354,7 +354,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
@@ -421,16 +421,16 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 unload_mod $MOD_TARGET_BUSY
 
-check_result "% modprobe $MOD_TARGET_BUSY block_transition=Y
+check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=Y
 $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init
 $MOD_TARGET_BUSY: busymod_work_func enter
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state
 livepatch: '$MOD_LIVEPATCH': starting patching transition
-% modprobe $MOD_TARGET
+% insmod test_modules/$MOD_TARGET.ko
 livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET'
 $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init
 $MOD_TARGET: ${MOD_TARGET}_init
@@ -467,7 +467,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -475,7 +475,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -523,7 +523,7 @@ disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -531,7 +531,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2 replace=1
+% insmod test_modules/$MOD_LIVEPATCH2.ko replace=1
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
diff --git a/tools/testing/selftests/livepatch/test-ftrace.sh b/tools/testing/selftests/livepatch/test-ftrace.sh
index 825540a5194d..730218bce99c 100755
--- a/tools/testing/selftests/livepatch/test-ftrace.sh
+++ b/tools/testing/selftests/livepatch/test-ftrace.sh
@@ -35,7 +35,7 @@ disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
 check_result "livepatch: kernel.ftrace_enabled = 0
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: failed to register ftrace handler for function 'cmdline_proc_show' (-16)
@@ -44,9 +44,9 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch
 livepatch: '$MOD_LIVEPATCH': completing unpatching transition
 livepatch: '$MOD_LIVEPATCH': unpatching complete
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Device or resource busy
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Device or resource busy
 livepatch: kernel.ftrace_enabled = 1
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
diff --git a/tools/testing/selftests/livepatch/test-livepatch.sh b/tools/testing/selftests/livepatch/test-livepatch.sh
index 5fe79ac34be1..e3455a6b1158 100755
--- a/tools/testing/selftests/livepatch/test-livepatch.sh
+++ b/tools/testing/selftests/livepatch/test-livepatch.sh
@@ -31,7 +31,7 @@ if [[ "$(cat /proc/cmdline)" == "$MOD_LIVEPATCH: this has been live patched" ]]
 	die "livepatch kselftest(s) failed"
 fi
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
@@ -75,14 +75,14 @@ unload_lp $MOD_LIVEPATCH
 grep 'live patched' /proc/cmdline > /dev/kmsg
 grep 'live patched' /proc/meminfo > /dev/kmsg
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 livepatch: '$MOD_LIVEPATCH': patching complete
 $MOD_LIVEPATCH: this has been live patched
-% modprobe $MOD_REPLACE replace=0
+% insmod test_modules/$MOD_REPLACE.ko replace=0
 livepatch: enabling patch '$MOD_REPLACE'
 livepatch: '$MOD_REPLACE': initializing patching transition
 livepatch: '$MOD_REPLACE': starting patching transition
@@ -135,14 +135,14 @@ unload_lp $MOD_REPLACE
 grep 'live patched' /proc/cmdline > /dev/kmsg
 grep 'live patched' /proc/meminfo > /dev/kmsg
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
 livepatch: '$MOD_LIVEPATCH': completing patching transition
 livepatch: '$MOD_LIVEPATCH': patching complete
 $MOD_LIVEPATCH: this has been live patched
-% modprobe $MOD_REPLACE replace=1
+% insmod test_modules/$MOD_REPLACE.ko replace=1
 livepatch: enabling patch '$MOD_REPLACE'
 livepatch: '$MOD_REPLACE': initializing patching transition
 livepatch: '$MOD_REPLACE': starting patching transition
diff --git a/tools/testing/selftests/livepatch/test-shadow-vars.sh b/tools/testing/selftests/livepatch/test-shadow-vars.sh
index e04cb354f56b..1218c155bffe 100755
--- a/tools/testing/selftests/livepatch/test-shadow-vars.sh
+++ b/tools/testing/selftests/livepatch/test-shadow-vars.sh
@@ -16,7 +16,7 @@ start_test "basic shadow variable API"
 load_mod $MOD_TEST
 unload_mod $MOD_TEST
 
-check_result "% modprobe $MOD_TEST
+check_result "% insmod test_modules/$MOD_TEST.ko
 $MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR0
 $MOD_TEST:   got expected NULL result
 $MOD_TEST: shadow_ctor: PTR3 -> PTR2
diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh
index 38656721c958..10a52ac06185 100755
--- a/tools/testing/selftests/livepatch/test-state.sh
+++ b/tools/testing/selftests/livepatch/test-state.sh
@@ -19,7 +19,7 @@ load_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -51,7 +51,7 @@ unload_lp $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 $MOD_LIVEPATCH: pre_patch_callback: vmlinux
@@ -61,7 +61,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition
 $MOD_LIVEPATCH: post_patch_callback: vmlinux
 $MOD_LIVEPATCH: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH': patching complete
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -96,7 +96,7 @@ disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH3
 
-check_result "% modprobe $MOD_LIVEPATCH2
+check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -106,7 +106,7 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition
 $MOD_LIVEPATCH2: post_patch_callback: vmlinux
 $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH2': patching complete
-% modprobe $MOD_LIVEPATCH3
+% insmod test_modules/$MOD_LIVEPATCH3.ko
 livepatch: enabling patch '$MOD_LIVEPATCH3'
 livepatch: '$MOD_LIVEPATCH3': initializing patching transition
 $MOD_LIVEPATCH3: pre_patch_callback: vmlinux
@@ -117,7 +117,7 @@ $MOD_LIVEPATCH3: post_patch_callback: vmlinux
 $MOD_LIVEPATCH3: fix_console_loglevel: taking over the console_loglevel change
 livepatch: '$MOD_LIVEPATCH3': patching complete
 % rmmod $MOD_LIVEPATCH2
-% modprobe $MOD_LIVEPATCH2
+% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -149,7 +149,7 @@ load_failing_mod $MOD_LIVEPATCH
 disable_lp $MOD_LIVEPATCH2
 unload_lp $MOD_LIVEPATCH2
 
-check_result "% modprobe $MOD_LIVEPATCH2
+check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko
 livepatch: enabling patch '$MOD_LIVEPATCH2'
 livepatch: '$MOD_LIVEPATCH2': initializing patching transition
 $MOD_LIVEPATCH2: pre_patch_callback: vmlinux
@@ -159,9 +159,9 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition
 $MOD_LIVEPATCH2: post_patch_callback: vmlinux
 $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel
 livepatch: '$MOD_LIVEPATCH2': patching complete
-% modprobe $MOD_LIVEPATCH
+% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: Livepatch patch ($MOD_LIVEPATCH) is not compatible with the already installed livepatches.
-modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Invalid argument
+insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Invalid parameters
 % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled
 livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition
 $MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux
diff --git a/tools/testing/selftests/livepatch/test-syscall.sh b/tools/testing/selftests/livepatch/test-syscall.sh
new file mode 100755
index 000000000000..b76a881d4013
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test-syscall.sh
@@ -0,0 +1,53 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2023 SUSE
+# Author: Marcos Paulo de Souza <mpdesouza@suse.com>
+
+. $(dirname $0)/functions.sh
+
+MOD_SYSCALL=test_klp_syscall
+
+setup_config
+
+# - Start _NRPROC processes calling getpid and load a livepatch to patch the
+#   getpid syscall. Check if all the processes transitioned to the livepatched
+#   state.
+
+start_test "patch getpid syscall while being heavily hammered"
+
+for i in $(seq 1 $(getconf _NPROCESSORS_ONLN)); do
+	./test_klp-call_getpid &
+	pids[$i]="$!"
+done
+
+pid_list=$(echo ${pids[@]} | tr ' ' ',')
+load_lp $MOD_SYSCALL klp_pids=$pid_list
+
+# wait for all tasks to transition to patched state
+loop_until 'grep -q '^0$' /sys/kernel/test_klp_syscall/npids'
+
+pending_pids=$(cat /sys/kernel/test_klp_syscall/npids)
+log "$MOD_SYSCALL: Remaining not livepatched processes: $pending_pids"
+
+for pid in ${pids[@]}; do
+	kill $pid || true
+done
+
+disable_lp $MOD_SYSCALL
+unload_lp $MOD_SYSCALL
+
+check_result "% insmod test_modules/$MOD_SYSCALL.ko klp_pids=$pid_list
+livepatch: enabling patch '$MOD_SYSCALL'
+livepatch: '$MOD_SYSCALL': initializing patching transition
+livepatch: '$MOD_SYSCALL': starting patching transition
+livepatch: '$MOD_SYSCALL': completing patching transition
+livepatch: '$MOD_SYSCALL': patching complete
+$MOD_SYSCALL: Remaining not livepatched processes: 0
+% echo 0 > /sys/kernel/livepatch/$MOD_SYSCALL/enabled
+livepatch: '$MOD_SYSCALL': initializing unpatching transition
+livepatch: '$MOD_SYSCALL': starting unpatching transition
+livepatch: '$MOD_SYSCALL': completing unpatching transition
+livepatch: '$MOD_SYSCALL': unpatching complete
+% rmmod $MOD_SYSCALL"
+
+exit 0
diff --git a/tools/testing/selftests/livepatch/test-sysfs.sh b/tools/testing/selftests/livepatch/test-sysfs.sh
index 7f76f280189a..6c646afa7395 100755
--- a/tools/testing/selftests/livepatch/test-sysfs.sh
+++ b/tools/testing/selftests/livepatch/test-sysfs.sh
@@ -27,7 +27,7 @@ disable_lp $MOD_LIVEPATCH
 
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe $MOD_LIVEPATCH
+check_result "% insmod test_modules/$MOD_LIVEPATCH.ko
 livepatch: enabling patch '$MOD_LIVEPATCH'
 livepatch: '$MOD_LIVEPATCH': initializing patching transition
 livepatch: '$MOD_LIVEPATCH': starting patching transition
@@ -56,7 +56,7 @@ check_sysfs_value  "$MOD_LIVEPATCH" "$MOD_TARGET/patched" "0"
 disable_lp $MOD_LIVEPATCH
 unload_lp $MOD_LIVEPATCH
 
-check_result "% modprobe test_klp_callbacks_demo
+check_result "% insmod test_modules/test_klp_callbacks_demo.ko
 livepatch: enabling patch 'test_klp_callbacks_demo'
 livepatch: 'test_klp_callbacks_demo': initializing patching transition
 test_klp_callbacks_demo: pre_patch_callback: vmlinux
@@ -64,7 +64,7 @@ livepatch: 'test_klp_callbacks_demo': starting patching transition
 livepatch: 'test_klp_callbacks_demo': completing patching transition
 test_klp_callbacks_demo: post_patch_callback: vmlinux
 livepatch: 'test_klp_callbacks_demo': patching complete
-% modprobe test_klp_callbacks_mod
+% insmod test_modules/test_klp_callbacks_mod.ko
 livepatch: applying patch 'test_klp_callbacks_demo' to loading module 'test_klp_callbacks_mod'
 test_klp_callbacks_demo: pre_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init
 test_klp_callbacks_demo: post_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init
diff --git a/tools/testing/selftests/livepatch/test_klp-call_getpid.c b/tools/testing/selftests/livepatch/test_klp-call_getpid.c
new file mode 100644
index 000000000000..ce321a2d7308
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_klp-call_getpid.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 SUSE
+ * Authors: Libor Pechacek <lpechacek@suse.cz>
+ *          Marcos Paulo de Souza <mpdesouza@suse.com>
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <signal.h>
+
+static int stop;
+static int sig_int;
+
+void hup_handler(int signum)
+{
+	stop = 1;
+}
+
+void int_handler(int signum)
+{
+	stop = 1;
+	sig_int = 1;
+}
+
+int main(int argc, char *argv[])
+{
+	long count = 0;
+
+	signal(SIGHUP, &hup_handler);
+	signal(SIGINT, &int_handler);
+
+	while (!stop) {
+		(void)syscall(SYS_getpid);
+		count++;
+	}
+
+	if (sig_int)
+		printf("%ld iterations done\n", count);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile
new file mode 100644
index 000000000000..e6e638c4bcba
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_modules/Makefile
@@ -0,0 +1,26 @@
+TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= /lib/modules/$(shell uname -r)/build
+
+obj-m += test_klp_atomic_replace.o \
+	test_klp_callbacks_busy.o \
+	test_klp_callbacks_demo.o \
+	test_klp_callbacks_demo2.o \
+	test_klp_callbacks_mod.o \
+	test_klp_livepatch.o \
+	test_klp_state.o \
+	test_klp_state2.o \
+	test_klp_state3.o \
+	test_klp_shadow_vars.o \
+	test_klp_syscall.o
+
+# Ensure that KDIR exists, otherwise skip the compilation
+modules:
+ifneq ("$(wildcard $(KDIR))", "")
+	$(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR)
+endif
+
+# Ensure that KDIR exists, otherwise skip the clean target
+clean:
+ifneq ("$(wildcard $(KDIR))", "")
+	$(Q)$(MAKE) -C $(KDIR) clean KBUILD_EXTMOD=$(TESTMODS_DIR)
+endif
diff --git a/lib/livepatch/test_klp_atomic_replace.c b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c
index 5af7093ca00c..5af7093ca00c 100644
--- a/lib/livepatch/test_klp_atomic_replace.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c
diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c
index 133929e0ce8f..133929e0ce8f 100644
--- a/lib/livepatch/test_klp_callbacks_busy.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c
diff --git a/lib/livepatch/test_klp_callbacks_demo.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c
index 3fd8fe1cd1cc..3fd8fe1cd1cc 100644
--- a/lib/livepatch/test_klp_callbacks_demo.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c
diff --git a/lib/livepatch/test_klp_callbacks_demo2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c
index 5417573e80af..5417573e80af 100644
--- a/lib/livepatch/test_klp_callbacks_demo2.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c
diff --git a/lib/livepatch/test_klp_callbacks_mod.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c
index 8fbe645b1c2c..8fbe645b1c2c 100644
--- a/lib/livepatch/test_klp_callbacks_mod.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c
diff --git a/lib/livepatch/test_klp_livepatch.c b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c
index aff08199de71..aff08199de71 100644
--- a/lib/livepatch/test_klp_livepatch.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c
diff --git a/lib/livepatch/test_klp_shadow_vars.c b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c
index b99116490858..b99116490858 100644
--- a/lib/livepatch/test_klp_shadow_vars.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c
diff --git a/lib/livepatch/test_klp_state.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c
index 57a4253acb01..57a4253acb01 100644
--- a/lib/livepatch/test_klp_state.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c
diff --git a/lib/livepatch/test_klp_state2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c
index c978ea4d5e67..c978ea4d5e67 100644
--- a/lib/livepatch/test_klp_state2.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c
diff --git a/lib/livepatch/test_klp_state3.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c
index 9226579d10c5..9226579d10c5 100644
--- a/lib/livepatch/test_klp_state3.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c
diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
new file mode 100644
index 000000000000..dd802783ea84
--- /dev/null
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017-2023 SUSE
+ * Authors: Libor Pechacek <lpechacek@suse.cz>
+ *          Nicolai Stange <nstange@suse.de>
+ *          Marcos Paulo de Souza <mpdesouza@suse.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/livepatch.h>
+
+#if defined(__x86_64__)
+#define FN_PREFIX __x64_
+#elif defined(__s390x__)
+#define FN_PREFIX __s390x_
+#elif defined(__aarch64__)
+#define FN_PREFIX __arm64_
+#else
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER */
+#define FN_PREFIX
+#endif
+
+/* Protects klp_pids */
+static DEFINE_MUTEX(kpid_mutex);
+
+static unsigned int npids, npids_pending;
+static int klp_pids[NR_CPUS];
+module_param_array(klp_pids, int, &npids_pending, 0);
+MODULE_PARM_DESC(klp_pids, "Array of pids to be transitioned to livepatched state.");
+
+static ssize_t npids_show(struct kobject *kobj, struct kobj_attribute *attr,
+			  char *buf)
+{
+	return sprintf(buf, "%u\n", npids_pending);
+}
+
+static struct kobj_attribute klp_attr = __ATTR_RO(npids);
+static struct kobject *klp_kobj;
+
+static asmlinkage long lp_sys_getpid(void)
+{
+	int i;
+
+	mutex_lock(&kpid_mutex);
+	if (npids_pending > 0) {
+		for (i = 0; i < npids; i++) {
+			if (current->pid == klp_pids[i]) {
+				klp_pids[i] = 0;
+				npids_pending--;
+				break;
+			}
+		}
+	}
+	mutex_unlock(&kpid_mutex);
+
+	return task_tgid_vnr(current);
+}
+
+static struct klp_func vmlinux_funcs[] = {
+	{
+		.old_name = __stringify(FN_PREFIX) "sys_getpid",
+		.new_func = lp_sys_getpid,
+	}, {}
+};
+
+static struct klp_object objs[] = {
+	{
+		/* name being NULL means vmlinux */
+		.funcs = vmlinux_funcs,
+	}, {}
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+};
+
+static int livepatch_init(void)
+{
+	int ret;
+
+	klp_kobj = kobject_create_and_add("test_klp_syscall", kernel_kobj);
+	if (!klp_kobj)
+		return -ENOMEM;
+
+	ret = sysfs_create_file(klp_kobj, &klp_attr.attr);
+	if (ret) {
+		kobject_put(klp_kobj);
+		return ret;
+	}
+
+	/*
+	 * Save the number pids to transition to livepatched state before the
+	 * number of pending pids is decremented.
+	 */
+	npids = npids_pending;
+
+	return klp_enable_patch(&patch);
+}
+
+static void livepatch_exit(void)
+{
+	kobject_put(klp_kobj);
+}
+
+module_init(livepatch_init);
+module_exit(livepatch_exit);
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");
+MODULE_AUTHOR("Libor Pechacek <lpechacek@suse.cz>");
+MODULE_AUTHOR("Nicolai Stange <nstange@suse.de>");
+MODULE_AUTHOR("Marcos Paulo de Souza <mpdesouza@suse.com>");
+MODULE_DESCRIPTION("Livepatch test: syscall transition");
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 0899019a7fcb..e14bdd4455f2 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Kselftest framework requirement - SKIP code is 4.
diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index 380b691d3eb9..b748c48908d9 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot,
 	if (map_ptr_orig == MAP_FAILED)
 		err(2, "initial mmap");
 
-	if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE))
+	if (madvise(map_ptr, len, MADV_HUGEPAGE))
 		err(2, "MADV_HUGEPAGE");
 
 	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c
index 193281560b61..86e8f2048a40 100644
--- a/tools/testing/selftests/mm/map_hugetlb.c
+++ b/tools/testing/selftests/mm/map_hugetlb.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <fcntl.h>
+#include "vm_util.h"
 
 #define LENGTH (256UL*1024*1024)
 #define PROTECTION (PROT_READ | PROT_WRITE)
@@ -58,10 +59,16 @@ int main(int argc, char **argv)
 {
 	void *addr;
 	int ret;
+	size_t hugepage_size;
 	size_t length = LENGTH;
 	int flags = FLAGS;
 	int shift = 0;
 
+	hugepage_size = default_huge_page_size();
+	/* munmap with fail if the length is not page aligned */
+	if (hugepage_size > length)
+		length = hugepage_size;
+
 	if (argc > 1)
 		length = atol(argv[1]) << 20;
 	if (argc > 2) {
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 1d4c1589c305..2f8b991f78cb 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -360,7 +360,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char pattern_seed)
 {
 	void *addr, *src_addr, *dest_addr, *dest_preamble_addr;
-	unsigned long long i;
+	int d;
+	unsigned long long t;
 	struct timespec t_start = {0, 0}, t_end = {0, 0};
 	long long  start_ns, end_ns, align_mask, ret, offset;
 	unsigned long long threshold;
@@ -378,8 +379,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Set byte pattern for source block. */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++)
-		memset((char *) src_addr + i, (char) rand(), 1);
+	for (t = 0; t < threshold; t++)
+		memset((char *) src_addr + t, (char) rand(), 1);
 
 	/* Mask to zero out lower bits of address for alignment */
 	align_mask = ~(c.dest_alignment - 1);
@@ -420,8 +421,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 		/* Set byte pattern for the dest preamble block. */
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++)
-			memset((char *) dest_preamble_addr + i, (char) rand(), 1);
+		for (d = 0; d < c.dest_preamble_size; d++)
+			memset((char *) dest_preamble_addr + d, (char) rand(), 1);
 	}
 
 	clock_gettime(CLOCK_MONOTONIC, &t_start);
@@ -437,14 +438,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 
 	/* Verify byte pattern after remapping */
 	srand(pattern_seed);
-	for (i = 0; i < threshold; i++) {
+	for (t = 0; t < threshold; t++) {
 		char c = (char) rand();
 
-		if (((char *) dest_addr)[i] != c) {
+		if (((char *) dest_addr)[t] != c) {
 			ksft_print_msg("Data after remap doesn't match at offset %llu\n",
-				       i);
+				       t);
 			ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					((char *) dest_addr)[i] & 0xff);
+					((char *) dest_addr)[t] & 0xff);
 			ret = -1;
 			goto clean_up_dest;
 		}
@@ -453,14 +454,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
 	/* Verify the dest preamble byte pattern after remapping */
 	if (c.dest_preamble_size) {
 		srand(pattern_seed);
-		for (i = 0; i < c.dest_preamble_size; i++) {
+		for (d = 0; d < c.dest_preamble_size; d++) {
 			char c = (char) rand();
 
-			if (((char *) dest_preamble_addr)[i] != c) {
+			if (((char *) dest_preamble_addr)[d] != c) {
 				ksft_print_msg("Preamble data after remap doesn't match at offset %d\n",
-					       i);
+					       d);
 				ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
-					       ((char *) dest_preamble_addr)[i] & 0xff);
+					       ((char *) dest_preamble_addr)[d] & 0xff);
 				ret = -1;
 				goto clean_up_dest;
 			}
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index cce90a10515a..2b9f8cc52639 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1517,6 +1517,12 @@ int main(int argc, char *argv[])
 				continue;
 
 			uffd_test_start("%s on %s", test->name, mem_type->name);
+			if ((mem_type->mem_flag == MEM_HUGETLB ||
+			    mem_type->mem_flag == MEM_HUGETLB_PRIVATE) &&
+			    (default_huge_page_size() == 0)) {
+				uffd_test_skip("huge page size is 0, feature missing?");
+				continue;
+			}
 			if (!uffd_feature_supported(test)) {
 				uffd_test_skip("feature missing");
 				continue;
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 45cae7cab27e..a0a75f302904 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -29,9 +29,15 @@ check_supported_x86_64()
 	# See man 1 gzip under '-f'.
 	local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
 
+	local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;}
+		else {print 1}; exit}' /proc/cpuinfo 2>/dev/null)
+
 	if [[ "${pg_table_levels}" -lt 5 ]]; then
 		echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
 		exit $ksft_skip
+	elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then
+		echo "$0: CPU does not have the necessary la57 flag to support page table level 5"
+		exit $ksft_skip
 	fi
 }
 
diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh
index 70a02301f4c2..3d2d2eb9d6ff 100755
--- a/tools/testing/selftests/mm/write_hugetlb_memory.sh
+++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 set -e
diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
index 50ed5d475dd1..bcf51d785a37 100644
--- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
+++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c
@@ -218,7 +218,7 @@ static bool move_mount_set_group_supported(void)
 	if (mount(NULL, SET_GROUP_FROM, NULL, MS_SHARED, 0))
 		return -1;
 
-	ret = syscall(SYS_move_mount, AT_FDCWD, SET_GROUP_FROM,
+	ret = syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_FROM,
 		      AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP);
 	umount2("/tmp", MNT_DETACH);
 
@@ -363,7 +363,7 @@ TEST_F(move_mount_set_group, complex_sharing_copying)
 		       CLONE_VM | CLONE_FILES); ASSERT_GT(pid, 0);
 	ASSERT_EQ(wait_for_pid(pid), 0);
 
-	ASSERT_EQ(syscall(SYS_move_mount, ca_from.mntfd, "",
+	ASSERT_EQ(syscall(__NR_move_mount, ca_from.mntfd, "",
 			  ca_to.mntfd, "", MOVE_MOUNT_SET_GROUP
 			  | MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH),
 		  0);
diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting
new file mode 100644
index 000000000000..a953c96aa16e
--- /dev/null
+++ b/tools/testing/selftests/mqueue/setting
@@ -0,0 +1 @@
+timeout=180
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 50818075e566..211753756bde 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -53,8 +53,7 @@ TEST_PROGS += bind_bhash.sh
 TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
-TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
-TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
+TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
@@ -84,6 +83,7 @@ TEST_PROGS += sctp_vrf.sh
 TEST_GEN_FILES += sctp_hello
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += nat6to4.o
+TEST_GEN_FILES += xdp_dummy.o
 TEST_GEN_FILES += ip_local_port_range
 TEST_GEN_FILES += bind_wildcard
 TEST_PROGS += test_vxlan_mdb.sh
@@ -95,6 +95,7 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
+TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
 include ../lib.mk
 
@@ -104,7 +105,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
 $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
-# Rules to generate bpf obj nat6to4.o
+# Rules to generate bpf objs
 CLANG ?= clang
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
@@ -139,7 +140,7 @@ endif
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
-$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
+$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS)
 	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index cde9a91c4797..2db9d15cd45f 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -122,7 +122,9 @@ do_netperf() {
 	local netns=$1
 
 	[ "$NF" = "6" ] && serip=$SERVER_IP6
-	ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
+
+	# use large write to be sure to generate big tcp packets
+	ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
 }
 
 do_test() {
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index f30bd57d5e38..8bc23fb4c82b 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -89,7 +89,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "TCLASS $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
@@ -126,7 +126,7 @@ for ovr in setsock cmsg both diff; do
 	check_result $? 0 "HOPLIMIT $prot $ovr - pass"
 
 	while [ -d /proc/$BG ]; do
-	    $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+	    $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
 	done
 
 	tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 19ff75051660..5e4390cac17e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -19,17 +19,27 @@ CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
+CONFIG_GENEVE=m
 CONFIG_IFB=y
 CONFIG_INET_DIAG=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_NET_FOU=y
+CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_IPV6_SIT=y
+CONFIG_IP_DCCP=m
 CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_RAW=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_L2TP_ETH=m
@@ -45,16 +55,26 @@ CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
+CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_MATCHALL=m
 CONFIG_NET_CLS_U32=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
+CONFIG_NET_IPIP=y
 CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NF_FLOW_TABLE=m
 CONFIG_PSAMPLE=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
@@ -63,7 +83,6 @@ CONFIG_TLS=m
 CONFIG_TRACEPOINTS=y
 CONFIG_NET_DROP_MONITOR=m
 CONFIG_NETDEVSIM=m
-CONFIG_NET_FOU=m
 CONFIG_MPLS_ROUTING=m
 CONFIG_MPLS_IPTUNNEL=m
 CONFIG_NET_SCH_INGRESS=m
@@ -80,3 +99,4 @@ CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
 CONFIG_XFRM_INTERFACE=m
+CONFIG_XFRM_USER=m
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 452693514be4..4de92632f483 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
 	vxlan_symmetric_ipv6.sh \
 	vxlan_symmetric.sh
 
-TEST_PROGS_EXTENDED := devlink_lib.sh \
+TEST_FILES := devlink_lib.sh \
 	ethtool_lib.sh \
 	fib_offload_lib.sh \
 	forwarding.config.sample \
diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
index 9af9f6964808..c62331b2e006 100755
--- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
@@ -327,10 +327,10 @@ locked_port_mab_redirect()
 	RET=0
 	check_port_mab_support || return 0
 
-	bridge link set dev $swp1 learning on locked on mab on
 	tc qdisc add dev $swp1 clsact
 	tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \
 		action mirred egress redirect dev $swp2
+	bridge link set dev $swp1 learning on locked on mab on
 
 	ping_do $h1 192.0.2.2
 	check_err $? "Ping did not work with redirection"
@@ -349,8 +349,8 @@ locked_port_mab_redirect()
 	check_err $? "Locked entry not created after deleting filter"
 
 	bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master
-	tc qdisc del dev $swp1 clsact
 	bridge link set dev $swp1 learning off locked off mab off
+	tc qdisc del dev $swp1 clsact
 
 	log_test "Locked port MAB redirect"
 }
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index 61348f71728c..d9d587454d20 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -329,7 +329,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) \"permanent\" entry has a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_err $? "\"permanent\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -346,7 +346,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_err $? "\"blocked\" source entry has a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -363,7 +363,7 @@ __cfg_test_port_ip_star_g()
 
 	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
 	check_err $? "(*, G) INCLUDE entry has a pending group timer"
-	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+	bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
 	check_fail $? "Source entry does not have a pending source timer"
 
 	bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -1252,14 +1252,17 @@ fwd_test()
 	echo
 	log_info "# Forwarding tests"
 
+	# Set the Max Response Delay to 100 centiseconds (1 second) so that the
+	# bridge will start forwarding according to its MDB soon after a
+	# multicast querier is enabled.
+	ip link set dev br0 type bridge mcast_query_response_interval 100
+
 	# Forwarding according to MDB entries only takes place when the bridge
 	# detects that there is a valid querier in the network. Set the bridge
 	# as the querier and assign it a valid IPv6 link-local address to be
 	# used as the source address for MLD queries.
 	ip -6 address add fe80::1/64 nodad dev br0
 	ip link set dev br0 type bridge mcast_querier 1
-	# Wait the default Query Response Interval (10 seconds) for the bridge
-	# to determine that there are no other queriers in the network.
 	sleep 10
 
 	fwd_test_host
@@ -1267,6 +1270,7 @@ fwd_test()
 
 	ip link set dev br0 type bridge mcast_querier 0
 	ip -6 address del fe80::1/64 dev br0
+	ip link set dev br0 type bridge mcast_query_response_interval 1000
 }
 
 ctrl_igmpv3_is_in_test()
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index b0f5e55d2d0b..589629636502 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -235,9 +235,6 @@ mirred_egress_to_ingress_tcp_test()
 	check_err $? "didn't mirred redirect ICMP"
 	tc_check_packets "dev $h1 ingress" 102 10
 	check_err $? "didn't drop mirred ICMP"
-	local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits)
-	test ${overlimits} = 10
-	check_err $? "wrong overlimits, expected 10 got ${overlimits}"
 
 	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
 	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
index 20a7cb7222b8..c2420bb72c12 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
@@ -209,14 +209,17 @@ test_l2_miss_multicast()
 	# both registered and unregistered multicast traffic.
 	bridge link set dev $swp2 mcast_router 2
 
+	# Set the Max Response Delay to 100 centiseconds (1 second) so that the
+	# bridge will start forwarding according to its MDB soon after a
+	# multicast querier is enabled.
+	ip link set dev br1 type bridge mcast_query_response_interval 100
+
 	# Forwarding according to MDB entries only takes place when the bridge
 	# detects that there is a valid querier in the network. Set the bridge
 	# as the querier and assign it a valid IPv6 link-local address to be
 	# used as the source address for MLD queries.
 	ip link set dev br1 type bridge mcast_querier 1
 	ip -6 address add fe80::1/64 nodad dev br1
-	# Wait the default Query Response Interval (10 seconds) for the bridge
-	# to determine that there are no other queriers in the network.
 	sleep 10
 
 	test_l2_miss_multicast_ipv4
@@ -224,6 +227,7 @@ test_l2_miss_multicast()
 
 	ip -6 address del fe80::1/64 dev br1
 	ip link set dev br1 type bridge mcast_querier 0
+	ip link set dev br1 type bridge mcast_query_response_interval 1000
 	bridge link set dev $swp2 mcast_router 1
 }
 
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 19352f106c1d..02c21ff4ca81 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -31,6 +31,11 @@ run_test() {
       1>>log.txt
     wait "${server_pid}"
     exit_code=$?
+    if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \
+          ${exit_code} -ne 0 ]]; then
+        echo "Ignoring errors due to slow environment" 1>&2
+        exit_code=0
+    fi
     if [[ "${exit_code}" -eq 0 ]]; then
         break;
     fi
diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index fe59ca3e5596..12491850ae98 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -367,14 +367,12 @@ run_test()
   local desc=$2
   local node_src=$3
   local node_dst=$4
-  local ip6_src=$5
-  local ip6_dst=$6
-  local if_dst=$7
-  local trace_type=$8
-  local ioam_ns=$9
-
-  ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \
-         $trace_type $ioam_ns &
+  local ip6_dst=$5
+  local trace_type=$6
+  local ioam_ns=$7
+  local type=$8
+
+  ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type &
   local spid=$!
   sleep 0.1
 
@@ -489,7 +487,7 @@ out_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -509,7 +507,7 @@ out_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -543,14 +541,14 @@ out_bits()
       if [ $cmd_res != 0 ]
       then
         npassed=$((npassed+1))
-        log_test_passed "$descr"
+        log_test_passed "$descr ($1 mode)"
       else
         nfailed=$((nfailed+1))
-        log_test_failed "$descr"
+        log_test_failed "$descr ($1 mode)"
       fi
     else
 	run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
     fi
   done
 
@@ -574,7 +572,7 @@ out_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 100 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -604,7 +602,7 @@ in_undef_ns()
          trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0x800000 0
+         db01::1 0x800000 0 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -624,7 +622,7 @@ in_no_room()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -651,7 +649,7 @@ in_bits()
            dev veth0
 
     run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \
-           $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
+           $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1
   done
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
@@ -679,7 +677,7 @@ in_oflag()
          trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xc00000 123
+         db01::1 0xc00000 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 
@@ -703,7 +701,7 @@ in_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 80 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \
-         db01::2 db01::1 veth0 0xfff002 123
+         db01::1 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down
 }
@@ -731,7 +729,7 @@ fwd_full_supp_trace()
          trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0
 
   run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \
-         db01::2 db02::2 veth0 0xfff002 123
+         db02::2 0xfff002 123 $1
 
   [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down
 }
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
index d9d1d4190126..895e5bb5044b 100644
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -8,7 +8,6 @@
 #include <errno.h>
 #include <limits.h>
 #include <linux/const.h>
-#include <linux/if_ether.h>
 #include <linux/ioam6.h>
 #include <linux/ipv6.h>
 #include <stdlib.h>
@@ -512,14 +511,6 @@ static int str2id(const char *tname)
 	return -1;
 }
 
-static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2)
-{
-	return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) |
-		(a1->s6_addr32[1] ^ a2->s6_addr32[1]) |
-		(a1->s6_addr32[2] ^ a2->s6_addr32[2]) |
-		(a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0;
-}
-
 static int get_u32(__u32 *val, const char *arg, int base)
 {
 	unsigned long res;
@@ -603,70 +594,80 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = {
 
 int main(int argc, char **argv)
 {
-	int fd, size, hoplen, tid, ret = 1;
-	struct in6_addr src, dst;
+	int fd, size, hoplen, tid, ret = 1, on = 1;
 	struct ioam6_hdr *opt;
-	struct ipv6hdr *ip6h;
-	__u8 buffer[400], *p;
-	__u16 ioam_ns;
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec iov;
+	__u8 buffer[512];
 	__u32 tr_type;
+	__u16 ioam_ns;
+	__u8 *ptr;
 
-	if (argc != 7)
+	if (argc != 5)
 		goto out;
 
-	tid = str2id(argv[2]);
+	tid = str2id(argv[1]);
 	if (tid < 0 || !func[tid])
 		goto out;
 
-	if (inet_pton(AF_INET6, argv[3], &src) != 1 ||
-	    inet_pton(AF_INET6, argv[4], &dst) != 1)
+	if (get_u32(&tr_type, argv[2], 16) ||
+	    get_u16(&ioam_ns, argv[3], 0))
 		goto out;
 
-	if (get_u32(&tr_type, argv[5], 16) ||
-	    get_u16(&ioam_ns, argv[6], 0))
+	fd = socket(PF_INET6, SOCK_RAW,
+		    !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6);
+	if (fd < 0)
 		goto out;
 
-	fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
-	if (!fd)
-		goto out;
+	setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS,  &on, sizeof(on));
 
-	if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
-		       argv[1], strlen(argv[1])))
+	iov.iov_len = 1;
+	iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer)));
+	if (!iov.iov_base)
 		goto close;
-
 recv:
-	size = recv(fd, buffer, sizeof(buffer), 0);
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = buffer;
+	msg.msg_controllen = CMSG_SPACE(sizeof(buffer));
+
+	size = recvmsg(fd, &msg, 0);
 	if (size <= 0)
 		goto close;
 
-	ip6h = (struct ipv6hdr *)buffer;
+	for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+		if (cmsg->cmsg_level != IPPROTO_IPV6 ||
+		    cmsg->cmsg_type != IPV6_HOPOPTS ||
+		    cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr))
+			continue;
 
-	if (!ipv6_addr_equal(&ip6h->saddr, &src) ||
-	    !ipv6_addr_equal(&ip6h->daddr, &dst))
-		goto recv;
+		ptr = (__u8 *)CMSG_DATA(cmsg);
 
-	if (ip6h->nexthdr != IPPROTO_HOPOPTS)
-		goto close;
+		hoplen = (ptr[1] + 1) << 3;
+		ptr += sizeof(struct ipv6_hopopt_hdr);
 
-	p = buffer + sizeof(*ip6h);
-	hoplen = (p[1] + 1) << 3;
-	p += sizeof(struct ipv6_hopopt_hdr);
+		while (hoplen > 0) {
+			opt = (struct ioam6_hdr *)ptr;
 
-	while (hoplen > 0) {
-		opt = (struct ioam6_hdr *)p;
+			if (opt->opt_type == IPV6_TLV_IOAM &&
+			    opt->type == IOAM6_TYPE_PREALLOC) {
+				ptr += sizeof(*opt);
+				ret = func[tid](tid,
+						(struct ioam6_trace_hdr *)ptr,
+						tr_type, ioam_ns);
+				goto close;
+			}
 
-		if (opt->opt_type == IPV6_TLV_IOAM &&
-		    opt->type == IOAM6_TYPE_PREALLOC) {
-			p += sizeof(*opt);
-			ret = func[tid](tid, (struct ioam6_trace_hdr *)p,
-					   tr_type, ioam_ns);
-			break;
+			ptr += opt->opt_len + 2;
+			hoplen -= opt->opt_len + 2;
 		}
-
-		p += opt->opt_len + 2;
-		hoplen -= opt->opt_len + 2;
 	}
+
+	goto recv;
 close:
+	free(iov.iov_base);
 	close(fd);
 out:
 	return ret;
diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c
index 0f217a1cc837..6ebd58869a63 100644
--- a/tools/testing/selftests/net/ip_local_port_range.c
+++ b/tools/testing/selftests/net/ip_local_port_range.c
@@ -16,6 +16,10 @@
 #define IP_LOCAL_PORT_RANGE 51
 #endif
 
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
 static __u32 pack_port_range(__u16 lo, __u16 hi)
 {
 	return (hi << 16) | (lo << 0);
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index dca549443801..f9fe182dfbd4 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -4,6 +4,9 @@
 ##############################################################################
 # Defines
 
+WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
+BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 # namespace list created by setup_ns
@@ -48,7 +51,7 @@ cleanup_ns()
 
 	for ns in "$@"; do
 		ip netns delete "${ns}" &> /dev/null
-		if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
 			ret=1
 		fi
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index e317c2e44dae..4f80014cae49 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IP6_NF_FILTER=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_ACT=y
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 04fcb8a077c9..75fc95675e2d 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -20,7 +20,7 @@ flush_pids()
 
 	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null
 
-	for _ in $(seq 10); do
+	for _ in $(seq $((timeout_poll * 10))); do
 		[ -z "$(ip netns pids "${ns}")" ] && break
 		sleep 0.1
 	done
@@ -62,14 +62,14 @@ __chk_nr()
 	nr=$(eval $command)
 
 	printf "%-50s" "$msg"
-	if [ $nr != $expected ]; then
-		if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then
+	if [ "$nr" != "$expected" ]; then
+		if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then
 			echo "[ skip ] Feature probably not supported"
 			mptcp_lib_result_skip "${msg}"
 		else
 			echo "[ fail ] expected $expected found $nr"
 			mptcp_lib_result_fail "${msg}"
-			ret=$test_cnt
+			ret=${KSFT_FAIL}
 		fi
 	else
 		echo "[  ok  ]"
@@ -91,6 +91,15 @@ chk_msk_nr()
 	__chk_msk_nr "grep -c token:" "$@"
 }
 
+chk_listener_nr()
+{
+	local expected=$1
+	local msg="$2"
+
+	__chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0
+	__chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows"
+}
+
 wait_msk_nr()
 {
 	local condition="grep -c token:"
@@ -115,11 +124,11 @@ wait_msk_nr()
 	if [ $i -ge $timeout ]; then
 		echo "[ fail ] timeout while expecting $expected max $max last $nr"
 		mptcp_lib_result_fail "${msg} # timeout"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	elif [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
 		mptcp_lib_result_fail "${msg} # unexpected result"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	else
 		echo "[  ok  ]"
 		mptcp_lib_result_pass "${msg}"
@@ -166,9 +175,13 @@ chk_msk_listen()
 chk_msk_inuse()
 {
 	local expected=$1
-	local msg="$2"
+	local msg="....chk ${2:-${expected}} msk in use"
 	local listen_nr
 
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
+
 	listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN)
 	expected=$((expected + listen_nr))
 
@@ -179,16 +192,21 @@ chk_msk_inuse()
 		sleep 0.1
 	done
 
-	__chk_nr get_msk_inuse $expected "$msg" 0
+	__chk_nr get_msk_inuse $expected "${msg}" 0
 }
 
 # $1: cestab nr
 chk_msk_cestab()
 {
-	local cestab=$1
+	local expected=$1
+	local msg="....chk ${2:-${expected}} cestab"
+
+	if [ "${expected}" -eq 0 ]; then
+		msg+=" after flush"
+	fi
 
 	__chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \
-		 "${cestab}" "....chk ${cestab} cestab" ""
+		 "${expected}" "${msg}" ""
 }
 
 wait_connected()
@@ -227,12 +245,12 @@ wait_connected $ns 10000
 chk_msk_nr 2 "after MPC handshake "
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
-chk_msk_inuse 2 "....chk 2 msk in use"
+chk_msk_inuse 2
 chk_msk_cestab 2
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "2->0"
+chk_msk_cestab 0 "2->0"
 
 echo "a" | \
 	timeout ${timeout_test} \
@@ -247,12 +265,12 @@ echo "b" | \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10001
 chk_msk_fallback_nr 1 "check fallback"
-chk_msk_inuse 1 "....chk 1 msk in use"
+chk_msk_inuse 1
 chk_msk_cestab 1
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "1->0"
+chk_msk_cestab 0 "1->0"
 
 NR_CLIENTS=100
 for I in `seq 1 $NR_CLIENTS`; do
@@ -273,12 +291,28 @@ for I in `seq 1 $NR_CLIENTS`; do
 done
 
 wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present"
-chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use"
-chk_msk_cestab $((NR_CLIENTS*2))
+chk_msk_inuse $((NR_CLIENTS*2)) "many"
+chk_msk_cestab $((NR_CLIENTS*2)) "many"
 flush_pids
 
-chk_msk_inuse 0 "....chk 0 msk in use after flush"
-chk_msk_cestab 0
+chk_msk_inuse 0 "many->0"
+chk_msk_cestab 0 "many->0"
+
+chk_listener_nr 0 "no listener sockets"
+NR_SERVERS=100
+for I in $(seq 1 $NR_SERVERS); do
+	ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \
+		-t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 &
+done
+mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001))
+
+chk_listener_nr $NR_SERVERS "many listener sockets"
+
+# graceful termination
+for I in $(seq 1 $NR_SERVERS); do
+	echo a | ip netns exec $ns ./mptcp_connect -p $((I + 20001)) 127.0.0.1 >/dev/null 2>&1 &
+done
+flush_pids
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 3a5b63026191..e4581b0dfb96 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -161,6 +161,11 @@ check_tools()
 		exit $ksft_skip
 	fi
 
+	if ! ss -h | grep -q MPTCP; then
+		echo "SKIP: ss tool does not support MPTCP"
+		exit $ksft_skip
+	fi
+
 	# Use the legacy version if available to support old kernel versions
 	if iptables-legacy -V &> /dev/null; then
 		iptables="iptables-legacy"
@@ -643,13 +648,6 @@ kill_events_pids()
 	mptcp_lib_kill_wait $evts_ns2_pid
 }
 
-kill_tests_wait()
-{
-	#shellcheck disable=SC2046
-	kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
-	wait
-}
-
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -3340,16 +3338,17 @@ userspace_pm_rm_sf()
 {
 	local evts=$evts_ns1
 	local t=${3:-1}
-	local ip=4
+	local ip
 	local tk da dp sp
 	local cnt
 
 	[ "$1" == "$ns2" ] && evts=$evts_ns2
-	if mptcp_lib_is_v6 $2; then ip=6; fi
+	[ -n "$(mptcp_lib_evts_get_info "saddr4" "$evts" $t)" ] && ip=4
+	[ -n "$(mptcp_lib_evts_get_info "saddr6" "$evts" $t)" ] && ip=6
 	tk=$(mptcp_lib_evts_get_info token "$evts")
-	da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t)
-	dp=$(mptcp_lib_evts_get_info dport "$evts" $t)
-	sp=$(mptcp_lib_evts_get_info sport "$evts" $t)
+	da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t $2)
+	dp=$(mptcp_lib_evts_get_info dport "$evts" $t $2)
+	sp=$(mptcp_lib_evts_get_info sport "$evts" $t $2)
 
 	cnt=$(rm_sf_count ${1})
 	ip netns exec $1 ./pm_nl_ctl dsf lip $2 lport $sp \
@@ -3436,24 +3435,27 @@ userspace_tests()
 	if reset_with_events "userspace pm add & remove address" &&
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
-		pm_nl_set_limits $ns2 1 1
+		pm_nl_set_limits $ns2 2 2
 		speed=5 \
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
 		wait_mpj $ns1
 		userspace_pm_add_addr $ns1 10.0.2.1 10
-		chk_join_nr 1 1 1
-		chk_add_nr 1 1
-		chk_mptcp_info subflows 1 subflows 1
-		chk_subflows_total 2 2
-		chk_mptcp_info add_addr_signal 1 add_addr_accepted 1
+		userspace_pm_add_addr $ns1 10.0.3.1 20
+		chk_join_nr 2 2 2
+		chk_add_nr 2 2
+		chk_mptcp_info subflows 2 subflows 2
+		chk_subflows_total 3 3
+		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 		userspace_pm_rm_addr $ns1 10
 		userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED
-		chk_rm_nr 1 1 invert
+		userspace_pm_rm_addr $ns1 20
+		userspace_pm_rm_sf $ns1 10.0.3.1 $SUB_ESTABLISHED
+		chk_rm_nr 2 2 invert
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create destroy subflow
@@ -3475,7 +3477,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create id 0 subflow
@@ -3494,7 +3496,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 2 2
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm remove initial subflow
@@ -3518,7 +3520,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm send RM_ADDR for ID 0
@@ -3544,7 +3546,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
@@ -3558,7 +3560,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		speed=slow \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint "creation" \
@@ -3573,7 +3576,7 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
 		pm_nl_check_endpoint "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	if reset "delete and re-add" &&
@@ -3582,7 +3585,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		test_linkfail=4 speed=20 \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns2
 		chk_subflow_nr "before delete" 2
@@ -3597,7 +3601,7 @@ endpoint_tests()
 		wait_mpj $ns2
 		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 022262a2cfe0..3777d66fc56d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -6,7 +6,7 @@ readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
 
 # shellcheck disable=SC2155 # declare and assign separately
-readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
+readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
 
 MPTCP_LIB_SUBTESTS=()
 
@@ -213,9 +213,9 @@ mptcp_lib_get_info_value() {
 	grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
 }
 
-# $1: info name ; $2: evts_ns ; $3: event type
+# $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
 mptcp_lib_evts_get_info() {
-	mptcp_lib_get_info_value "${1}" "^type:${3:-1}," < "${2}"
+	grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
 }
 
 # $1: PID
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 8f4ff123a7eb..71899a3ffa7a 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -183,7 +183,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow 10.0.1.1" "          (nobackup)"
 
 # fullmesh support has been added later
-ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh
+ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh 2>/dev/null
 if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" ||
    mptcp_lib_expect_all_features; then
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
@@ -194,6 +194,12 @@ subflow 10.0.1.1" "          (nofullmesh)"
 	ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh
 	check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \
 subflow,backup,fullmesh 10.0.1.1" "          (backup,fullmesh)"
+else
+	for st in fullmesh nofullmesh backup,fullmesh; do
+		st="          (${st})"
+		printf "%-50s%s\n" "${st}" "[SKIP]"
+		mptcp_lib_result_skip "${st}"
+	done
 fi
 
 mptcp_lib_result_print_all_tap
diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings
index 79b65bdf05db..abc5648b59ab 100644
--- a/tools/testing/selftests/net/mptcp/settings
+++ b/tools/testing/selftests/net/mptcp/settings
@@ -1 +1 @@
-timeout=1200
+timeout=1800
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index ae8ad5d6fb9d..8f9ddb3ad4fe 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -250,7 +250,8 @@ run_test()
 		[ $bail -eq 0 ] || exit $ret
 	fi
 
-	printf "%-60s" "$msg - reverse direction"
+	msg+=" - reverse direction"
+	printf "%-60s" "${msg}"
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
@@ -284,12 +285,12 @@ done
 
 setup
 run_test 10 10 0 0 "balanced bwidth"
-run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 30 10 0 0 "unbalanced bwidth"
-run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
-run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+run_test 10 3 0 0 "unbalanced bwidth"
+run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
+run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
 mptcp_lib_result_print_all_tap
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 6167837f48e1..1b94a75604fe 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -75,7 +75,7 @@ print_test()
 {
 	test_name="${1}"
 
-	_printf "%-63s" "${test_name}"
+	_printf "%-68s" "${test_name}"
 }
 
 print_results()
@@ -542,7 +542,7 @@ verify_subflow_events()
 	local remid
 	local info
 
-	info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})"
+	info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})"
 
 	if [ "$e_type" = "$SUB_ESTABLISHED" ]
 	then
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
index 4fe0befa13fb..6596fe03c77f 100755..100644
--- a/tools/testing/selftests/net/net_helper.sh
+++ b/tools/testing/selftests/net/net_helper.sh
@@ -8,13 +8,16 @@ wait_local_port_listen()
 	local listener_ns="${1}"
 	local port="${2}"
 	local protocol="${3}"
-	local port_hex
+	local pattern
 	local i
 
-	port_hex="$(printf "%04X" "${port}")"
+	pattern=":$(printf "%04X" "${port}") "
+
+	# for tcp protocol additionally check the socket state
+	[ ${protocol} = "tcp" ] && pattern="${pattern}0A"
 	for i in $(seq 10); do
-		if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \
-		   grep -q "${port_hex}"; then
+		if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
+		   /proc/net/"${protocol}"* | grep -q "${pattern}"; then
 			break
 		fi
 		sleep 0.1
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index f8499d4c87f3..36e40256ab92 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -502,9 +502,22 @@ test_netlink_checks () {
 	    wc -l) == 2 ] || \
 	      return 1
 
+	info "Checking clone depth"
 	ERR_MSG="Flow actions may not be safe on all matching packets"
 	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
 	ovs_add_flow "test_netlink_checks" nv0 \
+		'in_port(1),eth(),eth_type(0x800),ipv4()' \
+		'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \
+		>/dev/null 2>&1 && return 1
+	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
+
+	if [ "$PRE_TEST" == "$POST_TEST" ]; then
+		info "failed - clone depth too large"
+		return 1
+	fi
+
+	PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
+	ovs_add_flow "test_netlink_checks" nv0 \
 		'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \
 		&> /dev/null && return 1
 	POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index b97e621face9..5e0e539a323d 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -299,7 +299,7 @@ class ovsactions(nla):
         ("OVS_ACTION_ATTR_PUSH_NSH", "none"),
         ("OVS_ACTION_ATTR_POP_NSH", "flag"),
         ("OVS_ACTION_ATTR_METER", "none"),
-        ("OVS_ACTION_ATTR_CLONE", "none"),
+        ("OVS_ACTION_ATTR_CLONE", "recursive"),
         ("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"),
         ("OVS_ACTION_ATTR_ADD_MPLS", "none"),
         ("OVS_ACTION_ATTR_DEC_TTL", "none"),
@@ -465,29 +465,42 @@ class ovsactions(nla):
                     print_str += "pop_mpls"
             else:
                 datum = self.get_attr(field[0])
-                print_str += datum.dpstr(more)
+                if field[0] == "OVS_ACTION_ATTR_CLONE":
+                    print_str += "clone("
+                    print_str += datum.dpstr(more)
+                    print_str += ")"
+                else:
+                    print_str += datum.dpstr(more)
 
         return print_str
 
     def parse(self, actstr):
+        totallen = len(actstr)
         while len(actstr) != 0:
             parsed = False
+            parencount = 0
             if actstr.startswith("drop"):
                 # If no reason is provided, the implicit drop is used (i.e no
                 # action). If some reason is given, an explicit action is used.
-                actstr, reason = parse_extract_field(
-                    actstr,
-                    "drop(",
-                    "([0-9]+)",
-                    lambda x: int(x, 0),
-                    False,
-                    None,
-                )
+                reason = None
+                if actstr.startswith("drop("):
+                    parencount += 1
+
+                    actstr, reason = parse_extract_field(
+                        actstr,
+                        "drop(",
+                        "([0-9]+)",
+                        lambda x: int(x, 0),
+                        False,
+                        None,
+                    )
+
                 if reason is not None:
                     self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason])
                     parsed = True
                 else:
-                    return
+                    actstr = actstr[len("drop"): ]
+                    return (totallen - len(actstr))
 
             elif parse_starts_block(actstr, "^(\d+)", False, True):
                 actstr, output = parse_extract_field(
@@ -504,6 +517,7 @@ class ovsactions(nla):
                     False,
                     0,
                 )
+                parencount += 1
                 self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid])
                 parsed = True
 
@@ -516,12 +530,22 @@ class ovsactions(nla):
 
             for flat_act in parse_flat_map:
                 if parse_starts_block(actstr, flat_act[0], False):
-                    actstr += len(flat_act[0])
+                    actstr = actstr[len(flat_act[0]):]
                     self["attrs"].append([flat_act[1]])
                     actstr = actstr[strspn(actstr, ", ") :]
                     parsed = True
 
-            if parse_starts_block(actstr, "ct(", False):
+            if parse_starts_block(actstr, "clone(", False):
+                parencount += 1
+                subacts = ovsactions()
+                actstr = actstr[len("clone("):]
+                parsedLen = subacts.parse(actstr)
+                lst = []
+                self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts))
+                actstr = actstr[parsedLen:]
+                parsed = True
+            elif parse_starts_block(actstr, "ct(", False):
+                parencount += 1
                 actstr = actstr[len("ct(") :]
                 ctact = ovsactions.ctact()
 
@@ -553,6 +577,7 @@ class ovsactions(nla):
                         natact = ovsactions.ctact.natattr()
 
                         if actstr.startswith("("):
+                            parencount += 1
                             t = None
                             actstr = actstr[1:]
                             if actstr.startswith("src"):
@@ -607,15 +632,29 @@ class ovsactions(nla):
                                     actstr = actstr[strspn(actstr, ", ") :]
 
                         ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact])
-                        actstr = actstr[strspn(actstr, ",) ") :]
+                        actstr = actstr[strspn(actstr, ", ") :]
 
                 self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
                 parsed = True
 
-            actstr = actstr[strspn(actstr, "), ") :]
+            actstr = actstr[strspn(actstr, ", ") :]
+            while parencount > 0:
+                parencount -= 1
+                actstr = actstr[strspn(actstr, " "):]
+                if len(actstr) and actstr[0] != ")":
+                    raise ValueError("Action str: '%s' unbalanced" % actstr)
+                actstr = actstr[1:]
+
+            if len(actstr) and actstr[0] == ")":
+                return (totallen - len(actstr))
+
+            actstr = actstr[strspn(actstr, ", ") :]
+
             if not parsed:
                 raise ValueError("Action str: '%s' not supported" % actstr)
 
+        return (totallen - len(actstr))
+
 
 class ovskey(nla):
     nla_flags = NLA_F_NESTED
@@ -2111,6 +2150,8 @@ def main(argv):
     ovsflow = OvsFlow()
     ndb = NDB()
 
+    sys.setrecursionlimit(100000)
+
     if hasattr(args, "showdp"):
         found = False
         for iface in ndb.interfaces:
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f10879788f61..cfc84958025a 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -199,6 +199,7 @@
 #	Same as above but with IPv6
 
 source lib.sh
+source net_helper.sh
 
 PAUSE_ON_FAIL=no
 VERBOSE=0
@@ -707,23 +708,23 @@ setup_xfrm6() {
 }
 
 setup_xfrm4udp() {
-	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udp() {
-	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_xfrm4udprouted() {
-	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 4 4500
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udprouted() {
-	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
-	setup_nettest_xfrm 6 4500
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \
+		setup_nettest_xfrm 6 4500
 }
 
 setup_routing_old() {
@@ -1335,12 +1336,14 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 		else
 			TCPDST="TCP:[${dst}]:50000"
 		fi
-		${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile &
+		${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000,reuseaddr STDOUT > $tmpoutfile &
+		local socat_pid=$!
 
-		sleep 1
+		wait_local_port_listen ${NS_B} 50000 tcp
 
-		dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
+		dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
 
+		wait ${socat_pid}
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}
 
@@ -1954,6 +1957,13 @@ check_command() {
 	return 0
 }
 
+check_running() {
+	pid=${1}
+	cmd=${2}
+
+	[ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+}
+
 test_cleanup_vxlanX_exception() {
 	outer="${1}"
 	encap="vxlan"
@@ -1984,11 +1994,12 @@ test_cleanup_vxlanX_exception() {
 
 	${ns_a} ip link del dev veth_A-R1 &
 	iplink_pid=$!
-	sleep 1
-	if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
-		err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
-		return 1
-	fi
+	for i in $(seq 1 20); do
+		check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0
+		sleep 0.1
+	done
+	err "  can't delete veth device in a timely manner, PMTU dst likely leaked"
+	return 1
 }
 
 test_cleanup_ipv6_exception() {
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 4667d74579d1..874a2952aa8e 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -440,7 +440,6 @@ kci_test_encap_vxlan()
 	local ret=0
 	vxlan="test-vxlan0"
 	vlan="test-vlan0"
-	testns="$1"
 	run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
 		dev "$devdummy" dstport 4789
 	if [ $? -ne 0 ]; then
@@ -485,7 +484,6 @@ kci_test_encap_fou()
 {
 	local ret=0
 	name="test-fou"
-	testns="$1"
 	run_cmd_grep 'Usage: ip fou' ip fou help
 	if [ $? -ne 0 ];then
 		end_test "SKIP: fou: iproute2 too old"
@@ -526,8 +524,8 @@ kci_test_encap()
 	run_cmd ip -netns "$testns" link set lo up
 	run_cmd ip -netns "$testns" link add name "$devdummy" type dummy
 	run_cmd ip -netns "$testns" link set "$devdummy" up
-	run_cmd kci_test_encap_vxlan "$testns"
-	run_cmd kci_test_encap_fou "$testns"
+	run_cmd kci_test_encap_vxlan
+	run_cmd kci_test_encap_fou
 
 	ip netns del "$testns"
 	return $ret
diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh
index 2070b57849de..2070b57849de 100755..100644
--- a/tools/testing/selftests/net/setup_loopback.sh
+++ b/tools/testing/selftests/net/setup_loopback.sh
diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index a9a1759e035c..1f78a87f6f37 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,7 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up
 
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
index 3f06f4d286a9..5e861ad32a42 100755
--- a/tools/testing/selftests/net/so_txtime.sh
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -5,6 +5,7 @@
 
 set -e
 
+readonly ksft_skip=4
 readonly DEV="veth0"
 readonly BIN="./so_txtime"
 
@@ -46,7 +47,7 @@ ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
 ip -netns "${NS1}" addr add       fd::1/64 dev "${DEV}" nodad
 ip -netns "${NS2}" addr add       fd::2/64 dev "${DEV}" nodad
 
-do_test() {
+run_test() {
 	local readonly IP="$1"
 	local readonly CLOCK="$2"
 	local readonly TXARGS="$3"
@@ -64,12 +65,25 @@ do_test() {
 	fi
 
 	local readonly START="$(date +%s%N --date="+ 0.1 seconds")"
+
 	ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r &
 	ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}"
 	wait "$!"
 }
 
+do_test() {
+	run_test $@
+	[ $? -ne 0 ] && ret=1
+}
+
+do_fail_test() {
+	run_test $@
+	[ $? -eq 0 ] && ret=1
+}
+
 ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq
+set +e
+ret=0
 do_test 4 mono a,-1 a,-1
 do_test 6 mono a,0 a,0
 do_test 6 mono a,10 a,10
@@ -77,13 +91,20 @@ do_test 4 mono a,10,b,20 a,10,b,20
 do_test 6 mono a,20,b,10 b,20,a,20
 
 if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then
-	! do_test 4 tai a,-1 a,-1
-	! do_test 6 tai a,0 a,0
+	do_fail_test 4 tai a,-1 a,-1
+	do_fail_test 6 tai a,0 a,0
 	do_test 6 tai a,10 a,10
 	do_test 4 tai a,10,b,20 a,10,b,20
 	do_test 6 tai a,20,b,10 b,10,a,20
 else
 	echo "tc ($(tc -V)) does not support qdisc etf. skipping"
+	[ $ret -eq 0 ] && ret=$ksft_skip
 fi
 
-echo OK. All tests passed
+if [ $ret -eq 0 ]; then
+	echo OK. All tests passed
+elif [[ $ret -ne $ksft_skip && -n "$KSFT_MACHINE_SLOW" ]]; then
+	echo "Ignoring errors due to slow environment" 1>&2
+	ret=0
+fi
+exit $ret
diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config
new file mode 100644
index 000000000000..d3277a9de987
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/config
@@ -0,0 +1,10 @@
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_RMD160=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_TCP_AO=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_VETH=m
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index c48b4970ca17..24e62120b792 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -417,9 +417,9 @@ struct test_key {
 		matches_vrf		: 1,
 		is_current		: 1,
 		is_rnext		: 1,
-		used_on_handshake	: 1,
-		used_after_accept	: 1,
-		used_on_client		: 1;
+		used_on_server_tx	: 1,
+		used_on_client_tx	: 1,
+		skip_counters_checks	: 1;
 };
 
 struct key_collection {
@@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port)
 				addr = &this_ip_dest;
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			set_current = key->is_current;
-			set_rnext = key->is_rnext;
+			key->used_on_client_tx = set_current = key->is_current;
+			key->used_on_server_tx = set_rnext = key->is_rnext;
 		}
 
 		if (test_add_key_cr(sk, key->password, key->len,
 				    *addr, vrf, sndid, rcvid, key->maclen,
 				    key->alg, set_current, set_rnext))
 			test_key_error("setsockopt(TCP_AO_ADD_KEY)", key);
-		if (set_current || set_rnext)
-			key->used_on_handshake = 1;
 #ifdef DEBUG
 		test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}",
 			   server ? "server" : "client", i, collection.nr_keys,
@@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
 		uint8_t sndid, rcvid;
-		bool was_used;
+		bool rx_cnt_expected;
 
+		if (key->skip_counters_checks)
+			continue;
 		if (server) {
 			sndid = key->server_keyid;
 			rcvid = key->client_keyid;
-			if (is_listen_sk)
-				was_used = key->used_on_handshake;
-			else
-				was_used = key->used_after_accept;
+			rx_cnt_expected = key->used_on_client_tx;
 		} else {
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			was_used = key->used_on_client;
+			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used,
+		test_tcp_ao_key_counters_cmp(tst_name, a, b,
+					     rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
 					     sndid, rcvid);
 	}
 	test_tcp_ao_counters_free(a);
@@ -843,7 +841,7 @@ static void end_server(const char *tst_name, int sk,
 	synchronize_threads(); /* 4: verified => closed */
 	close(sk);
 
-	verify_counters(tst_name, true, false, begin, &end);
+	verify_counters(tst_name, false, true, begin, &end);
 	synchronize_threads(); /* 5: counters */
 }
 
@@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port,
 		current_index = nr_keys - 1;
 	if (rnext_index < 0)
 		rnext_index = nr_keys - 1;
-	collection.keys[current_index].used_on_handshake = 1;
-	collection.keys[rnext_index].used_after_accept = 1;
-	collection.keys[rnext_index].used_on_client = 1;
+	collection.keys[current_index].used_on_client_tx = 1;
+	collection.keys[rnext_index].used_on_server_tx = 1;
 
 	synchronize_threads(); /* 3: accepted => send data */
 	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
@@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port,
 		test_error("Can't change the current key");
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
-	collection.keys[rotate_to_index].used_after_accept = 1;
+	/* There is a race here: between setting the current_key with
+	 * setsockopt(TCP_AO_INFO) and starting to send some data - there
+	 * might have been a segment received with the desired
+	 * RNext_key set. In turn that would mean that the first outgoing
+	 * segment will have the desired current_key (flipped back).
+	 * Which is what the user/test wants. As it's racy, skip checking
+	 * the counters, yet check what are the resulting current/rnext
+	 * keys on both sides.
+	 */
+	collection.keys[rotate_to_index].skip_counters_checks = 1;
 
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
 }
@@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 		}
 		verify_current_rnext(tst_name, sk, -1,
 				     collection.keys[i].server_keyid);
-		collection.keys[i].used_on_client = 1;
+		collection.keys[i].used_on_server_tx = 1;
 		synchronize_threads(); /* verify current/rnext */
 	}
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index c75d82885a2e..15aeb0963058 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write)
 		return -ETIMEDOUT;
 	}
 
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret)
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen))
+		return -errno;
+	if (ret)
 		return -ret;
 	return 0;
 }
@@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 {
 	size_t buf_sz = msg_len * nr;
 	char *buf = alloca(buf_sz);
+	ssize_t ret;
 
 	randomize_buffer(buf, buf_sz);
-	if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz)
-		return -1;
-	return 0;
+	ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
+	if (ret < 0)
+		return (int)ret;
+	return ret != buf_sz ? -1 : 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index ac06009a7f5f..7df8b8700e39 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -1,10 +1,33 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Author: Dmitry Safonov <dima@arista.com> */
+/*
+ * The test checks that both active and passive reset have correct TCP-AO
+ * signature. An "active" reset (abort) here is procured from closing
+ * listen() socket with non-accepted connections in the queue:
+ * inet_csk_listen_stop() => inet_child_forget() =>
+ *                        => tcp_disconnect() => tcp_send_active_reset()
+ *
+ * The passive reset is quite hard to get on established TCP connections.
+ * It could be procured from non-established states, but the synchronization
+ * part from userspace in order to reliably get RST seems uneasy.
+ * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state.
+ *
+ * It's important to test both passive and active RST as they go through
+ * different code-paths:
+ * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb()
+ * - tcp_v*_send_reset() create their reply skbs and send them with
+ *   ip_send_unicast_reply()
+ *
+ * In both cases TCP-AO signatures have to be correct, which is verified by
+ * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters.
+ *
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
 #include <inttypes.h>
 #include "../../../../include/linux/kernel.h"
 #include "aolib.h"
 
 const size_t quota = 1000;
+const size_t packet_sz = 100;
 /*
  * Backlog == 0 means 1 connection in queue, see:
  * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...")
@@ -59,26 +82,6 @@ static void close_forced(int sk)
 	close(sk);
 }
 
-static int test_wait_for_exception(int sk, time_t sec)
-{
-	struct timeval tv = { .tv_sec = sec };
-	struct timeval *ptv = NULL;
-	fd_set efds;
-	int ret;
-
-	FD_ZERO(&efds);
-	FD_SET(sk, &efds);
-
-	if (sec)
-		ptv = &tv;
-
-	errno = 0;
-	ret = select(sk + 1, NULL, NULL, &efds, ptv);
-	if (ret < 0)
-		return -errno;
-	return ret ? sk : 0;
-}
-
 static void test_server_active_rst(unsigned int port)
 {
 	struct tcp_ao_counters cnt1, cnt2;
@@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port)
 			test_fail("server returned %zd", bytes);
 	}
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
+	synchronize_threads(); /* 4: close the server, creating twsk */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
-
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC);
 	close(sk);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
 	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
 
-	synchronize_threads(); /* 5: verified => closed */
-	close(sk);
+	synchronize_threads(); /* 6: server exits */
 }
 
 static void *server_fn(void *arg)
@@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("test_wait_fds(): %d", err);
 
 	synchronize_threads(); /* 3: close listen socket */
-	if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port)
 	struct tcp_sock_state img;
 	sockaddr_af saddr;
 	int sk, err;
-	socklen_t slen = sizeof(err);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
 	test_enable_repair(sk);
 	test_sock_checkpoint(sk, &img, &saddr);
 	test_ao_checkpoint(sk, &ao_img);
-	test_kill_sk(sk);
+	test_disable_repair(sk);
 
-	img.out.seq += quota;
+	synchronize_threads(); /* 4: close the server, creating twsk */
+
+	/*
+	 * The "corruption" in SEQ has to be small enough to fit into TCP
+	 * window, see tcp_timewait_state_process() for out-of-window
+	 * segments.
+	 */
+	img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */
+
+	/*
+	 * FIXME: This is kind-of ugly and dirty, but it works.
+	 *
+	 * At this moment, the server has close'ed(sk).
+	 * The passive RST that is being targeted here is new data after
+	 * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST
+	 *
+	 * What is needed here is:
+	 * (1) wait for FIN from the server
+	 * (2) make sure that the ACK from the client went out
+	 * (3) make sure that the ACK was received and processed by the server
+	 *
+	 * Otherwise, the data that will be sent from "repaired" socket
+	 * post SEQ corruption may get to the server before it's in
+	 * TCP_FIN_WAIT2.
+	 *
+	 * (1) is easy with select()/poll()
+	 * (2) is possible by polling tcpi_state from TCP_INFO
+	 * (3) is quite complex: as server's socket was already closed,
+	 *     probably the way to do it would be tcp-diag.
+	 */
+	sleep(TEST_RETRANSMIT_SEC);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
+	test_kill_sk(sk);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port)
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
 
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC))
-		test_ok("client connection broken post-seq-adjust");
-	else
-		test_fail("client connection still works post-seq-adjust");
-
-	test_wait_for_exception(sk, TEST_TIMEOUT_SEC);
-
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen))
-		test_error("getsockopt()");
-	if (err != ECONNRESET && err != EPIPE)
-		test_fail("client connection was not reset: %d", err);
+	/*
+	 * This is how "passive reset" is acquired in this test from TCP_TW_RST:
+	 *
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
+	 */
+	err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+	/* Make sure that the connection was reset, not timeouted */
+	if (err && err == -ECONNRESET)
+		test_ok("client sock was passively reset post-seq-adjust");
+	else if (err)
+		test_fail("client sock was not reset post-seq-adjust: %d", err);
 	else
-		test_ok("client connection was reset");
+		test_fail("client sock is yet connected post-seq-adjust");
 
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 
-	synchronize_threads(); /* 5: verified => closed */
+	synchronize_threads(); /* 6: server exits */
 	close(sk);
 	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
 }
@@ -410,6 +452,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(15, server_fn, client_fn);
+	test_init(14, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/settings b/tools/testing/selftests/net/tcp_ao/settings
new file mode 100644
index 000000000000..6091b45d226b
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/settings
@@ -0,0 +1 @@
+timeout=120
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index c5b568cd7d90..6b59a652159f 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -110,9 +110,9 @@ static void try_accept(const char *tst_name, unsigned int port,
 		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	if (sk > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void server_add_routes(void)
@@ -302,10 +302,10 @@ static void try_connect(const char *tst_name, unsigned int port,
 		test_ok("%s: connected", tst_name);
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 #define PREINSTALL_MD5_FIRST	BIT(0)
@@ -486,10 +486,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
 	}
 
 out:
-	synchronize_threads(); /* close() */
+	synchronize_threads(); /* test_kill_sk() */
 	/* _test_connect_socket() cleans up on failure */
 	if (ret > 0)
-		close(sk);
+		test_kill_sk(sk);
 }
 
 static void client_add_ip(union tcp_addr *client, const char *ip)
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
index 70a7d87ba2d2..1b3f89e2b86e 100755
--- a/tools/testing/selftests/net/test_bridge_backup_port.sh
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -124,6 +124,16 @@ tc_check_packets()
 	[[ $pkts == $count ]]
 }
 
+bridge_link_check()
+{
+	local ns=$1; shift
+	local dev=$1; shift
+	local state=$1; shift
+
+	bridge -n $ns -d -j link show dev $dev | \
+		jq -e ".[][\"state\"] == \"$state\"" &> /dev/null
+}
+
 ################################################################################
 # Setup
 
@@ -259,6 +269,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -268,6 +279,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure vx0 as the backup port of swp1 and check that packets are
@@ -284,6 +296,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -293,6 +306,7 @@ backup_port()
 	log_test $? 0 "Forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -314,6 +328,7 @@ backup_port()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -369,6 +384,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -382,6 +398,7 @@ backup_nhid()
 	log_test $? 0 "Forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	# Configure nexthop ID 10 as the backup nexthop ID of swp1 and check
@@ -398,6 +415,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding out of vx0"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -411,6 +429,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
 	log_test $? 0 "swp1 carrier on"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -441,6 +460,7 @@ backup_nhid()
 	log_test $? 0 "No forwarding using VXLAN FDB entry"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -497,6 +517,7 @@ backup_nhid_invalid()
 	log_test $? 0 "Valid nexthop as backup nexthop"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	log_test $? 0 "swp1 carrier off"
 
 	run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -604,7 +625,9 @@ backup_nhid_ping()
 	run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10"
 
 	run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
 	run_cmd "ip -n $sw2 link set dev swp1 carrier off"
+	busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled
 
 	run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
 	log_test $? 0 "Ping with backup nexthop ID"
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 7799e042a971..b95c249f81c2 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1002,12 +1002,12 @@ TEST_F(tls, recv_partial)
 
 	memset(recv_mem, 0, sizeof(recv_mem));
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first),
+		       MSG_WAITALL), strlen(test_str_first));
 	EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
 	memset(recv_mem, 0, sizeof(recv_mem));
-	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second),
-		       MSG_WAITALL), -1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second),
+		       MSG_WAITALL), strlen(test_str_second));
 	EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
 		  0);
 }
@@ -1485,6 +1485,51 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+TEST_F(tls, control_msg_nomerge)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec1, send_len), 0);
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len);
+	EXPECT_EQ(memcmp(buf, rec2, send_len), 0);
+}
+
+TEST_F(tls, data_control_data)
+{
+	char *rec1 = "1111";
+	char *rec2 = "2222";
+	char *rec3 = "3333";
+	int send_len = 5;
+	char buf[15];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	EXPECT_EQ(send(self->fd, rec1, send_len, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len);
+	EXPECT_EQ(send(self->fd, rec3, send_len, 0), send_len);
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+}
+
 TEST_F(tls, shutdown)
 {
 	char const *test_str = "test_read";
@@ -1874,13 +1919,13 @@ TEST_F(tls_err, poll_partial_rec_async)
 		/* Child should sleep in poll(), never get a wake */
 		pfd.fd = self->cfd2;
 		pfd.events = POLLIN;
-		EXPECT_EQ(poll(&pfd, 1, 5), 0);
+		EXPECT_EQ(poll(&pfd, 1, 20), 0);
 
 		EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */
 
 		pfd.fd = self->cfd2;
 		pfd.events = POLLIN;
-		EXPECT_EQ(poll(&pfd, 1, 5), 1);
+		EXPECT_EQ(poll(&pfd, 1, 20), 1);
 
 		exit(!_metadata->passed);
 	}
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index af5dc57c8ce9..8802604148dd 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 # set global exit status, but never reset nonzero one.
 check_err()
@@ -197,7 +197,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index cb664679b434..7080eae5312b 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -84,7 +84,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index dd47fa96f6b3..e1ff645bd3d1 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -85,12 +85,12 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
 if [ ! -f nat6to4.o ]; then
-	echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first"
+	echo "Missing nat6to4 helper. Run 'make' first"
 	exit -1
 fi
 
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index c079565add39..9cd5e885e91f 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,7 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+source net_helper.sh
+
+BPF_FILE="xdp_dummy.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
 readonly SRC=2
 readonly DST=1
@@ -37,6 +39,10 @@ create_ns() {
 	for ns in $NS_SRC $NS_DST; do
 		ip netns add $ns
 		ip -n $ns link set dev lo up
+
+		# disable route solicitations to decrease 'noise' traffic
+		ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0
+		ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0
 	done
 
 	ip link add name veth$SRC type veth peer name veth$DST
@@ -78,6 +84,12 @@ create_vxlan_pair() {
 		create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
 		ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
 	done
+
+	# preload neighbur cache, do avoid some noisy traffic
+	local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST  |jq -r '.[]["address"]')
+	local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC  |jq -r '.[]["address"]')
+	ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC
+	ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST
 }
 
 is_ipv6() {
@@ -117,9 +129,9 @@ run_test() {
 	# not enable GRO
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
-	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+	ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
@@ -166,9 +178,9 @@ run_bench() {
 	# bind the sender and the receiver to different CPUs to try
 	# get reproducible results
 	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
-	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
+	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100  &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index f35a924d4a30..1cbadd267c96 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -375,7 +375,7 @@ static void do_recv(void)
 			do_flush_udp(fd);
 
 		tnow = gettimeofday_ms();
-		if (tnow > treport) {
+		if (!cfg_expected_pkt_nr && tnow > treport) {
 			if (packets)
 				fprintf(stderr,
 					"%s rx: %6lu MB/s %8lu calls/s\n",
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2d073595c620..5ae85def0739 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
 readonly BASE=`basename $STATS`
 readonly SRC=2
@@ -218,7 +218,7 @@ while getopts "hs:" option; do
 done
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit 1
 fi
 
@@ -247,6 +247,20 @@ chk_gro "        - aggregation with TSO off" 1
 cleanup
 
 create_ns
+ip -n $NS_DST link set dev veth$DST up
+ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp
+chk_gro_flag "gro vs xdp while down - gro flag on" $DST on
+ip -n $NS_DST link set dev veth$DST down
+chk_gro_flag "                      - after down" $DST on
+ip -n $NS_DST link set dev veth$DST xdp off
+chk_gro_flag "                      - after xdp off" $DST off
+ip -n $NS_DST link set dev veth$DST up
+chk_gro_flag "                      - after up" $DST off
+ip -n $NS_SRC link set dev veth$SRC xdp object ${BPF_FILE} section xdp
+chk_gro_flag "                      - after peer xdp" $DST off
+cleanup
+
+create_ns
 chk_channels "default channels" $DST 1 1
 
 ip -n $NS_DST link set dev veth$DST down
diff --git a/tools/testing/selftests/net/xdp_dummy.c b/tools/testing/selftests/net/xdp_dummy.c
new file mode 100644
index 000000000000..d988b2e0cee8
--- /dev/null
+++ b/tools/testing/selftests/net/xdp_dummy.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index db27153eb4a0..936c3085bb83 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -7,7 +7,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
 	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
 	conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \
-	conntrack_sctp_collision.sh xt_string.sh
+	conntrack_sctp_collision.sh xt_string.sh \
+	bridge_netfilter.sh
 
 HOSTPKG_CONFIG := pkg-config
 
diff --git a/tools/testing/selftests/netfilter/bridge_netfilter.sh b/tools/testing/selftests/netfilter/bridge_netfilter.sh
new file mode 100644
index 000000000000..659b3ab02c8b
--- /dev/null
+++ b/tools/testing/selftests/netfilter/bridge_netfilter.sh
@@ -0,0 +1,188 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bridge netfilter + conntrack, a combination that doesn't really work,
+# with multicast/broadcast packets racing for hash table insertion.
+
+#           eth0    br0     eth0
+# setup is: ns1 <->,ns0 <-> ns3
+#           ns2 <-'    `'-> ns4
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+ns3="ns3-$sfx"
+ns4="ns4-$sfx"
+
+ebtables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ebtables"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+for i in $(seq 0 4); do
+  eval ip netns add \$ns$i
+done
+
+cleanup() {
+  for i in $(seq 0 4); do eval ip netns del \$ns$i;done
+}
+
+trap cleanup EXIT
+
+do_ping()
+{
+	fromns="$1"
+	dstip="$2"
+
+	ip netns exec $fromns ping -c 1 -q $dstip > /dev/null
+	if [ $? -ne 0 ]; then
+		echo "ERROR: ping from $fromns to $dstip"
+		ip netns exec ${ns0} nft list ruleset
+		ret=1
+	fi
+}
+
+bcast_ping()
+{
+	fromns="$1"
+	dstip="$2"
+
+	for i in $(seq 1 1000); do
+		ip netns exec $fromns ping -q -f -b -c 1 -q $dstip > /dev/null 2>&1
+		if [ $? -ne 0 ]; then
+			echo "ERROR: ping -b from $fromns to $dstip"
+			ip netns exec ${ns0} nft list ruleset
+			fi
+	done
+}
+
+ip link add veth1 netns ${ns0} type veth peer name eth0 netns ${ns1}
+if [ $? -ne 0 ]; then
+	echo "SKIP: Can't create veth device"
+	exit $ksft_skip
+fi
+
+ip link add veth2 netns ${ns0} type veth peer name eth0 netns $ns2
+ip link add veth3 netns ${ns0} type veth peer name eth0 netns $ns3
+ip link add veth4 netns ${ns0} type veth peer name eth0 netns $ns4
+
+ip -net ${ns0} link set lo up
+
+for i in $(seq 1 4); do
+  ip -net ${ns0} link set veth$i up
+done
+
+ip -net ${ns0} link add br0 type bridge stp_state 0 forward_delay 0 nf_call_iptables 1 nf_call_ip6tables 1 nf_call_arptables 1
+if [ $? -ne 0 ]; then
+	echo "SKIP: Can't create bridge br0"
+	exit $ksft_skip
+fi
+
+# make veth0,1,2 part of bridge.
+for i in $(seq 1 3); do
+  ip -net ${ns0} link set veth$i master br0
+done
+
+# add a macvlan on top of the bridge.
+MACVLAN_ADDR=ba:f3:13:37:42:23
+ip -net ${ns0} link add link br0 name macvlan0 type macvlan mode private
+ip -net ${ns0} link set macvlan0 address ${MACVLAN_ADDR}
+ip -net ${ns0} link set macvlan0 up
+ip -net ${ns0} addr add 10.23.0.1/24 dev macvlan0
+
+# add a macvlan on top of veth4.
+MACVLAN_ADDR=ba:f3:13:37:42:24
+ip -net ${ns0} link add link veth4 name macvlan4 type macvlan mode vepa
+ip -net ${ns0} link set macvlan4 address ${MACVLAN_ADDR}
+ip -net ${ns0} link set macvlan4 up
+
+# make the macvlan part of the bridge.
+# veth4 is not a bridge port, only the macvlan on top of it.
+ip -net ${ns0} link set macvlan4 master br0
+
+ip -net ${ns0} link set br0 up
+ip -net ${ns0} addr add 10.0.0.1/24 dev br0
+ip netns exec ${ns0} sysctl -q net.bridge.bridge-nf-call-iptables=1
+ret=$?
+if [ $ret -ne 0 ] ; then
+	echo "SKIP: bridge netfilter not available"
+	ret=$ksft_skip
+fi
+
+# for testing, so namespaces will reply to ping -b probes.
+ip netns exec ${ns0} sysctl -q net.ipv4.icmp_echo_ignore_broadcasts=0
+
+# enable conntrack in ns0 and drop broadcast packets in forward to
+# avoid them from getting confirmed in the postrouting hook before
+# the cloned skb is passed up the stack.
+ip netns exec ${ns0} nft -f - <<EOF
+table ip filter {
+	chain input {
+		type filter hook input priority 1; policy accept
+		iifname br0 counter
+		ct state new accept
+	}
+}
+
+table bridge filter {
+	chain forward {
+		type filter hook forward priority 0; policy accept
+		meta pkttype broadcast ip protocol icmp counter drop
+	}
+}
+EOF
+
+# place 1, 2 & 3 in same subnet, connected via ns0:br0.
+# ns4 is placed in same subnet as well, but its not
+# part of the bridge: the corresponding veth4 is not
+# part of the bridge, only its macvlan interface.
+for i in $(seq 1 4); do
+  eval ip -net \$ns$i link set lo up
+  eval ip -net \$ns$i link set eth0 up
+done
+for i in $(seq 1 2); do
+  eval ip -net \$ns$i addr add 10.0.0.1$i/24 dev eth0
+done
+
+ip -net ${ns3} addr add 10.23.0.13/24 dev eth0
+ip -net ${ns4} addr add 10.23.0.14/24 dev eth0
+
+# test basic connectivity
+do_ping ${ns1} 10.0.0.12
+do_ping ${ns3} 10.23.0.1
+do_ping ${ns4} 10.23.0.1
+
+if [ $ret -eq 0 ];then
+	echo "PASS: netns connectivity: ns1 can reach ns2, ns3 and ns4 can reach ns0"
+fi
+
+bcast_ping ${ns1} 10.0.0.255
+
+# This should deliver broadcast to macvlan0, which is on top of ns0:br0.
+bcast_ping ${ns3} 10.23.0.255
+
+# same, this time via veth4:macvlan4.
+bcast_ping ${ns4} 10.23.0.255
+
+read t < /proc/sys/kernel/tainted
+
+if [ $t -eq 0 ];then
+	echo PASS: kernel not tainted
+else
+	echo ERROR: kernel is tainted
+	ret=1
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
index f18c6db13bbf..b11ea8ee6719 100644
--- a/tools/testing/selftests/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
@@ -13,7 +13,7 @@
 #include "../kselftest_harness.h"
 
 #define TEST_ZONE_ID 123
-#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2)
+#define NF_CT_DEFAULT_ZONE_ID 0
 
 static int reply_counter;
 
@@ -336,6 +336,9 @@ FIXTURE_SETUP(conntrack_dump_flush)
 	ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5,
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
+	ret = conntrack_data_generate_v4(self->sock, 0xf6f6f6f6, 0xf7f7f7f7,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 
 	src = (struct in6_addr) {{
 		.__u6_addr32 = {
@@ -395,6 +398,26 @@ FIXTURE_SETUP(conntrack_dump_flush)
 					 TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 0);
 
+	src = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x07000000
+		}
+	}};
+	dst = (struct in6_addr) {{
+		.__u6_addr32 = {
+			0xb80d0120,
+			0x00000000,
+			0x00000000,
+			0x08000000
+		}
+	}};
+	ret = conntrack_data_generate_v6(self->sock, src, dst,
+					 NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
 	EXPECT_GE(ret, 2);
 	if (ret > 2)
@@ -425,6 +448,24 @@ TEST_F(conntrack_dump_flush, test_flush_by_zone)
 	EXPECT_EQ(ret, 2);
 	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
 	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+}
+
+TEST_F(conntrack_dump_flush, test_flush_by_zone_default)
+{
+	int ret;
+
+	ret = conntrack_flush_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
+	EXPECT_EQ(ret, 2);
+	ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+	EXPECT_EQ(ret, 0);
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
index 0930e2411dfb..cd51d547b751 100644
--- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -5,6 +5,7 @@
 #include <fcntl.h>
 #include <limits.h>
 #include <linux/types.h>
+#include <poll.h>
 #include <sched.h>
 #include <signal.h>
 #include <stdio.h>
@@ -129,6 +130,7 @@ FIXTURE(child)
 	 * When it is closed, the child will exit.
 	 */
 	int sk;
+	bool ignore_child_result;
 };
 
 FIXTURE_SETUP(child)
@@ -165,10 +167,14 @@ FIXTURE_SETUP(child)
 
 FIXTURE_TEARDOWN(child)
 {
+	int ret;
+
 	EXPECT_EQ(0, close(self->pidfd));
 	EXPECT_EQ(0, close(self->sk));
 
-	EXPECT_EQ(0, wait_for_pid(self->pid));
+	ret = wait_for_pid(self->pid);
+	if (!self->ignore_child_result)
+		EXPECT_EQ(0, ret);
 }
 
 TEST_F(child, disable_ptrace)
@@ -235,6 +241,29 @@ TEST(flags_set)
 	EXPECT_EQ(errno, EINVAL);
 }
 
+TEST_F(child, no_strange_EBADF)
+{
+	struct pollfd fds;
+
+	self->ignore_child_result = true;
+
+	fds.fd = self->pidfd;
+	fds.events = POLLIN;
+
+	ASSERT_EQ(kill(self->pid, SIGKILL), 0);
+	ASSERT_EQ(poll(&fds, 1, 5000), 1);
+
+	/*
+	 * It used to be that pidfd_getfd() could race with the exiting thread
+	 * between exit_files() and release_task(), and get a non-null task
+	 * with a NULL files struct, and you'd get EBADF, which was slightly
+	 * confusing.
+	 */
+	errno = 0;
+	EXPECT_EQ(sys_pidfd_getfd(self->pidfd, self->remote_fd, 0), -1);
+	EXPECT_EQ(errno, ESRCH);
+}
+
 #if __NR_pidfd_getfd == -1
 int main(void)
 {
diff --git a/tools/testing/selftests/power_supply/Makefile b/tools/testing/selftests/power_supply/Makefile
new file mode 100644
index 000000000000..44f0658d3d2e
--- /dev/null
+++ b/tools/testing/selftests/power_supply/Makefile
@@ -0,0 +1,4 @@
+TEST_PROGS := test_power_supply_properties.sh
+TEST_FILES := helpers.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/power_supply/helpers.sh b/tools/testing/selftests/power_supply/helpers.sh
new file mode 100644
index 000000000000..1ec90d7c9108
--- /dev/null
+++ b/tools/testing/selftests/power_supply/helpers.sh
@@ -0,0 +1,178 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022, 2024 Collabora Ltd
+SYSFS_SUPPLIES=/sys/class/power_supply
+
+calc() {
+	awk "BEGIN { print $* }";
+}
+
+test_sysfs_prop() {
+	PROP="$1"
+	VALUE="$2" # optional
+
+	PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP"
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	if [ -z "$VALUE" ]; then
+		ktap_test_result "$TEST_NAME" [ -f "$PROP_PATH" ]
+	else
+		ktap_test_result "$TEST_NAME" grep -q "$VALUE" "$PROP_PATH"
+	fi
+}
+
+to_human_readable_unit() {
+	VALUE="$1"
+	UNIT="$2"
+
+	case "$VALUE" in
+		*[!0-9]* ) return ;; # Not a number
+	esac
+
+	if [ "$UNIT" = "uA" ]; then
+		new_unit="mA"
+		div=1000
+	elif [ "$UNIT" = "uV" ]; then
+		new_unit="V"
+		div=1000000
+	elif [ "$UNIT" = "uAh" ]; then
+		new_unit="Ah"
+		div=1000000
+	elif [ "$UNIT" = "uW" ]; then
+		new_unit="mW"
+		div=1000
+	elif [ "$UNIT" = "uWh" ]; then
+		new_unit="Wh"
+		div=1000000
+	else
+		return
+	fi
+
+	value_converted=$(calc "$VALUE"/"$div")
+	echo "$value_converted" "$new_unit"
+}
+
+_check_sysfs_prop_available() {
+	PROP=$1
+
+	PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP"
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	if [ ! -e "$PROP_PATH" ] ; then
+		ktap_test_skip "$TEST_NAME"
+		return 1
+	fi
+
+	if ! cat "$PROP_PATH" >/dev/null; then
+		ktap_print_msg "Failed to read"
+		ktap_test_fail "$TEST_NAME"
+		return 1
+	fi
+
+	return 0
+}
+
+test_sysfs_prop_optional() {
+	PROP=$1
+	UNIT=$2 # optional
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))"
+	ktap_test_pass "$TEST_NAME"
+}
+
+test_sysfs_prop_optional_range() {
+	PROP=$1
+	MIN=$2
+	MAX=$3
+	UNIT=$4 # optional
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	if [ "$DATA" -lt "$MIN" ] || [ "$DATA" -gt "$MAX" ]; then
+		ktap_print_msg "'$DATA' is out of range (min=$MIN, max=$MAX)"
+		ktap_test_fail "$TEST_NAME"
+	else
+		ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))"
+		ktap_test_pass "$TEST_NAME"
+	fi
+}
+
+test_sysfs_prop_optional_list() {
+	PROP=$1
+	LIST=$2
+
+	TEST_NAME="$DEVNAME".sysfs."$PROP"
+
+	_check_sysfs_prop_available "$PROP" || return
+	DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP")
+
+	valid=0
+
+	OLDIFS=$IFS
+	IFS=","
+	for item in $LIST; do
+		if [ "$DATA" = "$item" ]; then
+			valid=1
+			break
+		fi
+	done
+	if [ "$valid" -eq 1 ]; then
+		ktap_print_msg "Reported: '$DATA'"
+		ktap_test_pass "$TEST_NAME"
+	else
+		ktap_print_msg "'$DATA' is not a valid value for this property"
+		ktap_test_fail "$TEST_NAME"
+	fi
+	IFS=$OLDIFS
+}
+
+dump_file() {
+	FILE="$1"
+	while read -r line; do
+		ktap_print_msg "$line"
+	done < "$FILE"
+}
+
+__test_uevent_prop() {
+	PROP="$1"
+	OPTIONAL="$2"
+	VALUE="$3" # optional
+
+	UEVENT_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/uevent
+	TEST_NAME="$DEVNAME".uevent."$PROP"
+
+	if ! grep -q "POWER_SUPPLY_$PROP=" "$UEVENT_PATH"; then
+		if [ "$OPTIONAL" -eq 1 ]; then
+			ktap_test_skip "$TEST_NAME"
+		else
+			ktap_print_msg "Missing property"
+			ktap_test_fail "$TEST_NAME"
+		fi
+		return
+	fi
+
+	if ! grep -q "POWER_SUPPLY_$PROP=$VALUE" "$UEVENT_PATH"; then
+		ktap_print_msg "Invalid value for uevent property, dumping..."
+		dump_file "$UEVENT_PATH"
+		ktap_test_fail "$TEST_NAME"
+	else
+		ktap_test_pass "$TEST_NAME"
+	fi
+}
+
+test_uevent_prop() {
+	__test_uevent_prop "$1" 0 "$2"
+}
+
+test_uevent_prop_optional() {
+	__test_uevent_prop "$1" 1 "$2"
+}
diff --git a/tools/testing/selftests/power_supply/test_power_supply_properties.sh b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
new file mode 100755
index 000000000000..df272dfe1d2a
--- /dev/null
+++ b/tools/testing/selftests/power_supply/test_power_supply_properties.sh
@@ -0,0 +1,114 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022, 2024 Collabora Ltd
+#
+# This test validates the power supply uAPI: namely, the files in sysfs and
+# lines in uevent that expose the power supply properties.
+#
+# By default all power supplies available are tested. Optionally the name of a
+# power supply can be passed as a parameter to test only that one instead.
+DIR="$(dirname "$(readlink -f "$0")")"
+
+. "${DIR}"/../kselftest/ktap_helpers.sh
+
+. "${DIR}"/helpers.sh
+
+count_tests() {
+	SUPPLIES=$1
+
+	# This needs to be updated every time a new test is added.
+	NUM_TESTS=33
+
+	total_tests=0
+
+	for i in $SUPPLIES; do
+		total_tests=$(("$total_tests" + "$NUM_TESTS"))
+	done
+
+	echo "$total_tests"
+}
+
+ktap_print_header
+
+SYSFS_SUPPLIES=/sys/class/power_supply/
+
+if [ $# -eq 0 ]; then
+	supplies=$(ls "$SYSFS_SUPPLIES")
+else
+	supplies=$1
+fi
+
+ktap_set_plan "$(count_tests "$supplies")"
+
+for DEVNAME in $supplies; do
+	ktap_print_msg Testing device "$DEVNAME"
+
+	if [ ! -d "$SYSFS_SUPPLIES"/"$DEVNAME" ]; then
+		ktap_test_fail "$DEVNAME".exists
+		ktap_exit_fail_msg Device does not exist
+	fi
+
+	ktap_test_pass "$DEVNAME".exists
+
+	test_uevent_prop NAME "$DEVNAME"
+
+	test_sysfs_prop type
+	SUPPLY_TYPE=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/type)
+	# This fails on kernels < 5.8 (needs 2ad3d74e3c69f)
+	test_uevent_prop TYPE "$SUPPLY_TYPE"
+
+	test_sysfs_prop_optional usb_type
+
+	test_sysfs_prop_optional_range online 0 2
+	test_sysfs_prop_optional_range present 0 1
+
+	test_sysfs_prop_optional_list status "Unknown","Charging","Discharging","Not charging","Full"
+
+	# Capacity is reported as percentage, thus any value less than 0 and
+	# greater than 100 are not allowed.
+	test_sysfs_prop_optional_range capacity 0 100 "%"
+
+	test_sysfs_prop_optional_list capacity_level "Unknown","Critical","Low","Normal","High","Full"
+
+	test_sysfs_prop_optional model_name
+	test_sysfs_prop_optional manufacturer
+	test_sysfs_prop_optional serial_number
+	test_sysfs_prop_optional_list technology "Unknown","NiMH","Li-ion","Li-poly","LiFe","NiCd","LiMn"
+
+	test_sysfs_prop_optional cycle_count
+
+	test_sysfs_prop_optional_list scope "Unknown","System","Device"
+
+	test_sysfs_prop_optional input_current_limit "uA"
+	test_sysfs_prop_optional input_voltage_limit "uV"
+
+	# Technically the power-supply class does not limit reported values.
+	# E.g. one could expose an RTC backup-battery, which goes below 1.5V or
+	# an electric vehicle battery with over 300V. But most devices do not
+	# have a step-up capable regulator behind the battery and operate with
+	# voltages considered safe to touch, so we limit the allowed range to
+	# 1.8V-60V to catch drivers reporting incorrectly scaled values. E.g. a
+	# common mistake is reporting data in mV instead of µV.
+	test_sysfs_prop_optional_range voltage_now 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_min 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_max 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_min_design 1800000 60000000 "uV"
+	test_sysfs_prop_optional_range voltage_max_design 1800000 60000000 "uV"
+
+	# current based systems
+	test_sysfs_prop_optional current_now "uA"
+	test_sysfs_prop_optional current_max "uA"
+	test_sysfs_prop_optional charge_now "uAh"
+	test_sysfs_prop_optional charge_full "uAh"
+	test_sysfs_prop_optional charge_full_design "uAh"
+
+	# power based systems
+	test_sysfs_prop_optional power_now "uW"
+	test_sysfs_prop_optional energy_now "uWh"
+	test_sysfs_prop_optional energy_full "uWh"
+	test_sysfs_prop_optional energy_full_design "uWh"
+	test_sysfs_prop_optional energy_full_design "uWh"
+done
+
+ktap_finished
diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c
index 7b1addd50420..8a64f63e37ce 100644
--- a/tools/testing/selftests/powerpc/math/fpu_signal.c
+++ b/tools/testing/selftests/powerpc/math/fpu_signal.c
@@ -18,6 +18,7 @@
 #include <pthread.h>
 
 #include "utils.h"
+#include "fpu.h"
 
 /* Number of times each thread should receive the signal */
 #define ITERATIONS 10
@@ -27,9 +28,7 @@
  */
 #define THREAD_FACTOR 8
 
-__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0,
-		     1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0,
-		     2.1};
+__thread double darray[32];
 
 bool bad_context;
 int threads_starting;
@@ -43,9 +42,9 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context)
 	ucontext_t *uc = context;
 	mcontext_t *mc = &uc->uc_mcontext;
 
-	/* Only the non volatiles were loaded up */
-	for (i = 14; i < 32; i++) {
-		if (mc->fp_regs[i] != darray[i - 14]) {
+	// Don't check f30/f31, they're used as scratches in check_all_fprs()
+	for (i = 0; i < 30; i++) {
+		if (mc->fp_regs[i] != darray[i]) {
 			bad_context = true;
 			break;
 		}
@@ -54,7 +53,6 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context)
 
 void *signal_fpu_c(void *p)
 {
-	int i;
 	long rc;
 	struct sigaction act;
 	act.sa_sigaction = signal_fpu_sig;
@@ -64,9 +62,7 @@ void *signal_fpu_c(void *p)
 		return p;
 
 	srand(pthread_self());
-	for (i = 0; i < 21; i++)
-		darray[i] = rand();
-
+	randomise_darray(darray, ARRAY_SIZE(darray));
 	rc = preempt_fpu(darray, &threads_starting, &running);
 
 	return (void *) rc;
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
index 98cbb9109ee6..505294da1b9f 100644
--- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -263,10 +263,10 @@ static int papr_vpd_system_loc_code(void)
 	off_t size;
 	int fd;
 
-	SKIP_IF_MSG(get_system_loc_code(&lc),
-		    "Cannot determine system location code");
 	SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
 		    DEVPATH " not present");
+	SKIP_IF_MSG(get_system_loc_code(&lc),
+		    "Cannot determine system location code");
 
 	FAIL_IF(devfd < 0);
 
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index d5a0d8a33c27..bbac5f4b03d0 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -567,7 +567,7 @@ then
 	torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog"
 	torture_set "clocksourcewd-1" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make
 
-	torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 clocksource.max_cswd_read_retries=1 tsc=watchdog"
+	torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog"
 	torture_set "clocksourcewd-2" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make
 
 	# In case our work is already done...
diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index bcbca356d56a..1b339d6bbff1 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -3,106 +3,59 @@
 #include <stdint.h>
 #include "resctrl.h"
 
-struct read_format {
-	__u64 nr;			/* The number of events */
-	struct {
-		__u64 value;		/* The value of the event */
-	} values[2];
-};
-
-static struct perf_event_attr pea_llc_miss;
-static struct read_format rf_cqm;
-static int fd_lm;
 char llc_occup_path[1024];
 
-static void initialize_perf_event_attr(void)
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 {
-	pea_llc_miss.type = PERF_TYPE_HARDWARE;
-	pea_llc_miss.size = sizeof(struct perf_event_attr);
-	pea_llc_miss.read_format = PERF_FORMAT_GROUP;
-	pea_llc_miss.exclude_kernel = 1;
-	pea_llc_miss.exclude_hv = 1;
-	pea_llc_miss.exclude_idle = 1;
-	pea_llc_miss.exclude_callchain_kernel = 1;
-	pea_llc_miss.inherit = 1;
-	pea_llc_miss.exclude_guest = 1;
-	pea_llc_miss.disabled = 1;
-}
-
-static void ioctl_perf_event_ioc_reset_enable(void)
-{
-	ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0);
-	ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0);
-}
-
-static int perf_event_open_llc_miss(pid_t pid, int cpu_no)
-{
-	fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1,
-				PERF_FLAG_FD_CLOEXEC);
-	if (fd_lm == -1) {
-		perror("Error opening leader");
-		ctrlc_handler(0, NULL, NULL);
-		return -1;
-	}
-
-	return 0;
-}
-
-static void initialize_llc_perf(void)
-{
-	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
-	memset(&rf_cqm, 0, sizeof(struct read_format));
-
-	/* Initialize perf_event_attr structures for HW_CACHE_MISSES */
-	initialize_perf_event_attr();
-
-	pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES;
-
-	rf_cqm.nr = 1;
+	memset(pea, 0, sizeof(*pea));
+	pea->type = PERF_TYPE_HARDWARE;
+	pea->size = sizeof(*pea);
+	pea->read_format = PERF_FORMAT_GROUP;
+	pea->exclude_kernel = 1;
+	pea->exclude_hv = 1;
+	pea->exclude_idle = 1;
+	pea->exclude_callchain_kernel = 1;
+	pea->inherit = 1;
+	pea->exclude_guest = 1;
+	pea->disabled = 1;
+	pea->config = config;
 }
 
-static int reset_enable_llc_perf(pid_t pid, int cpu_no)
+/* Start counters to log values */
+int perf_event_reset_enable(int pe_fd)
 {
-	int ret = 0;
+	int ret;
 
-	ret = perf_event_open_llc_miss(pid, cpu_no);
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
 	if (ret < 0)
 		return ret;
 
-	/* Start counters to log values */
-	ioctl_perf_event_ioc_reset_enable();
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
 
-/*
- * get_llc_perf:	llc cache miss through perf events
- * @llc_perf_miss:	LLC miss counter that is filled on success
- *
- * Perf events like HW_CACHE_MISSES could be used to validate number of
- * cache lines allocated.
- *
- * Return: =0 on success.  <0 on failure.
- */
-static int get_llc_perf(unsigned long *llc_perf_miss)
+void perf_event_initialize_read_format(struct perf_event_read *pe_read)
 {
-	__u64 total_misses;
-	int ret;
-
-	/* Stop counters after one span to get miss rate */
+	memset(pe_read, 0, sizeof(*pe_read));
+	pe_read->nr = 1;
+}
 
-	ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
+{
+	int pe_fd;
 
-	ret = read(fd_lm, &rf_cqm, sizeof(struct read_format));
-	if (ret == -1) {
-		perror("Could not get llc misses through perf");
+	pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
+	if (pe_fd == -1) {
+		ksft_perror("Error opening leader");
 		return -1;
 	}
 
-	total_misses = rf_cqm.values[0].value;
-	*llc_perf_miss = total_misses;
+	perf_event_reset_enable(pe_fd);
 
-	return 0;
+	return pe_fd;
 }
 
 /*
@@ -124,12 +77,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
 
 	fp = fopen(llc_occup_path, "r");
 	if (!fp) {
-		perror("Failed to open results file");
+		ksft_perror("Failed to open results file");
 
-		return errno;
+		return -1;
 	}
 	if (fscanf(fp, "%lu", llc_occupancy) <= 0) {
-		perror("Could not get llc occupancy");
+		ksft_perror("Could not get llc occupancy");
 		fclose(fp);
 
 		return -1;
@@ -146,163 +99,91 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  * @llc_value:		perf miss value /
  *			llc occupancy value reported by resctrl FS
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
-static int print_results_cache(char *filename, int bm_pid,
-			       unsigned long llc_value)
+static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value)
 {
 	FILE *fp;
 
 	if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
-		printf("Pid: %d \t LLC_value: %lu\n", bm_pid,
-		       llc_value);
+		printf("Pid: %d \t LLC_value: %llu\n", bm_pid, llc_value);
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
-			perror("Cannot open results file");
+			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
-		fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value);
+		fprintf(fp, "Pid: %d \t llc_value: %llu\n", bm_pid, llc_value);
 		fclose(fp);
 	}
 
 	return 0;
 }
 
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid)
+/*
+ * perf_event_measure - Measure perf events
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
+ *
+ * Measures perf events (e.g., cache misses) and writes the results into
+ * @filename. @bm_pid is written to the results file along with the measured
+ * value.
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid)
 {
-	unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0;
 	int ret;
 
-	/*
-	 * Measure cache miss from perf.
-	 */
-	if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) {
-		ret = get_llc_perf(&llc_perf_miss);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_perf_miss;
-	}
+	/* Stop counters after one span to get miss rate */
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
+	if (ret < 0)
+		return ret;
 
-	/*
-	 * Measure llc occupancy from resctrl.
-	 */
-	if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) {
-		ret = get_llc_occu_resctrl(&llc_occu_resc);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_occu_resc;
+	ret = read(pe_fd, pe_read, sizeof(*pe_read));
+	if (ret == -1) {
+		ksft_perror("Could not get perf value");
+		return -1;
 	}
-	ret = print_results_cache(param->filename, bm_pid, llc_value);
-	if (ret)
-		return ret;
 
-	return 0;
+	return print_results_cache(filename, bm_pid, pe_read->values[0].value);
 }
 
 /*
- * cache_val:		execute benchmark and measure LLC occupancy resctrl
- * and perf cache miss for the benchmark
- * @param:		parameters passed to cache_val()
- * @span:		buffer size for the benchmark
+ * measure_llc_resctrl - Measure resctrl LLC value from resctrl
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
  *
- * Return:		0 on success. non-zero on failure.
+ * Measures LLC occupancy from resctrl and writes the results into @filename.
+ * @bm_pid is written to the results file along with the measured value.
+ *
+ * Return: =0 on success. <0 on failure.
  */
-int cat_val(struct resctrl_val_param *param, size_t span)
+int measure_llc_resctrl(const char *filename, int bm_pid)
 {
-	int memflush = 1, operation = 0, ret = 0;
-	char *resctrl_val = param->resctrl_val;
-	pid_t bm_pid;
-
-	if (strcmp(param->filename, "") == 0)
-		sprintf(param->filename, "stdio");
-
-	bm_pid = getpid();
-
-	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
-	if (ret)
-		return ret;
+	unsigned long llc_occu_resc = 0;
+	int ret;
 
-	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
-				      resctrl_val);
-	if (ret)
+	ret = get_llc_occu_resctrl(&llc_occu_resc);
+	if (ret < 0)
 		return ret;
 
-	initialize_llc_perf();
-
-	/* Test runs until the callback setup() tells the test to stop. */
-	while (1) {
-		ret = param->setup(param);
-		if (ret == END_OF_TESTS) {
-			ret = 0;
-			break;
-		}
-		if (ret < 0)
-			break;
-		ret = reset_enable_llc_perf(bm_pid, param->cpu_no);
-		if (ret)
-			break;
-
-		if (run_fill_buf(span, memflush, operation, true)) {
-			fprintf(stderr, "Error-running fill buffer\n");
-			ret = -1;
-			goto pe_close;
-		}
-
-		sleep(1);
-		ret = measure_cache_vals(param, bm_pid);
-		if (ret)
-			goto pe_close;
-	}
-
-	return ret;
-
-pe_close:
-	close(fd_lm);
-	return ret;
+	return print_results_cache(filename, bm_pid, llc_occu_resc);
 }
 
 /*
- * show_cache_info:	show cache test result information
- * @sum_llc_val:	sum of LLC cache result data
- * @no_of_bits:		number of bits
- * @cache_span:		cache span in bytes for CMT or in lines for CAT
- * @max_diff:		max difference
- * @max_diff_percent:	max difference percentage
- * @num_of_runs:	number of runs
- * @platform:		show test information on this platform
- * @cmt:		CMT test or CAT test
- *
- * Return:		0 on success. non-zero on failure.
+ * show_cache_info - Show generic cache test information
+ * @no_of_bits:		Number of bits
+ * @avg_llc_val:	Average of LLC cache result data
+ * @cache_span:		Cache span
+ * @lines:		@cache_span in lines or bytes
  */
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt)
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines)
 {
-	unsigned long avg_llc_val = 0;
-	float diff_percent;
-	long avg_diff = 0;
-	int ret;
-
-	avg_llc_val = sum_llc_val / num_of_runs;
-	avg_diff = (long)abs(cache_span - avg_llc_val);
-	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
-
-	ret = platform && abs((int)diff_percent) > max_diff_percent &&
-	      (cmt ? (abs(avg_diff) > max_diff) : true);
-
-	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
-		       ret ? "Fail:" : "Pass:", max_diff_percent);
-
-	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
 	ksft_print_msg("Number of bits: %d\n", no_of_bits);
-	ksft_print_msg("Average LLC val: %lu\n", avg_llc_val);
-	ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines",
+	ksft_print_msg("Average LLC val: %llu\n", avg_llc_val);
+	ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes",
 		       cache_span);
-
-	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 224ba8544d8a..4cb991be8e31 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -11,108 +11,254 @@
 #include "resctrl.h"
 #include <unistd.h>
 
-#define RESULT_FILE_NAME1	"result_cat1"
-#define RESULT_FILE_NAME2	"result_cat2"
+#define RESULT_FILE_NAME	"result_cat"
 #define NUM_OF_RUNS		5
-#define MAX_DIFF_PERCENT	4
-#define MAX_DIFF		1000000
 
 /*
- * Change schemata. Write schemata to specified
- * con_mon grp, mon_grp in resctrl FS.
- * Run 5 times in order to get average values.
+ * Minimum difference in LLC misses between a test with n+1 bits CBM to the
+ * test with n bits is MIN_DIFF_PERCENT_PER_BIT * (n - 1). With e.g. 5 vs 4
+ * bits in the CBM mask, the minimum difference must be at least
+ * MIN_DIFF_PERCENT_PER_BIT * (4 - 1) = 3 percent.
+ *
+ * The relationship between number of used CBM bits and difference in LLC
+ * misses is not expected to be linear. With a small number of bits, the
+ * margin is smaller than with larger number of bits. For selftest purposes,
+ * however, linear approach is enough because ultimately only pass/fail
+ * decision has to be made and distinction between strong and stronger
+ * signal is irrelevant.
  */
-static int cat_setup(struct resctrl_val_param *p)
+#define MIN_DIFF_PERCENT_PER_BIT	1UL
+
+static int show_results_info(__u64 sum_llc_val, int no_of_bits,
+			     unsigned long cache_span,
+			     unsigned long min_diff_percent,
+			     unsigned long num_of_runs, bool platform,
+			     __s64 *prev_avg_llc_val)
 {
-	char schemata[64];
+	__u64 avg_llc_val = 0;
+	float avg_diff;
 	int ret = 0;
 
-	/* Run NUM_OF_RUNS times */
-	if (p->num_of_runs >= NUM_OF_RUNS)
-		return END_OF_TESTS;
+	avg_llc_val = sum_llc_val / num_of_runs;
+	if (*prev_avg_llc_val) {
+		float delta = (__s64)(avg_llc_val - *prev_avg_llc_val);
+
+		avg_diff = delta / *prev_avg_llc_val;
+		ret = platform && (avg_diff * 100) < (float)min_diff_percent;
+
+		ksft_print_msg("%s Check cache miss rate changed more than %.1f%%\n",
+			       ret ? "Fail:" : "Pass:", (float)min_diff_percent);
 
-	if (p->num_of_runs == 0) {
-		sprintf(schemata, "%lx", p->mask);
-		ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no,
-				     p->resctrl_val);
+		ksft_print_msg("Percent diff=%.1f\n", avg_diff * 100);
 	}
-	p->num_of_runs++;
+	*prev_avg_llc_val = avg_llc_val;
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, true);
 
 	return ret;
 }
 
-static int check_results(struct resctrl_val_param *param, size_t span)
+/* Remove the highest bit from CBM */
+static unsigned long next_mask(unsigned long current_mask)
+{
+	return current_mask & (current_mask >> 1);
+}
+
+static int check_results(struct resctrl_val_param *param, const char *cache_type,
+			 unsigned long cache_total_size, unsigned long full_cache_mask,
+			 unsigned long current_mask)
 {
 	char *token_array[8], temp[512];
-	unsigned long sum_llc_perf_miss = 0;
-	int runs = 0, no_of_bits = 0;
+	__u64 sum_llc_perf_miss = 0;
+	__s64 prev_avg_llc_val = 0;
+	unsigned long alloc_size;
+	int runs = 0;
+	int fail = 0;
+	int ret;
 	FILE *fp;
 
 	ksft_print_msg("Checking for pass/fail\n");
 	fp = fopen(param->filename, "r");
 	if (!fp) {
-		perror("# Cannot open file");
+		ksft_perror("Cannot open file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
 		char *token = strtok(temp, ":\t");
 		int fields = 0;
+		int bits;
 
 		while (token) {
 			token_array[fields++] = token;
 			token = strtok(NULL, ":\t");
 		}
-		/*
-		 * Discard the first value which is inaccurate due to monitoring
-		 * setup transition phase.
-		 */
-		if (runs > 0)
-			sum_llc_perf_miss += strtoul(token_array[3], NULL, 0);
+
+		sum_llc_perf_miss += strtoull(token_array[3], NULL, 0);
 		runs++;
+
+		if (runs < NUM_OF_RUNS)
+			continue;
+
+		if (!current_mask) {
+			ksft_print_msg("Unexpected empty cache mask\n");
+			break;
+		}
+
+		alloc_size = cache_portion_size(cache_total_size, current_mask, full_cache_mask);
+
+		bits = count_bits(current_mask);
+
+		ret = show_results_info(sum_llc_perf_miss, bits,
+					alloc_size / 64,
+					MIN_DIFF_PERCENT_PER_BIT * (bits - 1),
+					runs, get_vendor() == ARCH_INTEL,
+					&prev_avg_llc_val);
+		if (ret)
+			fail = 1;
+
+		runs = 0;
+		sum_llc_perf_miss = 0;
+		current_mask = next_mask(current_mask);
 	}
 
 	fclose(fp);
-	no_of_bits = count_bits(param->mask);
 
-	return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       get_vendor() == ARCH_INTEL, false);
+	return fail;
 }
 
 void cat_test_cleanup(void)
 {
-	remove(RESULT_FILE_NAME1);
-	remove(RESULT_FILE_NAME2);
+	remove(RESULT_FILE_NAME);
 }
 
-int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
+/*
+ * cat_test - Execute CAT benchmark and measure cache misses
+ * @test:		Test information structure
+ * @uparams:		User supplied parameters
+ * @param:		Parameters passed to cat_test()
+ * @span:		Buffer size for the benchmark
+ * @current_mask	Start mask for the first iteration
+ *
+ * Run CAT selftest by varying the allocated cache portion and comparing the
+ * impact on cache misses (the result analysis is done in check_results()
+ * and show_results_info(), not in this function).
+ *
+ * One bit is removed from the CAT allocation bit mask (in current_mask) for
+ * each subsequent test which keeps reducing the size of the allocated cache
+ * portion. A single test flushes the buffer, reads it to warm up the cache,
+ * and reads the buffer again. The cache misses are measured during the last
+ * read pass.
+ *
+ * Return:		0 when the test was run, < 0 on error.
+ */
+static int cat_test(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    struct resctrl_val_param *param,
+		    size_t span, unsigned long current_mask)
 {
-	unsigned long l_mask, l_mask_1;
-	int ret, pipefd[2], sibling_cpu_no;
-	unsigned long cache_size = 0;
-	unsigned long long_mask;
-	char cbm_mask[256];
+	char *resctrl_val = param->resctrl_val;
+	struct perf_event_read pe_read;
+	struct perf_event_attr pea;
+	cpu_set_t old_affinity;
+	unsigned char *buf;
+	char schemata[64];
+	int ret, i, pe_fd;
+	pid_t bm_pid;
+
+	if (strcmp(param->filename, "") == 0)
+		sprintf(param->filename, "stdio");
+
+	bm_pid = getpid();
+
+	/* Taskset benchmark to specified cpu */
+	ret = taskset_benchmark(bm_pid, uparams->cpu, &old_affinity);
+	if (ret)
+		return ret;
+
+	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
+	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
+				      resctrl_val);
+	if (ret)
+		goto reset_affinity;
+
+	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
+	perf_event_initialize_read_format(&pe_read);
+	pe_fd = perf_open(&pea, bm_pid, uparams->cpu);
+	if (pe_fd < 0) {
+		ret = -1;
+		goto reset_affinity;
+	}
+
+	buf = alloc_buffer(span, 1);
+	if (!buf) {
+		ret = -1;
+		goto pe_close;
+	}
+
+	while (current_mask) {
+		snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask);
+		ret = write_schemata("", schemata, uparams->cpu, test->resource);
+		if (ret)
+			goto free_buf;
+		snprintf(schemata, sizeof(schemata), "%lx", current_mask);
+		ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
+		if (ret)
+			goto free_buf;
+
+		for (i = 0; i < NUM_OF_RUNS; i++) {
+			mem_flush(buf, span);
+			fill_cache_read(buf, span, true);
+
+			ret = perf_event_reset_enable(pe_fd);
+			if (ret)
+				goto free_buf;
+
+			fill_cache_read(buf, span, true);
+
+			ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
+			if (ret)
+				goto free_buf;
+		}
+		current_mask = next_mask(current_mask);
+	}
+
+free_buf:
+	free(buf);
+pe_close:
+	close(pe_fd);
+reset_affinity:
+	taskset_restore(bm_pid, &old_affinity);
+
+	return ret;
+}
+
+static int cat_run_test(const struct resctrl_test *test, const struct user_params *uparams)
+{
+	unsigned long long_mask, start_mask, full_cache_mask;
+	unsigned long cache_total_size = 0;
+	int n = uparams->bits;
+	unsigned int start;
 	int count_of_bits;
-	char pipe_message;
 	size_t span;
+	int ret;
 
-	/* Get default cbm mask for L3/L2 cache */
-	ret = get_cbm_mask(cache_type, cbm_mask);
+	ret = get_full_cbm(test->resource, &full_cache_mask);
+	if (ret)
+		return ret;
+	/* Get the largest contiguous exclusive portion of the cache */
+	ret = get_mask_no_shareable(test->resource, &long_mask);
 	if (ret)
 		return ret;
-
-	long_mask = strtoul(cbm_mask, NULL, 16);
 
 	/* Get L3/L2 cache size */
-	ret = get_cache_size(cpu_no, cache_type, &cache_size);
+	ret = get_cache_size(uparams->cpu, test->resource, &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
-	/* Get max number of bits from default-cabm mask */
-	count_of_bits = count_bits(long_mask);
+	count_of_bits = count_contiguous_bits(long_mask, &start);
 
 	if (!n)
 		n = count_of_bits / 2;
@@ -123,89 +269,124 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 			       count_of_bits - 1);
 		return -1;
 	}
-
-	/* Get core id from same socket for running another thread */
-	sibling_cpu_no = get_core_sibling(cpu_no);
-	if (sibling_cpu_no < 0)
-		return -1;
+	start_mask = create_bit_mask(start, n);
 
 	struct resctrl_val_param param = {
 		.resctrl_val	= CAT_STR,
-		.cpu_no		= cpu_no,
-		.setup		= cat_setup,
+		.ctrlgrp	= "c1",
+		.filename	= RESULT_FILE_NAME,
+		.num_of_runs	= 0,
 	};
+	param.mask = long_mask;
+	span = cache_portion_size(cache_total_size, start_mask, full_cache_mask);
 
-	l_mask = long_mask >> n;
-	l_mask_1 = ~l_mask & long_mask;
+	remove(param.filename);
 
-	/* Set param values for parent thread which will be allocated bitmask
-	 * with (max_bits - n) bits
-	 */
-	span = cache_size * (count_of_bits - n) / count_of_bits;
-	strcpy(param.ctrlgrp, "c2");
-	strcpy(param.mongrp, "m2");
-	strcpy(param.filename, RESULT_FILE_NAME2);
-	param.mask = l_mask;
-	param.num_of_runs = 0;
-
-	if (pipe(pipefd)) {
-		perror("# Unable to create pipe");
-		return errno;
-	}
+	ret = cat_test(test, uparams, &param, span, start_mask);
+	if (ret)
+		goto out;
 
-	fflush(stdout);
-	bm_pid = fork();
+	ret = check_results(&param, test->resource,
+			    cache_total_size, full_cache_mask, start_mask);
+out:
+	cat_test_cleanup();
 
-	/* Set param values for child thread which will be allocated bitmask
-	 * with n bits
-	 */
-	if (bm_pid == 0) {
-		param.mask = l_mask_1;
-		strcpy(param.ctrlgrp, "c1");
-		strcpy(param.mongrp, "m1");
-		span = cache_size * n / count_of_bits;
-		strcpy(param.filename, RESULT_FILE_NAME1);
-		param.num_of_runs = 0;
-		param.cpu_no = sibling_cpu_no;
+	return ret;
+}
+
+static int noncont_cat_run_test(const struct resctrl_test *test,
+				const struct user_params *uparams)
+{
+	unsigned long full_cache_mask, cont_mask, noncont_mask;
+	unsigned int eax, ebx, ecx, edx, sparse_masks;
+	int bit_center, ret;
+	char schemata[64];
+
+	/* Check to compare sparse_masks content to CPUID output. */
+	ret = resource_info_unsigned_get(test->resource, "sparse_masks", &sparse_masks);
+	if (ret)
+		return ret;
+
+	if (!strcmp(test->resource, "L3"))
+		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
+	else if (!strcmp(test->resource, "L2"))
+		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
+	else
+		return -EINVAL;
+
+	if (sparse_masks != ((ecx >> 3) & 1)) {
+		ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n");
+		return 1;
 	}
 
-	remove(param.filename);
+	/* Write checks initialization. */
+	ret = get_full_cbm(test->resource, &full_cache_mask);
+	if (ret < 0)
+		return ret;
+	bit_center = count_bits(full_cache_mask) / 2;
 
-	ret = cat_val(&param, span);
-	if (ret == 0)
-		ret = check_results(&param, span);
-
-	if (bm_pid == 0) {
-		/* Tell parent that child is ready */
-		close(pipefd[0]);
-		pipe_message = 1;
-		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
-		    sizeof(pipe_message))
-			/*
-			 * Just print the error message.
-			 * Let while(1) run and wait for itself to be killed.
-			 */
-			perror("# failed signaling parent process");
-
-		close(pipefd[1]);
-		while (1)
-			;
-	} else {
-		/* Parent waits for child to be ready. */
-		close(pipefd[1]);
-		pipe_message = 0;
-		while (pipe_message != 1) {
-			if (read(pipefd[0], &pipe_message,
-				 sizeof(pipe_message)) < sizeof(pipe_message)) {
-				perror("# failed reading from child process");
-				break;
-			}
-		}
-		close(pipefd[0]);
-		kill(bm_pid, SIGKILL);
+	/*
+	 * The bit_center needs to be at least 3 to properly calculate the CBM
+	 * hole in the noncont_mask. If it's smaller return an error since the
+	 * cache mask is too short and that shouldn't happen.
+	 */
+	if (bit_center < 3)
+		return -EINVAL;
+	cont_mask = full_cache_mask >> bit_center;
+
+	/* Contiguous mask write check. */
+	snprintf(schemata, sizeof(schemata), "%lx", cont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret) {
+		ksft_print_msg("Write of contiguous CBM failed\n");
+		return 1;
 	}
 
-	cat_test_cleanup();
+	/*
+	 * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle.
+	 * Output is compared with support information to catch any edge case errors.
+	 */
+	noncont_mask = ~(0xfUL << (bit_center - 2)) & full_cache_mask;
+	snprintf(schemata, sizeof(schemata), "%lx", noncont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret && sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs supported but write of non-contiguous CBM failed\n");
+	else if (ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported and write of non-contiguous CBM failed as expected\n");
+	else if (!ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported but write of non-contiguous CBM succeeded\n");
+
+	return !ret == !sparse_masks;
+}
 
-	return ret;
+static bool noncont_cat_feature_check(const struct resctrl_test *test)
+{
+	if (!resctrl_resource_exists(test->resource))
+		return false;
+
+	return resource_info_file_exists(test->resource, "sparse_masks");
 }
+
+struct resctrl_test l3_cat_test = {
+	.name = "L3_CAT",
+	.group = "CAT",
+	.resource = "L3",
+	.feature_check = test_resource_feature_check,
+	.run_test = cat_run_test,
+};
+
+struct resctrl_test l3_noncont_cat_test = {
+	.name = "L3_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L3",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
+
+struct resctrl_test l2_noncont_cat_test = {
+	.name = "L2_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L2",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 50bdbce9fba9..a81f91222a89 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -16,7 +16,9 @@
 #define MAX_DIFF		2000000
 #define MAX_DIFF_PERCENT	15
 
-static int cmt_setup(struct resctrl_val_param *p)
+static int cmt_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	/* Run NUM_OF_RUNS times */
 	if (p->num_of_runs >= NUM_OF_RUNS)
@@ -27,6 +29,33 @@ static int cmt_setup(struct resctrl_val_param *p)
 	return 0;
 }
 
+static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
+			     unsigned long cache_span, unsigned long max_diff,
+			     unsigned long max_diff_percent, unsigned long num_of_runs,
+			     bool platform)
+{
+	unsigned long avg_llc_val = 0;
+	float diff_percent;
+	long avg_diff = 0;
+	int ret;
+
+	avg_llc_val = sum_llc_val / num_of_runs;
+	avg_diff = (long)abs(cache_span - avg_llc_val);
+	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
+
+	ret = platform && abs((int)diff_percent) > max_diff_percent &&
+	      abs(avg_diff) > max_diff;
+
+	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
+		       ret ? "Fail:" : "Pass:", max_diff_percent);
+
+	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, false);
+
+	return ret;
+}
+
 static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits)
 {
 	char *token_array[8], temp[512];
@@ -37,9 +66,9 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	ksft_print_msg("Checking for pass/fail\n");
 	fp = fopen(param->filename, "r");
 	if (!fp) {
-		perror("# Error in opening file\n");
+		ksft_perror("Error in opening file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
@@ -58,9 +87,8 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	}
 	fclose(fp);
 
-	return show_cache_info(sum_llc_occu_resc, no_of_bits, span,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       true, true);
+	return show_results_info(sum_llc_occu_resc, no_of_bits, span,
+				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true);
 }
 
 void cmt_test_cleanup(void)
@@ -68,28 +96,26 @@ void cmt_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
+static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	const char * const *cmd = benchmark_cmd;
+	const char * const *cmd = uparams->benchmark_cmd;
 	const char *new_cmd[BENCHMARK_ARGS];
-	unsigned long cache_size = 0;
+	unsigned long cache_total_size = 0;
+	int n = uparams->bits ? : 5;
 	unsigned long long_mask;
 	char *span_str = NULL;
-	char cbm_mask[256];
 	int count_of_bits;
 	size_t span;
 	int ret, i;
 
-	ret = get_cbm_mask("L3", cbm_mask);
+	ret = get_full_cbm("L3", &long_mask);
 	if (ret)
 		return ret;
 
-	long_mask = strtoul(cbm_mask, NULL, 16);
-
-	ret = get_cache_size(cpu_no, "L3", &cache_size);
+	ret = get_cache_size(uparams->cpu, "L3", &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
 	count_of_bits = count_bits(long_mask);
 
@@ -103,19 +129,18 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 		.resctrl_val	= CMT_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,
 		.setup		= cmt_setup,
 	};
 
-	span = cache_size * n / count_of_bits;
+	span = cache_portion_size(cache_total_size, param.mask, long_mask);
 
 	if (strcmp(cmd[0], "fill_buf") == 0) {
 		/* Duplicate the command to be able to replace span in it */
-		for (i = 0; benchmark_cmd[i]; i++)
-			new_cmd[i] = benchmark_cmd[i];
+		for (i = 0; uparams->benchmark_cmd[i]; i++)
+			new_cmd[i] = uparams->benchmark_cmd[i];
 		new_cmd[i] = NULL;
 
 		ret = asprintf(&span_str, "%zu", span);
@@ -127,11 +152,13 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(cmd, &param);
+	ret = resctrl_val(test, uparams, cmd, &param);
 	if (ret)
 		goto out;
 
 	ret = check_results(&param, span, n);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	cmt_test_cleanup();
@@ -139,3 +166,16 @@ out:
 
 	return ret;
 }
+
+static bool cmt_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       resctrl_mon_feature_exists("L3_MON", "llc_occupancy");
+}
+
+struct resctrl_test cmt_test = {
+	.name = "CMT",
+	.resource = "L3",
+	.feature_check = cmt_feature_check,
+	.run_test = cmt_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 0d425f26583a..ae120f1735c0 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -38,7 +38,7 @@ static void cl_flush(void *p)
 #endif
 }
 
-static void mem_flush(unsigned char *buf, size_t buf_size)
+void mem_flush(unsigned char *buf, size_t buf_size)
 {
 	unsigned char *cp = buf;
 	size_t i = 0;
@@ -51,39 +51,38 @@ static void mem_flush(unsigned char *buf, size_t buf_size)
 	sb();
 }
 
-static void *malloc_and_init_memory(size_t buf_size)
-{
-	void *p = NULL;
-	uint64_t *p64;
-	size_t s64;
-	int ret;
-
-	ret = posix_memalign(&p, PAGE_SIZE, buf_size);
-	if (ret < 0)
-		return NULL;
-
-	p64 = (uint64_t *)p;
-	s64 = buf_size / sizeof(uint64_t);
-
-	while (s64 > 0) {
-		*p64 = (uint64_t)rand();
-		p64 += (CL_SIZE / sizeof(uint64_t));
-		s64 -= (CL_SIZE / sizeof(uint64_t));
-	}
-
-	return p;
-}
+/*
+ * Buffer index step advance to workaround HW prefetching interfering with
+ * the measurements.
+ *
+ * Must be a prime to step through all indexes of the buffer.
+ *
+ * Some primes work better than others on some architectures (from MBA/MBM
+ * result stability point of view).
+ */
+#define FILL_IDX_MULT	23
 
 static int fill_one_span_read(unsigned char *buf, size_t buf_size)
 {
-	unsigned char *end_ptr = buf + buf_size;
-	unsigned char sum, *p;
-
-	sum = 0;
-	p = buf;
-	while (p < end_ptr) {
-		sum += *p;
-		p += (CL_SIZE / 2);
+	unsigned int size = buf_size / (CL_SIZE / 2);
+	unsigned int i, idx = 0;
+	unsigned char sum = 0;
+
+	/*
+	 * Read the buffer in an order that is unexpected by HW prefetching
+	 * optimizations to prevent them interfering with the caching pattern.
+	 *
+	 * The read order is (in terms of halves of cachelines):
+	 *	i * FILL_IDX_MULT % size
+	 * The formula is open-coded below to avoiding modulo inside the loop
+	 * as it improves MBA/MBM result stability on some architectures.
+	 */
+	for (i = 0; i < size; i++) {
+		sum += buf[idx * (CL_SIZE / 2)];
+
+		idx += FILL_IDX_MULT;
+		while (idx >= size)
+			idx -= size;
 	}
 
 	return sum;
@@ -101,10 +100,9 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size)
 	}
 }
 
-static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
-	FILE *fp;
 
 	while (1) {
 		ret = fill_one_span_read(buf, buf_size);
@@ -113,67 +111,59 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	}
 
 	/* Consume read result so that reading memory is not optimized out. */
-	fp = fopen("/dev/null", "w");
-	if (!fp) {
-		perror("Unable to write to /dev/null");
-		return -1;
-	}
-	fprintf(fp, "Sum: %d ", ret);
-	fclose(fp);
-
-	return 0;
+	*value_sink = ret;
 }
 
-static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
+static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
 {
 	while (1) {
 		fill_one_span_write(buf, buf_size);
 		if (once)
 			break;
 	}
-
-	return 0;
 }
 
-static int fill_cache(size_t buf_size, int memflush, int op, bool once)
+unsigned char *alloc_buffer(size_t buf_size, int memflush)
 {
-	unsigned char *buf;
+	void *buf = NULL;
+	uint64_t *p64;
+	size_t s64;
 	int ret;
 
-	buf = malloc_and_init_memory(buf_size);
-	if (!buf)
-		return -1;
-
-	/* Flush the memory before using to avoid "cache hot pages" effect */
-	if (memflush)
-		mem_flush(buf, buf_size);
-
-	if (op == 0)
-		ret = fill_cache_read(buf, buf_size, once);
-	else
-		ret = fill_cache_write(buf, buf_size, once);
+	ret = posix_memalign(&buf, PAGE_SIZE, buf_size);
+	if (ret < 0)
+		return NULL;
 
-	free(buf);
+	/* Initialize the buffer */
+	p64 = buf;
+	s64 = buf_size / sizeof(uint64_t);
 
-	if (ret) {
-		printf("\n Error in fill cache read/write...\n");
-		return -1;
+	while (s64 > 0) {
+		*p64 = (uint64_t)rand();
+		p64 += (CL_SIZE / sizeof(uint64_t));
+		s64 -= (CL_SIZE / sizeof(uint64_t));
 	}
 
+	/* Flush the memory before using to avoid "cache hot pages" effect */
+	if (memflush)
+		mem_flush(buf, buf_size);
 
-	return 0;
+	return buf;
 }
 
-int run_fill_buf(size_t span, int memflush, int op, bool once)
+int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
 {
-	size_t cache_size = span;
-	int ret;
+	unsigned char *buf;
 
-	ret = fill_cache(cache_size, memflush, op, once);
-	if (ret) {
-		printf("\n Error in fill cache\n");
+	buf = alloc_buffer(buf_size, memflush);
+	if (!buf)
 		return -1;
-	}
+
+	if (op == 0)
+		fill_cache_read(buf, buf_size, once);
+	else
+		fill_cache_write(buf, buf_size, once);
+	free(buf);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index d3bf4368341e..7946e32e85c8 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -22,7 +22,9 @@
  * con_mon grp, mon_grp in resctrl FS.
  * For each allocation, run 5 times in order to get average values.
  */
-static int mba_setup(struct resctrl_val_param *p)
+static int mba_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	static int runs_per_allocation, allocation = 100;
 	char allocation_str[64];
@@ -40,8 +42,7 @@ static int mba_setup(struct resctrl_val_param *p)
 
 	sprintf(allocation_str, "%d", allocation);
 
-	ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no,
-			     p->resctrl_val);
+	ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, test->resource);
 	if (ret < 0)
 		return ret;
 
@@ -109,9 +110,9 @@ static int check_results(void)
 
 	fp = fopen(output, "r");
 	if (!fp) {
-		perror(output);
+		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
@@ -141,13 +142,12 @@ void mba_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
+static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBA_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mba_setup
@@ -156,7 +156,7 @@ int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
@@ -167,3 +167,17 @@ out:
 
 	return ret;
 }
+
+static bool mba_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mba_test = {
+	.name = "MBA",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mba_feature_check,
+	.run_test = mba_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 741533f2b075..d67ffa3ec63a 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -59,9 +59,9 @@ static int check_results(size_t span)
 
 	fp = fopen(output, "r");
 	if (!fp) {
-		perror(output);
+		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
@@ -86,7 +86,9 @@ static int check_results(size_t span)
 	return ret;
 }
 
-static int mbm_setup(struct resctrl_val_param *p)
+static int mbm_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	int ret = 0;
 
@@ -95,9 +97,8 @@ static int mbm_setup(struct resctrl_val_param *p)
 		return END_OF_TESTS;
 
 	/* Set up shemata with 100% allocation on the first run. */
-	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
-		ret = write_schemata(p->ctrlgrp, "100", p->cpu_no,
-				     p->resctrl_val);
+	if (p->num_of_runs == 0 && resctrl_resource_exists("MB"))
+		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource);
 
 	p->num_of_runs++;
 
@@ -109,13 +110,12 @@ void mbm_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
+static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mbm_setup
@@ -124,14 +124,30 @@ int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
 	ret = check_results(DEFAULT_SPAN);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	mbm_test_cleanup();
 
 	return ret;
 }
+
+static bool mbm_feature_check(const struct resctrl_test *test)
+{
+	return resctrl_mon_feature_exists("L3_MON", "mbm_total_bytes") &&
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mbm_test = {
+	.name = "MBM",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mbm_feature_check,
+	.run_test = mbm_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a33f414f6019..2051bd135e0d 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -28,6 +28,12 @@
 #define PHYS_ID_PATH		"/sys/devices/system/cpu/cpu"
 #define INFO_PATH		"/sys/fs/resctrl/info"
 
+/*
+ * CPU vendor IDs
+ *
+ * Define as bits because they're used for vendor_specific bitmask in
+ * the struct resctrl_test.
+ */
 #define ARCH_INTEL     1
 #define ARCH_AMD       2
 
@@ -37,20 +43,52 @@
 
 #define DEFAULT_SPAN		(250 * MB)
 
-#define PARENT_EXIT(err_msg)			\
+#define PARENT_EXIT()				\
 	do {					\
-		perror(err_msg);		\
 		kill(ppid, SIGKILL);		\
 		umount_resctrlfs();		\
 		exit(EXIT_FAILURE);		\
 	} while (0)
 
 /*
+ * user_params:		User supplied parameters
+ * @cpu:		CPU number to which the benchmark will be bound to
+ * @bits:		Number of bits used for cache allocation size
+ * @benchmark_cmd:	Benchmark command to run during (some of the) tests
+ */
+struct user_params {
+	int cpu;
+	int bits;
+	const char *benchmark_cmd[BENCHMARK_ARGS];
+};
+
+/*
+ * resctrl_test:	resctrl test definition
+ * @name:		Test name
+ * @group:		Test group - a common name for tests that share some characteristic
+ *			(e.g., L3 CAT test belongs to the CAT group). Can be NULL
+ * @resource:		Resource to test (e.g., MB, L3, L2, etc.)
+ * @vendor_specific:	Bitmask for vendor-specific tests (can be 0 for universal tests)
+ * @disabled:		Test is disabled
+ * @feature_check:	Callback to check required resctrl features
+ * @run_test:		Callback to run the test
+ */
+struct resctrl_test {
+	const char	*name;
+	const char	*group;
+	const char	*resource;
+	unsigned int	vendor_specific;
+	bool		disabled;
+	bool		(*feature_check)(const struct resctrl_test *test);
+	int		(*run_test)(const struct resctrl_test *test,
+				    const struct user_params *uparams);
+};
+
+/*
  * resctrl_val_param:	resctrl test parameters
  * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
- * @cpu_no:		CPU number to which the benchmark would be binded
  * @filename:		Name of file to which the o/p should be written
  * @bw_report:		Bandwidth report type (reads vs writes)
  * @setup:		Call back function to setup test environment
@@ -59,12 +97,20 @@ struct resctrl_val_param {
 	char		*resctrl_val;
 	char		ctrlgrp[64];
 	char		mongrp[64];
-	int		cpu_no;
 	char		filename[64];
 	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
-	int		(*setup)(struct resctrl_val_param *param);
+	int		(*setup)(const struct resctrl_test *test,
+				 const struct user_params *uparams,
+				 struct resctrl_val_param *param);
+};
+
+struct perf_event_read {
+	__u64 nr;			/* The number of events */
+	struct {
+		__u64 value;		/* The value of the event */
+	} values[2];
 };
 
 #define MBM_STR			"mbm"
@@ -72,6 +118,13 @@ struct resctrl_val_param {
 #define CMT_STR			"cmt"
 #define CAT_STR			"cat"
 
+/*
+ * Memory location that consumes values compiler must not optimize away.
+ * Volatile ensures writes to this location cannot be optimized away by
+ * compiler.
+ */
+extern volatile int *value_sink;
+
 extern pid_t bm_pid, ppid;
 
 extern char llc_occup_path[1024];
@@ -79,42 +132,84 @@ extern char llc_occup_path[1024];
 int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
-int get_resource_id(int cpu_no, int *resource_id);
+int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
-bool validate_resctrl_feature_request(const char *resource, const char *feature);
+bool resctrl_resource_exists(const char *resource);
+bool resctrl_mon_feature_exists(const char *resource, const char *feature);
+bool resource_info_file_exists(const char *resource, const char *file);
+bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
-int taskset_benchmark(pid_t bm_pid, int cpu_no);
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no,
-		   char *resctrl_val);
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource);
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
-int run_fill_buf(size_t span, int memflush, int op, bool once);
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param);
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd);
+unsigned char *alloc_buffer(size_t buf_size, int memflush);
+void mem_flush(unsigned char *buf, size_t buf_size);
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
+int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
+		struct resctrl_val_param *param);
 void tests_cleanup(void);
 void mbm_test_cleanup(void);
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
-int get_cbm_mask(char *cache_type, char *cbm_mask);
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size);
+unsigned long create_bit_mask(unsigned int start, unsigned int len);
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
+int get_full_cbm(const char *cache_type, unsigned long *mask);
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
+int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
-int cat_val(struct resctrl_val_param *param, size_t span);
 void cat_test_cleanup(void);
-int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
-int get_core_sibling(int cpu_no);
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid);
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt);
+
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
+void perf_event_initialize_read_format(struct perf_event_read *pe_read);
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
+int perf_event_reset_enable(int pe_fd);
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid);
+int measure_llc_resctrl(const char *filename, int bm_pid);
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
+
+/*
+ * cache_portion_size - Calculate the size of a cache portion
+ * @cache_size:		Total cache size in bytes
+ * @portion_mask:	Cache portion mask
+ * @full_cache_mask:	Full Cache Bit Mask (CBM) for the cache
+ *
+ * Return: The size of the cache portion in bytes.
+ */
+static inline unsigned long cache_portion_size(unsigned long cache_size,
+					       unsigned long portion_mask,
+					       unsigned long full_cache_mask)
+{
+	unsigned int bits = count_bits(full_cache_mask);
+
+	/*
+	 * With no bits the full CBM, assume cache cannot be split into
+	 * smaller portions. To avoid divide by zero, return cache_size.
+	 */
+	if (!bits)
+		return cache_size;
+
+	return cache_size * count_bits(portion_mask) / bits;
+}
+
+extern struct resctrl_test mbm_test;
+extern struct resctrl_test mba_test;
+extern struct resctrl_test cmt_test;
+extern struct resctrl_test l3_cat_test;
+extern struct resctrl_test l3_noncont_cat_test;
+extern struct resctrl_test l2_noncont_cat_test;
 
 #endif /* RESCTRL_H */
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 2bbe3045a018..f3dc1b9696e7 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -10,6 +10,19 @@
  */
 #include "resctrl.h"
 
+/* Volatile memory sink to prevent compiler optimizations */
+static volatile int sink_target;
+volatile int *value_sink = &sink_target;
+
+static struct resctrl_test *resctrl_tests[] = {
+	&mbm_test,
+	&mba_test,
+	&cmt_test,
+	&l3_cat_test,
+	&l3_noncont_cat_test,
+	&l2_noncont_cat_test,
+};
+
 static int detect_vendor(void)
 {
 	FILE *inf = fopen("/proc/cpuinfo", "r");
@@ -49,11 +62,20 @@ int get_vendor(void)
 
 static void cmd_help(void)
 {
+	int i;
+
 	printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n");
 	printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n");
 	printf("\t   default benchmark is builtin fill_buf\n");
-	printf("\t-t test list: run tests specified in the test list, ");
+	printf("\t-t test list: run tests/groups specified by the list, ");
 	printf("e.g. -t mbm,mba,cmt,cat\n");
+	printf("\t\tSupported tests (group):\n");
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+		if (resctrl_tests[i]->group)
+			printf("\t\t\t%s (%s)\n", resctrl_tests[i]->name, resctrl_tests[i]->group);
+		else
+			printf("\t\t\t%s\n", resctrl_tests[i]->name);
+	}
 	printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n");
 	printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n");
 	printf("\t-h: help\n");
@@ -92,116 +114,63 @@ static void test_cleanup(void)
 	signal_handler_unregister();
 }
 
-static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
+static bool test_vendor_specific_check(const struct resctrl_test *test)
 {
-	int res;
-
-	ksft_print_msg("Starting MBM BW change ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
-		return;
-	}
-
-	if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n");
-		goto cleanup;
-	}
-
-	res = mbm_bw_change(cpu_no, benchmark_cmd);
-	ksft_test_result(!res, "MBM: bw change\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	if (!test->vendor_specific)
+		return true;
 
-cleanup:
-	test_cleanup();
+	return get_vendor() & test->vendor_specific;
 }
 
-static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
+static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	int res;
-
-	ksft_print_msg("Starting MBA Schemata change ...\n");
+	int ret;
 
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
+	if (test->disabled)
 		return;
-	}
 
-	if (!validate_resctrl_feature_request("MB", NULL) ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
-		goto cleanup;
+	if (!test_vendor_specific_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s\n", test->name);
+		return;
 	}
 
-	res = mba_schemata_change(cpu_no, benchmark_cmd);
-	ksft_test_result(!res, "MBA: schemata change\n");
-
-cleanup:
-	test_cleanup();
-}
-
-static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
-{
-	int res;
-
-	ksft_print_msg("Starting CMT test ...\n");
+	ksft_print_msg("Starting %s test ...\n", test->name);
 
 	if (test_prepare()) {
 		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
 		return;
 	}
 
-	if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
-	    !validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
+	if (!test->feature_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s or %s is disabled\n",
+				      test->name, test->name);
 		goto cleanup;
 	}
 
-	res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd);
-	ksft_test_result(!res, "CMT: test\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	ret = test->run_test(test, uparams);
+	ksft_test_result(!ret, "%s: test\n", test->name);
 
 cleanup:
 	test_cleanup();
 }
 
-static void run_cat_test(int cpu_no, int no_of_bits)
+static void init_user_params(struct user_params *uparams)
 {
-	int res;
-
-	ksft_print_msg("Starting CAT test ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
-		return;
-	}
-
-	if (!validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n");
-		goto cleanup;
-	}
+	memset(uparams, 0, sizeof(*uparams));
 
-	res = cat_perf_miss_val(cpu_no, no_of_bits, "L3");
-	ksft_test_result(!res, "CAT: test\n");
-
-cleanup:
-	test_cleanup();
+	uparams->cpu = 1;
+	uparams->bits = 0;
 }
 
 int main(int argc, char **argv)
 {
-	bool mbm_test = true, mba_test = true, cmt_test = true;
-	const char *benchmark_cmd[BENCHMARK_ARGS] = {};
-	int c, cpu_no = 1, i, no_of_bits = 0;
+	int tests = ARRAY_SIZE(resctrl_tests);
+	bool test_param_seen = false;
+	struct user_params uparams;
 	char *span_str = NULL;
-	bool cat_test = true;
-	int tests = 0;
-	int ret;
+	int ret, c, i;
+
+	init_user_params(&uparams);
 
 	while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) {
 		char *token;
@@ -219,32 +188,35 @@ int main(int argc, char **argv)
 
 			/* Extract benchmark command from command line. */
 			for (i = 0; i < argc - optind; i++)
-				benchmark_cmd[i] = argv[i + optind];
-			benchmark_cmd[i] = NULL;
+				uparams.benchmark_cmd[i] = argv[i + optind];
+			uparams.benchmark_cmd[i] = NULL;
 
 			goto last_arg;
 		case 't':
 			token = strtok(optarg, ",");
 
-			mbm_test = false;
-			mba_test = false;
-			cmt_test = false;
-			cat_test = false;
+			if (!test_param_seen) {
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+					resctrl_tests[i]->disabled = true;
+				tests = 0;
+				test_param_seen = true;
+			}
 			while (token) {
-				if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) {
-					mbm_test = true;
-					tests++;
-				} else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) {
-					mba_test = true;
-					tests++;
-				} else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) {
-					cmt_test = true;
-					tests++;
-				} else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) {
-					cat_test = true;
-					tests++;
-				} else {
-					printf("invalid argument\n");
+				bool found = false;
+
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+					if (!strcasecmp(token, resctrl_tests[i]->name) ||
+					    (resctrl_tests[i]->group &&
+					     !strcasecmp(token, resctrl_tests[i]->group))) {
+						if (resctrl_tests[i]->disabled)
+							tests++;
+						resctrl_tests[i]->disabled = false;
+						found = true;
+					}
+				}
+
+				if (!found) {
+					printf("invalid test: %s\n", token);
 
 					return -1;
 				}
@@ -252,11 +224,11 @@ int main(int argc, char **argv)
 			}
 			break;
 		case 'p':
-			cpu_no = atoi(optarg);
+			uparams.cpu = atoi(optarg);
 			break;
 		case 'n':
-			no_of_bits = atoi(optarg);
-			if (no_of_bits <= 0) {
+			uparams.bits = atoi(optarg);
+			if (uparams.bits <= 0) {
 				printf("Bail out! invalid argument for no_of_bits\n");
 				return -1;
 			}
@@ -291,32 +263,23 @@ last_arg:
 
 	filter_dmesg();
 
-	if (!benchmark_cmd[0]) {
+	if (!uparams.benchmark_cmd[0]) {
 		/* If no benchmark is given by "-b" argument, use fill_buf. */
-		benchmark_cmd[0] = "fill_buf";
+		uparams.benchmark_cmd[0] = "fill_buf";
 		ret = asprintf(&span_str, "%u", DEFAULT_SPAN);
 		if (ret < 0)
 			ksft_exit_fail_msg("Out of memory!\n");
-		benchmark_cmd[1] = span_str;
-		benchmark_cmd[2] = "1";
-		benchmark_cmd[3] = "0";
-		benchmark_cmd[4] = "false";
-		benchmark_cmd[5] = NULL;
+		uparams.benchmark_cmd[1] = span_str;
+		uparams.benchmark_cmd[2] = "1";
+		uparams.benchmark_cmd[3] = "0";
+		uparams.benchmark_cmd[4] = "false";
+		uparams.benchmark_cmd[5] = NULL;
 	}
 
-	ksft_set_plan(tests ? : 4);
-
-	if (mbm_test)
-		run_mbm_test(benchmark_cmd, cpu_no);
-
-	if (mba_test)
-		run_mba_test(benchmark_cmd, cpu_no);
-
-	if (cmt_test)
-		run_cmt_test(benchmark_cmd, cpu_no);
+	ksft_set_plan(tests);
 
-	if (cat_test)
-		run_cat_test(cpu_no, no_of_bits);
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+		run_single_test(resctrl_tests[i], &uparams);
 
 	free(span_str);
 	ksft_finished();
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 88789678917b..5a49f07a6c85 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -156,12 +156,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_type, "%s%s", imc_dir, "type");
 	fp = fopen(imc_counter_type, "r");
 	if (!fp) {
-		perror("Failed to open imc counter type file");
+		ksft_perror("Failed to open iMC counter type file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) {
-		perror("Could not get imc type");
+		ksft_perror("Could not get iMC type");
 		fclose(fp);
 
 		return -1;
@@ -175,12 +175,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME);
 	fp = fopen(imc_counter_cfg, "r");
 	if (!fp) {
-		perror("Failed to open imc config file");
+		ksft_perror("Failed to open iMC config file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%s", cas_count_cfg) <= 0) {
-		perror("Could not get imc cas count read");
+		ksft_perror("Could not get iMC cas count read");
 		fclose(fp);
 
 		return -1;
@@ -193,12 +193,12 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME);
 	fp = fopen(imc_counter_cfg, "r");
 	if (!fp) {
-		perror("Failed to open imc config file");
+		ksft_perror("Failed to open iMC config file");
 
 		return -1;
 	}
 	if  (fscanf(fp, "%s", cas_count_cfg) <= 0) {
-		perror("Could not get imc cas count write");
+		ksft_perror("Could not get iMC cas count write");
 		fclose(fp);
 
 		return -1;
@@ -262,12 +262,12 @@ static int num_of_imcs(void)
 		}
 		closedir(dp);
 		if (count == 0) {
-			perror("Unable find iMC counters!\n");
+			ksft_print_msg("Unable to find iMC counters\n");
 
 			return -1;
 		}
 	} else {
-		perror("Unable to open PMU directory!\n");
+		ksft_perror("Unable to open PMU directory");
 
 		return -1;
 	}
@@ -339,14 +339,14 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 
 		if (read(r->fd, &r->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			perror("Couldn't get read b/w through iMC");
+			ksft_perror("Couldn't get read b/w through iMC");
 
 			return -1;
 		}
 
 		if (read(w->fd, &w->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			perror("Couldn't get write bw through iMC");
+			ksft_perror("Couldn't get write bw through iMC");
 
 			return -1;
 		}
@@ -387,20 +387,20 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 	return 0;
 }
 
-void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
+void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
 {
 	if (ctrlgrp && mongrp)
 		sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH,
-			RESCTRL_PATH, ctrlgrp, mongrp, resource_id);
+			RESCTRL_PATH, ctrlgrp, mongrp, domain_id);
 	else if (!ctrlgrp && mongrp)
 		sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			mongrp, resource_id);
+			mongrp, domain_id);
 	else if (ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			ctrlgrp, resource_id);
+			ctrlgrp, domain_id);
 	else if (!ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			resource_id);
+			domain_id);
 }
 
 /*
@@ -413,23 +413,23 @@ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
 static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
 				      int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		perror("Could not get resource_id");
+	if (get_domain_id("MB", cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		set_mbm_path(ctrlgrp, mongrp, resource_id);
+		set_mbm_path(ctrlgrp, mongrp, domain_id);
 
 	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
 		if (ctrlgrp)
 			sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, ctrlgrp, resource_id);
+				RESCTRL_PATH, ctrlgrp, domain_id);
 		else
 			sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, resource_id);
+				RESCTRL_PATH, domain_id);
 	}
 }
 
@@ -449,12 +449,12 @@ static int get_mem_bw_resctrl(unsigned long *mbm_total)
 
 	fp = fopen(mbm_total_path, "r");
 	if (!fp) {
-		perror("Failed to open total bw file");
+		ksft_perror("Failed to open total bw file");
 
 		return -1;
 	}
 	if (fscanf(fp, "%lu", mbm_total) <= 0) {
-		perror("Could not get mbm local bytes");
+		ksft_perror("Could not get mbm local bytes");
 		fclose(fp);
 
 		return -1;
@@ -495,7 +495,7 @@ int signal_handler_register(void)
 	if (sigaction(SIGINT, &sigact, NULL) ||
 	    sigaction(SIGTERM, &sigact, NULL) ||
 	    sigaction(SIGHUP, &sigact, NULL)) {
-		perror("# sigaction");
+		ksft_perror("sigaction");
 		ret = -1;
 	}
 	return ret;
@@ -515,7 +515,7 @@ void signal_handler_unregister(void)
 	if (sigaction(SIGINT, &sigact, NULL) ||
 	    sigaction(SIGTERM, &sigact, NULL) ||
 	    sigaction(SIGHUP, &sigact, NULL)) {
-		perror("# sigaction");
+		ksft_perror("sigaction");
 	}
 }
 
@@ -526,7 +526,7 @@ void signal_handler_unregister(void)
  * @bw_imc:		perf imc counter value
  * @bw_resc:		memory bandwidth value
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
 static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 			    unsigned long bw_resc)
@@ -540,16 +540,16 @@ static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
-			perror("Cannot open results file");
+			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
 		if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n",
 			    bm_pid, bw_imc, bw_resc, diff) <= 0) {
+			ksft_print_msg("Could not log results\n");
 			fclose(fp);
-			perror("Could not log results.");
 
-			return errno;
+			return -1;
 		}
 		fclose(fp);
 	}
@@ -582,19 +582,20 @@ static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num)
 static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 					int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		perror("# Unable to resource_id");
+	if (get_domain_id("L3", cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		set_cmt_path(ctrlgrp, mongrp, resource_id);
+		set_cmt_path(ctrlgrp, mongrp, domain_id);
 }
 
-static int
-measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
+static int measure_vals(const struct user_params *uparams,
+			struct resctrl_val_param *param,
+			unsigned long *bw_resc_start)
 {
 	unsigned long bw_resc, bw_resc_end;
 	float bw_imc;
@@ -607,7 +608,7 @@ measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
 	 * Compare the two values to validate resctrl value.
 	 * It takes 1sec to measure the data.
 	 */
-	ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc);
+	ret = get_mem_bw_imc(uparams->cpu, param->bw_report, &bw_imc);
 	if (ret < 0)
 		return ret;
 
@@ -647,20 +648,24 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 	 * stdio (console)
 	 */
 	fp = freopen("/dev/null", "w", stdout);
-	if (!fp)
-		PARENT_EXIT("Unable to direct benchmark status to /dev/null");
+	if (!fp) {
+		ksft_perror("Unable to direct benchmark status to /dev/null");
+		PARENT_EXIT();
+	}
 
 	if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
 		/* Execute default fill_buf benchmark */
 		span = strtoul(benchmark_cmd[1], NULL, 10);
 		memflush =  atoi(benchmark_cmd[2]);
 		operation = atoi(benchmark_cmd[3]);
-		if (!strcmp(benchmark_cmd[4], "true"))
+		if (!strcmp(benchmark_cmd[4], "true")) {
 			once = true;
-		else if (!strcmp(benchmark_cmd[4], "false"))
+		} else if (!strcmp(benchmark_cmd[4], "false")) {
 			once = false;
-		else
-			PARENT_EXIT("Invalid once parameter");
+		} else {
+			ksft_print_msg("Invalid once parameter\n");
+			PARENT_EXIT();
+		}
 
 		if (run_fill_buf(span, memflush, operation, once))
 			fprintf(stderr, "Error in running fill buffer\n");
@@ -668,22 +673,28 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 		/* Execute specified benchmark */
 		ret = execvp(benchmark_cmd[0], benchmark_cmd);
 		if (ret)
-			perror("wrong\n");
+			ksft_perror("execvp");
 	}
 
 	fclose(stdout);
-	PARENT_EXIT("Unable to run specified benchmark");
+	ksft_print_msg("Unable to run specified benchmark\n");
+	PARENT_EXIT();
 }
 
 /*
  * resctrl_val:	execute benchmark and measure memory bandwidth on
  *			the benchmark
+ * @test:		test information structure
+ * @uparams:		user supplied parameters
  * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 when the test was run, < 0 on error.
  */
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param)
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
+		struct resctrl_val_param *param)
 {
 	char *resctrl_val = param->resctrl_val;
 	unsigned long bw_resc_start = 0;
@@ -709,7 +720,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	ppid = getpid();
 
 	if (pipe(pipefd)) {
-		perror("# Unable to create pipe");
+		ksft_perror("Unable to create pipe");
 
 		return -1;
 	}
@@ -721,7 +732,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	fflush(stdout);
 	bm_pid = fork();
 	if (bm_pid == -1) {
-		perror("# Unable to fork");
+		ksft_perror("Unable to fork");
 
 		return -1;
 	}
@@ -738,15 +749,17 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 		sigact.sa_flags = SA_SIGINFO;
 
 		/* Register for "SIGUSR1" signal from parent */
-		if (sigaction(SIGUSR1, &sigact, NULL))
-			PARENT_EXIT("Can't register child for signal");
+		if (sigaction(SIGUSR1, &sigact, NULL)) {
+			ksft_perror("Can't register child for signal");
+			PARENT_EXIT();
+		}
 
 		/* Tell parent that child is ready */
 		close(pipefd[0]);
 		pipe_message = 1;
 		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
 		    sizeof(pipe_message)) {
-			perror("# failed signaling parent process");
+			ksft_perror("Failed signaling parent process");
 			close(pipefd[1]);
 			return -1;
 		}
@@ -755,7 +768,8 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 		/* Suspend child until delivery of "SIGUSR1" from parent */
 		sigsuspend(&sigact.sa_mask);
 
-		PARENT_EXIT("Child is done");
+		ksft_perror("Child is done");
+		PARENT_EXIT();
 	}
 
 	ksft_print_msg("Benchmark PID: %d\n", bm_pid);
@@ -769,7 +783,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	value.sival_ptr = (void *)benchmark_cmd;
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
+	ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);
 	if (ret)
 		goto out;
 
@@ -786,17 +800,17 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 			goto out;
 
 		initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
-					  param->cpu_no, resctrl_val);
+					  uparams->cpu, resctrl_val);
 	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
-					    param->cpu_no, resctrl_val);
+					    uparams->cpu, resctrl_val);
 
 	/* Parent waits for child to be ready. */
 	close(pipefd[1]);
 	while (pipe_message != 1) {
 		if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) <
 		    sizeof(pipe_message)) {
-			perror("# failed reading message from child process");
+			ksft_perror("Failed reading message from child process");
 			close(pipefd[0]);
 			goto out;
 		}
@@ -805,8 +819,8 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 	/* Signal child to start benchmark */
 	if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
-		perror("# sigqueue SIGUSR1 to child");
-		ret = errno;
+		ksft_perror("sigqueue SIGUSR1 to child");
+		ret = -1;
 		goto out;
 	}
 
@@ -815,7 +829,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
-		ret = param->setup(param);
+		ret = param->setup(test, uparams, param);
 		if (ret == END_OF_TESTS) {
 			ret = 0;
 			break;
@@ -825,12 +839,12 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(param, &bw_resc_start);
+			ret = measure_vals(uparams, param, &bw_resc_start);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
 			sleep(1);
-			ret = measure_cache_vals(param, bm_pid);
+			ret = measure_llc_resctrl(param->filename, bm_pid);
 			if (ret)
 				break;
 		}
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 5ebd43683876..1cade75176eb 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -20,7 +20,7 @@ static int find_resctrl_mount(char *buffer)
 
 	mounts = fopen("/proc/mounts", "r");
 	if (!mounts) {
-		perror("/proc/mounts");
+		ksft_perror("/proc/mounts");
 		return -ENXIO;
 	}
 	while (!feof(mounts)) {
@@ -56,7 +56,7 @@ static int find_resctrl_mount(char *buffer)
  * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid
  * pre-existing settings interfering with the test results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int mount_resctrlfs(void)
 {
@@ -69,7 +69,7 @@ int mount_resctrlfs(void)
 	ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH);
 	ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL);
 	if (ret)
-		perror("# mount");
+		ksft_perror("mount");
 
 	return ret;
 }
@@ -86,41 +86,67 @@ int umount_resctrlfs(void)
 		return ret;
 
 	if (umount(mountpoint)) {
-		perror("# Unable to umount resctrl");
+		ksft_perror("Unable to umount resctrl");
 
-		return errno;
+		return -1;
 	}
 
 	return 0;
 }
 
 /*
- * get_resource_id - Get socket number/l3 id for a specified CPU
+ * get_cache_level - Convert cache level from string to integer
+ * @cache_type:		Cache level as string
+ *
+ * Return: cache level as integer or -1 if @cache_type is invalid.
+ */
+static int get_cache_level(const char *cache_type)
+{
+	if (!strcmp(cache_type, "L3"))
+		return 3;
+	if (!strcmp(cache_type, "L2"))
+		return 2;
+
+	ksft_print_msg("Invalid cache level\n");
+	return -1;
+}
+
+static int get_resource_cache_level(const char *resource)
+{
+	/* "MB" use L3 (LLC) as resource */
+	if (!strcmp(resource, "MB"))
+		return 3;
+	return get_cache_level(resource);
+}
+
+/*
+ * get_domain_id - Get resctrl domain ID for a specified CPU
+ * @resource:	resource name
  * @cpu_no:	CPU number
- * @resource_id: Socket number or l3_id
+ * @domain_id:	domain ID (cache ID; for MB, L3 cache ID)
  *
  * Return: >= 0 on success, < 0 on failure.
  */
-int get_resource_id(int cpu_no, int *resource_id)
+int get_domain_id(const char *resource, int cpu_no, int *domain_id)
 {
 	char phys_pkg_path[1024];
+	int cache_num;
 	FILE *fp;
 
-	if (get_vendor() == ARCH_AMD)
-		sprintf(phys_pkg_path, "%s%d/cache/index3/id",
-			PHYS_ID_PATH, cpu_no);
-	else
-		sprintf(phys_pkg_path, "%s%d/topology/physical_package_id",
-			PHYS_ID_PATH, cpu_no);
+	cache_num = get_resource_cache_level(resource);
+	if (cache_num < 0)
+		return cache_num;
+
+	sprintf(phys_pkg_path, "%s%d/cache/index%d/id", PHYS_ID_PATH, cpu_no, cache_num);
 
 	fp = fopen(phys_pkg_path, "r");
 	if (!fp) {
-		perror("Failed to open physical_package_id");
+		ksft_perror("Failed to open cache id file");
 
 		return -1;
 	}
-	if (fscanf(fp, "%d", resource_id) <= 0) {
-		perror("Could not get socket number or l3 id");
+	if (fscanf(fp, "%d", domain_id) <= 0) {
+		ksft_perror("Could not get domain ID");
 		fclose(fp);
 
 		return -1;
@@ -138,31 +164,26 @@ int get_resource_id(int cpu_no, int *resource_id)
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size)
 {
 	char cache_path[1024], cache_str[64];
 	int length, i, cache_num;
 	FILE *fp;
 
-	if (!strcmp(cache_type, "L3")) {
-		cache_num = 3;
-	} else if (!strcmp(cache_type, "L2")) {
-		cache_num = 2;
-	} else {
-		perror("Invalid cache level");
-		return -1;
-	}
+	cache_num = get_cache_level(cache_type);
+	if (cache_num < 0)
+		return cache_num;
 
 	sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size",
 		cpu_no, cache_num);
 	fp = fopen(cache_path, "r");
 	if (!fp) {
-		perror("Failed to open cache size");
+		ksft_perror("Failed to open cache size");
 
 		return -1;
 	}
 	if (fscanf(fp, "%s", cache_str) <= 0) {
-		perror("Could not get cache_size");
+		ksft_perror("Could not get cache_size");
 		fclose(fp);
 
 		return -1;
@@ -196,30 +217,29 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
 #define CORE_SIBLINGS_PATH	"/sys/bus/cpu/devices/cpu"
 
 /*
- * get_cbm_mask - Get cbm mask for given cache
- * @cache_type:	Cache level L2/L3
- * @cbm_mask:	cbm_mask returned as a string
+ * get_bit_mask - Get bit mask from given file
+ * @filename:	File containing the mask
+ * @mask:	The bit mask returned as unsigned long
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cbm_mask(char *cache_type, char *cbm_mask)
+static int get_bit_mask(const char *filename, unsigned long *mask)
 {
-	char cbm_mask_path[1024];
 	FILE *fp;
 
-	if (!cbm_mask)
+	if (!filename || !mask)
 		return -1;
 
-	sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type);
-
-	fp = fopen(cbm_mask_path, "r");
+	fp = fopen(filename, "r");
 	if (!fp) {
-		perror("Failed to open cache level");
-
+		ksft_print_msg("Failed to open bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		return -1;
 	}
-	if (fscanf(fp, "%s", cbm_mask) <= 0) {
-		perror("Could not get max cbm_mask");
+
+	if (fscanf(fp, "%lx", mask) <= 0) {
+		ksft_print_msg("Could not read bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		fclose(fp);
 
 		return -1;
@@ -230,64 +250,200 @@ int get_cbm_mask(char *cache_type, char *cbm_mask)
 }
 
 /*
- * get_core_sibling - Get sibling core id from the same socket for given CPU
- * @cpu_no:	CPU number
+ * resource_info_unsigned_get - Read an unsigned value from
+ * /sys/fs/resctrl/info/@resource/@filename
+ * @resource:	Resource name that matches directory name in
+ *		/sys/fs/resctrl/info
+ * @filename:	File in /sys/fs/resctrl/info/@resource
+ * @val:	Contains read value on success.
  *
- * Return:	> 0 on success, < 0 on failure.
+ * Return: = 0 on success, < 0 on failure. On success the read
+ * value is saved into @val.
  */
-int get_core_sibling(int cpu_no)
+int resource_info_unsigned_get(const char *resource, const char *filename,
+			       unsigned int *val)
 {
-	char core_siblings_path[1024], cpu_list_str[64];
-	int sibling_cpu_no = -1;
+	char file_path[PATH_MAX];
 	FILE *fp;
 
-	sprintf(core_siblings_path, "%s%d/topology/core_siblings_list",
-		CORE_SIBLINGS_PATH, cpu_no);
+	snprintf(file_path, sizeof(file_path), "%s/%s/%s", INFO_PATH, resource,
+		 filename);
 
-	fp = fopen(core_siblings_path, "r");
+	fp = fopen(file_path, "r");
 	if (!fp) {
-		perror("Failed to open core siblings path");
-
+		ksft_print_msg("Error opening %s: %m\n", file_path);
 		return -1;
 	}
-	if (fscanf(fp, "%s", cpu_list_str) <= 0) {
-		perror("Could not get core_siblings list");
-		fclose(fp);
 
+	if (fscanf(fp, "%u", val) <= 0) {
+		ksft_print_msg("Could not get contents of %s: %m\n", file_path);
+		fclose(fp);
 		return -1;
 	}
+
 	fclose(fp);
+	return 0;
+}
 
-	char *token = strtok(cpu_list_str, "-,");
+/*
+ * create_bit_mask- Create bit mask from start, len pair
+ * @start:	LSB of the mask
+ * @len		Number of bits in the mask
+ */
+unsigned long create_bit_mask(unsigned int start, unsigned int len)
+{
+	return ((1UL << len) - 1UL) << start;
+}
 
-	while (token) {
-		sibling_cpu_no = atoi(token);
-		/* Skipping core 0 as we don't want to run test on core 0 */
-		if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no)
-			break;
-		token = strtok(NULL, "-,");
+/*
+ * count_contiguous_bits - Returns the longest train of bits in a bit mask
+ * @val		A bit mask
+ * @start	The location of the least-significant bit of the longest train
+ *
+ * Return:	The length of the contiguous bits in the longest train of bits
+ */
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
+{
+	unsigned long last_val;
+	unsigned int count = 0;
+
+	while (val) {
+		last_val = val;
+		val &= (val >> 1);
+		count++;
+	}
+
+	if (start) {
+		if (count)
+			*start = ffsl(last_val) - 1;
+		else
+			*start = 0;
 	}
 
-	return sibling_cpu_no;
+	return count;
+}
+
+/*
+ * get_full_cbm - Get full Cache Bit Mask (CBM)
+ * @cache_type:	Cache type as "L2" or "L3"
+ * @mask:	Full cache bit mask representing the maximal portion of cache
+ *		available for allocation, returned as unsigned long.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_full_cbm(const char *cache_type, unsigned long *mask)
+{
+	char cbm_path[PATH_MAX];
+	int ret;
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(cbm_path, sizeof(cbm_path), "%s/%s/cbm_mask",
+		 INFO_PATH, cache_type);
+
+	ret = get_bit_mask(cbm_path, mask);
+	if (ret || !*mask)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * get_shareable_mask - Get shareable mask from shareable_bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @shareable_mask:	Shareable mask returned as unsigned long
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask)
+{
+	char mask_path[PATH_MAX];
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits",
+		 INFO_PATH, cache_type);
+
+	return get_bit_mask(mask_path, shareable_mask);
+}
+
+/*
+ * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @mask:		The largest exclusive portion of the cache out of the
+ *			full CBM, returned as unsigned long
+ *
+ * Parts of a cache may be shared with other devices such as GPU. This function
+ * calculates the largest exclusive portion of the cache where no other devices
+ * besides CPU have access to the cache portion.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
+{
+	unsigned long full_mask, shareable_mask;
+	unsigned int start, len;
+
+	if (get_full_cbm(cache_type, &full_mask) < 0)
+		return -1;
+	if (get_shareable_mask(cache_type, &shareable_mask) < 0)
+		return -1;
+
+	len = count_contiguous_bits(full_mask & ~shareable_mask, &start);
+	if (!len)
+		return -1;
+
+	*mask = create_bit_mask(start, len);
+
+	return 0;
 }
 
 /*
  * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
- * @bm_pid:	PID that should be binded
- * @cpu_no:	CPU number at which the PID would be binded
+ * @bm_pid:		PID that should be binded
+ * @cpu_no:		CPU number at which the PID would be binded
+ * @old_affinity:	When not NULL, set to old CPU affinity
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
-int taskset_benchmark(pid_t bm_pid, int cpu_no)
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity)
 {
 	cpu_set_t my_set;
 
+	if (old_affinity) {
+		CPU_ZERO(old_affinity);
+		if (sched_getaffinity(bm_pid, sizeof(*old_affinity),
+				      old_affinity)) {
+			ksft_perror("Unable to read CPU affinity");
+			return -1;
+		}
+	}
+
 	CPU_ZERO(&my_set);
 	CPU_SET(cpu_no, &my_set);
 
 	if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) {
-		perror("Unable to taskset benchmark");
+		ksft_perror("Unable to taskset benchmark");
+
+		return -1;
+	}
+
+	return 0;
+}
 
+/*
+ * taskset_restore - Taskset PID to the earlier CPU affinity
+ * @bm_pid:		PID that should be reset
+ * @old_affinity:	The old CPU affinity to restore
+ *
+ * Return: 0 on success, < 0 on error.
+ */
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity)
+{
+	if (sched_setaffinity(bm_pid, sizeof(*old_affinity), old_affinity)) {
+		ksft_perror("Unable to restore CPU affinity");
 		return -1;
 	}
 
@@ -300,7 +456,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no)
  * @grp:	Full path and name of the group
  * @parent_grp:	Full path and name of the parent group
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 {
@@ -325,7 +481,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 		}
 		closedir(dp);
 	} else {
-		perror("Unable to open resctrl for group");
+		ksft_perror("Unable to open resctrl for group");
 
 		return -1;
 	}
@@ -333,7 +489,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 	/* Requested grp doesn't exist, hence create it */
 	if (found_grp == 0) {
 		if (mkdir(grp, 0) == -1) {
-			perror("Unable to create group");
+			ksft_perror("Unable to create group");
 
 			return -1;
 		}
@@ -348,12 +504,12 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
 
 	fp = fopen(tasks, "w");
 	if (!fp) {
-		perror("Failed to open tasks file");
+		ksft_perror("Failed to open tasks file");
 
 		return -1;
 	}
 	if (fprintf(fp, "%d\n", pid) < 0) {
-		perror("Failed to wr pid to tasks file");
+		ksft_print_msg("Failed to write pid to tasks file\n");
 		fclose(fp);
 
 		return -1;
@@ -376,7 +532,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  * pid is not written, this means that pid is in con_mon grp and hence
  * should consult con_mon grp's mon_data directory for results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val)
@@ -420,7 +576,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 out:
 	ksft_print_msg("Writing benchmark parameters to resctrl FS\n");
 	if (ret)
-		perror("# writing to resctrlfs");
+		ksft_print_msg("Failed writing to resctrlfs\n");
 
 	return ret;
 }
@@ -430,23 +586,17 @@ out:
  * @ctrlgrp:		Name of the con_mon grp
  * @schemata:		Schemata that should be updated to
  * @cpu_no:		CPU number that the benchmark PID is binded to
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
+ * @resource:		Resctrl resource (Eg: MB, L3, L2, etc.)
  *
- * Update schemata of a con_mon grp *only* if requested resctrl feature is
+ * Update schemata of a con_mon grp *only* if requested resctrl resource is
  * allocation type
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
-	int resource_id, fd, schema_len = -1, ret = 0;
-
-	if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) &&
-	    strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) &&
-	    strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) &&
-	    strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		return -ENOENT;
+	int domain_id, fd, schema_len, ret = 0;
 
 	if (!schemata) {
 		ksft_print_msg("Skipping empty schemata update\n");
@@ -454,8 +604,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 		return -1;
 	}
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		sprintf(reason, "Failed to get resource id");
+	if (get_domain_id(resource, cpu_no, &domain_id) < 0) {
+		sprintf(reason, "Failed to get domain ID");
 		ret = -1;
 
 		goto out;
@@ -466,14 +616,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 	else
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
 
-	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) ||
-	    !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "L3:", resource_id, '=', schemata);
-	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "MB:", resource_id, '=', schemata);
+	schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n",
+			      resource, domain_id, schemata);
 	if (schema_len < 0 || schema_len >= sizeof(schema)) {
 		snprintf(reason, sizeof(reason),
 			 "snprintf() failed with return value : %d", schema_len);
@@ -564,20 +708,16 @@ char *fgrep(FILE *inf, const char *str)
 }
 
 /*
- * validate_resctrl_feature_request - Check if requested feature is valid.
- * @resource:	Required resource (e.g., MB, L3, L2, L3_MON, etc.)
- * @feature:	Required monitor feature (in mon_features file). Can only be
- *		set for L3_MON. Must be NULL for all other resources.
+ * resctrl_resource_exists - Check if a resource is supported.
+ * @resource:	Resctrl resource (e.g., MB, L3, L2, L3_MON, etc.)
  *
- * Return: True if the resource/feature is supported, else false. False is
+ * Return: True if the resource is supported, else false. False is
  *         also returned if resctrl FS is not mounted.
  */
-bool validate_resctrl_feature_request(const char *resource, const char *feature)
+bool resctrl_resource_exists(const char *resource)
 {
 	char res_path[PATH_MAX];
 	struct stat statbuf;
-	char *res;
-	FILE *inf;
 	int ret;
 
 	if (!resource)
@@ -592,8 +732,25 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	if (stat(res_path, &statbuf))
 		return false;
 
-	if (!feature)
-		return true;
+	return true;
+}
+
+/*
+ * resctrl_mon_feature_exists - Check if requested monitoring feature is valid.
+ * @resource:	Resource that uses the mon_features file. Currently only L3_MON
+ *		is valid.
+ * @feature:	Required monitor feature (in mon_features file).
+ *
+ * Return: True if the feature is supported, else false.
+ */
+bool resctrl_mon_feature_exists(const char *resource, const char *feature)
+{
+	char res_path[PATH_MAX];
+	char *res;
+	FILE *inf;
+
+	if (!feature || !resource)
+		return false;
 
 	snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource);
 	inf = fopen(res_path, "r");
@@ -607,6 +764,36 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	return !!res;
 }
 
+/*
+ * resource_info_file_exists - Check if a file is present inside
+ * /sys/fs/resctrl/info/@resource.
+ * @resource:	Required resource (Eg: MB, L3, L2, etc.)
+ * @file:	Required file.
+ *
+ * Return: True if the /sys/fs/resctrl/info/@resource/@file exists, else false.
+ */
+bool resource_info_file_exists(const char *resource, const char *file)
+{
+	char res_path[PATH_MAX];
+	struct stat statbuf;
+
+	if (!file || !resource)
+		return false;
+
+	snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, resource,
+		 file);
+
+	if (stat(res_path, &statbuf))
+		return false;
+
+	return true;
+}
+
+bool test_resource_feature_check(const struct resctrl_test *test)
+{
+	return resctrl_resource_exists(test->resource);
+}
+
 int filter_dmesg(void)
 {
 	char line[1024];
@@ -617,7 +804,7 @@ int filter_dmesg(void)
 
 	ret = pipe(pipefds);
 	if (ret) {
-		perror("pipe");
+		ksft_perror("pipe");
 		return ret;
 	}
 	fflush(stdout);
@@ -626,13 +813,13 @@ int filter_dmesg(void)
 		close(pipefds[0]);
 		dup2(pipefds[1], STDOUT_FILENO);
 		execlp("dmesg", "dmesg", NULL);
-		perror("executing dmesg");
+		ksft_perror("Executing dmesg");
 		exit(1);
 	}
 	close(pipefds[1]);
 	fp = fdopen(pipefds[0], "r");
 	if (!fp) {
-		perror("fdopen(pipe)");
+		ksft_perror("fdopen(pipe)");
 		kill(pid, SIGTERM);
 
 		return -1;
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index 887542961968..2348d2c20d0a 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -24,6 +24,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 #else
 # define RSEQ_PERCPU	RSEQ_PERCPU_CPU_ID
 static
@@ -36,6 +41,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 #endif
 
 struct percpu_lock_entry {
@@ -274,7 +284,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -299,7 +309,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 20403d58345c..2f37961240ca 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -288,6 +288,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_mm_cid_available();
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return false;	/* Use mm_cid */
+}
 # ifdef TEST_MEMBARRIER
 /*
  * Membarrier does not currently support targeting a mm_cid, so
@@ -312,6 +317,11 @@ bool rseq_validate_cpu_id(void)
 {
 	return rseq_current_cpu_raw() >= 0;
 }
+static
+bool rseq_use_cpu_index(void)
+{
+	return true;	/* Use cpu_id as index. */
+}
 # ifdef TEST_MEMBARRIER
 static
 int rseq_membarrier_expedited(int cpu)
@@ -715,7 +725,7 @@ void test_percpu_list(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		for (j = 1; j <= 100; j++) {
 			struct percpu_list_node *node;
@@ -752,7 +762,7 @@ void test_percpu_list(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_list_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_list_pop(&list, i))) {
@@ -902,7 +912,7 @@ void test_percpu_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -952,7 +962,7 @@ void test_percpu_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_buffer_node *node;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while ((node = __percpu_buffer_pop(&buffer, i))) {
@@ -1113,7 +1123,7 @@ void test_percpu_memcpy_buffer(void)
 	/* Generate list entries for every usable cpu. */
 	sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus);
 	for (i = 0; i < CPU_SETSIZE; i++) {
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 		/* Worse-case is every item in same CPU. */
 		buffer.c[i].array =
@@ -1160,7 +1170,7 @@ void test_percpu_memcpy_buffer(void)
 	for (i = 0; i < CPU_SETSIZE; i++) {
 		struct percpu_memcpy_buffer_node item;
 
-		if (!CPU_ISSET(i, &allowed_cpus))
+		if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus))
 			continue;
 
 		while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) {
diff --git a/tools/testing/selftests/rust/Makefile b/tools/testing/selftests/rust/Makefile
new file mode 100644
index 000000000000..fce1584d3bc0
--- /dev/null
+++ b/tools/testing/selftests/rust/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_PROGS += test_probe_samples.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/rust/config b/tools/testing/selftests/rust/config
new file mode 100644
index 000000000000..b4002acd40bc
--- /dev/null
+++ b/tools/testing/selftests/rust/config
@@ -0,0 +1,5 @@
+CONFIG_RUST=y
+CONFIG_SAMPLES=y
+CONFIG_SAMPLES_RUST=y
+CONFIG_SAMPLE_RUST_MINIMAL=m
+CONFIG_SAMPLE_RUST_PRINT=m
\ No newline at end of file
diff --git a/tools/testing/selftests/rust/test_probe_samples.sh b/tools/testing/selftests/rust/test_probe_samples.sh
new file mode 100755
index 000000000000..ad0397e4986f
--- /dev/null
+++ b/tools/testing/selftests/rust/test_probe_samples.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2023 Collabora Ltd
+#
+# This script tests whether the rust sample modules can
+# be added and removed correctly.
+#
+DIR="$(dirname "$(readlink -f "$0")")"
+
+KTAP_HELPERS="${DIR}/../kselftest/ktap_helpers.sh"
+if [ -e "$KTAP_HELPERS" ]; then
+    source "$KTAP_HELPERS"
+else
+    echo "$KTAP_HELPERS file not found [SKIP]"
+    exit 4
+fi
+
+rust_sample_modules=("rust_minimal" "rust_print")
+
+ktap_print_header
+
+for sample in "${rust_sample_modules[@]}"; do
+    if ! /sbin/modprobe -n -q "$sample"; then
+        ktap_skip_all "module $sample is not found in /lib/modules/$(uname -r)"
+        exit "$KSFT_SKIP"
+    fi
+done
+
+ktap_set_plan "${#rust_sample_modules[@]}"
+
+for sample in "${rust_sample_modules[@]}"; do
+    if /sbin/modprobe -q "$sample"; then
+        /sbin/modprobe -q -r "$sample"
+        ktap_test_pass "$sample"
+    else
+        ktap_test_fail "$sample"
+    fi
+done
+
+ktap_finished
diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c
index 7ba057154343..62fba7356af2 100644
--- a/tools/testing/selftests/sched/cs_prctl_test.c
+++ b/tools/testing/selftests/sched/cs_prctl_test.c
@@ -276,7 +276,7 @@ int main(int argc, char *argv[])
 	if (setpgid(0, 0) != 0)
 		handle_error("process group");
 
-	printf("\n## Create a thread/process/process group hiearchy\n");
+	printf("\n## Create a thread/process/process group hierarchy\n");
 	create_processes(num_processes, num_threads, procs);
 	need_cleanup = 1;
 	disp_processes(num_processes, procs);
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 5b5c9d558dee..97b86980b768 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -38,10 +38,10 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples)
 	i *= 1000000000ULL;
 	i += finish.tv_nsec - start.tv_nsec;
 
-	printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
-		finish.tv_sec, finish.tv_nsec,
-		start.tv_sec, start.tv_nsec,
-		i, (double)i / 1000000000.0);
+	ksft_print_msg("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n",
+		       finish.tv_sec, finish.tv_nsec,
+		       start.tv_sec, start.tv_nsec,
+		       i, (double)i / 1000000000.0);
 
 	return i;
 }
@@ -53,7 +53,7 @@ unsigned long long calibrate(void)
 	pid_t pid, ret;
 	int seconds = 15;
 
-	printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
+	ksft_print_msg("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds);
 
 	samples = 0;
 	pid = getpid();
@@ -98,24 +98,36 @@ bool le(int i_one, int i_two)
 }
 
 long compare(const char *name_one, const char *name_eval, const char *name_two,
-	     unsigned long long one, bool (*eval)(int, int), unsigned long long two)
+	     unsigned long long one, bool (*eval)(int, int), unsigned long long two,
+	     bool skip)
 {
 	bool good;
 
-	printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
-	       (long long)one, name_eval, (long long)two);
+	if (skip) {
+		ksft_test_result_skip("%s %s %s\n", name_one, name_eval,
+				      name_two);
+		return 0;
+	}
+
+	ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
+		       (long long)one, name_eval, (long long)two);
 	if (one > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)one);
-		return 1;
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one);
+		good = false;
+		goto out;
 	}
 	if (two > INT_MAX) {
-		printf("Miscalculation! Measurement went negative: %lld\n", (long long)two);
-		return 1;
+		ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two);
+		good = false;
+		goto out;
 	}
 
 	good = eval(one, two);
 	printf("%s\n", good ? "✔️" : "❌");
 
+out:
+	ksft_test_result(good, "%s %s %s\n", name_one, name_eval, name_two);
+
 	return good ? 0 : 1;
 }
 
@@ -142,15 +154,22 @@ int main(int argc, char *argv[])
 	unsigned long long samples, calc;
 	unsigned long long native, filter1, filter2, bitmap1, bitmap2;
 	unsigned long long entry, per_filter1, per_filter2;
+	bool skip = false;
 
 	setbuf(stdout, NULL);
 
-	printf("Running on:\n");
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	ksft_print_msg("Running on:\n");
+	ksft_print_msg("");
 	system("uname -a");
 
-	printf("Current BPF sysctl settings:\n");
+	ksft_print_msg("Current BPF sysctl settings:\n");
 	/* Avoid using "sysctl" which may not be installed. */
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_enable");
+	ksft_print_msg("");
 	system("grep -H . /proc/sys/net/core/bpf_jit_harden");
 
 	if (argc > 1)
@@ -158,11 +177,11 @@ int main(int argc, char *argv[])
 	else
 		samples = calibrate();
 
-	printf("Benchmarking %llu syscalls...\n", samples);
+	ksft_print_msg("Benchmarking %llu syscalls...\n", samples);
 
 	/* Native call */
 	native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid native: %llu ns\n", native);
+	ksft_print_msg("getpid native: %llu ns\n", native);
 
 	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
 	assert(ret == 0);
@@ -172,35 +191,37 @@ int main(int argc, char *argv[])
 	assert(ret == 0);
 
 	bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
+	ksft_print_msg("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
 
 	/* Second filter resulting in a bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
+	ksft_print_msg("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
 
 	/* Third filter, can no longer be converted to bitmap */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
 	assert(ret == 0);
 
 	filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
+	ksft_print_msg("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
 
 	/* Fourth filter, can not be converted to bitmap because of filter 3 */
 	ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
 	assert(ret == 0);
 
 	filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
-	printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
+	ksft_print_msg("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
 
 	/* Estimations */
 #define ESTIMATE(fmt, var, what)	do {			\
 		var = (what);					\
-		printf("Estimated " fmt ": %llu ns\n", var);	\
-		if (var > INT_MAX)				\
-			goto more_samples;			\
+		ksft_print_msg("Estimated " fmt ": %llu ns\n", var);	\
+		if (var > INT_MAX) {				\
+			skip = true;				\
+			ret |= 1;				\
+		}						\
 	} while (0)
 
 	ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc,
@@ -218,31 +239,34 @@ int main(int argc, char *argv[])
 	ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2,
 		 (filter2 - native - entry) / 4);
 
-	printf("Expectations:\n");
-	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
-	bits = compare("native", "≤", "1 filter", native, le, filter1);
+	ksft_print_msg("Expectations:\n");
+	ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1,
+		       skip);
+	bits = compare("native", "≤", "1 filter", native, le, filter1,
+		       skip);
 	if (bits)
-		goto more_samples;
+		skip = true;
 
 	ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)",
-			per_filter1, approx, per_filter2);
+		       per_filter1, approx, per_filter2, skip);
 
 	bits = compare("1 bitmapped", "≈", "2 bitmapped",
-			bitmap1 - native, approx, bitmap2 - native);
+		       bitmap1 - native, approx, bitmap2 - native, skip);
 	if (bits) {
-		printf("Skipping constant action bitmap expectations: they appear unsupported.\n");
-		goto out;
+		ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n");
+		skip = true;
 	}
 
-	ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native);
-	ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native);
+	ret |= compare("entry", "≈", "1 bitmapped", entry, approx,
+		       bitmap1 - native, skip);
+	ret |= compare("entry", "≈", "2 bitmapped", entry, approx,
+		       bitmap2 - native, skip);
 	ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total",
-			entry + (per_filter1 * 4) + native, approx, filter2);
-	if (ret == 0)
-		goto out;
+		       entry + (per_filter1 * 4) + native, approx, filter2,
+		       skip);
 
-more_samples:
-	printf("Saw unexpected benchmark result. Try running again with more samples?\n");
-out:
-	return 0;
+	if (ret)
+		ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n");
+
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/thermal/intel/power_floor/.gitignore b/tools/testing/selftests/thermal/intel/power_floor/.gitignore
new file mode 100644
index 000000000000..1b9a76406f18
--- /dev/null
+++ b/tools/testing/selftests/thermal/intel/power_floor/.gitignore
@@ -0,0 +1 @@
+power_floor_test
diff --git a/tools/testing/selftests/thermal/intel/workload_hint/.gitignore b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore
new file mode 100644
index 000000000000..d697b034a3a8
--- /dev/null
+++ b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore
@@ -0,0 +1 @@
+workload_hint_test
diff --git a/tools/testing/selftests/uevent/.gitignore b/tools/testing/selftests/uevent/.gitignore
new file mode 100644
index 000000000000..382afb74cd40
--- /dev/null
+++ b/tools/testing/selftests/uevent/.gitignore
@@ -0,0 +1 @@
+uevent_filtering
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 2456a399eb9a..afd18c678ff5 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 8f81fa007364..01870d50942a 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		duration = duration / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = duration / data->bucket_size;
+	bucket = duration / data->bucket_size;
 
 	total_duration = duration * count;
 
@@ -480,7 +479,11 @@ static void osnoise_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index f7c959be8677..457360db0767 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 47d3d8b53cb2..dbf154082f95 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu,
 	if (params->output_divisor)
 		latency = latency / params->output_divisor;
 
-	if (data->bucket_size)
-		bucket = latency / data->bucket_size;
+	bucket = latency / data->bucket_size;
 
 	if (!context) {
 		hist = data->hist[cpu].irq;
@@ -546,7 +545,11 @@ static void timerlat_hist_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 1640f121baca..3e9af2c38688 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage)
 
 	for (i = 0; msg[i]; i++)
 		fprintf(stderr, "%s\n", msg[i]);
-	exit(1);
+
+	if (usage)
+		exit(EXIT_FAILURE);
+
+	exit(EXIT_SUCCESS);
 }
 
 /*
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index c769d7b3842c..9ac71a66840c 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
 	return syscall(__NR_sched_setattr, pid, attr, flags);
 }
 
-static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
-				unsigned int size, unsigned int flags)
-{
-	return syscall(__NR_sched_getattr, pid, attr, size, flags);
-}
-
 int __set_sched_attr(int pid, struct sched_attr *attr)
 {
 	int flags = 0;
@@ -479,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param)
 		if (prio == INVALID_VAL)
 			return -1;
 
-		if (prio < sched_get_priority_min(SCHED_OTHER))
+		if (prio < MIN_NICE)
 			return -1;
-		if (prio > sched_get_priority_max(SCHED_OTHER))
+		if (prio > MAX_NICE)
 			return -1;
 
 		sched_param->sched_policy   = SCHED_OTHER;
-		sched_param->sched_priority = prio;
+		sched_param->sched_nice = prio;
 		break;
 	default:
 		return -1;
@@ -536,7 +530,7 @@ int set_cpu_dma_latency(int32_t latency)
  */
 static const int find_mount(const char *fs, char *mp, int sizeof_mp)
 {
-	char mount_point[MAX_PATH];
+	char mount_point[MAX_PATH+1];
 	char type[100];
 	int found = 0;
 	FILE *fp;
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 04ed1e650495..d44513e6c66a 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -9,6 +9,8 @@
  */
 #define BUFF_U64_STR_SIZE	24
 #define MAX_PATH		1024
+#define MAX_NICE		20
+#define MIN_NICE		-19
 
 #define container_of(ptr, type, member)({			\
 	const typeof(((type *)0)->member) *__mptr = (ptr);	\
diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 3d0f3888a58c..485f8aeddbe0 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -28,10 +28,15 @@ FOPTS	:=	-flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
 		-fasynchronous-unwind-tables -fstack-clash-protection
 WOPTS	:= 	-Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
 
+ifeq ($(CC),clang)
+  FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+  WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
 TRACEFS_HEADERS	:= $$($(PKG_CONFIG) --cflags libtracefs)
 
 CFLAGS	:=	-O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include
-LDFLAGS	:=	-ggdb $(EXTRA_LDFLAGS)
+LDFLAGS	:=	-flto=auto -ggdb $(EXTRA_LDFLAGS)
 LIBS	:=	$$($(PKG_CONFIG) --libs libtracefs)
 
 SRC	:=	$(wildcard src/*.c)
diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c
index ad28582bcf2b..f04479ecc96c 100644
--- a/tools/verification/rv/src/in_kernel.c
+++ b/tools/verification/rv/src/in_kernel.c
@@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name)
 static char *ikm_get_current_reactor(char *monitor_name)
 {
 	char *reactors = ikm_read_reactor(monitor_name);
+	char *curr_reactor = NULL;
 	char *start;
 	char *end;
-	char *curr_reactor;
 
 	if (!reactors)
 		return NULL;
diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py
index d0df5833f2c1..d29b918306b4 100644
--- a/tools/workqueue/wq_dump.py
+++ b/tools/workqueue/wq_dump.py
@@ -50,6 +50,7 @@ import drgn
 from drgn.helpers.linux.list import list_for_each_entry,list_empty
 from drgn.helpers.linux.percpu import per_cpu_ptr
 from drgn.helpers.linux.cpumask import for_each_cpu,for_each_possible_cpu
+from drgn.helpers.linux.nodemask import for_each_node
 from drgn.helpers.linux.idr import idr_for_each
 
 import argparse
@@ -75,6 +76,22 @@ def cpumask_str(cpumask):
         output += f'{v:08x}'
     return output.strip()
 
+wq_type_len = 9
+
+def wq_type_str(wq):
+    if wq.flags & WQ_BH:
+        return f'{"bh":{wq_type_len}}'
+    elif wq.flags & WQ_UNBOUND:
+        if wq.flags & WQ_ORDERED:
+            return f'{"ordered":{wq_type_len}}'
+        else:
+            if wq.unbound_attrs.affn_strict:
+                return f'{"unbound,S":{wq_type_len}}'
+            else:
+                return f'{"unbound":{wq_type_len}}'
+    else:
+        return f'{"percpu":{wq_type_len}}'
+
 worker_pool_idr         = prog['worker_pool_idr']
 workqueues              = prog['workqueues']
 wq_unbound_cpumask      = prog['wq_unbound_cpumask']
@@ -82,6 +99,7 @@ wq_pod_types            = prog['wq_pod_types']
 wq_affn_dfl             = prog['wq_affn_dfl']
 wq_affn_names           = prog['wq_affn_names']
 
+WQ_BH                   = prog['WQ_BH']
 WQ_UNBOUND              = prog['WQ_UNBOUND']
 WQ_ORDERED              = prog['__WQ_ORDERED']
 WQ_MEM_RECLAIM          = prog['WQ_MEM_RECLAIM']
@@ -92,6 +110,11 @@ WQ_AFFN_CACHE           = prog['WQ_AFFN_CACHE']
 WQ_AFFN_NUMA            = prog['WQ_AFFN_NUMA']
 WQ_AFFN_SYSTEM          = prog['WQ_AFFN_SYSTEM']
 
+POOL_BH                 = prog['POOL_BH']
+
+WQ_NAME_LEN             = prog['WQ_NAME_LEN'].value_()
+cpumask_str_len         = len(cpumask_str(wq_unbound_cpumask))
+
 print('Affinity Scopes')
 print('===============')
 
@@ -133,10 +156,12 @@ for pi, pool in idr_for_each(worker_pool_idr):
 
 for pi, pool in idr_for_each(worker_pool_idr):
     pool = drgn.Object(prog, 'struct worker_pool', address=pool)
-    print(f'pool[{pi:0{max_pool_id_len}}] ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='')
+    print(f'pool[{pi:0{max_pool_id_len}}] flags=0x{pool.flags.value_():02x} ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='')
     print(f'idle/workers={pool.nr_idle.value_():3}/{pool.nr_workers.value_():3} ', end='')
     if pool.cpu >= 0:
         print(f'cpu={pool.cpu.value_():3}', end='')
+        if pool.flags & POOL_BH:
+            print(' bh', end='')
     else:
         print(f'cpus={cpumask_str(pool.attrs.cpumask)}', end='')
         print(f' pod_cpus={cpumask_str(pool.attrs.__pod_cpumask)}', end='')
@@ -148,24 +173,13 @@ print('')
 print('Workqueue CPU -> pool')
 print('=====================')
 
-print('[    workqueue     \     type   CPU', end='')
+print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"type   CPU":{wq_type_len}}', end='')
 for cpu in for_each_possible_cpu(prog):
     print(f' {cpu:{max_pool_id_len}}', end='')
 print(' dfl]')
 
 for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
-    print(f'{wq.name.string_().decode()[-24:]:24}', end='')
-    if wq.flags & WQ_UNBOUND:
-        if wq.flags & WQ_ORDERED:
-            print(' ordered   ', end='')
-        else:
-            print(' unbound', end='')
-            if wq.unbound_attrs.affn_strict:
-                print(',S ', end='')
-            else:
-                print('   ', end='')
-    else:
-        print(' percpu    ', end='')
+    print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} {wq_type_str(wq):10}', end='')
 
     for cpu in for_each_possible_cpu(prog):
         pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_()
@@ -175,3 +189,65 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(
     if wq.flags & WQ_UNBOUND:
         print(f' {wq.dfl_pwq.pool.id.value_():{max_pool_id_len}}', end='')
     print('')
+
+print('')
+print('Workqueue -> rescuer')
+print('====================')
+
+ucpus_len = max(cpumask_str_len, len("unbound_cpus"))
+rcpus_len = max(cpumask_str_len, len("rescuer_cpus"))
+
+print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"unbound_cpus":{ucpus_len}}    pid {"rescuer_cpus":{rcpus_len}} ]')
+
+for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
+    if not (wq.flags & WQ_MEM_RECLAIM):
+        continue
+
+    print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='')
+    if wq.unbound_attrs.value_() != 0:
+        print(f' {cpumask_str(wq.unbound_attrs.cpumask):{ucpus_len}}', end='')
+    else:
+        print(f' {"":{ucpus_len}}', end='')
+
+    print(f' {wq.rescuer.task.pid.value_():6}', end='')
+    print(f' {cpumask_str(wq.rescuer.task.cpus_ptr):{rcpus_len}}', end='')
+    print('')
+
+print('')
+print('Unbound workqueue -> node_nr/max_active')
+print('=======================================')
+
+if 'node_to_cpumask_map' in prog:
+    __cpu_online_mask = prog['__cpu_online_mask']
+    node_to_cpumask_map = prog['node_to_cpumask_map']
+    nr_node_ids = prog['nr_node_ids'].value_()
+
+    print(f'online_cpus={cpumask_str(__cpu_online_mask.address_of_())}')
+    for node in for_each_node():
+        print(f'NODE[{node:02}]={cpumask_str(node_to_cpumask_map[node])}')
+    print('')
+
+    print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ min max', end='')
+    first = True
+    for node in for_each_node():
+        if first:
+            print(f'  NODE {node}', end='')
+            first = False
+        else:
+            print(f' {node:7}', end='')
+    print(f' {"dfl":>7} ]')
+    print('')
+
+    for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
+        if not (wq.flags & WQ_UNBOUND):
+            continue
+
+        print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} ', end='')
+        print(f'{wq.min_active.value_():3} {wq.max_active.value_():3}', end='')
+        for node in for_each_node():
+            nna = wq.node_nr_active[node]
+            print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}', end='')
+        nna = wq.node_nr_active[nr_node_ids]
+        print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}')
+else:
+    printf(f'node_to_cpumask_map not present, is NUMA enabled?')
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 10bfc88a69f7..0f50960b0e3a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1615,7 +1615,13 @@ static int check_memory_region_flags(struct kvm *kvm,
 		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
 #ifdef __KVM_HAVE_READONLY_MEM
-	valid_flags |= KVM_MEM_READONLY;
+	/*
+	 * GUEST_MEMFD is incompatible with read-only memslots, as writes to
+	 * read-only memslots have emulated MMIO, not page fault, semantics,
+	 * and KVM doesn't allow emulated MMIO for private memory.
+	 */
+	if (!(mem->flags & KVM_MEM_GUEST_MEMFD))
+		valid_flags |= KVM_MEM_READONLY;
 #endif
 
 	if (mem->flags & ~valid_flags)